build: use go 1.19 for testing & release builds

New docker image since the old one was deprecated, according to https://discuss.circleci.com/t/go-lang-docker-image-circleci-golang-1-19-is-missing/44961
build: update golangci-lint
2022-10-24 22:37:35 +02:00 · 2022-10-24 22:22:41 +02:00
53 changed files with 2431 additions and 4167 deletions
@@ -1,8 +1,5 @@
 version: 2.1
-orbs:
-  # NB: 1.7.2 is not the Go version, but the Orb version
-  # https://circleci.com/developer/orbs/orb/circleci/go#usage-go-modules-cache
-  go: circleci/go@1.7.2
+
 commands:
  setup-home-local-bin:
    steps:
@@ -27,12 +24,18 @@ commands:

  apt-update-and-install-common-deps:
    steps:
-      - run: sudo apt-get update
-      - run: sudo apt-get install -y gawk make
-      # CircleCI doesn't update its cimg/go images.
-      # So, need to update manually to get up-to-date trust chains.
-      # The need for this was required for cimg/go:1.12, but let's future proof this here and now.
-      - run: sudo apt-get install -y git ca-certificates
+      - run: sudo apt update && sudo apt install gawk make
+
+  restore-cache-gomod:
+    steps:
+      - restore_cache:
+          key: go-mod-v4-{{ checksum "go.sum" }}
+  save-cache-gomod:
+    steps:
+      - save_cache:
+          key: go-mod-v4-{{ checksum "go.sum" }}
+          paths:
+            - "/go/pkg/mod"

  install-godep:
    steps:
@@ -47,41 +50,94 @@ commands:
      - invoke-lazy-sh:
          subcommand: docdep

-  docs-publish-sh:
+  download-and-install-minio-client:
+    steps:
+      - setup-home-local-bin
+      - restore_cache:
+          key: minio-client-v2
+      - run:
+          shell: /bin/bash -eo pipefail
+          command: |
+            if which mc; then exit 0; fi
+            sudo curl -sSL https://dl.min.io/client/mc/release/linux-amd64/archive/mc.RELEASE.2020-08-20T00-23-01Z \
+              -o "$HOME/.local/bin/mc"
+            sudo chmod +x "$HOME/.local/bin/mc"
+      - save_cache:
+          key: minio-client-v2
+          paths:
+            - "$HOME/.local/bin/mc"
+
+  upload-minio:
    parameters:
-      push:
-        type: boolean
+      src:
+        type: string
+      dst:
+        type: string
    steps:
-      - checkout
      - run:
+          shell: /bin/bash -eo pipefail
+          when: always
          command: |
-            git config --global user.email "zreplbot@cschwarz.com"
-            git config --global user.name "zrepl-github-io-ci"
+            if [ -n "$CIRCLE_PR_NUMBER" ]; then # CIRCLE_PR_NUMBER is guaranteed to be only present in forked PRs (external)
+              echo "Forked PR detected. Sry, can't trust you with credentials to external artifact store, use CircleCI's instead."
+              exit 0
+            fi
+            set -u # from now on

-      # https://circleci.com/docs/2.0/add-ssh-key/#adding-multiple-keys-with-blank-hostnames
-      - run: ssh-add -D
-      # the default circleci ssh config only additional ssh keys for Host !github.com
+            mc config host add --api s3v4 zrepl-minio https://minio.cschwarz.com ${MINIO_ACCESS_KEY} ${MINIO_SECRET_KEY}
+
+            # keep in sync with set-github-minio-status
+            jobprefix=zrepl-ci-artifacts/${CIRCLE_SHA1}-pipeline-<<pipeline.number>>/${CIRCLE_JOB}
+
+            # Upload artifacts
+            mkdir -p ./artifacts
+            mc cp -r <<parameters.src>> "zrepl-minio/$jobprefix/<<parameters.dst>>"
+
+  set-github-minio-status:
+    parameters:
+      context:
+        type: string
+      description:
+        type: string
+      minio-dst:
+        type: string
+    steps:
      - run:
+          shell: /bin/bash -eo pipefail
          command: |
-            cat > ~/.ssh/config \<<EOF
-            Host *
-              IdentityFile /home/circleci/.ssh/id_rsa_458e62c517f6c480e40452126ce47421
-            EOF
-      - add_ssh_keys:
-          fingerprints:
-            # deploy key for zrepl.github.io
-            - "45:8e:62:c5:17:f6:c4:80:e4:04:52:12:6c:e4:74:21"
+            if [ -n "$CIRCLE_PR_NUMBER" ]; then # CIRCLE_PR_NUMBER is guaranteed to be only present in forked PRs (external)
+              echo "Forked PR detected. Sry, can't trust you with credentials to external artifact store, use CircleCI's instead."
+              exit 0
+            fi
+            set -u # from now on

-      # caller must install-docdep
-      - when:
-          condition: << parameters.push >>
+            # keep in sync with with upload-minio command
+            jobprefix=zrepl-ci-artifacts/${CIRCLE_SHA1}-pipeline-<<pipeline.number>>/${CIRCLE_JOB}
+            # Push Artifact Link to GitHub
+            REPO="zrepl/zrepl"
+            COMMIT="${CIRCLE_SHA1}"
+            JOB_NAME="${CIRCLE_JOB}"
+            CONTEXT="<<parameters.context>>"
+            DESCRIPTION="<<parameters.description>>"
+            TARGETURL=https://minio.cschwarz.com/minio/"$jobprefix"/"<<parameters.minio-dst>>"
+            curl "https://api.github.com/repos/$REPO/statuses/$COMMIT" \
+              -H "Content-Type: application/json" \
+              -H "Authorization: token $GITHUB_COMMIT_STATUS_TOKEN" \
+              -X POST \
+              -d '{"context":"'"$CONTEXT"'", "state": "success", "description":"'"$DESCRIPTION"'", "target_url":"'"$TARGETURL"'"}'
+
+
+  trigger-pipeline:
+    parameters:
+      body_no_shell_subst:
+        type: string
    steps:
-            - run: bash -x docs/publish.sh -c -a -P
-      - when:
-          condition:
-            not: << parameters.push >>
-          steps:
-            - run: bash -x docs/publish.sh -c -a
+      - run: |
+          curl -X POST https://circleci.com/api/v2/project/github/zrepl/zrepl/pipeline \
+            -H 'Content-Type: application/json' \
+            -H 'Accept: application/json' \
+            -H "Circle-Token: $ZREPL_BOT_CIRCLE_TOKEN" \
+            --data '<<parameters.body_no_shell_subst>>'

 parameters:
  do_ci:
@@ -94,7 +150,7 @@ parameters:

  release_docker_baseimage_tag:
    type: string
-    default: "1.21"
+    default: "1.19"

 workflows:
  version: 2
@@ -104,19 +160,19 @@ workflows:
    jobs:
      - quickcheck-docs
      - quickcheck-go: &quickcheck-go-smoketest
-          name: quickcheck-go-amd64-linux-1.21
-          goversion: &latest-go-release "1.21"
+          name: quickcheck-go-amd64-linux-1.19
+          goversion: &latest-go-release "1.19"
          goos: linux
          goarch: amd64
      - test-go-on-latest-go-release:
          goversion: *latest-go-release
      - quickcheck-go:
          requires:
-            - quickcheck-go-amd64-linux-1.21 #quickcheck-go-smoketest.name
+            - quickcheck-go-amd64-linux-1.19 #quickcheck-go-smoketest.name
          matrix: &quickcheck-go-matrix
            alias: quickcheck-go-matrix
            parameters:
-              goversion: [*latest-go-release, "1.20"]
+              goversion: [*latest-go-release, "1.12"]
              goos: ["linux", "freebsd"]
              goarch: ["amd64", "arm64"]
            exclude:
@@ -124,14 +180,10 @@ workflows:
              - goversion: *latest-go-release
                goos: linux
                goarch: amd64
-      - platformtest:
-          matrix:
-            parameters:
-              goversion: [*latest-go-release]
-              goos: ["linux"]
-              goarch: ["amd64"]
-          requires:
-            - quickcheck-go-<< matrix.goarch >>-<< matrix.goos >>-<< matrix.goversion >>
+              # not supported by Go 1.12
+              - goversion: "1.12"
+                goos: freebsd
+                goarch: arm64

  release:
    when: << pipeline.parameters.do_release >>
@@ -149,7 +201,20 @@ workflows:
            - release-deb
            - release-rpm

-  publish-zrepl.github.io:
+  periodic:
+    triggers:
+      - schedule:
+          cron: "00 17 * * *"
+          filters:
+            branches:
+              only:
+                - master
+                - stable
+                - problame/circleci-build
+    jobs:
+      - periodic-full-pipeline-run
+
+  zrepl.github.io:
    jobs:
      - publish-zrepl-github-io:
          filters:
@@ -160,15 +225,20 @@ workflows:
 jobs:
  quickcheck-docs:
    docker:
-      - image: cimg/base:2023.09
+      - image: cimg/base:2020.08
    steps:
      - checkout
      - install-docdep
-      # do the current docs build
      - run: make docs
-      # does the publish.sh script still work?
-      - docs-publish-sh:
-          push: false
+
+      - download-and-install-minio-client
+      - upload-minio:
+          src: artifacts
+          dst: ""
+      - set-github-minio-status:
+          context: artifacts/${CIRCLE_JOB}
+          description: artifacts of CI job ${CIRCLE_JOB}
+          minio-dst: ""

  quickcheck-go:
    parameters:
@@ -187,48 +257,29 @@ jobs:
    steps:
      - checkout

-      - go/load-cache:
-          key: quickcheck-<<parameters.goversion>>
-      - install-godep
+      - restore-cache-gomod
      - run: go mod download
      - run: cd build && go mod download
-      - go/save-cache:
-          key: quickcheck-<<parameters.goversion>>
+      - save-cache-gomod

+      - install-godep
      - run: make formatcheck
      - run: make generate-platform-test-list
      - run: make zrepl-bin test-platform-bin
      - run: make vet
      - run: make lint

+      - download-and-install-minio-client
      - run: rm -f artifacts/generate-platform-test-list
      - store_artifacts:
          path: artifacts
-      - persist_to_workspace:
-          root: .
-          paths: [.]
-
-  platformtest:
-    parameters:
-      goversion:
-        type: string
-      goos:
-        type: string
-      goarch:
-        type: string
-    machine:
-      image: ubuntu-2204:current
-    resource_class: medium
-    environment:
-      GOOS: <<parameters.goos>>
-      GOARCH: <<parameters.goarch>>
-    steps:
-      - attach_workspace:
-          at: .
-      - run: sudo apt-get update
-      - run: sudo apt-get install -y zfsutils-linux
-      - run: sudo zfs version
-      - run: sudo make test-platform GOOS="$GOOS" GOARCH="$GOARCH"
+      - upload-minio:
+          src: artifacts
+          dst: ""
+      - set-github-minio-status:
+          context: artifacts/${CIRCLE_JOB}
+          description: artifacts of CI job ${CIRCLE_JOB}
+          minio-dst: ""

  test-go-on-latest-go-release:
    parameters:
@@ -238,11 +289,9 @@ jobs:
      - image: cimg/go:<<parameters.goversion>>
    steps:
      - checkout
-      - go/load-cache:
-          key: make-test-go
+      - restore-cache-gomod
      - run: make test-go
-      - go/save-cache:
-          key: make-test-go
+      # don't save-cache-gomod here, test-go doesn't pull all the dependencies

  release-build:
    machine:
@@ -283,15 +332,48 @@ jobs:
    steps:
      - attach_workspace:
          at: .
-      - run: make wrapup-and-checksum
      - store_artifacts:
          path: artifacts
+      - download-and-install-minio-client
+      - upload-minio:
+          src: artifacts
+          dst: ""
+      - set-github-minio-status:
+          context: artifacts/release
+          description: CI-generated release artifacts
+          minio-dst: ""
+
+  periodic-full-pipeline-run:
+    docker:
+      - image: cimg/base:2020.08
+    steps:
+      - trigger-pipeline:
+          body_no_shell_subst: '{"branch":"<<pipeline.git.branch>>", "parameters": { "do_ci": true, "do_release": true }}'

  publish-zrepl-github-io:
    docker:
-      - image: cimg/base:2023.09
+      - image: cimg/python:3.7
    steps:
      - checkout
-      - install-docdep
-      - docs-publish-sh:
-          push: true
+      - invoke-lazy-sh:
+          subcommand: docdep
+      - run:
+          command: |
+            git config --global user.email "zreplbot@cschwarz.com"
+            git config --global user.name "zrepl-github-io-ci"
+
+      # https://circleci.com/docs/2.0/add-ssh-key/#adding-multiple-keys-with-blank-hostnames
+      - run: ssh-add -D
+      # the default circleci ssh config only additional ssh keys for Host !github.com
+      - run:
+          command: |
+            cat > ~/.ssh/config \<<EOF
+            Host *
+              IdentityFile /home/circleci/.ssh/id_rsa_458e62c517f6c480e40452126ce47421
+            EOF
+      - add_ssh_keys:
+          fingerprints:
+            # deploy key for zrepl.github.io
+            - "45:8e:62:c5:17:f6:c4:80:e4:04:52:12:6c:e4:74:21"
+
+      - run: bash -x docs/publish.sh -c -a
@@ -1,84 +0,0 @@
-import argparse
-from pathlib import Path
-import re
-
-import requests
-
-import time
-
-import os
-import argparse
-from pathlib import Path
-
-
-circle_token = os.environ.get('CIRCLE_TOKEN')
-if not circle_token:
-    raise ValueError('CIRCLE_TOKEN environment variable not set')
-
-parser = argparse.ArgumentParser(description='Download artifacts from CircleCI')
-parser.add_argument('build_num', type=str, help='Build number')
-parser.add_argument('dst', type=Path, help='Destination directory')
-parser.add_argument('--prefix', type=str, default='', help='Filter for prefix')
-parser.add_argument('--match', type=str, default='.*', help='Only include paths matching the given regex')
-
-args = parser.parse_args()
-
-res = requests.get(
-    f"https://circleci.com/api/v1.1/project/github/zrepl/zrepl/{args.build_num}/artifacts",
-    headers={
-        "Circle-Token": circle_token,
-    },
-)
-res.raise_for_status()
-
-# https://circleci.com/docs/api/v1/index.html#artifacts-of-a-job
-# [ {
-#   "path" : "raw-test-output/go-test-report.xml",
-#   "pretty_path" : "raw-test-output/go-test-report.xml",
-#   "node_index" : 0,
-#   "url" : "https://24-88881093-gh.circle-artifacts.com/0/raw-test-output/go-test-report.xml"
-# }, {
-#   "path" : "raw-test-output/go-test.out",
-#   "pretty_path" : "raw-test-output/go-test.out",
-#   "node_index" : 0,
-#   "url" : "https://24-88881093-gh.circle-artifacts.com/0/raw-test-output/go-test.out"
-# } ]
-res = res.json()
-
-for artifact in res:
-    if not artifact["pretty_path"].startswith(args.prefix):
-        continue
-    if not re.match(args.match, artifact["pretty_path"]):
-        continue
-    stripped = artifact["pretty_path"][len(args.prefix):]
-    print(f"Downloading {artifact['pretty_path']} to {args.dst / stripped}")
-    artifact_rel = Path(stripped)
-    artifact_dst = args.dst / artifact_rel
-    artifact_dst.parent.mkdir(parents=True, exist_ok=True)
-
-    res = requests.get(
-        artifact["url"],
-        headers={
-            "Circle-Token": circle_token,
-        },
-        stream=True,
-    )
-    res.raise_for_status()
-
-    total_size = int(res.headers.get("Content-Length", 0))
-    block_size = 128 * 1024
-    with open(artifact_dst, "wb") as f:
-        progress = 0
-        start_time = time.time()
-        for chunk in res.iter_content(chunk_size=block_size):
-            f.write(chunk)
-            progress += len(chunk)
-            percent = progress / total_size * 100
-            elapsed_time = time.time() - start_time
-            if elapsed_time >= 5:
-                print(f"Downloaded {progress}/{total_size} bytes ({percent:.2f}%)", end="\r")
-                start_time = time.time()
-        print(f"Downloaded {progress}/{total_size} bytes ({percent:.2f}%)")
-    print("Download complete!")
-
-print("All files downloaded")
@@ -28,7 +28,7 @@ GO_BUILDFLAGS := $(GO_MOD_READONLY) $(GO_EXTRA_BUILDFLAGS)
 GO_BUILD := $(GO_ENV_VARS) $(GO) build $(GO_BUILDFLAGS) -ldflags $(GO_LDFLAGS)
 GOLANGCI_LINT := golangci-lint
 GOCOVMERGE := gocovmerge
-RELEASE_DOCKER_BASEIMAGE_TAG ?= 1.21
+RELEASE_DOCKER_BASEIMAGE_TAG ?= 1.19
 RELEASE_DOCKER_BASEIMAGE ?= golang:$(RELEASE_DOCKER_BASEIMAGE_TAG)

 ifneq ($(GOARM),)
@@ -52,6 +52,12 @@ release: clean
 	$(MAKE) test-go
 	$(MAKE) bins-all
 	$(MAKE) noarch
+	$(MAKE) wrapup-and-checksum
+	$(MAKE) check-git-clean
+ifeq (SIGN, 1)
+	$(MAKE) sign
+endif
+	@echo "ZREPL RELEASE ARTIFACTS AVAILABLE IN artifacts/release"

 release-docker: $(ARTIFACTDIR)
 	sed 's/FROM.*!SUBSTITUTED_BY_MAKEFILE/FROM $(RELEASE_DOCKER_BASEIMAGE)/' build.Dockerfile > artifacts/release-docker.Dockerfile
@@ -128,17 +134,11 @@ endif

 deb-docker:
 	docker build -t zrepl_debian_pkg --pull -f packaging/deb/Dockerfile .
-	# Use a small open file limit to make fakeroot work. If we don't
-	# specify it, docker daemon will use its file limit. I don't know
-	# what changed (Docker, its systemd service, its Go version). But I
-	# observed fakeroot iterating close(i) up to i > 1000000, which costs
-	# a good amount of CPU time and makes the build slow.
 	docker run --rm -i -v $(CURDIR):/build/src -u $$(id -u):$$(id -g) \
-		--ulimit nofile=1024:1024 \
 		zrepl_debian_pkg \
 		make deb GOOS=$(GOOS) GOARCH=$(GOARCH) GOARM=$(GOARM)

-# expects `release`, `deb` & `rpm` targets to have run before
+# expects `release` target to have run before
 NOARCH_TARBALL := $(ARTIFACTDIR)/zrepl-noarch.tar
 wrapup-and-checksum:
 	rm -f $(NOARCH_TARBALL)
@@ -175,21 +175,16 @@ check-git-clean:

 tag-release:
 	test -n "$(ZREPL_TAG_VERSION)" || exit 1
-	git tag -u '328A6627FA98061D!' -m "$(ZREPL_TAG_VERSION)" "$(ZREPL_TAG_VERSION)"
+	git tag -u E27CA5FC -m "$(ZREPL_TAG_VERSION)" "$(ZREPL_TAG_VERSION)"

 sign:
-	gpg -u '328A6627FA98061D!' \
+	gpg -u "89BC 5D89 C845 568B F578  B306 CDBD 8EC8 E27C A5FC" \
 		--armor \
 		--detach-sign $(ARTIFACTDIR)/release/sha512sum.txt

 clean: docs-clean
 	rm -rf "$(ARTIFACTDIR)"

-download-circleci-release:
-	rm -rf "$(ARTIFACTDIR)"
-	mkdir -p "$(ARTIFACTDIR)/release"
-	python3 .circleci/download_artifacts.py --prefix 'artifacts/release/' "$(BUILD_NUM)" "$(ARTIFACTDIR)/release"
-
 ##################### BINARIES #####################
 .PHONY: bins-all lint test-go test-platform cover-merge cover-html vet zrepl-bin test-platform-bin generate-platform-test-list

@@ -2,18 +2,12 @@ FROM !SUBSTITUTED_BY_MAKEFILE

 RUN apt-get update && apt-get install -y \
    python3-pip \
-    python3-venv \
    unzip \
    gawk

 ADD build.installprotoc.bash ./
 RUN bash build.installprotoc.bash

-# setup venv
-ENV VIRTUAL_ENV=/opt/venv
-RUN python3 -m venv $VIRTUAL_ENV
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-
 ADD lazy.sh /tmp/lazy.sh
 ADD docs/requirements.txt /tmp/requirements.txt
 ENV ZREPL_LAZY_DOCS_REQPATH=/tmp/requirements.txt
@@ -4,37 +4,10 @@ go 1.12

 require (
 	github.com/alvaroloes/enumer v1.1.1
-	github.com/breml/bidichk v0.2.6 // indirect
-	github.com/breml/errchkjson v0.3.5 // indirect
-	github.com/chavacava/garif v0.1.0 // indirect
-	github.com/daixiang0/gci v0.11.1 // indirect
-	github.com/golangci/golangci-lint v1.54.2
-	github.com/golangci/revgrep v0.5.0 // indirect
-	github.com/hashicorp/errwrap v1.1.0 // indirect
-	github.com/jgautheron/goconst v1.6.0 // indirect
-	github.com/mattn/go-isatty v0.0.19 // indirect
-	github.com/mattn/go-runewidth v0.0.15 // indirect
-	github.com/mgechev/revive v1.3.3 // indirect
-	github.com/pelletier/go-toml/v2 v2.1.0 // indirect
-	github.com/polyfloyd/go-errorlint v1.4.5 // indirect
-	github.com/prometheus/client_golang v1.16.0 // indirect
-	github.com/prometheus/common v0.44.0 // indirect
-	github.com/prometheus/procfs v0.11.1 // indirect
-	github.com/rivo/uniseg v0.4.4 // indirect
-	github.com/ryanrolds/sqlclosecheck v0.5.1 // indirect
-	github.com/spf13/viper v1.16.0 // indirect
-	github.com/stretchr/objx v0.5.1 // indirect
-	github.com/subosito/gotenv v1.6.0 // indirect
-	github.com/tetafro/godot v1.4.15 // indirect
+	github.com/golangci/golangci-lint v1.50.1
+	github.com/spf13/jwalterweatherman v1.1.0 // indirect
 	github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad
-	github.com/xen0n/gosmopolitan v1.2.2 // indirect
-	gitlab.com/bosi/decorder v0.4.1 // indirect
-	go.uber.org/multierr v1.11.0 // indirect
-	go.uber.org/zap v1.25.0 // indirect
-	golang.org/x/exp v0.0.0-20230905200255-921286631fa9 // indirect
-	golang.org/x/exp/typeparams v0.0.0-20230905200255-921286631fa9 // indirect
-	golang.org/x/tools v0.13.0
-	google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.1.0
-	google.golang.org/protobuf v1.31.0
-	mvdan.cc/unparam v0.0.0-20230815095028-f7c6fb1088f0 // indirect
+	golang.org/x/tools v0.2.0
+	google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.1.0 // indirect
+	google.golang.org/protobuf v1.28.0
 )
@@ -374,7 +374,6 @@ func renderReplicationReport(t *stringbuilder.B, rep *report.Report, history *by
 			eta = time.Duration((float64(expected)-float64(replicated))/float64(rate)) * time.Second
 		}

-		if !latest.State.IsTerminal() {
 		t.Write("Progress: ")
 		t.DrawBar(50, replicated, expected, changeCount)
 		t.Write(fmt.Sprintf(" %s / %s @ %s/s", ByteCountBinaryUint(replicated), ByteCountBinaryUint(expected), ByteCountBinary(rate)))
@@ -382,7 +381,6 @@ func renderReplicationReport(t *stringbuilder.B, rep *report.Report, history *by
 			t.Write(fmt.Sprintf(" (%s remaining)", humanizeDuration(eta)))
 		}
 		t.Newline()
-		}
 		if containsInvalidSizeEstimates {
 			t.Write("NOTE: not all steps could be size-estimated, total estimate is likely imprecise!")
 			t.Newline()
@@ -495,7 +493,6 @@ func renderPrunerReport(t *stringbuilder.B, r *pruner.Report, fsfilter FilterFun
 	}

 	// global progress bar
-	if !state.IsTerminal() {
 	progress := int(math.Round(80 * float64(completedDestroyCount) / float64(totalDestroyCount)))
 	t.Write("Progress: ")
 	t.Write("[")
@@ -505,7 +502,6 @@ func renderPrunerReport(t *stringbuilder.B, r *pruner.Report, fsfilter FilterFun
 	t.Write("]")
 	t.Printf(" %d/%d snapshots", completedDestroyCount, totalDestroyCount)
 	t.Newline()
-	}

 	sort.SliceStable(all, func(i, j int) bool {
 		return strings.Compare(all[i].Filesystem, all[j].Filesystem) == -1
@@ -6,6 +6,8 @@ import (
 	"log/syslog"
 	"os"
 	"reflect"
+	"regexp"
+	"strconv"
 	"time"

 	"github.com/pkg/errors"
@@ -65,6 +67,7 @@ type ActiveJob struct {
 	Name               string                `yaml:"name"`
 	Connect            ConnectEnum           `yaml:"connect"`
 	Pruning            PruningSenderReceiver `yaml:"pruning"`
+	Debug              JobDebugSettings      `yaml:"debug,optional"`
 	Replication        *Replication          `yaml:"replication,optional,fromdefaults"`
 	ConflictResolution *ConflictResolution   `yaml:"conflict_resolution,optional,fromdefaults"`
 }
@@ -77,12 +80,14 @@ type PassiveJob struct {
 	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"`
 }
@@ -185,10 +190,13 @@ func (i *PositiveDurationOrManual) UnmarshalYAML(u func(interface{}, bool) error
 		return fmt.Errorf("value must not be empty")
 	default:
 		i.Manual = false
-		i.Interval, err = parsePositiveDuration(s)
+		i.Interval, err = time.ParseDuration(s)
 		if err != nil {
 			return err
 		}
+		if i.Interval <= 0 {
+			return fmt.Errorf("value must be a positive duration, got %q", s)
+		}
 	}
 	return nil
 }
@@ -222,9 +230,8 @@ type SnapshottingEnum struct {
 type SnapshottingPeriodic struct {
 	Type     string        `yaml:"type"`
 	Prefix   string        `yaml:"prefix"`
-	Interval        *PositiveDuration `yaml:"interval"`
+	Interval time.Duration `yaml:"interval,positive"`
 	Hooks    HookList      `yaml:"hooks,optional"`
-	TimestampFormat string            `yaml:"timestamp_format,optional,default=dense"`
 }

 type CronSpec struct {
@@ -257,7 +264,6 @@ type SnapshottingCron struct {
 	Prefix string   `yaml:"prefix"`
 	Cron   CronSpec `yaml:"cron"`
 	Hooks  HookList `yaml:"hooks,optional"`
-	TimestampFormat string   `yaml:"timestamp_format,optional,default=dense"`
 }

 type SnapshottingManual struct {
@@ -477,6 +483,14 @@ type GlobalStdinServer struct {
 	SockDir string `yaml:"sockdir,default=/var/run/zrepl/stdinserver"`
 }

+type JobDebugSettings struct {
+	Conn *struct {
+		ReadDump  string `yaml:"read_dump"`
+		WriteDump string `yaml:"write_dump"`
+	} `yaml:"conn,optional"`
+	RPCLog bool `yaml:"rpc_log,optional,default=false"`
+}
+
 type HookList []HookEnum

 type HookEnum struct {
@@ -701,3 +715,41 @@ func ParseConfigBytes(bytes []byte) (*Config, error) {
 	}
 	return c, nil
 }
+
+var durationStringRegex *regexp.Regexp = regexp.MustCompile(`^\s*(\d+)\s*(s|m|h|d|w)\s*$`)
+
+func parsePositiveDuration(e string) (d time.Duration, err error) {
+	comps := durationStringRegex.FindStringSubmatch(e)
+	if len(comps) != 3 {
+		err = fmt.Errorf("does not match regex: %s %#v", e, comps)
+		return
+	}
+
+	durationFactor, err := strconv.ParseInt(comps[1], 10, 64)
+	if err != nil {
+		return 0, err
+	}
+	if durationFactor <= 0 {
+		return 0, errors.New("duration must be positive integer")
+	}
+
+	var durationUnit time.Duration
+	switch comps[2] {
+	case "s":
+		durationUnit = time.Second
+	case "m":
+		durationUnit = time.Minute
+	case "h":
+		durationUnit = time.Hour
+	case "d":
+		durationUnit = 24 * time.Hour
+	case "w":
+		durationUnit = 24 * 7 * time.Hour
+	default:
+		err = fmt.Errorf("contains unknown time unit '%s'", comps[2])
+		return
+	}
+
+	d = time.Duration(durationFactor) * durationUnit
+	return
+}
@@ -1,106 +0,0 @@
-package config
-
-import (
-	"errors"
-	"fmt"
-	"regexp"
-	"strconv"
-	"time"
-
-	"github.com/kr/pretty"
-	"github.com/zrepl/yaml-config"
-)
-
-type Duration struct{ d time.Duration }
-
-func (d Duration) Duration() time.Duration { return d.d }
-
-var _ yaml.Unmarshaler = &Duration{}
-
-func (d *Duration) UnmarshalYAML(unmarshal func(v interface{}, not_strict bool) error) error {
-	var s string
-	err := unmarshal(&s, false)
-	if err != nil {
-		return err
-	}
-	d.d, err = parseDuration(s)
-	if err != nil {
-		d.d = 0
-		return &yaml.TypeError{Errors: []string{fmt.Sprintf("cannot parse value %q: %s", s, err)}}
-	}
-	return nil
-}
-
-type PositiveDuration struct{ d Duration }
-
-var _ yaml.Unmarshaler = &PositiveDuration{}
-
-func (d PositiveDuration) Duration() time.Duration { return d.d.Duration() }
-
-func (d *PositiveDuration) UnmarshalYAML(unmarshal func(v interface{}, not_strict bool) error) error {
-	err := d.d.UnmarshalYAML(unmarshal)
-	if err != nil {
-		return err
-	}
-	if d.d.Duration() <= 0 {
-		return fmt.Errorf("duration must be positive, got %s", d.d.Duration())
-	}
-	return nil
-}
-
-func parsePositiveDuration(e string) (time.Duration, error) {
-	d, err := parseDuration(e)
-	if err != nil {
-		return d, err
-	}
-	if d <= 0 {
-		return 0, errors.New("duration must be positive integer")
-	}
-	return d, err
-}
-
-var durationStringRegex *regexp.Regexp = regexp.MustCompile(`^\s*([\+-]?\d+)\s*(|s|m|h|d|w)\s*$`)
-
-func parseDuration(e string) (d time.Duration, err error) {
-	comps := durationStringRegex.FindStringSubmatch(e)
-	if comps == nil {
-		err = fmt.Errorf("must match %s", durationStringRegex)
-		return
-	}
-	if len(comps) != 3 {
-		panic(pretty.Sprint(comps))
-	}
-
-	durationFactor, err := strconv.ParseInt(comps[1], 10, 64)
-	if err != nil {
-		return 0, err
-	}
-
-	var durationUnit time.Duration
-	switch comps[2] {
-	case "":
-		if durationFactor != 0 {
-			err = fmt.Errorf("missing time unit")
-			return
-		} else {
-			// It's the case where user specified '0'.
-			// We want to allow this, just like time.ParseDuration.
-		}
-	case "s":
-		durationUnit = time.Second
-	case "m":
-		durationUnit = time.Minute
-	case "h":
-		durationUnit = time.Hour
-	case "d":
-		durationUnit = 24 * time.Hour
-	case "w":
-		durationUnit = 24 * 7 * time.Hour
-	default:
-		err = fmt.Errorf("contains unknown time unit '%s'", comps[2])
-		return
-	}
-
-	d = time.Duration(durationFactor) * durationUnit
-	return
-}
@@ -35,23 +35,8 @@ jobs:
  snapshotting:
    type: periodic
    prefix: zrepl_
-    timestamp_format: dense
    interval: 10m
 `
-	cron := `
-  snapshotting:
-    type: cron
-    prefix: zrepl_
-    timestamp_format: human
-    cron: "10 * * * *"
-`
-
-	periodicDaily := `
-  snapshotting:
-    type: periodic
-    prefix: zrepl_
-    interval: 1d
-`

 	hooks := `
  snapshotting:
@@ -89,27 +74,10 @@ jobs:
 		c = testValidConfig(t, fillSnapshotting(periodic))
 		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingPeriodic)
 		assert.Equal(t, "periodic", snp.Type)
-		assert.Equal(t, 10*time.Minute, snp.Interval.Duration())
+		assert.Equal(t, 10*time.Minute, snp.Interval)
 		assert.Equal(t, "zrepl_", snp.Prefix)
 	})

-	t.Run("periodicDaily", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(periodicDaily))
-		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingPeriodic)
-		assert.Equal(t, "periodic", snp.Type)
-		assert.Equal(t, 24*time.Hour, snp.Interval.Duration())
-		assert.Equal(t, "zrepl_", snp.Prefix)
-		assert.Equal(t, "dense", snp.TimestampFormat)
-	})
-
-	t.Run("cron", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(cron))
-		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingCron)
-		assert.Equal(t, "cron", snp.Type)
-		assert.Equal(t, "zrepl_", snp.Prefix)
-		assert.Equal(t, "human", snp.TimestampFormat)
-	})
-
 	t.Run("hooks", func(t *testing.T) {
 		c = testValidConfig(t, fillSnapshotting(hooks))
 		hs := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingPeriodic).Hooks
@@ -120,57 +88,3 @@ jobs:
 	})

 }
-
-func TestSnapshottingTimestampDefaults(t *testing.T) {
-	tmpl := `
-jobs:
- name: foo
-  type: push
-  connect:
-    type: local
-    listener_name: foo
-    client_identity: bar
-  filesystems: {"<": true}
-  %s
-  pruning:
-    keep_sender:
-    - type: last_n
-      count: 10
-    keep_receiver:
-    - type: last_n
-      count: 10
-`
-
-	periodic := `
-  snapshotting:
-    type: periodic
-    prefix: zrepl_
-    interval: 10m
-`
-	cron := `
-  snapshotting:
-    type: cron
-    prefix: zrepl_
-    cron: "10 * * * *"
-`
-
-	fillSnapshotting := func(s string) string { return fmt.Sprintf(tmpl, s) }
-	var c *Config
-
-	t.Run("periodic", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(periodic))
-		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingPeriodic)
-		assert.Equal(t, "periodic", snp.Type)
-		assert.Equal(t, 10*time.Minute, snp.Interval.Duration())
-		assert.Equal(t, "zrepl_", snp.Prefix)
-		assert.Equal(t, "dense", snp.TimestampFormat) // default was set correctly
-	})
-
-	t.Run("cron", func(t *testing.T) {
-		c = testValidConfig(t, fillSnapshotting(cron))
-		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingCron)
-		assert.Equal(t, "cron", snp.Type)
-		assert.Equal(t, "zrepl_", snp.Prefix)
-		assert.Equal(t, "dense", snp.TimestampFormat) // default was set correctly
-	})
-}
@@ -160,14 +160,6 @@ func (m DatasetMapFilter) Filter(p *zfs.DatasetPath) (pass bool, err error) {
 	return
 }

-func (m DatasetMapFilter) UserSpecifiedDatasets() (datasets zfs.UserSpecifiedDatasetsSet) {
-	datasets = make(zfs.UserSpecifiedDatasetsSet)
-	for i := range m.entries {
-		datasets[m.entries[i].path.ToString()] = true
-	}
-	return
-}
-
 // Construct a new filter-only DatasetMapFilter from a mapping
 // The new filter allows exactly those paths that were not forbidden by the mapping.
 func (m DatasetMapFilter) InvertedFilter() (inv *DatasetMapFilter, err error) {
@@ -199,16 +199,6 @@ const (
 	Done
 )

-// Returns true in case the State is a terminal state(PlanErr, ExecErr, Done)
-func (s State) IsTerminal() bool {
-	switch s {
-	case PlanErr, ExecErr, Done:
-		return true
-	default:
-		return false
-	}
-}
-
 type updater func(func(*Pruner))

 func (p *Pruner) Prune() {
@@ -10,7 +10,6 @@ import (

 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/hooks"
-	"github.com/zrepl/zrepl/util/suspendresumesafetimer"
 	"github.com/zrepl/zrepl/zfs"
 )

@@ -22,7 +21,6 @@ func cronFromConfig(fsf zfs.DatasetFilter, in config.SnapshottingCron) (*Cron, e
 	}
 	planArgs := planArgs{
 		prefix: in.Prefix,
-		timestampFormat: in.TimestampFormat,
 		hooks:  hooksList,
 	}
 	return &Cron{config: in, fsf: fsf, planArgs: planArgs}, nil
@@ -44,17 +42,38 @@ type Cron struct {

 func (s *Cron) Run(ctx context.Context, snapshotsTaken chan<- struct{}) {

+	t := time.NewTimer(0)
+	defer func() {
+		if !t.Stop() {
+			select {
+			case <-t.C:
+			default:
+			}
+		}
+	}()
 	for {
 		now := time.Now()
 		s.mtx.Lock()
 		s.wakeupTime = s.config.Cron.Schedule.Next(now)
 		s.mtx.Unlock()

-		ctxDone := suspendresumesafetimer.SleepUntil(ctx, s.wakeupTime)
-		if ctxDone != nil {
-			return
+		// Re-arm the timer.
+		// Need to Stop before Reset, see docs.
+		if !t.Stop() {
+			// Use non-blocking read from timer channel
+			// because, except for the first loop iteration,
+			// the channel is already drained
+			select {
+			case <-t.C:
+			default:
 			}
+		}
+		t.Reset(s.wakeupTime.Sub(now))

+		select {
+		case <-ctx.Done():
+			return
+		case <-t.C:
 			getLogger(ctx).Debug("cron timer fired")
 			s.mtx.Lock()
 			if s.running {
@@ -84,6 +103,7 @@ func (s *Cron) Run(ctx context.Context, snapshotsTaken chan<- struct{}) {
 				}
 			}()
 		}
+	}

 }

@@ -4,7 +4,6 @@ import (
 	"context"
 	"fmt"
 	"sort"
-	"strconv"
 	"strings"
 	"time"

@@ -16,7 +15,6 @@ import (

 type planArgs struct {
 	prefix string
-	timestampFormat string
 	hooks  *hooks.List
 }

@@ -60,21 +58,6 @@ type snapProgress struct {
 	runResults hooks.PlanReport
 }

-func (plan *plan) formatNow(format string) string {
-	now := time.Now().UTC()
-	switch strings.ToLower(format) {
-	case "dense":
-		format = "20060102_150405_000"
-	case "human":
-		format = "2006-01-02_15:04:05"
-	case "iso-8601":
-		format = "2006-01-02T15:04:05.000Z"
-	case "unix-seconds":
-		return strconv.FormatInt(now.Unix(), 10)
-	}
-	return now.Format(format)
-}
-
 func (plan *plan) execute(ctx context.Context, dryRun bool) (ok bool) {

 	hookMatchCount := make(map[hooks.Hook]int, len(*plan.args.hooks))
@@ -85,7 +68,7 @@ func (plan *plan) execute(ctx context.Context, dryRun bool) (ok bool) {
 	anyFsHadErr := false
 	// TODO channel programs -> allow a little jitter?
 	for fs, progress := range plan.snaps {
-		suffix := plan.formatNow(plan.args.timestampFormat)
+		suffix := time.Now().In(time.UTC).Format("20060102_150405_000")
 		snapname := fmt.Sprintf("%s%s", plan.args.prefix, suffix)

 		ctx := logging.WithInjectedField(ctx, "fs", fs.ToString())
@@ -15,7 +15,6 @@ import (
 	"github.com/zrepl/zrepl/daemon/hooks"
 	"github.com/zrepl/zrepl/daemon/logging"
 	"github.com/zrepl/zrepl/util/envconst"
-	"github.com/zrepl/zrepl/util/suspendresumesafetimer"
 	"github.com/zrepl/zrepl/zfs"
 )

@@ -23,7 +22,7 @@ func periodicFromConfig(g *config.Global, fsf zfs.DatasetFilter, in *config.Snap
 	if in.Prefix == "" {
 		return nil, errors.New("prefix must not be empty")
 	}
-	if in.Interval.Duration() <= 0 {
+	if in.Interval <= 0 {
 		return nil, errors.New("interval must be positive")
 	}

@@ -33,11 +32,10 @@ func periodicFromConfig(g *config.Global, fsf zfs.DatasetFilter, in *config.Snap
 	}

 	args := periodicArgs{
-		interval: in.Interval.Duration(),
+		interval: in.Interval,
 		fsf:      fsf,
 		planArgs: planArgs{
 			prefix: in.Prefix,
-			timestampFormat: in.TimestampFormat,
 			hooks:  hookList,
 		},
 		// ctx and log is set in Run()
@@ -173,13 +171,16 @@ func periodicStateSyncUp(a periodicArgs, u updater) state {
 	u(func(s *Periodic) {
 		s.sleepUntil = syncPoint
 	})
-	ctxDone := suspendresumesafetimer.SleepUntil(a.ctx, syncPoint)
-	if ctxDone != nil {
-		return onMainCtxDone(a.ctx, u)
-	}
+	t := time.NewTimer(time.Until(syncPoint))
+	defer t.Stop()
+	select {
+	case <-t.C:
 		return u(func(s *Periodic) {
 			s.state = Planning
 		}).sf()
+	case <-a.ctx.Done():
+		return onMainCtxDone(a.ctx, u)
+	}
 }

 func periodicStatePlan(a periodicArgs, u updater) state {
@@ -240,13 +241,17 @@ func periodicStateWait(a periodicArgs, u updater) state {
 		logFunc("enter wait-state after error")
 	})

-	ctxDone := suspendresumesafetimer.SleepUntil(a.ctx, sleepUntil)
-	if ctxDone != nil {
-		return onMainCtxDone(a.ctx, u)
-	}
+	t := time.NewTimer(time.Until(sleepUntil))
+	defer t.Stop()
+
+	select {
+	case <-t.C:
 		return u(func(snapper *Periodic) {
 			snapper.state = Planning
 		}).sf()
+	case <-a.ctx.Done():
+		return onMainCtxDone(a.ctx, u)
+	}
 }

 func listFSes(ctx context.Context, mf zfs.DatasetFilter) (fss []*zfs.DatasetPath, err error) {
@@ -1,23 +0,0 @@
-#!/sbin/openrc-run
-
-command='/usr/local/bin/zrepl'
-command_args='daemon'
-command_background='true'
-pidfile="/run/${RC_SVCNAME}.pid"
-output_log="/var/log/${RC_SVCNAME}.log"
-error_log="/var/log/${RC_SVCNAME}.log"
-
-zrepl_runtime_dir='/var/run/zrepl'
-
-start() {
-	mkdir -p "$zrepl_runtime_dir/stdinserver"
-	chmod -R 0700 "$zrepl_runtime_dir"
-	default_start
-}
-
-stop() {
-	rm -rf "$zrepl_runtime_dir"
-	default_stop
-}
-
-# vi: noet sw=8 sts=0
@@ -9,9 +9,6 @@ ExecStart=/usr/local/bin/zrepl --config /etc/zrepl/zrepl.yml daemon
 RuntimeDirectory=zrepl zrepl/stdinserver
 RuntimeDirectoryMode=0700

-# Make Go produce coredumps
-Environment=GOTRACEBACK='crash'
-
 ProtectSystem=strict
 #PrivateDevices=yes # TODO ZFS needs access to /dev/zfs, could we limit this?
 ProtectKernelTunables=yes
@@ -30,8 +27,7 @@ ProtectHome=read-only
 # SystemCallFilter
 #   ~@privileged doesn't work with Ubuntu 18.04 ssh
 SystemCallFilter=~ @mount @cpu-emulation @keyring @module @obsolete @raw-io @debug @clock @resources
-# Go1.19 added automatic RLIMIT_NOFILE changes, so, we need to allow that
-SystemCallFilter= setrlimit
+

 [Install]
 WantedBy=multi-user.target
@@ -10,11 +10,11 @@ BUILDDIR      = _build

 # Put it first so that "make" without argument is like "make help".
 help:
-	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" -c sphinxconf $(SPHINXOPTS) $(O)

 .PHONY: help Makefile

 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" -c sphinxconf $(SPHINXOPTS) $(O)
@@ -1,43 +0,0 @@
-/* https://github.com/sphinx-contrib/sphinxcontrib-versioning/blob/0b56210959c6b21bbb730072e81876491b4e1371/sphinxcontrib/versioning/_static/banner.css */
-
-.scv-banner {
-    padding: 3px;
-    border-radius: 2px;
-    font-size: 80%;
-    text-align: center;
-    color: white;
-    background: #d40 linear-gradient(-45deg,
-        rgba(255, 255, 255, 0.2) 0%,
-        rgba(255, 255, 255, 0.2) 25%,
-        transparent 25%,
-        transparent 50%,
-        rgba(255, 255, 255, 0.2) 50%,
-        rgba(255, 255, 255, 0.2) 75%,
-        transparent 75%,
-        transparent
-    );
-    background-size: 28px 28px;
-}
-.scv-banner > a {
-    color: white;
-}
-
-
-.scv-sphinx_rtd_theme {
-    background-color: #2980B9;
-}
-
-
-.scv-bizstyle {
-    background-color: #336699;
-}
-
-
-.scv-classic {
-    text-align: center !important;
-}
-
-
-.scv-traditional {
-    text-align: center !important;
-}
@@ -1,17 +0,0 @@
-{% extends "!page.html" %}
-{% block body %}
-{% if current_version and latest_version and current_version != latest_version %}
-<p class="scv-banner scv-sphinx_rtd_theme">
-  <strong>
-    {% if current_version.is_released %}
-    You're reading an old version of this documentation.
-    If you want up-to-date information, please have a look at <a href="{{ vpathto(latest_version.name) }}">{{latest_version.name}}</a>.
-    {% else %}
-    You're reading the documentation for a development version.
-    For the latest released version, please have a look at <a href="{{ vpathto(latest_version.name) }}">{{latest_version.name}}</a>.
-    {% endif %}
-  </strong>
-</p>
-{% endif %}
-{{ super() }}
-{% endblock %}%
@@ -1,27 +0,0 @@
-{%- if current_version %}
-<div class="rst-versions" data-toggle="rst-versions" role="note" aria-label="versions">
-  <span class="rst-current-version" data-toggle="rst-current-version">
-    <span class="fa fa-book"> Other Versions</span>
-    v: {{ current_version.name }}
-    <span class="fa fa-caret-down"></span>
-  </span>
-  <div class="rst-other-versions">
-    {%- if versions.tags %}
-    <dl>
-      <dt>Tags</dt>
-      {%- for item in versions.tags %}
-      <dd><a href="{{ item.url }}">{{ item.name }}</a></dd>
-      {%- endfor %}
-    </dl>
-    {%- endif %}
-    {%- if versions.branches %}
-    <dl>
-      <dt>Branches</dt>
-      {%- for item in versions.branches %}
-      <dd><a href="{{ item.url }}">{{ item.name }}</a></dd>
-      {%- endfor %}
-    </dl>
-    {%- endif %}
-  </div>
-</div>
-{%- endif %}
@@ -16,63 +16,13 @@ Changelog
 The changelog summarizes bugfixes that are deemed relevant for users and package maintainers.
 Developers should consult the git commit log or GitHub issue tracker.

-Next Release
------------
+0.6 (Unreleased)
+----------------

-The plan for the next release is to revisit how zrepl does snapshot management.
-High-level goals:
-
- Make it easy to decouple snapshot management (snapshotting, pruning) from replication.
- Ability to include/exclude snapshots from replication.
-  This is useful for aforementioned decoupling, e.g., separate snapshot prefixes for local & remote replication.
-  Also, it makes explicit that by default, zrepl replicates all snapshots, and that
-  replication has no concept of "zrepl-created snapshots", which is a common misconception.
- Use of ``zfs snapshot`` comma syntax or channel programs to take snapshots of multiple
-  datasets atomically.
- Provide an alternative to the ``grid`` pruning policy.
-  Most likely something based on hourly/daily/weekly/monthly "trains" plus a count.
- Ability to prune at the granularity of the **group** of snapshots created at a given
-  time, as opposed to the individual snapshots within a dataset.
-  Maybe this will be addressed by the alternative to the ``grid`` pruning policy,
-  as it will likely be more predictable.
-
-Those changes will likely come with some breakage in the config.
-However, I want to avoid breaking **use cases** that are satisfied by the current design.
-There will be beta/RC releases to give users a chance to evaluate.
-
-0.6.1
-----
-
-* |feature| add metric to detect filesystems rules that don't match any local dataset (thanks, `@gmekicaxcient <https://github.com/gmekicaxcient>`_).
-* |bugfix| ``zrepl status``: hide progress bar once all filesystems reach terminal state (thanks, `@0x3333 <https://github.com/0x3333>`_).
-* |bugfix| handling of tenative cursor presence if protection strategy doesn't use it (:issue:`714`).
-* |docs| address setup with two or more external disks (thanks, `@se-jaeger <https://github.com/se-jaeger>`_).
-* |docs| document ``replication`` and ``conflict_resolution`` options (thanks, `@InsanePrawn <https://github.com/InsanePrawn>`_).
-* |docs| docs: talks: add note on keep_bookmarks option (thanks, `@skirmess <https://github.com/skirmess>`_).
-* |maint| dist: add openrc service file (thanks, `@gramosg <https://github.com/gramosg>`_).
-* |maint| grafana: update dashboard to Grafana 9.3.6.
-* |maint| run platform tests as part of CI.
-* |maint| build: upgrade to Go 1.21 and update golangci-lint; minimum Go version for builds is now 1.20
-
-.. NOTE::
-  |  zrepl is a spare-time project primarily developed by `Christian Schwarz <https://cschwarz.com>`_.
-  |  You can support maintenance and feature development through one of the following services:
-  |  |Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal|
-  |  Note that PayPal processing fees are relatively high for small donations.
-  |  For SEPA wire transfer and **commercial support**, please `contact Christian directly <https://cschwarz.com>`_.
-
-0.6
---
+* `Feature Wishlist on GitHub <https://github.com/zrepl/zrepl/discussions/547>`_

 * |feature| :ref:`Schedule-based snapshotting<job-snapshotting--cron>` using ``cron`` syntax instead of an interval.
-* |feature| Configurable initial replication policy.
-  When a filesystem is first replicated to a receiver, this control whether just the newest
-  snapshot will be replicated vs. all existing snapshots. Learn more :ref:`in the docs <conflict_resolution-initial_replication>`.
-* |feature| Configurable timestamp format for snapshot names via :ref:`timestamp_format<job-snapshotting-timestamp_format>`
-  (Thanks, `@ydylla <https://github.com/ydylla>`_).
-* |feature| Add ``ZREPL_DESTROY_MAX_BATCH_SIZE`` env var (default 0=unlimited)
-  (Thanks, `@3nprob <https://github.com/3nprob>`_).
-* |feature| Add ``zrepl configcheck --skip-cert-check`` flag (Thanks, `@cole-h <https://github.com/cole-h>`_).
+* |feature| Add ``ZREPL_DESTROY_MAX_BATCH_SIZE`` env var (default 0=unlimited).
 * |bugfix| Fix resuming from interrupted replications that use ``send.raw`` on unencrypted datasets.

  * The send options introduced in zrepl 0.4 allow users to specify additional zfs send flags for zrepl to use.
@@ -84,7 +34,7 @@ There will be beta/RC releases to give users a chance to evaluate.
  * However, this means that the ``zrepl status`` UI no longer indicates whether a replication step uses encrypted sends or not.
    The setting is still effective though.

-* |break| convert Prometheus metric ``zrepl_version_daemon`` to ``zrepl_start_time`` metric
+* |break| |feature| convert Prometheus metric ``zrepl_version_daemon`` to ``zrepl_start_time`` metric

  * The metric still reports the zrepl version in a label.
    But the metric *value* is now the Unix timestamp at the time the daemon was started.
@@ -93,13 +43,6 @@ There will be beta/RC releases to give users a chance to evaluate.
 * |bugfix| transient zrepl status error: ``Post "http://unix/status": EOF``
 * |bugfix| don't treat receive-side bookmarks as a replication conflict.
  This facilitates chaining of replication jobs. See :issue:`490`.
-* |bugfix| workaround for Go/gRPC problem on Illumos where zrepl would
-  crash when using the ``local`` transport type (:issue:`598`).
-* |bugfix| fix active child tasks panic that cold occur during replication plannig (:issue:`193abbe`)
-* |bugfix| ``zrepl status`` off-by-one error in display of completed step count (:commit:`ce6701f`)
-* |bugfix| Allow using day & week units for ``snapshotting.interval`` (:commit:`ffb1d89`)
-* |docs| ``docs/overview`` improvements (Thanks, `@jtagcat <https://github.com/jtagcat>`_).
-* |maint| Update to Go 1.19.

 0.5
 ---
@@ -132,6 +75,14 @@ Note to all users: please read up on the following OpenZFS bugs, as you might be

 Finally, I'd like to point you to the `GitHub discussion <https://github.com/zrepl/zrepl/discussions/547>`_ about which bugfixes and features should be prioritized in zrepl 0.6 and beyond!

+.. NOTE::
+  |  zrepl is a spare-time project primarily developed by `Christian Schwarz <https://cschwarz.com>`_.
+  |  You can support maintenance and feature development through one of the following services:
+  |  |Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal|
+  |  Note that PayPal processing fees are relatively high for small donations.
+  |  For SEPA wire transfer and **commercial support**, please `contact Christian directly <https://cschwarz.com>`_.
+
+
 0.4.0
 -----

@@ -1,187 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-#
-# zrepl documentation build configuration file, created by
-# sphinx-quickstart on Wed Nov  8 22:28:10 2017.
-#
-# This file is execfile()d with the current directory set to its
-# containing dir.
-#
-# Note that not all possible configuration values are present in this
-# autogenerated file.
-#
-# All configuration values have a default; values that are commented out
-# serve to show the default.
-
-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-#
-# import os
-# import sys
-# sys.path.insert(0, os.path.abspath('.'))
-
-
-# -- General configuration ------------------------------------------------
-
-# If your documentation needs a minimal Sphinx version, state it here.
-#
-# needs_sphinx = '1.0'
-
-# Add any Sphinx extension module names here, as strings. They can be
-# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
-# ones.
-extensions = ['sphinx.ext.todo',
-    'sphinx.ext.githubpages',
-    'sphinx.ext.extlinks',
-    "sphinx_multiversion",
-]
-
-# suppress_warnings = ['image.nonlocal_uri']
-
-# Add any paths that contain templates here, relative to this directory.
-templates_path = ['./_templates']
-
-# The suffix(es) of source filenames.
-# You can specify multiple suffix as a list of string:
-#
-# source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
-
-# The master toctree document.
-master_doc = 'index'
-
-# General information about the project.
-project = 'zrepl'
-copyright = '2017-2023, Christian Schwarz'
-author = 'Christian Schwarz'
-
-# The version info for the project you're documenting, acts as replacement for
-# |version| and |release|, also used in various other places throughout the
-# built documents.
-#
-# The short X.Y version.
-#version = set by sphinxcontrib-versioning
-# The full version, including alpha/beta/rc tags.
-#release = version
-
-# The language for content autogenerated by Sphinx. Refer to documentation
-# for a list of supported languages.
-#
-# This is also used if you do content translation via gettext catalogs.
-# Usually you set "language" from the command line for these cases.
-language = 'en'
-
-# List of patterns, relative to source directory, that match files and
-# directories to ignore when looking for source files.
-# This patterns also effect to html_static_path and html_extra_path
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
-
-# The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'sphinx'
-
-# If true, `todo` and `todoList` produce output, else they produce nothing.
-todo_include_todos = True
-
-
-# -- Options for HTML output ----------------------------------------------
-
-# The theme to use for HTML and HTML Help pages.  See the documentation for
-# a list of builtin themes.
-#
-html_theme = 'sphinx_rtd_theme'
-
-# Theme options are theme-specific and customize the look and feel of a theme
-# further.  For a list of options available for each theme, see the
-# documentation.
-#
-# html_theme_options = {}
-
-# Add any paths that contain custom static files (such as style sheets) here,
-# relative to this directory. They are copied after the builtin static files,
-# so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
-
-html_css_files = [
-    'banner.css',
-]
-
-html_logo = '_static/zrepl.svg'
-
-html_context = {
-  # https://github.com/rtfd/sphinx_rtd_theme/issues/205
-  # Add 'Edit on Github' link instead of 'View page source'
-  "display_github": True,
-  "github_user": "zrepl",
-  "github_repo": "zrepl",
-  "github_version": "master",
-  "conf_py_path": "/docs/",
-  "source_suffix": source_suffix,
-}
-
-# -- Options for HTMLHelp output ------------------------------------------
-
-# Output file base name for HTML help builder.
-htmlhelp_basename = 'zrepldoc'
-
-
-# -- Options for LaTeX output ---------------------------------------------
-
-latex_elements = {
-    # The paper size ('letterpaper' or 'a4paper').
-    #
-    # 'papersize': 'letterpaper',
-
-    # The font size ('10pt', '11pt' or '12pt').
-    #
-    # 'pointsize': '10pt',
-
-    # Additional stuff for the LaTeX preamble.
-    #
-    # 'preamble': '',
-
-    # Latex figure (float) alignment
-    #
-    # 'figure_align': 'htbp',
-}
-
-# Grouping the document tree into LaTeX files. List of tuples
-# (source start file, target name, title,
-#  author, documentclass [howto, manual, or own class]).
-latex_documents = [
-    (master_doc, 'zrepl.tex', 'zrepl Documentation',
-     'Christian Schwarz', 'manual'),
-]
-
-
-# -- Options for manual page output ---------------------------------------
-
-# One entry per manual page. List of tuples
-# (source start file, name, description, authors, manual section).
-man_pages = [
-    (master_doc, 'zrepl', 'zrepl Documentation',
-     [author], 1)
-]
-
-
-# -- Options for Texinfo output -------------------------------------------
-
-# Grouping the document tree into Texinfo files. List of tuples
-# (source start file, target name, title, author,
-#  dir menu entry, description, category)
-texinfo_documents = [
-    (master_doc, 'zrepl', 'zrepl Documentation',
-     author, 'zrepl', 'One line description of project.',
-     'Miscellaneous'),
-]
-
-
-# -- Options for the extlinks extension -----------------------------------
-# http://www.sphinx-doc.org/en/stable/ext/extlinks.html
-extlinks = {
-    'issue':('https://github.com/zrepl/zrepl/issues/%s', 'issue #%s'),
-    'repomasterlink':('https://github.com/zrepl/zrepl/blob/master/%s', '%s'),
-    'sampleconf':('https://github.com/zrepl/zrepl/blob/master/config/samples%s', 'config/samples%s'),
-    'commit':('https://github.com/zrepl/zrepl/commit/%s', 'commit %s'),
-        }
-
@@ -0,0 +1 @@
+sphinxconf/conf.py
@@ -1,6 +1,5 @@
 .. include:: ../global.rst.inc

-.. _conflict_resolution-options:

 Conflict Resolution Options
 ===========================
@@ -16,7 +15,7 @@ Conflict Resolution Options

     ...

-.. _conflict_resolution-initial_replication:
+.. _conflict_resolution-initial_replication-option-send_all_snapshots:


 ``initial_replication`` option
@@ -30,10 +30,6 @@ Job Type ``push``
      - |snapshotting-spec|
    * - ``pruning``
      - |pruning-spec|
-    * - ``replication``
-      - |replication-options|
-    * - ``conflict_resolution``
-      - |conflict-resolution-options|

 Example config: :sampleconf:`/push.yml`

@@ -85,10 +81,6 @@ Job Type ``pull``
        | ``manual`` disables periodic pulling, replication then only happens on :ref:`wakeup <cli-signal-wakeup>`.
    * - ``pruning``
      - |pruning-spec|
-    * - ``replication``
-      - |replication-options|
-    * - ``conflict_resolution``
-      - |conflict-resolution-options|

 Example config: :sampleconf:`/pull.yml`

@@ -44,3 +44,27 @@ Interval & duration fields in job definitions, pruning configurations, etc. must

    var durationStringRegex *regexp.Regexp = regexp.MustCompile(`^\s*(\d+)\s*(s|m|h|d|w)\s*$`)
    // s = second, m = minute, h = hour, d = day, w = week (7 days)
+
+Super-Verbose Job Debugging
+---------------------------
+
+You have probably landed here because you opened an issue on GitHub and some developer told you to do this...
+So just read the annotated comments ;)
+
+::
+
+    job:
+    - name: ...
+      ...
+     # JOB DEBUGGING OPTIONS
+      # should be equal for all job types, but each job implements the debugging itself
+      debug:
+        conn: # debug the io.ReadWriteCloser connection
+          read_dump: /tmp/connlog_read   # dump results of Read() invocations to this file
+          write_dump: /tmp/connlog_write # dump results of Write() invocations to this file
+        rpc: # debug the RPC protocol implementation
+          log: true # log output from rpc layer to the job log
+
+.. ATTENTION::
+
+    Connection dumps will almost certainly contain your or other's private data. Do not share it in a bug report.
@@ -1,6 +1,5 @@
 .. include:: ../global.rst.inc

-.. _replication-options:

 Replication Options
 ===================
@@ -197,8 +197,11 @@ Mount behaviour
 * ``canmount``
 * ``overlay``

-Note: Before `OpenZFS 2.0.5 <https://github.com/openzfs/zfs/issues/11416>`_, inheriting or overriding the ``mountpoint`` property on ZVOLs fails in ``zfs recv``.
-If you are on such an older version, consider creating separate zrepl jobs for your ZVOL and filesystem datasets.
+Note: inheriting or overriding the ``mountpoint`` property on ZVOLs fails in ``zfs recv``.
+This is an `issue in OpenZFS <https://github.com/openzfs/zfs/issues/11416>`_ .
+As a workaround, consider creating separate zrepl jobs for your ZVOL and filesystem datasets.
+Please comment at zrepl :issue:`430` if you encounter this issue and/or would like zrepl to automatically work around it.
+

 Systemd
 -------
@@ -62,9 +62,6 @@ The ``periodic`` and ``cron`` snapshotting types share some common options and b
       type: periodic
       prefix: zrepl_
       interval: 10m
-       # Timestamp format that is used as snapshot suffix.
-       # Can be any of "dense" (default), "human", "iso-8601", "unix-seconds" or a custom Go time format (see https://go.dev/src/time/format.go)
-       timestamp_format: dense
       hooks: ...
    pruning: ...

@@ -94,9 +91,6 @@ The snapshotter uses the ``prefix`` to identify which snapshots it created.
       # (second, optional) minute hour day-of-month month day-of-week
       # This example takes snapshots daily at 3:00.
       cron: "0 3 * * *"
-       # Timestamp format that is used as snapshot suffix.
-       # Can be any of "dense" (default), "human", "iso-8601", "unix-seconds" or a custom Go time format (see https://go.dev/src/time/format.go)
-       timestamp_format: dense
     pruning: ...

 In ``cron`` mode, the snapshotter takes snaphots at fixed points in time.
@@ -104,21 +98,6 @@ See https://en.wikipedia.org/wiki/Cron for details on the syntax.
 zrepl uses the ``the github.com/robfig/cron/v3`` Go package for parsing.
 An optional field for "seconds" is supported to take snapshots at sub-minute frequencies.

-.. _job-snapshotting-timestamp_format:
-
-Timestamp Format
-~~~~~~~~~~~~~~~~
-
-The ``cron`` and ``periodic`` snapshotter support configuring a custom timestamp format that is used as suffix for the snapshot name.
-It can be used by setting ``timestamp_format`` to any of the following values:
-
-* ``dense`` (default) looks like ``20060102_150405_000``
-* ``human`` looks like ``2006-01-02_15:04:05``
-* ``iso-8601`` looks like ``2006-01-02T15:04:05.000Z``
-* ``unix-seconds`` looks like ``1136214245``
-* Any custom Go time format accepted by `time.Time#Format <https://go.dev/src/time/format.go>`_.
-
-
 ``manual`` Snapshotting
 -----------------------

@@ -1,15 +1,7 @@
 #!/usr/bin/env python3

-from pathlib import Path
 import subprocess
 import re
-import argparse
-import distutils
-
-argparser = argparse.ArgumentParser()
-argparser.add_argument("docsroot")
-argparser.add_argument("outdir")
-args = argparser.parse_args()

 output = subprocess.run(["git", "tag", "-l"], capture_output=True, check=True, text=True)
 tagRE = re.compile(r"^v(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(-rc(?P<rc>\d+))?$")
@@ -57,16 +49,26 @@ for (mm, l) in by_major_minor.items():
    latest_by_major_minor.append(l[-1])
 latest_by_major_minor.sort(key=lambda tag: (tag.major, tag.minor))

-cmdline = [
-    "sphinx-multiversion",
-    "-D", "smv_tag_whitelist=^({})$".format("|".join([re.escape(tag.orig) for tag in latest_by_major_minor])),
-    "-D", "smv_branch_whitelist=^(master|stable)$",
-    "-D", "smv_remote_whitelist=^.*$",
-    "-D", "smv_latest_version=stable",
-    "-D", r"smv_released_pattern=^refs/(tags|heads|remotes/[^/]+)/(?!master).*$", # treat everything except master as released, that way, the banner message makes sense
-    # "--dump-metadata", # for debugging
-    args.docsroot,
-    args.outdir,
-]
-print(cmdline)
-subprocess.run(cmdline, check=True)
+# print(by_major_minor)
+# print(latest_by_major_minor)
+
+cmdline = []
+
+for latest_patch in latest_by_major_minor:
+    cmdline.append("--whitelist-tags")
+    cmdline.append(f"^{re.escape(latest_patch.orig)}$")
+
+# we want flexibility to update docs for the latest stable release
+# => we have a branch for that, called `stable` which we move manually
+# TODO: in the future, have f"stable-{latest_by_major_minor[-1]}"
+default_version = "stable"
+cmdline.extend(["--whitelist-branches", default_version])
+
+cmdline.extend(["--root-ref", f"{default_version}"])
+cmdline.extend(["--banner-main-ref", f"{default_version}"])
+cmdline.extend(["--show-banner"])
+cmdline.extend(["--sort", "semver"])
+
+cmdline.extend(["--whitelist-branches", "master"])
+
+print(" ".join(cmdline))
@@ -26,8 +26,6 @@
 .. |connect-transport| replace:: :ref:`connect specification<transport>`
 .. |send-options| replace:: :ref:`send options<job-send-options>`, e.g. for encrypted sends
 .. |recv-options| replace:: :ref:`recv options<job-recv-options>`
-.. |replication-options| replace:: :ref:`replication options<replication-options>`
-.. |conflict-resolution-options| replace:: :ref:`conflict resolution options<conflict_resolution-options>`
 .. |snapshotting-spec| replace:: :ref:`snapshotting specification <job-snapshotting-spec>`
 .. |pruning-spec| replace:: :ref:`pruning specification <prune>`
 .. |filter-spec| replace:: :ref:`filter specification<pattern-filter>`
@@ -15,5 +15,3 @@ Talks & Presentations
  `Event <https://wiki.freebsd.org/DevSummit/201709>`__
  )

-  * Note: The remarks on ``keep_bookmarks`` are irrelevant as of zrepl 0.1 which introduced the zrepl-managed replication cursor bookmark.
-    Read the `Overview <overview-how-replication-works>`_ section to learn more.
@@ -3,8 +3,7 @@ set -euo pipefail

 NON_INTERACTIVE=false
 DO_CLONE=false
-PUSH=false
-while getopts "caP" arg; do
+while getopts "ca" arg; do
    case "$arg" in
        "a")
            NON_INTERACTIVE=true
@@ -12,9 +11,6 @@ while getopts "caP" arg; do
        "c")
            DO_CLONE=true
            ;;
-        "P")
-            PUSH=true
-            ;;
        *)
            echo "invalid option '-$arg'"
            exit 1
@@ -30,8 +26,8 @@ checkout_repo_msg() {
    echo "clone ${GHPAGESREPO} to ${PUBLICDIR}:"
 }

-if ! type sphinx-multiversion >/dev/null; then
-    echo "install sphinx-multiversion and come back"
+if ! type sphinx-versioning >/dev/null; then
+    echo "install sphinx-versioning and come back"
    exit 1
 fi

@@ -77,15 +73,22 @@ popd

 echo "building site"

-python3 run-sphinx-multiversion.py . ./public_git
-
+flags="$(python3 gen-sphinx-versioning-flags.py)"
+set -e
+sphinx-versioning build \
+   $flags \
+   docs ./public_git \
+   -- -c sphinxconf # older conf.py throw errors because they used
+                    # version = subprocess.show_output(["git", "describe"])
+                    # which fails when building with sphinxcontrib-versioning
+set +e

 CURRENT_COMMIT=$(git rev-parse HEAD)
 git status --porcelain
 if [[ "$(git status --porcelain)" != "" ]]; then
    CURRENT_COMMIT="${CURRENT_COMMIT}(dirty)" 
 fi
-COMMIT_MSG="render from publish.sh - $(date -u) - ${CURRENT_COMMIT}"
+COMMIT_MSG="sphinx-versioning render from publish.sh - $(date -u) - ${CURRENT_COMMIT}"

 pushd "$PUBLICDIR"

@@ -97,11 +100,6 @@ if [ "$(git status --porcelain)" != "" ]; then
 else
    echo "nothing to commit"
 fi
-
-if $PUSH; then
-    echo "pushing to GitHub pages repo"
-    git push origin master
-else
-    echo "not pushing to GitHub pages repo, set -P flag to push"
-fi
+echo "pushing to GitHub pages repo"
+git push origin master

@@ -33,17 +33,4 @@ You will likely want to customize some aspects mentioned in the top comment in t

 .. literalinclude:: ../../config/samples/quickstart_backup_to_external_disk.yml

-
-Offline Backups with two (or more) External Disks
-------------------------------------------------
-
-It can be desirable to have multiple disk-based backups of the same machine.
-To accomplish this,
-
-* create one zpool per external HDD, each with a unique name, and
-* define a pair of ``push`` and ``sink`` job **for each** of these zpools, each with a unique ``name``, ``listener_name``, and ``root_fs``.
-
-The unique names ensure that the jobs don't step on each others' toes when managing :ref:`zrepl's ZFS abstractions <zrepl-zfs-abstractions>` . 
-
-
 :ref:`Click here <quickstart-apply-config>` to go back to the quickstart guide.
@@ -1,24 +1,30 @@
-alabaster==0.7.13
-Babel==2.12.1
-certifi==2023.7.22
-charset-normalizer==3.2.0
-docutils==0.18.1
-idna==3.4
-imagesize==1.4.1
-Jinja2==3.1.2
-MarkupSafe==2.1.3
-packaging==23.1
-Pygments==2.16.1
-requests==2.31.0
-snowballstemmer==2.2.0
-Sphinx==7.2.5
-sphinx-multiversion @ git+https://github.com/zrepl/sphinx-multiversion/@52c915d7ad898d9641ec48c8bbccb7d4f079db93
-sphinx-rtd-theme==1.3.0
-sphinxcontrib-applehelp==1.0.7
-sphinxcontrib-devhelp==1.0.5
-sphinxcontrib-htmlhelp==2.0.4
-sphinxcontrib-jquery==4.1
+alabaster==0.7.12
+attrs==19.1.0
+Babel==2.7.0
+certifi==2019.6.16
+chardet==3.0.4
+Click==7.0
+colorclass==2.2.0
+docutils==0.15.2
+idna==2.8
+imagesize==1.1.0
+Jinja2==2.10.1
+MarkupSafe==1.1.1
+packaging==19.1
+Pygments==2.4.2
+pyparsing==2.4.2
+pytz==2019.2
+requests==2.22.0
+six==1.12.0
+snowballstemmer==1.9.1
+Sphinx==1.8.5
+sphinx-rtd-theme==0.4.3
+sphinxcontrib-applehelp==1.0.1
+sphinxcontrib-devhelp==1.0.1
+sphinxcontrib-htmlhelp==1.0.2
 sphinxcontrib-jsmath==1.0.1
-sphinxcontrib-qthelp==1.0.6
-sphinxcontrib-serializinghtml==1.1.9
-urllib3==2.0.4
+sphinxcontrib-qthelp==1.0.2
+sphinxcontrib-serializinghtml==1.1.3
+git+https://github.com/rwblair/sphinxcontrib-versioning.git@7e3885a389a809e17ea55261316b7b0e98dbf98f#egg=sphinxcontrib-versioning
+sphinxcontrib-websupport==1.1.2
+urllib3==1.25.3
@@ -0,0 +1,182 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# zrepl documentation build configuration file, created by
+# sphinx-quickstart on Wed Nov  8 22:28:10 2017.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = ['sphinx.ext.todo',
+    'sphinx.ext.githubpages',
+    'sphinx.ext.extlinks']
+
+suppress_warnings = ['image.nonlocal_uri']
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['../_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'zrepl'
+copyright = '2017-2019, Christian Schwarz'
+author = 'Christian Schwarz'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+#version = set by sphinxcontrib-versioning
+# The full version, including alpha/beta/rc tags.
+#release = version
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = True
+
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['../_static']
+
+
+html_logo = '../_static/zrepl.svg'
+
+html_context = {
+  # https://github.com/rtfd/sphinx_rtd_theme/issues/205
+  # Add 'Edit on Github' link instead of 'View page source'
+  "display_github": True, 
+  "github_user": "zrepl",
+  "github_repo": "zrepl",
+  "github_version": "master",
+  "conf_py_path": "/docs/",
+  "source_suffix": source_suffix,
+}
+
+# -- Options for HTMLHelp output ------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'zrepldoc'
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'zrepl.tex', 'zrepl Documentation',
+     'Christian Schwarz', 'manual'),
+]
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'zrepl', 'zrepl Documentation',
+     [author], 1)
+]
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'zrepl', 'zrepl Documentation',
+     author, 'zrepl', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+# -- Options for the extlinks extension -----------------------------------
+# http://www.sphinx-doc.org/en/stable/ext/extlinks.html
+extlinks = {
+    'issue':('https://github.com/zrepl/zrepl/issues/%s', 'issue #'),
+    '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 '),
+        }
+
@@ -32,7 +32,6 @@ We would like to thank the following people and organizations for supporting zre

   <div class="fa fa-code" style="width: 1em;"></div>

-* |supporter-std| `Max Christian Pohle <https://coderonline.de>`_
 * |supporter-gold| Prominic.NET, Inc.
 * |supporter-std| Torsten Blum
 * |supporter-gold| Cyberiada GmbH
@@ -7,7 +7,6 @@ import (
 	"fmt"
 	"io"
 	"path"
-	"strings"

 	"github.com/kr/pretty"
 	"github.com/pkg/errors"
@@ -234,21 +233,6 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 	//
 	// Note further that a resuming send, due to the idempotent nature of func CreateReplicationCursor and HoldStep,
 	// will never lose its step holds because we just (idempotently re-)created them above, before attempting the cleanup.
-	destroyTypes := AbstractionTypeSet{
-		AbstractionStepHold:                           true,
-		AbstractionTentativeReplicationCursorBookmark: true,
-	}
-	// The replication planner can also pick an endpoint zfs abstraction as FromVersion.
-	// Keep it, so that the replication will succeed.
-	//
-	// NB: there is no abstraction for snapshots, so, we only need to check bookmarks.
-	if sendArgs.FromVersion != nil && sendArgs.FromVersion.IsBookmark() {
-		dp, err := zfs.NewDatasetPath(sendArgs.FS)
-		if err != nil {
-			panic(err) // sendArgs is validated, this shouldn't happen
-		}
-		liveAbs = append(liveAbs, destroyTypes.ExtractBookmark(dp, sendArgs.FromVersion))
-	}
 	func() {
 		ctx, endSpan := trace.WithSpan(ctx, "cleanup-stale-abstractions")
 		defer endSpan()
@@ -261,45 +245,35 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 			return keep
 		}
 		check := func(obsoleteAbs []Abstraction) {
-			// Ensure that we don't delete `From` or `To`.
-			// Regardless of whether they are in AbstractionTypeSet or not.
-			// And produce a nice error message in case we do, to aid debugging the resulting panic.
-			//
-			// This is especially important for `From`. We could break incremental replication
-			// if we deleted the last common filesystem version between sender and receiver.
-			type Problem struct {
-				sendArgsWhat string
-				fullpath     string
-				obsoleteAbs  Abstraction
-			}
-			problems := make([]Problem, 0)
-			checkFullpaths := make(map[string]string, 2)
-			checkFullpaths["ToVersion"] = sendArgs.ToVersion.FullPath(sendArgs.FS)
+			// last line of defense: check that we don't destroy the incremental `from` and `to`
+			// if we did that, we might be about to blow away the last common filesystem version between sender and receiver
+			mustLiveVersions := []zfs.FilesystemVersion{sendArgs.ToVersion}
 			if sendArgs.FromVersion != nil {
-				checkFullpaths["FromVersion"] = sendArgs.FromVersion.FullPath(sendArgs.FS)
+				mustLiveVersions = append(mustLiveVersions, *sendArgs.FromVersion)
 			}
-			for _, a := range obsoleteAbs {
-				for what, fullpath := range checkFullpaths {
-					if a.GetFullPath() == fullpath && a.GetType().IsSnapshotOrBookmark() {
-						problems = append(problems, Problem{
-							sendArgsWhat: what,
-							fullpath:     fullpath,
-							obsoleteAbs:  a,
-						})
+			for _, staleVersion := range obsoleteAbs {
+				for _, mustLiveVersion := range mustLiveVersions {
+					isSendArg := zfs.FilesystemVersionEqualIdentity(mustLiveVersion, staleVersion.GetFilesystemVersion())
+					stepHoldBasedGuaranteeStrategy := false
+					k := replicationGuaranteeStrategy.Kind()
+					switch k {
+					case ReplicationGuaranteeKindResumability:
+						stepHoldBasedGuaranteeStrategy = true
+					case ReplicationGuaranteeKindIncremental:
+					case ReplicationGuaranteeKindNone:
+					default:
+						panic(fmt.Sprintf("this is supposed to be an exhaustive match, got %v", k))
+					}
+					isSnapshot := mustLiveVersion.IsSnapshot()
+					if isSendArg && (!isSnapshot || stepHoldBasedGuaranteeStrategy) {
+						panic(fmt.Sprintf("impl error: %q would be destroyed because it is considered stale but it is part of of sendArgs=%s", mustLiveVersion.String(), pretty.Sprint(sendArgs)))
 					}
 				}
 			}
-			if len(problems) == 0 {
-				return
 		}
-			var msg strings.Builder
-			fmt.Fprintf(&msg, "cleaning up send stale would destroy send args:\n")
-			fmt.Fprintf(&msg, "  SendArgs: %s\n", pretty.Sprint(sendArgs))
-			for _, check := range problems {
-				fmt.Fprintf(&msg, "would delete %s %s because it was deemed an obsolete abstraction: %s\n",
-					check.sendArgsWhat, check.fullpath, check.obsoleteAbs)
-			}
-			panic(msg.String())
+		destroyTypes := AbstractionTypeSet{
+			AbstractionStepHold:                           true,
+			AbstractionTentativeReplicationCursorBookmark: true,
 		}
 		abstractionsCacheSingleton.TryBatchDestroy(ctx, s.jobId, sendArgs.FS, destroyTypes, keep, check)
 	}()
@@ -454,7 +428,6 @@ func (p *Sender) Receive(ctx context.Context, r *pdu.ReceiveReq, _ io.ReadCloser

 type FSFilter interface { // FIXME unused
 	Filter(path *zfs.DatasetPath) (pass bool, err error)
-	UserSpecifiedDatasets() zfs.UserSpecifiedDatasetsSet
 }

 // FIXME: can we get away without error types here?
@@ -614,12 +587,6 @@ func (f subroot) Filter(p *zfs.DatasetPath) (pass bool, err error) {
 	return p.HasPrefix(f.localRoot) && !p.Equal(f.localRoot), nil
 }

-func (f subroot) UserSpecifiedDatasets() zfs.UserSpecifiedDatasetsSet {
-	return zfs.UserSpecifiedDatasetsSet{
-		f.localRoot.ToString(): true,
-	}
-}
-
 func (f subroot) MapToLocal(fs string) (*zfs.DatasetPath, error) {
 	p, err := zfs.NewDatasetPath(fs)
 	if err != nil {
@@ -89,8 +89,6 @@ func ReplicationGuaranteeFromKind(k ReplicationGuaranteeKind) ReplicationGuarant

 type ReplicationGuaranteeNone struct{}

-func (g ReplicationGuaranteeNone) String() string { return "none" }
-
 func (g ReplicationGuaranteeNone) Kind() ReplicationGuaranteeKind {
 	return ReplicationGuaranteeKindNone
 }
@@ -109,8 +107,6 @@ func (g ReplicationGuaranteeNone) SenderPostRecvConfirmed(ctx context.Context, j

 type ReplicationGuaranteeIncremental struct{}

-func (g ReplicationGuaranteeIncremental) String() string { return "incremental" }
-
 func (g ReplicationGuaranteeIncremental) Kind() ReplicationGuaranteeKind {
 	return ReplicationGuaranteeKindIncremental
 }
@@ -148,8 +144,6 @@ func (g ReplicationGuaranteeIncremental) SenderPostRecvConfirmed(ctx context.Con

 type ReplicationGuaranteeResumability struct{}

-func (g ReplicationGuaranteeResumability) String() string { return "resumability" }
-
 func (g ReplicationGuaranteeResumability) Kind() ReplicationGuaranteeKind {
 	return ReplicationGuaranteeKindResumability
 }
@@ -31,7 +31,7 @@ const (
 	AbstractionReplicationCursorBookmarkV2        AbstractionType = "replication-cursor-bookmark-v2"
 )

-var AbstractionTypesAll = AbstractionTypeSet{
+var AbstractionTypesAll = map[AbstractionType]bool{
 	AbstractionStepHold:                           true,
 	AbstractionLastReceivedHold:                   true,
 	AbstractionTentativeReplicationCursorBookmark: true,
@@ -181,38 +181,6 @@ func (s AbstractionTypeSet) Validate() error {
 	return nil
 }

-// Use the `BookmarkExtractor()` method of each abstraction type in this set
-// to try extract an abstraction from the given FilesystemVersion.
-//
-// Abstraction types in this set that don't have a bookmark extractor are skipped.
-//
-// Panics if more than one abstraction type matches.
-func (s AbstractionTypeSet) ExtractBookmark(dp *zfs.DatasetPath, v *zfs.FilesystemVersion) Abstraction {
-	matched := make(AbstractionTypeSet, 1)
-	var matchedAbs Abstraction
-	for absType := range s {
-		extractor := absType.BookmarkExtractor()
-		if extractor == nil {
-			continue
-		}
-		abstraction := extractor(dp, *v)
-		if abstraction != nil {
-			matched[absType] = true
-			matchedAbs = abstraction
-		}
-	}
-	if len(matched) == 0 {
-		return nil
-	}
-	if len(matched) == 1 {
-		if matchedAbs == nil {
-			panic("loop above should always set matchedAbs if there is a match")
-		}
-		return matchedAbs
-	}
-	panic(fmt.Sprintf("abstraction types extractors should not overlap: %s", matched))
-}
-
 type BookmarkExtractor func(fs *zfs.DatasetPath, v zfs.FilesystemVersion) Abstraction

 // returns nil if the abstraction type is not bookmark-based
@@ -270,23 +238,6 @@ func (t AbstractionType) BookmarkNamer() func(fs string, guid uint64, jobId JobI
 	}
 }

-func (t AbstractionType) IsSnapshotOrBookmark() bool {
-	switch t {
-	case AbstractionTentativeReplicationCursorBookmark:
-		return true
-	case AbstractionReplicationCursorBookmarkV1:
-		return true
-	case AbstractionReplicationCursorBookmarkV2:
-		return true
-	case AbstractionStepHold:
-		return false
-	case AbstractionLastReceivedHold:
-		return false
-	default:
-		panic(fmt.Sprintf("unimpl: %q", t))
-	}
-}
-
 type ListZFSHoldsAndBookmarksQuery struct {
 	FS ListZFSHoldsAndBookmarksQueryFilesystemFilter
 	// What abstraction types should match (any contained in the set)
@@ -150,7 +150,9 @@ func NewOutlets() *Outlets {
 func (os *Outlets) DeepCopy() (copy *Outlets) {
 	copy = NewOutlets()
 	for level := range os.outs {
-		copy.outs[level] = append(copy.outs[level], os.outs[level]...)
+		for i := range os.outs[level] {
+			copy.outs[level] = append(copy.outs[level], os.outs[level][i])
+		}
 	}
 	return copy
 }
@@ -7,8 +7,7 @@ RUN apt-get update && apt-get install -y \
    dh-exec \
 	binutils-aarch64-linux-gnu \
 	binutils-arm-linux-gnueabihf  \
-	binutils-i686-linux-gnu \
-	binutils-x86-64-linux-gnu
+	binutils-i686-linux-gnu

 RUN mkdir -p /build/src && chmod -R 0777 /build

@@ -4,21 +4,6 @@ export ZREPL_MOCK_ZFS_COMMAND_LOG="$1"
 shift
 export ZREPL_MOCK_ZFS_PATH="$1"
 shift
-dirname="$(dirname "${BASH_SOURCE[0]}")"
-# If we invoke this script from the top zrepl source tree, like so:
-#    ./platformtest/logmockzfs/logzfsenv ...
-# then dirname is relative, i.e., ./platformtest/logmockzfs.
-# If we put that relative dir in PATH, then Go >= 1.19 will refuse to
-# exec the `./platformtest/logmockzfs/zfs` wrapper script if it finds
-# it via PATH lookup. For Example:
-#   cmd := exec.Command("zfs")
-#   err := cmd.Run()
-# will fail with an error that errors.Is(err, exec.ErrDot), message:
-#   cannot run executable found relative to current directory
-# The solution is to use an abspath.
-# Learn more at https://pkg.go.dev/os/exec#hdr-Executables_in_the_current_directory
-# and https://go-review.googlesource.com/c/go/+/381374
-absdirname="$(readlink -e "$dirname")"
-export PATH="$absdirname":"$PATH"
+export PATH="$(dirname "${BASH_SOURCE[0]}" )":"$PATH"
 args=("$@")
 exec "${args[@]}"
@@ -20,7 +20,6 @@ var Cases = []Case{BatchDestroy,
 	ReplicationIncrementalCleansUpStaleAbstractionsWithCacheOnSecondReplication,
 	ReplicationIncrementalCleansUpStaleAbstractionsWithoutCacheOnSecondReplication,
 	ReplicationIncrementalDestroysStepHoldsIffIncrementalStepHoldsAreDisabledButStepHoldsExist,
-	ReplicationIncrementalHandlesFromVersionEqTentativeCursorCorrectly,
 	ReplicationIncrementalIsPossibleIfCommonSnapshotIsDestroyed,
 	ReplicationInitialAll,
 	ReplicationInitialFail,
@@ -248,10 +248,7 @@ func implReplicationIncrementalCleansUpStaleAbstractions(ctx *platformtest.Conte
 		require.NoError(ctx, err)
 		snap2Hold, err := endpoint.HoldStep(ctx, sfs, snap2, jobId) // no shadow
 		require.NoError(ctx, err)
-		// create artificial tentative cursor
-		snap3TentativeCursor, err := endpoint.CreateTentativeReplicationCursor(ctx, sfs, snap3, jobId)
-		require.NoError(ctx, err)
-		return []endpoint.Abstraction{snap2Cursor, snap1Hold, snap2Hold, snap3TentativeCursor}
+		return []endpoint.Abstraction{snap2Cursor, snap1Hold, snap2Hold}
 	}
 	createArtificalStaleAbstractions(sjid)
 	ojidSendAbstractions := createArtificalStaleAbstractions(ojid)
@@ -336,29 +333,21 @@ func implReplicationIncrementalCleansUpStaleAbstractions(ctx *platformtest.Conte
 		require.NoError(ctx, err)
 		snap2OjidCursorName, err := endpoint.ReplicationCursorBookmarkName(sfs, snap2.Guid, ojid)
 		require.NoError(ctx, err)
-		snap3SjidTentativeCursorName, err := endpoint.TentativeReplicationCursorBookmarkName(sfs, snap3.Guid, sjid)
-		require.NoError(ctx, err)
-		snap3OjidTentativeCursorName, err := endpoint.TentativeReplicationCursorBookmarkName(sfs, snap3.Guid, ojid)
-		require.NoError(ctx, err)
 		var bmNames []string
 		for _, bm := range sBms {
 			bmNames = append(bmNames, bm.Name)
 		}

 		if invalidateCacheBeforeSecondReplication {
-			require.Len(ctx, sBms, 4)
+			require.Len(ctx, sBms, 3)
 			require.Contains(ctx, bmNames, snap5SjidCursorName)
 			require.Contains(ctx, bmNames, snap2OjidCursorName)
-			require.Contains(ctx, bmNames, snap3OjidTentativeCursorName)
 			require.Contains(ctx, bmNames, "2")
 		} else {
-			require.Len(ctx, sBms, 6)
-			ctx.Logf("%s", pretty.Sprint(sBms))
+			require.Len(ctx, sBms, 4)
 			require.Contains(ctx, bmNames, snap5SjidCursorName)
 			require.Contains(ctx, bmNames, snap2SjidCursorName)
 			require.Contains(ctx, bmNames, snap2OjidCursorName)
-			require.Contains(ctx, bmNames, snap3SjidTentativeCursorName)
-			require.Contains(ctx, bmNames, snap3OjidTentativeCursorName)
 			require.Contains(ctx, bmNames, "2")
 		}
 	}
@@ -381,84 +370,6 @@ func implReplicationIncrementalCleansUpStaleAbstractions(ctx *platformtest.Conte

 }

-func ReplicationIncrementalHandlesFromVersionEqTentativeCursorCorrectly(ctx *platformtest.Context) {
-
-	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
-		CREATEROOT
-		+  "sender"
-		+  "sender@1"
-		+  "receiver"
-		R  zfs create -p "${ROOTDS}/receiver/${ROOTDS}"
-	`)
-
-	sjid := endpoint.MustMakeJobID("sender-job")
-	rjid := endpoint.MustMakeJobID("receiver-job")
-
-	sfs := ctx.RootDataset + "/sender"
-	rfsRoot := ctx.RootDataset + "/receiver"
-
-	rep := replicationInvocation{
-		sjid:    sjid,
-		rjid:    rjid,
-		sfs:     sfs,
-		rfsRoot: rfsRoot,
-		// It doesn't really matter what guarantee we use here, as the second replication will configure another.
-		// But, in the real world, the only way for a stale tentative cursor to appear is if the guarantee is set to
-		// incremental replication and we crash before converting the tentative cursor into a regular cursor.
-		guarantee: pdu.ReplicationConfigProtectionWithKind(pdu.ReplicationGuaranteeKind_GuaranteeIncrementalReplication),
-	}
-
-	// Do initial replication to set up the test.
-	rep1 := rep.Do(ctx)
-	ctx.Logf("\n%s", pretty.Sprint(rep1))
-	sfsDs := mustDatasetPath(sfs)
-	snap1_sender := mustGetFilesystemVersion(ctx, sfs+"@1")
-	snap1_replicationCursor_name, err := endpoint.ReplicationCursorBookmarkName(sfs, snap1_sender.Guid, sjid)
-	require.NoError(ctx, err)
-	snap1_replicationCursor := mustGetFilesystemVersion(ctx, sfs+"#"+snap1_replicationCursor_name)
-
-	// The second replication will be done with a guarantee kind that doesn't create tentative cursors by itself.
-	// So, it would generally be right to clean up any tentative cursors on sfs since they're stale abstractions.
-	// However, if the cursor is used as the `from` version in any send step, we must not destroy it, as that
-	// would break incremental replication.
-	// NB: we only need to test the first step as all subsequent steps will be snapshot->snapshot.
-	rep.guarantee = pdu.ReplicationConfigProtectionWithKind(pdu.ReplicationGuaranteeKind_GuaranteeNothing)
-	// create the artificial cursor
-	snap1_tentativeCursor, err := endpoint.CreateTentativeReplicationCursor(ctx, sfs, snap1_sender, sjid)
-	require.NoError(ctx, err)
-	endpoint.AbstractionsCacheInvalidate(sfs)
-	// remove other bookmarks of snap1, and snap1 itself, to force the replication planner to use the tentative cursor
-	err = zfs.ZFSDestroyFilesystemVersion(ctx, sfsDs, &snap1_sender)
-	require.NoError(ctx, err)
-	err = zfs.ZFSDestroyFilesystemVersion(ctx, sfsDs, &snap1_replicationCursor)
-	require.NoError(ctx, err)
-	versions, err := zfs.ZFSListFilesystemVersions(ctx, sfsDs, zfs.ListFilesystemVersionsOptions{})
-	require.NoError(ctx, err)
-	require.Len(ctx, versions, 1)
-	require.Equal(ctx, versions[0].Guid, snap1_tentativeCursor.GetFilesystemVersion().Guid)
-	// create another snapshot so that replication does one incremental step `tentative_cursor` -> `@2`
-	mustSnapshot(ctx, sfs+"@2")
-	mustGetFilesystemVersion(ctx, sfs+"@2")
-	// do the replication
-	rep2 := rep.Do(ctx)
-	ctx.Logf("\n%s", pretty.Sprint(rep2))
-
-	// Ensure that the tentative cursor was used.
-	require.Len(ctx, rep2.Attempts, 1)
-	require.Equal(ctx, rep2.Attempts[0].State, report.AttemptDone)
-	require.Len(ctx, rep2.Attempts[0].Filesystems, 1)
-	require.Nil(ctx, rep2.Attempts[0].Filesystems[0].Error())
-	require.Len(ctx, rep2.Attempts[0].Filesystems[0].Steps, 1)
-	require.EqualValues(ctx, rep2.Attempts[0].Filesystems[0].CurrentStep, 1)
-	require.Len(ctx, rep2.Attempts[0].Filesystems[0].Steps, 1)
-	require.Equal(ctx, rep2.Attempts[0].Filesystems[0].Steps[0].Info.From, snap1_tentativeCursor.GetFilesystemVersion().RelName())
-
-	// Ensure that the tentative cursor was destroyed as part of SendPost.
-	_, err = zfs.ZFSGetFilesystemVersion(ctx, snap1_replicationCursor.FullPath(sfs))
-	_, ok := err.(*zfs.DatasetDoesNotExist)
-	require.True(ctx, ok)
-}
-
 type PartialSender struct {
 	*endpoint.Sender
 	failAfterByteCount int64
@@ -192,14 +192,3 @@ func (r *Report) GetFailedFilesystemsCountInLatestAttempt() int {
 		return 0
 	}
 }
-
-// Returns true in case the AttemptState is a terminal
-// state(AttemptPlanningError, AttemptFanOutError, AttemptDone)
-func (a AttemptState) IsTerminal() bool {
-	switch a {
-	case AttemptPlanningError, AttemptFanOutError, AttemptDone:
-		return true
-	default:
-		return false
-	}
-}
@@ -107,31 +107,34 @@ func (c *Conn) RenewWriteDeadline() error {
 	return c.SetWriteDeadline(time.Now().Add(c.idleTimeout))
 }

-func (c *Conn) Read(p []byte) (n int, _ error) {
+func (c *Conn) Read(p []byte) (n int, err error) {
 	n = 0
+	err = nil
 restart:
 	if err := c.renewReadDeadline(); err != nil {
 		return n, err
 	}
 	var nCurRead int
-	nCurRead, err := c.Wire.Read(p[n:])
+	nCurRead, err = c.Wire.Read(p[n:])
 	n += nCurRead
 	if netErr, ok := err.(net.Error); ok && netErr.Timeout() && nCurRead > 0 {
+		err = nil
 		goto restart
 	}
 	return n, err
 }

-func (c *Conn) Write(p []byte) (n int, _ error) {
+func (c *Conn) Write(p []byte) (n int, err error) {
 	n = 0
 restart:
 	if err := c.RenewWriteDeadline(); err != nil {
 		return n, err
 	}
 	var nCurWrite int
-	nCurWrite, err := c.Wire.Write(p[n:])
+	nCurWrite, err = c.Wire.Write(p[n:])
 	n += nCurWrite
 	if netErr, ok := err.(net.Error); ok && netErr.Timeout() && nCurWrite > 0 {
+		err = nil
 		goto restart
 	}
 	return n, err
@@ -141,16 +144,17 @@ restart:
 // but is guaranteed to use the writev system call if the wrapped Wire
 // support it.
 // Note the Conn does not support writev through io.Copy(aConn, aNetBuffers).
-func (c *Conn) WritevFull(bufs net.Buffers) (n int64, _ error) {
+func (c *Conn) WritevFull(bufs net.Buffers) (n int64, err error) {
 	n = 0
 restart:
 	if err := c.RenewWriteDeadline(); err != nil {
 		return n, err
 	}
 	var nCurWrite int64
-	nCurWrite, err := io.Copy(c.Wire, &bufs)
+	nCurWrite, err = io.Copy(c.Wire, &bufs)
 	n += nCurWrite
 	if netErr, ok := err.(net.Error); ok && netErr.Timeout() && nCurWrite > 0 {
+		err = nil
 		goto restart
 	}
 	return n, err
@@ -1,96 +0,0 @@
-package suspendresumesafetimer
-
-import (
-	"context"
-	"time"
-
-	"github.com/zrepl/zrepl/util/envconst"
-)
-
-// The returned error is guaranteed to be the ctx.Err()
-func SleepUntil(ctx context.Context, sleepUntil time.Time) error {
-
-	// We use .Round(0) to strip the monotonic clock reading from the time.Time
-	// returned by time.Now(). That will make the before/after check in the ticker
-	// for-loop compare wall-clock times instead of monotonic time.
-	// Comparing wall clock time is necessary because monotonic time does not progress
-	// while the system is suspended.
-	//
-	// Background
-	//
-	// A time.Time carries a wallclock timestamp and optionally a monotonic clock timestamp.
-	// time.Now() returns a time.Time that carries both.
-	// time.Time.Add() applies the same delta to both timestamps in the time.Time.
-	// x.Sub(y) will return the *monotonic* delta if both x and y carry a monotonic timestamp.
-	// time.Until(x) == x.Sub(now) where `now` will have a monotonic timestamp.
-	// So, time.Until(x) with an `x` that has monotonic timestamp will return monotonic delta.
-	//
-	// Why Do We Care?
-	//
-	// On systems that suspend/resume, wall clock time progresses during suspend but
-	// monotonic time does not.
-	//
-	// So, suppose the following sequence of events:
-	//   x <== time.Now()
-	//   System suspends for 1 hour
-	//   delta <== time.Now().Sub(x)
-	// `delta` will be near 0 because time.Until() subtracts the monotonic
-	// timestamps, and monotonic time didn't progress during suspend.
-	//
-	// Now strip the timestamp using .Round(0)
-	//   x <== time.Now().Round(0)
-	//   System suspends for 1 hour
-	//   delta <== time.Now().Sub(x)
-	// `delta` will be 1 hour because time.Sub() subtracted wallclock timestamps
-	// because x didn't have a monotonic timestamp because we stripped it using .Round(0).
-	//
-	//
-	sleepUntil = sleepUntil.Round(0)
-
-	// Set up a timer so that, if the system doesn't suspend/resume,
-	// we get a precise wake-up time from the native Go timer.
-	monotonicClockTimer := time.NewTimer(time.Until(sleepUntil))
-	defer func() {
-		if !monotonicClockTimer.Stop() {
-			// non-blocking read since we can come here when
-			// we've already drained the channel through
-			//		case <-monotonicClockTimer.C
-			// in the `for` loop below.
-			select {
-			case <-monotonicClockTimer.C:
-			default:
-			}
-		}
-	}()
-
-	// Set up a ticker so that we're guaranteed to wake up periodically.
-	// We'll then get the current wall-clock time and check ourselves
-	// whether we're past the requested expiration time.
-	// Pick a 10 second check interval by default since it's rare that
-	// suspend/resume is done more frequently.
-	ticker := time.NewTicker(envconst.Duration("ZREPL_WALLCLOCKTIMER_MAX_DELAY", 10*time.Second))
-	defer ticker.Stop()
-
-	for {
-		select {
-		case <-monotonicClockTimer.C:
-			return nil
-		case <-ticker.C:
-			now := time.Now()
-			if now.Before(sleepUntil) {
-				// Continue waiting.
-
-				// Reset the monotonic timer to reset drift.
-				if !monotonicClockTimer.Stop() {
-					<-monotonicClockTimer.C
-				}
-				monotonicClockTimer.Reset(time.Until(sleepUntil))
-
-				continue
-			}
-			return nil
-		case <-ctx.Done():
-			return ctx.Err()
-		}
-	}
-}
@@ -3,20 +3,12 @@ package zfs
 import (
 	"context"
 	"fmt"
-
-	"github.com/zrepl/zrepl/zfs/zfscmd"
 )

 type DatasetFilter interface {
 	Filter(p *DatasetPath) (pass bool, err error)
-	// The caller owns the returned set.
-	// Implementations should return a copy.
-	UserSpecifiedDatasets() UserSpecifiedDatasetsSet
 }

-// A set of dataset names that the user specified in the configuration file.
-type UserSpecifiedDatasetsSet map[string]bool
-
 // Returns a DatasetFilter that does not filter (passes all paths)
 func NoFilter() DatasetFilter {
 	return noFilter{}
@@ -27,7 +19,6 @@ type noFilter struct{}
 var _ DatasetFilter = noFilter{}

 func (noFilter) Filter(p *DatasetPath) (pass bool, err error) { return true, nil }
-func (noFilter) UserSpecifiedDatasets() UserSpecifiedDatasetsSet { return nil }

 func ZFSListMapping(ctx context.Context, filter DatasetFilter) (datasets []*DatasetPath, err error) {
 	res, err := ZFSListMappingProperties(ctx, filter, nil)
@@ -70,7 +61,6 @@ func ZFSListMappingProperties(ctx context.Context, filter DatasetFilter, propert

 	go ZFSListChan(ctx, rchan, properties, nil, "-r", "-t", "filesystem,volume")

-	unmatchedUserSpecifiedDatasets := filter.UserSpecifiedDatasets()
 	datasets = make([]ZFSListMappingPropertiesResult, 0)
 	for r := range rchan {

@@ -84,8 +74,6 @@ func ZFSListMappingProperties(ctx context.Context, filter DatasetFilter, propert
 			return
 		}

-		delete(unmatchedUserSpecifiedDatasets, path.ToString())
-
 		pass, filterErr := filter.Filter(path)
 		if filterErr != nil {
 			return nil, fmt.Errorf("error calling filter: %s", filterErr)
@@ -99,9 +87,5 @@ func ZFSListMappingProperties(ctx context.Context, filter DatasetFilter, propert

 	}

-	jobid := zfscmd.GetJobIDOrDefault(ctx, "__nojobid")
-	metric := prom.ZFSListUnmatchedUserSpecifiedDatasetCount.WithLabelValues(jobid)
-	metric.Add(float64(len(unmatchedUserSpecifiedDatasets)))
-
 	return
 }
@@ -7,7 +7,6 @@ var prom struct {
 	ZFSSnapshotDuration              *prometheus.HistogramVec
 	ZFSBookmarkDuration              *prometheus.HistogramVec
 	ZFSDestroyDuration               *prometheus.HistogramVec
-	ZFSListUnmatchedUserSpecifiedDatasetCount *prometheus.GaugeVec
 }

 func init() {
@@ -35,15 +34,6 @@ func init() {
 		Name:      "destroy_duration",
 		Help:      "Duration it took to destroy a dataset",
 	}, []string{"dataset_type", "filesystem"})
-	prom.ZFSListUnmatchedUserSpecifiedDatasetCount = prometheus.NewGaugeVec(prometheus.GaugeOpts{
-		Namespace: "zrepl",
-		Subsystem: "zfs",
-		Name:      "list_unmatched_user_specified_dataset_count",
-		Help: "When evaluating a DatsetFilter against zfs list output, this counter " +
-			"is incremented for every DatasetFilter rule that did not match any " +
-			"filesystem name in the zfs list output. Monitor for increases to detect filesystem " +
-			"filter rules that have no effect because they don't match any local filesystem.",
-	}, []string{"jobid"})
 }

 func PrometheusRegister(registry prometheus.Registerer) error {
@@ -59,8 +49,5 @@ func PrometheusRegister(registry prometheus.Registerer) error {
 	if err := registry.Register(prom.ZFSDestroyDuration); err != nil {
 		return err
 	}
-	if err := registry.Register(prom.ZFSListUnmatchedUserSpecifiedDatasetCount); err != nil {
-		return err
-	}
 	return nil
 }
@@ -343,6 +343,7 @@ const (

 type SendStream struct {
 	cmd          *zfscmd.Cmd
+	kill         context.CancelFunc
 	stdoutReader io.ReadCloser // not *os.File for mocking during platformtest
 	stderrBuf    *circlog.CircularLog

@@ -415,29 +416,8 @@ func (s *SendStream) killAndWait() error {
 	debug("sendStream: killAndWait enter")
 	defer debug("sendStream: killAndWait leave")

-	// ensure this function is only called once
-	if s.state != sendStreamOpen {
-		panic(s.state)
-	}
-
 	// send SIGKILL
-	// In an earlier version, we used the starting context.Context's cancel function
-	// for this, but in Go > 1.19, doing so will cause .Wait() to return the
-	// context cancel error instead of the *exec.ExitError.
-	err := s.cmd.Process().Kill()
-	if err != nil {
-		if err == os.ErrProcessDone {
-			// This can happen if
-			// (1) the process has already been .Wait()ed, or
-			// (2) some other goroutine cancels the context, likely further up
-			//     the context tree.
-			// Case (1) can't happen to us because we only call
-			// this function in sendStreamOpen state.
-			// In Case (2), it's still our job to .Wait(), so, fallthrough.
-		} else {
-			return err
-		}
-	}
+	s.kill()

 	// Close our read-end of the pipe.
 	//
@@ -983,10 +963,10 @@ func ZFSSend(ctx context.Context, sendArgs ZFSSendArgsValidated) (*SendStream, e

 	stream := &SendStream{
 		cmd:          cmd,
+		kill:         cancel,
 		stdoutReader: stdoutReader,
 		stderrBuf:    stderrBuf,
 	}
-	_ = cancel // the SendStream.killAndWait() will kill the process

 	return stream, nil
 }
@@ -19,10 +19,6 @@ func WithJobID(ctx context.Context, jobID string) context.Context {
 	return context.WithValue(ctx, contextKeyJobID, jobID)
 }

-func GetJobIDOrDefault(ctx context.Context, def string) string {
-	return getJobIDOrDefault(ctx, def)
-}
-
 func getJobIDOrDefault(ctx context.Context, def string) string {
 	ret, ok := ctx.Value(contextKeyJobID).(string)
 	if !ok {