docs: 0.7 release notes

- compile release notes since 0.6.1
- move 'Next Release' from 'Changelog' to a new section

.circleci/config.yml

@@ -0,0 +1,386 @@
+version: 2.1
+orbs:
+  # NB: this is not the Go version, but the Orb version
+  # https://circleci.com/developer/orbs/orb/circleci/go#usage-go-modules-cache
+  go: circleci/go@1.11.0
+
+commands:
+  setup-home-local-bin:
+    steps:
+      - run:
+          shell: /bin/bash -euo pipefail
+          command: |
+            mkdir -p "$HOME/.local/bin"
+            line='export PATH="$HOME/.local/bin:$PATH"'
+            if grep "$line" $BASH_ENV >/dev/null; then
+              echo "$line" >> $BASH_ENV
+            fi
+
+  # NOTE: UV version is defined in .uv-version file at repository root
+  install-docdep:
+    steps:
+      - run:
+          name: Read UV version from .uv-version
+          command: |
+            UV_VERSION=$(cat .uv-version)
+            echo "export UV_VERSION=$UV_VERSION" >> $BASH_ENV
+      # Python is managed by uv - it will automatically download the version
+      # specified in docs/.python-version when needed
+      - run:
+          name: Install uv
+          command: curl -LsSf https://astral.sh/uv/${UV_VERSION}/install.sh | sh
+      - run:
+          name: Add uv to PATH and set cache dir
+          command: |
+            echo 'export PATH="$HOME/.local/bin:$PATH"' >> $BASH_ENV
+            echo 'export UV_CACHE_DIR="$HOME/.cache/uv"' >> $BASH_ENV
+      - restore_cache:
+          name: Restore uv cache
+          keys:
+            - uv-cache-v1-${UV_VERSION}-{{ checksum "docs/uv.lock" }}
+            - uv-cache-v1-${UV_VERSION}-
+
+  save-uv-cache:
+    steps:
+      - run:
+          name: Prune uv cache for CI
+          command: uv cache prune --ci
+      - save_cache:
+          name: Save uv cache
+          key: uv-cache-v1-${UV_VERSION}-{{ checksum "docs/uv.lock" }}
+          paths:
+            - ~/.cache/uv
+
+  install-zfs-from-source:
+    parameters:
+      zfs_release:
+        type: string
+    steps:
+      - run:
+          name: Record kernel version for cache key
+          command: uname -r > /tmp/kernel-version
+      - restore_cache:
+          name: Restore ZFS native debs cache
+          keys:
+            - zfs-debs-v2-<<parameters.zfs_release>>-{{ checksum "/tmp/kernel-version" }}
+      - run:
+          # https://openzfs.github.io/openzfs-docs/Developer%20Resources/Building%20ZFS.html
+          name: Build ZFS <<parameters.zfs_release>> native debs (if not cached)
+          no_output_timeout: 20m
+          command: |
+            # CircleCI machine images have pyenv Python 3.13 shadowing the system
+            # Python 3.12. The apt python3-* packages (setuptools, cffi, etc.) only
+            # install for the system Python, and ZFS's dpkg-buildpackage needs them
+            # for --enable-pyzfs. Use the system Python so apt packages are visible.
+            export PYENV_VERSION=system
+            if [ -d /tmp/zfs-debs ]; then
+              echo "ZFS debs cache hit, skipping build"
+              exit 0
+            fi
+            sudo apt-get update
+            sudo apt-get install -y \
+              alien autoconf automake build-essential debhelper-compat dh-autoreconf \
+              dh-dkms dh-python dkms fakeroot gawk git libaio-dev libattr1-dev \
+              libblkid-dev libcurl4-openssl-dev libelf-dev libffi-dev libpam0g-dev \
+              libssl-dev libtirpc-dev libtool libudev-dev linux-headers-$(uname -r) lsb-release \
+              parallel po-debconf python3 python3-all-dev python3-cffi python3-dev \
+              python3-packaging python3-setuptools python3-sphinx uuid-dev zlib1g-dev
+            mkdir -p /tmp/zfs-build
+            cd /tmp/zfs-build
+            git clone --depth 1 --branch <<parameters.zfs_release>> https://github.com/openzfs/zfs.git zfs-src
+            cd zfs-src
+            sh autogen.sh
+            ./configure
+            make native-deb
+            mkdir -p /tmp/zfs-debs
+            find /tmp/zfs-build -name '*.deb' -exec mv -t /tmp/zfs-debs/ {} +
+      - save_cache:
+          name: Save ZFS native debs cache
+          key: zfs-debs-v2-<<parameters.zfs_release>>-{{ checksum "/tmp/kernel-version" }}
+          paths:
+            - /tmp/zfs-debs
+      - run:
+          name: Install ZFS <<parameters.zfs_release>>
+          command: |
+            ls /tmp/zfs-debs/
+            # Only install the debs we need. Exclude dracut (conflicts with
+            # initramfs-tools), dkms (we have prebuilt modules), and packages
+            # we don't need (pyzfs, test, doc).
+            sudo apt-get install -y $(find /tmp/zfs-debs -name '*.deb' \
+              ! -name '*dracut*' \
+              ! -name '*dkms*' \
+              ! -name '*initramfs*' \
+              ! -name '*pyzfs*' \
+              ! -name '*doc*' \
+              ! -name '*test*' \
+              -print)
+            sudo modprobe zfs
+      - run:
+          name: Verify ZFS version
+          command: |
+            sudo zfs version
+            sudo zpool version
+
+  docs-publish-sh:
+    parameters:
+      push:
+        type: boolean
+    steps:
+      - checkout
+      - run:
+          command: |
+            git config --global user.email "zreplbot@cschwarz.com"
+            git config --global user.name "zrepl-github-io-ci"
+
+      # Configure git to use the GitHub token for HTTPS authentication.
+      # The token is stored in the 'zrepl-github-io-deploy' context.
+      - when:
+          condition: << parameters.push >>
+          steps:
+            - run:
+                name: Configure git to use GitHub token for push
+                # GITHUB_PAGES_TOKEN is from the 'zrepl-github-io-deploy' context.
+                # CircleCI's secret masking automatically redacts context variables in logs.
+                command: |
+                  # Unset CircleCI's SSH URL rewriting that checkout step configured
+                  git config --global --unset-all url."ssh://git@github.com".insteadOf || true
+                  # Set up credential helper with GitHub token
+                  git config --global credential.helper store
+                  echo "https://x-access-token:${GITHUB_PAGES_TOKEN}@github.com" > ~/.git-credentials
+                  chmod 600 ~/.git-credentials
+
+      # caller must install-docdep
+      - when:
+          condition: << parameters.push >>
+          steps:
+            - run: bash -x docs/publish.sh -c -a -P
+      - when:
+          condition:
+            not: << parameters.push >>
+          steps:
+            - run: bash -x docs/publish.sh -c -a
+
+parameters:
+  do_ci:
+    type: boolean
+    default: true
+
+  do_release:
+    type: boolean
+    default: false
+
+workflows:
+  version: 2
+
+  ci:
+    when: << pipeline.parameters.do_ci >>
+    jobs:
+      - run-docs-publish-sh:
+          name: quickcheck-docs
+          push: false
+      - quickcheck-go:
+          name: quickcheck-go-amd64-linux-1.25.7
+          goversion: &latest-go-release "1.25.7"
+          goos: linux
+          goarch: amd64
+      - test-go:
+          goversion: *latest-go-release
+      - quickcheck-go:
+          requires:
+            - quickcheck-go-amd64-linux-1.25.7 #quickcheck-go-smoketest.name
+          matrix:
+            alias: quickcheck-go-matrix
+            parameters:
+              goversion: [*latest-go-release, "1.24.13"]
+              goos: ["linux", "freebsd"]
+              goarch: ["amd64", "arm64"]
+            exclude:
+              # don't re-do quickcheck-go-smoketest
+              - goversion: *latest-go-release
+                goos: linux
+                goarch: amd64
+      - platformtest:
+          matrix:
+            parameters:
+              goversion: [*latest-go-release]
+              goos: ["linux"]
+              goarch: ["amd64"]
+              zfs_release: ["zfs-2.2.9", "zfs-2.3.5", "zfs-2.4.0"]
+          requires:
+            - test-go
+            - quickcheck-go-<< matrix.goarch >>-<< matrix.goos >>-<< matrix.goversion >>
+
+  release:
+    when: << pipeline.parameters.do_release >>
+    jobs:
+      - release-build
+      - release-deb:
+          requires:
+            - release-build
+      - release-rpm:
+          requires:
+            - release-build
+      - release-upload:
+          requires:
+            - release-build
+            - release-deb
+            - release-rpm
+
+  publish-zrepl.github.io:
+    jobs:
+      - run-docs-publish-sh:
+          name: publish-zrepl.github.io
+          push: true
+          context:
+            - zrepl-github-io-deploy
+          filters:
+            branches:
+              only:
+                - master
+
+jobs:
+  run-docs-publish-sh:
+    parameters:
+      push:
+        type: boolean
+    docker:
+      - image: cimg/base:current
+    steps:
+      - checkout
+      - install-docdep
+      - docs-publish-sh:
+          push: << parameters.push >>
+      - save-uv-cache
+
+  quickcheck-go:
+    parameters:
+      goversion:
+        type: string
+      goos:
+        type: string
+      goarch:
+        type: string
+    docker:
+      - image: &cimg_with_modern_go cimg/go:1.25
+    environment:
+      GOOS: <<parameters.goos>>
+      GOARCH: <<parameters.goarch>>
+      GOTOOLCHAIN: "go<<parameters.goversion>>"
+
+    steps:
+      - checkout
+
+      - go/load-cache:
+          key: quickcheck-<<parameters.goversion>>
+      - run: make build/install
+      - run: go mod download
+      - run: cd build && go mod download
+      - go/save-cache:
+          key: quickcheck-<<parameters.goversion>>
+
+      # ensure all code has been generated
+      - run: make generate
+      - run: |
+          if output=$(git status --porcelain) && [ -z "$output" ]; then
+            echo "Working directory clean"
+          else
+            echo "Uncommitted changes"
+            echo ""
+            echo "$output"
+            exit 1
+          fi
+
+      # other checks
+      - run: make zrepl-bin test-platform-bin
+      - run: make vet
+      - run: make lint
+
+      - store_artifacts:
+          path: artifacts
+      - persist_to_workspace:
+          root: .
+          paths: [.]
+
+  platformtest:
+    parameters:
+      goversion:
+        type: string
+      goos:
+        type: string
+      goarch:
+        type: string
+      zfs_release:
+        type: string
+    machine:
+      # pinned (not :current) to keep ZFS build cache valid across runs
+      image: ubuntu-2404:2025.09.1
+    resource_class: medium
+    environment:
+      GOOS: <<parameters.goos>>
+      GOARCH: <<parameters.goarch>>
+    steps:
+      - attach_workspace:
+          at: .
+      - install-zfs-from-source:
+          zfs_release: <<parameters.zfs_release>>
+      - run: sudo make test-platform GOOS="$GOOS" GOARCH="$GOARCH"
+
+  test-go:
+    parameters:
+      goversion:
+        type: string
+    docker:
+      - image: *cimg_with_modern_go
+    environment:
+      GOTOOLCHAIN: "go<<parameters.goversion>>"
+    steps:
+      - checkout
+      - go/load-cache:
+          key: make-test-go
+      - run: make test-go
+      - go/save-cache:
+          key: make-test-go
+
+  release-build:
+    machine:
+      image: &release-vm-image "ubuntu-2404:current"
+    resource_class: large
+    steps:
+      - checkout
+      - run: make release-docker
+      - persist_to_workspace:
+          root: .
+          paths: [.]
+  release-deb:
+    machine:
+      image: *release-vm-image
+    steps:
+      - attach_workspace:
+          at: .
+      - run: make debs-docker
+      - persist_to_workspace:
+          root: .
+          paths:
+            - "artifacts/*.deb"
+
+  release-rpm:
+    machine:
+      image: *release-vm-image
+    steps:
+      - attach_workspace:
+          at: .
+      - run: make rpms-docker
+      - persist_to_workspace:
+          root: .
+          paths:
+            - "artifacts/*.rpm"
+
+  release-upload:
+    docker:
+      - image: cimg/base:2024.09
+    steps:
+      - attach_workspace:
+          at: .
+      - run: make wrapup-and-checksum
+      - store_artifacts:
+          path: artifacts/release

.circleci/download_artifacts.py

@@ -0,0 +1,84 @@
+import argparse
+from pathlib import Path
+import re
+
+import requests
+
+import time
+
+import os
+import argparse
+from pathlib import Path
+
+
+circle_token = os.environ.get('CIRCLE_TOKEN')
+if not circle_token:
+    raise ValueError('CIRCLE_TOKEN environment variable not set')
+
+parser = argparse.ArgumentParser(description='Download artifacts from CircleCI')
+parser.add_argument('build_num', type=str, help='Build number')
+parser.add_argument('dst', type=Path, help='Destination directory')
+parser.add_argument('--prefix', type=str, default='', help='Filter for prefix')
+parser.add_argument('--match', type=str, default='.*', help='Only include paths matching the given regex')
+
+args = parser.parse_args()
+
+res = requests.get(
+    f"https://circleci.com/api/v1.1/project/github/zrepl/zrepl/{args.build_num}/artifacts",
+    headers={
+        "Circle-Token": circle_token,
+    },
+)
+res.raise_for_status()
+
+# https://circleci.com/docs/api/v1/index.html#artifacts-of-a-job
+# [ {
+#   "path" : "raw-test-output/go-test-report.xml",
+#   "pretty_path" : "raw-test-output/go-test-report.xml",
+#   "node_index" : 0,
+#   "url" : "https://24-88881093-gh.circle-artifacts.com/0/raw-test-output/go-test-report.xml"
+# }, {
+#   "path" : "raw-test-output/go-test.out",
+#   "pretty_path" : "raw-test-output/go-test.out",
+#   "node_index" : 0,
+#   "url" : "https://24-88881093-gh.circle-artifacts.com/0/raw-test-output/go-test.out"
+# } ]
+res = res.json()
+
+for artifact in res:
+    if not artifact["pretty_path"].startswith(args.prefix):
+        continue
+    if not re.match(args.match, artifact["pretty_path"]):
+        continue
+    stripped = artifact["pretty_path"][len(args.prefix):]
+    print(f"Downloading {artifact['pretty_path']} to {args.dst / stripped}")
+    artifact_rel = Path(stripped)
+    artifact_dst = args.dst / artifact_rel
+    artifact_dst.parent.mkdir(parents=True, exist_ok=True)
+
+    res = requests.get(
+        artifact["url"],
+        headers={
+            "Circle-Token": circle_token,
+        },
+        stream=True,
+    )
+    res.raise_for_status()
+
+    total_size = int(res.headers.get("Content-Length", 0))
+    block_size = 128 * 1024
+    with open(artifact_dst, "wb") as f:
+        progress = 0
+        start_time = time.time()
+        for chunk in res.iter_content(chunk_size=block_size):
+            f.write(chunk)
+            progress += len(chunk)
+            percent = progress / total_size * 100
+            elapsed_time = time.time() - start_time
+            if elapsed_time >= 5:
+                print(f"Downloaded {progress}/{total_size} bytes ({percent:.2f}%)", end="\r")
+                start_time = time.time()
+        print(f"Downloaded {progress}/{total_size} bytes ({percent:.2f}%)")
+    print("Download complete!")
+
+print("All files downloaded")

.github/FUNDING.yml

@@ -0,0 +1,5 @@
+github: problame
+patreon: zrepl
+liberapay: zrepl
+custom: https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96
+ko_fi: problame

.github/dependabot.yml

@@ -0,0 +1,9 @@
+version: 2
+updates:
+  # Docs use Python only for static site generation.
+  - package-ecosystem: "pip"
+    directory: /docs
+    schedule:
+      interval: "weekly"
+    ignore:
+      - dependency-name: "*"

.gitignore

@@ -1,5 +1,6 @@
 # Build
 artifacts/
+build/install.tmp
 
 # Golang
 vendor/

.golangci.yml

@@ -0,0 +1,42 @@
+version: "2"
+linters:
+  enable:
+    - revive
+  settings:
+    revive:
+      rules:
+        - name: time-equal
+  exclusions:
+    generated: lax
+    presets:
+      - comments
+      - common-false-positives
+      - legacy
+      - std-error-handling
+    rules:
+      - linters:
+          - errcheck
+        path: _test\.go
+      - linters:
+          - staticcheck
+        text: 'SA9003:'
+      - linters:
+          - staticcheck
+        text: '(QF1001|QF1011|ST1012|QF1008|ST1005|ST1023|QF1003|ST1006|ST1001|QF1004):'
+    paths:
+      - third_party$
+      - builtin$
+      - examples$
+formatters:
+  enable:
+    - goimports
+  settings:
+    goimports:
+      local-prefixes:
+        - github.com/zrepl/zrepl
+  exclusions:
+    generated: lax
+    paths:
+      - third_party$
+      - builtin$
+      - examples$

.uv-version

@@ -0,0 +1 @@
+0.9.30

Gopkg.lock

@@ -1,313 +0,0 @@
-# This file is autogenerated, do not edit; changes may be undone by the next 'dep ensure'.
-
-
-[[projects]]
-  branch = "master"
-  digest = "1:c0bec5f9b98d0bc872ff5e834fac186b807b656683bd29cb82fb207a1513fabb"
-  name = "github.com/beorn7/perks"
-  packages = ["quantile"]
-  pruneopts = ""
-  revision = "3a771d992973f24aa725d07868b467d1ddfceafb"
-
-[[projects]]
-  digest = "1:56c130d885a4aacae1dd9c7b71cfe39912c7ebc1ff7d2b46083c8812996dc43b"
-  name = "github.com/davecgh/go-spew"
-  packages = ["spew"]
-  pruneopts = ""
-  revision = "346938d642f2ec3594ed81d874461961cd0faa76"
-  version = "v1.1.0"
-
-[[projects]]
-  digest = "1:e988ed0ca0d81f4d28772760c02ee95084961311291bdfefc1b04617c178b722"
-  name = "github.com/fatih/color"
-  packages = ["."]
-  pruneopts = ""
-  revision = "5b77d2a35fb0ede96d138fc9a99f5c9b6aef11b4"
-  version = "v1.7.0"
-
-[[projects]]
-  branch = "master"
-  digest = "1:5d0a2385edf4ba44f3b7b76bc0436ceb8f62bf55aa5d540a9eb9ec6c58d86809"
-  name = "github.com/ftrvxmtrx/fd"
-  packages = ["."]
-  pruneopts = ""
-  revision = "c6d800382fff6dc1412f34269f71b7f83bd059ad"
-
-[[projects]]
-  branch = "master"
-  digest = "1:4416ad04caf950d004921268f777e418f8c328080ccf6a91e799f977dc128808"
-  name = "github.com/gdamore/encoding"
-  packages = ["."]
-  pruneopts = ""
-  revision = "b23993cbb6353f0e6aa98d0ee318a34728f628b9"
-
-[[projects]]
-  digest = "1:d8088c614a5bffaf38a40c116226e7d230750bafb77942dca25eab779ceeaf1f"
-  name = "github.com/gdamore/tcell"
-  packages = [
-    ".",
-    "termbox",
-    "terminfo",
-  ]
-  pruneopts = ""
-  revision = "de7e78efa4a71b3f36c7154989c529dbdf9ae623"
-  version = "v1.1.0"
-
-[[projects]]
-  digest = "1:6a4a01d58b227c4b6b11111b9f172ec5c17682b82724e58e6daf3f19f4faccd8"
-  name = "github.com/go-logfmt/logfmt"
-  packages = ["."]
-  pruneopts = ""
-  revision = "390ab7935ee28ec6b286364bba9b4dd6410cb3d5"
-  version = "v0.3.0"
-
-[[projects]]
-  digest = "1:3dd078fda7500c341bc26cfbc6c6a34614f295a2457149fc1045cab767cbcf18"
-  name = "github.com/golang/protobuf"
-  packages = ["proto"]
-  pruneopts = ""
-  revision = "aa810b61a9c79d51363740d207bb46cf8e620ed5"
-  version = "v1.2.0"
-
-[[projects]]
-  branch = "master"
-  digest = "1:cb09475f771b9167fb9333629f5d6a7161572602ea040f1094602b0dc8709878"
-  name = "github.com/jinzhu/copier"
-  packages = ["."]
-  pruneopts = ""
-  revision = "db4671f3a9b8df855e993f7c94ec5ef1ffb0a23b"
-
-[[projects]]
-  branch = "master"
-  digest = "1:1ed9eeebdf24aadfbca57eb50e6455bd1d2474525e0f0d4454de8c8e9bc7ee9a"
-  name = "github.com/kr/logfmt"
-  packages = ["."]
-  pruneopts = ""
-  revision = "b84e30acd515aadc4b783ad4ff83aff3299bdfe0"
-
-[[projects]]
-  branch = "master"
-  digest = "1:591a2778aa6e896980757ea87e659b3aa13d8c0e790310614028463a31c0998b"
-  name = "github.com/kr/pretty"
-  packages = ["."]
-  pruneopts = ""
-  revision = "cfb55aafdaf3ec08f0db22699ab822c50091b1c4"
-
-[[projects]]
-  branch = "master"
-  digest = "1:109e0a9b9e74c5c8adf94a2dc4dd4a9ca2a183d4d87ffecd4e62db69a5ede55a"
-  name = "github.com/kr/text"
-  packages = ["."]
-  pruneopts = ""
-  revision = "7cafcd837844e784b526369c9bce262804aebc60"
-
-[[projects]]
-  digest = "1:863ba095ae0954100963826333bd1503c169424bb798d9ce800d9f6651f4c234"
-  name = "github.com/lucasb-eyer/go-colorful"
-  packages = ["."]
-  pruneopts = ""
-  revision = "345fbb3dbcdb252d9985ee899a84963c0fa24c82"
-  version = "v1.0"
-
-[[projects]]
-  digest = "1:9ea83adf8e96d6304f394d40436f2eb44c1dc3250d223b74088cc253a6cd0a1c"
-  name = "github.com/mattn/go-colorable"
-  packages = ["."]
-  pruneopts = ""
-  revision = "167de6bfdfba052fa6b2d3664c8f5272e23c9072"
-  version = "v0.0.9"
-
-[[projects]]
-  digest = "1:78229b46ddb7434f881390029bd1af7661294af31f6802e0e1bedaad4ab0af3c"
-  name = "github.com/mattn/go-isatty"
-  packages = ["."]
-  pruneopts = ""
-  revision = "0360b2af4f38e8d38c7fce2a9f4e702702d73a39"
-  version = "v0.0.3"
-
-[[projects]]
-  digest = "1:82b912465c1da0668582a7d1117339c278e786c2536b3c3623029a0c7141c2d0"
-  name = "github.com/mattn/go-runewidth"
-  packages = ["."]
-  pruneopts = ""
-  revision = "ce7b0b5c7b45a81508558cd1dba6bb1e4ddb51bb"
-  version = "v0.0.3"
-
-[[projects]]
-  digest = "1:4c23ced97a470b17d9ffd788310502a077b9c1f60221a85563e49696276b4147"
-  name = "github.com/matttproud/golang_protobuf_extensions"
-  packages = ["pbutil"]
-  pruneopts = ""
-  revision = "3247c84500bff8d9fb6d579d800f20b3e091582c"
-  version = "v1.0.0"
-
-[[projects]]
-  digest = "1:7365acd48986e205ccb8652cc746f09c8b7876030d53710ea6ef7d0bd0dcd7ca"
-  name = "github.com/pkg/errors"
-  packages = ["."]
-  pruneopts = ""
-  revision = "645ef00459ed84a119197bfb8d8205042c6df63d"
-  version = "v0.8.0"
-
-[[projects]]
-  digest = "1:256484dbbcd271f9ecebc6795b2df8cad4c458dd0f5fd82a8c2fa0c29f233411"
-  name = "github.com/pmezard/go-difflib"
-  packages = ["difflib"]
-  pruneopts = ""
-  revision = "792786c7400a136282c1664665ae0a8db921c6c2"
-  version = "v1.0.0"
-
-[[projects]]
-  branch = "master"
-  digest = "1:1392748e290ca66ac8447ef24961f8ae9e1d846a53af0f58a5a0256982ce0577"
-  name = "github.com/problame/go-netssh"
-  packages = ["."]
-  pruneopts = ""
-  revision = "c56ad38d2c91397ad3c8dd9443d7448e328a9e9e"
-
-[[projects]]
-  branch = "master"
-  digest = "1:8c63c44f018bd52b03ebad65c9df26aabbc6793138e421df1c8c84c285a45bc6"
-  name = "github.com/problame/go-rwccmd"
-  packages = ["."]
-  pruneopts = ""
-  revision = "391d2c78c8404a9683d79f75dd24ab53040f89f7"
-
-[[projects]]
-  digest = "1:1bcbb0a7ad8d3392d446eb583ae5415ff987838a8f7331a36877789be20667e6"
-  name = "github.com/problame/go-streamrpc"
-  packages = [
-    ".",
-    "internal/pdu",
-  ]
-  pruneopts = ""
-  revision = "d5d111e014342fe1c37f0b71cc37ec5f2afdfd13"
-  version = "v0.5"
-
-[[projects]]
-  branch = "master"
-  digest = "1:ebf8ffdde9bdbf9c83e22121875c68c01d821776523546554b2a3ff6f72773ab"
-  name = "github.com/prometheus/client_golang"
-  packages = [
-    "prometheus",
-    "prometheus/promhttp",
-  ]
-  pruneopts = ""
-  revision = "e11c6ff8170beca9d5fd8b938e71165eeec53ac6"
-
-[[projects]]
-  branch = "master"
-  digest = "1:60aca47f4eeeb972f1b9da7e7db51dee15ff6c59f7b401c1588b8e6771ba15ef"
-  name = "github.com/prometheus/client_model"
-  packages = ["go"]
-  pruneopts = ""
-  revision = "99fa1f4be8e564e8a6b613da7fa6f46c9edafc6c"
-
-[[projects]]
-  branch = "master"
-  digest = "1:af21ee3e0a8212f17bb317cd7237f9920bcb2641a291ac111f30f63b3cab817f"
-  name = "github.com/prometheus/common"
-  packages = [
-    "expfmt",
-    "internal/bitbucket.org/ww/goautoneg",
-    "model",
-  ]
-  pruneopts = ""
-  revision = "d0f7cd64bda49e08b22ae8a730aa57aa0db125d6"
-
-[[projects]]
-  branch = "master"
-  digest = "1:61df0898746840afc7be5dc2c3eeec83022fab70df11ecee5b16c85e912cf5ed"
-  name = "github.com/prometheus/procfs"
-  packages = [
-    ".",
-    "internal/util",
-    "nfs",
-    "xfs",
-  ]
-  pruneopts = ""
-  revision = "8b1c2da0d56deffdbb9e48d4414b4e674bd8083e"
-
-[[projects]]
-  branch = "master"
-  digest = "1:146327ce93be37e68bd3ff8541090d96da8cb3adc9e35d57570e9170a29f6bf6"
-  name = "github.com/spf13/cobra"
-  packages = ["."]
-  pruneopts = ""
-  revision = "b78744579491c1ceeaaa3b40205e56b0591b93a3"
-
-[[projects]]
-  digest = "1:261bc565833ef4f02121450d74eb88d5ae4bd74bfe5d0e862cddb8550ec35000"
-  name = "github.com/spf13/pflag"
-  packages = ["."]
-  pruneopts = ""
-  revision = "e57e3eeb33f795204c1ca35f56c44f83227c6e66"
-  version = "v1.0.0"
-
-[[projects]]
-  digest = "1:3926a4ec9a4ff1a072458451aa2d9b98acd059a45b38f7335d31e06c3d6a0159"
-  name = "github.com/stretchr/testify"
-  packages = [
-    "assert",
-    "require",
-  ]
-  pruneopts = ""
-  revision = "69483b4bd14f5845b5a1e55bca19e954e827f1d0"
-  version = "v1.1.4"
-
-[[projects]]
-  branch = "v2"
-  digest = "1:9d92186f609a73744232323416ddafd56fae67cb552162cc190ab903e36900dd"
-  name = "github.com/zrepl/yaml-config"
-  packages = ["."]
-  pruneopts = ""
-  revision = "af27d27978ad95808723a62d87557d63c3ff0605"
-
-[[projects]]
-  branch = "master"
-  digest = "1:9c286cf11d0ca56368185bada5dd6d97b6be4648fc26c354fcba8df7293718f7"
-  name = "golang.org/x/sys"
-  packages = ["unix"]
-  pruneopts = ""
-  revision = "bf42f188b9bc6f2cf5b8ee5a912ef1aedd0eba4c"
-
-[[projects]]
-  digest = "1:5acd3512b047305d49e8763eef7ba423901e85d5dd2fd1e71778a0ea8de10bd4"
-  name = "golang.org/x/text"
-  packages = [
-    "encoding",
-    "encoding/internal/identifier",
-    "internal/gen",
-    "transform",
-    "unicode/cldr",
-  ]
-  pruneopts = ""
-  revision = "f21a4dfb5e38f5895301dc265a8def02365cc3d0"
-  version = "v0.3.0"
-
-[solve-meta]
-  analyzer-name = "dep"
-  analyzer-version = 1
-  input-imports = [
-    "github.com/fatih/color",
-    "github.com/gdamore/tcell/termbox",
-    "github.com/go-logfmt/logfmt",
-    "github.com/golang/protobuf/proto",
-    "github.com/jinzhu/copier",
-    "github.com/kr/pretty",
-    "github.com/mattn/go-isatty",
-    "github.com/pkg/errors",
-    "github.com/problame/go-netssh",
-    "github.com/problame/go-rwccmd",
-    "github.com/problame/go-streamrpc",
-    "github.com/prometheus/client_golang/prometheus",
-    "github.com/prometheus/client_golang/prometheus/promhttp",
-    "github.com/spf13/cobra",
-    "github.com/spf13/pflag",
-    "github.com/stretchr/testify/assert",
-    "github.com/stretchr/testify/require",
-    "github.com/zrepl/yaml-config",
-    "golang.org/x/sys/unix",
-  ]
-  solver-name = "gps-cdcl"
-  solver-version = 1

Gopkg.toml

@@ -1,75 +0,0 @@
-ignored = [ "github.com/inconshreveable/mousetrap" ]
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/ftrvxmtrx/fd"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/jinzhu/copier"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/kr/pretty"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/mitchellh/go-homedir"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/mitchellh/mapstructure"
-
-[[constraint]]
-  name = "github.com/pkg/errors"
-  version = "0.8.0"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/spf13/cobra"
-
-[[constraint]]
-  name = "github.com/spf13/viper"
-  version = "1.0.0"
-
-[[constraint]]
-  name = "github.com/stretchr/testify"
-  version = "1.1.4"
-
-[[constraint]]
-  branch = "v2"
-  name = "github.com/zrepl/yaml-config"
-
-[[constraint]]
-  name = "github.com/go-logfmt/logfmt"
-  version = "*"
-
-[[constraint]]
-  name = "github.com/problame/go-rwccmd"
-  branch = "master"
-
-[[constraint]]
-  name = "github.com/problame/go-netssh"
-  branch = "master"
-
-[[constraint]]
-  name = "github.com/prometheus/client_golang"
-  branch = "master"
-
-[[constraint]]
-  name = "github.com/golang/protobuf"
-  version = "1.2.0"
-
-[[constraint]]
-  name = "github.com/fatih/color"
-  version = "1.7.0"
-
-[[constraint]]
-  name = "github.com/problame/go-streamrpc"
-  version = "0.5.0"
-
-
-
-[[constraint]]
-  name = "github.com/gdamore/tcell"
-  version = "1.0.0"

Makefile

@@ -1,37 +1,6 @@
-.PHONY: generate build test vet cover release docs docs-clean clean vendordeps
-.DEFAULT_GOAL := build
-
-ROOT := github.com/zrepl/zrepl
-SUBPKGS += client
-SUBPKGS += config
-SUBPKGS += daemon
-SUBPKGS += daemon/filters
-SUBPKGS += daemon/job
-SUBPKGS += daemon/logging
-SUBPKGS += daemon/nethelpers
-SUBPKGS += daemon/pruner
-SUBPKGS += daemon/snapper
-SUBPKGS += daemon/streamrpcconfig
-SUBPKGS += daemon/transport
-SUBPKGS += daemon/transport/connecter
-SUBPKGS += daemon/transport/serve
-SUBPKGS += endpoint
-SUBPKGS += logger
-SUBPKGS += pruning
-SUBPKGS += pruning/retentiongrid
-SUBPKGS += replication
-SUBPKGS += replication/fsrep
-SUBPKGS += replication/pdu
-SUBPKGS += replication/internal/diff
-SUBPKGS += tlsconf
-SUBPKGS += util
-SUBPKGS += util/socketpair
-SUBPKGS += util/watchdog
-SUBPKGS += util/envconst
-SUBPKGS += version
-SUBPKGS += zfs
-
-_TESTPKGS := $(ROOT) $(foreach p,$(SUBPKGS),$(ROOT)/$(p))
+.PHONY: generate build test vet cover release docs docs-clean clean format lint platformtest
+.PHONY: release release-noarch
+.DEFAULT_GOAL := zrepl-bin
 
 ARTIFACTDIR := artifacts
 
@@ -39,105 +8,384 @@ ifdef ZREPL_VERSION
     _ZREPL_VERSION := $(ZREPL_VERSION)
 endif
 ifndef _ZREPL_VERSION
-    _ZREPL_VERSION := $(shell git describe --dirty 2>/dev/null || echo "ZREPL_BUILD_INVALID_VERSION" )
+    _ZREPL_VERSION := $(shell git describe --always --dirty 2>/dev/null || echo "ZREPL_BUILD_INVALID_VERSION" )
     ifeq ($(_ZREPL_VERSION),ZREPL_BUILD_INVALID_VERSION) # can't use .SHELLSTATUS because Debian Stretch is still on gmake 4.1
         $(error cannot infer variable ZREPL_VERSION using git and variable is not overriden by make invocation)
     endif
 endif
-GO_LDFLAGS := "-X github.com/zrepl/zrepl/version.zreplVersion=$(_ZREPL_VERSION)"
 
-GO_BUILD := go build -ldflags $(GO_LDFLAGS)
+ZREPL_PACKAGE_RELEASE := 1
 
-RELEASE_BINS := $(ARTIFACTDIR)/zrepl-freebsd-amd64
-RELEASE_BINS += $(ARTIFACTDIR)/zrepl-linux-amd64
-RELEASE_BINS += $(ARTIFACTDIR)/zrepl-darwin-amd64
+GO := go
+GOOS ?= $(shell bash -c 'source <($(GO) env) && echo "$$GOOS"')
+GOARCH ?= $(shell bash -c 'source <($(GO) env) && echo "$$GOARCH"')
+GOARM ?= $(shell bash -c 'source <($(GO) env) && echo "$$GOARM"')
+GOHOSTOS ?= $(shell bash -c 'source <($(GO) env) && echo "$$GOHOSTOS"')
+GOHOSTARCH ?= $(shell bash -c 'source <($(GO) env) && echo "$$GOHOSTARCH"')
+GO_ENV_VARS := CGO_ENABLED=0
+GO_LDFLAGS := "-X github.com/zrepl/zrepl/internal/version.zreplVersion=$(_ZREPL_VERSION)"
+GO_MOD_READONLY := -mod=readonly
+GO_EXTRA_BUILDFLAGS :=
+GO_BUILDFLAGS := $(GO_MOD_READONLY) $(GO_EXTRA_BUILDFLAGS)
+GO_BUILD := $(GO_ENV_VARS) $(GO) build $(GO_BUILDFLAGS) -ldflags $(GO_LDFLAGS)
+GOCOVMERGE := gocovmerge
+RELEASE_GOVERSION ?= go1.25.7
+STRIPPED_GOVERSION := $(subst go,,$(RELEASE_GOVERSION))
+RELEASE_DOCKER_BASEIMAGE ?= golang:$(STRIPPED_GOVERSION)
+RELEASE_DOCKER_CACHEMOUNT :=
 
-RELEASE_NOARCH := $(ARTIFACTDIR)/zrepl-noarch.tar
-THIS_PLATFORM_RELEASE_BIN := $(shell bash -c 'source <(go env) && echo "zrepl-$${GOOS}-$${GOARCH}"' )
-
-vendordeps:
-	dep ensure -v -vendor-only
-
-generate: #not part of the build, must do that manually
-	protoc -I=replication/pdu --go_out=replication/pdu replication/pdu/pdu.proto
-	@for pkg in $(_TESTPKGS); do\
-		go generate "$$pkg" || exit 1; \
-	done;
-
-build:
-	@echo "INFO: In case of missing dependencies, run 'make vendordeps'"
-	$(GO_BUILD) -o "$(ARTIFACTDIR)/zrepl"
-
-test:
-	@for pkg in $(_TESTPKGS); do \
-		echo "Testing $$pkg"; \
-		go test "$$pkg" || exit 1; \
-	done;
-
-vet:
-	@for pkg in $(_TESTPKGS); do \
-		echo "Vetting $$pkg"; \
-		go vet "$$pkg" || exit 1; \
-	done;
-
-cover: artifacts
-	@for pkg in $(_TESTPKGS); do \
-		profile="$(ARTIFACTDIR)/cover-$$(basename $$pkg).out"; \
-		go test -coverprofile "$$profile" $$pkg || exit 1; \
-		if [ -f "$$profile" ]; then \
-   			go tool cover -html="$$profile" -o "$${profile}.html" || exit 2; \
-		fi; \
-	done;
-
-$(ARTIFACTDIR):
-	mkdir -p "$@"
-
-$(ARTIFACTDIR)/docs: $(ARTIFACTDIR)
-	mkdir -p "$@"
-
-$(ARTIFACTDIR)/bash_completion: $(RELEASE_BINS)
-	artifacts/$(THIS_PLATFORM_RELEASE_BIN) bashcomp "$@"
-
-$(ARTIFACTDIR)/go_version.txt:
-	go version > $@
-
-docs: $(ARTIFACTDIR)/docs
-	make -C docs \
-		html \
-		BUILDDIR=../artifacts/docs \
-
-docs-clean:
-	make -C docs \
-		clean \
-		BUILDDIR=../artifacts/docs
+ifneq ($(GOARM),)
+	ZREPL_TARGET_TUPLE := $(GOOS)-$(GOARCH)v$(GOARM)
+else
+	ZREPL_TARGET_TUPLE := $(GOOS)-$(GOARCH)
+endif
 
 
-.PHONY: $(RELEASE_BINS)
-# TODO: two wildcards possible
-$(RELEASE_BINS): $(ARTIFACTDIR)/zrepl-%-amd64: generate $(ARTIFACTDIR) vet test
-	@echo "INFO: In case of missing dependencies, run 'make vendordeps'"
-	GOOS=$* GOARCH=amd64   $(GO_BUILD) -o "$(ARTIFACTDIR)/zrepl-$*-amd64"
+ifneq ($(RELEASE_DOCKER_CACHEMOUNT),)
+	_RELEASE_DOCKER_CACHEMOUNT := -v $(RELEASE_DOCKER_CACHEMOUNT)/mod:/go/pkg/mod -v $(RELEASE_DOCKER_CACHEMOUNT)/xdg-cache:/.cache/go-build
+.PHONY: release-docker-mkcachemount
+release-docker-mkcachemount:
+	mkdir -p $(RELEASE_DOCKER_CACHEMOUNT)
+	mkdir -p $(RELEASE_DOCKER_CACHEMOUNT)/mod
+	mkdir -p $(RELEASE_DOCKER_CACHEMOUNT)/xdg-cache
+else
+	_RELEASE_DOCKER_CACHEMOUNT :=
+.PHONY: release-docker-mkcachemount
+release-docker-mkcachemount:
+	# nothing to do
+endif
 
-$(RELEASE_NOARCH): docs $(ARTIFACTDIR)/bash_completion $(ARTIFACTDIR)/go_version.txt
+##################### PRODUCING A RELEASE #############
+.PHONY: release wrapup-and-checksum check-git-clean sign clean ensure-release-toolchain
+
+ensure-release-toolchain:
+	# ensure the toolchain is actually the one we expect
+	test $(RELEASE_GOVERSION) = "$$($(GO_ENV_VARS) $(GO) env GOVERSION)"
+
+release: ensure-release-toolchain
+	$(MAKE) _run_make_foreach_target_tuple RUN_MAKE_FOREACH_TARGET_TUPLE_ARG="vet"
+	$(MAKE) _run_make_foreach_target_tuple RUN_MAKE_FOREACH_TARGET_TUPLE_ARG="lint"
+	$(MAKE) _run_make_foreach_target_tuple RUN_MAKE_FOREACH_TARGET_TUPLE_ARG="zrepl-bin"
+	$(MAKE) _run_make_foreach_target_tuple RUN_MAKE_FOREACH_TARGET_TUPLE_ARG="test-platform-bin"
+	$(MAKE) noarch
+
+release-docker: $(ARTIFACTDIR) release-docker-mkcachemount
+	sed 's/FROM.*!SUBSTITUTED_BY_MAKEFILE/FROM $(RELEASE_DOCKER_BASEIMAGE)/' build/build.Dockerfile > $(ARTIFACTDIR)/build.Dockerfile
+	docker build -t zrepl_release --pull \
+		--build-arg BUILD_UID=$$(id -u) \
+		--build-arg BUILD_GID=$$(id -g) \
+		-f $(ARTIFACTDIR)/build.Dockerfile .
+	docker run --rm -i$$(test -t 0 && echo t) \
+		$(_RELEASE_DOCKER_CACHEMOUNT) \
+		-v $(CURDIR):/src \
+		zrepl_release \
+		make release \
+			GOOS=$(GOOS) GOARCH=$(GOARCH) GOARM=$(GOARM) \
+			ZREPL_VERSION=$(ZREPL_VERSION) ZREPL_PACKAGE_RELEASE=$(ZREPL_PACKAGE_RELEASE) \
+			RELEASE_GOVERSION=$(RELEASE_GOVERSION)
+
+debs-docker:
+	$(MAKE) _debs_or_rpms_docker _DEB_OR_RPM=deb
+rpms-docker:
+	$(MAKE) _debs_or_rpms_docker _DEB_OR_RPM=rpm
+_debs_or_rpms_docker: # artifacts/_zrepl.zsh_completion artifacts/bash_completion docs zrepl-bin
+	$(MAKE) $(_DEB_OR_RPM)-docker GOOS=linux GOARCH=amd64
+	$(MAKE) $(_DEB_OR_RPM)-docker GOOS=linux GOARCH=arm64
+	$(MAKE) $(_DEB_OR_RPM)-docker GOOS=linux GOARCH=arm GOARM=7
+	$(MAKE) $(_DEB_OR_RPM)-docker GOOS=linux GOARCH=386
+
+rpm: $(ARTIFACTDIR) # artifacts/_zrepl.zsh_completion artifacts/bash_completion docs zrepl-bin
+	$(eval _ZREPL_RPM_VERSION := $(subst -,.,$(_ZREPL_VERSION)))
+	$(eval _ZREPL_RPM_TOPDIR_ABS := $(CURDIR)/$(ARTIFACTDIR)/rpmbuild)
+	rm -rf "$(_ZREPL_RPM_TOPDIR_ABS)"
+	mkdir "$(_ZREPL_RPM_TOPDIR_ABS)"
+	for d in BUILD BUILDROOT RPMS SOURCES SPECS SRPMS; do \
+		mkdir -p "$(_ZREPL_RPM_TOPDIR_ABS)/$$d"; \
+	done
+	sed \
+		-e "s/^Version:.*/Version:          $(_ZREPL_RPM_VERSION)/g" \
+		-e "s/^Release:.*/Release:          $(ZREPL_PACKAGE_RELEASE)/g" \
+	    packaging/rpm/zrepl.spec \
+		>  $(_ZREPL_RPM_TOPDIR_ABS)/SPECS/zrepl.spec
+
+	# see /usr/lib/rpm/platform
+ifeq ($(GOARCH),amd64)
+	$(eval _ZREPL_RPMBUILD_TARGET := x86_64)
+else ifeq ($(GOARCH), 386)
+	$(eval _ZREPL_RPMBUILD_TARGET := i386)
+else ifeq ($(GOARCH), arm64)
+	$(eval _ZREPL_RPMBUILD_TARGET := aarch64)
+else ifeq ($(GOARCH), arm)
+	$(eval _ZREPL_RPMBUILD_TARGET := armv7hl)
+else
+	$(eval _ZREPL_RPMBUILD_TARGET := $(GOARCH))
+endif
+	rpmbuild \
+		--build-in-place \
+		--define "_sourcedir $(CURDIR)" \
+		--define "_topdir $(_ZREPL_RPM_TOPDIR_ABS)" \
+		--define "_zrepl_binary_filename zrepl-$(ZREPL_TARGET_TUPLE)" \
+		--target $(_ZREPL_RPMBUILD_TARGET) \
+		-bb "$(_ZREPL_RPM_TOPDIR_ABS)"/SPECS/zrepl.spec
+	cp "$(_ZREPL_RPM_TOPDIR_ABS)"/RPMS/$(_ZREPL_RPMBUILD_TARGET)/zrepl-$(_ZREPL_RPM_VERSION)*.rpm $(ARTIFACTDIR)/
+
+rpm-docker:
+	docker build -t zrepl_rpm_pkg --pull -f packaging/rpm/Dockerfile .
+	docker run --rm -i -v $(CURDIR):/build/src -u $$(id -u):$$(id -g) \
+		zrepl_rpm_pkg \
+		make rpm \
+			GOOS=$(GOOS) GOARCH=$(GOARCH) GOARM=$(GOARM) \
+			ZREPL_VERSION=$(ZREPL_VERSION) ZREPL_PACKAGE_RELEASE=$(ZREPL_PACKAGE_RELEASE)
+
+
+deb: $(ARTIFACTDIR) # artifacts/_zrepl.zsh_completion artifacts/bash_completion docs zrepl-bin
+
+	cp packaging/deb/debian/changelog.template packaging/deb/debian/changelog
+	sed -i 's/DATE_DASH_R_OUTPUT/$(shell date -R)/' packaging/deb/debian/changelog
+	VERSION="$(subst -,.,$(_ZREPL_VERSION))-$(ZREPL_PACKAGE_RELEASE)"; \
+		export VERSION="$${VERSION#v}"; \
+		sed -i 's/VERSION/'"$$VERSION"'/' packaging/deb/debian/changelog
+
+ifeq ($(GOARCH), arm)
+	$(eval  DEB_HOST_ARCH := armhf)
+else ifeq ($(GOARCH), 386)
+	$(eval DEB_HOST_ARCH := i386)
+else
+	$(eval DEB_HOST_ARCH := $(GOARCH))
+endif
+
+	export ZREPL_DPKG_ZREPL_BINARY_FILENAME=zrepl-$(ZREPL_TARGET_TUPLE); \
+		dpkg-buildpackage -b --no-sign --host-arch $(DEB_HOST_ARCH)
+	cp ../*.deb artifacts/
+
+deb-docker:
+	docker build -t zrepl_debian_pkg --pull -f packaging/deb/Dockerfile .
+	# Use a small open file limit to make fakeroot work. If we don't
+	# specify it, docker daemon will use its file limit. I don't know
+	# what changed (Docker, its systemd service, its Go version). But I
+	# observed fakeroot iterating close(i) up to i > 1000000, which costs
+	# a good amount of CPU time and makes the build slow.
+	docker run --rm -i -v $(CURDIR):/build/src -u $$(id -u):$$(id -g) \
+		--ulimit nofile=1024:1024 \
+		zrepl_debian_pkg \
+		make deb \
+			GOOS=$(GOOS) GOARCH=$(GOARCH) GOARM=$(GOARM) \
+			ZREPL_VERSION=$(ZREPL_VERSION) ZREPL_PACKAGE_RELEASE=$(ZREPL_PACKAGE_RELEASE)
+
+# expects `release`, `deb` & `rpm` targets to have run before
+NOARCH_TARBALL := $(ARTIFACTDIR)/zrepl-noarch.tar
+wrapup-and-checksum:
+	rm -f $(NOARCH_TARBALL)
 	tar --mtime='1970-01-01' --sort=name \
 		--transform 's/$(ARTIFACTDIR)/zrepl-$(_ZREPL_VERSION)-noarch/' \
-		-acf $@ \
+		--transform 's#dist#zrepl-$(_ZREPL_VERSION)-noarch/dist#' \
+		--transform 's#internal/config/samples#zrepl-$(_ZREPL_VERSION)-noarch/config#' \
+		-acf $(NOARCH_TARBALL) \
 		$(ARTIFACTDIR)/docs/html \
 		$(ARTIFACTDIR)/bash_completion \
-		$(ARTIFACTDIR)/go_version.txt
-
-release: $(RELEASE_BINS) $(RELEASE_NOARCH)
+		$(ARTIFACTDIR)/_zrepl.zsh_completion \
+		$(ARTIFACTDIR)/go_env.txt \
+		dist \
+		internal/config/samples
 	rm -rf "$(ARTIFACTDIR)/release"
 	mkdir -p "$(ARTIFACTDIR)/release"
-	cp $^ "$(ARTIFACTDIR)/release"
+	cp -l $(ARTIFACTDIR)/zrepl* \
+		$(ARTIFACTDIR)/platformtest-* \
+		"$(ARTIFACTDIR)/release"
 	cd "$(ARTIFACTDIR)/release" && sha512sum $$(ls | sort) > sha512sum.txt
+
+check-git-clean:
 	@# note that we use ZREPL_VERSION and not _ZREPL_VERSION because we want to detect the override
-	@if git describe --dirty 2>/dev/null | grep dirty >/dev/null; then \
-		if [ "$(ZREPL_VERSION)" == "" ]; then \
-			echo "[WARN] git checkout is dirty and make variable ZREPL_VERSION was not used to override"; \
+	@if git describe --always --dirty 2>/dev/null | grep dirty >/dev/null; then \
+        echo '[INFO] either git reports checkout is dirty or git is not installed or this is not a git checkout'; \
+		if [ "$(ZREPL_VERSION)" = "" ]; then \
+			echo '[WARN] git checkout is dirty and make variable ZREPL_VERSION was not used to override'; \
+			git status; \
+			echo "git diff:";  \
+			git diff | cat; \
 			exit 1; \
 		fi; \
 	fi;
 
+tag-release:
+	test -n "$(ZREPL_TAG_VERSION)" || exit 1
+	git tag -u '328A6627FA98061D!' -m "$(ZREPL_TAG_VERSION)" "$(ZREPL_TAG_VERSION)"
+
+sign:
+	gpg -u '328A6627FA98061D!' \
+		--armor \
+		--detach-sign $(ARTIFACTDIR)/release/sha512sum.txt
+
 clean: docs-clean
 	rm -rf "$(ARTIFACTDIR)"
+
+download-circleci-release:
+	rm -rf "$(ARTIFACTDIR)"
+	mkdir -p "$(ARTIFACTDIR)/release"
+	python3 .circleci/download_artifacts.py --prefix 'artifacts/release/' "$(BUILD_NUM)" "$(ARTIFACTDIR)/release"
+
+##################### MULTI-ARCH HELPERS #####################
+
+_run_make_foreach_target_tuple:
+	if [ "$(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG)" = "" ]; then \
+		echo "RUN_MAKE_FOREACH_TARGET_TUPLE_ARG must be set"; \
+		exit 1; \
+	fi
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=freebsd   GOARCH=amd64
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=freebsd   GOARCH=386
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=freebsd   GOARCH=arm	  GOARM=7
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=freebsd   GOARCH=arm64
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=linux     GOARCH=amd64
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=linux     GOARCH=arm64
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=linux     GOARCH=arm     GOARM=7
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=linux     GOARCH=386
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=darwin    GOARCH=amd64
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=solaris   GOARCH=amd64
+	$(MAKE) $(RUN_MAKE_FOREACH_TARGET_TUPLE_ARG) GOOS=illumos   GOARCH=amd64
+
+##################### REGULAR TARGETS #####################
+.PHONY: lint test-go test-platform cover-merge cover-html vet zrepl-bin test-platform-bin
+
+lint: build/install
+	$(GO_ENV_VARS) build/install/golangci_lint/golangci-lint run ./...
+
+vet:
+	$(GO_ENV_VARS) $(GO) vet $(GO_BUILDFLAGS) ./...
+
+test-go: $(ARTIFACTDIR)
+	rm -f "$(ARTIFACTDIR)/gotest.cover"
+ifeq ($(COVER),1)
+	$(GO_ENV_VARS) $(GO) test $(GO_BUILDFLAGS) \
+		-coverpkg github.com/zrepl/zrepl/... \
+		-covermode atomic \
+		-coverprofile "$(ARTIFACTDIR)/gotest.cover" \
+		./...
+else
+	$(GO_ENV_VARS) $(GO) test $(GO_BUILDFLAGS) \
+		./...
+endif
+
+zrepl-bin:
+	$(GO_BUILD) -o "$(ARTIFACTDIR)/zrepl-$(ZREPL_TARGET_TUPLE)"
+
+COVER_PLATFORM_BIN_PATH := $(ARTIFACTDIR)/platformtest-cover-$(ZREPL_TARGET_TUPLE)
+cover-platform-bin:
+	$(GO_ENV_VARS) $(GO) test $(GO_BUILDFLAGS) \
+		-c -o "$(COVER_PLATFORM_BIN_PATH)" \
+		-covermode=atomic -cover -coverpkg github.com/zrepl/zrepl/... \
+		./platformtest/harness
+cover-platform:
+	# do not track dependency on cover-platform-bin to allow build of binary outside of test VM
+	export _TEST_PLATFORM_CMD="$(COVER_PLATFORM_BIN_PATH) \
+		-test.coverprofile \"$(ARTIFACTDIR)/platformtest.cover\" \
+		-test.v \
+		__DEVEL--i-heard-you-like-tests"; \
+		$(MAKE) _test-or-cover-platform-impl
+
+TEST_PLATFORM_BIN_PATH := $(ARTIFACTDIR)/platformtest-$(ZREPL_TARGET_TUPLE)
+test-platform-bin:
+	$(GO_BUILD) -o "$(TEST_PLATFORM_BIN_PATH)" ./internal/platformtest/harness
+test-platform:
+	export _TEST_PLATFORM_CMD="\"$(TEST_PLATFORM_BIN_PATH)\""; \
+		$(MAKE) _test-or-cover-platform-impl
+
+ZREPL_PLATFORMTEST_POOLNAME := zreplplatformtest
+ZREPL_PLATFORMTEST_IMAGEPATH := /tmp/zreplplatformtest.pool.img
+ZREPL_PLATFORMTEST_MOUNTPOINT := /tmp/zreplplatformtest.pool
+ZREPL_PLATFORMTEST_ZFS_LOG := /tmp/zreplplatformtest.zfs.log
+# ZREPL_PLATFORMTEST_STOP_AND_KEEP := -failure.stop-and-keep-pool
+ZREPL_PLATFORMTEST_ARGS :=
+_test-or-cover-platform-impl: $(ARTIFACTDIR)
+ifndef _TEST_PLATFORM_CMD
+	$(error _TEST_PLATFORM_CMD is undefined, caller 'cover-platform' or 'test-platform' should have defined it)
+endif
+	rm -f "$(ZREPL_PLATFORMTEST_ZFS_LOG)"
+	rm -f "$(ARTIFACTDIR)/platformtest.cover"
+	internal/platformtest/logmockzfs/logzfsenv "$(ZREPL_PLATFORMTEST_ZFS_LOG)" `which zfs` \
+		$(_TEST_PLATFORM_CMD) \
+		-poolname "$(ZREPL_PLATFORMTEST_POOLNAME)" \
+		-imagepath "$(ZREPL_PLATFORMTEST_IMAGEPATH)" \
+		-mountpoint "$(ZREPL_PLATFORMTEST_MOUNTPOINT)" \
+		$(ZREPL_PLATFORMTEST_STOP_AND_KEEP) \
+		$(ZREPL_PLATFORMTEST_ARGS)
+
+cover-merge: $(ARTIFACTDIR)
+	$(GOCOVMERGE) $(ARTIFACTDIR)/platformtest.cover $(ARTIFACTDIR)/gotest.cover > $(ARTIFACTDIR)/merged.cover
+cover-html: cover-merge
+	$(GO) tool cover -html "$(ARTIFACTDIR)/merged.cover" -o "$(ARTIFACTDIR)/merged.cover.html"
+
+cover-full:
+	test "$$(id -u)" = "0" || echo "MUST RUN AS ROOT" 1>&2
+	$(MAKE) test-go COVER=1
+	$(MAKE) cover-platform-bin
+	$(MAKE) cover-platform
+	$(MAKE) cover-html
+
+##################### DEV TARGETS #####################
+# not part of the build, must do that manually
+.PHONY: generate format
+
+build/install:
+	rm -rf build/install.tmp
+	mkdir build/install.tmp
+
+	-echo "installing protoc"
+	mkdir build/install.tmp/protoc
+	bash -x build/get_protoc.bash build/install.tmp/protoc
+
+	-echo "installing golangci-lint"
+	mkdir -p build/install.tmp/golangci_lint
+	GOHOSTARCH=$(GOHOSTARCH) \
+		build/get_golangci_lint.bash build/install.tmp/golangci_lint
+
+	-echo "installing go tools"
+	build/go_install_tools.bash build/install.tmp/gobin
+
+	mv build/install.tmp build/install
+
+
+generate: build/install
+	# TODO: would be nice to run with a pure path here
+	PATH="$(CURDIR)/build/install/gobin:$(CURDIR)/build/install/protoc/bin:$$PATH" && \
+		build/install/protoc/bin/protoc -I=internal/replication/logic/pdu --go_out=internal/replication/logic/pdu --go-grpc_out=internal/replication/logic/pdu internal/replication/logic/pdu/pdu.proto && \
+		build/install/protoc/bin/protoc -I=internal/rpc/grpcclientidentity/example --go_out=internal/rpc/grpcclientidentity/example/pdu --go-grpc_out=internal/rpc/grpcclientidentity/example/pdu internal/rpc/grpcclientidentity/example/grpcauth.proto && \
+		$(GO) generate $(GO_BUILDFLAGS) -x ./... && \
+		true
+
+GOIMPORTS := goimports -srcdir . -local 'github.com/zrepl/zrepl'
+
+format: build/install
+	@ build/install/gobin/goimports -w -local 'github.com/zrepl/zrepl' $$(find . -type f -name '*.go' -not -path "./vendor/*" -not -name '*.pb.go' -not -name '*_enumer.go')
+
+##################### NOARCH #####################
+.PHONY: noarch $(ARTIFACTDIR)/bash_completion $(ARTIFACTDIR)/_zrepl.zsh_completion $(ARTIFACTDIR)/go_env.txt docs docs-clean
+
+
+$(ARTIFACTDIR):
+	mkdir -p "$@"
+$(ARTIFACTDIR)/docs: $(ARTIFACTDIR)
+	mkdir -p "$@"
+
+noarch: $(ARTIFACTDIR)/bash_completion $(ARTIFACTDIR)/_zrepl.zsh_completion $(ARTIFACTDIR)/go_env.txt docs
+	# pass
+
+$(ARTIFACTDIR)/bash_completion:
+	$(MAKE) zrepl-bin GOOS=$(GOHOSTOS) GOARCH=$(GOHOSTARCH)
+	artifacts/zrepl-$(GOHOSTOS)-$(GOHOSTARCH) gencompletion bash "$@"
+
+$(ARTIFACTDIR)/_zrepl.zsh_completion:
+	$(MAKE) zrepl-bin GOOS=$(GOHOSTOS) GOARCH=$(GOHOSTARCH)
+	artifacts/zrepl-$(GOHOSTOS)-$(GOHOSTARCH) gencompletion zsh "$@"
+
+$(ARTIFACTDIR)/go_env.txt:
+	$(GO_ENV_VARS) $(GO) env > $@
+	$(GO) version >> $@
+
+docs: $(ARTIFACTDIR)/docs
+	# https://www.sphinx-doc.org/en/master/man/sphinx-build.html
+	cd docs && uv sync --frozen
+	cd docs && uv run sphinx-build -W --keep-going -n . ../artifacts/docs/html
+
+docs-clean:
+	rm -rf artifacts/docs
+	rm -rf docs/.venv

README.md

@@ -1,3 +1,13 @@
+[![GitHub license](https://img.shields.io/github/license/zrepl/zrepl.svg)](https://github.com/zrepl/zrepl/blob/master/LICENSE)
+[![Language: Go](https://img.shields.io/badge/lang-Go-6ad7e5.svg)](https://golang.org/)
+[![User Docs](https://img.shields.io/badge/docs-web-blue.svg)](https://zrepl.github.io)
+[![Support me on Patreon](https://img.shields.io/badge/dynamic/json?color=yellow&label=Patreon&query=data.attributes.patron_count&url=https%3A%2F%2Fwww.patreon.com%2Fapi%2Fcampaigns%2F3095079)](https://patreon.com/zrepl)
+[![Donate via GitHub Sponsors](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&style=flat&color=yellow)](https://github.com/sponsors/problame)
+[![Donate via Liberapay](https://img.shields.io/liberapay/patrons/zrepl.svg?logo=liberapay)](https://liberapay.com/zrepl/donate)
+[![Donate via PayPal](https://img.shields.io/badge/donate-paypal-yellow.svg)](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96)
+[![Twitter](https://img.shields.io/twitter/url/https/github.com/zrepl/zrepl.svg?style=social)](https://twitter.com/intent/tweet?text=Wow:&url=https%3A%2F%2Fgithub.com%2Fzrepl%2Fzrepl)
+[![Chat](https://img.shields.io/badge/chat-matrix-blue.svg)](https://matrix.to/#/#zrepl:matrix.org)
+
 # zrepl
 zrepl is a one-stop ZFS backup & replication solution.
 
@@ -12,83 +22,182 @@ zrepl is a one-stop ZFS backup & replication solution.
 
 ## Feature Requests
 
-1. Does you feature request require default values / some kind of configuration?
+1. Does your feature request require default values / some kind of configuration?
    If so, think of an expressive configuration example.
 2. Think of at least one use case that generalizes from your concrete application.
 3. Open an issue on GitHub with example conf & use case attached.
+4. **Optional**: [Contact Christian Schwarz](https://cschwarz.com) for contract work.
 
 The above does not apply if you already implemented everything.
 Check out the *Coding Workflow* section below for details.
 
-## Package Maintainer Information
+## Development
 
-* Follow the steps in `docs/installation.rst -> Compiling from Source` and read the Makefile / shell scripts used in this process.
-* Make sure your distro is compatible with the paths in `docs/installation.rst`.
-* Ship a default config that adheres to your distro's `hier` and logging system.
-* Ship a service manager file and _please_ try to upstream it to this repository.
-* Use `make release ZREPL_VERSION='mydistro-1.2.3_1'`
-    * Your distro's name and any versioning supplemental to zrepl's (e.g. package revision) should be in this string
-* Make sure you are informed about new zrepl versions, e.g. by subscribing to GitHub's release RSS feed.
-
-## Developer Documentation
-
-zrepl is written in [Go](https://golang.org) and uses [`dep`](https://github.com/golang/dep) to manage dependencies.
+zrepl is written in [Go](https://golang.org) and uses [Go modules](https://github.com/golang/go/wiki/Modules) to manage dependencies.
 The documentation is written in [ReStructured Text](http://docutils.sourceforge.net/rst.html) using the [Sphinx](https://www.sphinx-doc.org) framework.
 
-To get started, run `./lazy.sh devsetup` to easily install build dependencies and read `docs/installation.rst -> Compiling from Source`.
+### Building
 
-### Overall Architecture
+#### Go Code
 
-The application architecture is documented as part of the user docs in the *Implementation* section (`docs/content/impl`).
-Make sure to develop an understanding how zrepl is typically used by studying the user docs first.
+Dependencies:
 
-### Project Structure
+* Go
+* GNU Make
+* Git
+* wget (`make generate`)
+* unzip (`make generate`)
 
-```
-├── cmd
-│   ├── endpoint            # implementations of endpoints for package replication
-│   ├── sampleconf          # example configuration
-├── docs                    # sphinx-based documentation
-│   ├── **/*.rst            # documentation in reStructuredText
-│   ├── sphinxconf
-│   │   └── conf.py         # sphinx config (see commit 445a280 why its not in docs/)
-│   ├── requirements.txt    # pip3 requirements to build documentation
-│   ├── publish.sh          # shell script for automated rendering & deploy to zrepl.github.io repo
-│   ├── public_git          # checkout of zrepl.github.io managed by above shell script
-├── logger                  # logger package used by zrepl
-├── replication             # replication functionality
-├── rpc                     # rpc protocol implementation
-├── util
-└── zfs                     # ZFS wrappers, filesystemm diffing
+Some Go code is **generated**, and generated code is committed to the source tree.
+Therefore, building does not require having code generation tools set up.
+When making changes that require code to be (re-)generated, run `make generate`.
+I downloads and installs pinned versions of the code generation tools into `./build/install`.
+There is a CI check that ensures Git state is clean, i.e., code generation has been done by a PR and is deterministic.
+
+#### Docs
+
+Install [uv](https://docs.astral.sh/uv/getting-started/installation/), then run `make docs`.
+uv automatically manages Python and dependencies.
+
+### Testing
+
+The **test suite** is split into pure **Go tests** (`make test-go`) and **platform tests** that interact with ZFS and thus generally **require root privileges** (`sudo make test-platform`).
+Platform tests run on their own pool with the name `zreplplatformtest`, which is created using the file vdev in `/tmp`.
+
+For a full **code coverage** profile, run `make test-go COVER=1 && sudo make test-platform && make cover-merge`.
+An HTML report can be generated using `make cover-html`.
+
+### Circle CI
+
+We use CircleCI for automated build & test pre- and post-merge.
+
+There are two workflows:
+
+* `ci` runs for every commit / branch / tag pushed to GitHub.
+  It is supposed to run very fast (<5min and provides quick feedback to developers).
+  It runs formatting checks, lints and tests on the most important OSes / architectures.
+
+* `release` runs
+  * on manual triggers through the CircleCI API (in order to produce a release)
+  * periodically on `master`
+
+Artifacts are stored in CircleCI.
+
+### Releasing
+
+All zrepl releases are git-tagged and then published as a GitHub Release.
+There is a git tag for each zrepl release, usually `vMAJOR.MINOR.0`.
+We don't move git tags once the release has been published.
+
+The procedure to issue a release is as follows:
+
+* Prepare the release (as a PR to `master`):
+  * Finalize `docs/changelog.rst` for the release.
+  * Merge the PR. Docs are auto-published to zrepl.github.io on merge.
+* Tag the release:
+  * Git tag the release on the `master` branch (e.g., `vMAJOR.MINOR.0`).
+  * Push the tag.
+* Build and publish:
+  * Run the `release` pipeline (trigger via CircleCI UI).
+  * Download artifacts: `make download-circleci-release BUILD_NUM=<circleci-build-number>`
+  * Create GitHub release and upload artifacts:
+    ```bash
+    gh release create vX.Y.Z --title "vX.Y.Z" --notes "See changelog" --draft
+    gh release upload vX.Y.Z artifacts/release/*
+    ```
+  * Review the draft release, edit the changelog, then publish.
+  * Add the .rpm and .deb files to the official zrepl repos.
+    * Code for management of these repos: https://github.com/zrepl/package-repo-ops (private repo at this time)
+* Update docs version list:
+  * Update `docs/_templates/versions.html` with the new release.
+  * Verify the link to `zrepl-noarch.tar` in the GitHub release works.
+  * Merge to `master` (docs auto-publish).
+
+#### Patch releases, Go toolchain updates, APT/RPM Package rebuilds
+
+`vMAJOR.MINOR.0` is typically a tagged commit on `master`, because development velocity isn't high
+and thus release branches for stabilization aren't necessary.
+
+Occasionally though there is a need for patch changes to a release, e.g.
+- security issue in a dependency
+- Go toolchain update (e.g. security issue in standard library)
+
+The procedure for this is the following
+- create a branch off the release tag we need to patch, named `releases/MAJOR.MINOR.X`
+- that branch will never be merged into `master`, it'll be a dead-end for this specific patch
+- make changes in that branch
+- make the final commit that bumps version numbers
+- create the git tag
+- follow general procedure for publishing the release (previous sectino
+
+For Go toolchain updates and package rebuilds with no source code changes, leverage the APT/RPM package revision field.
+Control via the `ZREPL_PACKAGE_RELEASE` Makefile variable, see `origin/releases/0.6.1-2` for an example.
+
+
+### Updating Dependencies
+
+- Update the `go` directive and `toolchain` directive in `go.mod`
+  - `go` is the minimum supported version
+  - `toolchain` is the preferred toolchain version if `GOTOOLCHAIN` is not specified
+
+Run `go mod tidy` to ensure consistency.
+
+Update Go module dependencies:
+
+```bash
+# Update all other dependencies
+go get -u -t ./...
+go mod tidy
+
+# Above might fail if there are version selection conflicts.
+# Figure out what's going on by updating packages from error messages first.
+# Example:
+go get -u google.golang.org/genproto google.golang.org/grpc google.golang.org/protobuf
 ```
 
-### Coding Workflow
+Update codegen & lint tools
+- `protoc` =>  `build/get_protoc.bash`
+  - GH releases publish sha256 sums
+- `golangci-lint` => `build/get_golangci_lint.bash`
+- bump versions in `build/tools.go`
+  - we use the tools.go trick:
+  - `go get -tags tools -u example.com/tool ; go mod tidy`
+  - review whether we're ready to switch to `go tool`: https://github.com/zrepl/zrepl/pull/909
 
-* Open an issue when starting to hack on a new feature
-* Commits should reference the issue they are related to
-* Docs improvements not documenting new features do not require an issue.
+Now run `make generate`.
 
-### Breaking Changes
+Run `make lint` and `make vet`.
 
-Backward-incompatible changes must be documented in the git commit message and are listed in `docs/changelog.rst`.
+Update the CI configuration `.circleci/config.yml`:
+- Update Go version references (we reference the minimum and max supported version)
+- Set `Makefile` `RELEASE_GOVERSION` to the new Go version
+- Update the pinned ZFS release tags in the `platformtest` matrix (`zfs_release` parameter) to the latest patch releases of each OpenZFS branch (currently 2.2, 2.3, 2.4)
+- Update the pinned Ubuntu machine image for `platformtest` (e.g. `ubuntu-2404:2025.09.1`) — this is pinned rather than `current` so the ZFS build cache stays valid across runs
 
-* Config-breaking changes must contain a line `BREAK CONFIG` in the commit message
-* Other breaking changes must contain a line `BREAK` in the commit message
+Update docs build tooling:
+- Update `uv` version in `.circleci/config.yml` (search for `astral.sh/uv/` and cache keys containing the version)
+- Check if there's now a CircleCI orb for uv that we could use
+- Update Python version in `docs/.python-version`
 
-### Glossary & Naming Inconsistencies
+Update docs dependencies (Sphinx, sphinx-rtd-theme):
+- Check current versions in `docs/pyproject.toml`
+- Review upstream changelogs for breaking changes
+- Update version constraints in `pyproject.toml` and the `uv` lockfile (see [uv docs on dependencies](https://docs.astral.sh/uv/concepts/projects/dependencies/)):
+- Test locally with `make docs`
 
-In ZFS, *dataset* refers to the objects *filesystem*, *ZVOL* and *snapshot*. <br />
-However, we need a word for *filesystem* & *ZVOL* but not a snapshot, bookmark, etc.
+Kick a full CI pipeline run (`do_ci=true` and `do_release=true`).
 
-Toward the user, the following terminology is used:
+Merge PR with merge commit.
 
-* **filesystem**: a ZFS filesystem or a ZVOL
-* **filesystem version**: a ZFS snapshot or a bookmark
-
-Sadly, the zrepl implementation is inconsistent in its use of these words:
-variables and types are often named *dataset* when they in fact refer to a *filesystem*.
-
-There will not be a big refactoring (an attempt was made, but it's destroying too much history without much gain).
-
-However, new contributions & patches should fix naming without further notice in the commit message.
+## Notes to Distro Package Maintainers
 
+* The `Makefile` in this project is not suitable for builds in distros.
+* Run the platform tests (Docs -> Usage -> Platform Tests) **on a test system** to validate that zrepl's abstractions on top of ZFS work with the system ZFS.
+* Ship a default config that adheres to your distro's `hier` and logging system.
+* Ship a service manager file and _please_ try to upstream it to this repository.
+  * `dist/systemd` contains a Systemd unit template.
+* Ship other material provided in `./dist`, e.g. in `/usr/share/zrepl/`.
+* Have a look at the `Makefile`'s `ZREPL_VERSION` variable and how it passed to Go's `ldFlags`.
+  This is how `zrepl version` knows what version number to show.
+  Your build system should set the `ldFlags` flags appropriately and add a prefix or suffix that indicates that the given zrepl binary is a distro build, not an official one.
+* Make sure you are informed about new zrepl versions, e.g. by subscribing to GitHub's release RSS feed.

build.Dockerfile

@@ -1,22 +0,0 @@
-FROM golang:latest
-
-RUN apt-get update && apt-get install -y \
-    python3-pip \
-    unzip
-
-RUN wget https://github.com/protocolbuffers/protobuf/releases/download/v3.6.1/protoc-3.6.1-linux-x86_64.zip
-RUN echo "6003de742ea3fcf703cfec1cd4a3380fd143081a2eb0e559065563496af27807  protoc-3.6.1-linux-x86_64.zip" | sha256sum -c
-RUN unzip -d /usr protoc-3.6.1-linux-x86_64.zip
-
-ADD lazy.sh /tmp/lazy.sh
-ADD docs/requirements.txt /tmp/requirements.txt
-ENV ZREPL_LAZY_DOCS_REQPATH=/tmp/requirements.txt
-RUN /tmp/lazy.sh devsetup
-
-# prepare volume mount of git checkout to /zrepl
-RUN mkdir -p /go/src/github.com/zrepl/zrepl
-RUN chmod -R 0777 /go
-RUN mkdir -p /.cache && chmod -R 0777 /.cache
-WORKDIR /go/src/github.com/zrepl/zrepl
-
-

build/.gitignore

@@ -0,0 +1 @@
+install/

build/build.Dockerfile

@@ -0,0 +1,30 @@
+FROM !SUBSTITUTED_BY_MAKEFILE
+
+ARG BUILD_UID=1000
+ARG BUILD_GID=1000
+
+RUN apt-get update && apt-get install -y \
+    python3 \
+    unzip \
+    gawk \
+    curl
+
+# Create build user with the host's UID/GID before installing uv
+RUN groupadd -g ${BUILD_GID} zrepl_build && \
+    useradd -u ${BUILD_UID} -g ${BUILD_GID} -m zrepl_build
+
+# Go toolchain uses xdg-cache
+RUN mkdir -p /.cache && chmod -R 0777 /.cache
+
+# Install uv as the build user - version from .uv-version file
+ADD .uv-version /tmp/.uv-version
+USER zrepl_build
+RUN UV_VERSION=$(cat /tmp/.uv-version) && \
+    curl -LsSf https://astral.sh/uv/${UV_VERSION}/install.sh | sh
+
+# Go devtools are managed by Makefile
+
+WORKDIR /src
+ENV PATH="/home/zrepl_build/.local/bin:$PATH" \
+    GOCACHE="/.cache/go-build"
+

build/get_golangci_lint.bash

@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+set -euo pipefail
+set -x
+
+# golangci-lint recommends against using `go get` and friends to install it
+
+cd "$1"
+
+VERSION=2.8.0
+FILENAME=golangci-lint-"$VERSION"-linux-"$GOHOSTARCH".tar.gz
+
+if [ -e "$FILENAME" ]; then
+    echo "$FILENAME" already exists 1>&2
+    exit 1
+fi
+
+wget --continue https://github.com/golangci/golangci-lint/releases/download/v"$VERSION"/"$FILENAME"
+
+stat "$FILENAME"
+
+# Select the correct checksum for the downloaded architecture
+case "$GOHOSTARCH" in
+    arm64) EXPECTED_SHA256="2a58388db8af5ab9330791cea0ebdd4100723cd05ad7185d92febaaee272ec9a" ;;
+    amd64) EXPECTED_SHA256="7048bc6b25c9515ed092c83f9fa8709ca97937ead52d9ff317a143299ee97a50" ;;
+    *)     echo "Unknown architecture: $GOHOSTARCH" >&2; exit 1 ;;
+esac
+
+# Verify checksum explicitly - fails if hash doesn't match
+echo "$EXPECTED_SHA256  $FILENAME" | sha256sum -c -
+
+tar -x  --strip-components=1 -f "$FILENAME"
+
+stat ./golangci-lint

build/get_protoc.bash

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+set -euo pipefail
+set -x
+
+cd "$1"
+
+MACH=$(uname -m)
+MACH="${MACH/aarch64/aarch_64}"
+
+VERSION=33.5
+FILENAME=protoc-"$VERSION"-linux-"$MACH".zip
+
+if [ -e "$FILENAME" ]; then
+    echo "$FILENAME" already exists 1>&2
+    exit 1
+fi
+
+wget --continue https://github.com/protocolbuffers/protobuf/releases/download/v"$VERSION"/"$FILENAME"
+
+stat "$FILENAME"
+
+# Select the correct checksum for the downloaded architecture
+case "$MACH" in
+    aarch_64) EXPECTED_SHA256="2b0fcf9b2c32cbadccc0eb7a88b841fffecd4a06fc80acdba2b5be45e815c38a" ;;
+    x86_64)   EXPECTED_SHA256="24e58fb231d50306ee28491f33a170301e99540f7e29ca461e0e80fd1239f8d1" ;;
+    *)        echo "Unknown architecture: $MACH" >&2; exit 1 ;;
+esac
+
+# Verify checksum explicitly - fails if hash doesn't match
+echo "$EXPECTED_SHA256  $FILENAME" | sha256sum -c -
+
+unzip -d . "$FILENAME"

build/go.mod

@@ -0,0 +1,24 @@
+module github.com/zrepl/zrepl/build
+
+go 1.24.13
+
+toolchain go1.25.7
+
+require (
+	github.com/alvaroloes/enumer v1.1.2
+	github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad
+	golang.org/x/tools v0.41.0
+	google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.6.1
+	google.golang.org/protobuf v1.36.11
+)
+
+require (
+	github.com/pascaldekloe/name v1.0.1 // indirect
+	golang.org/x/mod v0.32.0 // indirect
+	golang.org/x/sync v0.19.0 // indirect
+	golang.org/x/sys v0.41.0 // indirect
+	golang.org/x/telemetry v0.0.0-20260205145544-86a5c4bf3c8d // indirect
+	golang.org/x/text v0.31.0 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20250818200422-3122310a409c // indirect
+	google.golang.org/grpc v1.75.0 // indirect
+)

build/go.sum

@@ -0,0 +1,37 @@
+github.com/alvaroloes/enumer v1.1.2 h1:5khqHB33TZy1GWCO/lZwcroBFh7u+0j40T83VUbfAMY=
+github.com/alvaroloes/enumer v1.1.2/go.mod h1:FxrjvuXoDAx9isTJrv4c+T410zFi0DtXIT0m65DJ+Wo=
+github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
+github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
+github.com/pascaldekloe/name v0.0.0-20180628100202-0fd16699aae1/go.mod h1:eD5JxqMiuNYyFNmyY9rkJ/slN8y59oEu4Ei7F8OoKWQ=
+github.com/pascaldekloe/name v1.0.1 h1:9lnXOHeqeHHnWLbKfH6X98+4+ETVqFqxN09UXSjcMb0=
+github.com/pascaldekloe/name v1.0.1/go.mod h1:Z//MfYJnH4jVpQ9wkclwu2I2MkHmXTlT9wR5UZScttM=
+github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad h1:W0LEBv82YCGEtcmPA3uNZBI33/qF//HAAs3MawDjRa0=
+github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad/go.mod h1:Hy8o65+MXnS6EwGElrSRjUzQDLXreJlzYLlWiHtt8hM=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/mod v0.32.0 h1:9F4d3PHLljb6x//jOyokMv3eX+YDeepZSEo3mFJy93c=
+golang.org/x/mod v0.32.0/go.mod h1:SgipZ/3h2Ci89DlEtEXWUk/HteuRin+HHhN+WbNhguU=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.49.0 h1:eeHFmOGUTtaaPSGNmjBKpbng9MulQsJURQUAfUwY++o=
+golang.org/x/net v0.49.0/go.mod h1:/ysNB2EvaqvesRkuLAyjI1ycPZlQHM3q01F02UY/MV8=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.19.0 h1:vV+1eWNmZ5geRlYjzm2adRgW2/mcpevXNg50YZtPCE4=
+golang.org/x/sync v0.19.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.41.0 h1:Ivj+2Cp/ylzLiEU89QhWblYnOE9zerudt9Ftecq2C6k=
+golang.org/x/sys v0.41.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
+golang.org/x/telemetry v0.0.0-20260205145544-86a5c4bf3c8d h1:xjbyaj6khjO0ocYYa7k9sQLbdi4R1KwHnsS1QGijbsM=
+golang.org/x/telemetry v0.0.0-20260205145544-86a5c4bf3c8d/go.mod h1:b7fPSJ0pKZ3ccUh8gnTONJxhn3c/PS6tyzQvyqw4iA8=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.31.0 h1:aC8ghyu4JhP8VojJ2lEHBnochRno1sgL6nEi9WGFGMM=
+golang.org/x/text v0.31.0/go.mod h1:tKRAlv61yKIjGGHX/4tP1LTbc13YSec1pxVEWXzfoeM=
+golang.org/x/tools v0.0.0-20190524210228-3d17549cdc6b/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/tools v0.41.0 h1:a9b8iMweWG+S0OBnlU36rzLp20z1Rp10w+IY2czHTQc=
+golang.org/x/tools v0.41.0/go.mod h1:XSY6eDqxVNiYgezAVqqCeihT4j1U2CCsqvH3WhQpnlg=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20250818200422-3122310a409c h1:qXWI/sQtv5UKboZ/zUk7h+mrf/lXORyI+n9DKDAusdg=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20250818200422-3122310a409c/go.mod h1:gw1tLEfykwDz2ET4a12jcXt4couGAm7IwsVaTy0Sflo=
+google.golang.org/grpc v1.75.0 h1:+TW+dqTd2Biwe6KKfhE5JpiYIBWq865PhKGSXiivqt4=
+google.golang.org/grpc v1.75.0/go.mod h1:JtPAzKiq4v1xcAB2hydNlWI2RnF85XXcV0mhKXr2ecQ=
+google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.6.1 h1:/WILD1UcXj/ujCxgoL/DvRgt2CP3txG8+FwkUbb9110=
+google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.6.1/go.mod h1:YNKnb2OAApgYn2oYY47Rn7alMr1zWjb2U8Q0aoGWiNc=
+google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=
+google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=

build/go_install_host_tool.source

@@ -0,0 +1,6 @@
+export GO111MODULE=on # otherwise, a checkout of this repo in GOPATH will disable modules on Go 1.12 and earlier
+source <(go env)
+# build tools for the host platform
+export GOOS="$GOHOSTOS"
+export GOARCH="$GOHOSTARCH"
+# TODO GOARM=$GOHOSTARM?

build/go_install_tools.bash

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+set -x
+
+OUTDIR="$(readlink -f "$1")"
+if [ -e "$OUTDIR" ]; then
+    echo "$OUTDIR" already exists 1>&2
+    exit 1
+fi
+
+# go install command below will install tools to $GOBIN
+export GOBIN="$OUTDIR"
+
+cd "$(dirname "$0")"
+
+source ./go_install_host_tool.source
+
+cat tools.go | grep _ | awk -F'"' '{print $2}' | tee | xargs -tI '{}' go install '{}'

build/tools.go

@@ -0,0 +1,14 @@
+//go:build tools
+// +build tools
+
+package main
+
+// the lines are parsed by lazy.sh, do not edit
+import (
+	_ "github.com/alvaroloes/enumer"
+	_ "github.com/wadey/gocovmerge"
+	_ "golang.org/x/tools/cmd/goimports"
+	_ "golang.org/x/tools/cmd/stringer"
+	_ "google.golang.org/grpc/cmd/protoc-gen-go-grpc"
+	_ "google.golang.org/protobuf/cmd/protoc-gen-go"
+)

cli/cli.go

@@ -1,116 +0,0 @@
-package cli
-
-import (
-	"fmt"
-	"github.com/spf13/cobra"
-	"github.com/spf13/pflag"
-	"github.com/zrepl/zrepl/config"
-	"os"
-)
-
-var rootArgs struct {
-	configPath string
-}
-
-var rootCmd = &cobra.Command{
-	Use:   "zrepl",
-	Short: "One-stop ZFS replication solution",
-}
-
-var bashcompCmd = &cobra.Command{
-	Use:   "bashcomp path/to/out/file",
-	Short: "generate bash completions",
-	Run: func(cmd *cobra.Command, args []string) {
-		if len(args) != 1 {
-			fmt.Fprintf(os.Stderr, "specify exactly one positional agument\n")
-			cmd.Usage()
-			os.Exit(1)
-		}
-		if err := rootCmd.GenBashCompletionFile(args[0]); err != nil {
-			fmt.Fprintf(os.Stderr, "error generating bash completion: %s", err)
-			os.Exit(1)
-		}
-	},
-	Hidden: true,
-}
-
-func init() {
-	rootCmd.PersistentFlags().StringVar(&rootArgs.configPath, "config", "", "config file path")
-	rootCmd.AddCommand(bashcompCmd)
-}
-
-type Subcommand struct {
-	Use             string
-	Short           string
-	NoRequireConfig bool
-	Run             func(subcommand *Subcommand, args []string) error
-	SetupFlags      func(f *pflag.FlagSet)
-	SetupSubcommands  func() []*Subcommand
-
-	config *config.Config
-	configErr error
-}
-
-func (s *Subcommand) ConfigParsingError() error {
-	return s.configErr
-}
-
-func (s *Subcommand) Config() *config.Config {
-	if !s.NoRequireConfig && s.config == nil {
-		panic("command that requires config is running and has no config set")
-	}
-	return s.config
-}
-
-func (s *Subcommand) run(cmd *cobra.Command, args []string) {
-	s.tryParseConfig()
-	err := s.Run(s, args)
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "%s\n", err)
-		os.Exit(1)
-	}
-}
-
-func (s *Subcommand) tryParseConfig() {
-	config, err := config.ParseConfig(rootArgs.configPath)
-	s.configErr = err
-	if err != nil {
-		if s.NoRequireConfig {
-			// doesn't matter
-			return
-		} else {
-			fmt.Fprintf(os.Stderr, "could not parse config: %s\n", err)
-			os.Exit(1)
-		}
-	}
-	s.config = config
-}
-
-func AddSubcommand(s *Subcommand) {
-	addSubcommandToCobraCmd(rootCmd, s)
-}
-
-func addSubcommandToCobraCmd(c *cobra.Command, s *Subcommand) {
-	cmd := cobra.Command{
-		Use: s.Use,
-		Short: s.Short,
-	}
-	if s.SetupSubcommands == nil {
-		cmd.Run = s.run
-	} else {
-		for _, sub := range s.SetupSubcommands() {
-			addSubcommandToCobraCmd(&cmd, sub)
-		}
-	}
-	if s.SetupFlags != nil {
-		s.SetupFlags(cmd.Flags())
-	}
-	c.AddCommand(&cmd)
-}
-
-
-func Run() {
-	if err := rootCmd.Execute(); err != nil {
-		os.Exit(1)
-	}
-}

client/status.go

@@ -1,633 +0,0 @@
-package client
-
-import (
-	"fmt"
-	"github.com/gdamore/tcell/termbox"
-	"github.com/pkg/errors"
-	"github.com/spf13/pflag"
-	"github.com/zrepl/yaml-config"
-	"github.com/zrepl/zrepl/cli"
-	"github.com/zrepl/zrepl/daemon"
-	"github.com/zrepl/zrepl/daemon/job"
-	"github.com/zrepl/zrepl/daemon/pruner"
-	"github.com/zrepl/zrepl/replication"
-	"github.com/zrepl/zrepl/replication/fsrep"
-	"io"
-	"math"
-	"net/http"
-	"os"
-	"sort"
-	"strings"
-	"sync"
-	"time"
-)
-
-type bytesProgressHistory struct {
-	changeCounter     int
-	lastChangeAt      time.Time
-	last              int64
-	bpsIncreaseExpAvg float64
-}
-
-func (p *bytesProgressHistory) Update(currentVal int64) (bytesPerSecondAvg int64, changeCount int) {
-	if currentVal < p.last {
-		*p = bytesProgressHistory{
-			last: currentVal,
-			lastChangeAt: time.Now(),
-		}
-	}
-	defer func() {
-		p.last = currentVal
-	}()
-	if time.Now().Sub(p.lastChangeAt) > 3 *time.Second { // FIXME depends on refresh frequency
-		p.changeCounter = 0
-		p.bpsIncreaseExpAvg = 0
-	}
-	if currentVal != p.last {
-		p.changeCounter++
-		p.lastChangeAt = time.Now()
-	}
-
-	byteIncrease := float64(currentVal - p.last)
-	if byteIncrease < 0 {
-		byteIncrease = 0
-	}
-	const factor = 0.1
-	p.bpsIncreaseExpAvg = (1-factor) * p.bpsIncreaseExpAvg + factor *byteIncrease
-	return int64(p.bpsIncreaseExpAvg), p.changeCounter
-}
-
-type tui struct {
-	x, y   int
-	indent int
-
-	lock   sync.Mutex //For report and error
-	report map[string]job.Status
-	err    error
-
-	replicationProgress map[string]*bytesProgressHistory // by job name
-}
-
-func newTui() tui {
-	return tui{
-		replicationProgress: make(map[string]*bytesProgressHistory, 0),
-	}
-}
-
-func (t *tui) moveCursor(x, y int) {
-	t.x += x
-	t.y += y
-}
-
-const INDENT_MULTIPLIER = 4
-
-func (t *tui) moveLine(dl int, col int) {
-	t.y += dl
-	t.x = t.indent*INDENT_MULTIPLIER + col
-}
-
-func (t *tui) write(text string) {
-	for _, c := range text {
-		if c == '\n' {
-			t.newline()
-			continue
-		}
-		termbox.SetCell(t.x, t.y, c, termbox.ColorDefault, termbox.ColorDefault)
-		t.x += 1
-	}
-}
-
-func (t *tui) printf(text string, a ...interface{}) {
-	t.write(fmt.Sprintf(text, a...))
-}
-
-func wrap(s string, width int) string {
-	var b strings.Builder
-	for len(s) > 0 {
-		rem := width
-		if rem > len(s) {
-			rem = len(s)
-		}
-		if idx := strings.IndexAny(s, "\n\r"); idx != -1 && idx < rem {
-			rem = idx+1
-		}
-		untilNewline := strings.TrimSpace(s[:rem])
-		s = s[rem:]
-		if len(untilNewline) == 0 {
-			continue
-		}
-		b.WriteString(untilNewline)
-		b.WriteString("\n")
-	}
-	return strings.TrimSpace(b.String())
-}
-
-func (t *tui) printfDrawIndentedAndWrappedIfMultiline(format string, a ...interface{}) {
-	whole := fmt.Sprintf(format, a...)
-	width, _ := termbox.Size()
-	if !strings.ContainsAny(whole, "\n\r") && t.x + len(whole) <= width {
-		t.printf(format, a...)
-	} else {
-		t.addIndent(1)
-		t.newline()
-		t.write(wrap(whole, width - INDENT_MULTIPLIER*t.indent))
-		t.addIndent(-1)
-	}
-}
-
-func (t *tui) newline() {
-	t.moveLine(1, 0)
-}
-
-func (t *tui) setIndent(indent int) {
-	t.indent = indent
-	t.moveLine(0, 0)
-}
-
-func (t *tui) addIndent(indent int) {
-	t.indent += indent
-	t.moveLine(0, 0)
-}
-
-
-var statusFlags struct {
-	Raw bool
-}
-
-var StatusCmd = &cli.Subcommand{
-	Use:   "status",
-	Short: "show job activity or dump as JSON for monitoring",
-	SetupFlags: func(f *pflag.FlagSet) {
-		f.BoolVar(&statusFlags.Raw, "raw", false, "dump raw status description from zrepl daemon")
-	},
-	Run: runStatus,
-}
-
-func runStatus(s *cli.Subcommand, args []string) error {
-	httpc, err := controlHttpClient(s.Config().Global.Control.SockPath)
-	if err != nil {
-		return err
-	}
-
-	if statusFlags.Raw {
-		resp, err := httpc.Get("http://unix"+daemon.ControlJobEndpointStatus)
-		if err != nil {
-			return err
-		}
-		defer resp.Body.Close()
-		if resp.StatusCode != http.StatusOK {
-			fmt.Fprintf(os.Stderr, "Received error response:\n")
-			io.CopyN(os.Stderr, resp.Body, 4096)
-			return errors.Errorf("exit")
-		}
-		if _, err := io.Copy(os.Stdout, resp.Body); err != nil {
-			return err
-		}
-		return nil
-	}
-
-	t := newTui()
-	t.lock.Lock()
-	t.err = errors.New("Got no report yet")
-	t.lock.Unlock()
-
-	err = termbox.Init()
-	if err != nil {
-		return err
-	}
-	defer termbox.Close()
-
-	update := func() {
-		m := make(map[string]job.Status)
-
-		err2 := jsonRequestResponse(httpc, daemon.ControlJobEndpointStatus,
-			struct{}{},
-			&m,
-		)
-
-		t.lock.Lock()
-		t.err = err2
-		t.report = m
-		t.lock.Unlock()
-		t.draw()
-	}
-	update()
-
-	ticker := time.NewTicker(500 * time.Millisecond)
-	defer ticker.Stop()
-	go func() {
-		for _ = range ticker.C {
-			update()
-		}
-	}()
-
-	termbox.HideCursor()
-	termbox.Clear(termbox.ColorDefault, termbox.ColorDefault)
-
-loop:
-	for {
-		switch ev := termbox.PollEvent(); ev.Type {
-		case termbox.EventKey:
-			switch ev.Key {
-			case termbox.KeyEsc:
-				break loop
-			case termbox.KeyCtrlC:
-				break loop
-			}
-		case termbox.EventResize:
-			t.draw()
-		}
-	}
-
-	return nil
-
-}
-
-func (t *tui) getReplicationProgresHistory(jobName string) *bytesProgressHistory {
-	p, ok := t.replicationProgress[jobName]
-	if !ok {
-		p = &bytesProgressHistory{}
-		t.replicationProgress[jobName] = p
-	}
-	return p
-}
-
-func (t *tui) draw() {
-	t.lock.Lock()
-	defer t.lock.Unlock()
-
-	termbox.Clear(termbox.ColorDefault, termbox.ColorDefault)
-	t.x = 0
-	t.y = 0
-	t.indent = 0
-
-	if t.err != nil {
-		t.write(t.err.Error())
-	} else {
-		//Iterate over map in alphabetical order
-		keys := make([]string, len(t.report))
-		i := 0
-		for k, _ := range t.report {
-			keys[i] = k
-			i++
-		}
-		sort.Strings(keys)
-
-		for _, k := range keys {
-			v := t.report[k]
-			if len(k) == 0 || daemon.IsInternalJobName(k) { //Internal job
-				continue
-			}
-			t.setIndent(0)
-
-			t.printf("Job: %s", k)
-			t.setIndent(1)
-			t.newline()
-			t.printf("Type: %s", v.Type)
-			t.setIndent(1)
-			t.newline()
-
-			if v.Type != job.TypePush && v.Type != job.TypePull {
-				t.printf("No status representation for job type '%s', dumping as YAML", v.Type)
-				t.newline()
-				asYaml, err := yaml.Marshal(v.JobSpecific)
-				if err != nil {
-					t.printf("Error marshaling status to YAML: %s", err)
-					t.newline()
-					continue
-				}
-				t.write(string(asYaml))
-				t.newline()
-				continue
-			}
-
-			pushStatus, ok := v.JobSpecific.(*job.ActiveSideStatus)
-			if !ok || pushStatus == nil {
-				t.printf("ActiveSideStatus is null")
-				t.newline()
-				continue
-			}
-
-			t.printf("Replication:")
-			t.newline()
-			t.addIndent(1)
-			t.renderReplicationReport(pushStatus.Replication, t.getReplicationProgresHistory(k))
-			t.addIndent(-1)
-
-			t.printf("Pruning Sender:")
-			t.newline()
-			t.addIndent(1)
-			t.renderPrunerReport(pushStatus.PruningSender)
-			t.addIndent(-1)
-
-			t.printf("Pruning Receiver:")
-			t.newline()
-			t.addIndent(1)
-			t.renderPrunerReport(pushStatus.PruningReceiver)
-			t.addIndent(-1)
-
-		}
-	}
-	termbox.Flush()
-}
-
-func (t *tui) renderReplicationReport(rep *replication.Report, history *bytesProgressHistory) {
-	if rep == nil {
-		t.printf("...\n")
-		return
-	}
-
-	all := make([]*fsrep.Report, 0, len(rep.Completed)+len(rep.Pending) + 1)
-	all = append(all, rep.Completed...)
-	all = append(all, rep.Pending...)
-	if rep.Active != nil {
-		all = append(all, rep.Active)
-	}
-	sort.Slice(all, func(i, j int) bool {
-		return all[i].Filesystem < all[j].Filesystem
-	})
-
-	state, err := replication.StateString(rep.Status)
-	if err != nil {
-		t.printf("Status: %q (parse error: %q)\n", rep.Status, err)
-		return
-	}
-
-	t.printf("Status: %s", state)
-	t.newline()
-	if rep.Problem != "" {
-		t.printf("Problem: ")
-		t.printfDrawIndentedAndWrappedIfMultiline("%s", rep.Problem)
-		t.newline()
-	}
-	if rep.SleepUntil.After(time.Now()) && !state.IsTerminal() {
-		t.printf("Sleeping until %s (%s left)\n", rep.SleepUntil, rep.SleepUntil.Sub(time.Now()))
-	}
-
-	if state != replication.Planning && state != replication.PlanningError {
-		// Progress: [---------------]
-		sumUpFSRep := func(rep *fsrep.Report) (transferred, total int64) {
-			for _, s := range rep.Pending {
-				transferred += s.Bytes
-				total  += s.ExpectedBytes
-			}
-			for _, s := range rep.Completed {
-				transferred += s.Bytes
-				total += s.ExpectedBytes
-			}
-			return
-		}
-		var transferred, total int64
-		for _, fs := range all {
-			fstx, fstotal := sumUpFSRep(fs)
-			transferred += fstx
-			total += fstotal
-		}
-		rate, changeCount := history.Update(transferred)
-		t.write("Progress: ")
-		t.drawBar(50, transferred, total, changeCount)
-		t.write(fmt.Sprintf(" %s / %s @ %s/s", ByteCountBinary(transferred), ByteCountBinary(total), ByteCountBinary(rate)))
-		t.newline()
-	}
-
-	var maxFSLen int
-	for _, fs := range all {
-		if len(fs.Filesystem) > maxFSLen {
-			maxFSLen = len(fs.Filesystem)
-		}
-	}
-	for _, fs := range all {
-		t.printFilesystemStatus(fs, fs == rep.Active, maxFSLen)
-	}
-}
-
-func (t *tui) renderPrunerReport(r *pruner.Report) {
-	if r == nil {
-		t.printf("...\n")
-		return
-	}
-
-	state, err := pruner.StateString(r.State)
-	if err != nil {
-		t.printf("Status: %q (parse error: %q)\n", r.State, err)
-		return
-	}
-
-	t.printf("Status: %s", state)
-	t.newline()
-
-	if r.Error != "" {
-		t.printf("Error: %s\n", r.Error)
-	}
-	if r.SleepUntil.After(time.Now()) {
-		t.printf("Sleeping until %s (%s left)\n", r.SleepUntil, r.SleepUntil.Sub(time.Now()))
-	}
-
-	type commonFS struct {
-		*pruner.FSReport
-		completed bool
-	}
-	all := make([]commonFS, 0, len(r.Pending) + len(r.Completed))
-	for i := range r.Pending {
-		all = append(all, commonFS{&r.Pending[i], false})
-	}
-	for i := range r.Completed {
-		all = append(all, commonFS{&r.Completed[i], true})
-	}
-
-	switch state {
-	case pruner.Plan: fallthrough
-	case pruner.PlanWait: fallthrough
-	case pruner.ErrPerm:
-		return
-	}
-
-	if len(all) == 0 {
-		t.printf("nothing to do\n")
-		return
-	}
-
-	var totalDestroyCount, completedDestroyCount int
-	var maxFSname int
-	for _, fs := range all {
-		totalDestroyCount += len(fs.DestroyList)
-		if fs.completed {
-			completedDestroyCount += len(fs.DestroyList)
-		}
-		if maxFSname < len(fs.Filesystem) {
-			maxFSname = len(fs.Filesystem)
-		}
-	}
-
-	// global progress bar
-	progress := int(math.Round(80 * float64(completedDestroyCount) / float64(totalDestroyCount)))
-	t.write("Progress: ")
-	t.write("[")
-	t.write(times("=", progress))
-	t.write(">")
-	t.write(times("-", 80 - progress))
-	t.write("]")
-	t.printf(" %d/%d snapshots", completedDestroyCount, totalDestroyCount)
-	t.newline()
-
-	sort.SliceStable(all, func(i, j int) bool {
-		return strings.Compare(all[i].Filesystem, all[j].Filesystem) == -1
-	})
-
-	// Draw a table-like representation of 'all'
-	for _, fs := range all {
-		t.write(rightPad(fs.Filesystem, maxFSname, " "))
-		t.write(" ")
-		if fs.LastError != "" {
-			t.printf("ERROR (%d): %s\n", fs.ErrorCount, fs.LastError) // whitespace is padding
-			continue
-		}
-
-		pruneRuleActionStr := fmt.Sprintf("(destroy %d of %d snapshots)",
-			len(fs.DestroyList), len(fs.SnapshotList))
-
-		if fs.completed {
-			t.printf( "Completed  %s\n", pruneRuleActionStr)
-			continue
-		}
-
-		t.write("Pending    ") // whitespace is padding 10
-		if len(fs.DestroyList) == 1 {
-			t.write(fs.DestroyList[0].Name)
-		} else {
-			t.write(pruneRuleActionStr)
-		}
-		t.newline()
-	}
-
-}
-
-const snapshotIndent = 1
-func calculateMaxFSLength(all []*fsrep.Report) (maxFS, maxStatus int) {
-	for _, e := range all {
-		if len(e.Filesystem) > maxFS {
-			maxFS = len(e.Filesystem)
-		}
-		all2 := make([]*fsrep.StepReport, 0, len(e.Pending) + len(e.Completed))
-		all2 = append(all2, e.Pending...)
-		all2 = append(all2, e.Completed...)
-		for _, e2 := range all2 {
-			elen := len(e2.Problem) + len(e2.From) + len(e2.To) + 60 // random spacing, units, labels, etc
-			if elen > maxStatus {
-				maxStatus = elen
-			}
-		}
-	}
-	return
-}
-
-func times(str string, n int) (out string) {
-	for i := 0; i < n; i++ {
-		out += str
-	}
-	return
-}
-
-func rightPad(str string, length int, pad string) string {
-	if len(str) > length {
-		return str[:length]
-	}
-	return str + times(pad, length-len(str))
-}
-
-
-func leftPad(str string, length int, pad string) string {
-	if len(str) > length {
-		return str[len(str)-length:]
-	}
-	return times(pad, length-len(str)) + str
-}
-
-var arrowPositions = `>\|/`
-
-// changeCount = 0 indicates stall / no progresss
-func (t *tui) drawBar(length int, bytes, totalBytes int64, changeCount int) {
-	var completedLength int
-	if totalBytes > 0 {
-		completedLength = int(int64(length) * bytes / totalBytes)
-		if completedLength > length {
-			completedLength = length
-		}
-	} else if totalBytes == bytes {
-		completedLength = length
-	}
-
-	t.write("[")
-	t.write(times("=", completedLength))
-	t.write( string(arrowPositions[changeCount%len(arrowPositions)]))
-	t.write(times("-", length-completedLength))
-	t.write("]")
-}
-
-func StringStepState(s fsrep.StepState) string {
-	switch s {
-	case fsrep.StepReplicationReady: return "Ready"
-	case fsrep.StepMarkReplicatedReady: return "MarkReady"
-	case fsrep.StepCompleted: return "Completed"
-	default:
-		return fmt.Sprintf("UNKNOWN %d", s)
-	}
-}
-
-func (t *tui) printFilesystemStatus(rep *fsrep.Report, active bool, maxFS int) {
-
-	bytes := int64(0)
-	totalBytes := int64(0)
-	for _, s := range rep.Pending {
-		bytes += s.Bytes
-		totalBytes += s.ExpectedBytes
-	}
-	for _, s := range rep.Completed {
-		bytes += s.Bytes
-		totalBytes += s.ExpectedBytes
-	}
-
-
-	status := fmt.Sprintf("%s (step %d/%d, %s/%s)",
-		rep.Status,
-		len(rep.Completed), len(rep.Pending) + len(rep.Completed),
-		ByteCountBinary(bytes), ByteCountBinary(totalBytes),
-
-	)
-
-	activeIndicator := " "
-	if active {
-		activeIndicator = "*"
-	}
-	t.printf("%s %s %s ",
-		activeIndicator,
-		rightPad(rep.Filesystem, maxFS, " "),
-		status)
-
-	next := ""
-	if rep.Problem != "" {
-		next = rep.Problem
-	} else if len(rep.Pending) > 0 {
-		if rep.Pending[0].From != "" {
-			next = fmt.Sprintf("next: %s => %s", rep.Pending[0].From, rep.Pending[0].To)
-		} else {
-			next = fmt.Sprintf("next: %s (full)", rep.Pending[0].To)
-		}
-	}
-	t.printfDrawIndentedAndWrappedIfMultiline("%s", next)
-
-	t.newline()
-}
-
-func ByteCountBinary(b int64) string {
-	const unit = 1024
-	if b < unit {
-		return fmt.Sprintf("%d B", b)
-	}
-	div, exp := int64(unit), 0
-	for n := b / unit; n >= unit; n /= unit {
-		div *= unit
-		exp++
-	}
-	return fmt.Sprintf("%.1f %ciB", float64(b)/float64(div), "KMGTPE"[exp])
-}

client/testcmd.go

@@ -1,108 +0,0 @@
-package client
-
-import (
-	"fmt"
-	"github.com/spf13/pflag"
-	"github.com/zrepl/zrepl/cli"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/filters"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-var TestCmd = &cli.Subcommand {
-	Use: "test",
-	SetupSubcommands: func() []*cli.Subcommand {
-		return []*cli.Subcommand{testFilter}
-	},
-}
-
-var testFilterArgs struct {
-	job string
-	all bool
-	input string
-}
-
-var testFilter = &cli.Subcommand{
-	Use: "filesystems --job JOB [--all | --input INPUT]",
-	Short: "test filesystems filter specified in push or source job",
-	SetupFlags: func(f *pflag.FlagSet) {
-		f.StringVar(&testFilterArgs.job, "job", "", "the name of the push or source job")
-		f.StringVar(&testFilterArgs.input, "input", "", "a filesystem name to test against the job's filters")
-		f.BoolVar(&testFilterArgs.all, "all", false, "test all local filesystems")
-	},
-	Run: runTestFilterCmd,
-}
-
-func runTestFilterCmd(subcommand *cli.Subcommand, args []string) error {
-
-	if testFilterArgs.job == "" {
-		return fmt.Errorf("must specify --job flag")
-	}
-	if !(testFilterArgs.all != (testFilterArgs.input != "")) { // xor
-		return fmt.Errorf("must set one: --all or --input")
-	}
-
-	conf := subcommand.Config()
-
-	var confFilter config.FilesystemsFilter
-	job, err := conf.Job(testFilterArgs.job)
-	if err != nil {
-		return err
-	}
-	switch j := job.Ret.(type) {
-	case *config.SourceJob: confFilter = j.Filesystems
-	case *config.PushJob: confFilter = j.Filesystems
-	default:
-		return fmt.Errorf("job type %T does not have filesystems filter", j)
-	}
-
-	f, err := filters.DatasetMapFilterFromConfig(confFilter)
-	if err != nil {
-		return fmt.Errorf("filter invalid: %s", err)
-	}
-
-	var fsnames []string
-	if testFilterArgs.input != "" {
-		fsnames = []string{testFilterArgs.input}
-	} else {
-		out, err := zfs.ZFSList([]string{"name"})
-		if err != nil {
-			return fmt.Errorf("could not list ZFS filesystems: %s", err)
-		}
-		for _, row := range out {
-
-			fsnames = append(fsnames, row[0])
-		}
-	}
-
-	fspaths := make([]*zfs.DatasetPath, len(fsnames))
-	for i, fsname := range fsnames {
-		path, err := zfs.NewDatasetPath(fsname)
-		if err != nil {
-			return err
-		}
-		fspaths[i] = path
-	}
-
-	hadFilterErr := false
-	for _, in := range fspaths {
-		var res string
-		var errStr string
-		pass, err := f.Filter(in)
-		if err != nil {
-			res = "ERROR"
-			errStr = err.Error()
-			hadFilterErr = true
-		} else if pass {
-			res = "ACCEPT"
-		} else {
-			res = "REJECT"
-		}
-		fmt.Printf("%s\t%s\t%s\n", res, in.ToString(), errStr)
-	}
-
-	if hadFilterErr {
-		return fmt.Errorf("filter errors occurred")
-	}
-	return nil
-}

config/config.go

@@ -1,483 +0,0 @@
-package config
-
-import (
-	"fmt"
-	"github.com/pkg/errors"
-	"github.com/zrepl/yaml-config"
-	"io/ioutil"
-	"os"
-	"reflect"
-	"regexp"
-	"strconv"
-	"time"
-)
-
-type Config struct {
-	Jobs   []JobEnum `yaml:"jobs"`
-	Global *Global   `yaml:"global,optional,fromdefaults"`
-}
-
-func (c *Config) Job(name string) (*JobEnum, error) {
-	for _, j := range c.Jobs {
-		if j.Name() == name {
-			return &j, nil
-		}
-	}
-	return nil, fmt.Errorf("job %q not defined in config", name)
-}
-
-type JobEnum struct {
-	Ret interface{}
-}
-
-func (j JobEnum) Name() string {
-	var name string
-	switch v := j.Ret.(type) {
-	case *PushJob: name = v.Name
-	case *SinkJob: name = v.Name
-	case *PullJob: name = v.Name
-	case *SourceJob: name = v.Name
-	default:
-		panic(fmt.Sprintf("unknownn job type %T", v))
-	}
-	return name
-}
-
-type ActiveJob struct {
-	Type         string                `yaml:"type"`
-	Name         string                `yaml:"name"`
-	Connect     ConnectEnum     `yaml:"connect"`
-	Pruning      PruningSenderReceiver `yaml:"pruning"`
-	Debug        JobDebugSettings      `yaml:"debug,optional"`
-}
-
-type PassiveJob struct {
-	Type        string           `yaml:"type"`
-	Name        string           `yaml:"name"`
-	Serve       ServeEnum `yaml:"serve"`
-	Debug       JobDebugSettings `yaml:"debug,optional"`
-}
-
-type PushJob struct {
-	ActiveJob `yaml:",inline"`
-	Snapshotting SnapshottingEnum          `yaml:"snapshotting"`
-	Filesystems FilesystemsFilter `yaml:"filesystems"`
-}
-
-type PullJob struct {
-	ActiveJob `yaml:",inline"`
-	RootFS    string        `yaml:"root_fs"`
-	Interval  time.Duration `yaml:"interval,positive"`
-}
-
-type SinkJob struct {
-	PassiveJob `yaml:",inline"`
-	RootFS     string `yaml:"root_fs"`
-}
-
-type SourceJob struct {
-	PassiveJob `yaml:",inline"`
-	Snapshotting SnapshottingEnum      `yaml:"snapshotting"`
-	Filesystems FilesystemsFilter `yaml:"filesystems"`
-}
-
-type FilesystemsFilter map[string]bool
-
-type SnapshottingEnum struct {
-	Ret interface{}
-}
-
-type SnapshottingPeriodic struct {
-	Type string		`yaml:"type"`
-	Prefix string	`yaml:"prefix"`
-	Interval time.Duration `yaml:"interval,positive"`
-}
-
-type SnapshottingManual struct {
-	Type string `yaml:"type"`
-}
-
-type PruningSenderReceiver struct {
-	KeepSender   []PruningEnum `yaml:"keep_sender"`
-	KeepReceiver []PruningEnum `yaml:"keep_receiver"`
-}
-
-type PruningLocal struct {
-	Keep []PruningEnum `yaml:"keep"`
-}
-
-type LoggingOutletEnumList []LoggingOutletEnum
-
-func (l *LoggingOutletEnumList) SetDefault() {
-	def := `
-type: "stdout"
-time: true
-level: "warn"
-format: "human"
-`
-	s := &StdoutLoggingOutlet{}
-	err := yaml.UnmarshalStrict([]byte(def), &s)
-	if err != nil {
-		panic(err)
-	}
-	*l = []LoggingOutletEnum{LoggingOutletEnum{Ret: s}}
-}
-
-var _ yaml.Defaulter = &LoggingOutletEnumList{}
-
-type Global struct {
-	Logging    *LoggingOutletEnumList `yaml:"logging,optional,fromdefaults"`
-	Monitoring []MonitoringEnum       `yaml:"monitoring,optional"`
-	Control    *GlobalControl         `yaml:"control,optional,fromdefaults"`
-	Serve      *GlobalServe           `yaml:"serve,optional,fromdefaults"`
-	RPC        *RPCConfig             `yaml:"rpc,optional,fromdefaults"`
-}
-
-func Default(i interface{}) {
-	v := reflect.ValueOf(i)
-	if v.Kind() != reflect.Ptr {
-		panic(v)
-	}
-	y := `{}`
-	err := yaml.Unmarshal([]byte(y), v.Interface())
-	if err != nil {
-		panic(err)
-	}
-}
-
-type RPCConfig struct {
-	Timeout             time.Duration `yaml:"timeout,optional,positive,default=10s"`
-	TxChunkSize         uint32        `yaml:"tx_chunk_size,optional,default=32768"`
-	RxStructuredMaxLen  uint32        `yaml:"rx_structured_max,optional,default=16777216"`
-	RxStreamChunkMaxLen uint32        `yaml:"rx_stream_chunk_max,optional,default=16777216"`
-	RxHeaderMaxLen      uint32        `yaml:"rx_header_max,optional,default=40960"`
-	SendHeartbeatInterval             time.Duration `yaml:"send_heartbeat_interval,optional,positive,default=5s"`
-
-}
-
-type ConnectEnum struct {
-	Ret interface{}
-}
-
-type ConnectCommon struct {
-	Type string     `yaml:"type"`
-	RPC  *RPCConfig `yaml:"rpc,optional"`
-}
-
-type TCPConnect struct {
-	ConnectCommon `yaml:",inline"`
-	Address       string        `yaml:"address"`
-	DialTimeout   time.Duration `yaml:"dial_timeout,positive,default=10s"`
-}
-
-type TLSConnect struct {
-	ConnectCommon `yaml:",inline"`
-	Address       string        `yaml:"address"`
-	Ca            string        `yaml:"ca"`
-	Cert          string        `yaml:"cert"`
-	Key           string        `yaml:"key"`
-	ServerCN      string        `yaml:"server_cn"`
-	DialTimeout   time.Duration `yaml:"dial_timeout,positive,default=10s"`
-}
-
-type SSHStdinserverConnect struct {
-	ConnectCommon        `yaml:",inline"`
-	Host                 string        `yaml:"host"`
-	User                 string        `yaml:"user"`
-	Port                 uint16        `yaml:"port"`
-	IdentityFile         string        `yaml:"identity_file"`
-	TransportOpenCommand []string      `yaml:"transport_open_command,optional"` //TODO unused
-	SSHCommand           string        `yaml:"ssh_command,optional"`            //TODO unused
-	Options              []string      `yaml:"options,optional"`
-	DialTimeout          time.Duration `yaml:"dial_timeout,positive,default=10s"`
-}
-
-type LocalConnect struct {
-	ConnectCommon `yaml:",inline"`
-	ListenerName string `yaml:"listener_name"`
-	ClientIdentity string `yaml:"client_identity"`
-}
-
-type ServeEnum struct {
-	Ret interface{}
-}
-
-type ServeCommon struct {
-	Type string     `yaml:"type"`
-	RPC  *RPCConfig `yaml:"rpc,optional"`
-}
-
-type TCPServe struct {
-	ServeCommon `yaml:",inline"`
-	Listen      string            `yaml:"listen"`
-	Clients     map[string]string `yaml:"clients"`
-}
-
-type TLSServe struct {
-	ServeCommon      `yaml:",inline"`
-	Listen           string        `yaml:"listen"`
-	Ca               string        `yaml:"ca"`
-	Cert             string        `yaml:"cert"`
-	Key              string        `yaml:"key"`
-	ClientCNs        []string      `yaml:"client_cns"`
-	HandshakeTimeout time.Duration `yaml:"handshake_timeout,positive,default=10s"`
-}
-
-type StdinserverServer struct {
-	ServeCommon    `yaml:",inline"`
-	ClientIdentities []string `yaml:"client_identities"`
-}
-
-type LocalServe struct {
-	ServeCommon `yaml:",inline"`
-	ListenerName string `yaml:"listener_name"`
-}
-
-type PruningEnum struct {
-	Ret interface{}
-}
-
-type PruneKeepNotReplicated struct {
-	Type string `yaml:"type"`
-	KeepSnapshotAtCursor bool `yaml:"keep_snapshot_at_cursor,optional,default=true"`
-}
-
-type PruneKeepLastN struct {
-	Type  string `yaml:"type"`
-	Count int    `yaml:"count"`
-}
-
-type PruneKeepRegex struct { // FIXME rename to KeepRegex
-	Type  string `yaml:"type"`
-	Regex string `yaml:"regex"`
-}
-
-type LoggingOutletEnum struct {
-	Ret interface{}
-}
-
-type LoggingOutletCommon struct {
-	Type   string `yaml:"type"`
-	Level  string `yaml:"level"`
-	Format string `yaml:"format"`
-}
-
-type StdoutLoggingOutlet struct {
-	LoggingOutletCommon `yaml:",inline"`
-	Time                bool `yaml:"time,default=true"`
-	Color               bool `yaml:"color,default=true"`
-}
-
-type SyslogLoggingOutlet struct {
-	LoggingOutletCommon `yaml:",inline"`
-	RetryInterval       time.Duration `yaml:"retry_interval,positive,default=10s"`
-}
-
-type TCPLoggingOutlet struct {
-	LoggingOutletCommon `yaml:",inline"`
-	Address             string               `yaml:"address"`
-	Net                 string               `yaml:"net,default=tcp"`
-	RetryInterval       time.Duration        `yaml:"retry_interval,positive,default=10s"`
-	TLS                 *TCPLoggingOutletTLS `yaml:"tls,optional"`
-}
-
-type TCPLoggingOutletTLS struct {
-	CA   string `yaml:"ca"`
-	Cert string `yaml:"cert"`
-	Key  string `yaml:"key"`
-}
-
-type MonitoringEnum struct {
-	Ret interface{}
-}
-
-type PrometheusMonitoring struct {
-	Type   string `yaml:"type"`
-	Listen string `yaml:"listen"`
-}
-
-type GlobalControl struct {
-	SockPath string `yaml:"sockpath,default=/var/run/zrepl/control"`
-}
-
-type GlobalServe struct {
-	StdinServer *GlobalStdinServer `yaml:"stdinserver,optional,fromdefaults"`
-}
-
-type GlobalStdinServer struct {
-	SockDir string `yaml:"sockdir,default=/var/run/zrepl/stdinserver"`
-}
-
-type JobDebugSettings struct {
-	Conn *struct {
-		ReadDump  string `yaml:"read_dump"`
-		WriteDump string `yaml:"write_dump"`
-	} `yaml:"conn,optional"`
-	RPCLog bool `yaml:"rpc_log,optional,default=false"`
-}
-
-func enumUnmarshal(u func(interface{}, bool) error, types map[string]interface{}) (interface{}, error) {
-	var in struct {
-		Type string
-	}
-	if err := u(&in, true); err != nil {
-		return nil, err
-	}
-	if in.Type == "" {
-		return nil, &yaml.TypeError{Errors: []string{"must specify type"}}
-	}
-
-	v, ok := types[in.Type]
-	if !ok {
-		return nil, &yaml.TypeError{Errors: []string{fmt.Sprintf("invalid type name %q", in.Type)}}
-	}
-	if err := u(v, false); err != nil {
-		return nil, err
-	}
-	return v, nil
-}
-
-func (t *JobEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
-	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"push":   &PushJob{},
-		"sink":   &SinkJob{},
-		"pull":   &PullJob{},
-		"source": &SourceJob{},
-	})
-	return
-}
-
-func (t *ConnectEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
-	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"tcp":             &TCPConnect{},
-		"tls":             &TLSConnect{},
-		"ssh+stdinserver": &SSHStdinserverConnect{},
-		"local": 		   &LocalConnect{},
-	})
-	return
-}
-
-func (t *ServeEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
-	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"tcp":         &TCPServe{},
-		"tls":         &TLSServe{},
-		"stdinserver": &StdinserverServer{},
-		"local"      : &LocalServe{},
-	})
-	return
-}
-
-func (t *PruningEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
-	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"not_replicated": &PruneKeepNotReplicated{},
-		"last_n":         &PruneKeepLastN{},
-		"grid":           &PruneGrid{},
-		"regex":          &PruneKeepRegex{},
-	})
-	return
-}
-
-func (t *SnapshottingEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
-	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"periodic": &SnapshottingPeriodic{},
-		"manual": &SnapshottingManual{},
-	})
-	return
-}
-
-func (t *LoggingOutletEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
-	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"stdout": &StdoutLoggingOutlet{},
-		"syslog": &SyslogLoggingOutlet{},
-		"tcp":    &TCPLoggingOutlet{},
-	})
-	return
-}
-
-func (t *MonitoringEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
-	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"prometheus": &PrometheusMonitoring{},
-	})
-	return
-}
-
-var ConfigFileDefaultLocations = []string{
-	"/etc/zrepl/zrepl.yml",
-	"/usr/local/etc/zrepl/zrepl.yml",
-}
-
-func ParseConfig(path string) (i *Config, err error) {
-
-	if path == "" {
-		// Try default locations
-		for _, l := range ConfigFileDefaultLocations {
-			stat, statErr := os.Stat(l)
-			if statErr != nil {
-				continue
-			}
-			if !stat.Mode().IsRegular() {
-				err = errors.Errorf("file at default location is not a regular file: %s", l)
-				return
-			}
-			path = l
-			break
-		}
-	}
-
-	var bytes []byte
-
-	if bytes, err = ioutil.ReadFile(path); err != nil {
-		return
-	}
-
-	return ParseConfigBytes(bytes)
-}
-
-func ParseConfigBytes(bytes []byte) (*Config, error) {
-	var c *Config
-	if err := yaml.UnmarshalStrict(bytes, &c); err != nil {
-		return nil, err
-	}
-	if c == nil {
-		return nil, fmt.Errorf("config is empty or only consists of comments")
-	}
-	return c, nil
-}
-
-var durationStringRegex *regexp.Regexp = regexp.MustCompile(`^\s*(\d+)\s*(s|m|h|d|w)\s*$`)
-
-func parsePostitiveDuration(e string) (d time.Duration, err error) {
-	comps := durationStringRegex.FindStringSubmatch(e)
-	if len(comps) != 3 {
-		err = fmt.Errorf("does not match regex: %s %#v", e, comps)
-		return
-	}
-
-	durationFactor, err := strconv.ParseInt(comps[1], 10, 64)
-	if err != nil {
-		return 0, err
-	}
-	if durationFactor <= 0 {
-		return 0, errors.New("duration must be positive integer")
-	}
-
-	var durationUnit time.Duration
-	switch comps[2] {
-	case "s":
-		durationUnit = time.Second
-	case "m":
-		durationUnit = time.Minute
-	case "h":
-		durationUnit = time.Hour
-	case "d":
-		durationUnit = 24 * time.Hour
-	case "w":
-		durationUnit = 24 * 7 * time.Hour
-	default:
-		err = fmt.Errorf("contains unknown time unit '%s'", comps[2])
-		return
-	}
-
-	d = time.Duration(durationFactor) * durationUnit
-	return
-}

config/config_rpc_test.go

@@ -1,86 +0,0 @@
-package config
-
-import (
-	"github.com/stretchr/testify/assert"
-	"testing"
-	"time"
-)
-
-func TestRPC(t *testing.T) {
-	conf := testValidConfig(t, `
-jobs:
-- name: pull_servers
-  type: pull
-  connect:
-    type: tcp
-    address: "server1.foo.bar:8888"
-    rpc:
-      timeout: 20s # different form default, should merge
-  root_fs: "pool2/backup_servers"
-  interval: 10m
-  pruning:
-    keep_sender:
-      - type: not_replicated
-    keep_receiver:
-      - type: last_n
-        count: 100
-
-- name: pull_servers2
-  type: pull
-  connect:
-    type: tcp
-    address: "server1.foo.bar:8888"
-    rpc:
-      tx_chunk_size: 0xabcd # different from default, should merge
-  root_fs: "pool2/backup_servers"
-  interval: 10m
-  pruning:
-    keep_sender:
-    - type: not_replicated
-    keep_receiver:
-    - type: last_n
-      count: 100
-
-- type: sink
-  name: "laptop_sink"
-  root_fs: "pool2/backup_laptops"
-  serve:
-    type: tcp
-    listen: "192.168.122.189:8888"
-    clients: {
-	"10.23.42.23":"client1"
-    }
-    rpc:
-      rx_structured_max: 0x2342
-
-- type: sink
-  name: "other_sink"
-  root_fs: "pool2/backup_laptops"
-  serve:
-    type: tcp
-    listen: "192.168.122.189:8888"
-    clients: {
-	"10.23.42.23":"client1"
-    }
-    rpc:
-      send_heartbeat_interval: 10s
-
-`)
-
-	assert.Equal(t, 20*time.Second, conf.Jobs[0].Ret.(*PullJob).Connect.Ret.(*TCPConnect).RPC.Timeout)
-	assert.Equal(t, uint32(0xabcd), conf.Jobs[1].Ret.(*PullJob).Connect.Ret.(*TCPConnect).RPC.TxChunkSize)
-	assert.Equal(t, uint32(0x2342), conf.Jobs[2].Ret.(*SinkJob).Serve.Ret.(*TCPServe).RPC.RxStructuredMaxLen)
-	assert.Equal(t, 10*time.Second, conf.Jobs[3].Ret.(*SinkJob).Serve.Ret.(*TCPServe).RPC.SendHeartbeatInterval)
-	defConf := RPCConfig{}
-	Default(&defConf)
-	assert.Equal(t, defConf.Timeout, conf.Global.RPC.Timeout)
-}
-
-func TestGlobal_DefaultRPCConfig(t *testing.T) {
-	assert.NotPanics(t, func() {
-		var c RPCConfig
-		Default(&c)
-		assert.NotNil(t, c)
-		assert.Equal(t, c.TxChunkSize, uint32(1)<<15)
-	})
-}

config/config_snapshotting_test.go

@@ -1,57 +0,0 @@
-package config
-
-import (
-	"fmt"
-	"github.com/stretchr/testify/assert"
-	"testing"
-	"time"
-)
-
-func TestSnapshotting(t *testing.T) {
-	tmpl := `
-jobs:
-- name: foo
-  type: push
-  connect:
-    type: local
-    listener_name: foo
-    client_identity: bar
-  filesystems: {"<": true}
-  %s
-  pruning:
-    keep_sender:
-    - type: last_n
-      count: 10
-    keep_receiver:
-    - type: last_n
-      count: 10
-`
-	manual := `
-  snapshotting:
-    type: manual
-`
-	periodic := `
-  snapshotting:
-    type: periodic
-    prefix: zrepl_
-    interval: 10m
-`
-
-	fillSnapshotting := func(s string) string {return fmt.Sprintf(tmpl, s)}
-	var c *Config
-
-	t.Run("manual", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(manual))
-		snm := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingManual)
-		assert.Equal(t, "manual", snm.Type)
-	})
-
-	t.Run("periodic", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(periodic))
-		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingPeriodic)
-		assert.Equal(t, "periodic", snp.Type)
-		assert.Equal(t, 10*time.Minute, snp.Interval)
-		assert.Equal(t, "zrepl_" , snp.Prefix)
-	})
-
-}

config/config_test.go

@@ -1,50 +0,0 @@
-package config
-
-import (
-	"github.com/kr/pretty"
-	"github.com/stretchr/testify/require"
-	"path"
-	"path/filepath"
-	"testing"
-)
-
-func TestSampleConfigsAreParsedWithoutErrors(t *testing.T) {
-	paths, err := filepath.Glob("./samples/*")
-	if err != nil {
-		t.Errorf("glob failed: %+v", err)
-	}
-
-	for _, p := range paths {
-
-		if path.Ext(p) != ".yml" {
-			t.Logf("skipping file %s", p)
-			continue
-		}
-
-		t.Run(p, func(t *testing.T) {
-			c, err := ParseConfig(p)
-			if err != nil {
-				t.Errorf("error parsing %s:\n%+v", p, err)
-			}
-
-			t.Logf("file: %s", p)
-			t.Log(pretty.Sprint(c))
-		})
-
-	}
-
-}
-
-
-func testValidConfig(t *testing.T, input string) (*Config) {
-	t.Helper()
-	conf, err := testConfig(t, input)
-	require.NoError(t, err)
-	require.NotNil(t, conf)
-	return conf
-}
-
-func testConfig(t *testing.T, input string) (*Config, error) {
-	t.Helper()
-	return ParseConfigBytes([]byte(input))
-}

daemon/filters/fsvfilter.go

@@ -1,41 +0,0 @@
-package filters
-
-import (
-	"github.com/zrepl/zrepl/zfs"
-	"strings"
-)
-
-type AnyFSVFilter struct{}
-
-func NewAnyFSVFilter() AnyFSVFilter {
-	return AnyFSVFilter{}
-}
-
-var _ zfs.FilesystemVersionFilter = AnyFSVFilter{}
-
-func (AnyFSVFilter) Filter(t zfs.VersionType, name string) (accept bool, err error) {
-	return true, nil
-}
-
-
-type PrefixFilter struct {
-	prefix    string
-	fstype    zfs.VersionType
-	fstypeSet bool // optionals anyone?
-}
-
-var _ zfs.FilesystemVersionFilter = &PrefixFilter{}
-
-func NewPrefixFilter(prefix string) *PrefixFilter {
-	return &PrefixFilter{prefix: prefix}
-}
-
-func NewTypedPrefixFilter(prefix string, versionType zfs.VersionType) *PrefixFilter {
-	return &PrefixFilter{prefix, versionType, true}
-}
-
-func (f *PrefixFilter) Filter(t zfs.VersionType, name string) (accept bool, err error) {
-	fstypeMatches := (!f.fstypeSet || t == f.fstype)
-	prefixMatches := strings.HasPrefix(name, f.prefix)
-	return fstypeMatches && prefixMatches, nil
-}

daemon/job/active.go

@@ -1,422 +0,0 @@
-package job
-
-import (
-	"context"
-	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
-	"github.com/prometheus/client_golang/prometheus"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/filters"
-	"github.com/zrepl/zrepl/daemon/job/reset"
-	"github.com/zrepl/zrepl/daemon/job/wakeup"
-	"github.com/zrepl/zrepl/daemon/logging"
-	"github.com/zrepl/zrepl/daemon/pruner"
-	"github.com/zrepl/zrepl/daemon/snapper"
-	"github.com/zrepl/zrepl/daemon/transport/connecter"
-	"github.com/zrepl/zrepl/endpoint"
-	"github.com/zrepl/zrepl/replication"
-	"github.com/zrepl/zrepl/util/envconst"
-	"github.com/zrepl/zrepl/zfs"
-	"sync"
-	"time"
-)
-
-type ActiveSide struct {
-	mode          activeMode
-	name          string
-	clientFactory *connecter.ClientFactory
-
-	prunerFactory *pruner.PrunerFactory
-
-
-	promRepStateSecs *prometheus.HistogramVec // labels: state
-	promPruneSecs *prometheus.HistogramVec // labels: prune_side
-	promBytesReplicated *prometheus.CounterVec // labels: filesystem
-
-	tasksMtx sync.Mutex
-	tasks    activeSideTasks
-}
-
-
-//go:generate enumer -type=ActiveSideState
-type ActiveSideState int
-
-const (
-	ActiveSideReplicating ActiveSideState = 1 << iota
-	ActiveSidePruneSender
-	ActiveSidePruneReceiver
-	ActiveSideDone // also errors
-)
-
-
-type activeSideTasks struct {
-	state ActiveSideState
-
-	// valid for state ActiveSideReplicating, ActiveSidePruneSender, ActiveSidePruneReceiver, ActiveSideDone
-	replication *replication.Replication
-	replicationCancel context.CancelFunc
-
-	// valid for state ActiveSidePruneSender, ActiveSidePruneReceiver, ActiveSideDone
-	prunerSender, prunerReceiver *pruner.Pruner
-
-	// valid for state ActiveSidePruneReceiver, ActiveSideDone
-	prunerSenderCancel, prunerReceiverCancel context.CancelFunc
-}
-
-func (a *ActiveSide) updateTasks(u func(*activeSideTasks)) activeSideTasks {
-	a.tasksMtx.Lock()
-	defer a.tasksMtx.Unlock()
-	var copy activeSideTasks
-	copy = a.tasks
-	if u == nil {
-		return copy
-	}
-	u(&copy)
-	a.tasks = copy
-	return copy
-}
-
-type activeMode interface {
-	SenderReceiver(client *streamrpc.Client) (replication.Sender, replication.Receiver, error)
-	Type() Type
-	RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{})
-}
-
-type modePush struct {
-	fsfilter         endpoint.FSFilter
-	snapper *snapper.PeriodicOrManual
-}
-
-func (m *modePush) SenderReceiver(client *streamrpc.Client) (replication.Sender, replication.Receiver, error) {
-	sender := endpoint.NewSender(m.fsfilter)
-	receiver := endpoint.NewRemote(client)
-	return sender, receiver, nil
-}
-
-func (m *modePush) Type() Type { return TypePush }
-
-func (m *modePush) RunPeriodic(ctx context.Context, wakeUpCommon chan <- struct{}) {
-	m.snapper.Run(ctx, wakeUpCommon)
-}
-
-
-func modePushFromConfig(g *config.Global, in *config.PushJob) (*modePush, error) {
-	m := &modePush{}
-	fsf, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannnot build filesystem filter")
-	}
-	m.fsfilter = fsf
-
-	if m.snapper, err = snapper.FromConfig(g, fsf, in.Snapshotting); err != nil {
-		return nil, errors.Wrap(err, "cannot build snapper")
-	}
-
-	return m, nil
-}
-
-type modePull struct {
-	rootFS   *zfs.DatasetPath
-	interval time.Duration
-}
-
-func (m *modePull) SenderReceiver(client *streamrpc.Client) (replication.Sender, replication.Receiver, error) {
-	sender := endpoint.NewRemote(client)
-	receiver, err := endpoint.NewReceiver(m.rootFS)
-	return sender, receiver, err
-}
-
-func (*modePull) Type() Type { return TypePull }
-
-func (m *modePull) RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{}) {
-	t := time.NewTicker(m.interval)
-	defer t.Stop()
-	for {
-		select {
-		case <-t.C:
-			select {
-			case wakeUpCommon <- struct{}{}:
-			default:
-				GetLogger(ctx).
-					WithField("pull_interval", m.interval).
-					Warn("pull job took longer than pull interval")
-				wakeUpCommon <- struct{}{} // block anyways, to queue up the wakeup
-			}
-		case <-ctx.Done():
-			return
-		}
-	}
-}
-
-func modePullFromConfig(g *config.Global, in *config.PullJob) (m *modePull, err error) {
-	m = &modePull{}
-	if in.Interval <= 0 {
-		return nil, errors.New("interval must be positive")
-	}
-	m.interval = in.Interval
-
-	m.rootFS, err = zfs.NewDatasetPath(in.RootFS)
-	if err != nil {
-		return nil, errors.New("RootFS is not a valid zfs filesystem path")
-	}
-	if m.rootFS.Length() <= 0 {
-		return nil, errors.New("RootFS must not be empty") // duplicates error check of receiver
-	}
-
-	return m, nil
-}
-
-func activeSide(g *config.Global, in *config.ActiveJob, mode activeMode) (j *ActiveSide, err error) {
-
-	j = &ActiveSide{mode: mode}
-	j.name = in.Name
-	j.promRepStateSecs = prometheus.NewHistogramVec(prometheus.HistogramOpts{
-		Namespace:   "zrepl",
-		Subsystem:   "replication",
-		Name:        "state_time",
-		Help:        "seconds spent during replication",
-		ConstLabels: prometheus.Labels{"zrepl_job":j.name},
-	}, []string{"state"})
-	j.promBytesReplicated = prometheus.NewCounterVec(prometheus.CounterOpts{
-		Namespace:   "zrepl",
-		Subsystem:   "replication",
-		Name:        "bytes_replicated",
-		Help:        "number of bytes replicated from sender to receiver per filesystem",
-		ConstLabels: prometheus.Labels{"zrepl_job":j.name},
-	}, []string{"filesystem"})
-
-	j.clientFactory, err = connecter.FromConfig(g, in.Connect)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot build client")
-	}
-
-	j.promPruneSecs = prometheus.NewHistogramVec(prometheus.HistogramOpts{
-		Namespace:   "zrepl",
-		Subsystem:   "pruning",
-		Name:        "time",
-		Help:        "seconds spent in pruner",
-		ConstLabels: prometheus.Labels{"zrepl_job":j.name},
-	}, []string{"prune_side"})
-	j.prunerFactory, err = pruner.NewPrunerFactory(in.Pruning, j.promPruneSecs)
-	if err != nil {
-		return nil, err
-	}
-
-	return j, nil
-}
-
-func (j *ActiveSide) RegisterMetrics(registerer prometheus.Registerer) {
-	registerer.MustRegister(j.promRepStateSecs)
-	registerer.MustRegister(j.promPruneSecs)
-	registerer.MustRegister(j.promBytesReplicated)
-}
-
-func (j *ActiveSide) Name() string { return j.name }
-
-type ActiveSideStatus struct {
-	Replication *replication.Report
-	PruningSender, PruningReceiver *pruner.Report
-}
-
-func (j *ActiveSide) Status() *Status {
-	tasks := j.updateTasks(nil)
-
-	s := &ActiveSideStatus{}
-	t := j.mode.Type()
-	if tasks.replication != nil {
-		s.Replication = tasks.replication.Report()
-	}
-	if tasks.prunerSender != nil {
-		s.PruningSender = tasks.prunerSender.Report()
-	}
-	if tasks.prunerReceiver != nil {
-		s.PruningReceiver = tasks.prunerReceiver.Report()
-	}
-	return &Status{Type: t, JobSpecific: s}
-}
-
-func (j *ActiveSide) Run(ctx context.Context) {
-	log := GetLogger(ctx)
-	ctx = logging.WithSubsystemLoggers(ctx, log)
-
-	defer log.Info("job exiting")
-
-	periodicDone := make(chan struct{})
-	ctx, cancel := context.WithCancel(ctx)
-	defer cancel()
-	go j.mode.RunPeriodic(ctx, periodicDone)
-
-	invocationCount := 0
-outer:
-	for {
-		log.Info("wait for wakeups")
-		select {
-		case <-ctx.Done():
-			log.WithError(ctx.Err()).Info("context")
-			break outer
-
-		case <-wakeup.Wait(ctx):
-		case <-periodicDone:
-		}
-		invocationCount++
-		invLog := log.WithField("invocation", invocationCount)
-		j.do(WithLogger(ctx, invLog))
-	}
-}
-
-func (j *ActiveSide) do(ctx context.Context) {
-
-	log := GetLogger(ctx)
-	ctx = logging.WithSubsystemLoggers(ctx, log)
-
-	// allow cancellation of an invocation (this function)
-	ctx, cancelThisRun := context.WithCancel(ctx)
-	defer cancelThisRun()
-	go func() {
-		select {
-		case <-reset.Wait(ctx):
-			log.Info("reset received, cancelling current invocation")
-			cancelThisRun()
-		case <-ctx.Done():
-		}
-	}()
-
-	// The code after this watchdog goroutine is sequential and transitions the state from
-	//   ActiveSideReplicating -> ActiveSidePruneSender -> ActiveSidePruneReceiver -> ActiveSideDone
-	// If any of those sequential tasks 'gets stuck' (livelock, no progress), the watchdog will eventually
-	// cancel its context.
-	// If the task is written to support context cancellation, it will return immediately (in permanent error state),
-	// and the sequential code above transitions to the next state.
-	go func() {
-
-		wdto := envconst.Duration("ZREPL_JOB_WATCHDOG_TIMEOUT", 10*time.Minute)
-		jitter := envconst.Duration("ZREPL_JOB_WATCHDOG_JITTER", 1*time.Second)
-		// shadowing!
-		log := log.WithField("watchdog_timeout", wdto.String())
-
-		log.Debug("starting watchdog")
-		defer log.Debug("watchdog stopped")
-
-		t := time.NewTicker(wdto)
-		defer t.Stop()
-
-		for {
-			select {
-			case <-ctx.Done():
-				return
-			case <-t.C: // fall
-			}
-
-			j.updateTasks(func(tasks *activeSideTasks) {
-				// Since cancelling a task will cause the sequential code to transition to the next state immediately,
-				// we cannot check for its progress right then (no fallthrough).
-				// Instead, we return (not continue because we are in a closure) and give the new state another
-				// ZREPL_JOB_WATCHDOG_TIMEOUT interval to try make some progress.
-
-				log.WithField("state", tasks.state).Debug("watchdog firing")
-
-				const WATCHDOG_ENVCONST_NOTICE = " (adjust ZREPL_JOB_WATCHDOG_TIMEOUT env variable if inappropriate)"
-
-				switch tasks.state {
-				case ActiveSideReplicating:
-					log.WithField("replication_progress", tasks.replication.Progress.String()).
-						Debug("check replication progress")
-					if tasks.replication.Progress.CheckTimeout(wdto, jitter) {
-						log.Error("replication did not make progress, cancelling" + WATCHDOG_ENVCONST_NOTICE)
-						tasks.replicationCancel()
-						return
-					}
-				case ActiveSidePruneSender:
-					log.WithField("prune_sender_progress", tasks.replication.Progress.String()).
-						Debug("check pruner_sender progress")
-					if tasks.prunerSender.Progress.CheckTimeout(wdto, jitter) {
-						log.Error("pruner_sender did not make progress, cancelling" + WATCHDOG_ENVCONST_NOTICE)
-						tasks.prunerSenderCancel()
-						return
-					}
-				case ActiveSidePruneReceiver:
-					log.WithField("prune_receiver_progress", tasks.replication.Progress.String()).
-						Debug("check pruner_receiver progress")
-					if tasks.prunerReceiver.Progress.CheckTimeout(wdto, jitter) {
-						log.Error("pruner_receiver did not make progress, cancelling" + WATCHDOG_ENVCONST_NOTICE)
-						tasks.prunerReceiverCancel()
-						return
-					}
-				case ActiveSideDone:
-					// ignore, ctx will be Done() in a few milliseconds and the watchdog will exit
-				default:
-					log.WithField("state", tasks.state).
-						Error("watchdog implementation error: unknown active side state")
-				}
-			})
-
-		}
-	}()
-
-	client, err := j.clientFactory.NewClient()
-	if err != nil {
-		log.WithError(err).Error("factory cannot instantiate streamrpc client")
-	}
-	defer client.Close(ctx)
-
-	sender, receiver, err := j.mode.SenderReceiver(client)
-
-	{
-		select {
-		case <-ctx.Done():
-			return
-		default:
-		}
-		ctx, repCancel := context.WithCancel(ctx)
-		tasks := j.updateTasks(func(tasks *activeSideTasks) {
-			// reset it
-			*tasks = activeSideTasks{}
-			tasks.replicationCancel = repCancel
-			tasks.replication = replication.NewReplication(j.promRepStateSecs, j.promBytesReplicated)
-			tasks.state = ActiveSideReplicating
-		})
-		log.Info("start replication")
-		tasks.replication.Drive(ctx, sender, receiver)
-		repCancel() // always cancel to free up context resources
-	}
-
-	{
-		select {
-		case <-ctx.Done():
-			return
-		default:
-		}
-		ctx, senderCancel := context.WithCancel(ctx)
-		tasks := j.updateTasks(func(tasks *activeSideTasks) {
-			tasks.prunerSender = j.prunerFactory.BuildSenderPruner(ctx, sender, sender)
-			tasks.prunerSenderCancel = senderCancel
-			tasks.state = ActiveSidePruneSender
-		})
-		log.Info("start pruning sender")
-		tasks.prunerSender.Prune()
-		log.Info("finished pruning sender")
-		senderCancel()
-	}
-	{
-		select {
-		case <-ctx.Done():
-			return
-		default:
-		}
-		ctx, receiverCancel := context.WithCancel(ctx)
-		tasks := j.updateTasks(func(tasks *activeSideTasks) {
-			tasks.prunerReceiver = j.prunerFactory.BuildReceiverPruner(ctx, receiver, sender)
-			tasks.prunerReceiverCancel = receiverCancel
-			tasks.state = ActiveSidePruneReceiver
-		})
-		log.Info("start pruning receiver")
-		tasks.prunerReceiver.Prune()
-		log.Info("finished pruning receiver")
-		receiverCancel()
-	}
-
-	j.updateTasks(func(tasks *activeSideTasks) {
-		tasks.state = ActiveSideDone
-	})
-
-}

daemon/job/build_jobs.go

@@ -1,71 +0,0 @@
-package job
-
-import (
-	"fmt"
-	"github.com/pkg/errors"
-	"github.com/zrepl/zrepl/config"
-)
-
-func JobsFromConfig(c *config.Config) ([]Job, error) {
-	js := make([]Job, len(c.Jobs))
-	for i := range c.Jobs {
-		j, err := buildJob(c.Global, c.Jobs[i])
-		if err != nil {
-			return nil, err
-		}
-		if j == nil || j.Name() == "" {
-			panic(fmt.Sprintf("implementation error: job builder returned nil job type %T", c.Jobs[i].Ret))
-		}
-		js[i] = j
-	}
-	return js, nil
-}
-
-func buildJob(c *config.Global, in config.JobEnum) (j Job, err error) {
-	cannotBuildJob := func(e error, name string) (Job, error) {
-		return nil, errors.Wrapf(e, "cannot build job %q", name)
-	}
-	// FIXME prettify this
-	switch v := in.Ret.(type) {
-	case *config.SinkJob:
-		m, err := modeSinkFromConfig(c, v)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-		j, err = passiveSideFromConfig(c, &v.PassiveJob, m)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-	case *config.SourceJob:
-		m, err := modeSourceFromConfig(c, v)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-		j, err = passiveSideFromConfig(c, &v.PassiveJob, m)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-	case *config.PushJob:
-		m, err := modePushFromConfig(c, v)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-		j, err = activeSide(c, &v.ActiveJob, m)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-	case *config.PullJob:
-		m, err := modePullFromConfig(c, v)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-		j, err = activeSide(c, &v.ActiveJob, m)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-	default:
-		panic(fmt.Sprintf("implementation error: unknown job type %T", v))
-	}
-	return j, nil
-
-}

daemon/job/passive.go

@@ -1,196 +0,0 @@
-package job
-
-import (
-	"context"
-	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
-	"github.com/prometheus/client_golang/prometheus"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/filters"
-	"github.com/zrepl/zrepl/daemon/logging"
-	"github.com/zrepl/zrepl/daemon/transport/serve"
-	"github.com/zrepl/zrepl/daemon/snapper"
-	"github.com/zrepl/zrepl/endpoint"
-	"github.com/zrepl/zrepl/zfs"
-	"path"
-)
-
-type PassiveSide struct {
-	mode passiveMode
-	name     string
-	l        serve.ListenerFactory
-	rpcConf  *streamrpc.ConnConfig
-}
-
-type passiveMode interface {
-	ConnHandleFunc(ctx context.Context, conn serve.AuthenticatedConn) streamrpc.HandlerFunc
-	RunPeriodic(ctx context.Context)
-	Type() Type
-}
-
-type modeSink struct {
-	rootDataset *zfs.DatasetPath
-}
-
-func (m *modeSink) Type() Type { return TypeSink }
-
-func (m *modeSink) ConnHandleFunc(ctx context.Context, conn serve.AuthenticatedConn) streamrpc.HandlerFunc {
-	log := GetLogger(ctx)
-
-	clientRootStr := path.Join(m.rootDataset.ToString(), conn.ClientIdentity())
-	clientRoot, err := zfs.NewDatasetPath(clientRootStr)
-	if err != nil {
-		log.WithError(err).
-			WithField("client_identity", conn.ClientIdentity()).
-			Error("cannot build client filesystem map (client identity must be a valid ZFS FS name")
-	}
-	log.WithField("client_root", clientRoot).Debug("client root")
-
-	local, err := endpoint.NewReceiver(clientRoot)
-	if err != nil {
-		log.WithError(err).Error("unexpected error: cannot convert mapping to filter")
-		return nil
-	}
-
-	h := endpoint.NewHandler(local)
-	return h.Handle
-}
-
-func (m *modeSink) RunPeriodic(_ context.Context) {}
-
-func modeSinkFromConfig(g *config.Global, in *config.SinkJob) (m *modeSink, err error) {
-	m = &modeSink{}
-	m.rootDataset, err = zfs.NewDatasetPath(in.RootFS)
-	if err != nil {
-		return nil, errors.New("root dataset is not a valid zfs filesystem path")
-	}
-	if m.rootDataset.Length() <= 0 {
-		return nil, errors.New("root dataset must not be empty") // duplicates error check of receiver
-	}
-	return m, nil
-}
-
-type modeSource struct {
-	fsfilter zfs.DatasetFilter
-	snapper *snapper.PeriodicOrManual
-}
-
-func modeSourceFromConfig(g *config.Global, in *config.SourceJob) (m *modeSource, err error) {
-	// FIXME exact dedup of modePush
-	m = &modeSource{}
-	fsf, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannnot build filesystem filter")
-	}
-	m.fsfilter = fsf
-
-	if m.snapper, err = snapper.FromConfig(g, fsf, in.Snapshotting); err != nil {
-		return nil, errors.Wrap(err, "cannot build snapper")
-	}
-
-	return m, nil
-}
-
-func (m *modeSource) Type() Type { return TypeSource }
-
-func (m *modeSource) ConnHandleFunc(ctx context.Context, conn serve.AuthenticatedConn) streamrpc.HandlerFunc {
-	sender := endpoint.NewSender(m.fsfilter)
-	h := endpoint.NewHandler(sender)
-	return h.Handle
-}
-
-func (m *modeSource) RunPeriodic(ctx context.Context) {
-	m.snapper.Run(ctx, nil)
-}
-
-func passiveSideFromConfig(g *config.Global, in *config.PassiveJob, mode passiveMode) (s *PassiveSide, err error) {
-
-	s = &PassiveSide{mode: mode, name: in.Name}
-	if s.l, s.rpcConf, err = serve.FromConfig(g, in.Serve); err != nil {
-		return nil, errors.Wrap(err, "cannot build server")
-	}
-
-	return s, nil
-}
-
-func (j *PassiveSide) Name() string { return j.name }
-
-type PassiveStatus struct {}
-
-func (s *PassiveSide) Status() *Status {
-	return &Status{Type: s.mode.Type()} // FIXME PassiveStatus
-}
-
-func (*PassiveSide) RegisterMetrics(registerer prometheus.Registerer) {}
-
-func (j *PassiveSide) Run(ctx context.Context) {
-
-	log := GetLogger(ctx)
-	defer log.Info("job exiting")
-
-	l, err := j.l.Listen()
-	if err != nil {
-		log.WithError(err).Error("cannot listen")
-		return
-	}
-	defer l.Close()
-
-	{
-		ctx, cancel := context.WithCancel(logging.WithSubsystemLoggers(ctx, log)) // shadowing
-		defer cancel()
-		go j.mode.RunPeriodic(ctx)
-	}
-
-	log.WithField("addr", l.Addr()).Debug("accepting connections")
-	var connId int
-outer:
-	for {
-
-		select {
-		case res := <-accept(ctx, l):
-			if res.err != nil {
-				log.WithError(res.err).Info("accept error")
-				continue
-			}
-			conn := res.conn
-			connId++
-			connLog := log.
-				WithField("connID", connId)
-			connLog.
-				WithField("addr", conn.RemoteAddr()).
-				WithField("client_identity", conn.ClientIdentity()).
-				Info("handling connection")
-			go func() {
-				defer connLog.Info("finished handling connection")
-				defer conn.Close()
-				ctx := logging.WithSubsystemLoggers(ctx, connLog)
-				handleFunc := j.mode.ConnHandleFunc(ctx, conn)
-				if handleFunc == nil {
-					return
-				}
-				if err := streamrpc.ServeConn(ctx, conn, j.rpcConf, handleFunc); err != nil {
-					log.WithError(err).Error("error serving client")
-				}
-			}()
-
-		case <-ctx.Done():
-			break outer
-		}
-
-	}
-
-}
-
-type acceptResult struct {
-	conn serve.AuthenticatedConn
-	err  error
-}
-
-func accept(ctx context.Context, listener serve.AuthenticatedListener) <-chan acceptResult {
-	c := make(chan acceptResult, 1)
-	go func() {
-		conn, err := listener.Accept(ctx)
-		c <- acceptResult{conn, err}
-	}()
-	return c
-}

daemon/logging/adaptors.go

@@ -1,32 +0,0 @@
-package logging
-
-import (
-	"fmt"
-	"github.com/problame/go-streamrpc"
-	"github.com/zrepl/zrepl/logger"
-	"strings"
-)
-
-type streamrpcLogAdaptor = twoClassLogAdaptor
-
-type twoClassLogAdaptor struct {
-	logger.Logger
-}
-
-var _ streamrpc.Logger = twoClassLogAdaptor{}
-
-func (a twoClassLogAdaptor) Errorf(fmtStr string, args ...interface{}) {
-	const errorSuffix = ": %s"
-	if len(args) == 1 {
-		if err, ok := args[0].(error); ok && strings.HasSuffix(fmtStr, errorSuffix) {
-			msg := strings.TrimSuffix(fmtStr, errorSuffix)
-			a.WithError(err).Error(msg)
-			return
-		}
-	}
-	a.Logger.Error(fmt.Sprintf(fmtStr, args...))
-}
-
-func (a twoClassLogAdaptor) Infof(fmtStr string, args ...interface{}) {
-	a.Logger.Debug(fmt.Sprintf(fmtStr, args...))
-}

daemon/main.go

@@ -1,16 +0,0 @@
-package daemon
-
-import (
-	"github.com/zrepl/zrepl/cli"
-	"github.com/zrepl/zrepl/logger"
-)
-
-type Logger = logger.Logger
-
-var DaemonCmd = &cli.Subcommand {
-	Use:   "daemon",
-	Short: "run the zrepl daemon",
-	Run: func(subcommand *cli.Subcommand, args []string) error {
-		return Run(subcommand.Config())
-	},
-}

daemon/pruner/pruner.go

@@ -1,584 +0,0 @@
-package pruner
-
-import (
-	"context"
-	"fmt"
-	"github.com/pkg/errors"
-	"github.com/prometheus/client_golang/prometheus"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/logger"
-	"github.com/zrepl/zrepl/pruning"
-	"github.com/zrepl/zrepl/replication/pdu"
-	"github.com/zrepl/zrepl/util/envconst"
-	"github.com/zrepl/zrepl/util/watchdog"
-	"github.com/problame/go-streamrpc"
-	"net"
-	"sort"
-	"strings"
-	"sync"
-	"time"
-)
-
-// Try to keep it compatible with gitub.com/zrepl/zrepl/replication.Endpoint
-type History interface {
-	ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error)
-}
-
-type Target interface {
-	ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error)
-	ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) // fix depS
-	DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error)
-}
-
-type Logger = logger.Logger
-
-type contextKey int
-
-const contextKeyLogger contextKey = 0
-
-func WithLogger(ctx context.Context, log Logger) context.Context {
-	return context.WithValue(ctx, contextKeyLogger, log)
-}
-
-func GetLogger(ctx context.Context) Logger {
-	if l, ok := ctx.Value(contextKeyLogger).(Logger); ok {
-		return l
-	}
-	return logger.NewNullLogger()
-}
-
-type args struct {
-	ctx                            context.Context
-	target                         Target
-	receiver                       History
-	rules                          []pruning.KeepRule
-	retryWait                      time.Duration
-	considerSnapAtCursorReplicated bool
-	promPruneSecs prometheus.Observer
-}
-
-type Pruner struct {
-	args args
-
-	Progress watchdog.KeepAlive
-
-	mtx sync.RWMutex
-
-	state State
-
-	// State ErrWait|ErrPerm
-	sleepUntil time.Time
-	err        error
-
-	// State Exec
-	execQueue *execQueue
-}
-
-type PrunerFactory struct {
-	senderRules                    []pruning.KeepRule
-	receiverRules                  []pruning.KeepRule
-	retryWait                      time.Duration
-	considerSnapAtCursorReplicated bool
-	promPruneSecs *prometheus.HistogramVec
-}
-
-func checkContainsKeep1(rules []pruning.KeepRule) error {
-	if len(rules) == 0 {
-		return nil //No keep rules means keep all - ok
-	}
-	for _, e := range rules {
-		switch e.(type) {
-		case *pruning.KeepLastN:
-			return nil
-		}
-	}
-	return errors.New("sender keep rules must contain last_n or be empty so that the last snapshot is definitely kept")
-}
-
-func NewPrunerFactory(in config.PruningSenderReceiver, promPruneSecs *prometheus.HistogramVec) (*PrunerFactory, error) {
-	keepRulesReceiver, err := pruning.RulesFromConfig(in.KeepReceiver)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot build receiver pruning rules")
-	}
-
-	keepRulesSender, err := pruning.RulesFromConfig(in.KeepSender)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot build sender pruning rules")
-	}
-
-	considerSnapAtCursorReplicated := false
-	for _, r := range in.KeepSender {
-		knr, ok := r.Ret.(*config.PruneKeepNotReplicated)
-		if !ok {
-			continue
-		}
-		considerSnapAtCursorReplicated = considerSnapAtCursorReplicated || !knr.KeepSnapshotAtCursor
-	}
-	f := &PrunerFactory{
-		senderRules: keepRulesSender,
-		receiverRules: keepRulesReceiver,
-		retryWait: envconst.Duration("ZREPL_PRUNER_RETRY_INTERVAL", 10 * time.Second),
-		considerSnapAtCursorReplicated: considerSnapAtCursorReplicated,
-		promPruneSecs: promPruneSecs,
-	}
-	return f, nil
-}
-
-func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, receiver History) *Pruner {
-	p := &Pruner{
-		args: args{
-			WithLogger(ctx, GetLogger(ctx).WithField("prune_side", "sender")),
-			target,
-			receiver,
-			f.senderRules,
-			f.retryWait,
-			f.considerSnapAtCursorReplicated,
-			f.promPruneSecs.WithLabelValues("sender"),
-		},
-		state: Plan,
-	}
-	return p
-}
-
-func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target, receiver History) *Pruner {
-	p := &Pruner{
-		args: args{
-			WithLogger(ctx, GetLogger(ctx).WithField("prune_side", "receiver")),
-			target,
-			receiver,
-			f.receiverRules,
-			f.retryWait,
-			false, // senseless here anyways
-			f.promPruneSecs.WithLabelValues("receiver"),
-		},
-		state: Plan,
-	}
-	return p
-}
-
-//go:generate enumer -type=State
-type State int
-
-const (
-	Plan State = 1 << iota
-	PlanWait
-	Exec
-	ExecWait
-	ErrPerm
-	Done
-)
-
-func (s State) statefunc() state {
-	var statemap = map[State]state{
-		Plan:     statePlan,
-		PlanWait: statePlanWait,
-		Exec:     stateExec,
-		ExecWait: stateExecWait,
-		ErrPerm:  nil,
-		Done:     nil,
-	}
-	return statemap[s]
-}
-
-func (s State) IsTerminal() bool {
-	return s.statefunc() == nil
-}
-
-type updater func(func(*Pruner)) State
-type state func(args *args, u updater) state
-
-func (p *Pruner) Prune() {
-	p.prune(p.args)
-}
-
-func (p *Pruner) prune(args args) {
-	s := p.state.statefunc()
-	for s != nil {
-		pre := p.state
-		s = s(&args, func(f func(*Pruner)) State {
-			p.mtx.Lock()
-			defer p.mtx.Unlock()
-			f(p)
-			return p.state
-		})
-		post := p.state
-		GetLogger(args.ctx).
-			WithField("transition", fmt.Sprintf("%s=>%s", pre, post)).
-			Debug("state transition")
-		if err := p.Error(); err != nil {
-			GetLogger(args.ctx).
-				WithError(p.err).
-				WithField("state", post.String()).
-				Error("entering error state after error")
-		}
-	}
-}
-
-type Report struct {
-	State string
-	SleepUntil time.Time
-	Error string
-	Pending, Completed []FSReport
-}
-
-type FSReport struct {
-	Filesystem string
-	SnapshotList, DestroyList []SnapshotReport
-	ErrorCount int
-	LastError string
-}
-
-type SnapshotReport struct {
-	Name string
-	Replicated bool
-	Date time.Time
-}
-
-func (p *Pruner) Report() *Report {
-	p.mtx.Lock()
-	defer p.mtx.Unlock()
-
-	r := Report{State: p.state.String()}
-
-	if p.state & (PlanWait|ExecWait) != 0 {
-		r.SleepUntil = p.sleepUntil
-	}
-	if p.state & (PlanWait|ExecWait|ErrPerm) != 0 {
-		if p.err != nil {
-			r.Error = p.err.Error()
-		}
-	}
-
-	if p.execQueue != nil {
-		r.Pending, r.Completed = p.execQueue.Report()
-	}
-
-	return &r
-}
-
-func (p *Pruner) State() State {
-	p.mtx.Lock()
-	defer p.mtx.Unlock()
-	return p.state
-}
-
-func (p *Pruner) Error() error {
-	p.mtx.Lock()
-	defer p.mtx.Unlock()
-	if p.state & (PlanWait|ExecWait|ErrPerm) != 0 {
-		return p.err
-	}
-	return nil
-}
-
-type fs struct {
-	path  string
-
-	// snapshots presented by target
-	// (type snapshot)
-	snaps []pruning.Snapshot
-	// destroy list returned by pruning.PruneSnapshots(snaps)
-	// (type snapshot)
-	destroyList []pruning.Snapshot
-
-	mtx sync.RWMutex
-
-	// only during Exec state, also used by execQueue
-	execErrLast error
-	execErrCount int
-
-}
-
-func (f *fs) Report() FSReport {
-	f.mtx.Lock()
-	defer f.mtx.Unlock()
-
-	r := FSReport{}
-	r.Filesystem = f.path
-	r.ErrorCount = f.execErrCount
-	if f.execErrLast != nil {
-		r.LastError = f.execErrLast.Error()
-	}
-
-	r.SnapshotList = make([]SnapshotReport, len(f.snaps))
-	for i, snap := range f.snaps {
-		r.SnapshotList[i] = snap.(snapshot).Report()
-	}
-
-	r.DestroyList = make([]SnapshotReport, len(f.destroyList))
-	for i, snap := range f.destroyList{
-		r.DestroyList[i] = snap.(snapshot).Report()
-	}
-
-	return r
-}
-
-type snapshot struct {
-	replicated bool
-	date       time.Time
-	fsv        *pdu.FilesystemVersion
-}
-
-func (s snapshot) Report() SnapshotReport {
-	return SnapshotReport{
-		Name:       s.Name(),
-		Replicated: s.Replicated(),
-		Date:       s.Date(),
-	}
-}
-
-var _ pruning.Snapshot = snapshot{}
-
-func (s snapshot) Name() string { return s.fsv.Name }
-
-func (s snapshot) Replicated() bool { return s.replicated }
-
-func (s snapshot) Date() time.Time { return s.date }
-
-type Error interface {
-	error
-	Temporary() bool
-}
-
-var _ Error = net.Error(nil)
-var _ Error = streamrpc.Error(nil)
-
-func shouldRetry(e error) bool {
-	if neterr, ok := e.(net.Error); ok {
-		return neterr.Temporary()
-	}
-	return false
-}
-
-func onErr(u updater, e error) state {
-	return u(func(p *Pruner) {
-		p.err = e
-		if !shouldRetry(e) {
-			p.state = ErrPerm
-			return
-		}
-		switch p.state {
-		case Plan:
-			p.state = PlanWait
-		case Exec:
-			p.state = ExecWait
-		default:
-			panic(p.state)
-		}
-	}).statefunc()
-}
-
-func statePlan(a *args, u updater) state {
-
-	ctx, target, receiver := a.ctx, a.target, a.receiver
-	var ka *watchdog.KeepAlive
-	u(func(pruner *Pruner) {
-		ka = &pruner.Progress
-	})
-
-	tfss, err := target.ListFilesystems(ctx)
-	if err != nil {
-		return onErr(u, err)
-	}
-
-	pfss := make([]*fs, len(tfss))
-	for i, tfs := range tfss {
-
-		l := GetLogger(ctx).WithField("fs", tfs.Path)
-		l.Debug("plan filesystem")
-
-
-		pfs := &fs{
-			path:  tfs.Path,
-		}
-		pfss[i] = pfs
-
-		tfsvs, err := target.ListFilesystemVersions(ctx, tfs.Path)
-		if err != nil {
-			l.WithError(err).Error("cannot list filesystem versions")
-			return onErr(u, err)
-		}
-		// no progress here since we could run in a live-lock (must have used target AND receiver before progress)
-
-		pfs.snaps = make([]pruning.Snapshot, 0, len(tfsvs))
-
-		rcReq := &pdu.ReplicationCursorReq{
-			Filesystem: tfs.Path,
-			Op:         &pdu.ReplicationCursorReq_Get{
-				Get: &pdu.ReplicationCursorReq_GetOp{},
-			},
-		}
-		rc, err := receiver.ReplicationCursor(ctx, rcReq)
-		if err != nil {
-			l.WithError(err).Error("cannot get replication cursor")
-			return onErr(u, err)
-		}
-		if rc.GetError() != "" {
-			l.WithField("reqErr", rc.GetError()).Error("cannot get replication cursor")
-			return onErr(u, err)
-		}
-		ka.MadeProgress()
-
-
-		// scan from older to newer, all snapshots older than cursor are interpreted as replicated
-		sort.Slice(tfsvs, func(i, j int) bool {
-			return tfsvs[i].CreateTXG < tfsvs[j].CreateTXG
-		})
-
-		haveCursorSnapshot := false
-		for _, tfsv := range tfsvs {
-			if tfsv.Type != pdu.FilesystemVersion_Snapshot {
-				continue
-			}
-			if tfsv.Guid == rc.GetGuid() {
-				haveCursorSnapshot = true
-			}
-		}
-		preCursor := haveCursorSnapshot
-		for _, tfsv := range tfsvs {
-			if tfsv.Type != pdu.FilesystemVersion_Snapshot {
-				continue
-			}
-			creation, err := tfsv.CreationAsTime()
-			if err != nil {
-				err := fmt.Errorf("%s%s has invalid creation date: %s", tfs, tfsv.RelName(), err)
-				l.WithError(err).
-					WithField("tfsv", tfsv.RelName()).
-					Error("error with fileesystem version")
-				return onErr(u, err)
-			}
-			// note that we cannot use CreateTXG because target and receiver could be on different pools
-			atCursor := tfsv.Guid == rc.GetGuid()
-			preCursor = preCursor && !atCursor
-			pfs.snaps = append(pfs.snaps, snapshot{
-				replicated: preCursor || (a.considerSnapAtCursorReplicated && atCursor),
-				date:       creation,
-				fsv:        tfsv,
-			})
-		}
-		if preCursor {
-			err := fmt.Errorf("replication cursor not found in prune target filesystem versions")
-			l.Error(err.Error())
-			return onErr(u, err)
-		}
-
-		// Apply prune rules
-		pfs.destroyList = pruning.PruneSnapshots(pfs.snaps, a.rules)
-		ka.MadeProgress()
-	}
-
-	return u(func(pruner *Pruner) {
-		pruner.Progress.MadeProgress()
-		pruner.execQueue = newExecQueue(len(pfss))
-		for _, pfs := range pfss {
-			pruner.execQueue.Put(pfs, nil, false)
-		}
-		pruner.state = Exec
-	}).statefunc()
-}
-
-func stateExec(a *args, u updater) state {
-
-	var pfs *fs
-	state := u(func(pruner *Pruner) {
-		pfs = pruner.execQueue.Pop()
-		if pfs == nil {
-			nextState := Done
-			if pruner.execQueue.HasCompletedFSWithErrors() {
-				nextState = ErrPerm
-			}
-			pruner.state = nextState
-			return
-		}
-	})
-	if state != Exec {
-		return state.statefunc()
-	}
-
-	destroyList := make([]*pdu.FilesystemVersion, len(pfs.destroyList))
-	for i := range destroyList {
-		destroyList[i] = pfs.destroyList[i].(snapshot).fsv
-		GetLogger(a.ctx).
-			WithField("fs", pfs.path).
-			WithField("destroy_snap", destroyList[i].Name).
-			Debug("policy destroys snapshot")
-	}
-	req := pdu.DestroySnapshotsReq{
-		Filesystem: pfs.path,
-		Snapshots:  destroyList,
-	}
-	GetLogger(a.ctx).WithField("fs", pfs.path).Debug("destroying snapshots")
-	res, err := a.target.DestroySnapshots(a.ctx, &req)
-	if err != nil {
-		u(func(pruner *Pruner) {
-			pruner.execQueue.Put(pfs, err, false)
-		})
-		return onErr(u, err)
-	}
-	// check if all snapshots were destroyed
-	destroyResults := make(map[string]*pdu.DestroySnapshotRes)
-	for _, fsres := range res.Results {
-		destroyResults[fsres.Snapshot.Name] = fsres
-	}
-	err = nil
-	destroyFails := make([]*pdu.DestroySnapshotRes, 0)
-	for _, reqDestroy := range destroyList {
-		 res, ok := destroyResults[reqDestroy.Name]
-		 if !ok {
-		 	err = fmt.Errorf("missing destroy-result for %s", reqDestroy.RelName())
-		 	break
-		 } else if res.Error != "" {
-		 	destroyFails = append(destroyFails, res)
-		 }
-	}
-	if err == nil && len(destroyFails) > 0 {
-		names := make([]string, len(destroyFails))
-		pairs := make([]string, len(destroyFails))
-		allSame := true
-		lastMsg := destroyFails[0].Error
-		for i := 0; i < len(destroyFails); i++{
-			allSame = allSame && destroyFails[i].Error == lastMsg
-			relname := destroyFails[i].Snapshot.RelName()
-			names[i] = relname
-			pairs[i] = fmt.Sprintf("(%s: %s)", relname, destroyFails[i].Error)
-		}
-		if allSame {
-			err = fmt.Errorf("destroys failed %s: %s",
-				strings.Join(names, ", "), lastMsg)
-		} else {
-			err = fmt.Errorf("destroys failed: %s", strings.Join(pairs, ", "))
-		}
-	}
-	u(func(pruner *Pruner) {
-		pruner.execQueue.Put(pfs, err, err == nil)
-	})
-	if err != nil {
-		GetLogger(a.ctx).WithError(err).Error("target could not destroy snapshots")
-		return onErr(u, err)
-	}
-
-	return u(func(pruner *Pruner) {
-		pruner.Progress.MadeProgress()
-	}).statefunc()
-}
-
-func stateExecWait(a *args, u updater) state {
-	return doWait(Exec, a, u)
-}
-
-func statePlanWait(a *args, u updater) state {
-	return doWait(Plan, a, u)
-}
-
-func doWait(goback State, a *args, u updater) state {
-	timer := time.NewTimer(a.retryWait)
-	defer timer.Stop()
-	select {
-	case <-timer.C:
-		return u(func(pruner *Pruner) {
-			pruner.state = goback
-		}).statefunc()
-	case <-a.ctx.Done():
-		return onErr(u, a.ctx.Err())
-	}
-}

daemon/pruner/pruner_test.go

@@ -1,205 +0,0 @@
-package pruner
-
-import (
-	"context"
-	"fmt"
-	"github.com/stretchr/testify/assert"
-	"github.com/zrepl/zrepl/logger"
-	"github.com/zrepl/zrepl/pruning"
-	"github.com/zrepl/zrepl/replication/pdu"
-	"net"
-	"testing"
-	"time"
-)
-
-type mockFS struct {
-	path  string
-	snaps []string
-}
-
-func (m *mockFS) Filesystem() *pdu.Filesystem {
-	return &pdu.Filesystem{
-		Path: m.path,
-	}
-}
-
-func (m *mockFS) FilesystemVersions() []*pdu.FilesystemVersion {
-	versions := make([]*pdu.FilesystemVersion, len(m.snaps))
-	for i, v := range m.snaps {
-		versions[i] = &pdu.FilesystemVersion{
-			Type:     pdu.FilesystemVersion_Snapshot,
-			Name:     v,
-			Creation: pdu.FilesystemVersionCreation(time.Unix(0, 0)),
-			Guid: uint64(i),
-		}
-	}
-	return versions
-}
-
-type mockTarget struct {
-	fss                []mockFS
-	destroyed          map[string][]string
-	listVersionsErrs   map[string][]error
-	listFilesystemsErr []error
-	destroyErrs        map[string][]error
-}
-
-func (t *mockTarget) ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error) {
-	if len(t.listFilesystemsErr) > 0 {
-		e := t.listFilesystemsErr[0]
-		t.listFilesystemsErr = t.listFilesystemsErr[1:]
-		return nil, e
-	}
-	fss := make([]*pdu.Filesystem, len(t.fss))
-	for i := range fss {
-		fss[i] = t.fss[i].Filesystem()
-	}
-	return fss, nil
-}
-
-func (t *mockTarget) ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) {
-	if len(t.listVersionsErrs[fs]) != 0 {
-		e := t.listVersionsErrs[fs][0]
-		t.listVersionsErrs[fs] = t.listVersionsErrs[fs][1:]
-		return nil, e
-	}
-
-	for _, mfs := range t.fss {
-		if mfs.path != fs {
-			continue
-		}
-		return mfs.FilesystemVersions(), nil
-	}
-	return nil, fmt.Errorf("filesystem %s does not exist", fs)
-}
-
-func (t *mockTarget) DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error) {
-	fs, snaps := req.Filesystem, req.Snapshots
-	if len(t.destroyErrs[fs]) != 0 {
-		e := t.destroyErrs[fs][0]
-		t.destroyErrs[fs] = t.destroyErrs[fs][1:]
-		return nil, e
-	}
-	destroyed := t.destroyed[fs]
-	res := make([]*pdu.DestroySnapshotRes, len(snaps))
-	for i, s := range snaps {
-		destroyed = append(destroyed, s.Name)
-		res[i] = &pdu.DestroySnapshotRes{Error: "", Snapshot: s}
-	}
-	t.destroyed[fs] = destroyed
-	return &pdu.DestroySnapshotsRes{Results: res}, nil
-}
-
-type mockCursor struct {
-	snapname string
-	guid uint64
-}
-type mockHistory struct {
-	errs map[string][]error
-	cursors map[string]*mockCursor
-}
-
-func (r *mockHistory) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
-	fs := req.Filesystem
-	if len(r.errs[fs]) > 0 {
-		e := r.errs[fs][0]
-		r.errs[fs] = r.errs[fs][1:]
-		return nil, e
-	}
-	return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Guid{Guid: 0}}, nil
-}
-
-type stubNetErr struct {
-	msg string
-	temporary, timeout bool
-}
-
-var _ net.Error = stubNetErr{}
-
-func (e stubNetErr) Error() string {
-	return e.msg
-}
-
-func (e stubNetErr) Temporary() bool { return e.temporary }
-
-func (e stubNetErr) Timeout() bool { return e.timeout }
-
-func TestPruner_Prune(t *testing.T) {
-
-	var _ net.Error = &net.OpError{} // we use it below
-	target := &mockTarget{
-		listFilesystemsErr: []error{
-			stubNetErr{msg: "fakerror0", temporary: true},
-		},
-		listVersionsErrs: map[string][]error{
-			"zroot/foo": {
-				stubNetErr{msg: "fakeerror1", temporary: true},
-				stubNetErr{msg: "fakeerror2", temporary: true,},
-			},
-		},
-		destroyErrs: map[string][]error{
-			"zroot/baz": {
-				stubNetErr{msg: "fakeerror3", temporary: true}, // first error puts it back in the queue
-				stubNetErr{msg:"permanent error"}, // so it will be last when pruner gives up due to permanent err
-			},
-		},
-		destroyed: make(map[string][]string),
-		fss: []mockFS{
-			{
-				path: "zroot/foo",
-				snaps: []string{
-					"keep_a",
-					"keep_b",
-					"drop_c",
-					"keep_d",
-				},
-			},
-			{
-				path: "zroot/bar",
-				snaps: []string{
-					"keep_e",
-					"keep_f",
-					"drop_g",
-				},
-			},
-			{
-				path: "zroot/baz",
-				snaps: []string{
-					"keep_h",
-					"drop_i",
-				},
-			},
-		},
-	}
-	history := &mockHistory{
-		errs: map[string][]error{
-			"zroot/foo": {
-				stubNetErr{msg: "fakeerror4", temporary: true},
-			},
-		},
-	}
-
-	keepRules := []pruning.KeepRule{pruning.MustKeepRegex("^keep")}
-
-	p := Pruner{
-		args: args{
-			ctx: WithLogger(context.Background(), logger.NewTestLogger(t)),
-			target: target,
-			receiver: history,
-			rules: keepRules,
-			retryWait: 10*time.Millisecond,
-		},
-		state: Plan,
-	}
-	p.Prune()
-
-	exp := map[string][]string{
-		"zroot/foo": {"drop_c"},
-		"zroot/bar": {"drop_g"},
-	}
-
-	assert.Equal(t, exp, target.destroyed)
-
-	//assert.Equal(t, map[string][]error{}, target.listVersionsErrs, "retried")
-
-}

daemon/snapper/snapper.go

@@ -1,369 +0,0 @@
-package snapper
-
-import (
-	"github.com/zrepl/zrepl/config"
-	"github.com/pkg/errors"
-	"time"
-	"context"
-	"github.com/zrepl/zrepl/daemon/filters"
-	"fmt"
-	"github.com/zrepl/zrepl/zfs"
-	"sort"
-	"github.com/zrepl/zrepl/logger"
-	"sync"
-)
-
-
-//go:generate stringer -type=SnapState
-type SnapState uint
-
-const (
-	SnapPending SnapState = 1 << iota
-	SnapStarted
-	SnapDone
-	SnapError
-)
-
-type snapProgress struct {
-	state SnapState
-
-	// SnapStarted, SnapDone, SnapError
-	name string
-	startAt time.Time
-
-	// SnapDone
-	doneAt time.Time
-
-	// SnapErr
-	err error
-}
-
-type args struct {
-	ctx            context.Context
-	log            Logger
-	prefix         string
-	interval       time.Duration
-	fsf            *filters.DatasetMapFilter
-	snapshotsTaken chan<-struct{}
-}
-
-type Snapper struct {
-	args args
-
-	mtx sync.Mutex
-	state State
-
-	// set in state Plan, used in Waiting
-	lastInvocation time.Time
-
-	// valid for state Snapshotting
-	plan map[*zfs.DatasetPath]snapProgress
-
-	// valid for state SyncUp and Waiting
-	sleepUntil time.Time
-
-	// valid for state Err
-	err error
-}
-
-//go:generate stringer -type=State
-type State uint
-
-const (
-	SyncUp State = 1<<iota
-	Planning
-	Snapshotting
-	Waiting
-	ErrorWait
-	Stopped
-)
-
-func (s State) sf() state {
-	m := map[State]state{
-		SyncUp:       syncUp,
-		Planning:     plan,
-		Snapshotting: snapshot,
-		Waiting:      wait,
-		ErrorWait:    wait,
-		Stopped: 	   nil,
-	}
-	return m[s]
-}
-
-type updater func(u func(*Snapper)) State
-type state func(a args, u updater) state
-
-type contextKey int
-
-const (
-	contextKeyLog contextKey = 0
-)
-
-type Logger = logger.Logger
-
-func WithLogger(ctx context.Context, log Logger) context.Context {
-	return context.WithValue(ctx, contextKeyLog, log)
-}
-
-func getLogger(ctx context.Context) Logger {
-	if log, ok := ctx.Value(contextKeyLog).(Logger); ok {
-		return log
-	}
-	return logger.NewNullLogger()
-}
-
-func PeriodicFromConfig(g *config.Global, fsf *filters.DatasetMapFilter, in *config.SnapshottingPeriodic) (*Snapper, error) {
-	if in.Prefix == "" {
-		return nil, errors.New("prefix must not be empty")
-	}
-	if in.Interval <= 0 {
-		return nil, errors.New("interval must be positive")
-	}
-
-	args := args{
-		prefix: in.Prefix,
-		interval: in.Interval,
-		fsf: fsf,
-		// ctx and log is set in Run()
-	}
-
-	return &Snapper{state: SyncUp, args: args}, nil
-}
-
-func (s *Snapper) Run(ctx context.Context, snapshotsTaken chan<- struct{}) {
-
-	getLogger(ctx).Debug("start")
-	defer getLogger(ctx).Debug("stop")
-
-	s.args.snapshotsTaken = snapshotsTaken
-	s.args.ctx = ctx
-	s.args.log = getLogger(ctx)
-
-	u := func(u func(*Snapper)) State {
-		s.mtx.Lock()
-		defer s.mtx.Unlock()
-		if u != nil {
-			u(s)
-		}
-		return s.state
-	}
-
-	var st state = syncUp
-
-	for st != nil {
-		pre := u(nil)
-		st = st(s.args, u)
-		post := u(nil)
-		getLogger(ctx).
-			WithField("transition", fmt.Sprintf("%s=>%s", pre, post)).
-			Debug("state transition")
-
-	}
-
-}
-
-func onErr(err error, u updater) state {
-	return u(func(s *Snapper) {
-		s.err = err
-		s.state = ErrorWait
-	}).sf()
-}
-
-func onMainCtxDone(ctx context.Context, u updater) state {
-	return u(func(s *Snapper) {
-		s.err = ctx.Err()
-		s.state = Stopped
-	}).sf()
-}
-
-func syncUp(a args, u updater) state {
-	fss, err := listFSes(a.fsf)
-	if err != nil {
-		return onErr(err, u)
-	}
-	syncPoint, err := findSyncPoint(a.log, fss, a.prefix, a.interval)
-	if err != nil {
-		return onErr(err, u)
-	}
-	u(func(s *Snapper){
-		s.sleepUntil = syncPoint
-	})
-	t := time.NewTimer(syncPoint.Sub(time.Now()))
-	defer t.Stop()
-	select {
-	case <-t.C:
-		return u(func(s *Snapper) {
-			s.state = Planning
-		}).sf()
-	case <-a.ctx.Done():
-		return onMainCtxDone(a.ctx, u)
-	}
-}
-
-func plan(a args, u updater) state {
-	u(func(snapper *Snapper) {
-		snapper.lastInvocation = time.Now()
-	})
-	fss, err := listFSes(a.fsf)
-	if err != nil {
-		return onErr(err, u)
-	}
-
-	plan := make(map[*zfs.DatasetPath]snapProgress, len(fss))
-	for _, fs := range fss {
-		plan[fs] = snapProgress{state: SnapPending}
-	}
-	return u(func(s *Snapper) {
-		s.state = Snapshotting
-		s.plan = plan
-	}).sf()
-}
-
-func snapshot(a args, u updater) state {
-
-	var plan map[*zfs.DatasetPath]snapProgress
-	u(func(snapper *Snapper) {
-		plan = snapper.plan
-	})
-
-	hadErr := false
-	// TODO channel programs -> allow a little jitter?
-	for fs, progress := range plan {
-		suffix := time.Now().In(time.UTC).Format("20060102_150405_000")
-		snapname := fmt.Sprintf("%s%s", a.prefix, suffix)
-
-		l := a.log.
-			WithField("fs", fs.ToString()).
-			WithField("snap", snapname)
-
-		u(func(snapper *Snapper) {
-			progress.name = snapname
-			progress.startAt = time.Now()
-			progress.state = SnapStarted
-		})
-
-		l.Debug("create snapshot")
-		err := zfs.ZFSSnapshot(fs, snapname, false)
-		if err != nil {
-			hadErr = true
-			l.WithError(err).Error("cannot create snapshot")
-		}
-		doneAt := time.Now()
-
-		u(func(snapper *Snapper) {
-			progress.doneAt = doneAt
-			progress.state = SnapDone
-			if err != nil {
-				progress.state = SnapError
-				progress.err = err
-			}
-		})
-	}
-
-	select {
-	case a.snapshotsTaken <- struct{}{}:
-	default:
-		if a.snapshotsTaken != nil {
-			a.log.Warn("callback channel is full, discarding snapshot update event")
-		}
-	}
-
-	return u(func(snapper *Snapper) {
-		if hadErr {
-			snapper.state = ErrorWait
-			snapper.err = errors.New("one or more snapshots could not be created, check logs for details")
-		} else {
-			snapper.state = Waiting
-		}
-	}).sf()
-}
-
-func wait(a args, u updater) state {
-	var sleepUntil time.Time
-	u(func(snapper *Snapper) {
-		lastTick := snapper.lastInvocation
-		snapper.sleepUntil = lastTick.Add(a.interval)
-		sleepUntil = snapper.sleepUntil
-	})
-
-	t := time.NewTimer(sleepUntil.Sub(time.Now()))
-	defer t.Stop()
-
-	select {
-	case <-t.C:
-		return u(func(snapper *Snapper) {
-			snapper.state = Planning
-		}).sf()
-	case <-a.ctx.Done():
-		return onMainCtxDone(a.ctx, u)
-	}
-}
-
-func listFSes(mf *filters.DatasetMapFilter) (fss []*zfs.DatasetPath, err error) {
-	return zfs.ZFSListMapping(mf)
-}
-
-func findSyncPoint(log Logger, fss []*zfs.DatasetPath, prefix string, interval time.Duration) (syncPoint time.Time, err error) {
-	type snapTime struct {
-		ds   *zfs.DatasetPath
-		time time.Time
-	}
-
-	if len(fss) == 0 {
-		return time.Now(), nil
-	}
-
-	snaptimes := make([]snapTime, 0, len(fss))
-
-	now := time.Now()
-
-	log.Debug("examine filesystem state")
-	for _, d := range fss {
-
-		l := log.WithField("fs", d.ToString())
-
-		fsvs, err := zfs.ZFSListFilesystemVersions(d, filters.NewTypedPrefixFilter(prefix, zfs.Snapshot))
-		if err != nil {
-			l.WithError(err).Error("cannot list filesystem versions")
-			continue
-		}
-		if len(fsvs) <= 0 {
-			l.WithField("prefix", prefix).Debug("no filesystem versions with prefix")
-			continue
-		}
-
-		// Sort versions by creation
-		sort.SliceStable(fsvs, func(i, j int) bool {
-			return fsvs[i].CreateTXG < fsvs[j].CreateTXG
-		})
-
-		latest := fsvs[len(fsvs)-1]
-		l.WithField("creation", latest.Creation).
-			Debug("found latest snapshot")
-
-		since := now.Sub(latest.Creation)
-		if since < 0 {
-			l.WithField("snapshot", latest.Name).
-				WithField("creation", latest.Creation).
-				Error("snapshot is from the future")
-			continue
-		}
-		next := now
-		if since < interval {
-			next = latest.Creation.Add(interval)
-		}
-		snaptimes = append(snaptimes, snapTime{d, next})
-	}
-
-	if len(snaptimes) == 0 {
-		snaptimes = append(snaptimes, snapTime{nil, now})
-	}
-
-	sort.Slice(snaptimes, func(i, j int) bool {
-		return snaptimes[i].time.Before(snaptimes[j].time)
-	})
-
-	return snaptimes[0].time, nil
-
-}
-

daemon/snapper/snapper_all.go

@@ -1,39 +0,0 @@
-package snapper
-
-import (
-	"context"
-	"fmt"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/filters"
-)
-
-// FIXME: properly abstract snapshotting:
-//   - split up things that trigger snapshotting from the mechanism
-//     - timer-based trigger (periodic)
-//     - call from control socket (manual)
-//     - mixed modes?
-//   - support a `zrepl snapshot JOBNAME` subcommand for config.SnapshottingManual
-type PeriodicOrManual struct {
-	s *Snapper
-}
-
-func (s *PeriodicOrManual) Run(ctx context.Context, wakeUpCommon chan <- struct{}) {
-	if s.s != nil {
-		s.s.Run(ctx, wakeUpCommon)
-	}
-}
-
-func FromConfig(g *config.Global, fsf *filters.DatasetMapFilter, in config.SnapshottingEnum) (*PeriodicOrManual, error) {
-	switch v := in.Ret.(type) {
-	case *config.SnapshottingPeriodic:
-		snapper, err := PeriodicFromConfig(g, fsf, v)
-		if err != nil {
-			return nil, err
-		}
-		return &PeriodicOrManual{snapper}, nil
-	case *config.SnapshottingManual:
-		return &PeriodicOrManual{}, nil
-	default:
-		return nil, fmt.Errorf("unknown snapshotting type %T", v)
-	}
-}

daemon/snapper/state_string.go

@@ -1,35 +0,0 @@
-// Code generated by "stringer -type=State"; DO NOT EDIT.
-
-package snapper
-
-import "strconv"
-
-const (
-	_State_name_0 = "SyncUpPlanning"
-	_State_name_1 = "Snapshotting"
-	_State_name_2 = "Waiting"
-	_State_name_3 = "ErrorWait"
-	_State_name_4 = "Stopped"
-)
-
-var (
-	_State_index_0 = [...]uint8{0, 6, 14}
-)
-
-func (i State) String() string {
-	switch {
-	case 1 <= i && i <= 2:
-		i -= 1
-		return _State_name_0[_State_index_0[i]:_State_index_0[i+1]]
-	case i == 4:
-		return _State_name_1
-	case i == 8:
-		return _State_name_2
-	case i == 16:
-		return _State_name_3
-	case i == 32:
-		return _State_name_4
-	default:
-		return "State(" + strconv.FormatInt(int64(i), 10) + ")"
-	}
-}

daemon/streamrpcconfig/streamrpcconfig.go

@@ -1,25 +0,0 @@
-package streamrpcconfig
-
-import (
-	"github.com/problame/go-streamrpc"
-	"github.com/zrepl/zrepl/config"
-)
-
-func FromDaemonConfig(g *config.Global, in *config.RPCConfig) (*streamrpc.ConnConfig, error) {
-	conf := in
-	if conf == nil {
-		conf = g.RPC
-	}
-	srpcConf := &streamrpc.ConnConfig{
-		RxHeaderMaxLen:       conf.RxHeaderMaxLen,
-		RxStructuredMaxLen:   conf.RxStructuredMaxLen,
-		RxStreamMaxChunkSize: conf.RxStreamChunkMaxLen,
-		TxChunkSize:          conf.TxChunkSize,
-		Timeout: 			  conf.Timeout,
-		SendHeartbeatInterval: conf.SendHeartbeatInterval,
-	}
-	if err := srpcConf.Validate(); err != nil {
-		return nil, err
-	}
-	return srpcConf, nil
-}

daemon/transport/connecter/connect_local.go

@@ -1,30 +0,0 @@
-package connecter
-
-import (
-	"context"
-	"fmt"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/transport/serve"
-	"net"
-)
-
-type LocalConnecter struct {
-	listenerName string
-	clientIdentity string
-}
-
-func LocalConnecterFromConfig(in *config.LocalConnect) (*LocalConnecter, error) {
-	if in.ClientIdentity == "" {
-		return nil, fmt.Errorf("ClientIdentity must not be empty")
-	}
-	if in.ListenerName == "" {
-		return nil, fmt.Errorf("ListenerName must not be empty")
-	}
-	return &LocalConnecter{listenerName: in.ListenerName, clientIdentity: in.ClientIdentity}, nil
-}
-
-func (c *LocalConnecter) Connect(dialCtx context.Context) (conn net.Conn, err error) {
-	l := serve.GetLocalListener(c.listenerName)
-	return l.Connect(dialCtx, c.clientIdentity)
-}
-

daemon/transport/connecter/connect_tcp.go

@@ -1,24 +0,0 @@
-package connecter
-
-import (
-	"context"
-	"github.com/zrepl/zrepl/config"
-	"net"
-)
-
-type TCPConnecter struct {
-	Address string
-	dialer  net.Dialer
-}
-
-func TCPConnecterFromConfig(in *config.TCPConnect) (*TCPConnecter, error) {
-	dialer := net.Dialer{
-		Timeout: in.DialTimeout,
-	}
-
-	return &TCPConnecter{in.Address, dialer}, nil
-}
-
-func (c *TCPConnecter) Connect(dialCtx context.Context) (conn net.Conn, err error) {
-	return c.dialer.DialContext(dialCtx, "tcp", c.Address)
-}

daemon/transport/connecter/connecter.go

@@ -1,84 +0,0 @@
-package connecter
-
-import (
-	"context"
-	"fmt"
-	"github.com/problame/go-streamrpc"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/streamrpcconfig"
-	"github.com/zrepl/zrepl/daemon/transport"
-	"net"
-	"time"
-)
-
-
-type HandshakeConnecter struct {
-	connecter streamrpc.Connecter
-}
-
-func (c HandshakeConnecter) Connect(ctx context.Context) (net.Conn, error) {
-	conn, err := c.connecter.Connect(ctx)
-	if err != nil {
-		return nil, err
-	}
-	dl, ok := ctx.Deadline()
-	if !ok {
-		dl = time.Now().Add(10 * time.Second) // FIXME constant
-	}
-	if err := transport.DoHandshakeCurrentVersion(conn, dl); err != nil {
-		conn.Close()
-		return nil, err
-	}
-	return conn, nil
-}
-
-
-
-func FromConfig(g *config.Global, in config.ConnectEnum) (*ClientFactory, error) {
-	var (
-		connecter            streamrpc.Connecter
-		errConnecter, errRPC error
-		connConf             *streamrpc.ConnConfig
-	)
-	switch v := in.Ret.(type) {
-	case *config.SSHStdinserverConnect:
-		connecter, errConnecter = SSHStdinserverConnecterFromConfig(v)
-		connConf, errRPC = streamrpcconfig.FromDaemonConfig(g, v.RPC)
-	case *config.TCPConnect:
-		connecter, errConnecter = TCPConnecterFromConfig(v)
-		connConf, errRPC = streamrpcconfig.FromDaemonConfig(g, v.RPC)
-	case *config.TLSConnect:
-		connecter, errConnecter = TLSConnecterFromConfig(v)
-		connConf, errRPC = streamrpcconfig.FromDaemonConfig(g, v.RPC)
-	case *config.LocalConnect:
-		connecter, errConnecter = LocalConnecterFromConfig(v)
-		connConf, errRPC = streamrpcconfig.FromDaemonConfig(g, v.RPC)
-	default:
-		panic(fmt.Sprintf("implementation error: unknown connecter type %T", v))
-	}
-
-	if errConnecter != nil {
-		return nil, errConnecter
-	}
-	if errRPC != nil {
-		return nil, errRPC
-	}
-
-	config := streamrpc.ClientConfig{ConnConfig: connConf}
-	if err := config.Validate(); err != nil {
-		return nil, err
-	}
-
-	connecter = HandshakeConnecter{connecter}
-
-	return &ClientFactory{connecter: connecter, config: &config}, nil
-}
-
-type ClientFactory struct {
-	connecter streamrpc.Connecter
-	config    *streamrpc.ClientConfig
-}
-
-func (f ClientFactory) NewClient() (*streamrpc.Client, error) {
-	return streamrpc.NewClient(f.connecter, f.config)
-}

daemon/transport/handshake.go

@@ -1,136 +0,0 @@
-package transport
-
-import (
-	"bytes"
-	"fmt"
-	"io"
-	"net"
-	"strings"
-	"time"
-	"unicode/utf8"
-)
-
-type HandshakeMessage struct {
-	ProtocolVersion int
-	Extensions []string
-}
-
-func (m *HandshakeMessage) Encode() ([]byte, error) {
-	if m.ProtocolVersion <= 0 || m.ProtocolVersion > 9999 {
-		return nil, fmt.Errorf("protocol version must be in [1, 9999]")
-	}
-	if len(m.Extensions) >= 9999 {
-		return nil, fmt.Errorf("protocol only supports [0, 9999] extensions")
-	}
-	// EXTENSIONS is a count of subsequent \n separated lines that contain protocol extensions
-	var extensions strings.Builder
-	for i, ext := range m.Extensions {
-		if strings.ContainsAny(ext, "\n") {
-			return nil, fmt.Errorf("Extension #%d contains forbidden newline character", i)
-		}
-		if !utf8.ValidString(ext) {
-			return nil, fmt.Errorf("Extension #%d is not valid UTF-8", i)
-		}
-		extensions.WriteString(ext)
-		extensions.WriteString("\n")
-	}
-	withoutLen := fmt.Sprintf("ZREPL_ZFS_REPLICATION PROTOVERSION=%04d EXTENSIONS=%04d\n%s",
-		m.ProtocolVersion, len(m.Extensions), extensions.String())
-	withLen := fmt.Sprintf("%010d %s", len(withoutLen), withoutLen)
-	return []byte(withLen), nil
-}
-
-func (m *HandshakeMessage) DecodeReader(r io.Reader, maxLen int) error {
-	var lenAndSpace [11]byte
-	if _, err := io.ReadFull(r, lenAndSpace[:]); err != nil {
-		return err
-	}
-	if !utf8.Valid(lenAndSpace[:]) {
-		return fmt.Errorf("invalid start of handshake message: not valid UTF-8")
-	}
-	var followLen int
-	n, err := fmt.Sscanf(string(lenAndSpace[:]), "%010d ", &followLen)
-	if n != 1 || err != nil {
-		return fmt.Errorf("could not parse handshake message length")
-	}
-	if followLen > maxLen {
-		return fmt.Errorf("handshake message length exceeds max length (%d vs %d)",
-			followLen, maxLen)
-	}
-
-	var buf bytes.Buffer
-	_, err = io.Copy(&buf, io.LimitReader(r, int64(followLen)))
-	if err != nil {
-		return err
-	}
-
-	var (
-		protoVersion, extensionCount int
-	)
-	n, err = fmt.Fscanf(&buf, "ZREPL_ZFS_REPLICATION PROTOVERSION=%04d EXTENSIONS=%4d\n",
-		&protoVersion, &extensionCount)
-	if n != 2 || err != nil {
-		return fmt.Errorf("could not parse handshake message: %s", err)
-	}
-	if protoVersion < 1 {
-		return fmt.Errorf("invalid protocol version %q", protoVersion)
-	}
-	m.ProtocolVersion = protoVersion
-
-	if extensionCount < 0 {
-		return fmt.Errorf("invalid extension count %q", extensionCount)
-	}
-	if extensionCount == 0 {
-		if buf.Len() != 0 {
-			return fmt.Errorf("unexpected data trailing after header")
-		}
-		m.Extensions = nil
-		return nil
-	}
-	s := buf.String()
-	if strings.Count(s, "\n") != extensionCount {
-		return fmt.Errorf("inconsistent extension count: found %d, header says %d", len(m.Extensions), extensionCount)
-	}
-	exts := strings.Split(s, "\n")
-	if exts[len(exts)-1] != "" {
-		return fmt.Errorf("unexpected data trailing after last extension newline")
-	}
-	m.Extensions = exts[0:len(exts)-1]
-
-	return nil
-}
-
-func DoHandshakeCurrentVersion(conn net.Conn, deadline time.Time) error {
-	// current protocol version is hardcoded here
-	return DoHandshakeVersion(conn, deadline, 1)
-}
-
-func DoHandshakeVersion(conn net.Conn, deadline time.Time, version int) error {
-	ours := HandshakeMessage{
-		ProtocolVersion: version,
-		Extensions: nil,
-	}
-	hsb, err := ours.Encode()
-	if err != nil {
-		return fmt.Errorf("could not encode protocol banner: %s", err)
-	}
-
-	conn.SetDeadline(deadline)
-	_, err = io.Copy(conn, bytes.NewBuffer(hsb))
-	if err != nil {
-		return fmt.Errorf("could not send protocol banner: %s", err)
-	}
-
-	theirs := HandshakeMessage{}
-	if err := theirs.DecodeReader(conn, 16 * 4096); err != nil { // FIXME constant
-		return fmt.Errorf("could not decode protocol banner: %s", err)
-	}
-
-	if theirs.ProtocolVersion != ours.ProtocolVersion {
-		return fmt.Errorf("protocol versions do not match: ours is %d, theirs is %d",
-			ours.ProtocolVersion, theirs.ProtocolVersion)
-	}
-	// ignore extensions, we don't use them
-
-	return nil
-}

daemon/transport/serve/serve.go

@@ -1,147 +0,0 @@
-package serve
-
-import (
-	"github.com/pkg/errors"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/transport"
-	"net"
-	"github.com/zrepl/zrepl/daemon/streamrpcconfig"
-	"github.com/problame/go-streamrpc"
-	"context"
-	"github.com/zrepl/zrepl/logger"
-	"github.com/zrepl/zrepl/zfs"
-	"time"
-)
-
-type contextKey int
-
-const contextKeyLog contextKey = 0
-
-type Logger = logger.Logger
-
-func WithLogger(ctx context.Context, log Logger) context.Context {
-	return context.WithValue(ctx, contextKeyLog, log)
-}
-
-func getLogger(ctx context.Context) Logger {
-	if log, ok := ctx.Value(contextKeyLog).(Logger); ok {
-		return log
-	}
-	return logger.NewNullLogger()
-}
-
-type AuthenticatedConn interface {
-	net.Conn
-	// ClientIdentity must be a string that satisfies ValidateClientIdentity
-	ClientIdentity() string
-}
-
-// A client identity must be a single component in a ZFS filesystem path
-func ValidateClientIdentity(in string) (err error) {
-	path, err := zfs.NewDatasetPath(in)
-	if err != nil {
-		return err
-	}
-	if path.Length() != 1 {
-		return errors.New("client identity must be a single path comonent (not empty, no '/')")
-	}
-	return nil
-}
-
-type authConn struct {
-	net.Conn
-	clientIdentity string
-}
-
-var _ AuthenticatedConn = authConn{}
-
-func (c authConn) ClientIdentity() string {
-	if err := ValidateClientIdentity(c.clientIdentity); err != nil {
-		panic(err)
-	}
-	return c.clientIdentity
-}
-
-// like net.Listener, but with an AuthenticatedConn instead of net.Conn
-type AuthenticatedListener interface {
-	Addr() (net.Addr)
-	Accept(ctx context.Context) (AuthenticatedConn, error)
-	Close() error
-}
-
-type ListenerFactory interface {
-	Listen() (AuthenticatedListener, error)
-}
-
-type HandshakeListenerFactory struct {
-	lf ListenerFactory
-}
-
-func (lf HandshakeListenerFactory) Listen() (AuthenticatedListener, error) {
-	l, err := lf.lf.Listen()
-	if err != nil {
-		return nil, err
-	}
-	return HandshakeListener{l}, nil
-}
-
-type HandshakeListener struct {
-	l AuthenticatedListener
-}
-
-func (l HandshakeListener) Addr() (net.Addr) { return l.l.Addr() }
-
-func (l HandshakeListener) Close() error { return l.l.Close() }
-
-func (l HandshakeListener) Accept(ctx context.Context) (AuthenticatedConn, error) {
-	conn, err := l.l.Accept(ctx)
-	if err != nil {
-		return nil, err
-	}
-	dl, ok := ctx.Deadline()
-	if !ok {
-		dl = time.Now().Add(10*time.Second) // FIXME constant
-	}
-	if err := transport.DoHandshakeCurrentVersion(conn, dl); err != nil {
-		conn.Close()
-		return nil, err
-	}
-	return conn, nil
-}
-
-func FromConfig(g *config.Global, in config.ServeEnum) (lf ListenerFactory, conf *streamrpc.ConnConfig, _ error) {
-
-	var (
-		lfError, rpcErr error
-	)
-	switch v := in.Ret.(type) {
-	case *config.TCPServe:
-		lf, lfError = TCPListenerFactoryFromConfig(g, v)
-		conf, rpcErr = streamrpcconfig.FromDaemonConfig(g, v.RPC)
-	case *config.TLSServe:
-		lf, lfError = TLSListenerFactoryFromConfig(g, v)
-		conf, rpcErr = streamrpcconfig.FromDaemonConfig(g, v.RPC)
-	case *config.StdinserverServer:
-		lf, lfError = MultiStdinserverListenerFactoryFromConfig(g, v)
-		conf, rpcErr = streamrpcconfig.FromDaemonConfig(g, v.RPC)
-	case *config.LocalServe:
-		lf, lfError = LocalListenerFactoryFromConfig(g, v)
-		conf, rpcErr = streamrpcconfig.FromDaemonConfig(g, v.RPC)
-	default:
-		return nil, nil, errors.Errorf("internal error: unknown serve type %T", v)
-	}
-
-	if lfError != nil {
-		return nil, nil, lfError
-	}
-	if rpcErr != nil {
-		return nil, nil, rpcErr
-	}
-
-	lf = HandshakeListenerFactory{lf}
-
-	return lf, conf, nil
-
-}
-
-

daemon/transport/serve/serve_tcp.go

@@ -1,91 +0,0 @@
-package serve
-
-import (
-	"github.com/zrepl/zrepl/config"
-	"net"
-	"github.com/pkg/errors"
-	"context"
-)
-
-type TCPListenerFactory struct {
-	address *net.TCPAddr
-	clientMap *ipMap
-}
-
-type ipMapEntry struct {
-	ip net.IP
-	ident string
-}
-
-type ipMap struct {
-	entries []ipMapEntry
-}
-
-func ipMapFromConfig(clients map[string]string) (*ipMap, error) {
-	entries := make([]ipMapEntry, 0, len(clients))
-	for clientIPString, clientIdent := range clients {
-		clientIP := net.ParseIP(clientIPString)
-		if clientIP == nil {
-			return nil, errors.Errorf("cannot parse client IP %q", clientIPString)
-		}
-		if err := ValidateClientIdentity(clientIdent); err != nil {
-			return nil, errors.Wrapf(err,"invalid client identity for IP %q", clientIPString)
-		}
-		entries = append(entries, ipMapEntry{clientIP, clientIdent})
-	}
-	return &ipMap{entries: entries}, nil
-}
-
-func (m *ipMap) Get(ip net.IP) (string, error) {
-	for _, e := range m.entries {
-		if e.ip.Equal(ip) {
-			return e.ident, nil
-		}
-	}
-	return "", errors.Errorf("no identity mapping for client IP %s", ip)
-}
-
-func TCPListenerFactoryFromConfig(c *config.Global, in *config.TCPServe) (*TCPListenerFactory, error) {
-	addr, err := net.ResolveTCPAddr("tcp", in.Listen)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot parse listen address")
-	}
-	clientMap, err := ipMapFromConfig(in.Clients)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot parse client IP map")
-	}
-	lf := &TCPListenerFactory{
-		address: addr,
-		clientMap: clientMap,
-	}
-	return lf, nil
-}
-
-func (f *TCPListenerFactory) Listen() (AuthenticatedListener, error) {
-	l, err := net.ListenTCP("tcp", f.address)
-	if err != nil {
-		return nil, err
-	}
-	return &TCPAuthListener{l, f.clientMap}, nil
-}
-
-type TCPAuthListener struct {
-	*net.TCPListener
-	clientMap *ipMap
-}
-
-func (f *TCPAuthListener) Accept(ctx context.Context) (AuthenticatedConn, error) {
-	nc, err := f.TCPListener.Accept()
-	if err != nil {
-		return nil, err
-	}
-	clientIP := nc.RemoteAddr().(*net.TCPAddr).IP
-	clientIdent, err := f.clientMap.Get(clientIP)
-	if err != nil {
-		getLogger(ctx).WithField("ip", clientIP).Error("client IP not in client map")
-		nc.Close()
-		return nil, err
-	}
-	return authConn{nc, clientIdent}, nil
-}
-

daemon/transport/serve/serve_tls.go

@@ -1,83 +0,0 @@
-package serve
-
-import (
-	"crypto/tls"
-	"crypto/x509"
-	"fmt"
-	"github.com/pkg/errors"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/tlsconf"
-	"net"
-	"time"
-	"context"
-)
-
-type TLSListenerFactory struct {
-	address          string
-	clientCA         *x509.CertPool
-	serverCert       tls.Certificate
-	handshakeTimeout time.Duration
-	clientCNs map[string]struct{}
-}
-
-func TLSListenerFactoryFromConfig(c *config.Global, in *config.TLSServe) (lf *TLSListenerFactory, err error) {
-	lf = &TLSListenerFactory{
-		address: in.Listen,
-		handshakeTimeout: in.HandshakeTimeout,
-	}
-
-	if in.Ca == "" || in.Cert == "" || in.Key == "" {
-		return nil, errors.New("fields 'ca', 'cert' and 'key'must be specified")
-	}
-
-	lf.clientCA, err = tlsconf.ParseCAFile(in.Ca)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot parse ca file")
-	}
-
-	lf.serverCert, err = tls.LoadX509KeyPair(in.Cert, in.Key)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot parse cer/key pair")
-	}
-
-	lf.clientCNs = make(map[string]struct{}, len(in.ClientCNs))
-	for i, cn := range in.ClientCNs {
-		if err := ValidateClientIdentity(cn); err != nil {
-			return nil, errors.Wrapf(err, "unsuitable client_cn #%d %q", i, cn)
-		}
-		// dupes are ok fr now
-		lf.clientCNs[cn] = struct{}{}
-	}
-
-	return lf, nil
-}
-
-func (f *TLSListenerFactory) Listen() (AuthenticatedListener, error) {
-	l, err := net.Listen("tcp", f.address)
-	if err != nil {
-		return nil, err
-	}
-	tl := tlsconf.NewClientAuthListener(l, f.clientCA, f.serverCert, f.handshakeTimeout)
-	return tlsAuthListener{tl, f.clientCNs}, nil
-}
-
-type tlsAuthListener struct {
-	*tlsconf.ClientAuthListener
-	clientCNs map[string]struct{}
-}
-
-func (l tlsAuthListener) Accept(ctx context.Context) (AuthenticatedConn, error) {
-	c, cn, err := l.ClientAuthListener.Accept()
-	if err != nil {
-		return nil, err
-	}
-	if _, ok := l.clientCNs[cn]; !ok {
-		if err := c.Close(); err != nil {
-			getLogger(ctx).WithError(err).Error("error closing connection with unauthorized common name")
-		}
-		return nil, fmt.Errorf("unauthorized client common name %q from %s", cn, c.RemoteAddr())
-	}
-	return authConn{c, cn}, nil
-}
-
-

debian

@@ -0,0 +1 @@
+packaging/deb/debian

dist/openrc/zrepl

@@ -0,0 +1,23 @@
+#!/sbin/openrc-run
+
+command='/usr/local/bin/zrepl'
+command_args='daemon'
+command_background='true'
+pidfile="/run/${RC_SVCNAME}.pid"
+output_log="/var/log/${RC_SVCNAME}.log"
+error_log="/var/log/${RC_SVCNAME}.log"
+
+zrepl_runtime_dir='/var/run/zrepl'
+
+start() {
+	mkdir -p "$zrepl_runtime_dir/stdinserver"
+	chmod -R 0700 "$zrepl_runtime_dir"
+	default_start
+}
+
+stop() {
+	rm -rf "$zrepl_runtime_dir"
+	default_stop
+}
+
+# vi: noet sw=8 sts=0

dist/systemd/zrepl.service

@@ -0,0 +1,16 @@
+[Unit]
+Description=zrepl daemon
+Documentation=https://zrepl.github.io
+
+[Service]
+Type=simple
+ExecStartPre=/usr/local/bin/zrepl --config /etc/zrepl/zrepl.yml configcheck
+ExecStart=/usr/local/bin/zrepl --config /etc/zrepl/zrepl.yml daemon
+RuntimeDirectory=zrepl zrepl/stdinserver
+RuntimeDirectoryMode=0700
+
+# Make Go produce coredumps
+Environment=GOTRACEBACK='crash'
+
+[Install]
+WantedBy=multi-user.target

docs/.python-version

@@ -0,0 +1 @@
+3.14

docs/Makefile

@@ -10,11 +10,11 @@ BUILDDIR      = _build
 
 # Put it first so that "make" without argument is like "make help".
 help:
-	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" -c sphinxconf $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
 
 .PHONY: help Makefile
 
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" -c sphinxconf $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/_static/banner.css

@@ -0,0 +1,43 @@
+/* https://github.com/sphinx-contrib/sphinxcontrib-versioning/blob/0b56210959c6b21bbb730072e81876491b4e1371/sphinxcontrib/versioning/_static/banner.css */
+
+.scv-banner {
+    padding: 3px;
+    border-radius: 2px;
+    font-size: 80%;
+    text-align: center;
+    color: white;
+    background: #d40 linear-gradient(-45deg,
+        rgba(255, 255, 255, 0.2) 0%,
+        rgba(255, 255, 255, 0.2) 25%,
+        transparent 25%,
+        transparent 50%,
+        rgba(255, 255, 255, 0.2) 50%,
+        rgba(255, 255, 255, 0.2) 75%,
+        transparent 75%,
+        transparent
+    );
+    background-size: 28px 28px;
+}
+.scv-banner > a {
+    color: white;
+}
+
+
+.scv-sphinx_rtd_theme {
+    background-color: #2980B9;
+}
+
+
+.scv-bizstyle {
+    background-color: #336699;
+}
+
+
+.scv-classic {
+    text-align: center !important;
+}
+
+
+.scv-traditional {
+    text-align: center !important;
+}

docs/_templates/page.html

@@ -0,0 +1 @@
+{% extends "!page.html" %}

docs/_templates/versions.html

@@ -0,0 +1,24 @@
+<div class="rst-versions" data-toggle="rst-versions" role="note" aria-label="versions">
+  <span class="rst-current-version" data-toggle="rst-current-version">
+    <span class="fa fa-book"> Other Versions</span>
+    v: latest
+    <span class="fa fa-caret-down"></span>
+  </span>
+  <div class="rst-other-versions">
+    <dl>
+      <dt>Releases</dt>
+      <dd><a href="https://github.com/zrepl/zrepl/releases/tag/v0.6.1">v0.6.1</a></dd>
+      <dd><a href="https://github.com/zrepl/zrepl/releases/tag/v0.5.0">v0.5.0</a></dd>
+      <dd><a href="https://github.com/zrepl/zrepl/releases/tag/v0.4.0">v0.4.0</a></dd>
+      <dd><a href="https://github.com/zrepl/zrepl/releases">All releases...</a></dd>
+    </dl>
+    <dl>
+      <dt>Note</dt>
+      <dd style="white-space: normal;">
+        Release-specific docs are in the
+        <span style="font-family: monospace;">zrepl-noarch.tar</span>
+        asset on each GitHub release.
+      </dd>
+    </dl>
+  </div>
+</div>

docs/changelog.rst

@@ -1,27 +1,283 @@
+.. include:: global.rst.inc
+
 .. |break_config| replace:: **[CONFIG]**
 .. |break| replace:: **[BREAK]**
 .. |bugfix| replace:: [BUG]
 .. |docs| replace:: [DOCS]
 .. |feature| replace:: [FEATURE]
+.. |mig| replace:: **[MIGRATION]**
+.. |maint| replace:: [MAINT]
 
 .. _changelog:
 
 Changelog
 =========
 
-The changelog summarizes bugfixes that are deemed relevant for users and package maintainers.
-Developers should consult the git commit log or GitHub issue tracker.
+0.7.0
+-----
 
-We use the following annotations for classifying changes:
+* |feature| Config file inclusion using ``include`` directive.
+  This allows distributing zrepl job definitions across multiple YAML files in a ``conf.d`` style directory.
+  (:commit:`4d6583e`, thanks, `@ZeyadTamimi <https://github.com/zeyadtamimi>`_).
+* |feature| Add configurable timezone for snapshot name timestamps. The default remains UTC. (:commit:`b9b9ad1`, thanks, `@mjasnik <https://github.com/mjasnik>`_).
+* |feature| Improve Grafana dashboard with additional panels and refinements (:commit:`3f75127`, thanks, `@deajan <https://github.com/deajan>`_).
+* |bugfix| Fix replication of placeholder filesystems (:commit:`5615f49`).
+* |bugfix| Avoid using the word "error" in info-level log lines about ZFS command execution (:commit:`d3b2295`, thanks, `@bakhtiyarneyman <https://github.com/bakhtiyarneyman>`_).
+* |bugfix| Detect duplicate and internal job names at config parse time.
+  zrepl will now refuse to load a config with duplicate or internally reserved job names, instead of failing later at daemon startup.
+  (:commit:`860a9be`).
+* |docs| Add installation instructions for openSUSE (:commit:`40c4827`, thanks, `@findesgh <https://github.com/findesgh>`_).
+* |docs| Improve documentation on ``send_properties`` configuration and NFS/SMB considerations (:commit:`b5d8538`, thanks, `@Malvineous <https://github.com/Malvineous>`_).
+* |docs| Warn more prominently about the risks of the ``not_replicated`` keep rule (:commit:`affe00a`, thanks, `@wxiaoguang <https://github.com/wxiaoguang>`_).
+* |docs| Improve TLS/EasyRSA setup instructions (:commit:`e524b60`, thanks, `@alorimer <https://github.com/alorimer>`_).
+* |docs| ``zrepl.github.io``: auto-publish from ``master`` branch, retire ``stable`` branch (:commit:`4f950bb`).
+* |maint| ``zrepl status``: switch from the unmaintained ``cview`` fork back to the actively maintained ``tview`` library (:commit:`d7ede3f`).
+* |maint| Update to Go 1.25 toolchain with Go 1.24 language level & Go dependencies
+* |maint| Debian packages: proper bash completion placement (:commit:`2923009`)
+* |maint| RPM packages: AlmaLinux 8 for RPM builds (:commit:`27f4ad1`).
+* |maint| Improve build system & CI setup
 
-* |break_config| Change that breaks the config.
-  As a package maintainer, make sure to warn your users about config breakage somehow.
-* |break| Change that breaks interoperability or persistent state representation with previous releases.
-  As a package maintainer, make sure to warn your users about config breakage somehow.
-  Note that even updating the package on both sides might not be sufficient, e.g. if persistent state needs to be migrated to a new format.
-* |feature| Change that introduces new functionality.
-* |bugfix| Change that fixes a bug, no regressions or incompatibilities expected.
-* |docs| Change to the documentation.
+.. NOTE::
+  |  zrepl is a spare-time project primarily developed by `Christian Schwarz <https://cschwarz.com>`_.
+  |  You can support maintenance and feature development through one of the following services:
+  |  |Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal|
+  |  Note that PayPal processing fees are relatively high for small donations.
+  |  For SEPA wire transfer and **commercial support**, please `contact Christian directly <https://cschwarz.com>`_.
+
+0.6.1
+-----
+
+* |feature| add metric to detect filesystems rules that don't match any local dataset (thanks, `@gmekicaxcient <https://github.com/gmekicaxcient>`_).
+* |bugfix| ``zrepl status``: hide progress bar once all filesystems reach terminal state (thanks, `@0x3333 <https://github.com/0x3333>`_).
+* |bugfix| handling of tenative cursor presence if protection strategy doesn't use it (:issue:`714`).
+* |docs| address setup with two or more external disks (thanks, `@se-jaeger <https://github.com/se-jaeger>`_).
+* |docs| document ``replication`` and ``conflict_resolution`` options (thanks, `@InsanePrawn <https://github.com/InsanePrawn>`_).
+* |docs| docs: talks: add note on keep_bookmarks option (thanks, `@skirmess <https://github.com/skirmess>`_).
+* |maint| dist: add openrc service file (thanks, `@gramosg <https://github.com/gramosg>`_).
+* |maint| grafana: update dashboard to Grafana 9.3.6.
+* |maint| run platform tests as part of CI.
+* |maint| build: upgrade to Go 1.21 and update golangci-lint; minimum Go version for builds is now 1.20
+
+0.6
+---
+
+* |feature| :ref:`Schedule-based snapshotting<job-snapshotting--cron>` using ``cron`` syntax instead of an interval.
+* |feature| Configurable initial replication policy.
+  When a filesystem is first replicated to a receiver, this control whether just the newest
+  snapshot will be replicated vs. all existing snapshots. Learn more :ref:`in the docs <conflict_resolution-initial_replication>`.
+* |feature| Configurable timestamp format for snapshot names via :ref:`timestamp_format<job-snapshotting-timestamp_format>`
+  (Thanks, `@ydylla <https://github.com/ydylla>`_).
+* |feature| Add ``ZREPL_DESTROY_MAX_BATCH_SIZE`` env var (default 0=unlimited)
+  (Thanks, `@3nprob <https://github.com/3nprob>`_).
+* |feature| Add ``zrepl configcheck --skip-cert-check`` flag (Thanks, `@cole-h <https://github.com/cole-h>`_).
+* |bugfix| Fix resuming from interrupted replications that use ``send.raw`` on unencrypted datasets.
+
+  * The send options introduced in zrepl 0.4 allow users to specify additional zfs send flags for zrepl to use.
+    Before this fix, when setting ``send.raw=true`` on a job that replicates unencrypted datasets,
+    zrepl would not allow an interrupted replication to resume.
+    The reason were overly cautious checks to support the ``send.encrypted`` option.
+  * This bugfix removes these checks from the replication planner.
+    This makes ``send.encrypted`` a sender-side-only concern, much like all other ``send.*`` flags.
+  * However, this means that the ``zrepl status`` UI no longer indicates whether a replication step uses encrypted sends or not.
+    The setting is still effective though.
+
+* |break| convert Prometheus metric ``zrepl_version_daemon`` to ``zrepl_start_time`` metric
+
+  * The metric still reports the zrepl version in a label.
+    But the metric *value* is now the Unix timestamp at the time the daemon was started.
+    The Grafana dashboard in :repomasterlink:`dist/grafana` has been updated.
+
+* |bugfix| transient zrepl status error: ``Post "http://unix/status": EOF``
+* |bugfix| don't treat receive-side bookmarks as a replication conflict.
+  This facilitates chaining of replication jobs. See :issue:`490`.
+* |bugfix| workaround for Go/gRPC problem on Illumos where zrepl would
+  crash when using the ``local`` transport type (:issue:`598`).
+* |bugfix| fix active child tasks panic that cold occur during replication plannig (:issue:`193abbe`)
+* |bugfix| ``zrepl status`` off-by-one error in display of completed step count (:commit:`ce6701f`)
+* |bugfix| Allow using day & week units for ``snapshotting.interval`` (:commit:`ffb1d89`)
+* |docs| ``docs/overview`` improvements (Thanks, `@jtagcat <https://github.com/jtagcat>`_).
+* |maint| Update to Go 1.19.
+
+0.5
+---
+
+* |feature| :ref:`Bandwidth limiting <job-send-recv-options--bandwidth-limit>` (Thanks, Prominic.NET, Inc.)
+* |feature| zrepl status: use a ``*`` to indicate which filesystem is currently replicating
+* |feature| include daemon environment variables in zrepl status (currently only in ``--raw``)
+* |bugfix| **fix encrypt-on-receive + placeholders use case** (:issue:`504`)
+
+  * Before this fix, **plain sends** to a receiver with an encrypted ``root_fs`` **could be received unencrypted** if zrepl needed to create placeholders on the receiver.
+  * Existing zrepl users should :ref:`read the docs <job-recv-options--placeholder>` and check ``zfs get -r encryption,zrepl:placeholder PATH_TO_ROOTFS`` on the receiver.
+  * Thanks to `@mologie <https://github.com/mologie>`_ and `@razielgn <https://github.com/razielgn>`_ for reporting and testing!
+
+* |bugfix| Rename mis-spelled :ref:`send option <job-send-options>` ``embbeded_data`` to ``embedded_data``.
+* |bugfix| zrepl status: replication step numbers should start at 1
+* |bugfix| incorrect bandwidth averaging in ``zrepl status``.
+* |bugfix| FreeBSD with OpenZFS 2.0: zrepl would wait indefinitely for zfs send to exit on timeouts.
+* |bugfix| fix ``strconv.ParseInt: value out of range`` bug (and use the control RPCs).
+* |docs| improve description of multiple pruning rules.
+* |docs| document :ref:`platform tests <usage-platform-tests>`.
+* |docs| quickstart: make users aware that prune rules apply to all snapshots.
+* |maint| some platformtests were broken.
+* |maint| FreeBSD: release armv7 and arm64 binaries.
+* |maint| apt repo: update instructions due to ``apt-key`` deprecation.
+
+Note to all users: please read up on the following OpenZFS bugs, as you might be affected:
+
+* `ZFS send/recv with ashift 9->12 leads to data corruption <https://github.com/openzfs/zfs/issues/12762>`_.
+* Various bugs with encrypted send/recv (`Leadership meeting notes <https://openzfs.topicbox.com/groups/developer/T24bdaa2886c6cbf5-Mc039a11c3f1507ea0664817b/december-openzfs-leadership-meeting>`_)
+
+Finally, I'd like to point you to the `GitHub discussion <https://github.com/zrepl/zrepl/discussions/547>`_ about which bugfixes and features should be prioritized in zrepl 0.6 and beyond!
+
+0.4.0
+-----
+
+* |feature| support setting zfs send / recv flags in the config (send: ``-wLcepbS`` , recv: ``-ox`` ).
+  Config docs :ref:`here <job-send-options>` and :ref:`here <job-recv-options>` .
+* |feature| parallel replication is now configurable (disabled by default, :ref:`config docs here <replication-option-concurrency>` ).
+* |feature| New ``zrepl status`` UI:
+
+  * Interactive job selection.
+  * Interactively ``zrepl signal`` jobs.
+  * Filter filesystems in the job view by name.
+  * An approximation of the old UI is still included as `--mode legacy` but will be removed in a future release of zrepl.
+
+* |bugfix| Actually use concurrency when listing zrepl abstractions & doing size estimation.
+  These operations were accidentally made sequential in zrepl 0.3.
+* |bugfix| Job hang-up during second replication attempt.
+* |bugfix| Data races conditions in the dataconn rpc stack.
+* |maint| Update to protobuf v1.25 and grpc 1.35.
+
+For users who skipped the 0.3.1 update: please make sure your pruning grid config is correct.
+The following bugfix in 0.3.1 :issue:`caused problems for some users <400>`:
+
+* |bugfix| pruning: ``grid``:  add all snapshots that do not match the regex to the rule's destroy list.
+
+0.3.1
+-----
+
+Mostly a bugfix release for :ref:`zrepl 0.3 <release-0.3>`.
+
+* |feature| pruning: add optional ``regex`` field to ``last_n`` rule
+* |docs| pruning: ``grid`` : improve documentation and add an example
+* |bugfix| pruning: ``grid``:  add all snapshots that do not match the regex to the rule's destroy list.
+  This brings the implementation in line with the docs.
+* |bugfix| ``easyrsa`` script in docs
+* |bugfix| platformtest: fix skipping encryption-only tests on systems that don't support encryption
+* |bugfix| replication: report AttemptDone if no filesystems are replicated
+* |feature| status + replication: warning if replication succeeeded without any filesystem being replicated
+* |docs| update multi-job & multi-host setup section
+* RPM Packaging
+* CI infrastructure rework
+* Continuous deployment of that new `stable` branch to zrepl.github.io.
+
+.. _release-0.3:
+
+0.3
+---
+
+This is a big one! Headlining features:
+
+* **Resumable Send & Recv Support**
+  No knobs required, automatically used where supported.
+* **Encrypted Send & Recv Support** for OpenZFS native encryption,
+  :ref:`configurable <job-send-options>` at the job level, i.e., for all filesystems a job is responsible for.
+* **Replication Guarantees**
+  Automatic use of ZFS holds and bookmarks to protect a replicated filesystem from losing synchronization between sender and receiver.
+  By default, zrepl guarantees that incremental replication will always be possible and interrupted steps will always be resumable.
+
+.. TIP::
+
+   We highly recommend studying the updated :ref:`overview section of the configuration chapter <overview-how-replication-works>` to understand how replication works.
+
+.. TIP::
+
+   Go 1.15 changed the default TLS validation policy to **require Subject Alternative Names (SAN) in certificates**.
+   The openssl commands we provided in the quick-start guides up to and including the zrepl 0.3 docs seem not to work properly.
+   If you encounter certificate validation errors regarding SAN and wish to continue to use your old certificates, start the zrepl daemon with env var ``GODEBUG=x509ignoreCN=0``.
+   Alternatively, generate new certificates with SANs (see :ref:`both options int the TLS transport docs <transport-tcp+tlsclientauth-certgen>` ).
+
+Quick-start guides:
+
+* We have added :ref:`another quick-start guide for a typical workstation use case for zrepl <quickstart-backup-to-external-disk>`.
+  Check it out to learn how you can use zrepl to back up your workstation's OpenZFS natively-encrypted root filesystem to an external disk.
+
+Additional changelog:
+
+* |break| Go 1.15 TLS changes mentioned above.
+* |break| |break_config| **more restrictive job names than in prior zrepl versions**
+  Starting with this version, job names are going to be embedded into ZFS holds and bookmark names (see :ref:`this section for details <zrepl-zfs-abstractions>`).
+  Therefore you might need to adjust your job names.
+  **Note that jobs** cannot be renamed easily **once you start using zrepl 0.3.**
+* |break| |mig| replication cursor representation changed
+
+  * zrepl now manages the :ref:`replication cursor bookmark <zrepl-zfs-abstractions>` per job-filesystem tuple instead of a single replication cursor per filesystem.
+    In the future, this will permit multiple sending jobs to send from the same filesystems.
+  * ZFS does not allow bookmark renaming, thus we cannot migrate the old replication cursors.
+  * zrepl 0.3 will automatically create cursors in the new format for new replications, and warn if it still finds ones in the old format.
+  * Run ``zrepl migrate replication-cursor:v1-v2`` to safely destroy old-format cursors.
+    The migration will ensure that only those old-format cursors are destroyed that have been superseeded by new-format cursors.
+
+* |feature| New option ``listen_freebind`` (tcp, tls, prometheus listener)
+* |feature| :issue:`341` Prometheus metric for failing replications + corresponding Grafana panel
+* |feature| :issue:`265` transport/tcp: support for CIDR masks in client IP whitelist
+* |feature| documented subcommand to generate ``bash`` and ``zsh`` completions
+* |feature| :issue:`307` ``chrome://trace`` -compatible activity tracing of zrepl daemon activity
+* |feature| logging: trace IDs for better log entry correlation with concurrent replication jobs
+* |feature| experimental environment variable for parallel replication (see :issue:`306` )
+* |bugfix| missing logger context vars in control connection handlers
+* |bugfix| improved error messages on ``zfs send`` errors
+* |bugfix| |docs| snapshotting: clarify sync-up behavior and warn about filesystems
+* |bugfix| transport/ssh: do not leak zombie ssh process on connection failures
+  that will not be snapshotted until the sync-up phase is over
+* |docs| Installation: :ref:`FreeBSD jail with iocage <installation-freebsd-jail-with-iocage>`
+* |docs| Document new replication features in the :ref:`config overview <overview-how-replication-works>` and :repomasterlink:`replication/design.md`.
+* **[MAINTAINER NOTICE]** New platform tests in this version, please make sure you run them for your distro!
+* **[MAINTAINER NOTICE]** Please add the shell completions to the zrepl packages.
+
+0.2.1
+-----
+
+* |feature| Illumos (and Solaris) compatibility and binary builds (thanks, `MNX.io <https://mnx.io>`_ )
+* |feature| 32bit binaries for Linux and FreeBSD (untested, though)
+* |bugfix| better error messages in ``ssh+stdinserver`` transport
+* |bugfix| systemd + ``ssh+stdinserver``: automatically create ``/var/run/zrepl/stdinserver``
+* |bugfix| crash if Prometheus listening socket cannot be opened
+
+* [MAINTAINER NOTICE] ``Makefile`` refactoring, see commit :commit:`080f2c0`
+
+0.2
+---
+
+* |feature| :ref:`Pre- and Post-Snapshot Hooks <job-snapshotting-hooks>`
+  with built-in support for MySQL and Postgres checkpointing
+  as well as custom scripts (thanks, `@overhacked <https://github.com/overhacked>`_!)
+* |feature| Use ``zfs destroy pool/fs@snap1,snap2,...`` CLI feature if available
+* |feature| Linux ARM64 Docker build support & binary builds
+* |feature| ``zrepl status`` now displays snapshotting reports
+* |feature| ``zrepl status --job <JOBNAME>`` filter flag
+* |bugfix| i386 build
+* |bugfix| early validation of host:port tuples in config
+* |bugfix| ``zrepl status`` now supports ``TERM=screen`` (tmux on FreeBSD / FreeNAS)
+* |bugfix| ignore *connection reset by peer* errors when shutting down connections
+* |bugfix| correct error messages when receive-side pool or ``root_fs`` dataset is not imported
+* |bugfix| fail fast for misconfigured local transport
+* |bugfix| race condition in replication report generation would crash the daemon when running ``zrepl status``
+* |bugfix| rpc goroutine leak in ``push`` mode if zfs recv fails on the ``sink`` side
+* [MAINTAINER NOTICE] Go modules for dependency management both inside and outside of GOPATH
+  (``lazy.sh`` and ``Makefile`` force ``GO111MODULE=on``)
+* [MAINTAINER NOTICE] ``make platformtest`` target to check zrepl's ZFS abstractions (screen scraping, etc.).
+  These tests only work on a system with ZFS installed, and must be run as root because they create a file-backed pool for each test case.
+  The pool name ``zreplplatformtest`` is reserved for this use case.
+  Only run ``make platformtest`` on test systems, e.g. a FreeBSD VM image.
+
+0.1.1
+-----
+
+* |bugfix| :issue:`162` commit :commit:`d6304f4` : fix I/O timeout errors on variable receive rate
+
+  * A significant reduction or sudden stall of the receive rate (e.g. recv pool has other I/O to do)
+    would cause a ``writev I/O timeout`` error after approximately ten seconds.
 
 0.1
 ---
@@ -40,6 +296,7 @@ It breaks both configuration and transport format, and thus requires manual inte
 Notes to Package Maintainers
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
+* Notify users about config changes and migrations (see changes attributed with |break| and |mig| below)
 * If the daemon crashes, the stack trace produced by the Go runtime and possibly diagnostic output of zrepl will be written to stderr.
   This behavior is independent from the ``stdout`` outlet type.
   Please make sure the stderr output of the daemon is captured somewhere.
@@ -48,26 +305,43 @@ Notes to Package Maintainers
   This functionality will cause SIGABRT on panics and can be used to capture a coredump of the panicking process.
   To that extend, make sure that your package build system, your OS's coredump collection and the Go delve debugger work together.
   Use your build system to package the Go program in `this tutorial on Go coredumps and the delve debugger <https://rakyll.org/coredumps/>`_ , and make sure the symbol resolution etc. work on coredumps captured from the binary produced by your build system. (Special focus on symbol stripping, etc.)
-* Use of ``ssh+stdinserver`` :ref:`transport <transport-ssh+stdinserver>` is no longer encouraged.
-  Please encourage users to use the new ``tcp`` or ``tls`` transports.
-  You might as well mention some of the :ref:`tunneling options listed here <transport-tcp-tunneling>`.
+* Consider using the ``zrepl configcheck`` subcommand in startup scripts to abort a restart that would fail due to an invalid config.
 
 Changes
 ~~~~~~~
 
+* |break| |mig| Placeholder property representation changed
+
+  * The :ref:`placeholder property <replication-placeholder-property>` now uses ``on|off`` as values
+    instead of hashes of the dataset path. This permits renames of the sink filesystem without
+    updating all placeholder properties.
+  * Relevant for 0.0.X-0.1-rc* to 0.1 migrations
+  * Make sure your config is valid with ``zrepl configcheck``
+  * Run ``zrepl migrate 0.0.X:0.1:placeholder``
+
 * |feature| :issue:`55` : Push replication (see :ref:`push job <job-push>` and :ref:`sink job <job-sink>`)
 * |feature| :ref:`TCP Transport <transport-tcp>`
 * |feature| :ref:`TCP + TLS client authentication transport <transport-tcp+tlsclientauth>`
-* |feature| :issue:`78` :commit:`074f989` : Replication protocol rewrite
+* |feature| :issue:`111`: RPC protocol rewrite
 
-  * Uses ``github.com/problame/go-streamrpc`` for RPC layer
-  * |break| Protocol breakage, update and restart of all zrepl daemons is required
-  * |feature| :issue:`83`:  Improved error handling of network-level errors (zrepl retries instead of failing the entire job)
-  * |bugfix| :issue:`75` :issue:`81`: use connection timeouts and protocol-level heartbeats
-  * |break| |break_config|: mappings are no longer supported
+  * |break| Protocol breakage; Update and restart of all zrepl daemons is required.
+  * Use `gRPC <https://grpc.io/>`_ for control RPCs and a custom protocol for bulk data transfer.
+  * Automatic retries for network-temporary errors
 
-    * Receiving sides (``pull`` and ``sink`` job) specify a single ``root_fs``.
-      Received filesystems are then stored *per client* in ``${root_fs}/${client_identity}``.
+    * Limited to errors during replication for this release.
+      Addresses the common problem of ISP-forced reconnection at night, but will become
+      way more useful with resumable send & recv support.
+      Pruning errors are handled per FS, i.e., a prune RPC is attempted at least once per FS.
+
+* |feature| Proper timeout handling for the :ref:`SSH transport <transport-ssh+stdinserver>`
+
+  * |break| Requires Go 1.11 or later.
+
+* |break| |break_config|: mappings are no longer supported
+
+  * Receiving sides (``pull`` and ``sink`` job) specify a single ``root_fs``.
+    Received filesystems are then stored *per client* in ``${root_fs}/${client_identity}``.
+    See :ref:`job-overview` for details.
 
 * |feature| |break| |break_config| Manual snapshotting + triggering of replication
 
@@ -92,12 +366,18 @@ Changes
     * |break_config| ``keep_bookmarks`` parameter of the ``grid`` keep rule has been removed
 
 * |feature| ``zrepl status`` for live-updating replication progress (it's really cool!)
+* |feature| :ref:`Snapshot- & pruning-only job type <job-snap>` (for local snapshot management)
 * |feature| :issue:`67`: Expose `Prometheus <https://prometheus.io>`_ metrics via HTTP (:ref:`config docs <monitoring-prometheus>`)
 
+  * Compatible Grafana dashboard shipping in ``dist/grafana``
+
 * |break_config| Logging outlet types must be specified using the ``type`` instead of ``outlet`` key
 * |break| :issue:`53`: CLI: ``zrepl control *`` subcommands have been made direct subcommands of ``zrepl *``
 * |bugfix| Goroutine leak on ssh transport connection timeouts
 * |bugfix| :issue:`81` :issue:`77` : handle failed accepts correctly (``source`` job)
+* |bugfix| :issue:`100`: fix incompatibility with ZoL 0.8
+* |feature| :issue:`115`: logging: configurable syslog facility
+* |feature| Systemd unit file in ``dist/systemd``
 
 .. |lastrelease| replace:: 0.0.3
 
@@ -107,8 +387,3 @@ Previous Releases
 .. NOTE::
     Due to limitations in our documentation system, we only show the changelog since the last release and the time this documentation is built.
     For the changelog of previous releases, use the version selection in the hosted version of these docs at `zrepl.github.io <https://zrepl.github.io>`_.
-    
-    
-
-
-W

docs/conf.py

@@ -1 +0,0 @@
-sphinxconf/conf.py

docs/conf.py

@@ -0,0 +1,187 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# zrepl documentation build configuration file, created by
+# sphinx-quickstart on Wed Nov  8 22:28:10 2017.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.todo',
+    'sphinx.ext.githubpages',
+    'sphinx.ext.extlinks',
+]
+
+# suppress_warnings = ['image.nonlocal_uri']
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['./_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'zrepl'
+copyright = '2017-2026, Christian Schwarz'
+author = 'Christian Schwarz'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+version = 'latest'
+# The full version, including alpha/beta/rc tags.
+release = 'latest'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = 'en'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store', '.venv']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = True
+
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+html_css_files = [
+    'banner.css',
+]
+
+html_logo = '_static/zrepl.svg'
+
+html_context = {
+  # https://github.com/rtfd/sphinx_rtd_theme/issues/205
+  # Add 'Edit on Github' link instead of 'View page source'
+  "display_github": True,
+  "github_user": "zrepl",
+  "github_repo": "zrepl",
+  "github_version": "master",
+  "conf_py_path": "/docs/",
+  "source_suffix": source_suffix,
+}
+
+# -- Options for HTMLHelp output ------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'zrepldoc'
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'zrepl.tex', 'zrepl Documentation',
+     'Christian Schwarz', 'manual'),
+]
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'zrepl', 'zrepl Documentation',
+     [author], 1)
+]
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'zrepl', 'zrepl Documentation',
+     author, 'zrepl', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+# -- Options for the extlinks extension -----------------------------------
+# http://www.sphinx-doc.org/en/stable/ext/extlinks.html
+extlinks = {
+    'issue':('https://github.com/zrepl/zrepl/issues/%s', 'issue #%s'),
+    'repomasterlink':('https://github.com/zrepl/zrepl/blob/master/%s', '%s'),
+    'sampleconf':('https://github.com/zrepl/zrepl/blob/master/internal/config/samples%s', 'internal/config/samples%s'),
+    'commit':('https://github.com/zrepl/zrepl/commit/%s', '%s'),
+        }
+

docs/configuration.rst

@@ -7,10 +7,14 @@ Configuration
 
 .. toctree::
 
-    configuration/preface
+    configuration/overview
     configuration/jobs
     configuration/transports
     configuration/filter_syntax
+    configuration/sendrecvoptions
+    configuration/replication
+    configuration/conflict_resolution
+    configuration/snapshotting
     configuration/prune
     configuration/logging
     configuration/monitoring

docs/configuration/conflict_resolution.rst

@@ -0,0 +1,37 @@
+.. include:: ../global.rst.inc
+
+.. _conflict_resolution-options:
+
+Conflict Resolution Options
+===========================
+
+
+::
+
+   jobs:
+   - type: push
+     filesystems: ...
+     conflict_resolution:
+       initial_replication: most_recent | all | fail # default: most_recent
+
+     ...
+
+.. _conflict_resolution-initial_replication:
+
+
+``initial_replication`` option
+------------------------------
+
+The ``initial_replication`` option determines how many snapshots zrepl replicates if the filesystem has not been replicated before.
+If ``most_recent`` (the default), the initial replication will only transfer the most recent snapshot, while ignoring previous snapshots.
+If all snapshots should be replicated, specify ``all``.
+Use ``fail`` to make replication of the filesystem fail in case there is no corresponding fileystem on the receiver.
+
+For example, suppose there are snapshosts ``tank@1``, ``tank@2``, ``tank@3`` on a sender.
+Then ``most_recent`` will replicate just ``@3``, but ``all`` will replicate ``@1``, ``@2``, and ``@3``.
+
+If initial replication is interrupted, and there is at least one (maybe partial) snapshot on the receiver, zrepl will always resume in **incremental mode**.
+And that is regardless of where the initial replication was interrupted.
+
+For example, if ``initial_replication: all`` and the transfer of ``@1`` is interrupted, zrepl would retry/resume at ``@1``.
+And even if the user changes the config to ``initial_replication: most_recent`` before resuming, **incremental mode** will still resume at ``@1``.

docs/configuration/filter_syntax.rst

@@ -5,7 +5,7 @@
 Filter Syntax
 =============
 
-For :ref:`source jobs <job-source>` and :ref:`push jobs <job-push>`, a filesystem filter must be defined (field ``filesystems``).
+For :ref:`source<job-source>`, :ref:`push<job-push>` and :ref:`snap<job-snap>` jobs, a filesystem filter must be defined (field ``filesystems``).
 A filter takes a filesystem path (in the ZFS filesystem hierarchy) as parameter and returns ``true`` (pass) or ``false`` (block).
 
 A filter is specified as a **YAML dictionary** with patterns as keys and booleans as values.

docs/configuration/jobs.rst

@@ -1,159 +1,9 @@
 .. include:: ../global.rst.inc
 
-.. |serve-transport| replace:: :ref:`serve specification<transport>`
-.. |connect-transport| replace:: :ref:`connect specification<transport>`
-.. |snapshotting-spec| replace:: :ref:`snapshotting specification <job-snapshotting-spec>`
-.. |pruning-spec| replace:: :ref:`pruning specification <prune>`
-.. |filter-spec| replace:: :ref:`filter specification<pattern-filter>`
-
 .. _job:
 
-Job Types & Replication
-=======================
-
-Overview & Terminology
-----------------------
-
-A *job* is the unit of activity tracked by the zrepl daemon and configured in the |mainconfig|.
-Every job has a unique ``name``, a ``type`` and type-dependent fields which are documented on this page.
-
-Replication always happens between a pair of jobs: one is the **active side**, and one the **passive side**.
-The active side executes the replication logic whereas the passive side responds to requests after checking the active side's permissions.
-For communication, the active side connects to the passive side using a :ref:`transport <transport>` and starts issuing remote procedure calls (RPCs).
-
-The following table shows how different job types can be combined to achieve both push and pull mode setups:
-
-+-----------------------+--------------+----------------------------------+-----------------------------------------------+
-| Setup name            | active side  | passive side                     | use case                                      |
-+=======================+==============+==================================+===============================================+
-| Push mode             | ``push``     | ``sink``                         | * Laptop backup                               |
-|                       |              |                                  | * NAS behind NAT to offsite                   |
-+-----------------------+--------------+----------------------------------+-----------------------------------------------+
-| Pull mode             | ``pull``     | ``source``                       | * Central backup-server for many nodes        |
-|                       |              |                                  | * Remote server to NAS behind NAT             |
-+-----------------------+--------------+----------------------------------+-----------------------------------------------+
-| Local replication     | | ``push`` + ``sink`` in one config             | * Backup FreeBSD boot pool                    |
-|                       | | with :ref:`local transport <transport-local>` |                                               |
-+-----------------------+--------------+----------------------------------+-----------------------------------------------+
-
-How the Active Side Works
-~~~~~~~~~~~~~~~~~~~~~~~~~
-
-The active side (:ref:`push <job-push>` and :ref:`pull <job-pull>` job) executes the replication and pruning logic:
-
-* Wakeup because of finished snapshotting (``push`` job) or pull interval ticker (``pull`` job).
-* Connect to the corresponding passive side using a :ref:`transport <transport>` and instantiate an RPC client.
-* Replicate data from the sending to the receiving side.
-* Prune on sender & receiver.
-
-.. TIP::
-  The progress of the active side can be watched live using the ``zrepl status`` subcommand.
-
-How the Passive Side Works
-~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-The passive side (:ref:`sink <job-sink>` and :ref:`source <job-source>`) waits for connections from the corresponding active side,
-using the transport listener type specified in the ``serve`` field of the job configuration.
-Each transport listener provides a client's identity to the passive side job.
-It uses the client identity for access control:
-
-* The ``sink`` job only allows pushes to those ZFS filesystems to the active side that are located below ``root_fs/${client_identity}``.
-* The ``source`` job has a whitelist of client identities that are allowed pull access.
-
-.. TIP::
-   The implementation of the ``sink`` job requires that the connecting client identities be a valid ZFS filesystem name components.
-
-How Replication Works
-~~~~~~~~~~~~~~~~~~~~~
-
-One of the major design goals of the replication module is to avoid any duplication of the nontrivial logic.
-As such, the code works on abstract senders and receiver **endpoints**, where typically one will be implemented by a local program object and the other is an RPC client instance.
-Regardless of push- or pull-style setup, the logic executes on the active side, i.e. in the ``push`` or ``pull`` job.
-
-The following steps take place during replication and can be monitored using the ``zrepl status`` subcommand:
-
-* Plan the replication:
-
-  * Compare sender and receiver filesystem snapshots
-  * Build the **replication plan**
-
-    * Per filesystem, compute a diff between sender and receiver snapshots
-    * Build a list of replication steps
-
-      * If possible, use incremental sends (``zfs send -i``)
-      * Otherwise, use full send of most recent snapshot on sender
-      * Give up on filesystems that cannot be replicated without data loss
-
-  * Retry on errors that are likely temporary (i.e. network failures).
-  * Give up on filesystems where a permanent error was received over RPC.
-
-* Execute the plan
-
-  * Perform replication steps in the following order:
-    Among all filesystems with pending replication steps, pick the filesystem whose next replication step's snapshot is the oldest.
-  * After a successful replication step, update the replication cursor bookmark (see below)
-   
-The idea behind the execution order of replication steps is that if the sender snapshots all filesystems simultaneously at fixed intervals, the receiver will have all filesystems snapshotted at time ``T1`` before the first snapshot at ``T2 = T1 + $interval`` is replicated.
-
-.. _replication-cursor-bookmark:
-
-The **replication cursor bookmark** ``#zrepl_replication_cursor`` is kept per filesystem on the sending side of a replication setup:
-It is a bookmark of the most recent successfully replicated snapshot to the receiving side.
-It is is used by the :ref:`not_replicated <prune-keep-not-replicated>` keep rule to identify all snapshots that have not yet been replicated to the receiving side.
-Regardless of whether that keep rule is used, the bookmark ensures that replication can always continue incrementally.
-
-.. ATTENTION::
-
-    Currently, zrepl does not replicate filesystem properties.
-    Whe receiving a filesystem, it is never mounted (`-u` flag)  and `mountpoint=none` is set.
-    This is temporary and being worked on :issue:`24`.
-
-
-.. _job-snapshotting-spec:
-
-Taking Snaphots
----------------
-
-The ``push`` and ``source`` jobs can automatically take periodic snapshots of the filesystems matched by the ``filesystems`` filter field.
-The snapshot names are composed of a user-defined prefix followed by a UTC date formatted like ``20060102_150405_000``.
-We use UTC because it will avoid name conflicts when switching time zones or between summer and winter time.
-
-For ``push`` jobs, replication is automatically triggered after all filesystems have been snapshotted.
-
-::
-
-    jobs:
-    - type: push
-      filesystems: {
-        "<": true,
-        "tmp": false
-      }
-      snapshotting:
-        type: periodic
-        prefix: zrepl_
-        interval: 10m
-      ...
-
-There is also a ``manual`` snapshotting type, which covers the following use cases:
-
-* Existing infrastructure for automatic snapshots: you only want to use zrepl for replication.
-* Run scripts before and after taking snapshots (like locking database tables).
-  We are working on better integration for this use case: see :issue:`74`.
-
-Note that you will have to trigger replication manually using the ``zrepl signal wakeup JOB`` subcommand in that case.
-
-::
-
-   jobs:
-   - type: push
-     filesystems: {
-       "<": true,
-       "tmp": false
-     }
-     snapshotting:
-       type: manual
-     ...
-
+Job Types in Detail
+===================
 
 .. _job-push:
 
@@ -169,15 +19,21 @@ Job Type ``push``
     * - ``type``
       - = ``push``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``connect``
       - |connect-transport|
     * - ``filesystems``
       - |filter-spec| for filesystems to be snapshotted and pushed to the sink
+    * - ``send``
+      - |send-options| 
     * - ``snapshotting``
       - |snapshotting-spec|
     * - ``pruning``
       - |pruning-spec|
+    * - ``replication``
+      - |replication-options|
+    * - ``conflict_resolution``
+      - |conflict-resolution-options|
 
 Example config: :sampleconf:`/push.yml`
 
@@ -195,12 +51,12 @@ Job Type ``sink``
     * - ``type``
       - = ``sink``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``serve``
       - |serve-transport|
     * - ``root_fs``
-      - ZFS dataset path are received to
-        ``$root_fs/$client_identity``
+      - ZFS filesystems are received to
+        ``$root_fs/$client_identity/$source_path``
 
 Example config: :sampleconf:`/sink.yml`
 
@@ -218,16 +74,21 @@ Job Type ``pull``
     * - ``type``
       - = ``pull``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``connect``
       - |connect-transport|
     * - ``root_fs``
-      - ZFS dataset path are received to
-        ``$root_fs/$client_identity``
+      - ZFS filesystems are received to
+        ``$root_fs/$source_path``
     * - ``interval``
-      - Interval at which to pull from the source job
+      - | Interval at which to pull from the source job (e.g. ``10m``).
+        | ``manual`` disables periodic pulling, replication then only happens on :ref:`wakeup <cli-signal-wakeup>`.
     * - ``pruning``
       - |pruning-spec|
+    * - ``replication``
+      - |replication-options|
+    * - ``conflict_resolution``
+      - |conflict-resolution-options|
 
 Example config: :sampleconf:`/pull.yml`
 
@@ -245,16 +106,19 @@ Job Type ``source``
     * - ``type``
       - = ``source``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``serve``
       - |serve-transport|
     * - ``filesystems``
       - |filter-spec| for filesystems to be snapshotted and exposed to connecting clients
+    * - ``send``
+      - |send-options| 
     * - ``snapshotting``
       - |snapshotting-spec|
 
 Example config: :sampleconf:`/source.yml`
 
+
 .. _replication-local:
 
 Local replication
@@ -265,3 +129,28 @@ If you have the need for local replication (most likely between two local storag
 Example config: :sampleconf:`/local.yml`.
 
 
+.. _job-snap:
+
+Job Type ``snap`` (snapshot & prune only)
+-----------------------------------------
+
+Job type that only takes snapshots and performs pruning on the local machine.
+
+.. list-table::
+    :widths: 20 80
+    :header-rows: 1
+
+    * - Parameter
+      - Comment
+    * - ``type``
+      - = ``snap``
+    * - ``name``
+      - unique name of the job :issue:`(must not change)<327>`
+    * - ``filesystems``
+      - |filter-spec| for filesystems to be snapshotted
+    * - ``snapshotting``
+      - |snapshotting-spec|
+    * - ``pruning``
+      - |pruning-spec|
+
+Example config: :sampleconf:`/snap.yml`

docs/configuration/logging.rst

@@ -7,7 +7,7 @@ Logging
 
 zrepl uses structured logging to provide users with easily processable log messages.
 
-Logging outlets are configured in the ``global`` section of the |mainconfig|.
+Logging outlets are configured in the ``global`` section of the config file.
 
 ::
 
@@ -147,6 +147,8 @@ Can only be specified once.
       -  minimum  :ref:`log level <logging-levels>`
     * - ``format``
       - output :ref:`format <logging-formats>`
+    * - ``facility``
+      - Which syslog facility to use (default = ``local0``)
     * - ``retry_interval``
       - Interval between reconnection attempts to syslog (default = 0)
 
@@ -200,7 +202,7 @@ The latter is particularly useful in combination with log aggregation services.
 .. WARNING::
 
     zrepl drops log messages to the TCP outlet if the underlying connection is not fast enough.
-    Note that TCP buffering in the kernel must first run full becfore messages are dropped.
+    Note that TCP buffering in the kernel must first run full before messages are dropped.
 
     Make sure to always configure a ``stdout`` outlet as the special error outlet to be informed about problems
     with the TCP outlet (see :ref:`above <logging-error-outlet>` ).

docs/configuration/misc.rst

@@ -1,3 +1,5 @@
+.. _miscellaneous:
+
 Miscellaneous
 =============
 
@@ -6,16 +8,16 @@ Miscellaneous
 Runtime Directories & UNIX Sockets
 ----------------------------------
 
-zrepl daemon creates various UNIX sockets to allow communicating with it:
+The zrepl daemon needs to open various UNIX sockets in a runtime directory:
 
-* the :ref:`transport-ssh+stdinserver` transport connects to a socket named after ``client_identity`` parameter
-* the ``control`` CLI subcommand connects to a defined control socket
+* a ``control`` socket that the CLI commands use to interact with the daemon
+* the :ref:`transport-ssh+stdinserver` listener opens one socket per configured client, named after ``client_identity`` parameter
 
-There is no further authentication on these sockets.
-Therefore we have to make sure they can only be created and accessed by ``zrepl daemon``.
-In fact, ``zrepl daemon`` will not bind a socket to a path in a directory that is world-accessible.
+There is no authentication on these sockets except the UNIX permissions.
+The zrepl daemon will refuse to bind any of the above sockets in a directory that is world-accessible.
 
-The directories can be configured in the main configuration file, the defaults are provided below:
+The following sections of the ``global`` config shows the default paths.
+The shell script below shows how the default runtime directory can be created.
 
 ::
 
@@ -27,6 +29,12 @@ The directories can be configured in the main configuration file, the defaults a
           sockdir: /var/run/zrepl/stdinserver
 
 
+::
+
+    mkdir -p /var/run/zrepl/stdinserver
+    chmod -R 0700 /var/run/zrepl
+
+
 Durations & Intervals
 ---------------------
 
@@ -36,27 +44,3 @@ Interval & duration fields in job definitions, pruning configurations, etc. must
 
     var durationStringRegex *regexp.Regexp = regexp.MustCompile(`^\s*(\d+)\s*(s|m|h|d|w)\s*$`)
     // s = second, m = minute, h = hour, d = day, w = week (7 days)
-
-Super-Verbose Job Debugging
----------------------------
-
-You have probably landed here because you opened an issue on GitHub and some developer told you to do this...
-So just read the annotated comments ;)
-
-::
-
-    job:
-    - name: ...
-      ...
-     # JOB DEBUGGING OPTIONS
-      # should be equal for all job types, but each job implements the debugging itself
-      debug:
-        conn: # debug the io.ReadWriteCloser connection
-          read_dump: /tmp/connlog_read   # dump results of Read() invocations to this file
-          write_dump: /tmp/connlog_write # dump results of Write() invocations to this file
-        rpc: # debug the RPC protocol implementation
-          log: true # log output from rpc layer to the job log
-
-.. ATTENTION::
-
-    Connection dumps will almost certainly contain your or other's private data. Do not share it in a bug report.

docs/configuration/monitoring.rst

@@ -5,25 +5,33 @@
 Monitoring
 ==========
 
-Monitoring endpoints are configured in the ``global.monitoring`` section of the |mainconfig|.
+Monitoring endpoints are configured in the ``global.monitoring`` section of the config file.
 
 .. _monitoring-prometheus:
 
-Prometheus
-----------
+Prometheus & Grafana
+--------------------
 
 zrepl can expose `Prometheus metrics <https://prometheus.io/docs/instrumenting/exposition_formats/>`_ via HTTP.
-The ``listen`` attribute is a `net.Listen <https://golang.org/pkg/net/#Listen>`_  string for tcp, e.g. ``:9091`` or ``127.0.0.1:9091``.
+The ``listen`` attribute is a `net.Listen <https://golang.org/pkg/net/#Listen>`_  string for tcp, e.g. ``:9811`` or ``127.0.0.1:9811`` (port 9811 was reserved to zrepl `on the official list <https://github.com/prometheus/prometheus/wiki/Default-port-allocations/_compare/43e495dd251ee328ac0d08b58084665b5c0f7a7e...459195059b55b414193ebeb80c5ba463d2606951>`_).
+The ``listen_freebind`` attribute is :ref:`explained here <listen-freebind-explanation>`.
+The Prometheus monitoring job appears in the ``zrepl control`` job list and may be specified **at most once**.
 
-The Prometheues monitoring job appears in the ``zrepl control`` job list and may be specified **at most once**.
-At the time of writing, there is no stability guarantee on the exported metrics.
+zrepl also ships with an importable `Grafana <https://grafana.com>`_ dashboard that consumes the Prometheus metrics:
+see :repomasterlink:`dist/grafana`.
+The dashboard also contains some advice on which metrics are important to monitor.
+
+.. NOTE::
+
+  At the time of writing, there is no stability guarantee on the exported metrics.
 
 ::
 
     global:
       monitoring:
         - type: prometheus
-          listen: ':9091'
+          listen: ':9811'
+          listen_freebind: true # optional, default false
 
 
 

docs/configuration/overview.rst

@@ -0,0 +1,364 @@
+
+Overview & Terminology
+======================
+
+All work zrepl does is performed by the zrepl daemon which is configured in a single YAML configuration file loaded on startup.
+The following paths are searched, in this order:
+
+1. The path specified via the global ``--config`` flag
+2. ``/etc/zrepl/zrepl.yml``
+3. ``/usr/local/etc/zrepl/zrepl.yml``
+
+``zrepl configcheck`` can be used to validate the configuration.
+If the configuration is valid, it will output nothing and exit with code ``0``.
+The error messages vary in quality and usefulness: please report confusing config errors to the tracking :issue:`155`.
+
+Full example configs are available at :ref:`quick-start guides <quickstart-toc>` and :sampleconf:`/`.
+However, copy-pasting examples is no substitute for reading documentation!
+
+Config File Structure
+---------------------
+
+.. code-block:: yaml
+
+   global: ...
+   jobs:
+   - name: backup
+     type: push
+   - ...
+
+A zrepl configuration file is divided in to two main sections: ``global`` and ``jobs``.
+``global`` has sensible defaults. It is covered in :ref:`logging <logging>`, :ref:`monitoring <monitoring>` \& :ref:`miscellaneous <miscellaneous>`.
+
+
+``conf.d``: including config files
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+It is possible to distribute zrepl configurations over multiple YAML configuration
+files. This is achieved by using the `include` key which can only exist in the main
+configuration file.
+
+The list of included paths must point to either individual YAML files or directories.
+If the path points to a directory then all YAML files with a `.yml` extention in the
+directory will be included.
+
+.. code-block:: yaml
+
+    # /etc/zrepl/zrep.yml
+    global: ...
+    include:
+      - ./jobs.d/
+      - /opt/some_job.yml
+
+    # /etc/zrepl/jobs.d/backup.yml
+    jobs:
+    - name: backup
+      type: push
+    - ...
+
+    # /opt/some_job.yml
+    jobs:
+    - name: another_job
+      ...
+    - ...
+
+
+
+The paths are treated as absolute when starting with `/`, otherwise
+as a relative path to the main config file's parent directory.
+
+Job names must be unique across all included configuration files.
+
+.. _job-overview:
+
+Jobs \& How They Work Together
+------------------------------
+
+A *job* is the unit of activity tracked by the zrepl daemon.
+The ``type`` of a job determines its role in a replication setup and in snapshot management.
+Jobs are identified by their ``name``, both in log files and the ``zrepl status`` command.
+
+.. NOTE::
+   The job name is persisted in several places on disk and thus :issue:`cannot be changed easily<327>`.
+
+Replication always happens between a pair of jobs: one **active side** and one **passive side**.
+The active side connects to the passive side using a :ref:`transport <transport>` and starts executing the replication logic.
+The passive side responds to requests from the active side after checking its permissions.
+
+The following table shows how different job types can be combined to achieve **both push and pull mode setups**.
+Note that snapshot-creation denoted by "(snap)" is orthogonal to whether a job is active or passive.
+
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+| Setup name            | active side  | passive side                     | use case                                                                           |
++=======================+==============+==================================+====================================================================================+
+| Push mode             | ``push``     | ``sink``                         | * Laptop backup                                                                    |
+|                       | (snap)       |                                  | * NAS behind NAT to offsite                                                        |
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+| Pull mode             | ``pull``     | ``source``                       | * Central backup-server for many nodes                                             |
+|                       |              | (snap)                           | * Remote server to NAS behind NAT                                                  |
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+| Local replication     | | ``push`` + ``sink`` in one config             | * Backup to :ref:`locally attached disk <quickstart-backup-to-external-disk>`      |
+|                       | | with :ref:`local transport <transport-local>` | * Backup FreeBSD boot pool                                                         |
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+| Snap & prune-only     | ``snap``     | N/A                              | * | Snapshots & pruning but no replication                                         |
+|                       | (snap)       |                                  |   | required                                                                       |
+|                       |              |                                  | * Workaround for :ref:`source-side pruning <prune-workaround-source-side-pruning>` |
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+
+How the Active Side Works
+-------------------------
+
+The active side (:ref:`push <job-push>` and :ref:`pull <job-pull>` job) executes the replication and pruning logic:
+
+1. Wakeup after snapshotting (``push`` job) or pull interval ticker (``pull`` job).
+2. Connect to the passive side and instantiate an RPC client.
+3. Replicate data from the sender to the receiver.
+4. Prune on sender & receiver.
+
+.. TIP::
+  The progress of the active side can be watched live using ``zrepl status``.
+
+.. _overview-passive-side--client-identity:
+
+How the Passive Side Works
+--------------------------
+
+The passive side (:ref:`sink <job-sink>` and :ref:`source <job-source>`) waits for connections from the active side,
+on the :ref:`transport <transport>` specified with ``serve`` in the job configuration.
+The respective transport then perfoms authentication & authorization, resulting in a stable *client identity*.
+The passive side job uses this *client identity* as follows:
+
+   * In ``sink`` jobs, to map requests from different *client identities* to their respective sub-filesystem tree ``root_fs/${client_identity}``.
+   * *In the future, ``source`` might embed the client identity in :ref:`zrepl's ZFS abstraction names <zrepl-zfs-abstractions>`, to support multi-host replication.*
+
+.. TIP::
+   The use of the client identity in the ``sink`` job implies that it must be usable as a ZFS ZFS filesystem name component.
+
+.. _overview-how-replication-works:
+
+How Replication Works
+---------------------
+
+One of the major design goals of the replication module is to avoid any duplication of the nontrivial logic.
+As such, the code works on abstract senders and receiver **endpoints**, where typically one will be implemented by a local program object and the other is an RPC client instance.
+Regardless of push- or pull-style setup, the logic executes on the active side, i.e. in the ``push`` or ``pull`` job.
+
+The following high-level steps take place during replication and can be monitored using ``zrepl status``:
+
+* Plan the replication:
+
+  * Compare sender and receiver filesystem snapshots
+  * Build the **replication plan**
+
+    * Per filesystem, compute a diff between sender and receiver snapshots
+    * Build a list of **replication steps**
+
+      * If possible, use incremental and resumable sends
+      * Otherwise, use full send of most recent snapshot on sender
+
+  * Retry on errors that are likely temporary (i.e. network failures).
+  * Give up on filesystems where a permanent error was received over RPC.
+
+* Execute the plan
+
+  * Perform replication steps in the following order:
+    Among all filesystems with pending replication steps, pick the filesystem whose next replication step's snapshot is the oldest.
+  * Create placeholder filesystems on the receiving side to mirror the dataset paths on the sender to ``root_fs/${client_identity}``.
+  * Acquire send-side *step-holds* on the step's `from` and `to` snapshots.
+  * Perform the replication step.
+  * Move the **replication cursor** bookmark on the sending side (see below).
+  * Move the **last-received-hold** on the receiving side (see below).
+  * Release the send-side step-holds.
+
+The idea behind the execution order of replication steps is that if the sender snapshots all filesystems simultaneously at fixed intervals, the receiver will have all filesystems snapshotted at time ``T1`` before the first snapshot at ``T2 = T1 + $interval`` is replicated.
+
+ZFS Background Knowledge
+^^^^^^^^^^^^^^^^^^^^^^^^
+This section gives some background knowledge about ZFS features that zrepl uses to provide guarantees for a replication filesystem.
+Specifically, zrepl guarantees by default that **incremental replication is always possible and that started replication steps can always be resumed if they are interrupted.**
+
+**ZFS Send Modes & Bookmarks**
+ZFS supports full sends (``zfs send fs@to``) and incremental sends (``zfs send -i @from fs@to``).
+Full sends are used to create a new filesystem on the receiver with the send-side state of ``fs@to``.
+Incremental sends only transfer the delta between ``@from`` and ``@to``.
+Incremental sends require that ``@from`` be present on the receiving side when receiving the incremental stream.
+Incremental sends can also use a ZFS bookmark as *from* on the sending side (``zfs send -i #bm_from fs@to``), where ``#bm_from`` was created using ``zfs bookmark fs@from fs#bm_from``.
+The receiving side must always have the actual snapshot ``@from``, regardless of whether the sending side uses ``@from`` or a bookmark of it.
+
+.. _zfs-background-knowledge-plain-vs-raw-sends:
+
+**Plain and raw sends**
+By default, ``zfs send`` sends the most generic, backwards-compatible data stream format (so-called 'plain send').
+If the sent uses newer features, e.g. compression or encryption, ``zfs send`` has to un-do these operations on the fly to produce the plain send stream.
+If the receiver uses newer features (e.g. compression or encryption inherited from the parent FS), it applies the necessary transformations again on the fly during ``zfs recv``.
+
+Flags such as ``-e``, ``-c`` and ``-L``  tell ZFS to produce a send stream that is closer to how the data is stored on disk.
+Sending with those flags removes computational overhead from sender and receiver.
+However, the receiver will not apply certain transformations, e.g., it will not compress with the receive-side ``compression`` algorithm.
+
+The ``-w`` (``--raw``) flag produces a send stream that is as *raw* as possible.
+For unencrypted datasets, its current effect is the same as ``-Lce``.
+
+Encrypted datasets can only be sent plain (unencrypted) or raw (encrypted) using the ``-w`` flag.
+
+**Resumable Send & Recv**
+The ``-s`` flag for ``zfs recv`` tells zfs to save the partially received send stream in case it is interrupted.
+To resume the replication, the receiving side filesystem's ``receive_resume_token`` must be passed to a new ``zfs send -t <value> | zfs recv`` command.
+A full send can only be resumed if ``@to`` still exists.
+An incremental send can only be resumed if ``@to`` still exists *and* either ``@from`` still exists *or* a bookmark ``#fbm`` of ``@from`` still exists.
+
+**ZFS Holds**
+ZFS holds prevent a snapshot from being deleted through ``zfs destroy``, letting the destroy fail with a ``datset is busy`` error.
+Holds are created and referred to by a *tag*. They can be thought of as a named, persistent lock on the snapshot.
+
+
+.. _zrepl-zfs-abstractions:
+
+ZFS Abstractions Managed By zrepl
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+With the background knowledge from the previous paragraph, we now summarize the different on-disk ZFS objects that zrepl manages to provide its functionality.
+
+.. _replication-placeholder-property:
+
+**Placeholder filesystems** on the receiving side are regular ZFS filesystems with the ZFS property ``zrepl:placeholder=on``.
+Placeholders allow the receiving side to mirror the sender's ZFS dataset hierarchy without replicating every filesystem at every intermediary dataset path component.
+Consider the following example: ``S/H/J`` shall be replicated to ``R/sink/job/S/H/J``, but neither ``S/H`` nor ``S`` shall be replicated.
+ZFS requires the existence of ``R/sink/job/S`` and ``R/sink/job/S/H`` in order to receive into ``R/sink/job/S/H/J``.
+Thus, zrepl creates the parent filesystems as placeholders on the receiving side.
+If at some point ``S/H`` and ``S`` shall be replicated, the receiving side invalidates the placeholder flag automatically.
+The ``zrepl test placeholder`` command can be used to check whether a filesystem is a placeholder.
+
+.. _replication-cursor-and-last-received-hold:
+
+The **replication cursor** bookmark and **last-received-hold** are managed by zrepl to ensure that future replications can always be done incrementally.
+The replication cursor is a send-side bookmark of the most recent successfully replicated snapshot,
+and the last-received-hold is a hold of that snapshot on the receiving side.
+Both are moved atomically after the receiving side has confirmed that a replication step is complete.
+
+The replication cursor has the format ``#zrepl_CUSOR_G_<GUID>_J_<JOBNAME>``.
+The last-received-hold tag has the format ``zrepl_last_received_J_<JOBNAME>``.
+Encoding the job name in the names ensures that multiple sending jobs can replicate the same filesystem to different receivers without interference.
+
+.. _tentative-replication-cursor-bookmarks:
+
+**Tentative replication cursor bookmarks** are short-lived bookmarks that protect the atomic moving-forward of the replication cursor and last-received-hold (see :issue:`this issue <340>`).
+They are only necessary if step holds are not used as per the :ref:`replication.protection <replication-option-protection>` setting.
+The tentative replication cursor has the format ``#zrepl_CUSORTENTATIVE_G_<GUID>_J_<JOBNAME>``.
+The ``zrepl zfs-abstraction list`` command provides a listing of all bookmarks and holds managed by zrepl.
+
+.. _step-holds:
+
+**Step holds** are zfs holds managed by zrepl to ensure that a replication step can always be resumed if it is interrupted, e.g., due to network outage.
+zrepl creates step holds before it attempts a replication step and releases them after the receiver confirms that the replication step is complete.
+For an initial replication ``full @initial_snap``, zrepl puts a zfs hold on ``@initial_snap``.
+For an incremental send ``@from -> @to``, zrepl puts a zfs hold on both ``@from`` and ``@to``.
+Note that ``@from`` is not strictly necessary for resumability -- a bookmark on the sending side would be sufficient --, but size-estimation in currently used OpenZFS versions only works if ``@from`` is a snapshot.
+The hold tag has the format ``zrepl_STEP_J_<JOBNAME>``.
+A job only ever has one active send per filesystem.
+Thus, there are never more than two step holds for a given pair of ``(job,filesystem)``.
+
+**Step bookmarks** are zrepl's equivalent for holds on bookmarks (ZFS does not support putting holds on bookmarks).
+They are intended for a situation where a replication step uses a bookmark ``#bm`` as incremental ``from`` where ``#bm`` is not managed by zrepl.
+To ensure resumability, zrepl copies ``#bm`` to step bookmark ``#zrepl_STEP_G_<GUID>_J_<JOBNAME>``.
+If the replication is interrupted and ``#bm`` is deleted by the user, the step bookmark remains as an incremental source for the resumable send.
+Note that zrepl does not yet support creating step bookmarks because the `corresponding ZFS feature for copying bookmarks <https://github.com/openzfs/zfs/pull/9571>`_ is not yet widely available .
+Subscribe to zrepl :issue:`326` for details.
+
+The ``zrepl zfs-abstraction list`` command provides a listing of all bookmarks and holds managed by zrepl.
+
+.. NOTE::
+
+    More details can be found in the design document :repomasterlink:`replication/design.md`.
+
+
+Caveats With Complex Setups (More Than 2 Jobs or Machines)
+----------------------------------------------------------
+
+Most users are served well with a single sender and a single receiver job.
+This section documents considerations for more complex setups.
+
+.. ATTENTION::
+
+   Before you continue, make sure you have a working understanding of :ref:`how zrepl works <overview-how-replication-works>`
+   and :ref:`what zrepl does to ensure <zrepl-zfs-abstractions>` that replication between sender and receiver is always
+   possible without conflicts.
+   This will help you understand why certain kinds of multi-machine setups do not (yet) work.
+
+.. NOTE::
+
+   If you can't find your desired configuration, have questions or would like to see improvements to multi-job setups, please `open an issue on GitHub <https://github.com/zrepl/zrepl/issues/new>`_.
+
+Multiple Jobs on One Machine
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+As a general rule, multiple jobs configured on one machine **must operate on disjoint sets of filesystems**.
+Otherwise, concurrently running jobs might interfere when operating on the same filesystem.
+
+On your setup, ensure that
+
+* all ``filesystems`` filter specifications are disjoint
+* no ``root_fs`` is a prefix or equal to another ``root_fs``
+
+  * For ``sink`` jobs, consider all possible ``root_fs/${client_identity}``.
+
+* no ``filesystems`` filter matches any ``root_fs``
+
+**Exceptions to the rule**:
+
+* A ``snap`` and ``push`` job on the same machine can match the same ``filesystems``.
+  To avoid interference, only one of the jobs should be pruning snapshots on the sender, the other one should keep all snapshots.
+  Since the jobs won't coordinate, errors in the log are to be expected, but :ref:`zrepl's ZFS abstractions <zrepl-zfs-abstractions>` ensure that ``push`` and ``sink`` can always replicate incrementally.
+  This scenario is detailed in one of the :ref:`quick-start guides <quickstart-backup-to-external-disk>`.
+
+
+Two Or More Machines
+^^^^^^^^^^^^^^^^^^^^
+
+This section might be relevant to users who wish to *fan-in* (N machines replicate to 1) or *fan-out* (replicate 1 machine to N machines).
+
+**Working setups**:
+
+* **Fan-in: N servers replicated to one receiver, disjoint dataset trees.**
+
+  * This is the common use case of a centralized backup server.
+
+  * Implementation:
+
+    * N ``push`` jobs (one per sender server), 1 ``sink`` (as long as the different push jobs have a different :ref:`client identity <overview-passive-side--client-identity>`)
+    * N ``source`` jobs (one per sender server), N ``pull`` on the receiver server (unique names, disjoint  ``root_fs``)
+
+  * The ``sink`` job automatically constrains each client to a disjoint sub-tree of the sink-side dataset hierarchy ``${root_fs}/${client_identity}``.
+    Therefore, the different clients cannot interfere.
+
+  * The ``pull`` job only pulls from one host, so it's up to the zrepl user to ensure that the different ``pull`` jobs don't interfere.
+
+.. _fan-out-replication:
+
+* **Fan-out: 1 server replicated to N receivers**
+
+  * Can be implemented either in a pull or push fashion.
+
+    * **pull setup**: 1 ``pull`` job on each receiver server, each with a corresponding **unique** ``source`` job on the sender server.
+    * **push setup**: 1 ``sink`` job on each receiver server, each with a corresponding **unique** ``push`` job on the sender server.
+
+  * It is critical that we have one sending-side job (``source``, ``push``) per receiver.
+    The reason is that :ref:`zrepl's ZFS abstractions <zrepl-zfs-abstractions>` (``zrepl zfs-abstraction list``) include the name of the ``source``/``push`` job, but not the receive-side job name or client identity (see :issue:`380`).
+    As a counter-example, suppose we used multiple ``pull`` jobs with only one ``source`` job.
+    All ``pull`` jobs would share the same :ref:`replication cursor bookmark <replication-cursor-and-last-received-hold>` and trip over each other, breaking incremental replication guarantees quickly.
+    The anlogous problem exists for 1 ``push`` to N ``sink`` jobs.
+
+  * The ``filesystems`` matched by the sending side jobs (``source``, ``push``) need not necessarily be disjoint.
+    For this to work, we need to avoid interference between snapshotting and pruning of the different sending jobs.
+    The solution is to centralize sender-side snapshot management in a separate ``snap`` job.
+    Snapshotting in the ``source``/``push`` job should then be disabled (``type: manual``).
+    And sender-side pruning (``keep_sender``) needs to be disabled in the active side (``pull`` / ``push``), since that'll be done by the ``snap job``.
+
+  * **Restore limitations**: when restoring from one of the ``pull`` targets (e.g., using ``zfs send -R``), the replication cursor bookmarks don't exist on the restored system.
+    This can break incremental replication to all other receive-sides after restore.
+
+  * See :ref:`the fan-out replication quick-start guide <quickstart-fan-out-replication>` for an example of this setup.
+
+
+**Setups that do not work**:
+
+* N ``pull`` identities, 1 ``source`` job. Tracking :issue:`380`.
+

docs/configuration/preface.rst

@@ -1,39 +0,0 @@
-
-.. _configuration_preface:
-
-=======
-Preface
-=======
-
------------------------
-Configuration File Path
------------------------
-
-zrepl searches for its main configuration file in the following locations (in that order):
-
-* If set, the location specified via the global ``--config`` flag
-* ``/etc/zrepl/zrepl.yml``
-* ``/usr/local/etc/zrepl/zrepl.yml``
-
-The examples in the :ref:`tutorial` or the :sampleconf:`/` directory should provide a good starting point.
-
--------------------
-Runtime Directories
--------------------
-
-zrepl requires runtime directories for various UNIX sockets --- they are documented in the :ref:`config file<conf-runtime-directories>`.
-Your package maintainer / init script should take care of creating them.
-Alternatively, for default settings, the following should to the trick.
-
-::
-
-    mkdir -p /var/run/zrepl/stdinserver
-    chmod -R 0700 /var/run/zrepl
-
-
-----------
-Validating
-----------
-
-The config can be validated using the ``zrepl configcheck`` subcommand.
-

docs/configuration/prune.rst

@@ -4,16 +4,18 @@ Pruning Policies
 ================
 
 In zrepl, *pruning* means *destroying snapshots*.
-Pruning must happen on both sides of a replication or the systems would inevitable run out of disk space at some point.
+Pruning must happen on both sides of a replication or the systems would inevitably run out of disk space at some point.
 
 Typically, the requirements to temporal resolution and maximum retention time differ per side.
 For example, when using zrepl to back up a busy database server, you will want high temporal resolution (snapshots every 10 min) for the last 24h in case of administrative disasters, but cannot afford to store them for much longer because you might have high turnover volume in the database.
 On the receiving side, you may have more disk space available, or need to comply with other backup retention policies.
 
-zrepl uses a set of  **keep rules** to determine which snapshots shall be kept per filesystem.
+zrepl uses a set of  **keep rules** per sending and receiving side to determine which snapshots shall be kept per filesystem.
 **A snapshot that is not kept by any rule is destroyed.**
 The keep rules are **evaluated on the active side** (:ref:`push <job-push>` or :ref:`pull job <job-pull>`) of the replication setup, for both active and passive side, after replication completed or was determined to have failed permanently.
 
+
+
 Example Configuration:
 
 ::
@@ -44,23 +46,18 @@ Example Configuration:
              grid: 1x1h(keep=all) | 24x1h | 35x1d | 6x30d
              regex: "^zrepl_.*"
            # manually created snapshots will be kept forever on receiver
+           - type: regex
+             regex: "^manual_.*"
 
 .. DANGER::
+
     You might have **existing snapshots** of filesystems affected by pruning which you want to keep, i.e. not be destroyed by zrepl.
     Make sure to actually add the necessary ``regex`` keep rules on both sides, like with ``manual`` in the example above.
 
-.. ATTENTION::
-
-    It is currently not possible to define pruning on a source job.
-    The source job creates snapshots, which means that extended replication downtime will fill up the source's zpool with snapshots, since pruning is directed by the corresponding active side (pull job).
-    If this is a potential risk for you, consider using :ref:`push mode <job-push>`.
-
-
 .. _prune-keep-not-replicated:
 
 Policy ``not_replicated``
 -------------------------
-
 ::
 
    jobs:
@@ -71,8 +68,17 @@ Policy ``not_replicated``
      ...
 
 ``not_replicated`` keeps all snapshots that have not been replicated to the receiving side.
-It only makes sense to specify this rule on a sender (source or push job).
-The state required to evaluate this rule is stored in the :ref:`replication cursor bookmark <replication-cursor-bookmark>` on the sending side.
+It only makes sense to specify this rule for the ``keep_sender``.
+The reason is that, by definition, all snapshots on the receiver have already been replicated to there from the sender.
+To determine whether a sender-side snapshot has already been replicated, zrepl uses the :ref:`replication cursor bookmark <replication-cursor-and-last-received-hold>` which corresponds to the most recent successfully replicated snapshot.
+
+.. ATTENTION::
+
+    If you use ``not_replicated`` in your pruning rules, make sure to :ref:`monitor <monitoring>` replication.
+    If your replication gets stuck then ``not_replicated`` causes snapshots to pile uip on the sender.
+    ZFS and especially the ``zfs`` management command are known to degrade in performance with a lot of snapshots.
+    Such degradation impacts zrepl, any other scripts, and human ability to manage your zpool.
+
 
 .. _prune-keep-retention-grid:
 
@@ -88,35 +94,91 @@ Policy ``grid``
         - type: grid
           regex: "^zrepl_.*"
           grid: 1x1h(keep=all) | 24x1h | 35x1d | 6x30d
-                │                │
-                └─ one hour interval
-                                 │
-                                 └─ 24 adjacent one-hour intervals
+                │                │               │
+                └─ 1 repetition of a one-hour interval with keep=all
+                                 │               │
+                                 └─ 24 repetitions of a one-hour interval with keep=1
+                                                 │
+                                                 └─ 6 repetitions of a 30-day interval with keep=1
       ...
 
-The retention grid can be thought of as a time-based sieve:
-The ``grid`` field specifies a list of adjacent time intervals:
-the left edge of the leftmost (first) interval is the ``creation`` date of the youngest snapshot.
-All intervals to its right describe time intervals further in the past.
-
-Each interval carries a maximum number of snapshots to keep.
-It is specified via ``(keep=N)``, where ``N`` is either ``all`` (all snapshots are kept) or a positive integer.
-The default value is **keep=1**.
+The retention grid can be thought of as a time-based sieve that thins out snapshots as they get older.
 
+The ``grid`` field specifies a list of adjacent time intervals.
+Each interval is a bucket with a maximum capacity of ``keep`` snapshots.
 The following procedure happens during pruning:
 
 #. The list of snapshots is filtered by the regular expression in ``regex``.
-   Only snapshots names that match the regex are considered for this rule, all others are not affected.
-#. The filtered list of snapshots is sorted by ``creation``
-#. The left edge of the first interval is aligned to the ``creation`` date of the youngest snapshot
-#. A list of buckets is created, one for each interval
-#. The list of snapshots is split up into the buckets.
-#. For each bucket
+   Only snapshots names that match the regex are considered for this rule, all others will be pruned unless another rule keeps them.
+#. The snapshots that match ``regex`` are placed onto a time axis according to their ``creation`` date.
+   The youngest snapshot is on the left, the oldest on the right.
+#. The first buckets are placed "under" that axis so that the ``grid`` spec's first bucket's left edge aligns with youngest snapshot.
+#. All subsequent buckets are placed adjacent to their predecessor bucket.
+#. Now each snapshot on the axis either falls into one bucket or it is older than our rightmost bucket.
+   Buckets are left-inclusive and right-exclusive which means that a snapshot on the edge of bucket will always 'fall into the right one'.
+#. Snapshots older than the rightmost bucket are **not kept** by the grid specification.
+#. For each bucket, we only keep the ``keep`` oldest snapshots.
 
-   #. the contained snapshot list is sorted by creation.
-   #. snapshots from the list, oldest first, are destroyed until the specified ``keep`` count is reached.
-   #. all remaining snapshots on the list are kept.
+The syntax to describe the bucket list is as follows:
 
+::
+
+     Repeat x Duration (keep=all)
+
+* The **duration** specifies the length of the interval.
+* The **keep** count specifies the number of snapshots that fit into the bucket.
+  It can be either a positive integer or ``all`` (all snapshots are kept).
+* The **repeat** count repeats the bucket definition for the specified number of times.
+
+**Example**:
+
+::
+
+   Assume the following grid specification:
+
+      grid: 1x1h(keep=all) | 2x2h | 1x3h
+
+   This grid specification produces the following constellation of buckets:
+
+   0h        1h        2h        3h        4h        5h        6h        7h        8h        9h
+   |         |         |         |         |         |         |         |         |         |
+   |-Bucket1-|-----Bucket2-------|------Bucket3------|-----------Bucket4-----------|
+   | keep=all|      keep=1       |       keep=1      |            keep=1           |
+
+
+
+   Now assume that we have a set of snapshots @a, @b, ..., @D.
+   Snapshot @a is the most recent snapshot.
+   Snapshot @D is the oldest snapshot, it is almost 9 hours older than snapshot @a.
+   We place the snapshots on the same timeline as the buckets:
+
+
+   0h        1h        2h        3h        4h        5h        6h        7h        8h        9h
+   |         |         |         |         |         |         |         |         |         |
+   |-Bucket1-|-----Bucket2-------|------Bucket3------|-----------Bucket4-----------|
+   | keep=all|      keep=1       |       keep=1      |            keep=1           |
+   |         |                   |                   |                             |
+   | a  b  c | d  e  f  g  h  i  j  k  l  m  n  o  p |q  r  s  t  u  v  w  x  y  z |A  B  C  D
+
+   We obtain the following mapping of snapshots to buckets:
+
+   Bucket1:   a,b,c
+   Bucket2:   d,e,f,g,h,i
+   Bucket3:   j,k,l,m,n,o,p
+   Bucket4:   q,r,s,t,u,v,w,x,y,z
+   No bucket: A,B,C,D
+
+   For each bucket, we now prune snapshots until it only contains `keep` snapshots.
+   Newer snapshots are destroyed first.
+   Snapshots that do not fall into a bucket are always destroyed.
+
+   Result after pruning:
+
+   0h        1h        2h        3h        4h        5h        6h        7h        8h        9h
+   |         |         |         |         |         |         |         |         |         |
+   |-Bucket1-|-----Bucket2-------|------Bucket3------|-----------Bucket4-----------|
+   |         |                   |                   |                             |
+   | a  b  c |                i  |                 p |                           z |
 
 .. _prune-keep-last-n:
 
@@ -131,9 +193,11 @@ Policy ``last_n``
          keep_receiver:
          - type: last_n
            count: 10
+           regex: ^zrepl_.*$ # optional
      ...
 
-``last_n`` keeps the last ``count`` snapshots (last = youngest = most recent creation date).
+``last_n`` filters the snapshot list by ``regex``, then keeps the last ``count`` snapshots in that list (last = youngest = most recent creation date)
+All snapshots that don't match ``regex`` or exceed ``count`` in the filtered list are destroyed unless matched by other rules.
 
 .. _prune-keep-regex:
 
@@ -146,12 +210,75 @@ Policy ``regex``
      - type: push
        pruning:
          keep_receiver:
+         # keep all snapshots with prefix zrepl_ or manual_
          - type: regex
            regex: "^(zrepl|manual)_.*"
+
+     - type: push
+       snapshotting:
+         prefix: zrepl_
+       pruning:
+         keep_sender:
+         # keep all snapshots that were not created by zrepl
+         - type: regex
+           negate: true
+           regex: "^zrepl_.*"
+
+``regex`` keeps all snapshots whose names are matched by the regular expression in ``regex``.
+Like all other regular expression fields in prune policies, zrepl uses Go's `regexp.Regexp <https://golang.org/pkg/regexp/#Compile>`_ Perl-compatible regular expressions (`Syntax <https://golang.org/pkg/regexp/syntax>`_).
+The optional `negate` boolean field inverts the semantics: Use it if you want to keep all snapshots that *do not* match the given regex.
+
+.. _prune-workaround-source-side-pruning:
+
+Source-side snapshot pruning
+----------------------------
+
+A :ref:`source jobs<job-source>` takes snapshots on the system it runs on.
+The corresponding :ref:`pull job <job-pull>` on the replication target connects to the source job and replicates the snapshots.
+Afterwards, the pull job coordinates pruning on both sender (the source job side) and receiver (the pull job side).
+
+There is no built-in way to define and execute pruning on the source side independently of the pull side.
+The source job will continue taking snapshots which will not be pruned until the pull side connects.
+This means that **extended replication downtime will fill up the source's zpool with snapshots**.
+
+If the above is a conceivable situation for you, consider using :ref:`push mode <job-push>`, where pruning happens on the same side where snapshots are taken.
+
+Workaround using ``snap`` job
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As a workaround (see GitHub :issue:`102` for development progress), a pruning-only :ref:`snap job <job-snap>` can be defined on the source side:
+The snap job is in charge of snapshot creation & destruction, whereas the source job's role is reduced to just serving snapshots.
+However, since, jobs are run independently, it is possible that the snap job will prune snapshots that are queued for replication / destruction by the remote pull job that connects to the source job.
+Symptoms of such race conditions are spurious replication and destroy errors.
+
+Example configuration:
+
+::
+
+  # source side
+  jobs:
+  - type: snap
+    snapshotting:
+      type: periodic
+    pruning:
+      keep:
+        # source side pruning rules go here
     ...
 
-``regex`` keeps all snapshots whose names are matched by the regular expressionin ``regex``.
-Like all other regular expression fields in prune policies, zrepl uses Go's `regexp.Regexp <https://golang.org/pkg/regexp/#Compile>`_ Perl-compatible regular expressions (`Syntax <https://golang.org/pkg/regexp/syntax>`_).
-
-
+  - type: source
+    snapshotting:
+      type: manual
+    root_fs: ...
 
+  # pull side
+  jobs:
+  - type: pull
+    pruning:
+      keep_sender:
+        # let the source-side snap job do the pruning
+        - type: regex
+          regex: ".*"
+        ...
+      keep_receiver:
+        # feel free to prune on the pull side as desired
+        ...

docs/configuration/replication.rst

@@ -0,0 +1,75 @@
+.. include:: ../global.rst.inc
+
+.. _replication-options:
+
+Replication Options
+===================
+
+
+::
+   
+   jobs:
+   - type: push
+     filesystems: ...
+     replication:
+       protection:
+         initial:     guarantee_resumability # guarantee_{resumability,incremental,nothing}
+         incremental: guarantee_resumability # guarantee_{resumability,incremental,nothing}
+       concurrency:
+         size_estimates: 4
+         steps: 1
+
+     ...
+
+.. _replication-option-protection:
+
+``protection`` option
+--------------------------
+
+The ``protection`` variable controls the degree to which a replicated filesystem is protected from getting out of sync through a zrepl pruner or external tools that destroy snapshots.
+zrepl can guarantee :ref:`resumability <step-holds>` or just :ref:`incremental replication <replication-cursor-and-last-received-hold>`.
+
+``guarantee_resumability`` is the **default** value and guarantees that a replication step is always resumable and that incremental replication will always be possible.
+The implementation uses replication cursors, last-received-hold and step holds.
+
+``guarantee_incremental`` only guarantees that incremental replication will always be possible.
+If a step ``from -> to`` is interrupted and its `to` snapshot is destroyed, zrepl will remove the half-received ``to``'s resume state and start a new step ``from -> to2``.
+The implementation uses replication cursors, tentative replication cursors and last-received-hold.
+
+``guarantee_nothing`` does not make any guarantees with regards to keeping sending and receiving side in sync.
+No bookmarks or holds are created to protect sender and receiver from diverging.
+
+**Tradeoffs**
+
+Using ``guarantee_incremental`` instead of ``guarantee_resumability`` obviously removes the resumability guarantee.
+This means that replication progress is no longer monotonic which might lead to a replication setup that never makes progress if mid-step interruptions are too frequent (e.g. frequent network outages).
+However, the advantage and :issue:`reason for existence <288>` of the ``incremental`` mode is that it allows the pruner to delete snapshots of interrupted replication steps
+which is useful if replication happens so rarely (or fails so frequently) that the amount of disk space exclusively referenced by the step's snapshots becomes intolerable.
+
+.. NOTE::
+
+   When changing this flag, obsoleted zrepl-managed bookmarks and holds will be destroyed on the next replication step that is attempted for each filesystem.
+
+
+.. _replication-option-concurrency:
+
+``concurrency`` option
+----------------------
+
+The ``concurrency`` options control the maximum amount of concurrency during replication.
+The default values allow some concurrency during size estimation but no parallelism for the actual replication.
+
+* ``concurrency.steps`` (default = 1) controls the maximum number of concurrently executed :ref:`replication steps <overview-how-replication-works>`.
+  The planning step for each file system is counted as a single step.
+* ``concurrency.size_estimates`` (default = 4) controls the maximum number of concurrent step size estimations done by the job.
+
+Note that initial replication cannot start replicating child filesystems before the parent filesystem's initial replication step has completed.
+
+Some notes on tuning these values:
+
+* Disk: Size estimation is less I/O intensive than step execution because it does not need to access the data blocks.
+* CPU: Size estimation is usually a dense CPU burst whereas step execution CPU utilization is stretched out over time because of disk IO.
+  Faster disks, sending a compressed dataset in :ref:`plain mode <zfs-background-knowledge-plain-vs-raw-sends>` and the zrepl transport mode all contribute to higher CPU requirements.
+* Network bandwidth: Size estimation does not consume meaningful amounts of bandwidth, step execution does.
+* :ref:`zrepl ZFS abstractions <zrepl-zfs-abstractions>`: for each replication step zrepl needs to update its ZFS abstractions through the ``zfs`` command which often waits multiple seconds for the zpool to sync.
+  Thus, if the actual send & recv time of a step is small compared to the time spent on zrepl ZFS abstractions then increasing step execution concurrency will result in a lower overall turnaround time.

docs/configuration/sendrecvoptions.rst

@@ -0,0 +1,287 @@
+.. include:: ../global.rst.inc
+
+
+Send & Recv Options
+===================
+
+.. _job-send-options:
+
+Send Options
+~~~~~~~~~~~~
+
+:ref:`Source<job-source>` and :ref:`push<job-push>` jobs have an optional ``send`` configuration section.
+
+::
+
+   jobs:
+   - type: push
+     filesystems: ...
+     send:
+       # flags from the table below go here
+     ...
+
+The following table specifies the list of (boolean) options.
+Flags with an entry in the ``zfs send`` column map directly to the zfs send CLI flags.
+zrepl does not perform feature checks for these flags.
+If you enable a flag that is not supported by the installed version of ZFS, the zfs error will show up at runtime in the logs and zrepl status.
+See the `upstream man page <https://openzfs.github.io/openzfs-docs/man/8/zfs-send.8.html>`_ (``man zfs-send``) for their semantics.
+
+.. list-table::
+    :widths: 20 10 70
+    :header-rows: 1
+
+    * - ``send.``
+      - ``zfs send``
+      - Comment
+    * - ``encrypted``
+      -
+      - Specific to zrepl, :ref:`see below <job-send-options-encrypted>`.
+    * - ``bandwidth_limit``
+      -
+      - Specific to zrepl, :ref:`see below <job-send-recv-options--bandwidth-limit>`.
+    * - ``raw``
+      - ``-w``
+      - Use ``encrypted`` to only allow encrypted sends. Mixed sends are not supported.
+    * - ``send_properties``
+      - ``-p``
+      - **Be careful**, read the :ref:`note on property replication below <job-note-property-replication>`.
+    * - ``backup_properties``
+      - ``-b``
+      - **Be careful**, read the :ref:`note on property replication below <job-note-property-replication>`.
+    * - ``large_blocks``
+      - ``-L``
+      - **Potential data loss on OpenZFS < 2.0**, see :ref:`warning below <job-send-options-large-blocks>`.
+    * - ``compressed``
+      - ``-c``
+      -
+    * - ``embedded_data``
+      - ``-e``
+      -
+    * - ``saved``
+      - ``-S``
+      -
+
+.. _job-send-options-encrypted:
+
+``encrypted``
+-------------
+
+The ``encrypted`` option controls whether the matched filesystems are sent as `OpenZFS native encryption <http://open-zfs.org/wiki/ZFS-Native_Encryption>`_ raw sends.
+More specifically, if ``encrypted=true``, zrepl
+
+* checks for any of the filesystems matched by ``filesystems`` whether the ZFS ``encryption`` property indicates that the filesystem is actually encrypted with ZFS native encryption and
+* invokes the ``zfs send`` subcommand with the ``-w`` option (raw sends) and
+* expects the receiving side to support OpenZFS native encryption (recv will fail otherwise)
+
+Filesystems matched by ``filesystems`` that are not encrypted are not sent and will cause error log messages.
+
+If ``encrypted=false``, zrepl expects that filesystems matching ``filesystems`` are not encrypted or have loaded encryption keys.
+
+.. NOTE::
+
+   Use ``encrypted`` instead of ``raw`` to make your intent clear that zrepl must only replicate filesystems that are actually encrypted by OpenZFS native encryption.
+   It is meant as a safeguard to prevent unintended sends of unencrypted filesystems in raw mode.
+
+.. _job-send-options-properties:
+
+``send_properties``
+-------------------
+Sends the dataset properties along with snapshots.
+Please be careful with this option and read the :ref:`note on property replication below <job-note-property-replication>`.
+
+.. _job-send-options-backup-properties:
+
+``backup_properties``
+---------------------
+
+When properties are modified on a filesystem that was received from a send stream with ``send.properties=true``, ZFS archives the original received value internally.
+This also applies to :ref:`inheriting or overriding properties during zfs receive <job-recv-options--inherit-and-override>`.
+
+When sending those received filesystems another hop, the ``backup_properties`` flag instructs ZFS to send the original property values rather than the current locally set values.
+
+This is useful for replicating properties across multiple levels of backup machines.
+**Example:**
+Suppose we want to flow snapshots from Machine A to B, then from B to C.
+A will enable the :ref:`properties send option <job-send-options-properties>`.
+B will want to override :ref:`critical properties such as mountpoint or canmount <job-note-property-replication>`.
+But the job that replicates from B to C should be sending the original property values received from A.
+Thus, B sets the ``backup_properties`` option.
+
+Please be careful with this option and read the :ref:`note on property replication below <job-note-property-replication>`.
+
+.. _job-send-options-large-blocks:
+
+``large_blocks``
+----------------
+
+This flag should not be changed after initial replication.
+Prior to `OpenZFS commit 7bcb7f08 <https://github.com/openzfs/zfs/pull/10383/files#diff-4c1e47568f46fb63546e984943b09a3e6b051e2242649523f7835bbdfe2a9110R337-R342>`_
+it was possible to change this setting which resulted in **data loss on the receiver**.
+The commit in question is included in OpenZFS 2.0 and works around the problem by prohibiting receives of incremental streams with a flipped setting.
+
+.. WARNING::
+
+   This bug has **not been fixed in the OpenZFS 0.8 releases** which means that changing this flag after initial replication might cause **data loss** on the receiver.
+
+.. _job-recv-options:
+
+Recv Options
+~~~~~~~~~~~~
+
+:ref:`Sink<job-sink>` and :ref:`pull<job-pull>` jobs have an optional ``recv`` configuration section:
+
+::
+
+   jobs:
+   - type: pull
+     recv:
+       properties:
+         inherit:
+           - "mountpoint"
+         override: {
+           "org.openzfs.systemd:ignore": "on"
+         }
+       bandwidth_limit: ...
+       placeholder:
+         encryption: unspecified | off | inherit
+     ...
+
+Jump to
+:ref:`properties <job-recv-options--inherit-and-override>` ,
+:ref:`bandwidth_limit <job-send-recv-options--bandwidth-limit>` , and
+:ref:`placeholder <job-recv-options--placeholder>`.
+
+.. _job-recv-options--inherit-and-override:
+
+``properties``
+--------------
+
+``override`` maps directly to the `zfs recv -o flag <https://openzfs.github.io/openzfs-docs/man/8/zfs-recv.8.html>`_.
+Property name-value pairs specified in this map will apply to all received filesystems, regardless of whether the send stream contains properties or not.
+
+``inherit`` maps directly to the `zfs recv -x flag <https://openzfs.github.io/openzfs-docs/man/8/zfs-recv.8.html>`_.
+Property names specified in this list will be inherited from the receiving side's parent filesystem (e.g. ``root_fs``).
+
+With both options, the sending side's property value is still stored on the receiver, but the local override or inherit is the one that takes effect.
+You can send the original properties from the first receiver to another receiver using :ref:`send.backup_properties<job-send-options-backup-properties>`.
+
+
+.. _job-note-property-replication:
+
+A Note on Property Replication
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If a send stream contains properties, as per ``send.send_properties`` or ``send.backup_properties``,
+the default ZFS behavior is to use those properties on the receiving side, verbatim.
+
+In many use cases for zrepl, this can have devastating consequences.
+For example, when backing up a filesystem that has ``mountpoint=/`` to a storage server,
+that storage server's root filesystem will be shadowed by the received file system on some platforms.
+Also, many scripts and tools use ZFS user properties for configuration and do not check the property source (``local`` vs. ``received``).
+If they are installed on the receiving side as well as the sending side, property replication could have unintended effects.
+
+**zrepl currently does not provide any automatic safe-guards for property replication:**
+
+* Make sure to read the entire man page on zfs recv (`man zfs recv <https://openzfs.github.io/openzfs-docs/man/8/zfs-recv.8.html>`_) before enabling this feature.
+* Use ``recv.properties.override`` whenever possible, e.g. for ``mountpoint=none`` or ``canmount=off``.
+* Use ``recv.properties.inherit`` if that makes more sense to you.
+
+Below is an **non-exhaustive list of problematic properties**.
+Please open a pull request if you find a property that is missing from this list.
+(Both with regards to core ZFS tools and other software in the broader ecosystem.)
+
+Mount behaviour
+---------------
+
+* ``mountpoint``
+* ``canmount``
+* ``overlay``
+
+Note: Before `OpenZFS 2.0.5 <https://github.com/openzfs/zfs/issues/11416>`_, inheriting or overriding the ``mountpoint`` property on ZVOLs fails in ``zfs recv``.
+If you are on such an older version, consider creating separate zrepl jobs for your ZVOL and filesystem datasets.
+
+Systemd
+-------
+
+With systemd, you should also consider the properties processed by the `zfs-mount-generator <https://manpages.debian.org/buster-backports/zfsutils-linux/zfs-mount-generator.8.en.html>`_ .
+
+Most notably:
+
+* ``org.openzfs.systemd:ignore``
+* ``org.openzfs.systemd:wanted-by``
+* ``org.openzfs.systemd:required-by``
+
+Encryption
+----------
+
+If the sender filesystems are encrypted but the sender does :ref:`plain sends <zfs-background-knowledge-plain-vs-raw-sends>`
+and property replication is enabled, the receiver must :ref:`inherit the following properties<job-recv-options--inherit-and-override>`:
+
+* ``keylocation``
+* ``keyformat``
+* ``encryption``
+
+Sharing
+-------
+
+You may not want the replicated filesystem shared in the same way as the source is.
+
+* ``sharenfs``
+* ``sharesmb``
+
+.. _job-recv-options--placeholder:
+
+Placeholders
+~~~~~~~~~~~~
+
+::
+
+   placeholder:
+     encryption: unspecified | off | inherit
+
+During replication, zrepl :ref:`creates placeholder datasets <replication-placeholder-property>` on the receiving side if the sending side's ``filesystems`` filter creates gaps in the dataset hierarchy.
+This is generally fully transparent to the user.
+However, with OpenZFS Native Encryption, placeholders require zrepl user attention.
+Specifically, the problem is that, when zrepl attempts to create the placeholder dataset on the receiver, and that placeholder's parent dataset is encrypted, ZFS wants to inherit encryption to the placeholder.
+This is relevant to two use cases that zrepl supports:
+
+1. **encrypted-send-to-untrusted-receiver** In this use case, the sender sends an :ref:`encrypted send stream <job-send-options-encrypted>` and the receiver doesn't have the key loaded.
+2. **send-plain-encrypt-on-receive** The receive-side ``root_fs`` dataset is encrypted, and the senders are unencrypted.
+   The key of ``root_fs`` is loaded, and the goal is that the plain sends (e.g., from production) are encrypted on-the-fly during receive, with ``root_fs``'s key.
+
+For **encrypted-send-to-untrusted-receiver**, the placeholder datasets need to be created with ``-o encryption=off``.
+Without it, creation would fail with an error, indicating that the placeholder's parent dataset's key needs to be loaded.
+But we don't trust the receiver, so we can't expect that to ever happen.
+
+However, for **send-plain-encrypt-on-receive**, we cannot set ``-o encryption=off``.
+The reason is that if we did, any of the (non-placeholder) child datasets below the placeholder would inherit ``encryption=off``, thereby silently breaking our encrypt-on-receive use case.
+So, to cover this use case, we need to create placeholders without specifying ``-o encryption``.
+This will make ``zfs create`` inherit the encryption mode from the parent dataset, and thereby transitively from ``root_fs``.
+
+The zrepl config provides the `recv.placeholder.encryption` knob to control this behavior.
+In ``undefined`` mode (default), placeholder creation bails out and asks the user to configure a behavior.
+In ``off`` mode, the placeholder is created with ``encryption=off``, i.e., **encrypted-send-to-untrusted-rceiver** use case.
+In ``inherit`` mode, the placeholder is created without specifying ``-o encryption`` at all, i.e., the **send-plain-encrypt-on-receive** use case.
+
+
+Common Options
+~~~~~~~~~~~~~~
+
+.. _job-send-recv-options--bandwidth-limit:
+
+Bandwidth Limit (send & recv)
+-----------------------------
+
+::
+
+   bandwidth_limit:
+     max: 23.5 MiB # -1 is the default and disabled rate limiting
+     bucket_capacity: # token bucket capacity in bytes; defaults to 128KiB
+
+Both ``send`` and ``recv`` can be limited to a maximum bandwidth through ``bandwidth_limit``.
+For most users, it should be sufficient to just set ``bandwidth_limit.max``.
+The ``bandwidth_limit.bucket_capacity`` refers to the `token bucket size <https://github.com/juju/ratelimit>`_.
+
+The bandwidth limit only applies to the payload data, i.e., the ZFS send stream.
+It does not account for transport protocol overheads.
+The scope is the job level, i.e., all :ref:`concurrent <replication-option-concurrency>` sends or incoming receives of a job share the bandwidth limit.

docs/configuration/snapshotting.rst

@@ -0,0 +1,301 @@
+.. include:: ../global.rst.inc
+
+.. _job-snapshotting-spec:
+
+Taking Snaphots
+===============
+
+You can configure zrepl to take snapshots of the filesystems in the ``filesystems`` field specified in ``push``, ``source`` and ``snap`` jobs.
+
+The following snapshotting types are supported:
+
+
+.. list-table::
+    :widths: 20 70
+    :header-rows: 1
+
+    * - ``snapshotting.type``
+      - Comment
+    * - ``periodic``
+      - Ensure that snapshots are taken at a particular interval.
+    * - ``cron``
+      - Use cron spec to take snapshots at particular points in time.
+    * - ``manual``
+      - zrepl does not take any snapshots by itself.
+
+The ``periodic`` and ``cron`` snapshotting types share some common options and behavior:
+
+* **Naming:** The snapshot names are composed of a user-defined ``prefix`` followed by a UTC date formatted like ``20060102_150405_000`` by default.
+  We either use UTC or timestamp with timezone information because it will avoid name conflicts when switching time zones or between summer and winter time.
+  Note that if timestamp with time zone information is used, the "+" of the timezone (i.e. +02:00) is replaced by "_" (i.e. _02:00) to conform to allowed characters in ZFS snapshots.
+* **Hooks:** You can configure hooks to run before or after zrepl takes the snapshots. See :ref:`below <job-snapshotting-hooks>` for details.
+* **Push replication:** After creating all snapshots, the snapshotter will wake up the replication part of the job, if it's a ``push`` job.
+  Note that snapshotting is decoupled from replication, i.e., if it is down or takes too long, snapshots will still be taken.
+  Note further that other jobs are not woken up by snapshotting.
+
+.. NOTE::
+
+   There is **no concept of ownership** of the snapshots that are created by ``periodic`` or ``cron``.
+   Thus, there is no distinction between zrepl-created snapshots and user-created snapshots during replication or pruning.
+
+   In particular, pruning will take all snapshots into consideration by default.
+   To constrain pruning to just zrepl-created snapshots:
+
+     1. Assign a unique `prefix` to the snapshotter and
+     2. Use the ``regex`` functionality of the various pruning ``keep`` rules to just consider snapshots with that prefix.
+
+  There is currently no way to constrain replication to just zrepl-created snapshots.
+  Follow and comment at :issue:`403` if you need this functionality.
+
+.. NOTE::
+
+  The ``zrepl signal wakeup JOB`` subcommand does not trigger snapshotting.
+
+``periodic`` Snapshotting
+-------------------------
+
+::
+
+   jobs:
+   - ...
+     filesystems: { ... }
+     snapshotting:
+       type: periodic
+       prefix: zrepl_
+       interval: 10m
+       # Timestamp format that is used as snapshot suffix.
+       # Can be any of "dense" (default), "human", "iso-8601", "unix-seconds" or a custom Go time format (see https://go.dev/src/time/format.go)
+       timestamp_format: dense
+       # Specifies in which time zone the snapshot suffix is generated, optional, defaults to UTC, used only if time zone information is part of timestamp_format.
+       # Can be "UTC" (default), "Local" (time zone information from the OS) or any of the IANA Time Zone names (see https://nodatime.org/TimeZones)
+       timestamp_location: UTC
+       hooks: ...
+    pruning: ...
+
+The ``periodic`` snapshotter ensures that snapshots are taken in the specified ``interval``.
+If you use zrepl for backup, this translates into your recovery point objective (RPO).
+To meet your RPO, you still need to monitor that replication, which happens asynchronously to snapshotting, actually works.
+
+It is desirable to get all ``filesystems`` snapshotted simultaneously because it results in a more consistent backup.
+To accomplish this while still maintaining the ``interval``, the ``periodic`` snapshotter attempts to get the snapshotting rhythms in sync.
+To find that sync point, the most recent snapshot, created by the snapshotter, in any of the matched ``filesystems`` is used.
+A filesystem that does not have snapshots by the snapshotter has lower priority than filesystem that do, and thus might not be snapshotted (and replicated) until it is snapshotted at the next sync point.
+The snapshotter uses the ``prefix`` to identify which snapshots it created.
+
+.. _job-snapshotting--cron:
+
+``cron`` Snapshotting
+---------------------
+
+::
+
+   jobs:
+   - type: snap
+     filesystems: { ... }
+     snapshotting:
+       type: cron
+       prefix: zrepl_
+       # (second, optional) minute hour day-of-month month day-of-week
+       # This example takes snapshots daily at 3:00.
+       cron: "0 3 * * *"
+       # Timestamp format that is used as snapshot suffix.
+       # Can be any of "dense" (default), "human", "iso-8601", "unix-seconds" or a custom Go time format (see https://go.dev/src/time/format.go)
+       timestamp_format: dense
+       # Specifies in which time zone the snapshot suffix is generated, optional, defaults to UTC, used only if time zone information is part of timestamp_format.
+       # Can be "UTC" (default), "Local" (time zone information from the OS) or any of the IANA Time Zone names (see https://nodatime.org/TimeZones)
+       timestamp_location: UTC
+     pruning: ...
+
+In ``cron`` mode, the snapshotter takes snaphots at fixed points in time.
+See https://en.wikipedia.org/wiki/Cron for details on the syntax.
+zrepl uses the ``the github.com/robfig/cron/v3`` Go package for parsing.
+An optional field for "seconds" is supported to take snapshots at sub-minute frequencies.
+
+
+``manual`` Snapshotting
+-----------------------
+
+::
+
+   jobs:
+   - type: push
+     snapshotting:
+       type: manual
+     ...
+
+In ``manual`` mode, zrepl does not take snapshots by itself.
+Manual snapshotting is most useful if you have existing infrastructure for snapshot management.
+Or, if you want to decouple snapshot management from replication using a zrepl ``snap`` job.
+See :ref:`this quickstart guide <quickstart-backup-to-external-disk>` for an example.
+
+To trigger replication after taking snapshots, use the ``zrepl signal wakeup JOB`` command.
+
+.. _job-snapshotting-timestamp_format:
+
+Timestamp Format
+----------------
+
+The ``cron`` and ``periodic`` snapshotter support configuring a custom timestamp format that is used as suffix for the snapshot name.
+
+By default, the current time is converted to UTC and then formatted using the ``dense`` format.
+
+Both time zone and format can be customized by setting ``timestamp_format`` and/or ``timestamp_location``.
+
+``timestamp_location`` is fed verbatim into `time.LoadLocation <https://pkg.go.dev/time#LoadLocation>`_.
+
+ ``timestamp_format`` supports the following values (case-insensitive).
+
+* ``dense`` => Go format string ``20060102_150405_000``
+* ``human`` => Go format string ``2006-01-02_15:04:05``
+* ``iso-8601`` => Go format string ``2006-01-02T15:04:05.000Z07:00``
+* ``unix-seconds`` => Unix seconds since the epoch, formatted as a decimal string (`time.Time.Unix <https://pkg.go.dev/time#Time.Unix>`_)
+* Any custom Go time format accepted by `time.Time#Format <https://go.dev/src/time/format.go>`_.
+
+The ``dense``, ``human``, and ``unix-seconds`` formats require the ``timestamp_location`` to be ``UTC`` because they do not contain timezone information.
+
+The ``+`` character is `not allowed in ZFS snapshot names <https://github.com/openzfs/zfs/blob/1d3ba0bf01020f5459b1c28db3979129088924c0/module/zcommon/zfs_namecheck.c#L334-L351>`_.
+Format strings are disallowed to contain the ``+`` character (it's not a character that is interpreted by ``time.Time.Format``, so there's no reason to use it).
+If a format _produces_ a ``+``, that ``+`` is replaced by an `_`` character.
+
+.. _job-snapshotting-hooks:
+
+Pre- and Post-Snapshot Hooks
+----------------------------
+
+Jobs with `periodic snapshots <job-snapshotting-spec_>`_ can run hooks before and/or after taking the snapshot specified in ``snapshotting.hooks``:
+Hooks are called per filesystem before and after the snapshot is taken (pre- and post-edge).
+Pre-edge invocations are in configuration order, post-edge invocations in reverse order, i.e. like a stack.
+If a pre-snapshot invocation fails, ``err_is_fatal=true`` cuts off subsequent hooks, does not take a snapshot, and only invokes post-edges corresponding to previous successful pre-edges.
+``err_is_fatal=false`` logs the failed pre-edge invocation but does not affect subsequent hooks nor snapshotting itself.
+Post-edges are only invoked for hooks whose pre-edges ran without error.
+Note that hook failures for one filesystem never affect other filesystems.
+
+The optional ``timeout`` parameter specifies a period after which zrepl will kill the hook process and report an error.
+The default is 30 seconds and may be specified in any units understood by `time.ParseDuration <https://golang.org/pkg/time/#ParseDuration>`_.
+
+The optional ``filesystems`` filter which limits the filesystems the hook runs for. This uses the same |filter-spec| as jobs.
+
+Most hook types take additional parameters, please refer to the respective subsections below.
+
+.. list-table::
+    :widths: 20 10 70
+    :header-rows: 1
+
+    * - Hook ``type``
+      - Details
+      - Description
+    * - ``command``
+      - :ref:`Details <job-hook-type-command>`
+      - Arbitrary pre- and post snapshot scripts.
+    * - ``postgres-checkpoint``
+      - :ref:`Details <job-hook-type-postgres-checkpoint>`
+      - Execute Postgres ``CHECKPOINT`` SQL command before snapshot.
+    * - ``mysql-lock-tables``
+      - :ref:`Details <job-hook-type-mysql-lock-tables>`
+      - Flush and read-Lock MySQL tables while taking the snapshot.
+
+.. _job-hook-type-command:
+
+``command`` Hooks
+~~~~~~~~~~~~~~~~~
+
+::
+
+
+    jobs:
+    - type: push
+      filesystems: {
+        "<": true,
+        "tmp": false
+      }
+      snapshotting:
+        type: periodic
+        prefix: zrepl_
+        interval: 10m
+        hooks:
+        - type: command
+          path: /etc/zrepl/hooks/zrepl-notify.sh
+          timeout: 30s
+          err_is_fatal: false
+        - type: command
+          path: /etc/zrepl/hooks/special-snapshot.sh
+          filesystems: {
+            "tank/special": true
+          }
+      ...
+
+
+``command`` hooks take a ``path`` to an executable script or binary to be executed before and after the snapshot.
+``path`` must be absolute (e.g. ``/etc/zrepl/hooks/zrepl-notify.sh``).
+No arguments may be specified; create a wrapper script if zrepl must call an executable that requires arguments.
+The process standard output is logged at level INFO. Standard error is logged at level WARN.
+The following environment variables are set:
+
+* ``ZREPL_HOOKTYPE``: either "pre_snapshot" or "post_snapshot"
+* ``ZREPL_FS``: the ZFS filesystem name being snapshotted
+* ``ZREPL_SNAPNAME``: the zrepl-generated snapshot name (e.g. ``zrepl_20380119_031407_000``)
+* ``ZREPL_DRYRUN``: set to ``"true"`` if a dry run is in progress so scripts can print, but not run, their commands
+
+An empty template hook can be found in :sampleconf:`/hooks/template.sh`.
+
+.. _job-hook-type-postgres-checkpoint:
+
+``postgres-checkpoint`` Hook
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Connects to a Postgres server and executes the ``CHECKPOINT`` statement pre-snapshot.
+Checkpointing applies the WAL contents to all data files and syncs the data files to disk.
+This is not required for a consistent database backup: it merely forward-pays the "cost" of WAL replay to the time of snapshotting instead of at restore.
+However, the Postgres manual recommends against checkpointing during normal operation.
+Further, the operation requires Postgres superuser privileges.
+zrepl users must decide on their own whether this hook is useful for them (it likely isn't).
+
+.. ATTENTION::
+    Note that WALs and Postgres data directory (with all database data files) must be on the same filesystem to guarantee a correct point-in-time backup with the ZFS snapshot.
+
+DSN syntax documented here: `<https://godoc.org/github.com/lib/pq>`_
+
+.. code-block:: sql
+
+   CREATE USER zrepl_checkpoint PASSWORD yourpasswordhere;
+   ALTER ROLE zrepl_checkpoint SUPERUSER;
+
+.. code-block:: yaml
+
+  - type: postgres-checkpoint
+    dsn: "host=localhost port=5432 user=postgres password=yourpasswordhere sslmode=disable"
+    filesystems: {
+        "p1/postgres/data11": true
+    }
+
+.. _job-hook-type-mysql-lock-tables:
+
+``mysql-lock-tables`` Hook
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Connects to MySQL and executes
+
+* pre-snapshot ``FLUSH TABLES WITH READ LOCK`` to lock all tables in all databases in the MySQL server we connect to (`docs <https://dev.mysql.com/doc/refman/8.0/en/flush.html#flush-tables-with-read-lock>`_)
+* post-snapshot ``UNLOCK TABLES``  reverse above operation.
+
+Above procedure is documented in the `MySQL manual <https://dev.mysql.com/doc/mysql-backup-excerpt/5.7/en/backup-methods.html>`_
+as a means to produce a consistent backup of a MySQL DBMS installation (i.e., all databases).
+
+`DSN syntax <https://github.com/go-sql-driver/mysql#dsn-data-source-name>`_: ``[username[:password]@][protocol[(address)]]/dbname[?param1=value1&...&paramN=valueN]``
+
+.. ATTENTION::
+    All MySQL databases must be on the same ZFS filesystem to guarantee a consistent point-in-time backup with the ZFS snapshot.
+
+.. code-block:: sql
+
+   CREATE USER zrepl_lock_tables IDENTIFIED BY 'yourpasswordhere';
+   GRANT RELOAD ON *.* TO zrepl_lock_tables;
+   FLUSH PRIVILEGES;
+
+.. code-block:: yaml
+
+  - type: mysql-lock-tables
+    dsn: "zrepl_lock_tables:yourpasswordhere@tcp(localhost)/"
+    filesystems: {
+      "tank/mysql": true
+    }

docs/configuration/transports.rst

@@ -50,12 +50,25 @@ Serve
       serve:
         type: tcp
         listen: ":8888"
+        listen_freebind: true # optional, default false
         clients: {
-          "192.168.122.123" : "mysql01"
-          "192.168.122.123" : "mx01"
+          "192.168.122.123" :               "mysql01",
+          "192.168.122.42" :                "mx01",
+          "2001:0db8:85a3::8a2e:0370:7334": "gateway",
+
+          # CIDR masks require a '*' in the client identity string
+          # that is expanded to the client's IP address
+
+          "10.23.42.0/24":       "cluster-*"
+          "fde4:8dba:82e1::/64": "san-*"
         }
       ...
 
+.. _listen-freebind-explanation:
+
+``listen_freebind`` controls whether the socket is allowed to bind to non-local or unconfigured IP addresses (Linux ``IP_FREEBIND`` , FreeBSD ``IP_BINDANY``).
+Enable this option if you want to ``listen`` on a specific IP address that might not yet be configured when the zrepl daemon starts.
+
 Connect
 ~~~~~~~
 
@@ -76,8 +89,10 @@ Connect
 
 The ``tls`` transport uses TCP + TLS with client authentication using client certificates.
 The client identity is the common name (CN) presented in the client certificate.
+
 It is recommended to set up a dedicated CA infrastructure for this transport, e.g. using OpenVPN's `EasyRSA <https://github.com/OpenVPN/easy-rsa>`_.
-For a simple 2-machine setup, see the :ref:`instructions below<transport-tcp+tlsclientauth-2machineopenssl>`.
+For a simple 2-machine setup, mutual TLS might also be sufficient.
+We provide :ref:`copy-pastable instructions to generate the certificates below <transport-tcp+tlsclientauth-certgen>`.
 
 The implementation uses `Go's TLS library <https://golang.org/pkg/crypto/tls/>`_.
 Since Go binaries are statically linked, you or your distribution need to recompile zrepl when vulnerabilities in that library are disclosed.
@@ -85,6 +100,20 @@ Since Go binaries are statically linked, you or your distribution need to recomp
 All file paths are resolved relative to the zrepl daemon's working directory.
 Specify absolute paths if you are unsure what directory that is (or find out from your init system).
 
+If intermediate CAs are used, the **full chain** must be present in either in the ``ca`` file or the individual ``cert`` files.
+Regardless, the client's certificate must be first in the ``cert`` file, with each following certificate directly certifying the one preceding it (see `TLS's specification <https://tools.ietf.org/html/rfc5246#section-7.4.2>`_).
+This is the common default when using a CA management tool.
+
+.. NOTE::
+
+   As of Go 1.15 (zrepl 0.3.0 and newer), the Go TLS / x509 library **requrires Subject Alternative Names**
+   be present in certificates. You might need to re-generate your certificates using one of the :ref:`two alternatives
+   provided below<transport-tcp+tlsclientauth-certgen>`.
+
+   Note further that zrepl continues to use the CommonName field to assign client identities.
+   Hence, we recommend to keep the Subject Alternative Name and the CommonName in sync.
+
+
 Serve
 ~~~~~
 
@@ -96,15 +125,17 @@ Serve
         serve:
           type: tls
           listen: ":8888"
-          ca: /etc/zrepl/ca.crt
-          cert: /etc/zrepl/prod.crt
-          key: /etc/zrepl/prod.key
+          listen_freebind: true # optional, default false
+          ca:   /etc/zrepl/ca.crt
+          cert: /etc/zrepl/prod.fullchain
+          key:  /etc/zrepl/prod.key
           client_cns:
             - "laptop1"
             - "homeserver"
 
 The ``ca`` field specified the certificate authority used to validate client certificates.
 The ``client_cns`` list specifies a list of accepted client common names (which are also the client identities for this transport).
+The ``listen_freebind`` field is :ref:`explained here <listen-freebind-explanation>`.
 
 Connect
 ~~~~~~~
@@ -116,8 +147,8 @@ Connect
       connect:
         type: tls
         address: "server1.foo.bar:8888"
-        ca: /etc/zrepl/ca.crt
-        cert: /etc/zrepl/backupserver.crt
+        ca:   /etc/zrepl/ca.crt
+        cert: /etc/zrepl/backupserver.fullchain
         key:  /etc/zrepl/backupserver.key
         server_cn: "server1"
         dial_timeout: # optional, default 10s
@@ -127,45 +158,25 @@ The ``server_cn`` specifies the expected common name (CN) of the server's certif
 It overrides the hostname specified in ``address``.
 The connection fails if either do not match.
 
+.. _transport-tcp+tlsclientauth-certgen:
+
 .. _transport-tcp+tlsclientauth-2machineopenssl:
 
-Self-Signed Certificates
-~~~~~~~~~~~~~~~~~~~~~~~~
+Mutual-TLS between Two Machines
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Tools like `EasyRSA <https://github.com/OpenVPN/easy-rsa>`_ make it easy to manage CA infrastructure for multiple clients, e.g. a central zrepl backup server (in sink mode).
-However, for a two-machine setup, self-signed certificates distributed using an out-of-band mechanism will also work just fine:
+For a two-machine setup, self-signed certificates distributed using an out-of-band mechanism will also work just fine:
 
 Suppose you have a push-mode setup, with `backups.example.com` running the :ref:`sink job <job-sink>`, and `prod.example.com` running the :ref:`push job <job-push>`.
 Run the following OpenSSL commands on each host, substituting HOSTNAME in both filenames and the interactive input prompt by OpenSSL:
 
 .. code-block:: bash
-   :emphasize-lines: 1-5,24
 
-   openssl req -x509 -sha256 -nodes \
-      -newkey rsa:4096 \
-      -days 365 \
-      -keyout HOSTNAME.key \
-      -out HOSTNAME.crt
-
-   #Generating a 4096 bit RSA private key
-   #................++++
-   #.++++
-   #writing new private key to 'backups.key'
-   #-----
-   #You are about to be asked to enter information that will be incorporated
-   #into your certificate request.
-   #What you are about to enter is what is called a Distinguished Name or a DN.
-   #There are quite a few fields but you can leave some blank
-   #For some fields there will be a default value,
-   #If you enter '.', the field will be left blank.
-   #-----
-   #Country Name (2 letter code) [XX]:
-   #State or Province Name (full name) []:
-   #Locality Name (eg, city) [Default City]:
-   #Organization Name (eg, company) [Default Company Ltd]:
-   #Organizational Unit Name (eg, section) []:
-   #Common Name (eg, your name or your server's hostname) []:HOSTNAME
-   #Email Address []:
+   (name=HOSTNAME; openssl req -x509 -sha256 -nodes \
+    -newkey rsa:4096 \
+    -days 365 \
+    -keyout $name.key \
+    -out $name.crt -addext "subjectAltName = DNS:$name" -subj "/CN=$name")
 
 Now copy each machine's ``HOSTNAME.crt`` to the other machine's ``/etc/zrepl/HOSTNAME.crt``, for example using `scp`.
 The serve & connect configuration will thus look like the following:
@@ -196,18 +207,52 @@ The serve & connect configuration will thus look like the following:
      ...
 
 
+Certificate Authority using EasyRSA
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For more than two machines, it might make sense to set up a CA infrastructure.
+Tools like `EasyRSA <https://github.com/OpenVPN/easy-rsa>`_ make this very easy:
+
+::
+
+     #!/usr/bin/env bash
+     set -euo pipefail
+
+     HOSTS=(backupserver prod1 prod2 prod3 10.23.42.1)
+
+     curl -L https://github.com/OpenVPN/easy-rsa/releases/download/v3.2.5/EasyRSA-3.2.5.tgz > EasyRSA-3.2.5.tgz
+     echo "662ee3b453155aeb1dff7096ec052cd83176c460cfa82ac130ef8568ec4df490  EasyRSA-3.2.5.tgz" | sha256sum -c
+     rm -rf EasyRSA-3.2.5
+     tar -xf EasyRSA-3.2.5.tgz
+     cd EasyRSA-3.2.5
+     ./easyrsa --batch
+     ./easyrsa --batch init-pki
+     ./easyrsa --batch build-ca nopass
+
+     for host in "${HOSTS[@]}"; do
+         ./easyrsa --batch --auto-san build-serverClient-full $host nopass
+         echo cert for host $host available at pki/issued/$host.crt
+         echo key for host $host available at pki/private/$host.key
+     done
+     echo ca cert available at pki/ca.crt
+
+
 .. _transport-ssh+stdinserver:
 
 ``ssh+stdinserver`` Transport
 -----------------------------
 
-``ssh+stdinserver`` is inspired by `git shell <https://git-scm.com/docs/git-shell>`_ and `Borg Backup <https://borgbackup.readthedocs.io/en/stable/deployment.html>`_.
-It is provided by the Go package ``github.com/problame/go-netssh``.
+``ssh+stdinserver`` uses the ``ssh`` command and some features of the server-side SSH ``authorized_keys`` file.
+It is less efficient than other transports because the data passes through two more pipes.
+However, it is fairly convenient to set up and allows the zrepl daemon to not be directly exposed to the internet, because all traffic passes through the system's SSH server.
 
-.. ATTENTION::
+The concept is inspired by `git shell <https://git-scm.com/docs/git-shell>`_ and `Borg Backup <https://borgbackup.readthedocs.io/en/stable/deployment.html>`_.
+The implementation is provided by the Go package ``github.com/problame/go-netssh``.
 
-   ``ssh+stdinserver`` has inferior error detection and handling compared to the ``tcp`` and ``tls`` transports.
-   If you require tested timeout & retry handling, use ``tcp`` or ``tls`` transports, or help improve package go-netssh.
+.. NOTE::
+
+   ``ssh+stdinserver`` generally provides inferior error detection and handling compared to the ``tcp`` and ``tls`` transports.
+   When encountering such problems, consider using  ``tcp`` or ``tls`` transports, or help improve package go-netssh.
 
 .. _transport-ssh+stdinserver-serve:
 
@@ -278,9 +323,9 @@ Connect
         user: root
         port: 22
         identity_file: /etc/zrepl/ssh/identity
-        options: # optional, default [], `-o` arguments passed to ssh
-        - "Compression=on"
-        dial_timeout: # optional, default 10s, max time.Duration until initial handshake is completed
+        # options: # optional, default [], `-o` arguments passed to ssh
+        # - "Compression=yes"
+        # dial_timeout: 10s # optional, default 10s, max time.Duration until initial handshake is completed
 
 The connecting zrepl daemon
 
@@ -336,5 +381,6 @@ The ``client_identity`` is used by the sink as documented above.
         type: local
         listener_name: localsink
         client_identity: local_backup
+        dial_timeout: 2s # optional, 0 for no timeout
       ...
 

docs/future.rst

@@ -0,0 +1,33 @@
+.. include:: global.rst.inc
+
+.. _future:
+
+Future
+======
+
+This page contains some notes about future plans for zrepl.
+Then again, Christian only has very limited time available for zrepl maintenance these days.
+So, don't count on any of this happening in the near future.
+
+One big development that has happened in recent years is this fork of zrepl: https://github.com/dsh2dsh/zrepl
+We should figure out whether we can pull in features from there.
+
+The next major step in terms of new feature development for zrepl would be to revise snapshot management:
+
+- Make it easy to decouple snapshot management (snapshotting, pruning) from replication.
+- Ability to include/exclude snapshots from replication.
+  This is useful for aforementioned decoupling, e.g., separate snapshot prefixes for local & remote replication.
+  Also, it makes explicit that by default, zrepl replicates all snapshots, and that
+  replication has no concept of "zrepl-created snapshots", which is a common misconception.
+- Use of ``zfs snapshot`` comma syntax or channel programs to take snapshots of multiple
+  datasets atomically.
+- Provide an alternative to the ``grid`` pruning policy.
+  Most likely something based on hourly/daily/weekly/monthly "trains" plus a count.
+- Ability to prune at the granularity of the **group** of snapshots created at a given
+  time, as opposed to the individual snapshots within a dataset.
+  Maybe this will be addressed by the alternative to the ``grid`` pruning policy,
+  as it will likely be more predictable.
+
+Those changes will likely come with some breakage in the config.
+However, I want to avoid breaking **use cases** that are satisfied by the current design.
+There will be beta/RC releases to give users a chance to evaluate.

docs/global.rst.inc

@@ -1,3 +1,37 @@
 .. global list of substitutions
 
-.. |mainconfig| replace:: :ref:`main configuration file <mainconfigfile>`
+.. 
+  .. |macroname| replace:: macro expansion
+
+.. |GitHub license| image:: https://img.shields.io/github/license/zrepl/zrepl.svg
+   :target: https://github.com/zrepl/zrepl/blob/master/LICENSE
+.. |Language: Go| image:: https://img.shields.io/badge/lang-Go-6ad7e5.svg
+   :target: https://golang.org/
+.. |User Docs| image:: https://img.shields.io/badge/docs-web-blue.svg
+   :target: https://zrepl.github.io
+.. |Donate via PayPal| image:: https://img.shields.io/badge/donate-paypal-yellow.svg
+   :target: https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96
+.. |Donate via Liberapay| image:: https://img.shields.io/liberapay/patrons/zrepl.svg?logo=liberapay
+   :target: https://liberapay.com/zrepl/donate
+.. |Donate via Patreon| image:: https://img.shields.io/badge/dynamic/json?color=yellow&label=Patreon&query=data.attributes.patron_count&url=https%3A%2F%2Fwww.patreon.com%2Fapi%2Fcampaigns%2F3095079
+   :target: https://www.patreon.com/zrepl
+.. |Donate via GitHub Sponsors| image:: https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&style=flat&color=yellow
+   :target: https://github.com/sponsors/problame
+.. |Twitter| image:: https://img.shields.io/twitter/url/https/github.com/zrepl/zrepl.svg?style=social
+   :target: https://twitter.com/intent/tweet?text=Wow:&url=https%3A%2F%2Fgithub.com%2Fzrepl%2Fzrepl
+.. |Matrix| image:: https://img.shields.io/badge/chat-matrix-blue.svg
+   :target: https://matrix.to/#/#zrepl:matrix.org
+
+.. |serve-transport| replace:: :ref:`serve specification<transport>`
+.. |connect-transport| replace:: :ref:`connect specification<transport>`
+.. |send-options| replace:: :ref:`send options<job-send-options>`, e.g. for encrypted sends
+.. |recv-options| replace:: :ref:`recv options<job-recv-options>`
+.. |replication-options| replace:: :ref:`replication options<replication-options>`
+.. |conflict-resolution-options| replace:: :ref:`conflict resolution options<conflict_resolution-options>`
+.. |snapshotting-spec| replace:: :ref:`snapshotting specification <job-snapshotting-spec>`
+.. |pruning-spec| replace:: :ref:`pruning specification <prune>`
+.. |filter-spec| replace:: :ref:`filter specification<pattern-filter>`
+
+.. |br| raw:: html
+
+   <br/>

docs/implementation.rst

@@ -1,61 +0,0 @@
-.. _implementation_toc:
-
-Implementation Overview
-=======================
-
-.. WARNING::
-
-   Incomplete and possibly outdated.
-   Check out the :ref:`talks about zrepl <pr-talks>` at various conferences for up-to-date material.
-   Alternatively, have a `look at the source code <http://github.com/zrepl/zrepl>`_ ;)
-
-The following design aspects may convince you that ``zrepl`` is superior to a hacked-together shell script solution.
-Also check out the :ref:`talks about zrepl <pr-talks>` at various conferences.
-
-Testability & Performance
--------------------------
-
-zrepl is written in Go, a real programming language with type safety,
-reasonable performance, testing infrastructure and an (opinionated) idea of
-software engineering.
-
-* key parts & algorithms of zrepl are covered by unit tests (work in progress)
-* zrepl is noticably faster than comparable shell scripts
-
-
-RPC protocol
-------------
-
-While it is tempting to just issue a few ``ssh remote 'zfs send ...' | zfs recv``, this has a number of drawbacks:
-
-* The snapshot streams need to be compatible.
-* Communication is still unidirectional. Thus, you will most likely
-
-  * either not take advantage of advanced replication features such as *compressed send & recv*
-  * or issue additional ``ssh`` commands in advance to figure out what features are supported on the other side.
-
-* Advanced logic in shell scripts is ugly to read, poorly testable and a pain to maintain.
-
-zrepl takes a different approach:
-
-* Define an RPC protocol.
-* Establish an encrypted, authenticated, bidirectional communication channel.
-* Run daemons on both sides of the setup and let them talk to each other.
-
-This has several obvious benefits:
-
-* No blank root shell access is given to the other side.
-* An *authenticated* peer *requests* filesystem lists, snapshot streams, etc.
-* The server decides which filesystems it exposes to which peers.
-* The :ref:`transport mechanism <transport>` is decoupled from the remaining logic, which allows us to painlessly offer multiple transport mechanisms.
-
-Protocol Implementation
-~~~~~~~~~~~~~~~~~~~~~~~
-
-zrepl uses a custom RPC protol because, at the time of writing, existing solutions like gRPC do not provide efficient means to transport large amounts of data, whose size is unknown at send time (= zfs send streams).
-The package used is `github.com/problame/go-streamrpc <https://github.com/problame/go-streamrpc/tree/master>`_.
-
-Logging & Transparency
-----------------------
-
-zrepl comes with :ref:`rich, structured and configurable logging <logging>`, allowing administators to understand what the software is actually doing.

docs/index.rst

@@ -5,6 +5,9 @@
 
 .. include:: global.rst.inc
 
+|GitHub license| |Language: Go| |Twitter| |Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal| |Matrix|
+
+
 zrepl - ZFS replication
 -----------------------
 
@@ -12,16 +15,36 @@ zrepl - ZFS replication
 
 .. raw:: html
 
-   <div style="margin-bottom: 1em; background: #2e3436; min-height: 6em; max-width: 100%">
-     <a href="https://raw.githubusercontent.com/wiki/zrepl/zrepl/zrepl_0.1_status.mp4" target="_new" >
-       <video title="zrepl status subcommand" loop autoplay style="width: 100%; display: block;" src="https://raw.githubusercontent.com/wiki/zrepl/zrepl/zrepl_0.1_status.mp4"></video>
-     </a>
+   <div style="margin-bottom: 1em; background: #2e3436; color: white; font-size: 0.8em; min-height: 6em; max-width: 100%; overflow: auto;">
+     <pre>
+     Job: prod_to_backups
+     Type: push
+     Replication:
+         Attempt #1
+         Status: fan-out-filesystems
+         Progress: [=========================\----] 246.7 MiB / 264.7 MiB @ 11.5 MiB/s
+           zroot              STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
+           zroot/ROOT         DONE (step 2/2, 1.2 KiB/1.2 KiB)
+         * zroot/ROOT/default STEPPING (step 1/2, 123.4 MiB/129.3 MiB) next: @a => @b
+           zroot/tmp          STEPPING (step 1/2, 29.9 KiB/44.2 KiB) next: @a => @b
+           zroot/usr          STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
+         * zroot/usr/home     STEPPING (step 1/2, 123.3 MiB/135.3 MiB) next: @a => @b
+           zroot/var          STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
+           zroot/var/audit    DONE (step 2/2, 1.2 KiB/1.2 KiB)
+           zroot/var/crash    DONE (step 2/2, 1.2 KiB/1.2 KiB)
+           zroot/var/log      STEPPING (step 1/2, 22.0 KiB/29.2 KiB) next: @a => @b
+           zroot/var/mail     STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
+     Pruning Sender:
+         ...
+     Pruning Receiver:
+     </pre>
    </div>
 
+
 Getting started
 ~~~~~~~~~~~~~~~
 
-The :ref:`10 minutes tutorial setup <tutorial>` gives you a first impression.
+The :ref:`10 minute quick-start guides <quickstart-toc>` give you a first impression.
 
 Main Features
 ~~~~~~~~~~~~~
@@ -29,17 +52,26 @@ Main Features
 * **Filesystem replication**
 
   * [x] Pull & Push mode
-  * [x] Multiple transport :ref:`transports <transport>`: TCP, TCP + TLS client auth, SSH
+  * [x] Multiple :ref:`transport modes <transport>`: TCP, TCP + TLS client auth, SSH
 
   * Advanced replication features
 
-    * [ ] Resumable send & receive
-    * [ ] Compressed send & receive
-    * [ ] Raw encrypted send & receive
+    * [x] Automatic retries for temporary network errors
+    * [x] Automatic resumable send & receive
+    * [x] Automatic ZFS holds during send & receive
+    * [x] Automatic bookmark \& hold management for guaranteed incremental send & recv 
+    * [x] Encrypted raw send & receive to untrusted receivers (OpenZFS native encryption)
+    * [x] Properties send & receive
+    * [x] Compressed send & receive
+    * [x] Large blocks send & receive
+    * [x] Embedded data send & receive
+    * [x] Resume state send & receive
+    * [x] Bandwidth limiting
 
 * **Automatic snapshot management**
 
-  * [x] Periodic filesystem snapshots
+  * [x] Periodic :ref:`filesystem snapshots <job-snapshotting-spec>`
+  * [x] Support for :ref:`pre- and post-snapshot hooks <job-snapshotting-hooks>` with builtins for MySQL & Postgres
   * [x] Flexible :ref:`pruning rule system <prune>`
 
     * [x] Age-based fading (grandfathering scheme)
@@ -58,6 +90,7 @@ Main Features
 * **Maintainable implementation in Go**
 
   * [x] Cross platform
+  * [x] Dynamic feature checking
   * [x] Type safe & testable code
 
 
@@ -72,12 +105,14 @@ Contributing
 
 We are happy about any help we can get!
 
+* :ref:`Financial Support <supporters>`
 * Explore the codebase
 
   * These docs live in the ``docs/`` subdirectory
 
 * Document any non-obvious / confusing / plain broken behavior you encounter when setting up zrepl for the first time
-* Check the *Issues* and *Projects* sections for things to do
+* Check the *Issues* and *Projects* sections for things to do.
+  The `good first issues <https://github.com/zrepl/zrepl/labels/good%20first%20issue>`_ and `docs <https://github.com/zrepl/zrepl/labels/docs>`_ are suitable starting points.
 
 .. admonition:: Development Workflow
     :class: note
@@ -86,6 +121,8 @@ We are happy about any help we can get!
     Make sure to read the `Developer Documentation section <https://github.com/zrepl/zrepl>`_ and open new issues or pull requests there.
 
 
+
+
 Table of Contents
 ~~~~~~~~~~~~~~~~~
 
@@ -93,12 +130,14 @@ Table of Contents
    :maxdepth: 2
    :caption: Contents:
 
-   tutorial
+   quickstart
    installation
    configuration
    usage
-   implementation
    pr
    changelog
+   future
    GitHub Repository & Issue Tracker <https://github.com/zrepl/zrepl>
+   Chat: Matrix <https://matrix.to/#/#zrepl:matrix.org>
+   supporters
 

docs/installation.rst

@@ -1,88 +1,19 @@
-.. _binary releases: https://github.com/zrepl/zrepl/releases
 
-.. _installation:
+.. _installation_toc:
 
+************
 Installation
-============
+************
 
 .. TIP::
 
-    Note: check out the :ref:`tutorial` if you want a first impression of zrepl.
+    Note: check out the :ref:`quick-start guides <quickstart-toc>` if you want a first impression of zrepl.
 
-User Privileges
----------------
-
-It is possible to run zrepl as an unprivileged user in combination with
-`ZFS delegation <https://www.freebsd.org/doc/handbook/zfs-zfs-allow.html>`_.
-Also, there is the possibility to run it in a jail on FreeBSD by delegating a dataset to the jail.
-However, until we get around documenting those setups, you will have to run zrepl as root or experiment yourself :)
-
-Packages
---------
-
-zrepl source releases are signed & tagged by the author in the git repository.
-Your OS vendor may provide binary packages of zrepl through the package manager.
-Additionally, `binary releases`_ are provided on GitHub.
-The following list may be incomplete, feel free to submit a PR with an update:
-
-.. list-table::
-    :header-rows: 1
-
-    * - OS / Distro
-      - Install Command
-      - Link
-    * - FreeBSD
-      - ``pkg install zrepl``
-      - `<https://www.freshports.org/sysutils/zrepl/>`_
-    * - Others
-      -
-      - Use `binary releases`_ or build from source.
-
-Compile From Source
-~~~~~~~~~~~~~~~~~~~
-
-Producing a release requires **Go 1.9** or newer and **Python 3** + **pip3** + ``docs/requirements.txt`` for the Sphinx documentation.
-A tutorial to install Go is available over at `golang.org <https://golang.org/doc/install>`_.
-Python and pip3 should probably be installed via your distro's package manager.
-
-Alternatively, you can use the Docker build process:
-it is used to produce the official zrepl `binary releases`_
-and serves as a reference for build dependencies and procedure:
-
-::
-
-    git clone https://github.com/zrepl/zrepl.git
-    cd zrepl
-    sudo docker build -t zrepl_build -f build.Dockerfile .
-    sudo docker run -it --rm \
-        -v "${PWD}:/go/src/github.com/zrepl/zrepl" \
-        --user "$(id -u):$(id -g)" \
-        zrepl_build make vendordeps release
-
-Alternatively, you can install build dependencies on your local system and then build in your ``$GOPATH``:
-
-::
-
-    mkdir -p "${GOPATH}/src/github.com/zrepl/zrepl"
-    git clone https://github.com/zrepl/zrepl.git "${GOPATH}/src/github.com/zrepl/zrepl"
-    cd "${GOPATH}/src/github.com/zrepl/zrepl"
-    ./lazy.sh devsetup
-    make vendordeps release
-
-Build results are located in the ``artifacts/`` directory.
-
-.. NOTE::
-
-    It is your job to install the apropriate binary in the zrepl users's ``$PATH``, e.g. ``/usr/local/bin/zrepl``.
-    Otherwise, the examples in the :ref:`tutorial` may need to be adjusted.
-
-.. _mainconfigfile:
-
-What next?
-----------
-
-Read the :ref:`configuration chapter<configuration_toc>` and optionally create the :ref:`runtime directories <configuration_preface>`.
-Afterwards, continue with the :ref:`usage chapter<usage>`.
-
-**Reminder**: If you want a quick introduction, please read the :ref:`tutorial`.
+.. toctree::
 
+    installation/packages
+    installation/apt-repos
+    installation/rpm-repos
+    installation/user-privileges
+    installation/freebsd-jail-with-iocage
+    installation/what-next

docs/installation/apt-repos.rst

@@ -0,0 +1,40 @@
+
+.. _installation-apt-repos:
+
+Debian / Ubuntu APT repositories
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+We maintain APT repositories for Debian, Ubuntu and derivatives.
+The fingerprint of the signing key is ``E101 418F D3D6 FBCB 9D65  A62D 7086 99FC 5F2E BF16``.
+It is available at `<https://zrepl.cschwarz.com/apt/apt-key.asc>`_ .
+Please open an issue in on GitHub if you encounter any issues with the repository.
+
+::
+
+    (
+    set -ex
+    zrepl_apt_key_url=https://zrepl.cschwarz.com/apt/apt-key.asc
+    zrepl_apt_key_dst=/usr/share/keyrings/zrepl.gpg
+    zrepl_apt_repo_file=/etc/apt/sources.list.d/zrepl.list
+
+    # Install dependencies for subsequent commands
+    sudo apt update && sudo apt install curl gnupg lsb-release
+
+    # Deploy the zrepl apt key.
+    curl -fsSL "$zrepl_apt_key_url" | tee | gpg --dearmor | sudo tee "$zrepl_apt_key_dst" > /dev/null
+
+    # Add the zrepl apt repo.
+    ARCH="$(dpkg --print-architecture)"
+    CODENAME="$(lsb_release -i -s | tr '[:upper:]' '[:lower:]') $(lsb_release -c -s | tr '[:upper:]' '[:lower:]')"
+    echo "Using Distro and Codename: $CODENAME"
+    echo "deb [arch=$ARCH signed-by=$zrepl_apt_key_dst] https://zrepl.cschwarz.com/apt/$CODENAME main" | sudo tee "$zrepl_apt_repo_file" > /dev/null
+
+    # Update apt repos.
+    sudo apt update
+    )
+
+.. NOTE::
+
+   Until zrepl reaches 1.0, the repositories will be updated to the latest zrepl release immediately.
+   This includes breaking changes between zrepl versions.
+   Use ``apt-mark hold zrepl`` to prevent upgrades of zrepl.

docs/installation/freebsd-jail-with-iocage.rst

@@ -0,0 +1,152 @@
+.. include:: ../global.rst.inc
+
+.. _installation-freebsd-jail-with-iocage:
+
+FreeBSD Jail With iocage
+========================
+
+
+This tutorial shows how zrepl can be installed on FreeBSD, or FreeNAS in a jail using iocage.
+While this tutorial focuses on using iocage, much of the setup would be similar
+using a different jail manager.
+
+.. NOTE::
+
+   From a security perspective, just keep in mind that ``zfs send``/``recv`` was never designed with
+   jails in mind, an attacker could probably crash the receive-side kernel or worse induce stateful
+   damage to the receive-side pool if they were able to get access to the jail.
+
+   The jail doesn't provide security benefits, but only management ones.
+
+Requirements
+------------
+
+A dataset that will be delegated to the jail needs to be created if one does not already exist.
+For the tutorial ``tank/zrepl`` will be used.
+
+.. code-block:: bash
+
+   zfs create -o mountpoint=none tank/zrepl
+
+The only software requirements on the host system are ``iocage``, which can be installed
+from ports or packages.
+
+.. code-block:: bash
+
+   pkg install py37-iocage
+
+.. NOTE::
+
+   By default ``iocage`` will "activate" on first use which will set up some defaults such as
+   which pool will be used. To activate ``iocage`` manually the ``iocage activate`` command can be used.
+
+Jail Creation
+-------------
+
+There are two options for jail creation using FreeBSD.
+
+1. Manually set up the jail from scratch
+2. Create the jail using the ``zrepl`` plugin. On FreeNAS this is possible from the user interface using the community index.
+
+Manual Jail
+###########
+
+Create a jail, using the same release as the host, called ``zrepl`` that will be automatically started at boot.
+The jail will have ``tank/zrepl`` delegated into it.
+
+.. code-block:: bash
+
+   iocage create --release "$(freebsd-version -k | cut -d '-' -f '1,2')" --name zrepl \
+          boot=on nat=1 \
+          jail_zfs=on \
+          jail_zfs_dataset=zrepl \
+          jail_zfs_mountpoint='none'
+
+Enter the jail:
+
+.. code-block:: bash
+
+   iocage console zrepl
+
+Install ``zrepl``
+
+.. code-block:: bash
+
+   pkg update && pkg upgrade
+   pkg install zrepl
+
+Create the log file ``/var/log/zrepl.log``
+
+.. code-block:: bash
+
+   touch /var/log/zrepl.log && service newsyslog restart
+
+Tell syslogd to redirect facility local0 to the ``zrepl.log`` file:
+
+.. code-block:: bash
+
+   service syslogd reload
+
+Enable the zrepl daemon to start automatically at boot:
+
+.. code-block:: bash
+
+   sysrc zrepl_enable="YES"
+
+Now jump to :ref:`the summary <installation-freebsd-jail-summary>` below.
+
+Plugin
+######
+
+When using the plugin, ``zrepl`` will be installed for you in a jail using the following ``iocage`` properties.
+
+* ``nat=1``
+* ``jail_zfs=on``
+* ``jail_zfs_mountpoint=none``
+
+Additionally the delegated dataset should be specified upon creation, and optionally start on boot can be set.
+This can also be done from the FreeNAS webui.
+
+.. code-block:: bash
+
+   fetch https://raw.githubusercontent.com/ix-plugin-hub/iocage-plugin-index/master/zrepl.json -o /tmp/zrepl.json
+   iocage fetch -P /tmp/zrepl.json --name zrepl jail_zfs_dataset=zrepl boot=on
+
+Configuration
+-------------
+
+Now ``zrepl`` can be configured.
+
+Enter the jail.
+
+.. code-block:: bash
+
+   iocage console zrepl
+
+Modify the ``/usr/local/etc/zrepl/zrepl.yml`` configuration file.
+
+.. TIP::
+
+    Note: check out the :ref:`quick-start guides <quickstart-toc>` for examples of a ``sink`` job.
+
+Now ``zrepl`` can be started.
+
+.. code-block:: bash
+
+   service zrepl start
+
+Now jump to :ref:`the summary <installation-freebsd-jail-summary>` below.
+
+.. _installation-freebsd-jail-summary:
+
+Summary
+-------
+
+Congratulations, you have a working jail!
+
+.. NOTE::
+
+   With FreeBSD 13's transition to OpenZFS 2.0, please ensure that your jail's FreeBSD version matches the one in the kernel module.
+   If you are getting cryptic errors such as
+   ``cannot receive new filesystem stream: invalid backup stream``
+   the instructions posted `here <https://github.com/zrepl/zrepl/issues/500#issuecomment-966215205>`_ might help.

docs/installation/packages.rst

@@ -0,0 +1,50 @@
+.. _installation-packages:
+
+.. _binary releases: https://github.com/zrepl/zrepl/releases
+
+Packages
+--------
+
+zrepl source releases are signed & tagged by the author in the git repository.
+Your OS vendor may provide binary packages of zrepl through the package manager.
+Additionally, `binary releases`_ are provided on GitHub.
+The following list may be incomplete, feel free to submit a PR with an update:
+
+.. list-table::
+    :header-rows: 1
+
+    * - OS / Distro
+      - Install Command
+      - Link
+    * - any
+      - Statically linked binaries.
+      - `Official GitHub releases <binary releases_>`_
+    * - FreeBSD
+      - ``pkg install zrepl``
+      - `<https://www.freshports.org/sysutils/zrepl/>`_
+
+        :ref:`installation-freebsd-jail-with-iocage`
+    * - FreeNAS
+      -
+      - :ref:`installation-freebsd-jail-with-iocage`
+    * - MacOS
+      - ``brew install zrepl``
+      - Available on `homebrew <https://brew.sh>`_
+    * - Arch Linux
+      - ``yay install zrepl``
+      - Available on `AUR <https://aur.archlinux.org/packages/zrepl>`_
+    * - Fedora / RHEL / OpenSUSE
+      - ``dnf install zrepl``
+      - :ref:`RPM repository config <installation-rpm-repos>`
+    * - Debian + Ubuntu
+      - ``apt install zrepl``
+      - :ref:`APT repository config <installation-apt-repos>`
+    * - OmniOS
+      - ``pkg install zrepl``
+      - Available since `r151030 <https://pkg.omniosce.org/r151030/extra/en/search.shtml?token=zrepl&action=Search>`_
+    * - Void Linux
+      - ``xbps-install zrepl``
+      - Available since `a88a2a4 <https://github.com/void-linux/void-packages/commit/a88a2a4d7bf56072dadf61ab56b8424e39155890>`_
+    * - any
+      - Build from source
+      - :repomasterlink:`README.md`.

docs/installation/rpm-repos.rst

@@ -0,0 +1,55 @@
+.. _installation-rpm-repos:
+
+RPM repositories
+~~~~~~~~~~~~~~~~
+
+We provide a single RPM repository for all RPM-based Linux distros.
+The zrepl binary in the repo is the same as the one published to GitHub.
+Since Go binaries are statically linked, the RPM should work about everywhere.
+Please open an issue on GitHub if you encounter any issues with the repository.
+
+The fingerprint of the repo & package signing key is:
+``F6F6 E8EA 6F2F 1462 2878 B5DE 50E3 4417 826E 2CE6``.
+It is available at `<https://zrepl.cschwarz.com/rpm/rpm-key.asc>`_ .
+
+.. NOTE::
+
+   Until zrepl reaches 1.0, the repository will be updated to the latest zrepl release immediately.
+   This includes breaking changes between zrepl versions.
+   If that bothers you, use the `dnf versionlock plugin <https://dnf-plugins-core.readthedocs.io/en/latest/versionlock.html>`_ or ``zypper addlock zrepl`` to pin the version of zrepl on your system.
+
+
+
+Fedora / AlmaLinux / Rocky Linux / RHEL
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+For ``dnf``/``yum``-based distributions, copy-paste the following snippet:
+
+.. code-block:: bash
+
+    rpmkeys --import 'https://zrepl.cschwarz.com/rpm/rpm-key.asc'
+    cat > /etc/yum.repos.d/zrepl.repo <<EOF
+    [zrepl]
+    name = zrepl
+    baseurl = https://zrepl.cschwarz.com/rpm/repo
+    gpgkey = https://zrepl.cschwarz.com/rpm/rpm-key.asc
+    repo_gpgcheck = 1
+    EOF
+    dnf install zrepl
+    # Or if you're on an older system:
+    # yum install zrepl
+
+You will be asked by dnf to verify repository metadata (``repo_gpgcheck``).
+There is no way to automate that prompt.
+
+openSUSE
+^^^^^^^^
+
+For SUSE-based distributions that use ``zypper``, copy-paste the following snippet:
+
+.. code-block:: bash
+
+    rpmkeys --import 'https://zrepl.cschwarz.com/rpm/rpm-key.asc'
+    zypper ar --check --gpgcheck-strict --refresh https://zrepl.cschwarz.com/rpm/repo zrepl
+    zypper install zrepl
+

docs/installation/user-privileges.rst

@@ -0,0 +1,12 @@
+.. _installation-user-privileges:
+
+User Privileges
+---------------
+
+It is possible to run zrepl as an unprivileged user in combination with
+`ZFS delegation <https://www.freebsd.org/doc/handbook/zfs-zfs-allow.html>`_.
+Also, there is the possibility to run it in a jail on FreeBSD by delegating a dataset to the jail.
+
+.. TIP::
+
+    Note: check out the :ref:`installation-freebsd-jail-with-iocage` for FreeBSD jail setup instructions.

docs/installation/what-next.rst

@@ -0,0 +1,8 @@
+.. _installation-what-next:
+
+What next?
+----------
+
+Read the :ref:`configuration chapter<configuration_toc>` and then continue with the :ref:`usage chapter<usage>`.
+
+**Reminder**: If you want a quick introduction, please read the :ref:`quick-start guides <quickstart-toc>`.

docs/pr.rst

@@ -15,3 +15,5 @@ Talks & Presentations
   `Event <https://wiki.freebsd.org/DevSummit/201709>`__
   )
 
+  * Note: The remarks on ``keep_bookmarks`` are irrelevant as of zrepl 0.1 which introduced the zrepl-managed replication cursor bookmark.
+    Read the `Overview <overview-how-replication-works>`_ section to learn more.

docs/publish.sh

@@ -1,76 +1,94 @@
 #!/bin/bash
-set -eo pipefail
+set -euo pipefail
 
-GHPAGESREPO="git@github.com:zrepl/zrepl.github.io.git"
+GHPAGESREPO="https://github.com/zrepl/zrepl.github.io.git"
 SCRIPTDIR=$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )
 PUBLICDIR="${SCRIPTDIR}/public_git"
+ROOTDIR="${SCRIPTDIR}/.."
 
-checkout_repo_msg() {
-    echo "clone ${GHPAGESREPO} to ${PUBLICDIR}:"
-    echo "	git clone ${GHPAGESREPO} ${PUBLICDIR}"
-    git clone "${GHPAGESREPO}" "${PUBLICDIR}"
-}
+PUSH=false
+DO_CLONE=false
+NON_INTERACTIVE=false
 
-exit_msg() {
-    echo "error, exiting..."
-}
-trap exit_msg EXIT
-
-if ! type sphinx-versioning >/dev/null; then
-    echo "install sphinx-versioning and come back"
-    exit 1
-fi
+while getopts "caPh" arg; do
+    case "$arg" in
+        "a") NON_INTERACTIVE=true ;;
+        "c") DO_CLONE=true ;;
+        "P") PUSH=true ;;
+        "h") echo "Usage: $0 [-c clone] [-a auto/non-interactive] [-P push]"; exit 0 ;;
+        *) echo "invalid option"; exit 1 ;;
+    esac
+done
 
 cd "$SCRIPTDIR"
 
+# Clone or verify repo
 if [ ! -d "$PUBLICDIR" ]; then
-    checkout_repo_msg
+    if $DO_CLONE; then
+        git clone "${GHPAGESREPO}" "${PUBLICDIR}"
+    else
+        echo "Run with -c to clone ${GHPAGESREPO}"
+        exit 1
+    fi
+fi
+
+if ! $NON_INTERACTIVE; then
+    echo -n "PRESS ENTER to confirm you committed and pushed docs changes to the zrepl repo"
+    read -r
+fi
+
+# Verify we're in the right repo
+cd "$PUBLICDIR"
+REMOTE_URL=$(git remote get-url origin)
+if [[ "$REMOTE_URL" != *"zrepl.github.io"* ]]; then
+    echo "ERROR: ${PUBLICDIR} remote is '${REMOTE_URL}', expected zrepl.github.io repo"
     exit 1
 fi
 
-echo -n "PRESS ENTER to confirm you commited and pushed docs changes and tags to the zrepl repo"
-read
-
-pushd "$PUBLICDIR" 
-
-echo "verify we're in the GitHub pages repo..."
-git remote get-url origin | grep -E "^${GHPAGESREPO}\$"
-if [ "$?" -ne "0" ] ;then 
-    checkout_repo_msg
-    echo "finished checkout, please run again"
-    exit 1
-fi
-
-echo "resetting GitHub pages repo to latest commit"
+# Reset public repo to latest
+echo "Resetting GitHub pages repo to latest commit..."
 git fetch origin
 git reset --hard origin/master
 
-echo "cleaning GitHub pages repo"
-git rm -rf .
+# Clean everything
+echo "Cleaning GitHub pages repo..."
+git rm -rf . || true
 
-popd
+# GitHub Pages https://github.blog/news-insights/the-library/bypassing-jekyll-on-github-pages/
+touch .nojekyll
 
-echo "building site"
-set -e
-sphinx-versioning build \
-   --show-banner \
-   docs ./public_git \
-   -- -c sphinxconf # older conf.py throw errors because they used
-                    # version = subprocess.show_output(["git", "describe"])
-                    # which fails when building with sphinxcontrib-versioning
-set +e
+# Build docs
+echo "Building docs..."
+cd "$ROOTDIR"
+make docs
 
-CURRENT_COMMIT=$(git rev-parse HEAD)
-git status --porcelain
-if [[ "$(git status --porcelain)" != "" ]]; then
-    CURRENT_COMMIT="${CURRENT_COMMIT}(dirty)" 
-fi
-COMMIT_MSG="sphinx-versioning render from publish.sh - `date -u` - ${CURRENT_COMMIT}"
+# Copy built docs to public repo
+echo "Copying built docs..."
+cp -r artifacts/docs/html/* "$PUBLICDIR/"
 
-pushd "$PUBLICDIR"
-
-echo "adding and commiting all changes in GitHub pages repo"
+# Commit
+cd "$PUBLICDIR"
+cat > .gitignore <<EOF
+**/.doctrees
+EOF
+git add .gitignore
 git add -A
-git commit -m "$COMMIT_MSG"
-git push origin master
 
+CURRENT_COMMIT=$(git -C "$ROOTDIR" rev-parse HEAD)
+if [ "$(git -C "$ROOTDIR" status --porcelain)" != "" ]; then
+    CURRENT_COMMIT="${CURRENT_COMMIT}(dirty)"
+fi
+COMMIT_MSG="docs: $(date -u) - ${CURRENT_COMMIT}"
+
+if [ "$(git status --porcelain)" != "" ]; then
+    git commit -m "$COMMIT_MSG"
+else
+    echo "Nothing to commit"
+fi
+
+if $PUSH; then
+    echo "Pushing to GitHub pages repo..."
+    git push origin master
+else
+    echo "Not pushing. Use -P to push."
+fi

docs/pyproject.toml

@@ -0,0 +1,9 @@
+[project]
+name = "zrepl-docs"
+version = "0.0.0"
+description = "zrepl documentation build dependencies"
+requires-python = ">=3.14"
+dependencies = [
+    "Sphinx>=7.2,<8",
+    "sphinx-rtd-theme>=1.3,<2",
+]

docs/quickstart.rst

@@ -0,0 +1,101 @@
+.. include:: global.rst.inc
+
+.. _quickstart-toc:
+
+***********************
+Quick Start by Use Case
+***********************
+
+The goal of this quick-start guide is to give you an impression of how zrepl can accomodate your use case.
+
+Install zrepl
+=============
+
+Follow the :ref:`OS-specific installation instructions <installation_toc>` and come back here.
+
+Overview Of How zrepl Works
+============================
+
+Check out the :ref:`overview section <job-overview>` to get a rough idea of what you are going to configure in the next step, then come back here.
+
+Configuration Examples
+======================
+
+zrepl is configured through a YAML configuration file in ``/etc/zrepl/zrepl.yml``.
+We have prepared example use cases that show-case typical deployments and different functionality of zrepl.
+We encourage you to read through all of the examples to get an idea of what zrepl has to offer, and how you can mix-and-match configurations for your use case.
+Keep the :ref:`full config documentation <configuration_toc>` handy if a config snippet is unclear.
+
+**Example Use Cases**
+
+.. toctree::
+   :titlesonly:
+
+   quickstart/continuous_server_backup
+   quickstart/backup_to_external_disk
+   quickstart/fan_out_replication
+
+Use ``zrepl configcheck`` to validate your configuration.
+No output indicates that everything is fine.
+
+.. NOTE::
+
+   Please open an issue on GitHub if your use case for zrepl is significantly different from those listed above.
+   Or even better, write it up in the same style as above and open a PR!
+
+.. _quickstart-apply-config:
+
+Apply Configuration Changes
+===========================
+
+We hope that you have found a configuration that fits your use case.
+Use ``zrepl configcheck`` once again to make sure the config is correct (output indicates that everything is fine).
+Then restart the zrepl daemon on all systems involved in the replication, likely using ``service zrepl restart`` or ``systemctl restart zrepl``.
+
+.. WARNING::
+
+   Please :ref:`read up carefully <prune>` on the pruning rules before applying the config.
+   In particular, note that most example configs apply to all snapshots, not just zrepl-created snapshots.
+   Use the following keep rule on sender and receiver to prevent this:
+
+   ::
+      
+      - type: regex
+        negate: true
+        regex: "^zrepl_.*" # <- the 'prefix' specified in snapshotting.prefix
+
+
+Watch it Work
+=============
+
+Run ``zrepl status`` on the active side of the replication setup to monitor snaphotting, replication and pruning activity.
+To re-trigger replication (snapshots are separate!), use ``zrepl signal wakeup JOBNAME``.
+(refer to the example use case document if you are uncertain which job you want to wake up).
+
+You can also use basic UNIX tools to inspect see what's going on.
+If you like tmux, here is a handy script that works on FreeBSD: ::
+
+    pkg install gnu-watch tmux
+    tmux new -s zrepl -d
+    tmux split-window -t zrepl "tail -f /var/log/messages"
+    tmux split-window -t zrepl "gnu-watch 'zfs list -t snapshot -o name,creation -s creation'"
+    tmux split-window -t zrepl "zrepl status"
+    tmux select-layout -t zrepl tiled
+    tmux attach -t zrepl
+
+The Linux equivalent might look like this: ::
+
+    # make sure tmux is installed & let's assume you use systemd + journald
+    tmux new -s zrepl -d
+    tmux split-window -t zrepl  "journalctl -f -u zrepl.service"
+    tmux split-window -t zrepl "watch 'zfs list -t snapshot -o name,creation -s creation'"
+    tmux split-window -t zrepl "zrepl status"
+    tmux select-layout -t zrepl tiled
+    tmux attach -t zrepl
+
+What Next?
+==========
+
+* Read more about :ref:`configuration format, options & job types <configuration_toc>`
+* Configure :ref:`logging <logging>` \& :ref:`monitoring <monitoring>`.
+

docs/quickstart/backup_to_external_disk.rst

@@ -0,0 +1,49 @@
+.. include:: ../global.rst.inc
+
+.. _quickstart-backup-to-external-disk:
+
+Local Snapshots + Offline Backup to an External Disk
+====================================================
+
+This config example shows how we can use zrepl to make periodic snapshots of our local workstation and back it up to a zpool on an external disk which we occassionally connect.
+
+The local snapshots should be taken every 15 minutes for pain-free recovery from CLI disasters (``rm -rf /`` and the like).
+However, we do not want to keep the snapshots around for very long because our workstation is a little tight on disk space.
+Thus, we only keep one hour worth of high-resolution snapshots, then fade them out to one per hour for a day (24 hours), then one per day for 14 days.
+
+At the end of each work day, we connect our external disk that serves as our workstation's local offline backup.
+We want zrepl to inspect the filesystems and snapshots on the external pool, figure out which snapshots were created since the last time we connected the external disk, and use incremental replication to efficiently mirror our workstation to our backup disk.
+Afterwards, we want to clean up old snapshots on the backup pool: we want to keep all snapshots younger than one hour, 24 for each hour of the first day, then 360 daily backups.
+
+A few additional requirements:
+
+* Snapshot creation and pruning on our workstation should happen in the background, without interaction from our side.
+* However, we want to explicitly trigger replication via the command line.
+* We want to use OpenZFS native encryption to protect our data on the external disk.
+  It is absolutely critical that only encrypted data leaves our workstation.
+  **zrepl should provide an easy config knob for this and prevent replication of unencrypted datasets to the external disk.**
+* We want to be able to put off the backups for more than three weeks, i.e., longer than the lifetime of the automatically created snapshots on our workstation.
+  **zrepl should use bookmarks and holds to achieve this goal**.
+* When we yank out the drive during replication and go on a long vacation, we do *not* want the partially replicated snapshot to stick around as it would hold on to too much disk space over time.
+  Therefore, we want zrepl to deviate from its :ref:`default behavior <replication-option-protection>` and sacrifice resumability, but nonetheless retain the ability to do incremental replication once we return from our vacation.
+  **zrepl should provide an easy config knob to disable step holds for incremental replication**.
+
+The following config snippet implements the setup described above.
+You will likely want to customize some aspects mentioned in the top comment in the file.
+
+.. literalinclude:: ../../internal/config/samples/quickstart_backup_to_external_disk.yml
+
+
+Offline Backups with two (or more) External Disks
+-------------------------------------------------
+
+It can be desirable to have multiple disk-based backups of the same machine.
+To accomplish this,
+
+* create one zpool per external HDD, each with a unique name, and
+* define a pair of ``push`` and ``sink`` job **for each** of these zpools, each with a unique ``name``, ``listener_name``, and ``root_fs``.
+
+The unique names ensure that the jobs don't step on each others' toes when managing :ref:`zrepl's ZFS abstractions <zrepl-zfs-abstractions>` .
+
+
+:ref:`Click here <quickstart-apply-config>` to go back to the quickstart guide.

docs/quickstart/continuous_server_backup.rst

@@ -0,0 +1,94 @@
+.. include:: ../global.rst.inc
+
+.. _quickstart-continuous-replication:
+
+Continuous Backup of a Server
+=============================
+
+This config example shows how we can backup our ZFS-based server to another machine using a zrepl push job.
+
+* Production server ``prod`` with filesystems to back up:
+
+  * The entire pool ``zroot``
+  * except ``zroot/var/tmp`` and all child datasets of it
+  * and except ``zroot/usr/home/paranoid`` which belongs to a user doing backups themselves.
+
+* Backup server ``backups`` with a dataset sub-tree for use by zrepl:
+
+  * In our example, that will be ``storage/zrepl/sink/prod``.
+
+Our backup solution should fulfill the following requirements:
+
+* Periodically snapshot the filesystems on ``prod`` *every 10 minutes*
+* Incrementally replicate these snapshots to ``storage/zrepl/sink/prod/*`` on ``backups``
+* Keep only very few snapshots on ``prod`` to save disk space
+* Keep a fading history (24 hourly, 30 daily, 6 monthly) of snapshots on ``backups``
+* The network is untrusted - zrepl should use TLS to protect its communication and our data.
+
+Analysis
+--------
+
+We can model this situation as two jobs:
+
+* A **push job** on ``prod``
+
+  * Creates the snapshots
+  * Keeps a short history of local snapshots to enable incremental replication to ``backups``
+  * Connects to the ``zrepl daemon`` process on ``backups``
+  * Pushes snapshots ``backups``
+  * Prunes snapshots on ``backups`` after replication is complete
+
+* A **sink job** on ``backups``
+
+  * Accepts connections & responds to requests from ``prod``
+  * Limits client ``prod`` access to filesystem sub-tree ``storage/zrepl/sink/prod``
+
+Generate TLS Certificates
+-------------------------
+
+We use the :ref:`TLS client authentication transport <transport-tcp+tlsclientauth>` to protect our data on the wire.
+To get things going quickly, we skip setting up a CA and generate two self-signed certificates as described :ref:`here <transport-tcp+tlsclientauth-2machineopenssl>`.
+For convenience, we generate the key pairs on our local machine and distribute them using ssh:
+
+.. code-block:: bash
+
+   (name=backups; openssl req -x509 -sha256 -nodes \
+    -newkey rsa:4096 \
+    -days 365 \
+    -keyout $name.key \
+    -out $name.crt -addext "subjectAltName = DNS:$name" -subj "/CN=$name")
+
+   (name=prod; openssl req -x509 -sha256 -nodes \
+    -newkey rsa:4096 \
+    -days 365 \
+    -keyout $name.key \
+    -out $name.crt -addext "subjectAltName = DNS:$name" -subj "/CN=$name")
+
+   ssh root@backups "mkdir /etc/zrepl"
+   scp  backups.key backups.crt prod.crt root@backups:/etc/zrepl
+
+   ssh root@prod "mkdir /etc/zrepl"
+   scp  prod.key prod.crt backups.crt root@prod:/etc/zrepl
+
+Note that alternative transports exist, e.g. via :ref:`TCP without TLS <transport-tcp>` or :ref:`ssh <transport-ssh+stdinserver>`.
+
+Configure server ``prod``
+-------------------------
+
+We define a **push job** named ``prod_to_backups`` in ``/etc/zrepl/zrepl.yml`` on host ``prod`` :
+
+.. literalinclude:: ../../internal/config/samples/quickstart_continuous_server_backup_sender.yml
+
+.. _tutorial-configure-prod:
+
+Configure server ``backups``
+----------------------------
+
+We define a corresponding **sink job** named ``sink`` in ``/etc/zrepl/zrepl.yml`` on host ``backups`` :
+
+.. literalinclude:: ../../internal/config/samples/quickstart_continuous_server_backup_receiver.yml
+
+Go Back To Quickstart Guide
+---------------------------
+
+:ref:`Click here <quickstart-apply-config>` to go back to the quickstart guide.

docs/quickstart/fan_out_replication.rst

@@ -0,0 +1,93 @@
+.. include:: ../global.rst.inc
+
+.. _quickstart-fan-out-replication:
+
+Fan-out replication
+===================
+
+This quick-start example demonstrates how to implement a fan-out replication setup where datasets on a server (A) are replicated to multiple targets (B, C, etc.).
+
+This example uses multiple ``source`` jobs on server A and ``pull`` jobs on the target servers.
+
+.. WARNING::
+
+   Before implementing this setup, please see the caveats listed in the :ref:`fan-out replication configuration overview <fan-out-replication>`.
+
+Overview
+--------
+
+On the source server (A), there should be:
+
+* A ``snap`` job
+
+  * Creates the snapshots
+  * Handles the pruning of snapshots
+
+* A ``source`` job for target B
+
+  * Accepts connections from server B and B only
+
+* Further ``source`` jobs for each additional target (C, D, etc.)
+
+  * Listens on a unique port
+  * Only accepts connections from the specific target
+
+On each target server, there should be:
+
+* A ``pull`` job that connects to the corresponding ``source`` job on A
+
+  * ``prune_sender`` should keep all snapshots since A's ``snap`` job handles the pruning
+  * ``prune_receiver`` can be configured as appropriate on each target server
+
+Generate TLS Certificates
+-------------------------
+
+Mutual TLS via the :ref:`TLS client authentication transport <transport-tcp+tlsclientauth>` can be used to secure the connections between the servers. In this example, a self-signed certificate is created for each server without setting up a CA.
+
+.. code-block:: bash
+
+    source=a.example.com
+    targets=(
+        b.example.com
+        c.example.com
+        # ...
+    )
+
+    for server in "${source}" "${targets[@]}"; do
+        openssl req -x509 -sha256 -nodes \
+            -newkey rsa:4096 \
+            -days 365 \
+            -keyout "${server}.key" \
+            -out "${server}.crt" \
+            -addext "subjectAltName = DNS:${server}" \
+            -subj "/CN=${server}"
+    done
+
+    # Distribute each host's keypair
+    for server in "${source}" "${targets[@]}"; do
+        ssh root@"${server}" mkdir /etc/zrepl
+        scp "${server}".{crt,key} root@"${server}":/etc/zrepl/
+    done
+
+    # Distribute target certificates to the source
+    scp "${targets[@]/%/.crt}" root@"${source}":/etc/zrepl/
+
+    # Distribute source certificate to the targets
+    for server in "${targets[@]}"; do
+        scp "${source}.crt" root@"${server}":/etc/zrepl/
+    done
+
+Configure source server A
+-------------------------
+
+.. literalinclude:: ../../internal/config/samples/quickstart_fan_out_replication_source.yml
+
+Configure each target server
+----------------------------
+
+.. literalinclude:: ../../internal/config/samples/quickstart_fan_out_replication_target.yml
+
+Go Back To Quickstart Guide
+---------------------------
+
+:ref:`Click here <quickstart-apply-config>` to go back to the quickstart guide.

docs/requirements.txt

@@ -1,28 +0,0 @@
-Babel==2.5.1
-certifi==2017.11.5
-chardet==3.0.4
-click==6.7
-colorclass==2.2.0
-cryptography==1.7.1
-docutils==0.14
-idna==2.6
-imagesize==0.7.1
-Jinja2==2.10
-keyring==10.1
-keyrings.alt==1.3
-MarkupSafe==1.0
-pyasn1==0.1.9
-pycrypto==2.6.1
-Pygments==2.2.0
-pygobject==3.22.0
-pytz==2017.3
-pyxdg==0.25
-requests==2.18.4
-SecretStorage==2.3.1
-six==1.10.0
-snowballstemmer==1.2.1
-Sphinx==1.6.5
-sphinx-rtd-theme==0.2.4
-sphinxcontrib-versioning==2.2.1
-sphinxcontrib-websupport==1.0.1
-urllib3==1.22

docs/sphinxconf/conf.py

@@ -1,179 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-#
-# zrepl documentation build configuration file, created by
-# sphinx-quickstart on Wed Nov  8 22:28:10 2017.
-#
-# This file is execfile()d with the current directory set to its
-# containing dir.
-#
-# Note that not all possible configuration values are present in this
-# autogenerated file.
-#
-# All configuration values have a default; values that are commented out
-# serve to show the default.
-
-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-#
-# import os
-# import sys
-# sys.path.insert(0, os.path.abspath('.'))
-
-
-# -- General configuration ------------------------------------------------
-
-# If your documentation needs a minimal Sphinx version, state it here.
-#
-# needs_sphinx = '1.0'
-
-# Add any Sphinx extension module names here, as strings. They can be
-# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
-# ones.
-extensions = ['sphinx.ext.todo',
-    'sphinx.ext.githubpages',
-    'sphinx.ext.extlinks']
-
-# Add any paths that contain templates here, relative to this directory.
-templates_path = ['../_templates']
-
-# The suffix(es) of source filenames.
-# You can specify multiple suffix as a list of string:
-#
-# source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
-
-# The master toctree document.
-master_doc = 'index'
-
-# General information about the project.
-project = 'zrepl'
-copyright = '2017-2018, Christian Schwarz'
-author = 'Christian Schwarz'
-
-# The version info for the project you're documenting, acts as replacement for
-# |version| and |release|, also used in various other places throughout the
-# built documents.
-#
-# The short X.Y version.
-#version = set by sphinxcontrib-versioning
-# The full version, including alpha/beta/rc tags.
-#release = version
-
-# The language for content autogenerated by Sphinx. Refer to documentation
-# for a list of supported languages.
-#
-# This is also used if you do content translation via gettext catalogs.
-# Usually you set "language" from the command line for these cases.
-language = None
-
-# List of patterns, relative to source directory, that match files and
-# directories to ignore when looking for source files.
-# This patterns also effect to html_static_path and html_extra_path
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
-
-# The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'sphinx'
-
-# If true, `todo` and `todoList` produce output, else they produce nothing.
-todo_include_todos = True
-
-
-# -- Options for HTML output ----------------------------------------------
-
-# The theme to use for HTML and HTML Help pages.  See the documentation for
-# a list of builtin themes.
-#
-html_theme = 'sphinx_rtd_theme'
-
-# Theme options are theme-specific and customize the look and feel of a theme
-# further.  For a list of options available for each theme, see the
-# documentation.
-#
-# html_theme_options = {}
-
-# Add any paths that contain custom static files (such as style sheets) here,
-# relative to this directory. They are copied after the builtin static files,
-# so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['../_static']
-
-
-html_logo = '../_static/zrepl.svg'
-
-html_context = {
-  # https://github.com/rtfd/sphinx_rtd_theme/issues/205
-  # Add 'Edit on Github' link instead of 'View page source'
-  "display_github": True, 
-  "github_user": "zrepl",
-  "github_repo": "zrepl",
-  "github_version": "master",
-  "conf_py_path": "/docs/",
-  "source_suffix": source_suffix,
-}
-
-# -- Options for HTMLHelp output ------------------------------------------
-
-# Output file base name for HTML help builder.
-htmlhelp_basename = 'zrepldoc'
-
-
-# -- Options for LaTeX output ---------------------------------------------
-
-latex_elements = {
-    # The paper size ('letterpaper' or 'a4paper').
-    #
-    # 'papersize': 'letterpaper',
-
-    # The font size ('10pt', '11pt' or '12pt').
-    #
-    # 'pointsize': '10pt',
-
-    # Additional stuff for the LaTeX preamble.
-    #
-    # 'preamble': '',
-
-    # Latex figure (float) alignment
-    #
-    # 'figure_align': 'htbp',
-}
-
-# Grouping the document tree into LaTeX files. List of tuples
-# (source start file, target name, title,
-#  author, documentclass [howto, manual, or own class]).
-latex_documents = [
-    (master_doc, 'zrepl.tex', 'zrepl Documentation',
-     'Christian Schwarz', 'manual'),
-]
-
-
-# -- Options for manual page output ---------------------------------------
-
-# One entry per manual page. List of tuples
-# (source start file, name, description, authors, manual section).
-man_pages = [
-    (master_doc, 'zrepl', 'zrepl Documentation',
-     [author], 1)
-]
-
-
-# -- Options for Texinfo output -------------------------------------------
-
-# Grouping the document tree into Texinfo files. List of tuples
-# (source start file, target name, title, author,
-#  dir menu entry, description, category)
-texinfo_documents = [
-    (master_doc, 'zrepl', 'zrepl Documentation',
-     author, 'zrepl', 'One line description of project.',
-     'Miscellaneous'),
-]
-
-
-# -- Options for the extlinks extension -----------------------------------
-# http://www.sphinx-doc.org/en/stable/ext/extlinks.html
-extlinks = {
-    'issue':('https://github.com/zrepl/zrepl/issues/%s', 'issue #'),
-    'sampleconf':('https://github.com/zrepl/zrepl/blob/master/config/samples%s', 'config/samples'),
-    'commit':('https://github.com/zrepl/zrepl/commit/%s', 'commit '),
-        }
-

docs/supporters.rst

@@ -0,0 +1,60 @@
+.. include:: global.rst.inc
+
+.. _supporters:
+
+|Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal|
+
+zrepl is a spare-time project primarily developed by `Christian Schwarz <https://cschwarz.com>`_.
+You can support maintenance and feature development through one of the services listed above.
+For SEPA wire transfer and **commercial support**, please `contact Christian directly <https://cschwarz.com>`_.
+
+**Thanks for your support!**
+
+.. NOTE ::
+
+   PayPal takes a relatively high fixed processing fee plus percentage of the donation.
+   Larger less-frequent donations make more sense there.
+
+Supporters
+==========
+
+We would like to thank the following people and organizations for supporting zrepl through monetary and other means:
+
+.. |supporter-std| raw:: html
+
+   <div class="fa fa-star-o" style="width: 1em;"></div>
+
+.. |supporter-gold| raw:: html
+
+   <div class="fa fa-star" style="width: 1em;"></div>
+
+.. |supporter-code| raw:: html
+
+   <div class="fa fa-code" style="width: 1em;"></div>
+
+* |supporter-gold| `Hostsharing eG – die Hosting-Genossenschaft <https://www.hostsharing.net/>`_
+* |supporter-std| `Max Christian Pohle <https://coderonline.de>`_
+* |supporter-gold| Prominic.NET, Inc.
+* |supporter-std| Torsten Blum
+* |supporter-gold| Cyberiada GmbH
+* |supporter-std| `Gordon Schulz <https://github.com/azmodude>`_
+* |supporter-std| `@jwittlincohen <https://github.com/jwittlincohen>`_
+* |supporter-std| `Michael D. Schmitt <https://waterbendingscroll.dancingdragons.org>`_
+* |supporter-std| `Hans Schulz <https://github.com/schulzh>`_
+* |supporter-std| Henning Kessler
+* |supporter-std| `John Ramsden <https://github.com/johnramsden>`_
+* |supporter-std| `DrLuke <https://github.com/drluke>`_
+* |supporter-gold| `Mateusz Kwiatkowski (runhyve.app) <https://runhyve.app>`_
+* |supporter-std| `Gaelan D'costa <https://www.robot-disco.net>`_
+* |supporter-std| `Tenzin Lhakhang <https://confluence.tenzin.io>`_
+* |supporter-std| `Lapo Luchini <https://github.com/lapo-luchini>`_
+* |supporter-std| `F. Schmid <https://github.com/tdschmidl>`_
+* |supporter-gold| `MNX.io <https://mnx.io>`_
+* |supporter-std| `Marshall Clyburn <https://github.com/mdclyburn>`_
+* |supporter-code| `Ross Williams <https://github.com/overhacked>`_
+* |supporter-gold| Mike T.
+* |supporter-code| `Justin Scholz <https://github.com/JMoVS>`_
+* |supporter-code| `InsanePrawn <https://github.com/InsanePrawn>`_
+* |supporter-code| `Ben Woods <https://www.freshports.org/sysutils/zrepl/>`_
+* |supporter-code| `Janis Streib <https://github.com/janisstreib>`_
+* |supporter-code| `Anton Schirg <https://github.com/antonxy>`_

docs/tutorial.rst

@@ -1,180 +0,0 @@
-.. include:: global.rst.inc
-
-.. _tutorial:
-
-Tutorial
-========
-
-
-This tutorial shows how zrepl can be used to implement a ZFS-based push backup.
-We assume the following scenario:
-
-* Production server ``prod`` with filesystems to back up:
-
-  * ``zroot/var/db``
-  * ``zroot/usr/home`` and all its child filesystems
-  * **except** ``zroot/usr/home/paranoid`` belonging to a user doing backups themselves
-
-* Backup server ``backups`` with
-
-  * Filesystem ``storage/zrepl/sink/prod`` + children dedicated to backups of ``prod``
-
-Our backup solution should fulfill the following requirements:
-
-* Periodically snapshot the filesystems on ``prod`` *every 10 minutes*
-* Incrementally replicate these snapshots to ``storage/zrepl/sink/prod/*`` on ``backups``
-* Keep only very few snapshots on ``prod`` to save disk space
-* Keep a fading history (24 hourly, 30 daily, 6 monthly) of snapshots on ``backups``
-
-Analysis
---------
-
-We can model this situation as two jobs:
-
-* A **push job** on ``prod``
-
-  * Creates the snapshots
-  * Keeps a short history of local snapshots to enable incremental replication to ``backups``
-  * Connects to the ``zrepl daemon`` process on ``backups``
-  * Pushes snapshots ``backups``
-  * Prunes snapshots on ``backups`` after replication is complete
-
-* A **sink job** on ``backups``
-
-  * Accepts connections & responds to requests from ``prod``
-  * Limits client ``prod`` access to filesystem sub-tree ``storage/zrepl/sink/prod``
-
-Install zrepl
--------------
-
-Follow the :ref:`OS-specific installation instructions <installation>` and come back here.
-
-Generate TLS Certificates
--------------------------
-
-We use the `TLS client authentication transport <transport-tcp+tlsclientauth>` to protect our data on the wire.
-To get things going quickly, we skip setting up a CA and generate two self-signed certificates as described :ref:`here <transport-tcp+tlsclientauth-2machineopenssl>`.
-Again, for convenience, We generate the key pairs on our local machine and distribute them using ssh:
-
-.. code-block:: bash
-   :emphasize-lines: 6,13
-
-   openssl req -x509 -sha256 -nodes \
-      -newkey rsa:4096 \
-      -days 365 \
-      -keyout backups.key \
-      -out backups.crt
-   # ... and use "backups" as Common Name (CN)
-
-   openssl req -x509 -sha256 -nodes \
-      -newkey rsa:4096 \
-      -days 365 \
-      -keyout prod.key \
-      -out prod.crt
-   # ... and use "prod" as Common Name (CN)
-
-   ssh root@backups "mkdir /etc/zrepl"
-   scp  backups.key backups.crt prod.crt root@backups:/etc/zrepl
-
-   ssh root@prod "mkdir /etc/zrepl"
-   scp  prod.key prod.crt backups.crt root@prod:/etc/zrepl
-
-
-Configure server ``prod``
-----------------------------
-
-We define a **push job** named ``prod_to_backups`` in ``/etc/zrepl/zrepl.yml`` on host ``prod`` : ::
-
-    jobs:
-    - name: prod_to_backups
-      type: push 
-      connect:
-        type: tls
-        address: "backups.example.com:8888"
-        ca: /etc/zrepl/backups.crt
-        cert: /etc/zrepl/prod.crt
-        key:  /etc/zrepl/prod.key
-        server_cn: "backups"
-      filesystems: {
-        "zroot/var/db:": true,
-        "zroot/usr/home<": true,
-        "zroot/usr/home/paranoid": false
-      }
-      snapshotting:
-        type: periodic
-        prefix: zrepl_
-        interval: 10m
-      pruning:
-        keep_sender:
-        - type: not_replicated
-        - type: last_n
-          count: 10
-        keep_receiver:
-        - type: grid
-          grid: 1x1h(keep=all) | 24x1h | 30x1d | 6x30d
-          regex: "^zrepl_"
-
-.. _tutorial-configure-prod:
-
-Configure server ``prod``
--------------------------
-
-We define a corresponding **sink job** named ``sink`` in ``/etc/zrepl/zrepl.yml`` on host ``prod`` : ::
-
-    jobs:
-    - name: sink
-      type: sink 
-      serve:
-         type: tls
-         listen: ":8888"
-         ca: "/etc/zrepl/prod.crt"
-         cert: "/etc/zrepl/backups.crt"
-         key: "/etc/zrepl/backups.key"
-         client_cns:
-           - "prod"
-      root_fs: "storage/zrepl/sink"
-
-
-Apply Configuration Changes
----------------------------
-
-We use ``zrepl configcheck`` before to catch any configuration errors: no output indicates that everything is fine.
-If that is the case, restart the zrepl daemon on **both** ``prod`` and ``backups`` using ``service zrepl restart`` or ``systemctl restart zrepl``.
-
-
-Watch it Work
--------------
-
-Run ``zrepl status`` on ``prod`` to monitor the replication and pruning activity.
-To re-trigger replication (snapshots are separate!), use ``zrepl signal wakeup prod_to_backups`` on ``prod``.
-
-If you like tmux, here is a handy script that works on FreeBSD: ::
-
-    pkg install gnu-watch tmux
-    tmux new -s zrepl -d
-    tmux split-window -t zrepl "tail -f /var/log/messages"
-    tmux split-window -t zrepl "gnu-watch 'zfs list -t snapshot -o name,creation -s creation | grep zrepl_'"
-    tmux split-window -t zrepl "zrepl status"
-    tmux select-layout -t zrepl tiled
-    tmux attach -t zrepl
-
-The Linux equivalent might look like this: ::
-
-    # make sure tmux is installed & let's assume you use systemd + journald
-    tmux new -s zrepl -d
-    tmux split-window -t zrepl  "journalctl -f -u zrepl.service"
-    tmux split-window -t zrepl "watch 'zfs list -t snapshot -o name,creation -s creation | grep zrepl_'"
-    tmux split-window -t zrepl "zrepl status"
-    tmux select-layout -t zrepl tiled
-    tmux attach -t zrepl
-
-Summary
--------
-
-Congratulations, you have a working pull backup. Where to go next?
-
-* Read more about :ref:`configuration format, options & job types <configuration_toc>`
-* Configure :ref:`logging <logging>` \& :ref:`monitoring <monitoring>`.
-* Learn about :ref:`implementation details <implementation_toc>` of zrepl.
-
-

docs/usage.rst

@@ -13,6 +13,8 @@ CLI Overview
     The zrepl binary is self-documenting:
     run ``zrepl help`` for an overview of the available subcommands or ``zrepl SUBCOMMAND --help`` for information on available flags, etc.
 
+.. _cli-signal-wakeup:
+
 .. list-table::
     :widths: 30 70
     :header-rows: 1
@@ -24,7 +26,7 @@ CLI Overview
     * - ``zrepl daemon``
       - run the daemon, required for all zrepl functionality
     * - ``zrepl status``
-      - show job activity, or with ``--raw`` for JSON output
+      - show job activity, or with ``--mode raw`` for JSON output
     * - ``zrepl stdinserver``
       - see :ref:`transport-ssh+stdinserver`
     * - ``zrepl signal wakeup JOB``
@@ -33,6 +35,11 @@ CLI Overview
       - manually abort current replication + pruning of JOB
     * - ``zrepl configcheck``
       - check if config can be parsed without errors
+    * - ``zrepl migrate``
+      - | perform on-disk state / ZFS property migrations
+        | (see :ref:`changelog <changelog>` for details)
+    * - ``zrepl zfs-abstraction``
+      - list and remove zrepl's abstractions on top of ZFS, e.g. holds and step bookmarks (see :ref:`overview <replication-cursor-and-last-received-hold>` )
 
 .. _usage-zrepl-daemon:
 
@@ -43,7 +50,7 @@ zrepl daemon
 All actual work zrepl does is performed by a daemon process.
 The daemon supports structured :ref:`logging <logging>` and provides :ref:`monitoring endpoints <monitoring>`.
 
-When installating from a package, the package maintainer should have provided an init script / systemd.service file.
+When installing from a package, the package maintainer should have provided an init script / systemd.service file.
 You should thus be able to start zrepl daemon using your init system.
 
 Alternatively, or for running zrepl in the foreground, simply execute ``zrepl daemon``.
@@ -64,3 +71,80 @@ Restarting
 The daemon handles SIGINT and SIGTERM for graceful shutdown.
 Graceful shutdown means at worst that a job will not be rescheduled for the next interval.
 The daemon exits as soon as all jobs have reported shut down.
+
+Systemd Unit File
+~~~~~~~~~~~~~~~~~
+
+A systemd service definition template is available in :repomasterlink:`dist/systemd`.
+Note that some of the options only work on recent versions of systemd.
+Any help & improvements are very welcome, see :issue:`145`.
+
+
+
+============
+Ops Runbooks
+============
+
+
+.. toctree::
+
+   usage/runbooks/migrating_sending_side_to_new_zpool.rst
+
+
+.. _usage-platform-tests:
+
+==============
+Platform Tests
+==============
+
+Along with the main ``zrepl`` binary, we release the ``platformtest`` binaries.
+The zrepl platform tests are an integration test suite that is complementary to the pure Go unit tests.
+Any test that needs to interact with ZFS is a platform test.
+
+The platform need to run as root.
+For each test, we create a fresh dummy zpool backed by a file-based vdev.
+The file path, and a root mountpoint for the dummy zpool, must be specified on the command line:
+
+::
+
+   mkdir -p /tmp/zreplplatformtest
+   ./platformtest \
+       -poolname 'zreplplatformtest' \  # <- name must contain zreplplatformtest
+       -imagepath /tmp/zreplplatformtest.img \ # <- zrepl will create the file
+       -mountpoint /tmp/zreplplatformtest # <- must exist
+
+
+.. WARNING::
+
+   ``platformtest`` will unconditionally overwrite the file at `imagepath`
+   and unconditionally ``zpool destroy $poolname``.
+   So, don't use a production poolname, and consider running the test in a VM.
+   It'll be a lot faster as well because the underlying operations, ``zfs list`` in particular, will be faster.
+
+
+While the platformtests are running, there will be a log of log output.
+After all tests have run, it prints a summary with a list of tests, grouped by result type (success, failure, skipped):
+
+::
+
+   PASSING TESTS:
+     github.com/zrepl/zrepl/platformtest/tests.BatchDestroy
+     github.com/zrepl/zrepl/platformtest/tests.CreateReplicationCursor
+     github.com/zrepl/zrepl/platformtest/tests.GetNonexistent
+     github.com/zrepl/zrepl/platformtest/tests.HoldsWork
+     ...
+     github.com/zrepl/zrepl/platformtest/tests.SendStreamNonEOFReadErrorHandling
+     github.com/zrepl/zrepl/platformtest/tests.UndestroyableSnapshotParsing
+   SKIPPED TESTS:
+     github.com/zrepl/zrepl/platformtest/tests.SendArgsValidationEncryptedSendOfUnencryptedDatasetForbidden__EncryptionSupported_false
+   FAILED TESTS: []
+
+
+If there is a failure, or a skipped test that you believe should be passing, re-run the test suite, capture stderr & stdout to a text file, and create an issue on GitHub.
+
+To run a specific test case, or a subset of tests matched by regex, use the ``-run REGEX`` command line flag.
+
+To stop test execution at the first failing test, and prevent cleanup of the dummy zpool, use the ``-failure.stop-and-keep-pool`` flag.
+
+To build the platformtests yourself, use ``make test-platform-bin``.
+There's also the ``make test-platform`` target to run the platform tests with a default command line.

docs/usage/runbooks/migrating_sending_side_to_new_zpool.rst

@@ -0,0 +1,36 @@
+
+Migrating Sending Side
+~~~~~~~~~~~~~~~~~~~~~~
+
+**Objective**:
+Move sending-side zpool to new hardware.
+Make the move fully transparent to the sending-side jobs.
+After the move is done, all sending-side zrepl jobs should continue to work as if the move had not happened.
+In particular, incremental replication should be able to pick up where it left before the move.
+
+Suppose we want to migrate all data from one zpool ``oldpool`` to another zpool ``newpool``.
+A possible reason might be that we want to change RAID levels, ``ashift``, or just migrate over to next-gen hardware.
+
+If the pool names are different, zrepl's matching between sender and receiver dataset will break becase the receive-side dataset names contain ``oldpool``.
+To avoid this, we will need the name of the new pool to match that of the old pool.
+The following steps will accomplish this:
+
+1. Stop zrepl.
+2. Create the new pool: ``zpool create newpool ...``
+3. Take a snapshot of the old pool so that you have something that you can ``zfs send``.
+   For example, run ``zfs snapshot -r oldpool@migration_oldpool_newpool``.
+4. Send all of the oldpool's datasets to the new pool:
+   ``zfs send -R oldpool@migration_oldpool_newpool | zfs recv -F newpool``
+5. Export the old pool: ``zpool export oldpool``
+6. Export the new pool: ``zpool export newpool``
+7. (Optional) Change the name of the old pool to something that does not conflict with the new pool.
+   We are going to use the name ``oldoldpool`` in this example.
+   Use ``zpool import`` with no arguments to see the pool id.
+   Then ``zpool import <id> oldoldpool && zpool export oldoldpool``.
+8. Import the new pool, while changing the name to match the old pool: ``zpool import newpool oldpool``
+9. Start zrepl again and wake up the relevant jobs.
+10. Use ``zrepl status`` or you monitoring to ensure that replication works.
+    The best test is an end-to-end test where you write some junk data on a sender dataset and wait until a snapshot with that data appears on the receiving side.
+11. Once you are confident that replication is working, you may dispose of the old pool.
+
+Note that, depending on pruning rules, it will not be possible to switch back to the old pool seamlessly, i.e., without a full re-replication.

docs/uv.lock

@@ -0,0 +1,306 @@
+version = 1
+revision = 3
+requires-python = ">=3.14"
+
+[[package]]
+name = "alabaster"
+version = "0.7.16"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/c9/3e/13dd8e5ed9094e734ac430b5d0eb4f2bb001708a8b7856cbf8e084e001ba/alabaster-0.7.16.tar.gz", hash = "sha256:75a8b99c28a5dad50dd7f8ccdd447a121ddb3892da9e53d1ca5cca3106d58d65", size = 23776, upload-time = "2024-01-10T00:56:10.189Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/32/34/d4e1c02d3bee589efb5dfa17f88ea08bdb3e3eac12bc475462aec52ed223/alabaster-0.7.16-py3-none-any.whl", hash = "sha256:b46733c07dce03ae4e150330b975c75737fa60f0a7c591b6c8bf4928a28e2c92", size = 13511, upload-time = "2024-01-10T00:56:08.388Z" },
+]
+
+[[package]]
+name = "babel"
+version = "2.18.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7d/b2/51899539b6ceeeb420d40ed3cd4b7a40519404f9baf3d4ac99dc413a834b/babel-2.18.0.tar.gz", hash = "sha256:b80b99a14bd085fcacfa15c9165f651fbb3406e66cc603abf11c5750937c992d", size = 9959554, upload-time = "2026-02-01T12:30:56.078Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/77/f5/21d2de20e8b8b0408f0681956ca2c69f1320a3848ac50e6e7f39c6159675/babel-2.18.0-py3-none-any.whl", hash = "sha256:e2b422b277c2b9a9630c1d7903c2a00d0830c409c59ac8cae9081c92f1aeba35", size = 10196845, upload-time = "2026-02-01T12:30:53.445Z" },
+]
+
+[[package]]
+name = "certifi"
+version = "2026.1.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/e0/2d/a891ca51311197f6ad14a7ef42e2399f36cf2f9bd44752b3dc4eab60fdc5/certifi-2026.1.4.tar.gz", hash = "sha256:ac726dd470482006e014ad384921ed6438c457018f4b3d204aea4281258b2120", size = 154268, upload-time = "2026-01-04T02:42:41.825Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e6/ad/3cc14f097111b4de0040c83a525973216457bbeeb63739ef1ed275c1c021/certifi-2026.1.4-py3-none-any.whl", hash = "sha256:9943707519e4add1115f44c2bc244f782c0249876bf51b6599fee1ffbedd685c", size = 152900, upload-time = "2026-01-04T02:42:40.15Z" },
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.4.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/13/69/33ddede1939fdd074bce5434295f38fae7136463422fe4fd3e0e89b98062/charset_normalizer-3.4.4.tar.gz", hash = "sha256:94537985111c35f28720e43603b8e7b43a6ecfb2ce1d3058bbe955b73404e21a", size = 129418, upload-time = "2025-10-14T04:42:32.879Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2a/35/7051599bd493e62411d6ede36fd5af83a38f37c4767b92884df7301db25d/charset_normalizer-3.4.4-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:da3326d9e65ef63a817ecbcc0df6e94463713b754fe293eaa03da99befb9a5bd", size = 207746, upload-time = "2025-10-14T04:41:33.773Z" },
+    { url = "https://files.pythonhosted.org/packages/10/9a/97c8d48ef10d6cd4fcead2415523221624bf58bcf68a802721a6bc807c8f/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8af65f14dc14a79b924524b1e7fffe304517b2bff5a58bf64f30b98bbc5079eb", size = 147889, upload-time = "2025-10-14T04:41:34.897Z" },
+    { url = "https://files.pythonhosted.org/packages/10/bf/979224a919a1b606c82bd2c5fa49b5c6d5727aa47b4312bb27b1734f53cd/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74664978bb272435107de04e36db5a9735e78232b85b77d45cfb38f758efd33e", size = 143641, upload-time = "2025-10-14T04:41:36.116Z" },
+    { url = "https://files.pythonhosted.org/packages/ba/33/0ad65587441fc730dc7bd90e9716b30b4702dc7b617e6ba4997dc8651495/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:752944c7ffbfdd10c074dc58ec2d5a8a4cd9493b314d367c14d24c17684ddd14", size = 160779, upload-time = "2025-10-14T04:41:37.229Z" },
+    { url = "https://files.pythonhosted.org/packages/67/ed/331d6b249259ee71ddea93f6f2f0a56cfebd46938bde6fcc6f7b9a3d0e09/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d1f13550535ad8cff21b8d757a3257963e951d96e20ec82ab44bc64aeb62a191", size = 159035, upload-time = "2025-10-14T04:41:38.368Z" },
+    { url = "https://files.pythonhosted.org/packages/67/ff/f6b948ca32e4f2a4576aa129d8bed61f2e0543bf9f5f2b7fc3758ed005c9/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ecaae4149d99b1c9e7b88bb03e3221956f68fd6d50be2ef061b2381b61d20838", size = 152542, upload-time = "2025-10-14T04:41:39.862Z" },
+    { url = "https://files.pythonhosted.org/packages/16/85/276033dcbcc369eb176594de22728541a925b2632f9716428c851b149e83/charset_normalizer-3.4.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:cb6254dc36b47a990e59e1068afacdcd02958bdcce30bb50cc1700a8b9d624a6", size = 149524, upload-time = "2025-10-14T04:41:41.319Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/f2/6a2a1f722b6aba37050e626530a46a68f74e63683947a8acff92569f979a/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c8ae8a0f02f57a6e61203a31428fa1d677cbe50c93622b4149d5c0f319c1d19e", size = 150395, upload-time = "2025-10-14T04:41:42.539Z" },
+    { url = "https://files.pythonhosted.org/packages/60/bb/2186cb2f2bbaea6338cad15ce23a67f9b0672929744381e28b0592676824/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:47cc91b2f4dd2833fddaedd2893006b0106129d4b94fdb6af1f4ce5a9965577c", size = 143680, upload-time = "2025-10-14T04:41:43.661Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/a5/bf6f13b772fbb2a90360eb620d52ed8f796f3c5caee8398c3b2eb7b1c60d/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:82004af6c302b5d3ab2cfc4cc5f29db16123b1a8417f2e25f9066f91d4411090", size = 162045, upload-time = "2025-10-14T04:41:44.821Z" },
+    { url = "https://files.pythonhosted.org/packages/df/c5/d1be898bf0dc3ef9030c3825e5d3b83f2c528d207d246cbabe245966808d/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2b7d8f6c26245217bd2ad053761201e9f9680f8ce52f0fcd8d0755aeae5b2152", size = 149687, upload-time = "2025-10-14T04:41:46.442Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/42/90c1f7b9341eef50c8a1cb3f098ac43b0508413f33affd762855f67a410e/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:799a7a5e4fb2d5898c60b640fd4981d6a25f1c11790935a44ce38c54e985f828", size = 160014, upload-time = "2025-10-14T04:41:47.631Z" },
+    { url = "https://files.pythonhosted.org/packages/76/be/4d3ee471e8145d12795ab655ece37baed0929462a86e72372fd25859047c/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:99ae2cffebb06e6c22bdc25801d7b30f503cc87dbd283479e7b606f70aff57ec", size = 154044, upload-time = "2025-10-14T04:41:48.81Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/6f/8f7af07237c34a1defe7defc565a9bc1807762f672c0fde711a4b22bf9c0/charset_normalizer-3.4.4-cp314-cp314-win32.whl", hash = "sha256:f9d332f8c2a2fcbffe1378594431458ddbef721c1769d78e2cbc06280d8155f9", size = 99940, upload-time = "2025-10-14T04:41:49.946Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/51/8ade005e5ca5b0d80fb4aff72a3775b325bdc3d27408c8113811a7cbe640/charset_normalizer-3.4.4-cp314-cp314-win_amd64.whl", hash = "sha256:8a6562c3700cce886c5be75ade4a5db4214fda19fede41d9792d100288d8f94c", size = 107104, upload-time = "2025-10-14T04:41:51.051Z" },
+    { url = "https://files.pythonhosted.org/packages/da/5f/6b8f83a55bb8278772c5ae54a577f3099025f9ade59d0136ac24a0df4bde/charset_normalizer-3.4.4-cp314-cp314-win_arm64.whl", hash = "sha256:de00632ca48df9daf77a2c65a484531649261ec9f25489917f09e455cb09ddb2", size = 100743, upload-time = "2025-10-14T04:41:52.122Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/4c/925909008ed5a988ccbb72dcc897407e5d6d3bd72410d69e051fc0c14647/charset_normalizer-3.4.4-py3-none-any.whl", hash = "sha256:7a32c560861a02ff789ad905a2fe94e3f840803362c84fecf1851cb4cf3dc37f", size = 53402, upload-time = "2025-10-14T04:42:31.76Z" },
+]
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697, upload-time = "2022-10-25T02:36:22.414Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
+]
+
+[[package]]
+name = "docutils"
+version = "0.18.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/57/b1/b880503681ea1b64df05106fc7e3c4e3801736cf63deffc6fa7fc5404cf5/docutils-0.18.1.tar.gz", hash = "sha256:679987caf361a7539d76e584cbeddc311e3aee937877c87346f31debc63e9d06", size = 2043249, upload-time = "2021-11-23T17:49:42.043Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8d/14/69b4bad34e3f250afe29a854da03acb6747711f3df06c359fa053fae4e76/docutils-0.18.1-py2.py3-none-any.whl", hash = "sha256:23010f129180089fbcd3bc08cfefccb3b890b0050e1ca00c867036e9d161b98c", size = 570050, upload-time = "2021-11-23T17:49:38.556Z" },
+]
+
+[[package]]
+name = "idna"
+version = "3.11"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/6f/6d/0703ccc57f3a7233505399edb88de3cbd678da106337b9fcde432b65ed60/idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902", size = 194582, upload-time = "2025-10-12T14:55:20.501Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0e/61/66938bbb5fc52dbdf84594873d5b51fb1f7c7794e9c0f5bd885f30bc507b/idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea", size = 71008, upload-time = "2025-10-12T14:55:18.883Z" },
+]
+
+[[package]]
+name = "imagesize"
+version = "1.4.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a7/84/62473fb57d61e31fef6e36d64a179c8781605429fd927b5dd608c997be31/imagesize-1.4.1.tar.gz", hash = "sha256:69150444affb9cb0d5cc5a92b3676f0b2fb7cd9ae39e947a5e11a36b4497cd4a", size = 1280026, upload-time = "2022-07-01T12:21:05.687Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ff/62/85c4c919272577931d407be5ba5d71c20f0b616d31a0befe0ae45bb79abd/imagesize-1.4.1-py2.py3-none-any.whl", hash = "sha256:0d8d18d08f840c19d0ee7ca1fd82490fdc3729b7ac93f49870406ddde8ef8d8b", size = 8769, upload-time = "2022-07-01T12:21:02.467Z" },
+]
+
+[[package]]
+name = "jinja2"
+version = "3.1.6"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "markupsafe" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/df/bf/f7da0350254c0ed7c72f3e33cef02e048281fec7ecec5f032d4aac52226b/jinja2-3.1.6.tar.gz", hash = "sha256:0137fb05990d35f1275a587e9aee6d56da821fc83491a0fb838183be43f66d6d", size = 245115, upload-time = "2025-03-05T20:05:02.478Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/62/a1/3d680cbfd5f4b8f15abc1d571870c5fc3e594bb582bc3b64ea099db13e56/jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67", size = 134899, upload-time = "2025-03-05T20:05:00.369Z" },
+]
+
+[[package]]
+name = "markupsafe"
+version = "3.0.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7e/99/7690b6d4034fffd95959cbe0c02de8deb3098cc577c67bb6a24fe5d7caa7/markupsafe-3.0.3.tar.gz", hash = "sha256:722695808f4b6457b320fdc131280796bdceb04ab50fe1795cd540799ebe1698", size = 80313, upload-time = "2025-09-27T18:37:40.426Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/33/8a/8e42d4838cd89b7dde187011e97fe6c3af66d8c044997d2183fbd6d31352/markupsafe-3.0.3-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:eaa9599de571d72e2daf60164784109f19978b327a3910d3e9de8c97b5b70cfe", size = 11619, upload-time = "2025-09-27T18:37:06.342Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/64/7660f8a4a8e53c924d0fa05dc3a55c9cee10bbd82b11c5afb27d44b096ce/markupsafe-3.0.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c47a551199eb8eb2121d4f0f15ae0f923d31350ab9280078d1e5f12b249e0026", size = 12029, upload-time = "2025-09-27T18:37:07.213Z" },
+    { url = "https://files.pythonhosted.org/packages/da/ef/e648bfd021127bef5fa12e1720ffed0c6cbb8310c8d9bea7266337ff06de/markupsafe-3.0.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f34c41761022dd093b4b6896d4810782ffbabe30f2d443ff5f083e0cbbb8c737", size = 24408, upload-time = "2025-09-27T18:37:09.572Z" },
+    { url = "https://files.pythonhosted.org/packages/41/3c/a36c2450754618e62008bf7435ccb0f88053e07592e6028a34776213d877/markupsafe-3.0.3-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:457a69a9577064c05a97c41f4e65148652db078a3a509039e64d3467b9e7ef97", size = 23005, upload-time = "2025-09-27T18:37:10.58Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/20/b7fdf89a8456b099837cd1dc21974632a02a999ec9bf7ca3e490aacd98e7/markupsafe-3.0.3-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e8afc3f2ccfa24215f8cb28dcf43f0113ac3c37c2f0f0806d8c70e4228c5cf4d", size = 22048, upload-time = "2025-09-27T18:37:11.547Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/a7/591f592afdc734f47db08a75793a55d7fbcc6902a723ae4cfbab61010cc5/markupsafe-3.0.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:ec15a59cf5af7be74194f7ab02d0f59a62bdcf1a537677ce67a2537c9b87fcda", size = 23821, upload-time = "2025-09-27T18:37:12.48Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/33/45b24e4f44195b26521bc6f1a82197118f74df348556594bd2262bda1038/markupsafe-3.0.3-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:0eb9ff8191e8498cca014656ae6b8d61f39da5f95b488805da4bb029cccbfbaf", size = 21606, upload-time = "2025-09-27T18:37:13.485Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/0e/53dfaca23a69fbfbbf17a4b64072090e70717344c52eaaaa9c5ddff1e5f0/markupsafe-3.0.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:2713baf880df847f2bece4230d4d094280f4e67b1e813eec43b4c0e144a34ffe", size = 23043, upload-time = "2025-09-27T18:37:14.408Z" },
+    { url = "https://files.pythonhosted.org/packages/46/11/f333a06fc16236d5238bfe74daccbca41459dcd8d1fa952e8fbd5dccfb70/markupsafe-3.0.3-cp314-cp314-win32.whl", hash = "sha256:729586769a26dbceff69f7a7dbbf59ab6572b99d94576a5592625d5b411576b9", size = 14747, upload-time = "2025-09-27T18:37:15.36Z" },
+    { url = "https://files.pythonhosted.org/packages/28/52/182836104b33b444e400b14f797212f720cbc9ed6ba34c800639d154e821/markupsafe-3.0.3-cp314-cp314-win_amd64.whl", hash = "sha256:bdc919ead48f234740ad807933cdf545180bfbe9342c2bb451556db2ed958581", size = 15341, upload-time = "2025-09-27T18:37:16.496Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/18/acf23e91bd94fd7b3031558b1f013adfa21a8e407a3fdb32745538730382/markupsafe-3.0.3-cp314-cp314-win_arm64.whl", hash = "sha256:5a7d5dc5140555cf21a6fefbdbf8723f06fcd2f63ef108f2854de715e4422cb4", size = 14073, upload-time = "2025-09-27T18:37:17.476Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/f0/57689aa4076e1b43b15fdfa646b04653969d50cf30c32a102762be2485da/markupsafe-3.0.3-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:1353ef0c1b138e1907ae78e2f6c63ff67501122006b0f9abad68fda5f4ffc6ab", size = 11661, upload-time = "2025-09-27T18:37:18.453Z" },
+    { url = "https://files.pythonhosted.org/packages/89/c3/2e67a7ca217c6912985ec766c6393b636fb0c2344443ff9d91404dc4c79f/markupsafe-3.0.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:1085e7fbddd3be5f89cc898938f42c0b3c711fdcb37d75221de2666af647c175", size = 12069, upload-time = "2025-09-27T18:37:19.332Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/00/be561dce4e6ca66b15276e184ce4b8aec61fe83662cce2f7d72bd3249d28/markupsafe-3.0.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1b52b4fb9df4eb9ae465f8d0c228a00624de2334f216f178a995ccdcf82c4634", size = 25670, upload-time = "2025-09-27T18:37:20.245Z" },
+    { url = "https://files.pythonhosted.org/packages/50/09/c419f6f5a92e5fadde27efd190eca90f05e1261b10dbd8cbcb39cd8ea1dc/markupsafe-3.0.3-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fed51ac40f757d41b7c48425901843666a6677e3e8eb0abcff09e4ba6e664f50", size = 23598, upload-time = "2025-09-27T18:37:21.177Z" },
+    { url = "https://files.pythonhosted.org/packages/22/44/a0681611106e0b2921b3033fc19bc53323e0b50bc70cffdd19f7d679bb66/markupsafe-3.0.3-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f190daf01f13c72eac4efd5c430a8de82489d9cff23c364c3ea822545032993e", size = 23261, upload-time = "2025-09-27T18:37:22.167Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/57/1b0b3f100259dc9fffe780cfb60d4be71375510e435efec3d116b6436d43/markupsafe-3.0.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:e56b7d45a839a697b5eb268c82a71bd8c7f6c94d6fd50c3d577fa39a9f1409f5", size = 24835, upload-time = "2025-09-27T18:37:23.296Z" },
+    { url = "https://files.pythonhosted.org/packages/26/6a/4bf6d0c97c4920f1597cc14dd720705eca0bf7c787aebc6bb4d1bead5388/markupsafe-3.0.3-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:f3e98bb3798ead92273dc0e5fd0f31ade220f59a266ffd8a4f6065e0a3ce0523", size = 22733, upload-time = "2025-09-27T18:37:24.237Z" },
+    { url = "https://files.pythonhosted.org/packages/14/c7/ca723101509b518797fedc2fdf79ba57f886b4aca8a7d31857ba3ee8281f/markupsafe-3.0.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:5678211cb9333a6468fb8d8be0305520aa073f50d17f089b5b4b477ea6e67fdc", size = 23672, upload-time = "2025-09-27T18:37:25.271Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/df/5bd7a48c256faecd1d36edc13133e51397e41b73bb77e1a69deab746ebac/markupsafe-3.0.3-cp314-cp314t-win32.whl", hash = "sha256:915c04ba3851909ce68ccc2b8e2cd691618c4dc4c4232fb7982bca3f41fd8c3d", size = 14819, upload-time = "2025-09-27T18:37:26.285Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/8a/0402ba61a2f16038b48b39bccca271134be00c5c9f0f623208399333c448/markupsafe-3.0.3-cp314-cp314t-win_amd64.whl", hash = "sha256:4faffd047e07c38848ce017e8725090413cd80cbc23d86e55c587bf979e579c9", size = 15426, upload-time = "2025-09-27T18:37:27.316Z" },
+    { url = "https://files.pythonhosted.org/packages/70/bc/6f1c2f612465f5fa89b95bead1f44dcb607670fd42891d8fdcd5d039f4f4/markupsafe-3.0.3-cp314-cp314t-win_arm64.whl", hash = "sha256:32001d6a8fc98c8cb5c947787c5d08b0a50663d139f1305bac5885d98d9b40fa", size = 14146, upload-time = "2025-09-27T18:37:28.327Z" },
+]
+
+[[package]]
+name = "packaging"
+version = "26.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/65/ee/299d360cdc32edc7d2cf530f3accf79c4fca01e96ffc950d8a52213bd8e4/packaging-26.0.tar.gz", hash = "sha256:00243ae351a257117b6a241061796684b084ed1c516a08c48a3f7e147a9d80b4", size = 143416, upload-time = "2026-01-21T20:50:39.064Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b7/b9/c538f279a4e237a006a2c98387d081e9eb060d203d8ed34467cc0f0b9b53/packaging-26.0-py3-none-any.whl", hash = "sha256:b36f1fef9334a5588b4166f8bcd26a14e521f2b55e6b9de3aaa80d3ff7a37529", size = 74366, upload-time = "2026-01-21T20:50:37.788Z" },
+]
+
+[[package]]
+name = "pygments"
+version = "2.19.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b0/77/a5b8c569bf593b0140bde72ea885a803b82086995367bf2037de0159d924/pygments-2.19.2.tar.gz", hash = "sha256:636cb2477cec7f8952536970bc533bc43743542f70392ae026374600add5b887", size = 4968631, upload-time = "2025-06-21T13:39:12.283Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c7/21/705964c7812476f378728bdf590ca4b771ec72385c533964653c68e86bdc/pygments-2.19.2-py3-none-any.whl", hash = "sha256:86540386c03d588bb81d44bc3928634ff26449851e99741617ecb9037ee5ec0b", size = 1225217, upload-time = "2025-06-21T13:39:07.939Z" },
+]
+
+[[package]]
+name = "requests"
+version = "2.32.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "charset-normalizer" },
+    { name = "idna" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c9/74/b3ff8e6c8446842c3f5c837e9c3dfcfe2018ea6ecef224c710c85ef728f4/requests-2.32.5.tar.gz", hash = "sha256:dbba0bac56e100853db0ea71b82b4dfd5fe2bf6d3754a8893c3af500cec7d7cf", size = 134517, upload-time = "2025-08-18T20:46:02.573Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1e/db/4254e3eabe8020b458f1a747140d32277ec7a271daf1d235b70dc0b4e6e3/requests-2.32.5-py3-none-any.whl", hash = "sha256:2462f94637a34fd532264295e186976db0f5d453d1cdd31473c85a6a161affb6", size = 64738, upload-time = "2025-08-18T20:46:00.542Z" },
+]
+
+[[package]]
+name = "snowballstemmer"
+version = "3.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/75/a7/9810d872919697c9d01295633f5d574fb416d47e535f258272ca1f01f447/snowballstemmer-3.0.1.tar.gz", hash = "sha256:6d5eeeec8e9f84d4d56b847692bacf79bc2c8e90c7f80ca4444ff8b6f2e52895", size = 105575, upload-time = "2025-05-09T16:34:51.843Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c8/78/3565d011c61f5a43488987ee32b6f3f656e7f107ac2782dd57bdd7d91d9a/snowballstemmer-3.0.1-py3-none-any.whl", hash = "sha256:6cd7b3897da8d6c9ffb968a6781fa6532dce9c3618a4b127d920dab764a19064", size = 103274, upload-time = "2025-05-09T16:34:50.371Z" },
+]
+
+[[package]]
+name = "sphinx"
+version = "7.3.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "alabaster" },
+    { name = "babel" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "docutils" },
+    { name = "imagesize" },
+    { name = "jinja2" },
+    { name = "packaging" },
+    { name = "pygments" },
+    { name = "requests" },
+    { name = "snowballstemmer" },
+    { name = "sphinxcontrib-applehelp" },
+    { name = "sphinxcontrib-devhelp" },
+    { name = "sphinxcontrib-htmlhelp" },
+    { name = "sphinxcontrib-jsmath" },
+    { name = "sphinxcontrib-qthelp" },
+    { name = "sphinxcontrib-serializinghtml" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b7/0a/b88033900b1582f5ed8f880263363daef968d1cd064175e32abfd9714410/sphinx-7.3.7.tar.gz", hash = "sha256:a4a7db75ed37531c05002d56ed6948d4c42f473a36f46e1382b0bd76ca9627bc", size = 7094808, upload-time = "2024-04-19T04:44:48.297Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b4/fa/130c32ed94cf270e3d0b9ded16fb7b2c8fea86fa7263c29a696a30c1dde7/sphinx-7.3.7-py3-none-any.whl", hash = "sha256:413f75440be4cacf328f580b4274ada4565fb2187d696a84970c23f77b64d8c3", size = 3335650, upload-time = "2024-04-19T04:44:43.839Z" },
+]
+
+[[package]]
+name = "sphinx-rtd-theme"
+version = "1.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "docutils" },
+    { name = "sphinx" },
+    { name = "sphinxcontrib-jquery" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/db/3e/477c5b3ed78b6818d673f63512db12ace8c89e83eb9eecc913f9e2cc8416/sphinx_rtd_theme-1.3.0.tar.gz", hash = "sha256:590b030c7abb9cf038ec053b95e5380b5c70d61591eb0b552063fbe7c41f0931", size = 2785069, upload-time = "2023-08-21T18:28:35.63Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/18/01/76f40a18e9209bb098c1c1313c823dbbd001b23a2db71e7fd4eb5a48559c/sphinx_rtd_theme-1.3.0-py2.py3-none-any.whl", hash = "sha256:46ddef89cc2416a81ecfbeaceab1881948c014b1b6e4450b815311a89fb977b0", size = 2824803, upload-time = "2023-08-21T18:28:32.926Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-applehelp"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ba/6e/b837e84a1a704953c62ef8776d45c3e8d759876b4a84fe14eba2859106fe/sphinxcontrib_applehelp-2.0.0.tar.gz", hash = "sha256:2f29ef331735ce958efa4734873f084941970894c6090408b079c61b2e1c06d1", size = 20053, upload-time = "2024-07-29T01:09:00.465Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5d/85/9ebeae2f76e9e77b952f4b274c27238156eae7979c5421fba91a28f4970d/sphinxcontrib_applehelp-2.0.0-py3-none-any.whl", hash = "sha256:4cd3f0ec4ac5dd9c17ec65e9ab272c9b867ea77425228e68ecf08d6b28ddbdb5", size = 119300, upload-time = "2024-07-29T01:08:58.99Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-devhelp"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/d2/5beee64d3e4e747f316bae86b55943f51e82bb86ecd325883ef65741e7da/sphinxcontrib_devhelp-2.0.0.tar.gz", hash = "sha256:411f5d96d445d1d73bb5d52133377b4248ec79db5c793ce7dbe59e074b4dd1ad", size = 12967, upload-time = "2024-07-29T01:09:23.417Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/35/7a/987e583882f985fe4d7323774889ec58049171828b58c2217e7f79cdf44e/sphinxcontrib_devhelp-2.0.0-py3-none-any.whl", hash = "sha256:aefb8b83854e4b0998877524d1029fd3e6879210422ee3780459e28a1f03a8a2", size = 82530, upload-time = "2024-07-29T01:09:21.945Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-htmlhelp"
+version = "2.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/43/93/983afd9aa001e5201eab16b5a444ed5b9b0a7a010541e0ddfbbfd0b2470c/sphinxcontrib_htmlhelp-2.1.0.tar.gz", hash = "sha256:c9e2916ace8aad64cc13a0d233ee22317f2b9025b9cf3295249fa985cc7082e9", size = 22617, upload-time = "2024-07-29T01:09:37.889Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0a/7b/18a8c0bcec9182c05a0b3ec2a776bba4ead82750a55ff798e8d406dae604/sphinxcontrib_htmlhelp-2.1.0-py3-none-any.whl", hash = "sha256:166759820b47002d22914d64a075ce08f4c46818e17cfc9470a9786b759b19f8", size = 98705, upload-time = "2024-07-29T01:09:36.407Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-jquery"
+version = "4.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "sphinx" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/de/f3/aa67467e051df70a6330fe7770894b3e4f09436dea6881ae0b4f3d87cad8/sphinxcontrib-jquery-4.1.tar.gz", hash = "sha256:1620739f04e36a2c779f1a131a2dfd49b2fd07351bf1968ced074365933abc7a", size = 122331, upload-time = "2023-03-14T15:01:01.944Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/76/85/749bd22d1a68db7291c89e2ebca53f4306c3f205853cf31e9de279034c3c/sphinxcontrib_jquery-4.1-py2.py3-none-any.whl", hash = "sha256:f936030d7d0147dd026a4f2b5a57343d233f1fc7b363f68b3d4f1cb0993878ae", size = 121104, upload-time = "2023-03-14T15:01:00.356Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-jsmath"
+version = "1.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b2/e8/9ed3830aeed71f17c026a07a5097edcf44b692850ef215b161b8ad875729/sphinxcontrib-jsmath-1.0.1.tar.gz", hash = "sha256:a9925e4a4587247ed2191a22df5f6970656cb8ca2bd6284309578f2153e0c4b8", size = 5787, upload-time = "2019-01-21T16:10:16.347Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c2/42/4c8646762ee83602e3fb3fbe774c2fac12f317deb0b5dbeeedd2d3ba4b77/sphinxcontrib_jsmath-1.0.1-py2.py3-none-any.whl", hash = "sha256:2ec2eaebfb78f3f2078e73666b1415417a116cc848b72e5172e596c871103178", size = 5071, upload-time = "2019-01-21T16:10:14.333Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-qthelp"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/68/bc/9104308fc285eb3e0b31b67688235db556cd5b0ef31d96f30e45f2e51cae/sphinxcontrib_qthelp-2.0.0.tar.gz", hash = "sha256:4fe7d0ac8fc171045be623aba3e2a8f613f8682731f9153bb2e40ece16b9bbab", size = 17165, upload-time = "2024-07-29T01:09:56.435Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/27/83/859ecdd180cacc13b1f7e857abf8582a64552ea7a061057a6c716e790fce/sphinxcontrib_qthelp-2.0.0-py3-none-any.whl", hash = "sha256:b18a828cdba941ccd6ee8445dbe72ffa3ef8cbe7505d8cd1fa0d42d3f2d5f3eb", size = 88743, upload-time = "2024-07-29T01:09:54.885Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-serializinghtml"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3b/44/6716b257b0aa6bfd51a1b31665d1c205fb12cb5ad56de752dfa15657de2f/sphinxcontrib_serializinghtml-2.0.0.tar.gz", hash = "sha256:e9d912827f872c029017a53f0ef2180b327c3f7fd23c87229f7a8e8b70031d4d", size = 16080, upload-time = "2024-07-29T01:10:09.332Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/52/a7/d2782e4e3f77c8450f727ba74a8f12756d5ba823d81b941f1b04da9d033a/sphinxcontrib_serializinghtml-2.0.0-py3-none-any.whl", hash = "sha256:6e2cb0eef194e10c27ec0023bfeb25badbbb5868244cf5bc5bdc04e4464bf331", size = 92072, upload-time = "2024-07-29T01:10:08.203Z" },
+]
+
+[[package]]
+name = "urllib3"
+version = "2.6.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/c7/24/5f1b3bdffd70275f6661c76461e25f024d5a38a46f04aaca912426a2b1d3/urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed", size = 435556, upload-time = "2026-01-07T16:24:43.925Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4", size = 131584, upload-time = "2026-01-07T16:24:42.685Z" },
+]
+
+[[package]]
+name = "zrepl-docs"
+version = "0.0.0"
+source = { virtual = "." }
+dependencies = [
+    { name = "sphinx" },
+    { name = "sphinx-rtd-theme" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "sphinx", specifier = ">=7.2,<8" },
+    { name = "sphinx-rtd-theme", specifier = ">=1.3,<2" },
+]

endpoint/context.go

@@ -1,25 +0,0 @@
-package endpoint
-
-import (
-	"context"
-	"github.com/zrepl/zrepl/logger"
-)
-
-type contextKey int
-
-const (
-	contextKeyLogger contextKey = iota
-)
-
-type Logger = logger.Logger
-
-func WithLogger(ctx context.Context, log Logger) context.Context {
-	return context.WithValue(ctx, contextKeyLogger, log)
-}
-
-func getLogger(ctx context.Context) Logger {
-	if l, ok := ctx.Value(contextKeyLogger).(Logger); ok {
-		return l
-	}
-	return logger.NewNullLogger()
-}

endpoint/endpoint.go

@@ -1,614 +0,0 @@
-// Package endpoint implements replication endpoints for use with package replication.
-package endpoint
-
-import (
-	"bytes"
-	"context"
-	"fmt"
-	"github.com/golang/protobuf/proto"
-	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
-	"github.com/zrepl/zrepl/replication"
-	"github.com/zrepl/zrepl/replication/pdu"
-	"github.com/zrepl/zrepl/zfs"
-	"io"
-)
-
-// Sender implements replication.ReplicationEndpoint for a sending side
-type Sender struct {
-	FSFilter                zfs.DatasetFilter
-}
-
-func NewSender(fsf zfs.DatasetFilter) *Sender {
-	return &Sender{FSFilter: fsf}
-}
-
-func (s *Sender) filterCheckFS(fs string) (*zfs.DatasetPath, error) {
-	dp, err := zfs.NewDatasetPath(fs)
-	if err != nil {
-		return nil, err
-	}
-	if dp.Length() == 0 {
-		return nil, errors.New("empty filesystem not allowed")
-	}
-	pass, err := s.FSFilter.Filter(dp)
-	if err != nil {
-		return nil, err
-	}
-	if !pass {
-		return nil, replication.NewFilteredError(fs)
-	}
-	return dp, nil
-}
-
-func (p *Sender) ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error) {
-	fss, err := zfs.ZFSListMapping(p.FSFilter)
-	if err != nil {
-		return nil, err
-	}
-	rfss := make([]*pdu.Filesystem, len(fss))
-	for i := range fss {
-		rfss[i] = &pdu.Filesystem{
-			Path: fss[i].ToString(),
-			// FIXME: not supporting ResumeToken yet
-		}
-	}
-	return rfss, nil
-}
-
-func (p *Sender) ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) {
-	lp, err := p.filterCheckFS(fs)
-	if err != nil {
-		return nil, err
-	}
-	fsvs, err := zfs.ZFSListFilesystemVersions(lp, nil)
-	if err != nil {
-		return nil, err
-	}
-	rfsvs := make([]*pdu.FilesystemVersion, len(fsvs))
-	for i := range fsvs {
-		rfsvs[i] = pdu.FilesystemVersionFromZFS(&fsvs[i])
-	}
-	return rfsvs, nil
-}
-
-func (p *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.ReadCloser, error) {
-	_, err := p.filterCheckFS(r.Filesystem)
-	if err != nil {
-		return nil, nil, err
-	}
-
-	if r.DryRun {
-		si, err := zfs.ZFSSendDry(r.Filesystem, r.From, r.To, "")
-		if err != nil {
-			return nil, nil, err
-		}
-		var expSize int64 = 0 // protocol says 0 means no estimate
-		if si.SizeEstimate != -1 { // but si returns -1 for no size estimate
-			expSize = si.SizeEstimate
-		}
-		return &pdu.SendRes{ExpectedSize: expSize}, nil, nil
-	} else {
-		stream, err := zfs.ZFSSend(ctx, r.Filesystem, r.From, r.To, "")
-		if err != nil {
-			return nil, nil, err
-		}
-		return &pdu.SendRes{}, stream, nil
-	}
-}
-
-func (p *Sender) DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error) {
-	dp, err := p.filterCheckFS(req.Filesystem)
-	if err != nil {
-		return nil, err
-	}
-	return doDestroySnapshots(ctx, dp, req.Snapshots)
-}
-
-func (p *Sender) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
-	dp, err := p.filterCheckFS(req.Filesystem)
-	if err != nil {
-		return nil, err
-	}
-
-	switch op := req.Op.(type) {
-	case *pdu.ReplicationCursorReq_Get:
-		cursor, err := zfs.ZFSGetReplicationCursor(dp)
-		if err != nil {
-			return nil, err
-		}
-		if cursor == nil {
-			return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Error{Error: "cursor does not exist"}}, nil
-		}
-		return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Guid{Guid: cursor.Guid}}, nil
-	case *pdu.ReplicationCursorReq_Set:
-		guid, err := zfs.ZFSSetReplicationCursor(dp, op.Set.Snapshot)
-		if err != nil {
-			return nil, err
-		}
-		return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Guid{Guid: guid}}, nil
-	default:
-		return nil, errors.Errorf("unknown op %T", op)
-	}
-}
-
-type FSFilter interface { // FIXME unused
-	Filter(path *zfs.DatasetPath) (pass bool, err error)
-}
-
-// FIXME: can we get away without error types here?
-type FSMap interface { // FIXME unused
-	FSFilter
-	Map(path *zfs.DatasetPath) (*zfs.DatasetPath, error)
-	Invert() (FSMap, error)
-	AsFilter() FSFilter
-}
-
-// Receiver implements replication.ReplicationEndpoint for a receiving side
-type Receiver struct {
-	root *zfs.DatasetPath
-}
-
-func NewReceiver(rootDataset *zfs.DatasetPath) (*Receiver, error) {
-	if rootDataset.Length() <= 0 {
-		return nil, errors.New("root dataset must not be an empty path")
-	}
-	return &Receiver{root: rootDataset.Copy()}, nil
-}
-
-type subroot struct {
-	localRoot *zfs.DatasetPath
-}
-
-var _ zfs.DatasetFilter = subroot{}
-
-// Filters local p
-func (f subroot) Filter(p *zfs.DatasetPath) (pass bool, err error) {
-	return p.HasPrefix(f.localRoot) && !p.Equal(f.localRoot), nil
-}
-
-func (f subroot) MapToLocal(fs string) (*zfs.DatasetPath, error) {
-	p, err := zfs.NewDatasetPath(fs)
-	if err != nil {
-		return nil, err
-	}
-	if p.Length() == 0 {
-		return nil, errors.Errorf("cannot map empty filesystem")
-	}
-	c := f.localRoot.Copy()
-	c.Extend(p)
-	return c, nil
-}
-
-func (e *Receiver) ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error) {
-	filtered, err := zfs.ZFSListMapping(subroot{e.root})
-	if err != nil {
-		return nil, err
-	}
-	// present without prefix, and only those that are not placeholders
-	fss := make([]*pdu.Filesystem, 0, len(filtered))
-	for _, a := range filtered {
-		ph, err := zfs.ZFSIsPlaceholderFilesystem(a)
-		if err != nil {
-			getLogger(ctx).
-				WithError(err).
-				WithField("fs", a).
-				Error("inconsistent placeholder property")
-			return nil, errors.New("server error, see logs") // don't leak path
-		}
-		if ph {
-			continue
-		}
-		a.TrimPrefix(e.root)
-		fss = append(fss, &pdu.Filesystem{Path: a.ToString()})
-	}
-	return fss, nil
-}
-
-func (e *Receiver) ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) {
-	lp, err := subroot{e.root}.MapToLocal(fs)
-	if err != nil {
-		return nil, err
-	}
-
-	fsvs, err := zfs.ZFSListFilesystemVersions(lp, nil)
-	if err != nil {
-		return nil, err
-	}
-
-	rfsvs := make([]*pdu.FilesystemVersion, len(fsvs))
-	for i := range fsvs {
-		rfsvs[i] = pdu.FilesystemVersionFromZFS(&fsvs[i])
-	}
-
-	return rfsvs, nil
-}
-
-func (e *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, sendStream io.ReadCloser) error {
-	defer sendStream.Close()
-
-	lp, err := subroot{e.root}.MapToLocal(req.Filesystem)
-	if err != nil {
-		return err
-	}
-
-	getLogger(ctx).Debug("incoming Receive")
-
-	// create placeholder parent filesystems as appropriate
-	var visitErr error
-	f := zfs.NewDatasetPathForest()
-	f.Add(lp)
-	getLogger(ctx).Debug("begin tree-walk")
-	f.WalkTopDown(func(v zfs.DatasetPathVisit) (visitChildTree bool) {
-		if v.Path.Equal(lp) {
-			return false
-		}
-		_, err := zfs.ZFSGet(v.Path, []string{zfs.ZREPL_PLACEHOLDER_PROPERTY_NAME})
-		if err != nil {
-			// interpret this as an early exit of the zfs binary due to the fs not existing
-			if err := zfs.ZFSCreatePlaceholderFilesystem(v.Path); err != nil {
-				getLogger(ctx).
-					WithError(err).
-					WithField("placeholder_fs", v.Path).
-					Error("cannot create placeholder filesystem")
-				visitErr = err
-				return false
-			}
-		}
-		getLogger(ctx).WithField("filesystem", v.Path.ToString()).Debug("exists")
-		return true // leave this fs as is
-	})
-	getLogger(ctx).WithField("visitErr", visitErr).Debug("complete tree-walk")
-
-	if visitErr != nil {
-		return visitErr
-	}
-
-	needForceRecv := false
-	props, err := zfs.ZFSGet(lp, []string{zfs.ZREPL_PLACEHOLDER_PROPERTY_NAME})
-	if err == nil {
-		if isPlaceholder, _ := zfs.IsPlaceholder(lp, props.Get(zfs.ZREPL_PLACEHOLDER_PROPERTY_NAME)); isPlaceholder {
-			needForceRecv = true
-		}
-	}
-
-	args := make([]string, 0, 1)
-	if needForceRecv {
-		args = append(args, "-F")
-	}
-
-	getLogger(ctx).Debug("start receive command")
-
-	if err := zfs.ZFSRecv(ctx, lp.ToString(), sendStream, args...); err != nil {
-		getLogger(ctx).
-			WithError(err).
-			WithField("args", args).
-			Error("zfs receive failed")
-		sendStream.Close()
-		return err
-	}
-	return nil
-}
-
-func (e *Receiver) DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error) {
-	lp, err := subroot{e.root}.MapToLocal(req.Filesystem)
-	if err != nil {
-		return nil, err
-	}
-	return doDestroySnapshots(ctx, lp, req.Snapshots)
-}
-
-func doDestroySnapshots(ctx context.Context, lp *zfs.DatasetPath, snaps []*pdu.FilesystemVersion) (*pdu.DestroySnapshotsRes, error) {
-	fsvs := make([]*zfs.FilesystemVersion, len(snaps))
-	for i, fsv := range snaps {
-		if fsv.Type != pdu.FilesystemVersion_Snapshot {
-			return nil, fmt.Errorf("version %q is not a snapshot", fsv.Name)
-		}
-		var err error
-		fsvs[i], err = fsv.ZFSFilesystemVersion()
-		if err != nil {
-			return nil, err
-		}
-	}
-	res := &pdu.DestroySnapshotsRes{
-		Results: make([]*pdu.DestroySnapshotRes, len(fsvs)),
-	}
-	for i, fsv := range fsvs {
-		err := zfs.ZFSDestroyFilesystemVersion(lp, fsv)
-		errMsg := ""
-		if err != nil {
-			errMsg = err.Error()
-		}
-		res.Results[i] = &pdu.DestroySnapshotRes{
-			Snapshot: pdu.FilesystemVersionFromZFS(fsv),
-			Error:    errMsg,
-		}
-	}
-	return res, nil
-}
-
-// =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
-// RPC STUBS
-// =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
-
-const (
-	RPCListFilesystems        = "ListFilesystems"
-	RPCListFilesystemVersions = "ListFilesystemVersions"
-	RPCReceive                = "Receive"
-	RPCSend                   = "Send"
-	RPCSDestroySnapshots      = "DestroySnapshots"
-	RPCReplicationCursor      = "ReplicationCursor"
-)
-
-// Remote implements an endpoint stub that uses streamrpc as a transport.
-type Remote struct {
-	c *streamrpc.Client
-}
-
-func NewRemote(c *streamrpc.Client) Remote {
-	return Remote{c}
-}
-
-func (s Remote) ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error) {
-	req := pdu.ListFilesystemReq{}
-	b, err := proto.Marshal(&req)
-	if err != nil {
-		return nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCListFilesystems, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, err
-	}
-	if rs != nil {
-		rs.Close()
-		return nil, errors.New("response contains unexpected stream")
-	}
-	var res pdu.ListFilesystemRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return nil, err
-	}
-	return res.Filesystems, nil
-}
-
-func (s Remote) ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) {
-	req := pdu.ListFilesystemVersionsReq{
-		Filesystem: fs,
-	}
-	b, err := proto.Marshal(&req)
-	if err != nil {
-		return nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCListFilesystemVersions, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, err
-	}
-	if rs != nil {
-		rs.Close()
-		return nil, errors.New("response contains unexpected stream")
-	}
-	var res pdu.ListFilesystemVersionsRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return nil, err
-	}
-	return res.Versions, nil
-}
-
-func (s Remote) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.ReadCloser, error) {
-	b, err := proto.Marshal(r)
-	if err != nil {
-		return nil, nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCSend, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, nil, err
-	}
-	if !r.DryRun && rs == nil {
-		return nil, nil, errors.New("response does not contain a stream")
-	}
-	if r.DryRun && rs != nil {
-		rs.Close()
-		return nil, nil, errors.New("response contains unexpected stream (was dry run)")
-	}
-	var res pdu.SendRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		rs.Close()
-		return nil, nil, err
-	}
-	return &res, rs, nil
-}
-
-func (s Remote) Receive(ctx context.Context, r *pdu.ReceiveReq, sendStream io.ReadCloser) error {
-	defer sendStream.Close()
-	b, err := proto.Marshal(r)
-	if err != nil {
-		return err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCReceive, bytes.NewBuffer(b), sendStream)
-	getLogger(ctx).WithField("err", err).Debug("Remote.Receive RequestReplyReturned")
-	if err != nil {
-		return err
-	}
-	if rs != nil {
-		rs.Close()
-		return errors.New("response contains unexpected stream")
-	}
-	var res pdu.ReceiveRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return err
-	}
-	return nil
-}
-
-func (s Remote) DestroySnapshots(ctx context.Context, r *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error) {
-	b, err := proto.Marshal(r)
-	if err != nil {
-		return nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCSDestroySnapshots, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, err
-	}
-	if rs != nil {
-		rs.Close()
-		return nil, errors.New("response contains unexpected stream")
-	}
-	var res pdu.DestroySnapshotsRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return nil, err
-	}
-	return &res, nil
-}
-
-func (s Remote) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
-	b, err := proto.Marshal(req)
-	if err != nil {
-		return nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCReplicationCursor, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, err
-	}
-	if rs != nil {
-		rs.Close()
-		return nil, errors.New("response contains unexpected stream")
-	}
-	var res pdu.ReplicationCursorRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return nil, err
-	}
-	return &res, nil
-}
-
-// Handler implements the server-side streamrpc.HandlerFunc for a Remote endpoint stub.
-type Handler struct {
-	ep replication.Endpoint
-}
-
-func NewHandler(ep replication.Endpoint) Handler {
-	return Handler{ep}
-}
-
-func (a *Handler) Handle(ctx context.Context, endpoint string, reqStructured *bytes.Buffer, reqStream io.ReadCloser) (resStructured *bytes.Buffer, resStream io.ReadCloser, err error) {
-
-	switch endpoint {
-	case RPCListFilesystems:
-		var req pdu.ListFilesystemReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		fsses, err := a.ep.ListFilesystems(ctx)
-		if err != nil {
-			return nil, nil, err
-		}
-		res := &pdu.ListFilesystemRes{
-			Filesystems: fsses,
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, nil
-
-	case RPCListFilesystemVersions:
-
-		var req pdu.ListFilesystemVersionsReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		fsvs, err := a.ep.ListFilesystemVersions(ctx, req.Filesystem)
-		if err != nil {
-			return nil, nil, err
-		}
-		res := &pdu.ListFilesystemVersionsRes{
-			Versions: fsvs,
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, nil
-
-	case RPCSend:
-
-		sender, ok := a.ep.(replication.Sender)
-		if !ok {
-			goto Err
-		}
-
-		var req pdu.SendReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		res, sendStream, err := sender.Send(ctx, &req)
-		if err != nil {
-			return nil, nil, err
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), sendStream, err
-
-	case RPCReceive:
-
-		receiver, ok := a.ep.(replication.Receiver)
-		if !ok {
-			goto Err
-		}
-
-		var req pdu.ReceiveReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		err := receiver.Receive(ctx, &req, reqStream)
-		if err != nil {
-			return nil, nil, err
-		}
-		b, err := proto.Marshal(&pdu.ReceiveRes{})
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, err
-
-	case RPCSDestroySnapshots:
-
-		var req pdu.DestroySnapshotsReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-
-		res, err := a.ep.DestroySnapshots(ctx, &req)
-		if err != nil {
-			return nil, nil, err
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, nil
-
-	case RPCReplicationCursor:
-
-		sender, ok := a.ep.(replication.Sender)
-		if !ok {
-			goto Err
-		}
-
-		var req pdu.ReplicationCursorReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		res, err := sender.ReplicationCursor(ctx, &req)
-		if err != nil {
-			return nil, nil, err
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, nil
-
-	}
-Err:
-	return nil, nil, errors.New("no handler for given endpoint")
-}