address updated golangci-lint errors: S1011 (gosimple)

should replace loop with `copy.outs[level] = append(copy.outs[level], os.outs[level]...)` (gosimple)

.circleci/config.yml

@@ -0,0 +1,296 @@
+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:
+    steps:
+      - run:
+          shell: /bin/bash -euo pipefail
+          command: |
+            mkdir -p "$HOME/.local/bin"
+            line='export PATH="$HOME/.local/bin:$PATH"'
+            if grep "$line" $BASH_ENV >/dev/null; then
+              echo "$line" >> $BASH_ENV
+            fi
+
+  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"
+
+      # 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:
+    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
+
+  quickcheck-go:
+    parameters:
+      goversion:
+        type: string
+      goos:
+        type: string
+      goarch:
+        type: string
+    docker:
+      - image: cimg/go:<<parameters.goversion>>
+    environment:
+      GOOS: <<parameters.goos>>
+      GOARCH: <<parameters.goarch>>
+
+    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: .
+      - store_artifacts:
+          path: artifacts
+
+  publish-zrepl-github-io:
+    docker:
+      - image: cimg/base:2023.09
+    steps:
+      - checkout
+      - install-docdep
+      - docs-publish-sh:
+          push: true

.circleci/trigger_debian_binary_packaging_workflow.bash

@@ -0,0 +1,10 @@
+#!/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

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

.golangci.yml

@@ -0,0 +1,16 @@
+linters:
+  enable:
+  - goimports
+
+issues:
+  exclude-rules:
+    - 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:"
+

Gopkg.lock

@@ -1,313 +0,0 @@
-# This file is autogenerated, do not edit; changes may be undone by the next 'dep ensure'.
-
-
-[[projects]]
-  branch = "master"
-  digest = "1:c0bec5f9b98d0bc872ff5e834fac186b807b656683bd29cb82fb207a1513fabb"
-  name = "github.com/beorn7/perks"
-  packages = ["quantile"]
-  pruneopts = ""
-  revision = "3a771d992973f24aa725d07868b467d1ddfceafb"
-
-[[projects]]
-  digest = "1:56c130d885a4aacae1dd9c7b71cfe39912c7ebc1ff7d2b46083c8812996dc43b"
-  name = "github.com/davecgh/go-spew"
-  packages = ["spew"]
-  pruneopts = ""
-  revision = "346938d642f2ec3594ed81d874461961cd0faa76"
-  version = "v1.1.0"
-
-[[projects]]
-  digest = "1:e988ed0ca0d81f4d28772760c02ee95084961311291bdfefc1b04617c178b722"
-  name = "github.com/fatih/color"
-  packages = ["."]
-  pruneopts = ""
-  revision = "5b77d2a35fb0ede96d138fc9a99f5c9b6aef11b4"
-  version = "v1.7.0"
-
-[[projects]]
-  branch = "master"
-  digest = "1:5d0a2385edf4ba44f3b7b76bc0436ceb8f62bf55aa5d540a9eb9ec6c58d86809"
-  name = "github.com/ftrvxmtrx/fd"
-  packages = ["."]
-  pruneopts = ""
-  revision = "c6d800382fff6dc1412f34269f71b7f83bd059ad"
-
-[[projects]]
-  branch = "master"
-  digest = "1:4416ad04caf950d004921268f777e418f8c328080ccf6a91e799f977dc128808"
-  name = "github.com/gdamore/encoding"
-  packages = ["."]
-  pruneopts = ""
-  revision = "b23993cbb6353f0e6aa98d0ee318a34728f628b9"
-
-[[projects]]
-  digest = "1:d8088c614a5bffaf38a40c116226e7d230750bafb77942dca25eab779ceeaf1f"
-  name = "github.com/gdamore/tcell"
-  packages = [
-    ".",
-    "termbox",
-    "terminfo",
-  ]
-  pruneopts = ""
-  revision = "de7e78efa4a71b3f36c7154989c529dbdf9ae623"
-  version = "v1.1.0"
-
-[[projects]]
-  digest = "1:6a4a01d58b227c4b6b11111b9f172ec5c17682b82724e58e6daf3f19f4faccd8"
-  name = "github.com/go-logfmt/logfmt"
-  packages = ["."]
-  pruneopts = ""
-  revision = "390ab7935ee28ec6b286364bba9b4dd6410cb3d5"
-  version = "v0.3.0"
-
-[[projects]]
-  digest = "1:3dd078fda7500c341bc26cfbc6c6a34614f295a2457149fc1045cab767cbcf18"
-  name = "github.com/golang/protobuf"
-  packages = ["proto"]
-  pruneopts = ""
-  revision = "aa810b61a9c79d51363740d207bb46cf8e620ed5"
-  version = "v1.2.0"
-
-[[projects]]
-  branch = "master"
-  digest = "1:cb09475f771b9167fb9333629f5d6a7161572602ea040f1094602b0dc8709878"
-  name = "github.com/jinzhu/copier"
-  packages = ["."]
-  pruneopts = ""
-  revision = "db4671f3a9b8df855e993f7c94ec5ef1ffb0a23b"
-
-[[projects]]
-  branch = "master"
-  digest = "1:1ed9eeebdf24aadfbca57eb50e6455bd1d2474525e0f0d4454de8c8e9bc7ee9a"
-  name = "github.com/kr/logfmt"
-  packages = ["."]
-  pruneopts = ""
-  revision = "b84e30acd515aadc4b783ad4ff83aff3299bdfe0"
-
-[[projects]]
-  branch = "master"
-  digest = "1:591a2778aa6e896980757ea87e659b3aa13d8c0e790310614028463a31c0998b"
-  name = "github.com/kr/pretty"
-  packages = ["."]
-  pruneopts = ""
-  revision = "cfb55aafdaf3ec08f0db22699ab822c50091b1c4"
-
-[[projects]]
-  branch = "master"
-  digest = "1:109e0a9b9e74c5c8adf94a2dc4dd4a9ca2a183d4d87ffecd4e62db69a5ede55a"
-  name = "github.com/kr/text"
-  packages = ["."]
-  pruneopts = ""
-  revision = "7cafcd837844e784b526369c9bce262804aebc60"
-
-[[projects]]
-  digest = "1:863ba095ae0954100963826333bd1503c169424bb798d9ce800d9f6651f4c234"
-  name = "github.com/lucasb-eyer/go-colorful"
-  packages = ["."]
-  pruneopts = ""
-  revision = "345fbb3dbcdb252d9985ee899a84963c0fa24c82"
-  version = "v1.0"
-
-[[projects]]
-  digest = "1:9ea83adf8e96d6304f394d40436f2eb44c1dc3250d223b74088cc253a6cd0a1c"
-  name = "github.com/mattn/go-colorable"
-  packages = ["."]
-  pruneopts = ""
-  revision = "167de6bfdfba052fa6b2d3664c8f5272e23c9072"
-  version = "v0.0.9"
-
-[[projects]]
-  digest = "1:78229b46ddb7434f881390029bd1af7661294af31f6802e0e1bedaad4ab0af3c"
-  name = "github.com/mattn/go-isatty"
-  packages = ["."]
-  pruneopts = ""
-  revision = "0360b2af4f38e8d38c7fce2a9f4e702702d73a39"
-  version = "v0.0.3"
-
-[[projects]]
-  digest = "1:82b912465c1da0668582a7d1117339c278e786c2536b3c3623029a0c7141c2d0"
-  name = "github.com/mattn/go-runewidth"
-  packages = ["."]
-  pruneopts = ""
-  revision = "ce7b0b5c7b45a81508558cd1dba6bb1e4ddb51bb"
-  version = "v0.0.3"
-
-[[projects]]
-  digest = "1:4c23ced97a470b17d9ffd788310502a077b9c1f60221a85563e49696276b4147"
-  name = "github.com/matttproud/golang_protobuf_extensions"
-  packages = ["pbutil"]
-  pruneopts = ""
-  revision = "3247c84500bff8d9fb6d579d800f20b3e091582c"
-  version = "v1.0.0"
-
-[[projects]]
-  digest = "1:7365acd48986e205ccb8652cc746f09c8b7876030d53710ea6ef7d0bd0dcd7ca"
-  name = "github.com/pkg/errors"
-  packages = ["."]
-  pruneopts = ""
-  revision = "645ef00459ed84a119197bfb8d8205042c6df63d"
-  version = "v0.8.0"
-
-[[projects]]
-  digest = "1:256484dbbcd271f9ecebc6795b2df8cad4c458dd0f5fd82a8c2fa0c29f233411"
-  name = "github.com/pmezard/go-difflib"
-  packages = ["difflib"]
-  pruneopts = ""
-  revision = "792786c7400a136282c1664665ae0a8db921c6c2"
-  version = "v1.0.0"
-
-[[projects]]
-  branch = "master"
-  digest = "1:1392748e290ca66ac8447ef24961f8ae9e1d846a53af0f58a5a0256982ce0577"
-  name = "github.com/problame/go-netssh"
-  packages = ["."]
-  pruneopts = ""
-  revision = "c56ad38d2c91397ad3c8dd9443d7448e328a9e9e"
-
-[[projects]]
-  branch = "master"
-  digest = "1:8c63c44f018bd52b03ebad65c9df26aabbc6793138e421df1c8c84c285a45bc6"
-  name = "github.com/problame/go-rwccmd"
-  packages = ["."]
-  pruneopts = ""
-  revision = "391d2c78c8404a9683d79f75dd24ab53040f89f7"
-
-[[projects]]
-  digest = "1:c2ba1c9dc003c15856e4529dac028cacba08ee8924300f058b3467cde9acf7a9"
-  name = "github.com/problame/go-streamrpc"
-  packages = [
-    ".",
-    "internal/pdu",
-  ]
-  pruneopts = ""
-  revision = "de6f6a4041c77f700f02d8fe749e54efa50811f7"
-  version = "v0.4"
-
-[[projects]]
-  branch = "master"
-  digest = "1:ebf8ffdde9bdbf9c83e22121875c68c01d821776523546554b2a3ff6f72773ab"
-  name = "github.com/prometheus/client_golang"
-  packages = [
-    "prometheus",
-    "prometheus/promhttp",
-  ]
-  pruneopts = ""
-  revision = "e11c6ff8170beca9d5fd8b938e71165eeec53ac6"
-
-[[projects]]
-  branch = "master"
-  digest = "1:60aca47f4eeeb972f1b9da7e7db51dee15ff6c59f7b401c1588b8e6771ba15ef"
-  name = "github.com/prometheus/client_model"
-  packages = ["go"]
-  pruneopts = ""
-  revision = "99fa1f4be8e564e8a6b613da7fa6f46c9edafc6c"
-
-[[projects]]
-  branch = "master"
-  digest = "1:af21ee3e0a8212f17bb317cd7237f9920bcb2641a291ac111f30f63b3cab817f"
-  name = "github.com/prometheus/common"
-  packages = [
-    "expfmt",
-    "internal/bitbucket.org/ww/goautoneg",
-    "model",
-  ]
-  pruneopts = ""
-  revision = "d0f7cd64bda49e08b22ae8a730aa57aa0db125d6"
-
-[[projects]]
-  branch = "master"
-  digest = "1:61df0898746840afc7be5dc2c3eeec83022fab70df11ecee5b16c85e912cf5ed"
-  name = "github.com/prometheus/procfs"
-  packages = [
-    ".",
-    "internal/util",
-    "nfs",
-    "xfs",
-  ]
-  pruneopts = ""
-  revision = "8b1c2da0d56deffdbb9e48d4414b4e674bd8083e"
-
-[[projects]]
-  branch = "master"
-  digest = "1:146327ce93be37e68bd3ff8541090d96da8cb3adc9e35d57570e9170a29f6bf6"
-  name = "github.com/spf13/cobra"
-  packages = ["."]
-  pruneopts = ""
-  revision = "b78744579491c1ceeaaa3b40205e56b0591b93a3"
-
-[[projects]]
-  digest = "1:261bc565833ef4f02121450d74eb88d5ae4bd74bfe5d0e862cddb8550ec35000"
-  name = "github.com/spf13/pflag"
-  packages = ["."]
-  pruneopts = ""
-  revision = "e57e3eeb33f795204c1ca35f56c44f83227c6e66"
-  version = "v1.0.0"
-
-[[projects]]
-  digest = "1:3926a4ec9a4ff1a072458451aa2d9b98acd059a45b38f7335d31e06c3d6a0159"
-  name = "github.com/stretchr/testify"
-  packages = [
-    "assert",
-    "require",
-  ]
-  pruneopts = ""
-  revision = "69483b4bd14f5845b5a1e55bca19e954e827f1d0"
-  version = "v1.1.4"
-
-[[projects]]
-  branch = "v2"
-  digest = "1:9d92186f609a73744232323416ddafd56fae67cb552162cc190ab903e36900dd"
-  name = "github.com/zrepl/yaml-config"
-  packages = ["."]
-  pruneopts = ""
-  revision = "af27d27978ad95808723a62d87557d63c3ff0605"
-
-[[projects]]
-  branch = "master"
-  digest = "1:9c286cf11d0ca56368185bada5dd6d97b6be4648fc26c354fcba8df7293718f7"
-  name = "golang.org/x/sys"
-  packages = ["unix"]
-  pruneopts = ""
-  revision = "bf42f188b9bc6f2cf5b8ee5a912ef1aedd0eba4c"
-
-[[projects]]
-  digest = "1:5acd3512b047305d49e8763eef7ba423901e85d5dd2fd1e71778a0ea8de10bd4"
-  name = "golang.org/x/text"
-  packages = [
-    "encoding",
-    "encoding/internal/identifier",
-    "internal/gen",
-    "transform",
-    "unicode/cldr",
-  ]
-  pruneopts = ""
-  revision = "f21a4dfb5e38f5895301dc265a8def02365cc3d0"
-  version = "v0.3.0"
-
-[solve-meta]
-  analyzer-name = "dep"
-  analyzer-version = 1
-  input-imports = [
-    "github.com/fatih/color",
-    "github.com/gdamore/tcell/termbox",
-    "github.com/go-logfmt/logfmt",
-    "github.com/golang/protobuf/proto",
-    "github.com/jinzhu/copier",
-    "github.com/kr/pretty",
-    "github.com/mattn/go-isatty",
-    "github.com/pkg/errors",
-    "github.com/problame/go-netssh",
-    "github.com/problame/go-rwccmd",
-    "github.com/problame/go-streamrpc",
-    "github.com/prometheus/client_golang/prometheus",
-    "github.com/prometheus/client_golang/prometheus/promhttp",
-    "github.com/spf13/cobra",
-    "github.com/spf13/pflag",
-    "github.com/stretchr/testify/assert",
-    "github.com/stretchr/testify/require",
-    "github.com/zrepl/yaml-config",
-    "golang.org/x/sys/unix",
-  ]
-  solver-name = "gps-cdcl"
-  solver-version = 1

Gopkg.toml

@@ -1,75 +0,0 @@
-ignored = [ "github.com/inconshreveable/mousetrap" ]
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/ftrvxmtrx/fd"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/jinzhu/copier"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/kr/pretty"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/mitchellh/go-homedir"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/mitchellh/mapstructure"
-
-[[constraint]]
-  name = "github.com/pkg/errors"
-  version = "0.8.0"
-
-[[constraint]]
-  branch = "master"
-  name = "github.com/spf13/cobra"
-
-[[constraint]]
-  name = "github.com/spf13/viper"
-  version = "1.0.0"
-
-[[constraint]]
-  name = "github.com/stretchr/testify"
-  version = "1.1.4"
-
-[[constraint]]
-  branch = "v2"
-  name = "github.com/zrepl/yaml-config"
-
-[[constraint]]
-  name = "github.com/go-logfmt/logfmt"
-  version = "*"
-
-[[constraint]]
-  name = "github.com/problame/go-rwccmd"
-  branch = "master"
-
-[[constraint]]
-  name = "github.com/problame/go-netssh"
-  branch = "master"
-
-[[constraint]]
-  name = "github.com/prometheus/client_golang"
-  branch = "master"
-
-[[constraint]]
-  name = "github.com/golang/protobuf"
-  version = "1.2.0"
-
-[[constraint]]
-  name = "github.com/fatih/color"
-  version = "1.7.0"
-
-[[constraint]]
-  name = "github.com/problame/go-streamrpc"
-  version = "0.4.0"
-
-
-
-[[constraint]]
-  name = "github.com/gdamore/tcell"
-  version = "1.0.0"

Makefile

@@ -1,38 +1,6 @@
-.PHONY: generate build test vet cover release docs docs-clean clean vendordeps
-.DEFAULT_GOAL := build
-
-ROOT := github.com/zrepl/zrepl
-SUBPKGS += client
-SUBPKGS += config
-SUBPKGS += daemon
-SUBPKGS += daemon/filters
-SUBPKGS += daemon/job
-SUBPKGS += daemon/logging
-SUBPKGS += daemon/nethelpers
-SUBPKGS += daemon/pruner
-SUBPKGS += daemon/snapper
-SUBPKGS += daemon/streamrpcconfig
-SUBPKGS += daemon/transport
-SUBPKGS += daemon/transport/connecter
-SUBPKGS += daemon/transport/serve
-SUBPKGS += endpoint
-SUBPKGS += logger
-SUBPKGS += pruning
-SUBPKGS += pruning/retentiongrid
-SUBPKGS += replication
-SUBPKGS += replication/fsrep
-SUBPKGS += replication/pdu
-SUBPKGS += replication/internal/queue
-SUBPKGS += replication/internal/diff
-SUBPKGS += tlsconf
-SUBPKGS += util
-SUBPKGS += util/socketpair
-SUBPKGS += util/watchdog
-SUBPKGS += util/envconst
-SUBPKGS += version
-SUBPKGS += zfs
-
-_TESTPKGS := $(ROOT) $(foreach p,$(SUBPKGS),$(ROOT)/$(p))
+.PHONY: generate build test vet cover release docs docs-clean clean format lint platformtest
+.PHONY: release bins-all release-noarch
+.DEFAULT_GOAL := zrepl-bin
 
 ARTIFACTDIR := artifacts
 
@@ -40,105 +8,343 @@ ifdef ZREPL_VERSION
     _ZREPL_VERSION := $(ZREPL_VERSION)
 endif
 ifndef _ZREPL_VERSION
-    _ZREPL_VERSION := $(shell git describe --dirty 2>/dev/null || echo "ZREPL_BUILD_INVALID_VERSION" )
+    _ZREPL_VERSION := $(shell git describe --always --dirty 2>/dev/null || echo "ZREPL_BUILD_INVALID_VERSION" )
     ifeq ($(_ZREPL_VERSION),ZREPL_BUILD_INVALID_VERSION) # can't use .SHELLSTATUS because Debian Stretch is still on gmake 4.1
         $(error cannot infer variable ZREPL_VERSION using git and variable is not overriden by make invocation)
     endif
 endif
+
+GO := 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
 GO_LDFLAGS := "-X github.com/zrepl/zrepl/version.zreplVersion=$(_ZREPL_VERSION)"
+GO_MOD_READONLY := -mod=readonly
+GO_EXTRA_BUILDFLAGS :=
+GO_BUILDFLAGS := $(GO_MOD_READONLY) $(GO_EXTRA_BUILDFLAGS)
+GO_BUILD := $(GO_ENV_VARS) $(GO) build $(GO_BUILDFLAGS) -ldflags $(GO_LDFLAGS)
+GOLANGCI_LINT := golangci-lint
+GOCOVMERGE := gocovmerge
+RELEASE_DOCKER_BASEIMAGE_TAG ?= 1.21
+RELEASE_DOCKER_BASEIMAGE ?= golang:$(RELEASE_DOCKER_BASEIMAGE_TAG)
 
-GO_BUILD := go build -ldflags $(GO_LDFLAGS)
+ifneq ($(GOARM),)
+	ZREPL_TARGET_TUPLE := $(GOOS)-$(GOARCH)v$(GOARM)
+else
+	ZREPL_TARGET_TUPLE := $(GOOS)-$(GOARCH)
+endif
 
-RELEASE_BINS := $(ARTIFACTDIR)/zrepl-freebsd-amd64
-RELEASE_BINS += $(ARTIFACTDIR)/zrepl-linux-amd64
-RELEASE_BINS += $(ARTIFACTDIR)/zrepl-darwin-amd64
-
-RELEASE_NOARCH := $(ARTIFACTDIR)/zrepl-noarch.tar
-THIS_PLATFORM_RELEASE_BIN := $(shell bash -c 'source <(go env) && echo "zrepl-$${GOOS}-$${GOARCH}"' )
-
-vendordeps:
-	dep ensure -v -vendor-only
-
-generate: #not part of the build, must do that manually
-	protoc -I=replication/pdu --go_out=replication/pdu replication/pdu/pdu.proto
-	@for pkg in $(_TESTPKGS); do\
-		go generate "$$pkg" || exit 1; \
-	done;
-
-build:
-	@echo "INFO: In case of missing dependencies, run 'make vendordeps'"
-	$(GO_BUILD) -o "$(ARTIFACTDIR)/zrepl"
-
-test:
-	@for pkg in $(_TESTPKGS); do \
-		echo "Testing $$pkg"; \
-		go test "$$pkg" || exit 1; \
-	done;
-
-vet:
-	@for pkg in $(_TESTPKGS); do \
-		echo "Vetting $$pkg"; \
-		go vet "$$pkg" || exit 1; \
-	done;
-
-cover: artifacts
-	@for pkg in $(_TESTPKGS); do \
-		profile="$(ARTIFACTDIR)/cover-$$(basename $$pkg).out"; \
-		go test -coverprofile "$$profile" $$pkg || exit 1; \
-		if [ -f "$$profile" ]; then \
-   			go tool cover -html="$$profile" -o "$${profile}.html" || exit 2; \
-		fi; \
-	done;
-
-$(ARTIFACTDIR):
-	mkdir -p "$@"
-
-$(ARTIFACTDIR)/docs: $(ARTIFACTDIR)
-	mkdir -p "$@"
-
-$(ARTIFACTDIR)/bash_completion: $(RELEASE_BINS)
-	artifacts/$(THIS_PLATFORM_RELEASE_BIN) bashcomp "$@"
-
-$(ARTIFACTDIR)/go_version.txt:
-	go version > $@
-
-docs: $(ARTIFACTDIR)/docs
-	make -C docs \
-		html \
-		BUILDDIR=../artifacts/docs \
-
-docs-clean:
-	make -C docs \
-		clean \
-		BUILDDIR=../artifacts/docs
+.PHONY: printvars
+printvars:
+	@echo GOOS=$(GOOS)
+	@echo GOARCH=$(GOARCH)
+	@echo GOARM=$(GOARM)
 
 
-.PHONY: $(RELEASE_BINS)
-# TODO: two wildcards possible
-$(RELEASE_BINS): $(ARTIFACTDIR)/zrepl-%-amd64: generate $(ARTIFACTDIR) vet test
-	@echo "INFO: In case of missing dependencies, run 'make vendordeps'"
-	GOOS=$* GOARCH=amd64   $(GO_BUILD) -o "$(ARTIFACTDIR)/zrepl-$*-amd64"
+##################### PRODUCING A RELEASE #############
+.PHONY: release wrapup-and-checksum check-git-clean sign clean
 
-$(RELEASE_NOARCH): docs $(ARTIFACTDIR)/bash_completion $(ARTIFACTDIR)/go_version.txt
+release: clean
+	# no cross-platform support for target test
+	$(MAKE) test-go
+	$(MAKE) bins-all
+	$(MAKE) noarch
+	$(MAKE) wrapup-and-checksum
+	$(MAKE) check-git-clean
+ifeq (SIGN, 1)
+	$(MAKE) sign
+endif
+	@echo "ZREPL RELEASE ARTIFACTS AVAILABLE IN artifacts/release"
+
+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)
+
+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)"
+	mkdir -p "$(_ZREPL_RPM_TOPDIR_ABS)"/{SPECS,RPMS,BUILD,BUILDROOT}
+	sed "s/^Version:.*/Version:          $(_ZREPL_RPM_VERSION)/g" \
+	    packaging/rpm/zrepl.spec >  $(_ZREPL_RPM_TOPDIR_ABS)/SPECS/zrepl.spec
+
+	# see /usr/lib/rpm/platform
+ifeq ($(GOARCH),amd64)
+	$(eval _ZREPL_RPMBUILD_TARGET := x86_64)
+else ifeq ($(GOARCH), 386)
+	$(eval _ZREPL_RPMBUILD_TARGET := i386)
+else ifeq ($(GOARCH), arm64)
+	$(eval _ZREPL_RPMBUILD_TARGET := aarch64)
+else ifeq ($(GOARCH), arm)
+	$(eval _ZREPL_RPMBUILD_TARGET := armv7hl)
+else
+	$(eval _ZREPL_RPMBUILD_TARGET := $(GOARCH))
+endif
+	rpmbuild \
+		--build-in-place \
+		--define "_sourcedir $(CURDIR)" \
+		--define "_topdir $(_ZREPL_RPM_TOPDIR_ABS)" \
+		--define "_zrepl_binary_filename zrepl-$(ZREPL_TARGET_TUPLE)" \
+		--target $(_ZREPL_RPMBUILD_TARGET) \
+		-bb "$(_ZREPL_RPM_TOPDIR_ABS)"/SPECS/zrepl.spec
+	cp "$(_ZREPL_RPM_TOPDIR_ABS)"/RPMS/$(_ZREPL_RPMBUILD_TARGET)/zrepl-$(_ZREPL_RPM_VERSION)*.rpm $(ARTIFACTDIR)/
+
+rpm-docker:
+	docker build -t zrepl_rpm_pkg --pull -f packaging/rpm/Dockerfile .
+	docker run --rm -i -v $(CURDIR):/build/src -u $$(id -u):$$(id -g) \
+		zrepl_rpm_pkg \
+		make rpm GOOS=$(GOOS) GOARCH=$(GOARCH) GOARM=$(GOARM)
+
+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))"; \
+		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)
+
+# expects `release` target to have run before
+NOARCH_TARBALL := $(ARTIFACTDIR)/zrepl-noarch.tar
+wrapup-and-checksum:
+	rm -f $(NOARCH_TARBALL)
 	tar --mtime='1970-01-01' --sort=name \
 		--transform 's/$(ARTIFACTDIR)/zrepl-$(_ZREPL_VERSION)-noarch/' \
-		-acf $@ \
+		--transform 's#dist#zrepl-$(_ZREPL_VERSION)-noarch/dist#' \
+		--transform 's#config/samples#zrepl-$(_ZREPL_VERSION)-noarch/config#' \
+		-acf $(NOARCH_TARBALL) \
 		$(ARTIFACTDIR)/docs/html \
 		$(ARTIFACTDIR)/bash_completion \
-		$(ARTIFACTDIR)/go_version.txt
-
-release: $(RELEASE_BINS) $(RELEASE_NOARCH)
+		$(ARTIFACTDIR)/_zrepl.zsh_completion \
+		$(ARTIFACTDIR)/go_env.txt \
+		dist \
+		config/samples
 	rm -rf "$(ARTIFACTDIR)/release"
 	mkdir -p "$(ARTIFACTDIR)/release"
-	cp $^ "$(ARTIFACTDIR)/release"
+	cp -l $(ARTIFACTDIR)/zrepl-* \
+		$(ARTIFACTDIR)/platformtest-* \
+		"$(ARTIFACTDIR)/release"
 	cd "$(ARTIFACTDIR)/release" && sha512sum $$(ls | sort) > sha512sum.txt
+
+check-git-clean:
 	@# note that we use ZREPL_VERSION and not _ZREPL_VERSION because we want to detect the override
-	@if git describe --dirty 2>/dev/null | grep dirty >/dev/null; then \
-		if [ "$(ZREPL_VERSION)" == "" ]; then \
-			echo "[WARN] git checkout is dirty and make variable ZREPL_VERSION was not used to override"; \
+	@if git describe --always --dirty 2>/dev/null | grep dirty >/dev/null; then \
+        echo '[INFO] either git reports checkout is dirty or git is not installed or this is not a git checkout'; \
+		if [ "$(ZREPL_VERSION)" = "" ]; then \
+			echo '[WARN] git checkout is dirty and make variable ZREPL_VERSION was not used to override'; \
+			git status; \
+			echo "git diff:";  \
+			git diff | cat; \
 			exit 1; \
 		fi; \
 	fi;
 
+tag-release:
+	test -n "$(ZREPL_TAG_VERSION)" || exit 1
+	git tag -u E27CA5FC -m "$(ZREPL_TAG_VERSION)" "$(ZREPL_TAG_VERSION)"
+
+sign:
+	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)"
+
+##################### BINARIES #####################
+.PHONY: bins-all 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=freebsd   GOARCH=arm	  GOARM=7
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=freebsd   GOARCH=arm64
+	$(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 ./...
+
+vet:
+	$(GO_ENV_VARS) $(GO) vet $(GO_BUILDFLAGS) ./...
+
+test-go: $(ARTIFACTDIR)
+	rm -f "$(ARTIFACTDIR)/gotest.cover"
+ifeq ($(COVER),1)
+	$(GO_ENV_VARS) $(GO) test $(GO_BUILDFLAGS) \
+		-coverpkg github.com/zrepl/zrepl/... \
+		-covermode atomic \
+		-coverprofile "$(ARTIFACTDIR)/gotest.cover" \
+		./...
+else
+	$(GO_ENV_VARS) $(GO) test $(GO_BUILDFLAGS) \
+		./...
+endif
+
+zrepl-bin:
+	$(GO_BUILD) -o "$(ARTIFACTDIR)/zrepl-$(ZREPL_TARGET_TUPLE)"
+
+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:
+	$(GO_ENV_VARS) $(GO) test $(GO_BUILDFLAGS) \
+		-c -o "$(COVER_PLATFORM_BIN_PATH)" \
+		-covermode=atomic -cover -coverpkg github.com/zrepl/zrepl/... \
+		./platformtest/harness
+cover-platform:
+	# do not track dependency on cover-platform-bin to allow build of binary outside of test VM
+	export _TEST_PLATFORM_CMD="$(COVER_PLATFORM_BIN_PATH) \
+		-test.coverprofile \"$(ARTIFACTDIR)/platformtest.cover\" \
+		-test.v \
+		__DEVEL--i-heard-you-like-tests"; \
+		$(MAKE) _test-or-cover-platform-impl
+
+TEST_PLATFORM_BIN_PATH := $(ARTIFACTDIR)/platformtest-$(ZREPL_TARGET_TUPLE)
+test-platform-bin:
+	$(GO_BUILD) -o "$(TEST_PLATFORM_BIN_PATH)" ./platformtest/harness
+test-platform:
+	export _TEST_PLATFORM_CMD="\"$(TEST_PLATFORM_BIN_PATH)\""; \
+		$(MAKE) _test-or-cover-platform-impl
+
+ZREPL_PLATFORMTEST_POOLNAME := zreplplatformtest
+ZREPL_PLATFORMTEST_IMAGEPATH := /tmp/zreplplatformtest.pool.img
+ZREPL_PLATFORMTEST_MOUNTPOINT := /tmp/zreplplatformtest.pool
+ZREPL_PLATFORMTEST_ZFS_LOG := /tmp/zreplplatformtest.zfs.log
+# ZREPL_PLATFORMTEST_STOP_AND_KEEP := -failure.stop-and-keep-pool
+ZREPL_PLATFORMTEST_ARGS :=
+_test-or-cover-platform-impl: $(ARTIFACTDIR)
+ifndef _TEST_PLATFORM_CMD
+	$(error _TEST_PLATFORM_CMD is undefined, caller 'cover-platform' or 'test-platform' should have defined it)
+endif
+	rm -f "$(ZREPL_PLATFORMTEST_ZFS_LOG)"
+	rm -f "$(ARTIFACTDIR)/platformtest.cover"
+	platformtest/logmockzfs/logzfsenv "$(ZREPL_PLATFORMTEST_ZFS_LOG)" `which zfs` \
+		$(_TEST_PLATFORM_CMD) \
+		-poolname "$(ZREPL_PLATFORMTEST_POOLNAME)" \
+		-imagepath "$(ZREPL_PLATFORMTEST_IMAGEPATH)" \
+		-mountpoint "$(ZREPL_PLATFORMTEST_MOUNTPOINT)" \
+		$(ZREPL_PLATFORMTEST_STOP_AND_KEEP) \
+		$(ZREPL_PLATFORMTEST_ARGS)
+
+cover-merge: $(ARTIFACTDIR)
+	$(GOCOVMERGE) $(ARTIFACTDIR)/platformtest.cover $(ARTIFACTDIR)/gotest.cover > $(ARTIFACTDIR)/merged.cover
+cover-html: cover-merge
+	$(GO) tool cover -html "$(ARTIFACTDIR)/merged.cover" -o "$(ARTIFACTDIR)/merged.cover.html"
+
+cover-full:
+	test "$$(id -u)" = "0" || echo "MUST RUN AS ROOT" 1>&2
+	$(MAKE) test-go COVER=1
+	$(MAKE) cover-platform-bin
+	$(MAKE) cover-platform
+	$(MAKE) cover-html
+
+##################### DEV TARGETS #####################
+# not part of the build, must do that manually
+.PHONY: generate formatcheck 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
+	$(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))
+
+##################### NOARCH #####################
+.PHONY: noarch $(ARTIFACTDIR)/bash_completion $(ARTIFACTDIR)/_zrepl.zsh_completion $(ARTIFACTDIR)/go_env.txt docs docs-clean
+
+
+$(ARTIFACTDIR):
+	mkdir -p "$@"
+$(ARTIFACTDIR)/docs: $(ARTIFACTDIR)
+	mkdir -p "$@"
+
+noarch: $(ARTIFACTDIR)/bash_completion $(ARTIFACTDIR)/_zrepl.zsh_completion $(ARTIFACTDIR)/go_env.txt docs
+	# pass
+
+$(ARTIFACTDIR)/bash_completion:
+	$(MAKE) zrepl-bin GOOS=$(GOHOSTOS) GOARCH=$(GOHOSTARCH)
+	artifacts/zrepl-$(GOHOSTOS)-$(GOHOSTARCH) gencompletion bash "$@"
+
+$(ARTIFACTDIR)/_zrepl.zsh_completion:
+	$(MAKE) zrepl-bin GOOS=$(GOHOSTOS) GOARCH=$(GOHOSTARCH)
+	artifacts/zrepl-$(GOHOSTOS)-$(GOHOSTARCH) gencompletion zsh "$@"
+
+$(ARTIFACTDIR)/go_env.txt:
+	$(GO_ENV_VARS) $(GO) env > $@
+	$(GO) version >> $@
+
+docs: $(ARTIFACTDIR)/docs
+	# https://www.sphinx-doc.org/en/master/man/sphinx-build.html
+	$(MAKE) -C docs \
+		html \
+		BUILDDIR=../artifacts/docs \
+		SPHINXOPTS="-W --keep-going -n"
+
+docs-clean:
+	$(MAKE) -C docs \
+		clean \
+		BUILDDIR=../artifacts/docs

README.md

@@ -1,3 +1,13 @@
+[![GitHub license](https://img.shields.io/github/license/zrepl/zrepl.svg)](https://github.com/zrepl/zrepl/blob/master/LICENSE)
+[![Language: Go](https://img.shields.io/badge/lang-Go-6ad7e5.svg)](https://golang.org/)
+[![User Docs](https://img.shields.io/badge/docs-web-blue.svg)](https://zrepl.github.io)
+[![Support me on Patreon](https://img.shields.io/badge/dynamic/json?color=yellow&label=Patreon&query=data.attributes.patron_count&url=https%3A%2F%2Fwww.patreon.com%2Fapi%2Fcampaigns%2F3095079)](https://patreon.com/zrepl)
+[![Donate via GitHub Sponsors](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&style=flat&color=yellow)](https://github.com/sponsors/problame)
+[![Donate via Liberapay](https://img.shields.io/liberapay/patrons/zrepl.svg?logo=liberapay)](https://liberapay.com/zrepl/donate)
+[![Donate via PayPal](https://img.shields.io/badge/donate-paypal-yellow.svg)](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96)
+[![Twitter](https://img.shields.io/twitter/url/https/github.com/zrepl/zrepl.svg?style=social)](https://twitter.com/intent/tweet?text=Wow:&url=https%3A%2F%2Fgithub.com%2Fzrepl%2Fzrepl)
+[![Chat](https://img.shields.io/badge/chat-matrix-blue.svg)](https://matrix.to/#/#zrepl:matrix.org)
+
 # zrepl
 zrepl is a one-stop ZFS backup & replication solution.
 
@@ -12,57 +22,92 @@ zrepl is a one-stop ZFS backup & replication solution.
 
 ## Feature Requests
 
-1. Does you feature request require default values / some kind of configuration?
+1. Does your feature request require default values / some kind of configuration?
    If so, think of an expressive configuration example.
 2. Think of at least one use case that generalizes from your concrete application.
 3. Open an issue on GitHub with example conf & use case attached.
+4. **Optional**: [Post a bounty](https://www.bountysource.com/teams/zrepl) on the issue, or [contact Christian Schwarz](https://cschwarz.com) for contract work.
 
 The above does not apply if you already implemented everything.
 Check out the *Coding Workflow* section below for details.
 
-## Package Maintainer Information
+## Building, Releasing, Downstream-Packaging
 
-* Follow the steps in `docs/installation.rst -> Compiling from Source` and read the Makefile / shell scripts used in this process.
-* Make sure your distro is compatible with the paths in `docs/installation.rst`.
-* Ship a default config that adheres to your distro's `hier` and logging system.
-* Ship a service manager file and _please_ try to upstream it to this repository.
-* Use `make release ZREPL_VERSION='mydistro-1.2.3_1'`
-    * Your distro's name and any versioning supplemental to zrepl's (e.g. package revision) should be in this string
-* Make sure you are informed about new zrepl versions, e.g. by subscribing to GitHub's release RSS feed.
+This section provides an overview of the zrepl build & release process.
+Check out `docs/installation/compile-from-source.rst` for build-from-source instructions.
 
-## Developer Documentation
+### Overview
 
-zrepl is written in [Go](https://golang.org) and uses [`dep`](https://github.com/golang/dep) to manage dependencies.
+zrepl is written in [Go](https://golang.org) and uses [Go modules](https://github.com/golang/go/wiki/Modules) to manage dependencies.
 The documentation is written in [ReStructured Text](http://docutils.sourceforge.net/rst.html) using the [Sphinx](https://www.sphinx-doc.org) framework.
 
-To get started, run `./lazy.sh devsetup` to easily install build dependencies and read `docs/installation.rst -> Compiling from Source`.
+Install **build dependencies** using  `./lazy.sh devsetup`.
+`lazy.sh` uses `python3-pip` to fetch the build dependencies for the docs - you might want to use a [venv](https://docs.python.org/3/library/venv.html).
+If you just want to install the Go dependencies, run `./lazy.sh godep`.
 
-### Overall Architecture
+The **test suite** is split into pure **Go tests** (`make test-go`) and **platform tests** that interact with ZFS and thus generally **require root privileges** (`sudo make test-platform`).
+Platform tests run on their own pool with the name `zreplplatformtest`, which is created using the file vdev in `/tmp`.
 
-The application architecture is documented as part of the user docs in the *Implementation* section (`docs/content/impl`).
-Make sure to develop an understanding how zrepl is typically used by studying the user docs first.
+For a full **code coverage** profile, run `make test-go COVER=1 && sudo make test-platform && make cover-merge`.
+An HTML report can be generated using `make cover-html`.
 
-### Project Structure
+**Code generation** is triggered by `make generate`. Generated code is committed to the source tree.
 
-```
-├── cmd
-│   ├── endpoint            # implementations of endpoints for package replication
-│   ├── sampleconf          # example configuration
-├── docs                    # sphinx-based documentation
-│   ├── **/*.rst            # documentation in reStructuredText
-│   ├── sphinxconf
-│   │   └── conf.py         # sphinx config (see commit 445a280 why its not in docs/)
-│   ├── requirements.txt    # pip3 requirements to build documentation
-│   ├── publish.sh          # shell script for automated rendering & deploy to zrepl.github.io repo
-│   ├── public_git          # checkout of zrepl.github.io managed by above shell script
-├── logger                  # logger package used by zrepl
-├── replication             # replication functionality
-├── rpc                     # rpc protocol implementation
-├── util
-└── zfs                     # ZFS wrappers, filesystemm diffing
-```
+### Build & Release Process
 
-### Coding Workflow
+**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.
+
+**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
 
 * Open an issue when starting to hack on a new feature
 * Commits should reference the issue they are related to
@@ -72,9 +117,6 @@ Make sure to develop an understanding how zrepl is typically used by studying th
 
 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 />
@@ -91,4 +133,3 @@ 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.
-

build.Dockerfile

@@ -1,22 +1,36 @@
-FROM golang:latest
+FROM !SUBSTITUTED_BY_MAKEFILE
 
 RUN apt-get update && apt-get install -y \
     python3-pip \
-    unzip
+    python3-venv \
+    unzip \
+    gawk
 
-RUN wget https://github.com/protocolbuffers/protobuf/releases/download/v3.6.1/protoc-3.6.1-linux-x86_64.zip
-RUN echo "6003de742ea3fcf703cfec1cd4a3380fd143081a2eb0e559065563496af27807  protoc-3.6.1-linux-x86_64.zip" | sha256sum -c
-RUN unzip -d /usr protoc-3.6.1-linux-x86_64.zip
+ADD 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
-RUN /tmp/lazy.sh devsetup
+RUN /tmp/lazy.sh docdep
 
 # prepare volume mount of git checkout to /zrepl
-RUN mkdir -p /go/src/github.com/zrepl/zrepl
-RUN chmod -R 0777 /go
+RUN mkdir -p /src/github.com/zrepl/zrepl
 RUN mkdir -p /.cache && chmod -R 0777 /.cache
-WORKDIR /go/src/github.com/zrepl/zrepl
 
+# $GOPATH is /go
+# Go 1.12 doesn't use modules within GOPATH, but 1.13 and later do
+# => store source outside of GOPATH
+WORKDIR /src
+
+# Install build tools (e.g. protobuf generator, stringer) into $GOPATH/bin
+ADD build/ /tmp/build
+RUN /tmp/lazy.sh godep
+
+RUN chmod -R 0777 /go
 

build.installprotoc.bash

@@ -0,0 +1,25 @@
+#!/usr/bin/env bash
+set -euo pipefail
+set -x
+
+MACH=$(uname -m)
+MACH="${MACH/aarch64/aarch_64}"
+
+VERSION=3.6.1
+FILENAME=protoc-"$VERSION"-linux-"$MACH".zip
+
+if [ -e "$FILENAME" ]; then
+    echo "$FILENAME" already exists 1>&2
+    exit 1
+fi
+
+wget https://github.com/protocolbuffers/protobuf/releases/download/v"$VERSION"/"$FILENAME"
+
+stat "$FILENAME"
+
+sha256sum -c --ignore-missing <<EOF
+6003de742ea3fcf703cfec1cd4a3380fd143081a2eb0e559065563496af27807  protoc-3.6.1-linux-x86_64.zip
+af8e5aaaf39ddec62ec8dd2be1b8d9602c6da66564883a16393ade5f71170922  protoc-3.6.1-linux-aarch_64.zip
+EOF
+
+unzip -d /usr "$FILENAME"

build/go.mod

@@ -0,0 +1,40 @@
+module github.com/zrepl/zrepl/build
+
+go 1.12
+
+require (
+	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
+)

build/tools.go

@@ -0,0 +1,15 @@
+//go:build tools
+// +build tools
+
+package main
+
+// the lines are parsed by lazy.sh, do not edit
+import (
+	_ "github.com/alvaroloes/enumer"
+	_ "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

@@ -1,11 +1,16 @@
 package cli
 
 import (
+	"context"
 	"fmt"
+	"os"
+
 	"github.com/spf13/cobra"
 	"github.com/spf13/pflag"
+
+	"github.com/zrepl/zrepl/daemon/logging/trace"
+
 	"github.com/zrepl/zrepl/config"
-	"os"
 )
 
 var rootArgs struct {
@@ -17,37 +22,67 @@ var rootCmd = &cobra.Command{
 	Short: "One-stop ZFS replication solution",
 }
 
-var bashcompCmd = &cobra.Command{
-	Use:   "bashcomp path/to/out/file",
-	Short: "generate bash completions",
-	Run: func(cmd *cobra.Command, args []string) {
-		if len(args) != 1 {
-			fmt.Fprintf(os.Stderr, "specify exactly one positional agument\n")
-			cmd.Usage()
-			os.Exit(1)
-		}
-		if err := rootCmd.GenBashCompletionFile(args[0]); err != nil {
-			fmt.Fprintf(os.Stderr, "error generating bash completion: %s", err)
-			os.Exit(1)
-		}
+func init() {
+	rootCmd.PersistentFlags().StringVar(&rootArgs.configPath, "config", "", "config file path")
+}
+
+var genCompletionCmd = &cobra.Command{
+	Use:   "gencompletion",
+	Short: "generate shell auto-completions",
+}
+
+type completionCmdInfo struct {
+	genFunc func(outpath string) error
+	help    string
+}
+
+var completionCmdMap = map[string]completionCmdInfo{
+	"zsh": {
+		rootCmd.GenZshCompletionFile,
+		"  save to file `_zrepl` in your zsh's $fpath",
+	},
+	"bash": {
+		rootCmd.GenBashCompletionFile,
+		"  save to a path and source that path in your .bashrc",
 	},
-	Hidden: true,
 }
 
 func init() {
-	rootCmd.PersistentFlags().StringVar(&rootArgs.configPath, "config", "", "config file path")
-	rootCmd.AddCommand(bashcompCmd)
+	for sh, info := range completionCmdMap {
+		sh, info := sh, info
+		genCompletionCmd.AddCommand(&cobra.Command{
+			Use:     fmt.Sprintf("%s path/to/out/file", sh),
+			Short:   fmt.Sprintf("generate %s completions", sh),
+			Example: info.help,
+			Run: func(cmd *cobra.Command, args []string) {
+				if len(args) != 1 {
+					fmt.Fprintf(os.Stderr, "specify exactly one positional agument\n")
+					err := cmd.Usage()
+					if err != nil {
+						panic(err)
+					}
+					os.Exit(1)
+				}
+				if err := info.genFunc(args[0]); err != nil {
+					fmt.Fprintf(os.Stderr, "error generating %s completion: %s", sh, err)
+					os.Exit(1)
+				}
+			},
+		})
+	}
+	rootCmd.AddCommand(genCompletionCmd)
 }
 
 type Subcommand struct {
-	Use             string
-	Short           string
-	NoRequireConfig bool
-	Run             func(subcommand *Subcommand, args []string) error
-	SetupFlags      func(f *pflag.FlagSet)
-	SetupSubcommands  func() []*Subcommand
+	Use              string
+	Short            string
+	Example          string
+	NoRequireConfig  bool
+	Run              func(ctx context.Context, subcommand *Subcommand, args []string) error
+	SetupFlags       func(f *pflag.FlagSet)
+	SetupSubcommands func() []*Subcommand
 
-	config *config.Config
+	config    *config.Config
 	configErr error
 }
 
@@ -64,7 +99,11 @@ func (s *Subcommand) Config() *config.Config {
 
 func (s *Subcommand) run(cmd *cobra.Command, args []string) {
 	s.tryParseConfig()
-	err := s.Run(s, args)
+	ctx := context.Background()
+	endTask := trace.WithTaskFromStackUpdateCtx(&ctx)
+	defer endTask()
+	err := s.Run(ctx, s, args)
+	endTask()
 	if err != nil {
 		fmt.Fprintf(os.Stderr, "%s\n", err)
 		os.Exit(1)
@@ -92,8 +131,9 @@ func AddSubcommand(s *Subcommand) {
 
 func addSubcommandToCobraCmd(c *cobra.Command, s *Subcommand) {
 	cmd := cobra.Command{
-		Use: s.Use,
-		Short: s.Short,
+		Use:     s.Use,
+		Short:   s.Short,
+		Example: s.Example,
 	}
 	if s.SetupSubcommands == nil {
 		cmd.Run = s.run
@@ -108,9 +148,8 @@ func addSubcommandToCobraCmd(c *cobra.Command, s *Subcommand) {
 	c.AddCommand(&cmd)
 }
 
-
 func Run() {
 	if err := rootCmd.Execute(); err != nil {
 		os.Exit(1)
 	}
-}
+}

client/configcheck.go

@@ -1,41 +1,54 @@
 package client
 
 import (
+	"context"
 	"encoding/json"
 	"fmt"
+	"os"
+
 	"github.com/kr/pretty"
 	"github.com/pkg/errors"
 	"github.com/spf13/pflag"
 	"github.com/zrepl/yaml-config"
+
 	"github.com/zrepl/zrepl/cli"
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/job"
 	"github.com/zrepl/zrepl/daemon/logging"
 	"github.com/zrepl/zrepl/logger"
-	"os"
 )
 
 var configcheckArgs struct {
-	format string
-	what string
+	format        string
+	what          string
+	skipCertCheck bool
 }
 
 var ConfigcheckCmd = &cli.Subcommand{
-	Use: "configcheck",
+	Use:   "configcheck",
 	Short: "check if config can be parsed without errors",
 	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(subcommand *cli.Subcommand, args []string) error {
-		formatMap := map[string]func(interface{}) {
+	Run: func(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
+		formatMap := map[string]func(interface{}){
 			"": func(i interface{}) {},
-			"pretty": func(i interface{}) { pretty.Println(i) },
+			"pretty": func(i interface{}) {
+				if _, err := pretty.Println(i); err != nil {
+					panic(err)
+				}
+			},
 			"json": func(i interface{}) {
-				json.NewEncoder(os.Stdout).Encode(subcommand.Config())
+				if err := json.NewEncoder(os.Stdout).Encode(subcommand.Config()); err != nil {
+					panic(err)
+				}
 			},
 			"yaml": func(i interface{}) {
-				yaml.NewEncoder(os.Stdout).Encode(subcommand.Config())
+				if err := yaml.NewEncoder(os.Stdout).Encode(subcommand.Config()); err != nil {
+					panic(err)
+				}
 			},
 		}
 
@@ -45,8 +58,16 @@ 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())
+		confJobs, err := job.JobsFromConfig(subcommand.Config(), parseFlags)
+
 		if err != nil {
 			err := errors.Wrap(err, "cannot build jobs from config")
 			if configcheckArgs.what == "jobs" {
@@ -71,12 +92,11 @@ var ConfigcheckCmd = &cli.Subcommand{
 			}
 		}
 
-
-		whatMap := map[string]func() {
+		whatMap := map[string]func(){
 			"all": func() {
 				o := struct {
-					config *config.Config
-					jobs []job.Job
+					config  *config.Config
+					jobs    []job.Job
 					logging *logger.Outlets
 				}{
 					subcommand.Config(),
@@ -109,4 +129,3 @@ var ConfigcheckCmd = &cli.Subcommand{
 		}
 	},
 }
-

client/jsonclient.go

@@ -4,10 +4,11 @@ import (
 	"bytes"
 	"context"
 	"encoding/json"
-	"github.com/pkg/errors"
 	"io"
 	"net"
 	"net/http"
+
+	"github.com/pkg/errors"
 )
 
 func controlHttpClient(sockpath string) (client http.Client, err error) {
@@ -35,7 +36,7 @@ func jsonRequestResponse(c http.Client, endpoint string, req interface{}, res in
 
 	if resp.StatusCode != http.StatusOK {
 		var msg bytes.Buffer
-		io.CopyN(&msg, resp.Body, 4096)
+		_, _ = io.CopyN(&msg, resp.Body, 4096) // ignore error, just display what we got
 		return errors.Errorf("%s", msg.String())
 	}
 

client/migrate.go

@@ -0,0 +1,268 @@
+package client
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/fatih/color"
+	"github.com/kr/pretty"
+	"github.com/pkg/errors"
+	"github.com/spf13/pflag"
+
+	"github.com/zrepl/zrepl/daemon/job"
+	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/zfs"
+
+	"github.com/zrepl/zrepl/cli"
+	"github.com/zrepl/zrepl/config"
+)
+
+var (
+	MigrateCmd = &cli.Subcommand{
+		Use:   "migrate",
+		Short: "perform migration of the on-disk / zfs properties",
+		SetupSubcommands: func() []*cli.Subcommand {
+			return migrations
+		},
+	}
+)
+
+var migrations = []*cli.Subcommand{
+	&cli.Subcommand{
+		Use: "0.0.X:0.1:placeholder",
+		Run: doMigratePlaceholder0_1,
+		SetupFlags: func(f *pflag.FlagSet) {
+			f.BoolVar(&migratePlaceholder0_1Args.dryRun, "dry-run", false, "dry run")
+		},
+	},
+	&cli.Subcommand{
+		Use: "replication-cursor:v1-v2",
+		Run: doMigrateReplicationCursor,
+		SetupFlags: func(f *pflag.FlagSet) {
+			f.BoolVar(&migrateReplicationCursorArgs.dryRun, "dry-run", false, "dry run")
+		},
+	},
+}
+
+var migratePlaceholder0_1Args struct {
+	dryRun bool
+}
+
+func doMigratePlaceholder0_1(ctx context.Context, sc *cli.Subcommand, args []string) error {
+	if len(args) != 0 {
+		return fmt.Errorf("migration does not take arguments, got %v", args)
+	}
+
+	cfg := sc.Config()
+
+	allFSS, err := zfs.ZFSListMapping(ctx, zfs.NoFilter())
+	if err != nil {
+		return errors.Wrap(err, "cannot list filesystems")
+	}
+
+	type workItem struct {
+		jobName string
+		rootFS  *zfs.DatasetPath
+		fss     []*zfs.DatasetPath
+	}
+	var wis []workItem
+	for i, j := range cfg.Jobs {
+		var rfsS string
+		switch job := j.Ret.(type) {
+		case *config.SinkJob:
+			rfsS = job.RootFS
+		case *config.PullJob:
+			rfsS = job.RootFS
+		default:
+			fmt.Printf("ignoring job %q (%d/%d, type %T)\n", j.Name(), i, len(cfg.Jobs), j.Ret)
+			continue
+		}
+		rfs, err := zfs.NewDatasetPath(rfsS)
+		if err != nil {
+			return errors.Wrapf(err, "root fs for job %q is not a valid dataset path", j.Name())
+		}
+		var fss []*zfs.DatasetPath
+		for _, fs := range allFSS {
+			if fs.HasPrefix(rfs) {
+				fss = append(fss, fs)
+			}
+		}
+		wis = append(wis, workItem{j.Name(), rfs, fss})
+	}
+
+	for _, wi := range wis {
+		fmt.Printf("job %q => migrate filesystems below root_fs %q\n", wi.jobName, wi.rootFS.ToString())
+		if len(wi.fss) == 0 {
+			fmt.Printf("\tno filesystems\n")
+			continue
+		}
+		for _, fs := range wi.fss {
+			fmt.Printf("\t%q ... ", fs.ToString())
+			r, err := zfs.ZFSMigrateHashBasedPlaceholderToCurrent(ctx, fs, migratePlaceholder0_1Args.dryRun)
+			if err != nil {
+				fmt.Printf("error: %s\n", err)
+			} else if !r.NeedsModification {
+				fmt.Printf("unchanged (placeholder=%v)\n", r.OriginalState.IsPlaceholder)
+			} else {
+				fmt.Printf("migrate (placeholder=%v) (old value = %q)\n",
+					r.OriginalState.IsPlaceholder, r.OriginalState.RawLocalPropertyValue)
+			}
+		}
+	}
+
+	return nil
+}
+
+var migrateReplicationCursorArgs struct {
+	dryRun bool
+}
+
+var bold = color.New(color.Bold)
+var succ = color.New(color.FgGreen)
+var fail = color.New(color.FgRed)
+
+var migrateReplicationCursorSkipSentinel = fmt.Errorf("skipping this filesystem")
+
+func doMigrateReplicationCursor(ctx context.Context, sc *cli.Subcommand, args []string) error {
+	if len(args) != 0 {
+		return fmt.Errorf("migration does not take arguments, got %v", args)
+	}
+
+	cfg := sc.Config()
+	jobs, err := job.JobsFromConfig(cfg, config.ParseFlagsNone)
+	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")
+		return fmt.Errorf("exiting migration after error")
+	}
+
+	v1cursorJobs := make([]job.Job, 0, len(cfg.Jobs))
+	for i, j := range cfg.Jobs {
+		if jobs[i].Name() != j.Name() {
+			panic("implementation error")
+		}
+		switch j.Ret.(type) {
+		case *config.PushJob:
+			v1cursorJobs = append(v1cursorJobs, jobs[i])
+		case *config.SourceJob:
+			v1cursorJobs = append(v1cursorJobs, jobs[i])
+		default:
+			fmt.Printf("ignoring job %q (%d/%d, type %T), not supposed to create v1 replication cursors\n", j.Name(), i, len(cfg.Jobs), j.Ret)
+			continue
+		}
+	}
+
+	// scan all filesystems for v1 replication cursors
+
+	fss, err := zfs.ZFSListMapping(ctx, zfs.NoFilter())
+	if err != nil {
+		return errors.Wrap(err, "list filesystems")
+	}
+
+	var hadError bool
+	for _, fs := range fss {
+
+		bold.Printf("INSPECT FILESYSTEM %q\n", fs.ToString())
+
+		err := doMigrateReplicationCursorFS(ctx, v1cursorJobs, fs)
+		if err == migrateReplicationCursorSkipSentinel {
+			bold.Printf("FILESYSTEM SKIPPED\n")
+		} else if err != nil {
+			hadError = true
+			fail.Printf("MIGRATION FAILED: %s\n", err)
+		} else {
+			succ.Printf("FILESYSTEM %q COMPLETE\n", fs.ToString())
+		}
+	}
+
+	if hadError {
+		fail.Printf("\n\none or more filesystems could not be migrated, please inspect output and or re-run migration")
+		return errors.Errorf("")
+	}
+	return nil
+}
+
+func doMigrateReplicationCursorFS(ctx context.Context, v1CursorJobs []job.Job, fs *zfs.DatasetPath) error {
+
+	var owningJob job.Job = nil
+	for _, job := range v1CursorJobs {
+		conf := job.SenderConfig()
+		if conf == nil {
+			continue
+		}
+		pass, err := conf.FSF.Filter(fs)
+		if err != nil {
+			return errors.Wrapf(err, "filesystem filter error in job %q for fs %q", job.Name(), fs.ToString())
+		}
+		if !pass {
+			continue
+		}
+		if owningJob != nil {
+			return errors.Errorf("jobs %q and %q both match %q\ncannot attribute replication cursor to either one", owningJob.Name(), job.Name(), fs)
+		}
+		owningJob = job
+	}
+	if owningJob == nil {
+		fmt.Printf("no job's Filesystems filter matches\n")
+		return migrateReplicationCursorSkipSentinel
+	}
+	fmt.Printf("identified owning job %q\n", owningJob.Name())
+
+	bookmarks, err := zfs.ZFSListFilesystemVersions(ctx, fs, zfs.ListFilesystemVersionsOptions{
+		Types: zfs.Bookmarks,
+	})
+	if err != nil {
+		return errors.Wrapf(err, "list filesystem versions of %q", fs.ToString())
+	}
+
+	var oldCursor *zfs.FilesystemVersion
+	for i, fsv := range bookmarks {
+		_, _, err := endpoint.ParseReplicationCursorBookmarkName(fsv.ToAbsPath(fs))
+		if err != endpoint.ErrV1ReplicationCursor {
+			continue
+		}
+
+		if oldCursor != nil {
+			fmt.Printf("unexpected v1 replication cursor candidate: %q", fsv.ToAbsPath(fs))
+			return errors.Wrap(err, "multiple filesystem versions identified as v1 replication cursors")
+		}
+
+		oldCursor = &bookmarks[i]
+
+	}
+
+	if oldCursor == nil {
+		bold.Printf("no v1 replication cursor found for filesystem %q\n", fs.ToString())
+		return migrateReplicationCursorSkipSentinel
+	}
+
+	fmt.Printf("found v1 replication cursor:\n%s\n", pretty.Sprint(oldCursor))
+
+	mostRecentNew, err := endpoint.GetMostRecentReplicationCursorOfJob(ctx, fs.ToString(), owningJob.SenderConfig().JobID)
+	if err != nil {
+		return errors.Wrapf(err, "get most recent v2 replication cursor")
+	}
+
+	if mostRecentNew == nil {
+		return errors.Errorf("no v2 replication cursor found for job %q on filesystem %q", owningJob.SenderConfig().JobID, fs.ToString())
+	}
+
+	fmt.Printf("most recent v2 replication cursor:\n%#v", oldCursor)
+
+	if !(mostRecentNew.CreateTXG >= oldCursor.CreateTXG) {
+		return errors.Errorf("v1 replication cursor createtxg is higher than v2 cursor's, skipping this filesystem")
+	}
+
+	fmt.Printf("determined that v2 cursor is bookmark of same or newer version than v1 cursor\n")
+	fmt.Printf("destroying v1 cursor %q\n", oldCursor.ToAbsPath(fs))
+
+	if migrateReplicationCursorArgs.dryRun {
+		succ.Printf("DRY RUN\n")
+	} else {
+		if err := zfs.ZFSDestroyFilesystemVersion(ctx, fs, oldCursor); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}

client/migrate_test.go

@@ -0,0 +1,16 @@
+package client
+
+import "testing"
+
+func TestMigrationsUnambiguousNames(t *testing.T) {
+	names := make(map[string]bool)
+	for _, mig := range migrations {
+		if _, ok := names[mig.Use]; ok {
+			t.Errorf("duplicate migration name %q", mig.Use)
+			t.FailNow()
+			return
+		} else {
+			names[mig.Use] = true
+		}
+	}
+}

client/pprof.go

@@ -1,66 +1,10 @@
 package client
 
-import (
-	"errors"
-	"github.com/zrepl/zrepl/cli"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon"
-	"log"
-	"os"
-)
-
-var pprofArgs struct {
-	daemon.PprofServerControlMsg
-}
+import "github.com/zrepl/zrepl/cli"
 
 var PprofCmd = &cli.Subcommand{
-	Use:   "pprof off | [on TCP_LISTEN_ADDRESS]",
-	Short: "start a http server exposing go-tool-compatible profiling endpoints at TCP_LISTEN_ADDRESS",
-	Run: func(subcommand *cli.Subcommand, args []string) error {
-		if len(args) < 1 {
-			goto enargs
-		}
-		switch args[0] {
-		case "on":
-			pprofArgs.Run = true
-			if len(args) != 2 {
-				return errors.New("must specify TCP_LISTEN_ADDRESS as second positional argument")
-			}
-			pprofArgs.HttpListenAddress = args[1]
-		case "off":
-			if len(args) != 1 {
-				goto enargs
-			}
-			pprofArgs.Run = false
-		}
-
-		RunPProf(subcommand.Config())
-		return nil
-	enargs:
-		return errors.New("invalid number of positional arguments")
-
+	Use: "pprof",
+	SetupSubcommands: func() []*cli.Subcommand {
+		return []*cli.Subcommand{PprofListenCmd, pprofActivityTraceCmd}
 	},
 }
-
-func RunPProf(conf *config.Config) {
-	log := log.New(os.Stderr, "", 0)
-
-	die := func() {
-		log.Printf("exiting after error")
-		os.Exit(1)
-	}
-
-	log.Printf("connecting to zrepl daemon")
-
-	httpc, err := controlHttpClient(conf.Global.Control.SockPath)
-	if err != nil {
-		log.Printf("error creating http client: %s", err)
-		die()
-	}
-	err = jsonRequestResponse(httpc, daemon.ControlJobEndpointPProf, pprofArgs.PprofServerControlMsg, struct{}{})
-	if err != nil {
-		log.Printf("error sending control message: %s", err)
-		die()
-	}
-	log.Printf("finished")
-}

client/pprof_activity_trace.go

@@ -0,0 +1,44 @@
+package client
+
+import (
+	"context"
+	"io"
+	"log"
+	"os"
+
+	"golang.org/x/net/websocket"
+
+	"github.com/zrepl/zrepl/cli"
+)
+
+var pprofActivityTraceCmd = &cli.Subcommand{
+	Use:   "activity-trace ZREPL_PPROF_HOST:ZREPL_PPROF_PORT",
+	Short: "attach to zrepl daemon with activated pprof listener and dump an activity-trace to stdout",
+	Run:   runPProfActivityTrace,
+}
+
+func runPProfActivityTrace(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
+	log := log.New(os.Stderr, "", 0)
+
+	die := func() {
+		log.Printf("exiting after error")
+		os.Exit(1)
+	}
+
+	if len(args) != 1 {
+		log.Printf("exactly one positional argument is required")
+		die()
+	}
+
+	url := "ws://" + args[0] + "/debug/zrepl/activity-trace" // FIXME dont' repeat that
+
+	log.Printf("attaching to activity trace stream %s", url)
+	ws, err := websocket.Dial(url, "", url)
+	if err != nil {
+		log.Printf("error: %s", err)
+		die()
+	}
+
+	_, err = io.Copy(os.Stdout, ws)
+	return err
+}

client/pprof_listen.go

@@ -0,0 +1,68 @@
+package client
+
+import (
+	"context"
+	"errors"
+	"log"
+	"os"
+
+	"github.com/zrepl/zrepl/cli"
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/daemon"
+)
+
+var pprofListenCmd struct {
+	daemon.PprofServerControlMsg
+}
+
+var PprofListenCmd = &cli.Subcommand{
+	Use:   "listen off | [on TCP_LISTEN_ADDRESS]",
+	Short: "start a http server exposing go-tool-compatible profiling endpoints at TCP_LISTEN_ADDRESS",
+	Run: func(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
+		if len(args) < 1 {
+			goto enargs
+		}
+		switch args[0] {
+		case "on":
+			pprofListenCmd.Run = true
+			if len(args) != 2 {
+				return errors.New("must specify TCP_LISTEN_ADDRESS as second positional argument")
+			}
+			pprofListenCmd.HttpListenAddress = args[1]
+		case "off":
+			if len(args) != 1 {
+				goto enargs
+			}
+			pprofListenCmd.Run = false
+		}
+
+		RunPProf(subcommand.Config())
+		return nil
+	enargs:
+		return errors.New("invalid number of positional arguments")
+
+	},
+}
+
+func RunPProf(conf *config.Config) {
+	log := log.New(os.Stderr, "", 0)
+
+	die := func() {
+		log.Printf("exiting after error")
+		os.Exit(1)
+	}
+
+	log.Printf("connecting to zrepl daemon")
+
+	httpc, err := controlHttpClient(conf.Global.Control.SockPath)
+	if err != nil {
+		log.Printf("error creating http client: %s", err)
+		die()
+	}
+	err = jsonRequestResponse(httpc, daemon.ControlJobEndpointPProf, pprofListenCmd.PprofServerControlMsg, struct{}{})
+	if err != nil {
+		log.Printf("error sending control message: %s", err)
+		die()
+	}
+	log.Printf("finished")
+}

client/signal.go

@@ -1,7 +1,10 @@
 package client
 
 import (
+	"context"
+
 	"github.com/pkg/errors"
+
 	"github.com/zrepl/zrepl/cli"
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon"
@@ -10,7 +13,7 @@ import (
 var SignalCmd = &cli.Subcommand{
 	Use:   "signal [wakeup|reset] JOB",
 	Short: "wake up a job from wait state or abort its current invocation",
-	Run: func(subcommand *cli.Subcommand, args []string) error {
+	Run: func(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
 		return runSignalCmd(subcommand.Config(), args)
 	},
 }
@@ -28,10 +31,10 @@ func runSignalCmd(config *config.Config, args []string) error {
 	err = jsonRequestResponse(httpc, daemon.ControlJobEndpointSignal,
 		struct {
 			Name string
-			Op string
+			Op   string
 		}{
 			Name: args[1],
-			Op: args[0],
+			Op:   args[0],
 		},
 		struct{}{},
 	)

client/status.go

@@ -1,546 +0,0 @@
-package client
-
-import (
-	"fmt"
-	"github.com/gdamore/tcell/termbox"
-	"github.com/pkg/errors"
-	"github.com/spf13/pflag"
-	"github.com/zrepl/yaml-config"
-	"github.com/zrepl/zrepl/cli"
-	"github.com/zrepl/zrepl/daemon"
-	"github.com/zrepl/zrepl/daemon/job"
-	"github.com/zrepl/zrepl/daemon/pruner"
-	"github.com/zrepl/zrepl/replication"
-	"github.com/zrepl/zrepl/replication/fsrep"
-	"io"
-	"math"
-	"net/http"
-	"os"
-	"sort"
-	"strings"
-	"sync"
-	"time"
-)
-
-type tui struct {
-	x, y   int
-	indent int
-
-	lock   sync.Mutex //For report and error
-	report map[string]job.Status
-	err    error
-}
-
-func newTui() tui {
-	return tui{}
-}
-
-func (t *tui) moveCursor(x, y int) {
-	t.x += x
-	t.y += y
-}
-
-func (t *tui) moveLine(dl int, col int) {
-	t.y += dl
-	t.x = t.indent*4 + 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 (t *tui) newline() {
-	t.moveLine(1, 0)
-}
-
-func (t *tui) setIndent(indent int) {
-	t.indent = indent
-	t.moveLine(0, 0)
-}
-
-func (t *tui) addIndent(indent int) {
-	t.indent += indent
-	t.moveLine(0, 0)
-}
-
-var statusFlags struct {
-	Raw bool
-}
-
-var StatusCmd = &cli.Subcommand{
-	Use:   "status",
-	Short: "show job activity or dump as JSON for monitoring",
-	SetupFlags: func(f *pflag.FlagSet) {
-		f.BoolVar(&statusFlags.Raw, "raw", false, "dump raw status description from zrepl daemon")
-	},
-	Run: runStatus,
-}
-
-func runStatus(s *cli.Subcommand, args []string) error {
-	httpc, err := controlHttpClient(s.Config().Global.Control.SockPath)
-	if err != nil {
-		return err
-	}
-
-	if statusFlags.Raw {
-		resp, err := httpc.Get("http://unix"+daemon.ControlJobEndpointStatus)
-		if err != nil {
-			return err
-		}
-		defer resp.Body.Close()
-		if resp.StatusCode != http.StatusOK {
-			fmt.Fprintf(os.Stderr, "Received error response:\n")
-			io.CopyN(os.Stderr, resp.Body, 4096)
-			return errors.Errorf("exit")
-		}
-		if _, err := io.Copy(os.Stdout, resp.Body); err != nil {
-			return err
-		}
-		return nil
-	}
-
-	t := newTui()
-	t.lock.Lock()
-	t.err = errors.New("Got no report yet")
-	t.lock.Unlock()
-
-	err = termbox.Init()
-	if err != nil {
-		return err
-	}
-	defer termbox.Close()
-
-	update := func() {
-		m := make(map[string]job.Status)
-
-		err2 := jsonRequestResponse(httpc, daemon.ControlJobEndpointStatus,
-			struct{}{},
-			&m,
-		)
-
-		t.lock.Lock()
-		t.err = err2
-		t.report = m
-		t.lock.Unlock()
-		t.draw()
-	}
-	update()
-
-	ticker := time.NewTicker(500 * time.Millisecond)
-	defer ticker.Stop()
-	go func() {
-		for _ = range ticker.C {
-			update()
-		}
-	}()
-
-	termbox.HideCursor()
-	termbox.Clear(termbox.ColorDefault, termbox.ColorDefault)
-
-loop:
-	for {
-		switch ev := termbox.PollEvent(); ev.Type {
-		case termbox.EventKey:
-			switch ev.Key {
-			case termbox.KeyEsc:
-				break loop
-			case termbox.KeyCtrlC:
-				break loop
-			}
-		case termbox.EventResize:
-			t.draw()
-		}
-	}
-
-	return nil
-
-}
-
-func (t *tui) draw() {
-	t.lock.Lock()
-	defer t.lock.Unlock()
-
-	termbox.Clear(termbox.ColorDefault, termbox.ColorDefault)
-	t.x = 0
-	t.y = 0
-	t.indent = 0
-
-	if t.err != nil {
-		t.write(t.err.Error())
-	} else {
-		//Iterate over map in alphabetical order
-		keys := make([]string, len(t.report))
-		i := 0
-		for k, _ := range t.report {
-			keys[i] = k
-			i++
-		}
-		sort.Strings(keys)
-
-		for _, k := range keys {
-			v := t.report[k]
-			if len(k) == 0 || daemon.IsInternalJobName(k) { //Internal job
-				continue
-			}
-			t.setIndent(0)
-
-			t.printf("Job: %s", k)
-			t.setIndent(1)
-			t.newline()
-			t.printf("Type: %s", v.Type)
-			t.setIndent(1)
-			t.newline()
-
-			if v.Type != job.TypePush && v.Type != job.TypePull {
-				t.printf("No status representation for job type '%s', dumping as YAML", v.Type)
-				t.newline()
-				asYaml, err := yaml.Marshal(v.JobSpecific)
-				if err != nil {
-					t.printf("Error marshaling status to YAML: %s", err)
-					t.newline()
-					continue
-				}
-				t.write(string(asYaml))
-				t.newline()
-				continue
-			}
-
-			pushStatus, ok := v.JobSpecific.(*job.ActiveSideStatus)
-			if !ok || pushStatus == nil {
-				t.printf("ActiveSideStatus is null")
-				t.newline()
-				continue
-			}
-
-			t.printf("Replication:")
-			t.newline()
-			t.addIndent(1)
-			t.renderReplicationReport(pushStatus.Replication)
-			t.addIndent(-1)
-
-			t.printf("Pruning Sender:")
-			t.newline()
-			t.addIndent(1)
-			t.renderPrunerReport(pushStatus.PruningSender)
-			t.addIndent(-1)
-
-			t.printf("Pruning Receiver:")
-			t.newline()
-			t.addIndent(1)
-			t.renderPrunerReport(pushStatus.PruningReceiver)
-			t.addIndent(-1)
-
-		}
-	}
-	termbox.Flush()
-}
-
-func (t *tui) renderReplicationReport(rep *replication.Report) {
-	if rep == nil {
-		t.printf("...\n")
-		return
-	}
-
-	all := make([]*fsrep.Report, 0, len(rep.Completed)+len(rep.Pending) + 1)
-	all = append(all, rep.Completed...)
-	all = append(all, rep.Pending...)
-	if rep.Active != nil {
-		all = append(all, rep.Active)
-	}
-	sort.Slice(all, func(i, j int) bool {
-		return all[i].Filesystem < all[j].Filesystem
-	})
-
-	state, err := replication.StateString(rep.Status)
-	if err != nil {
-		t.printf("Status: %q (parse error: %q)\n", rep.Status, err)
-		return
-	}
-
-	t.printf("Status: %s", state)
-	t.newline()
-	if rep.Problem != "" {
-		t.printf("Problem: %s", rep.Problem)
-		t.newline()
-	}
-	if rep.SleepUntil.After(time.Now()) && !state.IsTerminal() {
-		t.printf("Sleeping until %s (%s left)\n", rep.SleepUntil, rep.SleepUntil.Sub(time.Now()))
-	}
-
-	if state != replication.Planning && state != replication.PlanningError {
-		// Progress: [---------------]
-		sumUpFSRep := func(rep *fsrep.Report) (transferred, total int64) {
-			for _, s := range rep.Pending {
-				transferred += s.Bytes
-				total  += s.ExpectedBytes
-			}
-			for _, s := range rep.Completed {
-				transferred += s.Bytes
-				total += s.ExpectedBytes
-			}
-			return
-		}
-		var transferred, total int64
-		for _, fs := range all {
-			fstx, fstotal := sumUpFSRep(fs)
-			transferred += fstx
-			total += fstotal
-		}
-		t.write("Progress: ")
-		t.drawBar(80, transferred, total)
-		t.write(fmt.Sprintf(" %s / %s", ByteCountBinary(transferred), ByteCountBinary(total)))
-		t.newline()
-	}
-
-	var maxFSLen int
-	for _, fs := range all {
-		if len(fs.Filesystem) > maxFSLen {
-			maxFSLen = len(fs.Filesystem)
-		}
-	}
-	for _, fs := range all {
-		printFilesystemStatus(fs, t, fs == rep.Active, maxFSLen)
-	}
-}
-
-func (t *tui) renderPrunerReport(r *pruner.Report) {
-	if r == nil {
-		t.printf("...\n")
-		return
-	}
-
-	state, err := pruner.StateString(r.State)
-	if err != nil {
-		t.printf("Status: %q (parse error: %q)\n", r.State, err)
-		return
-	}
-
-	t.printf("Status: %s", state)
-	t.newline()
-
-	if r.Error != "" {
-		t.printf("Error: %s\n", r.Error)
-	}
-	if r.SleepUntil.After(time.Now()) {
-		t.printf("Sleeping until %s (%s left)\n", r.SleepUntil, r.SleepUntil.Sub(time.Now()))
-	}
-
-	type commonFS struct {
-		*pruner.FSReport
-		completed bool
-	}
-	all := make([]commonFS, 0, len(r.Pending) + len(r.Completed))
-	for i := range r.Pending {
-		all = append(all, commonFS{&r.Pending[i], false})
-	}
-	for i := range r.Completed {
-		all = append(all, commonFS{&r.Completed[i], true})
-	}
-
-	switch state {
-	case pruner.Plan: fallthrough
-	case pruner.PlanWait: fallthrough
-	case pruner.ErrPerm:
-		return
-	}
-
-	if len(all) == 0 {
-		t.printf("nothing to do\n")
-		return
-	}
-
-	var totalDestroyCount, completedDestroyCount int
-	var maxFSname int
-	for _, fs := range all {
-		totalDestroyCount += len(fs.DestroyList)
-		if fs.completed {
-			completedDestroyCount += len(fs.DestroyList)
-		}
-		if maxFSname < len(fs.Filesystem) {
-			maxFSname = len(fs.Filesystem)
-		}
-	}
-
-	// global progress bar
-	progress := int(math.Round(80 * float64(completedDestroyCount) / float64(totalDestroyCount)))
-	t.write("Progress: ")
-	t.write("[")
-	t.write(times("=", progress))
-	t.write(">")
-	t.write(times("-", 80 - progress))
-	t.write("]")
-	t.printf(" %d/%d snapshots", completedDestroyCount, totalDestroyCount)
-	t.newline()
-
-	sort.SliceStable(all, func(i, j int) bool {
-		return strings.Compare(all[i].Filesystem, all[j].Filesystem) == -1
-	})
-
-	// Draw a table-like representation of 'all'
-	for _, fs := range all {
-		t.write(rightPad(fs.Filesystem, maxFSname, " "))
-		t.write(" ")
-		if fs.Error != "" {
-			t.printf("ERROR:    %s\n", fs.Error) // whitespace is padding
-			continue
-		}
-
-		pruneRuleActionStr := fmt.Sprintf("(destroy %d of %d snapshots)",
-			len(fs.DestroyList), len(fs.SnapshotList))
-
-		if fs.completed {
-			t.printf( "Completed %s\n", pruneRuleActionStr)
-			continue
-		}
-
-		t.write("Pending   ") // whitespace is padding 10
-		if len(fs.DestroyList) == 1 {
-			t.write(fs.DestroyList[0].Name)
-		} else {
-			t.write(pruneRuleActionStr)
-		}
-		t.newline()
-	}
-
-}
-
-const snapshotIndent = 1
-func calculateMaxFSLength(all []*fsrep.Report) (maxFS, maxStatus int) {
-	for _, e := range all {
-		if len(e.Filesystem) > maxFS {
-			maxFS = len(e.Filesystem)
-		}
-		all2 := make([]*fsrep.StepReport, 0, len(e.Pending) + len(e.Completed))
-		all2 = append(all2, e.Pending...)
-		all2 = append(all2, e.Completed...)
-		for _, e2 := range all2 {
-			elen := len(e2.Problem) + len(e2.From) + len(e2.To) + 60 // random spacing, units, labels, etc
-			if elen > maxStatus {
-				maxStatus = elen
-			}
-		}
-	}
-	return
-}
-
-func times(str string, n int) (out string) {
-	for i := 0; i < n; i++ {
-		out += str
-	}
-	return
-}
-
-func rightPad(str string, length int, pad string) string {
-	if len(str) > length {
-		return str[:length]
-	}
-	return str + times(pad, length-len(str))
-}
-
-
-func leftPad(str string, length int, pad string) string {
-	if len(str) > length {
-		return str[len(str)-length:]
-	}
-	return times(pad, length-len(str)) + str
-}
-
-func (t *tui) drawBar(length int, bytes, totalBytes int64) {
-	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(">")
-	t.write(times("-", length-completedLength))
-	t.write("]")
-}
-
-func StringStepState(s fsrep.StepState) string {
-	switch s {
-	case fsrep.StepReplicationReady: return "Ready"
-	case fsrep.StepReplicationRetry: return "Retry"
-	case fsrep.StepMarkReplicatedReady: return "MarkReady"
-	case fsrep.StepMarkReplicatedRetry: return "MarkRetry"
-	case fsrep.StepPermanentError: return "PermanentError"
-	case fsrep.StepCompleted: return "Completed"
-	default:
-		return fmt.Sprintf("UNKNOWN %d", s)
-	}
-}
-
-func filesystemStatusString(rep *fsrep.Report, active bool, fsWidth int) (line string, bytes, totalBytes int64) {
-	bytes = int64(0)
-	totalBytes = int64(0)
-	for _, s := range rep.Pending {
-		bytes += s.Bytes
-		totalBytes += s.ExpectedBytes
-	}
-	for _, s := range rep.Completed {
-		bytes += s.Bytes
-		totalBytes += s.ExpectedBytes
-	}
-
-	next := ""
-	if rep.Problem != "" {
-		next = " problem: " + rep.Problem
-	} else if len(rep.Pending) > 0 {
-		if rep.Pending[0].From != "" {
-			next = fmt.Sprintf(" next: %s => %s", rep.Pending[0].From, rep.Pending[0].To)
-		} else {
-			next = fmt.Sprintf(" next: %s (full)", rep.Pending[0].To)
-		}
-	}
-	status := fmt.Sprintf("%s (step %d/%d, %s/%s)%s",
-		rep.Status,
-		len(rep.Completed), len(rep.Pending) + len(rep.Completed),
-		ByteCountBinary(bytes), ByteCountBinary(totalBytes),
-		next,
-	)
-	activeIndicator := " "
-	if active {
-		activeIndicator = "*"
-	}
-	line = fmt.Sprintf("%s %s %s",
-		activeIndicator,
-		rightPad(rep.Filesystem, fsWidth, " "),
-		status)
-	return line, bytes, totalBytes
-}
-
-func printFilesystemStatus(rep *fsrep.Report, t *tui, active bool, maxFS int) {
-	totalStatus, _, _ := filesystemStatusString(rep, active, maxFS)
-	t.write(totalStatus)
-	t.newline()
-}
-
-func ByteCountBinary(b int64) string {
-	const unit = 1024
-	if b < unit {
-		return fmt.Sprintf("%d B", b)
-	}
-	div, exp := int64(unit), 0
-	for n := b / unit; n >= unit; n /= unit {
-		div *= unit
-		exp++
-	}
-	return fmt.Sprintf("%.1f %ciB", float64(b)/float64(div), "KMGTPE"[exp])
-}

client/status/client/client.go

@@ -0,0 +1,111 @@
+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

@@ -0,0 +1,97 @@
+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

@@ -0,0 +1,70 @@
+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

@@ -0,0 +1,347 @@
+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

@@ -0,0 +1,128 @@
+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

@@ -0,0 +1,18 @@
+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

@@ -0,0 +1,26 @@
+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

@@ -0,0 +1,49 @@
+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

@@ -0,0 +1,660 @@
+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

@@ -0,0 +1,119 @@
+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/stdinserver.go

@@ -1,13 +1,15 @@
 package client
 
 import (
-	"github.com/zrepl/zrepl/cli"
 	"os"
 
+	"github.com/problame/go-netssh"
+
+	"github.com/zrepl/zrepl/cli"
+	"github.com/zrepl/zrepl/config"
+
 	"context"
 	"errors"
-	"github.com/problame/go-netssh"
-	"github.com/zrepl/zrepl/config"
 	"log"
 	"path"
 )
@@ -15,7 +17,7 @@ import (
 var StdinserverCmd = &cli.Subcommand{
 	Use:   "stdinserver CLIENT_IDENTITY",
 	Short: "stdinserver transport mode (started from authorized_keys file as forced command)",
-	Run: func(subcommand *cli.Subcommand, args []string) error {
+	Run: func(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
 		return runStdinserver(subcommand.Config(), args)
 	},
 }

client/testcmd.go

@@ -1,29 +1,35 @@
 package client
 
 import (
+	"context"
+	"encoding/json"
 	"fmt"
+	"os"
+
+	"github.com/pkg/errors"
 	"github.com/spf13/pflag"
+
 	"github.com/zrepl/zrepl/cli"
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/filters"
 	"github.com/zrepl/zrepl/zfs"
 )
 
-var TestCmd = &cli.Subcommand {
+var TestCmd = &cli.Subcommand{
 	Use: "test",
 	SetupSubcommands: func() []*cli.Subcommand {
-		return []*cli.Subcommand{testFilter}
+		return []*cli.Subcommand{testFilter, testPlaceholder, testDecodeResumeToken}
 	},
 }
 
 var testFilterArgs struct {
-	job string
-	all bool
+	job   string
+	all   bool
 	input string
 }
 
 var testFilter = &cli.Subcommand{
-	Use: "filesystems --job JOB [--all | --input INPUT]",
+	Use:   "filesystems --job JOB [--all | --input INPUT]",
 	Short: "test filesystems filter specified in push or source job",
 	SetupFlags: func(f *pflag.FlagSet) {
 		f.StringVar(&testFilterArgs.job, "job", "", "the name of the push or source job")
@@ -33,7 +39,7 @@ var testFilter = &cli.Subcommand{
 	Run: runTestFilterCmd,
 }
 
-func runTestFilterCmd(subcommand *cli.Subcommand, args []string) error {
+func runTestFilterCmd(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
 
 	if testFilterArgs.job == "" {
 		return fmt.Errorf("must specify --job flag")
@@ -50,8 +56,12 @@ func runTestFilterCmd(subcommand *cli.Subcommand, args []string) error {
 		return err
 	}
 	switch j := job.Ret.(type) {
-	case *config.SourceJob: confFilter = j.Filesystems
-	case *config.PushJob: confFilter = j.Filesystems
+	case *config.SourceJob:
+		confFilter = j.Filesystems
+	case *config.PushJob:
+		confFilter = j.Filesystems
+	case *config.SnapJob:
+		confFilter = j.Filesystems
 	default:
 		return fmt.Errorf("job type %T does not have filesystems filter", j)
 	}
@@ -65,7 +75,7 @@ func runTestFilterCmd(subcommand *cli.Subcommand, args []string) error {
 	if testFilterArgs.input != "" {
 		fsnames = []string{testFilterArgs.input}
 	} else {
-		out, err := zfs.ZFSList([]string{"name"})
+		out, err := zfs.ZFSList(ctx, []string{"name"})
 		if err != nil {
 			return fmt.Errorf("could not list ZFS filesystems: %s", err)
 		}
@@ -105,4 +115,106 @@ func runTestFilterCmd(subcommand *cli.Subcommand, args []string) error {
 		return fmt.Errorf("filter errors occurred")
 	}
 	return nil
-}
+}
+
+var testPlaceholderArgs struct {
+	ds  string
+	all bool
+}
+
+var testPlaceholder = &cli.Subcommand{
+	Use:   "placeholder [--all | --dataset DATASET]",
+	Short: fmt.Sprintf("list received placeholder filesystems (zfs property %q)", zfs.PlaceholderPropertyName),
+	Example: `
+	placeholder --all
+	placeholder --dataset path/to/sink/clientident/fs`,
+	NoRequireConfig: true,
+	SetupFlags: func(f *pflag.FlagSet) {
+		f.StringVar(&testPlaceholderArgs.ds, "dataset", "", "dataset path (not required to exist)")
+		f.BoolVar(&testPlaceholderArgs.all, "all", false, "list tab-separated placeholder status of all filesystems")
+	},
+	Run: runTestPlaceholder,
+}
+
+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")
+		}
+		for _, row := range out {
+			dp, err := zfs.NewDatasetPath(row[0])
+			if err != nil {
+				panic(err)
+			}
+			checkDPs = append(checkDPs, dp)
+		}
+	} else {
+		datasetWasExplicitArgument = true
+		dp, err := zfs.NewDatasetPath(testPlaceholderArgs.ds)
+		if err != nil {
+			return err
+		}
+		if dp.Empty() {
+			return fmt.Errorf("must specify --dataset DATASET or --all")
+		}
+		checkDPs = append(checkDPs, dp)
+	}
+
+	fmt.Printf("IS_PLACEHOLDER\tDATASET\tzrepl:placeholder\n")
+	for _, dp := range checkDPs {
+		ph, err := zfs.ZFSGetFilesystemPlaceholderState(ctx, dp)
+		if err != nil {
+			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
+			}
+		}
+		is := "yes"
+		if !ph.IsPlaceholder {
+			is = "no"
+		}
+		fmt.Printf("%s\t%s\t%s\n", is, dp.ToString(), ph.RawLocalPropertyValue)
+	}
+	return nil
+}
+
+var testDecodeResumeTokenArgs struct {
+	token string
+}
+
+var testDecodeResumeToken = &cli.Subcommand{
+	Use:   "decoderesumetoken --token TOKEN",
+	Short: "decode resume token",
+	SetupFlags: func(f *pflag.FlagSet) {
+		f.StringVar(&testDecodeResumeTokenArgs.token, "token", "", "the resume token obtained from the receive_resume_token property")
+	},
+	Run: runTestDecodeResumeTokenCmd,
+}
+
+func runTestDecodeResumeTokenCmd(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
+	if testDecodeResumeTokenArgs.token == "" {
+		return fmt.Errorf("token argument must be specified")
+	}
+	token, err := zfs.ParseResumeToken(ctx, testDecodeResumeTokenArgs.token)
+	if err != nil {
+		return err
+	}
+	enc := json.NewEncoder(os.Stdout)
+	enc.SetIndent("", " ")
+	if err := enc.Encode(&token); err != nil {
+		panic(err)
+	}
+	return nil
+}

client/version.go

@@ -1,29 +1,32 @@
 package client
 
 import (
+	"context"
 	"fmt"
+	"os"
+
 	"github.com/spf13/pflag"
+
 	"github.com/zrepl/zrepl/cli"
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon"
 	"github.com/zrepl/zrepl/version"
-	"os"
 )
 
 var versionArgs struct {
-	Show   string
-	Config *config.Config
+	Show      string
+	Config    *config.Config
 	ConfigErr error
 }
 
 var VersionCmd = &cli.Subcommand{
-	Use:   "version",
-	Short: "print version of zrepl binary and running daemon",
+	Use:             "version",
+	Short:           "print version of zrepl binary and running daemon",
 	NoRequireConfig: true,
 	SetupFlags: func(f *pflag.FlagSet) {
 		f.StringVar(&versionArgs.Show, "show", "", "version info to show (client|daemon)")
 	},
-	Run: func(subcommand *cli.Subcommand, args []string) error {
+	Run: func(ctx context.Context, subcommand *cli.Subcommand, args []string) error {
 		versionArgs.Config = subcommand.Config()
 		versionArgs.ConfigErr = subcommand.ConfigParsingError()
 		return runVersionCmd()

client/zfsabstractions.go

@@ -0,0 +1,147 @@
+package client
+
+import (
+	"fmt"
+	"sort"
+	"strings"
+
+	"github.com/spf13/pflag"
+
+	"github.com/zrepl/zrepl/cli"
+	"github.com/zrepl/zrepl/daemon/filters"
+	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+var (
+	ZFSAbstractionsCmd = &cli.Subcommand{
+		Use:   "zfs-abstraction",
+		Short: "manage abstractions that zrepl builds on top of ZFS",
+		SetupSubcommands: func() []*cli.Subcommand {
+			return []*cli.Subcommand{
+				zabsCmdList,
+				zabsCmdReleaseAll,
+				zabsCmdReleaseStale,
+				zabsCmdCreate,
+			}
+		},
+	}
+)
+
+// a common set of CLI flags that map to the fields of an
+// endpoint.ListZFSHoldsAndBookmarksQuery
+type zabsFilterFlags struct {
+	Filesystems FilesystemsFilterFlag
+	Job         JobIDFlag
+	Types       AbstractionTypesFlag
+	Concurrency int64
+}
+
+// produce a query from the CLI flags
+func (f zabsFilterFlags) Query() (endpoint.ListZFSHoldsAndBookmarksQuery, error) {
+	q := endpoint.ListZFSHoldsAndBookmarksQuery{
+		FS:          f.Filesystems.FlagValue(),
+		What:        f.Types.FlagValue(),
+		JobID:       f.Job.FlagValue(),
+		Concurrency: f.Concurrency,
+	}
+	return q, q.Validate()
+}
+
+func (f *zabsFilterFlags) registerZabsFilterFlags(s *pflag.FlagSet, verb string) {
+	// Note: the default value is defined in the .FlagValue methods
+	s.Var(&f.Filesystems, "fs", fmt.Sprintf("only %s holds on the specified filesystem [default: all filesystems] [comma-separated list of <dataset-pattern>:<ok|!> pairs]", verb))
+	s.Var(&f.Job, "job", fmt.Sprintf("only %s holds created by the specified job [default: any job]", verb))
+
+	variants := make([]string, 0, len(endpoint.AbstractionTypesAll))
+	for v := range endpoint.AbstractionTypesAll {
+		variants = append(variants, string(v))
+	}
+	sort.Strings(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))
+
+	s.Int64VarP(&f.Concurrency, "concurrency", "p", 1, "number of concurrently queried filesystems")
+}
+
+type JobIDFlag struct{ J *endpoint.JobID }
+
+func (f *JobIDFlag) Set(s string) error {
+	if len(s) == 0 {
+		*f = JobIDFlag{J: nil}
+		return nil
+	}
+
+	jobID, err := endpoint.MakeJobID(s)
+	if err != nil {
+		return err
+	}
+	*f = JobIDFlag{J: &jobID}
+	return nil
+}
+func (f JobIDFlag) Type() string               { return "job-ID" }
+func (f JobIDFlag) String() string             { return fmt.Sprint(f.J) }
+func (f JobIDFlag) FlagValue() *endpoint.JobID { return f.J }
+
+type AbstractionTypesFlag map[endpoint.AbstractionType]bool
+
+func (f *AbstractionTypesFlag) Set(s string) error {
+	ats, err := endpoint.AbstractionTypeSetFromStrings(strings.Split(s, ","))
+	if err != nil {
+		return err
+	}
+	*f = AbstractionTypesFlag(ats)
+	return nil
+}
+func (f AbstractionTypesFlag) Type() string { return "abstraction-type" }
+func (f AbstractionTypesFlag) String() string {
+	return endpoint.AbstractionTypeSet(f).String()
+}
+func (f AbstractionTypesFlag) FlagValue() map[endpoint.AbstractionType]bool {
+	if len(f) > 0 {
+		return f
+	}
+	return endpoint.AbstractionTypesAll
+}
+
+type FilesystemsFilterFlag struct {
+	F endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter
+}
+
+func (flag *FilesystemsFilterFlag) Set(s string) error {
+	mappings := strings.Split(s, ",")
+	if len(mappings) == 1 && !strings.Contains(mappings[0], ":") {
+		flag.F = endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter{
+			FS: &mappings[0],
+		}
+		return nil
+	}
+
+	f := filters.NewDatasetMapFilter(len(mappings), true)
+	for _, m := range mappings {
+		thisMappingErr := fmt.Errorf("expecting comma-separated list of <dataset-pattern>:<ok|!> pairs, got %q", m)
+		lhsrhs := strings.SplitN(m, ":", 2)
+		if len(lhsrhs) != 2 {
+			return thisMappingErr
+		}
+		err := f.Add(lhsrhs[0], lhsrhs[1])
+		if err != nil {
+			return fmt.Errorf("%s: %s", thisMappingErr, err)
+		}
+	}
+	flag.F = endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter{
+		Filter: f,
+	}
+	return nil
+}
+func (flag FilesystemsFilterFlag) Type() string { return "filesystem filter spec" }
+func (flag FilesystemsFilterFlag) String() string {
+	return fmt.Sprintf("%v", flag.F)
+}
+func (flag FilesystemsFilterFlag) FlagValue() endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter {
+	var z FilesystemsFilterFlag
+	if flag == z {
+		return endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter{Filter: zfs.NoFilter()}
+	}
+	return flag.F
+}

client/zfsabstractions_create.go

@@ -0,0 +1,14 @@
+package client
+
+import "github.com/zrepl/zrepl/cli"
+
+var zabsCmdCreate = &cli.Subcommand{
+	Use:             "create",
+	NoRequireConfig: true,
+	Short:           `create zrepl ZFS abstractions (mostly useful for debugging & development, users should not need to use this command)`,
+	SetupSubcommands: func() []*cli.Subcommand {
+		return []*cli.Subcommand{
+			zabsCmdCreateStepHold,
+		}
+	},
+}

client/zfsabstractions_create_step_hold.go

@@ -0,0 +1,58 @@
+package client
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/pkg/errors"
+	"github.com/spf13/pflag"
+
+	"github.com/zrepl/zrepl/cli"
+	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+var zabsCreateStepHoldFlags struct {
+	target string
+	jobid  JobIDFlag
+}
+
+var zabsCmdCreateStepHold = &cli.Subcommand{
+	Use:             "step",
+	Run:             doZabsCreateStep,
+	NoRequireConfig: true,
+	Short:           `create a step hold or bookmark`,
+	SetupFlags: func(f *pflag.FlagSet) {
+		f.StringVarP(&zabsCreateStepHoldFlags.target, "target", "t", "", "snapshot to be held / bookmark to be held")
+		f.VarP(&zabsCreateStepHoldFlags.jobid, "jobid", "j", "jobid for which the hold is installed")
+	},
+}
+
+func doZabsCreateStep(ctx context.Context, sc *cli.Subcommand, args []string) error {
+	if len(args) > 0 {
+		return errors.New("subcommand takes no arguments")
+	}
+
+	f := &zabsCreateStepHoldFlags
+
+	fs, _, _, err := zfs.DecomposeVersionString(f.target)
+	if err != nil {
+		return errors.Wrapf(err, "%q invalid target", f.target)
+	}
+
+	if f.jobid.FlagValue() == nil {
+		return errors.Errorf("jobid must be set")
+	}
+
+	v, err := zfs.ZFSGetFilesystemVersion(ctx, f.target)
+	if err != nil {
+		return errors.Wrapf(err, "get info about target %q", f.target)
+	}
+
+	step, err := endpoint.HoldStep(ctx, fs, v, *f.jobid.FlagValue())
+	if err != nil {
+		return errors.Wrap(err, "create step hold")
+	}
+	fmt.Println(step.String())
+	return nil
+}

client/zfsabstractions_list.go

@@ -0,0 +1,100 @@
+package client
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"os"
+	"sync"
+
+	"github.com/fatih/color"
+	"github.com/pkg/errors"
+	"github.com/spf13/pflag"
+
+	"github.com/zrepl/zrepl/cli"
+	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/util/chainlock"
+)
+
+var zabsListFlags struct {
+	Filter zabsFilterFlags
+	Json   bool
+}
+
+var zabsCmdList = &cli.Subcommand{
+	Use:             "list",
+	Short:           `list zrepl ZFS abstractions`,
+	Run:             doZabsList,
+	NoRequireConfig: true,
+	SetupFlags: func(f *pflag.FlagSet) {
+		zabsListFlags.Filter.registerZabsFilterFlags(f, "list")
+		f.BoolVar(&zabsListFlags.Json, "json", false, "emit JSON")
+	},
+}
+
+func doZabsList(ctx context.Context, sc *cli.Subcommand, args []string) error {
+	var err error
+
+	if len(args) > 0 {
+		return errors.New("this subcommand takes no positional arguments")
+	}
+
+	q, err := zabsListFlags.Filter.Query()
+	if err != nil {
+		return errors.Wrap(err, "invalid filter specification on command line")
+	}
+
+	abstractions, errors, drainDone, 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()
+
+	// print results
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		enc := json.NewEncoder(os.Stdout)
+		for a := range abstractions {
+			func() {
+				defer line.Lock().Unlock()
+				if zabsListFlags.Json {
+					enc.SetIndent("", "  ")
+					if err := enc.Encode(a); err != nil {
+						panic(err)
+					}
+					fmt.Println()
+				} else {
+					fmt.Println(a)
+				}
+			}()
+		}
+	}()
+
+	// print errors to stderr
+	errorColor := color.New(color.FgRed)
+	var errorsSlice []endpoint.ListAbstractionsError
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		for err := range errors {
+			func() {
+				defer line.Lock().Unlock()
+				errorsSlice = append(errorsSlice, err)
+				errorColor.Fprintf(os.Stderr, "%s\n", err)
+			}()
+		}
+	}()
+	wg.Wait()
+	if len(errorsSlice) > 0 {
+		errorColor.Add(color.Bold).Fprintf(os.Stderr, "there were errors in listing the abstractions")
+		return fmt.Errorf("")
+	} else {
+		return nil
+	}
+
+}

client/zfsabstractions_release.go

@@ -0,0 +1,143 @@
+package client
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"os"
+
+	"github.com/fatih/color"
+	"github.com/pkg/errors"
+	"github.com/spf13/pflag"
+
+	"github.com/zrepl/zrepl/cli"
+	"github.com/zrepl/zrepl/endpoint"
+)
+
+// shared between release-all and release-step
+var zabsReleaseFlags struct {
+	Filter zabsFilterFlags
+	Json   bool
+	DryRun bool
+}
+
+func registerZabsReleaseFlags(s *pflag.FlagSet) {
+	zabsReleaseFlags.Filter.registerZabsFilterFlags(s, "release")
+	s.BoolVar(&zabsReleaseFlags.Json, "json", false, "emit json instead of pretty-printed")
+	s.BoolVar(&zabsReleaseFlags.DryRun, "dry-run", false, "do a dry-run")
+}
+
+var zabsCmdReleaseAll = &cli.Subcommand{
+	Use:             "release-all",
+	Run:             doZabsReleaseAll,
+	NoRequireConfig: true,
+	Short:           `(DANGEROUS) release ALL zrepl ZFS abstractions (mostly useful for uninstalling zrepl completely or for "de-zrepl-ing" a filesystem)`,
+	SetupFlags:      registerZabsReleaseFlags,
+}
+
+var zabsCmdReleaseStale = &cli.Subcommand{
+	Use:             "release-stale",
+	Run:             doZabsReleaseStale,
+	NoRequireConfig: true,
+	Short:           `release stale zrepl ZFS abstractions (useful if zrepl has a bug and does not do it by itself)`,
+	SetupFlags:      registerZabsReleaseFlags,
+}
+
+func doZabsReleaseAll(ctx context.Context, sc *cli.Subcommand, args []string) error {
+	var err error
+
+	if len(args) > 0 {
+		return errors.New("this subcommand takes no positional arguments")
+	}
+
+	q, err := zabsReleaseFlags.Filter.Query()
+	if err != nil {
+		return errors.Wrap(err, "invalid filter specification on command line")
+	}
+
+	abstractions, listErrors, err := endpoint.ListAbstractions(ctx, q)
+	if err != nil {
+		return err // context clear by invocation of command
+	}
+	if len(listErrors) > 0 {
+		color.New(color.FgRed).Fprintf(os.Stderr, "there were errors in listing the abstractions:\n%s\n", listErrors)
+		// proceed anyways with rest of abstractions
+	}
+
+	return doZabsRelease_Common(ctx, abstractions)
+}
+
+func doZabsReleaseStale(ctx context.Context, sc *cli.Subcommand, args []string) error {
+
+	var err error
+
+	if len(args) > 0 {
+		return errors.New("this subcommand takes no positional arguments")
+	}
+
+	q, err := zabsReleaseFlags.Filter.Query()
+	if err != nil {
+		return errors.Wrap(err, "invalid filter specification on command line")
+	}
+
+	stalenessInfo, err := endpoint.ListStale(ctx, q)
+	if err != nil {
+		return err // context clear by invocation of command
+	}
+
+	return doZabsRelease_Common(ctx, stalenessInfo.Stale)
+}
+
+func doZabsRelease_Common(ctx context.Context, destroy []endpoint.Abstraction) error {
+
+	if zabsReleaseFlags.DryRun {
+		if zabsReleaseFlags.Json {
+			m, err := json.MarshalIndent(destroy, "", "  ")
+			if err != nil {
+				panic(err)
+			}
+			if _, err := os.Stdout.Write(m); err != nil {
+				panic(err)
+			}
+			fmt.Println()
+		} else {
+			for _, a := range destroy {
+				fmt.Printf("would destroy %s\n", a)
+			}
+		}
+		return nil
+	}
+
+	outcome := endpoint.BatchDestroy(ctx, destroy)
+	hadErr := false
+
+	enc := json.NewEncoder(os.Stdout)
+	enc.SetIndent("", "  ")
+	colorErr := color.New(color.FgRed)
+	printfSuccess := color.New(color.FgGreen).FprintfFunc()
+	printfSection := color.New(color.Bold).FprintfFunc()
+
+	for res := range outcome {
+		hadErr = hadErr || res.DestroyErr != nil
+		if zabsReleaseFlags.Json {
+			err := enc.Encode(res)
+			if err != nil {
+				colorErr.Fprintf(os.Stderr, "cannot marshal there were errors in destroying the abstractions")
+			}
+		} else {
+			printfSection(os.Stdout, "destroy %s ...", res.Abstraction)
+			if res.DestroyErr != nil {
+				colorErr.Fprintf(os.Stdout, " failed:\n%s\n", res.DestroyErr)
+			} else {
+				printfSuccess(os.Stdout, " OK\n")
+			}
+		}
+	}
+
+	if hadErr {
+		colorErr.Add(color.Bold).Fprintf(os.Stderr, "there were errors in destroying the abstractions")
+		return fmt.Errorf("")
+	} else {
+		return nil
+	}
+}

config/config.go

@@ -2,14 +2,25 @@ package config
 
 import (
 	"fmt"
-	"github.com/pkg/errors"
-	"github.com/zrepl/yaml-config"
 	"io/ioutil"
+	"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 {
@@ -33,54 +44,175 @@ type JobEnum struct {
 func (j JobEnum) Name() string {
 	var name string
 	switch v := j.Ret.(type) {
-	case *PushJob: name = v.Name
-	case *SinkJob: name = v.Name
-	case *PullJob: name = v.Name
-	case *SourceJob: name = v.Name
+	case *SnapJob:
+		name = v.Name
+	case *PushJob:
+		name = v.Name
+	case *SinkJob:
+		name = v.Name
+	case *PullJob:
+		name = v.Name
+	case *SourceJob:
+		name = v.Name
 	default:
-		panic(fmt.Sprintf("unknownn job type %T", v))
+		panic(fmt.Sprintf("unknown job type %T", v))
 	}
 	return name
 }
 
 type ActiveJob struct {
-	Type         string                `yaml:"type"`
-	Name         string                `yaml:"name"`
-	Connect     ConnectEnum     `yaml:"connect"`
-	Pruning      PruningSenderReceiver `yaml:"pruning"`
-	Debug        JobDebugSettings      `yaml:"debug,optional"`
+	Type               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 PassiveJob struct {
-	Type        string           `yaml:"type"`
-	Name        string           `yaml:"name"`
-	Serve       ServeEnum `yaml:"serve"`
-	Debug       JobDebugSettings `yaml:"debug,optional"`
+	Type  string    `yaml:"type"`
+	Name  string    `yaml:"name"`
+	Serve ServeEnum `yaml:"serve"`
+}
+
+type SnapJob struct {
+	Type         string            `yaml:"type"`
+	Name         string            `yaml:"name"`
+	Pruning      PruningLocal      `yaml:"pruning"`
+	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"`
+
+	BandwidthLimit *BandwidthLimit `yaml:"bandwidth_limit,optional,fromdefaults"`
+}
+
+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{}
+
+type BandwidthLimit struct {
+	Max            datasizeunit.Bits `yaml:"max,default=-1 B"`
+	BucketCapacity datasizeunit.Bits `yaml:"bucket_capacity,default=128 KiB"`
+}
+
+type Replication struct {
+	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 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"`
 }
 
 type PushJob struct {
-	ActiveJob `yaml:",inline"`
-	Snapshotting SnapshottingEnum          `yaml:"snapshotting"`
-	Filesystems FilesystemsFilter `yaml:"filesystems"`
+	ActiveJob    `yaml:",inline"`
+	Snapshotting SnapshottingEnum  `yaml:"snapshotting"`
+	Filesystems  FilesystemsFilter `yaml:"filesystems"`
+	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  time.Duration `yaml:"interval,positive"`
+	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
+}
+
+var _ yaml.Unmarshaler = (*PositiveDurationOrManual)(nil)
+
+func (i *PositiveDurationOrManual) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
+	var s string
+	if err := u(&s, true); err != nil {
+		return err
+	}
+	switch s {
+	case "manual":
+		i.Manual = true
+		i.Interval = 0
+	case "":
+		return fmt.Errorf("value must not be empty")
+	default:
+		i.Manual = false
+		i.Interval, err = parsePositiveDuration(s)
+		if err != nil {
+			return err
+		}
+	}
+	return nil
 }
 
 type SinkJob struct {
 	PassiveJob `yaml:",inline"`
-	RootFS     string `yaml:"root_fs"`
+	RootFS     string       `yaml:"root_fs"`
+	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"`
-	Filesystems FilesystemsFilter `yaml:"filesystems"`
+	PassiveJob   `yaml:",inline"`
+	Snapshotting SnapshottingEnum  `yaml:"snapshotting"`
+	Filesystems  FilesystemsFilter `yaml:"filesystems"`
+	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 {
@@ -88,9 +220,44 @@ type SnapshottingEnum struct {
 }
 
 type SnapshottingPeriodic struct {
-	Type string		`yaml:"type"`
-	Prefix string	`yaml:"prefix"`
-	Interval time.Duration `yaml:"interval,positive"`
+	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 SnapshottingManual struct {
@@ -130,7 +297,6 @@ type Global struct {
 	Monitoring []MonitoringEnum       `yaml:"monitoring,optional"`
 	Control    *GlobalControl         `yaml:"control,optional,fromdefaults"`
 	Serve      *GlobalServe           `yaml:"serve,optional,fromdefaults"`
-	RPC        *RPCConfig             `yaml:"rpc,optional,fromdefaults"`
 }
 
 func Default(i interface{}) {
@@ -145,39 +311,28 @@ func Default(i interface{}) {
 	}
 }
 
-type RPCConfig struct {
-	Timeout             time.Duration `yaml:"timeout,optional,positive,default=10s"`
-	TxChunkSize         uint32        `yaml:"tx_chunk_size,optional,default=32768"`
-	RxStructuredMaxLen  uint32        `yaml:"rx_structured_max,optional,default=16777216"`
-	RxStreamChunkMaxLen uint32        `yaml:"rx_stream_chunk_max,optional,default=16777216"`
-	RxHeaderMaxLen      uint32        `yaml:"rx_header_max,optional,default=40960"`
-	SendHeartbeatInterval             time.Duration `yaml:"send_heartbeat_interval,optional,positive,default=5s"`
-
-}
-
 type ConnectEnum struct {
 	Ret interface{}
 }
 
 type ConnectCommon struct {
-	Type string     `yaml:"type"`
-	RPC  *RPCConfig `yaml:"rpc,optional"`
+	Type string `yaml:"type"`
 }
 
 type TCPConnect struct {
 	ConnectCommon `yaml:",inline"`
-	Address       string        `yaml:"address"`
-	DialTimeout   time.Duration `yaml:"dial_timeout,positive,default=10s"`
+	Address       string        `yaml:"address,hostport"`
+	DialTimeout   time.Duration `yaml:"dial_timeout,zeropositive,default=10s"`
 }
 
 type TLSConnect struct {
 	ConnectCommon `yaml:",inline"`
-	Address       string        `yaml:"address"`
+	Address       string        `yaml:"address,hostport"`
 	Ca            string        `yaml:"ca"`
 	Cert          string        `yaml:"cert"`
 	Key           string        `yaml:"key"`
 	ServerCN      string        `yaml:"server_cn"`
-	DialTimeout   time.Duration `yaml:"dial_timeout,positive,default=10s"`
+	DialTimeout   time.Duration `yaml:"dial_timeout,zeropositive,default=10s"`
 }
 
 type SSHStdinserverConnect struct {
@@ -189,13 +344,14 @@ type SSHStdinserverConnect struct {
 	TransportOpenCommand []string      `yaml:"transport_open_command,optional"` //TODO unused
 	SSHCommand           string        `yaml:"ssh_command,optional"`            //TODO unused
 	Options              []string      `yaml:"options,optional"`
-	DialTimeout          time.Duration `yaml:"dial_timeout,positive,default=10s"`
+	DialTimeout          time.Duration `yaml:"dial_timeout,zeropositive,default=10s"`
 }
 
 type LocalConnect struct {
-	ConnectCommon `yaml:",inline"`
-	ListenerName string `yaml:"listener_name"`
-	ClientIdentity string `yaml:"client_identity"`
+	ConnectCommon  `yaml:",inline"`
+	ListenerName   string        `yaml:"listener_name"`
+	ClientIdentity string        `yaml:"client_identity"`
+	DialTimeout    time.Duration `yaml:"dial_timeout,zeropositive,default=2s"`
 }
 
 type ServeEnum struct {
@@ -203,33 +359,34 @@ type ServeEnum struct {
 }
 
 type ServeCommon struct {
-	Type string     `yaml:"type"`
-	RPC  *RPCConfig `yaml:"rpc,optional"`
+	Type string `yaml:"type"`
 }
 
 type TCPServe struct {
-	ServeCommon `yaml:",inline"`
-	Listen      string            `yaml:"listen"`
-	Clients     map[string]string `yaml:"clients"`
+	ServeCommon    `yaml:",inline"`
+	Listen         string            `yaml:"listen,hostport"`
+	ListenFreeBind bool              `yaml:"listen_freebind,default=false"`
+	Clients        map[string]string `yaml:"clients"`
 }
 
 type TLSServe struct {
 	ServeCommon      `yaml:",inline"`
-	Listen           string        `yaml:"listen"`
+	Listen           string        `yaml:"listen,hostport"`
+	ListenFreeBind   bool          `yaml:"listen_freebind,default=false"`
 	Ca               string        `yaml:"ca"`
 	Cert             string        `yaml:"cert"`
 	Key              string        `yaml:"key"`
 	ClientCNs        []string      `yaml:"client_cns"`
-	HandshakeTimeout time.Duration `yaml:"handshake_timeout,positive,default=10s"`
+	HandshakeTimeout time.Duration `yaml:"handshake_timeout,zeropositive,default=10s"`
 }
 
 type StdinserverServer struct {
-	ServeCommon    `yaml:",inline"`
+	ServeCommon      `yaml:",inline"`
 	ClientIdentities []string `yaml:"client_identities"`
 }
 
 type LocalServe struct {
-	ServeCommon `yaml:",inline"`
+	ServeCommon  `yaml:",inline"`
 	ListenerName string `yaml:"listener_name"`
 }
 
@@ -238,18 +395,20 @@ type PruningEnum struct {
 }
 
 type PruneKeepNotReplicated struct {
-	Type string `yaml:"type"`
-	KeepSnapshotAtCursor bool `yaml:"keep_snapshot_at_cursor,optional,default=true"`
+	Type                 string `yaml:"type"`
+	KeepSnapshotAtCursor bool   `yaml:"keep_snapshot_at_cursor,optional,default=true"`
 }
 
 type PruneKeepLastN struct {
 	Type  string `yaml:"type"`
 	Count int    `yaml:"count"`
+	Regex string `yaml:"regex,optional"`
 }
 
 type PruneKeepRegex struct { // FIXME rename to KeepRegex
-	Type  string `yaml:"type"`
-	Regex string `yaml:"regex"`
+	Type   string `yaml:"type"`
+	Regex  string `yaml:"regex"`
+	Negate bool   `yaml:"negate,optional,default=false"`
 }
 
 type LoggingOutletEnum struct {
@@ -270,12 +429,13 @@ type StdoutLoggingOutlet struct {
 
 type SyslogLoggingOutlet struct {
 	LoggingOutletCommon `yaml:",inline"`
-	RetryInterval       time.Duration `yaml:"retry_interval,positive,default=10s"`
+	Facility            *SyslogFacility `yaml:"facility,optional,fromdefaults"`
+	RetryInterval       time.Duration   `yaml:"retry_interval,positive,default=10s"`
 }
 
 type TCPLoggingOutlet struct {
 	LoggingOutletCommon `yaml:",inline"`
-	Address             string               `yaml:"address"`
+	Address             string               `yaml:"address,hostport"`
 	Net                 string               `yaml:"net,default=tcp"`
 	RetryInterval       time.Duration        `yaml:"retry_interval,positive,default=10s"`
 	TLS                 *TCPLoggingOutletTLS `yaml:"tls,optional"`
@@ -292,10 +452,19 @@ type MonitoringEnum struct {
 }
 
 type PrometheusMonitoring struct {
-	Type   string `yaml:"type"`
-	Listen string `yaml:"listen"`
+	Type           string `yaml:"type"`
+	Listen         string `yaml:"listen,hostport"`
+	ListenFreeBind bool   `yaml:"listen_freebind,default=false"`
 }
 
+type SyslogFacility syslog.Priority
+
+func (f *SyslogFacility) SetDefault() {
+	*f = SyslogFacility(syslog.LOG_LOCAL0)
+}
+
+var _ yaml.Defaulter = (*SyslogFacility)(nil)
+
 type GlobalControl struct {
 	SockPath string `yaml:"sockpath,default=/var/run/zrepl/control"`
 }
@@ -308,12 +477,36 @@ 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 {
+	Ret interface{}
+}
+
+type HookCommand struct {
+	Path               string            `yaml:"path"`
+	Timeout            time.Duration     `yaml:"timeout,optional,positive,default=30s"`
+	Filesystems        FilesystemsFilter `yaml:"filesystems,optional,default={'<': true}"`
+	HookSettingsCommon `yaml:",inline"`
+}
+
+type HookPostgresCheckpoint struct {
+	HookSettingsCommon `yaml:",inline"`
+	DSN                string            `yaml:"dsn"`
+	Timeout            time.Duration     `yaml:"timeout,optional,positive,default=30s"`
+	Filesystems        FilesystemsFilter `yaml:"filesystems"` // required, user should not CHECKPOINT for every FS
+}
+
+type HookMySQLLockTables struct {
+	HookSettingsCommon `yaml:",inline"`
+	DSN                string            `yaml:"dsn"`
+	Timeout            time.Duration     `yaml:"timeout,optional,positive,default=30s"`
+	Filesystems        FilesystemsFilter `yaml:"filesystems"`
+}
+
+type HookSettingsCommon struct {
+	Type       string `yaml:"type"`
+	ErrIsFatal bool   `yaml:"err_is_fatal,optional,default=false"`
 }
 
 func enumUnmarshal(u func(interface{}, bool) error, types map[string]interface{}) (interface{}, error) {
@@ -339,6 +532,7 @@ func enumUnmarshal(u func(interface{}, bool) error, types map[string]interface{}
 
 func (t *JobEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
 	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
+		"snap":   &SnapJob{},
 		"push":   &PushJob{},
 		"sink":   &SinkJob{},
 		"pull":   &PullJob{},
@@ -352,7 +546,7 @@ func (t *ConnectEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error)
 		"tcp":             &TCPConnect{},
 		"tls":             &TLSConnect{},
 		"ssh+stdinserver": &SSHStdinserverConnect{},
-		"local": 		   &LocalConnect{},
+		"local":           &LocalConnect{},
 	})
 	return
 }
@@ -362,7 +556,7 @@ func (t *ServeEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
 		"tcp":         &TCPServe{},
 		"tls":         &TLSServe{},
 		"stdinserver": &StdinserverServer{},
-		"local"      : &LocalServe{},
+		"local":       &LocalServe{},
 	})
 	return
 }
@@ -380,7 +574,8 @@ func (t *PruningEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error)
 func (t *SnapshottingEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
 	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
 		"periodic": &SnapshottingPeriodic{},
-		"manual": &SnapshottingManual{},
+		"manual":   &SnapshottingManual{},
+		"cron":     &SnapshottingCron{},
 	})
 	return
 }
@@ -401,6 +596,69 @@ func (t *MonitoringEnum) UnmarshalYAML(u func(interface{}, bool) error) (err err
 	return
 }
 
+func (t *SyslogFacility) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
+	var s string
+	if err := u(&s, true); err != nil {
+		return err
+	}
+	var level syslog.Priority
+	switch s {
+	case "kern":
+		level = syslog.LOG_KERN
+	case "user":
+		level = syslog.LOG_USER
+	case "mail":
+		level = syslog.LOG_MAIL
+	case "daemon":
+		level = syslog.LOG_DAEMON
+	case "auth":
+		level = syslog.LOG_AUTH
+	case "syslog":
+		level = syslog.LOG_SYSLOG
+	case "lpr":
+		level = syslog.LOG_LPR
+	case "news":
+		level = syslog.LOG_NEWS
+	case "uucp":
+		level = syslog.LOG_UUCP
+	case "cron":
+		level = syslog.LOG_CRON
+	case "authpriv":
+		level = syslog.LOG_AUTHPRIV
+	case "ftp":
+		level = syslog.LOG_FTP
+	case "local0":
+		level = syslog.LOG_LOCAL0
+	case "local1":
+		level = syslog.LOG_LOCAL1
+	case "local2":
+		level = syslog.LOG_LOCAL2
+	case "local3":
+		level = syslog.LOG_LOCAL3
+	case "local4":
+		level = syslog.LOG_LOCAL4
+	case "local5":
+		level = syslog.LOG_LOCAL5
+	case "local6":
+		level = syslog.LOG_LOCAL6
+	case "local7":
+		level = syslog.LOG_LOCAL7
+	default:
+		return fmt.Errorf("invalid syslog level: %q", s)
+	}
+	*t = SyslogFacility(level)
+	return nil
+}
+
+func (t *HookEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
+	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
+		"command":             &HookCommand{},
+		"postgres-checkpoint": &HookPostgresCheckpoint{},
+		"mysql-lock-tables":   &HookMySQLLockTables{},
+	})
+	return
+}
+
 var ConfigFileDefaultLocations = []string{
 	"/etc/zrepl/zrepl.yml",
 	"/usr/local/etc/zrepl/zrepl.yml",
@@ -443,41 +701,3 @@ 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 parsePostitiveDuration(e string) (d time.Duration, err error) {
-	comps := durationStringRegex.FindStringSubmatch(e)
-	if len(comps) != 3 {
-		err = fmt.Errorf("does not match regex: %s %#v", e, comps)
-		return
-	}
-
-	durationFactor, err := strconv.ParseInt(comps[1], 10, 64)
-	if err != nil {
-		return 0, err
-	}
-	if durationFactor <= 0 {
-		return 0, errors.New("duration must be positive integer")
-	}
-
-	var durationUnit time.Duration
-	switch comps[2] {
-	case "s":
-		durationUnit = time.Second
-	case "m":
-		durationUnit = time.Minute
-	case "h":
-		durationUnit = time.Hour
-	case "d":
-		durationUnit = 24 * time.Hour
-	case "w":
-		durationUnit = 24 * 7 * time.Hour
-	default:
-		err = fmt.Errorf("contains unknown time unit '%s'", comps[2])
-		return
-	}
-
-	d = time.Duration(durationFactor) * durationUnit
-	return
-}

config/config_dep_test.go

@@ -0,0 +1,90 @@
+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

@@ -0,0 +1,106 @@
+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

@@ -1,10 +1,13 @@
 package config
 
 import (
+	"fmt"
+	"log/syslog"
+	"testing"
+
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"github.com/zrepl/yaml-config"
-	"testing"
 )
 
 func testValidGlobalSection(t *testing.T, s string) *Config {
@@ -18,11 +21,11 @@ jobs:
     clients: {
       "10.0.0.1":"foo"
     }
-  root_fs: zoot/foo
+  root_fs: zroot/foo
 `
 	_, err := ParseConfigBytes([]byte(jobdef))
 	require.NoError(t, err)
-	return testValidConfig(t, s + jobdef)
+	return testValidConfig(t, s+jobdef)
 }
 
 func TestOutletTypes(t *testing.T) {
@@ -67,9 +70,39 @@ func TestPrometheusMonitoring(t *testing.T) {
 global:
   monitoring:
     - type: prometheus
-      listen: ':9091'
+      listen: ':9811'
 `)
-	assert.Equal(t, ":9091", conf.Global.Monitoring[0].Ret.(*PrometheusMonitoring).Listen)	
+	assert.Equal(t, ":9811", conf.Global.Monitoring[0].Ret.(*PrometheusMonitoring).Listen)
+}
+
+func TestSyslogLoggingOutletFacility(t *testing.T) {
+	type SyslogFacilityPriority struct {
+		Facility string
+		Priority syslog.Priority
+	}
+	syslogFacilitiesPriorities := []SyslogFacilityPriority{
+		{"", syslog.LOG_LOCAL0}, // default
+		{"kern", syslog.LOG_KERN}, {"daemon", syslog.LOG_DAEMON}, {"auth", syslog.LOG_AUTH},
+		{"syslog", syslog.LOG_SYSLOG}, {"lpr", syslog.LOG_LPR}, {"news", syslog.LOG_NEWS},
+		{"uucp", syslog.LOG_UUCP}, {"cron", syslog.LOG_CRON}, {"authpriv", syslog.LOG_AUTHPRIV},
+		{"ftp", syslog.LOG_FTP}, {"local0", syslog.LOG_LOCAL0}, {"local1", syslog.LOG_LOCAL1},
+		{"local2", syslog.LOG_LOCAL2}, {"local3", syslog.LOG_LOCAL3}, {"local4", syslog.LOG_LOCAL4},
+		{"local5", syslog.LOG_LOCAL5}, {"local6", syslog.LOG_LOCAL6}, {"local7", syslog.LOG_LOCAL7},
+	}
+
+	for _, sFP := range syslogFacilitiesPriorities {
+		logcfg := fmt.Sprintf(`
+global:
+  logging:
+  - type: syslog
+    level: info
+    format: human
+    facility: %s
+`, sFP.Facility)
+		conf := testValidGlobalSection(t, logcfg)
+		assert.Equal(t, 1, len(*conf.Global.Logging))
+		assert.True(t, SyslogFacility(sFP.Priority) == *(*conf.Global.Logging)[0].Ret.(*SyslogLoggingOutlet).Facility)
+	}
 }
 
 func TestLoggingOutletEnumList_SetDefaults(t *testing.T) {

config/config_jobid_test.go

@@ -0,0 +1 @@
+package config

config/config_minimal_test.go

@@ -2,6 +2,7 @@ package config
 
 import (
 	"testing"
+
 	"github.com/stretchr/testify/assert"
 )
 
@@ -36,4 +37,4 @@ jobs:
     - type: last_n 
       count: 1
 `)
-}
+}

config/config_positiveintervalormanual_test.go

@@ -0,0 +1,41 @@
+package config
+
+import (
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/zrepl/yaml-config"
+)
+
+func TestPositiveDurationOrManual(t *testing.T) {
+	cases := []struct {
+		Comment, Input string
+		Result         *PositiveDurationOrManual
+	}{
+		{"empty is error", "", nil},
+		{"negative is error", "-1s", nil},
+		{"zero seconds is error", "0s", nil},
+		{"zero is error", "0", nil},
+		{"non-manual is error", "something", nil},
+		{"positive seconds works", "1s", &PositiveDurationOrManual{Manual: false, Interval: 1 * time.Second}},
+		{"manual works", "manual", &PositiveDurationOrManual{Manual: true, Interval: 0}},
+	}
+	for _, tc := range cases {
+		t.Run(tc.Comment, func(t *testing.T) {
+			var out struct {
+				FieldName PositiveDurationOrManual `yaml:"fieldname"`
+			}
+			input := fmt.Sprintf("\nfieldname: %s\n", tc.Input)
+			err := yaml.UnmarshalStrict([]byte(input), &out)
+			if tc.Result == nil {
+				assert.Error(t, err)
+				t.Logf("%#v", out)
+			} else {
+				assert.Equal(t, *tc.Result, out.FieldName)
+			}
+		})
+	}
+
+}

config/config_recv_test.go

@@ -0,0 +1,134 @@
+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_rpc_test.go

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

config/config_send_test.go

@@ -0,0 +1,146 @@
+package config
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestSendOptions(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
+`
+	encrypted_false := `
+  send:
+    encrypted: false
+`
+
+	encrypted_true := `
+  send:
+    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 := `
+  send: {}
+`
+
+	send_not_specified := `
+`
+
+	fill := func(s string) string { return fmt.Sprintf(tmpl, s) }
+
+	t.Run("encrypted_false", func(t *testing.T) {
+		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))
+		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("send_not_specified", func(t *testing.T) {
+		c := testValidConfig(t, fill(send_not_specified))
+		assert.NotNil(t, c)
+	})
+
+}

config/config_snapshotting_test.go

@@ -2,9 +2,10 @@ package config
 
 import (
 	"fmt"
-	"github.com/stretchr/testify/assert"
 	"testing"
 	"time"
+
+	"github.com/stretchr/testify/assert"
 )
 
 func TestSnapshotting(t *testing.T) {
@@ -34,10 +35,48 @@ jobs:
   snapshotting:
     type: periodic
     prefix: zrepl_
+    timestamp_format: dense
     interval: 10m
 `
+	cron := `
+  snapshotting:
+    type: cron
+    prefix: zrepl_
+    timestamp_format: human
+    cron: "10 * * * *"
+`
 
-	fillSnapshotting := func(s string) string {return fmt.Sprintf(tmpl, s)}
+	periodicDaily := `
+  snapshotting:
+    type: periodic
+    prefix: zrepl_
+    interval: 1d
+`
+
+	hooks := `
+  snapshotting:
+    type: periodic
+    prefix: zrepl_
+    interval: 10m
+    hooks:
+    - type: command
+      path: /tmp/path/to/command
+    - type: command
+      path: /tmp/path/to/command
+      filesystems: { "zroot<": true, "<": false }
+    - type: postgres-checkpoint
+      dsn: "host=localhost port=5432 user=postgres sslmode=disable"
+      filesystems: {
+          "tank/postgres/data11": true
+      }
+    - type: mysql-lock-tables
+      dsn: "root@tcp(localhost)/"
+      filesystems: {
+        "tank/mysql": true
+      }
+`
+
+	fillSnapshotting := func(s string) string { return fmt.Sprintf(tmpl, s) }
 	var c *Config
 
 	t.Run("manual", func(t *testing.T) {
@@ -50,8 +89,88 @@ 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)
-		assert.Equal(t, "zrepl_" , snp.Prefix)
+		assert.Equal(t, 10*time.Minute, snp.Interval.Duration())
+		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
+		assert.Equal(t, hs[0].Ret.(*HookCommand).Filesystems["<"], true)
+		assert.Equal(t, hs[1].Ret.(*HookCommand).Filesystems["zroot<"], true)
+		assert.Equal(t, hs[2].Ret.(*HookPostgresCheckpoint).Filesystems["tank/postgres/data11"], true)
+		assert.Equal(t, hs[3].Ret.(*HookMySQLLockTables).Filesystems["tank/mysql"], true)
 	})
 
 }
+
+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

@@ -1,11 +1,19 @@
 package config
 
 import (
-	"github.com/kr/pretty"
-	"github.com/stretchr/testify/require"
+	"bufio"
+	"bytes"
+	"fmt"
 	"path"
 	"path/filepath"
+	"strings"
 	"testing"
+	"text/template"
+
+	"github.com/kr/pretty"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"github.com/zrepl/yaml-config"
 )
 
 func TestSampleConfigsAreParsedWithoutErrors(t *testing.T) {
@@ -35,8 +43,23 @@ func TestSampleConfigsAreParsedWithoutErrors(t *testing.T) {
 
 }
 
+// template must be a template/text template with a single '{{ . }}' as placeholder for val
+//
+//nolint:deadcode,unused
+func testValidConfigTemplate(t *testing.T, tmpl string, val string) *Config {
+	tmp, err := template.New("master").Parse(tmpl)
+	if err != nil {
+		panic(err)
+	}
+	var buf bytes.Buffer
+	err = tmp.Execute(&buf, val)
+	if err != nil {
+		panic(err)
+	}
+	return testValidConfig(t, buf.String())
+}
 
-func testValidConfig(t *testing.T, input string) (*Config) {
+func testValidConfig(t *testing.T, input string) *Config {
 	t.Helper()
 	conf, err := testConfig(t, input)
 	require.NoError(t, err)
@@ -47,4 +70,71 @@ func testValidConfig(t *testing.T, input string) (*Config) {
 func testConfig(t *testing.T, input string) (*Config, error) {
 	t.Helper()
 	return ParseConfigBytes([]byte(input))
-}
+}
+
+func trimSpaceEachLineAndPad(s, pad string) string {
+	var out strings.Builder
+	scan := bufio.NewScanner(strings.NewReader(s))
+	for scan.Scan() {
+		fmt.Fprintf(&out, "%s%s\n", pad, bytes.TrimSpace(scan.Bytes()))
+	}
+	return out.String()
+}
+
+func TestTrimSpaceEachLineAndPad(t *testing.T) {
+	foo := `
+	foo
+	bar baz 
+	`
+	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/config_transport_test.go

@@ -0,0 +1,99 @@
+package config
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestTransportConnect(t *testing.T) {
+	tmpl := `
+jobs:
+- name: foo
+  type: push
+  connect:
+%s
+  filesystems: {"<": true}
+  snapshotting:
+    type: manual
+  pruning:
+    keep_sender:
+    - type: last_n
+      count: 10
+    keep_receiver:
+    - type: last_n
+      count: 10
+`
+
+	mconf := func(s string) string { return fmt.Sprintf(tmpl, s) }
+
+	type test struct {
+		Name        string
+		ExpectError bool
+		Connect     string
+	}
+
+	testTable := []test{
+		{
+			Name:        "tcp_with_address_and_port",
+			ExpectError: false,
+			Connect: `
+			type: tcp
+			address: 10.0.0.23:42
+			`,
+		},
+		{
+			Name:        "tls_with_host_and_port",
+			ExpectError: false,
+			Connect: `
+			type: tls
+			address: "server1.foo.bar:8888"
+			ca:   /etc/zrepl/ca.crt
+			cert: /etc/zrepl/backupserver.fullchain
+			key:  /etc/zrepl/backupserver.key
+			server_cn: "server1"
+			`,
+		},
+		{
+			Name:        "tcp_without_port",
+			ExpectError: true,
+			Connect: `
+			type: tcp
+			address: 10.0.0.23
+			`,
+		},
+		{
+			Name:        "tls_without_port",
+			ExpectError: true,
+			Connect: `
+			type: tls
+			address: 10.0.0.23
+			ca:   /etc/zrepl/ca.crt
+			cert: /etc/zrepl/backupserver.fullchain
+			key:  /etc/zrepl/backupserver.key
+			server_cn: "server1"
+			`,
+		},
+	}
+
+	for _, tc := range testTable {
+		t.Run(tc.Name, func(t *testing.T) {
+			require.NotEmpty(t, tc.Connect)
+			connect := trimSpaceEachLineAndPad(tc.Connect, "    ")
+			conf := mconf(connect)
+			config, err := testConfig(t, conf)
+			if tc.ExpectError && err == nil {
+				t.Errorf("expected test failure, but got valid config %v", config)
+				return
+			}
+			if !tc.ExpectError && err != nil {
+				t.Errorf("not expecint test failure but got error: %s", err)
+				return
+			}
+			t.Logf("error=%v", err)
+			t.Logf("config=%v", config)
+		})
+	}
+
+}

config/retentiongrid.go

@@ -11,9 +11,9 @@ import (
 type RetentionIntervalList []RetentionInterval
 
 type PruneGrid struct {
-	Type          string                `yaml:"type"`
-	Grid          RetentionIntervalList `yaml:"grid"`
-	Regex	      string                `yaml:"regex"`
+	Type  string                `yaml:"type"`
+	Grid  RetentionIntervalList `yaml:"grid"`
+	Regex string                `yaml:"regex"`
 }
 
 type RetentionInterval struct {
@@ -31,17 +31,13 @@ func (i *RetentionInterval) KeepCount() int {
 
 const RetentionGridKeepCountAll int = -1
 
-type RetentionGrid struct {
-	intervals []RetentionInterval
-}
-
 func (t *RetentionIntervalList) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
 	var in string
 	if err := u(&in, true); err != nil {
 		return err
 	}
 
-	intervals, err := parseRetentionGridIntervalsString(in)
+	intervals, err := ParseRetentionIntervalSpec(in)
 	if err != nil {
 		return err
 	}
@@ -68,7 +64,7 @@ func parseRetentionGridIntervalString(e string) (intervals []RetentionInterval,
 		return nil, fmt.Errorf("contains factor <= 0")
 	}
 
-	duration, err := parsePostitiveDuration(comps[2])
+	duration, err := parsePositiveDuration(comps[2])
 	if err != nil {
 		return nil, err
 	}
@@ -106,7 +102,7 @@ func parseRetentionGridIntervalString(e string) (intervals []RetentionInterval,
 
 }
 
-func parseRetentionGridIntervalsString(s string) (intervals []RetentionInterval, err error) {
+func ParseRetentionIntervalSpec(s string) (intervals []RetentionInterval, err error) {
 
 	ges := strings.Split(s, "|")
 	intervals = make([]RetentionInterval, 0, 7*len(ges))

config/samples/bandwidth_limit.yml

@@ -0,0 +1,41 @@
+
+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/hooks/template.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+set -e
+
+[ "$ZREPL_DRYRUN" = "true" ] && DRYRUN="echo DRYRUN: "
+
+pre_snapshot() {
+    $DRYRUN date
+}
+
+post_snapshot() {
+    $DRYRUN date
+}
+
+case "$ZREPL_HOOKTYPE" in
+    pre_snapshot|post_snapshot)
+        "$ZREPL_HOOKTYPE"
+        ;;
+    *)
+        printf 'Unrecognized hook type: %s\n' "$ZREPL_HOOKTYPE"
+        exit 255
+        ;;
+esac

config/samples/pull_ssh.yml

@@ -9,7 +9,7 @@ jobs:
     port: 22
     identity_file: /etc/zrepl/ssh/identity
     options: # optional, default [], `-o` arguments passed to ssh
-    - "Compression=on"
+    - "Compression=yes"
   root_fs: "pool2/backup_servers"
   interval: 10m
   pruning:

config/samples/push.yml

@@ -10,6 +10,8 @@ jobs:
       address: "backup-server.foo.bar:8888"
     snapshotting:
       type: manual
+    send:
+      encrypted: false
     pruning:
       keep_sender:
         - type: not_replicated

config/samples/quickstart_backup_to_external_disk.yml

@@ -0,0 +1,88 @@
+# 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

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

@@ -0,0 +1,28 @@
+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

@@ -0,0 +1,59 @@
+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

@@ -0,0 +1,30 @@
+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.yml

@@ -0,0 +1,14 @@
+jobs:
+- name: snapjob
+  type: snap
+  filesystems: {
+    "tank/frequently_changed<": true,
+  }
+  snapshotting:
+    type: periodic
+    interval: 2m
+    prefix: zrepl_snapjob_
+  pruning:
+    keep:
+      - type: last_n
+        count: 60

config/samples/snap_cron.yml

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

config/samples/source.yml

@@ -5,7 +5,11 @@ jobs:
     type: tcp
     listen: "0.0.0.0:8888"
     clients: {
-      "192.168.122.123" : "client1"
+      "192.168.122.123" :               "mysql01",
+      "192.168.122.42" :                "mx01",
+      "2001:0db8:85a3::8a2e:0370:7334": "gateway",
+      "10.23.42.0/24":       "cluster-*",
+      "fde4:8dba:82e1::/64": "san-*",
     }
   filesystems: {
     "<": true,

daemon/control.go

@@ -5,16 +5,23 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
-	"github.com/pkg/errors"
-	"github.com/prometheus/client_golang/prometheus"
-	"github.com/zrepl/zrepl/daemon/job"
-	"github.com/zrepl/zrepl/daemon/nethelpers"
-	"github.com/zrepl/zrepl/logger"
-	"github.com/zrepl/zrepl/version"
 	"io"
 	"net"
 	"net/http"
+	"os"
 	"time"
+
+	"github.com/pkg/errors"
+	"github.com/prometheus/client_golang/prometheus"
+
+	"github.com/zrepl/zrepl/daemon/job"
+	"github.com/zrepl/zrepl/daemon/nethelpers"
+	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/util/envconst"
+	"github.com/zrepl/zrepl/version"
+	"github.com/zrepl/zrepl/zfs"
+	"github.com/zrepl/zrepl/zfs/zfscmd"
 )
 
 type controlJob struct {
@@ -38,25 +45,29 @@ func (j *controlJob) Name() string { return jobNameControl }
 
 func (j *controlJob) Status() *job.Status { return &job.Status{Type: job.TypeInternal} }
 
+func (j *controlJob) OwnedDatasetSubtreeRoot() (p *zfs.DatasetPath, ok bool) { return nil, false }
+
+func (j *controlJob) SenderConfig() *endpoint.SenderConfig { return nil }
+
 var promControl struct {
-	requestBegin *prometheus.CounterVec
+	requestBegin    *prometheus.CounterVec
 	requestFinished *prometheus.HistogramVec
 }
 
 func (j *controlJob) RegisterMetrics(registerer prometheus.Registerer) {
 	promControl.requestBegin = prometheus.NewCounterVec(prometheus.CounterOpts{
-		Namespace:   "zrepl",
-		Subsystem:   "control",
-		Name:        "request_begin",
-		Help:        "number of request we started to handle",
+		Namespace: "zrepl",
+		Subsystem: "control",
+		Name:      "request_begin",
+		Help:      "number of request we started to handle",
 	}, []string{"endpoint"})
 
 	promControl.requestFinished = prometheus.NewHistogramVec(prometheus.HistogramOpts{
-		Namespace:   "zrepl",
-		Subsystem:   "control",
-		Name:        "request_finished",
-		Help:        "time it took a request to finih",
-		Buckets: []float64{1e-6, 10e-6, 100e-6, 500e-6, 1e-3,10e-3, 100e-3, 200e-3,400e-3,800e-3, 1, 10, 20},
+		Namespace: "zrepl",
+		Subsystem: "control",
+		Name:      "request_finished",
+		Help:      "time it took a request to finish",
+		Buckets:   []float64{1e-6, 10e-6, 100e-6, 500e-6, 1e-3, 10e-3, 100e-3, 200e-3, 400e-3, 800e-3, 1, 10, 20},
 	}, []string{"endpoint"})
 	registerer.MustRegister(promControl.requestBegin)
 	registerer.MustRegister(promControl.requestFinished)
@@ -81,10 +92,16 @@ func (j *controlJob) Run(ctx context.Context) {
 	}
 
 	pprofServer := NewPProfServer(ctx)
+	if listen := envconst.String("ZREPL_DAEMON_AUTOSTART_PPROF_SERVER", ""); listen != "" {
+		pprofServer.Control(PprofServerControlMsg{
+			Run:               true,
+			HttpListenAddress: listen,
+		})
+	}
 
 	mux := http.NewServeMux()
 	mux.Handle(ControlJobEndpointPProf,
-		requestLogger{log: log, handler: jsonRequestResponder{func(decoder jsonDecoder) (interface{}, error) {
+		requestLogger{log: log, handler: jsonRequestResponder{log, func(decoder jsonDecoder) (interface{}, error) {
 			var msg PprofServerControlMsg
 			err := decoder(&msg)
 			if err != nil {
@@ -95,21 +112,31 @@ func (j *controlJob) Run(ctx context.Context) {
 		}}})
 
 	mux.Handle(ControlJobEndpointVersion,
-		requestLogger{log: log, handler: jsonResponder{func() (interface{}, error) {
+		requestLogger{log: log, handler: jsonResponder{log, func() (interface{}, error) {
 			return version.NewZreplVersionInformation(), nil
 		}}})
 
 	mux.Handle(ControlJobEndpointStatus,
-		requestLogger{log: log, handler: jsonResponder{func() (interface{}, error) {
-			s := j.jobs.status()
+		// don't log requests to status endpoint, too spammy
+		jsonResponder{log, func() (interface{}, error) {
+			jobs := j.jobs.status()
+			globalZFS := zfscmd.GetReport()
+			envconstReport := envconst.GetReport()
+			s := Status{
+				Jobs: jobs,
+				Global: GlobalStatus{
+					ZFSCmds:   globalZFS,
+					Envconst:  envconstReport,
+					OsEnviron: os.Environ(),
+				}}
 			return s, nil
-		}}})
+		}})
 
 	mux.Handle(ControlJobEndpointSignal,
-		requestLogger{log: log, handler: jsonRequestResponder{func(decoder jsonDecoder) (interface{}, error) {
+		requestLogger{log: log, handler: jsonRequestResponder{log, func(decoder jsonDecoder) (interface{}, error) {
 			type reqT struct {
 				Name string
-				Op string
+				Op   string
 			}
 			var req reqT
 			if decoder(&req) != nil {
@@ -131,8 +158,8 @@ 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: 1*time.Second,
-		ReadTimeout: 1*time.Second,
+		WriteTimeout: envconst.Duration("ZREPL_DAEMON_CONTROL_SERVER_WRITE_TIMEOUT", 1*time.Second),
+		ReadTimeout:  envconst.Duration("ZREPL_DAEMON_CONTROL_SERVER_READ_TIMEOUT", 1*time.Second),
 	}
 
 outer:
@@ -147,7 +174,10 @@ outer:
 		select {
 		case <-ctx.Done():
 			log.WithError(ctx.Err()).Info("context done")
-			server.Shutdown(context.Background())
+			err := server.Shutdown(context.Background())
+			if err != nil {
+				log.WithError(err).Error("cannot shutdown server")
+			}
 			break outer
 		case err = <-served:
 			if err != nil {
@@ -161,33 +191,50 @@ outer:
 }
 
 type jsonResponder struct {
+	log      Logger
 	producer func() (interface{}, error)
 }
 
 func (j jsonResponder) ServeHTTP(w http.ResponseWriter, r *http.Request) {
+	logIoErr := func(err error) {
+		if err != nil {
+			j.log.WithError(err).Error("control handler io error")
+		}
+	}
 	res, err := j.producer()
 	if err != nil {
+		j.log.WithError(err).Error("control handler error")
 		w.WriteHeader(http.StatusInternalServerError)
-		io.WriteString(w, err.Error())
+		_, err = io.WriteString(w, err.Error())
+		logIoErr(err)
 		return
 	}
 	var buf bytes.Buffer
 	err = json.NewEncoder(&buf).Encode(res)
 	if err != nil {
+		j.log.WithError(err).Error("control handler json marshal error")
 		w.WriteHeader(http.StatusInternalServerError)
-		io.WriteString(w, err.Error())
+		_, err = io.WriteString(w, err.Error())
 	} else {
-		io.Copy(w, &buf)
+		_, err = io.Copy(w, &buf)
 	}
+	logIoErr(err)
 }
 
 type jsonDecoder = func(interface{}) error
 
 type jsonRequestResponder struct {
+	log      Logger
 	producer func(decoder jsonDecoder) (interface{}, error)
 }
 
 func (j jsonRequestResponder) ServeHTTP(w http.ResponseWriter, r *http.Request) {
+	logIoErr := func(err error) {
+		if err != nil {
+			j.log.WithError(err).Error("control handler io error")
+		}
+	}
+
 	var decodeError error
 	decoder := func(i interface{}) error {
 		err := json.NewDecoder(r.Body).Decode(&i)
@@ -199,22 +246,28 @@ func (j jsonRequestResponder) ServeHTTP(w http.ResponseWriter, r *http.Request)
 	//If we had a decode error ignore output of producer and return error
 	if decodeError != nil {
 		w.WriteHeader(http.StatusBadRequest)
-		io.WriteString(w, decodeError.Error())
+		_, err := io.WriteString(w, decodeError.Error())
+		logIoErr(err)
 		return
 	}
 	if producerErr != nil {
+		j.log.WithError(producerErr).Error("control handler error")
 		w.WriteHeader(http.StatusInternalServerError)
-		io.WriteString(w, producerErr.Error())
+		_, err := io.WriteString(w, producerErr.Error())
+		logIoErr(err)
 		return
 	}
 
 	var buf bytes.Buffer
 	encodeErr := json.NewEncoder(&buf).Encode(res)
 	if encodeErr != nil {
+		j.log.WithError(producerErr).Error("control handler json marshal error")
 		w.WriteHeader(http.StatusInternalServerError)
-		io.WriteString(w, encodeErr.Error())
+		_, err := io.WriteString(w, encodeErr.Error())
+		logIoErr(err)
 	} else {
-		io.Copy(w, &buf)
+		_, err := io.Copy(w, &buf)
+		logIoErr(err)
 	}
 }
 

daemon/daemon.go

@@ -3,8 +3,21 @@ package daemon
 import (
 	"context"
 	"fmt"
+	"math/rand"
+	"os"
+	"os/signal"
+	"strings"
+	"sync"
+	"syscall"
+	"time"
+
 	"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"
+
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/job"
 	"github.com/zrepl/zrepl/daemon/job/reset"
@@ -12,17 +25,11 @@ import (
 	"github.com/zrepl/zrepl/daemon/logging"
 	"github.com/zrepl/zrepl/logger"
 	"github.com/zrepl/zrepl/version"
-	"os"
-	"os/signal"
-	"strings"
-	"sync"
-	"syscall"
-	"time"
+	"github.com/zrepl/zrepl/zfs/zfscmd"
 )
 
-func Run(conf *config.Config) error {
-
-	ctx, cancel := context.WithCancel(context.Background())
+func Run(ctx context.Context, conf *config.Config) error {
+	ctx, cancel := context.WithCancel(ctx)
 
 	defer cancel()
 	sigChan := make(chan os.Signal, 1)
@@ -32,12 +39,19 @@ func Run(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)
+	confJobs, err := job.JobsFromConfig(conf, config.ParseFlagsNone)
 	if err != nil {
 		return errors.Wrap(err, "cannot build jobs from config")
 	}
@@ -45,14 +59,23 @@ func Run(conf *config.Config) error {
 	log := logger.NewLogger(outlets, 1*time.Second)
 	log.Info(version.NewZreplVersionInformation().String())
 
+	ctx = logging.WithLoggers(ctx, logging.SubsystemLoggersWithUniversalLogger(log))
+	trace.RegisterCallback(trace.Callback{
+		OnBegin: func(ctx context.Context) { logging.GetLogger(ctx, logging.SubsysTraceData).Debug("begin span") },
+		OnEnd: func(ctx context.Context, spanInfo trace.SpanInfo) {
+			logging.
+				GetLogger(ctx, logging.SubsysTraceData).
+				WithField("duration_s", spanInfo.EndedAt().Sub(spanInfo.StartedAt()).Seconds()).
+				Debug("finished span " + spanInfo.TaskAndSpanStack(trace.SpanStackKindAnnotation))
+		},
+	})
+
 	for _, job := range confJobs {
 		if IsInternalJobName(job.Name()) {
 			panic(fmt.Sprintf("internal job name used for config job '%s'", job.Name())) //FIXME
 		}
 	}
 
-	ctx = job.WithLogger(ctx, log)
-
 	jobs := newJobs()
 
 	// start control socket
@@ -74,11 +97,16 @@ func Run(conf *config.Config) error {
 			return errors.Errorf("unknown monitoring job #%d (type %T)", i, v)
 		}
 		if err != nil {
-			return errors.Wrapf(err,"cannot build monitorin gjob #%d", i)
+			return errors.Wrapf(err, "cannot build monitoring job #%d", i)
 		}
 		jobs.start(ctx, job, true)
 	}
 
+	// register global (=non job-local) metrics
+	version.PrometheusRegister(prometheus.DefaultRegisterer)
+	zfscmd.RegisterMetrics(prometheus.DefaultRegisterer)
+	trace.RegisterMetrics(prometheus.DefaultRegisterer)
+	endpoint.RegisterMetrics(prometheus.DefaultRegisterer)
 
 	log.Info("starting daemon")
 
@@ -93,6 +121,8 @@ func Run(conf *config.Config) error {
 	case <-ctx.Done():
 		log.WithError(ctx.Err()).Info("context finished")
 	}
+	log.Info("waiting for jobs to finish")
+	<-jobs.wait()
 	log.Info("daemon exiting")
 	return nil
 }
@@ -103,7 +133,7 @@ type jobs struct {
 	// m protects all fields below it
 	m       sync.RWMutex
 	wakeups map[string]wakeup.Func // by Job.Name
-	resets map[string]reset.Func // by Job.Name
+	resets  map[string]reset.Func  // by Job.Name
 	jobs    map[string]job.Job
 }
 
@@ -115,20 +145,26 @@ func newJobs() *jobs {
 	}
 }
 
-const (
-	logJobField    string = "job"
-	logTaskField   string = "task"
-	logSubsysField string = "subsystem"
-)
-
 func (s *jobs) wait() <-chan struct{} {
 	ch := make(chan struct{})
 	go func() {
 		s.wg.Wait()
+		close(ch)
 	}()
 	return ch
 }
 
+type Status struct {
+	Jobs   map[string]*job.Status
+	Global GlobalStatus
+}
+
+type GlobalStatus struct {
+	ZFSCmds   *zfscmd.Report
+	Envconst  *envconst.Report
+	OsEnviron []string
+}
+
 func (s *jobs) status() map[string]*job.Status {
 	s.m.RLock()
 	defer s.m.RUnlock()
@@ -190,9 +226,8 @@ func (s *jobs) start(ctx context.Context, j job.Job, internal bool) {
 	s.m.Lock()
 	defer s.m.Unlock()
 
-	jobLog := job.GetLogger(ctx).
-		WithField(logJobField, j.Name()).
-		WithOutlet(newPrometheusLogOutlet(j.Name()), logger.Debug)
+	ctx = logging.WithInjectedField(ctx, logging.JobField, j.Name())
+
 	jobName := j.Name()
 	if !internal && IsInternalJobName(jobName) {
 		panic(fmt.Sprintf("internal job name used for non-internal job %s", jobName))
@@ -207,7 +242,7 @@ func (s *jobs) start(ctx context.Context, j job.Job, internal bool) {
 	j.RegisterMetrics(prometheus.DefaultRegisterer)
 
 	s.jobs[jobName] = j
-	ctx = job.WithLogger(ctx, jobLog)
+	ctx = zfscmd.WithJobID(ctx, j.Name())
 	ctx, wakeup := wakeup.Context(ctx)
 	ctx, resetFunc := reset.Context(ctx)
 	s.wakeups[jobName] = wakeup
@@ -216,8 +251,8 @@ func (s *jobs) start(ctx context.Context, j job.Job, internal bool) {
 	s.wg.Add(1)
 	go func() {
 		defer s.wg.Done()
-		jobLog.Info("starting job")
-		defer jobLog.Info("job exited")
+		job.GetLogger(ctx).Info("starting job")
+		defer job.GetLogger(ctx).Info("job exited")
 		j.Run(ctx)
 	}()
 }

daemon/filters/fsmapfilter.go

@@ -2,10 +2,12 @@ package filters
 
 import (
 	"fmt"
+	"strings"
+
 	"github.com/pkg/errors"
+
 	"github.com/zrepl/zrepl/endpoint"
 	"github.com/zrepl/zrepl/zfs"
-	"strings"
 )
 
 type DatasetMapFilter struct {
@@ -158,8 +160,16 @@ 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 excactly those paths that were not forbidden by the mapping.
+// The new filter allows exactly those paths that were not forbidden by the mapping.
 func (m DatasetMapFilter) InvertedFilter() (inv *DatasetMapFilter, err error) {
 
 	if m.filterMode {

daemon/filters/fsmapfilter_test.go

@@ -0,0 +1,89 @@
+package filters
+
+import (
+	"testing"
+
+	"github.com/zrepl/zrepl/zfs"
+)
+
+func TestDatasetMapFilter(t *testing.T) {
+
+	type testCase struct {
+		name      string
+		filter    map[string]string
+		checkPass map[string]bool // each entry is checked to match the filter's `pass` return value
+	}
+
+	tcs := []testCase{
+		{
+			"default_no_match",
+			map[string]string{},
+			map[string]bool{
+				"":      false,
+				"foo":   false,
+				"zroot": false,
+			},
+		},
+		{
+			"more_specific_path_has_precedence",
+			map[string]string{
+				"tank<":         "ok",
+				"tank/tmp<":     "!",
+				"tank/home/x<":  "!",
+				"tank/home/x/1": "ok",
+			},
+			map[string]bool{
+				"zroot":         false,
+				"tank":          true,
+				"tank/tmp":      false,
+				"tank/tmp/foo":  false,
+				"tank/home/x":   false,
+				"tank/home/y":   true,
+				"tank/home/x/1": true,
+				"tank/home/x/2": false,
+			},
+		},
+		{
+			"precedence_of_specific_over_subtree_wildcard_on_same_path",
+			map[string]string{
+				"tank/home/bob":  "ok",
+				"tank/home/bob<": "!",
+			},
+			map[string]bool{
+				"tank/home/bob":           true,
+				"tank/home/bob/downloads": false,
+			},
+		},
+	}
+
+	for tc := range tcs {
+		t.Run(tcs[tc].name, func(t *testing.T) {
+			c := tcs[tc]
+			f := NewDatasetMapFilter(len(c.filter), true)
+			for p, a := range c.filter {
+				err := f.Add(p, a)
+				if err != nil {
+					t.Fatalf("incorrect filter spec: %s", err)
+				}
+			}
+			for p, checkPass := range c.checkPass {
+				zp, err := zfs.NewDatasetPath(p)
+				if err != nil {
+					t.Fatalf("incorrect path spec: %s", err)
+				}
+				pass, err := f.Filter(zp)
+				if err != nil {
+					t.Fatalf("unexpected filter error: %s", err)
+				}
+				ok := pass == checkPass
+				failstr := "OK"
+				if !ok {
+					failstr = "FAIL"
+					t.Fail()
+				}
+				t.Logf("%-40q  %5v  (exp=%v act=%v)", p, failstr, checkPass, pass)
+			}
+		})
+	}
+
+}

daemon/filters/fsvfilter.go

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

daemon/hooks/edge_string.go

@@ -0,0 +1,35 @@
+// Code generated by "stringer -type=Edge"; DO NOT EDIT.
+
+package hooks
+
+import "strconv"
+
+func _() {
+	// An "invalid array index" compiler error signifies that the constant values have changed.
+	// Re-run the stringer command to generate them again.
+	var x [1]struct{}
+	_ = x[Pre-1]
+	_ = x[Callback-2]
+	_ = x[Post-4]
+}
+
+const (
+	_Edge_name_0 = "PreCallback"
+	_Edge_name_1 = "Post"
+)
+
+var (
+	_Edge_index_0 = [...]uint8{0, 3, 11}
+)
+
+func (i Edge) String() string {
+	switch {
+	case 1 <= i && i <= 2:
+		i -= 1
+		return _Edge_name_0[_Edge_index_0[i]:_Edge_index_0[i+1]]
+	case i == 4:
+		return _Edge_name_1
+	default:
+		return "Edge(" + strconv.FormatInt(int64(i), 10) + ")"
+	}
+}

daemon/hooks/hook_config.go

@@ -0,0 +1,52 @@
+package hooks
+
+import (
+	"fmt"
+
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+type List []Hook
+
+func HookFromConfig(in config.HookEnum) (Hook, error) {
+	switch v := in.Ret.(type) {
+	case *config.HookCommand:
+		return NewCommandHook(v)
+	case *config.HookPostgresCheckpoint:
+		return PgChkptHookFromConfig(v)
+	case *config.HookMySQLLockTables:
+		return MyLockTablesFromConfig(v)
+	default:
+		return nil, fmt.Errorf("unknown hook type %T", v)
+	}
+}
+
+func ListFromConfig(in *config.HookList) (r *List, err error) {
+	hl := make(List, len(*in))
+
+	for i, h := range *in {
+		hl[i], err = HookFromConfig(h)
+		if err != nil {
+			return nil, fmt.Errorf("create hook #%d: %s", i+1, err)
+		}
+	}
+
+	return &hl, nil
+}
+
+func (l List) CopyFilteredForFilesystem(fs *zfs.DatasetPath) (ret List, err error) {
+	ret = make(List, 0, len(l))
+
+	for _, h := range l {
+		var passFilesystem bool
+		if passFilesystem, err = h.Filesystems().Filter(fs); err != nil {
+			return nil, err
+		}
+		if passFilesystem {
+			ret = append(ret, h)
+		}
+	}
+
+	return ret, nil
+}

daemon/hooks/hook_docs.go

@@ -0,0 +1,33 @@
+// Package hooks implements pre- and post snapshot hooks.
+//
+// Plan is a generic executor for ExpectStepReports before and after an activity specified in a callback.
+// It provides a reporting facility that can be polled while the plan is executing to gather progress information.
+//
+// This package also provides all supported hook type implementations and abstractions around them.
+//
+// # 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:
+//
+// The Hook interface requires a hook to provide a Filesystems() filter, which doesn't make sense for
+// all kinds of activities.
+//
+// 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
+//
+// Deserialize a config.List using ListFromConfig().
+// Then it MUST filter the list to only contain hooks for a particular filesystem using
+// hooksList.CopyFilteredForFilesystem(fs).
+//
+// Then create a CallbackHook using NewCallbackHookForFilesystem().
+//
+// Pass all of the above to NewPlan() which provides a Report() and Run() method:
+//
+// Plan.Run(ctx context.Context,dryRun bool) executes the plan and take a context as argument that should contain a logger added using hooks.WithLogger()).
+// The value of dryRun is passed through to the hooks' Run() method.
+// 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_exec.go

@@ -0,0 +1,292 @@
+package hooks
+
+import (
+	"context"
+	"fmt"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/zrepl/zrepl/zfs"
+)
+
+// Re-export type here so that
+// every file in package hooks doesn't
+// have to import github.com/zrepl/zrepl/zfs
+type Filter zfs.DatasetFilter
+
+type Hook interface {
+	Filesystems() Filter
+
+	// If true and the Pre edge invocation of Run fails, Post edge will not run and other Pre edges will not run.
+	ErrIsFatal() bool
+
+	// Run is invoked by HookPlan for a Pre edge.
+	// If HookReport.HadError() == false, the Post edge will be invoked, too.
+	Run(ctx context.Context, edge Edge, phase Phase, dryRun bool, extra Env, state map[interface{}]interface{}) HookReport
+
+	String() string
+}
+
+type Phase string
+
+const (
+	PhaseSnapshot = Phase("snapshot")
+	PhaseTesting  = Phase("testing")
+)
+
+func (p Phase) String() string {
+	return string(p)
+}
+
+//go:generate stringer -type=Edge
+type Edge uint
+
+const (
+	Pre = Edge(1 << iota)
+	Callback
+	Post
+)
+
+func (e Edge) StringForPhase(phase Phase) string {
+	return fmt.Sprintf("%s_%s", e.String(), phase.String())
+}
+
+//go:generate enumer -type=StepStatus -trimprefix=Step
+type StepStatus int
+
+const (
+	StepPending StepStatus = 1 << iota
+	StepExec
+	StepOk
+	StepErr
+	StepSkippedDueToFatalErr
+	StepSkippedDueToPreErr
+)
+
+type HookReport interface {
+	String() string
+	HadError() bool
+	Error() string
+}
+
+type Step struct {
+	Hook       Hook
+	Edge       Edge
+	Status     StepStatus
+	Begin, End time.Time
+	// Report may be nil
+	// FIXME cannot serialize this for client status, but contains interesting info (like what error happened)
+	Report HookReport
+	state  map[interface{}]interface{}
+}
+
+func (s Step) String() (out string) {
+	fatal := "~"
+	if s.Hook.ErrIsFatal() && s.Edge == Pre {
+		fatal = "!"
+	}
+	runTime := "..."
+	if s.Status != StepPending {
+		t := s.End.Sub(s.Begin)
+		runTime = t.Round(time.Millisecond).String()
+	}
+	return fmt.Sprintf("[%s] [%5s] %s [%s]  %s", s.Status, runTime, fatal, s.Edge, s.Hook)
+}
+
+type Plan struct {
+	mtx sync.RWMutex
+
+	steps []*Step
+	pre   []*Step // protected by mtx
+	cb    *Step
+	post  []*Step // not reversed, i.e. entry at index i corresponds to pre-edge in pre[i]
+
+	phase Phase
+	env   Env
+}
+
+func NewPlan(hooks *List, phase Phase, cb *CallbackHook, extra Env) (*Plan, error) {
+
+	var pre, post []*Step
+	// TODO sanity check unique name of hook?
+	for _, hook := range *hooks {
+		state := make(map[interface{}]interface{})
+		preE := &Step{
+			Hook:   hook,
+			Edge:   Pre,
+			Status: StepPending,
+			state:  state,
+		}
+		pre = append(pre, preE)
+		postE := &Step{
+			Hook:   hook,
+			Edge:   Post,
+			Status: StepPending,
+			state:  state,
+		}
+		post = append(post, postE)
+	}
+
+	cbE := &Step{
+		Hook:   cb,
+		Edge:   Callback,
+		Status: StepPending,
+	}
+
+	steps := make([]*Step, 0, len(pre)+len(post)+1)
+	steps = append(steps, pre...)
+	steps = append(steps, cbE)
+	for i := len(post) - 1; i >= 0; i-- {
+		steps = append(steps, post[i])
+	}
+
+	plan := &Plan{
+		phase: phase,
+		env:   extra,
+		steps: steps,
+		pre:   pre,
+		post:  post,
+		cb:    cbE,
+	}
+
+	return plan, nil
+}
+
+type PlanReport []Step
+
+func (p *Plan) Report() PlanReport {
+	p.mtx.RLock()
+	defer p.mtx.RUnlock()
+	rep := make([]Step, len(p.steps))
+	for i := range rep {
+		rep[i] = *p.steps[i]
+	}
+	return rep
+}
+
+func (r PlanReport) HadError() bool {
+	for _, e := range r {
+		if e.Status == StepErr {
+			return true
+		}
+	}
+	return false
+}
+
+func (r PlanReport) HadFatalError() bool {
+	for _, e := range r {
+		if e.Status == StepSkippedDueToFatalErr {
+			return true
+		}
+	}
+	return false
+}
+
+func (r PlanReport) String() string {
+	stepStrings := make([]string, len(r))
+	for i, e := range r {
+		stepStrings[i] = fmt.Sprintf("%02d %s", i+1, e)
+	}
+	return strings.Join(stepStrings, "\n")
+}
+
+func (p *Plan) Run(ctx context.Context, dryRun bool) {
+	p.mtx.RLock()
+	defer p.mtx.RUnlock()
+	w := func(f func()) {
+		p.mtx.RUnlock()
+		defer p.mtx.RLock()
+		p.mtx.Lock()
+		defer p.mtx.Unlock()
+		f()
+	}
+	runHook := func(s *Step, ctx context.Context, edge Edge) HookReport {
+		w(func() { s.Status = StepExec })
+		begin := time.Now()
+		r := s.Hook.Run(ctx, edge, p.phase, dryRun, p.env, s.state)
+		end := time.Now()
+		w(func() {
+			s.Report = r
+			s.Status = StepOk
+			if r.HadError() {
+				s.Status = StepErr
+			}
+			s.Begin, s.End = begin, end
+		})
+		return r
+	}
+
+	l := getLogger(ctx)
+
+	// it's a stack, execute until we reach the end of the list (last item in)
+	// or fail inbetween
+	l.Info("run pre-edges in configuration order")
+	next := 0
+	for ; next < len(p.pre); next++ {
+		e := p.pre[next]
+		l := l.WithField("hook", e.Hook)
+		r := runHook(e, ctx, Pre)
+		if r.HadError() {
+			l.WithError(r).Error("hook invocation failed for pre-edge")
+			if e.Hook.ErrIsFatal() {
+				l.Error("the hook run was aborted due to a fatal error in this hook")
+				break
+			}
+		}
+	}
+
+	hadFatalErr := next != len(p.pre)
+	if hadFatalErr {
+		l.Error("fatal error in a pre-snapshot hook invocation")
+		l.Error("no snapshot will be taken")
+		l.Error("only running post-edges for successful pre-edges")
+		w(func() {
+			p.post[next].Status = StepSkippedDueToFatalErr
+			for i := next + 1; i < len(p.pre); i++ {
+				p.pre[i].Status = StepSkippedDueToFatalErr
+				p.post[i].Status = StepSkippedDueToFatalErr
+			}
+			p.cb.Status = StepSkippedDueToFatalErr
+		})
+		return
+	}
+
+	l.Info("running callback")
+	cbR := runHook(p.cb, ctx, Callback)
+	if cbR.HadError() {
+		l.WithError(cbR).Error("callback failed")
+	}
+
+	l.Info("run post-edges for successful pre-edges in reverse configuration order")
+
+	// the constructor produces pre and post entries
+	// post is NOT reversed
+	next-- // now at index of last executed pre-edge
+	for ; next >= 0; next-- {
+		e := p.post[next]
+		l := l.WithField("hook", e.Hook)
+
+		if p.pre[next].Status != StepOk {
+			if p.pre[next].Status != StepErr {
+				panic(fmt.Sprintf("expecting a pre-edge hook report to be either Ok or Err, got %s", p.pre[next].Status))
+			}
+			l.Info("skip post-edge because pre-edge failed")
+			w(func() {
+				e.Status = StepSkippedDueToPreErr
+			})
+			continue
+		}
+
+		report := runHook(e, ctx, Post)
+
+		if report.HadError() {
+			l.WithError(report).Error("hook invocation failed for post-edge")
+			l.Error("subsequent post-edges run regardless of this post-edge failure")
+		}
+
+		// ErrIsFatal is only relevant for Pre
+
+	}
+
+}

daemon/hooks/hook_logging.go

@@ -0,0 +1,91 @@
+package hooks
+
+import (
+	"bufio"
+	"bytes"
+	"context"
+	"sync"
+
+	"github.com/zrepl/zrepl/daemon/logging"
+	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/util/envconst"
+)
+
+type Logger = logger.Logger
+
+func GetLogger(ctx context.Context) Logger { return getLogger(ctx) }
+
+func getLogger(ctx context.Context) Logger {
+	return logging.GetLogger(ctx, logging.SubsysHooks)
+}
+
+const MAX_HOOK_LOG_SIZE_DEFAULT int = 1 << 20
+
+type logWriter struct {
+	/*
+		Mutex prevents:
+			concurrent writes to buf, scanner in Write([]byte)
+			data race on scanner vs Write([]byte)
+				and concurrent write to buf (call to buf.Reset())
+				in Close()
+
+		(Also, Close() should generally block until any Write() call completes.)
+	*/
+	mtx     *sync.Mutex
+	buf     bytes.Buffer
+	scanner *bufio.Scanner
+	logger  Logger
+	level   logger.Level
+	field   string
+}
+
+func NewLogWriter(mtx *sync.Mutex, logger Logger, level logger.Level, field string) *logWriter {
+	w := new(logWriter)
+	w.mtx = mtx
+	w.scanner = bufio.NewScanner(&w.buf)
+	w.logger = logger
+	w.level = level
+	w.field = field
+	return w
+}
+
+func (w *logWriter) log(line string) {
+	w.logger.WithField(w.field, line).Log(w.level, "hook output")
+}
+
+func (w *logWriter) logUnreadBytes() error {
+	for w.scanner.Scan() {
+		w.log(w.scanner.Text())
+	}
+	if w.buf.Cap() > envconst.Int("ZREPL_MAX_HOOK_LOG_SIZE", MAX_HOOK_LOG_SIZE_DEFAULT) {
+		w.buf.Reset()
+	}
+
+	return nil
+}
+
+func (w *logWriter) Write(in []byte) (int, error) {
+	w.mtx.Lock()
+	defer w.mtx.Unlock()
+
+	n, bufErr := w.buf.Write(in)
+	if bufErr != nil {
+		return n, bufErr
+	}
+
+	err := w.logUnreadBytes()
+	if err != nil {
+		return n, err
+	}
+	// Always reset the scanner for the next Write
+	w.scanner = bufio.NewScanner(&w.buf)
+
+	return n, nil
+}
+
+func (w *logWriter) Close() (err error) {
+	w.mtx.Lock()
+	defer w.mtx.Unlock()
+
+	return w.logUnreadBytes()
+}

daemon/hooks/hook_type_callback.go

@@ -0,0 +1,65 @@
+package hooks
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/zrepl/zrepl/daemon/filters"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+type HookJobCallback func(ctx context.Context) error
+
+type CallbackHook struct {
+	cb            HookJobCallback
+	filter        Filter
+	displayString string
+}
+
+func NewCallbackHookForFilesystem(displayString string, fs *zfs.DatasetPath, cb HookJobCallback) *CallbackHook {
+	filter, _ := filters.DatasetMapFilterFromConfig(map[string]bool{fs.ToString(): true})
+	return NewCallbackHook(displayString, cb, filter)
+}
+
+func NewCallbackHook(displayString string, cb HookJobCallback, filter Filter) *CallbackHook {
+	return &CallbackHook{
+		cb:            cb,
+		filter:        filter,
+		displayString: displayString,
+	}
+}
+
+func (h *CallbackHook) Filesystems() Filter {
+	return h.filter
+}
+
+func (h *CallbackHook) ErrIsFatal() bool {
+	return false // callback is by definition
+}
+
+func (h *CallbackHook) String() string {
+	return h.displayString
+}
+
+type CallbackHookReport struct {
+	Name string
+	Err  error
+}
+
+func (r *CallbackHookReport) String() string {
+	if r.HadError() {
+		return r.Error()
+	}
+	return r.Name
+}
+
+func (r *CallbackHookReport) HadError() bool { return r.Err != nil }
+
+func (r *CallbackHookReport) Error() string {
+	return fmt.Sprintf("%s error: %s", r.Name, r.Err)
+}
+
+func (h *CallbackHook) Run(ctx context.Context, edge Edge, phase Phase, dryRun bool, extra Env, state map[interface{}]interface{}) HookReport {
+	err := h.cb(ctx)
+	return &CallbackHookReport{h.displayString, err}
+}

daemon/hooks/hook_type_command.go

@@ -0,0 +1,199 @@
+package hooks
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"math"
+	"os"
+	"os/exec"
+	"sort"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/daemon/filters"
+	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/util/circlog"
+	"github.com/zrepl/zrepl/util/envconst"
+)
+
+type HookEnvVar string
+
+const (
+	EnvType     HookEnvVar = "ZREPL_HOOKTYPE"
+	EnvDryRun   HookEnvVar = "ZREPL_DRYRUN"
+	EnvFS       HookEnvVar = "ZREPL_FS"
+	EnvSnapshot HookEnvVar = "ZREPL_SNAPNAME"
+	EnvTimeout  HookEnvVar = "ZREPL_TIMEOUT"
+)
+
+type Env map[HookEnvVar]string
+
+func NewHookEnv(edge Edge, phase Phase, dryRun bool, timeout time.Duration, extra Env) Env {
+	r := Env{
+		EnvTimeout: fmt.Sprintf("%.f", math.Floor(timeout.Seconds())),
+	}
+
+	edgeString := edge.StringForPhase(phase)
+	r[EnvType] = strings.ToLower(edgeString)
+
+	var dryRunString string
+	if dryRun {
+		dryRunString = "true"
+	} else {
+		dryRunString = ""
+	}
+	r[EnvDryRun] = dryRunString
+
+	for k, v := range extra {
+		r[k] = v
+	}
+
+	return r
+}
+
+type CommandHook struct {
+	edge       Edge
+	filter     Filter
+	errIsFatal bool
+	command    string
+	timeout    time.Duration
+}
+
+type CommandHookReport struct {
+	Command                      string
+	Args                         []string // currently always empty
+	Env                          Env
+	Err                          error
+	CapturedStdoutStderrCombined []byte
+}
+
+func (r *CommandHookReport) String() string {
+	// Reproduces a POSIX shell-compatible command line
+	var cmdLine strings.Builder
+	sep := ""
+
+	// Make sure environment variables are always
+	// printed in the same order
+	var hookEnvKeys []HookEnvVar
+	for k := range r.Env {
+		hookEnvKeys = append(hookEnvKeys, k)
+	}
+	sort.Slice(hookEnvKeys, func(i, j int) bool { return string(hookEnvKeys[i]) < string(hookEnvKeys[j]) })
+
+	for _, k := range hookEnvKeys {
+		cmdLine.WriteString(fmt.Sprintf("%s%s='%s'", sep, k, r.Env[k]))
+		sep = " "
+	}
+
+	cmdLine.WriteString(fmt.Sprintf("%s%s", sep, r.Command))
+	for _, a := range r.Args {
+		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
+}
+func (r *CommandHookReport) Error() string {
+	if r.Err == nil {
+		return ""
+	}
+	return fmt.Sprintf("%s FAILED with error: %s", r.String(), r.Err)
+}
+
+func (r *CommandHookReport) HadError() bool {
+	return r.Err != nil
+}
+
+func NewCommandHook(in *config.HookCommand) (r *CommandHook, err error) {
+	r = &CommandHook{
+		errIsFatal: in.ErrIsFatal,
+		command:    in.Path,
+		timeout:    in.Timeout,
+	}
+
+	r.filter, err = filters.DatasetMapFilterFromConfig(in.Filesystems)
+	if err != nil {
+		return nil, fmt.Errorf("cannot parse filesystem filter: %s", err)
+	}
+
+	r.edge = Pre | Post
+
+	return r, nil
+}
+
+func (h *CommandHook) Filesystems() Filter {
+	return h.filter
+}
+
+func (h *CommandHook) ErrIsFatal() bool {
+	return h.errIsFatal
+}
+
+func (h *CommandHook) String() string {
+	return h.command
+}
+
+func (h *CommandHook) Run(ctx context.Context, edge Edge, phase Phase, dryRun bool, extra Env, state map[interface{}]interface{}) HookReport {
+	l := getLogger(ctx).WithField("command", h.command)
+
+	cmdCtx, cancel := context.WithTimeout(ctx, h.timeout)
+	defer cancel()
+
+	cmdExec := exec.CommandContext(cmdCtx, h.command)
+
+	hookEnv := NewHookEnv(edge, phase, dryRun, h.timeout, extra)
+	cmdEnv := os.Environ()
+	for k, v := range hookEnv {
+		cmdEnv = append(cmdEnv, fmt.Sprintf("%s=%s", k, v))
+	}
+	cmdExec.Env = cmdEnv
+
+	var scanMutex sync.Mutex
+	combinedOutput, err := circlog.NewCircularLog(envconst.Int("ZREPL_MAX_HOOK_LOG_SIZE", MAX_HOOK_LOG_SIZE_DEFAULT))
+	if err != nil {
+		return &CommandHookReport{Err: err}
+	}
+	logErrWriter := NewLogWriter(&scanMutex, l, logger.Warn, "stderr")
+	logOutWriter := NewLogWriter(&scanMutex, l, logger.Info, "stdout")
+	defer logErrWriter.Close()
+	defer logOutWriter.Close()
+
+	cmdExec.Stderr = io.MultiWriter(logErrWriter, combinedOutput)
+	cmdExec.Stdout = io.MultiWriter(logOutWriter, combinedOutput)
+
+	report := &CommandHookReport{
+		Command: h.command,
+		Env:     hookEnv,
+		// no report.Args
+	}
+
+	err = cmdExec.Start()
+	if err != nil {
+		report.Err = err
+		return report
+	}
+
+	err = cmdExec.Wait()
+	combinedOutputBytes := combinedOutput.Bytes()
+	report.CapturedStdoutStderrCombined = make([]byte, len(combinedOutputBytes))
+	copy(report.CapturedStdoutStderrCombined, combinedOutputBytes)
+	if err != nil {
+		if cmdCtx.Err() == context.DeadlineExceeded {
+			report.Err = fmt.Errorf("timed out after %s: %s", h.timeout, err)
+			return report
+		}
+		report.Err = err
+		return report
+	}
+
+	return report
+}

daemon/hooks/hook_type_mysql_lock_tables.go

@@ -0,0 +1,148 @@
+package hooks
+
+import (
+	"context"
+	"database/sql"
+	"fmt"
+	"strings"
+
+	sqldriver "database/sql/driver"
+
+	"github.com/go-sql-driver/mysql"
+
+	"github.com/pkg/errors"
+
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/daemon/filters"
+	"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:
+//
+//	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.
+//
+//		Similar snapshot capabilities may be available in other file systems, such as LVM or ZFS.
+//
+
+type MySQLLockTables struct {
+	errIsFatal  bool
+	connector   sqldriver.Connector
+	filesystems Filter
+}
+
+type myLockTablesStateKey int
+
+const (
+	myLockTablesConnection myLockTablesStateKey = 1 + iota
+)
+
+func MyLockTablesFromConfig(in *config.HookMySQLLockTables) (*MySQLLockTables, error) {
+	conf, err := mysql.ParseDSN(in.DSN)
+	if err != nil {
+		return nil, errors.Wrap(err, "`dsn` invalid")
+	}
+	cn, err := mysql.NewConnector(conf)
+	if err != nil {
+		return nil, errors.Wrap(err, "`connect` invalid")
+	}
+
+	filesystems, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
+	if err != nil {
+		return nil, errors.Wrap(err, "`filesystems` invalid")
+	}
+
+	return &MySQLLockTables{
+		in.ErrIsFatal,
+		cn,
+		filesystems,
+	}, nil
+}
+
+func (h *MySQLLockTables) ErrIsFatal() bool    { return h.errIsFatal }
+func (h *MySQLLockTables) Filesystems() Filter { return h.filesystems }
+func (h *MySQLLockTables) String() string      { return "MySQL FLUSH TABLES WITH READ LOCK" }
+
+type MyLockTablesReport struct {
+	What string
+	Err  error
+}
+
+func (r *MyLockTablesReport) HadError() bool { return r.Err != nil }
+func (r *MyLockTablesReport) Error() string  { return r.String() }
+func (r *MyLockTablesReport) String() string {
+	var s strings.Builder
+	s.WriteString(r.What)
+	if r.Err != nil {
+		fmt.Fprintf(&s, ": %s", r.Err)
+	}
+	return s.String()
+}
+
+func (h *MySQLLockTables) Run(ctx context.Context, edge Edge, phase Phase, dryRun bool, extra Env, state map[interface{}]interface{}) HookReport {
+	fs, ok := extra[EnvFS]
+	if !ok {
+		panic(extra)
+	}
+	dp, err := zfs.NewDatasetPath(fs)
+	if err != nil {
+		panic(err)
+	}
+	if pass, err := h.filesystems.Filter(dp); err != nil {
+		return &MyLockTablesReport{What: "filesystem filter", Err: err}
+	} else if !pass {
+		getLogger(ctx).Debug("filesystem does not match filter, skipping")
+		return &MyLockTablesReport{What: "filesystem filter skipped this filesystem", Err: nil}
+	}
+
+	switch edge {
+	case Pre:
+		err := h.doRunPre(ctx, dp, dryRun, state)
+		return &MyLockTablesReport{"FLUSH TABLES WITH READ LOCK", err}
+	case Post:
+		err := h.doRunPost(ctx, dp, dryRun, state)
+		return &MyLockTablesReport{"UNLOCK TABLES", err}
+	}
+	return &MyLockTablesReport{What: "skipped this edge", Err: nil}
+}
+
+func (h *MySQLLockTables) doRunPre(ctx context.Context, fs *zfs.DatasetPath, dry bool, state map[interface{}]interface{}) (err error) {
+	db := sql.OpenDB(h.connector)
+	defer func(err *error) {
+		if *err != nil {
+			db.Close()
+		}
+	}(&err)
+
+	getLogger(ctx).Debug("do FLUSH TABLES WITH READ LOCK")
+	_, err = db.ExecContext(ctx, "FLUSH TABLES WITH READ LOCK")
+	if err != nil {
+		return
+	}
+
+	state[myLockTablesConnection] = db
+
+	return nil
+}
+
+func (h *MySQLLockTables) doRunPost(ctx context.Context, fs *zfs.DatasetPath, dry bool, state map[interface{}]interface{}) error {
+
+	db := state[myLockTablesConnection].(*sql.DB)
+	defer db.Close()
+
+	getLogger(ctx).Debug("do UNLOCK TABLES")
+	_, err := db.ExecContext(ctx, "UNLOCK TABLES")
+	if err != nil {
+		return err
+	}
+
+	return nil
+}

daemon/hooks/hook_type_postgres_checkpoint.go

@@ -0,0 +1,98 @@
+package hooks
+
+import (
+	"context"
+	"database/sql"
+	"fmt"
+	"math"
+	"time"
+
+	"github.com/lib/pq"
+	"github.com/pkg/errors"
+
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/daemon/filters"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+type PgChkptHook struct {
+	errIsFatal  bool
+	connector   *pq.Connector
+	filesystems Filter
+}
+
+func PgChkptHookFromConfig(in *config.HookPostgresCheckpoint) (*PgChkptHook, error) {
+	filesystems, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
+	if err != nil {
+		return nil, errors.Wrap(err, "`filesystems` invalid")
+	}
+	cn, err := pq.NewConnector(in.DSN)
+	if err != nil {
+		return nil, errors.Wrap(err, "`dsn` invalid")
+	}
+
+	return &PgChkptHook{
+		in.ErrIsFatal,
+		cn,
+		filesystems,
+	}, nil
+}
+
+func (h *PgChkptHook) ErrIsFatal() bool    { return h.errIsFatal }
+func (h *PgChkptHook) Filesystems() Filter { return h.filesystems }
+func (h *PgChkptHook) String() string      { return "postgres checkpoint" }
+
+type PgChkptHookReport struct{ Err error }
+
+func (r *PgChkptHookReport) HadError() bool { return r.Err != nil }
+func (r *PgChkptHookReport) Error() string  { return r.Err.Error() }
+func (r *PgChkptHookReport) String() string {
+	if r.Err != nil {
+		return fmt.Sprintf("postgres CHECKPOINT failed: %s", r.Err)
+	} else {
+		return "postgres CHECKPOINT completed"
+	}
+}
+
+func (h *PgChkptHook) Run(ctx context.Context, edge Edge, phase Phase, dryRun bool, extra Env, state map[interface{}]interface{}) HookReport {
+	if edge != Pre {
+		return &PgChkptHookReport{nil}
+	}
+	fs, ok := extra[EnvFS]
+	if !ok {
+		panic(extra)
+	}
+	dp, err := zfs.NewDatasetPath(fs)
+	if err != nil {
+		panic(err)
+	}
+	err = h.doRunPre(ctx, dp, dryRun)
+	return &PgChkptHookReport{err}
+}
+
+func (h *PgChkptHook) doRunPre(ctx context.Context, fs *zfs.DatasetPath, dry bool) error {
+
+	if pass, err := h.filesystems.Filter(fs); err != nil || !pass {
+		getLogger(ctx).Debug("filesystem does not match filter, skipping")
+		return err
+	}
+
+	db := sql.OpenDB(h.connector)
+	defer db.Close()
+	dl, ok := ctx.Deadline()
+	if ok {
+		timeout := uint64(math.Floor(time.Until(dl).Seconds() * 1000)) // TODO go1.13 milliseconds
+		getLogger(ctx).WithField("statement_timeout", timeout).Debug("setting statement timeout for CHECKPOINT")
+		_, err := db.ExecContext(ctx, "SET statement_timeout TO ?", timeout)
+		if err != nil {
+			return err
+		}
+	}
+	if dry {
+		getLogger(ctx).Debug("dry-run - use ping instead of CHECKPOINT")
+		return db.PingContext(ctx)
+	}
+	getLogger(ctx).Info("execute CHECKPOINT command")
+	_, err := db.ExecContext(ctx, "CHECKPOINT")
+	return err
+}

daemon/hooks/hooks_test.go

@@ -0,0 +1,489 @@
+package hooks_test
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"os"
+	"regexp"
+	"testing"
+	"text/template"
+
+	"github.com/stretchr/testify/require"
+
+	"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/logger"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+type comparisonAssertionFunc func(require.TestingT, interface{}, interface{}, ...interface{})
+type valueAssertionFunc func(require.TestingT, interface{}, ...interface{})
+
+type expectStep struct {
+	ExpectedEdge hooks.Edge
+	ExpectStatus hooks.StepStatus
+	OutputTest   valueAssertionFunc
+	ErrorTest    valueAssertionFunc
+}
+
+type testCase struct {
+	Name           string
+	Config         []string
+	IsSlow         bool
+	SuppressOutput bool
+
+	ExpectCallbackSkipped bool
+	ExpectHadFatalErr     bool
+	ExpectHadError        bool
+	ExpectStepReports     []expectStep
+}
+
+func curryLeft(f comparisonAssertionFunc, expected interface{}) valueAssertionFunc {
+	return curry(f, expected, false)
+}
+
+func curryRight(f comparisonAssertionFunc, expected interface{}) valueAssertionFunc {
+	return curry(f, expected, true)
+}
+
+func curry(f comparisonAssertionFunc, expected interface{}, right bool) (ret valueAssertionFunc) {
+	ret = func(t require.TestingT, s interface{}, v ...interface{}) {
+		var x interface{}
+		var y interface{}
+		if right {
+			x = s
+			y = expected
+		} else {
+			x = expected
+			y = s
+		}
+
+		if len(v) > 0 {
+			f(t, x, y, v)
+		} else {
+			f(t, x, y)
+		}
+	}
+	return
+}
+
+func TestHooks(t *testing.T) {
+	ctx, end := trace.WithTaskFromStack(context.Background())
+	defer end()
+
+	testFSName := "testpool/testdataset"
+	testSnapshotName := "testsnap"
+
+	tmpl, err := template.New("TestHooks").Parse(`
+jobs:
+- name: TestHooks
+  type: snap
+  filesystems: {"<": true}
+  snapshotting:
+    type: periodic
+    interval: 1m
+    prefix: zrepl_snapjob_
+    hooks:
+    {{- template "List" . }}
+  pruning:
+    keep:
+      - type: last_n
+        count: 10
+`)
+	if err != nil {
+		panic(err)
+	}
+
+	regexpTest := func(s string) valueAssertionFunc {
+		return curryLeft(require.Regexp, regexp.MustCompile(s))
+	}
+
+	containsTest := func(s string) valueAssertionFunc {
+		return curryRight(require.Contains, s)
+	}
+
+	testTable := []testCase{
+		testCase{
+			Name: "no_hooks",
+			ExpectStepReports: []expectStep{
+				{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+			},
+		},
+		testCase{
+			Name:           "timeout",
+			IsSlow:         true,
+			ExpectHadError: true,
+			Config:         []string{`{type: command, path: {{.WorkDir}}/test/test-timeout.sh, timeout: 2s}`},
+			ExpectStepReports: []expectStep{
+				expectStep{
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepErr,
+					OutputTest:   containsTest(fmt.Sprintf("TEST pre_testing %s@%s ZREPL_TIMEOUT=2", testFSName, testSnapshotName)),
+					ErrorTest:    regexpTest(`timed out after 2(.\d+)?s`),
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepSkippedDueToPreErr,
+				},
+			},
+		},
+		testCase{
+			Name:           "check_env",
+			Config:         []string{`{type: command, path: {{.WorkDir}}/test/test-report-env.sh}`},
+			ExpectHadError: false,
+			ExpectStepReports: []expectStep{
+				expectStep{
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   containsTest(fmt.Sprintf("TEST pre_testing %s@%s", testFSName, testSnapshotName)),
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   containsTest(fmt.Sprintf("TEST post_testing %s@%s", testFSName, testSnapshotName)),
+				},
+			},
+		},
+
+		testCase{
+			Name:                  "nonfatal_pre_error_continues",
+			ExpectCallbackSkipped: false,
+			ExpectHadError:        true,
+			Config:                []string{`{type: command, path: {{.WorkDir}}/test/test-error.sh}`},
+			ExpectStepReports: []expectStep{
+				expectStep{
+					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$"),
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepSkippedDueToPreErr, // post-edge is not executed for failing pre-edge
+				},
+			},
+		},
+
+		testCase{
+			Name:                  "pre_error_fatal_skips_subsequent_pre_edges_and_callback_and_its_post_edge_and_post_edges",
+			ExpectCallbackSkipped: true,
+			ExpectHadFatalErr:     true,
+			ExpectHadError:        true,
+			Config: []string{
+				`{type: command, path: {{.WorkDir}}/test/test-error.sh, err_is_fatal: true}`,
+				`{type: command, path: {{.WorkDir}}/test/test-report-env.sh}`,
+			},
+			ExpectStepReports: []expectStep{
+				expectStep{
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepErr,
+					OutputTest:   containsTest(fmt.Sprintf("TEST ERROR pre_testing %s@%s", testFSName, testSnapshotName)),
+					ErrorTest:    regexpTest("^command hook failed.*exit status 1$"),
+				},
+				expectStep{
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepSkippedDueToFatalErr,
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepSkippedDueToFatalErr},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepSkippedDueToFatalErr,
+				},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepSkippedDueToFatalErr,
+				},
+			},
+		},
+
+		testCase{
+			Name:              "post_error_fails_are_ignored_even_if_fatal",
+			ExpectHadFatalErr: false, // only occurs during Post, so it's not a fatal error
+			ExpectHadError:    true,
+			Config: []string{
+				`{type: command, path: {{.WorkDir}}/test/test-post-error.sh, err_is_fatal: true}`,
+				`{type: command, path: {{.WorkDir}}/test/test-report-env.sh}`,
+			},
+			ExpectStepReports: []expectStep{
+				expectStep{
+					// No-action run of test-post-error.sh
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   require.Empty,
+				},
+				expectStep{
+					// Pre run of test-report-env.sh
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   containsTest(fmt.Sprintf("TEST pre_testing %s@%s", testFSName, testSnapshotName)),
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   containsTest(fmt.Sprintf("TEST post_testing %s@%s", testFSName, testSnapshotName)),
+				},
+				expectStep{
+					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$"),
+				},
+			},
+		},
+
+		testCase{
+			Name:   "cleanup_check_env",
+			Config: []string{`{type: command, path: {{.WorkDir}}/test/test-report-env.sh}`},
+			ExpectStepReports: []expectStep{
+				expectStep{
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   containsTest(fmt.Sprintf("TEST pre_testing %s@%s", testFSName, testSnapshotName)),
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   containsTest(fmt.Sprintf("TEST post_testing %s@%s", testFSName, testSnapshotName)),
+				},
+			},
+		},
+
+		testCase{
+			Name:              "pre_error_cancels_post",
+			Config:            []string{`{type: command, path: {{.WorkDir}}/test/test-pre-error-post-ok.sh}`},
+			ExpectHadError:    true,
+			ExpectHadFatalErr: false,
+			ExpectStepReports: []expectStep{
+				expectStep{
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepErr,
+					OutputTest:   containsTest(fmt.Sprintf("TEST ERROR pre_testing %s@%s", testFSName, testSnapshotName)),
+					ErrorTest:    regexpTest("^command hook failed.*exit status 1$"),
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepSkippedDueToPreErr,
+				},
+			},
+		},
+
+		testCase{
+			Name: "pre_error_does_not_cancel_other_posts_but_itself",
+			Config: []string{
+				`{type: command, path: {{.WorkDir}}/test/test-report-env.sh}`,
+				`{type: command, path: {{.WorkDir}}/test/test-pre-error-post-ok.sh}`,
+			},
+			ExpectHadError:    true,
+			ExpectHadFatalErr: false,
+			ExpectStepReports: []expectStep{
+				expectStep{
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   containsTest(fmt.Sprintf("TEST pre_testing %s@%s", testFSName, testSnapshotName)),
+				},
+				expectStep{
+					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$"),
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepSkippedDueToPreErr,
+				},
+				expectStep{
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   containsTest(fmt.Sprintf("TEST post_testing %s@%s", testFSName, testSnapshotName)),
+				},
+			},
+		},
+
+		testCase{
+			Name:              "exceed_buffer_limit",
+			SuppressOutput:    true,
+			Config:            []string{`{type: command, path: {{.WorkDir}}/test/test-large-stdout.sh}`},
+			ExpectHadError:    false,
+			ExpectHadFatalErr: false,
+			ExpectStepReports: []expectStep{
+				expectStep{
+					ExpectedEdge: hooks.Pre,
+					ExpectStatus: hooks.StepOk,
+					OutputTest: func(t require.TestingT, s interface{}, v ...interface{}) {
+						require.Len(t, s, 1<<20)
+					},
+				},
+				expectStep{ExpectedEdge: hooks.Callback, ExpectStatus: hooks.StepOk},
+				expectStep{
+					// No-action run of above hook
+					ExpectedEdge: hooks.Post,
+					ExpectStatus: hooks.StepOk,
+					OutputTest:   require.Empty,
+				},
+			},
+		},
+
+		/*
+			Following not intended to test functionality of
+			filter package. Only to demonstrate that hook
+			filters are being applied. The following should
+			result in NO hooks running. If it does run, a
+			fatal hooks.RunReport will be returned.
+		*/
+		testCase{
+			Name: "exclude_all_filesystems",
+			Config: []string{
+				`{type: command, path: {{.WorkDir}}/test/test-error.sh, err_is_fatal: true, filesystems: {"<": false}}`,
+			},
+			ExpectStepReports: []expectStep{
+				expectStep{
+					ExpectedEdge: hooks.Callback,
+					ExpectStatus: hooks.StepOk,
+				},
+			},
+		},
+	}
+
+	parseHookConfig := func(t *testing.T, in string) *config.Config {
+		t.Helper()
+		conf, err := config.ParseConfigBytes([]byte(in))
+		require.NoError(t, err)
+		require.NotNil(t, conf)
+		return conf
+	}
+
+	fillHooks := func(tt *testCase) string {
+		// make hook path absolute
+		cwd, err := os.Getwd()
+		if err != nil {
+			panic("os.Getwd() failed")
+		}
+		var hooksTmpl string = "\n"
+		for _, l := range tt.Config {
+			hooksTmpl += fmt.Sprintf("    - %s\n", l)
+		}
+		tmpl.New("List").Parse(hooksTmpl)
+
+		var outBytes bytes.Buffer
+		data := struct {
+			WorkDir string
+		}{
+			WorkDir: cwd,
+		}
+		if err := tmpl.Execute(&outBytes, data); err != nil {
+			panic(err)
+		}
+
+		return outBytes.String()
+	}
+
+	var c *config.Config
+	fs, err := zfs.NewDatasetPath(testFSName)
+	require.NoError(t, err)
+
+	log := logger.NewTestLogger(t)
+
+	var cbReached bool
+	cb := hooks.NewCallbackHookForFilesystem("testcallback", fs, func(_ context.Context) error {
+		cbReached = true
+		return nil
+	})
+
+	hookEnvExtra := hooks.Env{
+		hooks.EnvFS:       fs.ToString(),
+		hooks.EnvSnapshot: testSnapshotName,
+	}
+
+	for _, tt := range testTable {
+		if testing.Short() && tt.IsSlow {
+			continue
+		}
+
+		t.Run(tt.Name, func(t *testing.T) {
+			c = parseHookConfig(t, fillHooks(&tt))
+			snp := c.Jobs[0].Ret.(*config.SnapJob).Snapshotting.Ret.(*config.SnapshottingPeriodic)
+			hookList, err := hooks.ListFromConfig(&snp.Hooks)
+			require.NoError(t, err)
+
+			filteredHooks, err := hookList.CopyFilteredForFilesystem(fs)
+			require.NoError(t, err)
+			plan, err := hooks.NewPlan(&filteredHooks, hooks.PhaseTesting, cb, hookEnvExtra)
+			require.NoError(t, err)
+			t.Logf("REPORT PRE EXECUTION:\n%s", plan.Report())
+
+			cbReached = false
+
+			if testing.Verbose() && !tt.SuppressOutput {
+				ctx = logging.WithLoggers(ctx, logging.SubsystemLoggersWithUniversalLogger(log))
+			}
+			plan.Run(ctx, false)
+			report := plan.Report()
+
+			t.Logf("REPORT POST EXECUTION:\n%s", report)
+
+			/*
+			 * TEST ASSERTIONS
+			 */
+
+			t.Logf("len(runReports)=%v", len(report))
+			t.Logf("len(tt.ExpectStepReports)=%v", len(tt.ExpectStepReports))
+			require.Equal(t, len(tt.ExpectStepReports), len(report), "ExpectStepReports must be same length as expected number of hook runs, excluding possible Callback")
+
+			// Check if callback ran, when required
+			if tt.ExpectCallbackSkipped {
+				require.False(t, cbReached, "callback ran but should not have run")
+			} else {
+				require.True(t, cbReached, "callback should have run but did not")
+			}
+
+			// Check if a fatal run error occurred and was expected
+			require.Equal(t, tt.ExpectHadFatalErr, report.HadFatalError(), "non-matching HadFatalError")
+			require.Equal(t, tt.ExpectHadError, report.HadError(), "non-matching HadError")
+
+			if tt.ExpectHadFatalErr {
+				require.True(t, tt.ExpectHadError, "ExpectHadFatalErr implies ExpectHadError")
+			}
+			if !tt.ExpectHadError {
+				require.False(t, tt.ExpectHadFatalErr, "!ExpectHadError implies !ExpectHadFatalErr")
+			}
+
+			// Iterate through each expected hook run
+			for i, hook := range tt.ExpectStepReports {
+				t.Logf("expecting report conforming to %v", hook)
+
+				exp, act := hook.ExpectStatus, report[i].Status
+				require.Equal(t, exp, act, "%s != %s", exp, act)
+
+				// Check for required ExpectedEdge
+				require.NotZero(t, hook.ExpectedEdge, "each hook must have an ExpectedEdge")
+				require.Equal(t, hook.ExpectedEdge, report[i].Edge,
+					"incorrect edge: expected %q, actual %q", hook.ExpectedEdge.String(), report[i].Edge.String(),
+				)
+
+				// Check for expected output
+				if hook.OutputTest != nil {
+					require.IsType(t, (*hooks.CommandHookReport)(nil), report[i].Report)
+					chr := report[i].Report.(*hooks.CommandHookReport)
+					hook.OutputTest(t, string(chr.CapturedStdoutStderrCombined))
+				}
+
+				// Check for expected errors
+				if hook.ErrorTest != nil {
+					hook.ErrorTest(t, string(report[i].Report.Error()))
+				}
+			}
+
+		})
+	}
+}

daemon/hooks/stepstatus_enumer.go

@@ -0,0 +1,77 @@
+// Code generated by "enumer -type=StepStatus -trimprefix=Step"; DO NOT EDIT.
+
+//
+package hooks
+
+import (
+	"fmt"
+)
+
+const (
+	_StepStatusName_0 = "PendingExec"
+	_StepStatusName_1 = "Ok"
+	_StepStatusName_2 = "Err"
+	_StepStatusName_3 = "SkippedDueToFatalErr"
+	_StepStatusName_4 = "SkippedDueToPreErr"
+)
+
+var (
+	_StepStatusIndex_0 = [...]uint8{0, 7, 11}
+	_StepStatusIndex_1 = [...]uint8{0, 2}
+	_StepStatusIndex_2 = [...]uint8{0, 3}
+	_StepStatusIndex_3 = [...]uint8{0, 20}
+	_StepStatusIndex_4 = [...]uint8{0, 18}
+)
+
+func (i StepStatus) String() string {
+	switch {
+	case 1 <= i && i <= 2:
+		i -= 1
+		return _StepStatusName_0[_StepStatusIndex_0[i]:_StepStatusIndex_0[i+1]]
+	case i == 4:
+		return _StepStatusName_1
+	case i == 8:
+		return _StepStatusName_2
+	case i == 16:
+		return _StepStatusName_3
+	case i == 32:
+		return _StepStatusName_4
+	default:
+		return fmt.Sprintf("StepStatus(%d)", i)
+	}
+}
+
+var _StepStatusValues = []StepStatus{1, 2, 4, 8, 16, 32}
+
+var _StepStatusNameToValueMap = map[string]StepStatus{
+	_StepStatusName_0[0:7]:  1,
+	_StepStatusName_0[7:11]: 2,
+	_StepStatusName_1[0:2]:  4,
+	_StepStatusName_2[0:3]:  8,
+	_StepStatusName_3[0:20]: 16,
+	_StepStatusName_4[0:18]: 32,
+}
+
+// StepStatusString retrieves an enum value from the enum constants string name.
+// Throws an error if the param is not part of the enum.
+func StepStatusString(s string) (StepStatus, error) {
+	if val, ok := _StepStatusNameToValueMap[s]; ok {
+		return val, nil
+	}
+	return 0, fmt.Errorf("%s does not belong to StepStatus values", s)
+}
+
+// StepStatusValues returns all values of the enum
+func StepStatusValues() []StepStatus {
+	return _StepStatusValues
+}
+
+// IsAStepStatus returns "true" if the value is listed in the enum definition. "false" otherwise
+func (i StepStatus) IsAStepStatus() bool {
+	for _, v := range _StepStatusValues {
+		if i == v {
+			return true
+		}
+	}
+	return false
+}

daemon/hooks/test/test-error.sh

@@ -0,0 +1,5 @@
+#!/bin/sh -eu
+
+>&2 echo "TEST ERROR $ZREPL_HOOKTYPE $ZREPL_FS@$ZREPL_SNAPNAME"
+
+exit 1

daemon/hooks/test/test-large-stdout.sh

@@ -0,0 +1,18 @@
+#!/bin/sh -eu
+
+# Exceed default hook log size of 1<<20 bytes by double
+# The Go test should fail if buffer size exceeds 1MB
+
+pre_testing() {
+	ln=0
+	while :; do printf '%06d: 012345678901234567890123456789012345678901234567890123456789012345678901\n' "$ln"; ln="$(($ln + 1))"; done \
+	| head -c$(( 2 << 20 ))
+}
+
+case "$ZREPL_HOOKTYPE" in
+	pre_testing)
+		"$ZREPL_HOOKTYPE";;
+	*)
+		# Not handled by this script
+		exit 0;;
+esac

daemon/hooks/test/test-post-error.sh

@@ -0,0 +1,15 @@
+#!/bin/sh -eu
+
+post_testing() {
+	>&2 echo "TEST ERROR $ZREPL_HOOKTYPE $ZREPL_FS@$ZREPL_SNAPNAME"
+
+	exit 1
+}
+
+case "$ZREPL_HOOKTYPE" in
+	post_testing)
+		"$ZREPL_HOOKTYPE";;
+	*)
+		# Not handled by this script
+		exit 0;;
+esac

daemon/hooks/test/test-pre-error-post-ok.sh

@@ -0,0 +1,11 @@
+#!/bin/sh -eu
+
+if [ "$ZREPL_HOOKTYPE" = "pre_testing" ]; then
+	>&2 echo "TEST ERROR $ZREPL_HOOKTYPE $ZREPL_FS@$ZREPL_SNAPNAME"
+	exit 1
+elif [ "$ZREPL_HOOKTYPE" = "post_testing" ]; then
+	echo "TEST $ZREPL_HOOKTYPE $ZREPL_FS@$ZREPL_SNAPNAME"
+else
+	printf "Unknown hook type: %s" "$ZREPL_HOOKTYPE" 
+	exit 255
+fi

daemon/hooks/test/test-report-env.sh

@@ -0,0 +1,3 @@
+#!/bin/sh -eu
+
+echo "TEST $ZREPL_HOOKTYPE $ZREPL_FS@$ZREPL_SNAPNAME ${ZREPL_DRYRUN:+(dry run)}"

daemon/hooks/test/test-timeout.sh

@@ -0,0 +1,5 @@
+#!/bin/sh -eu
+
+echo "TEST $ZREPL_HOOKTYPE $ZREPL_FS@$ZREPL_SNAPNAME ZREPL_TIMEOUT=$ZREPL_TIMEOUT"
+
+exec sleep $(($ZREPL_TIMEOUT + 1))

daemon/job/active.go

@@ -2,54 +2,80 @@ package job
 
 import (
 	"context"
+	"fmt"
+	"sync"
+	"time"
+
 	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
 	"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/job/reset"
 	"github.com/zrepl/zrepl/daemon/job/wakeup"
-	"github.com/zrepl/zrepl/daemon/transport/connecter"
-	"github.com/zrepl/zrepl/daemon/filters"
 	"github.com/zrepl/zrepl/daemon/pruner"
+	"github.com/zrepl/zrepl/daemon/snapper"
 	"github.com/zrepl/zrepl/endpoint"
 	"github.com/zrepl/zrepl/replication"
-	"github.com/zrepl/zrepl/util/envconst"
-	"github.com/zrepl/zrepl/util/watchdog"
+	"github.com/zrepl/zrepl/replication/driver"
+	"github.com/zrepl/zrepl/replication/logic"
+	"github.com/zrepl/zrepl/replication/report"
+	"github.com/zrepl/zrepl/rpc"
+	"github.com/zrepl/zrepl/transport"
+	"github.com/zrepl/zrepl/transport/fromconfig"
 	"github.com/zrepl/zrepl/zfs"
-	"sync"
-	"github.com/zrepl/zrepl/daemon/logging"
-	"github.com/zrepl/zrepl/daemon/snapper"
-	"time"
 )
 
 type ActiveSide struct {
-	mode          activeMode
-	name          string
-	clientFactory *connecter.ClientFactory
+	mode      activeMode
+	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
+	promRepStateSecs      *prometheus.HistogramVec // labels: state
+	promPruneSecs         *prometheus.HistogramVec // labels: prune_side
+	promBytesReplicated   *prometheus.CounterVec   // labels: filesystem
+	promReplicationErrors prometheus.Gauge
+	promLastSuccessful    prometheus.Gauge
 
 	tasksMtx sync.Mutex
 	tasks    activeSideTasks
 }
 
+//go:generate enumer -type=ActiveSideState
+type ActiveSideState int
+
+const (
+	ActiveSideReplicating ActiveSideState = 1 << iota
+	ActiveSidePruneSender
+	ActiveSidePruneReceiver
+	ActiveSideDone // also errors
+)
+
 type activeSideTasks struct {
-	replication *replication.Replication
+	state ActiveSideState
+
+	// valid for state ActiveSideReplicating, ActiveSidePruneSender, ActiveSidePruneReceiver, ActiveSideDone
+	replicationReport driver.ReportFunc
 	replicationCancel context.CancelFunc
+
+	// valid for state ActiveSidePruneSender, ActiveSidePruneReceiver, ActiveSideDone
 	prunerSender, prunerReceiver *pruner.Pruner
+
+	// valid for state ActiveSidePruneReceiver, ActiveSideDone
 	prunerSenderCancel, prunerReceiverCancel context.CancelFunc
 }
 
 func (a *ActiveSide) updateTasks(u func(*activeSideTasks)) activeSideTasks {
 	a.tasksMtx.Lock()
 	defer a.tasksMtx.Unlock()
-	var copy activeSideTasks
-	copy = a.tasks
+	copy := a.tasks
 	if u == nil {
 		return copy
 	}
@@ -59,38 +85,99 @@ func (a *ActiveSide) updateTasks(u func(*activeSideTasks)) activeSideTasks {
 }
 
 type activeMode interface {
-	SenderReceiver(client *streamrpc.Client) (replication.Sender, replication.Receiver, error)
+	ConnectEndpoints(ctx context.Context, connecter transport.Connecter)
+	DisconnectEndpoints()
+	SenderReceiver() (logic.Sender, logic.Receiver)
 	Type() Type
+	PlannerPolicy() logic.PlannerPolicy
 	RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{})
+	SnapperReport() *snapper.Report
+	ResetConnectBackoff()
 }
 
 type modePush struct {
-	fsfilter         endpoint.FSFilter
-	snapper *snapper.PeriodicOrManual
+	setupMtx      sync.Mutex
+	sender        *endpoint.Sender
+	receiver      *rpc.Client
+	senderConfig  *endpoint.SenderConfig
+	plannerPolicy *logic.PlannerPolicy
+	snapper       snapper.Snapper
 }
 
-func (m *modePush) SenderReceiver(client *streamrpc.Client) (replication.Sender, replication.Receiver, error) {
-	sender := endpoint.NewSender(m.fsfilter)
-	receiver := endpoint.NewRemote(client)
-	return sender, receiver, nil
+func (m *modePush) ConnectEndpoints(ctx context.Context, connecter transport.Connecter) {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	if m.receiver != nil || m.sender != nil {
+		panic("inconsistent use of ConnectEndpoints and DisconnectEndpoints")
+	}
+	m.sender = endpoint.NewSender(*m.senderConfig)
+	m.receiver = rpc.NewClient(connecter, rpc.GetLoggersOrPanic(ctx))
+}
+
+func (m *modePush) DisconnectEndpoints() {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	m.receiver.Close()
+	m.sender = nil
+	m.receiver = nil
+}
+
+func (m *modePush) SenderReceiver() (logic.Sender, logic.Receiver) {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	return m.sender, m.receiver
 }
 
 func (m *modePush) Type() Type { return TypePush }
 
-func (m *modePush) RunPeriodic(ctx context.Context, wakeUpCommon chan <- struct{}) {
+func (m *modePush) PlannerPolicy() logic.PlannerPolicy { return *m.plannerPolicy }
+
+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
+}
 
-func modePushFromConfig(g *config.Global, in *config.PushJob) (*modePush, error) {
-	m := &modePush{}
-	fsf, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannnot build filesystem filter")
+func (m *modePush) ResetConnectBackoff() {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	if m.receiver != nil {
+		m.receiver.ResetConnectBackoff()
 	}
-	m.fsfilter = fsf
+}
 
-	if m.snapper, err = snapper.FromConfig(g, fsf, in.Snapshotting); err != nil {
+func modePushFromConfig(g *config.Global, in *config.PushJob, jobID endpoint.JobID) (*modePush, error) {
+	m := &modePush{}
+	var err error
+
+	m.senderConfig, err = buildSenderConfig(in, jobID)
+	if err != nil {
+		return nil, errors.Wrap(err, "sender config")
+	}
+
+	replicationConfig, err := logic.ReplicationConfigFromConfig(in.Replication)
+	if err != nil {
+		return nil, errors.Wrap(err, "field `replication`")
+	}
+
+	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")
+	}
+
+	if m.snapper, err = snapper.FromConfig(g, m.senderConfig.FSF, in.Snapshotting); err != nil {
 		return nil, errors.Wrap(err, "cannot build snapper")
 	}
 
@@ -98,20 +185,49 @@ func modePushFromConfig(g *config.Global, in *config.PushJob) (*modePush, error)
 }
 
 type modePull struct {
-	rootFS   *zfs.DatasetPath
-	interval time.Duration
+	setupMtx       sync.Mutex
+	receiver       *endpoint.Receiver
+	receiverConfig endpoint.ReceiverConfig
+	sender         *rpc.Client
+	plannerPolicy  *logic.PlannerPolicy
+	interval       config.PositiveDurationOrManual
 }
 
-func (m *modePull) SenderReceiver(client *streamrpc.Client) (replication.Sender, replication.Receiver, error) {
-	sender := endpoint.NewRemote(client)
-	receiver, err := endpoint.NewReceiver(m.rootFS)
-	return sender, receiver, err
+func (m *modePull) ConnectEndpoints(ctx context.Context, connecter transport.Connecter) {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	if m.receiver != nil || m.sender != nil {
+		panic("inconsistent use of ConnectEndpoints and DisconnectEndpoints")
+	}
+	m.receiver = endpoint.NewReceiver(m.receiverConfig)
+	m.sender = rpc.NewClient(connecter, rpc.GetLoggersOrPanic(ctx))
+}
+
+func (m *modePull) DisconnectEndpoints() {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	m.sender.Close()
+	m.sender = nil
+	m.receiver = nil
+}
+
+func (m *modePull) SenderReceiver() (logic.Sender, logic.Receiver) {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	return m.sender, m.receiver
 }
 
 func (*modePull) Type() Type { return TypePull }
 
+func (m *modePull) PlannerPolicy() logic.PlannerPolicy { return *m.plannerPolicy }
+
 func (m *modePull) RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{}) {
-	t := time.NewTicker(m.interval)
+	if m.interval.Manual {
+		GetLogger(ctx).Info("manual pull configured, periodic pull disabled")
+		// "waiting for wakeups" is printed in common ActiveSide.do
+		return
+	}
+	t := time.NewTicker(m.interval.Interval)
 	defer t.Stop()
 	for {
 		select {
@@ -130,44 +246,109 @@ func (m *modePull) RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{}
 	}
 }
 
-func modePullFromConfig(g *config.Global, in *config.PullJob) (m *modePull, err error) {
-	m = &modePull{}
-	if in.Interval <= 0 {
-		return nil, errors.New("interval must be positive")
+func (m *modePull) SnapperReport() *snapper.Report {
+	return nil
+}
+
+func (m *modePull) ResetConnectBackoff() {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	if m.sender != nil {
+		m.sender.ResetConnectBackoff()
 	}
+}
+
+func modePullFromConfig(g *config.Global, in *config.PullJob, jobID endpoint.JobID) (m *modePull, err error) {
+	m = &modePull{}
 	m.interval = in.Interval
 
-	m.rootFS, err = zfs.NewDatasetPath(in.RootFS)
+	replicationConfig, err := logic.ReplicationConfigFromConfig(in.Replication)
 	if err != nil {
-		return nil, errors.New("RootFS is not a valid zfs filesystem path")
+		return nil, errors.Wrap(err, "field `replication`")
 	}
-	if m.rootFS.Length() <= 0 {
-		return nil, errors.New("RootFS must not be empty") // duplicates error check of receiver
+
+	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")
+	}
+
+	m.receiverConfig, err = buildReceiverConfig(in, jobID)
+	if err != nil {
+		return nil, err
 	}
 
 	return m, nil
 }
 
-func activeSide(g *config.Global, in *config.ActiveJob, mode activeMode) (j *ActiveSide, err error) {
+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) {
+
+	j = &ActiveSide{}
+	j.name, err = endpoint.MakeJobID(in.Name)
+	if err != nil {
+		return nil, errors.Wrap(err, "invalid job name")
+	}
+
+	switch v := configJob.(type) {
+	case *config.PushJob:
+		j.mode, err = modePushFromConfig(g, v, j.name) // shadow
+	case *config.PullJob:
+		j.mode, err = modePullFromConfig(g, v, j.name) // shadow
+	default:
+		panic(fmt.Sprintf("implementation error: unknown job type %T", v))
+	}
+	if err != nil {
+		return nil, err // no wrapping required
+	}
 
-	j = &ActiveSide{mode: mode}
-	j.name = in.Name
 	j.promRepStateSecs = prometheus.NewHistogramVec(prometheus.HistogramOpts{
 		Namespace:   "zrepl",
 		Subsystem:   "replication",
 		Name:        "state_time",
 		Help:        "seconds spent during replication",
-		ConstLabels: prometheus.Labels{"zrepl_job":j.name},
+		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
 	}, []string{"state"})
 	j.promBytesReplicated = prometheus.NewCounterVec(prometheus.CounterOpts{
 		Namespace:   "zrepl",
 		Subsystem:   "replication",
 		Name:        "bytes_replicated",
 		Help:        "number of bytes replicated from sender to receiver per filesystem",
-		ConstLabels: prometheus.Labels{"zrepl_job":j.name},
+		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.clientFactory, err = connecter.FromConfig(g, in.Connect)
+	j.connecter, err = fromconfig.ConnecterFromConfig(g, in.Connect, parseFlags)
 	if err != nil {
 		return nil, errors.Wrap(err, "cannot build client")
 	}
@@ -177,13 +358,18 @@ func activeSide(g *config.Global, in *config.ActiveJob, mode activeMode) (j *Act
 		Subsystem:   "pruning",
 		Name:        "time",
 		Help:        "seconds spent in pruner",
-		ConstLabels: prometheus.Labels{"zrepl_job":j.name},
+		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
 	}, []string{"prune_side"})
 	j.prunerFactory, err = pruner.NewPrunerFactory(in.Pruning, j.promPruneSecs)
 	if err != nil {
 		return nil, err
 	}
 
+	j.replicationDriverConfig, err = replicationDriverConfigFromConfig(in.Replication)
+	if err != nil {
+		return nil, errors.Wrap(err, "cannot build replication driver config")
+	}
+
 	return j, nil
 }
 
@@ -191,13 +377,16 @@ 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 }
+func (j *ActiveSide) Name() string { return j.name.String() }
 
 type ActiveSideStatus struct {
-	Replication *replication.Report
+	Replication                    *report.Report
 	PruningSender, PruningReceiver *pruner.Report
+	Snapshotting                   *snapper.Report
 }
 
 func (j *ActiveSide) Status() *Status {
@@ -205,8 +394,8 @@ func (j *ActiveSide) Status() *Status {
 
 	s := &ActiveSideStatus{}
 	t := j.mode.Type()
-	if tasks.replication != nil {
-		s.Replication = tasks.replication.Report()
+	if tasks.replicationReport != nil {
+		s.Replication = tasks.replicationReport()
 	}
 	if tasks.prunerSender != nil {
 		s.PruningSender = tasks.prunerSender.Report()
@@ -214,19 +403,53 @@ func (j *ActiveSide) Status() *Status {
 	if tasks.prunerReceiver != nil {
 		s.PruningReceiver = tasks.prunerReceiver.Report()
 	}
+	s.Snapshotting = j.mode.SnapperReport()
 	return &Status{Type: t, JobSpecific: s}
 }
 
+func (j *ActiveSide) OwnedDatasetSubtreeRoot() (rfs *zfs.DatasetPath, ok bool) {
+	pull, ok := j.mode.(*modePull)
+	if !ok {
+		_ = j.mode.(*modePush) // make sure we didn't introduce a new job type
+		return nil, false
+	}
+	return pull.receiverConfig.RootWithoutClientComponent.Copy(), true
+}
+
+func (j *ActiveSide) SenderConfig() *endpoint.SenderConfig {
+	push, ok := j.mode.(*modePush)
+	if !ok {
+		_ = j.mode.(*modePull) // make sure we didn't introduce a new job type
+		return nil
+	}
+	return push.senderConfig
+}
+
+// The active side of a replication uses one end (sender or receiver)
+// directly by method invocation, without going through a transport that
+// provides a client identity.
+// However, in order to avoid the need to distinguish between direct-method-invocating
+// clients and RPC client, we use an invalid client identity as a sentinel value.
+func FakeActiveSideDirectMethodInvocationClientIdentity(jobId endpoint.JobID) string {
+	return fmt.Sprintf("<local><active><job><client><identity><job=%q>", jobId.String())
+}
+
 func (j *ActiveSide) Run(ctx context.Context) {
+	ctx, endTask := trace.WithTaskAndSpan(ctx, "active-side-job", j.Name())
+	defer endTask()
+
+	ctx = context.WithValue(ctx, endpoint.ClientIdentityKey, FakeActiveSideDirectMethodInvocationClientIdentity(j.name))
+
 	log := GetLogger(ctx)
-	ctx = logging.WithSubsystemLoggers(ctx, log)
 
 	defer log.Info("job exiting")
 
 	periodicDone := make(chan struct{})
 	ctx, cancel := context.WithCancel(ctx)
 	defer cancel()
-	go j.mode.RunPeriodic(ctx, periodicDone)
+	periodicCtx, endTask := trace.WithTask(ctx, "periodic")
+	defer endTask()
+	go j.mode.RunPeriodic(periodicCtx, periodicDone)
 
 	invocationCount := 0
 outer:
@@ -238,27 +461,26 @@ outer:
 			break outer
 
 		case <-wakeup.Wait(ctx):
+			j.mode.ResetConnectBackoff()
 		case <-periodicDone:
 		}
 		invocationCount++
-		invLog := log.WithField("invocation", invocationCount)
-		j.do(WithLogger(ctx, invLog))
+		invocationCtx, endSpan := trace.WithSpan(ctx, fmt.Sprintf("invocation-%d", invocationCount))
+		j.do(invocationCtx)
+		endSpan()
 	}
 }
 
 func (j *ActiveSide) do(ctx context.Context) {
 
-	log := GetLogger(ctx)
-	ctx = logging.WithSubsystemLoggers(ctx, log)
+	j.mode.ConnectEndpoints(ctx, j.connecter)
+	defer j.mode.DisconnectEndpoints()
 
 	// allow cancellation of an invocation (this function)
 	ctx, cancelThisRun := context.WithCancel(ctx)
 	defer cancelThisRun()
-	runDone := make(chan struct{})
-	defer close(runDone)
 	go func() {
 		select {
-		case <-runDone:
 		case <-reset.Wait(ctx):
 			log.Info("reset received, cancelling current invocation")
 			cancelThisRun()
@@ -266,64 +488,7 @@ func (j *ActiveSide) do(ctx context.Context) {
 		}
 	}()
 
-	// watchdog
-	go func() {
-		// if no progress after 1 minute, kill the task
-		wdto := envconst.Duration("ZREPL_JOB_WATCHDOG_TIMEOUT", 1*time.Minute)
-		log.WithField("watchdog_timeout", wdto.String()).Debug("starting watchdog")
-
-		t := time.NewTicker(wdto)
-		defer t.Stop()
-
-		var (
-			rep, prunerSender, prunerReceiver watchdog.Progress
-		)
-		for {
-			select {
-			case <-runDone:
-				return
-			case <-ctx.Done():
-				return
-			case <-t.C: // fall
-			}
-
-			log := log.WithField("watchdog_timeout", wdto.String()) // shadowing!
-
-			j.updateTasks(func(tasks *activeSideTasks) {
-				if tasks.replication != nil &&
-					!tasks.replication.Progress.ExpectProgress(&rep) &&
-					!tasks.replication.State().IsTerminal() {
-					log.Error("replication did not make progress, cancelling")
-					tasks.replicationCancel()
-				}
-				if tasks.prunerSender != nil &&
-					!tasks.prunerSender.Progress.ExpectProgress(&prunerSender) &&
-					!tasks.prunerSender.State().IsTerminal() {
-					log.Error("pruner:sender did not make progress, cancelling")
-					tasks.prunerSenderCancel()
-				}
-				if tasks.prunerReceiver != nil &&
-					!tasks.prunerReceiver.Progress.ExpectProgress(&prunerReceiver) &&
-					!tasks.prunerReceiver.State().IsTerminal() {
-					log.Error("pruner:receiver did not make progress, cancelling")
-					tasks.prunerReceiverCancel()
-				}
-			})
-			log.WithField("replication_progress", rep.String()).
-				WithField("pruner_sender_progress", prunerSender.String()).
-				WithField("pruner_receiver_progress", prunerReceiver.String()).
-				Debug("watchdog did run")
-
-		}
-	}()
-
-	client, err := j.clientFactory.NewClient()
-	if err != nil {
-		log.WithError(err).Error("factory cannot instantiate streamrpc client")
-	}
-	defer client.Close(ctx)
-
-	sender, receiver, err := j.mode.SenderReceiver(client)
+	sender, receiver := j.mode.SenderReceiver()
 
 	{
 		select {
@@ -331,16 +496,30 @@ func (j *ActiveSide) do(ctx context.Context) {
 			return
 		default:
 		}
+		ctx, endSpan := trace.WithSpan(ctx, "replication")
 		ctx, repCancel := context.WithCancel(ctx)
-		tasks := j.updateTasks(func(tasks *activeSideTasks) {
+		var repWait driver.WaitFunc
+		j.updateTasks(func(tasks *activeSideTasks) {
 			// reset it
 			*tasks = activeSideTasks{}
-			tasks.replicationCancel = repCancel
-			tasks.replication = replication.NewReplication(j.promRepStateSecs, j.promBytesReplicated)
+			tasks.replicationCancel = func() { repCancel(); endSpan() }
+			tasks.replicationReport, repWait = replication.Do(
+				ctx, j.replicationDriverConfig, logic.NewPlanner(j.promRepStateSecs, j.promBytesReplicated, sender, receiver, j.mode.PlannerPolicy()),
+			)
+			tasks.state = ActiveSideReplicating
 		})
-		log.Info("start replication")
-		tasks.replication.Drive(ctx, sender, receiver)
-		repCancel() // always cancel to free up context resources
+		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()
 	}
 
 	{
@@ -349,15 +528,18 @@ func (j *ActiveSide) do(ctx context.Context) {
 			return
 		default:
 		}
+		ctx, endSpan := trace.WithSpan(ctx, "prune_sender")
 		ctx, senderCancel := context.WithCancel(ctx)
 		tasks := j.updateTasks(func(tasks *activeSideTasks) {
 			tasks.prunerSender = j.prunerFactory.BuildSenderPruner(ctx, sender, sender)
-			tasks.prunerSenderCancel = senderCancel
+			tasks.prunerSenderCancel = func() { senderCancel(); endSpan() }
+			tasks.state = ActiveSidePruneSender
 		})
-		log.Info("start pruning sender")
+		GetLogger(ctx).Info("start pruning sender")
 		tasks.prunerSender.Prune()
-		log.Info("finished pruning sender")
+		GetLogger(ctx).Info("finished pruning sender")
 		senderCancel()
+		endSpan()
 	}
 	{
 		select {
@@ -365,14 +547,22 @@ func (j *ActiveSide) do(ctx context.Context) {
 			return
 		default:
 		}
+		ctx, endSpan := trace.WithSpan(ctx, "prune_recever")
 		ctx, receiverCancel := context.WithCancel(ctx)
 		tasks := j.updateTasks(func(tasks *activeSideTasks) {
 			tasks.prunerReceiver = j.prunerFactory.BuildReceiverPruner(ctx, receiver, sender)
-			tasks.prunerReceiverCancel = receiverCancel
+			tasks.prunerReceiverCancel = func() { receiverCancel(); endSpan() }
+			tasks.state = ActiveSidePruneReceiver
 		})
-		log.Info("start pruning receiver")
+		GetLogger(ctx).Info("start pruning receiver")
 		tasks.prunerReceiver.Prune()
-		log.Info("finished pruning receiver")
+		GetLogger(ctx).Info("finished pruning receiver")
 		receiverCancel()
+		endSpan()
 	}
+
+	j.updateTasks(func(tasks *activeSideTasks) {
+		tasks.state = ActiveSideDone
+	})
+
 }

daemon/job/active_test.go

@@ -0,0 +1,20 @@
+package job
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/transport"
+)
+
+func TestFakeActiveSideDirectMethodInvocationClientIdentityDoesNotPassValidityTest(t *testing.T) {
+	jobid, err := endpoint.MakeJobID("validjobname")
+	require.NoError(t, err)
+	clientIdentity := FakeActiveSideDirectMethodInvocationClientIdentity(jobid)
+	t.Logf("%v", clientIdentity)
+	err = transport.ValidateClientIdentity(clientIdentity)
+	assert.Error(t, err)
+}

daemon/job/activesidestate_enumer.go

@@ -0,0 +1,67 @@
+// Code generated by "enumer -type=ActiveSideState"; DO NOT EDIT.
+
+//
+package job
+
+import (
+	"fmt"
+)
+
+const (
+	_ActiveSideStateName_0 = "ActiveSideReplicatingActiveSidePruneSender"
+	_ActiveSideStateName_1 = "ActiveSidePruneReceiver"
+	_ActiveSideStateName_2 = "ActiveSideDone"
+)
+
+var (
+	_ActiveSideStateIndex_0 = [...]uint8{0, 21, 42}
+	_ActiveSideStateIndex_1 = [...]uint8{0, 23}
+	_ActiveSideStateIndex_2 = [...]uint8{0, 14}
+)
+
+func (i ActiveSideState) String() string {
+	switch {
+	case 1 <= i && i <= 2:
+		i -= 1
+		return _ActiveSideStateName_0[_ActiveSideStateIndex_0[i]:_ActiveSideStateIndex_0[i+1]]
+	case i == 4:
+		return _ActiveSideStateName_1
+	case i == 8:
+		return _ActiveSideStateName_2
+	default:
+		return fmt.Sprintf("ActiveSideState(%d)", i)
+	}
+}
+
+var _ActiveSideStateValues = []ActiveSideState{1, 2, 4, 8}
+
+var _ActiveSideStateNameToValueMap = map[string]ActiveSideState{
+	_ActiveSideStateName_0[0:21]:  1,
+	_ActiveSideStateName_0[21:42]: 2,
+	_ActiveSideStateName_1[0:23]:  4,
+	_ActiveSideStateName_2[0:14]:  8,
+}
+
+// ActiveSideStateString retrieves an enum value from the enum constants string name.
+// Throws an error if the param is not part of the enum.
+func ActiveSideStateString(s string) (ActiveSideState, error) {
+	if val, ok := _ActiveSideStateNameToValueMap[s]; ok {
+		return val, nil
+	}
+	return 0, fmt.Errorf("%s does not belong to ActiveSideState values", s)
+}
+
+// ActiveSideStateValues returns all values of the enum
+func ActiveSideStateValues() []ActiveSideState {
+	return _ActiveSideStateValues
+}
+
+// IsAActiveSideState returns "true" if the value is listed in the enum definition. "false" otherwise
+func (i ActiveSideState) IsAActiveSideState() bool {
+	for _, v := range _ActiveSideStateValues {
+		if i == v {
+			return true
+		}
+	}
+	return false
+}

daemon/job/build_jobs.go

@@ -2,14 +2,19 @@ package job
 
 import (
 	"fmt"
+	"sort"
+	"strings"
+
 	"github.com/pkg/errors"
+
 	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/util/bandwidthlimit"
 )
 
-func JobsFromConfig(c *config.Config) ([]Job, error) {
+func JobsFromConfig(c *config.Config, parseFlags config.ParseFlags) ([]Job, error) {
 	js := make([]Job, len(c.Jobs))
 	for i := range c.Jobs {
-		j, err := buildJob(c.Global, c.Jobs[i])
+		j, err := buildJob(c.Global, c.Jobs[i], parseFlags)
 		if err != nil {
 			return nil, err
 		}
@@ -18,48 +23,53 @@ func JobsFromConfig(c *config.Config) ([]Job, error) {
 		}
 		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) (j Job, err error) {
+func buildJob(c *config.Global, in config.JobEnum, parseFlags config.ParseFlags) (j Job, err error) {
 	cannotBuildJob := func(e error, name string) (Job, error) {
 		return nil, errors.Wrapf(e, "cannot build job %q", name)
 	}
 	// FIXME prettify this
 	switch v := in.Ret.(type) {
 	case *config.SinkJob:
-		m, err := modeSinkFromConfig(c, v)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-		j, err = passiveSideFromConfig(c, &v.PassiveJob, m)
+		j, err = passiveSideFromConfig(c, &v.PassiveJob, v, parseFlags)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
 	case *config.SourceJob:
-		m, err := modeSourceFromConfig(c, v)
+		j, err = passiveSideFromConfig(c, &v.PassiveJob, v, parseFlags)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
-		j, err = passiveSideFromConfig(c, &v.PassiveJob, m)
+	case *config.SnapJob:
+		j, err = snapJobFromConfig(c, v)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
 	case *config.PushJob:
-		m, err := modePushFromConfig(c, v)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-		j, err = activeSide(c, &v.ActiveJob, m)
+		j, err = activeSide(c, &v.ActiveJob, v, parseFlags)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
 	case *config.PullJob:
-		m, err := modePullFromConfig(c, v)
-		if err != nil {
-			return cannotBuildJob(err, v.Name)
-		}
-		j, err = activeSide(c, &v.ActiveJob, m)
+		j, err = activeSide(c, &v.ActiveJob, v, parseFlags)
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
@@ -69,3 +79,42 @@ func buildJob(c *config.Global, in config.JobEnum) (j Job, err error) {
 	return j, nil
 
 }
+
+func validateReceivingSidesDoNotOverlap(receivingRootFSs []string) error {
+	if len(receivingRootFSs) == 0 {
+		return nil
+	}
+	rfss := make([]string, len(receivingRootFSs))
+	copy(rfss, receivingRootFSs)
+	sort.Slice(rfss, func(i, j int) bool {
+		return strings.Compare(rfss[i], rfss[j]) == -1
+	})
+	// add tailing slash because of hierarchy-simulation
+	// rootfs/ is not root of rootfs2/
+	for i := 0; i < len(rfss); i++ {
+		rfss[i] += "/"
+	}
+	// idea:
+	//   no path in rfss must be prefix of another
+	//
+	// rfss is now lexicographically sorted, which means that
+	// if i is prefix of j, i < j (in lexicographical order)
+	// thus,
+	// if any i is prefix of i+n (n >= 1), there is overlap
+	for i := 0; i < len(rfss)-1; i++ {
+		if strings.HasPrefix(rfss[i+1], rfss[i]) {
+			return fmt.Errorf("receiving jobs with overlapping root filesystems are forbidden")
+		}
+	}
+	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

@@ -0,0 +1,102 @@
+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

@@ -0,0 +1,318 @@
+package job
+
+import (
+	"fmt"
+	"path"
+	"path/filepath"
+	"testing"
+
+	"github.com/kr/pretty"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/zrepl/zrepl/config"
+)
+
+func TestValidateReceivingSidesDoNotOverlap(t *testing.T) {
+	type testCase struct {
+		err   bool
+		input []string
+	}
+	tcs := []testCase{
+		{false, nil},
+		{false, []string{}},
+		{false, []string{""}}, // not our job to determine valid paths
+		{false, []string{"a"}},
+		{false, []string{"some/path"}},
+		{false, []string{"zroot/sink1", "zroot/sink2", "zroot/sink3"}},
+		{false, []string{"zroot/foo", "zroot/foobar"}},
+		{true, []string{"zroot/b", "zroot/b"}},
+		{true, []string{"zroot/foo", "zroot/foo/bar", "zroot/baz"}},
+		{false, []string{"a/x", "b/x"}},
+		{false, []string{"a", "b"}},
+		{true, []string{"a", "a"}},
+		{true, []string{"a/x/y", "a/x"}},
+		{true, []string{"a/x", "a/x/y"}},
+		{true, []string{"a/x", "b/x", "a/x/y"}},
+		{true, []string{"a", "a/b", "a/c", "a/b"}},
+		{true, []string{"a/b", "a/c", "a/b", "a/d", "a/c"}},
+	}
+
+	for _, tc := range tcs {
+		t.Logf("input: %v", tc.input)
+		err := validateReceivingSidesDoNotOverlap(tc.input)
+		if tc.err {
+			assert.Error(t, err)
+		} else {
+			assert.NoError(t, err)
+		}
+	}
+}
+
+func TestJobIDErrorHandling(t *testing.T) {
+	tmpl := `
+jobs:
+- name: %s
+  type: push
+  connect:
+    type: local
+    listener_name: foo
+    client_identity: bar
+  filesystems: {"<": true}
+  snapshotting:
+    type: manual
+  pruning:
+    keep_sender:
+    - type: last_n
+      count: 10
+    keep_receiver:
+    - type: last_n
+      count: 10
+`
+	fill := func(s string) string { return fmt.Sprintf(tmpl, s) }
+
+	type Case struct {
+		jobName string
+		valid   bool
+	}
+	cases := []Case{
+		{"validjobname", true},
+		{"valid with spaces", true},
+		{"invalid\twith\ttabs", false},
+		{"invalid#withdelimiter", false},
+		{"invalid@withdelimiter", false},
+		{"withnewline\\nmiddle", false},
+		{"withnewline\\n", false},
+		{"withslash/", false},
+		{"withslash/inthemiddle", false},
+		{"/", false},
+	}
+
+	for i := range cases {
+		t.Run(cases[i].jobName, func(t *testing.T) {
+			c := cases[i]
+
+			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)
+
+			if c.valid {
+				assert.NoError(t, err)
+				require.Len(t, jobs, 1)
+				assert.Equal(t, c.jobName, jobs[0].Name())
+			} else {
+				t.Logf("error: %s", err)
+				assert.Error(t, err)
+				assert.Nil(t, 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/job.go

@@ -4,49 +4,45 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+
 	"github.com/prometheus/client_golang/prometheus"
+
+	"github.com/zrepl/zrepl/daemon/logging"
+	"github.com/zrepl/zrepl/endpoint"
 	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/zfs"
 )
 
 type Logger = logger.Logger
 
-type contextKey int
-
-const (
-	contextKeyLog contextKey = iota
-)
-
 func GetLogger(ctx context.Context) Logger {
-	if l, ok := ctx.Value(contextKeyLog).(Logger); ok {
-		return l
-	}
-	return logger.NewNullLogger()
+	return logging.GetLogger(ctx, logging.SubsysJob)
 }
 
-func WithLogger(ctx context.Context, l Logger) context.Context {
-	return context.WithValue(ctx, contextKeyLog, l)
-}
-
-
 type Job interface {
 	Name() string
 	Run(ctx context.Context)
 	Status() *Status
 	RegisterMetrics(registerer prometheus.Registerer)
+	// Jobs that return a subtree of the dataset hierarchy
+	// must return the root of that subtree as rfs and ok = true
+	OwnedDatasetSubtreeRoot() (rfs *zfs.DatasetPath, ok bool)
+	SenderConfig() *endpoint.SenderConfig
 }
 
 type Type string
 
 const (
 	TypeInternal Type = "internal"
-	TypePush Type = "push"
-	TypeSink Type = "sink"
-	TypePull Type  = "pull"
-	TypeSource Type = "source"
+	TypeSnap     Type = "snap"
+	TypePush     Type = "push"
+	TypeSink     Type = "sink"
+	TypePull     Type = "pull"
+	TypeSource   Type = "source"
 )
 
 type Status struct {
-	Type Type
+	Type        Type
 	JobSpecific interface{}
 }
 
@@ -59,8 +55,8 @@ func (s *Status) MarshalJSON() ([]byte, error) {
 	if err != nil {
 		return nil, err
 	}
-	m := map[string]json.RawMessage {
-		"type": typeJson,
+	m := map[string]json.RawMessage{
+		"type":         typeJson,
 		string(s.Type): jobJSON,
 	}
 	return json.Marshal(m)
@@ -84,16 +80,25 @@ func (s *Status) UnmarshalJSON(in []byte) (err error) {
 		return fmt.Errorf("field '%s', not found", key)
 	}
 	switch s.Type {
-	case TypePull: fallthrough
+	case TypeSnap:
+		var st SnapJobStatus
+		err = json.Unmarshal(jobJSON, &st)
+		s.JobSpecific = &st
+
+	case TypePull:
+		fallthrough
 	case TypePush:
 		var st ActiveSideStatus
 		err = json.Unmarshal(jobJSON, &st)
 		s.JobSpecific = &st
-	case TypeSource: fallthrough
+
+	case TypeSource:
+		fallthrough
 	case TypeSink:
 		var st PassiveStatus
 		err = json.Unmarshal(jobJSON, &st)
 		s.JobSpecific = &st
+
 	case TypeInternal:
 		// internal jobs do not report specifics
 	default:

daemon/job/passive.go

@@ -2,89 +2,75 @@ package job
 
 import (
 	"context"
+	"fmt"
+
 	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
 	"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/transport/serve"
 	"github.com/zrepl/zrepl/daemon/snapper"
 	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/rpc"
+	"github.com/zrepl/zrepl/transport"
+	"github.com/zrepl/zrepl/transport/fromconfig"
 	"github.com/zrepl/zrepl/zfs"
-	"path"
 )
 
 type PassiveSide struct {
-	mode passiveMode
-	name     string
-	l        serve.ListenerFactory
-	rpcConf  *streamrpc.ConnConfig
+	mode   passiveMode
+	name   endpoint.JobID
+	listen transport.AuthenticatedListenerFactory
 }
 
 type passiveMode interface {
-	ConnHandleFunc(ctx context.Context, conn serve.AuthenticatedConn) streamrpc.HandlerFunc
+	Handler() rpc.Handler
 	RunPeriodic(ctx context.Context)
+	SnapperReport() *snapper.Report // may be nil
 	Type() Type
 }
 
 type modeSink struct {
-	rootDataset *zfs.DatasetPath
+	receiverConfig endpoint.ReceiverConfig
 }
 
 func (m *modeSink) Type() Type { return TypeSink }
 
-func (m *modeSink) ConnHandleFunc(ctx context.Context, conn serve.AuthenticatedConn) streamrpc.HandlerFunc {
-	log := GetLogger(ctx)
-
-	clientRootStr := path.Join(m.rootDataset.ToString(), conn.ClientIdentity())
-	clientRoot, err := zfs.NewDatasetPath(clientRootStr)
-	if err != nil {
-		log.WithError(err).
-			WithField("client_identity", conn.ClientIdentity()).
-			Error("cannot build client filesystem map (client identity must be a valid ZFS FS name")
-	}
-	log.WithField("client_root", clientRoot).Debug("client root")
-
-	local, err := endpoint.NewReceiver(clientRoot)
-	if err != nil {
-		log.WithError(err).Error("unexpected error: cannot convert mapping to filter")
-		return nil
-	}
-
-	h := endpoint.NewHandler(local)
-	return h.Handle
+func (m *modeSink) Handler() rpc.Handler {
+	return endpoint.NewReceiver(m.receiverConfig)
 }
 
-func (m *modeSink) RunPeriodic(_ context.Context) {}
+func (m *modeSink) RunPeriodic(_ context.Context)  {}
+func (m *modeSink) SnapperReport() *snapper.Report { return nil }
 
-func modeSinkFromConfig(g *config.Global, in *config.SinkJob) (m *modeSink, err error) {
+func modeSinkFromConfig(g *config.Global, in *config.SinkJob, jobID endpoint.JobID) (m *modeSink, err error) {
 	m = &modeSink{}
-	m.rootDataset, err = zfs.NewDatasetPath(in.RootFS)
+
+	m.receiverConfig, err = buildReceiverConfig(in, jobID)
 	if err != nil {
-		return nil, errors.New("root dataset is not a valid zfs filesystem path")
-	}
-	if m.rootDataset.Length() <= 0 {
-		return nil, errors.New("root dataset must not be empty") // duplicates error check of receiver
+		return nil, err
 	}
+
 	return m, nil
 }
 
 type modeSource struct {
-	fsfilter zfs.DatasetFilter
-	snapper *snapper.PeriodicOrManual
+	senderConfig *endpoint.SenderConfig
+	snapper      snapper.Snapper
 }
 
-func modeSourceFromConfig(g *config.Global, in *config.SourceJob) (m *modeSource, err error) {
+func modeSourceFromConfig(g *config.Global, in *config.SourceJob, jobID endpoint.JobID) (m *modeSource, err error) {
 	// FIXME exact dedup of modePush
 	m = &modeSource{}
-	fsf, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
-	if err != nil {
-		return nil, errors.Wrap(err, "cannnot build filesystem filter")
-	}
-	m.fsfilter = fsf
 
-	if m.snapper, err = snapper.FromConfig(g, fsf, in.Snapshotting); err != nil {
+	m.senderConfig, err = buildSenderConfig(in, jobID)
+	if err != nil {
+		return nil, errors.Wrap(err, "send options")
+	}
+
+	if m.snapper, err = snapper.FromConfig(g, m.senderConfig.FSF, in.Snapshotting); err != nil {
 		return nil, errors.Wrap(err, "cannot build snapper")
 	}
 
@@ -93,104 +79,114 @@ func modeSourceFromConfig(g *config.Global, in *config.SourceJob) (m *modeSource
 
 func (m *modeSource) Type() Type { return TypeSource }
 
-func (m *modeSource) ConnHandleFunc(ctx context.Context, conn serve.AuthenticatedConn) streamrpc.HandlerFunc {
-	sender := endpoint.NewSender(m.fsfilter)
-	h := endpoint.NewHandler(sender)
-	return h.Handle
+func (m *modeSource) Handler() rpc.Handler {
+	return endpoint.NewSender(*m.senderConfig)
 }
 
 func (m *modeSource) RunPeriodic(ctx context.Context) {
 	m.snapper.Run(ctx, nil)
 }
 
-func passiveSideFromConfig(g *config.Global, in *config.PassiveJob, mode passiveMode) (s *PassiveSide, err error) {
+func (m *modeSource) SnapperReport() *snapper.Report {
+	r := m.snapper.Report()
+	return &r
+}
 
-	s = &PassiveSide{mode: mode, name: in.Name}
-	if s.l, s.rpcConf, err = serve.FromConfig(g, in.Serve); err != nil {
-		return nil, errors.Wrap(err, "cannot build server")
+func passiveSideFromConfig(g *config.Global, in *config.PassiveJob, configJob interface{}, parseFlags config.ParseFlags) (s *PassiveSide, err error) {
+
+	s = &PassiveSide{}
+
+	s.name, err = endpoint.MakeJobID(in.Name)
+	if err != nil {
+		return nil, errors.Wrap(err, "invalid job name")
+	}
+
+	switch v := configJob.(type) {
+	case *config.SinkJob:
+		s.mode, err = modeSinkFromConfig(g, v, s.name) // shadow
+	case *config.SourceJob:
+		s.mode, err = modeSourceFromConfig(g, v, s.name) // shadow
+	}
+	if err != nil {
+		return nil, err // no wrapping necessary
+	}
+
+	if s.listen, err = fromconfig.ListenerFactoryFromConfig(g, in.Serve, parseFlags); err != nil {
+		return nil, errors.Wrap(err, "cannot build listener factory")
 	}
 
 	return s, nil
 }
 
-func (j *PassiveSide) Name() string { return j.name }
+func (j *PassiveSide) Name() string { return j.name.String() }
 
-type PassiveStatus struct {}
+type PassiveStatus struct {
+	Snapper *snapper.Report
+}
 
 func (s *PassiveSide) Status() *Status {
-	return &Status{Type: s.mode.Type()} // FIXME PassiveStatus
+	st := &PassiveStatus{
+		Snapper: s.mode.SnapperReport(),
+	}
+	return &Status{Type: s.mode.Type(), JobSpecific: st}
+}
+
+func (j *PassiveSide) OwnedDatasetSubtreeRoot() (rfs *zfs.DatasetPath, ok bool) {
+	sink, ok := j.mode.(*modeSink)
+	if !ok {
+		_ = j.mode.(*modeSource) // make sure we didn't introduce a new job type
+		return nil, false
+	}
+	return sink.receiverConfig.RootWithoutClientComponent.Copy(), true
+}
+
+func (j *PassiveSide) SenderConfig() *endpoint.SenderConfig {
+	source, ok := j.mode.(*modeSource)
+	if !ok {
+		_ = j.mode.(*modeSink) // make sure we didn't introduce a new job type
+		return nil
+	}
+	return source.senderConfig
 }
 
 func (*PassiveSide) RegisterMetrics(registerer prometheus.Registerer) {}
 
 func (j *PassiveSide) Run(ctx context.Context) {
-
+	ctx, endTask := trace.WithTaskAndSpan(ctx, "passive-side-job", j.Name())
+	defer endTask()
 	log := GetLogger(ctx)
 	defer log.Info("job exiting")
-
-	l, err := j.l.Listen()
-	if err != nil {
-		log.WithError(err).Error("cannot listen")
-		return
-	}
-	defer l.Close()
-
 	{
-		ctx, cancel := context.WithCancel(logging.WithSubsystemLoggers(ctx, log)) // shadowing
+		ctx, endTask := trace.WithTask(ctx, "periodic") // shadowing
+		defer endTask()
+		ctx, cancel := context.WithCancel(ctx)
 		defer cancel()
 		go j.mode.RunPeriodic(ctx)
 	}
 
-	log.WithField("addr", l.Addr()).Debug("accepting connections")
-	var connId int
-outer:
-	for {
-
-		select {
-		case res := <-accept(ctx, l):
-			if res.err != nil {
-				log.WithError(res.err).Info("accept error")
-				continue
-			}
-			conn := res.conn
-			connId++
-			connLog := log.
-				WithField("connID", connId)
-			connLog.
-				WithField("addr", conn.RemoteAddr()).
-				WithField("client_identity", conn.ClientIdentity()).
-				Info("handling connection")
-			go func() {
-				defer connLog.Info("finished handling connection")
-				defer conn.Close()
-				ctx := logging.WithSubsystemLoggers(ctx, connLog)
-				handleFunc := j.mode.ConnHandleFunc(ctx, conn)
-				if handleFunc == nil {
-					return
-				}
-				if err := streamrpc.ServeConn(ctx, conn, j.rpcConf, handleFunc); err != nil {
-					log.WithError(err).Error("error serving client")
-				}
-			}()
-
-		case <-ctx.Done():
-			break outer
-		}
-
+	handler := j.mode.Handler()
+	if handler == nil {
+		panic(fmt.Sprintf("implementation error: j.mode.Handler() returned nil: %#v", j))
 	}
 
-}
+	ctxInterceptor := func(handlerCtx context.Context, info rpc.HandlerContextInterceptorData, handler func(ctx context.Context)) {
+		// the handlerCtx is clean => need to inherit logging and tracing config from job context
+		handlerCtx = logging.WithInherit(handlerCtx, ctx)
+		handlerCtx = trace.WithInherit(handlerCtx, ctx)
 
-type acceptResult struct {
-	conn serve.AuthenticatedConn
-	err  error
-}
+		handlerCtx, endTask := trace.WithTaskAndSpan(handlerCtx, "handler", fmt.Sprintf("job=%q client=%q method=%q", j.Name(), info.ClientIdentity(), info.FullMethod()))
+		defer endTask()
+		handler(handlerCtx)
+	}
 
-func accept(ctx context.Context, listener serve.AuthenticatedListener) <-chan acceptResult {
-	c := make(chan acceptResult, 1)
-	go func() {
-		conn, err := listener.Accept(ctx)
-		c <- acceptResult{conn, err}
-	}()
-	return c
+	rpcLoggers := rpc.GetLoggersOrPanic(ctx) // WithSubsystemLoggers above
+	server := rpc.NewServer(handler, rpcLoggers, ctxInterceptor)
+
+	listener, err := j.listen()
+	if err != nil {
+		log.WithError(err).Error("cannot listen")
+		return
+	}
+
+	server.Serve(ctx, listener)
 }

daemon/job/snapjob.go

@@ -0,0 +1,196 @@
+package job
+
+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/wakeup"
+	"github.com/zrepl/zrepl/daemon/pruner"
+	"github.com/zrepl/zrepl/daemon/snapper"
+	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/replication/logic/pdu"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+type SnapJob struct {
+	name     endpoint.JobID
+	fsfilter zfs.DatasetFilter
+	snapper  snapper.Snapper
+
+	prunerFactory *pruner.LocalPrunerFactory
+
+	promPruneSecs *prometheus.HistogramVec // labels: prune_side
+
+	prunerMtx sync.Mutex
+	pruner    *pruner.Pruner
+}
+
+func (j *SnapJob) Name() string { return j.name.String() }
+
+func (j *SnapJob) Type() Type { return TypeSnap }
+
+func snapJobFromConfig(g *config.Global, in *config.SnapJob) (j *SnapJob, err error) {
+	j = &SnapJob{}
+	fsf, err := filters.DatasetMapFilterFromConfig(in.Filesystems)
+	if err != nil {
+		return nil, errors.Wrap(err, "cannot build filesystem filter")
+	}
+	j.fsfilter = fsf
+
+	if j.snapper, err = snapper.FromConfig(g, fsf, in.Snapshotting); err != nil {
+		return nil, errors.Wrap(err, "cannot build snapper")
+	}
+	j.name, err = endpoint.MakeJobID(in.Name)
+	if err != nil {
+		return nil, errors.Wrap(err, "invalid job name")
+	}
+	j.promPruneSecs = prometheus.NewHistogramVec(prometheus.HistogramOpts{
+		Namespace:   "zrepl",
+		Subsystem:   "pruning",
+		Name:        "time",
+		Help:        "seconds spent in pruner",
+		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
+	}, []string{"prune_side"})
+	j.prunerFactory, err = pruner.NewLocalPrunerFactory(in.Pruning, j.promPruneSecs)
+	if err != nil {
+		return nil, errors.Wrap(err, "cannot build snapjob pruning rules")
+	}
+	return j, nil
+}
+
+func (j *SnapJob) RegisterMetrics(registerer prometheus.Registerer) {
+	registerer.MustRegister(j.promPruneSecs)
+}
+
+type SnapJobStatus struct {
+	Pruning      *pruner.Report
+	Snapshotting *snapper.Report // may be nil
+}
+
+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
+	return &Status{Type: t, JobSpecific: s}
+}
+
+func (j *SnapJob) OwnedDatasetSubtreeRoot() (rfs *zfs.DatasetPath, ok bool) {
+	return nil, false
+}
+
+func (j *SnapJob) SenderConfig() *endpoint.SenderConfig { return nil }
+
+func (j *SnapJob) Run(ctx context.Context) {
+	ctx, endTask := trace.WithTaskAndSpan(ctx, "snap-job", j.Name())
+	defer endTask()
+	log := GetLogger(ctx)
+
+	defer log.Info("job exiting")
+
+	periodicDone := make(chan struct{})
+	ctx, cancel := context.WithCancel(ctx)
+	defer cancel()
+	periodicCtx, endTask := trace.WithTask(ctx, "snapshotting")
+	defer endTask()
+	go j.snapper.Run(periodicCtx, periodicDone)
+
+	invocationCount := 0
+outer:
+	for {
+		log.Info("wait for wakeups")
+		select {
+		case <-ctx.Done():
+			log.WithError(ctx.Err()).Info("context")
+			break outer
+
+		case <-wakeup.Wait(ctx):
+		case <-periodicDone:
+		}
+		invocationCount++
+
+		invocationCtx, endSpan := trace.WithSpan(ctx, fmt.Sprintf("invocation-%d", invocationCount))
+		j.doPrune(invocationCtx)
+		endSpan()
+	}
+}
+
+// Adaptor that implements pruner.History around a pruner.Target.
+// The ReplicationCursor method is Get-op only and always returns
+// the filesystem's most recent version's GUID.
+//
+// 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,
+// 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
+// most recent filesystem version.
+type alwaysUpToDateReplicationCursorHistory struct {
+	// the Target passed as Target to BuildLocalPruner
+	target pruner.Target
+}
+
+var _ pruner.Sender = (*alwaysUpToDateReplicationCursorHistory)(nil)
+
+func (h alwaysUpToDateReplicationCursorHistory) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
+	fsvReq := &pdu.ListFilesystemVersionsReq{
+		Filesystem: req.GetFilesystem(),
+	}
+	res, err := h.target.ListFilesystemVersions(ctx, fsvReq)
+	if err != nil {
+		return nil, err
+	}
+	fsvs := res.GetVersions()
+	if len(fsvs) <= 0 {
+		return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Notexist{Notexist: true}}, nil
+	}
+	// always return must recent version
+	sort.Slice(fsvs, func(i, j int) bool {
+		return fsvs[i].CreateTXG < fsvs[j].CreateTXG
+	})
+	mostRecent := fsvs[len(fsvs)-1]
+	return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Guid{Guid: mostRecent.GetGuid()}}, nil
+}
+
+func (h alwaysUpToDateReplicationCursorHistory) ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error) {
+	return h.target.ListFilesystems(ctx, req)
+}
+
+func (j *SnapJob) doPrune(ctx context.Context) {
+	ctx, endSpan := trace.WithSpan(ctx, "snap-job-do-prune")
+	defer endSpan()
+	log := GetLogger(ctx)
+	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(),
+	})
+	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/logging/adaptors.go

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

daemon/logging/build_logging.go

@@ -4,18 +4,16 @@ import (
 	"context"
 	"crypto/tls"
 	"crypto/x509"
+	"log/syslog"
+	"os"
+
 	"github.com/mattn/go-isatty"
 	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
+
 	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/pruner"
-	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/daemon/logging/trace"
 	"github.com/zrepl/zrepl/logger"
-	"github.com/zrepl/zrepl/replication"
 	"github.com/zrepl/zrepl/tlsconf"
-	"os"
-	"github.com/zrepl/zrepl/daemon/snapper"
-	"github.com/zrepl/zrepl/daemon/transport/serve"
 )
 
 func OutletsFromConfig(in config.LoggingOutletEnumList) (*logger.Outlets, error) {
@@ -32,7 +30,7 @@ func OutletsFromConfig(in config.LoggingOutletEnumList) (*logger.Outlets, error)
 	var syslogOutlets, stdoutOutlets int
 	for lei, le := range in {
 
-		outlet, minLevel, err := parseOutlet(le)
+		outlet, minLevel, err := ParseOutlet(le)
 		if err != nil {
 			return nil, errors.Wrapf(err, "cannot parse outlet #%d", lei)
 		}
@@ -60,20 +58,119 @@ func OutletsFromConfig(in config.LoggingOutletEnumList) (*logger.Outlets, error)
 
 }
 
+type Subsystem string
+
 const (
-	SubsysReplication = "repl"
-	SubsysStreamrpc   = "rpc"
-	SubsyEndpoint     = "endpoint"
+	SubsysMeta         Subsystem = "meta"
+	SubsysJob          Subsystem = "job"
+	SubsysReplication  Subsystem = "repl"
+	SubsysEndpoint     Subsystem = "endpoint"
+	SubsysPruning      Subsystem = "pruning"
+	SubsysSnapshot     Subsystem = "snapshot"
+	SubsysHooks        Subsystem = "hook"
+	SubsysTransport    Subsystem = "transport"
+	SubsysTransportMux Subsystem = "transportmux"
+	SubsysRPC          Subsystem = "rpc"
+	SubsysRPCControl   Subsystem = "rpc.ctrl"
+	SubsysRPCData      Subsystem = "rpc.data"
+	SubsysZFSCmd       Subsystem = "zfs.cmd"
+	SubsysTraceData    Subsystem = "trace.data"
+	SubsysPlatformtest Subsystem = "platformtest"
 )
 
-func WithSubsystemLoggers(ctx context.Context, log logger.Logger) context.Context {
-	ctx = replication.WithLogger(ctx, log.WithField(SubsysField, "repl"))
-	ctx = streamrpc.ContextWithLogger(ctx, streamrpcLogAdaptor{log.WithField(SubsysField, "rpc")})
-	ctx = endpoint.WithLogger(ctx, log.WithField(SubsysField, "endpoint"))
-	ctx = pruner.WithLogger(ctx, log.WithField(SubsysField, "pruning"))
-	ctx = snapper.WithLogger(ctx, log.WithField(SubsysField, "snapshot"))
-	ctx = serve.WithLogger(ctx, log.WithField(SubsysField, "serve"))
-	return ctx
+var AllSubsystems = []Subsystem{
+	SubsysMeta,
+	SubsysJob,
+	SubsysReplication,
+	SubsysEndpoint,
+	SubsysPruning,
+	SubsysSnapshot,
+	SubsysHooks,
+	SubsysTransport,
+	SubsysTransportMux,
+	SubsysRPC,
+	SubsysRPCControl,
+	SubsysRPCData,
+	SubsysZFSCmd,
+	SubsysTraceData,
+	SubsysPlatformtest,
+}
+
+type injectedField struct {
+	field  string
+	value  interface{}
+	parent *injectedField
+}
+
+func WithInjectedField(ctx context.Context, field string, value interface{}) context.Context {
+	var parent *injectedField
+	parentI := ctx.Value(contextKeyInjectedField)
+	if parentI != nil {
+		parent = parentI.(*injectedField)
+	}
+	// TODO sanity-check `field` now
+	this := &injectedField{field, value, parent}
+	return context.WithValue(ctx, contextKeyInjectedField, this)
+}
+
+func iterInjectedFields(ctx context.Context, cb func(field string, value interface{})) {
+	injI := ctx.Value(contextKeyInjectedField)
+	if injI == nil {
+		return
+	}
+	inj := injI.(*injectedField)
+	for ; inj != nil; inj = inj.parent {
+		cb(inj.field, inj.value)
+	}
+}
+
+type SubsystemLoggers map[Subsystem]logger.Logger
+
+func SubsystemLoggersWithUniversalLogger(l logger.Logger) SubsystemLoggers {
+	loggers := make(SubsystemLoggers)
+	for _, s := range AllSubsystems {
+		loggers[s] = l
+	}
+	return loggers
+}
+
+func WithLoggers(ctx context.Context, loggers SubsystemLoggers) context.Context {
+	return context.WithValue(ctx, contextKeyLoggers, loggers)
+}
+
+func GetLoggers(ctx context.Context) SubsystemLoggers {
+	loggers, ok := ctx.Value(contextKeyLoggers).(SubsystemLoggers)
+	if !ok {
+		return nil
+	}
+	return loggers
+}
+
+func GetLogger(ctx context.Context, subsys Subsystem) logger.Logger {
+	return getLoggerImpl(ctx, subsys, true)
+}
+
+func getLoggerImpl(ctx context.Context, subsys Subsystem, panicIfEnded bool) logger.Logger {
+	loggers, ok := ctx.Value(contextKeyLoggers).(SubsystemLoggers)
+	if !ok || loggers == nil {
+		return logger.NewNullLogger()
+	}
+	l, ok := loggers[subsys]
+	if !ok {
+		return logger.NewNullLogger()
+	}
+
+	l = l.WithField(SubsysField, subsys)
+
+	l = l.WithField(SpanField, trace.GetSpanStackOrDefault(ctx, *trace.StackKindId, "NOSPAN"))
+
+	fields := make(logger.Fields)
+	iterInjectedFields(ctx, func(field string, value interface{}) {
+		fields[field] = value
+	})
+	l = l.WithFields(fields)
+
+	return l
 }
 
 func parseLogFormat(i interface{}) (f EntryFormatter, err error) {
@@ -98,7 +195,7 @@ func parseLogFormat(i interface{}) (f EntryFormatter, err error) {
 
 }
 
-func parseOutlet(in config.LoggingOutletEnum) (o logger.Outlet, level logger.Level, err error) {
+func ParseOutlet(in config.LoggingOutletEnum) (o logger.Outlet, level logger.Level, err error) {
 
 	parseCommon := func(common config.LoggingOutletCommon) (logger.Level, EntryFormatter, error) {
 		if common.Level == "" || common.Format == "" {
@@ -200,6 +297,7 @@ func parseSyslogOutlet(in *config.SyslogLoggingOutlet, formatter EntryFormatter)
 	out = &SyslogOutlet{}
 	out.Formatter = formatter
 	out.Formatter.SetMetadataFlags(MetadataNone)
+	out.Facility = syslog.Priority(*in.Facility)
 	out.RetryInterval = in.RetryInterval
 	return out, nil
 }