Revert "DROP THIS don't run tests in CI"

This reverts commit a3c6173b85dede625f51ca7172a53a5aff024fae.

.circleci/config.yml

@@ -1,304 +1,181 @@
-version: 2.1
-orbs:
-  # NB: 1.7.2 is not the Go version, but the Orb version
-  # https://circleci.com/developer/orbs/orb/circleci/go#usage-go-modules-cache
-  go: circleci/go@1.7.2
-commands:
-  setup-home-local-bin:
+version: 2.0
+workflows:
+  version: 2
+  build:
+    jobs:
+      - build-1.11
+      - build-1.12
+      - build-1.13
+      - build-1.14
+      - build-latest
+      - test-build-in-docker
+jobs:
+
+  # build-latest serves as the template
+  # we use YAML anchors & aliases to exchange the docker image (and hence Go version used for the build)
+  build-latest: &build-latest
+    description: Builds zrepl
+    parameters:
+      image:
+        description: "the docker image that the job should use"
+        type: string
+    docker:
+      - image: circleci/golang:latest
+    environment:
+      # required by lazy.sh
+      TERM: xterm
+    working_directory: /go/src/github.com/zrepl/zrepl
     steps:
+      - run:
+          name: Setup environment variables
+          command: |
+            # used by pip (for docs)
+            echo 'export PATH="$HOME/.local/bin:$PATH"' >> $BASH_ENV
+            # we use modules
+            echo 'export GO111MODULE=on' >> $BASH_ENV
+
+      - restore_cache:
+          keys:
+            - source
+            - protobuf
+
+      - checkout
+
+      - save_cache:
+          key: source
+          paths:
+            - ".git"
+      
+      # install deps
+      - run: wget https://github.com/protocolbuffers/protobuf/releases/download/v3.6.1/protoc-3.6.1-linux-x86_64.zip
+      - run: echo "6003de742ea3fcf703cfec1cd4a3380fd143081a2eb0e559065563496af27807  protoc-3.6.1-linux-x86_64.zip" | sha256sum -c
+      - run: sudo unzip -d /usr protoc-3.6.1-linux-x86_64.zip
+      - save_cache:
+          key: protobuf
+          paths:
+            - "/usr/include/google/protobuf"
+            
+      - run: sudo apt update && sudo apt install python3 python3-pip libgirepository1.0-dev gawk
+      - run: ./lazy.sh devsetup
+
+      - run: make zrepl-bin
+      - run: make test-platform-bin
+      - run: make vet
+      - run: make lint
+      - run: make release
+      - run: make test-go
+      # cannot run test-platform because circle-ci runs in linux containers
+
+      - store_artifacts:
+          path: ./artifacts/release
+          when: always
+
+      - run:
+          shell: /bin/bash -eo pipefail
+          when: always
+          command: |
+            if [ -n "$CIRCLE_PR_NUMBER" ]; then # CIRCLE_PR_NUMBER is guaranteed to be only present in forked PRs (external)
+              echo "Forked PR detected. Sry, can't trust you with credentials to external artifact store, use CircleCI's instead."
+              exit 0
+            fi
+            set -u # from now on
+            
+            # Download and install minio
+            curl -sSL https://dl.minio.io/client/mc/release/linux-amd64/mc -o ${GOPATH}/bin/mc
+            chmod +x ${GOPATH}/bin/mc
+            mc config host add --api s3v4 zrepl-minio https://minio.cschwarz.com ${MINIO_ACCESS_KEY} ${MINIO_SECRET_KEY}
+            
+            # Upload artifacts
+            mkdir -p artifacts/release
+            echo "$CIRCLE_BUILD_URL" > ./artifacts/release/cirlceci_build_url
+            mc cp -r artifacts/release "zrepl-minio/zrepl-ci-artifacts/${CIRCLE_SHA1}/${CIRCLE_JOB}/"
+
+            # Push Artifact Link to GitHub
+            REPO="zrepl/zrepl"
+            COMMIT="${CIRCLE_SHA1}"
+            JOB_NAME="${CIRCLE_JOB}"
+            curl "https://api.github.com/repos/$REPO/statuses/$COMMIT" \
+              -H "Content-Type: application/json" \
+              -H "Authorization: token $GITHUB_COMMIT_STATUS_TOKEN" \
+              -X POST \
+              -d '{"context":"zrepl/publish-ci-artifacts", "state": "success", "description":"CI Build Artifacts for '"$JOB_NAME"'", "target_url":"https://minio.cschwarz.com/minio/zrepl-ci-artifacts/'"$COMMIT"'/"}'
+
+      - run:
+          shell: /bin/bash -eo pipefail
+          when: always
+          command: |
+            if [ -n "$CIRCLE_PR_NUMBER" ]; then # CIRCLE_PR_NUMBER is guaranteed to be only present in forked PRs (external)
+              echo "Forked PR detected. Sry, can't trust you with credentials to external artifact store, use CircleCI's instead."
+              exit 0
+            fi
+            set -u # from now on
+
+            # Trigger Platform Tests
+            # ZREPL_BOT_GIT_PRWN_EU_ACCESS_TOKEN from secrets
+            ## Sync this commit to the GitLab
+            git remote add prwn-gitlab "https://zrepl-bot:$ZREPL_BOT_GIT_PRWN_EU_ACCESS_TOKEN@git.prwn.eu/problame/zrepl.git"
+            REMOTE_REF=circleci/$CIRCLE_BRANCH/$CIRCLE_BUILD_NUM
+            git push -f prwn-gitlab "HEAD:$REMOTE_REF"
+            ## Trigger Tests
+            curl -v --request POST \
+              --header "PRIVATE-TOKEN: $ZREPL_BOT_GIT_PRWN_EU_ACCESS_TOKEN" \
+              --header "Content-Type: application/json" \
+              --data '{ "ref":"'"$REMOTE_REF"'", "variables": [ {"key":"ZREPL_MAIN_REPO_COMMIT", "value": "'"$CIRCLE_SHA1"'" }, { "key":"ZREPL_CI_BUILDJOB", "value": "'"$CIRCLE_JOB"'" } ] } ' \
+              "https://git.prwn.eu/api/v4/projects/13/pipeline"
+
+
       - 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
+            # Trigger Debian Package Build
+            curl -v -X POST https://api.github.com/repos/zrepl/debian-binary-packaging/dispatches \
+              -H 'Accept: application/vnd.github.v3+json' \
+              -H "Authorization: token $ZREPL_DEBIAN_BINARYPACKAGIN_TRIGGER_BUILD_GITHUB_TOKEN" \
+              --data '{"event_type": "push", "client_payload": { "zrepl_main_repo_commit": "'"$CIRCLE_SHA1"'", "go_version": "'"${CIRCLE_JOB##build-}"'" }}'
 
-  invoke-lazy-sh:
-    parameters:
-      subcommand:
-        type: string
-    steps:
-      - run:
-          environment:
-            TERM: xterm
-          command: ./lazy.sh <<parameters.subcommand>>
-
-  apt-update-and-install-common-deps:
-    steps:
-      - run: sudo apt-get update
-      - run: sudo apt-get install -y gawk make
-      # CircleCI doesn't update its cimg/go images.
-      # So, need to update manually to get up-to-date trust chains.
-      # The need for this was required for cimg/go:1.12, but let's future proof this here and now.
-      - run: sudo apt-get install -y git ca-certificates
-
-  install-godep:
-    steps:
-      - apt-update-and-install-common-deps
-      - invoke-lazy-sh:
-          subcommand: godep
-
-  install-docdep:
-    steps:
-      - apt-update-and-install-common-deps
-      - run: sudo apt install python3 python3-pip libgirepository1.0-dev
-      - invoke-lazy-sh:
-          subcommand: docdep
-
-  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"
-
-      # if we're pushing, we need to add the deploy key
-      # which is stored as "Additional SSH Keys" in the CircleCI project settings.
-      # We can't use the CircleCI-manage deploy key because we're pushing
-      # to a different repo than the one we're building.
-      - when:
-          condition: << parameters.push >>
-          steps:
-            # https://circleci.com/docs/2.0/add-ssh-key/#adding-multiple-keys-with-blank-hostnames
-            - run: ssh-add -D
-            # the default circleci ssh config only additional ssh keys for Host !github.com
-            - run:
-                command: |
-                  cat > ~/.ssh/config \<<EOF
-                  Host *
-                    IdentityFile /home/circleci/.ssh/id_rsa_458e62c517f6c480e40452126ce47421
-                  EOF
-            - add_ssh_keys:
-                fingerprints:
-                  # deploy key for zrepl.github.io
-                  - "45:8e:62:c5:17:f6:c4:80:e4:04:52:12:6c:e4:74:21"
-
-      # 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
-
-  release_docker_baseimage_tag:
-    type: string
-    default: "1.21"
-
-workflows:
-  version: 2
-
-  ci:
-    when: << pipeline.parameters.do_ci >>
-    jobs:
-      - quickcheck-docs
-      - quickcheck-go: &quickcheck-go-smoketest
-          name: quickcheck-go-amd64-linux-1.21
-          goversion: &latest-go-release "1.21"
-          goos: linux
-          goarch: amd64
-      - test-go-on-latest-go-release:
-          goversion: *latest-go-release
-      - quickcheck-go:
-          requires:
-            - quickcheck-go-amd64-linux-1.21 #quickcheck-go-smoketest.name
-          matrix: &quickcheck-go-matrix
-            alias: quickcheck-go-matrix
-            parameters:
-              goversion: [*latest-go-release, "1.20"]
-              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"]
-          requires:
-            - 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:
-      - publish-zrepl-github-io:
-          filters:
-            branches:
-              only:
-                - stable
-
-jobs:
-  quickcheck-docs:
+  build-1.11:
+    <<: *build-latest
     docker:
-      - image: cimg/base:2023.09
-    steps:
-      - checkout
-      - install-docdep
-      # do the current docs build
-      - run: make docs
-      # does the publish.sh script still work?
-      - docs-publish-sh:
-          push: false
+    - image: circleci/golang:1.11
 
-  quickcheck-go:
-    parameters:
-      goversion:
-        type: string
-      goos:
-        type: string
-      goarch:
-        type: string
+  build-1.12:
+    <<: *build-latest
     docker:
-      - image: cimg/go:<<parameters.goversion>>
+    - image: circleci/golang:1.12
+
+  build-1.13:
+    <<: *build-latest
+    docker:
+    - image: circleci/golang:1.13
+
+  build-1.14:
+    <<: *build-latest
+    docker:
+    - image: circleci/golang:1.14
+
+  # this job tries to mimic the build-in-docker instructions
+  # given in docs/installation.rst
+  #
+  # However, CircleCI doesn't support volume mounts, so we have to copy
+  # the source into the build-container by modifying the Dockerfile
+  test-build-in-docker:
+    description: Check that build-in-docker works
+    docker:
+      - image: circleci/golang:latest
     environment:
-      GOOS: <<parameters.goos>>
-      GOARCH: <<parameters.goarch>>
-
+    working_directory: /go/src/github.com/zrepl/zrepl
     steps:
-      - checkout
-
-      - go/load-cache:
-          key: quickcheck-<<parameters.goversion>>
-      - install-godep
-      - run: go mod download
-      - run: cd build && go mod download
-      - go/save-cache:
-          key: quickcheck-<<parameters.goversion>>
-
-      - run: make formatcheck
-      - run: make generate-platform-test-list
-      - run: make zrepl-bin test-platform-bin
-      - run: make vet
-      - run: make lint
-
-      - run: rm -f artifacts/generate-platform-test-list
-      - store_artifacts:
-          path: artifacts
-      - persist_to_workspace:
-          root: .
-          paths: [.]
-
-  platformtest:
-    parameters:
-      goversion:
-        type: string
-      goos:
-        type: string
-      goarch:
-        type: string
-    machine:
-      image: ubuntu-2204:current
-    resource_class: medium
-    environment:
-      GOOS: <<parameters.goos>>
-      GOARCH: <<parameters.goarch>>
-    steps:
-      - attach_workspace:
-          at: .
-      - run: sudo apt-get update
-      - run: sudo apt-get install -y zfsutils-linux
-      - run: sudo zfs version
-      - run: sudo make test-platform GOOS="$GOOS" GOARCH="$GOARCH"
-
-  test-go-on-latest-go-release:
-    parameters:
-      goversion:
-        type: string
-    docker:
-      - image: cimg/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: ubuntu-2004:202201-02
-    steps:
-      - checkout
-      - run: make release-docker RELEASE_DOCKER_BASEIMAGE_TAG=<<pipeline.parameters.release_docker_baseimage_tag>>
-      - persist_to_workspace:
-          root: .
-          paths: [.]
-  release-deb:
-    machine:
-      image: ubuntu-2004:202201-02
-    steps:
-      - attach_workspace:
-          at: .
-      - run: make debs-docker
-      - persist_to_workspace:
-          root: .
-          paths:
-            - "artifacts/*.deb"
-
-  release-rpm:
-    machine:
-      image: ubuntu-2004:202201-02
-    steps:
-      - attach_workspace:
-          at: .
-      - run: make rpms-docker
-      - persist_to_workspace:
-          root: .
-          paths:
-            - "artifacts/*.rpm"
-
-  release-upload:
-    docker:
-      - image: cimg/base:2020.08
-    steps:
-      - attach_workspace:
-          at: .
-      - run: make wrapup-and-checksum
-      - store_artifacts:
-          path: artifacts
-
-  publish-zrepl-github-io:
-    docker:
-      - image: cimg/base:2023.09
-    steps:
-      - checkout
-      - install-docdep
-      - docs-publish-sh:
-          push: true
+    - checkout
+    - setup_remote_docker
+    - run:
+        name: (hacky) circleci doesn't allow volume mounts, so copy src to container
+        command: echo "ADD . /src" >> build.Dockerfile
+    - run:
+        name: (hacky) commit modified Dockerfile to avoid failing git clean check in Makefile
+        command: git -c user.name='circleci' -c user.email='circleci@localhost' commit -m 'CIRCLECI modified Dockerfile with zrepl src' --author 'autoauthor <circleci@localhost>' -- build.Dockerfile
+    - run:
+        name: build the build image (build deps)
+        command: docker build -t zrepl_build -f build.Dockerfile .
+    - run:
+        name: try compiling
+        command: docker run -it zrepl_build make release

.circleci/download_artifacts.py

@@ -1,84 +0,0 @@
-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")

.circleci/trigger_debian_binary_packaging_workflow.bash

@@ -1,10 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-COMMIT="$1"
-GO_VERSION="$2"
-
-curl -v -X POST https://api.github.com/repos/zrepl/debian-binary-packaging/dispatches \
-    -H 'Accept: application/vnd.github.v3+json' \
-    -H "Authorization: token $GITHUB_ACCESS_TOKEN" \
-    --data '{"event_type": "push", "client_payload": { "zrepl_main_repo_commit": "'"$COMMIT"'", "go_version": "'"$GO_VERSION"'" }}'

.github/FUNDING.yml

@@ -1,4 +1,3 @@
-github: problame
 patreon: zrepl
 liberapay: zrepl
 custom: https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96

.gitlab-ci.yml

@@ -0,0 +1,17 @@
+build-and-run-platformtests:
+  variables:
+    GIT_STRATEGY: none
+  script:
+    - mkdir artifacts
+    # platformtests are installed by the CI environment
+    - /opt/platformtest-linux-amd64
+      -test.coverprofile artifacts/platformtest.cover
+      -test.v
+      __DEVEL--i-heard-you-like-tests
+      -poolname zreplplatformtest
+      -imagepath /tmp/zreplplatformtest.pool.img
+      -mountpoint /tmp/zreplplatformtest.pool
+  artifacts:
+    paths:
+      - artifacts
+  image: "images:ubuntu/focal/cloud"

.golangci.yml

@@ -7,10 +7,4 @@ issues:
     - path: _test\.go
       linters:
         - errcheck
-    # Disable staticcheck 'Empty body in an if or else branch' as it's useful
-    # to put a comment into an empty else-clause that explains why whatever
-    # is done in the if-caluse is not necessary if the condition is false.
-    - linters:
-        - staticcheck
-      text: "SA9003:"
 

.platformtest-ci/download_ci_file.bash

@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "${BASH_SOURCE[0]}")"
+
+commit="$1"
+build="$2"
+src="$3"
+dst="$4"
+
+[ -n "$commit" -a -n "$build" -a -n "$src" -a -n "$dst" ] || ( echo "arguments must not be empty"; exit 1 )
+
+aws="aws --endpoint-url https://minio.cschwarz.com --no-sign-request"
+
+
+path="s3://zrepl-ci-artifacts/$commit/$build/$src"
+$aws s3 cp "$path" "$dst"

.travis.yml

@@ -0,0 +1,70 @@
+dist: xenial
+services:
+- docker
+
+env: # for allow_failures: https://docs.travis-ci.com/user/customizing-the-build/
+matrix:
+  include:
+
+  - language: go
+    name: "Build in Docker (docs/installation.rst)"
+    script:
+    - 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
+
+  - &zrepl_build_template
+    language: go
+    go_import_path: github.com/zrepl/zrepl
+    before_install:
+        - wget https://github.com/protocolbuffers/protobuf/releases/download/v3.6.1/protoc-3.6.1-linux-x86_64.zip
+        - echo "6003de742ea3fcf703cfec1cd4a3380fd143081a2eb0e559065563496af27807  protoc-3.6.1-linux-x86_64.zip" | sha256sum -c
+        - sudo unzip -d /usr protoc-3.6.1-linux-x86_64.zip
+        - ./lazy.sh godep
+        - make vendordeps
+    script:
+      - make
+      - make vet
+      - make test
+      - make lint
+      - make artifacts/zrepl-freebsd-amd64
+      - make artifacts/zrepl-linux-amd64
+      - make artifacts/zrepl-darwin-amd64
+    go:
+    - "1.11"
+
+  - <<: *zrepl_build_template
+    go:
+    - "1.12"
+
+  - <<: *zrepl_build_template
+    go:
+    - "master"
+
+  - &zrepl_docs_template 
+    language: python
+    python:
+    - "3.4"
+    install:
+    - sudo apt-get install libgirepository1.0-dev
+    - pip install -r docs/requirements.txt
+    script:
+    - make docs
+  - <<: *zrepl_docs_template
+    python:
+    - "3.5"
+  - <<: *zrepl_docs_template
+    python:
+    - "3.6"
+  - <<: *zrepl_docs_template
+    python:
+    - "3.7"
+  
+
+  allow_failures:
+  - <<: *zrepl_build_template
+    go:
+    - "master"

Makefile

@@ -1,5 +1,5 @@
 .PHONY: generate build test vet cover release docs docs-clean clean format lint platformtest
-.PHONY: release release-noarch
+.PHONY: release bins-all release-noarch
 .DEFAULT_GOAL := zrepl-bin
 
 ARTIFACTDIR := artifacts
@@ -14,15 +14,13 @@ ifndef _ZREPL_VERSION
     endif
 endif
 
-ZREPL_PACKAGE_RELEASE := 1
-
 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 := GO111MODULE=on CGO_ENABLED=0
+GO_ENV_VARS := GO111MODULE=on
 GO_LDFLAGS := "-X github.com/zrepl/zrepl/version.zreplVersion=$(_ZREPL_VERSION)"
 GO_MOD_READONLY := -mod=readonly
 GO_EXTRA_BUILDFLAGS :=
@@ -30,8 +28,6 @@ GO_BUILDFLAGS := $(GO_MOD_READONLY) $(GO_EXTRA_BUILDFLAGS)
 GO_BUILD := $(GO_ENV_VARS) $(GO) build $(GO_BUILDFLAGS) -ldflags $(GO_LDFLAGS)
 GOLANGCI_LINT := golangci-lint
 GOCOVMERGE := gocovmerge
-RELEASE_DOCKER_BASEIMAGE_TAG ?= 1.21
-RELEASE_DOCKER_BASEIMAGE ?= golang:$(RELEASE_DOCKER_BASEIMAGE_TAG)
 
 ifneq ($(GOARM),)
 	ZREPL_TARGET_TUPLE := $(GOOS)-$(GOARCH)v$(GOARM)
@@ -52,110 +48,16 @@ printvars:
 release: clean
 	# no cross-platform support for target test
 	$(MAKE) test-go
-	$(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) bins-all
 	$(MAKE) noarch
-
-release-docker: $(ARTIFACTDIR)
-	sed 's/FROM.*!SUBSTITUTED_BY_MAKEFILE/FROM $(RELEASE_DOCKER_BASEIMAGE)/' build.Dockerfile > artifacts/release-docker.Dockerfile
-	docker build -t zrepl_release --pull -f artifacts/release-docker.Dockerfile .
-	docker run --rm -i -v $(CURDIR):/src -u $$(id -u):$$(id -g) \
-		zrepl_release \
-		make release \
-			GOOS=$(GOOS) GOARCH=$(GOARCH) GOARM=$(GOARM) \
-			ZREPL_VERSION=$(ZREPL_VERSION) ZREPL_PACKAGE_RELEASE=$(ZREPL_PACKAGE_RELEASE)
-
-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))
+	$(MAKE) wrapup-and-checksum
+	$(MAKE) check-git-clean
+ifeq (SIGN, 1)
+	$(make) sign
 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)/
+	@echo "ZREPL RELEASE ARTIFACTS AVAILABLE IN artifacts/release"
 
-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
+# expects `release` target to have run before
 NOARCH_TARBALL := $(ARTIFACTDIR)/zrepl-noarch.tar
 wrapup-and-checksum:
 	rm -f $(NOARCH_TARBALL)
@@ -172,7 +74,7 @@ wrapup-and-checksum:
 		config/samples
 	rm -rf "$(ARTIFACTDIR)/release"
 	mkdir -p "$(ARTIFACTDIR)/release"
-	cp -l $(ARTIFACTDIR)/zrepl* \
+	cp -l $(ARTIFACTDIR)/zrepl-* \
 		$(ARTIFACTDIR)/platformtest-* \
 		"$(ARTIFACTDIR)/release"
 	cd "$(ARTIFACTDIR)/release" && sha512sum $$(ls | sort) > sha512sum.txt
@@ -190,44 +92,35 @@ check-git-clean:
 		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!' \
+	gpg -u "89BC 5D89 C845 568B F578  B306 CDBD 8EC8 E27C A5FC" \
 		--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"
+##################### BINARIES #####################
+.PHONY: bins-all lint test-go test-platform cover-merge cover-html vet zrepl-bin test-platform-bin generate-platform-test-list
 
-##################### 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 generate-platform-test-list
+BINS_ALL_TARGETS := zrepl-bin test-platform-bin vet lint
+GO_SUPPORTS_ILLUMOS := $(shell $(GO) version | gawk -F '.' '/^go version /{split($$0, comps, " "); split(comps[3], v, "."); if (v[1] == "go1" && v[2] >= 13) { print "illumos"; } else { print "noillumos"; }}')
+bins-all:
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=freebsd   GOARCH=amd64
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=freebsd   GOARCH=386
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=linux     GOARCH=amd64
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=linux     GOARCH=arm64
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=linux     GOARCH=arm     GOARM=7
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=linux     GOARCH=386
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=darwin    GOARCH=amd64
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=solaris   GOARCH=amd64
+ifeq ($(GO_SUPPORTS_ILLUMOS), illumos)
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=illumos   GOARCH=amd64
+else ifeq ($(GO_SUPPORTS_ILLUMOS), noillumos)
+	@echo "SKIPPING ILLUMOS BUILD BECAUSE GO VERSION DOESN'T SUPPORT IT"
+else
+	@echo "CANNOT DETERMINE WHETHER GO VERSION SUPPORTS GOOS=illumos"; exit 1
+endif
 
 lint:
 	$(GO_ENV_VARS) $(GOLANGCI_LINT) run ./...
@@ -254,41 +147,26 @@ zrepl-bin:
 generate-platform-test-list:
 	$(GO_BUILD) -o $(ARTIFACTDIR)/generate-platform-test-list ./platformtest/tests/gen
 
-COVER_PLATFORM_BIN_PATH := $(ARTIFACTDIR)/platformtest-cover-$(ZREPL_TARGET_TUPLE)
-cover-platform-bin:
+test-platform-bin:
 	$(GO_ENV_VARS) $(GO) test $(GO_BUILDFLAGS) \
-		-c -o "$(COVER_PLATFORM_BIN_PATH)" \
+		-c -o "$(ARTIFACTDIR)/platformtest-$(ZREPL_TARGET_TUPLE)" \
 		-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)" ./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
+ZREPL_PLATFORMTEST_ARGS := 
+test-platform: $(ARTIFACTDIR) # do not track dependency on test-platform-bin to allow build of platformtest outside of test VM
 	rm -f "$(ZREPL_PLATFORMTEST_ZFS_LOG)"
 	rm -f "$(ARTIFACTDIR)/platformtest.cover"
 	platformtest/logmockzfs/logzfsenv "$(ZREPL_PLATFORMTEST_ZFS_LOG)" `which zfs` \
-		$(_TEST_PLATFORM_CMD) \
+	"$(ARTIFACTDIR)/platformtest-$(ZREPL_TARGET_TUPLE)" \
+		-test.coverprofile "$(ARTIFACTDIR)/platformtest.cover" \
+		-test.v \
+		__DEVEL--i-heard-you-like-tests \
 		-poolname "$(ZREPL_PLATFORMTEST_POOLNAME)" \
 		-imagepath "$(ZREPL_PLATFORMTEST_IMAGEPATH)" \
 		-mountpoint "$(ZREPL_PLATFORMTEST_MOUNTPOINT)" \
@@ -300,32 +178,22 @@ cover-merge: $(ARTIFACTDIR)
 cover-html: cover-merge
 	$(GO) tool cover -html "$(ARTIFACTDIR)/merged.cover" -o "$(ARTIFACTDIR)/merged.cover.html"
 
-cover-full:
+test-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) test-platform
 	$(MAKE) cover-html
 
 ##################### DEV TARGETS #####################
 # not part of the build, must do that manually
-.PHONY: generate formatcheck format
+.PHONY: generate format
 
 generate: generate-platform-test-list
-	protoc -I=replication/logic/pdu --go_out=replication/logic/pdu --go-grpc_out=replication/logic/pdu replication/logic/pdu/pdu.proto
-	protoc -I=rpc/grpcclientidentity/example --go_out=rpc/grpcclientidentity/example/pdu --go-grpc_out=rpc/grpcclientidentity/example/pdu rpc/grpcclientidentity/example/grpcauth.proto
+	protoc -I=replication/logic/pdu --go_out=plugins=grpc:replication/logic/pdu replication/logic/pdu/pdu.proto
 	$(GO_ENV_VARS) $(GO) generate $(GO_BUILDFLAGS) -x ./...
 
-GOIMPORTS := goimports -srcdir . -local 'github.com/zrepl/zrepl'
-FINDSRCFILES := find . -type f -name '*.go' -not -path "./vendor/*" -not -name '*.pb.go' -not -name '*_enumer.go'
-
-formatcheck:
-	@# goimports doesn't have a knob to exit with non-zero status code if formatting is needed
-	@# see https://go-review.googlesource.com/c/tools/+/237378
-	@ affectedfiles=$$($(GOIMPORTS) -l $(shell $(FINDSRCFILES)) | tee /dev/stderr | wc -l); test "$$affectedfiles" = 0
-
 format:
-	@ $(GOIMPORTS) -w -d $(shell  $(FINDSRCFILES))
+	goimports -srcdir . -local 'github.com/zrepl/zrepl' -w $(shell 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
@@ -349,16 +217,13 @@ $(ARTIFACTDIR)/_zrepl.zsh_completion:
 
 $(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
-	$(MAKE) -C docs \
+	make -C docs \
 		html \
 		BUILDDIR=../artifacts/docs \
-		SPHINXOPTS="-W --keep-going -n"
 
 docs-clean:
-	$(MAKE) -C docs \
+	make -C docs \
 		clean \
 		BUILDDIR=../artifacts/docs

README.md

@@ -1,12 +1,10 @@
 [![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/)
+[![Language: Go](https://img.shields.io/badge/language-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 Patreon](https://img.shields.io/endpoint.svg?url=https%3A%2F%2Fshieldsio-patreon.herokuapp.com%2Fzrepl%2Fpledges&style=flat&color=yellow)](https://www.patreon.com/zrepl)
+[![Donate via Liberapay](https://img.shields.io/liberapay/receives/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.
@@ -22,7 +20,7 @@ zrepl is a one-stop ZFS backup & replication solution.
 
 ## Feature Requests
 
-1. Does your feature request require default values / some kind of configuration?
+1. Does you 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.
@@ -31,12 +29,20 @@ zrepl is a one-stop ZFS backup & replication solution.
 The above does not apply if you already implemented everything.
 Check out the *Coding Workflow* section below for details.
 
-## Building, Releasing, Downstream-Packaging
+## Package Maintainer Information
 
-This section provides an overview of the zrepl build & release process.
-Check out `docs/installation/compile-from-source.rst` for build-from-source instructions.
+* 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.
+  * `dist/systemd` contains a Systemd unit template.
+* Ship other material provided in `./dist`, e.g. in `/usr/share/zrepl/`.
+* 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
+* Use `sudo make test-platform` **on a test system** to validate that zrepl's abstractions on top of ZFS work with the system ZFS.
+* Make sure you are informed about new zrepl versions, e.g. by subscribing to GitHub's release RSS feed.
 
-### Overview
+## Developer Documentation
 
 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.
@@ -53,61 +59,60 @@ An HTML report can be generated using `make cover-html`.
 
 **Code generation** is triggered by `make generate`. Generated code is committed to the source tree.
 
-### Build & Release Process
+### Project Structure
 
-**The `Makefile` is catering to the needs of developers & CI, not distro packagers**.
-It provides phony targets for
-* local development (building, running tests, etc)
-* building a release in Docker (used by the CI & release management)
-* building .deb and .rpm packages out of the release artifacts.
+```
+├── artifacts               # build artifcats generate by make
+├── cli                     # wrapper around CLI package cobra
+├── client                  # all subcommands that are not `daemon`
+├── config                  # config data types (=> package yaml-config)
+│   └── samples
+├── daemon                  # the implementation of `zrepl daemon` subcommand
+│   ├── filters
+│   ├── hooks               # snapshot hooks
+│   ├── job                 # job implementations
+│   ├── logging             # logging outlets + formatters
+│   ├── nethelpers
+│   ├── prometheus
+│   ├── pruner              # pruner implementation
+│   ├── snapper             # snapshotter implementation
+├── dist                    # supplemental material for users & package maintainers
+├── 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
+├── endpoint                # implementation of replication endpoints (=> package replication)
+├── logger                  # our own logger package
+├── platformtest            # test suite for our zfs abstractions (error classification, etc)
+├── pruning                 # pruning rules (the logic, not the actual execution)
+│   └── retentiongrid
+├── replication
+│   ├── driver              # the driver of the replication logic (status reporting, error handling)
+│   ├── logic               # planning & executing replication steps via rpc
+|   |   └── pdu             # the generated gRPC & protobuf code used in replication (and endpoints)
+│   └── report              # the JSON-serializable report datastructures exposed to the client
+├── rpc                     # the hybrid gRPC + ./dataconn RPC client: connects to a remote replication.Endpoint
+│   ├── dataconn            # Bulk data-transfer RPC protocol
+│   ├── grpcclientidentity  # adaptor to inject package transport's 'client identity' concept into gRPC contexts
+│   ├── netadaptor          # adaptor to convert a package transport's Connecter and Listener into net.* primitives
+│   ├── transportmux        # TCP connecter and listener used to split control & data traffic
+│   └── versionhandshake    # replication protocol version handshake perfomed on newly established connections
+├── tlsconf                 # abstraction for Go TLS server + client config
+├── transport               # transport implementations
+│   ├── fromconfig
+│   ├── local
+│   ├── ssh
+│   ├── tcp
+│   └── tls
+├── util
+├── version                 # abstraction for versions (filled during build by Makefile)
+└── zfs                     # zfs(8) wrappers
+```
 
-**Build tooling & dependencies** are documented as code in `lazy.sh`.
-Go dependencies are then fetched by the go command and pip dependencies are pinned through a `requirements.txt`.
-
-**We use CircleCI for continuous integration**.
-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.
-  Artifacts are published to minio.cschwarz.com (see GitHub Commit Status).
-
-* `release` runs
-  * on manual triggers through the CircleCI API (in order to produce a release)
-  * periodically on `master`
-  Artifacts are published to minio.cschwarz.com (see GitHub Commit Status).
-
-**Releases** are issued via Git tags + GitHub Releases feature.
-The procedure to issue a release is as follows:
-* Issue the source release:
-  * Git tag the release on the `master` branch.
-  * Push the tag.
-  * Run `./docs/publish.sh` to re-build & push zrepl.github.io.
-* Issue the official binary release:
-  * Run the `release` pipeline (triggered via CircleCI API)
-  * Download the artifacts to the release manager's machine.
-  * Create a GitHub release, edit the changelog, upload all the release artifacts, including .rpm and .deb files.
-  * Issue the GitHub release.
-  * Add the .rpm and .deb files to the official zrepl repos, publish those.
-
-**Official binary releases are not re-built when Go receives an update. If the Go update is critical to zrepl (e.g. a Go security update that affects zrepl), we'd issue a new source release**.
-The rationale for this is that whereas distros provide a mechanism for this (`$zrepl_source_release-$distro_package_revision`), GitHub Releases doesn't which means we'd need to update the existing GitHub release's assets, which nobody would notice (no RSS feed updates, etc.).
-Downstream packagers can read the changelog to determine whether they want to push that minor release into their distro or simply skip it.
-
-### Additional Notes to Distro Package Maintainers
-
-* 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.
-
-
-## Contributing Code
+### Coding Workflow
 
 * Open an issue when starting to hack on a new feature
 * Commits should reference the issue they are related to
@@ -117,6 +122,9 @@ Downstream packagers can read the changelog to determine whether they want to pu
 
 Backward-incompatible changes must be documented in the git commit message and are listed in `docs/changelog.rst`.
 
+* 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
+
 ### Glossary & Naming Inconsistencies
 
 In ZFS, *dataset* refers to the objects *filesystem*, *ZVOL* and *snapshot*. <br />
@@ -133,3 +141,16 @@ variables and types are often named *dataset* when they in fact refer to a *file
 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.
+
+### RPC debugging
+
+Optionally, there are various RPC-related environment variables, that if set to something != `""` will produce additional debug output on stderr:
+
+https://github.com/zrepl/zrepl/blob/master/rpc/rpc_debug.go#L11
+
+https://github.com/zrepl/zrepl/blob/master/rpc/dataconn/dataconn_debug.go#L11
+
+https://github.com/zrepl/zrepl/blob/master/rpc/dataconn/stream/stream_debug.go#L11
+
+https://github.com/zrepl/zrepl/blob/master/rpc/dataconn/heartbeatconn/heartbeatconn_debug.go#L11
+

build.Dockerfile

@@ -1,19 +1,13 @@
-FROM !SUBSTITUTED_BY_MAKEFILE
+FROM golang:latest
 
 RUN apt-get update && apt-get install -y \
     python3-pip \
-    python3-venv \
     unzip \
     gawk
 
 ADD build.installprotoc.bash ./
 RUN bash build.installprotoc.bash
 
-# setup venv
-ENV VIRTUAL_ENV=/opt/venv
-RUN python3 -m venv $VIRTUAL_ENV
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-
 ADD lazy.sh /tmp/lazy.sh
 ADD docs/requirements.txt /tmp/requirements.txt
 ENV ZREPL_LAZY_DOCS_REQPATH=/tmp/requirements.txt

build/go.mod

@@ -3,38 +3,50 @@ module github.com/zrepl/zrepl/build
 go 1.12
 
 require (
+	github.com/OpenPeeDeeP/depguard v0.0.0-20181229194401-1f388ab2d810 // indirect
 	github.com/alvaroloes/enumer v1.1.1
-	github.com/breml/bidichk v0.2.6 // indirect
-	github.com/breml/errchkjson v0.3.5 // indirect
-	github.com/chavacava/garif v0.1.0 // indirect
-	github.com/daixiang0/gci v0.11.1 // indirect
-	github.com/golangci/golangci-lint v1.54.2
-	github.com/golangci/revgrep v0.5.0 // indirect
-	github.com/hashicorp/errwrap v1.1.0 // indirect
-	github.com/jgautheron/goconst v1.6.0 // indirect
-	github.com/mattn/go-isatty v0.0.19 // indirect
-	github.com/mattn/go-runewidth v0.0.15 // indirect
-	github.com/mgechev/revive v1.3.3 // indirect
-	github.com/pelletier/go-toml/v2 v2.1.0 // indirect
-	github.com/polyfloyd/go-errorlint v1.4.5 // indirect
-	github.com/prometheus/client_golang v1.16.0 // indirect
-	github.com/prometheus/common v0.44.0 // indirect
-	github.com/prometheus/procfs v0.11.1 // indirect
-	github.com/rivo/uniseg v0.4.4 // indirect
-	github.com/ryanrolds/sqlclosecheck v0.5.1 // indirect
-	github.com/spf13/viper v1.16.0 // indirect
-	github.com/stretchr/objx v0.5.1 // indirect
-	github.com/subosito/gotenv v1.6.0 // indirect
-	github.com/tetafro/godot v1.4.15 // indirect
-	github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad
-	github.com/xen0n/gosmopolitan v1.2.2 // indirect
-	gitlab.com/bosi/decorder v0.4.1 // indirect
-	go.uber.org/multierr v1.11.0 // indirect
-	go.uber.org/zap v1.25.0 // indirect
-	golang.org/x/exp v0.0.0-20230905200255-921286631fa9 // indirect
-	golang.org/x/exp/typeparams v0.0.0-20230905200255-921286631fa9 // indirect
-	golang.org/x/tools v0.13.0
-	google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.1.0
-	google.golang.org/protobuf v1.31.0
-	mvdan.cc/unparam v0.0.0-20230815095028-f7c6fb1088f0 // indirect
+	github.com/fatih/color v1.7.0 // indirect
+	github.com/go-critic/go-critic v0.3.4 // indirect
+	github.com/gogo/protobuf v1.2.1 // indirect
+	github.com/golang/mock v1.2.0 // indirect
+	github.com/golang/protobuf v1.2.0
+	github.com/golangci/errcheck v0.0.0-20181223084120-ef45e06d44b6 // indirect
+	github.com/golangci/go-tools v0.0.0-20190124090046-35a9f45a5db0 // indirect
+	github.com/golangci/gocyclo v0.0.0-20180528144436-0a533e8fa43d // indirect
+	github.com/golangci/gofmt v0.0.0-20181222123516-0b8337e80d98 // indirect
+	github.com/golangci/golangci-lint v1.17.1
+	github.com/golangci/gosec v0.0.0-20180901114220-8afd9cbb6cfb // indirect
+	github.com/golangci/lint-1 v0.0.0-20181222135242-d2cdd8c08219 // indirect
+	github.com/golangci/misspell v0.3.4 // indirect
+	github.com/golangci/revgrep v0.0.0-20180812185044-276a5c0a1039 // indirect
+	github.com/google/go-cmp v0.3.0 // indirect
+	github.com/konsorten/go-windows-terminal-sequences v1.0.2 // indirect
+	github.com/mitchellh/go-homedir v1.1.0 // indirect
+	github.com/pkg/errors v0.8.1 // indirect
+	github.com/sirupsen/logrus v1.4.2 // indirect
+	github.com/spf13/afero v1.2.2 // indirect
+	github.com/spf13/jwalterweatherman v1.1.0 // indirect
+	github.com/spf13/viper v1.3.2 // indirect
+	github.com/stretchr/testify v1.4.0 // indirect
+	github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad // indirect
+	golang.org/x/net v0.0.0-20190613194153-d28f0bde5980 // indirect
+	golang.org/x/sys v0.0.0-20191010194322-b09406accb47 // indirect
+	golang.org/x/tools v0.0.0-20190524210228-3d17549cdc6b
+	mvdan.cc/unparam v0.0.0-20190310220240-1b9ccfa71afe // indirect
+	sourcegraph.com/sqs/pbtypes v1.0.0 // indirect
+)
+
+// invalid dates in transitive dependencies (first validated in Go 1.13, didn't fail in earlier Go versions)
+replace (
+	github.com/go-critic/go-critic v0.0.0-20181204210945-1df300866540 => github.com/go-critic/go-critic v0.3.5-0.20190526074819-1df300866540
+	github.com/go-critic/go-critic v0.0.0-20181204210945-ee9bf5809ead => github.com/go-critic/go-critic v0.3.5-0.20190210220443-ee9bf5809ead
+	github.com/golangci/errcheck v0.0.0-20181003203344-ef45e06d44b6 => github.com/golangci/errcheck v0.0.0-20181223084120-ef45e06d44b6
+	github.com/golangci/go-tools v0.0.0-20180109140146-35a9f45a5db0 => github.com/golangci/go-tools v0.0.0-20190124090046-35a9f45a5db0
+	github.com/golangci/go-tools v0.0.0-20180109140146-af6baa5dc196 => github.com/golangci/go-tools v0.0.0-20190318060251-af6baa5dc196
+	github.com/golangci/gofmt v0.0.0-20181105071733-0b8337e80d98 => github.com/golangci/gofmt v0.0.0-20181222123516-0b8337e80d98
+	github.com/golangci/gosec v0.0.0-20180901114220-66fb7fc33547 => github.com/golangci/gosec v0.0.0-20190211064107-66fb7fc33547
+	github.com/golangci/ineffassign v0.0.0-20180808204949-42439a7714cc => github.com/golangci/ineffassign v0.0.0-20190609212857-42439a7714cc
+	github.com/golangci/lint-1 v0.0.0-20180610141402-ee948d087217 => github.com/golangci/lint-1 v0.0.0-20190420132249-ee948d087217
+	golang.org/x/tools v0.0.0-20190125232054-379209517ffe => golang.org/x/tools v0.0.0-20190205201329-379209517ffe
+	mvdan.cc/unparam v0.0.0-20190124213536-fbb59629db34 => mvdan.cc/unparam v0.0.0-20190209190245-fbb59629db34
 )

build/tools.go

@@ -1,15 +1,12 @@
-//go:build tools
 // +build tools
 
 package main
 
-// the lines are parsed by lazy.sh, do not edit
 import (
 	_ "github.com/alvaroloes/enumer"
+	_ "github.com/golang/protobuf/protoc-gen-go"
 	_ "github.com/golangci/golangci-lint/cmd/golangci-lint"
 	_ "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

@@ -7,7 +7,6 @@ import (
 
 	"github.com/spf13/cobra"
 	"github.com/spf13/pflag"
-
 	"github.com/zrepl/zrepl/daemon/logging/trace"
 
 	"github.com/zrepl/zrepl/config"

client/configcheck.go

@@ -19,9 +19,8 @@ import (
 )
 
 var configcheckArgs struct {
-	format        string
-	what          string
-	skipCertCheck bool
+	format string
+	what   string
 }
 
 var ConfigcheckCmd = &cli.Subcommand{
@@ -30,7 +29,6 @@ var ConfigcheckCmd = &cli.Subcommand{
 	SetupFlags: func(f *pflag.FlagSet) {
 		f.StringVar(&configcheckArgs.format, "format", "", "dump parsed config object [pretty|yaml|json]")
 		f.StringVar(&configcheckArgs.what, "what", "all", "what to print [all|config|jobs|logging]")
-		f.BoolVar(&configcheckArgs.skipCertCheck, "skip-cert-check", false, "skip checking cert files")
 	},
 	Run: func(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
 		formatMap := map[string]func(interface{}){
@@ -58,16 +56,8 @@ var ConfigcheckCmd = &cli.Subcommand{
 		}
 
 		var hadErr bool
-
-		parseFlags := config.ParseFlagsNone
-
-		if configcheckArgs.skipCertCheck {
-			parseFlags |= config.ParseFlagsNoCertCheck
-		}
-
 		// further: try to build jobs
-		confJobs, err := job.JobsFromConfig(subcommand.Config(), parseFlags)
-
+		confJobs, err := job.JobsFromConfig(subcommand.Config())
 		if err != nil {
 			err := errors.Wrap(err, "cannot build jobs from config")
 			if configcheckArgs.what == "jobs" {

client/migrate.go

@@ -129,7 +129,7 @@ func doMigrateReplicationCursor(ctx context.Context, sc *cli.Subcommand, args []
 	}
 
 	cfg := sc.Config()
-	jobs, err := job.JobsFromConfig(cfg, config.ParseFlagsNone)
+	jobs, err := job.JobsFromConfig(cfg)
 	if err != nil {
 		fmt.Printf("cannot parse config:\n%s\n\n", err)
 		fmt.Printf("NOTE: this migration was released together with a change in job name requirements.\n")

client/status.go

@@ -0,0 +1,811 @@
+package client
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"math"
+	"net/http"
+	"os"
+	"sort"
+	"strings"
+	"sync"
+	"time"
+
+	// tcell is the termbox-compatible library for abstracting away escape sequences, etc.
+	// as of tcell#252, the number of default distributed terminals is relatively limited
+	// additional terminal definitions can be included via side-effect import
+	// See https://github.com/gdamore/tcell/blob/master/terminfo/base/base.go
+	// See https://github.com/gdamore/tcell/issues/252#issuecomment-533836078
+	"github.com/gdamore/tcell/termbox"
+	_ "github.com/gdamore/tcell/terminfo/s/screen" // tmux on FreeBSD 11 & 12 without ncurses
+
+	"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/daemon/snapper"
+	"github.com/zrepl/zrepl/replication/report"
+)
+
+type byteProgressMeasurement struct {
+	time time.Time
+	val  int64
+}
+
+type bytesProgressHistory struct {
+	last        *byteProgressMeasurement // pointer as poor man's optional
+	changeCount int
+	lastChange  time.Time
+	bpsAvg      float64
+}
+
+func (p *bytesProgressHistory) Update(currentVal int64) (bytesPerSecondAvg int64, changeCount int) {
+
+	if p.last == nil {
+		p.last = &byteProgressMeasurement{
+			time: time.Now(),
+			val:  currentVal,
+		}
+		return 0, 0
+	}
+
+	if p.last.val != currentVal {
+		p.changeCount++
+		p.lastChange = time.Now()
+	}
+
+	if time.Since(p.lastChange) > 3*time.Second {
+		p.last = nil
+		return 0, 0
+	}
+
+	deltaV := currentVal - p.last.val
+	deltaT := time.Since(p.last.time)
+	rate := float64(deltaV) / deltaT.Seconds()
+
+	factor := 0.3
+	p.bpsAvg = (1-factor)*p.bpsAvg + factor*rate
+
+	p.last.time = time.Now()
+	p.last.val = currentVal
+
+	return int64(p.bpsAvg), p.changeCount
+}
+
+type tui struct {
+	x, y   int
+	indent int
+
+	lock   sync.Mutex //For report and error
+	report map[string]*job.Status
+	err    error
+
+	jobFilter string
+
+	replicationProgress map[string]*bytesProgressHistory // by job name
+}
+
+func newTui() tui {
+	return tui{
+		replicationProgress: make(map[string]*bytesProgressHistory),
+	}
+}
+
+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.TrimRight(s[:rem], "\n\r")
+		s = s[rem:]
+		if len(untilNewline) == 0 {
+			continue
+		}
+		b.WriteString(untilNewline)
+		b.WriteString("\n")
+	}
+	return strings.TrimRight(b.String(), "\n\r")
+}
+
+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
+	Job string
+}
+
+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")
+		f.StringVar(&statusFlags.Job, "job", "", "only dump specified job")
+	},
+	Run: runStatus,
+}
+
+func runStatus(ctx context.Context, 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")
+			_, err := io.CopyN(os.Stderr, resp.Body, 4096)
+			if err != nil {
+				return err
+			}
+			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()
+	t.jobFilter = statusFlags.Job
+
+	err = termbox.Init()
+	if err != nil {
+		return err
+	}
+	defer termbox.Close()
+
+	update := func() {
+		var m daemon.Status
+
+		err2 := jsonRequestResponse(httpc, daemon.ControlJobEndpointStatus,
+			struct{}{},
+			&m,
+		)
+
+		t.lock.Lock()
+		t.err = err2
+		t.report = m.Jobs
+		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) getReplicationProgressHistory(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, 0, len(t.report))
+		for k := range t.report {
+			if len(k) == 0 || daemon.IsInternalJobName(k) { //Internal job
+				continue
+			}
+			if t.jobFilter != "" && k != t.jobFilter {
+				continue
+			}
+			keys = append(keys, k)
+		}
+		sort.Strings(keys)
+
+		if len(keys) == 0 {
+			t.setIndent(0)
+			t.printf("no jobs to display")
+			t.newline()
+			termbox.Flush()
+			return
+		}
+
+		for _, k := range keys {
+			v := t.report[k]
+
+			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 {
+				activeStatus, ok := v.JobSpecific.(*job.ActiveSideStatus)
+				if !ok || activeStatus == nil {
+					t.printf("ActiveSideStatus is null")
+					t.newline()
+					continue
+				}
+
+				t.printf("Replication:")
+				t.newline()
+				t.addIndent(1)
+				t.renderReplicationReport(activeStatus.Replication, t.getReplicationProgressHistory(k))
+				t.addIndent(-1)
+
+				t.printf("Pruning Sender:")
+				t.newline()
+				t.addIndent(1)
+				t.renderPrunerReport(activeStatus.PruningSender)
+				t.addIndent(-1)
+
+				t.printf("Pruning Receiver:")
+				t.newline()
+				t.addIndent(1)
+				t.renderPrunerReport(activeStatus.PruningReceiver)
+				t.addIndent(-1)
+
+				if v.Type == job.TypePush {
+					t.printf("Snapshotting:")
+					t.newline()
+					t.addIndent(1)
+					t.renderSnapperReport(activeStatus.Snapshotting)
+					t.addIndent(-1)
+				}
+
+			} else if v.Type == job.TypeSnap {
+				snapStatus, ok := v.JobSpecific.(*job.SnapJobStatus)
+				if !ok || snapStatus == nil {
+					t.printf("SnapJobStatus is null")
+					t.newline()
+					continue
+				}
+				t.printf("Pruning snapshots:")
+				t.newline()
+				t.addIndent(1)
+				t.renderPrunerReport(snapStatus.Pruning)
+				t.addIndent(-1)
+				t.printf("Snapshotting:")
+				t.newline()
+				t.addIndent(1)
+				t.renderSnapperReport(snapStatus.Snapshotting)
+				t.addIndent(-1)
+			} else if v.Type == job.TypeSource {
+
+				st := v.JobSpecific.(*job.PassiveStatus)
+				t.printf("Snapshotting:\n")
+				t.addIndent(1)
+				t.renderSnapperReport(st.Snapper)
+				t.addIndent(-1)
+
+			} else {
+				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
+			}
+		}
+	}
+	termbox.Flush()
+}
+
+func (t *tui) renderReplicationReport(rep *report.Report, history *bytesProgressHistory) {
+	if rep == nil {
+		t.printf("...\n")
+		return
+	}
+
+	if rep.WaitReconnectError != nil {
+		t.printfDrawIndentedAndWrappedIfMultiline("Connectivity: %s", rep.WaitReconnectError)
+		t.newline()
+	}
+	if !rep.WaitReconnectSince.IsZero() {
+		delta := time.Until(rep.WaitReconnectUntil).Round(time.Second)
+		if rep.WaitReconnectUntil.IsZero() || delta > 0 {
+			var until string
+			if rep.WaitReconnectUntil.IsZero() {
+				until = "waiting indefinitely"
+			} else {
+				until = fmt.Sprintf("hard fail in %s @ %s", delta, rep.WaitReconnectUntil)
+			}
+			t.printfDrawIndentedAndWrappedIfMultiline("Connectivity: reconnecting with exponential backoff (since %s) (%s)",
+				rep.WaitReconnectSince, until)
+		} else {
+			t.printfDrawIndentedAndWrappedIfMultiline("Connectivity: reconnects reached hard-fail timeout @ %s", rep.WaitReconnectUntil)
+		}
+		t.newline()
+	}
+
+	// TODO visualize more than the latest attempt by folding all attempts into one
+	if len(rep.Attempts) == 0 {
+		t.printf("no attempts made yet")
+		return
+	} else {
+		t.printf("Attempt #%d", len(rep.Attempts))
+		if len(rep.Attempts) > 1 {
+			t.printf(". Previous attempts failed with the following statuses:")
+			t.newline()
+			t.addIndent(1)
+			for i, a := range rep.Attempts[:len(rep.Attempts)-1] {
+				t.printfDrawIndentedAndWrappedIfMultiline("#%d: %s (failed at %s) (ran %s)", i+1, a.State, a.FinishAt, a.FinishAt.Sub(a.StartAt))
+				t.newline()
+			}
+			t.addIndent(-1)
+		} else {
+			t.newline()
+		}
+	}
+
+	latest := rep.Attempts[len(rep.Attempts)-1]
+	sort.Slice(latest.Filesystems, func(i, j int) bool {
+		return latest.Filesystems[i].Info.Name < latest.Filesystems[j].Info.Name
+	})
+
+	t.printf("Status: %s", latest.State)
+	t.newline()
+	if latest.State == report.AttemptPlanningError {
+		t.printf("Problem: ")
+		t.printfDrawIndentedAndWrappedIfMultiline("%s", latest.PlanError)
+		t.newline()
+	} else if latest.State == report.AttemptFanOutError {
+		t.printf("Problem: one or more of the filesystems encountered errors")
+		t.newline()
+	}
+
+	if latest.State != report.AttemptPlanning && latest.State != report.AttemptPlanningError {
+		// Draw global progress bar
+		// Progress: [---------------]
+		expected, replicated, containsInvalidSizeEstimates := latest.BytesSum()
+		rate, changeCount := history.Update(replicated)
+		eta := time.Duration(0)
+		if rate > 0 {
+			eta = time.Duration((expected-replicated)/rate) * time.Second
+		}
+		t.write("Progress: ")
+		t.drawBar(50, replicated, expected, changeCount)
+		t.write(fmt.Sprintf(" %s / %s @ %s/s", ByteCountBinary(replicated), ByteCountBinary(expected), ByteCountBinary(rate)))
+		if eta != 0 {
+			t.write(fmt.Sprintf(" (%s remaining)", humanizeDuration(eta)))
+		}
+		t.newline()
+		if containsInvalidSizeEstimates {
+			t.write("NOTE: not all steps could be size-estimated, total estimate is likely imprecise!")
+			t.newline()
+		}
+
+		var maxFSLen int
+		for _, fs := range latest.Filesystems {
+			if len(fs.Info.Name) > maxFSLen {
+				maxFSLen = len(fs.Info.Name)
+			}
+		}
+		for _, fs := range latest.Filesystems {
+			t.printFilesystemStatus(fs, false, maxFSLen) // FIXME bring 'active' flag back
+		}
+
+	}
+
+}
+
+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)
+	}
+
+	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.PlanErr:
+		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.SkipReason.NotSkipped() {
+			t.printf("skipped: %s\n", fs.SkipReason)
+			continue
+		}
+		if fs.LastError != "" {
+			if strings.ContainsAny(fs.LastError, "\r\n") {
+				t.printf("ERROR:")
+				t.printfDrawIndentedAndWrappedIfMultiline("%s\n", fs.LastError)
+			} else {
+				t.printfDrawIndentedAndWrappedIfMultiline("ERROR: %s\n", fs.LastError)
+			}
+			t.newline()
+			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()
+	}
+
+}
+
+func (t *tui) renderSnapperReport(r *snapper.Report) {
+	if r == nil {
+		t.printf("<snapshot type does not have a report>\n")
+		return
+	}
+
+	t.printf("Status: %s", r.State)
+	t.newline()
+
+	if r.Error != "" {
+		t.printf("Error: %s\n", r.Error)
+	}
+	if !r.SleepUntil.IsZero() {
+		t.printf("Sleep until: %s\n", r.SleepUntil)
+	}
+
+	sort.Slice(r.Progress, func(i, j int) bool {
+		return strings.Compare(r.Progress[i].Path, r.Progress[j].Path) == -1
+	})
+
+	t.addIndent(1)
+	defer t.addIndent(-1)
+	dur := func(d time.Duration) string {
+		return d.Round(100 * time.Millisecond).String()
+	}
+
+	type row struct {
+		path, state, duration, remainder, hookReport string
+	}
+	var widths struct {
+		path, state, duration int
+	}
+	rows := make([]*row, len(r.Progress))
+	for i, fs := range r.Progress {
+		r := &row{
+			path:  fs.Path,
+			state: fs.State.String(),
+		}
+		if fs.HooksHadError {
+			r.hookReport = fs.Hooks // FIXME render here, not in daemon
+		}
+		switch fs.State {
+		case snapper.SnapPending:
+			r.duration = "..."
+			r.remainder = ""
+		case snapper.SnapStarted:
+			r.duration = dur(time.Since(fs.StartAt))
+			r.remainder = fmt.Sprintf("snap name: %q", fs.SnapName)
+		case snapper.SnapDone:
+			fallthrough
+		case snapper.SnapError:
+			r.duration = dur(fs.DoneAt.Sub(fs.StartAt))
+			r.remainder = fmt.Sprintf("snap name: %q", fs.SnapName)
+		}
+		rows[i] = r
+		if len(r.path) > widths.path {
+			widths.path = len(r.path)
+		}
+		if len(r.state) > widths.state {
+			widths.state = len(r.state)
+		}
+		if len(r.duration) > widths.duration {
+			widths.duration = len(r.duration)
+		}
+	}
+
+	for _, r := range rows {
+		path := rightPad(r.path, widths.path, " ")
+		state := rightPad(r.state, widths.state, " ")
+		duration := rightPad(r.duration, widths.duration, " ")
+		t.printf("%s %s %s", path, state, duration)
+		t.printfDrawIndentedAndWrappedIfMultiline(" %s", r.remainder)
+		if r.hookReport != "" {
+			t.printfDrawIndentedAndWrappedIfMultiline("%s", r.hookReport)
+		}
+		t.newline()
+	}
+
+}
+
+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 + strings.Repeat(pad, length-len(str))
+}
+
+var arrowPositions = `>\|/`
+
+// changeCount = 0 indicates stall / no progress
+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 (t *tui) printFilesystemStatus(rep *report.FilesystemReport, active bool, maxFS int) {
+
+	expected, replicated, containsInvalidSizeEstimates := rep.BytesSum()
+	sizeEstimationImpreciseNotice := ""
+	if containsInvalidSizeEstimates {
+		sizeEstimationImpreciseNotice = " (some steps lack size estimation)"
+	}
+	if rep.CurrentStep < len(rep.Steps) && rep.Steps[rep.CurrentStep].Info.BytesExpected == 0 {
+		sizeEstimationImpreciseNotice = " (step lacks size estimation)"
+	}
+
+	status := fmt.Sprintf("%s (step %d/%d, %s/%s)%s",
+		strings.ToUpper(string(rep.State)),
+		rep.CurrentStep, len(rep.Steps),
+		ByteCountBinary(replicated), ByteCountBinary(expected),
+		sizeEstimationImpreciseNotice,
+	)
+
+	activeIndicator := " "
+	if active {
+		activeIndicator = "*"
+	}
+	t.printf("%s %s %s ",
+		activeIndicator,
+		rightPad(rep.Info.Name, maxFS, " "),
+		status)
+
+	next := ""
+	if err := rep.Error(); err != nil {
+		next = err.Err
+	} else if rep.State != report.FilesystemDone {
+		if nextStep := rep.NextStep(); nextStep != nil {
+			if nextStep.IsIncremental() {
+				next = fmt.Sprintf("next: %s => %s", nextStep.Info.From, nextStep.Info.To)
+			} else {
+				next = fmt.Sprintf("next: full send %s", nextStep.Info.To)
+			}
+			attribs := []string{}
+
+			if nextStep.Info.Resumed {
+				attribs = append(attribs, "resumed")
+			}
+
+			attribs = append(attribs, fmt.Sprintf("encrypted=%s", nextStep.Info.Encrypted))
+
+			next += fmt.Sprintf(" (%s)", strings.Join(attribs, ", "))
+		} else {
+			next = "" // individual FSes may still be in planning state
+		}
+
+	}
+	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])
+}
+
+func humanizeDuration(duration time.Duration) string {
+	days := int64(duration.Hours() / 24)
+	hours := int64(math.Mod(duration.Hours(), 24))
+	minutes := int64(math.Mod(duration.Minutes(), 60))
+	seconds := int64(math.Mod(duration.Seconds(), 60))
+
+	var parts []string
+
+	force := false
+	chunks := []int64{days, hours, minutes, seconds}
+	for i, chunk := range chunks {
+		if force || chunk > 0 {
+			padding := 0
+			if force {
+				padding = 2
+			}
+			parts = append(parts, fmt.Sprintf("%*d%c", padding, chunk, "dhms"[i]))
+			force = true
+		}
+	}
+
+	return strings.Join(parts, " ")
+}

client/status/client/client.go

@@ -1,111 +0,0 @@
-package client
-
-import (
-	"bytes"
-	"context"
-	"encoding/json"
-	"io"
-	"net"
-	"net/http"
-
-	"github.com/pkg/errors"
-
-	"github.com/zrepl/zrepl/daemon"
-)
-
-type Client struct {
-	h *http.Client
-}
-
-func New(network, addr string) (*Client, error) {
-	httpc, err := makeControlHttpClient(func(_ context.Context) (net.Conn, error) { return net.Dial(network, addr) })
-	if err != nil {
-		return nil, err
-	}
-	return &Client{httpc}, nil
-}
-
-func (c *Client) Status() (s daemon.Status, _ error) {
-	err := jsonRequestResponse(c.h, daemon.ControlJobEndpointStatus,
-		struct{}{},
-		&s,
-	)
-	return s, err
-}
-
-func (c *Client) StatusRaw() ([]byte, error) {
-	var r json.RawMessage
-	err := jsonRequestResponse(c.h, daemon.ControlJobEndpointStatus, struct{}{}, &r)
-	if err != nil {
-		return nil, err
-	}
-	return r, nil
-}
-
-func (c *Client) signal(job, sig string) error {
-	return jsonRequestResponse(c.h, daemon.ControlJobEndpointSignal,
-		struct {
-			Name string
-			Op   string
-		}{
-			Name: job,
-			Op:   sig,
-		},
-		struct{}{},
-	)
-}
-
-func (c *Client) SignalWakeup(job string) error {
-	return c.signal(job, "wakeup")
-}
-
-func (c *Client) SignalReset(job string) error {
-	return c.signal(job, "reset")
-}
-
-func makeControlHttpClient(dialfunc func(context.Context) (net.Conn, error)) (client *http.Client, err error) {
-	return &http.Client{
-		Transport: &http.Transport{
-			DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
-				return dialfunc(ctx)
-			},
-		},
-	}, nil
-}
-
-func jsonRequestResponse(c *http.Client, endpoint string, req interface{}, res interface{}) error {
-	var buf bytes.Buffer
-	encodeErr := json.NewEncoder(&buf).Encode(req)
-	if encodeErr != nil {
-		return encodeErr
-	}
-
-	hreq, err := http.NewRequest("POST", "http://unix"+endpoint, &buf)
-	if err != nil {
-		return err
-	}
-	hreq.Header.Set("Content-Type", "application/json")
-	// Prevent EOF errors when client request frequency and server keepalive close are at the same time.
-	// Found this by watching http.Server.ConnState changes, then found
-	// https://stackoverflow.com/questions/17714494/golang-http-request-results-in-eof-errors-when-making-multiple-requests-successi
-	// Note: The issue seems even more prounounced with local TCP sockets than unix domain sockets. So, I used that for debugging.
-	hreq.Close = true
-	resp, err := c.Do(hreq)
-	if err != nil {
-		return err
-	}
-	defer resp.Body.Close()
-
-	if resp.StatusCode != http.StatusOK {
-		var msg bytes.Buffer
-		_, _ = io.CopyN(&msg, resp.Body, 4096) // ignore error, just display what we got
-		return errors.Errorf("%s", msg.String())
-	}
-
-	decodeError := json.NewDecoder(resp.Body).Decode(&res)
-	if decodeError != nil {
-		return decodeError
-	}
-
-	return nil
-}

client/status/status.go

@@ -1,97 +0,0 @@
-package status
-
-import (
-	"context"
-	"os"
-	"time"
-
-	"github.com/mattn/go-isatty"
-	"github.com/pkg/errors"
-	"github.com/spf13/pflag"
-
-	"github.com/zrepl/zrepl/cli"
-	"github.com/zrepl/zrepl/client/status/client"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon"
-	"github.com/zrepl/zrepl/util/choices"
-)
-
-type Client interface {
-	Status() (daemon.Status, error)
-	StatusRaw() ([]byte, error)
-	SignalWakeup(job string) error
-	SignalReset(job string) error
-}
-
-type statusFlags struct {
-	Mode  choices.Choices
-	Job   string
-	Delay time.Duration
-}
-
-var statusv2Flags statusFlags
-
-type statusv2Mode int
-
-const (
-	StatusV2ModeInteractive statusv2Mode = 1 + iota
-	StatusV2ModeDump
-	StatusV2ModeRaw
-	StatusV2ModeLegacy
-)
-
-var Subcommand = &cli.Subcommand{
-	Use:   "status",
-	Short: "retrieve & display daemon status information",
-	SetupFlags: func(f *pflag.FlagSet) {
-		statusv2Flags.Mode.Init(
-			"interactive", StatusV2ModeInteractive,
-			"dump", StatusV2ModeDump,
-			"raw", StatusV2ModeRaw,
-			"legacy", StatusV2ModeLegacy,
-		)
-		statusv2Flags.Mode.SetTypeString("mode")
-		statusv2Flags.Mode.SetDefaultValue(StatusV2ModeInteractive)
-		f.Var(&statusv2Flags.Mode, "mode", statusv2Flags.Mode.Usage())
-		f.StringVar(&statusv2Flags.Job, "job", "", "only show specified job (works in \"dump\" and \"interactive\" mode)")
-		f.DurationVarP(&statusv2Flags.Delay, "delay", "d", 1*time.Second, "use -d 3s for 3 seconds delay (minimum delay is 1s)")
-	},
-	Run: func(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
-		return runStatusV2Command(ctx, subcommand.Config(), args)
-	},
-}
-
-func runStatusV2Command(ctx context.Context, config *config.Config, args []string) error {
-
-	c, err := client.New("unix", config.Global.Control.SockPath)
-	if err != nil {
-		return errors.Wrapf(err, "connect to daemon socket at %q", config.Global.Control.SockPath)
-	}
-
-	mode := statusv2Flags.Mode.Value().(statusv2Mode)
-
-	if !isatty.IsTerminal(os.Stdout.Fd()) && mode != StatusV2ModeDump && mode != StatusV2ModeRaw {
-		dumpmode, err := statusv2Flags.Mode.InputForChoice(StatusV2ModeDump)
-		if err != nil {
-			panic(err)
-		}
-		rawmode, err := statusv2Flags.Mode.InputForChoice(StatusV2ModeRaw)
-		if err != nil {
-			panic(err)
-		}
-		return errors.Errorf("error: stdout is not a tty, please use --mode %s or --mode %s", dumpmode, rawmode)
-	}
-
-	switch mode {
-	case StatusV2ModeInteractive:
-		return interactive(c, statusv2Flags)
-	case StatusV2ModeDump:
-		return dump(c, statusv2Flags.Job)
-	case StatusV2ModeRaw:
-		return raw(c)
-	case StatusV2ModeLegacy:
-		return legacy(c, statusv2Flags)
-	default:
-		panic("unreachable")
-	}
-}

client/status/status_dump.go

@@ -1,70 +0,0 @@
-package status
-
-import (
-	"fmt"
-	"os"
-	"strings"
-
-	"github.com/gdamore/tcell"
-	"github.com/mattn/go-isatty"
-	"github.com/pkg/errors"
-
-	"github.com/zrepl/zrepl/client/status/viewmodel"
-)
-
-func dump(c Client, job string) error {
-	s, err := c.Status()
-	if err != nil {
-		return err
-	}
-
-	if job != "" {
-		if _, ok := s.Jobs[job]; !ok {
-			return errors.Errorf("job %q not found", job)
-		}
-	}
-
-	width := (1 << 31) - 1
-	wrap := false
-	hline := strings.Repeat("-", 80)
-	if isatty.IsTerminal(os.Stdout.Fd()) {
-		wrap = true
-		screen, err := tcell.NewScreen()
-		if err != nil {
-			return errors.Wrap(err, "get terminal dimensions")
-		}
-		if err := screen.Init(); err != nil {
-			return errors.Wrap(err, "init screen")
-		}
-		width, _ = screen.Size()
-		screen.Fini()
-		hline = strings.Repeat("-", width)
-	}
-
-	m := viewmodel.New()
-	params := viewmodel.Params{
-		Report:                  s.Jobs,
-		ReportFetchError:        nil,
-		SelectedJob:             nil,
-		FSFilter:                func(s string) bool { return true },
-		DetailViewWidth:         width,
-		DetailViewWrap:          wrap,
-		ShortKeybindingOverview: "",
-	}
-	m.Update(params)
-	for _, j := range m.Jobs() {
-		if job != "" && j.Name() != job {
-			continue
-		}
-		params.SelectedJob = j
-		m.Update(params)
-		fmt.Println(m.SelectedJob().FullDescription())
-		if job != "" {
-			return nil
-		} else {
-			fmt.Println(hline)
-		}
-	}
-
-	return nil
-}

client/status/status_interactive.go

@@ -1,347 +0,0 @@
-package status
-
-import (
-	"fmt"
-	"regexp"
-	"strings"
-	"sync"
-	"time"
-
-	"github.com/gdamore/tcell/v2"
-	tview "gitlab.com/tslocum/cview"
-
-	"github.com/zrepl/zrepl/client/status/viewmodel"
-)
-
-func interactive(c Client, flag statusFlags) error {
-
-	// Set this so we don't overwrite the default terminal colors
-	// See https://github.com/rivo/tview/blob/master/styles.go
-	tview.Styles.PrimitiveBackgroundColor = tcell.ColorDefault
-	tview.Styles.ContrastBackgroundColor = tcell.ColorDefault
-	tview.Styles.PrimaryTextColor = tcell.ColorDefault
-	tview.Styles.BorderColor = tcell.ColorDefault
-	app := tview.NewApplication()
-
-	jobDetailSplit := tview.NewFlex()
-	jobMenu := tview.NewTreeView()
-	jobMenuRoot := tview.NewTreeNode("jobs")
-	jobMenuRoot.SetSelectable(true)
-	jobMenu.SetRoot(jobMenuRoot)
-	jobMenu.SetCurrentNode(jobMenuRoot)
-	jobMenu.SetSelectedTextColor(tcell.ColorGreen)
-	jobTextDetail := tview.NewTextView()
-	jobTextDetail.SetWrap(false)
-
-	jobMenu.SetBorder(true)
-	jobTextDetail.SetBorder(true)
-
-	toolbarSplit := tview.NewFlex()
-	toolbarSplit.SetDirection(tview.FlexRow)
-	inputBarContainer := tview.NewFlex()
-	fsFilterInput := tview.NewInputField()
-	fsFilterInput.SetBorder(false)
-	fsFilterInput.SetFieldBackgroundColor(tcell.ColorDefault)
-	inputBarLabel := tview.NewTextView()
-	inputBarLabel.SetText("[::b]FILTER ")
-	inputBarLabel.SetDynamicColors(true)
-	inputBarContainer.AddItem(inputBarLabel, 7, 1, false)
-	inputBarContainer.AddItem(fsFilterInput, 0, 10, false)
-	toolbarSplit.AddItem(inputBarContainer, 1, 0, false)
-	toolbarSplit.AddItem(jobDetailSplit, 0, 10, false)
-
-	bottombar := tview.NewFlex()
-	bottombar.SetDirection(tview.FlexColumn)
-	bottombarDateView := tview.NewTextView()
-	bottombar.AddItem(bottombarDateView, len(time.Now().String()), 0, false)
-	bottomBarStatus := tview.NewTextView()
-	bottomBarStatus.SetDynamicColors(true)
-	bottomBarStatus.SetTextAlign(tview.AlignRight)
-	bottombar.AddItem(bottomBarStatus, 0, 10, false)
-	toolbarSplit.AddItem(bottombar, 1, 0, false)
-
-	tabbableWithJobMenu := []tview.Primitive{jobMenu, jobTextDetail, fsFilterInput}
-	tabbableWithoutJobMenu := []tview.Primitive{jobTextDetail, fsFilterInput}
-	var tabbable []tview.Primitive
-	tabbableActiveIndex := 0
-	tabbableRedraw := func() {
-		if len(tabbable) == 0 {
-			app.SetFocus(nil)
-			return
-		}
-		if tabbableActiveIndex >= len(tabbable) {
-			app.SetFocus(tabbable[0])
-			return
-		}
-		app.SetFocus(tabbable[tabbableActiveIndex])
-	}
-	tabbableCycle := func() {
-		if len(tabbable) == 0 {
-			return
-		}
-		tabbableActiveIndex = (tabbableActiveIndex + 1) % len(tabbable)
-		app.SetFocus(tabbable[tabbableActiveIndex])
-		tabbableRedraw()
-	}
-
-	jobMenuVisisble := false
-	reconfigureJobDetailSplit := func(setJobMenuVisible bool) {
-		if jobMenuVisisble == setJobMenuVisible {
-			return
-		}
-		jobMenuVisisble = setJobMenuVisible
-		if setJobMenuVisible {
-			jobDetailSplit.RemoveItem(jobTextDetail)
-			jobDetailSplit.AddItem(jobMenu, 0, 1, true)
-			jobDetailSplit.AddItem(jobTextDetail, 0, 5, false)
-			tabbable = tabbableWithJobMenu
-		} else {
-			jobDetailSplit.RemoveItem(jobMenu)
-			tabbable = tabbableWithoutJobMenu
-		}
-		tabbableRedraw()
-	}
-
-	showModal := func(m *tview.Modal, modalDoneFunc func(idx int, label string)) {
-		preModalFocus := app.GetFocus()
-		m.SetDoneFunc(func(idx int, label string) {
-			if modalDoneFunc != nil {
-				modalDoneFunc(idx, label)
-			}
-			app.SetRoot(toolbarSplit, true)
-			app.SetFocus(preModalFocus)
-			app.Draw()
-		})
-		app.SetRoot(m, true)
-		app.Draw()
-	}
-
-	app.SetRoot(toolbarSplit, true)
-	// initial focus
-	tabbableActiveIndex = len(tabbable)
-	tabbableCycle()
-	reconfigureJobDetailSplit(true)
-
-	m := viewmodel.New()
-	params := &viewmodel.Params{
-		Report:                  nil,
-		SelectedJob:             nil,
-		FSFilter:                func(_ string) bool { return true },
-		DetailViewWidth:         100,
-		DetailViewWrap:          false,
-		ShortKeybindingOverview: "[::b]Q[::-] quit  [::b]<TAB>[::-] switch panes [::b]W[::-] wrap lines  [::b]Shift+M[::-] toggle navbar  [::b]Shift+S[::-] signal job [::b]</>[::-] filter filesystems",
-	}
-	paramsMtx := &sync.Mutex{}
-	var redraw func()
-	viewmodelupdate := func(cb func(*viewmodel.Params)) {
-		paramsMtx.Lock()
-		defer paramsMtx.Unlock()
-		cb(params)
-		m.Update(*params)
-	}
-	redraw = func() {
-		jobs := m.Jobs()
-		if flag.Job != "" {
-			job_found := false
-			for _, job := range jobs {
-				if strings.Compare(flag.Job, job.Name()) == 0 {
-					jobs = []*viewmodel.Job{job}
-					job_found = true
-					break
-				}
-			}
-			if !job_found {
-				jobs = nil
-			}
-		}
-		redrawJobsList := false
-		var selectedJobN *tview.TreeNode
-		if len(jobMenuRoot.GetChildren()) == len(jobs) {
-			for i, jobN := range jobMenuRoot.GetChildren() {
-				if jobN.GetReference().(*viewmodel.Job) != jobs[i] {
-					redrawJobsList = true
-					break
-				}
-				if jobN.GetReference().(*viewmodel.Job) == m.SelectedJob() {
-					selectedJobN = jobN
-				}
-			}
-		} else {
-			redrawJobsList = true
-		}
-		if redrawJobsList {
-			selectedJobN = nil
-			children := make([]*tview.TreeNode, len(jobs))
-			for i := range jobs {
-				jobN := tview.NewTreeNode(jobs[i].JobTreeTitle())
-				jobN.SetReference(jobs[i])
-				jobN.SetSelectable(true)
-				children[i] = jobN
-				jobN.SetSelectedFunc(func() {
-					viewmodelupdate(func(p *viewmodel.Params) {
-						p.SelectedJob = jobN.GetReference().(*viewmodel.Job)
-					})
-				})
-				if jobs[i] == m.SelectedJob() {
-					selectedJobN = jobN
-				}
-			}
-			jobMenuRoot.SetChildren(children)
-		}
-
-		if selectedJobN != nil && jobMenu.GetCurrentNode() != selectedJobN {
-			jobMenu.SetCurrentNode(selectedJobN)
-		} else if selectedJobN == nil {
-			// select something, otherwise selection breaks (likely bug in tview)
-			jobMenu.SetCurrentNode(jobMenuRoot)
-		}
-
-		if selJ := m.SelectedJob(); selJ != nil {
-			jobTextDetail.SetText(selJ.FullDescription())
-		} else {
-			jobTextDetail.SetText("please select a job")
-		}
-
-		bottombardatestring := m.DateString()
-		bottombarDateView.SetText(bottombardatestring)
-		bottombar.ResizeItem(bottombarDateView, len(bottombardatestring), 0)
-
-		bottomBarStatus.SetText(m.BottomBarStatus())
-
-		app.Draw()
-
-	}
-
-	go func() {
-		defer func() {
-			if err := recover(); err != nil {
-				app.Suspend(func() {
-					panic(err)
-				})
-			}
-		}()
-		for {
-			st, err := c.Status()
-			viewmodelupdate(func(p *viewmodel.Params) {
-				p.Report = st.Jobs
-				p.ReportFetchError = err
-			})
-			app.QueueUpdateDraw(redraw)
-
-			time.Sleep(flag.Delay)
-		}
-	}()
-
-	jobMenu.SetChangedFunc(func(jobN *tview.TreeNode) {
-		viewmodelupdate(func(p *viewmodel.Params) {
-			p.SelectedJob, _ = jobN.GetReference().(*viewmodel.Job)
-		})
-		redraw()
-		jobTextDetail.ScrollToBeginning()
-	})
-	jobMenu.SetSelectedFunc(func(jobN *tview.TreeNode) {
-		app.SetFocus(jobTextDetail)
-	})
-
-	app.SetBeforeDrawFunc(func(screen tcell.Screen) bool {
-		viewmodelupdate(func(p *viewmodel.Params) {
-			_, _, p.DetailViewWidth, _ = jobTextDetail.GetInnerRect()
-		})
-		return false
-	})
-
-	app.SetInputCapture(func(e *tcell.EventKey) *tcell.EventKey {
-		if e.Key() == tcell.KeyTab {
-			tabbableCycle()
-			return nil
-		}
-
-		if e.Key() == tcell.KeyRune && app.GetFocus() == fsFilterInput {
-			return e
-		}
-
-		if e.Key() == tcell.KeyRune && e.Rune() == '/' {
-			if app.GetFocus() != fsFilterInput {
-				app.SetFocus(fsFilterInput)
-			}
-			return e
-		}
-
-		if e.Key() == tcell.KeyRune && e.Rune() == 'M' {
-			reconfigureJobDetailSplit(!jobMenuVisisble)
-			return nil
-		}
-
-		if e.Key() == tcell.KeyRune && e.Rune() == 'q' {
-			app.Stop()
-		}
-
-		if e.Key() == tcell.KeyRune && e.Rune() == 'S' {
-			job, ok := jobMenu.GetCurrentNode().GetReference().(*viewmodel.Job)
-			if !ok {
-				return nil
-			}
-			signals := []string{"wakeup", "reset"}
-			clientFuncs := []func(job string) error{c.SignalWakeup, c.SignalReset}
-			sigMod := tview.NewModal()
-			sigMod.SetBackgroundColor(tcell.ColorDefault)
-			sigMod.SetBorder(true)
-			sigMod.GetForm().SetButtonTextColorFocused(tcell.ColorGreen)
-			sigMod.AddButtons(signals)
-			sigMod.SetText(fmt.Sprintf("Send a signal to job %q", job.Name()))
-			showModal(sigMod, func(idx int, _ string) {
-				go func() {
-					if idx == -1 {
-						return
-					}
-					err := clientFuncs[idx](job.Name())
-					if err != nil {
-						app.QueueUpdate(func() {
-							me := tview.NewModal()
-							me.SetText(fmt.Sprintf("signal error: %s", err))
-							me.AddButtons([]string{"Close"})
-							showModal(me, nil)
-						})
-					}
-				}()
-			})
-		}
-
-		return e
-	})
-
-	fsFilterInput.SetChangedFunc(func(searchterm string) {
-		viewmodelupdate(func(p *viewmodel.Params) {
-			p.FSFilter = func(fs string) bool {
-				r, err := regexp.Compile(searchterm)
-				if err != nil {
-					return true
-				}
-				return r.MatchString(fs)
-			}
-		})
-		redraw()
-		jobTextDetail.ScrollToBeginning()
-	})
-	fsFilterInput.SetInputCapture(func(event *tcell.EventKey) *tcell.EventKey {
-		if event.Key() == tcell.KeyEnter {
-			app.SetFocus(jobTextDetail)
-			return nil
-		}
-		return event
-	})
-
-	jobTextDetail.SetInputCapture(func(event *tcell.EventKey) *tcell.EventKey {
-		if event.Key() == tcell.KeyRune && event.Rune() == 'w' {
-			// toggle wrapping
-			viewmodelupdate(func(p *viewmodel.Params) {
-				p.DetailViewWrap = !p.DetailViewWrap
-			})
-			redraw()
-			return nil
-		}
-		return event
-	})
-
-	return app.Run()
-}

client/status/status_legacy.go

@@ -1,128 +0,0 @@
-package status
-
-import (
-	"fmt"
-	"os"
-	"strings"
-	"sync"
-	"time"
-
-	"github.com/gdamore/tcell/v2"
-	"github.com/mattn/go-isatty"
-	"github.com/pkg/errors"
-	tview "gitlab.com/tslocum/cview"
-
-	"github.com/zrepl/zrepl/client/status/viewmodel"
-)
-
-func legacy(c Client, flag statusFlags) error {
-
-	// Set this so we don't overwrite the default terminal colors
-	// See https://github.com/rivo/tview/blob/master/styles.go
-	tview.Styles.PrimitiveBackgroundColor = tcell.ColorDefault
-	tview.Styles.ContrastBackgroundColor = tcell.ColorDefault
-	tview.Styles.PrimaryTextColor = tcell.ColorDefault
-	tview.Styles.BorderColor = tcell.ColorDefault
-	app := tview.NewApplication()
-
-	textView := tview.NewTextView()
-	textView.SetWrap(true)
-	textView.SetScrollable(true) // so that it allows us to set scroll position
-	textView.SetScrollBarVisibility(tview.ScrollBarNever)
-
-	app.SetRoot(textView, true)
-
-	width := (1 << 31) - 1
-	wrap := false
-	if isatty.IsTerminal(os.Stdout.Fd()) {
-		wrap = true
-		screen, err := tcell.NewScreen()
-		if err != nil {
-			return errors.Wrap(err, "get terminal dimensions")
-		}
-		if err := screen.Init(); err != nil {
-			return errors.Wrap(err, "init screen")
-		}
-		width, _ = screen.Size()
-		screen.Fini()
-	}
-
-	paramsMtx := &sync.Mutex{}
-	params := viewmodel.Params{
-		Report:                  nil,
-		ReportFetchError:        nil,
-		SelectedJob:             nil,
-		FSFilter:                func(s string) bool { return true },
-		DetailViewWidth:         width,
-		DetailViewWrap:          wrap,
-		ShortKeybindingOverview: "",
-	}
-
-	redraw := func() {
-		textView.Clear()
-
-		paramsMtx.Lock()
-		defer paramsMtx.Unlock()
-
-		if params.ReportFetchError != nil {
-			fmt.Fprintln(textView, params.ReportFetchError.Error())
-		} else if params.Report != nil {
-			m := viewmodel.New()
-			m.Update(params)
-			for _, j := range m.Jobs() {
-				if flag.Job != "" && j.Name() != flag.Job {
-					continue
-				}
-				params.SelectedJob = j
-				m.Update(params)
-				fmt.Fprintln(textView, m.SelectedJob().FullDescription())
-				if flag.Job != "" {
-					break
-				} else {
-					hline := strings.Repeat("-", params.DetailViewWidth)
-					fmt.Fprintln(textView, hline)
-				}
-			}
-		} else {
-			fmt.Fprintln(textView, "waiting for request results")
-		}
-		textView.ScrollToBeginning()
-	}
-
-	app.SetBeforeDrawFunc(func(screen tcell.Screen) bool {
-		// sync resizes to `params`
-		paramsMtx.Lock()
-		_, _, newWidth, _ := textView.GetInnerRect()
-		if newWidth != params.DetailViewWidth {
-			params.DetailViewWidth = newWidth
-			app.QueueUpdateDraw(redraw)
-		}
-		paramsMtx.Unlock()
-
-		textView.ScrollToBeginning() // has the effect of inhibiting user scrolls
-		return false
-	})
-
-	go func() {
-		defer func() {
-			if err := recover(); err != nil {
-				app.Suspend(func() {
-					panic(err)
-				})
-			}
-		}()
-		for {
-			st, err := c.Status()
-			paramsMtx.Lock()
-			params.Report = st.Jobs
-			params.ReportFetchError = err
-			paramsMtx.Unlock()
-
-			app.QueueUpdateDraw(redraw)
-
-			time.Sleep(flag.Delay)
-		}
-	}()
-
-	return app.Run()
-}

client/status/status_raw.go

@@ -1,18 +0,0 @@
-package status
-
-import (
-	"bytes"
-	"io"
-	"os"
-)
-
-func raw(c Client) error {
-	b, err := c.StatusRaw()
-	if err != nil {
-		return err
-	}
-	if _, err := io.Copy(os.Stdout, bytes.NewReader(b)); err != nil {
-		return err
-	}
-	return nil
-}

client/status/viewmodel/bytecountbinary.go

@@ -1,26 +0,0 @@
-package viewmodel
-
-import (
-	"fmt"
-	"math"
-)
-
-func ByteCountBinaryUint(b uint64) string {
-	if b > math.MaxInt64 {
-		panic(b)
-	}
-	return ByteCountBinary(int64(b))
-}
-
-func ByteCountBinary(b int64) string {
-	const unit = 1024
-	if b < unit {
-		return fmt.Sprintf("%d B", b)
-	}
-	div, exp := 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/status/viewmodel/bytesprogresshistory.go

@@ -1,49 +0,0 @@
-package viewmodel
-
-import "time"
-
-type byteProgressMeasurement struct {
-	time time.Time
-	val  uint64
-}
-
-type bytesProgressHistory struct {
-	last        *byteProgressMeasurement // pointer as poor man's optional
-	changeCount int
-	lastChange  time.Time
-}
-
-func (p *bytesProgressHistory) Update(currentVal uint64) (bytesPerSecondAvg int64, changeCount int) {
-
-	if p.last == nil {
-		p.last = &byteProgressMeasurement{
-			time: time.Now(),
-			val:  currentVal,
-		}
-		return 0, 0
-	}
-
-	if p.last.val != currentVal {
-		p.changeCount++
-		p.lastChange = time.Now()
-	}
-
-	if time.Since(p.lastChange) > 3*time.Second {
-		p.last = nil
-		return 0, 0
-	}
-
-	var deltaV int64
-	if currentVal >= p.last.val {
-		deltaV = int64(currentVal - p.last.val)
-	} else {
-		deltaV = -int64(p.last.val - currentVal)
-	}
-	deltaT := time.Since(p.last.time)
-	rate := float64(deltaV) / deltaT.Seconds()
-
-	p.last.time = time.Now()
-	p.last.val = currentVal
-
-	return int64(rate), p.changeCount
-}

client/status/viewmodel/render.go

@@ -1,660 +0,0 @@
-package viewmodel
-
-import (
-	"fmt"
-	"math"
-	"sort"
-	"strings"
-	"time"
-
-	"github.com/go-playground/validator/v10"
-	yaml "github.com/zrepl/yaml-config"
-
-	"github.com/zrepl/zrepl/client/status/viewmodel/stringbuilder"
-	"github.com/zrepl/zrepl/daemon"
-	"github.com/zrepl/zrepl/daemon/job"
-	"github.com/zrepl/zrepl/daemon/pruner"
-	"github.com/zrepl/zrepl/daemon/snapper"
-	"github.com/zrepl/zrepl/replication/report"
-)
-
-type M struct {
-	jobs            map[string]*Job
-	jobsList        []*Job
-	selectedJob     *Job
-	dateString      string
-	bottomBarStatus string
-}
-
-type Job struct {
-	// long-lived
-	name         string
-	byteProgress *bytesProgressHistory
-
-	lastStatus      *job.Status
-	fulldescription string
-}
-
-func New() *M {
-	return &M{
-		jobs:        make(map[string]*Job),
-		jobsList:    make([]*Job, 0),
-		selectedJob: nil,
-	}
-}
-
-type FilterFunc func(string) bool
-
-type Params struct {
-	Report                  map[string]*job.Status
-	ReportFetchError        error
-	SelectedJob             *Job
-	FSFilter                FilterFunc `validate:"required"`
-	DetailViewWidth         int        `validate:"gte=1"`
-	DetailViewWrap          bool
-	ShortKeybindingOverview string
-}
-
-var validate = validator.New()
-
-func (m *M) Update(p Params) {
-
-	if err := validate.Struct(p); err != nil {
-		panic(err)
-	}
-
-	if p.ReportFetchError != nil {
-		m.bottomBarStatus = fmt.Sprintf("[red::]status fetch: %s", p.ReportFetchError)
-	} else {
-		m.bottomBarStatus = p.ShortKeybindingOverview
-		for jobname, st := range p.Report {
-			// TODO handle job renames & deletions
-			j, ok := m.jobs[jobname]
-			if !ok {
-				j = &Job{
-					name:         jobname,
-					byteProgress: &bytesProgressHistory{},
-				}
-				m.jobs[jobname] = j
-				m.jobsList = append(m.jobsList, j)
-			}
-			j.lastStatus = st
-		}
-	}
-
-	// filter out internal jobs
-	var jobsList []*Job
-	for _, j := range m.jobsList {
-		if daemon.IsInternalJobName(j.name) {
-			continue
-		}
-		jobsList = append(jobsList, j)
-	}
-	m.jobsList = jobsList
-
-	// determinism!
-	sort.Slice(m.jobsList, func(i, j int) bool {
-		return strings.Compare(m.jobsList[i].name, m.jobsList[j].name) < 0
-	})
-
-	// try to not lose the selected job
-	m.selectedJob = nil
-	for _, j := range m.jobsList {
-		j.updateFullDescription(p)
-		if j == p.SelectedJob {
-			m.selectedJob = j
-		}
-	}
-
-	m.dateString = time.Now().Format(time.RFC3339)
-
-}
-
-func (m *M) BottomBarStatus() string { return m.bottomBarStatus }
-
-func (m *M) Jobs() []*Job { return m.jobsList }
-
-// may be nil
-func (m *M) SelectedJob() *Job { return m.selectedJob }
-
-func (m *M) DateString() string { return m.dateString }
-
-func (j *Job) updateFullDescription(p Params) {
-	width := p.DetailViewWidth
-	if !p.DetailViewWrap {
-		width = 10000000 // FIXME
-	}
-	b := stringbuilder.New(stringbuilder.Config{
-		IndentMultiplier: 3,
-		Width:            width,
-	})
-	drawJob(b, j.name, j.lastStatus, j.byteProgress, p.FSFilter)
-	j.fulldescription = b.String()
-}
-
-func (j *Job) JobTreeTitle() string {
-	return j.name
-}
-
-func (j *Job) FullDescription() string {
-	return j.fulldescription
-}
-
-func (j *Job) Name() string {
-	return j.name
-}
-
-func drawJob(t *stringbuilder.B, name string, v *job.Status, history *bytesProgressHistory, fsfilter FilterFunc) {
-
-	t.Printf("Job: %s\n", name)
-	t.Printf("Type: %s\n\n", v.Type)
-
-	if v.Type == job.TypePush || v.Type == job.TypePull {
-		activeStatus, ok := v.JobSpecific.(*job.ActiveSideStatus)
-		if !ok || activeStatus == nil {
-			t.Printf("ActiveSideStatus is null")
-			t.Newline()
-			return
-		}
-
-		t.Printf("Replication:")
-		t.AddIndentAndNewline(1)
-		renderReplicationReport(t, activeStatus.Replication, history, fsfilter)
-		t.AddIndentAndNewline(-1)
-
-		t.Printf("Pruning Sender:")
-		t.AddIndentAndNewline(1)
-		renderPrunerReport(t, activeStatus.PruningSender, fsfilter)
-		t.AddIndentAndNewline(-1)
-
-		t.Printf("Pruning Receiver:")
-		t.AddIndentAndNewline(1)
-		renderPrunerReport(t, activeStatus.PruningReceiver, fsfilter)
-		t.AddIndentAndNewline(-1)
-
-		if v.Type == job.TypePush {
-			t.Printf("Snapshotting:")
-			t.AddIndentAndNewline(1)
-			renderSnapperReport(t, activeStatus.Snapshotting, fsfilter)
-			t.AddIndentAndNewline(-1)
-		}
-
-	} else if v.Type == job.TypeSnap {
-		snapStatus, ok := v.JobSpecific.(*job.SnapJobStatus)
-		if !ok || snapStatus == nil {
-			t.Printf("SnapJobStatus is null")
-			t.Newline()
-			return
-		}
-		t.Printf("Pruning snapshots:")
-		t.AddIndentAndNewline(1)
-		renderPrunerReport(t, snapStatus.Pruning, fsfilter)
-		t.AddIndentAndNewline(-1)
-		t.Printf("Snapshotting:")
-		t.AddIndentAndNewline(1)
-		renderSnapperReport(t, snapStatus.Snapshotting, fsfilter)
-		t.AddIndentAndNewline(-1)
-	} else if v.Type == job.TypeSource {
-
-		st := v.JobSpecific.(*job.PassiveStatus)
-		t.Printf("Snapshotting:\n")
-		t.AddIndent(1)
-		renderSnapperReport(t, st.Snapper, fsfilter)
-		t.AddIndentAndNewline(-1)
-
-	} else {
-		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()
-			return
-		}
-		t.Write(string(asYaml))
-		t.Newline()
-	}
-}
-
-func printFilesystemStatus(t *stringbuilder.B, rep *report.FilesystemReport, maxFS int) {
-
-	expected, replicated, containsInvalidSizeEstimates := rep.BytesSum()
-	sizeEstimationImpreciseNotice := ""
-	if containsInvalidSizeEstimates {
-		sizeEstimationImpreciseNotice = " (some steps lack size estimation)"
-	}
-	if rep.CurrentStep < len(rep.Steps) && rep.Steps[rep.CurrentStep].Info.BytesExpected == 0 {
-		sizeEstimationImpreciseNotice = " (step lacks size estimation)"
-	}
-
-	userVisisbleCurrentStep, userVisibleTotalSteps := rep.CurrentStep, len(rep.Steps)
-	// `.CurrentStep` is == len(rep.Steps) if all steps are done.
-	// Until then, it's an index into .Steps that starts at 0.
-	// For the user, we want it to start at 1.
-	if rep.CurrentStep >= len(rep.Steps) {
-		// rep.CurrentStep is what we want to show.
-		// We check for >= and not == for robustness.
-	} else {
-		// We're not done yet, so, make step count start at 1
-		// (The `.State` is included in the output, indicating we're not done yet)
-		userVisisbleCurrentStep = rep.CurrentStep + 1
-	}
-	status := fmt.Sprintf("%s (step %d/%d, %s/%s)%s",
-		strings.ToUpper(string(rep.State)),
-		userVisisbleCurrentStep, userVisibleTotalSteps,
-		ByteCountBinaryUint(replicated), ByteCountBinaryUint(expected),
-		sizeEstimationImpreciseNotice,
-	)
-
-	activeIndicator := " "
-	if rep.BlockedOn == report.FsBlockedOnNothing &&
-		(rep.State == report.FilesystemPlanning || rep.State == report.FilesystemStepping) {
-		activeIndicator = "*"
-	}
-	t.AddIndent(1)
-	t.Printf("%s %s %s ",
-		activeIndicator,
-		stringbuilder.RightPad(rep.Info.Name, maxFS, " "),
-		status)
-
-	next := ""
-	if err := rep.Error(); err != nil {
-		next = err.Err
-	} else if rep.State != report.FilesystemDone {
-		if nextStep := rep.NextStep(); nextStep != nil {
-			if nextStep.IsIncremental() {
-				next = fmt.Sprintf("next: %s => %s", nextStep.Info.From, nextStep.Info.To)
-			} else {
-				next = fmt.Sprintf("next: full send %s", nextStep.Info.To)
-			}
-			attribs := []string{}
-
-			if nextStep.Info.Resumed {
-				attribs = append(attribs, "resumed")
-			}
-
-			if len(attribs) > 0 {
-				next += fmt.Sprintf(" (%s)", strings.Join(attribs, ", "))
-			}
-		} else {
-			next = "" // individual FSes may still be in planning state
-		}
-
-	}
-	t.Printf("%s", next)
-
-	t.AddIndent(-1)
-	t.Newline()
-}
-
-func renderReplicationReport(t *stringbuilder.B, rep *report.Report, history *bytesProgressHistory, fsfilter FilterFunc) {
-	if rep == nil {
-		t.Printf("...\n")
-		return
-	}
-
-	if rep.WaitReconnectError != nil {
-		t.PrintfDrawIndentedAndWrappedIfMultiline("Connectivity: %s", rep.WaitReconnectError)
-		t.Newline()
-	}
-	if !rep.WaitReconnectSince.IsZero() {
-		delta := time.Until(rep.WaitReconnectUntil).Round(time.Second)
-		if rep.WaitReconnectUntil.IsZero() || delta > 0 {
-			var until string
-			if rep.WaitReconnectUntil.IsZero() {
-				until = "waiting indefinitely"
-			} else {
-				until = fmt.Sprintf("hard fail in %s @ %s", delta, rep.WaitReconnectUntil)
-			}
-			t.PrintfDrawIndentedAndWrappedIfMultiline("Connectivity: reconnecting with exponential backoff (since %s) (%s)",
-				rep.WaitReconnectSince, until)
-		} else {
-			t.PrintfDrawIndentedAndWrappedIfMultiline("Connectivity: reconnects reached hard-fail timeout @ %s", rep.WaitReconnectUntil)
-		}
-		t.Newline()
-	}
-
-	// TODO visualize more than the latest attempt by folding all attempts into one
-	if len(rep.Attempts) == 0 {
-		t.Printf("no attempts made yet")
-		return
-	} else {
-		t.Printf("Attempt #%d", len(rep.Attempts))
-		if len(rep.Attempts) > 1 {
-			t.Printf(". Previous attempts failed with the following statuses:")
-			t.AddIndentAndNewline(1)
-			for i, a := range rep.Attempts[:len(rep.Attempts)-1] {
-				t.PrintfDrawIndentedAndWrappedIfMultiline("#%d: %s (failed at %s) (ran %s)\n", i+1, a.State, a.FinishAt, a.FinishAt.Sub(a.StartAt))
-			}
-			t.AddIndentAndNewline(-1)
-		} else {
-			t.Newline()
-		}
-	}
-
-	latest := rep.Attempts[len(rep.Attempts)-1]
-	sort.Slice(latest.Filesystems, func(i, j int) bool {
-		return latest.Filesystems[i].Info.Name < latest.Filesystems[j].Info.Name
-	})
-
-	// apply filter
-	filtered := make([]*report.FilesystemReport, 0, len(latest.Filesystems))
-	for _, fs := range latest.Filesystems {
-		if !fsfilter(fs.Info.Name) {
-			continue
-		}
-		filtered = append(filtered, fs)
-	}
-	latest.Filesystems = filtered
-
-	t.Printf("Status: %s", latest.State)
-	t.Newline()
-	if !latest.FinishAt.IsZero() {
-		t.Printf("Last Run: %s (lasted %s)\n", latest.FinishAt.Round(time.Second), latest.FinishAt.Sub(latest.StartAt).Round(time.Second))
-	} else {
-		t.Printf("Started: %s (lasting %s)\n", latest.StartAt.Round(time.Second), time.Since(latest.StartAt).Round(time.Second))
-	}
-
-	if latest.State == report.AttemptPlanningError {
-		t.Printf("Problem: ")
-		t.PrintfDrawIndentedAndWrappedIfMultiline("%s", latest.PlanError)
-		t.Newline()
-	} else if latest.State == report.AttemptFanOutError {
-		t.Printf("Problem: one or more of the filesystems encountered errors")
-		t.Newline()
-	}
-
-	if latest.State != report.AttemptPlanning && latest.State != report.AttemptPlanningError {
-		// Draw global progress bar
-		// Progress: [---------------]
-		expected, replicated, containsInvalidSizeEstimates := latest.BytesSum()
-		rate, changeCount := history.Update(replicated)
-		eta := time.Duration(0)
-		if rate > 0 {
-			eta = time.Duration((float64(expected)-float64(replicated))/float64(rate)) * time.Second
-		}
-
-		if !latest.State.IsTerminal() {
-			t.Write("Progress: ")
-			t.DrawBar(50, replicated, expected, changeCount)
-			t.Write(fmt.Sprintf(" %s / %s @ %s/s", ByteCountBinaryUint(replicated), ByteCountBinaryUint(expected), ByteCountBinary(rate)))
-			if eta != 0 {
-				t.Write(fmt.Sprintf(" (%s remaining)", humanizeDuration(eta)))
-			}
-			t.Newline()
-		}
-		if containsInvalidSizeEstimates {
-			t.Write("NOTE: not all steps could be size-estimated, total estimate is likely imprecise!")
-			t.Newline()
-		}
-
-		if len(latest.Filesystems) == 0 {
-			t.Write("NOTE: no filesystems were considered for replication!")
-			t.Newline()
-		}
-
-		var maxFSLen int
-		for _, fs := range latest.Filesystems {
-			if len(fs.Info.Name) > maxFSLen {
-				maxFSLen = len(fs.Info.Name)
-			}
-		}
-		for _, fs := range latest.Filesystems {
-			printFilesystemStatus(t, fs, maxFSLen)
-		}
-
-	}
-}
-
-func humanizeDuration(duration time.Duration) string {
-	days := int64(duration.Hours() / 24)
-	hours := int64(math.Mod(duration.Hours(), 24))
-	minutes := int64(math.Mod(duration.Minutes(), 60))
-	seconds := int64(math.Mod(duration.Seconds(), 60))
-
-	var parts []string
-
-	force := false
-	chunks := []int64{days, hours, minutes, seconds}
-	for i, chunk := range chunks {
-		if force || chunk > 0 {
-			padding := 0
-			if force {
-				padding = 2
-			}
-			parts = append(parts, fmt.Sprintf("%*d%c", padding, chunk, "dhms"[i]))
-			force = true
-		}
-	}
-
-	return strings.Join(parts, " ")
-}
-
-func renderPrunerReport(t *stringbuilder.B, r *pruner.Report, fsfilter FilterFunc) {
-	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)
-	}
-
-	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})
-	}
-
-	// filter all
-	filtered := make([]commonFS, 0, len(all))
-	for _, fs := range all {
-		if fsfilter(fs.FSReport.Filesystem) {
-			filtered = append(filtered, fs)
-		}
-	}
-	all = filtered
-
-	switch state {
-	case pruner.Plan:
-		fallthrough
-	case pruner.PlanErr:
-		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
-	if !state.IsTerminal() {
-		progress := int(math.Round(80 * float64(completedDestroyCount) / float64(totalDestroyCount)))
-		t.Write("Progress: ")
-		t.Write("[")
-		t.Write(stringbuilder.Times("=", progress))
-		t.Write(">")
-		t.Write(stringbuilder.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(stringbuilder.RightPad(fs.Filesystem, maxFSname, " "))
-		t.Write(" ")
-		if !fs.SkipReason.NotSkipped() {
-			t.Printf("skipped: %s\n", fs.SkipReason)
-			continue
-		}
-		if fs.LastError != "" {
-			if strings.ContainsAny(fs.LastError, "\r\n") {
-				t.Printf("ERROR:")
-				t.PrintfDrawIndentedAndWrappedIfMultiline("%s\n", fs.LastError)
-			} else {
-				t.PrintfDrawIndentedAndWrappedIfMultiline("ERROR: %s\n", fs.LastError)
-			}
-			t.Newline()
-			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()
-	}
-
-}
-
-func renderSnapperReport(t *stringbuilder.B, r *snapper.Report, fsfilter FilterFunc) {
-	if r == nil {
-		t.Printf("<no snapshotting report available>\n")
-		return
-	}
-	t.Printf("Type: %s\n", r.Type)
-	if r.Periodic != nil {
-		renderSnapperReportPeriodic(t, r.Periodic, fsfilter)
-	} else if r.Cron != nil {
-		renderSnapperReportCron(t, r.Cron, fsfilter)
-	} else {
-		t.Printf("<no details available>")
-	}
-}
-
-func renderSnapperReportPeriodic(t *stringbuilder.B, r *snapper.PeriodicReport, fsfilter FilterFunc) {
-	t.Printf("Status: %s", r.State)
-	t.Newline()
-
-	if r.Error != "" {
-		t.Printf("Error: %s\n", r.Error)
-	}
-	if !r.SleepUntil.IsZero() {
-		t.Printf("Sleep until: %s\n", r.SleepUntil)
-	}
-
-	renderSnapperPlanReportFilesystem(t, r.Progress, fsfilter)
-}
-
-func renderSnapperReportCron(t *stringbuilder.B, r *snapper.CronReport, fsfilter FilterFunc) {
-	t.Printf("State: %s\n", r.State)
-
-	now := time.Now()
-	if r.WakeupTime.After(now) {
-		t.Printf("Sleep until: %s (%s remaining)\n", r.WakeupTime, r.WakeupTime.Sub(now).Round(time.Second))
-	} else {
-		t.Printf("Started: %s (lasting %s)\n", r.WakeupTime, now.Sub(r.WakeupTime).Round(time.Second))
-	}
-
-	renderSnapperPlanReportFilesystem(t, r.Progress, fsfilter)
-}
-
-func renderSnapperPlanReportFilesystem(t *stringbuilder.B, fss []*snapper.ReportFilesystem, fsfilter FilterFunc) {
-	sort.Slice(fss, func(i, j int) bool {
-		return strings.Compare(fss[i].Path, fss[j].Path) == -1
-	})
-
-	dur := func(d time.Duration) string {
-		return d.Round(100 * time.Millisecond).String()
-	}
-
-	type row struct {
-		path, state, duration, remainder, hookReport string
-	}
-	var widths struct {
-		path, state, duration int
-	}
-	rows := make([]*row, 0, len(fss))
-	for _, fs := range fss {
-		if !fsfilter(fs.Path) {
-			continue
-		}
-		r := &row{
-			path:  fs.Path,
-			state: fs.State.String(),
-		}
-		if fs.HooksHadError {
-			r.hookReport = fs.Hooks // FIXME render here, not in daemon
-		}
-		switch fs.State {
-		case snapper.SnapPending:
-			r.duration = "..."
-			r.remainder = ""
-		case snapper.SnapStarted:
-			r.duration = dur(time.Since(fs.StartAt))
-			r.remainder = fmt.Sprintf("snap name: %q", fs.SnapName)
-		case snapper.SnapDone:
-			fallthrough
-		case snapper.SnapError:
-			r.duration = dur(fs.DoneAt.Sub(fs.StartAt))
-			r.remainder = fmt.Sprintf("snap name: %q", fs.SnapName)
-		}
-		rows = append(rows, r)
-		if len(r.path) > widths.path {
-			widths.path = len(r.path)
-		}
-		if len(r.state) > widths.state {
-			widths.state = len(r.state)
-		}
-		if len(r.duration) > widths.duration {
-			widths.duration = len(r.duration)
-		}
-	}
-
-	for _, r := range rows {
-		path := stringbuilder.RightPad(r.path, widths.path, " ")
-		state := stringbuilder.RightPad(r.state, widths.state, " ")
-		duration := stringbuilder.RightPad(r.duration, widths.duration, " ")
-		t.Printf("%s %s %s", path, state, duration)
-		t.PrintfDrawIndentedAndWrappedIfMultiline(" %s", r.remainder)
-		if r.hookReport != "" {
-			t.AddIndent(1)
-			t.Newline()
-			t.Printf("%s", r.hookReport)
-			t.AddIndent(-1)
-		}
-		t.Newline()
-	}
-}

client/status/viewmodel/stringbuilder/stringbuilder.go

@@ -1,119 +0,0 @@
-package stringbuilder
-
-import (
-	"fmt"
-	"strings"
-
-	"github.com/go-playground/validator/v10"
-)
-
-type B struct {
-	// const
-	indentMultiplier int
-
-	// mut
-	sb     *strings.Builder
-	indent int
-	width  int
-	x, y   int
-}
-
-type Config struct {
-	IndentMultiplier int `validate:"gte=1"`
-	Width            int `validate:"gte=1"`
-}
-
-var validate = validator.New()
-
-func New(config Config) *B {
-
-	if err := validate.Struct(config); err != nil {
-		panic(err)
-	}
-
-	return &B{sb: &strings.Builder{}, width: config.Width, indentMultiplier: config.IndentMultiplier}
-}
-
-func (b *B) String() string { return b.sb.String() }
-
-func (w *B) Newline() {
-	w.Write("\n")
-}
-
-func (w *B) PrintfDrawIndentedAndWrappedIfMultiline(format string, args ...interface{}) {
-	whole := fmt.Sprintf(format, args...)
-	if strings.ContainsAny(whole, "\n\r") {
-		w.AddIndent(1)
-		defer w.AddIndent(-1)
-	}
-	w.Write(whole)
-}
-
-func (w *B) Printf(format string, args ...interface{}) {
-	whole := fmt.Sprintf(format, args...)
-	w.Write(whole)
-}
-
-func (t *B) AddIndent(delta int) {
-	t.indent += delta * t.indentMultiplier
-}
-
-func (t *B) AddIndentAndNewline(delta int) {
-	t.indent += delta * t.indentMultiplier
-	t.Write("\n")
-}
-
-func (w *B) Write(s string) {
-	for _, c := range s {
-		if c == '\n' {
-			fmt.Fprint(w.sb, "\n")
-			w.x = 0
-			fmt.Fprint(w.sb, Times(" ", w.indent-w.x))
-			w.x = w.indent
-			w.y++
-			continue
-		}
-		if w.x >= w.width {
-			fmt.Fprint(w.sb, "\n")
-			w.x = 0
-			fmt.Fprint(w.sb, Times(" ", w.indent-w.x))
-			w.x = w.indent
-		}
-		fmt.Fprintf(w.sb, "%c", c)
-		w.x++
-	}
-}
-
-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 + strings.Repeat(pad, length-len(str))
-}
-
-// changeCount = 0 indicates stall / no progress
-func (w *B) DrawBar(length int, bytes, totalBytes uint64, changeCount int) {
-	const arrowPositions = `>\|/`
-	var completedLength int
-	if totalBytes > 0 {
-		completedLength = int(uint64(length) * bytes / totalBytes)
-		if completedLength > length {
-			completedLength = length
-		}
-	} else if totalBytes == bytes {
-		completedLength = length
-	}
-
-	w.Write("[")
-	w.Write(Times("=", completedLength))
-	w.Write(string(arrowPositions[changeCount%len(arrowPositions)]))
-	w.Write(Times("-", length-completedLength))
-	w.Write("]")
-}

client/testcmd.go

@@ -139,11 +139,9 @@ var testPlaceholder = &cli.Subcommand{
 func runTestPlaceholder(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
 
 	var checkDPs []*zfs.DatasetPath
-	var datasetWasExplicitArgument bool
 
 	// all actions first
 	if testPlaceholderArgs.all {
-		datasetWasExplicitArgument = false
 		out, err := zfs.ZFSList(ctx, []string{"name"})
 		if err != nil {
 			return errors.Wrap(err, "could not list ZFS filesystems")
@@ -156,7 +154,6 @@ func runTestPlaceholder(ctx context.Context, subcommand *cli.Subcommand, args []
 			checkDPs = append(checkDPs, dp)
 		}
 	} else {
-		datasetWasExplicitArgument = true
 		dp, err := zfs.NewDatasetPath(testPlaceholderArgs.ds)
 		if err != nil {
 			return err
@@ -174,12 +171,7 @@ func runTestPlaceholder(ctx context.Context, subcommand *cli.Subcommand, args []
 			return errors.Wrap(err, "cannot get placeholder state")
 		}
 		if !ph.FSExists {
-			if datasetWasExplicitArgument {
-				return errors.Errorf("filesystem %q does not exist", ph.FS)
-			} else {
-				// got deleted between ZFSList and ZFSGetFilesystemPlaceholderState
-				continue
-			}
+			panic("placeholder state inconsistent: filesystem " + ph.FS + " must exist in this context")
 		}
 		is := "yes"
 		if !ph.IsPlaceholder {

client/zfsabstractions.go

@@ -57,7 +57,7 @@ func (f *zabsFilterFlags) registerZabsFilterFlags(s *pflag.FlagSet, verb string)
 	for v := range endpoint.AbstractionTypesAll {
 		variants = append(variants, string(v))
 	}
-	sort.Strings(variants)
+	variants = sort.StringSlice(variants)
 	variantsJoined := strings.Join(variants, "|")
 	s.Var(&f.Types, "type", fmt.Sprintf("only %s holds of the specified type [default: all] [comma-separated list of %s]", verb, variantsJoined))
 

client/zfsabstractions_list.go

@@ -44,18 +44,17 @@ func doZabsList(ctx context.Context, sc *cli.Subcommand, args []string) error {
 		return errors.Wrap(err, "invalid filter specification on command line")
 	}
 
-	abstractions, errors, drainDone, err := endpoint.ListAbstractionsStreamed(ctx, q)
+	abstractions, errors, err := endpoint.ListAbstractionsStreamed(ctx, q)
 	if err != nil {
 		return err // context clear by invocation of command
 	}
-	defer drainDone()
 
 	var line chainlock.L
 	var wg sync.WaitGroup
 	defer wg.Wait()
+	wg.Add(1)
 
 	// print results
-	wg.Add(1)
 	go func() {
 		defer wg.Done()
 		enc := json.NewEncoder(os.Stdout)
@@ -64,7 +63,7 @@ func doZabsList(ctx context.Context, sc *cli.Subcommand, args []string) error {
 				defer line.Lock().Unlock()
 				if zabsListFlags.Json {
 					enc.SetIndent("", "  ")
-					if err := enc.Encode(a); err != nil {
+					if err := enc.Encode(abstractions); err != nil {
 						panic(err)
 					}
 					fmt.Println()

config/config.go

@@ -6,21 +6,12 @@ import (
 	"log/syslog"
 	"os"
 	"reflect"
+	"regexp"
+	"strconv"
 	"time"
 
 	"github.com/pkg/errors"
-	"github.com/robfig/cron/v3"
 	"github.com/zrepl/yaml-config"
-
-	"github.com/zrepl/zrepl/util/datasizeunit"
-	zfsprop "github.com/zrepl/zrepl/zfs/property"
-)
-
-type ParseFlags uint
-
-const (
-	ParseFlagsNone        ParseFlags = 0
-	ParseFlagsNoCertCheck ParseFlags = 1 << iota
 )
 
 type Config struct {
@@ -61,114 +52,56 @@ func (j JobEnum) Name() string {
 }
 
 type ActiveJob struct {
-	Type               string                `yaml:"type"`
-	Name               string                `yaml:"name"`
-	Connect            ConnectEnum           `yaml:"connect"`
-	Pruning            PruningSenderReceiver `yaml:"pruning"`
-	Replication        *Replication          `yaml:"replication,optional,fromdefaults"`
-	ConflictResolution *ConflictResolution   `yaml:"conflict_resolution,optional,fromdefaults"`
-}
-
-type ConflictResolution struct {
-	InitialReplication string `yaml:"initial_replication,optional,default=most_recent"`
+	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"`
+	Type  string           `yaml:"type"`
+	Name  string           `yaml:"name"`
+	Serve ServeEnum        `yaml:"serve"`
+	Debug JobDebugSettings `yaml:"debug,optional"`
 }
 
 type SnapJob struct {
 	Type         string            `yaml:"type"`
 	Name         string            `yaml:"name"`
 	Pruning      PruningLocal      `yaml:"pruning"`
+	Debug        JobDebugSettings  `yaml:"debug,optional"`
 	Snapshotting SnapshottingEnum  `yaml:"snapshotting"`
 	Filesystems  FilesystemsFilter `yaml:"filesystems"`
 }
 
 type SendOptions struct {
-	Encrypted        bool `yaml:"encrypted,optional,default=false"`
-	Raw              bool `yaml:"raw,optional,default=false"`
-	SendProperties   bool `yaml:"send_properties,optional,default=false"`
-	BackupProperties bool `yaml:"backup_properties,optional,default=false"`
-	LargeBlocks      bool `yaml:"large_blocks,optional,default=false"`
-	Compressed       bool `yaml:"compressed,optional,default=false"`
-	EmbeddedData     bool `yaml:"embedded_data,optional,default=false"`
-	Saved            bool `yaml:"saved,optional,default=false"`
+	Encrypted bool                 `yaml:"encrypted"`
+	StepHolds SendOptionsStepHolds `yaml:"step_holds,optional"`
+}
 
-	BandwidthLimit *BandwidthLimit `yaml:"bandwidth_limit,optional,fromdefaults"`
+type SendOptionsStepHolds struct {
+	DisableIncremental bool `yaml:"disable_incremental,optional"`
+}
+
+var _ yaml.Defaulter = (*SendOptions)(nil)
+
+func (l *SendOptions) SetDefault() {
+	*l = SendOptions{Encrypted: false}
 }
 
 type RecvOptions struct {
 	// Note: we cannot enforce encrypted recv as the ZFS cli doesn't provide a mechanism for it
 	// Encrypted bool `yaml:"may_encrypted"`
+
 	// Future:
 	// Reencrypt bool `yaml:"reencrypt"`
-
-	Properties *PropertyRecvOptions `yaml:"properties,fromdefaults"`
-
-	BandwidthLimit *BandwidthLimit `yaml:"bandwidth_limit,optional,fromdefaults"`
-
-	Placeholder *PlaceholderRecvOptions `yaml:"placeholder,fromdefaults"`
 }
 
-var _ yaml.Unmarshaler = &datasizeunit.Bits{}
+var _ yaml.Defaulter = (*RecvOptions)(nil)
 
-type BandwidthLimit struct {
-	Max            datasizeunit.Bits `yaml:"max,default=-1 B"`
-	BucketCapacity datasizeunit.Bits `yaml:"bucket_capacity,default=128 KiB"`
-}
-
-type Replication struct {
-	Triggers    []*ReplicationTriggerEnum
-	Protection  *ReplicationOptionsProtection  `yaml:"protection,optional,fromdefaults"`
-	Concurrency *ReplicationOptionsConcurrency `yaml:"concurrency,optional,fromdefaults"`
-}
-
-type ReplicationOptionsProtection struct {
-	Initial     string `yaml:"initial,optional,default=guarantee_resumability"`
-	Incremental string `yaml:"incremental,optional,default=guarantee_resumability"`
-}
-
-type ReplicationOptionsConcurrency struct {
-	Steps         int `yaml:"steps,optional,default=1"`
-	SizeEstimates int `yaml:"size_estimates,optional,default=4"`
-}
-
-type ReplicationTriggerEnum struct {
-	Ret interface{}
-}
-
-func (t *ReplicationTriggerEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
-	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"manual":   &ReplicationTriggerManual{},
-		"periodic": &ReplicationTriggerPeriodic{},
-	})
-	return
-}
-
-type ReplicationTriggerManual struct {
-	Type string `yaml:"type"`
-}
-
-type ReplicationTriggerPeriodic struct {
-	Type     string            `yaml:"type"`
-	Interval *PositiveDuration `yaml:"interval"`
-}
-
-type ReplicationTriggerCron struct {
-	Type string   `yaml:"type"`
-	Cron CronSpec `yaml:"cron"`
-}
-
-type PropertyRecvOptions struct {
-	Inherit  []zfsprop.Property          `yaml:"inherit,optional"`
-	Override map[zfsprop.Property]string `yaml:"override,optional"`
-}
-
-type PlaceholderRecvOptions struct {
-	Encryption string `yaml:"encryption,default=unspecified"`
+func (l *RecvOptions) SetDefault() {
+	*l = RecvOptions{}
 }
 
 type PushJob struct {
@@ -178,19 +111,13 @@ type PushJob struct {
 	Send         *SendOptions      `yaml:"send,fromdefaults,optional"`
 }
 
-func (j *PushJob) GetFilesystems() FilesystemsFilter { return j.Filesystems }
-func (j *PushJob) GetSendOptions() *SendOptions      { return j.Send }
-
 type PullJob struct {
 	ActiveJob `yaml:",inline"`
 	RootFS    string                   `yaml:"root_fs"`
+	Interval  PositiveDurationOrManual `yaml:"interval"`
 	Recv      *RecvOptions             `yaml:"recv,fromdefaults,optional"`
 }
 
-func (j *PullJob) GetRootFS() string             { return j.RootFS }
-func (j *PullJob) GetAppendClientIdentity() bool { return false }
-func (j *PullJob) GetRecvOptions() *RecvOptions  { return j.Recv }
-
 type PositiveDurationOrManual struct {
 	Interval time.Duration
 	Manual   bool
@@ -211,10 +138,13 @@ func (i *PositiveDurationOrManual) UnmarshalYAML(u func(interface{}, bool) error
 		return fmt.Errorf("value must not be empty")
 	default:
 		i.Manual = false
-		i.Interval, err = parsePositiveDuration(s)
+		i.Interval, err = time.ParseDuration(s)
 		if err != nil {
 			return err
 		}
+		if i.Interval <= 0 {
+			return fmt.Errorf("value must be a positive duration, got %q", s)
+		}
 	}
 	return nil
 }
@@ -225,10 +155,6 @@ type SinkJob struct {
 	Recv       *RecvOptions `yaml:"recv,optional,fromdefaults"`
 }
 
-func (j *SinkJob) GetRootFS() string             { return j.RootFS }
-func (j *SinkJob) GetAppendClientIdentity() bool { return true }
-func (j *SinkJob) GetRecvOptions() *RecvOptions  { return j.Recv }
-
 type SourceJob struct {
 	PassiveJob   `yaml:",inline"`
 	Snapshotting SnapshottingEnum  `yaml:"snapshotting"`
@@ -236,9 +162,6 @@ type SourceJob struct {
 	Send         *SendOptions      `yaml:"send,optional,fromdefaults"`
 }
 
-func (j *SourceJob) GetFilesystems() FilesystemsFilter { return j.Filesystems }
-func (j *SourceJob) GetSendOptions() *SendOptions      { return j.Send }
-
 type FilesystemsFilter map[string]bool
 
 type SnapshottingEnum struct {
@@ -246,44 +169,10 @@ type SnapshottingEnum struct {
 }
 
 type SnapshottingPeriodic struct {
-	Type            string            `yaml:"type"`
-	Prefix          string            `yaml:"prefix"`
-	Interval        *PositiveDuration `yaml:"interval"`
-	Hooks           HookList          `yaml:"hooks,optional"`
-	TimestampFormat string            `yaml:"timestamp_format,optional,default=dense"`
-}
-
-type CronSpec struct {
-	Schedule cron.Schedule
-}
-
-var _ yaml.Unmarshaler = &CronSpec{}
-
-func (s *CronSpec) UnmarshalYAML(unmarshal func(v interface{}, not_strict bool) error) error {
-	var specString string
-	if err := unmarshal(&specString, false); err != nil {
-		return err
-	}
-
-	// Use standard cron format.
-	// Disable the various "descriptors" (@daily, etc)
-	// They are just aliases to "top of hour", "midnight", etc.
-	parser := cron.NewParser(cron.Minute | cron.Hour | cron.Dom | cron.Month | cron.Dow | cron.SecondOptional)
-
-	sched, err := parser.Parse(specString)
-	if err != nil {
-		return errors.Wrap(err, "cron syntax invalid")
-	}
-	s.Schedule = sched
-	return nil
-}
-
-type SnapshottingCron struct {
-	Type            string   `yaml:"type"`
-	Prefix          string   `yaml:"prefix"`
-	Cron            CronSpec `yaml:"cron"`
-	Hooks           HookList `yaml:"hooks,optional"`
-	TimestampFormat string   `yaml:"timestamp_format,optional,default=dense"`
+	Type     string        `yaml:"type"`
+	Prefix   string        `yaml:"prefix"`
+	Interval time.Duration `yaml:"interval,positive"`
+	Hooks    HookList      `yaml:"hooks,optional"`
 }
 
 type SnapshottingManual struct {
@@ -428,7 +317,6 @@ type PruneKeepNotReplicated struct {
 type PruneKeepLastN struct {
 	Type  string `yaml:"type"`
 	Count int    `yaml:"count"`
-	Regex string `yaml:"regex,optional"`
 }
 
 type PruneKeepRegex struct { // FIXME rename to KeepRegex
@@ -503,6 +391,14 @@ 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"`
+}
+
 type HookList []HookEnum
 
 type HookEnum struct {
@@ -601,7 +497,6 @@ func (t *SnapshottingEnum) UnmarshalYAML(u func(interface{}, bool) error) (err e
 	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
 		"periodic": &SnapshottingPeriodic{},
 		"manual":   &SnapshottingManual{},
-		"cron":     &SnapshottingCron{},
 	})
 	return
 }
@@ -727,3 +622,41 @@ func ParseConfigBytes(bytes []byte) (*Config, error) {
 	}
 	return c, nil
 }
+
+var durationStringRegex *regexp.Regexp = regexp.MustCompile(`^\s*(\d+)\s*(s|m|h|d|w)\s*$`)
+
+func parsePositiveDuration(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_dep_test.go

@@ -1,90 +0,0 @@
-package config
-
-import (
-	"fmt"
-	"testing"
-
-	"github.com/stretchr/testify/require"
-	"github.com/zrepl/yaml-config"
-)
-
-type A struct {
-	B  *B     `yaml:"b,optional,fromdefaults"`
-	A1 string `yaml:"a1,optional"`
-}
-
-type B struct {
-	C *C     `yaml:"c,optional,fromdefaults"`
-	D string `yaml:"d,default=ddd"`
-	E string `yaml:"e,optional"`
-}
-
-type C struct {
-	Q string `yaml:"q,optional"`
-	R string `yaml:"r,default=r"`
-}
-
-func TestDepFromDefaults(t *testing.T) {
-
-	type testcase struct {
-		name   string
-		yaml   string
-		expect *A
-	}
-
-	tcs := []testcase{
-		{
-			name: "empty",
-			yaml: `{}`,
-			expect: &A{
-				B: &B{
-					C: &C{
-						R: "r",
-					},
-					D: "ddd",
-				},
-			},
-		},
-		{
-			name: "a1 set",
-			yaml: `{"a1":"blah"}`,
-			expect: &A{
-				A1: "blah",
-				B: &B{
-					C: &C{
-						R: "r",
-					},
-					D: "ddd",
-				},
-			},
-		},
-		{
-			name: "D set",
-			yaml: `
-b:
-  d: 4d
-`,
-			expect: &A{
-				B: &B{
-					D: "4d",
-					C: &C{
-						R: "r",
-					},
-				},
-			},
-		},
-	}
-
-	for tci := range tcs {
-		t.Run(fmt.Sprintf("%d-%s", tci, tcs[tci].name), func(t *testing.T) {
-			tc := tcs[tci]
-
-			var a A
-			err := yaml.UnmarshalStrict([]byte(tc.yaml), &a)
-			require.NoError(t, err)
-
-			require.Equal(t, tc.expect, &a)
-		})
-	}
-
-}

config/config_duration.go

@@ -1,106 +0,0 @@
-package config
-
-import (
-	"errors"
-	"fmt"
-	"regexp"
-	"strconv"
-	"time"
-
-	"github.com/kr/pretty"
-	"github.com/zrepl/yaml-config"
-)
-
-type Duration struct{ d time.Duration }
-
-func (d Duration) Duration() time.Duration { return d.d }
-
-var _ yaml.Unmarshaler = &Duration{}
-
-func (d *Duration) UnmarshalYAML(unmarshal func(v interface{}, not_strict bool) error) error {
-	var s string
-	err := unmarshal(&s, false)
-	if err != nil {
-		return err
-	}
-	d.d, err = parseDuration(s)
-	if err != nil {
-		d.d = 0
-		return &yaml.TypeError{Errors: []string{fmt.Sprintf("cannot parse value %q: %s", s, err)}}
-	}
-	return nil
-}
-
-type PositiveDuration struct{ d Duration }
-
-var _ yaml.Unmarshaler = &PositiveDuration{}
-
-func (d PositiveDuration) Duration() time.Duration { return d.d.Duration() }
-
-func (d *PositiveDuration) UnmarshalYAML(unmarshal func(v interface{}, not_strict bool) error) error {
-	err := d.d.UnmarshalYAML(unmarshal)
-	if err != nil {
-		return err
-	}
-	if d.d.Duration() <= 0 {
-		return fmt.Errorf("duration must be positive, got %s", d.d.Duration())
-	}
-	return nil
-}
-
-func parsePositiveDuration(e string) (time.Duration, error) {
-	d, err := parseDuration(e)
-	if err != nil {
-		return d, err
-	}
-	if d <= 0 {
-		return 0, errors.New("duration must be positive integer")
-	}
-	return d, err
-}
-
-var durationStringRegex *regexp.Regexp = regexp.MustCompile(`^\s*([\+-]?\d+)\s*(|s|m|h|d|w)\s*$`)
-
-func parseDuration(e string) (d time.Duration, err error) {
-	comps := durationStringRegex.FindStringSubmatch(e)
-	if comps == nil {
-		err = fmt.Errorf("must match %s", durationStringRegex)
-		return
-	}
-	if len(comps) != 3 {
-		panic(pretty.Sprint(comps))
-	}
-
-	durationFactor, err := strconv.ParseInt(comps[1], 10, 64)
-	if err != nil {
-		return 0, err
-	}
-
-	var durationUnit time.Duration
-	switch comps[2] {
-	case "":
-		if durationFactor != 0 {
-			err = fmt.Errorf("missing time unit")
-			return
-		} else {
-			// It's the case where user specified '0'.
-			// We want to allow this, just like time.ParseDuration.
-		}
-	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_global_test.go

@@ -70,9 +70,9 @@ func TestPrometheusMonitoring(t *testing.T) {
 global:
   monitoring:
     - type: prometheus
-      listen: ':9811'
+      listen: ':9091'
 `)
-	assert.Equal(t, ":9811", conf.Global.Monitoring[0].Ret.(*PrometheusMonitoring).Listen)
+	assert.Equal(t, ":9091", conf.Global.Monitoring[0].Ret.(*PrometheusMonitoring).Listen)
 }
 
 func TestSyslogLoggingOutletFacility(t *testing.T) {

config/config_recv_test.go

@@ -1,134 +0,0 @@
-package config
-
-import (
-	"fmt"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	zfsprop "github.com/zrepl/zrepl/zfs/property"
-)
-
-func TestRecvOptions(t *testing.T) {
-	tmpl := `
-jobs:
-- name: foo
-  type: pull
-  connect:
-    type: local
-    listener_name: foo
-    client_identity: bar
-  root_fs: "zreplplatformtest"
-  %s
-  interval: manual
-  pruning:
-    keep_sender:
-    - type: last_n
-      count: 10
-    keep_receiver:
-    - type: last_n
-      count: 10
-
-`
-
-	recv_properties_empty := `
-  recv:
-    properties:
-`
-
-	recv_inherit_empty := `
-  recv:
-    properties:
-      inherit:
-`
-
-	recv_inherit := `
-  recv:
-    properties:
-      inherit:
-        - testprop
-`
-
-	recv_override_empty := `
-  recv:
-    properties:
-      override:
-`
-
-	recv_override := `
-  recv:
-    properties:
-      override:
-        testprop2: "test123"
-`
-
-	recv_override_and_inherit := `
-  recv:
-    properties:
-      inherit:
-        - testprop
-      override:
-        testprop2: "test123"
-`
-
-	recv_empty := `
-  recv: {}
-`
-
-	recv_not_specified := `
-`
-
-	fill := func(s string) string { return fmt.Sprintf(tmpl, s) }
-
-	t.Run("recv_inherit_empty", func(t *testing.T) {
-		c := testValidConfig(t, fill(recv_inherit_empty))
-		assert.NotNil(t, c)
-	})
-
-	t.Run("recv_inherit", func(t *testing.T) {
-		c := testValidConfig(t, fill(recv_inherit))
-		inherit := c.Jobs[0].Ret.(*PullJob).Recv.Properties.Inherit
-		assert.NotEmpty(t, inherit)
-		assert.Contains(t, inherit, zfsprop.Property("testprop"))
-	})
-
-	t.Run("recv_override_empty", func(t *testing.T) {
-		c := testValidConfig(t, fill(recv_override_empty))
-		assert.NotNil(t, c)
-	})
-
-	t.Run("recv_override", func(t *testing.T) {
-		c := testValidConfig(t, fill(recv_override))
-		override := c.Jobs[0].Ret.(*PullJob).Recv.Properties.Override
-		require.Len(t, override, 1)
-		require.Equal(t, "test123", override["testprop2"])
-
-	})
-
-	t.Run("recv_override_and_inherit", func(t *testing.T) {
-		c := testValidConfig(t, fill(recv_override_and_inherit))
-		inherit := c.Jobs[0].Ret.(*PullJob).Recv.Properties.Inherit
-		override := c.Jobs[0].Ret.(*PullJob).Recv.Properties.Override
-		assert.NotEmpty(t, inherit)
-		assert.Contains(t, inherit, zfsprop.Property("testprop"))
-		assert.NotEmpty(t, override)
-		assert.Equal(t, "test123", override["testprop2"])
-	})
-
-	t.Run("recv_properties_empty", func(t *testing.T) {
-		c := testValidConfig(t, fill(recv_properties_empty))
-		assert.NotNil(t, c)
-	})
-
-	t.Run("recv_empty", func(t *testing.T) {
-		c := testValidConfig(t, fill(recv_empty))
-		assert.NotNil(t, c)
-	})
-
-	t.Run("send_not_specified", func(t *testing.T) {
-		c := testValidConfig(t, fill(recv_not_specified))
-		assert.NotNil(t, c)
-	})
-
-}

config/config_send_test.go

@@ -38,41 +38,7 @@ jobs:
     encrypted: true
 `
 
-	raw_true := `
-  send:
-    raw: true
-
-`
-
-	raw_false := `
-  send:
-    raw: false
-
-`
-
-	raw_and_encrypted := `
-  send:
-    encrypted: true
-    raw: true
-`
-
-	properties_and_encrypted := `
-  send:
-    encrypted: true
-    send_properties: true
-`
-
-	properties_true := `
-  send:
-    send_properties: true
-`
-
-	properties_false := `
-  send:
-    send_properties: false
-`
-
-	send_empty := `
+	encrypted_unspecified := `
   send: {}
 `
 
@@ -80,66 +46,28 @@ jobs:
 `
 
 	fill := func(s string) string { return fmt.Sprintf(tmpl, s) }
+	var c *Config
 
 	t.Run("encrypted_false", func(t *testing.T) {
-		c := testValidConfig(t, fill(encrypted_false))
+		c = testValidConfig(t, fill(encrypted_false))
 		encrypted := c.Jobs[0].Ret.(*PushJob).Send.Encrypted
 		assert.Equal(t, false, encrypted)
 	})
 	t.Run("encrypted_true", func(t *testing.T) {
-		c := testValidConfig(t, fill(encrypted_true))
+		c = testValidConfig(t, fill(encrypted_true))
 		encrypted := c.Jobs[0].Ret.(*PushJob).Send.Encrypted
 		assert.Equal(t, true, encrypted)
 	})
 
-	t.Run("send_empty", func(t *testing.T) {
-		c := testValidConfig(t, fill(send_empty))
-		encrypted := c.Jobs[0].Ret.(*PushJob).Send.Encrypted
-		assert.Equal(t, false, encrypted)
-	})
-
-	t.Run("properties_and_encrypted", func(t *testing.T) {
-		c := testValidConfig(t, fill(properties_and_encrypted))
-		encrypted := c.Jobs[0].Ret.(*PushJob).Send.Encrypted
-		properties := c.Jobs[0].Ret.(*PushJob).Send.SendProperties
-		assert.Equal(t, true, encrypted)
-		assert.Equal(t, true, properties)
-	})
-
-	t.Run("properties_false", func(t *testing.T) {
-		c := testValidConfig(t, fill(properties_false))
-		properties := c.Jobs[0].Ret.(*PushJob).Send.SendProperties
-		assert.Equal(t, false, properties)
-	})
-
-	t.Run("properties_true", func(t *testing.T) {
-		c := testValidConfig(t, fill(properties_true))
-		properties := c.Jobs[0].Ret.(*PushJob).Send.SendProperties
-		assert.Equal(t, true, properties)
-	})
-
-	t.Run("raw_true", func(t *testing.T) {
-		c := testValidConfig(t, fill(raw_true))
-		raw := c.Jobs[0].Ret.(*PushJob).Send.Raw
-		assert.Equal(t, true, raw)
-	})
-
-	t.Run("raw_false", func(t *testing.T) {
-		c := testValidConfig(t, fill(raw_false))
-		raw := c.Jobs[0].Ret.(*PushJob).Send.Raw
-		assert.Equal(t, false, raw)
-	})
-
-	t.Run("raw_and_encrypted", func(t *testing.T) {
-		c := testValidConfig(t, fill(raw_and_encrypted))
-		raw := c.Jobs[0].Ret.(*PushJob).Send.Raw
-		encrypted := c.Jobs[0].Ret.(*PushJob).Send.Encrypted
-		assert.Equal(t, true, raw)
-		assert.Equal(t, true, encrypted)
+	t.Run("encrypted_unspecified", func(t *testing.T) {
+		c, err := testConfig(t, fill(encrypted_unspecified))
+		assert.Error(t, err)
+		assert.Nil(t, c)
 	})
 
 	t.Run("send_not_specified", func(t *testing.T) {
-		c := testValidConfig(t, fill(send_not_specified))
+		c, err := testConfig(t, fill(send_not_specified))
+		assert.NoError(t, err)
 		assert.NotNil(t, c)
 	})
 

config/config_snapshotting_test.go

@@ -35,23 +35,8 @@ jobs:
   snapshotting:
     type: periodic
     prefix: zrepl_
-    timestamp_format: dense
     interval: 10m
 `
-	cron := `
-  snapshotting:
-    type: cron
-    prefix: zrepl_
-    timestamp_format: human
-    cron: "10 * * * *"
-`
-
-	periodicDaily := `
-  snapshotting:
-    type: periodic
-    prefix: zrepl_
-    interval: 1d
-`
 
 	hooks := `
   snapshotting:
@@ -89,27 +74,10 @@ jobs:
 		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.Duration())
+		assert.Equal(t, 10*time.Minute, snp.Interval)
 		assert.Equal(t, "zrepl_", snp.Prefix)
 	})
 
-	t.Run("periodicDaily", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(periodicDaily))
-		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingPeriodic)
-		assert.Equal(t, "periodic", snp.Type)
-		assert.Equal(t, 24*time.Hour, snp.Interval.Duration())
-		assert.Equal(t, "zrepl_", snp.Prefix)
-		assert.Equal(t, "dense", snp.TimestampFormat)
-	})
-
-	t.Run("cron", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(cron))
-		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingCron)
-		assert.Equal(t, "cron", snp.Type)
-		assert.Equal(t, "zrepl_", snp.Prefix)
-		assert.Equal(t, "human", snp.TimestampFormat)
-	})
-
 	t.Run("hooks", func(t *testing.T) {
 		c = testValidConfig(t, fillSnapshotting(hooks))
 		hs := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingPeriodic).Hooks
@@ -120,57 +88,3 @@ jobs:
 	})
 
 }
-
-func TestSnapshottingTimestampDefaults(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
-`
-
-	periodic := `
-  snapshotting:
-    type: periodic
-    prefix: zrepl_
-    interval: 10m
-`
-	cron := `
-  snapshotting:
-    type: cron
-    prefix: zrepl_
-    cron: "10 * * * *"
-`
-
-	fillSnapshotting := func(s string) string { return fmt.Sprintf(tmpl, s) }
-	var c *Config
-
-	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.Duration())
-		assert.Equal(t, "zrepl_", snp.Prefix)
-		assert.Equal(t, "dense", snp.TimestampFormat) // default was set correctly
-	})
-
-	t.Run("cron", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(cron))
-		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingCron)
-		assert.Equal(t, "cron", snp.Type)
-		assert.Equal(t, "zrepl_", snp.Prefix)
-		assert.Equal(t, "dense", snp.TimestampFormat) // default was set correctly
-	})
-}

config/config_test.go

@@ -13,7 +13,6 @@ import (
 	"github.com/kr/pretty"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
-	"github.com/zrepl/yaml-config"
 )
 
 func TestSampleConfigsAreParsedWithoutErrors(t *testing.T) {
@@ -44,8 +43,7 @@ func TestSampleConfigsAreParsedWithoutErrors(t *testing.T) {
 }
 
 // template must be a template/text template with a single '{{ . }}' as placeholder for val
-//
-//nolint:deadcode,unused
+//nolint[:deadcode,unused]
 func testValidConfigTemplate(t *testing.T, tmpl string, val string) *Config {
 	tmp, err := template.New("master").Parse(tmpl)
 	if err != nil {
@@ -88,53 +86,3 @@ func TestTrimSpaceEachLineAndPad(t *testing.T) {
 	`
 	assert.Equal(t, "  \n  foo\n  bar baz\n  \n", trimSpaceEachLineAndPad(foo, "  "))
 }
-
-func TestCronSpec(t *testing.T) {
-
-	expectAccept := []string{
-		`"* * * * *"`,
-		`"0-10 * * * *"`,
-		`"* 0-5,8,12 * * *"`,
-	}
-
-	expectFail := []string{
-		`* * * *`,
-		``,
-		`23`,
-		`"@reboot"`,
-		`"@every 1h30m"`,
-		`"@daily"`,
-		`* * * * * *`,
-	}
-
-	for _, input := range expectAccept {
-		t.Run(input, func(t *testing.T) {
-			s := fmt.Sprintf("spec: %s\n", input)
-			var v struct {
-				Spec CronSpec
-			}
-			v.Spec.Schedule = nil
-			t.Logf("input:\n%s", s)
-			err := yaml.UnmarshalStrict([]byte(s), &v)
-			t.Logf("error: %T %s", err, err)
-			require.NoError(t, err)
-			require.NotNil(t, v.Spec.Schedule)
-		})
-	}
-
-	for _, input := range expectFail {
-		t.Run(input, func(t *testing.T) {
-			s := fmt.Sprintf("spec: %s\n", input)
-			var v struct {
-				Spec CronSpec
-			}
-			v.Spec.Schedule = nil
-			t.Logf("input: %q", s)
-			err := yaml.UnmarshalStrict([]byte(s), &v)
-			t.Logf("error: %T %s", err, err)
-			require.Error(t, err)
-			require.Nil(t, v.Spec.Schedule)
-		})
-	}
-
-}

config/retentiongrid.go

@@ -37,7 +37,7 @@ func (t *RetentionIntervalList) UnmarshalYAML(u func(interface{}, bool) error) (
 		return err
 	}
 
-	intervals, err := ParseRetentionIntervalSpec(in)
+	intervals, err := parseRetentionGridIntervalsString(in)
 	if err != nil {
 		return err
 	}
@@ -102,7 +102,7 @@ func parseRetentionGridIntervalString(e string) (intervals []RetentionInterval,
 
 }
 
-func ParseRetentionIntervalSpec(s string) (intervals []RetentionInterval, err error) {
+func parseRetentionGridIntervalsString(s string) (intervals []RetentionInterval, err error) {
 
 	ges := strings.Split(s, "|")
 	intervals = make([]RetentionInterval, 0, 7*len(ges))

config/samples/bandwidth_limit.yml

@@ -1,41 +0,0 @@
-
-jobs:
-  - type: sink
-    name: "limited_sink"
-    root_fs: "fs0"
-    recv:
-      bandwidth_limit:
-        max: 12345 B
-    serve:
-      type: local
-      listener_name: localsink
-
-  - type: push
-    name: "limited_push"
-    connect:
-      type: local
-      listener_name: localsink
-      client_identity: local_backup
-    filesystems: {
-      "root<": true,
-    }
-    send:
-      bandwidth_limit:
-        max: 54321 B
-        bucket_capacity: 1024 B
-    snapshotting:
-      type: manual
-    pruning:
-      keep_sender:
-        - type: last_n
-          count: 1
-      keep_receiver:
-        - type: last_n
-          count: 1
-
-  - type: sink
-    name: "nolimit_sink"
-    root_fs: "fs1"
-    serve:
-      type: local
-      listener_name: localsink

config/samples/quickstart_backup_to_external_disk.yml

@@ -1,88 +0,0 @@
-# This config serves as an example for a local zrepl installation that
-# backups the entire zpool `system` to `backuppool/zrepl/sink`
-#
-# The requirements covered by this setup are described in the zrepl documentation's
-# quick start section which inlines this example.
-#
-# CUSTOMIZATIONS YOU WILL LIKELY WANT TO APPLY:
-# - adjust the name of the production pool `system` in the `filesystems` filter of jobs `snapjob` and `push_to_drive`
-# - adjust the name of the backup pool `backuppool` in the `backuppool_sink` job
-# - adjust the occurences of `myhostname` to the name of the system you are backing up (cannot be easily changed once you start replicating)
-# - make sure the `zrepl_` prefix is not being used by any other zfs tools you might have installed (it likely isn't)
-
-jobs:
-
-# this job takes care of snapshot creation + pruning
-- name: snapjob
-  type: snap
-  filesystems: {
-      "system<": true,
-  }
-  # create snapshots with prefix `zrepl_` every 15 minutes
-  snapshotting:
-    type: periodic
-    interval: 15m
-    prefix: zrepl_
-  pruning:
-    keep:
-    # fade-out scheme for snapshots starting with `zrepl_`
-    # - keep all created in the last hour
-    # - then destroy snapshots such that we keep 24 each 1 hour apart
-    # - then destroy snapshots such that we keep 14 each 1 day apart
-    # - then destroy all older snapshots
-    - type: grid
-      grid: 1x1h(keep=all) | 24x1h | 14x1d
-      regex: "^zrepl_.*"
-    # keep all snapshots that don't have the `zrepl_` prefix
-    - type: regex
-      negate: true
-      regex: "^zrepl_.*"
-
-# This job pushes to the local sink defined in job `backuppool_sink`.
-# We trigger replication manually from the command line / udev rules using
-#  `zrepl signal wakeup push_to_drive`
-- type: push
-  name: push_to_drive
-  connect:
-    type: local
-    listener_name: backuppool_sink
-    client_identity: myhostname
-  filesystems: {
-      "system<": true
-  }
-  send:
-    encrypted: true
-  replication:
-    protection:
-      initial: guarantee_resumability
-      # Downgrade protection to guarantee_incremental which uses zfs bookmarks instead of zfs holds.
-      # Thus, when we yank out the backup drive during replication
-      # - we might not be able to resume the interrupted replication step because the partially received `to` snapshot of a `from`->`to` step may be pruned any time
-      # - but in exchange we get back the disk space allocated by `to` when we prune it
-      # - and because we still have the bookmarks created by `guarantee_incremental`, we can still do incremental replication of `from`->`to2` in the future
-      incremental: guarantee_incremental
-  snapshotting:
-    type: manual
-  pruning:
-    # no-op prune rule on sender (keep all snapshots), job `snapshot` takes care of this
-    keep_sender:
-    - type: regex
-      regex: ".*"
-    # retain 
-    keep_receiver:
-    # longer retention on the backup drive, we have more space there
-    - type: grid
-      grid: 1x1h(keep=all) | 24x1h | 360x1d
-      regex: "^zrepl_.*"
-    # retain all non-zrepl snapshots on the backup drive
-    - type: regex
-      negate: true
-      regex: "^zrepl_.*"
-
-# This job receives from job `push_to_drive` into `backuppool/zrepl/sink/myhostname`
-- type: sink
-  name: backuppool_sink
-  root_fs: "backuppool/zrepl/sink"
-  serve:
-    type: local
-    listener_name: backuppool_sink

config/samples/quickstart_continuous_server_backup_receiver.yml

@@ -1,12 +0,0 @@
-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"

config/samples/quickstart_continuous_server_backup_sender.yml

@@ -1,28 +0,0 @@
-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<": true,
-    "zroot/var/tmp<": false,
-    "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_"

config/samples/quickstart_fan_out_replication_source.yml

@@ -1,59 +0,0 @@
-jobs:
-# Separate job for snapshots and pruning
-- name: snapshots
-  type: snap
-  filesystems:
-    'tank<': true # all filesystems
-  snapshotting:
-    type: periodic
-    prefix: zrepl_
-    interval: 10m
-  pruning:
-    keep:
-      # Keep non-zrepl snapshots
-      - type: regex
-        negate: true
-        regex: '^zrepl_'
-      # Time-based snapshot retention
-      - type: grid
-        grid: 1x1h(keep=all) | 24x1h | 30x1d | 12x30d
-        regex: '^zrepl_'
-
-# Source job for target B
-- name: target_b
-  type: source
-  serve:
-    type: tls
-    listen: :8888
-    ca: /etc/zrepl/b.example.com.crt
-    cert: /etc/zrepl/a.example.com.crt
-    key: /etc/zrepl/a.example.com.key
-    client_cns:
-      - b.example.com
-  filesystems:
-    'tank<': true # all filesystems
-  # Snapshots are handled by the separate snap job
-  snapshotting:
-    type: manual
-
-# Source job for target C
-- name: target_c
-  type: source
-  serve:
-    type: tls
-    listen: :8889
-    ca: /etc/zrepl/c.example.com.crt
-    cert: /etc/zrepl/a.example.com.crt
-    key: /etc/zrepl/a.example.com.key
-    client_cns:
-      - c.example.com
-  filesystems:
-    'tank<': true # all filesystems
-  # Snapshots are handled by the separate snap job
-  snapshotting:
-    type: manual
-
-# Source jobs for remaining targets. Each one should listen on a different port
-# and reference the correct certificate and client CN.
-# - name: target_c
-#   ...

config/samples/quickstart_fan_out_replication_target.yml

@@ -1,30 +0,0 @@
-jobs:
-# Pull from source server A
-- name: source_a
-  type: pull
-  connect:
-    type: tls
-    # Use the correct port for this specific client (eg. B is 8888, C is 8889, etc.)
-    address: a.example.com:8888
-    ca: /etc/zrepl/a.example.com.crt
-    # Use the correct key pair for this specific client
-    cert: /etc/zrepl/b.example.com.crt
-    key: /etc/zrepl/b.example.com.key
-    server_cn: a.example.com
-  root_fs: pool0/backup
-  interval: 10m
-  pruning:
-    keep_sender:
-      # Source does the pruning in its snap job
-      - type: regex
-        regex: '.*'
-    # Receiver-side pruning can be configured as desired on each target server
-    keep_receiver:
-      # Keep non-zrepl snapshots
-      - type: regex
-        negate: true
-        regex: '^zrepl_'
-      # Time-based snapshot retention
-      - type: grid
-        grid: 1x1h(keep=all) | 24x1h | 30x1d | 12x30d
-        regex: '^zrepl_'

config/samples/snap_cron.yml

@@ -1,14 +0,0 @@
-jobs:
-- name: snapjob
-  type: snap
-  filesystems: {
-    "tank<": true,
-  }
-  snapshotting:
-    type: cron
-    prefix: zrepl_snapjob_
-    cron: "*/5 * * * *"
-  pruning:
-    keep:
-      - type: last_n
-        count: 60

daemon/control.go

@@ -8,7 +8,6 @@ import (
 	"io"
 	"net"
 	"net/http"
-	"os"
 	"time"
 
 	"github.com/pkg/errors"
@@ -125,9 +124,8 @@ func (j *controlJob) Run(ctx context.Context) {
 			s := Status{
 				Jobs: jobs,
 				Global: GlobalStatus{
-					ZFSCmds:   globalZFS,
-					Envconst:  envconstReport,
-					OsEnviron: os.Environ(),
+					ZFSCmds:  globalZFS,
+					Envconst: envconstReport,
 				}}
 			return s, nil
 		}})
@@ -158,8 +156,8 @@ func (j *controlJob) Run(ctx context.Context) {
 	server := http.Server{
 		Handler: mux,
 		// control socket is local, 1s timeout should be more than sufficient, even on a loaded system
-		WriteTimeout: envconst.Duration("ZREPL_DAEMON_CONTROL_SERVER_WRITE_TIMEOUT", 1*time.Second),
-		ReadTimeout:  envconst.Duration("ZREPL_DAEMON_CONTROL_SERVER_READ_TIMEOUT", 1*time.Second),
+		WriteTimeout: 1 * time.Second,
+		ReadTimeout:  1 * time.Second,
 	}
 
 outer:

daemon/daemon.go

@@ -3,7 +3,6 @@ package daemon
 import (
 	"context"
 	"fmt"
-	"math/rand"
 	"os"
 	"os/signal"
 	"strings"
@@ -13,7 +12,6 @@ import (
 
 	"github.com/pkg/errors"
 	"github.com/prometheus/client_golang/prometheus"
-
 	"github.com/zrepl/zrepl/daemon/logging/trace"
 	"github.com/zrepl/zrepl/endpoint"
 	"github.com/zrepl/zrepl/util/envconst"
@@ -39,19 +37,13 @@ func Run(ctx context.Context, conf *config.Config) error {
 		cancel()
 	}()
 
-	// The math/rand package is used presently for generating trace IDs, we
-	// seed it with the current time and pid so that the IDs are mostly
-	// unique.
-	rand.Seed(time.Now().UnixNano())
-	rand.Seed(int64(os.Getpid()))
-
 	outlets, err := logging.OutletsFromConfig(*conf.Global.Logging)
 	if err != nil {
 		return errors.Wrap(err, "cannot build logging from config")
 	}
 	outlets.Add(newPrometheusLogOutlet(), logger.Debug)
 
-	confJobs, err := job.JobsFromConfig(conf, config.ParseFlagsNone)
+	confJobs, err := job.JobsFromConfig(conf)
 	if err != nil {
 		return errors.Wrap(err, "cannot build jobs from config")
 	}
@@ -103,7 +95,6 @@ func Run(ctx context.Context, conf *config.Config) error {
 	}
 
 	// register global (=non job-local) metrics
-	version.PrometheusRegister(prometheus.DefaultRegisterer)
 	zfscmd.RegisterMetrics(prometheus.DefaultRegisterer)
 	trace.RegisterMetrics(prometheus.DefaultRegisterer)
 	endpoint.RegisterMetrics(prometheus.DefaultRegisterer)
@@ -160,9 +151,8 @@ type Status struct {
 }
 
 type GlobalStatus struct {
-	ZFSCmds   *zfscmd.Report
-	Envconst  *envconst.Report
-	OsEnviron []string
+	ZFSCmds  *zfscmd.Report
+	Envconst *envconst.Report
 }
 
 func (s *jobs) status() map[string]*job.Status {

daemon/filters/fsmapfilter.go

@@ -160,14 +160,6 @@ func (m DatasetMapFilter) Filter(p *zfs.DatasetPath) (pass bool, err error) {
 	return
 }
 
-func (m DatasetMapFilter) UserSpecifiedDatasets() (datasets zfs.UserSpecifiedDatasetsSet) {
-	datasets = make(zfs.UserSpecifiedDatasetsSet)
-	for i := range m.entries {
-		datasets[m.entries[i].path.ToString()] = true
-	}
-	return
-}
-
 // Construct a new filter-only DatasetMapFilter from a mapping
 // The new filter allows exactly those paths that were not forbidden by the mapping.
 func (m DatasetMapFilter) InvertedFilter() (inv *DatasetMapFilter, err error) {

daemon/hooks/hook_docs.go

@@ -5,7 +5,7 @@
 //
 // This package also provides all supported hook type implementations and abstractions around them.
 //
-// # Use For Other Kinds Of ExpectStepReports
+// Use For Other Kinds Of ExpectStepReports
 //
 // This package REQUIRES REFACTORING before it can be used for other activities than snapshots, e.g. pre- and post-replication:
 //
@@ -15,7 +15,7 @@
 // The hook implementations should move out of this package.
 // However, there is a lot of tight coupling which to untangle isn't worth it ATM.
 //
-// # How This Package Is Used By Package Snapper
+// How This Package Is Used By Package Snapper
 //
 // Deserialize a config.List using ListFromConfig().
 // Then it MUST filter the list to only contain hooks for a particular filesystem using
@@ -30,4 +30,5 @@
 // Command hooks make it available in the environment variable ZREPL_DRYRUN.
 //
 // Plan.Report() can be called while Plan.Run() is executing to give an overview of plan execution progress (future use in "zrepl status").
+//
 package hooks

daemon/hooks/hook_type_command.go

@@ -93,14 +93,7 @@ func (r *CommandHookReport) String() string {
 		cmdLine.WriteString(fmt.Sprintf("%s'%s'", sep, a))
 	}
 
-	var msg string
-	if r.Err == nil {
-		msg = "command hook"
-	} else {
-		msg = fmt.Sprintf("command hook failed with %q", r.Err)
-	}
-
-	return fmt.Sprintf("%s: \"%s\"", msg, cmdLine.String()) // no %q to make copy-pastable
+	return fmt.Sprintf("command hook invocation: \"%s\"", cmdLine.String()) // no %q to make copy-pastable
 }
 func (r *CommandHookReport) Error() string {
 	if r.Err == nil {

daemon/hooks/hook_type_mysql_lock_tables.go

@@ -17,22 +17,19 @@ import (
 	"github.com/zrepl/zrepl/zfs"
 )
 
-// Hook to implement the following recommmendation from MySQL docs
 // https://dev.mysql.com/doc/mysql-backup-excerpt/5.7/en/backup-methods.html
 //
-//	Making Backups Using a File System Snapshot:
+// Making Backups Using a File System Snapshot:
 //
-//	If you are using a Veritas file system, you can make a backup like this:
+//  If you are using a Veritas file system, you can make a backup like this:
 //
-//	   	From a client program, execute FLUSH TABLES WITH READ LOCK.
-//	   	From another shell, execute mount vxfs snapshot.
-//	   	From the first client, execute UNLOCK TABLES.
-//	   	Copy files from the snapshot.
-//	   	Unmount the snapshot.
+//    	From a client program, execute FLUSH TABLES WITH READ LOCK.
+//    	From another shell, execute mount vxfs snapshot.
+//    	From the first client, execute UNLOCK TABLES.
+//    	Copy files from the snapshot.
+//    	Unmount the snapshot.
 //
-//		Similar snapshot capabilities may be available in other file systems, such as LVM or ZFS.
-//
-
+//	Similar snapshot capabilities may be available in other file systems, such as LVM or ZFS.
 type MySQLLockTables struct {
 	errIsFatal  bool
 	connector   sqldriver.Connector

daemon/hooks/hooks_test.go

@@ -10,7 +10,6 @@ import (
 	"text/template"
 
 	"github.com/stretchr/testify/require"
-
 	"github.com/zrepl/zrepl/daemon/logging/trace"
 
 	"github.com/zrepl/zrepl/config"
@@ -161,7 +160,7 @@ jobs:
 					ExpectedEdge: hooks.Pre,
 					ExpectStatus: hooks.StepErr,
 					OutputTest:   containsTest(fmt.Sprintf("TEST ERROR pre_testing %s@%s", testFSName, testSnapshotName)),
-					ErrorTest:    regexpTest("^command hook failed.*exit status 1$"),
+					ErrorTest:    regexpTest("^command hook invocation.*exit status 1$"),
 				},
 				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
 				expectStep{
@@ -185,7 +184,7 @@ jobs:
 					ExpectedEdge: hooks.Pre,
 					ExpectStatus: hooks.StepErr,
 					OutputTest:   containsTest(fmt.Sprintf("TEST ERROR pre_testing %s@%s", testFSName, testSnapshotName)),
-					ErrorTest:    regexpTest("^command hook failed.*exit status 1$"),
+					ErrorTest:    regexpTest("^command hook invocation.*exit status 1$"),
 				},
 				expectStep{
 					ExpectedEdge: hooks.Pre,
@@ -234,7 +233,7 @@ jobs:
 					ExpectedEdge: hooks.Post,
 					ExpectStatus: hooks.StepErr,
 					OutputTest:   containsTest(fmt.Sprintf("TEST ERROR post_testing %s@%s", testFSName, testSnapshotName)),
-					ErrorTest:    regexpTest("^command hook failed.*exit status 1$"),
+					ErrorTest:    regexpTest("^command hook invocation.*exit status 1$"),
 				},
 			},
 		},
@@ -267,7 +266,7 @@ jobs:
 					ExpectedEdge: hooks.Pre,
 					ExpectStatus: hooks.StepErr,
 					OutputTest:   containsTest(fmt.Sprintf("TEST ERROR pre_testing %s@%s", testFSName, testSnapshotName)),
-					ErrorTest:    regexpTest("^command hook failed.*exit status 1$"),
+					ErrorTest:    regexpTest("^command hook invocation.*exit status 1$"),
 				},
 				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
 				expectStep{
@@ -295,7 +294,7 @@ jobs:
 					ExpectedEdge: hooks.Pre,
 					ExpectStatus: hooks.StepErr,
 					OutputTest:   containsTest(fmt.Sprintf("TEST ERROR pre_testing %s@%s", testFSName, testSnapshotName)),
-					ErrorTest:    regexpTest("^command hook failed.*exit status 1$"),
+					ErrorTest:    regexpTest("^command hook invocation.*exit status 1$"),
 				},
 				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
 				expectStep{

daemon/job/active.go

@@ -9,13 +9,11 @@ import (
 	"github.com/pkg/errors"
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/prometheus/common/log"
-
 	"github.com/zrepl/zrepl/daemon/logging/trace"
-	"github.com/zrepl/zrepl/util/envconst"
 
 	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/daemon/filters"
 	"github.com/zrepl/zrepl/daemon/job/reset"
-	"github.com/zrepl/zrepl/daemon/job/trigger"
 	"github.com/zrepl/zrepl/daemon/job/wakeup"
 	"github.com/zrepl/zrepl/daemon/pruner"
 	"github.com/zrepl/zrepl/daemon/snapper"
@@ -35,17 +33,11 @@ type ActiveSide struct {
 	name      endpoint.JobID
 	connecter transport.Connecter
 
-	replicationDriverConfig driver.Config
-
 	prunerFactory *pruner.PrunerFactory
 
-	promRepStateSecs      *prometheus.HistogramVec // labels: state
-	promPruneSecs         *prometheus.HistogramVec // labels: prune_side
-	promBytesReplicated   *prometheus.CounterVec   // labels: filesystem
-	promReplicationErrors prometheus.Gauge
-	promLastSuccessful    prometheus.Gauge
-
-	triggers *trigger.Triggers
+	promRepStateSecs    *prometheus.HistogramVec // labels: state
+	promPruneSecs       *prometheus.HistogramVec // labels: prune_side
+	promBytesReplicated *prometheus.CounterVec   // labels: filesystem
 
 	tasksMtx sync.Mutex
 	tasks    activeSideTasks
@@ -93,7 +85,7 @@ type activeMode interface {
 	SenderReceiver() (logic.Sender, logic.Receiver)
 	Type() Type
 	PlannerPolicy() logic.PlannerPolicy
-	RunPeriodic(ctx context.Context, wakeReplication *trigger.Manual)
+	RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{})
 	SnapperReport() *snapper.Report
 	ResetConnectBackoff()
 }
@@ -104,7 +96,7 @@ type modePush struct {
 	receiver      *rpc.Client
 	senderConfig  *endpoint.SenderConfig
 	plannerPolicy *logic.PlannerPolicy
-	snapper       snapper.Snapper
+	snapper       *snapper.PeriodicOrManual
 }
 
 func (m *modePush) ConnectEndpoints(ctx context.Context, connecter transport.Connecter) {
@@ -135,13 +127,12 @@ func (m *modePush) Type() Type { return TypePush }
 
 func (m *modePush) PlannerPolicy() logic.PlannerPolicy { return *m.plannerPolicy }
 
-func (m *modePush) RunPeriodic(ctx context.Context, trigger *trigger.Manual) {
-	m.snapper.Run(ctx, trigger)
+func (m *modePush) RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{}) {
+	m.snapper.Run(ctx, wakeUpCommon)
 }
 
 func (m *modePush) SnapperReport() *snapper.Report {
-	r := m.snapper.Report()
-	return &r
+	return m.snapper.Report()
 }
 
 func (m *modePush) ResetConnectBackoff() {
@@ -154,33 +145,23 @@ func (m *modePush) ResetConnectBackoff() {
 
 func modePushFromConfig(g *config.Global, in *config.PushJob, jobID endpoint.JobID) (*modePush, error) {
 	m := &modePush{}
-	var err error
 
-	m.senderConfig, err = buildSenderConfig(in, jobID)
+	fsf, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
 	if err != nil {
-		return nil, errors.Wrap(err, "sender config")
+		return nil, errors.Wrap(err, "cannot build filesystem filter")
 	}
 
-	replicationConfig, err := logic.ReplicationConfigFromConfig(in.Replication)
-	if err != nil {
-		return nil, errors.Wrap(err, "field `replication`")
+	m.senderConfig = &endpoint.SenderConfig{
+		FSF:                         fsf,
+		Encrypt:                     &zfs.NilBool{B: in.Send.Encrypted},
+		DisableIncrementalStepHolds: in.Send.StepHolds.DisableIncremental,
+		JobID:                       jobID,
 	}
-
-	conflictResolution, err := logic.ConflictResolutionFromConfig(in.ConflictResolution)
-	if err != nil {
-		return nil, errors.Wrap(err, "field `conflict_resolution`")
-	}
-
 	m.plannerPolicy = &logic.PlannerPolicy{
-		ConflictResolution:        conflictResolution,
-		ReplicationConfig:         replicationConfig,
-		SizeEstimationConcurrency: in.Replication.Concurrency.SizeEstimates,
-	}
-	if err := m.plannerPolicy.Validate(); err != nil {
-		return nil, errors.Wrap(err, "cannot build planner policy")
+		EncryptedSend: logic.TriFromBool(in.Send.Encrypted),
 	}
 
-	if m.snapper, err = snapper.FromConfig(g, m.senderConfig.FSF, in.Snapshotting); err != nil {
+	if m.snapper, err = snapper.FromConfig(g, fsf, in.Snapshotting); err != nil {
 		return nil, errors.Wrap(err, "cannot build snapper")
 	}
 
@@ -192,6 +173,7 @@ type modePull struct {
 	receiver       *endpoint.Receiver
 	receiverConfig endpoint.ReceiverConfig
 	sender         *rpc.Client
+	rootFS         *zfs.DatasetPath
 	plannerPolicy  *logic.PlannerPolicy
 	interval       config.PositiveDurationOrManual
 }
@@ -224,7 +206,7 @@ func (*modePull) Type() Type { return TypePull }
 
 func (m *modePull) PlannerPolicy() logic.PlannerPolicy { return *m.plannerPolicy }
 
-func (m *modePull) RunPeriodic(ctx context.Context, wakeReplication *trigger.Manual) {
+func (m *modePull) RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{}) {
 	if m.interval.Manual {
 		GetLogger(ctx).Info("manual pull configured, periodic pull disabled")
 		// "waiting for wakeups" is printed in common ActiveSide.do
@@ -235,7 +217,14 @@ func (m *modePull) RunPeriodic(ctx context.Context, wakeReplication *trigger.Man
 	for {
 		select {
 		case <-t.C:
-			wakeReplication.Fire()
+			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
 		}
@@ -258,44 +247,32 @@ func modePullFromConfig(g *config.Global, in *config.PullJob, jobID endpoint.Job
 	m = &modePull{}
 	m.interval = in.Interval
 
-	replicationConfig, err := logic.ReplicationConfigFromConfig(in.Replication)
+	m.rootFS, err = zfs.NewDatasetPath(in.RootFS)
 	if err != nil {
-		return nil, errors.Wrap(err, "field `replication`")
+		return nil, errors.New("RootFS is not a valid zfs filesystem path")
 	}
-
-	conflictResolution, err := logic.ConflictResolutionFromConfig(in.ConflictResolution)
-	if err != nil {
-		return nil, errors.Wrap(err, "field `conflict_resolution`")
+	if m.rootFS.Length() <= 0 {
+		return nil, errors.New("RootFS must not be empty") // duplicates error check of receiver
 	}
 
 	m.plannerPolicy = &logic.PlannerPolicy{
-		ConflictResolution:        conflictResolution,
-		ReplicationConfig:         replicationConfig,
-		SizeEstimationConcurrency: in.Replication.Concurrency.SizeEstimates,
-	}
-	if err := m.plannerPolicy.Validate(); err != nil {
-		return nil, errors.Wrap(err, "cannot build planner policy")
+		EncryptedSend: logic.DontCare,
 	}
 
-	m.receiverConfig, err = buildReceiverConfig(in, jobID)
-	if err != nil {
-		return nil, err
+	m.receiverConfig = endpoint.ReceiverConfig{
+		JobID:                      jobID,
+		RootWithoutClientComponent: m.rootFS,
+		AppendClientIdentity:       false, // !
+		UpdateLastReceivedHold:     true,
+	}
+	if err := m.receiverConfig.Validate(); err != nil {
+		return nil, errors.Wrap(err, "cannot build receiver config")
 	}
 
 	return m, nil
 }
 
-func replicationDriverConfigFromConfig(in *config.Replication) (c driver.Config, err error) {
-	c = driver.Config{
-		StepQueueConcurrency:     in.Concurrency.Steps,
-		MaxAttempts:              envconst.Int("ZREPL_REPLICATION_MAX_ATTEMPTS", 3),
-		ReconnectHardFailTimeout: envconst.Duration("ZREPL_REPLICATION_RECONNECT_HARD_FAIL_TIMEOUT", 10*time.Minute),
-	}
-	err = c.Validate()
-	return c, err
-}
-
-func activeSide(g *config.Global, in *config.ActiveJob, configJob interface{}, parseFlags config.ParseFlags) (j *ActiveSide, err error) {
+func activeSide(g *config.Global, in *config.ActiveJob, configJob interface{}) (j *ActiveSide, err error) {
 
 	j = &ActiveSide{}
 	j.name, err = endpoint.MakeJobID(in.Name)
@@ -329,22 +306,8 @@ func activeSide(g *config.Global, in *config.ActiveJob, configJob interface{}, p
 		Help:        "number of bytes replicated from sender to receiver per filesystem",
 		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
 	}, []string{"filesystem"})
-	j.promReplicationErrors = prometheus.NewGauge(prometheus.GaugeOpts{
-		Namespace:   "zrepl",
-		Subsystem:   "replication",
-		Name:        "filesystem_errors",
-		Help:        "number of filesystems that failed replication in the latest replication attempt, or -1 if the job failed before enumerating the filesystems",
-		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
-	})
-	j.promLastSuccessful = prometheus.NewGauge(prometheus.GaugeOpts{
-		Namespace:   "zrepl",
-		Subsystem:   "replication",
-		Name:        "last_successful",
-		Help:        "timestamp of last successful replication",
-		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
-	})
 
-	j.connecter, err = fromconfig.ConnecterFromConfig(g, in.Connect, parseFlags)
+	j.connecter, err = fromconfig.ConnecterFromConfig(g, in.Connect)
 	if err != nil {
 		return nil, errors.Wrap(err, "cannot build client")
 	}
@@ -361,16 +324,6 @@ func activeSide(g *config.Global, in *config.ActiveJob, configJob interface{}, p
 		return nil, err
 	}
 
-	j.replicationDriverConfig, err = replicationDriverConfigFromConfig(in.Replication)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot build replication driver config")
-	}
-
-	j.triggers, err = trigger.FromConfig(in.Replication.Triggers)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot build triggers")
-	}
-
 	return j, nil
 }
 
@@ -378,8 +331,6 @@ func (j *ActiveSide) RegisterMetrics(registerer prometheus.Registerer) {
 	registerer.MustRegister(j.promRepStateSecs)
 	registerer.MustRegister(j.promPruneSecs)
 	registerer.MustRegister(j.promBytesReplicated)
-	registerer.MustRegister(j.promReplicationErrors)
-	registerer.MustRegister(j.promLastSuccessful)
 }
 
 func (j *ActiveSide) Name() string { return j.name.String() }
@@ -414,7 +365,7 @@ func (j *ActiveSide) OwnedDatasetSubtreeRoot() (rfs *zfs.DatasetPath, ok bool) {
 		_ = j.mode.(*modePush) // make sure we didn't introduce a new job type
 		return nil, false
 	}
-	return pull.receiverConfig.RootWithoutClientComponent.Copy(), true
+	return pull.rootFS.Copy(), true
 }
 
 func (j *ActiveSide) SenderConfig() *endpoint.SenderConfig {
@@ -445,17 +396,12 @@ func (j *ActiveSide) Run(ctx context.Context) {
 
 	defer log.Info("job exiting")
 
+	periodicDone := make(chan struct{})
 	ctx, cancel := context.WithCancel(ctx)
 	defer cancel()
-
-	periodCtx, endTask := trace.WithTask(ctx, "periodic")
-	defer endTask()
-	go j.mode.RunPeriodic(periodCtx, periodicTrigger)
-
-	wakeupTrigger := wakeup.Trigger(ctx)
-
-	triggered, endTask := j.triggers.Spawn(ctx, []*trigger.Trigger{periodicTrigger, wakeupTrigger})
+	periodicCtx, endTask := trace.WithTask(ctx, "periodic")
 	defer endTask()
+	go j.mode.RunPeriodic(periodicCtx, periodicDone)
 
 	invocationCount := 0
 outer:
@@ -465,15 +411,10 @@ outer:
 		case <-ctx.Done():
 			log.WithError(ctx.Err()).Info("context")
 			break outer
-		case trigger := <-triggered:
-			log :=
-				log.WithField("trigger_id", trigger.ID())
-			log.Info("triggered")
-			switch trigger {
-			case wakeupTrigger:
-				log.Info("trigger is wakeup command, resetting connection backoff")
-				j.mode.ResetConnectBackoff()
-			}
+
+		case <-wakeup.Wait(ctx):
+			j.mode.ResetConnectBackoff()
+		case <-periodicDone:
 		}
 		invocationCount++
 		invocationCtx, endSpan := trace.WithSpan(ctx, fmt.Sprintf("invocation-%d", invocationCount))
@@ -515,21 +456,13 @@ func (j *ActiveSide) do(ctx context.Context) {
 			*tasks = activeSideTasks{}
 			tasks.replicationCancel = func() { repCancel(); endSpan() }
 			tasks.replicationReport, repWait = replication.Do(
-				ctx, j.replicationDriverConfig, logic.NewPlanner(j.promRepStateSecs, j.promBytesReplicated, sender, receiver, j.mode.PlannerPolicy()),
+				ctx, logic.NewPlanner(j.promRepStateSecs, j.promBytesReplicated, sender, receiver, j.mode.PlannerPolicy()),
 			)
 			tasks.state = ActiveSideReplicating
 		})
 		GetLogger(ctx).Info("start replication")
 		repWait(true) // wait blocking
 		repCancel()   // always cancel to free up context resources
-
-		replicationReport := j.tasks.replicationReport()
-		var numErrors = replicationReport.GetFailedFilesystemsCountInLatestAttempt()
-		j.promReplicationErrors.Set(float64(numErrors))
-		if numErrors == 0 {
-			j.promLastSuccessful.SetToCurrentTime()
-		}
-
 		endSpan()
 	}
 

daemon/job/active_test.go

@@ -5,7 +5,6 @@ import (
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
-
 	"github.com/zrepl/zrepl/endpoint"
 	"github.com/zrepl/zrepl/transport"
 )

daemon/job/build_jobs.go

@@ -8,13 +8,12 @@ import (
 	"github.com/pkg/errors"
 
 	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/util/bandwidthlimit"
 )
 
-func JobsFromConfig(c *config.Config, parseFlags config.ParseFlags) ([]Job, error) {
+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], parseFlags)
+		j, err := buildJob(c.Global, c.Jobs[i])
 		if err != nil {
 			return nil, err
 		}
@@ -24,22 +23,37 @@ func JobsFromConfig(c *config.Config, parseFlags config.ParseFlags) ([]Job, erro
 		js[i] = j
 	}
 
+	// receiving-side root filesystems must not overlap
+	{
+		rfss := make([]string, 0, len(js))
+		for _, j := range js {
+			jrfs, ok := j.OwnedDatasetSubtreeRoot()
+			if !ok {
+				continue
+			}
+			rfss = append(rfss, jrfs.ToString())
+		}
+		if err := validateReceivingSidesDoNotOverlap(rfss); err != nil {
+			return nil, err
+		}
+	}
+
 	return js, nil
 }
 
-func buildJob(c *config.Global, in config.JobEnum, parseFlags config.ParseFlags) (j Job, err error) {
+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:
-		j, err = passiveSideFromConfig(c, &v.PassiveJob, v, parseFlags)
+		j, err = passiveSideFromConfig(c, &v.PassiveJob, v)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
 	case *config.SourceJob:
-		j, err = passiveSideFromConfig(c, &v.PassiveJob, v, parseFlags)
+		j, err = passiveSideFromConfig(c, &v.PassiveJob, v)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
@@ -49,12 +63,12 @@ func buildJob(c *config.Global, in config.JobEnum, parseFlags config.ParseFlags)
 			return cannotBuildJob(err, v.Name)
 		}
 	case *config.PushJob:
-		j, err = activeSide(c, &v.ActiveJob, v, parseFlags)
+		j, err = activeSide(c, &v.ActiveJob, v)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
 	case *config.PullJob:
-		j, err = activeSide(c, &v.ActiveJob, v, parseFlags)
+		j, err = activeSide(c, &v.ActiveJob, v)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
@@ -93,13 +107,3 @@ func validateReceivingSidesDoNotOverlap(receivingRootFSs []string) error {
 	}
 	return nil
 }
-
-func buildBandwidthLimitConfig(in *config.BandwidthLimit) (c bandwidthlimit.Config, _ error) {
-	if in.Max.ToBytes() > 0 && int64(in.Max.ToBytes()) == 0 {
-		return c, fmt.Errorf("bandwidth limit `max` is too small, must at least specify one byte")
-	}
-	return bandwidthlimit.Config{
-		Max:            int64(in.Max.ToBytes()),
-		BucketCapacity: int64(in.BucketCapacity.ToBytes()),
-	}, nil
-}

daemon/job/build_jobs_sendrecvoptions.go

@@ -1,102 +0,0 @@
-package job
-
-import (
-	"github.com/pkg/errors"
-
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/filters"
-	"github.com/zrepl/zrepl/endpoint"
-	"github.com/zrepl/zrepl/util/nodefault"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-type SendingJobConfig interface {
-	GetFilesystems() config.FilesystemsFilter
-	GetSendOptions() *config.SendOptions // must not be nil
-}
-
-func buildSenderConfig(in SendingJobConfig, jobID endpoint.JobID) (*endpoint.SenderConfig, error) {
-
-	fsf, err := filters.DatasetMapFilterFromConfig(in.GetFilesystems())
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot build filesystem filter")
-	}
-	sendOpts := in.GetSendOptions()
-	bwlim, err := buildBandwidthLimitConfig(sendOpts.BandwidthLimit)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannot build bandwith limit config")
-	}
-
-	sc := &endpoint.SenderConfig{
-		FSF:   fsf,
-		JobID: jobID,
-
-		Encrypt:              &nodefault.Bool{B: sendOpts.Encrypted},
-		SendRaw:              sendOpts.Raw,
-		SendProperties:       sendOpts.SendProperties,
-		SendBackupProperties: sendOpts.BackupProperties,
-		SendLargeBlocks:      sendOpts.LargeBlocks,
-		SendCompressed:       sendOpts.Compressed,
-		SendEmbeddedData:     sendOpts.EmbeddedData,
-		SendSaved:            sendOpts.Saved,
-
-		BandwidthLimit: bwlim,
-	}
-
-	if err := sc.Validate(); err != nil {
-		return nil, errors.Wrap(err, "cannot build sender config")
-	}
-
-	return sc, nil
-}
-
-type ReceivingJobConfig interface {
-	GetRootFS() string
-	GetAppendClientIdentity() bool
-	GetRecvOptions() *config.RecvOptions
-}
-
-func buildReceiverConfig(in ReceivingJobConfig, jobID endpoint.JobID) (rc endpoint.ReceiverConfig, err error) {
-	rootFs, err := zfs.NewDatasetPath(in.GetRootFS())
-	if err != nil {
-		return rc, errors.New("root_fs is not a valid zfs filesystem path")
-	}
-	if rootFs.Length() <= 0 {
-		return rc, errors.New("root_fs must not be empty") // duplicates error check of receiver
-	}
-
-	recvOpts := in.GetRecvOptions()
-
-	bwlim, err := buildBandwidthLimitConfig(recvOpts.BandwidthLimit)
-	if err != nil {
-		return rc, errors.Wrap(err, "cannot build bandwith limit config")
-	}
-
-	placeholderEncryption, err := endpoint.PlaceholderCreationEncryptionPropertyString(recvOpts.Placeholder.Encryption)
-	if err != nil {
-		options := []string{}
-		for _, v := range endpoint.PlaceholderCreationEncryptionPropertyValues() {
-			options = append(options, endpoint.PlaceholderCreationEncryptionProperty(v).String())
-		}
-		return rc, errors.Errorf("placeholder encryption value %q is invalid, must be one of %s",
-			recvOpts.Placeholder.Encryption, options)
-	}
-
-	rc = endpoint.ReceiverConfig{
-		JobID:                      jobID,
-		RootWithoutClientComponent: rootFs,
-		AppendClientIdentity:       in.GetAppendClientIdentity(),
-
-		InheritProperties:  recvOpts.Properties.Inherit,
-		OverrideProperties: recvOpts.Properties.Override,
-
-		BandwidthLimit: bwlim,
-
-		PlaceholderEncryption: placeholderEncryption,
-	}
-	if err := rc.Validate(); err != nil {
-		return rc, errors.Wrap(err, "cannot build receiver config")
-	}
-
-	return rc, nil
-}

daemon/job/build_jobs_test.go

@@ -2,11 +2,8 @@ package job
 
 import (
 	"fmt"
-	"path"
-	"path/filepath"
 	"testing"
 
-	"github.com/kr/pretty"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
@@ -95,7 +92,7 @@ jobs:
 			conf, err := config.ParseConfigBytes([]byte(fill(c.jobName)))
 			require.NoError(t, err, "not expecting yaml-config to know about job ids")
 			require.NotNil(t, conf)
-			jobs, err := JobsFromConfig(conf, config.ParseFlagsNone)
+			jobs, err := JobsFromConfig(conf)
 
 			if c.valid {
 				assert.NoError(t, err)
@@ -111,208 +108,3 @@ jobs:
 	}
 
 }
-
-func TestSampleConfigsAreBuiltWithoutErrors(t *testing.T) {
-	paths, err := filepath.Glob("../../config/samples/*")
-	if err != nil {
-		t.Errorf("glob failed: %+v", err)
-	}
-
-	type additionalCheck struct {
-		state int
-		test  func(t *testing.T, jobs []Job)
-	}
-	additionalChecks := map[string]*additionalCheck{
-		"bandwidth_limit.yml": {test: testSampleConfig_BandwidthLimit},
-	}
-
-	for _, p := range paths {
-
-		if path.Ext(p) != ".yml" {
-			t.Logf("skipping file %s", p)
-			continue
-		}
-
-		filename := path.Base(p)
-		t.Logf("checking for presence additonal checks for file %q", filename)
-		additionalCheck := additionalChecks[filename]
-		if additionalCheck == nil {
-			t.Logf("no additional checks")
-		} else {
-			t.Logf("additional check present")
-			additionalCheck.state = 1
-		}
-
-		t.Run(p, func(t *testing.T) {
-			c, err := config.ParseConfig(p)
-			if err != nil {
-				t.Fatalf("error parsing %s:\n%+v", p, err)
-			}
-
-			t.Logf("file: %s", p)
-			t.Log(pretty.Sprint(c))
-
-			jobs, err := JobsFromConfig(c, config.ParseFlagsNoCertCheck)
-			t.Logf("jobs: %#v", jobs)
-			require.NoError(t, err)
-
-			if additionalCheck != nil {
-				additionalCheck.test(t, jobs)
-				additionalCheck.state = 2
-			}
-		})
-
-	}
-
-	for basename, c := range additionalChecks {
-		if c.state == 0 {
-			panic("univisited additional check " + basename)
-		}
-	}
-
-}
-
-func testSampleConfig_BandwidthLimit(t *testing.T, jobs []Job) {
-	require.Len(t, jobs, 3)
-
-	{
-		limitedSink, ok := jobs[0].(*PassiveSide)
-		require.True(t, ok, "%T", jobs[0])
-		limitedSinkMode, ok := limitedSink.mode.(*modeSink)
-		require.True(t, ok, "%T", limitedSink)
-
-		assert.Equal(t, int64(12345), limitedSinkMode.receiverConfig.BandwidthLimit.Max)
-		assert.Equal(t, int64(1<<17), limitedSinkMode.receiverConfig.BandwidthLimit.BucketCapacity)
-	}
-
-	{
-		limitedPush, ok := jobs[1].(*ActiveSide)
-		require.True(t, ok, "%T", jobs[1])
-		limitedPushMode, ok := limitedPush.mode.(*modePush)
-		require.True(t, ok, "%T", limitedPush)
-
-		assert.Equal(t, int64(54321), limitedPushMode.senderConfig.BandwidthLimit.Max)
-		assert.Equal(t, int64(1024), limitedPushMode.senderConfig.BandwidthLimit.BucketCapacity)
-	}
-
-	{
-		unlimitedSink, ok := jobs[2].(*PassiveSide)
-		require.True(t, ok, "%T", jobs[2])
-		unlimitedSinkMode, ok := unlimitedSink.mode.(*modeSink)
-		require.True(t, ok, "%T", unlimitedSink)
-
-		max := unlimitedSinkMode.receiverConfig.BandwidthLimit.Max
-		assert.Less(t, max, int64(0), max, "unlimited mode <=> negative value for .Max, see bandwidthlimit.Config")
-	}
-
-}
-
-func TestReplicationOptions(t *testing.T) {
-	tmpl := `
-jobs:
-- name: foo
-  type: push
-  connect:
-    type: local
-    listener_name: foo
-    client_identity: bar
-  filesystems: {"<": true}
-  %s
-  snapshotting:
-    type: manual
-  pruning:
-    keep_sender:
-    - type: last_n
-      count: 10
-    keep_receiver:
-    - type: last_n
-      count: 10
-`
-
-	type Test struct {
-		name        string
-		input       string
-		expectOk    func(t *testing.T, a *ActiveSide, m *modePush)
-		expectError bool
-	}
-
-	tests := []Test{
-		{
-			name: "defaults",
-			input: `
-  replication: {}
-`,
-			expectOk: func(t *testing.T, a *ActiveSide, m *modePush) {},
-		},
-		{
-			name: "steps_zero",
-			input: `
-  replication:
-    concurrency:
-      steps: 0
-`,
-			expectError: true,
-		},
-		{
-			name: "size_estimates_zero",
-			input: `
-  replication:
-    concurrency:
-      size_estimates: 0
-`,
-			expectError: true,
-		},
-		{
-			name: "custom_values",
-			input: `
-  replication:
-    concurrency:
-      steps: 23
-      size_estimates: 42
-`,
-			expectOk: func(t *testing.T, a *ActiveSide, m *modePush) {
-				assert.Equal(t, 23, a.replicationDriverConfig.StepQueueConcurrency)
-				assert.Equal(t, 42, m.plannerPolicy.SizeEstimationConcurrency)
-			},
-		},
-		{
-			name: "negative_values_forbidden",
-			input: `
-  replication:
-    concurrency:
-      steps: -23
-      size_estimates: -42
-`,
-			expectError: true,
-		},
-	}
-
-	fill := func(s string) string { return fmt.Sprintf(tmpl, s) }
-
-	for _, ts := range tests {
-		t.Run(ts.name, func(t *testing.T) {
-			assert.True(t, (ts.expectError) != (ts.expectOk != nil))
-
-			cstr := fill(ts.input)
-			t.Logf("testing config:\n%s", cstr)
-			c, err := config.ParseConfigBytes([]byte(cstr))
-			require.NoError(t, err)
-			jobs, err := JobsFromConfig(c, config.ParseFlagsNone)
-			if ts.expectOk != nil {
-				require.NoError(t, err)
-				require.NotNil(t, c)
-				require.NoError(t, err)
-				require.Len(t, jobs, 1)
-				a := jobs[0].(*ActiveSide)
-				m := a.mode.(*modePush)
-				ts.expectOk(t, a, m)
-			} else if ts.expectError {
-				require.Error(t, err)
-			} else {
-				t.Fatalf("test must define expectOk or expectError")
-			}
-
-		})
-	}
-
-}

daemon/job/passive.go

@@ -6,10 +6,10 @@ import (
 
 	"github.com/pkg/errors"
 	"github.com/prometheus/client_golang/prometheus"
-
 	"github.com/zrepl/zrepl/daemon/logging/trace"
 
 	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/daemon/filters"
 	"github.com/zrepl/zrepl/daemon/logging"
 	"github.com/zrepl/zrepl/daemon/snapper"
 	"github.com/zrepl/zrepl/endpoint"
@@ -48,9 +48,19 @@ func (m *modeSink) SnapperReport() *snapper.Report { return nil }
 func modeSinkFromConfig(g *config.Global, in *config.SinkJob, jobID endpoint.JobID) (m *modeSink, err error) {
 	m = &modeSink{}
 
-	m.receiverConfig, err = buildReceiverConfig(in, jobID)
+	rootDataset, err := zfs.NewDatasetPath(in.RootFS)
 	if err != nil {
-		return nil, err
+		return nil, errors.New("root dataset is not a valid zfs filesystem path")
+	}
+
+	m.receiverConfig = endpoint.ReceiverConfig{
+		JobID:                      jobID,
+		RootWithoutClientComponent: rootDataset,
+		AppendClientIdentity:       true, // !
+		UpdateLastReceivedHold:     true,
+	}
+	if err := m.receiverConfig.Validate(); err != nil {
+		return nil, errors.Wrap(err, "cannot build receiver config")
 	}
 
 	return m, nil
@@ -58,19 +68,24 @@ func modeSinkFromConfig(g *config.Global, in *config.SinkJob, jobID endpoint.Job
 
 type modeSource struct {
 	senderConfig *endpoint.SenderConfig
-	snapper      snapper.Snapper
+	snapper      *snapper.PeriodicOrManual
 }
 
 func modeSourceFromConfig(g *config.Global, in *config.SourceJob, jobID endpoint.JobID) (m *modeSource, err error) {
 	// FIXME exact dedup of modePush
 	m = &modeSource{}
-
-	m.senderConfig, err = buildSenderConfig(in, jobID)
+	fsf, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
 	if err != nil {
-		return nil, errors.Wrap(err, "send options")
+		return nil, errors.Wrap(err, "cannot build filesystem filter")
+	}
+	m.senderConfig = &endpoint.SenderConfig{
+		FSF:                         fsf,
+		Encrypt:                     &zfs.NilBool{B: in.Send.Encrypted},
+		DisableIncrementalStepHolds: in.Send.StepHolds.DisableIncremental,
+		JobID:                       jobID,
 	}
 
-	if m.snapper, err = snapper.FromConfig(g, m.senderConfig.FSF, in.Snapshotting); err != nil {
+	if m.snapper, err = snapper.FromConfig(g, fsf, in.Snapshotting); err != nil {
 		return nil, errors.Wrap(err, "cannot build snapper")
 	}
 
@@ -88,11 +103,10 @@ func (m *modeSource) RunPeriodic(ctx context.Context) {
 }
 
 func (m *modeSource) SnapperReport() *snapper.Report {
-	r := m.snapper.Report()
-	return &r
+	return m.snapper.Report()
 }
 
-func passiveSideFromConfig(g *config.Global, in *config.PassiveJob, configJob interface{}, parseFlags config.ParseFlags) (s *PassiveSide, err error) {
+func passiveSideFromConfig(g *config.Global, in *config.PassiveJob, configJob interface{}) (s *PassiveSide, err error) {
 
 	s = &PassiveSide{}
 
@@ -111,7 +125,7 @@ func passiveSideFromConfig(g *config.Global, in *config.PassiveJob, configJob in
 		return nil, err // no wrapping necessary
 	}
 
-	if s.listen, err = fromconfig.ListenerFactoryFromConfig(g, in.Serve, parseFlags); err != nil {
+	if s.listen, err = fromconfig.ListenerFactoryFromConfig(g, in.Serve); err != nil {
 		return nil, errors.Wrap(err, "cannot build listener factory")
 	}
 

daemon/job/snapjob.go

@@ -4,18 +4,13 @@ import (
 	"context"
 	"fmt"
 	"sort"
-	"sync"
 
 	"github.com/pkg/errors"
 	"github.com/prometheus/client_golang/prometheus"
-
 	"github.com/zrepl/zrepl/daemon/logging/trace"
-	"github.com/zrepl/zrepl/util/bandwidthlimit"
-	"github.com/zrepl/zrepl/util/nodefault"
 
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/filters"
-	"github.com/zrepl/zrepl/daemon/job/trigger"
 	"github.com/zrepl/zrepl/daemon/job/wakeup"
 	"github.com/zrepl/zrepl/daemon/pruner"
 	"github.com/zrepl/zrepl/daemon/snapper"
@@ -27,14 +22,13 @@ import (
 type SnapJob struct {
 	name     endpoint.JobID
 	fsfilter zfs.DatasetFilter
-	snapper  snapper.Snapper
+	snapper  *snapper.PeriodicOrManual
 
 	prunerFactory *pruner.LocalPrunerFactory
 
 	promPruneSecs *prometheus.HistogramVec // labels: prune_side
 
-	prunerMtx sync.Mutex
-	pruner    *pruner.Pruner
+	pruner *pruner.Pruner
 }
 
 func (j *SnapJob) Name() string { return j.name.String() }
@@ -82,13 +76,10 @@ type SnapJobStatus struct {
 func (j *SnapJob) Status() *Status {
 	s := &SnapJobStatus{}
 	t := j.Type()
-	j.prunerMtx.Lock()
 	if j.pruner != nil {
 		s.Pruning = j.pruner.Report()
 	}
-	j.prunerMtx.Unlock()
-	r := j.snapper.Report()
-	s.Snapshotting = &r
+	s.Snapshotting = j.snapper.Report()
 	return &Status{Type: t, JobSpecific: s}
 }
 
@@ -105,18 +96,12 @@ func (j *SnapJob) Run(ctx context.Context) {
 
 	defer log.Info("job exiting")
 
-	wakeupTrigger := wakeup.Trigger(ctx)
-
-	snapshottingTrigger := trigger.New("periodic")
+	periodicDone := make(chan struct{})
 	ctx, cancel := context.WithCancel(ctx)
 	defer cancel()
 	periodicCtx, endTask := trace.WithTask(ctx, "snapshotting")
 	defer endTask()
-	go j.snapper.Run(periodicCtx, snapshottingTrigger)
-
-	triggers := trigger.Empty()
-	triggered, endTask := triggers.Spawn(ctx, []trigger.Trigger{snapshottingTrigger, wakeupTrigger})
-	defer endTask()
+	go j.snapper.Run(periodicCtx, periodicDone)
 
 	invocationCount := 0
 outer:
@@ -126,7 +111,9 @@ outer:
 		case <-ctx.Done():
 			log.WithError(ctx.Err()).Info("context")
 			break outer
-		case <-triggered:
+
+		case <-wakeup.Wait(ctx):
+		case <-periodicDone:
 		}
 		invocationCount++
 
@@ -143,7 +130,7 @@ outer:
 // TODO:
 // This is a work-around for the current package daemon/pruner
 // and package pruning.Snapshot limitation: they require the
-// `Replicated` getter method be present, but obviously,
+//  `Replicated` getter method be present, but obviously,
 // a local job like SnapJob can't deliver on that.
 // But the pruner.Pruner gives up on an FS if no replication
 // cursor is present, which is why this pruner returns the
@@ -153,7 +140,7 @@ type alwaysUpToDateReplicationCursorHistory struct {
 	target pruner.Target
 }
 
-var _ pruner.Sender = (*alwaysUpToDateReplicationCursorHistory)(nil)
+var _ pruner.History = (*alwaysUpToDateReplicationCursorHistory)(nil)
 
 func (h alwaysUpToDateReplicationCursorHistory) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
 	fsvReq := &pdu.ListFilesystemVersionsReq{
@@ -186,15 +173,12 @@ func (j *SnapJob) doPrune(ctx context.Context) {
 	sender := endpoint.NewSender(endpoint.SenderConfig{
 		JobID: j.name,
 		FSF:   j.fsfilter,
-		// FIXME the following config fields are irrelevant for SnapJob
-		// because the endpoint is only used as pruner.Target.
-		// However, the implementation requires them to be set.
-		Encrypt:        &nodefault.Bool{B: true},
-		BandwidthLimit: bandwidthlimit.NoLimitConfig(),
+		// FIXME encryption setting is irrelevant for SnapJob because the endpoint is only used as pruner.Target
+		Encrypt: &zfs.NilBool{B: true},
+		// FIXME DisableIncrementalStepHolds setting is irrelevant for SnapJob because the endpoint is only used as pruner.Target
+		DisableIncrementalStepHolds: false,
 	})
-	j.prunerMtx.Lock()
 	j.pruner = j.prunerFactory.BuildLocalPruner(ctx, sender, alwaysUpToDateReplicationCursorHistory{sender})
-	j.prunerMtx.Unlock()
 	log.Info("start pruning")
 	j.pruner.Prune()
 	log.Info("finished pruning")

daemon/job/trigger/cron.go

@@ -1,23 +0,0 @@
-package trigger
-
-import (
-	"context"
-
-	"github.com/robfig/cron/v3"
-)
-
-type Cron struct {
-	spec cron.Schedule
-}
-
-var _ Trigger = &Cron{}
-
-func NewCron(spec cron.Schedule) *Cron {
-	return &Cron{spec: spec}
-}
-
-func (t *Cron) ID() string { return "cron" }
-
-func (t *Cron) run(ctx context.Context, signal chan<- struct{}) {
-	panic("unimpl: extract from cron snapper")
-}

daemon/job/trigger/from_config.go

@@ -1,30 +0,0 @@
-package trigger
-
-import (
-	"fmt"
-
-	"github.com/zrepl/zrepl/config"
-)
-
-func FromConfig(in []*config.ReplicationTriggerEnum) (*Triggers, error) {
-	triggers := make([]Trigger, len(in))
-	for i, e := range in {
-		var t Trigger = nil
-		switch te := e.Ret.(type) {
-		case *config.ReplicationTriggerManual:
-			// not a trigger
-			t = NewManual("manual")
-		case *config.ReplicationTriggerPeriodic:
-			t = NewPeriodic(te.Interval.Duration())
-		case *config.ReplicationTriggerCron:
-			t = NewCron(te.Cron.Schedule)
-		default:
-			return nil, fmt.Errorf("unknown trigger type %T", te)
-		}
-		triggers[i] = t
-	}
-	return &Triggers{
-		spawned:  false,
-		triggers: triggers,
-	}, nil
-}

daemon/job/trigger/logger.go

@@ -1,12 +0,0 @@
-package trigger
-
-import (
-	"context"
-
-	"github.com/zrepl/zrepl/logger"
-)
-
-
-func getLogger(ctx context.Context) logger.Logger {
-	panic("unimpl")
-}

daemon/job/trigger/manual.go

@@ -1,33 +0,0 @@
-package trigger
-
-import "context"
-
-type Manual struct {
-	id     string
-	signal chan<- struct{}
-}
-
-var _ Trigger = &Manual{}
-
-func NewManual(id string) *Manual {
-	return &Manual{
-		id:     id,
-		signal: nil,
-	}
-}
-
-func (t *Manual) ID() string {
-	return t.id
-}
-
-func (t *Manual) run(ctx context.Context, signal chan<- struct{}) {
-	if t.signal != nil {
-		panic("run must only be called once")
-	}
-	t.signal = signal
-}
-
-// Panics if called before the trigger has been spanwed as part of a `Triggers`.
-func (t *Manual) Fire() {
-	t.signal <- struct{}{}
-}

daemon/job/trigger/periodic.go

@@ -1,33 +0,0 @@
-package trigger
-
-import (
-	"context"
-	"time"
-)
-
-type Periodic struct {
-	interval time.Duration
-}
-
-var _ Trigger = &Periodic{}
-
-func NewPeriodic(interval time.Duration) *Periodic {
-	return &Periodic{
-		interval: interval,
-	}
-}
-
-func (p *Periodic) ID() string { return "periodic" }
-
-func (p *Periodic) run(ctx context.Context, signal chan<- struct{}) {
-	t := time.NewTicker(p.interval)
-	defer t.Stop()
-	for {
-		select {
-		case <-t.C:
-			signal <- struct{}{}
-		case <-ctx.Done():
-			return
-		}
-	}
-}

daemon/job/trigger/trigger.go

@@ -1,91 +0,0 @@
-package trigger
-
-import (
-	"context"
-	"github.com/zrepl/zrepl/daemon/logging/trace"
-)
-
-type Triggers struct {
-	spawned  bool
-	triggers []Trigger
-}
-
-type Trigger interface {
-	ID() string
-	run(context.Context, chan<- struct{})
-}
-
-func Empty() *Triggers {
-	return &Triggers{
-		spawned:  false,
-		triggers: nil,
-	}
-}
-
-func (t *Triggers) Spawn(ctx context.Context, additionalTriggers []Trigger) (chan Trigger, trace.DoneFunc) {
-	if t.spawned {
-		panic("must only spawn once")
-	}
-	t.spawned = true
-	t.triggers = append(t.triggers, additionalTriggers...)
-	sink := make(chan Trigger)
-	endTask := t.spawn(ctx, sink)
-	return sink, endTask
-}
-
-type triggering struct {
-	trigger Trigger
-	handled chan struct{}
-}
-
-func (t *Triggers) spawn(ctx context.Context, sink chan Trigger) trace.DoneFunc {
-	ctx, endTask := trace.WithTask(ctx, "triggers")
-	ctx, add, wait := trace.WithTaskGroup(ctx, "trigger-tasks")
-	triggered := make(chan triggering, len(t.triggers))
-	for _, t := range t.triggers {
-		t := t
-		signal := make(chan struct{})
-		go add(func(ctx context.Context) {
-			t.run(ctx, signal)
-		})
-		go func() {
-			for {
-				select {
-				case <-ctx.Done():
-					return
-				case <-signal:
-					handled := make(chan struct{})
-					select {
-					case triggered <- triggering{trigger: t, handled: handled}:
-					default:
-						panic("this funtion ensures that there's always room in the channel")
-					}
-					select {
-					case <-handled:
-					case <-ctx.Done():
-						return
-					}
-				}
-			}
-		}()
-	}
-	go func() {
-		defer wait()
-		for {
-			select {
-			case <-ctx.Done():
-				return
-			case triggering := <-triggered:
-				select {
-				case sink <- triggering.trigger:
-				default:
-					getLogger(ctx).
-						WithField("trigger_id", triggering.trigger.ID()).
-						Warn("dropping triggering because job is busy")
-				}
-				close(triggering.handled)
-			}
-		}
-	}()
-	return endTask
-}

daemon/job/wakeup/wakeup.go

@@ -3,8 +3,6 @@ package wakeup
 import (
 	"context"
 	"errors"
-
-	"github.com/zrepl/zrepl/daemon/job/trigger"
 )
 
 type contextKey int
@@ -19,10 +17,6 @@ func Wait(ctx context.Context) <-chan struct{} {
 	return wc
 }
 
-func Trigger(ctx context.Context) trigger.Trigger {
-	panic("unimpl")
-}
-
 type Func func() error
 
 var AlreadyWokenUp = errors.New("already woken up")

daemon/logging/build_logging.go

@@ -9,7 +9,6 @@ import (
 
 	"github.com/mattn/go-isatty"
 	"github.com/pkg/errors"
-
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/logging/trace"
 	"github.com/zrepl/zrepl/logger"
@@ -63,7 +62,6 @@ type Subsystem string
 const (
 	SubsysMeta         Subsystem = "meta"
 	SubsysJob          Subsystem = "job"
-	SubsysTrigger      Subsystem = "trigger"
 	SubsysReplication  Subsystem = "repl"
 	SubsysEndpoint     Subsystem = "endpoint"
 	SubsysPruning      Subsystem = "pruning"

daemon/logging/trace/trace.go

@@ -1,6 +1,6 @@
 // package trace provides activity tracing via ctx through Tasks and Spans
 //
-// # Basic Concepts
+// Basic Concepts
 //
 // Tracing can be used to identify where a piece of code spends its time.
 //
@@ -10,50 +10,51 @@
 // to tech-savvy users (albeit not developers).
 //
 // This package provides the concept of Tasks and Spans to express what activity is happening within an application:
-// - Neither task nor span is really tangible but instead contained within the context.Context tree
-// - Tasks represent concurrent activity (i.e. goroutines).
-// - Spans represent a semantic stack trace within a task.
+//
+//  - Neither task nor span is really tangible but instead contained within the context.Context tree
+//  - Tasks represent concurrent activity (i.e. goroutines).
+//  - Spans represent a semantic stack trace within a task.
+//
 // As a consequence, whenever a context is propagated across goroutine boundary, you need to create a child task:
 //
-//	go func(ctx context.Context) {
-//	  ctx, endTask = WithTask(ctx, "what-happens-inside-the-child-task")
-//	  defer endTask()
-//	  // ...
-//	}(ctx)
+//   go func(ctx context.Context) {
+//     ctx, endTask = WithTask(ctx, "what-happens-inside-the-child-task")
+//     defer endTask()
+//     // ...
+//   }(ctx)
 //
 // Within the task, you can open up a hierarchy of spans.
 // In contrast to tasks, which have can multiple concurrently running child tasks,
 // spans must nest and not cross the goroutine boundary.
 //
-//	ctx, endSpan = WithSpan(ctx, "copy-dir")
-//	defer endSpan()
-//	for _, f := range dir.Files() {
-//	  func() {
-//	    ctx, endSpan := WithSpan(ctx, fmt.Sprintf("copy-file %q", f))
-//	    defer endspan()
-//	    b, _ := ioutil.ReadFile(f)
-//	    _ = ioutil.WriteFile(f + ".copy", b, 0600)
-//	  }()
-//	}
+//  ctx, endSpan = WithSpan(ctx, "copy-dir")
+//  defer endSpan()
+//  for _, f := range dir.Files() {
+//    func() {
+//      ctx, endSpan := WithSpan(ctx, fmt.Sprintf("copy-file %q", f))
+//      defer endspan()
+//      b, _ := ioutil.ReadFile(f)
+//      _ = ioutil.WriteFile(f + ".copy", b, 0600)
+//    }()
+//  }
 //
 // In combination:
-//
-//	ctx, endTask = WithTask(ctx, "copy-dirs")
-//	defer endTask()
-//	for i := range dirs {
-//	  go func(dir string) {
-//	    ctx, endTask := WithTask(ctx, "copy-dir")
-//	    defer endTask()
-//	    for _, f := range filesIn(dir) {
-//	      func() {
-//	        ctx, endSpan := WithSpan(ctx, fmt.Sprintf("copy-file %q", f))
-//	        defer endspan()
-//	        b, _ := ioutil.ReadFile(f)
-//	        _ = ioutil.WriteFile(f + ".copy", b, 0600)
-//	      }()
-//	    }
-//	  }()
-//	}
+//  ctx, endTask = WithTask(ctx, "copy-dirs")
+//  defer endTask()
+//  for i := range dirs {
+//    go func(dir string) {
+//      ctx, endTask := WithTask(ctx, "copy-dir")
+//      defer endTask()
+//      for _, f := range filesIn(dir) {
+//        func() {
+//          ctx, endSpan := WithSpan(ctx, fmt.Sprintf("copy-file %q", f))
+//          defer endspan()
+//          b, _ := ioutil.ReadFile(f)
+//          _ = ioutil.WriteFile(f + ".copy", b, 0600)
+//        }()
+//      }
+//    }()
+//  }
 //
 // Note that a span ends at the time you call endSpan - not before and not after that.
 // If you violate the stack-like nesting of spans by forgetting an endSpan() invocation,
@@ -64,7 +65,8 @@
 //
 // Recovering from endSpan() or endTask() panics will corrupt the trace stack and lead to corrupt tracefile output.
 //
-// # Best Practices For Naming Tasks And Spans
+//
+// Best Practices For Naming Tasks And Spans
 //
 // Tasks should always have string constants as names, and must not contain the `#` character. WHy?
 // First, the visualization by chrome://tracing draws a horizontal bar for each task in the trace.
@@ -72,7 +74,8 @@
 // Note that the `#NUM` suffix will be reused if a task has ended, in order to avoid an
 // infinite number of horizontal bars in the visualization.
 //
-// # Chrome-compatible Tracefile Support
+//
+// Chrome-compatible Tracefile Support
 //
 // The activity trace generated by usage of WithTask and WithSpan can be rendered to a JSON output file
 // that can be loaded into chrome://tracing .
@@ -90,15 +93,11 @@ package trace
 import (
 	"context"
 	"fmt"
-	"os"
-	runtimedebug "runtime/debug"
 	"strings"
 	"time"
 
-	"github.com/kr/pretty"
 	"github.com/pkg/errors"
 	"github.com/prometheus/client_golang/prometheus"
-
 	"github.com/zrepl/zrepl/util/chainlock"
 )
 
@@ -121,19 +120,15 @@ func RegisterMetrics(r prometheus.Registerer) {
 }
 
 type traceNode struct {
-	// NOTE: members with prefix debug are only valid if the package variable debugEnabled is true.
-
-	id                 string
-	annotation         string
-	parentTask         *traceNode
-	debugCreationStack string // debug: stack trace of when the traceNode was created
+	id         string
+	annotation string
+	parentTask *traceNode
 
 	mtx chainlock.L
 
-	activeChildTasks      int32               // only for task nodes, insignificant for span nodes
-	debugActiveChildTasks map[*traceNode]bool // debug: set of active child tasks
-	parentSpan            *traceNode
-	activeChildSpan       *traceNode // nil if task or span doesn't have an active child span
+	activeChildTasks int32 // only for task nodes, insignificant for span nodes
+	parentSpan       *traceNode
+	activeChildSpan  *traceNode // nil if task or span doesn't have an active child span
 
 	startedAt time.Time
 	endedAt   time.Time
@@ -142,14 +137,6 @@ type traceNode struct {
 func (s *traceNode) StartedAt() time.Time { return s.startedAt }
 func (s *traceNode) EndedAt() time.Time   { return s.endedAt }
 
-// caller must hold mtx
-func (s *traceNode) debugString() string {
-	if !debugEnabled {
-		return "<debugEnabled=false>"
-	}
-	return pretty.Sprint(s)
-}
-
 // Returned from WithTask or WithSpan.
 // Must be called once the task or span ends.
 // See package-level docs for nesting rules.
@@ -209,16 +196,8 @@ func WithTask(ctx context.Context, taskName string) (context.Context, DoneFunc)
 		endedAt:   time.Time{},
 	}
 
-	if debugEnabled {
-		this.debugCreationStack = string(runtimedebug.Stack())
-		this.debugActiveChildTasks = map[*traceNode]bool{}
-	}
-
 	if parentTask != nil {
 		this.parentTask.activeChildTasks++
-		if debugEnabled {
-			this.parentTask.debugActiveChildTasks[this] = true
-		}
 		parentTask.mtx.Unlock()
 	}
 
@@ -239,11 +218,7 @@ func WithTask(ctx context.Context, taskName string) (context.Context, DoneFunc)
 			defer this.mtx.Lock().Unlock()
 
 			if this.activeChildTasks != 0 {
-				if debugEnabled {
-					// the debugString can be quite long and panic won't print it completely
-					fmt.Fprintf(os.Stderr, "going to panic due to activeChildTasks:\n%s\n", this.debugString())
-				}
-				panic(errors.WithMessagef(ErrTaskStillHasActiveChildTasks, "end task: %v active child tasks (run daemon with env var %s=1 for more details)\n", this.activeChildTasks, debugEnabledEnvVar))
+				panic(errors.Wrapf(ErrTaskStillHasActiveChildTasks, "end task: %v active child tasks", this.activeChildTasks))
 			}
 
 			// support idempotent task ends
@@ -254,15 +229,8 @@ func WithTask(ctx context.Context, taskName string) (context.Context, DoneFunc)
 
 			if this.parentTask != nil {
 				this.parentTask.activeChildTasks--
-				if debugEnabled {
-					delete(this.parentTask.debugActiveChildTasks, this)
-				}
 				if this.parentTask.activeChildTasks < 0 {
-					if debugEnabled {
-						// the debugString can be quite long and panic won't print it completely
-						fmt.Fprintf(os.Stderr, "going to panic due to activeChildTasks < 0:\n%s\n", this.parentTask.debugString())
-					}
-					panic(fmt.Sprintf("impl error: parent task with negative activeChildTasks count: %v", this.parentTask.activeChildTasks))
+					panic("impl error: parent task with negative activeChildTasks count")
 				}
 			}
 			return false
@@ -311,10 +279,6 @@ func WithSpan(ctx context.Context, annotation string) (context.Context, DoneFunc
 		endedAt:   time.Time{},
 	}
 
-	if debugEnabled {
-		this.debugCreationStack = string(runtimedebug.Stack())
-	}
-
 	parentSpan.mtx.HoldWhile(func() {
 		if parentSpan.activeChildSpan != nil {
 			panic(ErrAlreadyActiveChildSpan)

daemon/logging/trace/trace_convenience.go

@@ -11,6 +11,8 @@ import (
 // use like this:
 //
 //	defer WithSpanFromStackUpdateCtx(&existingCtx)()
+//
+//
 func WithSpanFromStackUpdateCtx(ctx *context.Context) DoneFunc {
 	childSpanCtx, end := WithSpan(*ctx, getMyCallerOrPanic())
 	*ctx = childSpanCtx
@@ -41,19 +43,15 @@ func WithTaskAndSpan(ctx context.Context, task string, span string) (context.Con
 }
 
 // create a span during which several child tasks are spawned using the `add` function
-//
-// IMPORTANT FOR USERS: Caller must ensure that the capturing behavior is correct, the Go linter doesn't catch this.
 func WithTaskGroup(ctx context.Context, taskGroup string) (_ context.Context, add func(f func(context.Context)), waitEnd DoneFunc) {
 	var wg sync.WaitGroup
 	ctx, endSpan := WithSpan(ctx, taskGroup)
 	add = func(f func(context.Context)) {
 		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			ctx, endTask := WithTask(ctx, taskGroup)
-			defer endTask()
-			f(ctx)
-		}()
+		defer wg.Done()
+		ctx, endTask := WithTask(ctx, taskGroup)
+		defer endTask()
+		f(ctx)
 	}
 	waitEnd = func() {
 		wg.Wait()

daemon/logging/trace/trace_convenience_test.go

@@ -1,10 +1,7 @@
 package trace
 
 import (
-	"context"
-	"sync/atomic"
 	"testing"
-	"time"
 
 	"github.com/stretchr/testify/assert"
 )
@@ -17,46 +14,3 @@ func TestGetCallerOrPanic(t *testing.T) {
 	// zrepl prefix is stripped
 	assert.Equal(t, "daemon/logging/trace.TestGetCallerOrPanic", ret)
 }
-
-func TestWithTaskGroupRunTasksConcurrently(t *testing.T) {
-
-	// spawn a task group where each task waits for the other to start
-	// => without concurrency, they would hang
-
-	rootCtx, endRoot := WithTaskFromStack(context.Background())
-	defer endRoot()
-
-	_, add, waitEnd := WithTaskGroup(rootCtx, "test-task-group")
-
-	schedulerTimeout := 2 * time.Second
-	timeout := time.After(schedulerTimeout)
-	var hadTimeout uint32
-	started0, started1 := make(chan struct{}), make(chan struct{})
-	for i := 0; i < 2; i++ {
-		i := i // capture by copy
-		add(func(ctx context.Context) {
-			switch i {
-			case 0:
-				close(started0)
-				select {
-				case <-started1:
-				case <-timeout:
-					atomic.AddUint32(&hadTimeout, 1)
-				}
-			case 1:
-				close(started1)
-				select {
-				case <-started0:
-				case <-timeout:
-					atomic.AddUint32(&hadTimeout, 1)
-				}
-			default:
-				panic("unreachable")
-			}
-		})
-	}
-
-	waitEnd()
-	assert.Zero(t, hadTimeout, "either bad impl or scheduler timeout (which is %v)", schedulerTimeout)
-
-}

daemon/logging/trace/trace_debug.go

@@ -3,13 +3,9 @@ package trace
 import (
 	"fmt"
 	"os"
-
-	"github.com/zrepl/zrepl/util/envconst"
 )
 
-const debugEnabledEnvVar = "ZREPL_TRACE_DEBUG_ENABLED"
-
-var debugEnabled = envconst.Bool(debugEnabledEnvVar, false)
+const debugEnabled = false
 
 func debug(format string, args ...interface{}) {
 	if !debugEnabled {

daemon/logging/trace/trace_genID.go

@@ -3,11 +3,20 @@ package trace
 import (
 	"encoding/base64"
 	"math/rand"
+	"os"
 	"strings"
+	"time"
 
 	"github.com/zrepl/zrepl/util/envconst"
 )
 
+var genIdPRNG = rand.New(rand.NewSource(1))
+
+func init() {
+	genIdPRNG.Seed(time.Now().UnixNano())
+	genIdPRNG.Seed(int64(os.Getpid()))
+}
+
 var genIdNumBytes = envconst.Int("ZREPL_TRACE_ID_NUM_BYTES", 3)
 
 func init() {
@@ -21,7 +30,7 @@ func genID() string {
 	enc := base64.NewEncoder(base64.RawStdEncoding, &out)
 	buf := make([]byte, genIdNumBytes)
 	for i := 0; i < len(buf); {
-		n, err := rand.Read(buf[i:])
+		n, err := genIdPRNG.Read(buf[i:])
 		if err != nil {
 			panic(err)
 		}

daemon/pruner/pruner.go

@@ -19,20 +19,12 @@ import (
 	"github.com/zrepl/zrepl/util/envconst"
 )
 
-// The sender in the replication setup.
-// The pruner uses the Sender to determine which of the Target's filesystems need to be pruned.
-// Also, it asks the Sender about the replication cursor of each filesystem
-// to enable the 'not_replicated' pruning rule.
-//
 // Try to keep it compatible with github.com/zrepl/zrepl/endpoint.Endpoint
-type Sender interface {
+type History interface {
 	ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error)
 	ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error)
 }
 
-// The pruning target, i.e., on which snapshots are destroyed.
-// This can be a replication sender or receiver.
-//
 // Try to keep it compatible with github.com/zrepl/zrepl/endpoint.Endpoint
 type Target interface {
 	ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error)
@@ -56,7 +48,7 @@ func GetLogger(ctx context.Context) Logger {
 type args struct {
 	ctx                            context.Context
 	target                         Target
-	sender                         Sender
+	receiver                       History
 	rules                          []pruning.KeepRule
 	retryWait                      time.Duration
 	considerSnapAtCursorReplicated bool
@@ -140,12 +132,12 @@ func NewPrunerFactory(in config.PruningSenderReceiver, promPruneSecs *prometheus
 	return f, nil
 }
 
-func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, sender Sender) *Pruner {
+func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, receiver History) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "sender"),
 			target,
-			sender,
+			receiver,
 			f.senderRules,
 			f.retryWait,
 			f.considerSnapAtCursorReplicated,
@@ -156,12 +148,12 @@ func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, se
 	return p
 }
 
-func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target, sender Sender) *Pruner {
+func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target, receiver History) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "receiver"),
 			target,
-			sender,
+			receiver,
 			f.receiverRules,
 			f.retryWait,
 			false, // senseless here anyways
@@ -172,12 +164,12 @@ func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target,
 	return p
 }
 
-func (f *LocalPrunerFactory) BuildLocalPruner(ctx context.Context, target Target, history Sender) *Pruner {
+func (f *LocalPrunerFactory) BuildLocalPruner(ctx context.Context, target Target, receiver History) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "local"),
 			target,
-			history,
+			receiver,
 			f.keepRules,
 			f.retryWait,
 			false, // considerSnapAtCursorReplicated is not relevant for local pruning
@@ -199,16 +191,6 @@ const (
 	Done
 )
 
-// Returns true in case the State is a terminal state(PlanErr, ExecErr, Done)
-func (s State) IsTerminal() bool {
-	switch s {
-	case PlanErr, ExecErr, Done:
-		return true
-	default:
-		return false
-	}
-}
-
 type updater func(func(*Pruner))
 
 func (p *Pruner) Prune() {
@@ -361,9 +343,9 @@ func (s snapshot) Date() time.Time { return s.date }
 
 func doOneAttempt(a *args, u updater) {
 
-	ctx, target, sender := a.ctx, a.target, a.sender
+	ctx, target, receiver := a.ctx, a.target, a.receiver
 
-	sfssres, err := sender.ListFilesystems(ctx, &pdu.ListFilesystemReq{})
+	sfssres, err := receiver.ListFilesystems(ctx, &pdu.ListFilesystemReq{})
 	if err != nil {
 		u(func(p *Pruner) {
 			p.state = PlanErr
@@ -428,7 +410,7 @@ tfss_loop:
 		rcReq := &pdu.ReplicationCursorReq{
 			Filesystem: tfs.Path,
 		}
-		rc, err := sender.ReplicationCursor(ctx, rcReq)
+		rc, err := receiver.ReplicationCursor(ctx, rcReq)
 		if err != nil {
 			pfsPlanErrAndLog(err, "cannot get replication cursor bookmark")
 			continue tfss_loop
@@ -474,7 +456,7 @@ tfss_loop:
 			})
 		}
 		if preCursor {
-			pfsPlanErrAndLog(fmt.Errorf("prune target has no snapshot that corresponds to sender replication cursor bookmark"), "")
+			pfsPlanErrAndLog(fmt.Errorf("replication cursor not found in prune target filesystem versions"), "")
 			continue tfss_loop
 		}
 

daemon/snapper/cron.go

@@ -1,147 +0,0 @@
-package snapper
-
-import (
-	"context"
-	"fmt"
-	"sync"
-	"time"
-
-	"github.com/pkg/errors"
-
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/hooks"
-	"github.com/zrepl/zrepl/daemon/job/trigger"
-	"github.com/zrepl/zrepl/util/suspendresumesafetimer"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-func cronFromConfig(fsf zfs.DatasetFilter, in config.SnapshottingCron) (*Cron, error) {
-
-	hooksList, err := hooks.ListFromConfig(&in.Hooks)
-	if err != nil {
-		return nil, errors.Wrap(err, "hook config error")
-	}
-	planArgs := planArgs{
-		prefix:          in.Prefix,
-		timestampFormat: in.TimestampFormat,
-		hooks:           hooksList,
-	}
-	return &Cron{config: in, fsf: fsf, planArgs: planArgs}, nil
-}
-
-type Cron struct {
-	config   config.SnapshottingCron
-	fsf      zfs.DatasetFilter
-	planArgs planArgs
-
-	mtx sync.RWMutex
-
-	running                 bool
-	wakeupTime              time.Time // zero value means uninit
-	lastError               error
-	lastPlan                *plan
-	wakeupWhileRunningCount int
-}
-
-func (s *Cron) Run(ctx context.Context, snapshotsTaken *trigger.Manual) {
-
-	for {
-		now := time.Now()
-		s.mtx.Lock()
-		s.wakeupTime = s.config.Cron.Schedule.Next(now)
-		s.mtx.Unlock()
-
-		ctxDone := suspendresumesafetimer.SleepUntil(ctx, s.wakeupTime)
-		if ctxDone != nil {
-			return
-		}
-
-		getLogger(ctx).Debug("cron timer fired")
-		s.mtx.Lock()
-		if s.running {
-			getLogger(ctx).Warn("snapshotting triggered according to cron rules but previous snapshotting is not done; not taking a snapshot this time")
-			s.wakeupWhileRunningCount++
-			s.mtx.Unlock()
-			continue
-		}
-		s.lastError = nil
-		s.lastPlan = nil
-		s.wakeupWhileRunningCount = 0
-		s.running = true
-		s.mtx.Unlock()
-		go func() {
-			err := s.do(ctx)
-			s.mtx.Lock()
-			s.lastError = err
-			s.running = false
-			s.mtx.Unlock()
-
-			snapshotsTaken.Fire()
-		}()
-	}
-
-}
-
-func (s *Cron) do(ctx context.Context) error {
-	fss, err := zfs.ZFSListMapping(ctx, s.fsf)
-	if err != nil {
-		return errors.Wrap(err, "cannot list filesystems")
-	}
-	p := makePlan(s.planArgs, fss)
-
-	s.mtx.Lock()
-	s.lastPlan = p
-	s.lastError = nil
-	s.mtx.Unlock()
-
-	ok := p.execute(ctx, false)
-	if !ok {
-		return errors.New("one or more snapshots could not be created, check logs for details")
-	} else {
-		return nil
-	}
-}
-
-type CronState string
-
-const (
-	CronStateRunning CronState = "running"
-	CronStateWaiting CronState = "waiting"
-)
-
-type CronReport struct {
-	State      CronState
-	WakeupTime time.Time
-	Errors     []string
-	Progress   []*ReportFilesystem
-}
-
-func (s *Cron) Report() Report {
-
-	s.mtx.Lock()
-	defer s.mtx.Unlock()
-
-	r := CronReport{}
-
-	r.WakeupTime = s.wakeupTime
-
-	if s.running {
-		r.State = CronStateRunning
-	} else {
-		r.State = CronStateWaiting
-	}
-
-	if s.lastError != nil {
-		r.Errors = append(r.Errors, s.lastError.Error())
-	}
-	if s.wakeupWhileRunningCount > 0 {
-		r.Errors = append(r.Errors, fmt.Sprintf("cron frequency is too high; snapshots were not taken %d times", s.wakeupWhileRunningCount))
-	}
-
-	r.Progress = nil
-	if s.lastPlan != nil {
-		r.Progress = s.lastPlan.report()
-	}
-
-	return Report{Type: TypeCron, Cron: &r}
-}

daemon/snapper/cron_test.go

@@ -1,68 +0,0 @@
-package snapper
-
-import (
-	"fmt"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"github.com/zrepl/yaml-config"
-
-	"github.com/zrepl/zrepl/config"
-)
-
-func TestCronLibraryWorks(t *testing.T) {
-
-	type testCase struct {
-		spec   string
-		in     time.Time
-		expect time.Time
-	}
-	dhm := func(day, hour, minutes int) time.Time {
-		return time.Date(2022, 7, day, hour, minutes, 0, 0, time.UTC)
-	}
-	hm := func(hour, minutes int) time.Time {
-		return dhm(23, hour, minutes)
-	}
-
-	tcs := []testCase{
-		{"0-10 * * * *", dhm(17, 1, 10), dhm(17, 2, 0)},
-		{"0-10 * * * *", dhm(17, 23, 10), dhm(18, 0, 0)},
-		{"0-10 * * * *", hm(1, 9), hm(1, 10)},
-		{"0-10 * * * *", hm(1, 9), hm(1, 10)},
-
-		{"1,3,5 * * * *", hm(1, 1), hm(1, 3)},
-		{"1,3,5 * * * *", hm(1, 2), hm(1, 3)},
-		{"1,3,5 * * * *", hm(1, 3), hm(1, 5)},
-		{"1,3,5 * * * *", hm(1, 5), hm(2, 1)},
-
-		{"* 0-5,8,12 * * *", hm(0, 0), hm(0, 1)},
-		{"* 0-5,8,12 * * *", hm(4, 59), hm(5, 0)},
-		{"* 0-5,8,12 * * *", hm(5, 0), hm(5, 1)},
-		{"* 0-5,8,12 * * *", hm(5, 59), hm(8, 0)},
-		{"* 0-5,8,12 * * *", hm(8, 59), hm(12, 0)},
-
-		// https://github.com/zrepl/zrepl/pull/614#issuecomment-1188358989
-		{"53 17,18,19 * * *", dhm(23, 17, 52), dhm(23, 17, 53)},
-		{"53 17,18,19 * * *", dhm(23, 17, 53), dhm(23, 18, 53)},
-		{"53 17,18,19 * * *", dhm(23, 18, 53), dhm(23, 19, 53)},
-		{"53 17,18,19 * * *", dhm(23, 19, 53), dhm(24 /* ! */, 17, 53)},
-	}
-
-	for i, tc := range tcs {
-		t.Run(fmt.Sprintf("%d", i), func(t *testing.T) {
-			var s struct {
-				Cron config.CronSpec `yaml:"cron"`
-			}
-			inp := fmt.Sprintf("cron: %q", tc.spec)
-			fmt.Println("spec is ", inp)
-			err := yaml.UnmarshalStrict([]byte(inp), &s)
-			require.NoError(t, err)
-
-			actual := s.Cron.Schedule.Next(tc.in)
-			assert.Equal(t, tc.expect, actual)
-		})
-	}
-
-}

daemon/snapper/impl.go

@@ -1,268 +0,0 @@
-package snapper
-
-import (
-	"context"
-	"fmt"
-	"sort"
-	"strconv"
-	"strings"
-	"time"
-
-	"github.com/zrepl/zrepl/daemon/hooks"
-	"github.com/zrepl/zrepl/daemon/logging"
-	"github.com/zrepl/zrepl/util/chainlock"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-type planArgs struct {
-	prefix          string
-	timestampFormat string
-	hooks           *hooks.List
-}
-
-type plan struct {
-	mtx   chainlock.L
-	args  planArgs
-	snaps map[*zfs.DatasetPath]*snapProgress
-}
-
-func makePlan(args planArgs, fss []*zfs.DatasetPath) *plan {
-	snaps := make(map[*zfs.DatasetPath]*snapProgress, len(fss))
-	for _, fs := range fss {
-		snaps[fs] = &snapProgress{state: SnapPending}
-	}
-	return &plan{snaps: snaps, args: args}
-}
-
-//go:generate stringer -type=SnapState
-type SnapState uint
-
-const (
-	SnapPending SnapState = 1 << iota
-	SnapStarted
-	SnapDone
-	SnapError
-)
-
-// All fields protected by Snapper.mtx
-type snapProgress struct {
-	state SnapState
-
-	// SnapStarted, SnapDone, SnapError
-	name     string
-	startAt  time.Time
-	hookPlan *hooks.Plan
-
-	// SnapDone
-	doneAt time.Time
-
-	// SnapErr TODO disambiguate state
-	runResults hooks.PlanReport
-}
-
-func (plan *plan) formatNow(format string) string {
-	now := time.Now().UTC()
-	switch strings.ToLower(format) {
-	case "dense":
-		format = "20060102_150405_000"
-	case "human":
-		format = "2006-01-02_15:04:05"
-	case "iso-8601":
-		format = "2006-01-02T15:04:05.000Z"
-	case "unix-seconds":
-		return strconv.FormatInt(now.Unix(), 10)
-	}
-	return now.Format(format)
-}
-
-func (plan *plan) execute(ctx context.Context, dryRun bool) (ok bool) {
-
-	hookMatchCount := make(map[hooks.Hook]int, len(*plan.args.hooks))
-	for _, h := range *plan.args.hooks {
-		hookMatchCount[h] = 0
-	}
-
-	anyFsHadErr := false
-	// TODO channel programs -> allow a little jitter?
-	for fs, progress := range plan.snaps {
-		suffix := plan.formatNow(plan.args.timestampFormat)
-		snapname := fmt.Sprintf("%s%s", plan.args.prefix, suffix)
-
-		ctx := logging.WithInjectedField(ctx, "fs", fs.ToString())
-		ctx = logging.WithInjectedField(ctx, "snap", snapname)
-
-		hookEnvExtra := hooks.Env{
-			hooks.EnvFS:       fs.ToString(),
-			hooks.EnvSnapshot: snapname,
-		}
-
-		jobCallback := hooks.NewCallbackHookForFilesystem("snapshot", fs, func(ctx context.Context) (err error) {
-			l := getLogger(ctx)
-			l.Debug("create snapshot")
-			err = zfs.ZFSSnapshot(ctx, fs, snapname, false) // TODO propagate context to ZFSSnapshot
-			if err != nil {
-				l.WithError(err).Error("cannot create snapshot")
-			}
-			return
-		})
-
-		fsHadErr := false
-		var hookPlanReport hooks.PlanReport
-		var hookPlan *hooks.Plan
-		{
-			filteredHooks, err := plan.args.hooks.CopyFilteredForFilesystem(fs)
-			if err != nil {
-				getLogger(ctx).WithError(err).Error("unexpected filter error")
-				fsHadErr = true
-				goto updateFSState
-			}
-			// account for running hooks
-			for _, h := range filteredHooks {
-				hookMatchCount[h] = hookMatchCount[h] + 1
-			}
-
-			var planErr error
-			hookPlan, planErr = hooks.NewPlan(&filteredHooks, hooks.PhaseSnapshot, jobCallback, hookEnvExtra)
-			if planErr != nil {
-				fsHadErr = true
-				getLogger(ctx).WithError(planErr).Error("cannot create job hook plan")
-				goto updateFSState
-			}
-		}
-
-		plan.mtx.HoldWhile(func() {
-			progress.name = snapname
-			progress.startAt = time.Now()
-			progress.hookPlan = hookPlan
-			progress.state = SnapStarted
-		})
-
-		{
-			getLogger(ctx).WithField("report", hookPlan.Report().String()).Debug("begin run job plan")
-			hookPlan.Run(ctx, dryRun)
-			hookPlanReport = hookPlan.Report()
-			fsHadErr = hookPlanReport.HadError() // not just fatal errors
-			if fsHadErr {
-				getLogger(ctx).WithField("report", hookPlanReport.String()).Error("end run job plan with error")
-			} else {
-				getLogger(ctx).WithField("report", hookPlanReport.String()).Info("end run job plan successful")
-			}
-		}
-
-	updateFSState:
-		anyFsHadErr = anyFsHadErr || fsHadErr
-		plan.mtx.HoldWhile(func() {
-			progress.doneAt = time.Now()
-			progress.state = SnapDone
-			if fsHadErr {
-				progress.state = SnapError
-			}
-			progress.runResults = hookPlanReport
-		})
-	}
-
-	for h, mc := range hookMatchCount {
-		if mc == 0 {
-			hookIdx := -1
-			for idx, ah := range *plan.args.hooks {
-				if ah == h {
-					hookIdx = idx
-					break
-				}
-			}
-			getLogger(ctx).WithField("hook", h.String()).WithField("hook_number", hookIdx+1).Warn("hook did not match any snapshotted filesystems")
-		}
-	}
-
-	return !anyFsHadErr
-}
-
-type ReportFilesystem struct {
-	Path  string
-	State SnapState
-
-	// Valid in SnapStarted and later
-	SnapName      string
-	StartAt       time.Time
-	Hooks         string
-	HooksHadError bool
-
-	// Valid in SnapDone | SnapError
-	DoneAt time.Time
-}
-
-func (plan *plan) report() []*ReportFilesystem {
-	plan.mtx.Lock()
-	defer plan.mtx.Unlock()
-
-	pReps := make([]*ReportFilesystem, 0, len(plan.snaps))
-	for fs, p := range plan.snaps {
-		var hooksStr string
-		var hooksHadError bool
-		if p.hookPlan != nil {
-			hooksStr, hooksHadError = p.report()
-		}
-		pReps = append(pReps, &ReportFilesystem{
-			Path:          fs.ToString(),
-			State:         p.state,
-			SnapName:      p.name,
-			StartAt:       p.startAt,
-			DoneAt:        p.doneAt,
-			Hooks:         hooksStr,
-			HooksHadError: hooksHadError,
-		})
-	}
-
-	sort.Slice(pReps, func(i, j int) bool {
-		return strings.Compare(pReps[i].Path, pReps[j].Path) == -1
-	})
-
-	return pReps
-}
-
-func (p *snapProgress) report() (hooksStr string, hooksHadError bool) {
-	hr := p.hookPlan.Report()
-	// FIXME: technically this belongs into client
-	// but we can't serialize hooks.Step ATM
-	rightPad := func(str string, length int, pad string) string {
-		if len(str) > length {
-			return str[:length]
-		}
-		return str + strings.Repeat(pad, length-len(str))
-	}
-	hooksHadError = hr.HadError()
-	rows := make([][]string, len(hr))
-	const numCols = 4
-	lens := make([]int, numCols)
-	for i, e := range hr {
-		rows[i] = make([]string, numCols)
-		rows[i][0] = fmt.Sprintf("%d", i+1)
-		rows[i][1] = e.Status.String()
-		runTime := "..."
-		if e.Status != hooks.StepPending {
-			runTime = e.End.Sub(e.Begin).Round(time.Millisecond).String()
-		}
-		rows[i][2] = runTime
-		rows[i][3] = ""
-		if e.Report != nil {
-			rows[i][3] = e.Report.String()
-		}
-		for j, col := range lens {
-			if len(rows[i][j]) > col {
-				lens[j] = len(rows[i][j])
-			}
-		}
-	}
-	rowsFlat := make([]string, len(hr))
-	for i, r := range rows {
-		colsPadded := make([]string, len(r))
-		for j, c := range r[:len(r)-1] {
-			colsPadded[j] = rightPad(c, lens[j], " ")
-		}
-		colsPadded[len(r)-1] = r[len(r)-1]
-		rowsFlat[i] = strings.Join(colsPadded, " ")
-	}
-	hooksStr = strings.Join(rowsFlat, "\n")
-
-	return hooksStr, hooksHadError
-}

daemon/snapper/manual.go

@@ -1,17 +0,0 @@
-package snapper
-
-import (
-	"context"
-
-	"github.com/zrepl/zrepl/daemon/job/trigger"
-)
-
-type manual struct{}
-
-func (s *manual) Run(ctx context.Context, snapshotsTaken *trigger.Manual) {
-	// nothing to do
-}
-
-func (s *manual) Report() Report {
-	return Report{Type: TypeManual, Manual: &struct{}{}}
-}

daemon/snapper/periodic.go

@@ -1,389 +0,0 @@
-package snapper
-
-import (
-	"context"
-	"fmt"
-	"sort"
-	"sync"
-	"time"
-
-	"github.com/pkg/errors"
-
-	"github.com/zrepl/zrepl/daemon/job/trigger"
-	"github.com/zrepl/zrepl/daemon/logging/trace"
-
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/hooks"
-	"github.com/zrepl/zrepl/daemon/logging"
-	"github.com/zrepl/zrepl/util/envconst"
-	"github.com/zrepl/zrepl/util/suspendresumesafetimer"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-func periodicFromConfig(g *config.Global, fsf zfs.DatasetFilter, in *config.SnapshottingPeriodic) (*Periodic, error) {
-	if in.Prefix == "" {
-		return nil, errors.New("prefix must not be empty")
-	}
-	if in.Interval.Duration() <= 0 {
-		return nil, errors.New("interval must be positive")
-	}
-
-	hookList, err := hooks.ListFromConfig(&in.Hooks)
-	if err != nil {
-		return nil, errors.Wrap(err, "hook config error")
-	}
-
-	args := periodicArgs{
-		interval: in.Interval.Duration(),
-		fsf:      fsf,
-		planArgs: planArgs{
-			prefix:          in.Prefix,
-			timestampFormat: in.TimestampFormat,
-			hooks:           hookList,
-		},
-		// ctx and log is set in Run()
-	}
-
-	return &Periodic{state: SyncUp, args: args}, nil
-}
-
-type periodicArgs struct {
-	ctx            context.Context
-	interval       time.Duration
-	fsf            zfs.DatasetFilter
-	planArgs       planArgs
-	snapshotsTaken *trigger.Manual
-	dryRun         bool
-}
-
-type Periodic struct {
-	args periodicArgs
-
-	mtx   sync.Mutex
-	state State
-
-	// set in state Plan, used in Waiting
-	lastInvocation time.Time
-
-	// valid for state Snapshotting
-	plan *plan
-
-	// 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
-	SyncUpErrWait
-	Planning
-	Snapshotting
-	Waiting
-	ErrorWait
-	Stopped
-)
-
-func (s State) sf() state {
-	m := map[State]state{
-		SyncUp:        periodicStateSyncUp,
-		SyncUpErrWait: periodicStateWait,
-		Planning:      periodicStatePlan,
-		Snapshotting:  periodicStateSnapshot,
-		Waiting:       periodicStateWait,
-		ErrorWait:     periodicStateWait,
-		Stopped:       nil,
-	}
-	return m[s]
-}
-
-type updater func(u func(*Periodic)) State
-type state func(a periodicArgs, u updater) state
-
-func (s *Periodic) Run(ctx context.Context, snapshotsTaken *trigger.Manual) {
-	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
-	getLogger(ctx).Debug("start")
-	defer getLogger(ctx).Debug("stop")
-
-	s.args.snapshotsTaken = snapshotsTaken
-	s.args.ctx = ctx
-	s.args.dryRun = false // for future expansion
-
-	u := func(u func(*Periodic)) State {
-		s.mtx.Lock()
-		defer s.mtx.Unlock()
-		if u != nil {
-			u(s)
-		}
-		return s.state
-	}
-
-	var st state = periodicStateSyncUp
-
-	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 *Periodic) {
-		s.err = err
-		preState := s.state
-		switch s.state {
-		case SyncUp:
-			s.state = SyncUpErrWait
-		case Planning:
-			fallthrough
-		case Snapshotting:
-			s.state = ErrorWait
-		}
-		getLogger(s.args.ctx).WithError(err).WithField("pre_state", preState).WithField("post_state", s.state).Error("snapshotting error")
-	}).sf()
-}
-
-func onMainCtxDone(ctx context.Context, u updater) state {
-	return u(func(s *Periodic) {
-		s.err = ctx.Err()
-		s.state = Stopped
-	}).sf()
-}
-
-func periodicStateSyncUp(a periodicArgs, u updater) state {
-	u(func(snapper *Periodic) {
-		snapper.lastInvocation = time.Now()
-	})
-	fss, err := listFSes(a.ctx, a.fsf)
-	if err != nil {
-		return onErr(err, u)
-	}
-	syncPoint, err := findSyncPoint(a.ctx, fss, a.planArgs.prefix, a.interval)
-	if err != nil {
-		return onErr(err, u)
-	}
-	u(func(s *Periodic) {
-		s.sleepUntil = syncPoint
-	})
-	ctxDone := suspendresumesafetimer.SleepUntil(a.ctx, syncPoint)
-	if ctxDone != nil {
-		return onMainCtxDone(a.ctx, u)
-	}
-	return u(func(s *Periodic) {
-		s.state = Planning
-	}).sf()
-}
-
-func periodicStatePlan(a periodicArgs, u updater) state {
-	u(func(snapper *Periodic) {
-		snapper.lastInvocation = time.Now()
-	})
-	fss, err := listFSes(a.ctx, a.fsf)
-	if err != nil {
-		return onErr(err, u)
-	}
-	p := makePlan(a.planArgs, fss)
-	return u(func(s *Periodic) {
-		s.state = Snapshotting
-		s.plan = p
-		s.err = nil
-	}).sf()
-}
-
-func periodicStateSnapshot(a periodicArgs, u updater) state {
-
-	var plan *plan
-	u(func(snapper *Periodic) {
-		plan = snapper.plan
-	})
-
-	ok := plan.execute(a.ctx, false)
-
-	a.snapshotsTaken.Fire()
-
-	return u(func(snapper *Periodic) {
-		if !ok {
-			snapper.state = ErrorWait
-			snapper.err = errors.New("one or more snapshots could not be created, check logs for details")
-		} else {
-			snapper.state = Waiting
-			snapper.err = nil
-		}
-	}).sf()
-}
-
-func periodicStateWait(a periodicArgs, u updater) state {
-	var sleepUntil time.Time
-	u(func(snapper *Periodic) {
-		lastTick := snapper.lastInvocation
-		snapper.sleepUntil = lastTick.Add(a.interval)
-		sleepUntil = snapper.sleepUntil
-		log := getLogger(a.ctx).WithField("sleep_until", sleepUntil).WithField("duration", a.interval)
-		logFunc := log.Debug
-		if snapper.state == ErrorWait || snapper.state == SyncUpErrWait {
-			logFunc = log.Error
-		}
-		logFunc("enter wait-state after error")
-	})
-
-	ctxDone := suspendresumesafetimer.SleepUntil(a.ctx, sleepUntil)
-	if ctxDone != nil {
-		return onMainCtxDone(a.ctx, u)
-	}
-	return u(func(snapper *Periodic) {
-		snapper.state = Planning
-	}).sf()
-}
-
-func listFSes(ctx context.Context, mf zfs.DatasetFilter) (fss []*zfs.DatasetPath, err error) {
-	return zfs.ZFSListMapping(ctx, mf)
-}
-
-var syncUpWarnNoSnapshotUntilSyncupMinDuration = envconst.Duration("ZREPL_SNAPPER_SYNCUP_WARN_MIN_DURATION", 1*time.Second)
-
-// see docs/snapshotting.rst
-func findSyncPoint(ctx context.Context, fss []*zfs.DatasetPath, prefix string, interval time.Duration) (syncPoint time.Time, err error) {
-
-	const (
-		prioHasVersions int = iota
-		prioNoVersions
-	)
-
-	type snapTime struct {
-		ds   *zfs.DatasetPath
-		prio int // lower is higher
-		time time.Time
-	}
-
-	if len(fss) == 0 {
-		return time.Now(), nil
-	}
-
-	snaptimes := make([]snapTime, 0, len(fss))
-	hardErrs := 0
-
-	now := time.Now()
-
-	getLogger(ctx).Debug("examine filesystem state to find sync point")
-	for _, d := range fss {
-		ctx := logging.WithInjectedField(ctx, "fs", d.ToString())
-		syncPoint, err := findSyncPointFSNextOptimalSnapshotTime(ctx, now, interval, prefix, d)
-		if err == findSyncPointFSNoFilesystemVersionsErr {
-			snaptimes = append(snaptimes, snapTime{
-				ds:   d,
-				prio: prioNoVersions,
-				time: now,
-			})
-		} else if err != nil {
-			hardErrs++
-			getLogger(ctx).WithError(err).Error("cannot determine optimal sync point for this filesystem")
-		} else {
-			getLogger(ctx).WithField("syncPoint", syncPoint).Debug("found optimal sync point for this filesystem")
-			snaptimes = append(snaptimes, snapTime{
-				ds:   d,
-				prio: prioHasVersions,
-				time: syncPoint,
-			})
-		}
-	}
-
-	if hardErrs == len(fss) {
-		return time.Time{}, fmt.Errorf("hard errors in determining sync point for every matching filesystem")
-	}
-
-	if len(snaptimes) == 0 {
-		panic("implementation error: loop must either inc hardErrs or add result to snaptimes")
-	}
-
-	// sort ascending by (prio,time)
-	// => those filesystems with versions win over those without any
-	sort.Slice(snaptimes, func(i, j int) bool {
-		if snaptimes[i].prio == snaptimes[j].prio {
-			return snaptimes[i].time.Before(snaptimes[j].time)
-		}
-		return snaptimes[i].prio < snaptimes[j].prio
-	})
-
-	winnerSyncPoint := snaptimes[0].time
-	l := getLogger(ctx).WithField("syncPoint", winnerSyncPoint.String())
-	l.Info("determined sync point")
-	if winnerSyncPoint.Sub(now) > syncUpWarnNoSnapshotUntilSyncupMinDuration {
-		for _, st := range snaptimes {
-			if st.prio == prioNoVersions {
-				l.WithField("fs", st.ds.ToString()).Warn("filesystem will not be snapshotted until sync point")
-			}
-		}
-	}
-
-	return snaptimes[0].time, nil
-
-}
-
-var findSyncPointFSNoFilesystemVersionsErr = fmt.Errorf("no filesystem versions")
-
-func findSyncPointFSNextOptimalSnapshotTime(ctx context.Context, now time.Time, interval time.Duration, prefix string, d *zfs.DatasetPath) (time.Time, error) {
-
-	fsvs, err := zfs.ZFSListFilesystemVersions(ctx, d, zfs.ListFilesystemVersionsOptions{
-		Types:           zfs.Snapshots,
-		ShortnamePrefix: prefix,
-	})
-	if err != nil {
-		return time.Time{}, errors.Wrap(err, "list filesystem versions")
-	}
-	if len(fsvs) <= 0 {
-		return time.Time{}, findSyncPointFSNoFilesystemVersionsErr
-	}
-
-	// Sort versions by creation
-	sort.SliceStable(fsvs, func(i, j int) bool {
-		return fsvs[i].CreateTXG < fsvs[j].CreateTXG
-	})
-
-	latest := fsvs[len(fsvs)-1]
-	getLogger(ctx).WithField("creation", latest.Creation).Debug("found latest snapshot")
-
-	since := now.Sub(latest.Creation)
-	if since < 0 {
-		return time.Time{}, fmt.Errorf("snapshot %q is from the future: creation=%q now=%q", latest.ToAbsPath(d), latest.Creation, now)
-	}
-
-	return latest.Creation.Add(interval), nil
-}
-
-type PeriodicReport struct {
-	State State
-	// valid in state SyncUp and Waiting
-	SleepUntil time.Time
-	// valid in state Err
-	Error string
-	// valid in state Snapshotting
-	Progress []*ReportFilesystem
-}
-
-func (s *Periodic) Report() Report {
-	s.mtx.Lock()
-	defer s.mtx.Unlock()
-
-	var progress []*ReportFilesystem = nil
-	if s.plan != nil {
-		progress = s.plan.report()
-	}
-
-	r := &PeriodicReport{
-		State:      s.state,
-		SleepUntil: s.sleepUntil,
-		Error:      errOrEmptyString(s.err),
-		Progress:   progress,
-	}
-
-	return Report{Type: TypePeriodic, Periodic: r}
-}

daemon/snapper/snapper.go

@@ -3,41 +3,497 @@ package snapper
 import (
 	"context"
 	"fmt"
+	"sort"
+	"sync"
+	"time"
+
+	"github.com/pkg/errors"
+	"github.com/zrepl/zrepl/daemon/logging/trace"
 
 	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/job/trigger"
+	"github.com/zrepl/zrepl/daemon/filters"
+	"github.com/zrepl/zrepl/daemon/hooks"
+	"github.com/zrepl/zrepl/daemon/logging"
+	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/util/envconst"
 	"github.com/zrepl/zrepl/zfs"
 )
 
-type Type string
+//go:generate stringer -type=SnapState
+type SnapState uint
 
 const (
-	TypePeriodic Type = "periodic"
-	TypeCron     Type = "cron"
-	TypeManual   Type = "manual"
+	SnapPending SnapState = 1 << iota
+	SnapStarted
+	SnapDone
+	SnapError
 )
 
-type Snapper interface {
-	Run(ctx context.Context, snapshotsTaken *trigger.Manual)
-	Report() Report
+// All fields protected by Snapper.mtx
+type snapProgress struct {
+	state SnapState
+
+	// SnapStarted, SnapDone, SnapError
+	name     string
+	startAt  time.Time
+	hookPlan *hooks.Plan
+
+	// SnapDone
+	doneAt time.Time
+
+	// SnapErr TODO disambiguate state
+	runResults hooks.PlanReport
 }
 
-type Report struct {
-	Type     Type
-	Periodic *PeriodicReport
-	Cron     *CronReport
-	Manual   *struct{}
+type args struct {
+	ctx            context.Context
+	prefix         string
+	interval       time.Duration
+	fsf            *filters.DatasetMapFilter
+	snapshotsTaken chan<- struct{}
+	hooks          *hooks.List
+	dryRun         bool
 }
 
-func FromConfig(g *config.Global, fsf zfs.DatasetFilter, in config.SnapshottingEnum) (Snapper, error) {
-	switch v := in.Ret.(type) {
-	case *config.SnapshottingPeriodic:
-		return periodicFromConfig(g, fsf, v)
-	case *config.SnapshottingCron:
-		return cronFromConfig(fsf, *v)
-	case *config.SnapshottingManual:
-		return &manual{}, nil
-	default:
-		return nil, fmt.Errorf("unknown snapshotting type %T", v)
+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
+	SyncUpErrWait
+	Planning
+	Snapshotting
+	Waiting
+	ErrorWait
+	Stopped
+)
+
+func (s State) sf() state {
+	m := map[State]state{
+		SyncUp:        syncUp,
+		SyncUpErrWait: wait,
+		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 Logger = logger.Logger
+
+func getLogger(ctx context.Context) Logger {
+	return logging.GetLogger(ctx, logging.SubsysSnapshot)
+}
+
+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")
+	}
+
+	hookList, err := hooks.ListFromConfig(&in.Hooks)
+	if err != nil {
+		return nil, errors.Wrap(err, "hook config error")
+	}
+
+	args := args{
+		prefix:   in.Prefix,
+		interval: in.Interval,
+		fsf:      fsf,
+		hooks:    hookList,
+		// ctx and log is set in Run()
+	}
+
+	return &Snapper{state: SyncUp, args: args}, nil
+}
+
+func (s *Snapper) Run(ctx context.Context, snapshotsTaken chan<- struct{}) {
+	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
+	getLogger(ctx).Debug("start")
+	defer getLogger(ctx).Debug("stop")
+
+	s.args.snapshotsTaken = snapshotsTaken
+	s.args.ctx = ctx
+	s.args.dryRun = false // for future expansion
+
+	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
+		preState := s.state
+		switch s.state {
+		case SyncUp:
+			s.state = SyncUpErrWait
+		case Planning:
+			fallthrough
+		case Snapshotting:
+			s.state = ErrorWait
+		}
+		getLogger(s.args.ctx).WithError(err).WithField("pre_state", preState).WithField("post_state", s.state).Error("snapshotting error")
+	}).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 {
+	u(func(snapper *Snapper) {
+		snapper.lastInvocation = time.Now()
+	})
+	fss, err := listFSes(a.ctx, a.fsf)
+	if err != nil {
+		return onErr(err, u)
+	}
+	syncPoint, err := findSyncPoint(a.ctx, fss, a.prefix, a.interval)
+	if err != nil {
+		return onErr(err, u)
+	}
+	u(func(s *Snapper) {
+		s.sleepUntil = syncPoint
+	})
+	t := time.NewTimer(time.Until(syncPoint))
+	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.ctx, 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
+		s.err = nil
+	}).sf()
+}
+
+func snapshot(a args, u updater) state {
+
+	var plan map[*zfs.DatasetPath]*snapProgress
+	u(func(snapper *Snapper) {
+		plan = snapper.plan
+	})
+
+	hookMatchCount := make(map[hooks.Hook]int, len(*a.hooks))
+	for _, h := range *a.hooks {
+		hookMatchCount[h] = 0
+	}
+
+	anyFsHadErr := 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)
+
+		ctx := logging.WithInjectedField(a.ctx, "fs", fs.ToString())
+		ctx = logging.WithInjectedField(ctx, "snap", snapname)
+
+		hookEnvExtra := hooks.Env{
+			hooks.EnvFS:       fs.ToString(),
+			hooks.EnvSnapshot: snapname,
+		}
+
+		jobCallback := hooks.NewCallbackHookForFilesystem("snapshot", fs, func(ctx context.Context) (err error) {
+			l := getLogger(ctx)
+			l.Debug("create snapshot")
+			err = zfs.ZFSSnapshot(ctx, fs, snapname, false) // TODO propagate context to ZFSSnapshot
+			if err != nil {
+				l.WithError(err).Error("cannot create snapshot")
+			}
+			return
+		})
+
+		fsHadErr := false
+		var planReport hooks.PlanReport
+		var plan *hooks.Plan
+		{
+			filteredHooks, err := a.hooks.CopyFilteredForFilesystem(fs)
+			if err != nil {
+				getLogger(ctx).WithError(err).Error("unexpected filter error")
+				fsHadErr = true
+				goto updateFSState
+			}
+			// account for running hooks
+			for _, h := range filteredHooks {
+				hookMatchCount[h] = hookMatchCount[h] + 1
+			}
+
+			var planErr error
+			plan, planErr = hooks.NewPlan(&filteredHooks, hooks.PhaseSnapshot, jobCallback, hookEnvExtra)
+			if planErr != nil {
+				fsHadErr = true
+				getLogger(ctx).WithError(planErr).Error("cannot create job hook plan")
+				goto updateFSState
+			}
+		}
+		u(func(snapper *Snapper) {
+			progress.name = snapname
+			progress.startAt = time.Now()
+			progress.hookPlan = plan
+			progress.state = SnapStarted
+		})
+		{
+			getLogger(ctx).WithField("report", plan.Report().String()).Debug("begin run job plan")
+			plan.Run(ctx, a.dryRun)
+			planReport = plan.Report()
+			fsHadErr = planReport.HadError() // not just fatal errors
+			if fsHadErr {
+				getLogger(ctx).WithField("report", planReport.String()).Error("end run job plan with error")
+			} else {
+				getLogger(ctx).WithField("report", planReport.String()).Info("end run job plan successful")
+			}
+		}
+
+	updateFSState:
+		anyFsHadErr = anyFsHadErr || fsHadErr
+		u(func(snapper *Snapper) {
+			progress.doneAt = time.Now()
+			progress.state = SnapDone
+			if fsHadErr {
+				progress.state = SnapError
+			}
+			progress.runResults = planReport
+		})
+	}
+
+	select {
+	case a.snapshotsTaken <- struct{}{}:
+	default:
+		if a.snapshotsTaken != nil {
+			getLogger(a.ctx).Warn("callback channel is full, discarding snapshot update event")
+		}
+	}
+
+	for h, mc := range hookMatchCount {
+		if mc == 0 {
+			hookIdx := -1
+			for idx, ah := range *a.hooks {
+				if ah == h {
+					hookIdx = idx
+					break
+				}
+			}
+			getLogger(a.ctx).WithField("hook", h.String()).WithField("hook_number", hookIdx+1).Warn("hook did not match any snapshotted filesystems")
+		}
+	}
+
+	return u(func(snapper *Snapper) {
+		if anyFsHadErr {
+			snapper.state = ErrorWait
+			snapper.err = errors.New("one or more snapshots could not be created, check logs for details")
+		} else {
+			snapper.state = Waiting
+			snapper.err = nil
+		}
+	}).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
+		log := getLogger(a.ctx).WithField("sleep_until", sleepUntil).WithField("duration", a.interval)
+		logFunc := log.Debug
+		if snapper.state == ErrorWait || snapper.state == SyncUpErrWait {
+			logFunc = log.Error
+		}
+		logFunc("enter wait-state after error")
+	})
+
+	t := time.NewTimer(time.Until(sleepUntil))
+	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(ctx context.Context, mf *filters.DatasetMapFilter) (fss []*zfs.DatasetPath, err error) {
+	return zfs.ZFSListMapping(ctx, mf)
+}
+
+var syncUpWarnNoSnapshotUntilSyncupMinDuration = envconst.Duration("ZREPL_SNAPPER_SYNCUP_WARN_MIN_DURATION", 1*time.Second)
+
+// see docs/snapshotting.rst
+func findSyncPoint(ctx context.Context, fss []*zfs.DatasetPath, prefix string, interval time.Duration) (syncPoint time.Time, err error) {
+
+	const (
+		prioHasVersions int = iota
+		prioNoVersions
+	)
+
+	type snapTime struct {
+		ds   *zfs.DatasetPath
+		prio int // lower is higher
+		time time.Time
+	}
+
+	if len(fss) == 0 {
+		return time.Now(), nil
+	}
+
+	snaptimes := make([]snapTime, 0, len(fss))
+	hardErrs := 0
+
+	now := time.Now()
+
+	getLogger(ctx).Debug("examine filesystem state to find sync point")
+	for _, d := range fss {
+		ctx := logging.WithInjectedField(ctx, "fs", d.ToString())
+		syncPoint, err := findSyncPointFSNextOptimalSnapshotTime(ctx, now, interval, prefix, d)
+		if err == findSyncPointFSNoFilesystemVersionsErr {
+			snaptimes = append(snaptimes, snapTime{
+				ds:   d,
+				prio: prioNoVersions,
+				time: now,
+			})
+		} else if err != nil {
+			hardErrs++
+			getLogger(ctx).WithError(err).Error("cannot determine optimal sync point for this filesystem")
+		} else {
+			getLogger(ctx).WithField("syncPoint", syncPoint).Debug("found optimal sync point for this filesystem")
+			snaptimes = append(snaptimes, snapTime{
+				ds:   d,
+				prio: prioHasVersions,
+				time: syncPoint,
+			})
+		}
+	}
+
+	if hardErrs == len(fss) {
+		return time.Time{}, fmt.Errorf("hard errors in determining sync point for every matching filesystem")
+	}
+
+	if len(snaptimes) == 0 {
+		panic("implementation error: loop must either inc hardErrs or add result to snaptimes")
+	}
+
+	// sort ascending by (prio,time)
+	// => those filesystems with versions win over those without any
+	sort.Slice(snaptimes, func(i, j int) bool {
+		if snaptimes[i].prio == snaptimes[j].prio {
+			return snaptimes[i].time.Before(snaptimes[j].time)
+		}
+		return snaptimes[i].prio < snaptimes[j].prio
+	})
+
+	winnerSyncPoint := snaptimes[0].time
+	l := getLogger(ctx).WithField("syncPoint", winnerSyncPoint.String())
+	l.Info("determined sync point")
+	if winnerSyncPoint.Sub(now) > syncUpWarnNoSnapshotUntilSyncupMinDuration {
+		for _, st := range snaptimes {
+			if st.prio == prioNoVersions {
+				l.WithField("fs", st.ds.ToString()).Warn("filesystem will not be snapshotted until sync point")
+			}
+		}
+	}
+
+	return snaptimes[0].time, nil
+
+}
+
+var findSyncPointFSNoFilesystemVersionsErr = fmt.Errorf("no filesystem versions")
+
+func findSyncPointFSNextOptimalSnapshotTime(ctx context.Context, now time.Time, interval time.Duration, prefix string, d *zfs.DatasetPath) (time.Time, error) {
+
+	fsvs, err := zfs.ZFSListFilesystemVersions(ctx, d, zfs.ListFilesystemVersionsOptions{
+		Types:           zfs.Snapshots,
+		ShortnamePrefix: prefix,
+	})
+	if err != nil {
+		return time.Time{}, errors.Wrap(err, "list filesystem versions")
+	}
+	if len(fsvs) <= 0 {
+		return time.Time{}, findSyncPointFSNoFilesystemVersionsErr
+	}
+
+	// Sort versions by creation
+	sort.SliceStable(fsvs, func(i, j int) bool {
+		return fsvs[i].CreateTXG < fsvs[j].CreateTXG
+	})
+
+	latest := fsvs[len(fsvs)-1]
+	getLogger(ctx).WithField("creation", latest.Creation).Debug("found latest snapshot")
+
+	since := now.Sub(latest.Creation)
+	if since < 0 {
+		return time.Time{}, fmt.Errorf("snapshot %q is from the future: creation=%q now=%q", latest.ToAbsPath(d), latest.Creation, now)
+	}
+
+	return latest.Creation.Add(interval), nil
+}

daemon/snapper/snapper_all.go

@@ -0,0 +1,48 @@
+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)
+	}
+}
+
+// Returns nil if manual
+func (s *PeriodicOrManual) Report() *Report {
+	if s.s != nil {
+		return s.s.Report()
+	}
+	return nil
+}
+
+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/snapper_report.go

@@ -0,0 +1,118 @@
+package snapper
+
+import (
+	"fmt"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/zrepl/zrepl/daemon/hooks"
+)
+
+type Report struct {
+	State State
+	// valid in state SyncUp and Waiting
+	SleepUntil time.Time
+	// valid in state Err
+	Error string
+	// valid in state Snapshotting
+	Progress []*ReportFilesystem
+}
+
+type ReportFilesystem struct {
+	Path  string
+	State SnapState
+
+	// Valid in SnapStarted and later
+	SnapName      string
+	StartAt       time.Time
+	Hooks         string
+	HooksHadError bool
+
+	// Valid in SnapDone | SnapError
+	DoneAt time.Time
+}
+
+func errOrEmptyString(e error) string {
+	if e != nil {
+		return e.Error()
+	}
+	return ""
+}
+
+func (s *Snapper) Report() *Report {
+	s.mtx.Lock()
+	defer s.mtx.Unlock()
+
+	pReps := make([]*ReportFilesystem, 0, len(s.plan))
+	for fs, p := range s.plan {
+		var hooksStr string
+		var hooksHadError bool
+		if p.hookPlan != nil {
+			hr := p.hookPlan.Report()
+			// FIXME: technically this belongs into client
+			// but we can't serialize hooks.Step ATM
+			rightPad := func(str string, length int, pad string) string {
+				if len(str) > length {
+					return str[:length]
+				}
+				return str + strings.Repeat(pad, length-len(str))
+			}
+			hooksHadError = hr.HadError()
+			rows := make([][]string, len(hr))
+			const numCols = 4
+			lens := make([]int, numCols)
+			for i, e := range hr {
+				rows[i] = make([]string, numCols)
+				rows[i][0] = fmt.Sprintf("%d", i+1)
+				rows[i][1] = e.Status.String()
+				runTime := "..."
+				if e.Status != hooks.StepPending {
+					runTime = e.End.Sub(e.Begin).Round(time.Millisecond).String()
+				}
+				rows[i][2] = runTime
+				rows[i][3] = ""
+				if e.Report != nil {
+					rows[i][3] = e.Report.String()
+				}
+				for j, col := range lens {
+					if len(rows[i][j]) > col {
+						lens[j] = len(rows[i][j])
+					}
+				}
+			}
+			rowsFlat := make([]string, len(hr))
+			for i, r := range rows {
+				colsPadded := make([]string, len(r))
+				for j, c := range r[:len(r)-1] {
+					colsPadded[j] = rightPad(c, lens[j], " ")
+				}
+				colsPadded[len(r)-1] = r[len(r)-1]
+				rowsFlat[i] = strings.Join(colsPadded, " ")
+			}
+			hooksStr = strings.Join(rowsFlat, "\n")
+		}
+		pReps = append(pReps, &ReportFilesystem{
+			Path:          fs.ToString(),
+			State:         p.state,
+			SnapName:      p.name,
+			StartAt:       p.startAt,
+			DoneAt:        p.doneAt,
+			Hooks:         hooksStr,
+			HooksHadError: hooksHadError,
+		})
+	}
+
+	sort.Slice(pReps, func(i, j int) bool {
+		return strings.Compare(pReps[i].Path, pReps[j].Path) == -1
+	})
+
+	r := &Report{
+		State:      s.state,
+		SleepUntil: s.sleepUntil,
+		Error:      errOrEmptyString(s.err),
+		Progress:   pReps,
+	}
+
+	return r
+}

daemon/snapper/util.go

@@ -1,21 +0,0 @@
-package snapper
-
-import (
-	"context"
-
-	"github.com/zrepl/zrepl/daemon/logging"
-	"github.com/zrepl/zrepl/logger"
-)
-
-type Logger = logger.Logger
-
-func getLogger(ctx context.Context) Logger {
-	return logging.GetLogger(ctx, logging.SubsysSnapshot)
-}
-
-func errOrEmptyString(e error) string {
-	if e != nil {
-		return e.Error()
-	}
-	return ""
-}

debian

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

dist/grafana/grafana-prometheus-zrepl-0.1.json

@@ -0,0 +1,595 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "$$hashKey": "object:3351",
+        "builtIn": 1,
+        "datasource": "-- Grafana --",
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "gnetId": null,
+  "graphTooltip": 1,
+  "id": 7,
+  "iteration": 1552746418826,
+  "links": [],
+  "panels": [
+    {
+      "content": "# zrepl Prometheus Metrics\n\nzrepl exposes Prometheus metrics and ships with this Grafana dashboard.\nThe exported metrics are suitable for health checks:\n\n* The log should generally be warning & error-free\n  * The `Log Messages that require attention` graph visualizes log message counts indicating problems.\n* The number of goroutines should not grow unboundedly over time.\n  * During replication, the number of goroutines can be way higher than during idle time.\n  * If the goroutine count grows with each replication, there is clearly a goroutine leak. Please open a bug report.\n* The sys memory consumption should not grow unboundedly over time.\n  * Note that the Go runtime pre-allocates some of its heap from the OS.\n  * zrepl actually uses much less memory than allocated from the OS.\n  * Since Go 1.11, Go pre-allocates more aggressively.\n* Monitor that some data is replicated, although that metric does not guarantee that replication was successful.\n\n**In general, note that the exported metrics are not stable unless declared otherwise.**",
+      "gridPos": {
+        "h": 9,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 35,
+      "mode": "markdown",
+      "title": "Panel Title",
+      "type": "text"
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": null,
+      "fill": 1,
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 9
+      },
+      "id": 15,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": true,
+      "steppedLine": false,
+      "targets": [
+        {
+          "$$hashKey": "object:3436",
+          "expr": "up{job='$prom_job_name'}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "zrepl Instances Up",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": "5",
+          "min": "0",
+          "show": true
+        },
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ]
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": null,
+      "fill": 1,
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 9
+      },
+      "id": 22,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "expr": "increase(zrepl_daemon_log_entries{job='$prom_job_name',level=~'warn|error'}[$__interval])",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "Log Messages that require attention",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": "0",
+          "show": true
+        },
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ]
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": null,
+      "fill": 1,
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 18
+      },
+      "id": 33,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [
+        {
+          "alias": "/replicated bytes in last.*/",
+          "yaxis": 2
+        }
+      ],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "expr": "sum(rate(zrepl_replication_bytes_replicated{job='$prom_job_name'}[$__interval])) by (zrepl_job)",
+          "format": "time_series",
+          "hide": false,
+          "interval": "",
+          "intervalFactor": 1,
+          "legendFormat": "replication data rate zrepl_job={{zrepl_job}}",
+          "refId": "A"
+        },
+        {
+          "expr": "sum(increase(zrepl_replication_bytes_replicated{job='$prom_job_name'}[10m])) by (zrepl_job)",
+          "format": "time_series",
+          "hide": false,
+          "interval": "",
+          "intervalFactor": 1,
+          "legendFormat": "replicated bytes in last 10min zrepl_job={{zrepl_job}}",
+          "refId": "B"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "Replication Data Rate and Volume(integrates last 10min)",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "Bps",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "format": "bytes",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ]
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": null,
+      "fill": 1,
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 18
+      },
+      "id": 23,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "expr": "sum(increase(zrepl_daemon_log_entries{job='$prom_job_name',zrepl_job=~\"^[^_].*\"}[$__interval])) by (instance,zrepl_job)",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "Log Activity (without internal jobs)",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": "0",
+          "show": true
+        },
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ]
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": null,
+      "fill": 1,
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 27
+      },
+      "id": 17,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "$$hashKey": "object:3535",
+          "expr": "go_memstats_sys_bytes{job='$prom_job_name'}",
+          "format": "time_series",
+          "hide": false,
+          "intervalFactor": 1,
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "Memory Allocated by the Go runtime from the OS (should not grow unboundedly)",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "bytes",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": "0",
+          "show": true
+        },
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ]
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": null,
+      "fill": 1,
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 27
+      },
+      "id": 19,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "links": [],
+      "nullPointMode": "null",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "expr": "go_goroutines{job='$prom_job_name'}",
+          "format": "time_series",
+          "intervalFactor": 1,
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "number of goroutines (should not grow unboundedly)",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": "0",
+          "show": true
+        },
+        {
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        }
+      ]
+    }
+  ],
+  "refresh": "1m",
+  "schemaVersion": 16,
+  "style": "dark",
+  "tags": [],
+  "templating": {
+    "list": [
+      {
+        "allValue": null,
+        "current": {
+          "text": "zrepl",
+          "value": "zrepl"
+        },
+        "datasource": "prometheus",
+        "hide": 0,
+        "includeAll": false,
+        "label": "Prometheus Job Name",
+        "multi": false,
+        "name": "prom_job_name",
+        "options": [],
+        "query": "label_values(up, job)",
+        "refresh": 1,
+        "regex": "",
+        "sort": 1,
+        "tagValuesQuery": "",
+        "tags": [],
+        "tagsQuery": "",
+        "type": "query",
+        "useTags": false
+      }
+    ]
+  },
+  "time": {
+    "from": "now-2d",
+    "to": "now"
+  },
+  "timepicker": {
+    "refresh_intervals": [
+      "5s",
+      "10s",
+      "30s",
+      "1m",
+      "5m",
+      "15m",
+      "30m",
+      "1h",
+      "2h",
+      "1d"
+    ],
+    "time_options": [
+      "5m",
+      "15m",
+      "1h",
+      "6h",
+      "12h",
+      "24h",
+      "2d",
+      "7d",
+      "30d"
+    ]
+  },
+  "timezone": "",
+  "title": "zrepl 0.1",
+  "uid": "xTljn4qmk",
+  "version": 6
+}

dist/openrc/zrepl

@@ -1,23 +0,0 @@
-#!/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

@@ -9,9 +9,6 @@ ExecStart=/usr/local/bin/zrepl --config /etc/zrepl/zrepl.yml daemon
 RuntimeDirectory=zrepl zrepl/stdinserver
 RuntimeDirectoryMode=0700
 
-# Make Go produce coredumps
-Environment=GOTRACEBACK='crash'
-
 ProtectSystem=strict
 #PrivateDevices=yes # TODO ZFS needs access to /dev/zfs, could we limit this?
 ProtectKernelTunables=yes
@@ -30,8 +27,7 @@ ProtectHome=read-only
 # SystemCallFilter
 #   ~@privileged doesn't work with Ubuntu 18.04 ssh
 SystemCallFilter=~ @mount @cpu-emulation @keyring @module @obsolete @raw-io @debug @clock @resources
-# Go1.19 added automatic RLIMIT_NOFILE changes, so, we need to allow that
-SystemCallFilter= setrlimit
+
 
 [Install]
 WantedBy=multi-user.target

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)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" -c sphinxconf $(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)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" -c sphinxconf $(SPHINXOPTS) $(O)

docs/_static/banner.css

@@ -1,43 +0,0 @@
-/* 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

@@ -1,17 +0,0 @@
-{% extends "!page.html" %}
-{% block body %}
-{% if current_version and latest_version and current_version != latest_version %}
-<p class="scv-banner scv-sphinx_rtd_theme">
-  <strong>
-    {% if current_version.is_released %}
-    You're reading an old version of this documentation.
-    If you want up-to-date information, please have a look at <a href="{{ vpathto(latest_version.name) }}">{{latest_version.name}}</a>.
-    {% else %}
-    You're reading the documentation for a development version.
-    For the latest released version, please have a look at <a href="{{ vpathto(latest_version.name) }}">{{latest_version.name}}</a>.
-    {% endif %}
-  </strong>
-</p>
-{% endif %}
-{{ super() }}
-{% endblock %}%

docs/_templates/versions.html

@@ -1,27 +0,0 @@
-{%- if current_version %}
-<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: {{ current_version.name }}
-    <span class="fa fa-caret-down"></span>
-  </span>
-  <div class="rst-other-versions">
-    {%- if versions.tags %}
-    <dl>
-      <dt>Tags</dt>
-      {%- for item in versions.tags %}
-      <dd><a href="{{ item.url }}">{{ item.name }}</a></dd>
-      {%- endfor %}
-    </dl>
-    {%- endif %}
-    {%- if versions.branches %}
-    <dl>
-      <dt>Branches</dt>
-      {%- for item in versions.branches %}
-      <dd><a href="{{ item.url }}">{{ item.name }}</a></dd>
-      {%- endfor %}
-    </dl>
-    {%- endif %}
-  </div>
-</div>
-{%- endif %}

docs/changelog.rst

@@ -6,7 +6,6 @@
 .. |docs| replace:: [DOCS]
 .. |feature| replace:: [FEATURE]
 .. |mig| replace:: **[MIGRATION]**
-.. |maint| replace:: [MAINT]
 
 .. _changelog:
 
@@ -16,165 +15,17 @@ 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.
 
-Next Release
-------------
+We use the following annotations for classifying changes:
 
-The plan for the next release is to revisit how zrepl does snapshot management.
-High-level goals:
-
-- 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.
-
-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
-
-.. 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
----
-
-* |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:
+* |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.
+* |mig| Migration that must be run by the user.
+* |feature| Change that introduces new functionality.
+* |bugfix| Change that fixes a bug, no regressions or incompatibilities expected.
+* |docs| Change to the documentation.
 
 0.3
 ---
@@ -183,38 +34,27 @@ This is a big one! Headlining features:
 
 * **Resumable Send & Recv Support**
   No knobs required, automatically used where supported.
+* **Hold-Protected Send & Recv**
+  Automatic ZFS holds to ensure that we can always use resumable send&recv for a replication step.
 * **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.
+* **Receive-side hold on last received dataset**
+  The counterpart to the replication cursor bookmark on the send-side.
+  Ensures that incremental replication will always be possible between a sender and receiver.
 
 .. 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.
+   We highly recommend studying the :ref:`overview section of the configuration chapter <overview-how-replication-works>` to understand how replication works.
 
 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>`).
+  Starting with this version, job names are going to be embedded into ZFS holds and bookmark names (see :ref:`here<replication-cursor-and-last-received-hold>` and :ref:`here<step-holds-and-bookmarks>`).
   Therefore you might need to adjust your job names.
-  **Note that jobs** cannot be renamed easily **once you start using zrepl 0.3.**
+  **Note that jobs** :issue:`cannot be renamed easily<327>` **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.
+  * zrepl now manages the :ref:`replication cursor bookmark <replication-cursor-and-last-received-hold>` 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.
@@ -222,12 +62,11 @@ Additional changelog:
     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| :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| :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` )
+* |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
@@ -238,6 +77,13 @@ Additional changelog:
 * **[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.
 
+.. 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 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>`_.
+
 0.2.1
 -----
 
@@ -339,7 +185,7 @@ Changes
 * |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``.

docs/conf.py

@@ -1,187 +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',
-    "sphinx_multiversion",
-]
-
-# 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 = '2017-2023, 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 = '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']
-
-# 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/config/samples%s', 'config/samples%s'),
-    'commit':('https://github.com/zrepl/zrepl/commit/%s', 'commit %s'),
-        }
-

docs/conf.py

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

docs/configuration.rst

@@ -12,8 +12,6 @@ Configuration
     configuration/transports
     configuration/filter_syntax
     configuration/sendrecvoptions
-    configuration/replication
-    configuration/conflict_resolution
     configuration/snapshotting
     configuration/prune
     configuration/logging

docs/configuration/conflict_resolution.rst

@@ -1,37 +0,0 @@
-.. 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/jobs.rst

@@ -30,10 +30,6 @@ Job Type ``push``
       - |snapshotting-spec|
     * - ``pruning``
       - |pruning-spec|
-    * - ``replication``
-      - |replication-options|
-    * - ``conflict_resolution``
-      - |conflict-resolution-options|
 
 Example config: :sampleconf:`/push.yml`
 
@@ -85,10 +81,6 @@ Job Type ``pull``
         | ``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`
 

docs/configuration/misc.rst

@@ -1,5 +1,3 @@
-.. _miscellaneous:
-
 Miscellaneous
 =============
 
@@ -44,3 +42,27 @@ 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.