docs: fix publish.sh branch whitelisting

hotfix #161 for 0.1: limit concurrency of zfs send & recv commands

.circleci/config.yml

@@ -0,0 +1,102 @@
+version: 2.0
+workflows:
+  version: 2
+  build:
+    jobs:
+      - build-1.11
+      - build-1.12
+      - build-latest
+jobs:
+  # build-latest serves as the template
+  # we use YAML anchors & aliases to exchange the docker image (and hence Go version used for the build)
+  build-latest: &build-latest
+    description: Builds zrepl
+    parameters:
+      image:
+        description: "the docker image that the job should use"
+        type: string
+    docker:
+      - image: circleci/golang:latest
+    environment:
+      # required by lazy.sh
+      TERM: xterm
+    working_directory: /go/src/github.com/zrepl/zrepl
+    steps:
+      - run:
+          name: Setup environment variables
+          command: |
+            # used by pip (for docs)
+            echo 'export PATH="$HOME/.local/bin:$PATH"' >> $BASH_ENV
+
+      - restore_cache:
+          keys:
+            - source
+            - vendor
+            - protobuf
+
+      - checkout
+
+      - save_cache:
+          key: source
+          paths:
+            - ".git"
+      
+      # install deps
+      - run: wget https://github.com/protocolbuffers/protobuf/releases/download/v3.6.1/protoc-3.6.1-linux-x86_64.zip
+      - run: echo "6003de742ea3fcf703cfec1cd4a3380fd143081a2eb0e559065563496af27807  protoc-3.6.1-linux-x86_64.zip" | sha256sum -c
+      - run: sudo unzip -d /usr protoc-3.6.1-linux-x86_64.zip
+      - save_cache:
+          key: protobuf
+          paths:
+            - "/usr/include/google/protobuf"
+            
+      - run: sudo apt install python3 python3-pip libgirepository1.0-dev
+      - run: ./lazy.sh devsetup
+
+      - run:
+          name: Install minio client, prepare minio
+          command: |
+            curl -sSL https://dl.minio.io/client/mc/release/linux-amd64/mc -o ${GOPATH}/bin/mc
+            chmod +x ${GOPATH}/bin/mc
+            mc config host add --api s3v4 zrepl-minio https://minio.cschwarz.com ${MINIO_ACCESS_KEY} ${MINIO_SECRET_KEY}
+
+      - run: make vendordeps
+      - save_cache:
+          key: vendor
+          paths:
+            - "./vendor"
+            
+      - run: make
+      - run: make vet
+      - run: make test
+      - run: make lint
+      - run: make release
+
+
+      - store_artifacts:
+          path: ./artifacts/release
+          when: always
+
+      - run:
+          shell: /bin/bash -euo pipefail
+          when: always
+          command: |
+            echo "$CIRCLE_BUILD_URL" > ./artifacts/release/cirlceci_build_url
+            mc cp -r artifacts/release "zrepl-minio/zrepl-ci-artifacts/${CIRCLE_SHA1}/${CIRCLE_JOB}/"
+            REPO="zrepl/zrepl"
+            COMMIT="${CIRCLE_SHA1}"
+            JOB_NAME="${CIRCLE_JOB}"
+            curl "https://api.github.com/repos/$REPO/statuses/$COMMIT?access_token=$GITHUB_COMMIT_STATUS_TOKEN" \
+              -H "Content-Type: application/json" \
+              -X POST \
+              -d '{"context":"zrepl/publish-ci-artifacts", "state": "success", "description":"CI Build Artifacts for '"$JOB_NAME"'", "target_url":"https://minio.cschwarz.com/minio/zrepl-ci-artifacts/'"$COMMIT"'/"}'
+
+
+  build-1.11:
+    <<: *build-latest
+    docker:
+      - image: circleci/golang:1.11
+  build-1.12:
+    <<: *build-latest
+    docker:
+    - image: circleci/golang:1.12

.golangci.yml

@@ -0,0 +1,10 @@
+linters:
+  enable:
+  - goimports
+
+issues:
+  exclude-rules:
+    - path: _test\.go
+      linters:
+        - errcheck
+

.travis.yml

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

Gopkg.lock

@@ -1,6 +1,30 @@
 # This file is autogenerated, do not edit; changes may be undone by the next 'dep ensure'.
 
 
+[[projects]]
+  digest = "1:e4b30804a381d7603b8a344009987c1ba351c26043501b23b8c7ce21f0b67474"
+  name = "github.com/BurntSushi/toml"
+  packages = ["."]
+  pruneopts = ""
+  revision = "3012a1dbe2e4bd1391d42b32f0577cb7bbc7f005"
+  version = "v0.3.1"
+
+[[projects]]
+  branch = "master"
+  digest = "1:bf241ce6eec44d9ebca17e22af43f13c25f55267b308ce8b29b9820c0d6d1d25"
+  name = "github.com/OpenPeeDeeP/depguard"
+  packages = ["."]
+  pruneopts = ""
+  revision = "1f388ab2d81096755d25043aa729e2fb889f3dae"
+
+[[projects]]
+  branch = "master"
+  digest = "1:8cf2cf1ab10480b5e0df950dac1517aaabde05d055d9d955652997ae4b9ecbbf"
+  name = "github.com/alvaroloes/enumer"
+  packages = ["."]
+  pruneopts = ""
+  revision = "6bcfe2edaac32ad71b88ce4cf92d34cd643e4ecb"
+
 [[projects]]
   branch = "master"
   digest = "1:c0bec5f9b98d0bc872ff5e834fac186b807b656683bd29cb82fb207a1513fabb"
@@ -25,6 +49,14 @@
   revision = "5b77d2a35fb0ede96d138fc9a99f5c9b6aef11b4"
   version = "v1.7.0"
 
+[[projects]]
+  digest = "1:eb53021a8aa3f599d29c7102e65026242bdedce998a54837dc67f14b6a97c5fd"
+  name = "github.com/fsnotify/fsnotify"
+  packages = ["."]
+  pruneopts = ""
+  revision = "c2828203cd70a50dcccfb2761f8b1f8ceef9a8e9"
+  version = "v1.4.7"
+
 [[projects]]
   branch = "master"
   digest = "1:5d0a2385edf4ba44f3b7b76bc0436ceb8f62bf55aa5d540a9eb9ec6c58d86809"
@@ -53,6 +85,28 @@
   revision = "de7e78efa4a71b3f36c7154989c529dbdf9ae623"
   version = "v1.1.0"
 
+[[projects]]
+  digest = "1:9d3f086381a257229b34fcd5690c3e5cadcb5f365cb35757536f3c51ccbb9049"
+  name = "github.com/go-critic/go-critic"
+  packages = [
+    "checkers",
+    "checkers/internal/lintutil",
+  ]
+  pruneopts = ""
+  revision = "d7b3038bc7a1c35a1d02fdd7cf4094f0f1a12001"
+  version = "v0.3.4"
+
+[[projects]]
+  digest = "1:50907242db0cb4c5d982ae213b995e9176b917edb269b645097af3289d9a15da"
+  name = "github.com/go-lintpack/lintpack"
+  packages = [
+    ".",
+    "astwalk",
+  ]
+  pruneopts = ""
+  revision = "80adc0715ac409128d0b7212719896ad8d3444b7"
+  version = "v0.5.2"
+
 [[projects]]
   digest = "1:6a4a01d58b227c4b6b11111b9f172ec5c17682b82724e58e6daf3f19f4faccd8"
   name = "github.com/go-logfmt/logfmt"
@@ -61,14 +115,349 @@
   revision = "390ab7935ee28ec6b286364bba9b4dd6410cb3d5"
   version = "v0.3.0"
 
+[[projects]]
+  digest = "1:1119997895278e1b27810308d8f802590e713bf0263b13be304ca9e086bd22a7"
+  name = "github.com/go-toolsmith/astcast"
+  packages = ["."]
+  pruneopts = ""
+  revision = "a6cb19f07b66b859a53f3f2be6e4c3bba892db7e"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:bcff57ad40d16a950986eb45dae40ed142d51c702e41fad2177518071bcc3d40"
+  name = "github.com/go-toolsmith/astcopy"
+  packages = ["."]
+  pruneopts = ""
+  revision = "245af3020944a15e09072c8ad3883c1451d1fdef"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:f6629a0ef3b819e34d4634c7540edf0cb392054ade814c4a9587ab6a23685def"
+  name = "github.com/go-toolsmith/astequal"
+  packages = ["."]
+  pruneopts = ""
+  revision = "dcb477bfacd6e00a13c6d63bfc73db28dd343160"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:05a2d85ca9e1164efa7cfb988d44bff221382658e567d958a78734bb9cccb758"
+  name = "github.com/go-toolsmith/astfmt"
+  packages = ["."]
+  pruneopts = ""
+  revision = "0d74c731079884bda287cf8df9ce7b92e688af8c"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:a6f3d4784ec69928a0a54521dd2536e6bacc73edf988edefc2820230d7be7703"
+  name = "github.com/go-toolsmith/astp"
+  packages = ["."]
+  pruneopts = ""
+  revision = "6373270dee65bfb0479f2acd16d4c8e9d5db13f8"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:9ba1aaf89cddc1cfe5d9a4a83d16ff8778369eaa358278a3fa2ef97847ebdb35"
+  name = "github.com/go-toolsmith/strparse"
+  packages = ["."]
+  pruneopts = ""
+  revision = "830b6daa1241714c12a9b9a4a56849fe2f93aedc"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:b827014e6963ac236f3698ce5ca1c85ad3ccfbf722186eab207836e1d7b9d615"
+  name = "github.com/go-toolsmith/typep"
+  packages = ["."]
+  pruneopts = ""
+  revision = "cab1745ffd84a567b524317c7f90e96755b18fcf"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:9ab1b1c637d7c8f49e39d8538a650d7eb2137b076790cff69d160823b505964c"
+  name = "github.com/gobwas/glob"
+  packages = [
+    ".",
+    "compiler",
+    "match",
+    "syntax",
+    "syntax/ast",
+    "syntax/lexer",
+    "util/runes",
+    "util/strings",
+  ]
+  pruneopts = ""
+  revision = "5ccd90ef52e1e632236f7326478d4faa74f99438"
+  version = "v0.2.3"
+
+[[projects]]
+  digest = "1:fd53b471edb4c28c7d297f617f4da0d33402755f58d6301e7ca1197ef0a90937"
+  name = "github.com/gogo/protobuf"
+  packages = ["proto"]
+  pruneopts = ""
+  revision = "ba06b47c162d49f2af050fb4c75bcbc86a159d5c"
+  version = "v1.2.1"
+
+[[projects]]
+  digest = "1:530233672f656641b365f8efb38ed9fba80e420baff2ce87633813ab3755ed6d"
+  name = "github.com/golang/mock"
+  packages = ["gomock"]
+  pruneopts = ""
+  revision = "51421b967af1f557f93a59e0057aaf15ca02e29c"
+  version = "v1.2.0"
+
 [[projects]]
   digest = "1:3dd078fda7500c341bc26cfbc6c6a34614f295a2457149fc1045cab767cbcf18"
   name = "github.com/golang/protobuf"
-  packages = ["proto"]
+  packages = [
+    "proto",
+    "protoc-gen-go",
+    "protoc-gen-go/descriptor",
+    "protoc-gen-go/generator",
+    "protoc-gen-go/generator/internal/remap",
+    "protoc-gen-go/grpc",
+    "protoc-gen-go/plugin",
+    "ptypes",
+    "ptypes/any",
+    "ptypes/duration",
+    "ptypes/timestamp",
+  ]
   pruneopts = ""
   revision = "aa810b61a9c79d51363740d207bb46cf8e620ed5"
   version = "v1.2.0"
 
+[[projects]]
+  branch = "master"
+  digest = "1:f6a3ed95affdd867195dec281bf1d328dddb37590463eba1f7b39b44a9829e3d"
+  name = "github.com/golangci/check"
+  packages = [
+    "cmd/structcheck",
+    "cmd/varcheck",
+  ]
+  pruneopts = ""
+  revision = "cfe4005ccda277a820149d44d6ededc400cc99a2"
+
+[[projects]]
+  branch = "master"
+  digest = "1:262000a2de14b1d0a802acb611e7ee69208b7e3e08f7d0e62226bb324f12e375"
+  name = "github.com/golangci/dupl"
+  packages = [
+    ".",
+    "job",
+    "printer",
+    "suffixtree",
+    "syntax",
+    "syntax/golang",
+  ]
+  pruneopts = ""
+  revision = "3e9179ac440a0386ac7cc9a085fc44397c6b9bbc"
+
+[[projects]]
+  branch = "master"
+  digest = "1:2298a8780ede449cb58108de23925ac2a14cca8ac151cfae45ea5992054d6cf2"
+  name = "github.com/golangci/errcheck"
+  packages = [
+    "golangci",
+    "internal/errcheck",
+  ]
+  pruneopts = ""
+  revision = "ef45e06d44b6e018d817c16c762d448990adc5e0"
+
+[[projects]]
+  branch = "master"
+  digest = "1:9b38ad496c9dabd1c820609c481f59c6c9597926c6125810af3d7a71bf2d649c"
+  name = "github.com/golangci/go-misc"
+  packages = ["deadcode"]
+  pruneopts = ""
+  revision = "927a3d87b613e9f6f0fb7ef8bb8de8b83c30a5a2"
+
+[[projects]]
+  branch = "master"
+  digest = "1:e4bbd53b867030ca8b2e0f6d7338cec2373baf14109858312daa51a144f4a091"
+  name = "github.com/golangci/go-tools"
+  packages = [
+    "arg",
+    "callgraph",
+    "callgraph/static",
+    "config",
+    "deprecated",
+    "functions",
+    "internal/sharedcheck",
+    "lint",
+    "lint/lintdsl",
+    "lint/lintutil",
+    "lint/lintutil/format",
+    "simple",
+    "ssa",
+    "ssa/ssautil",
+    "ssautil",
+    "staticcheck",
+    "staticcheck/vrp",
+    "stylecheck",
+    "unused",
+    "version",
+  ]
+  pruneopts = ""
+  revision = "35a9f45a5db090b0227d692d823151104cd695fa"
+
+[[projects]]
+  branch = "master"
+  digest = "1:bc3387ddcbdacf135af0a16b9e9ec6ac7bf5a1f822f679d8d29c2d97cfcce205"
+  name = "github.com/golangci/goconst"
+  packages = ["."]
+  pruneopts = ""
+  revision = "041c5f2b40f3dd334a4a6ee6a3f84ca3fc70680a"
+
+[[projects]]
+  branch = "master"
+  digest = "1:c5c9e52a4aaca585c1ce9c79f5ea31d74d03da39dfccda0b140f93d6a1be17b7"
+  name = "github.com/golangci/gocyclo"
+  packages = ["pkg/gocyclo"]
+  pruneopts = ""
+  revision = "0a533e8fa43d6605069e94f455bf9d79d4b8ea8c"
+
+[[projects]]
+  branch = "master"
+  digest = "1:edccfa947bd237dcd1bceef56d1670c22930831ca196ff04f0e2c4a8483bf97b"
+  name = "github.com/golangci/gofmt"
+  packages = [
+    "gofmt",
+    "goimports",
+  ]
+  pruneopts = ""
+  revision = "0b8337e80d98f7eec18e4504a4557b34423fd039"
+
+[[projects]]
+  digest = "1:0071a728673f03bd75b65863a37d4b1c5bb06ffc4a4416f1a8b6b90f36b2c5e3"
+  name = "github.com/golangci/golangci-lint"
+  packages = [
+    "cmd/golangci-lint",
+    "pkg/commands",
+    "pkg/config",
+    "pkg/exitcodes",
+    "pkg/fsutils",
+    "pkg/golinters",
+    "pkg/goutil",
+    "pkg/lint",
+    "pkg/lint/astcache",
+    "pkg/lint/linter",
+    "pkg/lint/lintersdb",
+    "pkg/logutils",
+    "pkg/packages",
+    "pkg/printers",
+    "pkg/report",
+    "pkg/result",
+    "pkg/result/processors",
+    "pkg/timeutils",
+  ]
+  pruneopts = ""
+  revision = "901cf25e20f86b7e9dc6f73eaba5afbd0cbdc257"
+  version = "v1.15.0"
+
+[[projects]]
+  branch = "master"
+  digest = "1:30c45dd735f55c7dbd0ea6040e3ccc35f867532b8e1919016c0565510392417a"
+  name = "github.com/golangci/gosec"
+  packages = [
+    ".",
+    "rules",
+  ]
+  pruneopts = ""
+  revision = "8afd9cbb6cfb34a3b4d4d5711bafdc6640ae892f"
+
+[[projects]]
+  branch = "master"
+  digest = "1:081d9ed8ba13ebbd4bd3e1f17cd703f77268416074588c38ce985d654b1fc0e1"
+  name = "github.com/golangci/govet"
+  packages = [
+    ".",
+    "lib/cfg",
+    "lib/whitelist",
+  ]
+  pruneopts = ""
+  revision = "44ddbe260190d79165f4150b828650780405d801"
+
+[[projects]]
+  branch = "master"
+  digest = "1:7da7fde58cf7cf5e19f6a1c77eb153945b28cf03bab227e0d831897b7070b546"
+  name = "github.com/golangci/ineffassign"
+  packages = ["."]
+  pruneopts = ""
+  revision = "2ee8f2867dde308c46d401d6d30f6c644094b167"
+
+[[projects]]
+  branch = "master"
+  digest = "1:8e50794fcb5f229576cd7eda5627a6c2f20341079f0c571077a7ab807c518da9"
+  name = "github.com/golangci/lint-1"
+  packages = ["."]
+  pruneopts = ""
+  revision = "d2cdd8c0821928c61cb0903441f8b35457a98a61"
+
+[[projects]]
+  branch = "master"
+  digest = "1:8665edfb3c5371fbac9820d127fa0d9aed813cc2349a27a7d16064dd89fed146"
+  name = "github.com/golangci/maligned"
+  packages = ["."]
+  pruneopts = ""
+  revision = "b1d89398deca2fd3f8578e5a9551e819bd01ca5f"
+
+[[projects]]
+  digest = "1:dbf28ceee27335219701dd4c6639c767eee31e2abb61485cdb1044587a04c077"
+  name = "github.com/golangci/misspell"
+  packages = ["."]
+  pruneopts = ""
+  revision = "b90dc15cfd220ecf8bbc9043ecb928cef381f011"
+  version = "v0.3.4"
+
+[[projects]]
+  branch = "master"
+  digest = "1:045c2735b360cbebf398a0e9312aeafebf08fd38f0d51cb2aa0f9420364c3cd1"
+  name = "github.com/golangci/prealloc"
+  packages = ["."]
+  pruneopts = ""
+  revision = "215b22d4de21190b80ce05e7d8466677c1aa3223"
+
+[[projects]]
+  branch = "master"
+  digest = "1:c23cf3c7078c3ba927492557a40c1ee1755734d4fff0e7fbe6d2f092604dae6d"
+  name = "github.com/golangci/revgrep"
+  packages = ["."]
+  pruneopts = ""
+  revision = "276a5c0a103935ee65af49afc254a65335bf1fcf"
+
+[[projects]]
+  branch = "master"
+  digest = "1:c553e7c7483f2d6db1e84a27a18df144ed4041792d7556916369f86ccf5409fe"
+  name = "github.com/golangci/unconvert"
+  packages = ["."]
+  pruneopts = ""
+  revision = "28b1c447d1f4a810737ee6ab40ea6c1d0ceae4ad"
+
+[[projects]]
+  digest = "1:ad92aa49f34cbc3546063c7eb2cabb55ee2278b72842eda80e2a20a8a06a8d73"
+  name = "github.com/google/uuid"
+  packages = ["."]
+  pruneopts = ""
+  revision = "0cd6bf5da1e1c83f8b45653022c74f71af0538a4"
+  version = "v1.1.1"
+
+[[projects]]
+  digest = "1:d14365c51dd1d34d5c79833ec91413bfbb166be978724f15701e17080dc06dec"
+  name = "github.com/hashicorp/hcl"
+  packages = [
+    ".",
+    "hcl/ast",
+    "hcl/parser",
+    "hcl/printer",
+    "hcl/scanner",
+    "hcl/strconv",
+    "hcl/token",
+    "json/parser",
+    "json/scanner",
+    "json/token",
+  ]
+  pruneopts = ""
+  revision = "8cb6e5b959231cc1119e43259c4a608f9c51a241"
+  version = "v1.0.0"
+
 [[projects]]
   branch = "master"
   digest = "1:cb09475f771b9167fb9333629f5d6a7161572602ea040f1094602b0dc8709878"
@@ -77,6 +466,25 @@
   pruneopts = ""
   revision = "db4671f3a9b8df855e993f7c94ec5ef1ffb0a23b"
 
+[[projects]]
+  digest = "1:765270f95ea68ad2150f6143eb8b9c0c17b038a7e2255b46580674471af00e27"
+  name = "github.com/kisielk/gotool"
+  packages = [
+    ".",
+    "internal/load",
+  ]
+  pruneopts = ""
+  revision = "80517062f582ea3340cd4baf70e86d539ae7d84d"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:0f51cee70b0d254dbc93c22666ea2abf211af81c1701a96d04e2284b408621db"
+  name = "github.com/konsorten/go-windows-terminal-sequences"
+  packages = ["."]
+  pruneopts = ""
+  revision = "f55edac94c9bbba5d6182a4be46d86a2c9b5b50e"
+  version = "v1.0.2"
+
 [[projects]]
   branch = "master"
   digest = "1:1ed9eeebdf24aadfbca57eb50e6455bd1d2474525e0f0d4454de8c8e9bc7ee9a"
@@ -109,6 +517,14 @@
   revision = "345fbb3dbcdb252d9985ee899a84963c0fa24c82"
   version = "v1.0"
 
+[[projects]]
+  digest = "1:961dc3b1d11f969370533390fdf203813162980c858e1dabe827b60940c909a5"
+  name = "github.com/magiconair/properties"
+  packages = ["."]
+  pruneopts = ""
+  revision = "c2353362d570a7bfa228149c62842019201cfb71"
+  version = "v1.8.0"
+
 [[projects]]
   digest = "1:9ea83adf8e96d6304f394d40436f2eb44c1dc3250d223b74088cc253a6cd0a1c"
   name = "github.com/mattn/go-colorable"
@@ -141,6 +557,64 @@
   revision = "3247c84500bff8d9fb6d579d800f20b3e091582c"
   version = "v1.0.0"
 
+[[projects]]
+  digest = "1:6dbb0eb72090871f2e58d1e37973fe3cb8c0f45f49459398d3fc740cb30e13bd"
+  name = "github.com/mitchellh/go-homedir"
+  packages = ["."]
+  pruneopts = ""
+  revision = "af06845cf3004701891bf4fdb884bfe4920b3727"
+  version = "v1.1.0"
+
+[[projects]]
+  digest = "1:bcc46a0fbd9e933087bef394871256b5c60269575bb661935874729c65bbbf60"
+  name = "github.com/mitchellh/mapstructure"
+  packages = ["."]
+  pruneopts = ""
+  revision = "3536a929edddb9a5b34bd6861dc4a9647cb459fe"
+  version = "v1.1.2"
+
+[[projects]]
+  digest = "1:4ff67dde814694496d7aa31be44b900f9717a10c8bc9136b13f49c8ef97f439a"
+  name = "github.com/montanaflynn/stats"
+  packages = ["."]
+  pruneopts = ""
+  revision = "63fbb2597b7a13043b453a4b819945badb8f8926"
+  version = "v0.5.0"
+
+[[projects]]
+  digest = "1:9da71b9d17d6231f1486dc62d81af3f9d34535703ba9e7a60a902433c3091e3b"
+  name = "github.com/nbutton23/zxcvbn-go"
+  packages = [
+    ".",
+    "adjacency",
+    "data",
+    "entropy",
+    "frequency",
+    "match",
+    "matching",
+    "scoring",
+    "utils/math",
+  ]
+  pruneopts = ""
+  revision = "eafdab6b0663b4b528c35975c8b0e78be6e25261"
+  version = "v0.1"
+
+[[projects]]
+  branch = "master"
+  digest = "1:f60ff065b58bd53e641112b38bbda9d2684deb828393c7ffb89c69a1ee301d17"
+  name = "github.com/pascaldekloe/name"
+  packages = ["."]
+  pruneopts = ""
+  revision = "0fd16699aae1833640fca52a937944c6f3b1d58c"
+
+[[projects]]
+  digest = "1:894aef961c056b6d85d12bac890bf60c44e99b46292888bfa66caf529f804457"
+  name = "github.com/pelletier/go-toml"
+  packages = ["."]
+  pruneopts = ""
+  revision = "c01d1270ff3e442a8a57cddc1c92dc1138598194"
+  version = "v1.2.0"
+
 [[projects]]
   digest = "1:7365acd48986e205ccb8652cc746f09c8b7876030d53710ea6ef7d0bd0dcd7ca"
   name = "github.com/pkg/errors"
@@ -149,6 +623,14 @@
   revision = "645ef00459ed84a119197bfb8d8205042c6df63d"
   version = "v0.8.0"
 
+[[projects]]
+  digest = "1:1cbc6b98173422a756ae79e485952cb37a0a460c710541c75d3e9961c5a60782"
+  name = "github.com/pkg/profile"
+  packages = ["."]
+  pruneopts = ""
+  revision = "5b67d428864e92711fcbd2f8629456121a56d91f"
+  version = "v1.2.1"
+
 [[projects]]
   digest = "1:256484dbbcd271f9ecebc6795b2df8cad4c458dd0f5fd82a8c2fa0c29f233411"
   name = "github.com/pmezard/go-difflib"
@@ -159,30 +641,11 @@
 
 [[projects]]
   branch = "master"
-  digest = "1:1392748e290ca66ac8447ef24961f8ae9e1d846a53af0f58a5a0256982ce0577"
+  digest = "1:fa72f780ae3b4820ed12cef7a034291ab10d83e2da4ab5ba81afa44d5bf3a529"
   name = "github.com/problame/go-netssh"
   packages = ["."]
   pruneopts = ""
-  revision = "c56ad38d2c91397ad3c8dd9443d7448e328a9e9e"
-
-[[projects]]
-  branch = "master"
-  digest = "1:8c63c44f018bd52b03ebad65c9df26aabbc6793138e421df1c8c84c285a45bc6"
-  name = "github.com/problame/go-rwccmd"
-  packages = ["."]
-  pruneopts = ""
-  revision = "391d2c78c8404a9683d79f75dd24ab53040f89f7"
-
-[[projects]]
-  digest = "1:1bcbb0a7ad8d3392d446eb583ae5415ff987838a8f7331a36877789be20667e6"
-  name = "github.com/problame/go-streamrpc"
-  packages = [
-    ".",
-    "internal/pdu",
-  ]
-  pruneopts = ""
-  revision = "d5d111e014342fe1c37f0b71cc37ec5f2afdfd13"
-  version = "v0.5"
+  revision = "09d6bc45d284784cb3e5aaa1998513f37eb19cc6"
 
 [[projects]]
   branch = "master"
@@ -228,6 +691,41 @@
   pruneopts = ""
   revision = "8b1c2da0d56deffdbb9e48d4414b4e674bd8083e"
 
+[[projects]]
+  digest = "1:3962f553b77bf6c03fc07cd687a22dd3b00fe11aa14d31194f5505f5bb65cdc8"
+  name = "github.com/sergi/go-diff"
+  packages = ["diffmatchpatch"]
+  pruneopts = ""
+  revision = "1744e2970ca51c86172c8190fadad617561ed6e7"
+  version = "v1.0.0"
+
+[[projects]]
+  digest = "1:b73fe282e350b3ef2c71d8ff08e929e0b9670b1bb5b7fde1d3c1b4cd6e6dc8b1"
+  name = "github.com/sirupsen/logrus"
+  packages = ["."]
+  pruneopts = ""
+  revision = "dae0fa8d5b0c810a8ab733fbd5510c7cae84eca4"
+  version = "v1.4.0"
+
+[[projects]]
+  digest = "1:956f655c87b7255c6b1ae6c203ebb0af98cf2a13ef2507e34c9bf1c0332ac0f5"
+  name = "github.com/spf13/afero"
+  packages = [
+    ".",
+    "mem",
+  ]
+  pruneopts = ""
+  revision = "588a75ec4f32903aa5e39a2619ba6a4631e28424"
+  version = "v1.2.2"
+
+[[projects]]
+  digest = "1:ae3493c780092be9d576a1f746ab967293ec165e8473425631f06658b6212afc"
+  name = "github.com/spf13/cast"
+  packages = ["."]
+  pruneopts = ""
+  revision = "8c9545af88b134710ab1cd196795e7f2388358d7"
+  version = "v1.3.0"
+
 [[projects]]
   branch = "master"
   digest = "1:146327ce93be37e68bd3ff8541090d96da8cb3adc9e35d57570e9170a29f6bf6"
@@ -236,6 +734,14 @@
   pruneopts = ""
   revision = "b78744579491c1ceeaaa3b40205e56b0591b93a3"
 
+[[projects]]
+  digest = "1:cc15ae4fbdb02ce31f3392361a70ac041f4f02e0485de8ffac92bd8033e3d26e"
+  name = "github.com/spf13/jwalterweatherman"
+  packages = ["."]
+  pruneopts = ""
+  revision = "94f6ae3ed3bceceafa716478c5fbf8d29ca601a1"
+  version = "v1.1.0"
+
 [[projects]]
   digest = "1:261bc565833ef4f02121450d74eb88d5ae4bd74bfe5d0e862cddb8550ec35000"
   name = "github.com/spf13/pflag"
@@ -244,6 +750,14 @@
   revision = "e57e3eeb33f795204c1ca35f56c44f83227c6e66"
   version = "v1.0.0"
 
+[[projects]]
+  digest = "1:90fe60ab6f827e308b0c8cc1e11dce8ff1e96a927c8b171271a3cb04dd517606"
+  name = "github.com/spf13/viper"
+  packages = ["."]
+  pruneopts = ""
+  revision = "9e56dacc08fbbf8c9ee2dbc717553c758ce42bc9"
+  version = "v1.3.2"
+
 [[projects]]
   digest = "1:3926a4ec9a4ff1a072458451aa2d9b98acd059a45b38f7335d31e06c3d6a0159"
   name = "github.com/stretchr/testify"
@@ -256,58 +770,269 @@
   version = "v1.1.4"
 
 [[projects]]
-  branch = "v2"
-  digest = "1:9d92186f609a73744232323416ddafd56fae67cb552162cc190ab903e36900dd"
-  name = "github.com/zrepl/yaml-config"
-  packages = ["."]
+  digest = "1:f80053a92d9ac874ad97d665d3005c1118ed66e9e88401361dc32defe6bef21c"
+  name = "github.com/theckman/goconstraint"
+  packages = ["go1.11/gte"]
   pruneopts = ""
-  revision = "af27d27978ad95808723a62d87557d63c3ff0605"
+  revision = "93babf24513d0e8277635da8169fcc5a46ae3f6a"
+  version = "v1.11.0"
+
+[[projects]]
+  digest = "1:529ed3f98838f69e13761788d0cc71b44e130058fab13bae2ce09f7a176bced4"
+  name = "github.com/yudai/gojsondiff"
+  packages = [
+    ".",
+    "formatter",
+  ]
+  pruneopts = ""
+  revision = "7b1b7adf999dab73a6eb02669c3d82dbb27a3dd6"
+  version = "1.0.0"
 
 [[projects]]
   branch = "master"
-  digest = "1:9c286cf11d0ca56368185bada5dd6d97b6be4648fc26c354fcba8df7293718f7"
-  name = "golang.org/x/sys"
-  packages = ["unix"]
+  digest = "1:9857bb2293f372b2181004d8b62179bbdb4ab0982ec6f762abe6cf2bfedaff85"
+  name = "github.com/yudai/golcs"
+  packages = ["."]
   pruneopts = ""
-  revision = "bf42f188b9bc6f2cf5b8ee5a912ef1aedd0eba4c"
+  revision = "ecda9a501e8220fae3b4b600c3db4b0ba22cfc68"
+
+[[projects]]
+  branch = "v2"
+  digest = "1:6b8a6afafde7ed31cd0c577ba40d88ce39e8f1c5eb76d7836be7d5b74f1c534a"
+  name = "github.com/zrepl/yaml-config"
+  packages = ["."]
+  pruneopts = ""
+  revision = "08227ad854131f7dfcdfb12579fb73dd8a38a03a"
+
+[[projects]]
+  branch = "master"
+  digest = "1:36ef1d8645934b1744cc7d8726e00d3dd9d8d84c18617bf7367a3a6d532f3370"
+  name = "golang.org/x/crypto"
+  packages = ["ssh/terminal"]
+  pruneopts = ""
+  revision = "a5d413f7728c81fb97d96a2b722368945f651e78"
+
+[[projects]]
+  branch = "master"
+  digest = "1:ea539c13b066dac72a940b62f37600a20ab8e88057397c78f3197c1a48475425"
+  name = "golang.org/x/net"
+  packages = [
+    "context",
+    "http/httpguts",
+    "http2",
+    "http2/hpack",
+    "idna",
+    "internal/timeseries",
+    "trace",
+  ]
+  pruneopts = ""
+  revision = "351d144fa1fc0bd934e2408202be0c29f25e35a0"
+
+[[projects]]
+  branch = "master"
+  digest = "1:0142c968b74c157abbb0220c05fa2bdde8a3a4509d6134b35ef75d5b58afb721"
+  name = "golang.org/x/sync"
+  packages = ["semaphore"]
+  pruneopts = ""
+  revision = "e225da77a7e68af35c70ccbf71af2b83e6acac3c"
+
+[[projects]]
+  branch = "master"
+  digest = "1:f358024b019f87eecaadcb098113a40852c94fe58ea670ef3c3e2d2c7bd93db1"
+  name = "golang.org/x/sys"
+  packages = [
+    "unix",
+    "windows",
+  ]
+  pruneopts = ""
+  revision = "4ed8d59d0b35e1e29334a206d1b3f38b1e5dfb31"
 
 [[projects]]
   digest = "1:5acd3512b047305d49e8763eef7ba423901e85d5dd2fd1e71778a0ea8de10bd4"
   name = "golang.org/x/text"
   packages = [
+    "collate",
+    "collate/build",
     "encoding",
     "encoding/internal/identifier",
+    "internal/colltab",
     "internal/gen",
+    "internal/tag",
+    "internal/triegen",
+    "internal/ucd",
+    "language",
+    "secure/bidirule",
     "transform",
+    "unicode/bidi",
     "unicode/cldr",
+    "unicode/norm",
+    "unicode/rangetable",
+    "width",
   ]
   pruneopts = ""
   revision = "f21a4dfb5e38f5895301dc265a8def02365cc3d0"
   version = "v0.3.0"
 
+[[projects]]
+  branch = "master"
+  digest = "1:4cd780b2ee42c8eac9c02bfb6e6b52dcbaef770774458c8938f5cbfb73a7b6d3"
+  name = "golang.org/x/tools"
+  packages = [
+    "cmd/goimports",
+    "cmd/stringer",
+    "go/ast/astutil",
+    "go/buildutil",
+    "go/gcexportdata",
+    "go/internal/cgo",
+    "go/internal/gcimporter",
+    "go/loader",
+    "go/packages",
+    "go/ssa",
+    "go/ssa/ssautil",
+    "go/types/typeutil",
+    "imports",
+    "internal/fastwalk",
+    "internal/gopathwalk",
+    "internal/semver",
+  ]
+  pruneopts = ""
+  revision = "d0ca3933b724e6be513276cc2edb34e10d667438"
+
+[[projects]]
+  branch = "master"
+  digest = "1:5fc6c317675b746d0c641b29aa0aab5fcb403c0d07afdbf0de86b0d447a0502a"
+  name = "google.golang.org/genproto"
+  packages = ["googleapis/rpc/status"]
+  pruneopts = ""
+  revision = "bd91e49a0898e27abb88c339b432fa53d7497ac0"
+
+[[projects]]
+  digest = "1:d141efe4aaad714e3059c340901aab3147b6253e58c85dafbcca3dd8b0e88ad6"
+  name = "google.golang.org/grpc"
+  packages = [
+    ".",
+    "balancer",
+    "balancer/base",
+    "balancer/roundrobin",
+    "binarylog/grpc_binarylog_v1",
+    "codes",
+    "connectivity",
+    "credentials",
+    "credentials/internal",
+    "encoding",
+    "encoding/proto",
+    "grpclog",
+    "internal",
+    "internal/backoff",
+    "internal/binarylog",
+    "internal/channelz",
+    "internal/envconfig",
+    "internal/grpcrand",
+    "internal/grpcsync",
+    "internal/syscall",
+    "internal/transport",
+    "keepalive",
+    "metadata",
+    "naming",
+    "peer",
+    "resolver",
+    "resolver/dns",
+    "resolver/passthrough",
+    "stats",
+    "status",
+    "tap",
+  ]
+  pruneopts = ""
+  revision = "df014850f6dee74ba2fc94874043a9f3f75fbfd8"
+  version = "v1.17.0"
+
+[[projects]]
+  digest = "1:cedccf16b71e86db87a24f8d4c70b0a855872eb967cb906a66b95de56aefbd0d"
+  name = "gopkg.in/yaml.v2"
+  packages = ["."]
+  pruneopts = ""
+  revision = "51d6538a90f86fe93ac480b35f37b2be17fef232"
+  version = "v2.2.2"
+
+[[projects]]
+  branch = "master"
+  digest = "1:2a6012038cdeb9851f1a71497544820e17ff2772b3cf799d24a76208cb9843b8"
+  name = "mvdan.cc/interfacer"
+  packages = ["check"]
+  pruneopts = ""
+  revision = "c20040233aedb03da82d460eca6130fcd91c629a"
+
+[[projects]]
+  branch = "master"
+  digest = "1:68e12be99c0d3355e04eecba6bc302876268a134a0eecd75258d8fefe44a94ed"
+  name = "mvdan.cc/lint"
+  packages = ["."]
+  pruneopts = ""
+  revision = "adc824a0674b99099789b6188a058d485eaf61c0"
+
+[[projects]]
+  branch = "master"
+  digest = "1:4af0788cd865cab3c8276462de56bad858e178199415241c2420e13e95d8594c"
+  name = "mvdan.cc/unparam"
+  packages = ["check"]
+  pruneopts = ""
+  revision = "1b9ccfa71afe53433971717161c9666adfc4d8c5"
+
+[[projects]]
+  digest = "1:0778809e0f18d0c0c05105a5c1e583d2253c5fd66fbd2b79b00e5f6439402491"
+  name = "sourcegraph.com/sourcegraph/go-diff"
+  packages = ["diff"]
+  pruneopts = ""
+  revision = "c613306ac97fb4807862c088149199f0dab8685a"
+  version = "v0.5.0"
+
+[[projects]]
+  digest = "1:ffc8cfc88692d5daab7abac1d989e9f7fc09727e42a945702f8f2d6d67f0fd6c"
+  name = "sourcegraph.com/sqs/pbtypes"
+  packages = ["."]
+  pruneopts = ""
+  revision = "688c2c2cb411327a50aae0f89119af9f38b0fc03"
+  version = "v1.0.0"
+
 [solve-meta]
   analyzer-name = "dep"
   analyzer-version = 1
   input-imports = [
+    "github.com/alvaroloes/enumer",
     "github.com/fatih/color",
     "github.com/gdamore/tcell/termbox",
     "github.com/go-logfmt/logfmt",
     "github.com/golang/protobuf/proto",
+    "github.com/golang/protobuf/protoc-gen-go",
+    "github.com/golangci/golangci-lint/cmd/golangci-lint",
+    "github.com/google/uuid",
     "github.com/jinzhu/copier",
     "github.com/kr/pretty",
     "github.com/mattn/go-isatty",
+    "github.com/montanaflynn/stats",
     "github.com/pkg/errors",
+    "github.com/pkg/profile",
     "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/yudai/gojsondiff",
+    "github.com/yudai/gojsondiff/formatter",
     "github.com/zrepl/yaml-config",
+    "golang.org/x/net/context",
+    "golang.org/x/sync/semaphore",
     "golang.org/x/sys/unix",
+    "golang.org/x/tools/cmd/goimports",
+    "golang.org/x/tools/cmd/stringer",
+    "google.golang.org/grpc",
+    "google.golang.org/grpc/codes",
+    "google.golang.org/grpc/credentials",
+    "google.golang.org/grpc/keepalive",
+    "google.golang.org/grpc/peer",
+    "google.golang.org/grpc/status",
   ]
   solver-name = "gps-cdcl"
   solver-version = 1

Gopkg.toml

@@ -1,8 +1,13 @@
-ignored = [ "github.com/inconshreveable/mousetrap" ]
+ignored = [
+    "github.com/inconshreveable/mousetrap",
+]
 
-[[constraint]]
-  branch = "master"
-  name = "github.com/ftrvxmtrx/fd"
+required = [
+    "golang.org/x/tools/cmd/stringer",
+    "github.com/alvaroloes/enumer",
+    "github.com/golangci/golangci-lint/cmd/golangci-lint",
+    "golang.org/x/tools/cmd/goimports",
+]
 
 [[constraint]]
   branch = "master"
@@ -12,14 +17,6 @@ ignored = [ "github.com/inconshreveable/mousetrap" ]
   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"
@@ -28,10 +25,6 @@ ignored = [ "github.com/inconshreveable/mousetrap" ]
   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"
@@ -44,10 +37,6 @@ ignored = [ "github.com/inconshreveable/mousetrap" ]
   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"
@@ -58,18 +47,21 @@ ignored = [ "github.com/inconshreveable/mousetrap" ]
 
 [[constraint]]
   name = "github.com/golang/protobuf"
-  version = "1.2.0"
+  version = "1"
 
 [[constraint]]
   name = "github.com/fatih/color"
   version = "1.7.0"
 
-[[constraint]]
-  name = "github.com/problame/go-streamrpc"
-  version = "0.5.0"
-
-
 
 [[constraint]]
   name = "github.com/gdamore/tcell"
   version = "1.0.0"
+
+[[constraint]]
+  name = "google.golang.org/grpc"
+  version = "1"
+  
+[[constraint]]
+  version = "1.1.0"
+  name = "github.com/google/uuid"

Makefile

@@ -1,45 +1,13 @@
-.PHONY: generate build test vet cover release docs docs-clean clean vendordeps
+.PHONY: generate build test vet cover release docs docs-clean clean vendordeps format lint
 .DEFAULT_GOAL := build
 
-ROOT := github.com/zrepl/zrepl
-SUBPKGS += client
-SUBPKGS += config
-SUBPKGS += daemon
-SUBPKGS += daemon/filters
-SUBPKGS += daemon/job
-SUBPKGS += daemon/logging
-SUBPKGS += daemon/nethelpers
-SUBPKGS += daemon/pruner
-SUBPKGS += daemon/snapper
-SUBPKGS += daemon/streamrpcconfig
-SUBPKGS += daemon/transport
-SUBPKGS += daemon/transport/connecter
-SUBPKGS += daemon/transport/serve
-SUBPKGS += endpoint
-SUBPKGS += logger
-SUBPKGS += pruning
-SUBPKGS += pruning/retentiongrid
-SUBPKGS += replication
-SUBPKGS += replication/fsrep
-SUBPKGS += replication/pdu
-SUBPKGS += replication/internal/diff
-SUBPKGS += tlsconf
-SUBPKGS += util
-SUBPKGS += util/socketpair
-SUBPKGS += util/watchdog
-SUBPKGS += util/envconst
-SUBPKGS += version
-SUBPKGS += zfs
-
-_TESTPKGS := $(ROOT) $(foreach p,$(SUBPKGS),$(ROOT)/$(p))
-
 ARTIFACTDIR := artifacts
 
 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
@@ -59,35 +27,27 @@ 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;
+	protoc -I=replication/logic/pdu --go_out=plugins=grpc:replication/logic/pdu replication/logic/pdu/pdu.proto
+	go generate -x ./...
+
+format:
+	goimports -srcdir . -local 'github.com/zrepl/zrepl' -w $(shell find . -type f -name '*.go' -not -path "./vendor/*" -not -name '*.pb.go' -not -name '*_enumer.go')
+
+lint:
+	golangci-lint run ./...
 
 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;
+	go test ./...
 
 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;
+	# for each supported platform to cover conditional compilation
+	GOOS=linux   go vet ./...
+	GOOS=darwin  go vet ./...
+	GOOS=freebsd go vet ./...
 
 $(ARTIFACTDIR):
 	mkdir -p "$@"
@@ -114,7 +74,7 @@ docs-clean:
 
 .PHONY: $(RELEASE_BINS)
 # TODO: two wildcards possible
-$(RELEASE_BINS): $(ARTIFACTDIR)/zrepl-%-amd64: generate $(ARTIFACTDIR) vet test
+$(RELEASE_BINS): $(ARTIFACTDIR)/zrepl-%-amd64: generate $(ARTIFACTDIR) vet test lint
 	@echo "INFO: In case of missing dependencies, run 'make vendordeps'"
 	GOOS=$* GOARCH=amd64   $(GO_BUILD) -o "$(ARTIFACTDIR)/zrepl-$*-amd64"
 
@@ -132,9 +92,10 @@ release: $(RELEASE_BINS) $(RELEASE_NOARCH)
 	cp $^ "$(ARTIFACTDIR)/release"
 	cd "$(ARTIFACTDIR)/release" && sha512sum $$(ls | sort) > sha512sum.txt
 	@# 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'; \
 			exit 1; \
 		fi; \
 	fi;

README.md

@@ -1,3 +1,10 @@
+[![GitHub license](https://img.shields.io/github/license/zrepl/zrepl.svg)](https://github.com/zrepl/zrepl/blob/master/LICENSE)
+[![Language: Go](https://img.shields.io/badge/language-Go-6ad7e5.svg)](https://golang.org/)
+[![User Docs](https://img.shields.io/badge/docs-web-blue.svg)](https://zrepl.github.io)
+[![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)
+[![Donate via Liberapay](https://img.shields.io/badge/donate-liberapay-yellow.svg)](https://liberapay.com/zrepl/donate)
+[![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)
+
 # zrepl
 zrepl is a one-stop ZFS backup & replication solution.
 
@@ -26,6 +33,8 @@ Check out the *Coding Workflow* section below for details.
 * Make sure your distro is compatible with the paths in `docs/installation.rst`.
 * Ship a default config that adheres to your distro's `hier` and logging system.
 * Ship a service manager file and _please_ try to upstream it to this repository.
+  * `dist/systemd` contains a Systemd unit template.
+* Ship other material provided in `./dist`, e.g. in `/usr/share/zrepl/`.
 * Use `make release ZREPL_VERSION='mydistro-1.2.3_1'`
     * Your distro's name and any versioning supplemental to zrepl's (e.g. package revision) should be in this string
 * Make sure you are informed about new zrepl versions, e.g. by subscribing to GitHub's release RSS feed.
@@ -45,21 +54,53 @@ Make sure to develop an understanding how zrepl is typically used by studying th
 ### Project Structure
 
 ```
-├── cmd
-│   ├── endpoint            # implementations of endpoints for package replication
-│   ├── sampleconf          # example configuration
+├── artifacts               # build artifcats generate by make
+├── cli                     # wrapper around CLI package cobra
+├── client                  # all subcommands that are not `daemon`
+├── config                  # config data types (=> package yaml-config)
+│   └── samples
+├── daemon                  # the implementation of `zrepl daemon` subcommand
+│   ├── filters
+│   ├── job                 # job implementations
+│   ├── logging             # logging outlets + formatters
+│   ├── nethelpers
+│   ├── prometheus
+│   ├── pruner              # pruner implementation
+│   ├── snapper             # snapshotter implementation
 ├── docs                    # sphinx-based documentation
+├── dist                    # supplemental material for users & package maintainers
 │   ├── **/*.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
+│   └── public_git          # checkout of zrepl.github.io managed by above shell script
+├── endpoint                # implementation of replication endpoints (=> package replication)
+├── logger                  # our own logger package
+├── pruning                 # pruning rules (the logic, not the actual execution)
+│   └── retentiongrid
+├── replication
+│   ├── driver              # the driver of the replication logic (status reporting, error handling)
+│   ├── logic               # planning & executing replication steps via rpc
+|   |   └── pdu             # the generated gRPC & protobuf code used in replication (and endpoints)
+│   └── report              # the JSON-serializable report datastructures exposed to the client
+├── rpc                     # the hybrid gRPC + ./dataconn RPC client: connects to a remote replication.Endpoint
+│   ├── dataconn            # Bulk data-transfer RPC protocol
+│   ├── grpcclientidentity  # adaptor to inject package transport's 'client identity' concept into gRPC contexts
+│   ├── netadaptor          # adaptor to convert a package transport's Connecter and Listener into net.* primitives
+│   ├── transportmux        # TCP connecter and listener used to split control & data traffic
+│   └── versionhandshake    # replication protocol version handshake perfomed on newly established connections
+├── tlsconf                 # abstraction for Go TLS server + client config
+├── transport               # transports implementation
+│   ├── fromconfig
+│   ├── local
+│   ├── ssh
+│   ├── tcp
+│   └── tls
 ├── util
-└── zfs                     # ZFS wrappers, filesystemm diffing
+├── vendor                  # managed by dep
+├── version                 # abstraction for versions (filled during build by Makefile)
+└── zfs                     # zfs(8) wrappers
 ```
 
 ### Coding Workflow

build.Dockerfile

@@ -11,12 +11,21 @@ RUN unzip -d /usr protoc-3.6.1-linux-x86_64.zip
 ADD lazy.sh /tmp/lazy.sh
 ADD docs/requirements.txt /tmp/requirements.txt
 ENV ZREPL_LAZY_DOCS_REQPATH=/tmp/requirements.txt
-RUN /tmp/lazy.sh devsetup
+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 /.cache && chmod -R 0777 /.cache
 WORKDIR /go/src/github.com/zrepl/zrepl
 
+ADD Gopkg.toml Gopkg.lock  ./
+
+# godep will install the Go dependencies to vendor in order to then build and install
+# build dependencies like stringer to $GOPATH/bin.
+# However, since users volume-mount their Git checkout into /go/src/github.com/zrepl/zrepl
+# the vendor directory will be empty at build time, allowing them to experiment with
+# new checkouts, etc.
+# Thus, we only use the vendored deps for building dependencies.
+RUN /tmp/lazy.sh godep
+RUN chmod -R 0777 /go
 

build/build.go

@@ -0,0 +1,23 @@
+//+build windows
+
+// This package cannot actually be built, and since the Travis
+// tests run go test ./..., we have to avoid a build attempt.
+// Windows is not supported atm, so this works ¯\_(ツ)_/¯
+
+// This package is a pseudo-user of build-time dependencies for zrepl,
+// mostly for various code-generation tools.
+//
+// The imports are necessary to satisfy go dep
+package main
+
+import (
+	"fmt"
+
+	_ "github.com/alvaroloes/enumer"
+	_ "github.com/golang/protobuf/protoc-gen-go"
+	_ "golang.org/x/tools/cmd/stringer"
+)
+
+func main() {
+	fmt.Println("just a placeholder")
+}

cli/cli.go

@@ -2,10 +2,12 @@ package cli
 
 import (
 	"fmt"
+	"os"
+
 	"github.com/spf13/cobra"
 	"github.com/spf13/pflag"
+
 	"github.com/zrepl/zrepl/config"
-	"os"
 )
 
 var rootArgs struct {
@@ -23,7 +25,10 @@ var bashcompCmd = &cobra.Command{
 	Run: func(cmd *cobra.Command, args []string) {
 		if len(args) != 1 {
 			fmt.Fprintf(os.Stderr, "specify exactly one positional agument\n")
-			cmd.Usage()
+			err := cmd.Usage()
+			if err != nil {
+				panic(err)
+			}
 			os.Exit(1)
 		}
 		if err := rootCmd.GenBashCompletionFile(args[0]); err != nil {
@@ -40,14 +45,15 @@ func init() {
 }
 
 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(subcommand *Subcommand, args []string) error
+	SetupFlags       func(f *pflag.FlagSet)
+	SetupSubcommands func() []*Subcommand
 
-	config *config.Config
+	config    *config.Config
 	configErr error
 }
 
@@ -92,8 +98,9 @@ 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 +115,8 @@ func addSubcommandToCobraCmd(c *cobra.Command, s *Subcommand) {
 	c.AddCommand(&cmd)
 }
 
-
 func Run() {
 	if err := rootCmd.Execute(); err != nil {
 		os.Exit(1)
 	}
-}
+}

client/configcheck.go

@@ -3,39 +3,49 @@ package client
 import (
 	"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
+	what   string
 }
 
 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]")
 	},
 	Run: func(subcommand *cli.Subcommand, args []string) error {
-		formatMap := map[string]func(interface{}) {
+		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)
+				}
 			},
 		}
 
@@ -71,12 +81,11 @@ 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 +118,3 @@ 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 +1,104 @@
+package client
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/pkg/errors"
+	"github.com/spf13/pflag"
+
+	"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")
+		},
+	},
+}
+
+var migratePlaceholder0_1Args struct {
+	dryRun bool
+}
+
+func doMigratePlaceholder0_1(sc *cli.Subcommand, args []string) error {
+	if len(args) != 0 {
+		return fmt.Errorf("migration does not take arguments, got %v", args)
+	}
+
+	cfg := sc.Config()
+
+	ctx := context.Background()
+	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(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
+}

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

@@ -2,11 +2,12 @@ package client
 
 import (
 	"errors"
+	"log"
+	"os"
+
 	"github.com/zrepl/zrepl/cli"
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon"
-	"log"
-	"os"
 )
 
 var pprofArgs struct {

client/signal.go

@@ -2,6 +2,7 @@ package client
 
 import (
 	"github.com/pkg/errors"
+
 	"github.com/zrepl/zrepl/cli"
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon"
@@ -28,10 +29,10 @@ 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

@@ -2,16 +2,6 @@ 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"
@@ -20,41 +10,62 @@ import (
 	"strings"
 	"sync"
 	"time"
+
+	"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/report"
 )
 
+type byteProgressMeasurement struct {
+	time time.Time
+	val  int64
+}
+
 type bytesProgressHistory struct {
-	changeCounter     int
-	lastChangeAt      time.Time
-	last              int64
-	bpsIncreaseExpAvg float64
+	last        *byteProgressMeasurement // pointer as poor man's optional
+	changeCount int
+	lastChange  time.Time
+	bpsAvg      float64
 }
 
 func (p *bytesProgressHistory) Update(currentVal int64) (bytesPerSecondAvg int64, changeCount int) {
-	if currentVal < p.last {
-		*p = bytesProgressHistory{
-			last: currentVal,
-			lastChangeAt: time.Now(),
+
+	if p.last == nil {
+		p.last = &byteProgressMeasurement{
+			time: time.Now(),
+			val:  currentVal,
 		}
-	}
-	defer func() {
-		p.last = currentVal
-	}()
-	if time.Now().Sub(p.lastChangeAt) > 3 *time.Second { // FIXME depends on refresh frequency
-		p.changeCounter = 0
-		p.bpsIncreaseExpAvg = 0
-	}
-	if currentVal != p.last {
-		p.changeCounter++
-		p.lastChangeAt = time.Now()
+		return 0, 0
 	}
 
-	byteIncrease := float64(currentVal - p.last)
-	if byteIncrease < 0 {
-		byteIncrease = 0
+	if p.last.val != currentVal {
+		p.changeCount++
+		p.lastChange = time.Now()
 	}
-	const factor = 0.1
-	p.bpsIncreaseExpAvg = (1-factor) * p.bpsIncreaseExpAvg + factor *byteIncrease
-	return int64(p.bpsIncreaseExpAvg), p.changeCounter
+
+	if time.Since(p.lastChange) > 3*time.Second {
+		p.last = nil
+		return 0, 0
+	}
+
+	deltaV := currentVal - p.last.val
+	deltaT := time.Since(p.last.time)
+	rate := float64(deltaV) / deltaT.Seconds()
+
+	factor := 0.3
+	p.bpsAvg = (1-factor)*p.bpsAvg + factor*rate
+
+	p.last.time = time.Now()
+	p.last.val = currentVal
+
+	return int64(p.bpsAvg), p.changeCount
 }
 
 type tui struct {
@@ -70,15 +81,10 @@ type tui struct {
 
 func newTui() tui {
 	return tui{
-		replicationProgress: make(map[string]*bytesProgressHistory, 0),
+		replicationProgress: make(map[string]*bytesProgressHistory),
 	}
 }
 
-func (t *tui) moveCursor(x, y int) {
-	t.x += x
-	t.y += y
-}
-
 const INDENT_MULTIPLIER = 4
 
 func (t *tui) moveLine(dl int, col int) {
@@ -109,9 +115,9 @@ func wrap(s string, width int) string {
 			rem = len(s)
 		}
 		if idx := strings.IndexAny(s, "\n\r"); idx != -1 && idx < rem {
-			rem = idx+1
+			rem = idx + 1
 		}
-		untilNewline := strings.TrimSpace(s[:rem])
+		untilNewline := strings.TrimRight(s[:rem], "\n\r")
 		s = s[rem:]
 		if len(untilNewline) == 0 {
 			continue
@@ -119,18 +125,18 @@ func wrap(s string, width int) string {
 		b.WriteString(untilNewline)
 		b.WriteString("\n")
 	}
-	return strings.TrimSpace(b.String())
+	return strings.TrimRight(b.String(), "\n\r")
 }
 
 func (t *tui) printfDrawIndentedAndWrappedIfMultiline(format string, a ...interface{}) {
 	whole := fmt.Sprintf(format, a...)
 	width, _ := termbox.Size()
-	if !strings.ContainsAny(whole, "\n\r") && t.x + len(whole) <= width {
+	if !strings.ContainsAny(whole, "\n\r") && t.x+len(whole) <= width {
 		t.printf(format, a...)
 	} else {
 		t.addIndent(1)
 		t.newline()
-		t.write(wrap(whole, width - INDENT_MULTIPLIER*t.indent))
+		t.write(wrap(whole, width-INDENT_MULTIPLIER*t.indent))
 		t.addIndent(-1)
 	}
 }
@@ -149,7 +155,6 @@ func (t *tui) addIndent(indent int) {
 	t.moveLine(0, 0)
 }
 
-
 var statusFlags struct {
 	Raw bool
 }
@@ -170,14 +175,17 @@ func runStatus(s *cli.Subcommand, args []string) error {
 	}
 
 	if statusFlags.Raw {
-		resp, err := httpc.Get("http://unix"+daemon.ControlJobEndpointStatus)
+		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)
+			_, err := io.CopyN(os.Stderr, resp.Body, 4096)
+			if err != nil {
+				return err
+			}
 			return errors.Errorf("exit")
 		}
 		if _, err := io.Copy(os.Stdout, resp.Body); err != nil {
@@ -216,7 +224,7 @@ func runStatus(s *cli.Subcommand, args []string) error {
 	ticker := time.NewTicker(500 * time.Millisecond)
 	defer ticker.Stop()
 	go func() {
-		for _ = range ticker.C {
+		for range ticker.C {
 			update()
 		}
 	}()
@@ -267,7 +275,7 @@ func (t *tui) draw() {
 		//Iterate over map in alphabetical order
 		keys := make([]string, len(t.report))
 		i := 0
-		for k, _ := range t.report {
+		for k := range t.report {
 			keys[i] = k
 			i++
 		}
@@ -287,7 +295,44 @@ func (t *tui) draw() {
 			t.setIndent(1)
 			t.newline()
 
-			if v.Type != job.TypePush && v.Type != job.TypePull {
+			if v.Type == job.TypePush || v.Type == job.TypePull {
+				activeStatus, ok := v.JobSpecific.(*job.ActiveSideStatus)
+				if !ok || activeStatus == nil {
+					t.printf("ActiveSideStatus is null")
+					t.newline()
+					continue
+				}
+
+				t.printf("Replication:")
+				t.newline()
+				t.addIndent(1)
+				t.renderReplicationReport(activeStatus.Replication, t.getReplicationProgresHistory(k))
+				t.addIndent(-1)
+
+				t.printf("Pruning Sender:")
+				t.newline()
+				t.addIndent(1)
+				t.renderPrunerReport(activeStatus.PruningSender)
+				t.addIndent(-1)
+
+				t.printf("Pruning Receiver:")
+				t.newline()
+				t.addIndent(1)
+				t.renderPrunerReport(activeStatus.PruningReceiver)
+				t.addIndent(-1)
+			} else if v.Type == job.TypeSnap {
+				snapStatus, ok := v.JobSpecific.(*job.SnapJobStatus)
+				if !ok || snapStatus == nil {
+					t.printf("SnapJobStatus is null")
+					t.newline()
+					continue
+				}
+				t.printf("Pruning snapshots:")
+				t.newline()
+				t.addIndent(1)
+				t.renderPrunerReport(snapStatus.Pruning)
+				t.addIndent(-1)
+			} else {
 				t.printf("No status representation for job type '%s', dumping as YAML", v.Type)
 				t.newline()
 				asYaml, err := yaml.Marshal(v.JobSpecific)
@@ -300,105 +345,96 @@ func (t *tui) draw() {
 				t.newline()
 				continue
 			}
-
-			pushStatus, ok := v.JobSpecific.(*job.ActiveSideStatus)
-			if !ok || pushStatus == nil {
-				t.printf("ActiveSideStatus is null")
-				t.newline()
-				continue
-			}
-
-			t.printf("Replication:")
-			t.newline()
-			t.addIndent(1)
-			t.renderReplicationReport(pushStatus.Replication, t.getReplicationProgresHistory(k))
-			t.addIndent(-1)
-
-			t.printf("Pruning Sender:")
-			t.newline()
-			t.addIndent(1)
-			t.renderPrunerReport(pushStatus.PruningSender)
-			t.addIndent(-1)
-
-			t.printf("Pruning Receiver:")
-			t.newline()
-			t.addIndent(1)
-			t.renderPrunerReport(pushStatus.PruningReceiver)
-			t.addIndent(-1)
-
 		}
 	}
 	termbox.Flush()
 }
 
-func (t *tui) renderReplicationReport(rep *replication.Report, history *bytesProgressHistory) {
+func (t *tui) renderReplicationReport(rep *report.Report, history *bytesProgressHistory) {
 	if rep == nil {
 		t.printf("...\n")
 		return
 	}
 
-	all := make([]*fsrep.Report, 0, len(rep.Completed)+len(rep.Pending) + 1)
-	all = append(all, rep.Completed...)
-	all = append(all, rep.Pending...)
-	if rep.Active != nil {
-		all = append(all, rep.Active)
+	if rep.WaitReconnectError != nil {
+		t.printfDrawIndentedAndWrappedIfMultiline("Connectivity: %s", rep.WaitReconnectError)
+		t.newline()
 	}
-	sort.Slice(all, func(i, j int) bool {
-		return all[i].Filesystem < all[j].Filesystem
+	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 follwing statuses:")
+			t.newline()
+			t.addIndent(1)
+			for i, a := range rep.Attempts[:len(rep.Attempts)-1] {
+				t.printfDrawIndentedAndWrappedIfMultiline("#%d: %s (failed at %s) (ran %s)", i+1, a.State, a.FinishAt, a.FinishAt.Sub(a.StartAt))
+				t.newline()
+			}
+			t.addIndent(-1)
+		} else {
+			t.newline()
+		}
+	}
+
+	latest := rep.Attempts[len(rep.Attempts)-1]
+	sort.Slice(latest.Filesystems, func(i, j int) bool {
+		return latest.Filesystems[i].Info.Name < latest.Filesystems[j].Info.Name
 	})
 
-	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.printf("Status: %s", latest.State)
 	t.newline()
-	if rep.Problem != "" {
+	if latest.State == report.AttemptPlanningError {
 		t.printf("Problem: ")
-		t.printfDrawIndentedAndWrappedIfMultiline("%s", rep.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 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 {
+	if latest.State != report.AttemptPlanning && latest.State != report.AttemptPlanningError {
+		// Draw global progress bar
 		// Progress: [---------------]
-		sumUpFSRep := func(rep *fsrep.Report) (transferred, total int64) {
-			for _, s := range rep.Pending {
-				transferred += s.Bytes
-				total  += s.ExpectedBytes
-			}
-			for _, s := range rep.Completed {
-				transferred += s.Bytes
-				total += s.ExpectedBytes
-			}
-			return
-		}
-		var transferred, total int64
-		for _, fs := range all {
-			fstx, fstotal := sumUpFSRep(fs)
-			transferred += fstx
-			total += fstotal
-		}
-		rate, changeCount := history.Update(transferred)
+		expected, replicated := latest.BytesSum()
+		rate, changeCount := history.Update(replicated)
 		t.write("Progress: ")
-		t.drawBar(50, transferred, total, changeCount)
-		t.write(fmt.Sprintf(" %s / %s @ %s/s", ByteCountBinary(transferred), ByteCountBinary(total), ByteCountBinary(rate)))
+		t.drawBar(50, replicated, expected, changeCount)
+		t.write(fmt.Sprintf(" %s / %s @ %s/s", ByteCountBinary(replicated), ByteCountBinary(expected), ByteCountBinary(rate)))
 		t.newline()
+
+		var maxFSLen int
+		for _, fs := range latest.Filesystems {
+			if len(fs.Info.Name) > maxFSLen {
+				maxFSLen = len(fs.Info.Name)
+			}
+		}
+		for _, fs := range latest.Filesystems {
+			t.printFilesystemStatus(fs, false, maxFSLen) // FIXME bring 'active' flag back
+		}
+
 	}
 
-	var maxFSLen int
-	for _, fs := range all {
-		if len(fs.Filesystem) > maxFSLen {
-			maxFSLen = len(fs.Filesystem)
-		}
-	}
-	for _, fs := range all {
-		t.printFilesystemStatus(fs, fs == rep.Active, maxFSLen)
-	}
 }
 
 func (t *tui) renderPrunerReport(r *pruner.Report) {
@@ -419,15 +455,12 @@ func (t *tui) renderPrunerReport(r *pruner.Report) {
 	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))
+	all := make([]commonFS, 0, len(r.Pending)+len(r.Completed))
 	for i := range r.Pending {
 		all = append(all, commonFS{&r.Pending[i], false})
 	}
@@ -436,9 +469,9 @@ func (t *tui) renderPrunerReport(r *pruner.Report) {
 	}
 
 	switch state {
-	case pruner.Plan: fallthrough
-	case pruner.PlanWait: fallthrough
-	case pruner.ErrPerm:
+	case pruner.Plan:
+		fallthrough
+	case pruner.PlanErr:
 		return
 	}
 
@@ -465,7 +498,7 @@ func (t *tui) renderPrunerReport(r *pruner.Report) {
 	t.write("[")
 	t.write(times("=", progress))
 	t.write(">")
-	t.write(times("-", 80 - progress))
+	t.write(times("-", 80-progress))
 	t.write("]")
 	t.printf(" %d/%d snapshots", completedDestroyCount, totalDestroyCount)
 	t.newline()
@@ -478,8 +511,18 @@ func (t *tui) renderPrunerReport(r *pruner.Report) {
 	for _, fs := range all {
 		t.write(rightPad(fs.Filesystem, maxFSname, " "))
 		t.write(" ")
+		if !fs.SkipReason.NotSkipped() {
+			t.printf("skipped: %s\n", fs.SkipReason)
+			continue
+		}
 		if fs.LastError != "" {
-			t.printf("ERROR (%d): %s\n", fs.ErrorCount, fs.LastError) // whitespace is padding
+			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
 		}
 
@@ -487,7 +530,7 @@ func (t *tui) renderPrunerReport(r *pruner.Report) {
 			len(fs.DestroyList), len(fs.SnapshotList))
 
 		if fs.completed {
-			t.printf( "Completed  %s\n", pruneRuleActionStr)
+			t.printf("Completed  %s\n", pruneRuleActionStr)
 			continue
 		}
 
@@ -502,25 +545,6 @@ func (t *tui) renderPrunerReport(r *pruner.Report) {
 
 }
 
-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
@@ -535,14 +559,6 @@ func rightPad(str string, length int, pad string) string {
 	return str + times(pad, length-len(str))
 }
 
-
-func leftPad(str string, length int, pad string) string {
-	if len(str) > length {
-		return str[len(str)-length:]
-	}
-	return times(pad, length-len(str)) + str
-}
-
 var arrowPositions = `>\|/`
 
 // changeCount = 0 indicates stall / no progresss
@@ -559,40 +575,18 @@ func (t *tui) drawBar(length int, bytes, totalBytes int64, changeCount int) {
 
 	t.write("[")
 	t.write(times("=", completedLength))
-	t.write( string(arrowPositions[changeCount%len(arrowPositions)]))
+	t.write(string(arrowPositions[changeCount%len(arrowPositions)]))
 	t.write(times("-", length-completedLength))
 	t.write("]")
 }
 
-func StringStepState(s fsrep.StepState) string {
-	switch s {
-	case fsrep.StepReplicationReady: return "Ready"
-	case fsrep.StepMarkReplicatedReady: return "MarkReady"
-	case fsrep.StepCompleted: return "Completed"
-	default:
-		return fmt.Sprintf("UNKNOWN %d", s)
-	}
-}
-
-func (t *tui) printFilesystemStatus(rep *fsrep.Report, active bool, maxFS int) {
-
-	bytes := int64(0)
-	totalBytes := int64(0)
-	for _, s := range rep.Pending {
-		bytes += s.Bytes
-		totalBytes += s.ExpectedBytes
-	}
-	for _, s := range rep.Completed {
-		bytes += s.Bytes
-		totalBytes += s.ExpectedBytes
-	}
-
+func (t *tui) printFilesystemStatus(rep *report.FilesystemReport, active bool, maxFS int) {
 
+	expected, replicated := rep.BytesSum()
 	status := fmt.Sprintf("%s (step %d/%d, %s/%s)",
-		rep.Status,
-		len(rep.Completed), len(rep.Pending) + len(rep.Completed),
-		ByteCountBinary(bytes), ByteCountBinary(totalBytes),
-
+		strings.ToUpper(string(rep.State)),
+		rep.CurrentStep, len(rep.Steps),
+		ByteCountBinary(replicated), ByteCountBinary(expected),
 	)
 
 	activeIndicator := " "
@@ -601,18 +595,23 @@ func (t *tui) printFilesystemStatus(rep *fsrep.Report, active bool, maxFS int) {
 	}
 	t.printf("%s %s %s ",
 		activeIndicator,
-		rightPad(rep.Filesystem, maxFS, " "),
+		rightPad(rep.Info.Name, maxFS, " "),
 		status)
 
 	next := ""
-	if rep.Problem != "" {
-		next = rep.Problem
-	} else if len(rep.Pending) > 0 {
-		if rep.Pending[0].From != "" {
-			next = fmt.Sprintf("next: %s => %s", rep.Pending[0].From, rep.Pending[0].To)
+	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: %s (full)", nextStep.Info.To)
+			}
 		} else {
-			next = fmt.Sprintf("next: %s (full)", rep.Pending[0].To)
+			next = "" // individual FSes may still be in planning state
 		}
+
 	}
 	t.printfDrawIndentedAndWrappedIfMultiline("%s", next)
 

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"
 )

client/testcmd.go

@@ -2,28 +2,31 @@ package client
 
 import (
 	"fmt"
+
+	"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}
 	},
 }
 
 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")
@@ -50,8 +53,10 @@ 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
 	default:
 		return fmt.Errorf("job type %T does not have filesystems filter", j)
 	}
@@ -105,4 +110,69 @@ 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(subcommand *cli.Subcommand, args []string) error {
+
+	var checkDPs []*zfs.DatasetPath
+
+	// all actions first
+	if testPlaceholderArgs.all {
+		out, err := zfs.ZFSList([]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 {
+		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(dp)
+		if err != nil {
+			return errors.Wrap(err, "cannot get placeholder state")
+		}
+		if !ph.FSExists {
+			panic("placeholder state inconsistent: filesystem " + ph.FS + " must exist in this context")
+		}
+		is := "yes"
+		if !ph.IsPlaceholder {
+			is = "no"
+		}
+		fmt.Printf("%s\t%s\t%s\n", is, dp.ToString(), ph.RawLocalPropertyValue)
+	}
+	return nil
+}

client/version.go

@@ -2,23 +2,25 @@ package client
 
 import (
 	"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)")

config/config.go

@@ -2,14 +2,16 @@ 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/zrepl/yaml-config"
 )
 
 type Config struct {
@@ -33,41 +35,87 @@ 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"`
+	Debug   JobDebugSettings      `yaml:"debug,optional"`
 }
 
 type PassiveJob struct {
-	Type        string           `yaml:"type"`
-	Name        string           `yaml:"name"`
-	Serve       ServeEnum `yaml:"serve"`
-	Debug       JobDebugSettings `yaml:"debug,optional"`
+	Type  string           `yaml:"type"`
+	Name  string           `yaml:"name"`
+	Serve ServeEnum        `yaml:"serve"`
+	Debug JobDebugSettings `yaml:"debug,optional"`
+}
+
+type SnapJob struct {
+	Type         string            `yaml:"type"`
+	Name         string            `yaml:"name"`
+	Pruning      PruningLocal      `yaml:"pruning"`
+	Debug        JobDebugSettings  `yaml:"debug,optional"`
+	Snapshotting SnapshottingEnum  `yaml:"snapshotting"`
+	Filesystems  FilesystemsFilter `yaml:"filesystems"`
 }
 
 type PushJob struct {
-	ActiveJob `yaml:",inline"`
-	Snapshotting SnapshottingEnum          `yaml:"snapshotting"`
-	Filesystems FilesystemsFilter `yaml:"filesystems"`
+	ActiveJob    `yaml:",inline"`
+	Snapshotting SnapshottingEnum  `yaml:"snapshotting"`
+	Filesystems  FilesystemsFilter `yaml:"filesystems"`
 }
 
 type PullJob struct {
 	ActiveJob `yaml:",inline"`
-	RootFS    string        `yaml:"root_fs"`
-	Interval  time.Duration `yaml:"interval,positive"`
+	RootFS    string                   `yaml:"root_fs"`
+	Interval  PositiveDurationOrManual `yaml:"interval"`
+}
+
+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 = time.ParseDuration(s)
+		if err != nil {
+			return err
+		}
+		if i.Interval <= 0 {
+			return fmt.Errorf("value must be a positive duration, got %q", s)
+		}
+	}
+	return nil
 }
 
 type SinkJob struct {
@@ -76,9 +124,9 @@ type SinkJob struct {
 }
 
 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"`
 }
 
 type FilesystemsFilter map[string]bool
@@ -88,8 +136,8 @@ type SnapshottingEnum struct {
 }
 
 type SnapshottingPeriodic struct {
-	Type string		`yaml:"type"`
-	Prefix string	`yaml:"prefix"`
+	Type     string        `yaml:"type"`
+	Prefix   string        `yaml:"prefix"`
 	Interval time.Duration `yaml:"interval,positive"`
 }
 
@@ -130,7 +178,6 @@ 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{}) {
@@ -145,29 +192,18 @@ 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"`
+	DialTimeout   time.Duration `yaml:"dial_timeout,zeropositive,default=10s"`
 }
 
 type TLSConnect struct {
@@ -177,7 +213,7 @@ type TLSConnect struct {
 	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 {
@@ -189,12 +225,12 @@ 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"`
+	ConnectCommon  `yaml:",inline"`
+	ListenerName   string `yaml:"listener_name"`
 	ClientIdentity string `yaml:"client_identity"`
 }
 
@@ -203,8 +239,7 @@ type ServeEnum struct {
 }
 
 type ServeCommon struct {
-	Type string     `yaml:"type"`
-	RPC  *RPCConfig `yaml:"rpc,optional"`
+	Type string `yaml:"type"`
 }
 
 type TCPServe struct {
@@ -220,16 +255,16 @@ type TLSServe struct {
 	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"`
 }
 
@@ -238,8 +273,8 @@ 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 {
@@ -248,8 +283,9 @@ type PruneKeepLastN struct {
 }
 
 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 {
@@ -270,7 +306,8 @@ 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 {
@@ -296,6 +333,14 @@ type PrometheusMonitoring struct {
 	Listen string `yaml:"listen"`
 }
 
+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"`
 }
@@ -339,6 +384,7 @@ 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 +398,7 @@ 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 +408,7 @@ func (t *ServeEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
 		"tcp":         &TCPServe{},
 		"tls":         &TLSServe{},
 		"stdinserver": &StdinserverServer{},
-		"local"      : &LocalServe{},
+		"local":       &LocalServe{},
 	})
 	return
 }
@@ -380,7 +426,7 @@ 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{},
 	})
 	return
 }
@@ -401,6 +447,60 @@ 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
+}
+
 var ConfigFileDefaultLocations = []string{
 	"/etc/zrepl/zrepl.yml",
 	"/usr/local/etc/zrepl/zrepl.yml",

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 {
@@ -22,7 +25,7 @@ jobs:
 `
 	_, err := ParseConfigBytes([]byte(jobdef))
 	require.NoError(t, err)
-	return testValidConfig(t, s + jobdef)
+	return testValidConfig(t, s+jobdef)
 }
 
 func TestOutletTypes(t *testing.T) {
@@ -69,7 +72,37 @@ global:
     - type: prometheus
       listen: ':9091'
 `)
-	assert.Equal(t, ":9091", conf.Global.Monitoring[0].Ret.(*PrometheusMonitoring).Listen)	
+	assert.Equal(t, ":9091", 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_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_rpc_test.go

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

config/config_snapshotting_test.go

@@ -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) {
@@ -37,7 +38,7 @@ jobs:
     interval: 10m
 `
 
-	fillSnapshotting := func(s string) string {return fmt.Sprintf(tmpl, s)}
+	fillSnapshotting := func(s string) string { return fmt.Sprintf(tmpl, s) }
 	var c *Config
 
 	t.Run("manual", func(t *testing.T) {
@@ -51,7 +52,7 @@ jobs:
 		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, "zrepl_", snp.Prefix)
 	})
 
 }

config/config_test.go

@@ -1,11 +1,14 @@
 package config
 
 import (
-	"github.com/kr/pretty"
-	"github.com/stretchr/testify/require"
+	"bytes"
 	"path"
 	"path/filepath"
 	"testing"
+	"text/template"
+
+	"github.com/kr/pretty"
+	"github.com/stretchr/testify/require"
 )
 
 func TestSampleConfigsAreParsedWithoutErrors(t *testing.T) {
@@ -35,8 +38,22 @@ func TestSampleConfigsAreParsedWithoutErrors(t *testing.T) {
 
 }
 
+// template must be a template/text template with a single '{{ . }}' as placehodler 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 +64,4 @@ func testValidConfig(t *testing.T, input string) (*Config) {
 func testConfig(t *testing.T, input string) (*Config, error) {
 	t.Helper()
 	return ParseConfigBytes([]byte(input))
-}
+}

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 {
@@ -31,10 +31,6 @@ 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 {

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

daemon/control.go

@@ -5,16 +5,19 @@ 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"
 	"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/logger"
+	"github.com/zrepl/zrepl/version"
+	"github.com/zrepl/zrepl/zfs"
 )
 
 type controlJob struct {
@@ -38,25 +41,27 @@ 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 }
+
 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 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},
 	}, []string{"endpoint"})
 	registerer.MustRegister(promControl.requestBegin)
 	registerer.MustRegister(promControl.requestFinished)
@@ -84,7 +89,7 @@ func (j *controlJob) Run(ctx context.Context) {
 
 	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 {
@@ -95,22 +100,22 @@ 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,
 		// don't log requests to status endpoint, too spammy
-		jsonResponder{func() (interface{}, error) {
+		jsonResponder{log, func() (interface{}, error) {
 			s := j.jobs.status()
 			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 {
@@ -132,8 +137,8 @@ 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: 1 * time.Second,
+		ReadTimeout:  1 * time.Second,
 	}
 
 outer:
@@ -148,7 +153,10 @@ 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 {
@@ -162,33 +170,50 @@ 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)
@@ -200,22 +225,28 @@ 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 marhsal 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 +3,16 @@ package daemon
 import (
 	"context"
 	"fmt"
+	"os"
+	"os/signal"
+	"strings"
+	"sync"
+	"syscall"
+	"time"
+
 	"github.com/pkg/errors"
 	"github.com/prometheus/client_golang/prometheus"
+
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/job"
 	"github.com/zrepl/zrepl/daemon/job/reset"
@@ -12,12 +20,6 @@ import (
 	"github.com/zrepl/zrepl/daemon/logging"
 	"github.com/zrepl/zrepl/logger"
 	"github.com/zrepl/zrepl/version"
-	"os"
-	"os/signal"
-	"strings"
-	"sync"
-	"syscall"
-	"time"
 )
 
 func Run(conf *config.Config) error {
@@ -74,12 +76,11 @@ 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 monitorin gjob #%d", i)
 		}
 		jobs.start(ctx, job, true)
 	}
 
-
 	log.Info("starting daemon")
 
 	// start regular jobs
@@ -103,7 +104,7 @@ 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
 }
 
@@ -116,9 +117,7 @@ func newJobs() *jobs {
 }
 
 const (
-	logJobField    string = "job"
-	logTaskField   string = "task"
-	logSubsysField string = "subsystem"
+	logJobField string = "job"
 )
 
 func (s *jobs) wait() <-chan struct{} {

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 {

daemon/filters/fsvfilter.go

@@ -1,8 +1,9 @@
 package filters
 
 import (
-	"github.com/zrepl/zrepl/zfs"
 	"strings"
+
+	"github.com/zrepl/zrepl/zfs"
 )
 
 type AnyFSVFilter struct{}
@@ -17,7 +18,6 @@ func (AnyFSVFilter) Filter(t zfs.VersionType, name string) (accept bool, err err
 	return true, nil
 }
 
-
 type PrefixFilter struct {
 	prefix    string
 	fstype    zfs.VersionType

daemon/job/active.go

@@ -2,9 +2,12 @@ package job
 
 import (
 	"context"
+	"sync"
+	"time"
+
 	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
 	"github.com/prometheus/client_golang/prometheus"
+
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/filters"
 	"github.com/zrepl/zrepl/daemon/job/reset"
@@ -12,32 +15,32 @@ import (
 	"github.com/zrepl/zrepl/daemon/logging"
 	"github.com/zrepl/zrepl/daemon/pruner"
 	"github.com/zrepl/zrepl/daemon/snapper"
-	"github.com/zrepl/zrepl/daemon/transport/connecter"
 	"github.com/zrepl/zrepl/endpoint"
 	"github.com/zrepl/zrepl/replication"
-	"github.com/zrepl/zrepl/util/envconst"
+	"github.com/zrepl/zrepl/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"
-	"time"
 )
 
 type ActiveSide struct {
-	mode          activeMode
-	name          string
-	clientFactory *connecter.ClientFactory
+	mode      activeMode
+	name      string
+	connecter transport.Connecter
 
 	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
 
 	tasksMtx sync.Mutex
 	tasks    activeSideTasks
 }
 
-
 //go:generate enumer -type=ActiveSideState
 type ActiveSideState int
 
@@ -48,12 +51,11 @@ const (
 	ActiveSideDone // also errors
 )
 
-
 type activeSideTasks struct {
 	state ActiveSideState
 
 	// valid for state ActiveSideReplicating, ActiveSidePruneSender, ActiveSidePruneReceiver, ActiveSideDone
-	replication *replication.Replication
+	replicationReport driver.ReportFunc
 	replicationCancel context.CancelFunc
 
 	// valid for state ActiveSidePruneSender, ActiveSidePruneReceiver, ActiveSideDone
@@ -66,8 +68,7 @@ type activeSideTasks struct {
 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
 	}
@@ -77,28 +78,59 @@ func (a *ActiveSide) updateTasks(u func(*activeSideTasks)) activeSideTasks {
 }
 
 type activeMode interface {
-	SenderReceiver(client *streamrpc.Client) (replication.Sender, replication.Receiver, error)
+	ConnectEndpoints(rpcLoggers rpc.Loggers, connecter transport.Connecter)
+	DisconnectEndpoints()
+	SenderReceiver() (logic.Sender, logic.Receiver)
 	Type() Type
 	RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{})
+	ResetConnectBackoff()
 }
 
 type modePush struct {
-	fsfilter         endpoint.FSFilter
-	snapper *snapper.PeriodicOrManual
+	setupMtx sync.Mutex
+	sender   *endpoint.Sender
+	receiver *rpc.Client
+	fsfilter endpoint.FSFilter
+	snapper  *snapper.PeriodicOrManual
 }
 
-func (m *modePush) SenderReceiver(client *streamrpc.Client) (replication.Sender, replication.Receiver, error) {
-	sender := endpoint.NewSender(m.fsfilter)
-	receiver := endpoint.NewRemote(client)
-	return sender, receiver, nil
+func (m *modePush) ConnectEndpoints(loggers rpc.Loggers, 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.fsfilter)
+	m.receiver = rpc.NewClient(connecter, loggers)
+}
+
+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) RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{}) {
 	m.snapper.Run(ctx, wakeUpCommon)
 }
 
+func (m *modePush) ResetConnectBackoff() {
+	m.setupMtx.Lock()
+	defer m.setupMtx.Unlock()
+	if m.receiver != nil {
+		m.receiver.ResetConnectBackoff()
+	}
+}
 
 func modePushFromConfig(g *config.Global, in *config.PushJob) (*modePush, error) {
 	m := &modePush{}
@@ -116,20 +148,46 @@ func modePushFromConfig(g *config.Global, in *config.PushJob) (*modePush, error)
 }
 
 type modePull struct {
+	setupMtx sync.Mutex
+	receiver *endpoint.Receiver
+	sender   *rpc.Client
 	rootFS   *zfs.DatasetPath
-	interval time.Duration
+	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(loggers rpc.Loggers, 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.rootFS, false)
+	m.sender = rpc.NewClient(connecter, loggers)
+}
+
+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) 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 {
@@ -148,11 +206,16 @@ func (m *modePull) RunPeriodic(ctx context.Context, wakeUpCommon chan<- struct{}
 	}
 }
 
+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) (m *modePull, err error) {
 	m = &modePull{}
-	if in.Interval <= 0 {
-		return nil, errors.New("interval must be positive")
-	}
 	m.interval = in.Interval
 
 	m.rootFS, err = zfs.NewDatasetPath(in.RootFS)
@@ -175,17 +238,17 @@ func activeSide(g *config.Global, in *config.ActiveJob, mode activeMode) (j *Act
 		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{"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{"filesystem"})
 
-	j.clientFactory, err = connecter.FromConfig(g, in.Connect)
+	j.connecter, err = fromconfig.ConnecterFromConfig(g, in.Connect)
 	if err != nil {
 		return nil, errors.Wrap(err, "cannot build client")
 	}
@@ -195,7 +258,7 @@ 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{"prune_side"})
 	j.prunerFactory, err = pruner.NewPrunerFactory(in.Pruning, j.promPruneSecs)
 	if err != nil {
@@ -214,7 +277,7 @@ func (j *ActiveSide) RegisterMetrics(registerer prometheus.Registerer) {
 func (j *ActiveSide) Name() string { return j.name }
 
 type ActiveSideStatus struct {
-	Replication *replication.Report
+	Replication                    *report.Report
 	PruningSender, PruningReceiver *pruner.Report
 }
 
@@ -223,8 +286,8 @@ 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()
@@ -235,6 +298,15 @@ func (j *ActiveSide) Status() *Status {
 	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.rootFS.Copy(), true
+}
+
 func (j *ActiveSide) Run(ctx context.Context) {
 	log := GetLogger(ctx)
 	ctx = logging.WithSubsystemLoggers(ctx, log)
@@ -256,6 +328,7 @@ outer:
 			break outer
 
 		case <-wakeup.Wait(ctx):
+			j.mode.ResetConnectBackoff()
 		case <-periodicDone:
 		}
 		invocationCount++
@@ -268,6 +341,9 @@ func (j *ActiveSide) do(ctx context.Context) {
 
 	log := GetLogger(ctx)
 	ctx = logging.WithSubsystemLoggers(ctx, log)
+	loggers := rpc.GetLoggersOrPanic(ctx) // filled by WithSubsystemLoggers
+	j.mode.ConnectEndpoints(loggers, j.connecter)
+	defer j.mode.DisconnectEndpoints()
 
 	// allow cancellation of an invocation (this function)
 	ctx, cancelThisRun := context.WithCancel(ctx)
@@ -281,85 +357,7 @@ func (j *ActiveSide) do(ctx context.Context) {
 		}
 	}()
 
-	// The code after this watchdog goroutine is sequential and transitions the state from
-	//   ActiveSideReplicating -> ActiveSidePruneSender -> ActiveSidePruneReceiver -> ActiveSideDone
-	// If any of those sequential tasks 'gets stuck' (livelock, no progress), the watchdog will eventually
-	// cancel its context.
-	// If the task is written to support context cancellation, it will return immediately (in permanent error state),
-	// and the sequential code above transitions to the next state.
-	go func() {
-
-		wdto := envconst.Duration("ZREPL_JOB_WATCHDOG_TIMEOUT", 10*time.Minute)
-		jitter := envconst.Duration("ZREPL_JOB_WATCHDOG_JITTER", 1*time.Second)
-		// shadowing!
-		log := log.WithField("watchdog_timeout", wdto.String())
-
-		log.Debug("starting watchdog")
-		defer log.Debug("watchdog stopped")
-
-		t := time.NewTicker(wdto)
-		defer t.Stop()
-
-		for {
-			select {
-			case <-ctx.Done():
-				return
-			case <-t.C: // fall
-			}
-
-			j.updateTasks(func(tasks *activeSideTasks) {
-				// Since cancelling a task will cause the sequential code to transition to the next state immediately,
-				// we cannot check for its progress right then (no fallthrough).
-				// Instead, we return (not continue because we are in a closure) and give the new state another
-				// ZREPL_JOB_WATCHDOG_TIMEOUT interval to try make some progress.
-
-				log.WithField("state", tasks.state).Debug("watchdog firing")
-
-				const WATCHDOG_ENVCONST_NOTICE = " (adjust ZREPL_JOB_WATCHDOG_TIMEOUT env variable if inappropriate)"
-
-				switch tasks.state {
-				case ActiveSideReplicating:
-					log.WithField("replication_progress", tasks.replication.Progress.String()).
-						Debug("check replication progress")
-					if tasks.replication.Progress.CheckTimeout(wdto, jitter) {
-						log.Error("replication did not make progress, cancelling" + WATCHDOG_ENVCONST_NOTICE)
-						tasks.replicationCancel()
-						return
-					}
-				case ActiveSidePruneSender:
-					log.WithField("prune_sender_progress", tasks.replication.Progress.String()).
-						Debug("check pruner_sender progress")
-					if tasks.prunerSender.Progress.CheckTimeout(wdto, jitter) {
-						log.Error("pruner_sender did not make progress, cancelling" + WATCHDOG_ENVCONST_NOTICE)
-						tasks.prunerSenderCancel()
-						return
-					}
-				case ActiveSidePruneReceiver:
-					log.WithField("prune_receiver_progress", tasks.replication.Progress.String()).
-						Debug("check pruner_receiver progress")
-					if tasks.prunerReceiver.Progress.CheckTimeout(wdto, jitter) {
-						log.Error("pruner_receiver did not make progress, cancelling" + WATCHDOG_ENVCONST_NOTICE)
-						tasks.prunerReceiverCancel()
-						return
-					}
-				case ActiveSideDone:
-					// ignore, ctx will be Done() in a few milliseconds and the watchdog will exit
-				default:
-					log.WithField("state", tasks.state).
-						Error("watchdog implementation error: unknown active side state")
-				}
-			})
-
-		}
-	}()
-
-	client, err := j.clientFactory.NewClient()
-	if err != nil {
-		log.WithError(err).Error("factory cannot instantiate streamrpc client")
-	}
-	defer client.Close(ctx)
-
-	sender, receiver, err := j.mode.SenderReceiver(client)
+	sender, receiver := j.mode.SenderReceiver()
 
 	{
 		select {
@@ -368,16 +366,19 @@ func (j *ActiveSide) do(ctx context.Context) {
 		default:
 		}
 		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.replicationReport, repWait = replication.Do(
+				ctx, logic.NewPlanner(j.promRepStateSecs, j.promBytesReplicated, sender, receiver),
+			)
 			tasks.state = ActiveSideReplicating
 		})
 		log.Info("start replication")
-		tasks.replication.Drive(ctx, sender, receiver)
-		repCancel() // always cancel to free up context resources
+		repWait(true) // wait blocking
+		repCancel()   // always cancel to free up context resources
 	}
 
 	{

daemon/job/build_jobs.go

@@ -2,7 +2,11 @@ package job
 
 import (
 	"fmt"
+	"sort"
+	"strings"
+
 	"github.com/pkg/errors"
+
 	"github.com/zrepl/zrepl/config"
 )
 
@@ -18,6 +22,22 @@ 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
 }
 
@@ -45,6 +65,11 @@ func buildJob(c *config.Global, in config.JobEnum) (j Job, err error) {
 		if err != nil {
 			return cannotBuildJob(err, v.Name)
 		}
+	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 {
@@ -69,3 +94,27 @@ 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
+	})
+	// 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
+}

daemon/job/build_jobs_test.go

@@ -0,0 +1,42 @@
+package job
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+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"}},
+		{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)
+		}
+	}
+}

daemon/job/job.go

@@ -4,8 +4,11 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+
 	"github.com/prometheus/client_golang/prometheus"
+
 	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/zfs"
 )
 
 type Logger = logger.Logger
@@ -27,26 +30,29 @@ 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)
 }
 
 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 +65,8 @@ 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 +90,25 @@ 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

@@ -2,28 +2,30 @@ package job
 
 import (
 	"context"
+	"fmt"
+
 	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
 	"github.com/prometheus/client_golang/prometheus"
+
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/filters"
 	"github.com/zrepl/zrepl/daemon/logging"
-	"github.com/zrepl/zrepl/daemon/transport/serve"
 	"github.com/zrepl/zrepl/daemon/snapper"
 	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/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   string
+	listen transport.AuthenticatedListenerFactory
 }
 
 type passiveMode interface {
-	ConnHandleFunc(ctx context.Context, conn serve.AuthenticatedConn) streamrpc.HandlerFunc
+	Handler() rpc.Handler
 	RunPeriodic(ctx context.Context)
 	Type() Type
 }
@@ -34,26 +36,8 @@ type modeSink struct {
 
 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.rootDataset, true)
 }
 
 func (m *modeSink) RunPeriodic(_ context.Context) {}
@@ -72,7 +56,7 @@ func modeSinkFromConfig(g *config.Global, in *config.SinkJob) (m *modeSink, err
 
 type modeSource struct {
 	fsfilter zfs.DatasetFilter
-	snapper *snapper.PeriodicOrManual
+	snapper  *snapper.PeriodicOrManual
 }
 
 func modeSourceFromConfig(g *config.Global, in *config.SourceJob) (m *modeSource, err error) {
@@ -93,10 +77,8 @@ 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.fsfilter)
 }
 
 func (m *modeSource) RunPeriodic(ctx context.Context) {
@@ -106,8 +88,8 @@ func (m *modeSource) RunPeriodic(ctx context.Context) {
 func passiveSideFromConfig(g *config.Global, in *config.PassiveJob, mode passiveMode) (s *PassiveSide, err error) {
 
 	s = &PassiveSide{mode: mode, name: in.Name}
-	if s.l, s.rpcConf, err = serve.FromConfig(g, in.Serve); err != nil {
-		return nil, errors.Wrap(err, "cannot build server")
+	if s.listen, err = fromconfig.ListenerFactoryFromConfig(g, in.Serve); err != nil {
+		return nil, errors.Wrap(err, "cannot build listener factory")
 	}
 
 	return s, nil
@@ -115,82 +97,51 @@ func passiveSideFromConfig(g *config.Global, in *config.PassiveJob, mode passive
 
 func (j *PassiveSide) Name() string { return j.name }
 
-type PassiveStatus struct {}
+type PassiveStatus struct{}
 
 func (s *PassiveSide) Status() *Status {
 	return &Status{Type: s.mode.Type()} // FIXME PassiveStatus
 }
 
+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.rootDataset.Copy(), true
+}
+
 func (*PassiveSide) RegisterMetrics(registerer prometheus.Registerer) {}
 
 func (j *PassiveSide) Run(ctx context.Context) {
 
 	log := GetLogger(ctx)
 	defer log.Info("job exiting")
-
-	l, err := j.l.Listen()
-	if err != nil {
-		log.WithError(err).Error("cannot listen")
-		return
-	}
-	defer l.Close()
-
+	ctx = logging.WithSubsystemLoggers(ctx, log)
 	{
-		ctx, cancel := context.WithCancel(logging.WithSubsystemLoggers(ctx, log)) // shadowing
+		ctx, cancel := context.WithCancel(ctx) // shadowing
 		defer cancel()
 		go j.mode.RunPeriodic(ctx)
 	}
 
-	log.WithField("addr", l.Addr()).Debug("accepting connections")
-	var connId int
-outer:
-	for {
-
-		select {
-		case res := <-accept(ctx, l):
-			if res.err != nil {
-				log.WithError(res.err).Info("accept error")
-				continue
-			}
-			conn := res.conn
-			connId++
-			connLog := log.
-				WithField("connID", connId)
-			connLog.
-				WithField("addr", conn.RemoteAddr()).
-				WithField("client_identity", conn.ClientIdentity()).
-				Info("handling connection")
-			go func() {
-				defer connLog.Info("finished handling connection")
-				defer conn.Close()
-				ctx := logging.WithSubsystemLoggers(ctx, connLog)
-				handleFunc := j.mode.ConnHandleFunc(ctx, conn)
-				if handleFunc == nil {
-					return
-				}
-				if err := streamrpc.ServeConn(ctx, conn, j.rpcConf, handleFunc); err != nil {
-					log.WithError(err).Error("error serving client")
-				}
-			}()
-
-		case <-ctx.Done():
-			break outer
-		}
-
+	handler := j.mode.Handler()
+	if handler == nil {
+		panic(fmt.Sprintf("implementation error: j.mode.Handler() returned nil: %#v", j))
 	}
 
-}
+	ctxInterceptor := func(handlerCtx context.Context) context.Context {
+		return logging.WithSubsystemLoggers(handlerCtx, log)
+	}
 
-type acceptResult struct {
-	conn serve.AuthenticatedConn
-	err  error
-}
+	rpcLoggers := rpc.GetLoggersOrPanic(ctx) // WithSubsystemLoggers above
+	server := rpc.NewServer(handler, rpcLoggers, ctxInterceptor)
 
-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
+	listener, err := j.listen()
+	if err != nil {
+		log.WithError(err).Error("cannot listen")
+		return
+	}
+
+	server.Serve(ctx, listener)
 }

daemon/job/snapjob.go

@@ -0,0 +1,168 @@
+package job
+
+import (
+	"context"
+	"fmt"
+	"sort"
+
+	"github.com/pkg/errors"
+	"github.com/prometheus/client_golang/prometheus"
+
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/daemon/filters"
+	"github.com/zrepl/zrepl/daemon/job/wakeup"
+	"github.com/zrepl/zrepl/daemon/logging"
+	"github.com/zrepl/zrepl/daemon/pruner"
+	"github.com/zrepl/zrepl/daemon/snapper"
+	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/replication/logic/pdu"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+type SnapJob struct {
+	name     string
+	fsfilter zfs.DatasetFilter
+	snapper  *snapper.PeriodicOrManual
+
+	prunerFactory *pruner.LocalPrunerFactory
+
+	promPruneSecs *prometheus.HistogramVec // labels: prune_side
+
+	pruner *pruner.Pruner
+}
+
+func (j *SnapJob) Name() string { return j.name }
+
+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, "cannnot 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 = in.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{"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
+}
+
+func (j *SnapJob) Status() *Status {
+	s := &SnapJobStatus{}
+	t := j.Type()
+	if j.pruner != nil {
+		s.Pruning = j.pruner.Report()
+	}
+	return &Status{Type: t, JobSpecific: s}
+}
+
+func (j *SnapJob) OwnedDatasetSubtreeRoot() (rfs *zfs.DatasetPath, ok bool) {
+	return nil, false
+}
+
+func (j *SnapJob) Run(ctx context.Context) {
+	log := GetLogger(ctx)
+	ctx = logging.WithSubsystemLoggers(ctx, log)
+
+	defer log.Info("job exiting")
+
+	periodicDone := make(chan struct{})
+	ctx, cancel := context.WithCancel(ctx)
+	defer cancel()
+	go j.snapper.Run(ctx, periodicDone)
+
+	invocationCount := 0
+outer:
+	for {
+		log.Info("wait for wakeups")
+		select {
+		case <-ctx.Done():
+			log.WithError(ctx.Err()).Info("context")
+			break outer
+
+		case <-wakeup.Wait(ctx):
+		case <-periodicDone:
+		}
+		invocationCount++
+		invLog := log.WithField("invocation", invocationCount)
+		j.doPrune(WithLogger(ctx, invLog))
+	}
+}
+
+// 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.History = (*alwaysUpToDateReplicationCursorHistory)(nil)
+
+func (h alwaysUpToDateReplicationCursorHistory) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
+	if req.GetGet() == nil {
+		return nil, fmt.Errorf("unsupported ReplicationCursor request: SnapJob only supports GETting a (faked) cursor")
+	}
+	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) {
+	log := GetLogger(ctx)
+	ctx = logging.WithSubsystemLoggers(ctx, log)
+	sender := endpoint.NewSender(j.fsfilter)
+	j.pruner = j.prunerFactory.BuildLocalPruner(ctx, sender, alwaysUpToDateReplicationCursorHistory{sender})
+	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 +4,23 @@ 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/daemon/snapper"
 	"github.com/zrepl/zrepl/endpoint"
 	"github.com/zrepl/zrepl/logger"
-	"github.com/zrepl/zrepl/replication"
+	"github.com/zrepl/zrepl/replication/driver"
+	"github.com/zrepl/zrepl/replication/logic"
+	"github.com/zrepl/zrepl/rpc"
+	"github.com/zrepl/zrepl/rpc/transportmux"
 	"github.com/zrepl/zrepl/tlsconf"
-	"os"
-	"github.com/zrepl/zrepl/daemon/snapper"
-	"github.com/zrepl/zrepl/daemon/transport/serve"
+	"github.com/zrepl/zrepl/transport"
 )
 
 func OutletsFromConfig(in config.LoggingOutletEnumList) (*logger.Outlets, error) {
@@ -60,22 +65,42 @@ func OutletsFromConfig(in config.LoggingOutletEnumList) (*logger.Outlets, error)
 
 }
 
+type Subsystem string
+
 const (
-	SubsysReplication = "repl"
-	SubsysStreamrpc   = "rpc"
-	SubsyEndpoint     = "endpoint"
+	SubsysReplication  Subsystem = "repl"
+	SubsyEndpoint      Subsystem = "endpoint"
+	SubsysPruning      Subsystem = "pruning"
+	SubsysSnapshot     Subsystem = "snapshot"
+	SubsysTransport    Subsystem = "transport"
+	SubsysTransportMux Subsystem = "transportmux"
+	SubsysRPC          Subsystem = "rpc"
+	SubsysRPCControl   Subsystem = "rpc.ctrl"
+	SubsysRPCData      Subsystem = "rpc.data"
 )
 
 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"))
+	ctx = logic.WithLogger(ctx, log.WithField(SubsysField, SubsysReplication))
+	ctx = driver.WithLogger(ctx, log.WithField(SubsysField, SubsysReplication))
+	ctx = endpoint.WithLogger(ctx, log.WithField(SubsysField, SubsyEndpoint))
+	ctx = pruner.WithLogger(ctx, log.WithField(SubsysField, SubsysPruning))
+	ctx = snapper.WithLogger(ctx, log.WithField(SubsysField, SubsysSnapshot))
+	ctx = transport.WithLogger(ctx, log.WithField(SubsysField, SubsysTransport))
+	ctx = transportmux.WithLogger(ctx, log.WithField(SubsysField, SubsysTransportMux))
+	ctx = rpc.WithLoggers(ctx,
+		rpc.Loggers{
+			General: log.WithField(SubsysField, SubsysRPC),
+			Control: log.WithField(SubsysField, SubsysRPCControl),
+			Data:    log.WithField(SubsysField, SubsysRPCData),
+		},
+	)
 	return ctx
 }
 
+func LogSubsystem(log logger.Logger, subsys Subsystem) logger.Logger {
+	return log.ReplaceField(SubsysField, subsys)
+}
+
 func parseLogFormat(i interface{}) (f EntryFormatter, err error) {
 	var is string
 	switch j := i.(type) {
@@ -200,6 +225,7 @@ 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
 }

daemon/logging/logging_formatters.go

@@ -4,11 +4,13 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
+	"time"
+
 	"github.com/fatih/color"
 	"github.com/go-logfmt/logfmt"
 	"github.com/pkg/errors"
+
 	"github.com/zrepl/zrepl/logger"
-	"time"
 )
 
 const (
@@ -159,10 +161,16 @@ func (f *LogfmtFormatter) Format(e *logger.Entry) ([]byte, error) {
 	enc := logfmt.NewEncoder(&buf)
 
 	if f.metadataFlags&MetadataTime != 0 {
-		enc.EncodeKeyval(FieldTime, e.Time)
+		err := enc.EncodeKeyval(FieldTime, e.Time)
+		if err != nil {
+			return nil, errors.Wrap(err, "logfmt: encode time")
+		}
 	}
 	if f.metadataFlags&MetadataLevel != 0 {
-		enc.EncodeKeyval(FieldLevel, e.Level)
+		err := enc.EncodeKeyval(FieldLevel, e.Level)
+		if err != nil {
+			return nil, errors.Wrap(err, "logfmt: encode level")
+		}
 	}
 
 	// at least try and put job and task in front
@@ -179,8 +187,10 @@ func (f *LogfmtFormatter) Format(e *logger.Entry) ([]byte, error) {
 		prefixed[pf] = true
 	}
 
-	enc.EncodeKeyval(FieldMessage, e.Message)
-
+	err := enc.EncodeKeyval(FieldMessage, e.Message)
+	if err != nil {
+		return nil, errors.Wrap(err, "logfmt: encode message")
+	}
 	for k, v := range e.Fields {
 		if !prefixed[k] {
 			if err := logfmtTryEncodeKeyval(enc, k, v); err != nil {
@@ -199,7 +209,10 @@ func logfmtTryEncodeKeyval(enc *logfmt.Encoder, field, value interface{}) error
 	case nil: // ok
 		return nil
 	case logfmt.ErrUnsupportedValueType:
-		enc.EncodeKeyval(field, fmt.Sprintf("<%T>", value))
+		err := enc.EncodeKeyval(field, fmt.Sprintf("<%T>", value))
+		if err != nil {
+			return errors.Wrap(err, "cannot encode unsuuported value type Go type")
+		}
 		return nil
 	}
 	return errors.Wrapf(err, "cannot encode field '%s'", field)

daemon/logging/logging_outlets.go

@@ -4,12 +4,14 @@ import (
 	"bytes"
 	"context"
 	"crypto/tls"
-	"github.com/pkg/errors"
-	"github.com/zrepl/zrepl/logger"
 	"io"
 	"log/syslog"
 	"net"
 	"time"
+
+	"github.com/pkg/errors"
+
+	"github.com/zrepl/zrepl/logger"
 )
 
 type EntryFormatter interface {
@@ -28,7 +30,10 @@ func (h WriterOutlet) WriteEntry(entry logger.Entry) error {
 		return err
 	}
 	_, err = h.writer.Write(bytes)
-	h.writer.Write([]byte("\n"))
+	if err != nil {
+		return err
+	}
+	_, err = h.writer.Write([]byte("\n"))
 	return err
 }
 
@@ -92,8 +97,10 @@ func (h *TCPOutlet) outLoop(retryInterval time.Duration) {
 				conn = nil
 			}
 		}
-		conn.SetWriteDeadline(time.Now().Add(retryInterval))
-		_, err = io.Copy(conn, msg)
+		err = conn.SetWriteDeadline(time.Now().Add(retryInterval))
+		if err == nil {
+			_, err = io.Copy(conn, msg)
+		}
 		if err != nil {
 			retry = time.Now().Add(retryInterval)
 			conn.Close()
@@ -124,6 +131,7 @@ func (h *TCPOutlet) WriteEntry(e logger.Entry) error {
 type SyslogOutlet struct {
 	Formatter          EntryFormatter
 	RetryInterval      time.Duration
+	Facility           syslog.Priority
 	writer             *syslog.Writer
 	lastConnectAttempt time.Time
 }
@@ -142,7 +150,7 @@ func (o *SyslogOutlet) WriteEntry(entry logger.Entry) error {
 		if now.Sub(o.lastConnectAttempt) < o.RetryInterval {
 			return nil // not an error toward logger
 		}
-		o.writer, err = syslog.New(syslog.LOG_LOCAL0, "zrepl")
+		o.writer, err = syslog.New(o.Facility, "zrepl")
 		o.lastConnectAttempt = time.Now()
 		if err != nil {
 			o.writer = nil

daemon/main.go

@@ -7,7 +7,7 @@ import (
 
 type Logger = logger.Logger
 
-var DaemonCmd = &cli.Subcommand {
+var DaemonCmd = &cli.Subcommand{
 	Use:   "daemon",
 	Short: "run the zrepl daemon",
 	Run: func(subcommand *cli.Subcommand, args []string) error {

daemon/nethelpers/helpers.go

@@ -1,10 +1,11 @@
 package nethelpers
 
 import (
-	"github.com/pkg/errors"
 	"net"
 	"os"
 	"path/filepath"
+
+	"github.com/pkg/errors"
 )
 
 func PreparePrivateSockpath(sockpath string) error {

daemon/pprof.go

@@ -7,11 +7,12 @@ import (
 	"context"
 	"net"
 	"net/http/pprof"
+
+	"github.com/zrepl/zrepl/daemon/job"
 )
 
 type pprofServer struct {
 	cc       chan PprofServerControlMsg
-	state    PprofServerControlMsg
 	listener net.Listener
 }
 
@@ -63,7 +64,14 @@ outer:
 			mux.Handle("/debug/pprof/profile", http.HandlerFunc(pprof.Profile))
 			mux.Handle("/debug/pprof/symbol", http.HandlerFunc(pprof.Symbol))
 			mux.Handle("/debug/pprof/trace", http.HandlerFunc(pprof.Trace))
-			go http.Serve(s.listener, mux)
+			go func() {
+				err := http.Serve(s.listener, mux)
+				if ctx.Err() != nil {
+					return
+				} else if err != nil {
+					job.GetLogger(ctx).WithError(err).Error("pprof server serve error")
+				}
+			}()
 			continue
 		}
 

daemon/prometheus.go

@@ -2,14 +2,17 @@ package daemon
 
 import (
 	"context"
+	"net"
+	"net/http"
+
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
+
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/job"
 	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/rpc/dataconn/frameconn"
 	"github.com/zrepl/zrepl/zfs"
-	"net"
-	"net/http"
 )
 
 type prometheusJob struct {
@@ -24,7 +27,7 @@ func newPrometheusJobFromConfig(in *config.PrometheusMonitoring) (*prometheusJob
 }
 
 var prom struct {
-	taskLogEntries         *prometheus.CounterVec
+	taskLogEntries *prometheus.CounterVec
 }
 
 func init() {
@@ -41,6 +44,8 @@ func (j *prometheusJob) Name() string { return jobNamePrometheus }
 
 func (j *prometheusJob) Status() *job.Status { return &job.Status{Type: job.TypeInternal} }
 
+func (j *prometheusJob) OwnedDatasetSubtreeRoot() (p *zfs.DatasetPath, ok bool) { return nil, false }
+
 func (j *prometheusJob) RegisterMetrics(registerer prometheus.Registerer) {}
 
 func (j *prometheusJob) Run(ctx context.Context) {
@@ -49,6 +54,10 @@ func (j *prometheusJob) Run(ctx context.Context) {
 		panic(err)
 	}
 
+	if err := frameconn.PrometheusRegister(prometheus.DefaultRegisterer); err != nil {
+		panic(err)
+	}
+
 	log := job.GetLogger(ctx)
 
 	l, err := net.Listen("tcp", j.listen)
@@ -56,17 +65,15 @@ func (j *prometheusJob) Run(ctx context.Context) {
 		log.WithError(err).Error("cannot listen")
 	}
 	go func() {
-		select {
-		case <-ctx.Done():
-			l.Close()
-		}
+		<-ctx.Done()
+		l.Close()
 	}()
 
 	mux := http.NewServeMux()
 	mux.Handle("/metrics", promhttp.Handler())
 
 	err = http.Serve(l, mux)
-	if err != nil {
+	if err != nil && ctx.Err() == nil {
 		log.WithError(err).Error("error while serving")
 	}
 
@@ -86,4 +93,3 @@ func (o prometheusJobOutlet) WriteEntry(entry logger.Entry) error {
 	prom.taskLogEntries.WithLabelValues(o.jobName, entry.Level.String()).Inc()
 	return nil
 }
-

daemon/pruner/pruner.go

@@ -3,30 +3,31 @@ package pruner
 import (
 	"context"
 	"fmt"
-	"github.com/pkg/errors"
-	"github.com/prometheus/client_golang/prometheus"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/logger"
-	"github.com/zrepl/zrepl/pruning"
-	"github.com/zrepl/zrepl/replication/pdu"
-	"github.com/zrepl/zrepl/util/envconst"
-	"github.com/zrepl/zrepl/util/watchdog"
-	"github.com/problame/go-streamrpc"
-	"net"
 	"sort"
 	"strings"
 	"sync"
 	"time"
+
+	"github.com/pkg/errors"
+	"github.com/prometheus/client_golang/prometheus"
+
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/pruning"
+	"github.com/zrepl/zrepl/replication/logic/pdu"
+	"github.com/zrepl/zrepl/util/envconst"
 )
 
-// Try to keep it compatible with gitub.com/zrepl/zrepl/replication.Endpoint
+// Try to keep it compatible with gitub.com/zrepl/zrepl/endpoint.Endpoint
 type History interface {
 	ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error)
+	ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error)
 }
 
+// Try to keep it compatible with gitub.com/zrepl/zrepl/endpoint.Endpoint
 type Target interface {
-	ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error)
-	ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) // fix depS
+	ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error)
+	ListFilesystemVersions(ctx context.Context, req *pdu.ListFilesystemVersionsReq) (*pdu.ListFilesystemVersionsRes, error)
 	DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error)
 }
 
@@ -54,21 +55,18 @@ type args struct {
 	rules                          []pruning.KeepRule
 	retryWait                      time.Duration
 	considerSnapAtCursorReplicated bool
-	promPruneSecs prometheus.Observer
+	promPruneSecs                  prometheus.Observer
 }
 
 type Pruner struct {
 	args args
 
-	Progress watchdog.KeepAlive
-
 	mtx sync.RWMutex
 
 	state State
 
-	// State ErrWait|ErrPerm
-	sleepUntil time.Time
-	err        error
+	// State PlanErr
+	err error
 
 	// State Exec
 	execQueue *execQueue
@@ -79,20 +77,33 @@ type PrunerFactory struct {
 	receiverRules                  []pruning.KeepRule
 	retryWait                      time.Duration
 	considerSnapAtCursorReplicated bool
+	promPruneSecs                  *prometheus.HistogramVec
+}
+
+type LocalPrunerFactory struct {
+	keepRules     []pruning.KeepRule
+	retryWait     time.Duration
 	promPruneSecs *prometheus.HistogramVec
 }
 
-func checkContainsKeep1(rules []pruning.KeepRule) error {
-	if len(rules) == 0 {
-		return nil //No keep rules means keep all - ok
+func NewLocalPrunerFactory(in config.PruningLocal, promPruneSecs *prometheus.HistogramVec) (*LocalPrunerFactory, error) {
+	rules, err := pruning.RulesFromConfig(in.Keep)
+	if err != nil {
+		return nil, errors.Wrap(err, "cannot build pruning rules")
 	}
-	for _, e := range rules {
-		switch e.(type) {
-		case *pruning.KeepLastN:
-			return nil
+	for _, r := range in.Keep {
+		if _, ok := r.Ret.(*config.PruneKeepNotReplicated); ok {
+			// rule NotReplicated  for a local pruner doesn't make sense
+			// because no replication happens with that job type
+			return nil, fmt.Errorf("single-site pruner cannot support `not_replicated` keep rule")
 		}
 	}
-	return errors.New("sender keep rules must contain last_n or be empty so that the last snapshot is definitely kept")
+	f := &LocalPrunerFactory{
+		keepRules:     rules,
+		retryWait:     envconst.Duration("ZREPL_PRUNER_RETRY_INTERVAL", 10*time.Second),
+		promPruneSecs: promPruneSecs,
+	}
+	return f, nil
 }
 
 func NewPrunerFactory(in config.PruningSenderReceiver, promPruneSecs *prometheus.HistogramVec) (*PrunerFactory, error) {
@@ -115,11 +126,11 @@ func NewPrunerFactory(in config.PruningSenderReceiver, promPruneSecs *prometheus
 		considerSnapAtCursorReplicated = considerSnapAtCursorReplicated || !knr.KeepSnapshotAtCursor
 	}
 	f := &PrunerFactory{
-		senderRules: keepRulesSender,
-		receiverRules: keepRulesReceiver,
-		retryWait: envconst.Duration("ZREPL_PRUNER_RETRY_INTERVAL", 10 * time.Second),
+		senderRules:                    keepRulesSender,
+		receiverRules:                  keepRulesReceiver,
+		retryWait:                      envconst.Duration("ZREPL_PRUNER_RETRY_INTERVAL", 10*time.Second),
 		considerSnapAtCursorReplicated: considerSnapAtCursorReplicated,
-		promPruneSecs: promPruneSecs,
+		promPruneSecs:                  promPruneSecs,
 	}
 	return f, nil
 }
@@ -156,82 +167,70 @@ func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target,
 	return p
 }
 
+func (f *LocalPrunerFactory) BuildLocalPruner(ctx context.Context, target Target, receiver History) *Pruner {
+	p := &Pruner{
+		args: args{
+			ctx,
+			target,
+			receiver,
+			f.keepRules,
+			f.retryWait,
+			false, // considerSnapAtCursorReplicated is not relevant for local pruning
+			f.promPruneSecs.WithLabelValues("local"),
+		},
+		state: Plan,
+	}
+	return p
+}
+
 //go:generate enumer -type=State
 type State int
 
 const (
 	Plan State = 1 << iota
-	PlanWait
+	PlanErr
 	Exec
-	ExecWait
-	ErrPerm
+	ExecErr
 	Done
 )
 
-func (s State) statefunc() state {
-	var statemap = map[State]state{
-		Plan:     statePlan,
-		PlanWait: statePlanWait,
-		Exec:     stateExec,
-		ExecWait: stateExecWait,
-		ErrPerm:  nil,
-		Done:     nil,
-	}
-	return statemap[s]
-}
-
-func (s State) IsTerminal() bool {
-	return s.statefunc() == nil
-}
-
-type updater func(func(*Pruner)) State
-type state func(args *args, u updater) state
+type updater func(func(*Pruner))
 
 func (p *Pruner) Prune() {
 	p.prune(p.args)
 }
 
 func (p *Pruner) prune(args args) {
-	s := p.state.statefunc()
-	for s != nil {
-		pre := p.state
-		s = s(&args, func(f func(*Pruner)) State {
-			p.mtx.Lock()
-			defer p.mtx.Unlock()
-			f(p)
-			return p.state
-		})
-		post := p.state
-		GetLogger(args.ctx).
-			WithField("transition", fmt.Sprintf("%s=>%s", pre, post)).
-			Debug("state transition")
-		if err := p.Error(); err != nil {
-			GetLogger(args.ctx).
-				WithError(p.err).
-				WithField("state", post.String()).
-				Error("entering error state after error")
-		}
+	u := func(f func(*Pruner)) {
+		p.mtx.Lock()
+		defer p.mtx.Unlock()
+		f(p)
 	}
+	// TODO support automatic retries
+	// It is advisable to merge this code with package replication/driver before
+	// That will likely require re-modelling struct fs like replication/driver.attempt,
+	// including figuring out how to resume a plan after being interrupted by network errors
+	// The non-retrying code in this package should move straight to replication/logic.
+	doOneAttempt(&args, u)
 }
 
 type Report struct {
-	State string
-	SleepUntil time.Time
-	Error string
+	State              string
+	Error              string
 	Pending, Completed []FSReport
 }
 
 type FSReport struct {
-	Filesystem string
+	Filesystem                string
 	SnapshotList, DestroyList []SnapshotReport
-	ErrorCount int
-	LastError string
+	SkipReason                FSSkipReason
+	LastError                 string
 }
 
 type SnapshotReport struct {
-	Name string
+	Name       string
 	Replicated bool
-	Date time.Time
+	Date       time.Time
 }
 
 func (p *Pruner) Report() *Report {
@@ -240,13 +239,8 @@ func (p *Pruner) Report() *Report {
 
 	r := Report{State: p.state.String()}
 
-	if p.state & (PlanWait|ExecWait) != 0 {
-		r.SleepUntil = p.sleepUntil
-	}
-	if p.state & (PlanWait|ExecWait|ErrPerm) != 0 {
-		if p.err != nil {
-			r.Error = p.err.Error()
-		}
+	if p.err != nil {
+		r.Error = p.err.Error()
 	}
 
 	if p.execQueue != nil {
@@ -262,17 +256,16 @@ func (p *Pruner) State() State {
 	return p.state
 }
 
-func (p *Pruner) Error() error {
-	p.mtx.Lock()
-	defer p.mtx.Unlock()
-	if p.state & (PlanWait|ExecWait|ErrPerm) != 0 {
-		return p.err
-	}
-	return nil
-}
-
 type fs struct {
-	path  string
+	path string
+
+	// permanent error during planning
+	planErr        error
+	planErrContext string
+
+	// if != "", the fs was skipped for planning and the field
+	// contains the reason
+	skipReason FSSkipReason
 
 	// snapshots presented by target
 	// (type snapshot)
@@ -285,8 +278,18 @@ type fs struct {
 
 	// only during Exec state, also used by execQueue
 	execErrLast error
-	execErrCount int
+}
 
+type FSSkipReason string
+
+const (
+	NotSkipped                   = ""
+	SkipPlaceholder              = "filesystem is placeholder"
+	SkipNoCorrespondenceOnSender = "filesystem has no correspondence on sender"
+)
+
+func (r FSSkipReason) NotSkipped() bool {
+	return r == NotSkipped
 }
 
 func (f *fs) Report() FSReport {
@@ -295,8 +298,14 @@ func (f *fs) Report() FSReport {
 
 	r := FSReport{}
 	r.Filesystem = f.path
-	r.ErrorCount = f.execErrCount
-	if f.execErrLast != nil {
+	r.SkipReason = f.skipReason
+	if !r.SkipReason.NotSkipped() {
+		return r
+	}
+
+	if f.planErr != nil {
+		r.LastError = f.planErr.Error()
+	} else if f.execErrLast != nil {
 		r.LastError = f.execErrLast.Error()
 	}
 
@@ -306,7 +315,7 @@ func (f *fs) Report() FSReport {
 	}
 
 	r.DestroyList = make([]SnapshotReport, len(f.destroyList))
-	for i, snap := range f.destroyList{
+	for i, snap := range f.destroyList {
 		r.DestroyList[i] = snap.(snapshot).Report()
 	}
 
@@ -335,90 +344,88 @@ func (s snapshot) Replicated() bool { return s.replicated }
 
 func (s snapshot) Date() time.Time { return s.date }
 
-type Error interface {
-	error
-	Temporary() bool
-}
-
-var _ Error = net.Error(nil)
-var _ Error = streamrpc.Error(nil)
-
-func shouldRetry(e error) bool {
-	if neterr, ok := e.(net.Error); ok {
-		return neterr.Temporary()
-	}
-	return false
-}
-
-func onErr(u updater, e error) state {
-	return u(func(p *Pruner) {
-		p.err = e
-		if !shouldRetry(e) {
-			p.state = ErrPerm
-			return
-		}
-		switch p.state {
-		case Plan:
-			p.state = PlanWait
-		case Exec:
-			p.state = ExecWait
-		default:
-			panic(p.state)
-		}
-	}).statefunc()
-}
-
-func statePlan(a *args, u updater) state {
+func doOneAttempt(a *args, u updater) {
 
 	ctx, target, receiver := a.ctx, a.target, a.receiver
-	var ka *watchdog.KeepAlive
-	u(func(pruner *Pruner) {
-		ka = &pruner.Progress
-	})
 
-	tfss, err := target.ListFilesystems(ctx)
+	sfssres, err := receiver.ListFilesystems(ctx, &pdu.ListFilesystemReq{})
 	if err != nil {
-		return onErr(u, err)
+		u(func(p *Pruner) {
+			p.state = PlanErr
+			p.err = err
+		})
+		return
+	}
+	sfss := make(map[string]*pdu.Filesystem)
+	for _, sfs := range sfssres.GetFilesystems() {
+		sfss[sfs.GetPath()] = sfs
 	}
 
+	tfssres, err := target.ListFilesystems(ctx, &pdu.ListFilesystemReq{})
+	if err != nil {
+		u(func(p *Pruner) {
+			p.state = PlanErr
+			p.err = err
+		})
+		return
+	}
+	tfss := tfssres.GetFilesystems()
+
 	pfss := make([]*fs, len(tfss))
+tfss_loop:
 	for i, tfs := range tfss {
 
 		l := GetLogger(ctx).WithField("fs", tfs.Path)
 		l.Debug("plan filesystem")
 
-
 		pfs := &fs{
-			path:  tfs.Path,
+			path: tfs.Path,
 		}
 		pfss[i] = pfs
 
-		tfsvs, err := target.ListFilesystemVersions(ctx, tfs.Path)
-		if err != nil {
-			l.WithError(err).Error("cannot list filesystem versions")
-			return onErr(u, err)
+		if tfs.GetIsPlaceholder() {
+			pfs.skipReason = SkipPlaceholder
+			l.WithField("skip_reason", pfs.skipReason).Debug("skipping filesystem")
+			continue
+		} else if sfs := sfss[tfs.GetPath()]; sfs == nil {
+			pfs.skipReason = SkipNoCorrespondenceOnSender
+			l.WithField("skip_reason", pfs.skipReason).WithField("sfs", sfs.GetPath()).Debug("skipping filesystem")
+			continue
 		}
+
+		pfsPlanErrAndLog := func(err error, message string) {
+			t := fmt.Sprintf("%T", err)
+			pfs.planErr = err
+			pfs.planErrContext = message
+			l.WithField("orig_err_type", t).WithError(err).Error(fmt.Sprintf("%s: plan error, skipping filesystem", message))
+		}
+
+		tfsvsres, err := target.ListFilesystemVersions(ctx, &pdu.ListFilesystemVersionsReq{Filesystem: tfs.Path})
+		if err != nil {
+			pfsPlanErrAndLog(err, "cannot list filesystem versions")
+			continue tfss_loop
+		}
+		tfsvs := tfsvsres.GetVersions()
 		// no progress here since we could run in a live-lock (must have used target AND receiver before progress)
 
 		pfs.snaps = make([]pruning.Snapshot, 0, len(tfsvs))
 
 		rcReq := &pdu.ReplicationCursorReq{
 			Filesystem: tfs.Path,
-			Op:         &pdu.ReplicationCursorReq_Get{
+			Op: &pdu.ReplicationCursorReq_Get{
 				Get: &pdu.ReplicationCursorReq_GetOp{},
 			},
 		}
 		rc, err := receiver.ReplicationCursor(ctx, rcReq)
 		if err != nil {
-			l.WithError(err).Error("cannot get replication cursor")
-			return onErr(u, err)
+			pfsPlanErrAndLog(err, "cannot get replication cursor bookmark")
+			continue tfss_loop
 		}
-		if rc.GetError() != "" {
-			l.WithField("reqErr", rc.GetError()).Error("cannot get replication cursor")
-			return onErr(u, err)
+		if rc.GetNotexist() {
+			err := errors.New("replication cursor bookmark does not exist (one successful replication is required before pruning works)")
+			pfsPlanErrAndLog(err, "")
+			continue tfss_loop
 		}
-		ka.MadeProgress()
-
 
 		// scan from older to newer, all snapshots older than cursor are interpreted as replicated
 		sort.Slice(tfsvs, func(i, j int) bool {
@@ -441,11 +448,9 @@ func statePlan(a *args, u updater) state {
 			}
 			creation, err := tfsv.CreationAsTime()
 			if err != nil {
-				err := fmt.Errorf("%s%s has invalid creation date: %s", tfs, tfsv.RelName(), err)
-				l.WithError(err).
-					WithField("tfsv", tfsv.RelName()).
-					Error("error with fileesystem version")
-				return onErr(u, err)
+				err := fmt.Errorf("%s: %s", tfsv.RelName(), err)
+				pfsPlanErrAndLog(err, "fs version with invalid creation date")
+				continue tfss_loop
 			}
 			// note that we cannot use CreateTXG because target and receiver could be on different pools
 			atCursor := tfsv.Guid == rc.GetGuid()
@@ -457,43 +462,61 @@ func statePlan(a *args, u updater) state {
 			})
 		}
 		if preCursor {
-			err := fmt.Errorf("replication cursor not found in prune target filesystem versions")
-			l.Error(err.Error())
-			return onErr(u, err)
+			pfsPlanErrAndLog(fmt.Errorf("replication cursor not found in prune target filesystem versions"), "")
+			continue tfss_loop
 		}
 
 		// Apply prune rules
 		pfs.destroyList = pruning.PruneSnapshots(pfs.snaps, a.rules)
-		ka.MadeProgress()
 	}
 
-	return u(func(pruner *Pruner) {
-		pruner.Progress.MadeProgress()
+	u(func(pruner *Pruner) {
 		pruner.execQueue = newExecQueue(len(pfss))
 		for _, pfs := range pfss {
 			pruner.execQueue.Put(pfs, nil, false)
 		}
 		pruner.state = Exec
-	}).statefunc()
-}
+	})
 
-func stateExec(a *args, u updater) state {
-
-	var pfs *fs
-	state := u(func(pruner *Pruner) {
-		pfs = pruner.execQueue.Pop()
+	for {
+		var pfs *fs
+		u(func(pruner *Pruner) {
+			pfs = pruner.execQueue.Pop()
+		})
 		if pfs == nil {
-			nextState := Done
-			if pruner.execQueue.HasCompletedFSWithErrors() {
-				nextState = ErrPerm
-			}
-			pruner.state = nextState
-			return
+			break
+		}
+		doOneAttemptExec(a, u, pfs)
+	}
+
+	var rep *Report
+	{
+		// must not hold lock for report
+		var pruner *Pruner
+		u(func(p *Pruner) {
+			pruner = p
+		})
+		rep = pruner.Report()
+	}
+	u(func(p *Pruner) {
+		if len(rep.Pending) > 0 {
+			panic("queue should not have pending items at this point")
+		}
+		hadErr := false
+		for _, fsr := range rep.Completed {
+			hadErr = hadErr || fsr.SkipReason.NotSkipped() && fsr.LastError != ""
+		}
+		if hadErr {
+			p.state = ExecErr
+		} else {
+			p.state = Done
 		}
 	})
-	if state != Exec {
-		return state.statefunc()
-	}
+
+}
+
+// attempts to exec pfs, puts it back into the queue with the result
+func doOneAttemptExec(a *args, u updater, pfs *fs) {
 
 	destroyList := make([]*pdu.FilesystemVersion, len(pfs.destroyList))
 	for i := range destroyList {
@@ -513,7 +536,7 @@ func stateExec(a *args, u updater) state {
 		u(func(pruner *Pruner) {
 			pruner.execQueue.Put(pfs, err, false)
 		})
-		return onErr(u, err)
+		return
 	}
 	// check if all snapshots were destroyed
 	destroyResults := make(map[string]*pdu.DestroySnapshotRes)
@@ -523,20 +546,20 @@ func stateExec(a *args, u updater) state {
 	err = nil
 	destroyFails := make([]*pdu.DestroySnapshotRes, 0)
 	for _, reqDestroy := range destroyList {
-		 res, ok := destroyResults[reqDestroy.Name]
-		 if !ok {
-		 	err = fmt.Errorf("missing destroy-result for %s", reqDestroy.RelName())
-		 	break
-		 } else if res.Error != "" {
-		 	destroyFails = append(destroyFails, res)
-		 }
+		res, ok := destroyResults[reqDestroy.Name]
+		if !ok {
+			err = fmt.Errorf("missing destroy-result for %s", reqDestroy.RelName())
+			break
+		} else if res.Error != "" {
+			destroyFails = append(destroyFails, res)
+		}
 	}
 	if err == nil && len(destroyFails) > 0 {
 		names := make([]string, len(destroyFails))
 		pairs := make([]string, len(destroyFails))
 		allSame := true
 		lastMsg := destroyFails[0].Error
-		for i := 0; i < len(destroyFails); i++{
+		for i := 0; i < len(destroyFails); i++ {
 			allSame = allSame && destroyFails[i].Error == lastMsg
 			relname := destroyFails[i].Snapshot.RelName()
 			names[i] = relname
@@ -554,31 +577,6 @@ func stateExec(a *args, u updater) state {
 	})
 	if err != nil {
 		GetLogger(a.ctx).WithError(err).Error("target could not destroy snapshots")
-		return onErr(u, err)
-	}
-
-	return u(func(pruner *Pruner) {
-		pruner.Progress.MadeProgress()
-	}).statefunc()
-}
-
-func stateExecWait(a *args, u updater) state {
-	return doWait(Exec, a, u)
-}
-
-func statePlanWait(a *args, u updater) state {
-	return doWait(Plan, a, u)
-}
-
-func doWait(goback State, a *args, u updater) state {
-	timer := time.NewTimer(a.retryWait)
-	defer timer.Stop()
-	select {
-	case <-timer.C:
-		return u(func(pruner *Pruner) {
-			pruner.state = goback
-		}).statefunc()
-	case <-a.ctx.Done():
-		return onErr(u, a.ctx.Err())
+		return
 	}
 }

daemon/pruner/pruner_queue.go

@@ -7,13 +7,13 @@ import (
 )
 
 type execQueue struct {
-	mtx sync.Mutex
+	mtx                sync.Mutex
 	pending, completed []*fs
 }
 
 func newExecQueue(cap int) *execQueue {
 	q := execQueue{
-		pending: make([]*fs, 0, cap),
+		pending:   make([]*fs, 0, cap),
 		completed: make([]*fs, 0, cap),
 	}
 	return &q
@@ -55,13 +55,10 @@ func (q *execQueue) Pop() *fs {
 	return fs
 }
 
-func(q *execQueue) Put(fs *fs, err error, done bool) {
+func (q *execQueue) Put(fs *fs, err error, done bool) {
 	fs.mtx.Lock()
 	fs.execErrLast = err
-	if err != nil {
-		fs.execErrCount++
-	}
-	if done || (err != nil && !shouldRetry(fs.execErrLast)) {
+	if done || err != nil {
 		fs.mtx.Unlock()
 		q.mtx.Lock()
 		q.completed = append(q.completed, fs)
@@ -78,12 +75,8 @@ func(q *execQueue) Put(fs *fs, err error, done bool) {
 		defer q.pending[i].mtx.Unlock()
 		q.pending[j].mtx.Lock()
 		defer q.pending[j].mtx.Unlock()
-		if q.pending[i].execErrCount != q.pending[j].execErrCount {
-			return q.pending[i].execErrCount < q.pending[j].execErrCount
-		}
 		return strings.Compare(q.pending[i].path, q.pending[j].path) == -1
 	})
 	q.mtx.Unlock()
 
-
-}
+}

daemon/pruner/pruner_test.go

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

daemon/pruner/state_enumer.go

@@ -7,19 +7,17 @@ import (
 )
 
 const (
-	_StateName_0 = "PlanPlanWait"
+	_StateName_0 = "PlanPlanErr"
 	_StateName_1 = "Exec"
-	_StateName_2 = "ExecWait"
-	_StateName_3 = "ErrPerm"
-	_StateName_4 = "Done"
+	_StateName_2 = "ExecErr"
+	_StateName_3 = "Done"
 )
 
 var (
-	_StateIndex_0 = [...]uint8{0, 4, 12}
+	_StateIndex_0 = [...]uint8{0, 4, 11}
 	_StateIndex_1 = [...]uint8{0, 4}
-	_StateIndex_2 = [...]uint8{0, 8}
-	_StateIndex_3 = [...]uint8{0, 7}
-	_StateIndex_4 = [...]uint8{0, 4}
+	_StateIndex_2 = [...]uint8{0, 7}
+	_StateIndex_3 = [...]uint8{0, 4}
 )
 
 func (i State) String() string {
@@ -33,22 +31,19 @@ func (i State) String() string {
 		return _StateName_2
 	case i == 16:
 		return _StateName_3
-	case i == 32:
-		return _StateName_4
 	default:
 		return fmt.Sprintf("State(%d)", i)
 	}
 }
 
-var _StateValues = []State{1, 2, 4, 8, 16, 32}
+var _StateValues = []State{1, 2, 4, 8, 16}
 
 var _StateNameToValueMap = map[string]State{
 	_StateName_0[0:4]:  1,
-	_StateName_0[4:12]: 2,
+	_StateName_0[4:11]: 2,
 	_StateName_1[0:4]:  4,
-	_StateName_2[0:8]:  8,
-	_StateName_3[0:7]:  16,
-	_StateName_4[0:4]:  32,
+	_StateName_2[0:7]:  8,
+	_StateName_3[0:4]:  16,
 }
 
 // StateString retrieves an enum value from the enum constants string name.

daemon/snapper/snapper.go

@@ -1,18 +1,19 @@
 package snapper
 
 import (
-	"github.com/zrepl/zrepl/config"
-	"github.com/pkg/errors"
-	"time"
 	"context"
-	"github.com/zrepl/zrepl/daemon/filters"
 	"fmt"
-	"github.com/zrepl/zrepl/zfs"
 	"sort"
-	"github.com/zrepl/zrepl/logger"
 	"sync"
-)
+	"time"
 
+	"github.com/pkg/errors"
+
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/daemon/filters"
+	"github.com/zrepl/zrepl/logger"
+	"github.com/zrepl/zrepl/zfs"
+)
 
 //go:generate stringer -type=SnapState
 type SnapState uint
@@ -28,7 +29,7 @@ type snapProgress struct {
 	state SnapState
 
 	// SnapStarted, SnapDone, SnapError
-	name string
+	name    string
 	startAt time.Time
 
 	// SnapDone
@@ -44,13 +45,13 @@ type args struct {
 	prefix         string
 	interval       time.Duration
 	fsf            *filters.DatasetMapFilter
-	snapshotsTaken chan<-struct{}
+	snapshotsTaken chan<- struct{}
 }
 
 type Snapper struct {
 	args args
 
-	mtx sync.Mutex
+	mtx   sync.Mutex
 	state State
 
 	// set in state Plan, used in Waiting
@@ -70,7 +71,8 @@ type Snapper struct {
 type State uint
 
 const (
-	SyncUp State = 1<<iota
+	SyncUp State = 1 << iota
+	SyncUpErrWait
 	Planning
 	Snapshotting
 	Waiting
@@ -80,12 +82,13 @@ const (
 
 func (s State) sf() state {
 	m := map[State]state{
-		SyncUp:       syncUp,
-		Planning:     plan,
-		Snapshotting: snapshot,
-		Waiting:      wait,
-		ErrorWait:    wait,
-		Stopped: 	   nil,
+		SyncUp:        syncUp,
+		SyncUpErrWait: wait,
+		Planning:      plan,
+		Snapshotting:  snapshot,
+		Waiting:       wait,
+		ErrorWait:     wait,
+		Stopped:       nil,
 	}
 	return m[s]
 }
@@ -121,9 +124,9 @@ func PeriodicFromConfig(g *config.Global, fsf *filters.DatasetMapFilter, in *con
 	}
 
 	args := args{
-		prefix: in.Prefix,
+		prefix:   in.Prefix,
 		interval: in.Interval,
-		fsf: fsf,
+		fsf:      fsf,
 		// ctx and log is set in Run()
 	}
 
@@ -165,7 +168,16 @@ func (s *Snapper) Run(ctx context.Context, snapshotsTaken chan<- struct{}) {
 func onErr(err error, u updater) state {
 	return u(func(s *Snapper) {
 		s.err = err
-		s.state = ErrorWait
+		preState := s.state
+		switch s.state {
+		case SyncUp:
+			s.state = SyncUpErrWait
+		case Planning:
+			fallthrough
+		case Snapshotting:
+			s.state = ErrorWait
+		}
+		s.args.log.WithError(err).WithField("pre_state", preState).WithField("post_state", s.state).Error("snapshotting error")
 	}).sf()
 }
 
@@ -177,7 +189,10 @@ func onMainCtxDone(ctx context.Context, u updater) state {
 }
 
 func syncUp(a args, u updater) state {
-	fss, err := listFSes(a.fsf)
+	u(func(snapper *Snapper) {
+		snapper.lastInvocation = time.Now()
+	})
+	fss, err := listFSes(a.ctx, a.fsf)
 	if err != nil {
 		return onErr(err, u)
 	}
@@ -185,10 +200,10 @@ func syncUp(a args, u updater) state {
 	if err != nil {
 		return onErr(err, u)
 	}
-	u(func(s *Snapper){
+	u(func(s *Snapper) {
 		s.sleepUntil = syncPoint
 	})
-	t := time.NewTimer(syncPoint.Sub(time.Now()))
+	t := time.NewTimer(time.Until(syncPoint))
 	defer t.Stop()
 	select {
 	case <-t.C:
@@ -204,7 +219,7 @@ func plan(a args, u updater) state {
 	u(func(snapper *Snapper) {
 		snapper.lastInvocation = time.Now()
 	})
-	fss, err := listFSes(a.fsf)
+	fss, err := listFSes(a.ctx, a.fsf)
 	if err != nil {
 		return onErr(err, u)
 	}
@@ -284,9 +299,15 @@ func wait(a args, u updater) state {
 		lastTick := snapper.lastInvocation
 		snapper.sleepUntil = lastTick.Add(a.interval)
 		sleepUntil = snapper.sleepUntil
+		log := a.log.WithField("sleep_until", sleepUntil).WithField("duration", a.interval)
+		logFunc := log.Debug
+		if snapper.state == ErrorWait || snapper.state == SyncUpErrWait {
+			logFunc = log.Error
+		}
+		logFunc("enter wait-state after error")
 	})
 
-	t := time.NewTimer(sleepUntil.Sub(time.Now()))
+	t := time.NewTimer(time.Until(sleepUntil))
 	defer t.Stop()
 
 	select {
@@ -299,8 +320,8 @@ func wait(a args, u updater) state {
 	}
 }
 
-func listFSes(mf *filters.DatasetMapFilter) (fss []*zfs.DatasetPath, err error) {
-	return zfs.ZFSListMapping(mf)
+func listFSes(ctx context.Context, mf *filters.DatasetMapFilter) (fss []*zfs.DatasetPath, err error) {
+	return zfs.ZFSListMapping(ctx, mf)
 }
 
 func findSyncPoint(log Logger, fss []*zfs.DatasetPath, prefix string, interval time.Duration) (syncPoint time.Time, err error) {
@@ -366,4 +387,3 @@ func findSyncPoint(log Logger, fss []*zfs.DatasetPath, prefix string, interval t
 	return snaptimes[0].time, nil
 
 }
-

daemon/snapper/snapper_all.go

@@ -3,6 +3,7 @@ package snapper
 import (
 	"context"
 	"fmt"
+
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/filters"
 )
@@ -17,7 +18,7 @@ type PeriodicOrManual struct {
 	s *Snapper
 }
 
-func (s *PeriodicOrManual) Run(ctx context.Context, wakeUpCommon chan <- struct{}) {
+func (s *PeriodicOrManual) Run(ctx context.Context, wakeUpCommon chan<- struct{}) {
 	if s.s != nil {
 		s.s.Run(ctx, wakeUpCommon)
 	}

daemon/snapper/state_string.go

@@ -5,15 +5,16 @@ package snapper
 import "strconv"
 
 const (
-	_State_name_0 = "SyncUpPlanning"
-	_State_name_1 = "Snapshotting"
-	_State_name_2 = "Waiting"
-	_State_name_3 = "ErrorWait"
-	_State_name_4 = "Stopped"
+	_State_name_0 = "SyncUpSyncUpErrWait"
+	_State_name_1 = "Planning"
+	_State_name_2 = "Snapshotting"
+	_State_name_3 = "Waiting"
+	_State_name_4 = "ErrorWait"
+	_State_name_5 = "Stopped"
 )
 
 var (
-	_State_index_0 = [...]uint8{0, 6, 14}
+	_State_index_0 = [...]uint8{0, 6, 19}
 )
 
 func (i State) String() string {
@@ -29,6 +30,8 @@ func (i State) String() string {
 		return _State_name_3
 	case i == 32:
 		return _State_name_4
+	case i == 64:
+		return _State_name_5
 	default:
 		return "State(" + strconv.FormatInt(int64(i), 10) + ")"
 	}

daemon/streamrpcconfig/streamrpcconfig.go

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

daemon/transport/connecter/connecter.go

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

daemon/transport/handshake.go

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

daemon/transport/serve/serve.go

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

daemon/transport/serve/serve_tls.go

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

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

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

dist/systemd/zrepl.service

@@ -0,0 +1,41 @@
+[Unit]
+Description=zrepl daemon
+Documentation=https://zrepl.github.io
+
+[Service]
+Type=simple
+ExecStart=/usr/local/bin/zrepl --config /etc/zrepl/zrepl.yml daemon
+RuntimeDirectory=zrepl
+RuntimeDirectoryMode=0700
+
+ProtectSystem=strict
+#PrivateDevices=yes # TODO ZFS needs access to /dev/zfs, could we limit this?
+ProtectKernelTunables=yes
+ProtectControlGroups=yes
+PrivateTmp=yes
+#PrivateUsers=yes # TODO Does not work, why?
+ProtectKernelModules=true
+RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
+RestrictNamespaces=true
+RestrictRealtime=yes
+SystemCallArchitectures=native
+
+# BEGIN ProtectHome
+ProtectHome=read-only   # DEBIAN STRETCH
+# ProtectHome=tmpfs     # FEDORA 28 / 29
+# END ProtectHome
+
+# BEGIN SystemCallFilter
+## BEGIN DEBIAN STRETCH
+SystemCallFilter=~ @mount @cpu-emulation @keyring @module @obsolete @privileged @raw-io @debug @clock @resources
+## END DEBIAN STRETCH
+## BEGIN FEDORA 28/29 
+## Syscall blacklist (should be fairly stable)
+#SystemCallFilter=~ @mount @aio @cpu-emulation @keyring @memlock @module @obsolete @privileged @raw-io @reboot @setuid @swap @sync @timer @debug @clock @chown @resources
+## Syscall whitelist (not sure how stable)
+#SystemCallFilter=@default @file-system @process @basic-io @ipc @network-io @signal @io-event brk mprotect sched_getaffinity ioctl getrandom
+## END END FEDORA 28/29
+# END SystemCallFilter
+
+[Install]
+WantedBy=multi-user.target

docs/changelog.rst

@@ -3,6 +3,7 @@
 .. |bugfix| replace:: [BUG]
 .. |docs| replace:: [DOCS]
 .. |feature| replace:: [FEATURE]
+.. |mig| replace:: **[MIGRATION]**
 
 .. _changelog:
 
@@ -19,6 +20,7 @@ We use the following annotations for classifying changes:
 * |break| Change that breaks interoperability or persistent state representation with previous releases.
   As a package maintainer, make sure to warn your users about config breakage somehow.
   Note that even updating the package on both sides might not be sufficient, e.g. if persistent state needs to be migrated to a new format.
+* |mig| Migration that must be run by the user.
 * |feature| Change that introduces new functionality.
 * |bugfix| Change that fixes a bug, no regressions or incompatibilities expected.
 * |docs| Change to the documentation.
@@ -40,6 +42,7 @@ It breaks both configuration and transport format, and thus requires manual inte
 Notes to Package Maintainers
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
+* Notify users about config changes and migrations (see changes attributed with |break| and |mig| below)
 * If the daemon crashes, the stack trace produced by the Go runtime and possibly diagnostic output of zrepl will be written to stderr.
   This behavior is independent from the ``stdout`` outlet type.
   Please make sure the stderr output of the daemon is captured somewhere.
@@ -48,26 +51,43 @@ Notes to Package Maintainers
   This functionality will cause SIGABRT on panics and can be used to capture a coredump of the panicking process.
   To that extend, make sure that your package build system, your OS's coredump collection and the Go delve debugger work together.
   Use your build system to package the Go program in `this tutorial on Go coredumps and the delve debugger <https://rakyll.org/coredumps/>`_ , and make sure the symbol resolution etc. work on coredumps captured from the binary produced by your build system. (Special focus on symbol stripping, etc.)
-* Use of ``ssh+stdinserver`` :ref:`transport <transport-ssh+stdinserver>` is no longer encouraged.
-  Please encourage users to use the new ``tcp`` or ``tls`` transports.
-  You might as well mention some of the :ref:`tunneling options listed here <transport-tcp-tunneling>`.
+* Consider using the ``zrepl configcheck`` subcommand in startup scripts to abort a restart that would fail due to an invalid config.
 
 Changes
 ~~~~~~~
 
+* |break| |mig| Placeholder property representation changed
+
+  * The :ref:`placeholder property <replication-placeholder-property>` now uses ``on|off`` as values
+    instead of hashes of the dataset path. This permits renames of the sink filesystem without
+    updating all placeholder properties.
+  * Relevant for 0.0.X-0.1-rc* to 0.1 migrations
+  * Make sure your config is valid with ``zrepl configcheck``
+  * Run ``zrepl migrate 0.0.X:0.1:placeholder``
+
 * |feature| :issue:`55` : Push replication (see :ref:`push job <job-push>` and :ref:`sink job <job-sink>`)
 * |feature| :ref:`TCP Transport <transport-tcp>`
 * |feature| :ref:`TCP + TLS client authentication transport <transport-tcp+tlsclientauth>`
-* |feature| :issue:`78` :commit:`074f989` : Replication protocol rewrite
+* |feature| :issue:`111`: RPC protocol rewrite
 
-  * Uses ``github.com/problame/go-streamrpc`` for RPC layer
-  * |break| Protocol breakage, update and restart of all zrepl daemons is required
-  * |feature| :issue:`83`:  Improved error handling of network-level errors (zrepl retries instead of failing the entire job)
-  * |bugfix| :issue:`75` :issue:`81`: use connection timeouts and protocol-level heartbeats
-  * |break| |break_config|: mappings are no longer supported
+  * |break| Protocol breakage; Update and restart of all zrepl daemons is required.
+  * Use `gRPC <https://grpc.io/>`_ for control RPCs and a custom protocol for bulk data transfer.
+  * Automatic retries for network-temporary errors
 
-    * Receiving sides (``pull`` and ``sink`` job) specify a single ``root_fs``.
-      Received filesystems are then stored *per client* in ``${root_fs}/${client_identity}``.
+    * Limited to errors during replication for this release.
+      Addresses the common problem of ISP-forced reconnection at night, but will become
+      way more useful with resumable send & recv support.
+      Pruning errors are handled per FS, i.e., a prune RPC is attempted at least once per FS.
+
+* |feature| Proper timeout handling for the :ref:`SSH transport <transport-ssh+stdinserver>`
+
+  * |break| Requires Go 1.11 or later.
+  
+* |break| |break_config|: mappings are no longer supported
+
+  * Receiving sides (``pull`` and ``sink`` job) specify a single ``root_fs``.
+    Received filesystems are then stored *per client* in ``${root_fs}/${client_identity}``.
+    See :ref:`job-overview` for details.
 
 * |feature| |break| |break_config| Manual snapshotting + triggering of replication
 
@@ -92,12 +112,18 @@ Changes
     * |break_config| ``keep_bookmarks`` parameter of the ``grid`` keep rule has been removed
 
 * |feature| ``zrepl status`` for live-updating replication progress (it's really cool!)
+* |feature| :ref:`Snapshot- & pruning-only job type <job-snap>` (for local snapshot management)
 * |feature| :issue:`67`: Expose `Prometheus <https://prometheus.io>`_ metrics via HTTP (:ref:`config docs <monitoring-prometheus>`)
 
+  * Compatible Grafana dashboard shipping in ``dist/grafana``
+
 * |break_config| Logging outlet types must be specified using the ``type`` instead of ``outlet`` key
 * |break| :issue:`53`: CLI: ``zrepl control *`` subcommands have been made direct subcommands of ``zrepl *``
 * |bugfix| Goroutine leak on ssh transport connection timeouts
 * |bugfix| :issue:`81` :issue:`77` : handle failed accepts correctly (``source`` job)
+* |bugfix| :issue:`100`: fix incompatibility with ZoL 0.8
+* |feature| :issue:`115`: logging: configurable syslog facility
+* |feature| Systemd unit file in ``dist/systemd``
 
 .. |lastrelease| replace:: 0.0.3
 
@@ -107,8 +133,3 @@ Previous Releases
 .. NOTE::
     Due to limitations in our documentation system, we only show the changelog since the last release and the time this documentation is built.
     For the changelog of previous releases, use the version selection in the hosted version of these docs at `zrepl.github.io <https://zrepl.github.io>`_.
-    
-    
-
-
-W

docs/configuration/jobs.rst

@@ -11,10 +11,12 @@
 Job Types & Replication
 =======================
 
+.. _job-overview:
+
 Overview & Terminology
 ----------------------
 
-A *job* is the unit of activity tracked by the zrepl daemon and configured in the |mainconfig|.
+A *job* is the unit of activity tracked by the zrepl daemon.
 Every job has a unique ``name``, a ``type`` and type-dependent fields which are documented on this page.
 
 Replication always happens between a pair of jobs: one is the **active side**, and one the **passive side**.
@@ -23,18 +25,22 @@ For communication, the active side connects to the passive side using a :ref:`tr
 
 The following table shows how different job types can be combined to achieve both push and pull mode setups:
 
-+-----------------------+--------------+----------------------------------+-----------------------------------------------+
-| Setup name            | active side  | passive side                     | use case                                      |
-+=======================+==============+==================================+===============================================+
-| Push mode             | ``push``     | ``sink``                         | * Laptop backup                               |
-|                       |              |                                  | * NAS behind NAT to offsite                   |
-+-----------------------+--------------+----------------------------------+-----------------------------------------------+
-| Pull mode             | ``pull``     | ``source``                       | * Central backup-server for many nodes        |
-|                       |              |                                  | * Remote server to NAS behind NAT             |
-+-----------------------+--------------+----------------------------------+-----------------------------------------------+
-| Local replication     | | ``push`` + ``sink`` in one config             | * Backup FreeBSD boot pool                    |
-|                       | | with :ref:`local transport <transport-local>` |                                               |
-+-----------------------+--------------+----------------------------------+-----------------------------------------------+
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+| Setup name            | active side  | passive side                     | use case                                                                           |
++=======================+==============+==================================+====================================================================================+
+| Push mode             | ``push``     | ``sink``                         | * Laptop backup                                                                    |
+|                       |              |                                  | * NAS behind NAT to offsite                                                        |
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+| Pull mode             | ``pull``     | ``source``                       | * Central backup-server for many nodes                                             |
+|                       |              |                                  | * Remote server to NAS behind NAT                                                  |
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+| Local replication     | | ``push`` + ``sink`` in one config             | * Backup FreeBSD boot pool                                                         |
+|                       | | with :ref:`local transport <transport-local>` |                                                                                    |
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
+| Snap & prune-only     | ``snap``     | N/A                              | * | Snapshots & pruning but no replication                                         |
+|                       |              |                                  |   | required                                                                       |
+|                       |              |                                  | * Workaround for :ref:`source-side pruning <prune-workaround-source-side-pruning>` |
++-----------------------+--------------+----------------------------------+------------------------------------------------------------------------------------+
 
 How the Active Side Works
 ~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -57,7 +63,7 @@ using the transport listener type specified in the ``serve`` field of the job co
 Each transport listener provides a client's identity to the passive side job.
 It uses the client identity for access control:
 
-* The ``sink`` job only allows pushes to those ZFS filesystems to the active side that are located below ``root_fs/${client_identity}``.
+* The ``sink`` job maps requests from different client identities to their respective sub-filesystem tree ``root_fs/${client_identity}``.
 * The ``source`` job has a whitelist of client identities that are allowed pull access.
 
 .. TIP::
@@ -91,7 +97,8 @@ The following steps take place during replication and can be monitored using the
 
   * Perform replication steps in the following order:
     Among all filesystems with pending replication steps, pick the filesystem whose next replication step's snapshot is the oldest.
-  * After a successful replication step, update the replication cursor bookmark (see below)
+  * Create placeholder filesystems on the receiving side to mirror the dataset paths on the sender to ``root_fs/${client_identity}``.
+  * After a successful replication step, update the replication cursor bookmark (see below).
    
 The idea behind the execution order of replication steps is that if the sender snapshots all filesystems simultaneously at fixed intervals, the receiver will have all filesystems snapshotted at time ``T1`` before the first snapshot at ``T2 = T1 + $interval`` is replicated.
 
@@ -101,6 +108,17 @@ The **replication cursor bookmark** ``#zrepl_replication_cursor`` is kept per fi
 It is a bookmark of the most recent successfully replicated snapshot to the receiving side.
 It is is used by the :ref:`not_replicated <prune-keep-not-replicated>` keep rule to identify all snapshots that have not yet been replicated to the receiving side.
 Regardless of whether that keep rule is used, the bookmark ensures that replication can always continue incrementally.
+Note that there is only one cursor bookmark per filesystem, which prohibits multiple jobs to replicate the same filesystem (:ref:`see below<jobs-multiple-jobs>`).
+
+.. _replication-placeholder-property:
+
+**Placeholder filesystems** on the receiving side are regular ZFS filesystems with the placeholder property ``zrepl:placeholder=on``.
+Placeholders allow the receiving side to mirror the sender's ZFS dataset hierachy without replicating every filesystem at every intermediary dataset path component.
+Consider the following example: ``S/H/J`` shall be replicated to ``R/sink/job/S/H/J``, but neither ``S/H`` nor ``S`` shall be replicated.
+ZFS requires the existence of ``R/sink/job/S`` and ``R/sink/job/S/H`` in order to receive into ``R/sink/job/S/H/J``.
+Thus, zrepl creates the parent filesystems as placeholders on the receiving side.
+If at some point ``S/H`` and ``S`` shall be replicated, the receiving side invalidates the placeholder flag automatically.
+The ``zrepl test placeholder`` command can be used to check whether a filesystem is a placeholder.
 
 .. ATTENTION::
 
@@ -114,7 +132,7 @@ Regardless of whether that keep rule is used, the bookmark ensures that replicat
 Taking Snaphots
 ---------------
 
-The ``push`` and ``source`` jobs can automatically take periodic snapshots of the filesystems matched by the ``filesystems`` filter field.
+The ``push``, ``source`` and ``snap`` jobs can automatically take periodic snapshots of the filesystems matched by the ``filesystems`` filter field.
 The snapshot names are composed of a user-defined prefix followed by a UTC date formatted like ``20060102_150405_000``.
 We use UTC because it will avoid name conflicts when switching time zones or between summer and winter time.
 
@@ -136,9 +154,10 @@ For ``push`` jobs, replication is automatically triggered after all filesystems
 
 There is also a ``manual`` snapshotting type, which covers the following use cases:
 
-* Existing infrastructure for automatic snapshots: you only want to use zrepl for replication.
+* Existing infrastructure for automatic snapshots: you only want to use this zrepl job for replication.
 * Run scripts before and after taking snapshots (like locking database tables).
   We are working on better integration for this use case: see :issue:`74`.
+* Handling snapshotting through a separate ``snap`` job.
 
 Note that you will have to trigger replication manually using the ``zrepl signal wakeup JOB`` subcommand in that case.
 
@@ -154,6 +173,50 @@ Note that you will have to trigger replication manually using the ``zrepl signal
        type: manual
      ...
 
+.. _jobs-multiple-jobs:
+
+Multiple Jobs & More than 2 Machines
+------------------------------------
+
+.. ATTENTION::
+
+  When using multiple jobs across single or multiple machines, the following rules are critical to avoid race conditions & data loss:
+
+  1. The sets of ZFS filesystems matched by the ``filesystems`` filter fields must be disjoint across all jobs configured on a machine.
+  2. The ZFS filesystem subtrees of jobs with ``root_fs`` must be disjoint.
+  3. Across all zrepl instances on all machines in the replication domain, there must be a 1:1 correspondence between active and passive jobs.
+
+  Explanations & exceptions to above rules are detailed below.
+
+If you would like to see improvements to multi-job setups, please `open an issue on GitHub <https://github.com/zrepl/zrepl/issues/new>`_.
+
+No Overlapping
+~~~~~~~~~~~~~~
+
+Jobs run independently of each other.
+If two jobs match the same filesystem with their ``filesystems`` filter, they will operate on that filesystem independently and potentially in parallel.
+For example, if job A prunes snapshots that job B is planning to replicate, the replication will fail because B asssumed the snapshot to still be present.
+More subtle race conditions can occur with the :ref:`replication cursor bookmark <replication-cursor-bookmark>`, which currently only exists once per filesystem.
+
+N push jobs to 1 sink
+~~~~~~~~~~~~~~~~~~~~~
+
+The :ref:`sink job <job-sink>` namespaces by client identity.
+It is thus safe to push to one sink job with different client identities.
+If the push jobs have the same client identity, the filesystems matched by the push jobs must be disjoint to avoid races.
+
+N pull jobs from 1 source
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Multiple pull jobs pulling from the same source have potential for race conditions during pruning:
+each pull job prunes the source side independently, causing replication-prune and prune-prune races.
+
+There is currently no way for a pull job to filter which snapshots it should attempt to replicate.
+Thus, it is not possibe to just manually assert that the prune rules of all pull jobs are disjoint to avoid replication-prune and prune-prune races.
+
+
+------------------------------------------------------------------------------
+
 
 .. _job-push:
 
@@ -199,8 +262,8 @@ Job Type ``sink``
     * - ``serve``
       - |serve-transport|
     * - ``root_fs``
-      - ZFS dataset path are received to
-        ``$root_fs/$client_identity``
+      - ZFS filesystems are received to
+        ``$root_fs/$client_identity/$source_path``
 
 Example config: :sampleconf:`/sink.yml`
 
@@ -222,10 +285,11 @@ Job Type ``pull``
     * - ``connect``
       - |connect-transport|
     * - ``root_fs``
-      - ZFS dataset path are received to
-        ``$root_fs/$client_identity``
+      - ZFS filesystems are received to
+        ``$root_fs/$source_path``
     * - ``interval``
-      - Interval at which to pull from the source job
+      - | Interval at which to pull from the source job (e.g. ``10m``).
+        | ``manual`` disables periodic pulling, replication then only happens on :ref:`wakeup <cli-signal-wakeup>`.
     * - ``pruning``
       - |pruning-spec|
 
@@ -255,6 +319,7 @@ Job Type ``source``
 
 Example config: :sampleconf:`/source.yml`
 
+
 .. _replication-local:
 
 Local replication
@@ -265,3 +330,28 @@ If you have the need for local replication (most likely between two local storag
 Example config: :sampleconf:`/local.yml`.
 
 
+.. _job-snap:
+
+Job Type ``snap`` (snapshot & prune only)
+-----------------------------------------
+
+Job type that only takes snapshots and performs pruning on the local machine.
+
+.. list-table::
+    :widths: 20 80
+    :header-rows: 1
+
+    * - Parameter
+      - Comment
+    * - ``type``
+      - = ``snap``
+    * - ``name``
+      - unique name of the job
+    * - ``filesystems``
+      - |filter-spec| for filesystems to be snapshotted
+    * - ``snapshotting``
+      - |snapshotting-spec|
+    * - ``pruning``
+      - |pruning-spec|
+
+Example config: :sampleconf:`/snap.yml`

docs/configuration/logging.rst

@@ -7,7 +7,7 @@ Logging
 
 zrepl uses structured logging to provide users with easily processable log messages.
 
-Logging outlets are configured in the ``global`` section of the |mainconfig|.
+Logging outlets are configured in the ``global`` section of the config file.
 
 ::
 
@@ -147,6 +147,8 @@ Can only be specified once.
       -  minimum  :ref:`log level <logging-levels>`
     * - ``format``
       - output :ref:`format <logging-formats>`
+    * - ``facility``
+      - Which syslog facility to use (default = ``local0``)
     * - ``retry_interval``
       - Interval between reconnection attempts to syslog (default = 0)
 

docs/configuration/monitoring.rst

@@ -5,18 +5,24 @@
 Monitoring
 ==========
 
-Monitoring endpoints are configured in the ``global.monitoring`` section of the |mainconfig|.
+Monitoring endpoints are configured in the ``global.monitoring`` section of the config file.
 
 .. _monitoring-prometheus:
 
-Prometheus
-----------
+Prometheus & Grafana
+--------------------
 
 zrepl can expose `Prometheus metrics <https://prometheus.io/docs/instrumenting/exposition_formats/>`_ via HTTP.
 The ``listen`` attribute is a `net.Listen <https://golang.org/pkg/net/#Listen>`_  string for tcp, e.g. ``:9091`` or ``127.0.0.1:9091``.
-
 The Prometheues monitoring job appears in the ``zrepl control`` job list and may be specified **at most once**.
-At the time of writing, there is no stability guarantee on the exported metrics.
+
+zrepl also ships with an importable `Grafana <https://grafana.com>`_ dashboard that consumes the Prometheus metrics:
+see :repomasterlink:`dist/grafana`.
+The dashboard also contains some advice on which metrics are important to monitor.
+
+.. NOTE::
+
+  At the time of writing, there is no stability guarantee on the exported metrics.
 
 ::
 

docs/configuration/prune.rst

@@ -10,10 +10,12 @@ Typically, the requirements to temporal resolution and maximum retention time di
 For example, when using zrepl to back up a busy database server, you will want high temporal resolution (snapshots every 10 min) for the last 24h in case of administrative disasters, but cannot afford to store them for much longer because you might have high turnover volume in the database.
 On the receiving side, you may have more disk space available, or need to comply with other backup retention policies.
 
-zrepl uses a set of  **keep rules** to determine which snapshots shall be kept per filesystem.
+zrepl uses a set of  **keep rules** per sending and receiving side to determine which snapshots shall be kept per filesystem.
 **A snapshot that is not kept by any rule is destroyed.**
 The keep rules are **evaluated on the active side** (:ref:`push <job-push>` or :ref:`pull job <job-pull>`) of the replication setup, for both active and passive side, after replication completed or was determined to have failed permanently.
 
+
+
 Example Configuration:
 
 ::
@@ -49,18 +51,10 @@ Example Configuration:
     You might have **existing snapshots** of filesystems affected by pruning which you want to keep, i.e. not be destroyed by zrepl.
     Make sure to actually add the necessary ``regex`` keep rules on both sides, like with ``manual`` in the example above.
 
-.. ATTENTION::
-
-    It is currently not possible to define pruning on a source job.
-    The source job creates snapshots, which means that extended replication downtime will fill up the source's zpool with snapshots, since pruning is directed by the corresponding active side (pull job).
-    If this is a potential risk for you, consider using :ref:`push mode <job-push>`.
-
-
 .. _prune-keep-not-replicated:
 
 Policy ``not_replicated``
 -------------------------
-
 ::
 
    jobs:
@@ -146,12 +140,75 @@ Policy ``regex``
      - type: push
        pruning:
          keep_receiver:
+         # keep all snapshots with prefix zrepl_ or manual_
          - type: regex
            regex: "^(zrepl|manual)_.*"
-    ...
+
+     - type: push
+       snapshotting:
+         prefix: zrepl_
+       pruning:
+         keep_sender:
+         # keep all snapshots that were not created by zrepl
+         - type: regex
+           negate: true
+           regex: "^zrepl_.*"
 
 ``regex`` keeps all snapshots whose names are matched by the regular expressionin ``regex``.
 Like all other regular expression fields in prune policies, zrepl uses Go's `regexp.Regexp <https://golang.org/pkg/regexp/#Compile>`_ Perl-compatible regular expressions (`Syntax <https://golang.org/pkg/regexp/syntax>`_).
+The optional `negate` boolean field inverts the semantics: Use it if you want to keep all snapshots that *do not* match the given regex.
 
+.. _prune-workaround-source-side-pruning:
 
+Source-side snapshot pruning
+----------------------------
 
+A :ref:`source jobs<job-source>` takes snapshots on the system it runs on.
+The corresponding :ref:`pull job <job-pull>` on the replication target connects to the source job and replicates the snapshots.
+Afterwards, the pull job coordinates pruning on both sender (the source job side) and receiver (the pull job side).
+
+There is no built-in way to define and execute pruning on the source side independently of the pull side.
+The source job will continue taking snapshots which will not be pruned until the pull side connects.
+This means that **extended replication downtime will fill up the source's zpool with snapshots**.
+
+If the above is a conceivable situation for you, consider using :ref:`push mode <job-push>`, where pruning happens on the same side where snapshots are taken.
+
+Workaround using ``snap`` job
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As a workaround (see GitHub :issue:`102` for development progress), a pruning-only :ref:`snap job <job-snap>` can be defined on the source side:
+The snap job is in charge of snapshot creation & destruction, whereas the source job's role is reduced to just serving snapshots.
+However, since, jobs are run independently, it is possible that the snap job will prune snapshots that are queued for replication / destruction by the remote pull job that connects to the source job.
+Symptoms of such race conditions are spurious replication and destroy errors.
+
+Example configuration:
+
+::
+
+  # source side
+  jobs:
+  - type: snap
+    snapshotting:
+      type: periodic
+    pruning:
+      keep:
+        # source side pruning rules go here
+    ...
+
+  - type: source
+    snapshotting:
+      type: manual
+    root_fs: ...
+
+  # pull side
+  jobs:
+  - type: pull
+    pruning:
+      keep_sender:
+        # let the source-side snap job do the pruning
+        - type: regex
+          regex: ".*"
+        ...
+      keep_receiver:
+        # feel free to prune on the pull side as desired
+        ...

docs/configuration/transports.rst

@@ -76,6 +76,7 @@ Connect
 
 The ``tls`` transport uses TCP + TLS with client authentication using client certificates.
 The client identity is the common name (CN) presented in the client certificate.
+
 It is recommended to set up a dedicated CA infrastructure for this transport, e.g. using OpenVPN's `EasyRSA <https://github.com/OpenVPN/easy-rsa>`_.
 For a simple 2-machine setup, see the :ref:`instructions below<transport-tcp+tlsclientauth-2machineopenssl>`.
 
@@ -85,6 +86,10 @@ Since Go binaries are statically linked, you or your distribution need to recomp
 All file paths are resolved relative to the zrepl daemon's working directory.
 Specify absolute paths if you are unsure what directory that is (or find out from your init system).
 
+If intermediate CAs are used, the **full chain** must be present in either in the ``ca`` file or the individual ``cert`` files.
+Regardless, the client's certificate must be first in the ``cert`` file, with each following certificate directly certifying the one preceding it (see `TLS's specification <https://tools.ietf.org/html/rfc5246#section-7.4.2>`_).
+This is the common default when using a CA management tool.
+
 Serve
 ~~~~~
 
@@ -96,9 +101,9 @@ Serve
         serve:
           type: tls
           listen: ":8888"
-          ca: /etc/zrepl/ca.crt
-          cert: /etc/zrepl/prod.crt
-          key: /etc/zrepl/prod.key
+          ca:   /etc/zrepl/ca.crt
+          cert: /etc/zrepl/prod.fullchain
+          key:  /etc/zrepl/prod.key
           client_cns:
             - "laptop1"
             - "homeserver"
@@ -116,8 +121,8 @@ Connect
       connect:
         type: tls
         address: "server1.foo.bar:8888"
-        ca: /etc/zrepl/ca.crt
-        cert: /etc/zrepl/backupserver.crt
+        ca:   /etc/zrepl/ca.crt
+        cert: /etc/zrepl/backupserver.fullchain
         key:  /etc/zrepl/backupserver.key
         server_cn: "server1"
         dial_timeout: # optional, default 10s
@@ -201,13 +206,17 @@ The serve & connect configuration will thus look like the following:
 ``ssh+stdinserver`` Transport
 -----------------------------
 
-``ssh+stdinserver`` is inspired by `git shell <https://git-scm.com/docs/git-shell>`_ and `Borg Backup <https://borgbackup.readthedocs.io/en/stable/deployment.html>`_.
-It is provided by the Go package ``github.com/problame/go-netssh``.
+``ssh+stdinserver`` uses the ``ssh`` command and some features of the server-side SSH ``authorized_keys`` file.
+It is less efficient than other transports because the data passes through two more pipes.
+However, it is fairly convenient to set up and allows the zrepl daemon to not be directly exposed to the internet, because all traffic passes through the system's SSH server.
 
-.. ATTENTION::
+The concept is inspired by `git shell <https://git-scm.com/docs/git-shell>`_ and `Borg Backup <https://borgbackup.readthedocs.io/en/stable/deployment.html>`_.
+The implementation is provided by the Go package ``github.com/problame/go-netssh``.
 
-   ``ssh+stdinserver`` has inferior error detection and handling compared to the ``tcp`` and ``tls`` transports.
-   If you require tested timeout & retry handling, use ``tcp`` or ``tls`` transports, or help improve package go-netssh.
+.. NOTE::
+
+   ``ssh+stdinserver`` generally provides inferior error detection and handling compared to the ``tcp`` and ``tls`` transports.
+   When encountering such problems, consider using  ``tcp`` or ``tls`` transports, or help improve package go-netssh.
 
 .. _transport-ssh+stdinserver-serve:
 

docs/global.rst.inc

@@ -1,3 +1,4 @@
 .. global list of substitutions
 
-.. |mainconfig| replace:: :ref:`main configuration file <mainconfigfile>`
+.. 
+  .. |macroname| replace:: macro expansion

docs/index.rst

@@ -5,6 +5,22 @@
 
 .. include:: global.rst.inc
 
+|GitHub license| |Language: Go| |User Docs| |Donate via PayPal| |Donate
+via Liberapay| |Twitter|
+
+.. |GitHub license| image:: https://img.shields.io/github/license/zrepl/zrepl.svg
+   :target: https://github.com/zrepl/zrepl/blob/master/LICENSE
+.. |Language: Go| image:: https://img.shields.io/badge/language-Go-6ad7e5.svg
+   :target: https://golang.org/
+.. |User Docs| image:: https://img.shields.io/badge/docs-web-blue.svg
+   :target: https://zrepl.github.io
+.. |Donate via PayPal| image:: https://img.shields.io/badge/donate-paypal-yellow.svg
+   :target: https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96
+.. |Donate via Liberapay| image:: https://img.shields.io/badge/donate-liberapay-yellow.svg
+   :target: https://liberapay.com/zrepl/donate
+.. |Twitter| image:: https://img.shields.io/twitter/url/https/github.com/zrepl/zrepl.svg?style=social
+   :target: https://twitter.com/intent/tweet?text=Wow:&url=https%3A%2F%2Fgithub.com%2Fzrepl%2Fzrepl
+
 zrepl - ZFS replication
 -----------------------
 
@@ -12,12 +28,32 @@ zrepl - ZFS replication
 
 .. raw:: html
 
-   <div style="margin-bottom: 1em; background: #2e3436; min-height: 6em; max-width: 100%">
-     <a href="https://raw.githubusercontent.com/wiki/zrepl/zrepl/zrepl_0.1_status.mp4" target="_new" >
-       <video title="zrepl status subcommand" loop autoplay style="width: 100%; display: block;" src="https://raw.githubusercontent.com/wiki/zrepl/zrepl/zrepl_0.1_status.mp4"></video>
-     </a>
+   <div style="margin-bottom: 1em; background: #2e3436; color: white; font-size: 0.8em; min-height: 6em; max-width: 100%; overflow: auto;">
+     <pre>
+     Job: prod_to_backups
+     Type: push
+     Replication:
+         Attempt #1
+         Status: fan-out-filesystems
+         Progress: [=========================\----] 246.7 MiB / 264.7 MiB @ 11.5 MiB/s
+           zroot              STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
+           zroot/ROOT         DONE (step 2/2, 1.2 KiB/1.2 KiB)
+           zroot/ROOT/default STEPPING (step 1/2, 123.4 MiB/129.3 MiB) next: @a => @b
+           zroot/tmp          STEPPING (step 1/2, 29.9 KiB/44.2 KiB) next: @a => @b
+           zroot/usr          STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
+           zroot/usr/home     STEPPING (step 1/2, 123.3 MiB/135.3 MiB) next: @a => @b
+           zroot/var          STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
+           zroot/var/audit    DONE (step 2/2, 1.2 KiB/1.2 KiB)
+           zroot/var/crash    DONE (step 2/2, 1.2 KiB/1.2 KiB)
+           zroot/var/log      STEPPING (step 1/2, 22.0 KiB/29.2 KiB) next: @a => @b
+           zroot/var/mail     STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
+     Pruning Sender:
+         ...
+     Pruning Receiver:
+     </pre>
    </div>
 
+
 Getting started
 ~~~~~~~~~~~~~~~
 
@@ -33,6 +69,7 @@ Main Features
 
   * Advanced replication features
 
+    * [x] Automatic retries for temporary network errors
     * [ ] Resumable send & receive
     * [ ] Compressed send & receive
     * [ ] Raw encrypted send & receive
@@ -77,7 +114,8 @@ We are happy about any help we can get!
   * These docs live in the ``docs/`` subdirectory
 
 * Document any non-obvious / confusing / plain broken behavior you encounter when setting up zrepl for the first time
-* Check the *Issues* and *Projects* sections for things to do
+* Check the *Issues* and *Projects* sections for things to do.
+  The `good first issues <https://github.com/zrepl/zrepl/labels/good%20first%20issue>`_ and `docs <https://github.com/zrepl/zrepl/labels/docs>`_ are suitable starting points.
 
 .. admonition:: Development Workflow
     :class: note

docs/installation.rst

@@ -66,18 +66,20 @@ Alternatively, you can install build dependencies on your local system and then
     mkdir -p "${GOPATH}/src/github.com/zrepl/zrepl"
     git clone https://github.com/zrepl/zrepl.git "${GOPATH}/src/github.com/zrepl/zrepl"
     cd "${GOPATH}/src/github.com/zrepl/zrepl"
+    python3 -m venv3
+    source venv3/bin/activate
     ./lazy.sh devsetup
     make vendordeps release
 
-Build results are located in the ``artifacts/`` directory.
+The Python venv is used for the documentation build dependencies.
+If you just want to build the zrepl binary, leave it out and use `./lazy.sh godep` instead.
+Either way, all build results are located in the ``artifacts/`` directory.
 
 .. NOTE::
 
     It is your job to install the apropriate binary in the zrepl users's ``$PATH``, e.g. ``/usr/local/bin/zrepl``.
     Otherwise, the examples in the :ref:`tutorial` may need to be adjusted.
 
-.. _mainconfigfile:
-
 What next?
 ----------
 

docs/publish.sh

@@ -54,6 +54,9 @@ echo "building site"
 set -e
 sphinx-versioning build \
    --show-banner \
+   --whitelist-branches '^master$' \
+   --whitelist-tags '(v)?\d+\.\d+\.\d+$' \
+   --whitelist-tags '(v)?0.1.0-rc(3|4)$' \
    docs ./public_git \
    -- -c sphinxconf # older conf.py throw errors because they used
                     # version = subprocess.show_output(["git", "describe"])

docs/requirements.txt

@@ -1,28 +1,20 @@
-Babel==2.5.1
-certifi==2017.11.5
+alabaster==0.7.12
+Babel==2.6.0
+certifi==2018.10.15
 chardet==3.0.4
-click==6.7
-colorclass==2.2.0
-cryptography==1.7.1
 docutils==0.14
-idna==2.6
-imagesize==0.7.1
+idna==2.7
+imagesize==1.1.0
 Jinja2==2.10
-keyring==10.1
-keyrings.alt==1.3
-MarkupSafe==1.0
-pyasn1==0.1.9
-pycrypto==2.6.1
+MarkupSafe==1.1.0
+packaging==18.0
 Pygments==2.2.0
-pygobject==3.22.0
-pytz==2017.3
-pyxdg==0.25
-requests==2.18.4
-SecretStorage==2.3.1
-six==1.10.0
+pyparsing==2.3.0
+pytz==2018.7
+requests==2.20.1
+six==1.11.0
 snowballstemmer==1.2.1
-Sphinx==1.6.5
-sphinx-rtd-theme==0.2.4
-sphinxcontrib-versioning==2.2.1
-sphinxcontrib-websupport==1.0.1
-urllib3==1.22
+Sphinx==1.8.2
+sphinx-rtd-theme==0.4.2
+sphinxcontrib-websupport==1.1.0
+urllib3==1.24.1

docs/sphinxconf/conf.py

@@ -35,6 +35,8 @@ extensions = ['sphinx.ext.todo',
     'sphinx.ext.githubpages',
     'sphinx.ext.extlinks']
 
+suppress_warnings = ['image.nonlocal_uri']
+
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['../_templates']
 
@@ -49,7 +51,7 @@ master_doc = 'index'
 
 # General information about the project.
 project = 'zrepl'
-copyright = '2017-2018, Christian Schwarz'
+copyright = '2017-2019, Christian Schwarz'
 author = 'Christian Schwarz'
 
 # The version info for the project you're documenting, acts as replacement for
@@ -173,6 +175,7 @@ texinfo_documents = [
 # http://www.sphinx-doc.org/en/stable/ext/extlinks.html
 extlinks = {
     'issue':('https://github.com/zrepl/zrepl/issues/%s', 'issue #'),
+    'repomasterlink':('https://github.com/zrepl/zrepl/blob/master/%s', ''),
     'sampleconf':('https://github.com/zrepl/zrepl/blob/master/config/samples%s', 'config/samples'),
     'commit':('https://github.com/zrepl/zrepl/commit/%s', 'commit '),
         }

docs/tutorial.rst

@@ -81,7 +81,7 @@ Again, for convenience, We generate the key pairs on our local machine and distr
 
 
 Configure server ``prod``
-----------------------------
+-------------------------
 
 We define a **push job** named ``prod_to_backups`` in ``/etc/zrepl/zrepl.yml`` on host ``prod`` : ::
 
@@ -116,8 +116,8 @@ We define a **push job** named ``prod_to_backups`` in ``/etc/zrepl/zrepl.yml`` o
 
 .. _tutorial-configure-prod:
 
-Configure server ``prod``
--------------------------
+Configure server ``backups``
+----------------------------
 
 We define a corresponding **sink job** named ``sink`` in ``/etc/zrepl/zrepl.yml`` on host ``prod`` : ::
 
@@ -171,7 +171,7 @@ The Linux equivalent might look like this: ::
 Summary
 -------
 
-Congratulations, you have a working pull backup. Where to go next?
+Congratulations, you have a working push backup. Where to go next?
 
 * Read more about :ref:`configuration format, options & job types <configuration_toc>`
 * Configure :ref:`logging <logging>` \& :ref:`monitoring <monitoring>`.

docs/usage.rst

@@ -13,6 +13,8 @@ CLI Overview
     The zrepl binary is self-documenting:
     run ``zrepl help`` for an overview of the available subcommands or ``zrepl SUBCOMMAND --help`` for information on available flags, etc.
 
+.. _cli-signal-wakeup:
+
 .. list-table::
     :widths: 30 70
     :header-rows: 1
@@ -33,6 +35,9 @@ CLI Overview
       - manually abort current replication + pruning of JOB
     * - ``zrepl configcheck``
       - check if config can be parsed without errors
+    * - ``zrepl migrate``
+      - | perform on-disk state / ZFS property migrations
+        | (see :ref:`changelog <changelog>` for details)
 
 .. _usage-zrepl-daemon:
 
@@ -64,3 +69,10 @@ Restarting
 The daemon handles SIGINT and SIGTERM for graceful shutdown.
 Graceful shutdown means at worst that a job will not be rescheduled for the next interval.
 The daemon exits as soon as all jobs have reported shut down.
+
+Systemd Unit File
+~~~~~~~~~~~~~~~~~
+
+A systemd service defintion template is available in :repomasterlink:`dist/systemd`.
+Note that some of the options only work on recent versions of systemd.
+Any help & improvements are very welcome, see :issue:`145`.

endpoint/context.go

@@ -2,6 +2,7 @@ package endpoint
 
 import (
 	"context"
+
 	"github.com/zrepl/zrepl/logger"
 )
 
@@ -9,6 +10,7 @@ type contextKey int
 
 const (
 	contextKeyLogger contextKey = iota
+	ClientIdentityKey
 )
 
 type Logger = logger.Logger

endpoint/endpoint.go

@@ -2,21 +2,22 @@
 package endpoint
 
 import (
-	"bytes"
 	"context"
 	"fmt"
-	"github.com/golang/protobuf/proto"
+	"path"
+
 	"github.com/pkg/errors"
-	"github.com/problame/go-streamrpc"
-	"github.com/zrepl/zrepl/replication"
-	"github.com/zrepl/zrepl/replication/pdu"
+
+	"github.com/zrepl/zrepl/replication/logic/pdu"
+	"github.com/zrepl/zrepl/util/chainlock"
+	"github.com/zrepl/zrepl/util/envconst"
+	"github.com/zrepl/zrepl/util/semaphore"
 	"github.com/zrepl/zrepl/zfs"
-	"io"
 )
 
 // Sender implements replication.ReplicationEndpoint for a sending side
 type Sender struct {
-	FSFilter                zfs.DatasetFilter
+	FSFilter zfs.DatasetFilter
 }
 
 func NewSender(fsf zfs.DatasetFilter) *Sender {
@@ -36,13 +37,13 @@ func (s *Sender) filterCheckFS(fs string) (*zfs.DatasetPath, error) {
 		return nil, err
 	}
 	if !pass {
-		return nil, replication.NewFilteredError(fs)
+		return nil, fmt.Errorf("endpoint does not allow access to filesystem %s", fs)
 	}
 	return dp, nil
 }
 
-func (p *Sender) ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error) {
-	fss, err := zfs.ZFSListMapping(p.FSFilter)
+func (s *Sender) ListFilesystems(ctx context.Context, r *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error) {
+	fss, err := zfs.ZFSListMapping(ctx, s.FSFilter)
 	if err != nil {
 		return nil, err
 	}
@@ -51,13 +52,15 @@ func (p *Sender) ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error)
 		rfss[i] = &pdu.Filesystem{
 			Path: fss[i].ToString(),
 			// FIXME: not supporting ResumeToken yet
+			IsPlaceholder: false, // sender FSs are never placeholders
 		}
 	}
-	return rfss, nil
+	res := &pdu.ListFilesystemRes{Filesystems: rfss}
+	return res, nil
 }
 
-func (p *Sender) ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) {
-	lp, err := p.filterCheckFS(fs)
+func (s *Sender) ListFilesystemVersions(ctx context.Context, r *pdu.ListFilesystemVersionsReq) (*pdu.ListFilesystemVersionsRes, error) {
+	lp, err := s.filterCheckFS(r.GetFilesystem())
 	if err != nil {
 		return nil, err
 	}
@@ -69,32 +72,49 @@ func (p *Sender) ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.
 	for i := range fsvs {
 		rfsvs[i] = pdu.FilesystemVersionFromZFS(&fsvs[i])
 	}
-	return rfsvs, nil
+	res := &pdu.ListFilesystemVersionsRes{Versions: rfsvs}
+	return res, nil
+
 }
 
-func (p *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.ReadCloser, error) {
-	_, err := p.filterCheckFS(r.Filesystem)
+var maxConcurrentZFSSendSemaphore = semaphore.New(envconst.Int64("ZREPL_ENDPOINT_MAX_CONCURRENT_SEND", 10))
+
+func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, zfs.StreamCopier, error) {
+	_, err := s.filterCheckFS(r.Filesystem)
 	if err != nil {
 		return nil, nil, err
 	}
 
-	if r.DryRun {
-		si, err := zfs.ZFSSendDry(r.Filesystem, r.From, r.To, "")
-		if err != nil {
-			return nil, nil, err
-		}
-		var expSize int64 = 0 // protocol says 0 means no estimate
-		if si.SizeEstimate != -1 { // but si returns -1 for no size estimate
-			expSize = si.SizeEstimate
-		}
-		return &pdu.SendRes{ExpectedSize: expSize}, nil, nil
-	} else {
-		stream, err := zfs.ZFSSend(ctx, r.Filesystem, r.From, r.To, "")
-		if err != nil {
-			return nil, nil, err
-		}
-		return &pdu.SendRes{}, stream, nil
+	getLogger(ctx).Debug("acquire concurrent send semaphore")
+	// TODO use try-acquire and fail with resource-exhaustion rpc status
+	// => would require handling on the client-side
+	// => this is a dataconn endpoint, doesn't have the status code semantics of gRPC
+	guard, err := maxConcurrentZFSSendSemaphore.Acquire(ctx)
+	if err != nil {
+		return nil, nil, err
 	}
+	defer guard.Release()
+
+	si, err := zfs.ZFSSendDry(r.Filesystem, r.From, r.To, "")
+	if err != nil {
+		return nil, nil, err
+	}
+
+	var expSize int64 = 0      // protocol says 0 means no estimate
+	if si.SizeEstimate != -1 { // but si returns -1 for no size estimate
+		expSize = si.SizeEstimate
+	}
+	res := &pdu.SendRes{ExpectedSize: expSize}
+
+	if r.DryRun {
+		return res, nil, nil
+	}
+
+	streamCopier, err := zfs.ZFSSend(ctx, r.Filesystem, r.From, r.To, "")
+	if err != nil {
+		return nil, nil, err
+	}
+	return res, streamCopier, nil
 }
 
 func (p *Sender) DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error) {
@@ -105,6 +125,21 @@ func (p *Sender) DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshots
 	return doDestroySnapshots(ctx, dp, req.Snapshots)
 }
 
+func (p *Sender) Ping(ctx context.Context, req *pdu.PingReq) (*pdu.PingRes, error) {
+	res := pdu.PingRes{
+		Echo: req.GetMessage(),
+	}
+	return &res, nil
+}
+
+func (p *Sender) PingDataconn(ctx context.Context, req *pdu.PingReq) (*pdu.PingRes, error) {
+	return p.Ping(ctx, req)
+}
+
+func (p *Sender) WaitForConnectivity(ctx context.Context) error {
+	return nil
+}
+
 func (p *Sender) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
 	dp, err := p.filterCheckFS(req.Filesystem)
 	if err != nil {
@@ -118,7 +153,7 @@ func (p *Sender) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCurs
 			return nil, err
 		}
 		if cursor == nil {
-			return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Error{Error: "cursor does not exist"}}, nil
+			return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Notexist{Notexist: true}}, nil
 		}
 		return &pdu.ReplicationCursorRes{Result: &pdu.ReplicationCursorRes_Guid{Guid: cursor.Guid}}, nil
 	case *pdu.ReplicationCursorReq_Set:
@@ -132,6 +167,10 @@ func (p *Sender) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCurs
 	}
 }
 
+func (p *Sender) Receive(ctx context.Context, r *pdu.ReceiveReq, receive zfs.StreamCopier) (*pdu.ReceiveRes, error) {
+	return nil, fmt.Errorf("sender does not implement Receive()")
+}
+
 type FSFilter interface { // FIXME unused
 	Filter(path *zfs.DatasetPath) (pass bool, err error)
 }
@@ -146,14 +185,56 @@ type FSMap interface { // FIXME unused
 
 // Receiver implements replication.ReplicationEndpoint for a receiving side
 type Receiver struct {
-	root *zfs.DatasetPath
+	rootWithoutClientComponent *zfs.DatasetPath
+	appendClientIdentity       bool
+
+	recvParentCreationMtx *chainlock.L
 }
 
-func NewReceiver(rootDataset *zfs.DatasetPath) (*Receiver, error) {
+func NewReceiver(rootDataset *zfs.DatasetPath, appendClientIdentity bool) *Receiver {
 	if rootDataset.Length() <= 0 {
-		return nil, errors.New("root dataset must not be an empty path")
+		panic(fmt.Sprintf("root dataset must not be an empty path: %v", rootDataset))
 	}
-	return &Receiver{root: rootDataset.Copy()}, nil
+	return &Receiver{
+		rootWithoutClientComponent: rootDataset.Copy(),
+		appendClientIdentity:       appendClientIdentity,
+		recvParentCreationMtx:      chainlock.New(),
+	}
+}
+
+func TestClientIdentity(rootFS *zfs.DatasetPath, clientIdentity string) error {
+	_, err := clientRoot(rootFS, clientIdentity)
+	return err
+}
+
+func clientRoot(rootFS *zfs.DatasetPath, clientIdentity string) (*zfs.DatasetPath, error) {
+	rootFSLen := rootFS.Length()
+	clientRootStr := path.Join(rootFS.ToString(), clientIdentity)
+	clientRoot, err := zfs.NewDatasetPath(clientRootStr)
+	if err != nil {
+		return nil, err
+	}
+	if rootFSLen+1 != clientRoot.Length() {
+		return nil, fmt.Errorf("client identity must be a single ZFS filesystem path component")
+	}
+	return clientRoot, nil
+}
+
+func (s *Receiver) clientRootFromCtx(ctx context.Context) *zfs.DatasetPath {
+	if !s.appendClientIdentity {
+		return s.rootWithoutClientComponent.Copy()
+	}
+
+	clientIdentity, ok := ctx.Value(ClientIdentityKey).(string)
+	if !ok {
+		panic(fmt.Sprintf("ClientIdentityKey context value must be set"))
+	}
+
+	clientRoot, err := clientRoot(s.rootWithoutClientComponent, clientIdentity)
+	if err != nil {
+		panic(fmt.Sprintf("ClientIdentityContextKey must have been validated before invoking Receiver: %s", err))
+	}
+	return clientRoot
 }
 
 type subroot struct {
@@ -180,33 +261,40 @@ func (f subroot) MapToLocal(fs string) (*zfs.DatasetPath, error) {
 	return c, nil
 }
 
-func (e *Receiver) ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error) {
-	filtered, err := zfs.ZFSListMapping(subroot{e.root})
+func (s *Receiver) ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error) {
+	root := s.clientRootFromCtx(ctx)
+	filtered, err := zfs.ZFSListMapping(ctx, subroot{root})
 	if err != nil {
 		return nil, err
 	}
-	// present without prefix, and only those that are not placeholders
+	// present filesystem without the root_fs prefix
 	fss := make([]*pdu.Filesystem, 0, len(filtered))
 	for _, a := range filtered {
-		ph, err := zfs.ZFSIsPlaceholderFilesystem(a)
+		l := getLogger(ctx).WithField("fs", a)
+		ph, err := zfs.ZFSGetFilesystemPlaceholderState(a)
 		if err != nil {
-			getLogger(ctx).
-				WithError(err).
-				WithField("fs", a).
-				Error("inconsistent placeholder property")
-			return nil, errors.New("server error, see logs") // don't leak path
+			l.WithError(err).Error("error getting placeholder state")
+			return nil, errors.Wrapf(err, "cannot get placeholder state for fs %q", a)
 		}
-		if ph {
-			continue
+		l.WithField("placeholder_state", fmt.Sprintf("%#v", ph)).Debug("placeholder state")
+		if !ph.FSExists {
+			l.Error("inconsistent placeholder state: filesystem must exists")
+			err := errors.Errorf("inconsistent placeholder state: filesystem %q must exist in this context", a.ToString())
+			return nil, err
 		}
-		a.TrimPrefix(e.root)
-		fss = append(fss, &pdu.Filesystem{Path: a.ToString()})
+		a.TrimPrefix(root)
+		fss = append(fss, &pdu.Filesystem{Path: a.ToString(), IsPlaceholder: ph.IsPlaceholder})
 	}
-	return fss, nil
+	if len(fss) == 0 {
+		getLogger(ctx).Debug("no filesystems found")
+		return &pdu.ListFilesystemRes{}, nil
+	}
+	return &pdu.ListFilesystemRes{Filesystems: fss}, nil
 }
 
-func (e *Receiver) ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) {
-	lp, err := subroot{e.root}.MapToLocal(fs)
+func (s *Receiver) ListFilesystemVersions(ctx context.Context, req *pdu.ListFilesystemVersionsReq) (*pdu.ListFilesystemVersionsRes, error) {
+	root := s.clientRootFromCtx(ctx)
+	lp, err := subroot{root}.MapToLocal(req.GetFilesystem())
 	if err != nil {
 		return nil, err
 	}
@@ -221,77 +309,135 @@ func (e *Receiver) ListFilesystemVersions(ctx context.Context, fs string) ([]*pd
 		rfsvs[i] = pdu.FilesystemVersionFromZFS(&fsvs[i])
 	}
 
-	return rfsvs, nil
+	return &pdu.ListFilesystemVersionsRes{Versions: rfsvs}, nil
 }
 
-func (e *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, sendStream io.ReadCloser) error {
-	defer sendStream.Close()
-
-	lp, err := subroot{e.root}.MapToLocal(req.Filesystem)
-	if err != nil {
-		return err
+func (s *Receiver) Ping(ctx context.Context, req *pdu.PingReq) (*pdu.PingRes, error) {
+	res := pdu.PingRes{
+		Echo: req.GetMessage(),
 	}
+	return &res, nil
+}
 
-	getLogger(ctx).Debug("incoming Receive")
+func (s *Receiver) PingDataconn(ctx context.Context, req *pdu.PingReq) (*pdu.PingRes, error) {
+	return s.Ping(ctx, req)
+}
 
-	// create placeholder parent filesystems as appropriate
-	var visitErr error
-	f := zfs.NewDatasetPathForest()
-	f.Add(lp)
-	getLogger(ctx).Debug("begin tree-walk")
-	f.WalkTopDown(func(v zfs.DatasetPathVisit) (visitChildTree bool) {
-		if v.Path.Equal(lp) {
-			return false
-		}
-		_, err := zfs.ZFSGet(v.Path, []string{zfs.ZREPL_PLACEHOLDER_PROPERTY_NAME})
-		if err != nil {
-			// interpret this as an early exit of the zfs binary due to the fs not existing
-			if err := zfs.ZFSCreatePlaceholderFilesystem(v.Path); err != nil {
-				getLogger(ctx).
-					WithError(err).
-					WithField("placeholder_fs", v.Path).
-					Error("cannot create placeholder filesystem")
-				visitErr = err
-				return false
-			}
-		}
-		getLogger(ctx).WithField("filesystem", v.Path.ToString()).Debug("exists")
-		return true // leave this fs as is
-	})
-	getLogger(ctx).WithField("visitErr", visitErr).Debug("complete tree-walk")
-
-	if visitErr != nil {
-		return visitErr
-	}
-
-	needForceRecv := false
-	props, err := zfs.ZFSGet(lp, []string{zfs.ZREPL_PLACEHOLDER_PROPERTY_NAME})
-	if err == nil {
-		if isPlaceholder, _ := zfs.IsPlaceholder(lp, props.Get(zfs.ZREPL_PLACEHOLDER_PROPERTY_NAME)); isPlaceholder {
-			needForceRecv = true
-		}
-	}
-
-	args := make([]string, 0, 1)
-	if needForceRecv {
-		args = append(args, "-F")
-	}
-
-	getLogger(ctx).Debug("start receive command")
-
-	if err := zfs.ZFSRecv(ctx, lp.ToString(), sendStream, args...); err != nil {
-		getLogger(ctx).
-			WithError(err).
-			WithField("args", args).
-			Error("zfs receive failed")
-		sendStream.Close()
-		return err
-	}
+func (s *Receiver) WaitForConnectivity(ctx context.Context) error {
 	return nil
 }
 
-func (e *Receiver) DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error) {
-	lp, err := subroot{e.root}.MapToLocal(req.Filesystem)
+func (s *Receiver) ReplicationCursor(context.Context, *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
+	return nil, fmt.Errorf("ReplicationCursor not implemented for Receiver")
+}
+
+func (s *Receiver) Send(ctx context.Context, req *pdu.SendReq) (*pdu.SendRes, zfs.StreamCopier, error) {
+	return nil, nil, fmt.Errorf("receiver does not implement Send()")
+}
+
+var maxConcurrentZFSRecvSemaphore = semaphore.New(envconst.Int64("ZREPL_ENDPOINT_MAX_CONCURRENT_RECV", 10))
+
+func (s *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, receive zfs.StreamCopier) (*pdu.ReceiveRes, error) {
+	getLogger(ctx).Debug("incoming Receive")
+	defer receive.Close()
+
+	root := s.clientRootFromCtx(ctx)
+	lp, err := subroot{root}.MapToLocal(req.Filesystem)
+	if err != nil {
+		return nil, err
+	}
+
+	// create placeholder parent filesystems as appropriate
+	//
+	// Manipulating the ZFS dataset hierarchy must happen exclusively.
+	// TODO: Use fine-grained locking to allow separate clients / requests to pass
+	// 		 through the following section concurrently when operating on disjoint
+	//       ZFS dataset hierarchy subtrees.
+	var visitErr error
+	func() {
+		getLogger(ctx).Debug("begin aquire recvParentCreationMtx")
+		defer s.recvParentCreationMtx.Lock().Unlock()
+		getLogger(ctx).Debug("end aquire recvParentCreationMtx")
+		defer getLogger(ctx).Debug("release recvParentCreationMtx")
+
+		f := zfs.NewDatasetPathForest()
+		f.Add(lp)
+		getLogger(ctx).Debug("begin tree-walk")
+		f.WalkTopDown(func(v zfs.DatasetPathVisit) (visitChildTree bool) {
+			if v.Path.Equal(lp) {
+				return false
+			}
+			ph, err := zfs.ZFSGetFilesystemPlaceholderState(v.Path)
+			getLogger(ctx).
+				WithField("fs", v.Path.ToString()).
+				WithField("placeholder_state", fmt.Sprintf("%#v", ph)).
+				WithField("err", fmt.Sprintf("%s", err)).
+				WithField("errType", fmt.Sprintf("%T", err)).
+				Debug("placeholder state for filesystem")
+			if err != nil {
+				visitErr = err
+				return false
+			}
+
+			if !ph.FSExists {
+				l := getLogger(ctx).WithField("placeholder_fs", v.Path)
+				l.Debug("create placeholder filesystem")
+				err := zfs.ZFSCreatePlaceholderFilesystem(v.Path)
+				if err != nil {
+					l.WithError(err).Error("cannot create placeholder filesystem")
+					visitErr = err
+					return false
+				}
+				return true
+			}
+			getLogger(ctx).WithField("filesystem", v.Path.ToString()).Debug("exists")
+			return true // leave this fs as is
+		})
+	}()
+	getLogger(ctx).WithField("visitErr", visitErr).Debug("complete tree-walk")
+	if visitErr != nil {
+		return nil, visitErr
+	}
+
+	// determine whether we need to rollback the filesystem / change its placeholder state
+	var clearPlaceholderProperty bool
+	var recvOpts zfs.RecvOptions
+	ph, err := zfs.ZFSGetFilesystemPlaceholderState(lp)
+	if err == nil && ph.FSExists && ph.IsPlaceholder {
+		recvOpts.RollbackAndForceRecv = true
+		clearPlaceholderProperty = true
+	}
+	if clearPlaceholderProperty {
+		if err := zfs.ZFSSetPlaceholder(lp, false); err != nil {
+			return nil, fmt.Errorf("cannot clear placeholder property for forced receive: %s", err)
+		}
+	}
+
+	getLogger(ctx).Debug("acquire concurrent recv semaphore")
+	// TODO use try-acquire and fail with resource-exhaustion rpc status
+	// => would require handling on the client-side
+	// => this is a dataconn endpoint, doesn't have the status code semantics of gRPC
+	guard, err := maxConcurrentZFSRecvSemaphore.Acquire(ctx)
+	if err != nil {
+		return nil, err
+	}
+	defer guard.Release()
+
+	getLogger(ctx).WithField("opts", fmt.Sprintf("%#v", recvOpts)).Debug("start receive command")
+
+	if err := zfs.ZFSRecv(ctx, lp.ToString(), receive, recvOpts); err != nil {
+		getLogger(ctx).
+			WithError(err).
+			WithField("opts", recvOpts).
+			Error("zfs receive failed")
+		return nil, err
+	}
+	return &pdu.ReceiveRes{}, nil
+}
+
+func (s *Receiver) DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error) {
+	root := s.clientRootFromCtx(ctx)
+	lp, err := subroot{root}.MapToLocal(req.Filesystem)
 	if err != nil {
 		return nil, err
 	}
@@ -326,289 +472,3 @@ func doDestroySnapshots(ctx context.Context, lp *zfs.DatasetPath, snaps []*pdu.F
 	}
 	return res, nil
 }
-
-// =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
-// RPC STUBS
-// =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
-
-const (
-	RPCListFilesystems        = "ListFilesystems"
-	RPCListFilesystemVersions = "ListFilesystemVersions"
-	RPCReceive                = "Receive"
-	RPCSend                   = "Send"
-	RPCSDestroySnapshots      = "DestroySnapshots"
-	RPCReplicationCursor      = "ReplicationCursor"
-)
-
-// Remote implements an endpoint stub that uses streamrpc as a transport.
-type Remote struct {
-	c *streamrpc.Client
-}
-
-func NewRemote(c *streamrpc.Client) Remote {
-	return Remote{c}
-}
-
-func (s Remote) ListFilesystems(ctx context.Context) ([]*pdu.Filesystem, error) {
-	req := pdu.ListFilesystemReq{}
-	b, err := proto.Marshal(&req)
-	if err != nil {
-		return nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCListFilesystems, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, err
-	}
-	if rs != nil {
-		rs.Close()
-		return nil, errors.New("response contains unexpected stream")
-	}
-	var res pdu.ListFilesystemRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return nil, err
-	}
-	return res.Filesystems, nil
-}
-
-func (s Remote) ListFilesystemVersions(ctx context.Context, fs string) ([]*pdu.FilesystemVersion, error) {
-	req := pdu.ListFilesystemVersionsReq{
-		Filesystem: fs,
-	}
-	b, err := proto.Marshal(&req)
-	if err != nil {
-		return nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCListFilesystemVersions, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, err
-	}
-	if rs != nil {
-		rs.Close()
-		return nil, errors.New("response contains unexpected stream")
-	}
-	var res pdu.ListFilesystemVersionsRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return nil, err
-	}
-	return res.Versions, nil
-}
-
-func (s Remote) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.ReadCloser, error) {
-	b, err := proto.Marshal(r)
-	if err != nil {
-		return nil, nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCSend, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, nil, err
-	}
-	if !r.DryRun && rs == nil {
-		return nil, nil, errors.New("response does not contain a stream")
-	}
-	if r.DryRun && rs != nil {
-		rs.Close()
-		return nil, nil, errors.New("response contains unexpected stream (was dry run)")
-	}
-	var res pdu.SendRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		rs.Close()
-		return nil, nil, err
-	}
-	return &res, rs, nil
-}
-
-func (s Remote) Receive(ctx context.Context, r *pdu.ReceiveReq, sendStream io.ReadCloser) error {
-	defer sendStream.Close()
-	b, err := proto.Marshal(r)
-	if err != nil {
-		return err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCReceive, bytes.NewBuffer(b), sendStream)
-	getLogger(ctx).WithField("err", err).Debug("Remote.Receive RequestReplyReturned")
-	if err != nil {
-		return err
-	}
-	if rs != nil {
-		rs.Close()
-		return errors.New("response contains unexpected stream")
-	}
-	var res pdu.ReceiveRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return err
-	}
-	return nil
-}
-
-func (s Remote) DestroySnapshots(ctx context.Context, r *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error) {
-	b, err := proto.Marshal(r)
-	if err != nil {
-		return nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCSDestroySnapshots, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, err
-	}
-	if rs != nil {
-		rs.Close()
-		return nil, errors.New("response contains unexpected stream")
-	}
-	var res pdu.DestroySnapshotsRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return nil, err
-	}
-	return &res, nil
-}
-
-func (s Remote) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
-	b, err := proto.Marshal(req)
-	if err != nil {
-		return nil, err
-	}
-	rb, rs, err := s.c.RequestReply(ctx, RPCReplicationCursor, bytes.NewBuffer(b), nil)
-	if err != nil {
-		return nil, err
-	}
-	if rs != nil {
-		rs.Close()
-		return nil, errors.New("response contains unexpected stream")
-	}
-	var res pdu.ReplicationCursorRes
-	if err := proto.Unmarshal(rb.Bytes(), &res); err != nil {
-		return nil, err
-	}
-	return &res, nil
-}
-
-// Handler implements the server-side streamrpc.HandlerFunc for a Remote endpoint stub.
-type Handler struct {
-	ep replication.Endpoint
-}
-
-func NewHandler(ep replication.Endpoint) Handler {
-	return Handler{ep}
-}
-
-func (a *Handler) Handle(ctx context.Context, endpoint string, reqStructured *bytes.Buffer, reqStream io.ReadCloser) (resStructured *bytes.Buffer, resStream io.ReadCloser, err error) {
-
-	switch endpoint {
-	case RPCListFilesystems:
-		var req pdu.ListFilesystemReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		fsses, err := a.ep.ListFilesystems(ctx)
-		if err != nil {
-			return nil, nil, err
-		}
-		res := &pdu.ListFilesystemRes{
-			Filesystems: fsses,
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, nil
-
-	case RPCListFilesystemVersions:
-
-		var req pdu.ListFilesystemVersionsReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		fsvs, err := a.ep.ListFilesystemVersions(ctx, req.Filesystem)
-		if err != nil {
-			return nil, nil, err
-		}
-		res := &pdu.ListFilesystemVersionsRes{
-			Versions: fsvs,
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, nil
-
-	case RPCSend:
-
-		sender, ok := a.ep.(replication.Sender)
-		if !ok {
-			goto Err
-		}
-
-		var req pdu.SendReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		res, sendStream, err := sender.Send(ctx, &req)
-		if err != nil {
-			return nil, nil, err
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), sendStream, err
-
-	case RPCReceive:
-
-		receiver, ok := a.ep.(replication.Receiver)
-		if !ok {
-			goto Err
-		}
-
-		var req pdu.ReceiveReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		err := receiver.Receive(ctx, &req, reqStream)
-		if err != nil {
-			return nil, nil, err
-		}
-		b, err := proto.Marshal(&pdu.ReceiveRes{})
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, err
-
-	case RPCSDestroySnapshots:
-
-		var req pdu.DestroySnapshotsReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-
-		res, err := a.ep.DestroySnapshots(ctx, &req)
-		if err != nil {
-			return nil, nil, err
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, nil
-
-	case RPCReplicationCursor:
-
-		sender, ok := a.ep.(replication.Sender)
-		if !ok {
-			goto Err
-		}
-
-		var req pdu.ReplicationCursorReq
-		if err := proto.Unmarshal(reqStructured.Bytes(), &req); err != nil {
-			return nil, nil, err
-		}
-		res, err := sender.ReplicationCursor(ctx, &req)
-		if err != nil {
-			return nil, nil, err
-		}
-		b, err := proto.Marshal(res)
-		if err != nil {
-			return nil, nil, err
-		}
-		return bytes.NewBuffer(b), nil, nil
-
-	}
-Err:
-	return nil, nil, errors.New("no handler for given endpoint")
-}

lazy.sh

@@ -25,23 +25,28 @@ fi
 
 CHECKOUTPATH="${GOPATH}/src/github.com/zrepl/zrepl"
 
-builddep() {
-    step "Install build depdencies using 'go get' to \$GOPATH/bin"
-    go get -u golang.org/x/tools/cmd/stringer
+godep() {
+    step "Install go dep using 'go get' to \$GOPATH/bin"
     go get -u github.com/golang/dep/cmd/dep
-    go get -u github.com/golang/protobuf/protoc-gen-go
-    go get -u github.com/alvaroloes/enumer
-    if ! type stringer || ! type dep || ! type protoc-gen-go || ! type enumer ; then
+    if ! type dep ; then
+        echo "Unable to install go dep" 1>&2
+        exit 1
+    fi
+    step "Fetching dependencies using 'dep ensure'"
+    dep ensure -v -vendor-only
+    step "go install build dependencies fetched using dep"
+    # these will be in the vendor directory
+    go build -o "$GOPATH/bin/stringer"      ./vendor/golang.org/x/tools/cmd/stringer
+    go build -o "$GOPATH/bin/protoc-gen-go" ./vendor/github.com/golang/protobuf/protoc-gen-go
+    go build -o "$GOPATH/bin/enumer"        ./vendor/github.com/alvaroloes/enumer
+    go build -o "$GOPATH/bin/goimports"     ./vendor/golang.org/x/tools/cmd/goimports
+    go build -o "$GOPATH/bin/golangci-lint" ./vendor/github.com/golangci/golangci-lint/cmd/golangci-lint
+    if ! type stringer || ! type protoc-gen-go || ! type enumer || ! type goimports || ! type golangci-lint; then
         echo "Installed dependencies but can't find them in \$PATH, adjust it to contain \$GOPATH/bin" 1>&2
         exit 1
     fi
 }
 
-godep() {
-    step "Fetching dependencies using 'dep ensure'"
-    dep ensure
-}
-
 docdep() {
     if ! type pip3; then
         step "pip3 binary not installed or not in \$PATH" 1>&2
@@ -62,13 +67,13 @@ release() {
 
 for cmd in "$@"; do
     case "$cmd" in
-        builddep|godep|docdep|release_bins|docs)
+        godep|docdep|release_bins|docs)
             eval $cmd
             continue
             ;;
         devsetup)
             step "Installing development dependencies"
-            builddep
+            godep
             docdep
             step "Development dependencies installed"
             continue

logger/datastructures.go

@@ -4,10 +4,11 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"github.com/fatih/color"
-	"github.com/pkg/errors"
 	"sync"
 	"time"
+
+	"github.com/fatih/color"
+	"github.com/pkg/errors"
 )
 
 type Level int
@@ -66,7 +67,7 @@ func (l Level) Short() string {
 	case Error:
 		return "ERRO"
 	default:
-		return fmt.Sprintf("%s", l)
+		return l.String()
 	}
 }
 
@@ -81,7 +82,7 @@ func (l Level) String() string {
 	case Error:
 		return "error"
 	default:
-		return fmt.Sprintf("%s", string(l))
+		return string(l)
 	}
 }
 

logger/logger.go

@@ -66,7 +66,8 @@ func (l *loggerImpl) logInternalError(outlet Outlet, err string) {
 		time.Now(),
 		fields,
 	}
-	l.outlets.GetLoggerErrorOutlet().WriteEntry(entry)
+	// ignore errors at this point (still better than panicking if the error is temporary)
+	_ = l.outlets.GetLoggerErrorOutlet().WriteEntry(entry)
 }
 
 func (l *loggerImpl) log(level Level, msg string) {

logger/logger_test.go

@@ -2,10 +2,12 @@ package logger_test
 
 import (
 	"fmt"
-	"github.com/kr/pretty"
-	"github.com/zrepl/zrepl/logger"
 	"testing"
 	"time"
+
+	"github.com/kr/pretty"
+
+	"github.com/zrepl/zrepl/logger"
 )
 
 type TestOutlet struct {

logger/stderrlogger.go

@@ -0,0 +1,23 @@
+package logger
+
+import (
+	"fmt"
+	"os"
+)
+
+type stderrLoggerOutlet struct{}
+
+func (stderrLoggerOutlet) WriteEntry(entry Entry) error {
+	fmt.Fprintf(os.Stderr, "%#v\n", entry)
+	return nil
+}
+
+var _ Logger = testLogger{}
+
+func NewStderrDebugLogger() Logger {
+	outlets := NewOutlets()
+	outlets.Add(&stderrLoggerOutlet{}, Debug)
+	return &testLogger{
+		Logger: NewLogger(outlets, 0),
+	}
+}

main.go

@@ -16,6 +16,7 @@ func init() {
 	cli.AddSubcommand(client.VersionCmd)
 	cli.AddSubcommand(client.PprofCmd)
 	cli.AddSubcommand(client.TestCmd)
+	cli.AddSubcommand(client.MigrateCmd)
 }
 
 func main() {

pruning/keep_grid.go

@@ -2,12 +2,14 @@ package pruning
 
 import (
 	"fmt"
-	"github.com/pkg/errors"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/pruning/retentiongrid"
 	"regexp"
 	"sort"
 	"time"
+
+	"github.com/pkg/errors"
+
+	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/pruning/retentiongrid"
 )
 
 // KeepGrid fits snapshots that match a given regex into a retentiongrid.Grid,
@@ -15,7 +17,7 @@ import (
 // and deletes all snapshots that do not fit the grid specification.
 type KeepGrid struct {
 	retentionGrid *retentiongrid.Grid
-	re *regexp.Regexp
+	re            *regexp.Regexp
 }
 
 func NewKeepGrid(in *config.PruneGrid) (p *KeepGrid, err error) {

pruning/keep_helpers_test.go

@@ -1,8 +1,9 @@
 package pruning
 
 import (
-	"github.com/stretchr/testify/assert"
 	"testing"
+
+	"github.com/stretchr/testify/assert"
 )
 
 func TestShallowCopySnapList(t *testing.T) {

pruning/keep_last_n.go

@@ -1,8 +1,9 @@
 package pruning
 
 import (
-	"github.com/pkg/errors"
 	"sort"
+
+	"github.com/pkg/errors"
 )
 
 type KeepLastN struct {

pruning/keep_last_n_test.go

@@ -1,9 +1,10 @@
 package pruning
 
 import (
-	"github.com/stretchr/testify/assert"
 	"testing"
 	"time"
+
+	"github.com/stretchr/testify/assert"
 )
 
 func TestKeepLastN(t *testing.T) {

pruning/keep_not_replicated.go

@@ -1,8 +1,6 @@
 package pruning
 
-type KeepNotReplicated struct {
-	forceConstructor struct{}
-}
+type KeepNotReplicated struct{}
 
 func (*KeepNotReplicated) KeepRule(snaps []Snapshot) (destroyList []Snapshot) {
 	return filterSnapList(snaps, func(snapshot Snapshot) bool {

pruning/keep_regex.go

@@ -5,21 +5,22 @@ import (
 )
 
 type KeepRegex struct {
-	expr *regexp.Regexp
+	expr   *regexp.Regexp
+	negate bool
 }
 
 var _ KeepRule = &KeepRegex{}
 
-func NewKeepRegex(expr string) (*KeepRegex, error) {
+func NewKeepRegex(expr string, negate bool) (*KeepRegex, error) {
 	re, err := regexp.Compile(expr)
 	if err != nil {
 		return nil, err
 	}
-	return &KeepRegex{re}, nil
+	return &KeepRegex{re, negate}, nil
 }
 
-func MustKeepRegex(expr string) *KeepRegex {
-	k, err := NewKeepRegex(expr)
+func MustKeepRegex(expr string, negate bool) *KeepRegex {
+	k, err := NewKeepRegex(expr, negate)
 	if err != nil {
 		panic(err)
 	}
@@ -28,6 +29,10 @@ func MustKeepRegex(expr string) *KeepRegex {
 
 func (k *KeepRegex) KeepRule(snaps []Snapshot) []Snapshot {
 	return filterSnapList(snaps, func(s Snapshot) bool {
-		return k.expr.FindStringIndex(s.Name()) == nil
+		if k.negate {
+			return k.expr.FindStringIndex(s.Name()) != nil
+		} else {
+			return k.expr.FindStringIndex(s.Name()) == nil
+		}
 	})
 }

pruning/keep_regex_test.go

@@ -0,0 +1,32 @@
+package pruning
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestKeepRegexNegation(t *testing.T) {
+
+	noneg := MustKeepRegex("^zrepl_", false)
+	neg := MustKeepRegex("^zrepl_", true)
+
+	snaps := []Snapshot{
+		stubSnap{name: "zrepl_foobar"},
+		stubSnap{name: "zrepl"},
+		stubSnap{name: "barfoo"},
+	}
+
+	destroyNonNeg := snapshotList(noneg.KeepRule(snaps))
+	t.Logf("non-negated rule destroys: %#v", destroyNonNeg.NameList())
+	assert.True(t, destroyNonNeg.ContainsName("zrepl"))
+	assert.True(t, destroyNonNeg.ContainsName("barfoo"))
+	assert.False(t, destroyNonNeg.ContainsName("zrepl_foobar"))
+
+	destroyNeg := snapshotList(neg.KeepRule(snaps))
+	t.Logf("negated rule destroys: %#v", destroyNeg.NameList())
+	assert.False(t, destroyNeg.ContainsName("zrepl"))
+	assert.False(t, destroyNeg.ContainsName("barfoo"))
+	assert.True(t, destroyNeg.ContainsName("zrepl_foobar"))
+
+}

pruning/pruning.go

@@ -2,9 +2,11 @@ package pruning
 
 import (
 	"fmt"
-	"github.com/pkg/errors"
-	"github.com/zrepl/zrepl/config"
 	"time"
+
+	"github.com/pkg/errors"
+
+	"github.com/zrepl/zrepl/config"
 )
 
 type KeepRule interface {
@@ -20,7 +22,7 @@ type Snapshot interface {
 // The returned snapshot list is guaranteed to only contains elements of input parameter snaps
 func PruneSnapshots(snaps []Snapshot, keepRules []KeepRule) []Snapshot {
 
-	if keepRules == nil || len(keepRules) == 0 {
+	if len(keepRules) == 0 {
 		return []Snapshot{}
 	}
 
@@ -60,7 +62,7 @@ func RuleFromConfig(in config.PruningEnum) (KeepRule, error) {
 	case *config.PruneKeepLastN:
 		return NewKeepLastN(v.Count)
 	case *config.PruneKeepRegex:
-		return NewKeepRegex(v.Regex)
+		return NewKeepRegex(v.Regex, v.Negate)
 	case *config.PruneGrid:
 		return NewKeepGrid(v)
 	default:

pruning/pruning_test.go

@@ -24,6 +24,25 @@ type testCase struct {
 	expDestroyAlternatives []map[string]bool
 }
 
+type snapshotList []Snapshot
+
+func (l snapshotList) ContainsName(n string) bool {
+	for _, s := range l {
+		if s.Name() == n {
+			return true
+		}
+	}
+	return false
+}
+
+func (l snapshotList) NameList() []string {
+	res := make([]string, len(l))
+	for i, s := range l {
+		res[i] = s.Name()
+	}
+	return res
+}
+
 func testTable(tcs map[string]testCase, t *testing.T) {
 	mapEqual := func(a, b map[string]bool) bool {
 		if len(a) != len(b) {
@@ -79,7 +98,7 @@ func TestPruneSnapshots(t *testing.T) {
 		"simple": {
 			inputs: inputs["s1"],
 			rules: []KeepRule{
-				MustKeepRegex("foo_"),
+				MustKeepRegex("foo_", false),
 			},
 			expDestroy: map[string]bool{
 				"bar_123": true,
@@ -88,16 +107,16 @@ func TestPruneSnapshots(t *testing.T) {
 		"multipleRules": {
 			inputs: inputs["s1"],
 			rules: []KeepRule{
-				MustKeepRegex("foo_"),
-				MustKeepRegex("bar_"),
+				MustKeepRegex("foo_", false),
+				MustKeepRegex("bar_", false),
 			},
 			expDestroy: map[string]bool{},
 		},
 		"onlyThoseRemovedByAllAreRemoved": {
 			inputs: inputs["s1"],
 			rules: []KeepRule{
-				MustKeepRegex("notInS1"), // would remove all
-				MustKeepRegex("bar_"),    // would remove all but bar_, i.e. foo_.*
+				MustKeepRegex("notInS1", false), // would remove all
+				MustKeepRegex("bar_", false),    // would remove all but bar_, i.e. foo_.*
 			},
 			expDestroy: map[string]bool{
 				"foo_123": true,
@@ -117,7 +136,7 @@ func TestPruneSnapshots(t *testing.T) {
 		"noSnaps": {
 			inputs: []Snapshot{},
 			rules: []KeepRule{
-				MustKeepRegex("foo_"),
+				MustKeepRegex("foo_", false),
 			},
 			expDestroy: map[string]bool{},
 		},

pruning/retentiongrid/retentiongrid_test.go

@@ -2,11 +2,12 @@ package retentiongrid
 
 import (
 	"fmt"
-	"github.com/stretchr/testify/assert"
 	"strconv"
 	"strings"
 	"testing"
 	"time"
+
+	"github.com/stretchr/testify/assert"
 )
 
 type retentionIntervalStub struct {

replication/driver/errorclass_enumer.go

@@ -0,0 +1,49 @@
+// Code generated by "enumer -type=errorClass"; DO NOT EDIT.
+
+package driver
+
+import (
+	"fmt"
+)
+
+const _errorClassName = "errorClassPermanenterrorClassTemporaryConnectivityRelated"
+
+var _errorClassIndex = [...]uint8{0, 19, 57}
+
+func (i errorClass) String() string {
+	if i < 0 || i >= errorClass(len(_errorClassIndex)-1) {
+		return fmt.Sprintf("errorClass(%d)", i)
+	}
+	return _errorClassName[_errorClassIndex[i]:_errorClassIndex[i+1]]
+}
+
+var _errorClassValues = []errorClass{0, 1}
+
+var _errorClassNameToValueMap = map[string]errorClass{
+	_errorClassName[0:19]:  0,
+	_errorClassName[19:57]: 1,
+}
+
+// errorClassString retrieves an enum value from the enum constants string name.
+// Throws an error if the param is not part of the enum.
+func errorClassString(s string) (errorClass, error) {
+	if val, ok := _errorClassNameToValueMap[s]; ok {
+		return val, nil
+	}
+	return 0, fmt.Errorf("%s does not belong to errorClass values", s)
+}
+
+// errorClassValues returns all values of the enum
+func errorClassValues() []errorClass {
+	return _errorClassValues
+}
+
+// IsAerrorClass returns "true" if the value is listed in the enum definition. "false" otherwise
+func (i errorClass) IsAerrorClass() bool {
+	for _, v := range _errorClassValues {
+		if i == v {
+			return true
+		}
+	}
+	return false
+}

replication/driver/replication_driver.go

@@ -0,0 +1,633 @@
+package driver
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"net"
+	"sort"
+	"strings"
+	"sync"
+	"time"
+
+	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/status"
+
+	"github.com/zrepl/zrepl/replication/report"
+	"github.com/zrepl/zrepl/util/chainlock"
+	"github.com/zrepl/zrepl/util/envconst"
+)
+
+type interval struct {
+	begin time.Time
+	end   time.Time
+}
+
+func (w *interval) SetZero() {
+	w.begin = time.Time{}
+	w.end = time.Time{}
+}
+
+// Duration of 0 means indefinite length
+func (w *interval) Set(begin time.Time, duration time.Duration) {
+	if begin.IsZero() {
+		panic("zero begin time now allowed")
+	}
+	w.begin = begin
+	w.end = begin.Add(duration)
+}
+
+// Returns the End of the interval if it has a defined length.
+// For indefinite lengths, returns the zero value.
+func (w *interval) End() time.Time {
+	return w.end
+}
+
+// Return a context with a deadline at the interval's end.
+// If the interval has indefinite length (duration 0 on Set), return ctx as is.
+// The returned context.CancelFunc can be called either way.
+func (w *interval) ContextWithDeadlineAtEnd(ctx context.Context) (context.Context, context.CancelFunc) {
+	if w.begin.IsZero() {
+		panic("must call Set before ContextWIthDeadlineAtEnd")
+	}
+	if w.end.IsZero() {
+		// indefinite length, just return context as is
+		return ctx, func() {}
+	} else {
+		return context.WithDeadline(ctx, w.end)
+	}
+}
+
+type run struct {
+	l *chainlock.L
+
+	startedAt, finishedAt time.Time
+
+	waitReconnect      interval
+	waitReconnectError *timedError
+
+	// the attempts attempted so far:
+	// All but the last in this slice must have finished with some errors.
+	// The last attempt may not be finished and may not have errors.
+	attempts []*attempt
+}
+
+type Planner interface {
+	Plan(context.Context) ([]FS, error)
+	WaitForConnectivity(context.Context) error
+}
+
+// an attempt represents a single planning & execution of fs replications
+type attempt struct {
+	planner Planner
+
+	l *chainlock.L
+
+	startedAt, finishedAt time.Time
+
+	// after Planner.Plan was called, planErr and fss are mutually exclusive with regards to nil-ness
+	// if both are nil, it must be assumed that Planner.Plan is active
+	planErr *timedError
+	fss     []*fs
+}
+
+type timedError struct {
+	Err  error
+	Time time.Time
+}
+
+func newTimedError(err error, t time.Time) *timedError {
+	if err == nil {
+		panic("error must be non-nil")
+	}
+	if t.IsZero() {
+		panic("t must be non-zero")
+	}
+	return &timedError{err, t}
+}
+
+func (e *timedError) IntoReportError() *report.TimedError {
+	if e == nil {
+		return nil
+	}
+	return report.NewTimedError(e.Err.Error(), e.Time)
+}
+
+type FS interface {
+	// Returns true if this FS and fs refer to the same filesystem returned
+	// by Planner.Plan in a previous attempt.
+	EqualToPreviousAttempt(fs FS) bool
+	// The returned steps are assumed to be dependent on exactly
+	// their direct predecessors in the returned list.
+	PlanFS(context.Context) ([]Step, error)
+	ReportInfo() *report.FilesystemInfo
+}
+
+type Step interface {
+	// Returns true iff the target snapshot is the same for this Step and other.
+	// We do not use TargetDate to avoid problems with wrong system time on
+	// snapshot creation.
+	//
+	// Implementations can assume that `other` is a step of the same filesystem,
+	// although maybe from a previous attempt.
+	// (`same` as defined by FS.EqualToPreviousAttempt)
+	//
+	// Note that TargetEquals should return true in a situation with one
+	// originally sent snapshot and a subsequent attempt's step that uses
+	// resumable send & recv.
+	TargetEquals(other Step) bool
+	TargetDate() time.Time
+	Step(context.Context) error
+	ReportInfo() *report.StepInfo
+}
+
+type fs struct {
+	fs FS
+
+	l *chainlock.L
+
+	planning struct {
+		done bool
+		err  *timedError
+	}
+
+	// valid iff planning.done && planning.err == nil
+	planned struct {
+		// valid iff planning.done && planning.err == nil
+		stepErr *timedError
+		// all steps, in the order in which they must be completed
+		steps []*step
+		// index into steps, pointing at the step that is currently executing
+		// if step >= len(steps), no more work needs to be done
+		step int
+	}
+}
+
+type step struct {
+	l    *chainlock.L
+	step Step
+}
+
+type ReportFunc func() *report.Report
+type WaitFunc func(block bool) (done bool)
+
+var maxAttempts = envconst.Int64("ZREPL_REPLICATION_MAX_ATTEMPTS", 3)
+var reconnectHardFailTimeout = envconst.Duration("ZREPL_REPLICATION_RECONNECT_HARD_FAIL_TIMEOUT", 10*time.Minute)
+
+func Do(ctx context.Context, planner Planner) (ReportFunc, WaitFunc) {
+	log := getLog(ctx)
+	l := chainlock.New()
+	run := &run{
+		l:         l,
+		startedAt: time.Now(),
+	}
+
+	done := make(chan struct{})
+	go func() {
+		defer close(done)
+
+		defer run.l.Lock().Unlock()
+		log.Debug("begin run")
+		defer log.Debug("run ended")
+		var prev *attempt
+		mainLog := log
+		for ano := 0; ano < int(maxAttempts) || maxAttempts == 0; ano++ {
+			log := mainLog.WithField("attempt_number", ano)
+			log.Debug("start attempt")
+
+			run.waitReconnect.SetZero()
+			run.waitReconnectError = nil
+
+			// do current attempt
+			cur := &attempt{
+				l:         l,
+				startedAt: time.Now(),
+				planner:   planner,
+			}
+			run.attempts = append(run.attempts, cur)
+			run.l.DropWhile(func() {
+				cur.do(ctx, prev)
+			})
+			prev = cur
+			if ctx.Err() != nil {
+				log.WithError(ctx.Err()).Info("context error")
+				return
+			}
+
+			// error classification, bail out if done / permanent error
+			rep := cur.report()
+			log.WithField("attempt_state", rep.State).Debug("attempt state")
+			errRep := cur.errorReport()
+
+			if rep.State == report.AttemptDone {
+				log.Debug("attempt completed successfully")
+				break
+			}
+
+			mostRecentErr, mostRecentErrClass := errRep.MostRecent()
+			log.WithField("most_recent_err", mostRecentErr).WithField("most_recent_err_class", mostRecentErrClass).Debug("most recent error used for re-connect decision")
+			if mostRecentErr == nil {
+				// inconsistent reporting, let's bail out
+				log.Warn("attempt does not report done but error report does not report errors, aborting run")
+				break
+			}
+			log.WithError(mostRecentErr.Err).Error("most recent error in this attempt")
+			shouldReconnect := mostRecentErrClass == errorClassTemporaryConnectivityRelated
+			log.WithField("reconnect_decision", shouldReconnect).Debug("reconnect decision made")
+			if shouldReconnect {
+				run.waitReconnect.Set(time.Now(), reconnectHardFailTimeout)
+				log.WithField("deadline", run.waitReconnect.End()).Error("temporary connectivity-related error identified, start waiting for reconnect")
+				var connectErr error
+				var connectErrTime time.Time
+				run.l.DropWhile(func() {
+					ctx, cancel := run.waitReconnect.ContextWithDeadlineAtEnd(ctx)
+					defer cancel()
+					connectErr = planner.WaitForConnectivity(ctx)
+					connectErrTime = time.Now()
+				})
+				if connectErr == nil {
+					log.Error("reconnect successful") // same level as 'begin with reconnect' message above
+					continue
+				} else {
+					run.waitReconnectError = newTimedError(connectErr, connectErrTime)
+					log.WithError(connectErr).Error("reconnecting failed, aborting run")
+					break
+				}
+			} else {
+				log.Error("most recent error cannot be solved by reconnecting, aborting run")
+				return
+			}
+
+		}
+
+	}()
+
+	wait := func(block bool) bool {
+		if block {
+			<-done
+		}
+		select {
+		case <-done:
+			return true
+		default:
+			return false
+		}
+	}
+	report := func() *report.Report {
+		defer run.l.Lock().Unlock()
+		return run.report()
+	}
+	return report, wait
+}
+
+func (a *attempt) do(ctx context.Context, prev *attempt) {
+	pfss, err := a.planner.Plan(ctx)
+	errTime := time.Now()
+	defer a.l.Lock().Unlock()
+	if err != nil {
+		a.planErr = newTimedError(err, errTime)
+		a.fss = nil
+		a.finishedAt = time.Now()
+		return
+	}
+
+	for _, pfs := range pfss {
+		fs := &fs{
+			fs: pfs,
+			l:  a.l,
+		}
+		a.fss = append(a.fss, fs)
+	}
+
+	prevs := make(map[*fs]*fs)
+	{
+		prevFSs := make(map[*fs][]*fs, len(pfss))
+		if prev != nil {
+			debug("previous attempt has %d fss", len(a.fss))
+			for _, fs := range a.fss {
+				for _, prevFS := range prev.fss {
+					if fs.fs.EqualToPreviousAttempt(prevFS.fs) {
+						l := prevFSs[fs]
+						l = append(l, prevFS)
+						prevFSs[fs] = l
+					}
+				}
+			}
+		}
+		type inconsistency struct {
+			cur   *fs
+			prevs []*fs
+		}
+		var inconsistencies []inconsistency
+		for cur, fss := range prevFSs {
+			if len(fss) > 1 {
+				inconsistencies = append(inconsistencies, inconsistency{cur, fss})
+			}
+		}
+		sort.SliceStable(inconsistencies, func(i, j int) bool {
+			return inconsistencies[i].cur.fs.ReportInfo().Name < inconsistencies[j].cur.fs.ReportInfo().Name
+		})
+		if len(inconsistencies) > 0 {
+			var msg strings.Builder
+			msg.WriteString("cannot determine filesystem correspondences between different attempts:\n")
+			var inconsistencyLines []string
+			for _, i := range inconsistencies {
+				var prevNames []string
+				for _, prev := range i.prevs {
+					prevNames = append(prevNames, prev.fs.ReportInfo().Name)
+				}
+				l := fmt.Sprintf("  %s => %v", i.cur.fs.ReportInfo().Name, prevNames)
+				inconsistencyLines = append(inconsistencyLines, l)
+			}
+			fmt.Fprint(&msg, strings.Join(inconsistencyLines, "\n"))
+			now := time.Now()
+			a.planErr = newTimedError(errors.New(msg.String()), now)
+			a.fss = nil
+			a.finishedAt = now
+			return
+		}
+		for cur, fss := range prevFSs {
+			if len(fss) > 0 {
+				prevs[cur] = fss[0]
+			}
+		}
+	}
+	// invariant: prevs contains an entry for each unambigious correspondence
+
+	stepQueue := newStepQueue()
+	defer stepQueue.Start(1)() // TODO parallel replication
+	var fssesDone sync.WaitGroup
+	for _, f := range a.fss {
+		fssesDone.Add(1)
+		go func(f *fs) {
+			defer fssesDone.Done()
+			f.do(ctx, stepQueue, prevs[f])
+		}(f)
+	}
+	a.l.DropWhile(func() {
+		fssesDone.Wait()
+	})
+	a.finishedAt = time.Now()
+}
+
+func (fs *fs) do(ctx context.Context, pq *stepQueue, prev *fs) {
+	psteps, err := fs.fs.PlanFS(ctx)
+	errTime := time.Now()
+	defer fs.l.Lock().Unlock()
+	debug := debugPrefix("fs=%s", fs.fs.ReportInfo().Name)
+	fs.planning.done = true
+	if err != nil {
+		fs.planning.err = newTimedError(err, errTime)
+		return
+	}
+	for _, pstep := range psteps {
+		step := &step{
+			l:    fs.l,
+			step: pstep,
+		}
+		fs.planned.steps = append(fs.planned.steps, step)
+	}
+	debug("iniital len(fs.planned.steps) = %d", len(fs.planned.steps))
+
+	// for not-first attempts, only allow fs.planned.steps
+	// up to including the originally planned target snapshot
+	if prev != nil && prev.planning.done && prev.planning.err == nil {
+		prevUncompleted := prev.planned.steps[prev.planned.step:]
+		if len(prevUncompleted) == 0 {
+			debug("prevUncompleted is empty")
+			return
+		}
+		if len(fs.planned.steps) == 0 {
+			debug("fs.planned.steps is empty")
+			return
+		}
+		prevFailed := prevUncompleted[0]
+		curFirst := fs.planned.steps[0]
+		// we assume that PlanFS retries prevFailed (using curFirst)
+		if !prevFailed.step.TargetEquals(curFirst.step) {
+			debug("Targets don't match")
+			// Two options:
+			// A: planning algorithm is broken
+			// B: manual user intervention inbetween
+			// Neither way will we make progress, so let's error out
+			stepFmt := func(step *step) string {
+				r := step.report()
+				s := r.Info
+				if r.IsIncremental() {
+					return fmt.Sprintf("%s=>%s", s.From, s.To)
+				} else {
+					return fmt.Sprintf("full=>%s", s.To)
+				}
+			}
+			msg := fmt.Sprintf("last attempt's uncompleted step %s does not correspond to this attempt's first planned step %s",
+				stepFmt(prevFailed), stepFmt(curFirst))
+			fs.planned.stepErr = newTimedError(errors.New(msg), time.Now())
+			return
+		}
+		// only allow until step targets diverge
+		min := len(prevUncompleted)
+		if min > len(fs.planned.steps) {
+			min = len(fs.planned.steps)
+		}
+		diverge := 0
+		for ; diverge < min; diverge++ {
+			debug("diverge compare iteration %d", diverge)
+			if !fs.planned.steps[diverge].step.TargetEquals(prevUncompleted[diverge].step) {
+				break
+			}
+		}
+		debug("diverge is %d", diverge)
+		fs.planned.steps = fs.planned.steps[0:diverge]
+	}
+	debug("post-prev-merge len(fs.planned.steps) = %d", len(fs.planned.steps))
+
+	for i, s := range fs.planned.steps {
+		var (
+			err     error
+			errTime time.Time
+		)
+		// lock must not be held while executing step in order for reporting to work
+		fs.l.DropWhile(func() {
+			targetDate := s.step.TargetDate()
+			defer pq.WaitReady(fs, targetDate)()
+			err = s.step.Step(ctx) // no shadow
+			errTime = time.Now()   // no shadow
+		})
+		if err != nil {
+			fs.planned.stepErr = newTimedError(err, errTime)
+			break
+		}
+		fs.planned.step = i + 1 // fs.planned.step must be == len(fs.planned.steps) if all went OK
+	}
+}
+
+// caller must hold lock l
+func (r *run) report() *report.Report {
+	report := &report.Report{
+		Attempts:           make([]*report.AttemptReport, len(r.attempts)),
+		StartAt:            r.startedAt,
+		FinishAt:           r.finishedAt,
+		WaitReconnectSince: r.waitReconnect.begin,
+		WaitReconnectUntil: r.waitReconnect.end,
+		WaitReconnectError: r.waitReconnectError.IntoReportError(),
+	}
+	for i := range report.Attempts {
+		report.Attempts[i] = r.attempts[i].report()
+	}
+	return report
+}
+
+// caller must hold lock l
+func (a *attempt) report() *report.AttemptReport {
+
+	r := &report.AttemptReport{
+		// State is set below
+		Filesystems: make([]*report.FilesystemReport, len(a.fss)),
+		StartAt:     a.startedAt,
+		FinishAt:    a.finishedAt,
+		PlanError:   a.planErr.IntoReportError(),
+	}
+
+	for i := range r.Filesystems {
+		r.Filesystems[i] = a.fss[i].report()
+	}
+
+	state := report.AttemptPlanning
+	if a.planErr != nil {
+		state = report.AttemptPlanningError
+	} else if a.fss != nil {
+		if a.finishedAt.IsZero() {
+			state = report.AttemptFanOutFSs
+		} else {
+			fsWithError := false
+			for _, s := range r.Filesystems {
+				fsWithError = fsWithError || s.Error() != nil
+			}
+			state = report.AttemptDone
+			if fsWithError {
+				state = report.AttemptFanOutError
+			}
+		}
+	}
+	r.State = state
+
+	return r
+}
+
+// caller must hold lock l
+func (f *fs) report() *report.FilesystemReport {
+	state := report.FilesystemPlanningErrored
+	if f.planning.err == nil {
+		if f.planning.done {
+			if f.planned.stepErr != nil {
+				state = report.FilesystemSteppingErrored
+			} else if f.planned.step < len(f.planned.steps) {
+				state = report.FilesystemStepping
+			} else {
+				state = report.FilesystemDone
+			}
+		} else {
+			state = report.FilesystemPlanning
+		}
+	}
+	r := &report.FilesystemReport{
+		Info:        f.fs.ReportInfo(),
+		State:       state,
+		PlanError:   f.planning.err.IntoReportError(),
+		StepError:   f.planned.stepErr.IntoReportError(),
+		Steps:       make([]*report.StepReport, len(f.planned.steps)),
+		CurrentStep: f.planned.step,
+	}
+	for i := range r.Steps {
+		r.Steps[i] = f.planned.steps[i].report()
+	}
+	return r
+}
+
+// caller must hold lock l
+func (s *step) report() *report.StepReport {
+	r := &report.StepReport{
+		Info: s.step.ReportInfo(),
+	}
+	return r
+}
+
+//go:generate enumer -type=errorClass
+type errorClass int
+
+const (
+	errorClassPermanent errorClass = iota
+	errorClassTemporaryConnectivityRelated
+)
+
+type errorReport struct {
+	flattened []*timedError
+	// sorted DESCending by err time
+	byClass map[errorClass][]*timedError
+}
+
+// caller must hold lock l
+func (a *attempt) errorReport() *errorReport {
+	r := &errorReport{}
+	if a.planErr != nil {
+		r.flattened = append(r.flattened, a.planErr)
+	}
+	for _, fs := range a.fss {
+		if fs.planning.done && fs.planning.err != nil {
+			r.flattened = append(r.flattened, fs.planning.err)
+		} else if fs.planning.done && fs.planned.stepErr != nil {
+			r.flattened = append(r.flattened, fs.planned.stepErr)
+		}
+	}
+
+	// build byClass
+	{
+		r.byClass = make(map[errorClass][]*timedError)
+		putClass := func(err *timedError, class errorClass) {
+			errs := r.byClass[class]
+			errs = append(errs, err)
+			r.byClass[class] = errs
+		}
+		for _, err := range r.flattened {
+			if neterr, ok := err.Err.(net.Error); ok && neterr.Temporary() {
+				putClass(err, errorClassTemporaryConnectivityRelated)
+				continue
+			}
+			if st, ok := status.FromError(err.Err); ok && st.Code() == codes.Unavailable {
+				// technically, codes.Unavailable could be returned by the gRPC endpoint, indicating overload, etc.
+				// for now, let's assume it only happens for connectivity issues, as specified in
+				// https://grpc.io/grpc/core/md_doc_statuscodes.html
+				putClass(err, errorClassTemporaryConnectivityRelated)
+				continue
+			}
+			putClass(err, errorClassPermanent)
+		}
+		for _, errs := range r.byClass {
+			sort.Slice(errs, func(i, j int) bool {
+				return errs[i].Time.After(errs[j].Time) // sort descendingly
+			})
+		}
+	}
+
+	return r
+}
+
+func (r *errorReport) AnyError() *timedError {
+	for _, err := range r.flattened {
+		if err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func (r *errorReport) MostRecent() (err *timedError, errClass errorClass) {
+	for class, errs := range r.byClass {
+		// errs are sorted descendingly during construction
+		if len(errs) > 0 && (err == nil || errs[0].Time.After(err.Time)) {
+			err = errs[0]
+			errClass = class
+		}
+	}
+	return
+}

replication/driver/replication_driver_debug.go

@@ -0,0 +1,31 @@
+package driver
+
+import (
+	"fmt"
+	"os"
+)
+
+var debugEnabled bool = false
+
+func init() {
+	if os.Getenv("ZREPL_REPLICATION_DRIVER_DEBUG") != "" {
+		debugEnabled = true
+	}
+}
+
+//nolint[:deadcode,unused]
+func debug(format string, args ...interface{}) {
+	if debugEnabled {
+		fmt.Fprintf(os.Stderr, "repl: driver: %s\n", fmt.Sprintf(format, args...))
+	}
+}
+
+type debugFunc func(format string, args ...interface{})
+
+//nolint[:deadcode,unused]
+func debugPrefix(prefixFormat string, prefixFormatArgs ...interface{}) debugFunc {
+	prefix := fmt.Sprintf(prefixFormat, prefixFormatArgs...)
+	return func(format string, args ...interface{}) {
+		debug("%s: %s", prefix, fmt.Sprintf(format, args))
+	}
+}

replication/driver/replication_driver_logging.go

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

replication/driver/replication_driver_test.go

@@ -0,0 +1,216 @@
+package driver
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"sort"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/zrepl/zrepl/replication/report"
+
+	"github.com/stretchr/testify/assert"
+
+	jsondiff "github.com/yudai/gojsondiff"
+	jsondiffformatter "github.com/yudai/gojsondiff/formatter"
+)
+
+type mockPlanner struct {
+	stepCounter uint32
+	fss         []FS // *mockFS
+}
+
+func (p *mockPlanner) Plan(ctx context.Context) ([]FS, error) {
+	time.Sleep(1 * time.Second)
+	p.fss = []FS{
+		&mockFS{
+			&p.stepCounter,
+			"zroot/one",
+			nil,
+		},
+		&mockFS{
+			&p.stepCounter,
+			"zroot/two",
+			nil,
+		},
+	}
+	return p.fss, nil
+}
+
+func (p *mockPlanner) WaitForConnectivity(context.Context) error {
+	return nil
+}
+
+type mockFS struct {
+	globalStepCounter *uint32
+	name              string
+	steps             []Step
+}
+
+func (f *mockFS) EqualToPreviousAttempt(other FS) bool {
+	return f.name == other.(*mockFS).name
+}
+
+func (f *mockFS) PlanFS(ctx context.Context) ([]Step, error) {
+	if f.steps != nil {
+		panic("PlanFS used twice")
+	}
+	switch f.name {
+	case "zroot/one":
+		f.steps = []Step{
+			&mockStep{
+				fs:         f,
+				ident:      "a",
+				duration:   1 * time.Second,
+				targetDate: time.Unix(2, 0),
+			},
+			&mockStep{
+				fs:         f,
+				ident:      "b",
+				duration:   1 * time.Second,
+				targetDate: time.Unix(10, 0),
+			},
+			&mockStep{
+				fs:         f,
+				ident:      "c",
+				duration:   1 * time.Second,
+				targetDate: time.Unix(20, 0),
+			},
+		}
+	case "zroot/two":
+		f.steps = []Step{
+			&mockStep{
+				fs:         f,
+				ident:      "u",
+				duration:   500 * time.Millisecond,
+				targetDate: time.Unix(15, 0),
+			},
+			&mockStep{
+				fs:         f,
+				duration:   500 * time.Millisecond,
+				ident:      "v",
+				targetDate: time.Unix(30, 0),
+			},
+		}
+	default:
+		panic("unimplemented")
+	}
+
+	return f.steps, nil
+}
+
+func (f *mockFS) ReportInfo() *report.FilesystemInfo {
+	return &report.FilesystemInfo{Name: f.name}
+}
+
+type mockStep struct {
+	fs         *mockFS
+	ident      string
+	duration   time.Duration
+	targetDate time.Time
+
+	// filled by method Step
+	globalCtr uint32
+}
+
+func (f *mockStep) String() string {
+	return fmt.Sprintf("%s{%s} targetDate=%s globalCtr=%v", f.fs.name, f.ident, f.targetDate, f.globalCtr)
+}
+
+func (f *mockStep) Step(ctx context.Context) error {
+	f.globalCtr = atomic.AddUint32(f.fs.globalStepCounter, 1)
+	time.Sleep(f.duration)
+	return nil
+}
+
+func (f *mockStep) TargetEquals(s Step) bool {
+	return f.ident == s.(*mockStep).ident
+}
+
+func (f *mockStep) TargetDate() time.Time {
+	return f.targetDate
+}
+
+func (f *mockStep) ReportInfo() *report.StepInfo {
+	return &report.StepInfo{From: f.ident, To: f.ident, BytesExpected: 100, BytesReplicated: 25}
+}
+
+// TODO: add meaningful validation (i.e. actual checks)
+// Since the stepqueue is not deterministic due to scheduler jitter,
+// we cannot test for any definitive sequence of steps here.
+// Such checks would further only be sensible for a non-concurrent step-queue,
+// but we're going to have concurrent replication in the future.
+//
+// For the time being, let's just exercise the code a bit.
+func TestReplication(t *testing.T) {
+
+	ctx := context.Background()
+
+	mp := &mockPlanner{}
+	getReport, wait := Do(ctx, mp)
+	begin := time.Now()
+	fireAt := []time.Duration{
+		// the following values are relative to the start
+		500 * time.Millisecond,  // planning
+		1500 * time.Millisecond, // nothing is done, a is running
+		2500 * time.Millisecond, // a done,  b running
+		3250 * time.Millisecond, // a,b done, u running
+		3750 * time.Millisecond, // a,b,u done, c running
+		4750 * time.Millisecond, // a,b,u,c done, v running
+		5250 * time.Millisecond, // a,b,u,c,v done
+	}
+	reports := make([]*report.Report, len(fireAt))
+	for i := range fireAt {
+		sleepUntil := begin.Add(fireAt[i])
+		time.Sleep(time.Until(sleepUntil))
+		reports[i] = getReport()
+		// uncomment for viewing non-diffed results
+		// t.Logf("report @ %6.4f:\n%s", fireAt[i].Seconds(), pretty.Sprint(reports[i]))
+	}
+	waitBegin := time.Now()
+	wait(true)
+	waitDuration := time.Since(waitBegin)
+	assert.True(t, waitDuration < 10*time.Millisecond, "%v", waitDuration) // and that's gratious
+
+	prev, err := json.Marshal(reports[0])
+	require.NoError(t, err)
+	for _, r := range reports[1:] {
+		this, err := json.Marshal(r)
+		require.NoError(t, err)
+		differ := jsondiff.New()
+		diff, err := differ.Compare(prev, this)
+		require.NoError(t, err)
+		df := jsondiffformatter.NewDeltaFormatter()
+		_, err = df.Format(diff)
+		require.NoError(t, err)
+		// uncomment the following line to get json diffs between each captured step
+		// t.Logf("%s", res)
+		prev, err = json.Marshal(r)
+		require.NoError(t, err)
+	}
+
+	steps := make([]*mockStep, 0)
+	for _, fs := range mp.fss {
+		for _, step := range fs.(*mockFS).steps {
+			steps = append(steps, step.(*mockStep))
+		}
+	}
+
+	// sort steps in pq order (although, remember, pq is not deterministic)
+	sort.Slice(steps, func(i, j int) bool {
+		return steps[i].targetDate.Before(steps[j].targetDate)
+	})
+
+	// manual inspection of the globalCtr value should show that, despite
+	// scheduler-dependent behavior of pq, steps should generally be taken
+	// from oldest to newest target date (globally, not per FS).
+	t.Logf("steps sorted by target date:")
+	for _, step := range steps {
+		t.Logf("\t%s", step)
+	}
+
+}

replication/driver/replication_stepqueue.go

@@ -0,0 +1,163 @@
+package driver
+
+import (
+	"container/heap"
+	"time"
+
+	"github.com/zrepl/zrepl/util/chainlock"
+)
+
+type stepQueueRec struct {
+	ident      interface{}
+	targetDate time.Time
+	wakeup     chan StepCompletedFunc
+}
+
+type stepQueue struct {
+	stop chan struct{}
+	reqs chan stepQueueRec
+}
+
+type stepQueueHeapItem struct {
+	idx int
+	req stepQueueRec
+}
+type stepQueueHeap []*stepQueueHeapItem
+
+func (h stepQueueHeap) Less(i, j int) bool {
+	return h[i].req.targetDate.Before(h[j].req.targetDate)
+}
+
+func (h stepQueueHeap) Swap(i, j int) {
+	h[i], h[j] = h[j], h[i]
+	h[i].idx = i
+	h[j].idx = j
+}
+
+func (h stepQueueHeap) Len() int {
+	return len(h)
+}
+
+func (h *stepQueueHeap) Push(elem interface{}) {
+	hitem := elem.(*stepQueueHeapItem)
+	hitem.idx = h.Len()
+	*h = append(*h, hitem)
+}
+
+func (h *stepQueueHeap) Pop() interface{} {
+	elem := (*h)[h.Len()-1]
+	elem.idx = -1
+	*h = (*h)[:h.Len()-1]
+	return elem
+}
+
+// returned stepQueue must be closed with method Close
+func newStepQueue() *stepQueue {
+	q := &stepQueue{
+		stop: make(chan struct{}),
+		reqs: make(chan stepQueueRec),
+	}
+	return q
+}
+
+// the returned done function must be called to free resources
+// allocated by the call to Start
+//
+// No WaitReady calls must be active at the time done is called
+// The behavior of calling WaitReady after done was called is undefined
+func (q *stepQueue) Start(concurrency int) (done func()) {
+	if concurrency < 1 {
+		panic("concurrency must be >= 1")
+	}
+	// l protects pending and queueItems
+	l := chainlock.New()
+	pendingCond := l.NewCond()
+	// priority queue
+	pending := &stepQueueHeap{}
+	// ident => queueItem
+	queueItems := make(map[interface{}]*stepQueueHeapItem)
+	// stopped is used for cancellation of "wake" goroutine
+	stopped := false
+	active := 0
+	go func() { // "stopper" goroutine
+		<-q.stop
+		defer l.Lock().Unlock()
+		stopped = true
+		pendingCond.Broadcast()
+	}()
+	go func() { // "reqs" goroutine
+		for {
+			select {
+			case <-q.stop:
+				select {
+				case <-q.reqs:
+					panic("WaitReady call active while calling Close")
+				default:
+					return
+				}
+			case req := <-q.reqs:
+				func() {
+					defer l.Lock().Unlock()
+					if _, ok := queueItems[req.ident]; ok {
+						panic("WaitReady must not be called twice for the same ident")
+					}
+					qitem := &stepQueueHeapItem{
+						req: req,
+					}
+					queueItems[req.ident] = qitem
+					heap.Push(pending, qitem)
+					pendingCond.Broadcast()
+				}()
+			}
+		}
+	}()
+	go func() { // "wake" goroutine
+		defer l.Lock().Unlock()
+		for {
+
+			for !stopped && (active >= concurrency || pending.Len() == 0) {
+				pendingCond.Wait()
+			}
+			if stopped {
+				return
+			}
+			if pending.Len() <= 0 {
+				return
+			}
+			active++
+			next := heap.Pop(pending).(*stepQueueHeapItem).req
+			delete(queueItems, next.ident)
+
+			next.wakeup <- func() {
+				defer l.Lock().Unlock()
+				active--
+				pendingCond.Broadcast()
+			}
+		}
+	}()
+
+	done = func() {
+		close(q.stop)
+	}
+	return done
+}
+
+type StepCompletedFunc func()
+
+func (q *stepQueue) sendAndWaitForWakeup(ident interface{}, targetDate time.Time) StepCompletedFunc {
+	req := stepQueueRec{
+		ident,
+		targetDate,
+		make(chan StepCompletedFunc),
+	}
+	q.reqs <- req
+	return <-req.wakeup
+}
+
+// Wait for the ident with targetDate to be selected to run.
+func (q *stepQueue) WaitReady(ident interface{}, targetDate time.Time) StepCompletedFunc {
+	if targetDate.IsZero() {
+		panic("targetDate of zero is reserved for marking Done")
+	}
+	return q.sendAndWaitForWakeup(ident, targetDate)
+}

replication/driver/replication_stepqueue_test.go

@@ -0,0 +1,177 @@
+package driver
+
+import (
+	"fmt"
+	"math"
+	"sort"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/montanaflynn/stats"
+	"github.com/stretchr/testify/assert"
+)
+
+// FIXME: this test relies on timing and is thus rather flaky
+// (relies on scheduler responsivity of < 500ms)
+func TestPqNotconcurrent(t *testing.T) {
+	var ctr uint32
+	q := newStepQueue()
+	var wg sync.WaitGroup
+	wg.Add(4)
+	go func() {
+		defer wg.Done()
+		defer q.WaitReady("1", time.Unix(9999, 0))()
+		ret := atomic.AddUint32(&ctr, 1)
+		assert.Equal(t, uint32(1), ret)
+		time.Sleep(1 * time.Second)
+	}()
+
+	// give goroutine "1" 500ms to enter queue, get the active slot and enter time.Sleep
+	defer q.Start(1)()
+	time.Sleep(500 * time.Millisecond)
+
+	// while "1" is still running, queue in "2", "3" and "4"
+	go func() {
+		defer wg.Done()
+		defer q.WaitReady("2", time.Unix(2, 0))()
+		ret := atomic.AddUint32(&ctr, 1)
+		assert.Equal(t, uint32(2), ret)
+	}()
+	go func() {
+		defer wg.Done()
+		defer q.WaitReady("3", time.Unix(3, 0))()
+		ret := atomic.AddUint32(&ctr, 1)
+		assert.Equal(t, uint32(3), ret)
+	}()
+	go func() {
+		defer wg.Done()
+		defer q.WaitReady("4", time.Unix(4, 0))()
+		ret := atomic.AddUint32(&ctr, 1)
+		assert.Equal(t, uint32(4), ret)
+	}()
+
+	wg.Wait()
+}
+
+type record struct {
+	fs        int
+	step      int
+	globalCtr uint32
+	wakeAt    time.Duration // relative to begin
+}
+
+func (r record) String() string {
+	return fmt.Sprintf("fs %08d step %08d globalCtr %08d wakeAt %2.8f", r.fs, r.step, r.globalCtr, r.wakeAt.Seconds())
+}
+
+// This tests uses stepPq concurrently, simulating the following scenario:
+// Given a number of filesystems F, each filesystem has N steps to take.
+// The number of concurrent steps is limited to C.
+// The target date for each step is the step number N.
+// Hence, there are always F filesystems runnable (calling WaitReady)
+// The priority queue prioritizes steps with lower target data (= lower step number).
+// Hence, all steps with lower numbers should be woken up before steps with higher numbers.
+// However, scheduling is not 100% deterministic (runtime, OS scheduler, etc).
+// Hence, perform some statistics on the wakeup times and assert that the mean wakeup
+// times for each step are close together.
+func TestPqConcurrent(t *testing.T) {
+
+	q := newStepQueue()
+	var wg sync.WaitGroup
+	filesystems := 100
+	stepsPerFS := 20
+	sleepTimePerStep := 50 * time.Millisecond
+	wg.Add(filesystems)
+	var globalCtr uint32
+
+	begin := time.Now()
+	records := make(chan []record, filesystems)
+	for fs := 0; fs < filesystems; fs++ {
+		go func(fs int) {
+			defer wg.Done()
+			recs := make([]record, 0)
+			for step := 0; step < stepsPerFS; step++ {
+				pos := atomic.AddUint32(&globalCtr, 1)
+				t := time.Unix(int64(step), 0)
+				done := q.WaitReady(fs, t)
+				wakeAt := time.Since(begin)
+				time.Sleep(sleepTimePerStep)
+				done()
+				recs = append(recs, record{fs, step, pos, wakeAt})
+			}
+			records <- recs
+		}(fs)
+	}
+	concurrency := 5
+	defer q.Start(concurrency)()
+	wg.Wait()
+	close(records)
+	t.Logf("loop done")
+
+	flattenedRecs := make([]record, 0)
+	for recs := range records {
+		flattenedRecs = append(flattenedRecs, recs...)
+	}
+
+	sort.Slice(flattenedRecs, func(i, j int) bool {
+		return flattenedRecs[i].globalCtr < flattenedRecs[j].globalCtr
+	})
+
+	wakeTimesByStep := map[int][]float64{}
+	for _, rec := range flattenedRecs {
+		wakeTimes, ok := wakeTimesByStep[rec.step]
+		if !ok {
+			wakeTimes = []float64{}
+		}
+		wakeTimes = append(wakeTimes, rec.wakeAt.Seconds())
+		wakeTimesByStep[rec.step] = wakeTimes
+	}
+
+	meansByStepId := make([]float64, stepsPerFS)
+	interQuartileRangesByStepIdx := make([]float64, stepsPerFS)
+	for step := 0; step < stepsPerFS; step++ {
+		t.Logf("step %d", step)
+		mean, _ := stats.Mean(wakeTimesByStep[step])
+		meansByStepId[step] = mean
+		t.Logf("\tmean: %v", mean)
+		median, _ := stats.Median(wakeTimesByStep[step])
+		t.Logf("\tmedian: %v", median)
+		midhinge, _ := stats.Midhinge(wakeTimesByStep[step])
+		t.Logf("\tmidhinge: %v", midhinge)
+		min, _ := stats.Min(wakeTimesByStep[step])
+		t.Logf("\tmin: %v", min)
+		max, _ := stats.Max(wakeTimesByStep[step])
+		t.Logf("\tmax: %v", max)
+		quartiles, _ := stats.Quartile(wakeTimesByStep[step])
+		t.Logf("\t%#v", quartiles)
+		interQuartileRange, _ := stats.InterQuartileRange(wakeTimesByStep[step])
+		t.Logf("\tinter-quartile range: %v", interQuartileRange)
+		interQuartileRangesByStepIdx[step] = interQuartileRange
+	}
+
+	iqrMean, _ := stats.Mean(interQuartileRangesByStepIdx)
+	t.Logf("inter-quartile-range mean: %v", iqrMean)
+	iqrDev, _ := stats.StandardDeviation(interQuartileRangesByStepIdx)
+	t.Logf("inter-quartile-range deviation: %v", iqrDev)
+
+	// each step should have the same "distribution" (=~ "spread")
+	assert.True(t, iqrDev < 0.01)
+
+	minTimeForAllStepsWithIdxI := sleepTimePerStep.Seconds() * float64(filesystems) / float64(concurrency)
+	t.Logf("minTimeForAllStepsWithIdxI = %11.8f", minTimeForAllStepsWithIdxI)
+	for i, mean := range meansByStepId {
+		// we can't just do (i + 0.5) * minTimeforAllStepsWithIdxI
+		// because this doesn't account for drift
+		idealMean := 0.5 * minTimeForAllStepsWithIdxI
+		if i > 0 {
+			previousMean := meansByStepId[i-1]
+			idealMean = previousMean + minTimeForAllStepsWithIdxI
+		}
+		deltaFromIdeal := idealMean - mean
+		t.Logf("step %02d delta from ideal mean wake time: %11.8f - %11.8f = %11.8f", i, idealMean, mean, deltaFromIdeal)
+		assert.True(t, math.Abs(deltaFromIdeal) < 0.05)
+	}
+
+}