docs: continous_server_backup: simplify by removing need for recv.placeholder

closes https://github.com/zrepl/zrepl/pull/552
fixes https://github.com/zrepl/zrepl/issues/551

Signed-off-by: Andrew Gunnerson <chillermillerlong@hotmail.com>
Co-authored-by: Christian Schwarz <me@cschwarz.com>

.circleci/config.yml

@@ -150,7 +150,7 @@ parameters:
 
   release_docker_baseimage_tag:
     type: string
-    default: "1.16"
+    default: "1.17"
 
 workflows:
   version: 2
@@ -160,15 +160,15 @@ workflows:
     jobs:
       - quickcheck-docs
       - quickcheck-go: &quickcheck-go-smoketest
-          name: quickcheck-go-amd64-linux-1.16
-          goversion: &latest-go-release "1.16"
+          name: quickcheck-go-amd64-linux-1.17
+          goversion: &latest-go-release "1.17"
           goos: linux
           goarch: amd64
       - test-go-on-latest-go-release:
           goversion: *latest-go-release
       - quickcheck-go:
           requires:
-            - quickcheck-go-amd64-linux-1.16 #quickcheck-go-smoketest.name
+            - quickcheck-go-amd64-linux-1.17 #quickcheck-go-smoketest.name
           matrix: &quickcheck-go-matrix
             alias: quickcheck-go-matrix
             parameters:
@@ -231,8 +231,6 @@ jobs:
       - install-docdep
       - run: make docs
 
-      - store_artifacts:
-          path: artifacts
       - download-and-install-minio-client
       - upload-minio:
           src: artifacts
@@ -358,7 +356,7 @@ jobs:
           subcommand: docdep
       - run:
           command: |
-            git config --global user.email "me@cschwarz.com"
+            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

Makefile

@@ -28,7 +28,7 @@ GO_BUILDFLAGS := $(GO_MOD_READONLY) $(GO_EXTRA_BUILDFLAGS)
 GO_BUILD := $(GO_ENV_VARS) $(GO) build $(GO_BUILDFLAGS) -ldflags $(GO_LDFLAGS)
 GOLANGCI_LINT := golangci-lint
 GOCOVMERGE := gocovmerge
-RELEASE_DOCKER_BASEIMAGE_TAG ?= 1.16
+RELEASE_DOCKER_BASEIMAGE_TAG ?= 1.17
 RELEASE_DOCKER_BASEIMAGE ?= golang:$(RELEASE_DOCKER_BASEIMAGE_TAG)
 
 ifneq ($(GOARM),)
@@ -189,6 +189,8 @@ GO_SUPPORTS_ILLUMOS := $(shell $(GO) version | gawk -F '.' '/^go version /{split
 bins-all:
 	$(MAKE) $(BINS_ALL_TARGETS) GOOS=freebsd   GOARCH=amd64
 	$(MAKE) $(BINS_ALL_TARGETS) GOOS=freebsd   GOARCH=386
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=freebsd   GOARCH=arm	  GOARM=7
+	$(MAKE) $(BINS_ALL_TARGETS) GOOS=freebsd   GOARCH=arm64
 	$(MAKE) $(BINS_ALL_TARGETS) GOOS=linux     GOARCH=amd64
 	$(MAKE) $(BINS_ALL_TARGETS) GOOS=linux     GOARCH=arm64
 	$(MAKE) $(BINS_ALL_TARGETS) GOOS=linux     GOARCH=arm     GOARM=7

README.md

@@ -1,11 +1,12 @@
 [![GitHub license](https://img.shields.io/github/license/zrepl/zrepl.svg)](https://github.com/zrepl/zrepl/blob/master/LICENSE)
-[![Language: Go](https://img.shields.io/badge/language-Go-6ad7e5.svg)](https://golang.org/)
+[![Language: Go](https://img.shields.io/badge/lang-Go-6ad7e5.svg)](https://golang.org/)
 [![User Docs](https://img.shields.io/badge/docs-web-blue.svg)](https://zrepl.github.io)
-[![Support me on Patreon](https://img.shields.io/badge/dynamic/json?color=yellow&label=Patreon&query=data.attributes.patron_count&suffix=%20patrons&url=https%3A%2F%2Fwww.patreon.com%2Fapi%2Fcampaigns%2F3095079)](https://patreon.com/zrepl)
+[![Support me on Patreon](https://img.shields.io/badge/dynamic/json?color=yellow&label=Patreon&query=data.attributes.patron_count&url=https%3A%2F%2Fwww.patreon.com%2Fapi%2Fcampaigns%2F3095079)](https://patreon.com/zrepl)
 [![Donate via GitHub Sponsors](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&style=flat&color=yellow)](https://github.com/sponsors/problame)
 [![Donate via Liberapay](https://img.shields.io/liberapay/patrons/zrepl.svg?logo=liberapay)](https://liberapay.com/zrepl/donate)
 [![Donate via PayPal](https://img.shields.io/badge/donate-paypal-yellow.svg)](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96)
 [![Twitter](https://img.shields.io/twitter/url/https/github.com/zrepl/zrepl.svg?style=social)](https://twitter.com/intent/tweet?text=Wow:&url=https%3A%2F%2Fgithub.com%2Fzrepl%2Fzrepl)
+[![Chat](https://img.shields.io/badge/chat-matrix-blue.svg)](https://matrix.to/#/#zrepl:matrix.org)
 
 # zrepl
 zrepl is a one-stop ZFS backup & replication solution.
@@ -95,7 +96,7 @@ Downstream packagers can read the changelog to determine whether they want to pu
 
 ### Additional Notes to Distro Package Maintainers
 
-* Use `sudo make test-platform-bin && sudo make test-platform` **on a test system** to validate that zrepl's abstractions on top of ZFS work with the system ZFS.
+* Run the platform tests (Docs -> Usage -> Platform Tests) **on a test system** to validate that zrepl's abstractions on top of ZFS work with the system ZFS.
 * Ship a default config that adheres to your distro's `hier` and logging system.
 * Ship a service manager file and _please_ try to upstream it to this repository.
   * `dist/systemd` contains a Systemd unit template.

build/tools.go

@@ -1,3 +1,4 @@
+//go:build tools
 // +build tools
 
 package main

client/status.go

@@ -1,816 +0,0 @@
-package client
-
-import (
-	"context"
-	"fmt"
-	"io"
-	"math"
-	"net/http"
-	"os"
-	"sort"
-	"strings"
-	"sync"
-	"time"
-
-	// tcell is the termbox-compatible library for abstracting away escape sequences, etc.
-	// as of tcell#252, the number of default distributed terminals is relatively limited
-	// additional terminal definitions can be included via side-effect import
-	// See https://github.com/gdamore/tcell/blob/master/terminfo/base/base.go
-	// See https://github.com/gdamore/tcell/issues/252#issuecomment-533836078
-	"github.com/gdamore/tcell/termbox"
-	_ "github.com/gdamore/tcell/terminfo/s/screen" // tmux on FreeBSD 11 & 12 without ncurses
-
-	"github.com/pkg/errors"
-	"github.com/spf13/pflag"
-	"github.com/zrepl/yaml-config"
-
-	"github.com/zrepl/zrepl/cli"
-	"github.com/zrepl/zrepl/daemon"
-	"github.com/zrepl/zrepl/daemon/job"
-	"github.com/zrepl/zrepl/daemon/pruner"
-	"github.com/zrepl/zrepl/daemon/snapper"
-	"github.com/zrepl/zrepl/replication/report"
-)
-
-type byteProgressMeasurement struct {
-	time time.Time
-	val  int64
-}
-
-type bytesProgressHistory struct {
-	last        *byteProgressMeasurement // pointer as poor man's optional
-	changeCount int
-	lastChange  time.Time
-	bpsAvg      float64
-}
-
-func (p *bytesProgressHistory) Update(currentVal int64) (bytesPerSecondAvg int64, changeCount int) {
-
-	if p.last == nil {
-		p.last = &byteProgressMeasurement{
-			time: time.Now(),
-			val:  currentVal,
-		}
-		return 0, 0
-	}
-
-	if p.last.val != currentVal {
-		p.changeCount++
-		p.lastChange = time.Now()
-	}
-
-	if time.Since(p.lastChange) > 3*time.Second {
-		p.last = nil
-		return 0, 0
-	}
-
-	deltaV := currentVal - p.last.val
-	deltaT := time.Since(p.last.time)
-	rate := float64(deltaV) / deltaT.Seconds()
-
-	factor := 0.3
-	p.bpsAvg = (1-factor)*p.bpsAvg + factor*rate
-
-	p.last.time = time.Now()
-	p.last.val = currentVal
-
-	return int64(p.bpsAvg), p.changeCount
-}
-
-type tui struct {
-	x, y   int
-	indent int
-
-	lock   sync.Mutex //For report and error
-	report map[string]*job.Status
-	err    error
-
-	jobFilter string
-
-	replicationProgress map[string]*bytesProgressHistory // by job name
-}
-
-func newTui() tui {
-	return tui{
-		replicationProgress: make(map[string]*bytesProgressHistory),
-	}
-}
-
-const INDENT_MULTIPLIER = 4
-
-func (t *tui) moveLine(dl int, col int) {
-	t.y += dl
-	t.x = t.indent*INDENT_MULTIPLIER + col
-}
-
-func (t *tui) write(text string) {
-	for _, c := range text {
-		if c == '\n' {
-			t.newline()
-			continue
-		}
-		termbox.SetCell(t.x, t.y, c, termbox.ColorDefault, termbox.ColorDefault)
-		t.x += 1
-	}
-}
-
-func (t *tui) printf(text string, a ...interface{}) {
-	t.write(fmt.Sprintf(text, a...))
-}
-
-func wrap(s string, width int) string {
-	var b strings.Builder
-	for len(s) > 0 {
-		rem := width
-		if rem > len(s) {
-			rem = len(s)
-		}
-		if idx := strings.IndexAny(s, "\n\r"); idx != -1 && idx < rem {
-			rem = idx + 1
-		}
-		untilNewline := strings.TrimRight(s[:rem], "\n\r")
-		s = s[rem:]
-		if len(untilNewline) == 0 {
-			continue
-		}
-		b.WriteString(untilNewline)
-		b.WriteString("\n")
-	}
-	return strings.TrimRight(b.String(), "\n\r")
-}
-
-func (t *tui) printfDrawIndentedAndWrappedIfMultiline(format string, a ...interface{}) {
-	whole := fmt.Sprintf(format, a...)
-	width, _ := termbox.Size()
-	if !strings.ContainsAny(whole, "\n\r") && t.x+len(whole) <= width {
-		t.printf(format, a...)
-	} else {
-		t.addIndent(1)
-		t.newline()
-		t.write(wrap(whole, width-INDENT_MULTIPLIER*t.indent))
-		t.addIndent(-1)
-	}
-}
-
-func (t *tui) newline() {
-	t.moveLine(1, 0)
-}
-
-func (t *tui) setIndent(indent int) {
-	t.indent = indent
-	t.moveLine(0, 0)
-}
-
-func (t *tui) addIndent(indent int) {
-	t.indent += indent
-	t.moveLine(0, 0)
-}
-
-var statusFlags struct {
-	Raw bool
-	Job string
-}
-
-var StatusCmd = &cli.Subcommand{
-	Use:   "status",
-	Short: "show job activity or dump as JSON for monitoring",
-	SetupFlags: func(f *pflag.FlagSet) {
-		f.BoolVar(&statusFlags.Raw, "raw", false, "dump raw status description from zrepl daemon")
-		f.StringVar(&statusFlags.Job, "job", "", "only dump specified job")
-	},
-	Run: runStatus,
-}
-
-func runStatus(ctx context.Context, s *cli.Subcommand, args []string) error {
-	httpc, err := controlHttpClient(s.Config().Global.Control.SockPath)
-	if err != nil {
-		return err
-	}
-
-	if statusFlags.Raw {
-		resp, err := httpc.Get("http://unix" + daemon.ControlJobEndpointStatus)
-		if err != nil {
-			return err
-		}
-		defer resp.Body.Close()
-		if resp.StatusCode != http.StatusOK {
-			fmt.Fprintf(os.Stderr, "Received error response:\n")
-			_, err := io.CopyN(os.Stderr, resp.Body, 4096)
-			if err != nil {
-				return err
-			}
-			return errors.Errorf("exit")
-		}
-		if _, err := io.Copy(os.Stdout, resp.Body); err != nil {
-			return err
-		}
-		return nil
-	}
-
-	t := newTui()
-	t.lock.Lock()
-	t.err = errors.New("Got no report yet")
-	t.lock.Unlock()
-	t.jobFilter = statusFlags.Job
-
-	err = termbox.Init()
-	if err != nil {
-		return err
-	}
-	defer termbox.Close()
-
-	update := func() {
-		var m daemon.Status
-
-		err2 := jsonRequestResponse(httpc, daemon.ControlJobEndpointStatus,
-			struct{}{},
-			&m,
-		)
-
-		t.lock.Lock()
-		t.err = err2
-		t.report = m.Jobs
-		t.lock.Unlock()
-		t.draw()
-	}
-	update()
-
-	ticker := time.NewTicker(500 * time.Millisecond)
-	defer ticker.Stop()
-	go func() {
-		for range ticker.C {
-			update()
-		}
-	}()
-
-	termbox.HideCursor()
-	termbox.Clear(termbox.ColorDefault, termbox.ColorDefault)
-
-loop:
-	for {
-		switch ev := termbox.PollEvent(); ev.Type {
-		case termbox.EventKey:
-			switch ev.Key {
-			case termbox.KeyEsc:
-				break loop
-			case termbox.KeyCtrlC:
-				break loop
-			}
-		case termbox.EventResize:
-			t.draw()
-		}
-	}
-
-	return nil
-
-}
-
-func (t *tui) getReplicationProgressHistory(jobName string) *bytesProgressHistory {
-	p, ok := t.replicationProgress[jobName]
-	if !ok {
-		p = &bytesProgressHistory{}
-		t.replicationProgress[jobName] = p
-	}
-	return p
-}
-
-func (t *tui) draw() {
-	t.lock.Lock()
-	defer t.lock.Unlock()
-
-	termbox.Clear(termbox.ColorDefault, termbox.ColorDefault)
-	t.x = 0
-	t.y = 0
-	t.indent = 0
-
-	if t.err != nil {
-		t.write(t.err.Error())
-	} else {
-		//Iterate over map in alphabetical order
-		keys := make([]string, 0, len(t.report))
-		for k := range t.report {
-			if len(k) == 0 || daemon.IsInternalJobName(k) { //Internal job
-				continue
-			}
-			if t.jobFilter != "" && k != t.jobFilter {
-				continue
-			}
-			keys = append(keys, k)
-		}
-		sort.Strings(keys)
-
-		if len(keys) == 0 {
-			t.setIndent(0)
-			t.printf("no jobs to display")
-			t.newline()
-			termbox.Flush()
-			return
-		}
-
-		for _, k := range keys {
-			v := t.report[k]
-
-			t.setIndent(0)
-
-			t.printf("Job: %s", k)
-			t.setIndent(1)
-			t.newline()
-			t.printf("Type: %s", v.Type)
-			t.setIndent(1)
-			t.newline()
-
-			if v.Type == job.TypePush || v.Type == job.TypePull {
-				activeStatus, ok := v.JobSpecific.(*job.ActiveSideStatus)
-				if !ok || activeStatus == nil {
-					t.printf("ActiveSideStatus is null")
-					t.newline()
-					continue
-				}
-
-				t.printf("Replication:")
-				t.newline()
-				t.addIndent(1)
-				t.renderReplicationReport(activeStatus.Replication, t.getReplicationProgressHistory(k))
-				t.addIndent(-1)
-
-				t.printf("Pruning Sender:")
-				t.newline()
-				t.addIndent(1)
-				t.renderPrunerReport(activeStatus.PruningSender)
-				t.addIndent(-1)
-
-				t.printf("Pruning Receiver:")
-				t.newline()
-				t.addIndent(1)
-				t.renderPrunerReport(activeStatus.PruningReceiver)
-				t.addIndent(-1)
-
-				if v.Type == job.TypePush {
-					t.printf("Snapshotting:")
-					t.newline()
-					t.addIndent(1)
-					t.renderSnapperReport(activeStatus.Snapshotting)
-					t.addIndent(-1)
-				}
-
-			} else if v.Type == job.TypeSnap {
-				snapStatus, ok := v.JobSpecific.(*job.SnapJobStatus)
-				if !ok || snapStatus == nil {
-					t.printf("SnapJobStatus is null")
-					t.newline()
-					continue
-				}
-				t.printf("Pruning snapshots:")
-				t.newline()
-				t.addIndent(1)
-				t.renderPrunerReport(snapStatus.Pruning)
-				t.addIndent(-1)
-				t.printf("Snapshotting:")
-				t.newline()
-				t.addIndent(1)
-				t.renderSnapperReport(snapStatus.Snapshotting)
-				t.addIndent(-1)
-			} else if v.Type == job.TypeSource {
-
-				st := v.JobSpecific.(*job.PassiveStatus)
-				t.printf("Snapshotting:\n")
-				t.addIndent(1)
-				t.renderSnapperReport(st.Snapper)
-				t.addIndent(-1)
-
-			} else {
-				t.printf("No status representation for job type '%s', dumping as YAML", v.Type)
-				t.newline()
-				asYaml, err := yaml.Marshal(v.JobSpecific)
-				if err != nil {
-					t.printf("Error marshaling status to YAML: %s", err)
-					t.newline()
-					continue
-				}
-				t.write(string(asYaml))
-				t.newline()
-				continue
-			}
-		}
-	}
-	termbox.Flush()
-}
-
-func (t *tui) renderReplicationReport(rep *report.Report, history *bytesProgressHistory) {
-	if rep == nil {
-		t.printf("...\n")
-		return
-	}
-
-	if rep.WaitReconnectError != nil {
-		t.printfDrawIndentedAndWrappedIfMultiline("Connectivity: %s", rep.WaitReconnectError)
-		t.newline()
-	}
-	if !rep.WaitReconnectSince.IsZero() {
-		delta := time.Until(rep.WaitReconnectUntil).Round(time.Second)
-		if rep.WaitReconnectUntil.IsZero() || delta > 0 {
-			var until string
-			if rep.WaitReconnectUntil.IsZero() {
-				until = "waiting indefinitely"
-			} else {
-				until = fmt.Sprintf("hard fail in %s @ %s", delta, rep.WaitReconnectUntil)
-			}
-			t.printfDrawIndentedAndWrappedIfMultiline("Connectivity: reconnecting with exponential backoff (since %s) (%s)",
-				rep.WaitReconnectSince, until)
-		} else {
-			t.printfDrawIndentedAndWrappedIfMultiline("Connectivity: reconnects reached hard-fail timeout @ %s", rep.WaitReconnectUntil)
-		}
-		t.newline()
-	}
-
-	// TODO visualize more than the latest attempt by folding all attempts into one
-	if len(rep.Attempts) == 0 {
-		t.printf("no attempts made yet")
-		return
-	} else {
-		t.printf("Attempt #%d", len(rep.Attempts))
-		if len(rep.Attempts) > 1 {
-			t.printf(". Previous attempts failed with the following statuses:")
-			t.newline()
-			t.addIndent(1)
-			for i, a := range rep.Attempts[:len(rep.Attempts)-1] {
-				t.printfDrawIndentedAndWrappedIfMultiline("#%d: %s (failed at %s) (ran %s)", i+1, a.State, a.FinishAt, a.FinishAt.Sub(a.StartAt))
-				t.newline()
-			}
-			t.addIndent(-1)
-		} else {
-			t.newline()
-		}
-	}
-
-	latest := rep.Attempts[len(rep.Attempts)-1]
-	sort.Slice(latest.Filesystems, func(i, j int) bool {
-		return latest.Filesystems[i].Info.Name < latest.Filesystems[j].Info.Name
-	})
-
-	t.printf("Status: %s", latest.State)
-	t.newline()
-	if latest.State == report.AttemptPlanningError {
-		t.printf("Problem: ")
-		t.printfDrawIndentedAndWrappedIfMultiline("%s", latest.PlanError)
-		t.newline()
-	} else if latest.State == report.AttemptFanOutError {
-		t.printf("Problem: one or more of the filesystems encountered errors")
-		t.newline()
-	}
-
-	if latest.State != report.AttemptPlanning && latest.State != report.AttemptPlanningError {
-		// Draw global progress bar
-		// Progress: [---------------]
-		expected, replicated, containsInvalidSizeEstimates := latest.BytesSum()
-		rate, changeCount := history.Update(replicated)
-		eta := time.Duration(0)
-		if rate > 0 {
-			eta = time.Duration((expected-replicated)/rate) * time.Second
-		}
-		t.write("Progress: ")
-		t.drawBar(50, replicated, expected, changeCount)
-		t.write(fmt.Sprintf(" %s / %s @ %s/s", ByteCountBinary(replicated), ByteCountBinary(expected), ByteCountBinary(rate)))
-		if eta != 0 {
-			t.write(fmt.Sprintf(" (%s remaining)", humanizeDuration(eta)))
-		}
-		t.newline()
-		if containsInvalidSizeEstimates {
-			t.write("NOTE: not all steps could be size-estimated, total estimate is likely imprecise!")
-			t.newline()
-		}
-
-		if len(latest.Filesystems) == 0 {
-			t.write("NOTE: no filesystems were considered for replication!")
-			t.newline()
-		}
-
-		var maxFSLen int
-		for _, fs := range latest.Filesystems {
-			if len(fs.Info.Name) > maxFSLen {
-				maxFSLen = len(fs.Info.Name)
-			}
-		}
-		for _, fs := range latest.Filesystems {
-			t.printFilesystemStatus(fs, false, maxFSLen) // FIXME bring 'active' flag back
-		}
-
-	}
-
-}
-
-func (t *tui) renderPrunerReport(r *pruner.Report) {
-	if r == nil {
-		t.printf("...\n")
-		return
-	}
-
-	state, err := pruner.StateString(r.State)
-	if err != nil {
-		t.printf("Status: %q (parse error: %q)\n", r.State, err)
-		return
-	}
-
-	t.printf("Status: %s", state)
-	t.newline()
-
-	if r.Error != "" {
-		t.printf("Error: %s\n", r.Error)
-	}
-
-	type commonFS struct {
-		*pruner.FSReport
-		completed bool
-	}
-	all := make([]commonFS, 0, len(r.Pending)+len(r.Completed))
-	for i := range r.Pending {
-		all = append(all, commonFS{&r.Pending[i], false})
-	}
-	for i := range r.Completed {
-		all = append(all, commonFS{&r.Completed[i], true})
-	}
-
-	switch state {
-	case pruner.Plan:
-		fallthrough
-	case pruner.PlanErr:
-		return
-	}
-
-	if len(all) == 0 {
-		t.printf("nothing to do\n")
-		return
-	}
-
-	var totalDestroyCount, completedDestroyCount int
-	var maxFSname int
-	for _, fs := range all {
-		totalDestroyCount += len(fs.DestroyList)
-		if fs.completed {
-			completedDestroyCount += len(fs.DestroyList)
-		}
-		if maxFSname < len(fs.Filesystem) {
-			maxFSname = len(fs.Filesystem)
-		}
-	}
-
-	// global progress bar
-	progress := int(math.Round(80 * float64(completedDestroyCount) / float64(totalDestroyCount)))
-	t.write("Progress: ")
-	t.write("[")
-	t.write(times("=", progress))
-	t.write(">")
-	t.write(times("-", 80-progress))
-	t.write("]")
-	t.printf(" %d/%d snapshots", completedDestroyCount, totalDestroyCount)
-	t.newline()
-
-	sort.SliceStable(all, func(i, j int) bool {
-		return strings.Compare(all[i].Filesystem, all[j].Filesystem) == -1
-	})
-
-	// Draw a table-like representation of 'all'
-	for _, fs := range all {
-		t.write(rightPad(fs.Filesystem, maxFSname, " "))
-		t.write(" ")
-		if !fs.SkipReason.NotSkipped() {
-			t.printf("skipped: %s\n", fs.SkipReason)
-			continue
-		}
-		if fs.LastError != "" {
-			if strings.ContainsAny(fs.LastError, "\r\n") {
-				t.printf("ERROR:")
-				t.printfDrawIndentedAndWrappedIfMultiline("%s\n", fs.LastError)
-			} else {
-				t.printfDrawIndentedAndWrappedIfMultiline("ERROR: %s\n", fs.LastError)
-			}
-			t.newline()
-			continue
-		}
-
-		pruneRuleActionStr := fmt.Sprintf("(destroy %d of %d snapshots)",
-			len(fs.DestroyList), len(fs.SnapshotList))
-
-		if fs.completed {
-			t.printf("Completed  %s\n", pruneRuleActionStr)
-			continue
-		}
-
-		t.write("Pending    ") // whitespace is padding 10
-		if len(fs.DestroyList) == 1 {
-			t.write(fs.DestroyList[0].Name)
-		} else {
-			t.write(pruneRuleActionStr)
-		}
-		t.newline()
-	}
-
-}
-
-func (t *tui) renderSnapperReport(r *snapper.Report) {
-	if r == nil {
-		t.printf("<snapshot type does not have a report>\n")
-		return
-	}
-
-	t.printf("Status: %s", r.State)
-	t.newline()
-
-	if r.Error != "" {
-		t.printf("Error: %s\n", r.Error)
-	}
-	if !r.SleepUntil.IsZero() {
-		t.printf("Sleep until: %s\n", r.SleepUntil)
-	}
-
-	sort.Slice(r.Progress, func(i, j int) bool {
-		return strings.Compare(r.Progress[i].Path, r.Progress[j].Path) == -1
-	})
-
-	t.addIndent(1)
-	defer t.addIndent(-1)
-	dur := func(d time.Duration) string {
-		return d.Round(100 * time.Millisecond).String()
-	}
-
-	type row struct {
-		path, state, duration, remainder, hookReport string
-	}
-	var widths struct {
-		path, state, duration int
-	}
-	rows := make([]*row, len(r.Progress))
-	for i, fs := range r.Progress {
-		r := &row{
-			path:  fs.Path,
-			state: fs.State.String(),
-		}
-		if fs.HooksHadError {
-			r.hookReport = fs.Hooks // FIXME render here, not in daemon
-		}
-		switch fs.State {
-		case snapper.SnapPending:
-			r.duration = "..."
-			r.remainder = ""
-		case snapper.SnapStarted:
-			r.duration = dur(time.Since(fs.StartAt))
-			r.remainder = fmt.Sprintf("snap name: %q", fs.SnapName)
-		case snapper.SnapDone:
-			fallthrough
-		case snapper.SnapError:
-			r.duration = dur(fs.DoneAt.Sub(fs.StartAt))
-			r.remainder = fmt.Sprintf("snap name: %q", fs.SnapName)
-		}
-		rows[i] = r
-		if len(r.path) > widths.path {
-			widths.path = len(r.path)
-		}
-		if len(r.state) > widths.state {
-			widths.state = len(r.state)
-		}
-		if len(r.duration) > widths.duration {
-			widths.duration = len(r.duration)
-		}
-	}
-
-	for _, r := range rows {
-		path := rightPad(r.path, widths.path, " ")
-		state := rightPad(r.state, widths.state, " ")
-		duration := rightPad(r.duration, widths.duration, " ")
-		t.printf("%s %s %s", path, state, duration)
-		t.printfDrawIndentedAndWrappedIfMultiline(" %s", r.remainder)
-		if r.hookReport != "" {
-			t.printfDrawIndentedAndWrappedIfMultiline("%s", r.hookReport)
-		}
-		t.newline()
-	}
-
-}
-
-func times(str string, n int) (out string) {
-	for i := 0; i < n; i++ {
-		out += str
-	}
-	return
-}
-
-func rightPad(str string, length int, pad string) string {
-	if len(str) > length {
-		return str[:length]
-	}
-	return str + strings.Repeat(pad, length-len(str))
-}
-
-var arrowPositions = `>\|/`
-
-// changeCount = 0 indicates stall / no progress
-func (t *tui) drawBar(length int, bytes, totalBytes int64, changeCount int) {
-	var completedLength int
-	if totalBytes > 0 {
-		completedLength = int(int64(length) * bytes / totalBytes)
-		if completedLength > length {
-			completedLength = length
-		}
-	} else if totalBytes == bytes {
-		completedLength = length
-	}
-
-	t.write("[")
-	t.write(times("=", completedLength))
-	t.write(string(arrowPositions[changeCount%len(arrowPositions)]))
-	t.write(times("-", length-completedLength))
-	t.write("]")
-}
-
-func (t *tui) printFilesystemStatus(rep *report.FilesystemReport, active bool, maxFS int) {
-
-	expected, replicated, containsInvalidSizeEstimates := rep.BytesSum()
-	sizeEstimationImpreciseNotice := ""
-	if containsInvalidSizeEstimates {
-		sizeEstimationImpreciseNotice = " (some steps lack size estimation)"
-	}
-	if rep.CurrentStep < len(rep.Steps) && rep.Steps[rep.CurrentStep].Info.BytesExpected == 0 {
-		sizeEstimationImpreciseNotice = " (step lacks size estimation)"
-	}
-
-	status := fmt.Sprintf("%s (step %d/%d, %s/%s)%s",
-		strings.ToUpper(string(rep.State)),
-		rep.CurrentStep, len(rep.Steps),
-		ByteCountBinary(replicated), ByteCountBinary(expected),
-		sizeEstimationImpreciseNotice,
-	)
-
-	activeIndicator := " "
-	if active {
-		activeIndicator = "*"
-	}
-	t.printf("%s %s %s ",
-		activeIndicator,
-		rightPad(rep.Info.Name, maxFS, " "),
-		status)
-
-	next := ""
-	if err := rep.Error(); err != nil {
-		next = err.Err
-	} else if rep.State != report.FilesystemDone {
-		if nextStep := rep.NextStep(); nextStep != nil {
-			if nextStep.IsIncremental() {
-				next = fmt.Sprintf("next: %s => %s", nextStep.Info.From, nextStep.Info.To)
-			} else {
-				next = fmt.Sprintf("next: full send %s", nextStep.Info.To)
-			}
-			attribs := []string{}
-
-			if nextStep.Info.Resumed {
-				attribs = append(attribs, "resumed")
-			}
-
-			attribs = append(attribs, fmt.Sprintf("encrypted=%s", nextStep.Info.Encrypted))
-
-			next += fmt.Sprintf(" (%s)", strings.Join(attribs, ", "))
-		} else {
-			next = "" // individual FSes may still be in planning state
-		}
-
-	}
-	t.printfDrawIndentedAndWrappedIfMultiline("%s", next)
-
-	t.newline()
-}
-
-func ByteCountBinary(b int64) string {
-	const unit = 1024
-	if b < unit {
-		return fmt.Sprintf("%d B", b)
-	}
-	div, exp := int64(unit), 0
-	for n := b / unit; n >= unit; n /= unit {
-		div *= unit
-		exp++
-	}
-	return fmt.Sprintf("%.1f %ciB", float64(b)/float64(div), "KMGTPE"[exp])
-}
-
-func humanizeDuration(duration time.Duration) string {
-	days := int64(duration.Hours() / 24)
-	hours := int64(math.Mod(duration.Hours(), 24))
-	minutes := int64(math.Mod(duration.Minutes(), 60))
-	seconds := int64(math.Mod(duration.Seconds(), 60))
-
-	var parts []string
-
-	force := false
-	chunks := []int64{days, hours, minutes, seconds}
-	for i, chunk := range chunks {
-		if force || chunk > 0 {
-			padding := 0
-			if force {
-				padding = 2
-			}
-			parts = append(parts, fmt.Sprintf("%*d%c", padding, chunk, "dhms"[i]))
-			force = true
-		}
-	}
-
-	return strings.Join(parts, " ")
-}

client/status/client/client.go

@@ -0,0 +1,101 @@
+package client
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"io"
+	"net"
+	"net/http"
+
+	"github.com/pkg/errors"
+
+	"github.com/zrepl/zrepl/daemon"
+)
+
+type Client struct {
+	h http.Client
+}
+
+func New(network, addr string) (*Client, error) {
+	httpc, err := controlHttpClient(func(_ context.Context) (net.Conn, error) { return net.Dial(network, addr) })
+	if err != nil {
+		return nil, err
+	}
+	return &Client{httpc}, nil
+}
+
+func (c *Client) Status() (s daemon.Status, _ error) {
+	err := jsonRequestResponse(c.h, daemon.ControlJobEndpointStatus,
+		struct{}{},
+		&s,
+	)
+	return s, err
+}
+
+func (c *Client) StatusRaw() ([]byte, error) {
+	var r json.RawMessage
+	err := jsonRequestResponse(c.h, daemon.ControlJobEndpointStatus, struct{}{}, &r)
+	if err != nil {
+		return nil, err
+	}
+	return r, nil
+}
+
+func (c *Client) signal(job, sig string) error {
+	return jsonRequestResponse(c.h, daemon.ControlJobEndpointSignal,
+		struct {
+			Name string
+			Op   string
+		}{
+			Name: job,
+			Op:   sig,
+		},
+		struct{}{},
+	)
+}
+
+func (c *Client) SignalWakeup(job string) error {
+	return c.signal(job, "wakeup")
+}
+
+func (c *Client) SignalReset(job string) error {
+	return c.signal(job, "reset")
+}
+
+func controlHttpClient(dialfunc func(context.Context) (net.Conn, error)) (client http.Client, err error) {
+	return http.Client{
+		Transport: &http.Transport{
+			DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+				return dialfunc(ctx)
+			},
+		},
+	}, nil
+}
+
+func jsonRequestResponse(c http.Client, endpoint string, req interface{}, res interface{}) error {
+	var buf bytes.Buffer
+	encodeErr := json.NewEncoder(&buf).Encode(req)
+	if encodeErr != nil {
+		return encodeErr
+	}
+
+	resp, err := c.Post("http://unix"+endpoint, "application/json", &buf)
+	if err != nil {
+		return err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		var msg bytes.Buffer
+		_, _ = io.CopyN(&msg, resp.Body, 4096) // ignore error, just display what we got
+		return errors.Errorf("%s", msg.String())
+	}
+
+	decodeError := json.NewDecoder(resp.Body).Decode(&res)
+	if decodeError != nil {
+		return decodeError
+	}
+
+	return nil
+}

client/status/status.go

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

client/status/status_dump.go

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

client/status/status_interactive.go

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

client/status/status_legacy.go

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

client/status/status_raw.go

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

client/status/viewmodel/bytecountbinary.go

@@ -0,0 +1,26 @@
+package viewmodel
+
+import (
+	"fmt"
+	"math"
+)
+
+func ByteCountBinaryUint(b uint64) string {
+	if b > math.MaxInt64 {
+		panic(b)
+	}
+	return ByteCountBinary(int64(b))
+}
+
+func ByteCountBinary(b int64) string {
+	const unit = 1024
+	if b < unit {
+		return fmt.Sprintf("%d B", b)
+	}
+	div, exp := unit, 0
+	for n := b / unit; n >= unit; n /= unit {
+		div *= unit
+		exp++
+	}
+	return fmt.Sprintf("%.1f %ciB", float64(b)/float64(div), "KMGTPE"[exp])
+}

client/status/viewmodel/bytesprogresshistory.go

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

client/status/viewmodel/render.go

@@ -0,0 +1,619 @@
+package viewmodel
+
+import (
+	"fmt"
+	"math"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/go-playground/validator/v10"
+	yaml "github.com/zrepl/yaml-config"
+
+	"github.com/zrepl/zrepl/client/status/viewmodel/stringbuilder"
+	"github.com/zrepl/zrepl/daemon"
+	"github.com/zrepl/zrepl/daemon/job"
+	"github.com/zrepl/zrepl/daemon/pruner"
+	"github.com/zrepl/zrepl/daemon/snapper"
+	"github.com/zrepl/zrepl/replication/report"
+)
+
+type M struct {
+	jobs            map[string]*Job
+	jobsList        []*Job
+	selectedJob     *Job
+	dateString      string
+	bottomBarStatus string
+}
+
+type Job struct {
+	// long-lived
+	name         string
+	byteProgress *bytesProgressHistory
+
+	lastStatus      *job.Status
+	fulldescription string
+}
+
+func New() *M {
+	return &M{
+		jobs:        make(map[string]*Job),
+		jobsList:    make([]*Job, 0),
+		selectedJob: nil,
+	}
+}
+
+type FilterFunc func(string) bool
+
+type Params struct {
+	Report                  map[string]*job.Status
+	ReportFetchError        error
+	SelectedJob             *Job
+	FSFilter                FilterFunc `validate:"required"`
+	DetailViewWidth         int        `validate:"gte=1"`
+	DetailViewWrap          bool
+	ShortKeybindingOverview string
+}
+
+var validate = validator.New()
+
+func (m *M) Update(p Params) {
+
+	if err := validate.Struct(p); err != nil {
+		panic(err)
+	}
+
+	if p.ReportFetchError != nil {
+		m.bottomBarStatus = fmt.Sprintf("[red::]status fetch: %s", p.ReportFetchError)
+	} else {
+		m.bottomBarStatus = p.ShortKeybindingOverview
+		for jobname, st := range p.Report {
+			// TODO handle job renames & deletions
+			j, ok := m.jobs[jobname]
+			if !ok {
+				j = &Job{
+					name:         jobname,
+					byteProgress: &bytesProgressHistory{},
+				}
+				m.jobs[jobname] = j
+				m.jobsList = append(m.jobsList, j)
+			}
+			j.lastStatus = st
+		}
+	}
+
+	// filter out internal jobs
+	var jobsList []*Job
+	for _, j := range m.jobsList {
+		if daemon.IsInternalJobName(j.name) {
+			continue
+		}
+		jobsList = append(jobsList, j)
+	}
+	m.jobsList = jobsList
+
+	// determinism!
+	sort.Slice(m.jobsList, func(i, j int) bool {
+		return strings.Compare(m.jobsList[i].name, m.jobsList[j].name) < 0
+	})
+
+	// try to not lose the selected job
+	m.selectedJob = nil
+	for _, j := range m.jobsList {
+		j.updateFullDescription(p)
+		if j == p.SelectedJob {
+			m.selectedJob = j
+		}
+	}
+
+	m.dateString = time.Now().Format(time.RFC3339)
+
+}
+
+func (m *M) BottomBarStatus() string { return m.bottomBarStatus }
+
+func (m *M) Jobs() []*Job { return m.jobsList }
+
+// may be nil
+func (m *M) SelectedJob() *Job { return m.selectedJob }
+
+func (m *M) DateString() string { return m.dateString }
+
+func (j *Job) updateFullDescription(p Params) {
+	width := p.DetailViewWidth
+	if !p.DetailViewWrap {
+		width = 10000000 // FIXME
+	}
+	b := stringbuilder.New(stringbuilder.Config{
+		IndentMultiplier: 3,
+		Width:            width,
+	})
+	drawJob(b, j.name, j.lastStatus, j.byteProgress, p.FSFilter)
+	j.fulldescription = b.String()
+}
+
+func (j *Job) JobTreeTitle() string {
+	return j.name
+}
+
+func (j *Job) FullDescription() string {
+	return j.fulldescription
+}
+
+func (j *Job) Name() string {
+	return j.name
+}
+
+func drawJob(t *stringbuilder.B, name string, v *job.Status, history *bytesProgressHistory, fsfilter FilterFunc) {
+
+	t.Printf("Job: %s\n", name)
+	t.Printf("Type: %s\n\n", v.Type)
+
+	if v.Type == job.TypePush || v.Type == job.TypePull {
+		activeStatus, ok := v.JobSpecific.(*job.ActiveSideStatus)
+		if !ok || activeStatus == nil {
+			t.Printf("ActiveSideStatus is null")
+			t.Newline()
+			return
+		}
+
+		t.Printf("Replication:")
+		t.AddIndentAndNewline(1)
+		renderReplicationReport(t, activeStatus.Replication, history, fsfilter)
+		t.AddIndentAndNewline(-1)
+
+		t.Printf("Pruning Sender:")
+		t.AddIndentAndNewline(1)
+		renderPrunerReport(t, activeStatus.PruningSender, fsfilter)
+		t.AddIndentAndNewline(-1)
+
+		t.Printf("Pruning Receiver:")
+		t.AddIndentAndNewline(1)
+		renderPrunerReport(t, activeStatus.PruningReceiver, fsfilter)
+		t.AddIndentAndNewline(-1)
+
+		if v.Type == job.TypePush {
+			t.Printf("Snapshotting:")
+			t.AddIndentAndNewline(1)
+			renderSnapperReport(t, activeStatus.Snapshotting, fsfilter)
+			t.AddIndentAndNewline(-1)
+		}
+
+	} else if v.Type == job.TypeSnap {
+		snapStatus, ok := v.JobSpecific.(*job.SnapJobStatus)
+		if !ok || snapStatus == nil {
+			t.Printf("SnapJobStatus is null")
+			t.Newline()
+			return
+		}
+		t.Printf("Pruning snapshots:")
+		t.AddIndentAndNewline(1)
+		renderPrunerReport(t, snapStatus.Pruning, fsfilter)
+		t.AddIndentAndNewline(-1)
+		t.Printf("Snapshotting:")
+		t.AddIndentAndNewline(1)
+		renderSnapperReport(t, snapStatus.Snapshotting, fsfilter)
+		t.AddIndentAndNewline(-1)
+	} else if v.Type == job.TypeSource {
+
+		st := v.JobSpecific.(*job.PassiveStatus)
+		t.Printf("Snapshotting:\n")
+		t.AddIndent(1)
+		renderSnapperReport(t, st.Snapper, fsfilter)
+		t.AddIndentAndNewline(-1)
+
+	} else {
+		t.Printf("No status representation for job type '%s', dumping as YAML", v.Type)
+		t.Newline()
+		asYaml, err := yaml.Marshal(v.JobSpecific)
+		if err != nil {
+			t.Printf("Error marshaling status to YAML: %s", err)
+			t.Newline()
+			return
+		}
+		t.Write(string(asYaml))
+		t.Newline()
+	}
+}
+
+func printFilesystemStatus(t *stringbuilder.B, rep *report.FilesystemReport, maxFS int) {
+
+	expected, replicated, containsInvalidSizeEstimates := rep.BytesSum()
+	sizeEstimationImpreciseNotice := ""
+	if containsInvalidSizeEstimates {
+		sizeEstimationImpreciseNotice = " (some steps lack size estimation)"
+	}
+	if rep.CurrentStep < len(rep.Steps) && rep.Steps[rep.CurrentStep].Info.BytesExpected == 0 {
+		sizeEstimationImpreciseNotice = " (step lacks size estimation)"
+	}
+
+	userVisisbleCurrentStep, userVisibleTotalSteps := rep.CurrentStep, len(rep.Steps)
+	if len(rep.Steps) > 0 {
+		userVisisbleCurrentStep = rep.CurrentStep + 1 // CurrentStep is an index that starts at 0
+	}
+	status := fmt.Sprintf("%s (step %d/%d, %s/%s)%s",
+		strings.ToUpper(string(rep.State)),
+		userVisisbleCurrentStep, userVisibleTotalSteps,
+		ByteCountBinaryUint(replicated), ByteCountBinaryUint(expected),
+		sizeEstimationImpreciseNotice,
+	)
+
+	activeIndicator := " "
+	if rep.BlockedOn == report.FsBlockedOnNothing &&
+		(rep.State == report.FilesystemPlanning || rep.State == report.FilesystemStepping) {
+		activeIndicator = "*"
+	}
+	t.AddIndent(1)
+	t.Printf("%s %s %s ",
+		activeIndicator,
+		stringbuilder.RightPad(rep.Info.Name, maxFS, " "),
+		status)
+
+	next := ""
+	if err := rep.Error(); err != nil {
+		next = err.Err
+	} else if rep.State != report.FilesystemDone {
+		if nextStep := rep.NextStep(); nextStep != nil {
+			if nextStep.IsIncremental() {
+				next = fmt.Sprintf("next: %s => %s", nextStep.Info.From, nextStep.Info.To)
+			} else {
+				next = fmt.Sprintf("next: full send %s", nextStep.Info.To)
+			}
+			attribs := []string{}
+
+			if nextStep.Info.Resumed {
+				attribs = append(attribs, "resumed")
+			}
+
+			attribs = append(attribs, fmt.Sprintf("encrypted=%s", nextStep.Info.Encrypted))
+
+			next += fmt.Sprintf(" (%s)", strings.Join(attribs, ", "))
+		} else {
+			next = "" // individual FSes may still be in planning state
+		}
+
+	}
+	t.Printf("%s", next)
+
+	t.AddIndent(-1)
+	t.Newline()
+}
+
+func renderReplicationReport(t *stringbuilder.B, rep *report.Report, history *bytesProgressHistory, fsfilter FilterFunc) {
+	if rep == nil {
+		t.Printf("...\n")
+		return
+	}
+
+	if rep.WaitReconnectError != nil {
+		t.PrintfDrawIndentedAndWrappedIfMultiline("Connectivity: %s", rep.WaitReconnectError)
+		t.Newline()
+	}
+	if !rep.WaitReconnectSince.IsZero() {
+		delta := time.Until(rep.WaitReconnectUntil).Round(time.Second)
+		if rep.WaitReconnectUntil.IsZero() || delta > 0 {
+			var until string
+			if rep.WaitReconnectUntil.IsZero() {
+				until = "waiting indefinitely"
+			} else {
+				until = fmt.Sprintf("hard fail in %s @ %s", delta, rep.WaitReconnectUntil)
+			}
+			t.PrintfDrawIndentedAndWrappedIfMultiline("Connectivity: reconnecting with exponential backoff (since %s) (%s)",
+				rep.WaitReconnectSince, until)
+		} else {
+			t.PrintfDrawIndentedAndWrappedIfMultiline("Connectivity: reconnects reached hard-fail timeout @ %s", rep.WaitReconnectUntil)
+		}
+		t.Newline()
+	}
+
+	// TODO visualize more than the latest attempt by folding all attempts into one
+	if len(rep.Attempts) == 0 {
+		t.Printf("no attempts made yet")
+		return
+	} else {
+		t.Printf("Attempt #%d", len(rep.Attempts))
+		if len(rep.Attempts) > 1 {
+			t.Printf(". Previous attempts failed with the following statuses:")
+			t.AddIndentAndNewline(1)
+			for i, a := range rep.Attempts[:len(rep.Attempts)-1] {
+				t.PrintfDrawIndentedAndWrappedIfMultiline("#%d: %s (failed at %s) (ran %s)\n", i+1, a.State, a.FinishAt, a.FinishAt.Sub(a.StartAt))
+			}
+			t.AddIndentAndNewline(-1)
+		} else {
+			t.Newline()
+		}
+	}
+
+	latest := rep.Attempts[len(rep.Attempts)-1]
+	sort.Slice(latest.Filesystems, func(i, j int) bool {
+		return latest.Filesystems[i].Info.Name < latest.Filesystems[j].Info.Name
+	})
+
+	// apply filter
+	filtered := make([]*report.FilesystemReport, 0, len(latest.Filesystems))
+	for _, fs := range latest.Filesystems {
+		if !fsfilter(fs.Info.Name) {
+			continue
+		}
+		filtered = append(filtered, fs)
+	}
+	latest.Filesystems = filtered
+
+	t.Printf("Status: %s", latest.State)
+	t.Newline()
+	if !latest.FinishAt.IsZero() {
+		t.Printf("Last Run: %s (lasted %s)\n", latest.FinishAt.Round(time.Second), latest.FinishAt.Sub(latest.StartAt).Round(time.Second))
+	} else {
+		t.Printf("Started: %s (lasting %s)\n", latest.StartAt.Round(time.Second), time.Since(latest.StartAt).Round(time.Second))
+	}
+
+	if latest.State == report.AttemptPlanningError {
+		t.Printf("Problem: ")
+		t.PrintfDrawIndentedAndWrappedIfMultiline("%s", latest.PlanError)
+		t.Newline()
+	} else if latest.State == report.AttemptFanOutError {
+		t.Printf("Problem: one or more of the filesystems encountered errors")
+		t.Newline()
+	}
+
+	if latest.State != report.AttemptPlanning && latest.State != report.AttemptPlanningError {
+		// Draw global progress bar
+		// Progress: [---------------]
+		expected, replicated, containsInvalidSizeEstimates := latest.BytesSum()
+		rate, changeCount := history.Update(replicated)
+		eta := time.Duration(0)
+		if rate > 0 {
+			eta = time.Duration((float64(expected)-float64(replicated))/float64(rate)) * time.Second
+		}
+
+		t.Write("Progress: ")
+		t.DrawBar(50, replicated, expected, changeCount)
+		t.Write(fmt.Sprintf(" %s / %s @ %s/s", ByteCountBinaryUint(replicated), ByteCountBinaryUint(expected), ByteCountBinary(rate)))
+		if eta != 0 {
+			t.Write(fmt.Sprintf(" (%s remaining)", humanizeDuration(eta)))
+		}
+		t.Newline()
+		if containsInvalidSizeEstimates {
+			t.Write("NOTE: not all steps could be size-estimated, total estimate is likely imprecise!")
+			t.Newline()
+		}
+
+		if len(latest.Filesystems) == 0 {
+			t.Write("NOTE: no filesystems were considered for replication!")
+			t.Newline()
+		}
+
+		var maxFSLen int
+		for _, fs := range latest.Filesystems {
+			if len(fs.Info.Name) > maxFSLen {
+				maxFSLen = len(fs.Info.Name)
+			}
+		}
+		for _, fs := range latest.Filesystems {
+			printFilesystemStatus(t, fs, maxFSLen)
+		}
+
+	}
+}
+
+func humanizeDuration(duration time.Duration) string {
+	days := int64(duration.Hours() / 24)
+	hours := int64(math.Mod(duration.Hours(), 24))
+	minutes := int64(math.Mod(duration.Minutes(), 60))
+	seconds := int64(math.Mod(duration.Seconds(), 60))
+
+	var parts []string
+
+	force := false
+	chunks := []int64{days, hours, minutes, seconds}
+	for i, chunk := range chunks {
+		if force || chunk > 0 {
+			padding := 0
+			if force {
+				padding = 2
+			}
+			parts = append(parts, fmt.Sprintf("%*d%c", padding, chunk, "dhms"[i]))
+			force = true
+		}
+	}
+
+	return strings.Join(parts, " ")
+}
+
+func renderPrunerReport(t *stringbuilder.B, r *pruner.Report, fsfilter FilterFunc) {
+	if r == nil {
+		t.Printf("...\n")
+		return
+	}
+
+	state, err := pruner.StateString(r.State)
+	if err != nil {
+		t.Printf("Status: %q (parse error: %q)\n", r.State, err)
+		return
+	}
+
+	t.Printf("Status: %s", state)
+	t.Newline()
+
+	if r.Error != "" {
+		t.Printf("Error: %s\n", r.Error)
+	}
+
+	type commonFS struct {
+		*pruner.FSReport
+		completed bool
+	}
+	all := make([]commonFS, 0, len(r.Pending)+len(r.Completed))
+	for i := range r.Pending {
+		all = append(all, commonFS{&r.Pending[i], false})
+	}
+	for i := range r.Completed {
+		all = append(all, commonFS{&r.Completed[i], true})
+	}
+
+	// filter all
+	filtered := make([]commonFS, 0, len(all))
+	for _, fs := range all {
+		if fsfilter(fs.FSReport.Filesystem) {
+			filtered = append(filtered, fs)
+		}
+	}
+	all = filtered
+
+	switch state {
+	case pruner.Plan:
+		fallthrough
+	case pruner.PlanErr:
+		return
+	}
+
+	if len(all) == 0 {
+		t.Printf("nothing to do\n")
+		return
+	}
+
+	var totalDestroyCount, completedDestroyCount int
+	var maxFSname int
+	for _, fs := range all {
+		totalDestroyCount += len(fs.DestroyList)
+		if fs.completed {
+			completedDestroyCount += len(fs.DestroyList)
+		}
+		if maxFSname < len(fs.Filesystem) {
+			maxFSname = len(fs.Filesystem)
+		}
+	}
+
+	// global progress bar
+	progress := int(math.Round(80 * float64(completedDestroyCount) / float64(totalDestroyCount)))
+	t.Write("Progress: ")
+	t.Write("[")
+	t.Write(stringbuilder.Times("=", progress))
+	t.Write(">")
+	t.Write(stringbuilder.Times("-", 80-progress))
+	t.Write("]")
+	t.Printf(" %d/%d snapshots", completedDestroyCount, totalDestroyCount)
+	t.Newline()
+
+	sort.SliceStable(all, func(i, j int) bool {
+		return strings.Compare(all[i].Filesystem, all[j].Filesystem) == -1
+	})
+
+	// Draw a table-like representation of 'all'
+	for _, fs := range all {
+		t.Write(stringbuilder.RightPad(fs.Filesystem, maxFSname, " "))
+		t.Write(" ")
+		if !fs.SkipReason.NotSkipped() {
+			t.Printf("skipped: %s\n", fs.SkipReason)
+			continue
+		}
+		if fs.LastError != "" {
+			if strings.ContainsAny(fs.LastError, "\r\n") {
+				t.Printf("ERROR:")
+				t.PrintfDrawIndentedAndWrappedIfMultiline("%s\n", fs.LastError)
+			} else {
+				t.PrintfDrawIndentedAndWrappedIfMultiline("ERROR: %s\n", fs.LastError)
+			}
+			t.Newline()
+			continue
+		}
+
+		pruneRuleActionStr := fmt.Sprintf("(destroy %d of %d snapshots)",
+			len(fs.DestroyList), len(fs.SnapshotList))
+
+		if fs.completed {
+			t.Printf("Completed  %s\n", pruneRuleActionStr)
+			continue
+		}
+
+		t.Write("Pending    ") // whitespace is padding 10
+		if len(fs.DestroyList) == 1 {
+			t.Write(fs.DestroyList[0].Name)
+		} else {
+			t.Write(pruneRuleActionStr)
+		}
+		t.Newline()
+	}
+
+}
+
+func renderSnapperReport(t *stringbuilder.B, r *snapper.Report, fsfilter FilterFunc) {
+	if r == nil {
+		t.Printf("<snapshot type does not have a report>\n")
+		return
+	}
+
+	t.Printf("Status: %s", r.State)
+	t.Newline()
+
+	if r.Error != "" {
+		t.Printf("Error: %s\n", r.Error)
+	}
+	if !r.SleepUntil.IsZero() {
+		t.Printf("Sleep until: %s\n", r.SleepUntil)
+	}
+
+	sort.Slice(r.Progress, func(i, j int) bool {
+		return strings.Compare(r.Progress[i].Path, r.Progress[j].Path) == -1
+	})
+
+	dur := func(d time.Duration) string {
+		return d.Round(100 * time.Millisecond).String()
+	}
+
+	type row struct {
+		path, state, duration, remainder, hookReport string
+	}
+	var widths struct {
+		path, state, duration int
+	}
+	rows := make([]*row, 0, len(r.Progress))
+	for _, fs := range r.Progress {
+		if !fsfilter(fs.Path) {
+			continue
+		}
+		r := &row{
+			path:  fs.Path,
+			state: fs.State.String(),
+		}
+		if fs.HooksHadError {
+			r.hookReport = fs.Hooks // FIXME render here, not in daemon
+		}
+		switch fs.State {
+		case snapper.SnapPending:
+			r.duration = "..."
+			r.remainder = ""
+		case snapper.SnapStarted:
+			r.duration = dur(time.Since(fs.StartAt))
+			r.remainder = fmt.Sprintf("snap name: %q", fs.SnapName)
+		case snapper.SnapDone:
+			fallthrough
+		case snapper.SnapError:
+			r.duration = dur(fs.DoneAt.Sub(fs.StartAt))
+			r.remainder = fmt.Sprintf("snap name: %q", fs.SnapName)
+		}
+		rows = append(rows, r)
+		if len(r.path) > widths.path {
+			widths.path = len(r.path)
+		}
+		if len(r.state) > widths.state {
+			widths.state = len(r.state)
+		}
+		if len(r.duration) > widths.duration {
+			widths.duration = len(r.duration)
+		}
+	}
+
+	for _, r := range rows {
+		path := stringbuilder.RightPad(r.path, widths.path, " ")
+		state := stringbuilder.RightPad(r.state, widths.state, " ")
+		duration := stringbuilder.RightPad(r.duration, widths.duration, " ")
+		t.Printf("%s %s %s", path, state, duration)
+		t.PrintfDrawIndentedAndWrappedIfMultiline(" %s", r.remainder)
+		if r.hookReport != "" {
+			t.PrintfDrawIndentedAndWrappedIfMultiline("%s", r.hookReport)
+		}
+		t.Newline()
+	}
+
+}

client/status/viewmodel/stringbuilder/stringbuilder.go

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

client/testcmd.go

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

config/config.go

@@ -13,6 +13,7 @@ import (
 	"github.com/pkg/errors"
 	"github.com/zrepl/yaml-config"
 
+	"github.com/zrepl/zrepl/util/datasizeunit"
 	zfsprop "github.com/zrepl/zrepl/zfs/property"
 )
 
@@ -85,8 +86,10 @@ type SendOptions struct {
 	BackupProperties bool `yaml:"backup_properties,optional,default=false"`
 	LargeBlocks      bool `yaml:"large_blocks,optional,default=false"`
 	Compressed       bool `yaml:"compressed,optional,default=false"`
-	EmbeddedData     bool `yaml:"embbeded_data,optional,default=false"`
+	EmbeddedData     bool `yaml:"embedded_data,optional,default=false"`
 	Saved            bool `yaml:"saved,optional,default=false"`
+
+	BandwidthLimit *BandwidthLimit `yaml:"bandwidth_limit,optional,fromdefaults"`
 }
 
 type RecvOptions struct {
@@ -96,6 +99,17 @@ type RecvOptions struct {
 	// Reencrypt bool `yaml:"reencrypt"`
 
 	Properties *PropertyRecvOptions `yaml:"properties,fromdefaults"`
+
+	BandwidthLimit *BandwidthLimit `yaml:"bandwidth_limit,optional,fromdefaults"`
+
+	Placeholder *PlaceholderRecvOptions `yaml:"placeholder,fromdefaults"`
+}
+
+var _ yaml.Unmarshaler = &datasizeunit.Bits{}
+
+type BandwidthLimit struct {
+	Max            datasizeunit.Bits `yaml:"max,default=-1 B"`
+	BucketCapacity datasizeunit.Bits `yaml:"bucket_capacity,default=128 KiB"`
 }
 
 type Replication struct {
@@ -113,15 +127,15 @@ type ReplicationOptionsConcurrency struct {
 	SizeEstimates int `yaml:"size_estimates,optional,default=4"`
 }
 
-func (l *RecvOptions) SetDefault() {
-	*l = RecvOptions{Properties: &PropertyRecvOptions{}}
-}
-
 type PropertyRecvOptions struct {
 	Inherit  []zfsprop.Property          `yaml:"inherit,optional"`
 	Override map[zfsprop.Property]string `yaml:"override,optional"`
 }
 
+type PlaceholderRecvOptions struct {
+	Encryption string `yaml:"encryption,default=unspecified"`
+}
+
 type PushJob struct {
 	ActiveJob    `yaml:",inline"`
 	Snapshotting SnapshottingEnum  `yaml:"snapshotting"`

config/config_global_test.go

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

config/samples/bandwidth_limit.yml

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

config/samples/quickstart_backup_to_external_disk.yml

@@ -5,7 +5,7 @@
 # quick start section which inlines this example.
 #
 # CUSTOMIZATIONS YOU WILL LIKELY WANT TO APPLY:
-# - adjust the name of the production pool `system` in the `filesystems` filter of jobs `snapjob` and `push_to_derive`
+# - adjust the name of the production pool `system` in the `filesystems` filter of jobs `snapjob` and `push_to_drive`
 # - adjust the name of the backup pool `backuppool` in the `backuppool_sink` job
 # - adjust the occurences of `myhostname` to the name of the system you are backing up (cannot be easily changed once you start replicating)
 # - make sure the `zrepl_` prefix is not being used by any other zfs tools you might have installed (it likely isn't)

config/samples/quickstart_continuous_server_backup_sender.yml

@@ -9,8 +9,8 @@ jobs:
     key:  /etc/zrepl/prod.key
     server_cn: "backups"
   filesystems: {
-    "zroot/var/db": true,
-    "zroot/usr/home<": true,
+    "zroot<": true,
+    "zroot/var/tmp<": false,
     "zroot/usr/home/paranoid": false
   }
   snapshotting:

config/samples/quickstart_fan_out_replication_source.yml

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

config/samples/quickstart_fan_out_replication_target.yml

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

daemon/control.go

@@ -8,6 +8,7 @@ import (
 	"io"
 	"net"
 	"net/http"
+	"os"
 	"time"
 
 	"github.com/pkg/errors"
@@ -126,6 +127,7 @@ func (j *controlJob) Run(ctx context.Context) {
 				Global: GlobalStatus{
 					ZFSCmds:   globalZFS,
 					Envconst:  envconstReport,
+					OsEnviron: os.Environ(),
 				}}
 			return s, nil
 		}})
@@ -156,8 +158,8 @@ func (j *controlJob) Run(ctx context.Context) {
 	server := http.Server{
 		Handler: mux,
 		// control socket is local, 1s timeout should be more than sufficient, even on a loaded system
-		WriteTimeout: 1 * time.Second,
-		ReadTimeout:  1 * time.Second,
+		WriteTimeout: envconst.Duration("ZREPL_DAEMON_CONTROL_SERVER_WRITE_TIMEOUT", 1*time.Second),
+		ReadTimeout:  envconst.Duration("ZREPL_DAEMON_CONTROL_SERVER_READ_TIMEOUT", 1*time.Second),
 	}
 
 outer:

daemon/daemon.go

@@ -162,6 +162,7 @@ type Status struct {
 type GlobalStatus struct {
 	ZFSCmds   *zfscmd.Report
 	Envconst  *envconst.Report
+	OsEnviron []string
 }
 
 func (s *jobs) status() map[string]*job.Status {

daemon/job/active.go

@@ -42,6 +42,7 @@ type ActiveSide struct {
 	promPruneSecs         *prometheus.HistogramVec // labels: prune_side
 	promBytesReplicated   *prometheus.CounterVec   // labels: filesystem
 	promReplicationErrors prometheus.Gauge
+	promLastSuccessful    prometheus.Gauge
 
 	tasksMtx sync.Mutex
 	tasks    activeSideTasks
@@ -321,7 +322,6 @@ func activeSide(g *config.Global, in *config.ActiveJob, configJob interface{}) (
 		Help:        "number of bytes replicated from sender to receiver per filesystem",
 		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
 	}, []string{"filesystem"})
-
 	j.promReplicationErrors = prometheus.NewGauge(prometheus.GaugeOpts{
 		Namespace:   "zrepl",
 		Subsystem:   "replication",
@@ -329,6 +329,13 @@ func activeSide(g *config.Global, in *config.ActiveJob, configJob interface{}) (
 		Help:        "number of filesystems that failed replication in the latest replication attempt, or -1 if the job failed before enumerating the filesystems",
 		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
 	})
+	j.promLastSuccessful = prometheus.NewGauge(prometheus.GaugeOpts{
+		Namespace:   "zrepl",
+		Subsystem:   "replication",
+		Name:        "last_successful",
+		Help:        "timestamp of last successful replication",
+		ConstLabels: prometheus.Labels{"zrepl_job": j.name.String()},
+	})
 
 	j.connecter, err = fromconfig.ConnecterFromConfig(g, in.Connect)
 	if err != nil {
@@ -360,6 +367,7 @@ func (j *ActiveSide) RegisterMetrics(registerer prometheus.Registerer) {
 	registerer.MustRegister(j.promPruneSecs)
 	registerer.MustRegister(j.promBytesReplicated)
 	registerer.MustRegister(j.promReplicationErrors)
+	registerer.MustRegister(j.promLastSuccessful)
 }
 
 func (j *ActiveSide) Name() string { return j.name.String() }
@@ -494,7 +502,11 @@ func (j *ActiveSide) do(ctx context.Context) {
 		repCancel()   // always cancel to free up context resources
 
 		replicationReport := j.tasks.replicationReport()
-		j.promReplicationErrors.Set(float64(replicationReport.GetFailedFilesystemsCountInLatestAttempt()))
+		var numErrors = replicationReport.GetFailedFilesystemsCountInLatestAttempt()
+		j.promReplicationErrors.Set(float64(numErrors))
+		if numErrors == 0 {
+			j.promLastSuccessful.SetToCurrentTime()
+		}
 
 		endSpan()
 	}

daemon/job/build_jobs.go

@@ -8,6 +8,7 @@ import (
 	"github.com/pkg/errors"
 
 	"github.com/zrepl/zrepl/config"
+	"github.com/zrepl/zrepl/util/bandwidthlimit"
 )
 
 func JobsFromConfig(c *config.Config) ([]Job, error) {
@@ -107,3 +108,13 @@ func validateReceivingSidesDoNotOverlap(receivingRootFSs []string) error {
 	}
 	return nil
 }
+
+func buildBandwidthLimitConfig(in *config.BandwidthLimit) (c bandwidthlimit.Config, _ error) {
+	if in.Max.ToBytes() > 0 && int64(in.Max.ToBytes()) == 0 {
+		return c, fmt.Errorf("bandwidth limit `max` is too small, must at least specify one byte")
+	}
+	return bandwidthlimit.Config{
+		Max:            int64(in.Max.ToBytes()),
+		BucketCapacity: int64(in.BucketCapacity.ToBytes()),
+	}, nil
+}

daemon/job/build_jobs_sendrecvoptions.go

@@ -22,7 +22,12 @@ func buildSenderConfig(in SendingJobConfig, jobID endpoint.JobID) (*endpoint.Sen
 		return nil, errors.Wrap(err, "cannot build filesystem filter")
 	}
 	sendOpts := in.GetSendOptions()
-	return &endpoint.SenderConfig{
+	bwlim, err := buildBandwidthLimitConfig(sendOpts.BandwidthLimit)
+	if err != nil {
+		return nil, errors.Wrap(err, "cannot build bandwith limit config")
+	}
+
+	sc := &endpoint.SenderConfig{
 		FSF:   fsf,
 		JobID: jobID,
 
@@ -34,7 +39,15 @@ func buildSenderConfig(in SendingJobConfig, jobID endpoint.JobID) (*endpoint.Sen
 		SendCompressed:       sendOpts.Compressed,
 		SendEmbeddedData:     sendOpts.EmbeddedData,
 		SendSaved:            sendOpts.Saved,
-	}, nil
+
+		BandwidthLimit: bwlim,
+	}
+
+	if err := sc.Validate(); err != nil {
+		return nil, errors.Wrap(err, "cannot build sender config")
+	}
+
+	return sc, nil
 }
 
 type ReceivingJobConfig interface {
@@ -53,6 +66,22 @@ func buildReceiverConfig(in ReceivingJobConfig, jobID endpoint.JobID) (rc endpoi
 	}
 
 	recvOpts := in.GetRecvOptions()
+
+	bwlim, err := buildBandwidthLimitConfig(recvOpts.BandwidthLimit)
+	if err != nil {
+		return rc, errors.Wrap(err, "cannot build bandwith limit config")
+	}
+
+	placeholderEncryption, err := endpoint.PlaceholderCreationEncryptionPropertyString(recvOpts.Placeholder.Encryption)
+	if err != nil {
+		options := []string{}
+		for _, v := range endpoint.PlaceholderCreationEncryptionPropertyValues() {
+			options = append(options, endpoint.PlaceholderCreationEncryptionProperty(v).String())
+		}
+		return rc, errors.Errorf("placeholder encryption value %q is invalid, must be one of %s",
+			recvOpts.Placeholder.Encryption, options)
+	}
+
 	rc = endpoint.ReceiverConfig{
 		JobID:                      jobID,
 		RootWithoutClientComponent: rootFs,
@@ -60,6 +89,10 @@ func buildReceiverConfig(in ReceivingJobConfig, jobID endpoint.JobID) (rc endpoi
 
 		InheritProperties:  recvOpts.Properties.Inherit,
 		OverrideProperties: recvOpts.Properties.Override,
+
+		BandwidthLimit: bwlim,
+
+		PlaceholderEncryption: placeholderEncryption,
 	}
 	if err := rc.Validate(); err != nil {
 		return rc, errors.Wrap(err, "cannot build receiver config")

daemon/job/build_jobs_test.go

@@ -119,6 +119,14 @@ func TestSampleConfigsAreBuiltWithoutErrors(t *testing.T) {
 		t.Errorf("glob failed: %+v", err)
 	}
 
+	type additionalCheck struct {
+		state int
+		test  func(t *testing.T, jobs []Job)
+	}
+	additionalChecks := map[string]*additionalCheck{
+		"bandwidth_limit.yml": {test: testSampleConfig_BandwidthLimit},
+	}
+
 	for _, p := range paths {
 
 		if path.Ext(p) != ".yml" {
@@ -126,10 +134,20 @@ func TestSampleConfigsAreBuiltWithoutErrors(t *testing.T) {
 			continue
 		}
 
+		filename := path.Base(p)
+		t.Logf("checking for presence additonal checks for file %q", filename)
+		additionalCheck := additionalChecks[filename]
+		if additionalCheck == nil {
+			t.Logf("no additional checks")
+		} else {
+			t.Logf("additional check present")
+			additionalCheck.state = 1
+		}
+
 		t.Run(p, func(t *testing.T) {
 			c, err := config.ParseConfig(p)
 			if err != nil {
-				t.Errorf("error parsing %s:\n%+v", p, err)
+				t.Fatalf("error parsing %s:\n%+v", p, err)
 			}
 
 			t.Logf("file: %s", p)
@@ -138,11 +156,57 @@ func TestSampleConfigsAreBuiltWithoutErrors(t *testing.T) {
 			tls.FakeCertificateLoading(t)
 			jobs, err := JobsFromConfig(c)
 			t.Logf("jobs: %#v", jobs)
-			assert.NoError(t, err)
+			require.NoError(t, err)
+
+			if additionalCheck != nil {
+				additionalCheck.test(t, jobs)
+				additionalCheck.state = 2
+			}
 		})
 
 	}
 
+	for basename, c := range additionalChecks {
+		if c.state == 0 {
+			panic("univisited additional check " + basename)
+		}
+	}
+
+}
+
+func testSampleConfig_BandwidthLimit(t *testing.T, jobs []Job) {
+	require.Len(t, jobs, 3)
+
+	{
+		limitedSink, ok := jobs[0].(*PassiveSide)
+		require.True(t, ok, "%T", jobs[0])
+		limitedSinkMode, ok := limitedSink.mode.(*modeSink)
+		require.True(t, ok, "%T", limitedSink)
+
+		assert.Equal(t, int64(12345), limitedSinkMode.receiverConfig.BandwidthLimit.Max)
+		assert.Equal(t, int64(1<<17), limitedSinkMode.receiverConfig.BandwidthLimit.BucketCapacity)
+	}
+
+	{
+		limitedPush, ok := jobs[1].(*ActiveSide)
+		require.True(t, ok, "%T", jobs[1])
+		limitedPushMode, ok := limitedPush.mode.(*modePush)
+		require.True(t, ok, "%T", limitedPush)
+
+		assert.Equal(t, int64(54321), limitedPushMode.senderConfig.BandwidthLimit.Max)
+		assert.Equal(t, int64(1024), limitedPushMode.senderConfig.BandwidthLimit.BucketCapacity)
+	}
+
+	{
+		unlimitedSink, ok := jobs[2].(*PassiveSide)
+		require.True(t, ok, "%T", jobs[2])
+		unlimitedSinkMode, ok := unlimitedSink.mode.(*modeSink)
+		require.True(t, ok, "%T", unlimitedSink)
+
+		max := unlimitedSinkMode.receiverConfig.BandwidthLimit.Max
+		assert.Less(t, max, int64(0), max, "unlimited mode <=> negative value for .Max, see bandwidthlimit.Config")
+	}
+
 }
 
 func TestReplicationOptions(t *testing.T) {

daemon/job/snapjob.go

@@ -10,6 +10,7 @@ import (
 	"github.com/prometheus/client_golang/prometheus"
 
 	"github.com/zrepl/zrepl/daemon/logging/trace"
+	"github.com/zrepl/zrepl/util/bandwidthlimit"
 	"github.com/zrepl/zrepl/util/nodefault"
 
 	"github.com/zrepl/zrepl/config"
@@ -146,7 +147,7 @@ type alwaysUpToDateReplicationCursorHistory struct {
 	target pruner.Target
 }
 
-var _ pruner.History = (*alwaysUpToDateReplicationCursorHistory)(nil)
+var _ pruner.Sender = (*alwaysUpToDateReplicationCursorHistory)(nil)
 
 func (h alwaysUpToDateReplicationCursorHistory) ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error) {
 	fsvReq := &pdu.ListFilesystemVersionsReq{
@@ -179,8 +180,11 @@ func (j *SnapJob) doPrune(ctx context.Context) {
 	sender := endpoint.NewSender(endpoint.SenderConfig{
 		JobID: j.name,
 		FSF:   j.fsfilter,
-		// FIXME encryption setting is irrelevant for SnapJob because the endpoint is only used as pruner.Target
+		// FIXME the following config fields are irrelevant for SnapJob
+		// because the endpoint is only used as pruner.Target.
+		// However, the implementation requires them to be set.
 		Encrypt:        &nodefault.Bool{B: true},
+		BandwidthLimit: bandwidthlimit.NoLimitConfig(),
 	})
 	j.prunerMtx.Lock()
 	j.pruner = j.prunerFactory.BuildLocalPruner(ctx, sender, alwaysUpToDateReplicationCursorHistory{sender})

daemon/logging/trace/trace.go

@@ -246,7 +246,7 @@ func WithTask(ctx context.Context, taskName string) (context.Context, DoneFunc)
 					// the debugString can be quite long and panic won't print it completely
 					fmt.Fprintf(os.Stderr, "going to panic due to activeChildTasks:\n%s\n", this.debugString())
 				}
-				panic(errors.WithMessagef(ErrTaskStillHasActiveChildTasks, "end task: %v active child tasks\n", this.activeChildTasks))
+				panic(errors.WithMessagef(ErrTaskStillHasActiveChildTasks, "end task: %v active child tasks (run daemon with env var %s=1 for more details)\n", this.activeChildTasks, debugEnabledEnvVar))
 			}
 
 			// support idempotent task ends

daemon/logging/trace/trace_debug.go

@@ -7,7 +7,9 @@ import (
 	"github.com/zrepl/zrepl/util/envconst"
 )
 
-var debugEnabled = envconst.Bool("ZREPL_TRACE_DEBUG_ENABLED", false)
+const debugEnabledEnvVar = "ZREPL_TRACE_DEBUG_ENABLED"
+
+var debugEnabled = envconst.Bool(debugEnabledEnvVar, false)
 
 func debug(format string, args ...interface{}) {
 	if !debugEnabled {

daemon/pruner/pruner.go

@@ -19,12 +19,20 @@ import (
 	"github.com/zrepl/zrepl/util/envconst"
 )
 
+// The sender in the replication setup.
+// The pruner uses the Sender to determine which of the Target's filesystems need to be pruned.
+// Also, it asks the Sender about the replication cursor of each filesystem
+// to enable the 'not_replicated' pruning rule.
+//
 // Try to keep it compatible with github.com/zrepl/zrepl/endpoint.Endpoint
-type History interface {
+type Sender interface {
 	ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error)
 	ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error)
 }
 
+// The pruning target, i.e., on which snapshots are destroyed.
+// This can be a replication sender or receiver.
+//
 // Try to keep it compatible with github.com/zrepl/zrepl/endpoint.Endpoint
 type Target interface {
 	ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error)
@@ -48,7 +56,7 @@ func GetLogger(ctx context.Context) Logger {
 type args struct {
 	ctx                            context.Context
 	target                         Target
-	receiver                       History
+	sender                         Sender
 	rules                          []pruning.KeepRule
 	retryWait                      time.Duration
 	considerSnapAtCursorReplicated bool
@@ -132,12 +140,12 @@ func NewPrunerFactory(in config.PruningSenderReceiver, promPruneSecs *prometheus
 	return f, nil
 }
 
-func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, receiver History) *Pruner {
+func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, sender Sender) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "sender"),
 			target,
-			receiver,
+			sender,
 			f.senderRules,
 			f.retryWait,
 			f.considerSnapAtCursorReplicated,
@@ -148,12 +156,12 @@ func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, re
 	return p
 }
 
-func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target, receiver History) *Pruner {
+func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target, sender Sender) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "receiver"),
 			target,
-			receiver,
+			sender,
 			f.receiverRules,
 			f.retryWait,
 			false, // senseless here anyways
@@ -164,12 +172,12 @@ func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target,
 	return p
 }
 
-func (f *LocalPrunerFactory) BuildLocalPruner(ctx context.Context, target Target, receiver History) *Pruner {
+func (f *LocalPrunerFactory) BuildLocalPruner(ctx context.Context, target Target, history Sender) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "local"),
 			target,
-			receiver,
+			history,
 			f.keepRules,
 			f.retryWait,
 			false, // considerSnapAtCursorReplicated is not relevant for local pruning
@@ -343,9 +351,9 @@ func (s snapshot) Date() time.Time { return s.date }
 
 func doOneAttempt(a *args, u updater) {
 
-	ctx, target, receiver := a.ctx, a.target, a.receiver
+	ctx, target, sender := a.ctx, a.target, a.sender
 
-	sfssres, err := receiver.ListFilesystems(ctx, &pdu.ListFilesystemReq{})
+	sfssres, err := sender.ListFilesystems(ctx, &pdu.ListFilesystemReq{})
 	if err != nil {
 		u(func(p *Pruner) {
 			p.state = PlanErr
@@ -410,7 +418,7 @@ tfss_loop:
 		rcReq := &pdu.ReplicationCursorReq{
 			Filesystem: tfs.Path,
 		}
-		rc, err := receiver.ReplicationCursor(ctx, rcReq)
+		rc, err := sender.ReplicationCursor(ctx, rcReq)
 		if err != nil {
 			pfsPlanErrAndLog(err, "cannot get replication cursor bookmark")
 			continue tfss_loop
@@ -456,7 +464,7 @@ tfss_loop:
 			})
 		}
 		if preCursor {
-			pfsPlanErrAndLog(fmt.Errorf("replication cursor not found in prune target filesystem versions"), "")
+			pfsPlanErrAndLog(fmt.Errorf("prune target has no snapshot that corresponds to sender replication cursor bookmark"), "")
 			continue tfss_loop
 		}
 

docs/changelog.rst

@@ -6,6 +6,7 @@
 .. |docs| replace:: [DOCS]
 .. |feature| replace:: [FEATURE]
 .. |mig| replace:: **[MIGRATION]**
+.. |maint| replace:: [MAINT]
 
 .. _changelog:
 
@@ -15,17 +16,68 @@ 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.
 
-We use the following annotations for classifying changes:
+0.5
+---
 
-* |break_config| Change that breaks the config.
-  As a package maintainer, make sure to warn your users about config breakage somehow.
-* |break| Change that breaks interoperability or persistent state representation with previous releases.
-  As a package maintainer, make sure to warn your users about config breakage somehow.
-  Note that even updating the package on both sides might not be sufficient, e.g. if persistent state needs to be migrated to a new format.
-* |mig| Migration that must be run by the user.
-* |feature| Change that introduces new functionality.
-* |bugfix| Change that fixes a bug, no regressions or incompatibilities expected.
-* |docs| Change to the documentation.
+* |feature| :ref:`Bandwidth limiting <job-send-recv-options--bandwidth-limit>` (Thanks, Prominic.NET, Inc.)
+* |feature| zrepl status: use a ``*`` to indicate which filesystem is currently replicating
+* |feature| include daemon environment variables in zrepl status (currently only in ``--raw``)
+* |bugfix| **fix encrypt-on-receive + placeholders use case** (:issue:`504`)
+
+  * Before this fix, **plain sends** to a receiver with an encrypted ``root_fs`` **could be received unencrypted** if zrepl needed to create placeholders on the receiver.
+  * Existing zrepl users should :ref:`read the docs <job-recv-options--placeholder>` and check ``zfs get -r encryption,zrepl:placeholder PATH_TO_ROOTFS`` on the receiver.
+  * Thanks to `@mologie <https://github.com/mologie>`_ and `@razielgn <https://github.com/razielgn>`_ for reporting and testing!
+
+* |bugfix| Rename mis-spelled :ref:`send option <job-send-options>` ``embbeded_data`` to ``embedded_data``.
+* |bugfix| zrepl status: replication step numbers should start at 1
+* |bugfix| incorrect bandwidth averaging in ``zrepl status``.
+* |bugfix| FreeBSD with OpenZFS 2.0: zrepl would wait indefinitely for zfs send to exit on timeouts.
+* |bugfix| fix ``strconv.ParseInt: value out of range`` bug (and use the control RPCs).
+* |docs| improve description of multiple pruning rules.
+* |docs| document :ref:`platform tests <usage-platform-tests>`.
+* |docs| quickstart: make users aware that prune rules apply to all snapshots.
+* |maint| some platformtests were broken.
+* |maint| FreeBSD: release armv7 and arm64 binaries.
+* |maint| apt repo: update instructions due to ``apt-key`` deprecation.
+
+Note to all users: please read up on the following OpenZFS bugs, as you might be affected:
+
+* `ZFS send/recv with ashift 9->12 leads to data corruption <https://github.com/openzfs/zfs/issues/12762>`_.
+* Various bugs with encrypted send/recv (`Leadership meeting notes <https://openzfs.topicbox.com/groups/developer/T24bdaa2886c6cbf5-Mc039a11c3f1507ea0664817b/december-openzfs-leadership-meeting>`_)
+
+Finally, I'd like to point you to the `GitHub discussion <https://github.com/zrepl/zrepl/discussions/547>`_ about which bugfixes and features should be prioritized in zrepl 0.6 and beyond!
+
+.. 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
+-----
+
+* |feature| support setting zfs send / recv flags in the config (send: ``-wLcepbS`` , recv: ``-ox`` ).
+  Config docs :ref:`here <job-send-options>` and :ref:`here <job-recv-options>` .
+* |feature| parallel replication is now configurable (disabled by default, :ref:`config docs here <replication-option-concurrency>` ).
+* |feature| New ``zrepl status`` UI:
+
+  * Interactive job selection.
+  * Interactively ``zrepl signal`` jobs.
+  * Filter filesystems in the job view by name.
+  * An approximation of the old UI is still included as `--mode legacy` but will be removed in a future release of zrepl.
+
+* |bugfix| Actually use concurrency when listing zrepl abstractions & doing size estimation.
+  These operations were accidentally made sequential in zrepl 0.3.
+* |bugfix| Job hang-up during second replication attempt.
+* |bugfix| Data races conditions in the dataconn rpc stack.
+* |maint| Update to protobuf v1.25 and grpc 1.35.
+
+For users who skipped the 0.3.1 update: please make sure your pruning grid config is correct.
+The following bugfix in 0.3.1 :issue:`caused problems for some users <400>`:
+
+* |bugfix| pruning: ``grid``:  add all snapshots that do not match the regex to the rule's destroy list.
 
 0.3.1
 -----
@@ -45,13 +97,6 @@ Mostly a bugfix release for :ref:`zrepl 0.3 <release-0.3>`.
 * CI infrastructure rework
 * Continuous deployment of that new `stable` branch to zrepl.github.io.
 
-.. 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>`_.
-
 .. _release-0.3:
 
 0.3

docs/configuration/monitoring.rst

@@ -13,7 +13,7 @@ Prometheus & Grafana
 --------------------
 
 zrepl can expose `Prometheus metrics <https://prometheus.io/docs/instrumenting/exposition_formats/>`_ via HTTP.
-The ``listen`` attribute is a `net.Listen <https://golang.org/pkg/net/#Listen>`_  string for tcp, e.g. ``:9091`` or ``127.0.0.1:9091``.
+The ``listen`` attribute is a `net.Listen <https://golang.org/pkg/net/#Listen>`_  string for tcp, e.g. ``:9811`` or ``127.0.0.1:9811`` (port 9811 was reserved to zrepl `on the official list <https://github.com/prometheus/prometheus/wiki/Default-port-allocations/_compare/43e495dd251ee328ac0d08b58084665b5c0f7a7e...459195059b55b414193ebeb80c5ba463d2606951>`_).
 The ``listen_freebind`` attribute is :ref:`explained here <listen-freebind-explanation>`.
 The Prometheus monitoring job appears in the ``zrepl control`` job list and may be specified **at most once**.
 
@@ -30,7 +30,7 @@ The dashboard also contains some advice on which metrics are important to monito
     global:
       monitoring:
         - type: prometheus
-          listen: ':9091'
+          listen: ':9811'
           listen_freebind: true # optional, default false
 
 

docs/configuration/overview.rst

@@ -248,7 +248,7 @@ Limitations
 Multiple Jobs & More than 2 Machines
 ------------------------------------
 
-The quick-start guides focus on simple setups with a single sender and a single receiver.
+Most users are served well with a single sender and a single receiver job.
 This section documents considerations for more complex setups.
 
 .. ATTENTION::
@@ -288,11 +288,46 @@ This section might be relevant to users who wish to *fan-in* (N machines replica
 
 **Working setups**:
 
-* N ``push`` identities, 1 ``sink`` (as long as the different push jobs have a different :ref:`client identity <overview-passive-side--client-identity>`)
+* **Fan-in: N servers replicated to one receiver, disjoint dataset trees.**
 
-  * ``sink`` constrains each client to a disjoint sub-tree of the sink-side dataset hierarchy ``${root_fs}/${client_identity}``.
+  * This is the common use case of a centralized backup server.
+
+  * Implementation:
+
+    * N ``push`` jobs (one per sender server), 1 ``sink`` (as long as the different push jobs have a different :ref:`client identity <overview-passive-side--client-identity>`)
+    * N ``source`` jobs (one per sender server), N ``pull`` on the receiver server (unique names, disjoing  ``root_fs``)
+
+  * The ``sink`` job automatically constrains each client to a disjoint sub-tree of the sink-side dataset hierarchy ``${root_fs}/${client_identity}``.
     Therefore, the different clients cannot interfere.
 
+  * The ``pull`` job only pulls from one host, so it's up to the zrepl user to ensure that the different ``pull`` jobs don't interfere.
+
+.. _fan-out-replication:
+
+* **Fan-out: 1 server replicated to N receivers**
+
+  * Can be implemented either in a pull or push fashion.
+
+    * **pull setup**: 1 ``pull`` job on each receiver server, each with a corresponding **unique** ``source`` job on the sender server.
+    * **push setup**: 1 ``sink`` job on each receiver server, each with a corresponding **unique** ``push`` job on the sender server.
+
+  * It is critical that we have one sending-side job (``source``, ``push``) per receiver.
+    The reason is that :ref:`zrepl's ZFS abstractions <zrepl-zfs-abstractions>` (``zrepl zfs-abstraction list``) include the name of the ``source``/``push`` job, but not the receive-side job name or client identity (see :issue:`380`).
+    As a counter-example, suppose we used multiple ``pull`` jobs with only one ``source`` job.
+    All ``pull`` jobs would share the same :ref:`replication cursor bookmark <replication-cursor-and-last-received-hold>` and trip over each other, breaking incremental replication guarantees quickly.
+    The anlogous problem exists for 1 ``push`` to N ``sink`` jobs.
+
+  * The ``filesystems`` matched by the sending side jobs (``source``, ``push``) need not necessarily be disjoint.
+    For this to work, we need to avoid interference between snapshotting and pruning of the different sending jobs.
+    The solution is to centralize sender-side snapshot management in a separate ``snap`` job.
+    Snapshotting in the ``source``/``push`` job should then be disabled (``type: manual``).
+    And sender-side pruning (``keep_sender``) needs to be disabled in the active side (``pull`` / ``push``), since that'll be done by the ``snap job``.
+
+  * **Restore limitations**: when restoring from one of the ``pull`` targets (e.g., using ``zfs send -R``), the replication cursor bookmarks don't exist on the restored system.
+    This can break incremental replication to all other receive-sides after restore.
+
+  * See :ref:`the fan-out replication quick-start guide <quickstart-fan-out-replication>` for an example of this setup.
+
 
 **Setups that do not work**:
 

docs/configuration/prune.rst

@@ -67,8 +67,9 @@ Policy ``not_replicated``
      ...
 
 ``not_replicated`` keeps all snapshots that have not been replicated to the receiving side.
-It only makes sense to specify this rule on a sender (source or push job).
-The state required to evaluate this rule is stored in the :ref:`replication cursor bookmark <replication-cursor-and-last-received-hold>` on the sending side.
+It only makes sense to specify this rule for the ``keep_sender``.
+The reason is that, by definition, all snapshots on the receiver have already been replicated to there from the sender.
+To determine whether a sender-side snapshot has already been replicated, zrepl uses the :ref:`replication cursor bookmark <replication-cursor-and-last-received-hold>` which corresponds to the most recent successfully replicated snapshot.
 
 .. _prune-keep-retention-grid:
 
@@ -106,7 +107,7 @@ The following procedure happens during pruning:
 #. All subsequent buckets are placed adjacent to their predecessor bucket.
 #. Now each snapshot on the axis either falls into one bucket or it is older than our rightmost bucket.
    Buckets are left-inclusive and right-exclusive which means that a snapshot on the edge of bucket will always 'fall into the right one'.
-#. Snapshots older than the rightmost bucket **not kept** by this gridspec.
+#. Snapshots older than the rightmost bucket are **not kept** by the grid specification.
 #. For each bucket, we only keep the ``keep`` oldest snapshots.
 
 The syntax to describe the bucket list is as follows:
@@ -124,43 +125,51 @@ The syntax to describe the bucket list is as follows:
 
 ::
 
-          This grid spec produces the following list of adjacent buckets. For the sake of simplicity,
-          we subject all snapshots to the grid pruning policy by settings `regex: .*`.
+   Assume the following grid specification:
 
-          `
       grid: 1x1h(keep=all) | 2x2h | 1x3h
-           regex: .*
-          `
+
+   This grid specification produces the following constellation of buckets:
 
    0h        1h        2h        3h        4h        5h        6h        7h        8h        9h
    |         |         |         |         |         |         |         |         |         |
-          |-Bucket1-|-----Bucket 2------|------Bucket 3-----|-----------Bucket 4----------|
+   |-Bucket1-|-----Bucket2-------|------Bucket3------|-----------Bucket4-----------|
    | keep=all|      keep=1       |       keep=1      |            keep=1           |
 
 
 
-          Let us consider the following set of snapshots @a-zA-C:
+   Now assume that we have a set of snapshots @a, @b, ..., @D.
+   Snapshot @a is the most recent snapshot.
+   Snapshot @D is the oldest snapshot, it is almost 9 hours older than snapshot @a.
+   We place the snapshots on the same timeline as the buckets:
 
 
-          |  a  b  c  d  e  f  g  h  i  j  k  l  m  n  o  p  q  r  s  t  u  v  w  x  y  z  A  B  C  D        |
+   0h        1h        2h        3h        4h        5h        6h        7h        8h        9h
+   |         |         |         |         |         |         |         |         |         |
+   |-Bucket1-|-----Bucket2-------|------Bucket3------|-----------Bucket4-----------|
+   | keep=all|      keep=1       |       keep=1      |            keep=1           |
+   |         |                   |                   |                             |
+   | a  b  c | d  e  f  g  h  i  j  k  l  m  n  o  p |q  r  s  t  u  v  w  x  y  z |A  B  C  D
 
-          The `grid` algorithm maps them to their respective buckets:
+   We obtain the following mapping of snapshots to buckets:
 
    Bucket1:   a,b,c
-          Bucket 2: d,e,f,g,h,i,j
-          Bucket 3: k,l,m,n,o,p
-          Bucket 4: q,r, q,r,s,t,u,v,w,x,y,z
-          None:     A,B,C,D
+   Bucket2:   d,e,f,g,h,i
+   Bucket3:   j,k,l,m,n,o,p
+   Bucket4:   q,r,s,t,u,v,w,x,y,z
+   No bucket: A,B,C,D
 
-          It then applies the per-bucket pruning logic described above which resulting in the
-          following list of remaining snapshots.
+   For each bucket, we now prune snapshots until it only contains `keep` snapshots.
+   Newer snapshots are destroyed first.
+   Snapshots that do not fall into a bucket are always destroyed.
 
-          |  a  b  c                    j                 p                             z                    |
-
-          Note that it only makes sense to grow (not shorten) the interval duration for buckets
-          further in the past since each bucket acts like a low-pass filter for incoming snapshots
-          and adding a less-low-pass-filter after a low-pass one has no effect.
+   Result after pruning:
 
+   0h        1h        2h        3h        4h        5h        6h        7h        8h        9h
+   |         |         |         |         |         |         |         |         |         |
+   |-Bucket1-|-----Bucket2-------|------Bucket3------|-----------Bucket4-----------|
+   |         |                   |                   |                             |
+   | a  b  c |                i  |                 p |                           z |
 
 .. _prune-keep-last-n:
 

docs/configuration/sendrecvoptions.rst

@@ -36,9 +36,12 @@ See the `upstream man page <https://openzfs.github.io/openzfs-docs/man/8/zfs-sen
     * - ``encrypted``
       -
       - Specific to zrepl, :ref:`see below <job-send-options-encrypted>`.
+    * - ``bandwidth_limit``
+      -
+      - Specific to zrepl, :ref:`see below <job-send-recv-options--bandwidth-limit>`.
     * - ``raw``
       - ``-w``
-      - Use ``encrypted`` to only allow encrypted sends.
+      - Use ``encrypted`` to only allow encrypted sends. Mixed sends are not supported.
     * - ``send_properties``
       - ``-p``
       - **Be careful**, read the :ref:`note on property replication below <job-note-property-replication>`.
@@ -51,7 +54,7 @@ See the `upstream man page <https://openzfs.github.io/openzfs-docs/man/8/zfs-sen
     * - ``compressed``
       - ``-c``
       -
-    * - ``embbeded_data``
+    * - ``embedded_data``
       - ``-e``
       -
     * - ``saved``
@@ -138,8 +141,16 @@ Recv Options
          override: {
            "org.openzfs.systemd:ignore": "on"
          }
+       bandwidth_limit: ...
+       placeholder:
+         encryption: unspecified | off | inherit
      ...
 
+Jump to
+:ref:`properties <job-recv-options--inherit-and-override>` ,
+:ref:`bandwidth_limit <job-send-recv-options--bandwidth-limit>` , and
+:ref:`bandwidth_limit <job-recv-options--placeholder>`.
+
 .. _job-recv-options--inherit-and-override:
 
 ``properties``
@@ -186,6 +197,12 @@ Mount behaviour
 * ``canmount``
 * ``overlay``
 
+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
 -------
 
@@ -206,3 +223,55 @@ and property replication is enabled, the receiver must :ref:`inherit the followi
 * ``keylocation``
 * ``keyformat``
 * ``encryption``
+
+.. _job-recv-options--placeholder:
+
+Placeholders
+------------
+
+During replication, zrepl :ref:`creates placeholder datasets <replication-placeholder-property>` on the receiving side if the sending side's ``filesystems`` filter creates gaps in the dataset hierarchy.
+This is generally fully transparent to the user.
+However, with OpenZFS Native Encryption, placeholders require zrepl user attention.
+Specifically, the problem is that, when zrepl attempts to create the placeholder dataset on the receiver, and that placeholder's parent dataset is encrypted, ZFS wants to inherit encryption to the placeholder.
+This is relevant to two use cases that zrepl supports:
+
+1. **encrypted-send-to-untrusted-receiver** In this use case, the sender sends an :ref:`encrypted send stream <job-send-options-encrypted>` and the receiver doesn't have the key loaded.
+2. **send-plain-encrypt-on-receive** The receive-side ``root_fs`` dataset is encrypted, and the senders are unencrypted.
+   The key of ``root_fs`` is loaded, and the goal is that the plain sends (e.g., from production) are encrypted on-the-fly during receive, with ``root_fs``'s key.
+
+For **encrypted-send-to-untrusted-receiver**, the placeholder datasets need to be created with ``-o encryption=off``.
+Without it, creation would fail with an error, indicating that the placeholder's parent dataset's key needs to be loaded.
+But we don't trust the receiver, so we can't expect that to ever happen.
+
+However, for **send-plain-encrypt-on-receive**, we cannot set ``-o encryption=off``.
+The reason is that if we did, any of the (non-placeholder) child datasets below the placeholder would inherit ``encryption=off``, thereby silently breaking our encrypt-on-receive use case.
+So, to cover this use case, we need to create placeholders without specifying ``-o encryption``.
+This will make ``zfs create`` inherit the encryption mode from the parent dataset, and thereby transitively from ``root_fs``.
+
+The zrepl config provides the `recv.placeholder.encryption` knob to control this behavior.
+In ``undefined`` mode (default), placeholder creation bails out and asks the user to configure a behavior.
+In ``off`` mode, the placeholder is created with ``encryption=off``, i.e., **encrypted-send-to-untrusted-rceiver** use case.
+In ``inherit`` mode, the placeholder is created without specifying ``-o encryption`` at all, i.e., the **send-plain-encrypt-on-receive** use case.
+
+
+Common Options
+~~~~~~~~~~~~~~
+
+.. _job-send-recv-options--bandwidth-limit:
+
+Bandwidth Limit (send & recv)
+-----------------------------
+
+::
+
+   bandwidth_limit:
+     max: 23.5 MiB # -1 is the default and disabled rate limiting
+     bucket_capacity: # token bucket capacity in bytes; defaults to 128KiB
+
+Both ``send`` and ``recv`` can be limited to a maximum bandwidth through ``bandwidth_limit``.
+For most users, it should be sufficient to just set ``bandwidth_limit.max``.
+The ``bandwidth_limit.bucket_capacity`` refers to the `token bucket size <https://github.com/juju/ratelimit>`_.
+
+The bandwidth limit only applies to the payload data, i.e., the ZFS send stream.
+It does not account for transport protocol overheads.
+The scope is the job level, i.e., all :ref:`concurrent <replication-option-concurrency>` sends or incoming receives of a job share the bandwidth limit.

docs/global.rst.inc

@@ -5,7 +5,7 @@
 
 .. |GitHub license| image:: https://img.shields.io/github/license/zrepl/zrepl.svg
    :target: https://github.com/zrepl/zrepl/blob/master/LICENSE
-.. |Language: Go| image:: https://img.shields.io/badge/language-Go-6ad7e5.svg
+.. |Language: Go| image:: https://img.shields.io/badge/lang-Go-6ad7e5.svg
    :target: https://golang.org/
 .. |User Docs| image:: https://img.shields.io/badge/docs-web-blue.svg
    :target: https://zrepl.github.io
@@ -13,13 +13,14 @@
    :target: https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96
 .. |Donate via Liberapay| image:: https://img.shields.io/liberapay/patrons/zrepl.svg?logo=liberapay
    :target: https://liberapay.com/zrepl/donate
-.. |Donate via Patreon| image:: https://img.shields.io/badge/dynamic/json?color=yellow&label=Patreon&query=data.attributes.patron_count&suffix=%20patrons&url=https%3A%2F%2Fwww.patreon.com%2Fapi%2Fcampaigns%2F3095079
+.. |Donate via Patreon| image:: https://img.shields.io/badge/dynamic/json?color=yellow&label=Patreon&query=data.attributes.patron_count&url=https%3A%2F%2Fwww.patreon.com%2Fapi%2Fcampaigns%2F3095079
    :target: https://www.patreon.com/zrepl
 .. |Donate via GitHub Sponsors| image:: https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&style=flat&color=yellow
    :target: https://github.com/sponsors/problame
 .. |Twitter| image:: https://img.shields.io/twitter/url/https/github.com/zrepl/zrepl.svg?style=social
    :target: https://twitter.com/intent/tweet?text=Wow:&url=https%3A%2F%2Fgithub.com%2Fzrepl%2Fzrepl
-
+.. |Matrix| image:: https://img.shields.io/badge/chat-matrix-blue.svg
+   :target: https://matrix.to/#/#zrepl:matrix.org
 
 .. |serve-transport| replace:: :ref:`serve specification<transport>`
 .. |connect-transport| replace:: :ref:`connect specification<transport>`

docs/index.rst

@@ -5,7 +5,7 @@
 
 .. include:: global.rst.inc
 
-|GitHub license| |Language: Go| |Twitter| |Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal|
+|GitHub license| |Language: Go| |Twitter| |Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal| |Matrix|
 
 
 zrepl - ZFS replication
@@ -25,10 +25,10 @@ zrepl - ZFS replication
          Progress: [=========================\----] 246.7 MiB / 264.7 MiB @ 11.5 MiB/s
            zroot              STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
            zroot/ROOT         DONE (step 2/2, 1.2 KiB/1.2 KiB)
-           zroot/ROOT/default STEPPING (step 1/2, 123.4 MiB/129.3 MiB) next: @a => @b
+         * zroot/ROOT/default STEPPING (step 1/2, 123.4 MiB/129.3 MiB) next: @a => @b
            zroot/tmp          STEPPING (step 1/2, 29.9 KiB/44.2 KiB) next: @a => @b
            zroot/usr          STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
-           zroot/usr/home     STEPPING (step 1/2, 123.3 MiB/135.3 MiB) next: @a => @b
+         * zroot/usr/home     STEPPING (step 1/2, 123.3 MiB/135.3 MiB) next: @a => @b
            zroot/var          STEPPING (step 1/2, 624 B/1.2 KiB) next: @a => @b
            zroot/var/audit    DONE (step 2/2, 1.2 KiB/1.2 KiB)
            zroot/var/crash    DONE (step 2/2, 1.2 KiB/1.2 KiB)
@@ -66,6 +66,7 @@ Main Features
     * [x] Large blocks send & receive
     * [x] Embedded data send & receive
     * [x] Resume state send & receive
+    * [x] Bandwidth limiting
 
 * **Automatic snapshot management**
 
@@ -136,5 +137,6 @@ Table of Contents
    pr
    changelog
    GitHub Repository & Issue Tracker <https://github.com/zrepl/zrepl>
+   Chat: Matrix <https://matrix.to/#/#zrepl:matrix.org>
    supporters
 

docs/installation/apt-repos.rst

@@ -9,18 +9,29 @@ The fingerprint of the signing key is ``E101 418F D3D6 FBCB 9D65  A62D 7086 99FC
 It is available at `<https://zrepl.cschwarz.com/apt/apt-key.asc>`_ .
 Please open an issue in on GitHub if you encounter any issues with the repository.
 
-The following snippet configure the repository for your Debian or Ubuntu release:
-
 ::
 
-    apt update && apt install curl gnupg lsb-release; \
-    ARCH="$(dpkg --print-architecture)"; \
-    CODENAME="$(lsb_release -i -s | tr '[:upper:]' '[:lower:]') $(lsb_release -c -s | tr '[:upper:]' '[:lower:]')"; \
-    echo "Using Distro and Codename: $CODENAME"; \
-    (curl https://zrepl.cschwarz.com/apt/apt-key.asc | apt-key add -) && \
-    (echo "deb [arch=$ARCH] https://zrepl.cschwarz.com/apt/$CODENAME main" > /etc/apt/sources.list.d/zrepl.list) && \
-    apt update
+    (
+    set -ex
+    zrepl_apt_key_url=https://zrepl.cschwarz.com/apt/apt-key.asc
+    zrepl_apt_key_dst=/usr/share/keyrings/zrepl.gpg
+    zrepl_apt_repo_file=/etc/apt/sources.list.d/zrepl.list
 
+    # Install dependencies for subsequent commands
+    sudo apt update && sudo apt install curl gnupg lsb-release
+
+    # Deploy the zrepl apt key.
+    curl -fsSL "$zrepl_apt_key_url" | tee | gpg --dearmor | sudo tee "$zrepl_apt_key_dst" > /dev/null
+
+    # Add the zrepl apt repo.
+    ARCH="$(dpkg --print-architecture)"
+    CODENAME="$(lsb_release -i -s | tr '[:upper:]' '[:lower:]') $(lsb_release -c -s | tr '[:upper:]' '[:lower:]')"
+    echo "Using Distro and Codename: $CODENAME"
+    echo "deb [arch=$ARCH signed-by=$zrepl_apt_key_dst] https://zrepl.cschwarz.com/apt/$CODENAME main" | sudo tee /etc/apt/sources.list.d/zrepl.list
+
+    # Update apt repos.
+    sudo apt update
+    )
 
 .. NOTE::
 

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

@@ -93,6 +93,7 @@ Enable the zrepl daemon to start automatically at boot:
 
    sysrc zrepl_enable="YES"
 
+Now jump to :ref:`the summary <installation-freebsd-jail-summary>` below.
 
 Plugin
 ######
@@ -134,7 +135,18 @@ Now ``zrepl`` can be started.
 
    service zrepl start
 
+Now jump to :ref:`the summary <installation-freebsd-jail-summary>` below.
+
+.. _installation-freebsd-jail-summary:
+
 Summary
 -------
 
 Congratulations, you have a working jail!
+
+.. NOTE::
+
+   With FreeBSD 13's transition to OpenZFS 2.0, please ensure that your jail's FreeBSD version matches the one in the kernel module.
+   If you are getting cryptic errors such as
+   ``cannot receive new filesystem stream: invalid backup stream``
+   the instructions posted `here <https://github.com/zrepl/zrepl/issues/500#issuecomment-966215205>`_ might help.

docs/publish.sh

@@ -1,6 +1,5 @@
 #!/bin/bash
-set -eo pipefail
-
+set -euo pipefail
 
 NON_INTERACTIVE=false
 DO_CLONE=false
@@ -13,7 +12,7 @@ while getopts "ca" arg; do
             DO_CLONE=true
             ;;
         *)
-            echo invalid option
+            echo "invalid option '-$arg'"
             exit 1
             ;;
     esac
@@ -27,11 +26,6 @@ checkout_repo_msg() {
     echo "clone ${GHPAGESREPO} to ${PUBLICDIR}:"
 }
 
-exit_msg() {
-    echo "error, exiting..."
-}
-trap exit_msg EXIT
-
 if ! type sphinx-versioning >/dev/null; then
     echo "install sphinx-versioning and come back"
     exit 1
@@ -71,6 +65,9 @@ git reset --hard origin/master
 
 echo "cleaning GitHub pages repo"
 git rm -rf .
+cat > .gitignore <<EOF
+**/.doctrees
+EOF
 
 popd
 
@@ -96,7 +93,13 @@ COMMIT_MSG="sphinx-versioning render from publish.sh - $(date -u) - ${CURRENT_CO
 pushd "$PUBLICDIR"
 
 echo "adding and commiting all changes in GitHub pages repo"
+git add .gitignore
 git add -A
+if [ "$(git status --porcelain)" != "" ]; then
     git commit -m "$COMMIT_MSG"
+else
+    echo "nothing to commit"
+fi
+echo "pushing to GitHub pages repo"
 git push origin master
 

docs/quickstart.rst

@@ -33,6 +33,7 @@ Keep the :ref:`full config documentation <configuration_toc>` handy if a config
 
    quickstart/continuous_server_backup
    quickstart/backup_to_external_disk
+   quickstart/fan_out_replication
 
 Use ``zrepl configcheck`` to validate your configuration.
 No output indicates that everything is fine.
@@ -51,6 +52,19 @@ We hope that you have found a configuration that fits your use case.
 Use ``zrepl configcheck`` once again to make sure the config is correct (output indicates that everything is fine).
 Then restart the zrepl daemon on all systems involved in the replication, likely using ``service zrepl restart`` or ``systemctl restart zrepl``.
 
+.. WARNING::
+
+   Please :ref:`read up carefully <prune>` on the pruning rules before applying the config.
+   In particular, note that most example configs apply to all snapshots, not just zrepl-created snapshots.
+   Use the following keep rule on sender and receiver to prevent this:
+
+   ::
+      
+      - type: regex
+        negate: true
+        regex: "^zrepl_.*" # <- the 'prefix' specified in snapshotting.prefix
+
+
 Watch it Work
 =============
 

docs/quickstart/continuous_server_backup.rst

@@ -9,13 +9,13 @@ This config example shows how we can backup our ZFS-based server to another mach
 
 * Production server ``prod`` with filesystems to back up:
 
-  * ``zroot/var/db``
-  * ``zroot/usr/home`` and all its child filesystems
-  * **except** ``zroot/usr/home/paranoid`` belonging to a user doing backups themselves
+  * The entire pool ``zroot``
+  * except ``zroot/var/tmp`` and all child datasets of it
+  * and except ``zroot/usr/home/paranoid`` which belongs to a user doing backups themselves.
 
-* Backup server ``backups`` with
+* Backup server ``backups`` with a dataset sub-tree for use by zrepl:
 
-  * Filesystem ``storage/zrepl/sink/prod`` + children dedicated to backups of ``prod``
+  * In our example, that will be ``storage/zrepl/sink/prod``.
 
 Our backup solution should fulfill the following requirements:
 

docs/quickstart/fan_out_replication.rst

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

docs/supporters.rst

@@ -32,6 +32,8 @@ We would like to thank the following people and organizations for supporting zre
 
    <div class="fa fa-code" style="width: 1em;"></div>
 
+* |supporter-gold| Prominic.NET, Inc.
+* |supporter-std| Torsten Blum
 * |supporter-gold| Cyberiada GmbH
 * |supporter-std| `Gordon Schulz <https://github.com/azmodude>`_
 * |supporter-std| `@jwittlincohen <https://github.com/jwittlincohen>`_

docs/usage.rst

@@ -78,3 +78,73 @@ Systemd Unit File
 A systemd service definition template is available in :repomasterlink:`dist/systemd`.
 Note that some of the options only work on recent versions of systemd.
 Any help & improvements are very welcome, see :issue:`145`.
+
+
+
+============
+Ops Runbooks
+============
+
+
+.. toctree::
+
+   usage/runbooks/migrating_sending_side_to_new_zpool.rst
+
+
+.. _usage-platform-tests:
+
+==============
+Platform Tests
+==============
+
+Along with the main ``zrepl`` binary, we release the ``platformtest`` binaries.
+The zrepl platform tests are an integration test suite that is complementary to the pure Go unit tests.
+Any test that needs to interact with ZFS is a platform test.
+
+The platform need to run as root.
+For each test, we create a fresh dummy zpool backed by a file-based vdev.
+The file path, and a root mountpoint for the dummy zpool, must be specified on the command line:
+
+::
+
+   mkdir -p /tmp/zreplplatformtest
+   ./platformtest \
+       -poolname 'zreplplatformtest' \  # <- name must contain zreplplatformtest
+       -imagepath /tmp/zreplplatformtest.img \ # <- zrepl will create the file
+       -mountpoint /tmp/zreplplatformtest # <- must exist
+
+
+.. WARNING::
+
+   ``platformtest`` will unconditionally overwrite the file at `imagepath`
+   and unconditionally ``zpool destroy $poolname``.
+   So, don't use a production poolname, and consider running the test in a VM.
+   It'll be a lot faster as well because the underlying operations, ``zfs list`` in particular, will be faster.
+
+
+While the platformtests are running, there will be a log of log output.
+After all tests have run, it prints a summary with a list of tests, grouped by result type (success, failure, skipped):
+
+::
+
+   PASSING TESTS:
+     github.com/zrepl/zrepl/platformtest/tests.BatchDestroy
+     github.com/zrepl/zrepl/platformtest/tests.CreateReplicationCursor
+     github.com/zrepl/zrepl/platformtest/tests.GetNonexistent
+     github.com/zrepl/zrepl/platformtest/tests.HoldsWork
+     ...
+     github.com/zrepl/zrepl/platformtest/tests.SendStreamNonEOFReadErrorHandling
+     github.com/zrepl/zrepl/platformtest/tests.UndestroyableSnapshotParsing
+   SKIPPED TESTS:
+     github.com/zrepl/zrepl/platformtest/tests.SendArgsValidationEncryptedSendOfUnencryptedDatasetForbidden__EncryptionSupported_false
+   FAILED TESTS: []
+
+
+If there is a failure, or a skipped test that you believe should be passing, re-run the test suite, capture stderr & stdout to a text file, and create an issue on GitHub.
+
+To run a specific test case, or a subset of tests matched by regex, use the ``-run REGEX`` command line flag.
+
+To stop test execution at the first failing test, and prevent cleanup of the dummy zpool, use the ``-failure.stop-and-keep-pool`` flag.
+
+To build the platformtests yourself, use ``make test-platform-bin``.
+There's also the ``make test-platform`` target to run the platform tests with a default command line.

docs/usage/runbooks/migrating_sending_side_to_new_zpool.rst

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

endpoint/endpoint.go

@@ -14,6 +14,7 @@ import (
 	"github.com/zrepl/zrepl/daemon/logging/trace"
 
 	"github.com/zrepl/zrepl/replication/logic/pdu"
+	"github.com/zrepl/zrepl/util/bandwidthlimit"
 	"github.com/zrepl/zrepl/util/chainedio"
 	"github.com/zrepl/zrepl/util/chainlock"
 	"github.com/zrepl/zrepl/util/envconst"
@@ -34,6 +35,8 @@ type SenderConfig struct {
 	SendCompressed       bool
 	SendEmbeddedData     bool
 	SendSaved            bool
+
+	BandwidthLimit bandwidthlimit.Config
 }
 
 func (c *SenderConfig) Validate() error {
@@ -44,6 +47,9 @@ func (c *SenderConfig) Validate() error {
 	if _, err := StepHoldTag(c.JobID); err != nil {
 		return fmt.Errorf("JobID cannot be used for hold tag: %s", err)
 	}
+	if err := bandwidthlimit.ValidateConfig(c.BandwidthLimit); err != nil {
+		return errors.Wrap(err, "`BandwidthLimit` field invalid")
+	}
 	return nil
 }
 
@@ -54,16 +60,21 @@ type Sender struct {
 	FSFilter zfs.DatasetFilter
 	jobId    JobID
 	config   SenderConfig
+	bwLimit  bandwidthlimit.Wrapper
 }
 
 func NewSender(conf SenderConfig) *Sender {
 	if err := conf.Validate(); err != nil {
 		panic("invalid config" + err.Error())
 	}
+
+	ratelimiter := bandwidthlimit.WrapperFromConfig(conf.BandwidthLimit)
+
 	return &Sender{
 		FSFilter: conf.FSF,
 		jobId:    conf.JobID,
 		config:   conf,
+		bwLimit:  ratelimiter,
 	}
 }
 
@@ -148,12 +159,11 @@ func sendArgsFromPDUAndValidateExistsAndGetVersion(ctx context.Context, fs strin
 	return version, nil
 }
 
-func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.ReadCloser, error) {
-	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
+func (s *Sender) sendMakeArgs(ctx context.Context, r *pdu.SendReq) (sendArgs zfs.ZFSSendArgsValidated, _ error) {
 
 	_, err := s.filterCheckFS(r.Filesystem)
 	if err != nil {
-		return nil, nil, err
+		return sendArgs, err
 	}
 	switch r.Encrypted {
 	case pdu.Tri_DontCare:
@@ -161,16 +171,16 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 		// ok, fallthrough outer
 	case pdu.Tri_False:
 		if s.config.Encrypt.B {
-			return nil, nil, errors.New("only encrypted sends allowed (send -w + encryption!= off), but unencrypted send requested")
+			return sendArgs, errors.New("only encrypted sends allowed (send -w + encryption!= off), but unencrypted send requested")
 		}
 		// fallthrough outer
 	case pdu.Tri_True:
 		if !s.config.Encrypt.B {
-			return nil, nil, errors.New("only unencrypted sends allowed, but encrypted send requested")
+			return sendArgs, errors.New("only unencrypted sends allowed, but encrypted send requested")
 		}
 		// fallthrough outer
 	default:
-		return nil, nil, fmt.Errorf("unknown pdu.Tri variant %q", r.Encrypted)
+		return sendArgs, fmt.Errorf("unknown pdu.Tri variant %q", r.Encrypted)
 	}
 
 	sendArgsUnvalidated := zfs.ZFSSendArgsUnvalidated{
@@ -190,30 +200,19 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 		},
 	}
 
-	sendArgs, err := sendArgsUnvalidated.Validate(ctx)
+	sendArgs, err = sendArgsUnvalidated.Validate(ctx)
 	if err != nil {
-		return nil, nil, errors.Wrap(err, "validate send arguments")
+		return sendArgs, errors.Wrap(err, "validate send arguments")
+	}
+	return sendArgs, nil
 }
 
-	si, err := zfs.ZFSSendDry(ctx, sendArgs)
+func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.ReadCloser, error) {
+	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
+
+	sendArgs, err := s.sendMakeArgs(ctx, r)
 	if err != nil {
-		return nil, nil, errors.Wrap(err, "zfs send dry failed")
-	}
-
-	// From now on, assume that sendArgs has been validated by ZFSSendDry
-	// (because validation involves shelling out, it's actually a little expensive)
-
-	var expSize int64 = 0      // protocol says 0 means no estimate
-	if si.SizeEstimate != -1 { // but si returns -1 for no size estimate
-		expSize = si.SizeEstimate
-	}
-	res := &pdu.SendRes{
-		ExpectedSize:    expSize,
-		UsedResumeToken: r.ResumeToken != "",
-	}
-
-	if r.DryRun {
-		return res, nil, nil
+		return nil, nil, err
 	}
 
 	// create holds or bookmarks of `From` and `To` to guarantee one of the following:
@@ -301,15 +300,47 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 		abstractionsCacheSingleton.TryBatchDestroy(ctx, s.jobId, sendArgs.FS, destroyTypes, keep, check)
 	}()
 
-	sendStream, err := zfs.ZFSSend(ctx, sendArgs)
+	var sendStream io.ReadCloser
+	sendStream, err = zfs.ZFSSend(ctx, sendArgs)
 	if err != nil {
 		// it's ok to not destroy the abstractions we just created here, a new send attempt will take care of it
 		return nil, nil, errors.Wrap(err, "zfs send failed")
 	}
 
+	// apply rate limit
+	sendStream = s.bwLimit.WrapReadCloser(sendStream)
+
+	res := &pdu.SendRes{
+		ExpectedSize:    0,
+		UsedResumeToken: r.ResumeToken != "",
+	}
+
 	return res, sendStream, nil
 }
 
+func (s *Sender) SendDry(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, error) {
+	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
+
+	sendArgs, err := s.sendMakeArgs(ctx, r)
+	if err != nil {
+		return nil, err
+	}
+
+	si, err := zfs.ZFSSendDry(ctx, sendArgs)
+	if err != nil {
+		return nil, errors.Wrap(err, "zfs send dry failed")
+	}
+
+	// From now on, assume that sendArgs has been validated by ZFSSendDry
+	// (because validation involves shelling out, it's actually a little expensive)
+
+	res := &pdu.SendRes{
+		ExpectedSize:    si.SizeEstimate,
+		UsedResumeToken: r.ResumeToken != "",
+	}
+	return res, nil
+}
+
 func (p *Sender) SendCompleted(ctx context.Context, r *pdu.SendCompletedReq) (*pdu.SendCompletedRes, error) {
 	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
 
@@ -439,8 +470,22 @@ type ReceiverConfig struct {
 
 	InheritProperties  []zfsprop.Property
 	OverrideProperties map[zfsprop.Property]string
+
+	BandwidthLimit bandwidthlimit.Config
+
+	PlaceholderEncryption PlaceholderCreationEncryptionProperty
 }
 
+//go:generate enumer -type=PlaceholderCreationEncryptionProperty -transform=kebab -trimprefix=PlaceholderCreationEncryptionProperty
+type PlaceholderCreationEncryptionProperty int
+
+// Note: the constant names, transformed through enumer, are part of the config format!
+const (
+	PlaceholderCreationEncryptionPropertyUnspecified PlaceholderCreationEncryptionProperty = 1 << iota
+	PlaceholderCreationEncryptionPropertyInherit
+	PlaceholderCreationEncryptionPropertyOff
+)
+
 func (c *ReceiverConfig) copyIn() {
 	c.RootWithoutClientComponent = c.RootWithoutClientComponent.Copy()
 
@@ -475,6 +520,15 @@ func (c *ReceiverConfig) Validate() error {
 	if c.RootWithoutClientComponent.Length() <= 0 {
 		return errors.New("RootWithoutClientComponent must not be an empty dataset path")
 	}
+
+	if err := bandwidthlimit.ValidateConfig(c.BandwidthLimit); err != nil {
+		return errors.Wrap(err, "`BandwidthLimit` field invalid")
+	}
+
+	if !c.PlaceholderEncryption.IsAPlaceholderCreationEncryptionProperty() {
+		return errors.Errorf("`PlaceholderEncryption` field is invalid")
+	}
+
 	return nil
 }
 
@@ -484,7 +538,11 @@ type Receiver struct {
 
 	conf ReceiverConfig // validated
 
+	bwLimit bandwidthlimit.Wrapper
+
 	recvParentCreationMtx *chainlock.L
+
+	Test_OverrideClientIdentityFunc func() string // for use by platformtest
 }
 
 func NewReceiver(config ReceiverConfig) *Receiver {
@@ -495,6 +553,7 @@ func NewReceiver(config ReceiverConfig) *Receiver {
 	return &Receiver{
 		conf:                  config,
 		recvParentCreationMtx: chainlock.New(),
+		bwLimit:               bandwidthlimit.WrapperFromConfig(config.BandwidthLimit),
 	}
 }
 
@@ -521,10 +580,16 @@ func (s *Receiver) clientRootFromCtx(ctx context.Context) *zfs.DatasetPath {
 		return s.conf.RootWithoutClientComponent.Copy()
 	}
 
-	clientIdentity, ok := ctx.Value(ClientIdentityKey).(string)
+	var clientIdentity string
+	if s.Test_OverrideClientIdentityFunc != nil {
+		clientIdentity = s.Test_OverrideClientIdentityFunc()
+	} else {
+		var ok bool
+		clientIdentity, ok = ctx.Value(ClientIdentityKey).(string) // no shadow
 		if !ok {
 			panic("ClientIdentityKey context value must be set")
 		}
+	}
 
 	clientRoot, err := clientRoot(s.conf.RootWithoutClientComponent, clientIdentity)
 	if err != nil {
@@ -564,7 +629,8 @@ func (s *Receiver) ListFilesystems(ctx context.Context, req *pdu.ListFilesystemR
 	if rphs, err := zfs.ZFSGetFilesystemPlaceholderState(ctx, s.conf.RootWithoutClientComponent); err != nil {
 		return nil, errors.Wrap(err, "cannot determine whether root_fs exists")
 	} else if !rphs.FSExists {
-		return nil, errors.New("root_fs does not exist")
+		getLogger(ctx).WithField("root_fs", s.conf.RootWithoutClientComponent).Error("root_fs does not exist")
+		return nil, errors.Errorf("root_fs does not exist")
 	}
 
 	root := s.clientRootFromCtx(ctx)
@@ -668,6 +734,38 @@ func (s *Receiver) Send(ctx context.Context, req *pdu.SendReq) (*pdu.SendRes, io
 	return nil, nil, fmt.Errorf("receiver does not implement Send()")
 }
 
+func (s *Receiver) SendDry(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, error) {
+	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
+	return nil, fmt.Errorf("receiver does not implement SendDry()")
+}
+
+func (s *Receiver) receive_GetPlaceholderCreationEncryptionValue(client_root, path *zfs.DatasetPath) (zfs.FilesystemPlaceholderCreateEncryptionValue, error) {
+	if !s.conf.PlaceholderEncryption.IsAPlaceholderCreationEncryptionProperty() {
+		panic(s.conf.PlaceholderEncryption)
+	}
+
+	if client_root.Equal(path) && s.conf.PlaceholderEncryption == PlaceholderCreationEncryptionPropertyUnspecified {
+		// If our Receiver is configured to append a client component to s.conf.RootWithoutClientComponent
+		// then that dataset is always going to be a placeholder.
+		// We don't want to burden users with the concept of placeholders if their `filesystems` filter on the sender
+		// doesn't introduce any gaps.
+		// Since the dataset hierarchy up to and including that client component dataset is still fully controlled by us,
+		// using `inherit` is going to make it work in all expected use cases.
+		return zfs.FilesystemPlaceholderCreateEncryptionInherit, nil
+	}
+
+	switch s.conf.PlaceholderEncryption {
+	case PlaceholderCreationEncryptionPropertyUnspecified:
+		return 0, fmt.Errorf("placeholder filesystem encryption handling is unspecified in receiver config")
+	case PlaceholderCreationEncryptionPropertyInherit:
+		return zfs.FilesystemPlaceholderCreateEncryptionInherit, nil
+	case PlaceholderCreationEncryptionPropertyOff:
+		return zfs.FilesystemPlaceholderCreateEncryptionOff, nil
+	default:
+		panic(s.conf.PlaceholderEncryption)
+	}
+}
+
 func (s *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, receive io.ReadCloser) (*pdu.ReceiveRes, error) {
 	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
 
@@ -708,15 +806,18 @@ func (s *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, receive io.
 			if v.Path.Equal(lp) {
 				return false
 			}
+
+			l := getLogger(ctx).
+				WithField("placeholder_fs", v.Path.ToString()).
+				WithField("receive_fs", lp.ToString())
+
 			ph, err := zfs.ZFSGetFilesystemPlaceholderState(ctx, v.Path)
-			getLogger(ctx).
-				WithField("fs", v.Path.ToString()).
-				WithField("placeholder_state", fmt.Sprintf("%#v", ph)).
+			l.WithField("placeholder_state", fmt.Sprintf("%#v", ph)).
 				WithField("err", fmt.Sprintf("%s", err)).
 				WithField("errType", fmt.Sprintf("%T", err)).
-				Debug("placeholder state for filesystem")
+				Debug("get placeholder state for filesystem")
 			if err != nil {
-				visitErr = err
+				visitErr = errors.Wrapf(err, "cannot get placeholder state of %s", v.Path.ToString())
 				return false
 			}
 
@@ -727,21 +828,34 @@ func (s *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, receive io.
 					} else {
 						visitErr = fmt.Errorf("root_fs %q does not exist", s.conf.RootWithoutClientComponent.ToString())
 					}
-					getLogger(ctx).WithError(visitErr).Error("placeholders are only created automatically below root_fs")
+					l.WithError(visitErr).Error("placeholders are only created automatically below root_fs")
 					return false
 				}
-				l := getLogger(ctx).WithField("placeholder_fs", v.Path)
-				l.Debug("create placeholder filesystem")
-				err := zfs.ZFSCreatePlaceholderFilesystem(ctx, v.Path, v.Parent.Path)
+
+				// compute the value lazily so that users who don't rely on
+				// placeholders can use the default value PlaceholderCreationEncryptionPropertyUnspecified
+				placeholderEncryption, err := s.receive_GetPlaceholderCreationEncryptionValue(root, v.Path)
 				if err != nil {
-					l.WithError(err).Error("cannot create placeholder filesystem")
-					visitErr = err
+					l.WithError(err).Error("cannot create placeholder filesystem") // logger already contains path
+					visitErr = errors.Wrapf(err, "cannot create placeholder filesystem %s", v.Path.ToString())
 					return false
 				}
-				return true
+
+				l := l.WithField("encryption", placeholderEncryption)
+
+				l.Debug("creating placeholder filesystem")
+				err = zfs.ZFSCreatePlaceholderFilesystem(ctx, v.Path, v.Parent.Path, placeholderEncryption)
+				if err != nil {
+					l.WithError(err).Error("cannot create placeholder filesystem") // logger already contains path
+					visitErr = errors.Wrapf(err, "cannot create placeholder filesystem %s", v.Path.ToString())
+					return false
 				}
-			getLogger(ctx).WithField("filesystem", v.Path.ToString()).Debug("exists")
+				l.Info("created placeholder filesystem")
+				return true
+			} else {
+				l.Debug("filesystem exists")
 				return true // leave this fs as is
+			}
 		})
 	}()
 	getLogger(ctx).WithField("visitErr", visitErr).Debug("complete tree-walk")
@@ -787,6 +901,9 @@ func (s *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, receive io.
 		return nil, errors.Wrap(err, "cannot determine whether we can use resumable send & recv")
 	}
 
+	// apply rate limit
+	receive = s.bwLimit.WrapReadCloser(receive)
+
 	var peek bytes.Buffer
 	var MaxPeek = envconst.Int64("ZREPL_ENDPOINT_RECV_PEEK_SIZE", 1<<20)
 	log.WithField("max_peek_bytes", MaxPeek).Info("peeking incoming stream")

endpoint/placeholdercreationencryptionproperty_enumer.go

@@ -0,0 +1,62 @@
+// Code generated by "enumer -type=PlaceholderCreationEncryptionProperty -transform=kebab -trimprefix=PlaceholderCreationEncryptionProperty"; DO NOT EDIT.
+
+//
+package endpoint
+
+import (
+	"fmt"
+)
+
+const (
+	_PlaceholderCreationEncryptionPropertyName_0 = "unspecifiedinherit"
+	_PlaceholderCreationEncryptionPropertyName_1 = "off"
+)
+
+var (
+	_PlaceholderCreationEncryptionPropertyIndex_0 = [...]uint8{0, 11, 18}
+	_PlaceholderCreationEncryptionPropertyIndex_1 = [...]uint8{0, 3}
+)
+
+func (i PlaceholderCreationEncryptionProperty) String() string {
+	switch {
+	case 1 <= i && i <= 2:
+		i -= 1
+		return _PlaceholderCreationEncryptionPropertyName_0[_PlaceholderCreationEncryptionPropertyIndex_0[i]:_PlaceholderCreationEncryptionPropertyIndex_0[i+1]]
+	case i == 4:
+		return _PlaceholderCreationEncryptionPropertyName_1
+	default:
+		return fmt.Sprintf("PlaceholderCreationEncryptionProperty(%d)", i)
+	}
+}
+
+var _PlaceholderCreationEncryptionPropertyValues = []PlaceholderCreationEncryptionProperty{1, 2, 4}
+
+var _PlaceholderCreationEncryptionPropertyNameToValueMap = map[string]PlaceholderCreationEncryptionProperty{
+	_PlaceholderCreationEncryptionPropertyName_0[0:11]:  1,
+	_PlaceholderCreationEncryptionPropertyName_0[11:18]: 2,
+	_PlaceholderCreationEncryptionPropertyName_1[0:3]:   4,
+}
+
+// PlaceholderCreationEncryptionPropertyString retrieves an enum value from the enum constants string name.
+// Throws an error if the param is not part of the enum.
+func PlaceholderCreationEncryptionPropertyString(s string) (PlaceholderCreationEncryptionProperty, error) {
+	if val, ok := _PlaceholderCreationEncryptionPropertyNameToValueMap[s]; ok {
+		return val, nil
+	}
+	return 0, fmt.Errorf("%s does not belong to PlaceholderCreationEncryptionProperty values", s)
+}
+
+// PlaceholderCreationEncryptionPropertyValues returns all values of the enum
+func PlaceholderCreationEncryptionPropertyValues() []PlaceholderCreationEncryptionProperty {
+	return _PlaceholderCreationEncryptionPropertyValues
+}
+
+// IsAPlaceholderCreationEncryptionProperty returns "true" if the value is listed in the enum definition. "false" otherwise
+func (i PlaceholderCreationEncryptionProperty) IsAPlaceholderCreationEncryptionProperty() bool {
+	for _, v := range _PlaceholderCreationEncryptionPropertyValues {
+		if i == v {
+			return true
+		}
+	}
+	return false
+}

go.mod

@@ -5,14 +5,16 @@ go 1.12
 require (
 	github.com/fatih/color v1.7.0
 	github.com/gdamore/tcell v1.2.0
+	github.com/gdamore/tcell/v2 v2.2.0
 	github.com/gitchander/permutation v0.0.0-20181107151852-9e56b92e9909
 	github.com/go-logfmt/logfmt v0.4.0
-	github.com/go-playground/universal-translator v0.17.0 // indirect
 	github.com/go-playground/validator v9.31.0+incompatible
+	github.com/go-playground/validator/v10 v10.4.1
 	github.com/go-sql-driver/mysql v1.4.1-0.20190907122137-b2c03bcae3d4
 	github.com/golang/protobuf v1.4.3
 	github.com/google/uuid v1.1.2
 	github.com/jinzhu/copier v0.0.0-20170922082739-db4671f3a9b8
+	github.com/juju/ratelimit v1.0.1
 	github.com/kisielk/gotool v1.0.0 // indirect
 	github.com/kr/pretty v0.1.0
 	github.com/leodido/go-urn v1.2.1 // indirect
@@ -37,10 +39,10 @@ require (
 	github.com/yudai/gojsondiff v0.0.0-20170107030110-7b1b7adf999d
 	github.com/yudai/golcs v0.0.0-20170316035057-ecda9a501e82 // go1.12 thinks it needs this
 	github.com/zrepl/yaml-config v0.0.0-20191220194647-cbb6b0cf4bdd
+	gitlab.com/tslocum/cview v1.5.3
 	golang.org/x/net v0.0.0-20210119194325-5f4716e94777
 	golang.org/x/sync v0.0.0-20190423024810-112230192c58
 	golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c
-	golang.org/x/text v0.3.5 // indirect
 	golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135
 	gonum.org/v1/gonum v0.7.0 // indirect
 	google.golang.org/genproto v0.0.0-20210122163508-8081c04a3579 // indirect

go.sum

@@ -46,6 +46,11 @@ github.com/gdamore/encoding v1.0.0 h1:+7OoQ1Bc6eTm5niUzBa0Ctsh6JbMW6Ra+YNuAtDBdk
 github.com/gdamore/encoding v1.0.0/go.mod h1:alR0ol34c49FCSBLjhosxzcPHQbf2trDkoo5dl+VrEg=
 github.com/gdamore/tcell v1.2.0 h1:ikixzsxc8K8o3V2/CEmyoEW8mJZaNYQQ3NP3VIQdUe4=
 github.com/gdamore/tcell v1.2.0/go.mod h1:Hjvr+Ofd+gLglo7RYKxxnzCBmev3BzsS67MebKS4zMM=
+github.com/gdamore/tcell v1.4.0 h1:vUnHwJRvcPQa3tzi+0QI4U9JINXYJlOz9yiaiPQ2wMU=
+github.com/gdamore/tcell/v2 v2.0.0-dev/go.mod h1:vSVL/GV5mCSlPC6thFP5kfOFdM9MGZcalipmpTxTgQA=
+github.com/gdamore/tcell/v2 v2.1.1-0.20201225194624-29bb185874fd/go.mod h1:vSVL/GV5mCSlPC6thFP5kfOFdM9MGZcalipmpTxTgQA=
+github.com/gdamore/tcell/v2 v2.2.0 h1:vSyEgKwraXPSOkvCk7IwOSyX+Pv3V2cV9CikJMXg4U4=
+github.com/gdamore/tcell/v2 v2.2.0/go.mod h1:cTTuF84Dlj/RqmaCIV5p4w8uG1zWdk0SF6oBpwHp4fU=
 github.com/gitchander/permutation v0.0.0-20181107151852-9e56b92e9909 h1:9NC8seTx6/zRmMTAdsHj/uOMi0EGHGQtjyLafBjk77Q=
 github.com/gitchander/permutation v0.0.0-20181107151852-9e56b92e9909/go.mod h1:lP+DW8LR6Rw3ru9Vo2/y/3iiLaLWmofYql/va+7zJOk=
 github.com/go-critic/go-critic v0.3.4/go.mod h1:AHR42Lk/E/aOznsrYdMYeIQS5RH10HZHSqP+rD6AJrc=
@@ -59,12 +64,15 @@ github.com/go-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9
 github.com/go-logfmt/logfmt v0.4.0 h1:MP4Eh7ZCb31lleYCFuwm0oe4/YGak+5l1vA2NOE80nA=
 github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk=
 github.com/go-ole/go-ole v1.2.1/go.mod h1:7FAglXiTm7HKlQRDeOQ6ZNUHidzCWXuZWq/1dTyBNF8=
+github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/locales v0.13.0 h1:HyWk6mgj5qFqCT5fjGBuRArbVDfE4hi8+e8ceBS/t7Q=
 github.com/go-playground/locales v0.13.0/go.mod h1:taPMhCMXrRLJO55olJkUXHZBHCxTMfnGwq/HNwmWNS8=
 github.com/go-playground/universal-translator v0.17.0 h1:icxd5fm+REJzpZx7ZfpaD876Lmtgy7VtROAbHHXk8no=
 github.com/go-playground/universal-translator v0.17.0/go.mod h1:UkSxE5sNxxRwHyU+Scu5vgOQjsIJAF8j9muTVoKLVtA=
 github.com/go-playground/validator v9.31.0+incompatible h1:UA72EPEogEnq76ehGdEDp4Mit+3FDh548oRqwVgNsHA=
 github.com/go-playground/validator v9.31.0+incompatible/go.mod h1:yrEkQXlcI+PugkyDjY2bRrL/UBU4f3rvrgkN3V8JEig=
+github.com/go-playground/validator/v10 v10.4.1 h1:pH2c5ADXtd66mxoE0Zm9SUhxE20r7aM3F26W0hOn+GE=
+github.com/go-playground/validator/v10 v10.4.1/go.mod h1:nlOn6nFhuKACm19sB/8EGNn9GlaMV7XkbRSipzJ0Ii4=
 github.com/go-sql-driver/mysql v1.4.1-0.20190907122137-b2c03bcae3d4 h1:0suja/iKSDbEIYLbrS/8C7iArJiWpgCNcR+zwAHu7Ig=
 github.com/go-sql-driver/mysql v1.4.1-0.20190907122137-b2c03bcae3d4/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
 github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
@@ -156,6 +164,8 @@ github.com/jinzhu/copier v0.0.0-20170922082739-db4671f3a9b8 h1:+dKzeuiDYbD/Cfi/s
 github.com/jinzhu/copier v0.0.0-20170922082739-db4671f3a9b8/go.mod h1:yL958EeXv8Ylng6IfnvG4oflryUi3vgA3xPs9hmII1s=
 github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
 github.com/json-iterator/go v1.1.7/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
+github.com/juju/ratelimit v1.0.1 h1:+7AIFJVQ0EQgq/K9+0Krm7m530Du7tIz0METWzN0RgY=
+github.com/juju/ratelimit v1.0.1/go.mod h1:qapgC/Gy+xNh9UxzV13HGGl/6UXNN+ct+vwSgWNm/qk=
 github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
 github.com/jung-kurt/gofpdf v1.0.3-0.20190309125859-24315acbbda5/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
 github.com/k0kubun/colorstring v0.0.0-20150214042306-9440f1994b88 h1:uC1QfSlInpQF+M0ao65imhwqKnz3Q2z/d8PWZRMQvDM=
@@ -177,6 +187,7 @@ github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORN
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
+github.com/leodido/go-urn v1.2.0/go.mod h1:+8+nEpDfqqsY+g338gtMEUOtuK+4dEMhiQEgxpxOKII=
 github.com/leodido/go-urn v1.2.1 h1:BqpAaACuzVSgi/VLzGZIobT2z4v53pjosyNd9Yv6n/w=
 github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
 github.com/lib/pq v1.2.0 h1:LXpIM/LZ5xGFhOpXAQUIMM1HdyqzVYM13zNdjCEEcA0=
@@ -184,6 +195,8 @@ github.com/lib/pq v1.2.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
 github.com/logrusorgru/aurora v0.0.0-20181002194514-a7b3b318ed4e/go.mod h1:7rIyQOR62GCctdiQpZ/zOJlFyk6y+94wXzv6RNZgaR4=
 github.com/lucasb-eyer/go-colorful v1.0.2 h1:mCMFu6PgSozg9tDNMMK3g18oJBX7oYGrC09mS6CXfO4=
 github.com/lucasb-eyer/go-colorful v1.0.2/go.mod h1:0MS4r+7BZKSJ5mw4/S5MPN+qHFF1fYclkSPilDOKW0s=
+github.com/lucasb-eyer/go-colorful v1.0.3 h1:QIbQXiugsb+q10B+MI+7DI1oQLdmnep86tWFlaaUAac=
+github.com/lucasb-eyer/go-colorful v1.0.3/go.mod h1:R4dSotOR9KMtayYi1e77YzuveK+i7ruzyGqttikkLy0=
 github.com/magiconair/properties v1.7.6/go.mod h1:PppfXfuXeibc/6YijjN8zIbojt8czPbwD3XqdrwzmxQ=
 github.com/magiconair/properties v1.8.0/go.mod h1:PppfXfuXeibc/6YijjN8zIbojt8czPbwD3XqdrwzmxQ=
 github.com/mattn/go-colorable v0.0.9 h1:UVL0vNpWh04HeJXV0KLcaT7r06gOH2l4OW6ddYRUIY4=
@@ -196,6 +209,10 @@ github.com/mattn/go-isatty v0.0.8 h1:HLtExJ+uU2HOZ+wI0Tt5DtUDrx8yhUqDcp7fYERX4CE
 github.com/mattn/go-isatty v0.0.8/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
 github.com/mattn/go-runewidth v0.0.4 h1:2BvfKmzob6Bmd4YsL0zygOqfdFnK7GR4QL06Do4/p7Y=
 github.com/mattn/go-runewidth v0.0.4/go.mod h1:LwmH8dsx7+W8Uxz3IHJYH5QSwggIsqBzpuz5H//U1FU=
+github.com/mattn/go-runewidth v0.0.7/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
+github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
+github.com/mattn/go-runewidth v0.0.10 h1:CoZ3S2P7pvtP45xOtBw+/mDL2z0RKI576gSkzRRpdGg=
+github.com/mattn/go-runewidth v0.0.10/go.mod h1:RAqKPSqVFrSLVXbA8x7dzmKdmGzieGRCM46jaSJTDAk=
 github.com/mattn/goveralls v0.0.2/go.mod h1:8d1ZMHsd7fW6IRPKQh46F2WRpyib5/X4FOpevwGNQEw=
 github.com/matttproud/golang_protobuf_extensions v1.0.0/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
 github.com/matttproud/golang_protobuf_extensions v1.0.1 h1:4hp9jkHxhMHkqkrB3Ix0jegS5sx/RkqARlsWZ6pIwiU=
@@ -264,6 +281,9 @@ github.com/prometheus/procfs v0.0.2/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsT
 github.com/prometheus/procfs v0.0.5 h1:3+auTFlqw+ZaQYJARz6ArODtkaIwtvBTx3N2NehQlL8=
 github.com/prometheus/procfs v0.0.5/go.mod h1:4A/X28fw3Fc593LaREMrKMqOKvUAntwMDaekg4FpcdQ=
 github.com/quasilyte/go-consistent v0.0.0-20190521200055-c6f3937de18c/go.mod h1:5STLWrekHfjyYwxBRVRXNOSewLJ3PWfDJd1VyTS21fI=
+github.com/rivo/uniseg v0.1.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
+github.com/rivo/uniseg v0.2.0 h1:S1pD9weZBuJdFmowNwbpi7BJ8TNftyUImj/0WQi72jY=
+github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rogpeppe/go-internal v1.1.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/rogpeppe/go-internal v1.2.1/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/ryanuber/go-glob v0.0.0-20170128012129-256dc444b735/go.mod h1:807d1WSdnB0XRJzKNil9Om6lcp/3a0v4qIHxIXzX/Yc=
@@ -332,11 +352,17 @@ github.com/zrepl/yaml-config v0.0.0-20190928121844-af7ca3f8448f/go.mod h1:JmNwis
 github.com/zrepl/yaml-config v0.0.0-20191220194647-cbb6b0cf4bdd h1:SSo67WLS+99QESvbW8Meibz7zCrxshP71U9dH5KOCXM=
 github.com/zrepl/yaml-config v0.0.0-20191220194647-cbb6b0cf4bdd/go.mod h1:JmNwisZzOvW4GfpfLvhZ+gtyKLsIiA+WC+wNKJGJaFg=
 github.com/zrepl/zrepl v0.2.0/go.mod h1:M3Zv2IGSO8iYpUjsZD6ayZ2LHy7zyMfzet9XatKOrZ8=
+gitlab.com/tslocum/cbind v0.1.4 h1:cbZXPPcieXspk8cShoT6efz7HAT8yMNQcofYWNizis4=
+gitlab.com/tslocum/cbind v0.1.4/go.mod h1:RvwYE3auSjBNlCmWeGspzn+jdLUVQ8C2QGC+0nP9ChI=
+gitlab.com/tslocum/cview v1.5.3 h1:6OTCtIUp1EkfGeLqQFRHtW8ynMJ66BhoBwuW8oZ84AQ=
+gitlab.com/tslocum/cview v1.5.3/go.mod h1:k/eLWRIF3B26VLDgtRRPkjLUXmcCsy+YCSPEAtNQgIY=
 golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20181203042331-505ab145d0a9/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20190313024323-a1f597ede03a/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20190325154230-a5d413f7728c/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9 h1:psW17arqaxU48Z5kZ0CQnkZWQJsqcURM6tKiBApRjXI=
+golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20180807140117-3d87b88a115f/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
@@ -357,6 +383,7 @@ golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73r
 golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190313220215-9f648a60d977/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190613194153-d28f0bde5980 h1:dfGZHvZk057jK2MCeWus/TowKpJ8y4AmooUzdBSR9GU=
 golang.org/x/net v0.0.0-20190613194153-d28f0bde5980/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20210119194325-5f4716e94777 h1:003p0dJM77cxMSyCPFphvZf/Y5/NXf5fzg6ufd1/Oew=
@@ -376,6 +403,7 @@ golang.org/x/sys v0.0.0-20181205085412-a5c9d58dba9a/go.mod h1:STP8DvDyc/dI5b8T5h
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190626150813-e07cf5db2756 h1:9nuHUbU8dRnRRfj9KjWUVrJeoexdbeMjttk6Oh1rD10=
 golang.org/x/sys v0.0.0-20190626150813-e07cf5db2756/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -383,10 +411,14 @@ golang.org/x/sys v0.0.0-20191010194322-b09406accb47 h1:/XfQ9z7ib8eEJX2hdgFTZJ/nt
 golang.org/x/sys v0.0.0-20191010194322-b09406accb47/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191026070338-33540a1f6037 h1:YyJpGZS1sBuBCzLAR1VEpK193GlqGZbnPFnPV/5Rsb4=
 golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20201013132646-2da7054afaeb/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210113181707-4bcb84eeeb78/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c h1:VwygUrnw9jn88c4u8GD3rZQbqrP/tgas88tPUbBxQrk=
 golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20201210144234-2321bbc49cbf h1:MZ2shdL+ZM/XzY3ZGOnh4Nlpnxz5GSOhOmtHo3iPU6M=
+golang.org/x/term v0.0.0-20201210144234-2321bbc49cbf/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.0.0-20170915090833-1cbadb444a80/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.0 h1:g61tztE5qeGQ89tm6NTjjM9VPIm088od1l6aSorWRWg=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=

main.go

@@ -4,12 +4,13 @@ package main
 import (
 	"github.com/zrepl/zrepl/cli"
 	"github.com/zrepl/zrepl/client"
+	"github.com/zrepl/zrepl/client/status"
 	"github.com/zrepl/zrepl/daemon"
 )
 
 func init() {
 	cli.AddSubcommand(daemon.DaemonCmd)
-	cli.AddSubcommand(client.StatusCmd)
+	cli.AddSubcommand(status.Subcommand)
 	cli.AddSubcommand(client.SignalCmd)
 	cli.AddSubcommand(client.StdinserverCmd)
 	cli.AddSubcommand(client.ConfigcheckCmd)

packaging/deb/Dockerfile

@@ -1,9 +1,13 @@
 FROM debian:latest
 
+# binutils are for cross-compilation to work in bullseye
 RUN apt-get update && apt-get install -y \
 	build-essential \
     devscripts \
-    dh-exec
+    dh-exec \
+	binutils-aarch64-linux-gnu \
+	binutils-arm-linux-gnueabihf  \
+	binutils-i686-linux-gnu
 
 RUN mkdir -p /build/src && chmod -R 0777 /build
 

platformtest/harness/harness.go

@@ -37,6 +37,7 @@ func main() {
 	flag.StringVar(&args.CreateArgs.Mountpoint, "mountpoint", "", "")
 	flag.BoolVar(&args.StopAndKeepPoolOnFail, "failure.stop-and-keep-pool", false, "if a test case fails, stop test execution and keep pool as it was when the test failed")
 	flag.StringVar(&args.Run, "run", "", "")
+	flag.DurationVar(&platformtest.ZpoolExportTimeout, "zfs.zpool-export-timeout", platformtest.ZpoolExportTimeout, "")
 	flag.Parse()
 
 	if err := HarnessRun(args); err != nil {

platformtest/platformtest_zpool.go

@@ -5,12 +5,17 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"runtime"
+	"strings"
+	"time"
 
 	"github.com/pkg/errors"
 
 	"github.com/zrepl/zrepl/zfs"
 )
 
+var ZpoolExportTimeout time.Duration = 500 * time.Millisecond
+
 type Zpool struct {
 	args ZpoolCreateArgs
 }
@@ -93,9 +98,24 @@ func (p *Zpool) Name() string { return p.args.PoolName }
 
 func (p *Zpool) Destroy(ctx context.Context, e Execer) error {
 
-	if err := e.RunExpectSuccessNoOutput(ctx, "zpool", "export", p.args.PoolName); err != nil {
+	exportDeadline := time.Now().Add(ZpoolExportTimeout)
+
+	for {
+		if time.Now().After(exportDeadline) {
+			return errors.Errorf("could not zpool export (got 'pool is busy'): %s", p.args.PoolName)
+		}
+		err := e.RunExpectSuccessNoOutput(ctx, "zpool", "export", p.args.PoolName)
+		if err == nil {
+			break
+		}
+		if strings.Contains(err.Error(), "pool is busy") {
+			runtime.Gosched()
+			continue
+		}
+		if err != nil {
 			return errors.Wrapf(err, "export pool %q", p.args.PoolName)
 		}
+	}
 
 	if err := os.Remove(p.args.ImagePath); err != nil {
 		return errors.Wrapf(err, "remove pool image")

platformtest/tests/generated_cases.go

@@ -24,6 +24,9 @@ var Cases = []Case{BatchDestroy,
 	ReplicationIsResumableFullSend__both_GuaranteeResumability,
 	ReplicationIsResumableFullSend__initial_GuaranteeIncrementalReplication_incremental_GuaranteeIncrementalReplication,
 	ReplicationIsResumableFullSend__initial_GuaranteeResumability_incremental_GuaranteeIncrementalReplication,
+	ReplicationPlaceholderEncryption__EncryptOnReceiverUseCase__WorksIfConfiguredWithInherit,
+	ReplicationPlaceholderEncryption__UnspecifiedIsOkForClientIdentityPlaceholder,
+	ReplicationPlaceholderEncryption__UnspecifiedLeadsToFailureAtRuntimeWhenCreatingPlaceholders,
 	ReplicationPropertyReplicationWorks,
 	ReplicationReceiverErrorWhileStillSending,
 	ReplicationStepCompletedLostBehavior__GuaranteeIncrementalReplication,
@@ -34,5 +37,10 @@ var Cases = []Case{BatchDestroy,
 	SendArgsValidationEncryptedSendOfUnencryptedDatasetForbidden__EncryptionSupported_true,
 	SendArgsValidationResumeTokenDifferentFilesystemForbidden,
 	SendArgsValidationResumeTokenEncryptionMismatchForbidden,
+	SendStreamCloseAfterBlockedOnPipeWrite,
+	SendStreamCloseAfterEOFRead,
+	SendStreamMultipleCloseAfterEOF,
+	SendStreamMultipleCloseBeforeEOF,
+	SendStreamNonEOFReadErrorHandling,
 	UndestroyableSnapshotParsing,
 }

platformtest/tests/helpers.go

@@ -10,6 +10,7 @@ import (
 
 	"github.com/stretchr/testify/require"
 
+	"github.com/zrepl/zrepl/daemon/filters"
 	"github.com/zrepl/zrepl/platformtest"
 	"github.com/zrepl/zrepl/util/limitio"
 	"github.com/zrepl/zrepl/zfs"
@@ -174,3 +175,8 @@ func datasetToStringSortedTrimPrefix(prefix *zfs.DatasetPath, paths []*zfs.Datas
 	sort.Strings(pstrs)
 	return pstrs
 }
+
+func mustAddToSFilter(ctx *platformtest.Context, f *filters.DatasetMapFilter, fs string) {
+	err := f.Add(fs, "ok")
+	require.NoError(ctx, err)
+}

platformtest/tests/recvRollback.go

@@ -40,6 +40,7 @@ func ReceiveForceRollbackWorksUnencrypted(ctx *platformtest.Context) {
 
 	sendStream, err := zfs.ZFSSend(ctx, sendArgs)
 	require.NoError(ctx, err)
+	defer sendStream.Close()
 
 	recvOpts := zfs.RecvOptions{
 		RollbackAndForceRecv: true,

platformtest/tests/replication.go

@@ -7,6 +7,7 @@ import (
 	"os"
 	"path"
 	"sort"
+	"strings"
 	"time"
 
 	"github.com/kr/pretty"
@@ -20,6 +21,7 @@ import (
 	"github.com/zrepl/zrepl/replication/logic"
 	"github.com/zrepl/zrepl/replication/logic/pdu"
 	"github.com/zrepl/zrepl/replication/report"
+	"github.com/zrepl/zrepl/util/bandwidthlimit"
 	"github.com/zrepl/zrepl/util/limitio"
 	"github.com/zrepl/zrepl/util/nodefault"
 	"github.com/zrepl/zrepl/zfs"
@@ -66,6 +68,7 @@ func (i replicationInvocation) Do(ctx *platformtest.Context) *report.Report {
 		FSF:            i.sfilter.AsFilter(),
 		Encrypt:        &nodefault.Bool{B: false},
 		JobID:          i.sjid,
+		BandwidthLimit: bandwidthlimit.NoLimitConfig(),
 	}
 	if i.senderConfigHook != nil {
 		i.senderConfigHook(&senderConfig)
@@ -75,6 +78,8 @@ func (i replicationInvocation) Do(ctx *platformtest.Context) *report.Report {
 		JobID:                      i.rjid,
 		AppendClientIdentity:       false,
 		RootWithoutClientComponent: mustDatasetPath(i.rfsRoot),
+		BandwidthLimit:             bandwidthlimit.NoLimitConfig(),
+		PlaceholderEncryption:      endpoint.PlaceholderCreationEncryptionPropertyUnspecified,
 	}
 	if i.receiverConfigHook != nil {
 		i.receiverConfigHook(&receiverConfig)
@@ -90,6 +95,7 @@ func (i replicationInvocation) Do(ctx *platformtest.Context) *report.Report {
 		ReplicationConfig: &pdu.ReplicationConfig{
 			Protection: i.guarantee,
 		},
+		SizeEstimationConcurrency: 1,
 	}
 
 	report, wait := replication.Do(
@@ -804,13 +810,22 @@ type NeverEndingSender struct {
 	*endpoint.Sender
 }
 
+func (s *NeverEndingSender) SendDry(ctx context.Context, req *pdu.SendReq) (r *pdu.SendRes, err error) {
+	r, _, err = s.sendImpl(ctx, req, true)
+	return r, err
+}
+
 func (s *NeverEndingSender) Send(ctx context.Context, req *pdu.SendReq) (r *pdu.SendRes, stream io.ReadCloser, _ error) {
+	return s.sendImpl(ctx, req, false)
+}
+
+func (s *NeverEndingSender) sendImpl(ctx context.Context, req *pdu.SendReq, dry bool) (r *pdu.SendRes, stream io.ReadCloser, _ error) {
 	stream = nil
 	r = &pdu.SendRes{
 		UsedResumeToken: false,
 		ExpectedSize:    1 << 30,
 	}
-	if req.DryRun {
+	if dry {
 		return r, stream, nil
 	}
 	dz, err := os.Open("/dev/zero")
@@ -889,13 +904,9 @@ func ReplicationFailingInitialParentProhibitsChildReplication(ctx *platformtest.
 	fsAA := ctx.RootDataset + "/sender/aa"
 
 	sfilter := filters.NewDatasetMapFilter(3, true)
-	mustAddToSFilter := func(fs string) {
-		err := sfilter.Add(fs, "ok")
-		require.NoError(ctx, err)
-	}
-	mustAddToSFilter(fsA)
-	mustAddToSFilter(fsAChild)
-	mustAddToSFilter(fsAA)
+	mustAddToSFilter(ctx, sfilter, fsA)
+	mustAddToSFilter(ctx, sfilter, fsAChild)
+	mustAddToSFilter(ctx, sfilter, fsAA)
 	rfsRoot := ctx.RootDataset + "/receiver"
 
 	mockRecvErr := fmt.Errorf("yifae4ohPhaquaes0hohghiep9oufie4roo7quoWooluaj2ee8")
@@ -951,6 +962,7 @@ func ReplicationPropertyReplicationWorks(ctx *platformtest.Context) {
 		+  "sender/a/child"
 		+  "sender/a/child@1"
 		+  "receiver"
+		R  zfs create -p "${ROOTDS}/receiver/${ROOTDS}/sender"
 	`)
 
 	sjid := endpoint.MustMakeJobID("sender-job")
@@ -960,12 +972,8 @@ func ReplicationPropertyReplicationWorks(ctx *platformtest.Context) {
 	fsAChild := ctx.RootDataset + "/sender/a/child"
 
 	sfilter := filters.NewDatasetMapFilter(2, true)
-	mustAddToSFilter := func(fs string) {
-		err := sfilter.Add(fs, "ok")
-		require.NoError(ctx, err)
-	}
-	mustAddToSFilter(fsA)
-	mustAddToSFilter(fsAChild)
+	mustAddToSFilter(ctx, sfilter, fsA)
+	mustAddToSFilter(ctx, sfilter, fsAChild)
 	rfsRoot := ctx.RootDataset + "/receiver"
 
 	type testPropExpectation struct {
@@ -1054,6 +1062,9 @@ func ReplicationPropertyReplicationWorks(ctx *platformtest.Context) {
 		rep := fsByName[fs]
 		require.Len(ctx, rep.Steps, 1)
 		require.Nil(ctx, rep.PlanError)
+		if rep.StepError != nil && strings.Contains(rep.StepError.Error(), "invalid option 'x'") {
+			ctx.SkipNow() // XXX feature detection
+		}
 		require.Nil(ctx, rep.StepError)
 		require.Len(ctx, rep.Steps, 1)
 		require.Equal(ctx, 1, rep.CurrentStep)
@@ -1090,3 +1101,208 @@ func ReplicationPropertyReplicationWorks(ctx *platformtest.Context) {
 		}
 	}
 }
+
+func ReplicationPlaceholderEncryption__UnspecifiedLeadsToFailureAtRuntimeWhenCreatingPlaceholders(ctx *platformtest.Context) {
+
+	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
+		CREATEROOT
+		+  "sender"
+		+  "sender/a"
+		+  "sender/a/child"
+		+  "receiver"
+		R  zfs snapshot -r ${ROOTDS}/sender@initial
+	`)
+
+	sjid := endpoint.MustMakeJobID("sender-job")
+	rjid := endpoint.MustMakeJobID("receiver-job")
+
+	childfs := ctx.RootDataset + "/sender/a/child"
+
+	sfilter := filters.NewDatasetMapFilter(3, true)
+
+	mustAddToSFilter(ctx, sfilter, childfs)
+	rfsRoot := ctx.RootDataset + "/receiver"
+
+	rep := replicationInvocation{
+		sjid:      sjid,
+		rjid:      rjid,
+		sfilter:   sfilter,
+		rfsRoot:   rfsRoot,
+		guarantee: pdu.ReplicationConfigProtectionWithKind(pdu.ReplicationGuaranteeKind_GuaranteeResumability),
+		receiverConfigHook: func(rc *endpoint.ReceiverConfig) {
+			rc.PlaceholderEncryption = endpoint.PlaceholderCreationEncryptionPropertyUnspecified
+		},
+	}
+
+	r := rep.Do(ctx)
+	ctx.Logf("\n%s", pretty.Sprint(r))
+
+	require.Len(ctx, r.Attempts, 1)
+	attempt := r.Attempts[0]
+	require.Nil(ctx, attempt.PlanError)
+	require.Len(ctx, attempt.Filesystems, 1)
+
+	afs := attempt.Filesystems[0]
+	require.Equal(ctx, childfs, afs.Info.Name)
+
+	require.Equal(ctx, 1, len(afs.Steps))
+	require.Equal(ctx, 0, afs.CurrentStep)
+
+	require.Equal(ctx, report.FilesystemSteppingErrored, afs.State)
+
+	childfsFirstComponent := strings.Split(childfs, "/")[0]
+	require.Contains(ctx, afs.StepError.Err, "cannot create placeholder filesystem "+rfsRoot+"/"+childfsFirstComponent+": placeholder filesystem encryption handling is unspecified in receiver config")
+}
+
+type ClientIdentityReceiver struct {
+	clientIdentity string
+	*endpoint.Receiver
+}
+
+func (r *ClientIdentityReceiver) Receive(ctx context.Context, req *pdu.ReceiveReq, stream io.ReadCloser) (*pdu.ReceiveRes, error) {
+	ctx = context.WithValue(ctx, endpoint.ClientIdentityKey, r.clientIdentity)
+	return r.Receiver.Receive(ctx, req, stream)
+}
+
+func ReplicationPlaceholderEncryption__UnspecifiedIsOkForClientIdentityPlaceholder(ctx *platformtest.Context) {
+	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
+		CREATEROOT
+		+  "receiver"
+	`)
+
+	sjid := endpoint.MustMakeJobID("sender-job")
+	rjid := endpoint.MustMakeJobID("receiver-job")
+
+	sfilter := filters.NewDatasetMapFilter(1, true)
+
+	// hacky...
+	comps := strings.Split(ctx.RootDataset, "/")
+	require.GreaterOrEqual(ctx, len(comps), 2)
+	pool := comps[0]
+	require.Contains(ctx, pool, "zreplplatformtest", "don't want to cause accidents")
+	poolchild := pool + "/" + comps[1]
+
+	err := zfs.ZFSSnapshot(ctx, mustDatasetPath(pool), "testsnap", false)
+	require.NoError(ctx, err)
+
+	err = zfs.ZFSSnapshot(ctx, mustDatasetPath(poolchild), "testsnap", false)
+	require.NoError(ctx, err)
+
+	mustAddToSFilter(ctx, sfilter, pool)
+	mustAddToSFilter(ctx, sfilter, poolchild)
+
+	clientIdentity := "testclientid"
+
+	rfsRoot := ctx.RootDataset + "/receiver"
+
+	rep := replicationInvocation{
+		sjid:      sjid,
+		rjid:      rjid,
+		sfilter:   sfilter,
+		rfsRoot:   rfsRoot,
+		guarantee: pdu.ReplicationConfigProtectionWithKind(pdu.ReplicationGuaranteeKind_GuaranteeResumability),
+		receiverConfigHook: func(rc *endpoint.ReceiverConfig) {
+			rc.PlaceholderEncryption = endpoint.PlaceholderCreationEncryptionPropertyUnspecified
+			rc.AppendClientIdentity = true
+		},
+		interceptReceiver: func(r *endpoint.Receiver) logic.Receiver {
+			r.Test_OverrideClientIdentityFunc = func() string { return clientIdentity }
+			return r
+		},
+	}
+
+	r := rep.Do(ctx)
+	ctx.Logf("\n%s", pretty.Sprint(r))
+
+	require.Len(ctx, r.Attempts, 1)
+	attempt := r.Attempts[0]
+	require.Nil(ctx, attempt.PlanError)
+	require.Len(ctx, attempt.Filesystems, 2)
+
+	filesystemsByName := make(map[string]*report.FilesystemReport)
+	for _, fs := range attempt.Filesystems {
+		filesystemsByName[fs.Info.Name] = fs
+	}
+	require.Len(ctx, filesystemsByName, len(attempt.Filesystems))
+
+	afs, ok := filesystemsByName[pool]
+	require.True(ctx, ok)
+	require.Nil(ctx, afs.PlanError)
+	require.Nil(ctx, afs.StepError)
+	require.Equal(ctx, report.FilesystemDone, afs.State)
+
+	afs, ok = filesystemsByName[poolchild]
+	require.True(ctx, ok)
+	require.Nil(ctx, afs.PlanError)
+	require.Nil(ctx, afs.StepError)
+	require.Equal(ctx, report.FilesystemDone, afs.State)
+
+	mustGetFilesystemVersion(ctx, rfsRoot+"/"+clientIdentity+"/"+pool+"@testsnap")
+	mustGetFilesystemVersion(ctx, rfsRoot+"/"+clientIdentity+"/"+poolchild+"@testsnap")
+
+}
+
+func replicationPlaceholderEncryption__EncryptOnReceiverUseCase__impl(ctx *platformtest.Context, placeholderEncryption endpoint.PlaceholderCreationEncryptionProperty) {
+
+	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
+		CREATEROOT
+		+  "sender"
+		+  "sender/a"
+		+  "sender/a/child"
+		+  "receiver" encrypted
+		R  zfs snapshot -r ${ROOTDS}/sender@initial
+	`)
+
+	sjid := endpoint.MustMakeJobID("sender-job")
+	rjid := endpoint.MustMakeJobID("receiver-job")
+
+	childfs := ctx.RootDataset + "/sender/a/child"
+
+	sfilter := filters.NewDatasetMapFilter(3, true)
+
+	mustAddToSFilter(ctx, sfilter, childfs)
+	rfsRoot := ctx.RootDataset + "/receiver"
+
+	rep := replicationInvocation{
+		sjid:      sjid,
+		rjid:      rjid,
+		sfilter:   sfilter,
+		rfsRoot:   rfsRoot,
+		guarantee: pdu.ReplicationConfigProtectionWithKind(pdu.ReplicationGuaranteeKind_GuaranteeResumability),
+		receiverConfigHook: func(rc *endpoint.ReceiverConfig) {
+			rc.PlaceholderEncryption = placeholderEncryption
+			rc.AppendClientIdentity = false
+		},
+	}
+
+	r := rep.Do(ctx)
+	ctx.Logf("\n%s", pretty.Sprint(r))
+
+	require.Len(ctx, r.Attempts, 1)
+	attempt := r.Attempts[0]
+	require.Equal(ctx, report.AttemptDone, attempt.State)
+	require.Len(ctx, attempt.Filesystems, 1)
+	afs := attempt.Filesystems[0]
+	require.Equal(ctx, childfs, afs.Info.Name)
+
+	require.Equal(ctx, 1, len(afs.Steps))
+
+	rfs := mustDatasetPath(rfsRoot + "/" + childfs)
+	mustGetFilesystemVersion(ctx, rfs.ToString()+"@initial")
+}
+
+func ReplicationPlaceholderEncryption__EncryptOnReceiverUseCase__WorksIfConfiguredWithInherit(ctx *platformtest.Context) {
+	placeholderEncryption := endpoint.PlaceholderCreationEncryptionPropertyInherit
+
+	replicationPlaceholderEncryption__EncryptOnReceiverUseCase__impl(ctx, placeholderEncryption)
+	childfs := ctx.RootDataset + "/sender/a/child"
+	rfsRoot := ctx.RootDataset + "/receiver"
+	rfs := mustDatasetPath(rfsRoot + "/" + childfs)
+
+	// The leaf child dataset should be inhering from rfsRoot.
+	// If we had replicated with PlaceholderCreationEncryptionPropertyOff
+	// then it would be unencrypted and inherit from the placeholder.
+	props, err := zfs.ZFSGet(ctx, rfs, []string{"encryptionroot"})
+	require.NoError(ctx, err)
+	require.Equal(ctx, rfsRoot, props.Get("encryptionroot"))
+}

platformtest/tests/sendStream.go

@@ -0,0 +1,186 @@
+package tests
+
+import (
+	"fmt"
+	"io"
+	"io/ioutil"
+	"os"
+	"os/exec"
+	"path"
+	"syscall"
+	"time"
+
+	"github.com/stretchr/testify/require"
+	"golang.org/x/sys/unix"
+
+	"github.com/zrepl/zrepl/platformtest"
+	"github.com/zrepl/zrepl/util/nodefault"
+	"github.com/zrepl/zrepl/zfs"
+)
+
+func sendStreamTest(ctx *platformtest.Context) *zfs.SendStream {
+
+	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
+		DESTROYROOT
+		CREATEROOT
+		+  "sender"
+	`)
+
+	fs := fmt.Sprintf("%s/sender", ctx.RootDataset)
+
+	fsmpo, err := zfs.ZFSGetMountpoint(ctx, fs)
+	require.NoError(ctx, err)
+
+	writeDummyData(path.Join(fsmpo.Mountpoint, "dummy.data"), 1<<26)
+	mustSnapshot(ctx, fs+"@1")
+	snap := fsversion(ctx, fs, "@1")
+	snapSendArg := snap.ToSendArgVersion()
+
+	sendArgs, err := zfs.ZFSSendArgsUnvalidated{
+		FS:   fs,
+		From: nil,
+		To:   &snapSendArg,
+		ZFSSendFlags: zfs.ZFSSendFlags{
+			Encrypted: &nodefault.Bool{B: false},
+		},
+	}.Validate(ctx)
+	require.NoError(ctx, err)
+
+	sendStream, err := zfs.ZFSSend(ctx, sendArgs)
+	require.NoError(ctx, err)
+
+	return sendStream
+
+}
+
+func SendStreamCloseAfterBlockedOnPipeWrite(ctx *platformtest.Context) {
+
+	sendStream := sendStreamTest(ctx)
+
+	// let the pipe buffer fill and the zfs process block uninterruptibly
+
+	ctx.Logf("waiting for pipe write to block")
+	time.Sleep(5 * time.Second) // XXX need a platform-neutral way to detect that the pipe is full and the writer is blocked
+
+	ctx.Logf("closing send stream")
+	err := sendStream.Close() // this is what this test case is about
+	ctx.Logf("close error: %T %s", err, err)
+	require.NoError(ctx, err)
+
+	exitErrZfsError := sendStream.TestOnly_ExitErr()
+	require.Contains(ctx, exitErrZfsError.Error(), "signal")
+	require.Error(ctx, exitErrZfsError)
+	exitErr, ok := exitErrZfsError.WaitErr.(*exec.ExitError)
+	require.True(ctx, ok)
+	if exitErr.Exited() {
+		// some ZFS impls (FreeBSD 12) behaves that way
+		return
+	}
+
+	// ProcessState is only available after exit
+	// => use as proxy that the process was wait()ed upon and is gone
+	ctx.Logf("%#v", exitErr.ProcessState)
+	require.NotNil(ctx, exitErr.ProcessState)
+	// and let's verify that the process got killed, so that we know it was the call to .Close() above
+	waitStatus := exitErr.ProcessState.Sys().(syscall.WaitStatus)
+	ctx.Logf("wait status: %#v", waitStatus)
+	ctx.Logf("exit status: %v", waitStatus.ExitStatus())
+	require.True(ctx, waitStatus.Signaled())
+	switch waitStatus.Signal() {
+	case unix.SIGKILL:
+		fallthrough
+	case unix.SIGPIPE:
+		// ok
+
+	default:
+		ctx.Errorf("%T %s\n%v", waitStatus.Signal(), waitStatus.Signal(), waitStatus.Signal())
+		ctx.FailNow()
+	}
+}
+
+func SendStreamCloseAfterEOFRead(ctx *platformtest.Context) {
+
+	sendStream := sendStreamTest(ctx)
+
+	_, err := io.Copy(ioutil.Discard, sendStream)
+	require.NoError(ctx, err)
+
+	var buf [128]byte
+	n, err := sendStream.Read(buf[:])
+	require.Zero(ctx, n)
+	require.Equal(ctx, io.EOF, err)
+
+	err = sendStream.Close()
+	require.NoError(ctx, err)
+
+	n, err = sendStream.Read(buf[:])
+	require.Zero(ctx, n)
+	require.Equal(ctx, os.ErrClosed, err, "same read error should be returned")
+}
+
+func SendStreamMultipleCloseAfterEOF(ctx *platformtest.Context) {
+
+	sendStream := sendStreamTest(ctx)
+
+	_, err := io.Copy(ioutil.Discard, sendStream)
+	require.NoError(ctx, err)
+
+	var buf [128]byte
+	n, err := sendStream.Read(buf[:])
+	require.Zero(ctx, n)
+	require.Equal(ctx, io.EOF, err)
+
+	err = sendStream.Close()
+	require.NoError(ctx, err)
+
+	err = sendStream.Close()
+	require.Equal(ctx, os.ErrClosed, err)
+}
+
+func SendStreamMultipleCloseBeforeEOF(ctx *platformtest.Context) {
+
+	sendStream := sendStreamTest(ctx)
+
+	err := sendStream.Close()
+	require.NoError(ctx, err)
+
+	err = sendStream.Close()
+	require.Equal(ctx, os.ErrClosed, err)
+}
+
+type failingReadCloser struct {
+	err error
+}
+
+var _ io.ReadCloser = &failingReadCloser{}
+
+func (c *failingReadCloser) Read(p []byte) (int, error) { return 0, c.err }
+func (c *failingReadCloser) Close() error               { return c.err }
+
+func SendStreamNonEOFReadErrorHandling(ctx *platformtest.Context) {
+
+	sendStream := sendStreamTest(ctx)
+
+	var buf [128]byte
+	n, err := sendStream.Read(buf[:])
+	require.Equal(ctx, len(buf), n)
+	require.NoError(ctx, err)
+
+	var mockError = fmt.Errorf("taeghaefow4piesahwahjocu7ul5tiachaiLipheijae8ooZ8Pies8shohGee9feeTeirai5aiFeiyaecai4kiaLoh4azeih0tea")
+	mock := &failingReadCloser{err: mockError}
+	orig := sendStream.TestOnly_ReplaceStdoutReader(mock)
+
+	n, err = sendStream.Read(buf[:])
+	require.Equal(ctx, 0, n)
+	require.Equal(ctx, mockError, err)
+
+	if sendStream.TestOnly_ReplaceStdoutReader(orig) != mock {
+		panic("incorrect test impl")
+	}
+
+	err = sendStream.Close()
+	require.NoError(ctx, err) // if we can't kill the child then this will be a flaky test, but let's assume we can kill the child
+
+	err = sendStream.Close()
+	require.Equal(ctx, os.ErrClosed, err)
+}

pruning/keep_last_n.go

@@ -57,6 +57,11 @@ func (k KeepLastN) KeepRule(snaps []Snapshot) (destroyList []Snapshot) {
 		// then lexicographically descending (e.g. b, a)
 		return strings.Compare(matching[i].Name(), matching[j].Name()) == 1
 	})
-	destroyList = append(destroyList, matching[k.n:]...)
+
+	n := k.n
+	if n > len(matching) {
+		n = len(matching)
+	}
+	destroyList = append(destroyList, matching[n:]...)
 	return destroyList
 }

pruning/keep_last_n_test.go

@@ -83,6 +83,19 @@ func TestKeepLastN(t *testing.T) {
 				"b1": true,
 			},
 		},
+		"keep_more_than_matching": {
+			inputs: []Snapshot{
+				stubSnap{"a1", false, o(10)},
+				stubSnap{"b1", false, o(11)},
+				stubSnap{"a2", false, o(12)},
+			},
+			rules: []KeepRule{
+				MustKeepLastN(3, "a"),
+			},
+			expDestroy: map[string]bool{
+				"b1": true,
+			},
+		},
 	}
 
 	testTable(tcs, t)

replication/driver/replication_driver.go

@@ -151,6 +151,8 @@ type fs struct {
 
 	l *chainlock.L
 
+	blockedOn report.FsBlockedOn
+
 	// ordering relationship that must be maintained for initial replication
 	initialRepOrd struct {
 		parents, children []*fs
@@ -158,6 +160,7 @@ type fs struct {
 	}
 
 	planning struct {
+		waitingForStepQueue bool
 		done                bool
 		err                 *timedError
 	}
@@ -339,6 +342,7 @@ func (a *attempt) doGlobalPlanning(ctx context.Context, prev *attempt) map[*fs]*
 		fs := &fs{
 			fs:        pfs,
 			l:         a.l,
+			blockedOn: report.FsBlockedOnNothing,
 		}
 		fs.initialRepOrd.parentDidUpdate = make(chan struct{}, 1)
 		a.fss = append(a.fss, fs)
@@ -448,6 +452,10 @@ func (a *attempt) doFilesystems(ctx context.Context, prevs map[*fs]*fs) {
 			ctx, endTask := trace.WithTaskAndSpan(ctx, "repl-fs", f.report().Info.Name)
 			defer endTask()
 			f.do(ctx, stepQueue, prevs[f])
+			f.l.HoldWhile(func() {
+				// every return from f means it's unblocked...
+				f.blockedOn = report.FsBlockedOnNothing
+			})
 		}(f)
 	}
 	a.l.DropWhile(func() {
@@ -486,11 +494,16 @@ func (f *fs) do(ctx context.Context, pq *stepQueue, prev *fs) {
 	var psteps []Step
 	var errTime time.Time
 	var err error
+	f.blockedOn = report.FsBlockedOnPlanningStepQueue
 	f.l.DropWhile(func() {
 		// TODO hacky
 		// choose target time that is earlier than any snapshot, so fs planning is always prioritized
 		targetDate := time.Unix(0, 0)
 		defer pq.WaitReady(ctx, f, targetDate)()
+		f.l.HoldWhile(func() {
+			// transition before we call PlanFS
+			f.blockedOn = report.FsBlockedOnNothing
+		})
 		psteps, err = f.fs.PlanFS(ctx) // no shadow
 		errTime = time.Now()           // no shadow
 	})
@@ -545,6 +558,7 @@ func (f *fs) do(ctx context.Context, pq *stepQueue, prev *fs) {
 	f.planning.done = true
 
 	// wait for parents' initial replication
+	f.blockedOn = report.FsBlockedOnParentInitialRepl
 	var parents []string
 	for _, p := range f.initialRepOrd.parents {
 		parents = append(parents, p.fs.ReportInfo().Name)
@@ -613,7 +627,6 @@ func (f *fs) do(ctx context.Context, pq *stepQueue, prev *fs) {
 			select {
 			case <-ctx.Done():
 				f.planned.stepErr = newTimedError(ctx.Err(), time.Now())
-				return
 			case <-f.initialRepOrd.parentDidUpdate:
 				// loop
 			}
@@ -631,7 +644,9 @@ func (f *fs) do(ctx context.Context, pq *stepQueue, prev *fs) {
 		f.l.DropWhile(func() {
 			// wait for parallel replication
 			targetDate := s.step.TargetDate()
+			f.l.HoldWhile(func() { f.blockedOn = report.FsBlockedOnReplStepQueue })
 			defer pq.WaitReady(ctx, f, targetDate)()
+			f.l.HoldWhile(func() { f.blockedOn = report.FsBlockedOnNothing })
 			// do the step
 			ctx, endSpan := trace.WithSpan(ctx, fmt.Sprintf("%#v", s.step.ReportInfo()))
 			defer endSpan()
@@ -725,6 +740,7 @@ func (f *fs) report() *report.FilesystemReport {
 	r := &report.FilesystemReport{
 		Info:        f.fs.ReportInfo(),
 		State:       state,
+		BlockedOn:   f.blockedOn,
 		PlanError:   f.planning.err.IntoReportError(),
 		StepError:   f.planned.stepErr.IntoReportError(),
 		Steps:       make([]*report.StepReport, len(f.planned.steps)),

replication/driver/replication_stepqueue_test.go

@@ -14,11 +14,12 @@ import (
 	"github.com/stretchr/testify/assert"
 
 	"github.com/zrepl/zrepl/daemon/logging/trace"
+	"github.com/zrepl/zrepl/util/zreplcircleci"
 )
 
-// FIXME: this test relies on timing and is thus rather flaky
-// (relies on scheduler responsiveness of < 500ms)
 func TestPqNotconcurrent(t *testing.T) {
+	zreplcircleci.SkipOnCircleCI(t, "because it relies on scheduler responsiveness < 500ms")
+
 	ctx, end := trace.WithTaskFromStack(context.Background())
 	defer end()
 	var ctr uint32
@@ -90,6 +91,8 @@ func (r record) String() string {
 // Hence, perform some statistics on the wakeup times and assert that the mean wakeup
 // times for each step are close together.
 func TestPqConcurrent(t *testing.T) {
+	zreplcircleci.SkipOnCircleCI(t, "because it relies on scheduler responsiveness < 500ms")
+
 	ctx, end := trace.WithTaskFromStack(context.Background())
 	defer end()
 

replication/logic/pdu/pdu.pb.go

@@ -518,8 +518,7 @@ type SendReq struct {
 	// encoded in the ResumeToken. Otherwise, the Sender MUST return an error.
 	ResumeToken       string             `protobuf:"bytes,4,opt,name=ResumeToken,proto3" json:"ResumeToken,omitempty"`
 	Encrypted         Tri                `protobuf:"varint,5,opt,name=Encrypted,proto3,enum=Tri" json:"Encrypted,omitempty"`
-	DryRun            bool               `protobuf:"varint,6,opt,name=DryRun,proto3" json:"DryRun,omitempty"`
-	ReplicationConfig *ReplicationConfig `protobuf:"bytes,7,opt,name=ReplicationConfig,proto3" json:"ReplicationConfig,omitempty"`
+	ReplicationConfig *ReplicationConfig `protobuf:"bytes,6,opt,name=ReplicationConfig,proto3" json:"ReplicationConfig,omitempty"`
 }
 
 func (x *SendReq) Reset() {
@@ -589,13 +588,6 @@ func (x *SendReq) GetEncrypted() Tri {
 	return Tri_DontCare
 }
 
-func (x *SendReq) GetDryRun() bool {
-	if x != nil {
-		return x.DryRun
-	}
-	return false
-}
-
 func (x *SendReq) GetReplicationConfig() *ReplicationConfig {
 	if x != nil {
 		return x.ReplicationConfig
@@ -766,12 +758,11 @@ type SendRes struct {
 	unknownFields protoimpl.UnknownFields
 
 	// Whether the resume token provided in the request has been used or not.
-	// If the SendReq.ResumeToken == "", this field has no meaning.
-	UsedResumeToken bool `protobuf:"varint,2,opt,name=UsedResumeToken,proto3" json:"UsedResumeToken,omitempty"`
+	// If the SendReq.ResumeToken == "", this field MUST be false.
+	UsedResumeToken bool `protobuf:"varint,1,opt,name=UsedResumeToken,proto3" json:"UsedResumeToken,omitempty"`
 	// Expected stream size determined by dry run, not exact.
 	// 0 indicates that for the given SendReq, no size estimate could be made.
-	ExpectedSize int64       `protobuf:"varint,3,opt,name=ExpectedSize,proto3" json:"ExpectedSize,omitempty"`
-	Properties   []*Property `protobuf:"bytes,4,rep,name=Properties,proto3" json:"Properties,omitempty"`
+	ExpectedSize uint64 `protobuf:"varint,2,opt,name=ExpectedSize,proto3" json:"ExpectedSize,omitempty"`
 }
 
 func (x *SendRes) Reset() {
@@ -813,20 +804,13 @@ func (x *SendRes) GetUsedResumeToken() bool {
 	return false
 }
 
-func (x *SendRes) GetExpectedSize() int64 {
+func (x *SendRes) GetExpectedSize() uint64 {
 	if x != nil {
 		return x.ExpectedSize
 	}
 	return 0
 }
 
-func (x *SendRes) GetProperties() []*Property {
-	if x != nil {
-		return x.Properties
-	}
-	return nil
-}
-
 type SendCompletedReq struct {
 	state         protoimpl.MessageState
 	sizeCache     protoimpl.SizeCache
@@ -1443,7 +1427,7 @@ var file_pdu_proto_rawDesc = []byte{
 	0x72, 0x65, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x22, 0x29, 0x0a, 0x0b, 0x56, 0x65, 0x72, 0x73, 0x69,
 	0x6f, 0x6e, 0x54, 0x79, 0x70, 0x65, 0x12, 0x0c, 0x0a, 0x08, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68,
 	0x6f, 0x74, 0x10, 0x00, 0x12, 0x0c, 0x0a, 0x08, 0x42, 0x6f, 0x6f, 0x6b, 0x6d, 0x61, 0x72, 0x6b,
-	0x10, 0x01, 0x22, 0x95, 0x02, 0x0a, 0x07, 0x53, 0x65, 0x6e, 0x64, 0x52, 0x65, 0x71, 0x12, 0x1e,
+	0x10, 0x01, 0x22, 0xfd, 0x01, 0x0a, 0x07, 0x53, 0x65, 0x6e, 0x64, 0x52, 0x65, 0x71, 0x12, 0x1e,
 	0x0a, 0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x18, 0x01, 0x20, 0x01,
 	0x28, 0x09, 0x52, 0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x12, 0x26,
 	0x0a, 0x04, 0x46, 0x72, 0x6f, 0x6d, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x46,
@@ -1455,122 +1439,119 @@ var file_pdu_proto_rawDesc = []byte{
 	0x0b, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x12, 0x22, 0x0a, 0x09,
 	0x45, 0x6e, 0x63, 0x72, 0x79, 0x70, 0x74, 0x65, 0x64, 0x18, 0x05, 0x20, 0x01, 0x28, 0x0e, 0x32,
 	0x04, 0x2e, 0x54, 0x72, 0x69, 0x52, 0x09, 0x45, 0x6e, 0x63, 0x72, 0x79, 0x70, 0x74, 0x65, 0x64,
-	0x12, 0x16, 0x0a, 0x06, 0x44, 0x72, 0x79, 0x52, 0x75, 0x6e, 0x18, 0x06, 0x20, 0x01, 0x28, 0x08,
-	0x52, 0x06, 0x44, 0x72, 0x79, 0x52, 0x75, 0x6e, 0x12, 0x40, 0x0a, 0x11, 0x52, 0x65, 0x70, 0x6c,
-	0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x18, 0x07, 0x20,
-	0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f,
-	0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x52, 0x11, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61,
-	0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x22, 0x51, 0x0a, 0x11, 0x52, 0x65,
-	0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x12,
-	0x3c, 0x0a, 0x0a, 0x70, 0x72, 0x6f, 0x74, 0x65, 0x63, 0x74, 0x69, 0x6f, 0x6e, 0x18, 0x01, 0x20,
-	0x01, 0x28, 0x0b, 0x32, 0x1c, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f,
-	0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x50, 0x72, 0x6f, 0x74, 0x65, 0x63, 0x74, 0x69, 0x6f,
-	0x6e, 0x52, 0x0a, 0x70, 0x72, 0x6f, 0x74, 0x65, 0x63, 0x74, 0x69, 0x6f, 0x6e, 0x22, 0x8f, 0x01,
-	0x0a, 0x1b, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e,
-	0x66, 0x69, 0x67, 0x50, 0x72, 0x6f, 0x74, 0x65, 0x63, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x33, 0x0a,
-	0x07, 0x49, 0x6e, 0x69, 0x74, 0x69, 0x61, 0x6c, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0e, 0x32, 0x19,
-	0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x47, 0x75, 0x61, 0x72,
-	0x61, 0x6e, 0x74, 0x65, 0x65, 0x4b, 0x69, 0x6e, 0x64, 0x52, 0x07, 0x49, 0x6e, 0x69, 0x74, 0x69,
-	0x61, 0x6c, 0x12, 0x3b, 0x0a, 0x0b, 0x49, 0x6e, 0x63, 0x72, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x61,
-	0x6c, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0e, 0x32, 0x19, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63,
-	0x61, 0x74, 0x69, 0x6f, 0x6e, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x4b, 0x69,
-	0x6e, 0x64, 0x52, 0x0b, 0x49, 0x6e, 0x63, 0x72, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x61, 0x6c, 0x22,
-	0x34, 0x0a, 0x08, 0x50, 0x72, 0x6f, 0x70, 0x65, 0x72, 0x74, 0x79, 0x12, 0x12, 0x0a, 0x04, 0x4e,
-	0x61, 0x6d, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x4e, 0x61, 0x6d, 0x65, 0x12,
-	0x14, 0x0a, 0x05, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05,
-	0x56, 0x61, 0x6c, 0x75, 0x65, 0x22, 0x82, 0x01, 0x0a, 0x07, 0x53, 0x65, 0x6e, 0x64, 0x52, 0x65,
-	0x73, 0x12, 0x28, 0x0a, 0x0f, 0x55, 0x73, 0x65, 0x64, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x54,
-	0x6f, 0x6b, 0x65, 0x6e, 0x18, 0x02, 0x20, 0x01, 0x28, 0x08, 0x52, 0x0f, 0x55, 0x73, 0x65, 0x64,
-	0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x12, 0x22, 0x0a, 0x0c, 0x45,
-	0x78, 0x70, 0x65, 0x63, 0x74, 0x65, 0x64, 0x53, 0x69, 0x7a, 0x65, 0x18, 0x03, 0x20, 0x01, 0x28,
-	0x03, 0x52, 0x0c, 0x45, 0x78, 0x70, 0x65, 0x63, 0x74, 0x65, 0x64, 0x53, 0x69, 0x7a, 0x65, 0x12,
-	0x29, 0x0a, 0x0a, 0x50, 0x72, 0x6f, 0x70, 0x65, 0x72, 0x74, 0x69, 0x65, 0x73, 0x18, 0x04, 0x20,
-	0x03, 0x28, 0x0b, 0x32, 0x09, 0x2e, 0x50, 0x72, 0x6f, 0x70, 0x65, 0x72, 0x74, 0x79, 0x52, 0x0a,
-	0x50, 0x72, 0x6f, 0x70, 0x65, 0x72, 0x74, 0x69, 0x65, 0x73, 0x22, 0x3e, 0x0a, 0x10, 0x53, 0x65,
-	0x6e, 0x64, 0x43, 0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x52, 0x65, 0x71, 0x12, 0x2a,
-	0x0a, 0x0b, 0x4f, 0x72, 0x69, 0x67, 0x69, 0x6e, 0x61, 0x6c, 0x52, 0x65, 0x71, 0x18, 0x02, 0x20,
-	0x01, 0x28, 0x0b, 0x32, 0x08, 0x2e, 0x53, 0x65, 0x6e, 0x64, 0x52, 0x65, 0x71, 0x52, 0x0b, 0x4f,
-	0x72, 0x69, 0x67, 0x69, 0x6e, 0x61, 0x6c, 0x52, 0x65, 0x71, 0x22, 0x12, 0x0a, 0x10, 0x53, 0x65,
-	0x6e, 0x64, 0x43, 0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x52, 0x65, 0x73, 0x22, 0xbe,
-	0x01, 0x0a, 0x0a, 0x52, 0x65, 0x63, 0x65, 0x69, 0x76, 0x65, 0x52, 0x65, 0x71, 0x12, 0x1e, 0x0a,
-	0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x18, 0x01, 0x20, 0x01, 0x28,
-	0x09, 0x52, 0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x12, 0x22, 0x0a,
-	0x02, 0x54, 0x6f, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x46, 0x69, 0x6c, 0x65,
-	0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x52, 0x02, 0x54,
-	0x6f, 0x12, 0x2a, 0x0a, 0x10, 0x43, 0x6c, 0x65, 0x61, 0x72, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65,
-	0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x18, 0x03, 0x20, 0x01, 0x28, 0x08, 0x52, 0x10, 0x43, 0x6c, 0x65,
-	0x61, 0x72, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x12, 0x40, 0x0a,
+	0x12, 0x40, 0x0a, 0x11, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43,
+	0x6f, 0x6e, 0x66, 0x69, 0x67, 0x18, 0x06, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x52, 0x65,
+	0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x52,
 	0x11, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66,
-	0x69, 0x67, 0x18, 0x04, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69,
-	0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x52, 0x11, 0x52, 0x65,
-	0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x22,
-	0x0c, 0x0a, 0x0a, 0x52, 0x65, 0x63, 0x65, 0x69, 0x76, 0x65, 0x52, 0x65, 0x73, 0x22, 0x67, 0x0a,
-	0x13, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74,
-	0x73, 0x52, 0x65, 0x71, 0x12, 0x1e, 0x0a, 0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74,
-	0x65, 0x6d, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79,
-	0x73, 0x74, 0x65, 0x6d, 0x12, 0x30, 0x0a, 0x09, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74,
-	0x73, 0x18, 0x02, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79,
-	0x73, 0x74, 0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x52, 0x09, 0x53, 0x6e, 0x61,
-	0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x22, 0x5a, 0x0a, 0x12, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f,
-	0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x52, 0x65, 0x73, 0x12, 0x2e, 0x0a, 0x08,
-	0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12,
-	0x2e, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69,
-	0x6f, 0x6e, 0x52, 0x08, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x12, 0x14, 0x0a, 0x05,
-	0x45, 0x72, 0x72, 0x6f, 0x72, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x45, 0x72, 0x72,
-	0x6f, 0x72, 0x22, 0x44, 0x0a, 0x13, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61,
-	0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x52, 0x65, 0x73, 0x12, 0x2d, 0x0a, 0x07, 0x52, 0x65, 0x73,
-	0x75, 0x6c, 0x74, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x13, 0x2e, 0x44, 0x65, 0x73,
-	0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x52, 0x65, 0x73, 0x52,
-	0x07, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x73, 0x22, 0x36, 0x0a, 0x14, 0x52, 0x65, 0x70, 0x6c,
-	0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x75, 0x72, 0x73, 0x6f, 0x72, 0x52, 0x65, 0x71,
+	0x69, 0x67, 0x22, 0x51, 0x0a, 0x11, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f,
+	0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x12, 0x3c, 0x0a, 0x0a, 0x70, 0x72, 0x6f, 0x74, 0x65,
+	0x63, 0x74, 0x69, 0x6f, 0x6e, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x1c, 0x2e, 0x52, 0x65,
+	0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x50,
+	0x72, 0x6f, 0x74, 0x65, 0x63, 0x74, 0x69, 0x6f, 0x6e, 0x52, 0x0a, 0x70, 0x72, 0x6f, 0x74, 0x65,
+	0x63, 0x74, 0x69, 0x6f, 0x6e, 0x22, 0x8f, 0x01, 0x0a, 0x1b, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63,
+	0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x50, 0x72, 0x6f, 0x74, 0x65,
+	0x63, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x33, 0x0a, 0x07, 0x49, 0x6e, 0x69, 0x74, 0x69, 0x61, 0x6c,
+	0x18, 0x01, 0x20, 0x01, 0x28, 0x0e, 0x32, 0x19, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61,
+	0x74, 0x69, 0x6f, 0x6e, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x4b, 0x69, 0x6e,
+	0x64, 0x52, 0x07, 0x49, 0x6e, 0x69, 0x74, 0x69, 0x61, 0x6c, 0x12, 0x3b, 0x0a, 0x0b, 0x49, 0x6e,
+	0x63, 0x72, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x61, 0x6c, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0e, 0x32,
+	0x19, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x47, 0x75, 0x61,
+	0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x4b, 0x69, 0x6e, 0x64, 0x52, 0x0b, 0x49, 0x6e, 0x63, 0x72,
+	0x65, 0x6d, 0x65, 0x6e, 0x74, 0x61, 0x6c, 0x22, 0x34, 0x0a, 0x08, 0x50, 0x72, 0x6f, 0x70, 0x65,
+	0x72, 0x74, 0x79, 0x12, 0x12, 0x0a, 0x04, 0x4e, 0x61, 0x6d, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28,
+	0x09, 0x52, 0x04, 0x4e, 0x61, 0x6d, 0x65, 0x12, 0x14, 0x0a, 0x05, 0x56, 0x61, 0x6c, 0x75, 0x65,
+	0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x22, 0x57, 0x0a,
+	0x07, 0x53, 0x65, 0x6e, 0x64, 0x52, 0x65, 0x73, 0x12, 0x28, 0x0a, 0x0f, 0x55, 0x73, 0x65, 0x64,
+	0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x18, 0x01, 0x20, 0x01, 0x28,
+	0x08, 0x52, 0x0f, 0x55, 0x73, 0x65, 0x64, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x54, 0x6f, 0x6b,
+	0x65, 0x6e, 0x12, 0x22, 0x0a, 0x0c, 0x45, 0x78, 0x70, 0x65, 0x63, 0x74, 0x65, 0x64, 0x53, 0x69,
+	0x7a, 0x65, 0x18, 0x02, 0x20, 0x01, 0x28, 0x04, 0x52, 0x0c, 0x45, 0x78, 0x70, 0x65, 0x63, 0x74,
+	0x65, 0x64, 0x53, 0x69, 0x7a, 0x65, 0x22, 0x3e, 0x0a, 0x10, 0x53, 0x65, 0x6e, 0x64, 0x43, 0x6f,
+	0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x52, 0x65, 0x71, 0x12, 0x2a, 0x0a, 0x0b, 0x4f, 0x72,
+	0x69, 0x67, 0x69, 0x6e, 0x61, 0x6c, 0x52, 0x65, 0x71, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0b, 0x32,
+	0x08, 0x2e, 0x53, 0x65, 0x6e, 0x64, 0x52, 0x65, 0x71, 0x52, 0x0b, 0x4f, 0x72, 0x69, 0x67, 0x69,
+	0x6e, 0x61, 0x6c, 0x52, 0x65, 0x71, 0x22, 0x12, 0x0a, 0x10, 0x53, 0x65, 0x6e, 0x64, 0x43, 0x6f,
+	0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x52, 0x65, 0x73, 0x22, 0xbe, 0x01, 0x0a, 0x0a, 0x52,
+	0x65, 0x63, 0x65, 0x69, 0x76, 0x65, 0x52, 0x65, 0x71, 0x12, 0x1e, 0x0a, 0x0a, 0x46, 0x69, 0x6c,
+	0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0a, 0x46,
+	0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x12, 0x22, 0x0a, 0x02, 0x54, 0x6f, 0x18,
+	0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74,
+	0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x52, 0x02, 0x54, 0x6f, 0x12, 0x2a, 0x0a,
+	0x10, 0x43, 0x6c, 0x65, 0x61, 0x72, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x54, 0x6f, 0x6b, 0x65,
+	0x6e, 0x18, 0x03, 0x20, 0x01, 0x28, 0x08, 0x52, 0x10, 0x43, 0x6c, 0x65, 0x61, 0x72, 0x52, 0x65,
+	0x73, 0x75, 0x6d, 0x65, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x12, 0x40, 0x0a, 0x11, 0x52, 0x65, 0x70,
+	0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x18, 0x04,
+	0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69,
+	0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x52, 0x11, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63,
+	0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x22, 0x0c, 0x0a, 0x0a, 0x52,
+	0x65, 0x63, 0x65, 0x69, 0x76, 0x65, 0x52, 0x65, 0x73, 0x22, 0x67, 0x0a, 0x13, 0x44, 0x65, 0x73,
+	0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x52, 0x65, 0x71,
 	0x12, 0x1e, 0x0a, 0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x18, 0x01,
 	0x20, 0x01, 0x28, 0x09, 0x52, 0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d,
-	0x22, 0x54, 0x0a, 0x14, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43,
-	0x75, 0x72, 0x73, 0x6f, 0x72, 0x52, 0x65, 0x73, 0x12, 0x14, 0x0a, 0x04, 0x47, 0x75, 0x69, 0x64,
-	0x18, 0x01, 0x20, 0x01, 0x28, 0x04, 0x48, 0x00, 0x52, 0x04, 0x47, 0x75, 0x69, 0x64, 0x12, 0x1c,
-	0x0a, 0x08, 0x4e, 0x6f, 0x74, 0x65, 0x78, 0x69, 0x73, 0x74, 0x18, 0x02, 0x20, 0x01, 0x28, 0x08,
-	0x48, 0x00, 0x52, 0x08, 0x4e, 0x6f, 0x74, 0x65, 0x78, 0x69, 0x73, 0x74, 0x42, 0x08, 0x0a, 0x06,
-	0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x23, 0x0a, 0x07, 0x50, 0x69, 0x6e, 0x67, 0x52, 0x65,
-	0x71, 0x12, 0x18, 0x0a, 0x07, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x18, 0x01, 0x20, 0x01,
-	0x28, 0x09, 0x52, 0x07, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x1d, 0x0a, 0x07, 0x50,
-	0x69, 0x6e, 0x67, 0x52, 0x65, 0x73, 0x12, 0x12, 0x0a, 0x04, 0x45, 0x63, 0x68, 0x6f, 0x18, 0x01,
-	0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x45, 0x63, 0x68, 0x6f, 0x2a, 0x28, 0x0a, 0x03, 0x54, 0x72,
-	0x69, 0x12, 0x0c, 0x0a, 0x08, 0x44, 0x6f, 0x6e, 0x74, 0x43, 0x61, 0x72, 0x65, 0x10, 0x00, 0x12,
-	0x09, 0x0a, 0x05, 0x46, 0x61, 0x6c, 0x73, 0x65, 0x10, 0x01, 0x12, 0x08, 0x0a, 0x04, 0x54, 0x72,
-	0x75, 0x65, 0x10, 0x02, 0x2a, 0x86, 0x01, 0x0a, 0x18, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61,
-	0x74, 0x69, 0x6f, 0x6e, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x4b, 0x69, 0x6e,
-	0x64, 0x12, 0x14, 0x0a, 0x10, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x49, 0x6e,
-	0x76, 0x61, 0x6c, 0x69, 0x64, 0x10, 0x00, 0x12, 0x19, 0x0a, 0x15, 0x47, 0x75, 0x61, 0x72, 0x61,
-	0x6e, 0x74, 0x65, 0x65, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x61, 0x62, 0x69, 0x6c, 0x69, 0x74, 0x79,
-	0x10, 0x01, 0x12, 0x23, 0x0a, 0x1f, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x49,
-	0x6e, 0x63, 0x72, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x61, 0x6c, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63,
-	0x61, 0x74, 0x69, 0x6f, 0x6e, 0x10, 0x02, 0x12, 0x14, 0x0a, 0x10, 0x47, 0x75, 0x61, 0x72, 0x61,
-	0x6e, 0x74, 0x65, 0x65, 0x4e, 0x6f, 0x74, 0x68, 0x69, 0x6e, 0x67, 0x10, 0x03, 0x32, 0xf0, 0x02,
-	0x0a, 0x0b, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x1a, 0x0a,
-	0x04, 0x50, 0x69, 0x6e, 0x67, 0x12, 0x08, 0x2e, 0x50, 0x69, 0x6e, 0x67, 0x52, 0x65, 0x71, 0x1a,
-	0x08, 0x2e, 0x50, 0x69, 0x6e, 0x67, 0x52, 0x65, 0x73, 0x12, 0x39, 0x0a, 0x0f, 0x4c, 0x69, 0x73,
-	0x74, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x73, 0x12, 0x12, 0x2e, 0x4c,
-	0x69, 0x73, 0x74, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x52, 0x65, 0x71,
-	0x1a, 0x12, 0x2e, 0x4c, 0x69, 0x73, 0x74, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65,
-	0x6d, 0x52, 0x65, 0x73, 0x12, 0x50, 0x0a, 0x16, 0x4c, 0x69, 0x73, 0x74, 0x46, 0x69, 0x6c, 0x65,
-	0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x1a,
-	0x2e, 0x4c, 0x69, 0x73, 0x74, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x56,
-	0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x73, 0x52, 0x65, 0x71, 0x1a, 0x1a, 0x2e, 0x4c, 0x69, 0x73,
+	0x12, 0x30, 0x0a, 0x09, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x18, 0x02, 0x20,
+	0x03, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d,
+	0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x52, 0x09, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f,
+	0x74, 0x73, 0x22, 0x5a, 0x0a, 0x12, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61,
+	0x70, 0x73, 0x68, 0x6f, 0x74, 0x52, 0x65, 0x73, 0x12, 0x2e, 0x0a, 0x08, 0x53, 0x6e, 0x61, 0x70,
+	0x73, 0x68, 0x6f, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x46, 0x69, 0x6c,
+	0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x52, 0x08,
+	0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x12, 0x14, 0x0a, 0x05, 0x45, 0x72, 0x72, 0x6f,
+	0x72, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x45, 0x72, 0x72, 0x6f, 0x72, 0x22, 0x44,
+	0x0a, 0x13, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f,
+	0x74, 0x73, 0x52, 0x65, 0x73, 0x12, 0x2d, 0x0a, 0x07, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x73,
+	0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x13, 0x2e, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f, 0x79,
+	0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x52, 0x65, 0x73, 0x52, 0x07, 0x52, 0x65, 0x73,
+	0x75, 0x6c, 0x74, 0x73, 0x22, 0x36, 0x0a, 0x14, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74,
+	0x69, 0x6f, 0x6e, 0x43, 0x75, 0x72, 0x73, 0x6f, 0x72, 0x52, 0x65, 0x71, 0x12, 0x1e, 0x0a, 0x0a,
+	0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09,
+	0x52, 0x0a, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x22, 0x54, 0x0a, 0x14,
+	0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x75, 0x72, 0x73, 0x6f,
+	0x72, 0x52, 0x65, 0x73, 0x12, 0x14, 0x0a, 0x04, 0x47, 0x75, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01,
+	0x28, 0x04, 0x48, 0x00, 0x52, 0x04, 0x47, 0x75, 0x69, 0x64, 0x12, 0x1c, 0x0a, 0x08, 0x4e, 0x6f,
+	0x74, 0x65, 0x78, 0x69, 0x73, 0x74, 0x18, 0x02, 0x20, 0x01, 0x28, 0x08, 0x48, 0x00, 0x52, 0x08,
+	0x4e, 0x6f, 0x74, 0x65, 0x78, 0x69, 0x73, 0x74, 0x42, 0x08, 0x0a, 0x06, 0x52, 0x65, 0x73, 0x75,
+	0x6c, 0x74, 0x22, 0x23, 0x0a, 0x07, 0x50, 0x69, 0x6e, 0x67, 0x52, 0x65, 0x71, 0x12, 0x18, 0x0a,
+	0x07, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x07,
+	0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x1d, 0x0a, 0x07, 0x50, 0x69, 0x6e, 0x67, 0x52,
+	0x65, 0x73, 0x12, 0x12, 0x0a, 0x04, 0x45, 0x63, 0x68, 0x6f, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09,
+	0x52, 0x04, 0x45, 0x63, 0x68, 0x6f, 0x2a, 0x28, 0x0a, 0x03, 0x54, 0x72, 0x69, 0x12, 0x0c, 0x0a,
+	0x08, 0x44, 0x6f, 0x6e, 0x74, 0x43, 0x61, 0x72, 0x65, 0x10, 0x00, 0x12, 0x09, 0x0a, 0x05, 0x46,
+	0x61, 0x6c, 0x73, 0x65, 0x10, 0x01, 0x12, 0x08, 0x0a, 0x04, 0x54, 0x72, 0x75, 0x65, 0x10, 0x02,
+	0x2a, 0x86, 0x01, 0x0a, 0x18, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e,
+	0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x4b, 0x69, 0x6e, 0x64, 0x12, 0x14, 0x0a,
+	0x10, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x49, 0x6e, 0x76, 0x61, 0x6c, 0x69,
+	0x64, 0x10, 0x00, 0x12, 0x19, 0x0a, 0x15, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65,
+	0x52, 0x65, 0x73, 0x75, 0x6d, 0x61, 0x62, 0x69, 0x6c, 0x69, 0x74, 0x79, 0x10, 0x01, 0x12, 0x23,
+	0x0a, 0x1f, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65, 0x49, 0x6e, 0x63, 0x72, 0x65,
+	0x6d, 0x65, 0x6e, 0x74, 0x61, 0x6c, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f,
+	0x6e, 0x10, 0x02, 0x12, 0x14, 0x0a, 0x10, 0x47, 0x75, 0x61, 0x72, 0x61, 0x6e, 0x74, 0x65, 0x65,
+	0x4e, 0x6f, 0x74, 0x68, 0x69, 0x6e, 0x67, 0x10, 0x03, 0x32, 0x8f, 0x03, 0x0a, 0x0b, 0x52, 0x65,
+	0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x1a, 0x0a, 0x04, 0x50, 0x69, 0x6e,
+	0x67, 0x12, 0x08, 0x2e, 0x50, 0x69, 0x6e, 0x67, 0x52, 0x65, 0x71, 0x1a, 0x08, 0x2e, 0x50, 0x69,
+	0x6e, 0x67, 0x52, 0x65, 0x73, 0x12, 0x39, 0x0a, 0x0f, 0x4c, 0x69, 0x73, 0x74, 0x46, 0x69, 0x6c,
+	0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x73, 0x12, 0x12, 0x2e, 0x4c, 0x69, 0x73, 0x74, 0x46,
+	0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x52, 0x65, 0x71, 0x1a, 0x12, 0x2e, 0x4c,
+	0x69, 0x73, 0x74, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x52, 0x65, 0x73,
+	0x12, 0x50, 0x0a, 0x16, 0x4c, 0x69, 0x73, 0x74, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74,
+	0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x1a, 0x2e, 0x4c, 0x69, 0x73,
 	0x74, 0x46, 0x69, 0x6c, 0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69,
-	0x6f, 0x6e, 0x73, 0x52, 0x65, 0x73, 0x12, 0x3e, 0x0a, 0x10, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f,
-	0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x12, 0x14, 0x2e, 0x44, 0x65, 0x73,
-	0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x52, 0x65, 0x71,
-	0x1a, 0x14, 0x2e, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68,
-	0x6f, 0x74, 0x73, 0x52, 0x65, 0x73, 0x12, 0x41, 0x0a, 0x11, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63,
-	0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x75, 0x72, 0x73, 0x6f, 0x72, 0x12, 0x15, 0x2e, 0x52, 0x65,
-	0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x75, 0x72, 0x73, 0x6f, 0x72, 0x52,
-	0x65, 0x71, 0x1a, 0x15, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e,
-	0x43, 0x75, 0x72, 0x73, 0x6f, 0x72, 0x52, 0x65, 0x73, 0x12, 0x35, 0x0a, 0x0d, 0x53, 0x65, 0x6e,
-	0x64, 0x43, 0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x12, 0x11, 0x2e, 0x53, 0x65, 0x6e,
-	0x64, 0x43, 0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x52, 0x65, 0x71, 0x1a, 0x11, 0x2e,
-	0x53, 0x65, 0x6e, 0x64, 0x43, 0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x52, 0x65, 0x73,
-	0x42, 0x07, 0x5a, 0x05, 0x2e, 0x3b, 0x70, 0x64, 0x75, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f,
-	0x33,
+	0x6f, 0x6e, 0x73, 0x52, 0x65, 0x71, 0x1a, 0x1a, 0x2e, 0x4c, 0x69, 0x73, 0x74, 0x46, 0x69, 0x6c,
+	0x65, 0x73, 0x79, 0x73, 0x74, 0x65, 0x6d, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x73, 0x52,
+	0x65, 0x73, 0x12, 0x3e, 0x0a, 0x10, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61,
+	0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x12, 0x14, 0x2e, 0x44, 0x65, 0x73, 0x74, 0x72, 0x6f, 0x79,
+	0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x52, 0x65, 0x71, 0x1a, 0x14, 0x2e, 0x44,
+	0x65, 0x73, 0x74, 0x72, 0x6f, 0x79, 0x53, 0x6e, 0x61, 0x70, 0x73, 0x68, 0x6f, 0x74, 0x73, 0x52,
+	0x65, 0x73, 0x12, 0x41, 0x0a, 0x11, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f,
+	0x6e, 0x43, 0x75, 0x72, 0x73, 0x6f, 0x72, 0x12, 0x15, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63,
+	0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x75, 0x72, 0x73, 0x6f, 0x72, 0x52, 0x65, 0x71, 0x1a, 0x15,
+	0x2e, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x75, 0x72, 0x73,
+	0x6f, 0x72, 0x52, 0x65, 0x73, 0x12, 0x1d, 0x0a, 0x07, 0x53, 0x65, 0x6e, 0x64, 0x44, 0x72, 0x79,
+	0x12, 0x08, 0x2e, 0x53, 0x65, 0x6e, 0x64, 0x52, 0x65, 0x71, 0x1a, 0x08, 0x2e, 0x53, 0x65, 0x6e,
+	0x64, 0x52, 0x65, 0x73, 0x12, 0x35, 0x0a, 0x0d, 0x53, 0x65, 0x6e, 0x64, 0x43, 0x6f, 0x6d, 0x70,
+	0x6c, 0x65, 0x74, 0x65, 0x64, 0x12, 0x11, 0x2e, 0x53, 0x65, 0x6e, 0x64, 0x43, 0x6f, 0x6d, 0x70,
+	0x6c, 0x65, 0x74, 0x65, 0x64, 0x52, 0x65, 0x71, 0x1a, 0x11, 0x2e, 0x53, 0x65, 0x6e, 0x64, 0x43,
+	0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x52, 0x65, 0x73, 0x42, 0x07, 0x5a, 0x05, 0x2e,
+	0x3b, 0x70, 0x64, 0x75, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33,
 }
 
 var (
@@ -1625,30 +1606,31 @@ var file_pdu_proto_depIdxs = []int32{
 	11, // 7: ReplicationConfig.protection:type_name -> ReplicationConfigProtection
 	1,  // 8: ReplicationConfigProtection.Initial:type_name -> ReplicationGuaranteeKind
 	1,  // 9: ReplicationConfigProtection.Incremental:type_name -> ReplicationGuaranteeKind
-	12, // 10: SendRes.Properties:type_name -> Property
-	9,  // 11: SendCompletedReq.OriginalReq:type_name -> SendReq
-	8,  // 12: ReceiveReq.To:type_name -> FilesystemVersion
-	10, // 13: ReceiveReq.ReplicationConfig:type_name -> ReplicationConfig
-	8,  // 14: DestroySnapshotsReq.Snapshots:type_name -> FilesystemVersion
-	8,  // 15: DestroySnapshotRes.Snapshot:type_name -> FilesystemVersion
-	19, // 16: DestroySnapshotsRes.Results:type_name -> DestroySnapshotRes
-	23, // 17: Replication.Ping:input_type -> PingReq
-	3,  // 18: Replication.ListFilesystems:input_type -> ListFilesystemReq
-	6,  // 19: Replication.ListFilesystemVersions:input_type -> ListFilesystemVersionsReq
-	18, // 20: Replication.DestroySnapshots:input_type -> DestroySnapshotsReq
-	21, // 21: Replication.ReplicationCursor:input_type -> ReplicationCursorReq
+	9,  // 10: SendCompletedReq.OriginalReq:type_name -> SendReq
+	8,  // 11: ReceiveReq.To:type_name -> FilesystemVersion
+	10, // 12: ReceiveReq.ReplicationConfig:type_name -> ReplicationConfig
+	8,  // 13: DestroySnapshotsReq.Snapshots:type_name -> FilesystemVersion
+	8,  // 14: DestroySnapshotRes.Snapshot:type_name -> FilesystemVersion
+	19, // 15: DestroySnapshotsRes.Results:type_name -> DestroySnapshotRes
+	23, // 16: Replication.Ping:input_type -> PingReq
+	3,  // 17: Replication.ListFilesystems:input_type -> ListFilesystemReq
+	6,  // 18: Replication.ListFilesystemVersions:input_type -> ListFilesystemVersionsReq
+	18, // 19: Replication.DestroySnapshots:input_type -> DestroySnapshotsReq
+	21, // 20: Replication.ReplicationCursor:input_type -> ReplicationCursorReq
+	9,  // 21: Replication.SendDry:input_type -> SendReq
 	14, // 22: Replication.SendCompleted:input_type -> SendCompletedReq
 	24, // 23: Replication.Ping:output_type -> PingRes
 	4,  // 24: Replication.ListFilesystems:output_type -> ListFilesystemRes
 	7,  // 25: Replication.ListFilesystemVersions:output_type -> ListFilesystemVersionsRes
 	20, // 26: Replication.DestroySnapshots:output_type -> DestroySnapshotsRes
 	22, // 27: Replication.ReplicationCursor:output_type -> ReplicationCursorRes
-	15, // 28: Replication.SendCompleted:output_type -> SendCompletedRes
-	23, // [23:29] is the sub-list for method output_type
-	17, // [17:23] is the sub-list for method input_type
-	17, // [17:17] is the sub-list for extension type_name
-	17, // [17:17] is the sub-list for extension extendee
-	0,  // [0:17] is the sub-list for field type_name
+	13, // 28: Replication.SendDry:output_type -> SendRes
+	15, // 29: Replication.SendCompleted:output_type -> SendCompletedRes
+	23, // [23:30] is the sub-list for method output_type
+	16, // [16:23] is the sub-list for method input_type
+	16, // [16:16] is the sub-list for extension type_name
+	16, // [16:16] is the sub-list for extension extendee
+	0,  // [0:16] is the sub-list for field type_name
 }
 
 func init() { file_pdu_proto_init() }

replication/logic/pdu/pdu.proto

@@ -8,6 +8,7 @@ service Replication {
       returns (ListFilesystemVersionsRes);
   rpc DestroySnapshots(DestroySnapshotsReq) returns (DestroySnapshotsRes);
   rpc ReplicationCursor(ReplicationCursorReq) returns (ReplicationCursorRes);
+  rpc SendDry(SendReq) returns (SendRes);
   rpc SendCompleted(SendCompletedReq) returns (SendCompletedRes);
   // for Send and Recv, see package rpc
 }
@@ -60,9 +61,7 @@ message SendReq {
   string ResumeToken = 4;
   Tri Encrypted = 5;
 
-  bool DryRun = 6;
-
-  ReplicationConfig ReplicationConfig = 7;
+  ReplicationConfig ReplicationConfig = 6;
 }
 
 message ReplicationConfig {
@@ -89,14 +88,12 @@ message Property {
 
 message SendRes {
   // Whether the resume token provided in the request has been used or not.
-  // If the SendReq.ResumeToken == "", this field has no meaning.
-  bool UsedResumeToken = 2;
+  // If the SendReq.ResumeToken == "", this field MUST be false.
+  bool UsedResumeToken = 1;
 
   // Expected stream size determined by dry run, not exact.
   // 0 indicates that for the given SendReq, no size estimate could be made.
-  int64 ExpectedSize = 3;
-
-  repeated Property Properties = 4;
+  uint64 ExpectedSize = 2;
 }
 
 message SendCompletedReq {

replication/logic/pdu/pdu_grpc.pb.go

@@ -23,6 +23,7 @@ type ReplicationClient interface {
 	ListFilesystemVersions(ctx context.Context, in *ListFilesystemVersionsReq, opts ...grpc.CallOption) (*ListFilesystemVersionsRes, error)
 	DestroySnapshots(ctx context.Context, in *DestroySnapshotsReq, opts ...grpc.CallOption) (*DestroySnapshotsRes, error)
 	ReplicationCursor(ctx context.Context, in *ReplicationCursorReq, opts ...grpc.CallOption) (*ReplicationCursorRes, error)
+	SendDry(ctx context.Context, in *SendReq, opts ...grpc.CallOption) (*SendRes, error)
 	SendCompleted(ctx context.Context, in *SendCompletedReq, opts ...grpc.CallOption) (*SendCompletedRes, error)
 }
 
@@ -79,6 +80,15 @@ func (c *replicationClient) ReplicationCursor(ctx context.Context, in *Replicati
 	return out, nil
 }
 
+func (c *replicationClient) SendDry(ctx context.Context, in *SendReq, opts ...grpc.CallOption) (*SendRes, error) {
+	out := new(SendRes)
+	err := c.cc.Invoke(ctx, "/Replication/SendDry", in, out, opts...)
+	if err != nil {
+		return nil, err
+	}
+	return out, nil
+}
+
 func (c *replicationClient) SendCompleted(ctx context.Context, in *SendCompletedReq, opts ...grpc.CallOption) (*SendCompletedRes, error) {
 	out := new(SendCompletedRes)
 	err := c.cc.Invoke(ctx, "/Replication/SendCompleted", in, out, opts...)
@@ -97,6 +107,7 @@ type ReplicationServer interface {
 	ListFilesystemVersions(context.Context, *ListFilesystemVersionsReq) (*ListFilesystemVersionsRes, error)
 	DestroySnapshots(context.Context, *DestroySnapshotsReq) (*DestroySnapshotsRes, error)
 	ReplicationCursor(context.Context, *ReplicationCursorReq) (*ReplicationCursorRes, error)
+	SendDry(context.Context, *SendReq) (*SendRes, error)
 	SendCompleted(context.Context, *SendCompletedReq) (*SendCompletedRes, error)
 	mustEmbedUnimplementedReplicationServer()
 }
@@ -120,6 +131,9 @@ func (UnimplementedReplicationServer) DestroySnapshots(context.Context, *Destroy
 func (UnimplementedReplicationServer) ReplicationCursor(context.Context, *ReplicationCursorReq) (*ReplicationCursorRes, error) {
 	return nil, status.Errorf(codes.Unimplemented, "method ReplicationCursor not implemented")
 }
+func (UnimplementedReplicationServer) SendDry(context.Context, *SendReq) (*SendRes, error) {
+	return nil, status.Errorf(codes.Unimplemented, "method SendDry not implemented")
+}
 func (UnimplementedReplicationServer) SendCompleted(context.Context, *SendCompletedReq) (*SendCompletedRes, error) {
 	return nil, status.Errorf(codes.Unimplemented, "method SendCompleted not implemented")
 }
@@ -226,6 +240,24 @@ func _Replication_ReplicationCursor_Handler(srv interface{}, ctx context.Context
 	return interceptor(ctx, in, info, handler)
 }
 
+func _Replication_SendDry_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
+	in := new(SendReq)
+	if err := dec(in); err != nil {
+		return nil, err
+	}
+	if interceptor == nil {
+		return srv.(ReplicationServer).SendDry(ctx, in)
+	}
+	info := &grpc.UnaryServerInfo{
+		Server:     srv,
+		FullMethod: "/Replication/SendDry",
+	}
+	handler := func(ctx context.Context, req interface{}) (interface{}, error) {
+		return srv.(ReplicationServer).SendDry(ctx, req.(*SendReq))
+	}
+	return interceptor(ctx, in, info, handler)
+}
+
 func _Replication_SendCompleted_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
 	in := new(SendCompletedReq)
 	if err := dec(in); err != nil {
@@ -271,6 +303,10 @@ var Replication_ServiceDesc = grpc.ServiceDesc{
 			MethodName: "ReplicationCursor",
 			Handler:    _Replication_ReplicationCursor_Handler,
 		},
+		{
+			MethodName: "SendDry",
+			Handler:    _Replication_SendDry_Handler,
+		},
 		{
 			MethodName: "SendCompleted",
 			Handler:    _Replication_SendCompleted_Handler,

replication/logic/replication_logic.go

@@ -41,6 +41,7 @@ type Sender interface {
 	// any next call to the parent github.com/zrepl/zrepl/replication.Endpoint.
 	// If the send request is for dry run the io.ReadCloser will be nil
 	Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.ReadCloser, error)
+	SendDry(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, error)
 	SendCompleted(ctx context.Context, r *pdu.SendCompletedReq) (*pdu.SendCompletedRes, error)
 	ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error)
 }
@@ -158,7 +159,7 @@ type Step struct {
 	encrypt     tri
 	resumeToken string // empty means no resume token shall be used
 
-	expectedSize int64 // 0 means no size estimate present / possible
+	expectedSize uint64 // 0 means no size estimate present / possible
 
 	// byteCounter is nil initially, and set later in Step.doReplication
 	// => concurrent read of that pointer from Step.ReportInfo must be protected
@@ -189,7 +190,7 @@ func (s *Step) Step(ctx context.Context) error {
 func (s *Step) ReportInfo() *report.StepInfo {
 
 	// get current byteCounter value
-	var byteCounter int64
+	var byteCounter uint64
 	s.byteCounterMtx.Lock()
 	if s.byteCounter != nil {
 		byteCounter = s.byteCounter.Count()
@@ -546,10 +547,10 @@ func (s *Step) updateSizeEstimate(ctx context.Context) error {
 
 	log := getLogger(ctx)
 
-	sr := s.buildSendRequest(true)
+	sr := s.buildSendRequest()
 
 	log.Debug("initiate dry run send request")
-	sres, _, err := s.sender.Send(ctx, sr)
+	sres, err := s.sender.SendDry(ctx, sr)
 	if err != nil {
 		log.WithError(err).Error("dry run send request failed")
 		return err
@@ -563,7 +564,7 @@ func (s *Step) updateSizeEstimate(ctx context.Context) error {
 	return nil
 }
 
-func (s *Step) buildSendRequest(dryRun bool) (sr *pdu.SendReq) {
+func (s *Step) buildSendRequest() (sr *pdu.SendReq) {
 	fs := s.parent.Path
 	sr = &pdu.SendReq{
 		Filesystem:        fs,
@@ -571,7 +572,6 @@ func (s *Step) buildSendRequest(dryRun bool) (sr *pdu.SendReq) {
 		To:                s.to,
 		Encrypted:         s.encrypt.ToPDU(),
 		ResumeToken:       s.resumeToken,
-		DryRun:            dryRun,
 		ReplicationConfig: s.parent.policy.ReplicationConfig,
 	}
 	return sr
@@ -582,7 +582,7 @@ func (s *Step) doReplication(ctx context.Context) error {
 	fs := s.parent.Path
 
 	log := getLogger(ctx).WithField("filesystem", fs)
-	sr := s.buildSendRequest(false)
+	sr := s.buildSendRequest()
 
 	log.Debug("initiate send request")
 	sres, stream, err := s.sender.Send(ctx, sr)

replication/report/replication_report.go

@@ -62,11 +62,23 @@ const (
 	FilesystemDone            FilesystemState = "done"
 )
 
+type FsBlockedOn string
+
+const (
+	FsBlockedOnNothing           FsBlockedOn = "nothing"
+	FsBlockedOnPlanningStepQueue FsBlockedOn = "plan-queue"
+	FsBlockedOnParentInitialRepl FsBlockedOn = "parent-initial-repl"
+	FsBlockedOnReplStepQueue     FsBlockedOn = "repl-queue"
+)
+
 type FilesystemReport struct {
 	Info *FilesystemInfo
 
 	State FilesystemState
 
+	// Always valid.
+	BlockedOn FsBlockedOn
+
 	// Valid in State = FilesystemPlanningErrored
 	PlanError *TimedError
 	// Valid in State = FilesystemSteppingErrored
@@ -97,11 +109,11 @@ type StepInfo struct {
 	From, To        string
 	Resumed         bool
 	Encrypted       EncryptedEnum
-	BytesExpected   int64
-	BytesReplicated int64
+	BytesExpected   uint64
+	BytesReplicated uint64
 }
 
-func (a *AttemptReport) BytesSum() (expected, replicated int64, containsInvalidSizeEstimates bool) {
+func (a *AttemptReport) BytesSum() (expected, replicated uint64, containsInvalidSizeEstimates bool) {
 	for _, fs := range a.Filesystems {
 		e, r, fsContainsInvalidEstimate := fs.BytesSum()
 		containsInvalidSizeEstimates = containsInvalidSizeEstimates || fsContainsInvalidEstimate
@@ -111,7 +123,7 @@ func (a *AttemptReport) BytesSum() (expected, replicated int64, containsInvalidS
 	return expected, replicated, containsInvalidSizeEstimates
 }
 
-func (f *FilesystemReport) BytesSum() (expected, replicated int64, containsInvalidSizeEstimates bool) {
+func (f *FilesystemReport) BytesSum() (expected, replicated uint64, containsInvalidSizeEstimates bool) {
 	for _, step := range f.Steps {
 		expected += step.Info.BytesExpected
 		replicated += step.Info.BytesReplicated

rpc/dataconn/dataconn_client.go

@@ -114,12 +114,6 @@ func (c *Client) ReqSend(ctx context.Context, req *pdu.SendReq) (*pdu.SendRes, i
 	if err != nil {
 		return nil, nil, err
 	}
-	putWireOnReturn := true
-	defer func() {
-		if putWireOnReturn {
-			c.putWire(conn)
-		}
-	}()
 
 	if err := c.send(ctx, conn, EndpointSend, req, nil); err != nil {
 		return nil, nil, err
@@ -131,14 +125,10 @@ func (c *Client) ReqSend(ctx context.Context, req *pdu.SendReq) (*pdu.SendRes, i
 	}
 
 	var stream io.ReadCloser
-	if !req.DryRun {
-		putWireOnReturn = false
 	stream, err = conn.ReadStream(ZFSStream, true) // no shadow
 	if err != nil {
 		return nil, nil, err
 	}
-	}
-
 	return &res, stream, nil
 }
 

rpc/dataconn/dataconn_server.go

@@ -172,6 +172,15 @@ func (s *Server) serveConnRequest(ctx context.Context, endpoint string, c *strea
 			return
 		}
 		res, sendStream, handlerErr = s.h.Send(ctx, &req) // SHADOWING
+		// ensure that we always close the sendStream
+		if sendStream != nil {
+			defer func() {
+				err := sendStream.Close()
+				if err != nil {
+					s.log.WithError(err).Error("cannot close send stream")
+				}
+			}()
+		}
 	case EndpointRecv:
 		var req pdu.ReceiveReq
 		if err := proto.Unmarshal(reqStructured, &req); err != nil {
@@ -239,12 +248,9 @@ func (s *Server) serveConnRequest(ctx context.Context, endpoint string, c *strea
 
 	if sendStream != nil {
 		err := c.SendStream(ctx, sendStream, ZFSStream)
-		closeErr := sendStream.Close()
-		if closeErr != nil {
-			s.log.WithError(err).Error("cannot close send stream")
-		}
 		if err != nil {
 			s.log.WithError(err).Error("cannot write send stream")
 		}
+		// sendStream.Close() done via defer above
 	}
 }

rpc/dataconn/timeoutconn/timeoutconn_readv_unsupported.go

@@ -1,3 +1,4 @@
+//go:build illumos || solaris
 // +build illumos solaris
 
 package timeoutconn

rpc/dataconn/timeoutconn/timeoutconn_test.go

@@ -14,6 +14,7 @@ import (
 	"github.com/stretchr/testify/require"
 
 	"github.com/zrepl/zrepl/util/socketpair"
+	"github.com/zrepl/zrepl/util/zreplcircleci"
 )
 
 func TestReadTimeout(t *testing.T) {
@@ -81,6 +82,8 @@ func TestWriteTimeout(t *testing.T) {
 }
 
 func TestNoPartialReadsDueToDeadline(t *testing.T) {
+	zreplcircleci.SkipOnCircleCI(t, "needs predictable low scheduling latency")
+
 	a, b, err := socketpair.SocketPair()
 	require.NoError(t, err)
 	defer a.Close()
@@ -151,6 +154,7 @@ func (c *partialWriteMockConn) Write(p []byte) (int, error) {
 }
 
 func TestPartialWriteMockConn(t *testing.T) {
+	zreplcircleci.SkipOnCircleCI(t, "because it relies on scheduler responsiveness < 50ms")
 	mc := newPartialWriteMockConn(100*time.Millisecond, 5)
 	buf := []byte{1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
 	begin := time.Now()

rpc/dataconn/timeoutconn/timoutconn_readv.go

@@ -1,5 +1,5 @@
-// +build !illumos
-// +build !solaris
+//go:build !illumos && !solaris
+// +build !illumos,!solaris
 
 package timeoutconn
 

rpc/rpc_client.go

@@ -108,6 +108,13 @@ func (c *Client) Receive(ctx context.Context, req *pdu.ReceiveReq, stream io.Rea
 	return c.dataClient.ReqRecv(ctx, req, stream)
 }
 
+func (c *Client) SendDry(ctx context.Context, in *pdu.SendReq) (*pdu.SendRes, error) {
+	ctx, endSpan := trace.WithSpan(ctx, "rpc.client.SendDry")
+	defer endSpan()
+
+	return c.controlClient.SendDry(ctx, in)
+}
+
 func (c *Client) ListFilesystems(ctx context.Context, in *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error) {
 	ctx, endSpan := trace.WithSpan(ctx, "rpc.client.ListFilesystems")
 	defer endSpan()

rpc/versionhandshake/versionhandshake.go

@@ -152,7 +152,7 @@ func (m *HandshakeMessage) DecodeReader(r io.Reader, maxLen int) error {
 
 func DoHandshakeCurrentVersion(conn net.Conn, deadline time.Time) *HandshakeError {
 	// current protocol version is hardcoded here
-	return DoHandshakeVersion(conn, deadline, 5)
+	return DoHandshakeVersion(conn, deadline, 6)
 }
 
 const HandshakeMessageMaxLen = 16 * 4096

transport/tcp/serve_tcp_ipmap_test.go

@@ -93,13 +93,10 @@ func TestIPMap(t *testing.T) {
 			expect: map[string]testCaseExpect{
 				"10.1.2.3":      {expectNoMapping: true},
 				"192.168.23.1":  {expectIdent: "db-192.168.23.1"},
+				"192.168.42.1":  {expectIdent: "web-192.168.42.1"},
 				"192.168.23.23": {expectIdent: "db-twentythree"},
-				"192.168.023.001": {expectIdent: "db-192.168.23.1"},
 				"10.1.4.5":      {expectIdent: "my-10.1.4.5-server"},
 
-				// normalization
-				"192.168.42.1":    {expectIdent: "web-192.168.42.1"},
-				"192.168.042.001": {expectIdent: "web-192.168.42.1"},
 				// v6 matching
 				"fe80::23:42%eth1": {expectIdent: "san-fe80::23:42-eth1"},
 				"fe80::23:42%eth2": {expectNoMapping: true},
@@ -179,7 +176,8 @@ func TestIPMap(t *testing.T) {
 			for input, expect := range c.expect {
 				// reuse newIPMapEntry to parse test case input
 				// "test" is not used during testing but must not be empty.
-				ipMapEntry, _ := newIPMapEntry(input, "test")
+				ipMapEntry, err := newIPMapEntry(input, "test")
+				require.NoError(t, err)
 				ones, bits := ipMapEntry.subnet.Mask.Size()
 				require.Equal(t, bits, net.IPv6len*8, "and we know ipMapEntry always expands its IPs to 16bytes")
 				require.Equal(t, ones, net.IPv6len*8, "test case addresses must be fully specified")

util/bandwidthlimit/bandwidthlimit.go

@@ -0,0 +1,79 @@
+package bandwidthlimit
+
+import (
+	"errors"
+	"io"
+
+	"github.com/juju/ratelimit"
+)
+
+type Wrapper interface {
+	WrapReadCloser(io.ReadCloser) io.ReadCloser
+}
+
+type Config struct {
+	// Units in this struct are in _bytes_.
+
+	Max            int64 // < 0 means no limit, BucketCapacity is irrelevant then
+	BucketCapacity int64
+}
+
+func NoLimitConfig() Config {
+	return Config{
+		Max:            -1,
+		BucketCapacity: -1,
+	}
+}
+
+func ValidateConfig(conf Config) error {
+	if conf.BucketCapacity == 0 {
+		return errors.New("BucketCapacity must not be zero")
+	}
+	return nil
+}
+
+func WrapperFromConfig(conf Config) Wrapper {
+	if err := ValidateConfig(conf); err != nil {
+		panic(err)
+	}
+
+	if conf.Max < 0 {
+		return noLimit{}
+	}
+
+	return &withLimit{
+		bucket: ratelimit.NewBucketWithRate(float64(conf.Max), conf.BucketCapacity),
+	}
+}
+
+type noLimit struct{}
+
+func (_ noLimit) WrapReadCloser(rc io.ReadCloser) io.ReadCloser { return rc }
+
+type withLimit struct {
+	bucket *ratelimit.Bucket
+}
+
+func (l *withLimit) WrapReadCloser(rc io.ReadCloser) io.ReadCloser {
+	return WrapReadCloser(rc, l.bucket)
+}
+
+type withLimitReadCloser struct {
+	orig    io.Closer
+	limited io.Reader
+}
+
+func (r *withLimitReadCloser) Read(buf []byte) (int, error) {
+	return r.limited.Read(buf)
+}
+
+func (r *withLimitReadCloser) Close() error {
+	return r.orig.Close()
+}
+
+func WrapReadCloser(rc io.ReadCloser, bucket *ratelimit.Bucket) io.ReadCloser {
+	return &withLimitReadCloser{
+		limited: ratelimit.Reader(rc, bucket),
+		orig:    rc,
+	}
+}

util/bandwidthlimit/bandwidthlimit_test.go

@@ -0,0 +1,19 @@
+package bandwidthlimit
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestNoLimitConfig(t *testing.T) {
+
+	conf := NoLimitConfig()
+
+	err := ValidateConfig(conf)
+	require.NoError(t, err)
+
+	require.NotPanics(t, func() {
+		_ = WrapperFromConfig(conf)
+	})
+}

util/bytecounter/bytecounter_readcloser.go

@@ -9,7 +9,7 @@ import (
 // its interface and counting the bytes written to during copying.
 type ReadCloser interface {
 	io.ReadCloser
-	Count() int64
+	Count() uint64
 }
 
 // NewReadCloser wraps rc.
@@ -19,11 +19,11 @@ func NewReadCloser(rc io.ReadCloser) ReadCloser {
 
 type readCloser struct {
 	rc    io.ReadCloser
-	count int64
+	count uint64
 }
 
-func (r *readCloser) Count() int64 {
-	return atomic.LoadInt64(&r.count)
+func (r *readCloser) Count() uint64 {
+	return atomic.LoadUint64(&r.count)
 }
 
 var _ io.ReadCloser = &readCloser{}
@@ -34,6 +34,9 @@ func (r *readCloser) Close() error {
 
 func (r *readCloser) Read(p []byte) (int, error) {
 	n, err := r.rc.Read(p)
-	atomic.AddInt64(&r.count, int64(n))
+	if n < 0 {
+		panic("expecting n >= 0")
+	}
+	atomic.AddUint64(&r.count, uint64(n))
 	return n, err
 }

util/choices/choices.go

@@ -0,0 +1,98 @@
+// Package choice implements a flag.Value type that accepts a set of choices.
+//
+// See test cases or grep the code base for usage hints.
+package choices
+
+import (
+	"flag"
+	"fmt"
+	"strings"
+)
+
+type Choices struct {
+	choices    map[string]interface{}
+	typeString string
+	value      interface{}
+}
+
+var _ flag.Value = (*Choices)(nil)
+
+func new(pairs ...interface{}) Choices {
+	if (len(pairs) % 2) != 0 {
+		panic("must provide a sequence of key value pairs")
+	}
+	c := Choices{
+		choices: make(map[string]interface{}, len(pairs)/2),
+		value:   nil,
+	}
+	for i := 0; i < len(pairs); {
+		key, ok := pairs[i].(string)
+		if !ok {
+			panic(fmt.Sprintf("argument %d is %T but should be a string, value: %#v", i, pairs[i], pairs[i]))
+		}
+		c.choices[key] = pairs[i+1]
+		i += 2
+	}
+	c.typeString = strings.Join(c.choicesList(true), ",") // overrideable by setter
+	return c
+}
+
+func (c *Choices) Init(pairs ...interface{}) {
+	*c = new(pairs...)
+}
+
+func (c Choices) choicesList(escaped bool) []string {
+	keys := make([]string, len(c.choices))
+	i := 0
+	for k := range c.choices {
+		e := k
+		if escaped {
+			e = fmt.Sprintf("%q", k)
+		}
+		keys[i] = e
+		i += 1
+	}
+	return keys
+}
+
+func (c Choices) Usage() string {
+	return fmt.Sprintf("one of %s", strings.Join(c.choicesList(true), ","))
+}
+
+func (c Choices) InputForChoice(v interface{}) (string, error) {
+	for input, choice := range c.choices {
+		if choice == v {
+			return input, nil
+		}
+	}
+	return "", fmt.Errorf("choice not registered at .Init(): %v", v)
+}
+
+func (c *Choices) SetDefaultValue(v interface{}) {
+	c.value = v
+}
+
+func (c Choices) Value() interface{} {
+	return c.value
+}
+
+func (c *Choices) Set(input string) error {
+	v, ok := c.choices[input]
+	if !ok {
+		return fmt.Errorf("invalid value %q: must be one of %s", input, c.Usage())
+	}
+	c.value = v
+	return nil
+}
+
+func (c *Choices) String() string {
+	return "" // c.value.(fmt.Stringer).String()
+}
+
+func (c *Choices) SetTypeString(ts string) {
+	c.typeString = ts
+}
+
+func (c *Choices) Type() string {
+	return c.typeString
+}

util/choices/choices_test.go

@@ -0,0 +1,50 @@
+package choices_test
+
+import (
+	"bytes"
+	"flag"
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/zrepl/zrepl/util/choices"
+)
+
+func TestChoices(t *testing.T) {
+
+	var c choices.Choices
+
+	fs := flag.NewFlagSet("testset", flag.ContinueOnError)
+	c.Init("append", os.O_APPEND, "overwrite", os.O_TRUNC|os.O_CREATE)
+	fs.Var(&c, "mode", c.Usage())
+	var o bytes.Buffer
+	fs.SetOutput(&o)
+
+	fs.Usage()
+	usage := o.String()
+	o.Reset()
+
+	t.Logf("usage:\n%s", usage)
+	require.Contains(t, usage, "\"append\"")
+	require.Contains(t, usage, "\"overwrite\"")
+
+	err := fs.Parse([]string{"-mode", "append"})
+	require.NoError(t, err)
+	o.Reset()
+	require.Equal(t, os.O_APPEND, c.Value())
+
+	c.SetDefaultValue(nil)
+	err = fs.Parse([]string{})
+	require.NoError(t, err)
+	o.Reset()
+	require.Nil(t, c.Value())
+
+	// a little whitebox testing: this is allowed ATM, we don't check that the default value was specified as a choice in init
+	c.SetDefaultValue(os.O_RDWR)
+	err = fs.Parse([]string{})
+	require.NoError(t, err)
+	o.Reset()
+	require.Equal(t, os.O_RDWR, c.Value())
+
+}

util/datasizeunit/datasizeunit.go

@@ -0,0 +1,86 @@
+package datasizeunit
+
+import (
+	"errors"
+	"fmt"
+	"math"
+	"regexp"
+	"strconv"
+	"strings"
+)
+
+type Bits struct {
+	bits float64
+}
+
+func (b Bits) ToBits() float64    { return b.bits }
+func (b Bits) ToBytes() float64   { return b.bits / 8 }
+func FromBytesInt64(i int64) Bits { return Bits{float64(i) * 8} }
+
+var datarateRegex = regexp.MustCompile(`^([-0-9\.]*)\s*(bit|(|K|Ki|M|Mi|G|Gi|T|Ti)([bB]))$`)
+
+func (r *Bits) UnmarshalYAML(u func(interface{}, bool) error) (_ error) {
+
+	var s string
+	err := u(&s, false)
+	if err != nil {
+		return err
+	}
+
+	genericErr := func(err error) error {
+		var buf strings.Builder
+		fmt.Fprintf(&buf, "cannot parse %q using regex %s", s, datarateRegex)
+		if err != nil {
+			fmt.Fprintf(&buf, ": %s", err)
+		}
+		return errors.New(buf.String())
+	}
+
+	match := datarateRegex.FindStringSubmatch(s)
+	if match == nil {
+		return genericErr(nil)
+	}
+
+	bps, err := strconv.ParseFloat(match[1], 64)
+	if err != nil {
+		return genericErr(err)
+	}
+
+	if match[2] == "bit" {
+		if math.Round(bps) != bps {
+			return genericErr(fmt.Errorf("unit bit must be an integer value"))
+		}
+		r.bits = bps
+		return nil
+	}
+
+	factorMap := map[string]uint64{
+		"": 1,
+
+		"K": 1e3,
+		"M": 1e6,
+		"G": 1e9,
+		"T": 1e12,
+
+		"Ki": 1 << 10,
+		"Mi": 1 << 20,
+		"Gi": 1 << 30,
+		"Ti": 1 << 40,
+	}
+	factor, ok := factorMap[match[3]]
+	if !ok {
+		panic(match)
+	}
+
+	baseUnitFactorMap := map[string]uint64{
+		"b": 1,
+		"B": 8,
+	}
+	baseUnitFactor, ok := baseUnitFactorMap[match[4]]
+	if !ok {
+		panic(match)
+	}
+
+	r.bits = bps * float64(factor) * float64(baseUnitFactor)
+	return nil
+}

util/datasizeunit/datasizeunit_test.go

@@ -0,0 +1,57 @@
+package datasizeunit
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"github.com/zrepl/yaml-config"
+)
+
+func TestBits(t *testing.T) {
+
+	tcs := []struct {
+		input      string
+		expectRate float64
+		expectErr  string
+	}{
+		{`23 bit`, 23, ""}, // bit special case works
+		{`23bit`, 23, ""},  // also without space
+
+		{`10MiB`, 10 * (1 << 20) * 8, ""},  // integer unit without space
+		{`10 MiB`, 8 * 10 * (1 << 20), ""}, // integer unit with space
+
+		{`10.5 Kib`, 10.5 * (1 << 10), ""}, // floating point with bit unit works with space
+		{`10.5Kib`, 10.5 * (1 << 10), ""},  // floating point with bit unit works without space
+
+		// unit checks
+		{`1 bit`, 1, ""},
+		{`1 B`, 1 * 8, ""},
+		{`1 Kb`, 1e3, ""},
+		{`1 Kib`, 1 << 10, ""},
+		{`1 Mb`, 1e6, ""},
+		{`1 Mib`, 1 << 20, ""},
+		{`1 Gb`, 1e9, ""},
+		{`1 Gib`, 1 << 30, ""},
+		{`1 Tb`, 1e12, ""},
+		{`1 Tib`, 1 << 40, ""},
+	}
+
+	for _, tc := range tcs {
+		t.Run(tc.input, func(t *testing.T) {
+
+			var bits Bits
+			err := yaml.Unmarshal([]byte(tc.input), &bits)
+			if tc.expectErr != "" {
+				assert.Error(t, err)
+				assert.Regexp(t, tc.expectErr, err.Error())
+				assert.Zero(t, bits.bits)
+			} else {
+				require.NoError(t, err)
+				assert.Equal(t, tc.expectRate, bits.bits)
+			}
+		})
+
+	}
+
+}

util/envconst/envconst.go

@@ -73,6 +73,24 @@ func Int64(varname string, def int64) (d int64) {
 	return d
 }
 
+func Uint64(varname string, def uint64) (d uint64) {
+	var err error
+	if v, ok := cache.Load(varname); ok {
+		return v.(uint64)
+	}
+	e := os.Getenv(varname)
+	if e == "" {
+		d = def
+	} else {
+		d, err = strconv.ParseUint(e, 10, 64)
+		if err != nil {
+			panic(err)
+		}
+	}
+	cache.Store(varname, d)
+	return d
+}
+
 func Bool(varname string, def bool) (d bool) {
 	var err error
 	if v, ok := cache.Load(varname); ok {

util/optionaldeadline/optionaldeadline_test.go

@@ -9,9 +9,11 @@ import (
 	"github.com/stretchr/testify/require"
 
 	"github.com/zrepl/zrepl/util/chainlock"
+	"github.com/zrepl/zrepl/util/zreplcircleci"
 )
 
 func TestContextWithOptionalDeadline(t *testing.T) {
+	zreplcircleci.SkipOnCircleCI(t, "test relies on predictably low scheduler latency")
 
 	ctx := context.Background()
 	cctx, enforceDeadline := ContextWithOptionalDeadline(ctx)
@@ -72,6 +74,7 @@ func TestContextWithOptionalDeadlineNegativeDeadline(t *testing.T) {
 }
 
 func TestContextWithOptionalDeadlineParentCancellation(t *testing.T) {
+	zreplcircleci.SkipOnCircleCI(t, "test relies on predictably low scheduler latency")
 
 	pctx, cancel := context.WithCancel(context.Background())
 	cctx, enforceDeadline := ContextWithOptionalDeadline(pctx)

util/tcpsock/tcpsock_freebind_freebsd.go

@@ -1,3 +1,4 @@
+//go:build freebsd
 // +build freebsd
 
 package tcpsock

util/tcpsock/tcpsock_freebind_linux.go

@@ -1,3 +1,4 @@
+//go:build linux
 // +build linux
 
 package tcpsock

util/tcpsock/tcpsock_freebind_unsupported.go

@@ -1,3 +1,4 @@
+//go:build !linux && !freebsd
 // +build !linux,!freebsd
 
 package tcpsock

util/zreplcircleci/zreplcircleci.go

@@ -0,0 +1,13 @@
+package zreplcircleci
+
+import (
+	"fmt"
+	"os"
+	"testing"
+)
+
+func SkipOnCircleCI(t *testing.T, reasonFmt string, args ...interface{}) {
+	if os.Getenv("CIRCLECI") != "" {
+		t.Skipf("This test is skipped in CircleCI. Reason: %s", fmt.Sprintf(reasonFmt, args...))
+	}
+}

zfs/filesystemplaceholdercreateencryptionvalue_enumer.go

@@ -0,0 +1,51 @@
+// Code generated by "enumer -type=FilesystemPlaceholderCreateEncryptionValue -trimprefix=FilesystemPlaceholderCreateEncryption"; DO NOT EDIT.
+
+//
+package zfs
+
+import (
+	"fmt"
+)
+
+const _FilesystemPlaceholderCreateEncryptionValueName = "InheritOff"
+
+var _FilesystemPlaceholderCreateEncryptionValueIndex = [...]uint8{0, 7, 10}
+
+func (i FilesystemPlaceholderCreateEncryptionValue) String() string {
+	i -= 1
+	if i < 0 || i >= FilesystemPlaceholderCreateEncryptionValue(len(_FilesystemPlaceholderCreateEncryptionValueIndex)-1) {
+		return fmt.Sprintf("FilesystemPlaceholderCreateEncryptionValue(%d)", i+1)
+	}
+	return _FilesystemPlaceholderCreateEncryptionValueName[_FilesystemPlaceholderCreateEncryptionValueIndex[i]:_FilesystemPlaceholderCreateEncryptionValueIndex[i+1]]
+}
+
+var _FilesystemPlaceholderCreateEncryptionValueValues = []FilesystemPlaceholderCreateEncryptionValue{1, 2}
+
+var _FilesystemPlaceholderCreateEncryptionValueNameToValueMap = map[string]FilesystemPlaceholderCreateEncryptionValue{
+	_FilesystemPlaceholderCreateEncryptionValueName[0:7]:  1,
+	_FilesystemPlaceholderCreateEncryptionValueName[7:10]: 2,
+}
+
+// FilesystemPlaceholderCreateEncryptionValueString retrieves an enum value from the enum constants string name.
+// Throws an error if the param is not part of the enum.
+func FilesystemPlaceholderCreateEncryptionValueString(s string) (FilesystemPlaceholderCreateEncryptionValue, error) {
+	if val, ok := _FilesystemPlaceholderCreateEncryptionValueNameToValueMap[s]; ok {
+		return val, nil
+	}
+	return 0, fmt.Errorf("%s does not belong to FilesystemPlaceholderCreateEncryptionValue values", s)
+}
+
+// FilesystemPlaceholderCreateEncryptionValueValues returns all values of the enum
+func FilesystemPlaceholderCreateEncryptionValueValues() []FilesystemPlaceholderCreateEncryptionValue {
+	return _FilesystemPlaceholderCreateEncryptionValueValues
+}
+
+// IsAFilesystemPlaceholderCreateEncryptionValue returns "true" if the value is listed in the enum definition. "false" otherwise
+func (i FilesystemPlaceholderCreateEncryptionValue) IsAFilesystemPlaceholderCreateEncryptionValue() bool {
+	for _, v := range _FilesystemPlaceholderCreateEncryptionValueValues {
+		if i == v {
+			return true
+		}
+	}
+	return false
+}

zfs/placeholder.go

@@ -80,7 +80,15 @@ func ZFSGetFilesystemPlaceholderState(ctx context.Context, p *DatasetPath) (stat
 	return state, nil
 }
 
-func ZFSCreatePlaceholderFilesystem(ctx context.Context, fs *DatasetPath, parent *DatasetPath) (err error) {
+//go:generate enumer -type=FilesystemPlaceholderCreateEncryptionValue -trimprefix=FilesystemPlaceholderCreateEncryption
+type FilesystemPlaceholderCreateEncryptionValue int
+
+const (
+	FilesystemPlaceholderCreateEncryptionInherit FilesystemPlaceholderCreateEncryptionValue = 1 << iota
+	FilesystemPlaceholderCreateEncryptionOff
+)
+
+func ZFSCreatePlaceholderFilesystem(ctx context.Context, fs *DatasetPath, parent *DatasetPath, encryption FilesystemPlaceholderCreateEncryptionValue) (err error) {
 	if fs.Length() == 1 {
 		return fmt.Errorf("cannot create %q: pools cannot be created with zfs create", fs.ToString())
 	}
@@ -90,11 +98,19 @@ func ZFSCreatePlaceholderFilesystem(ctx context.Context, fs *DatasetPath, parent
 		"-o", fmt.Sprintf("%s=%s", PlaceholderPropertyName, placeholderPropertyOn),
 		"-o", "mountpoint=none",
 	}
-	if parentEncrypted, err := ZFSGetEncryptionEnabled(ctx, parent.ToString()); err != nil {
-		return errors.Wrap(err, "cannot determine encryption support")
-	} else if parentEncrypted {
-		cmdline = append(cmdline, "-o", "encryption=off")
+
+	if !encryption.IsAFilesystemPlaceholderCreateEncryptionValue() {
+		panic(encryption)
 	}
+	switch encryption {
+	case FilesystemPlaceholderCreateEncryptionInherit:
+		// no-op
+	case FilesystemPlaceholderCreateEncryptionOff:
+		cmdline = append(cmdline, "-o", "encryption=off")
+	default:
+		panic(encryption)
+	}
+
 	cmdline = append(cmdline, fs.ToString())
 	cmd := zfscmd.CommandContext(ctx, ZFS_BINARY, cmdline...)
 
@@ -148,3 +164,34 @@ func ZFSMigrateHashBasedPlaceholderToCurrent(ctx context.Context, fs *DatasetPat
 	}
 	return &report, nil
 }
+
+func ZFSListPlaceholderFilesystemsWithAdditionalProps(ctx context.Context, root string, additionalProps []string) (map[string]*ZFSProperties, error) {
+
+	props := []string{PlaceholderPropertyName}
+	if len(additionalProps) > 0 {
+		props = append(props, additionalProps...)
+	}
+
+	propsByFS, err := zfsGetRecursive(ctx, root, -1, []string{"filesystem", "volume"}, props, SourceAny)
+	if err != nil {
+		return nil, errors.Wrapf(err, "cannot get placeholder filesystems under %q", root)
+	}
+
+	filtered := make(map[string]*ZFSProperties)
+	for fs, props := range propsByFS {
+		details := props.GetDetails(PlaceholderPropertyName)
+		if details.Source != SourceLocal {
+			continue
+		}
+		fsp, err := NewDatasetPath(fs)
+		if err != nil {
+			return nil, errors.Wrapf(err, "zfs get returned invalid dataset path %q", fs)
+		}
+		if !isLocalPlaceholderPropertyValuePlaceholder(fsp, details.Value) {
+			continue
+		}
+		filtered[fs] = props
+	}
+
+	return filtered, nil
+}

zfs/propertysource_enumer.go

@@ -38,14 +38,14 @@ func (i PropertySource) String() string {
 		return _PropertySourceName_3
 	case i == 32:
 		return _PropertySourceName_4
-	case i == 18446744073709551615:
+	case i == 4294967295:
 		return _PropertySourceName_5
 	default:
 		return fmt.Sprintf("PropertySource(%d)", i)
 	}
 }
 
-var _PropertySourceValues = []PropertySource{1, 2, 4, 8, 16, 32, 18446744073709551615}
+var _PropertySourceValues = []PropertySource{1, 2, 4, 8, 16, 32, 4294967295}
 
 var _PropertySourceNameToValueMap = map[string]PropertySource{
 	_PropertySourceName_0[0:5]:  1,
@@ -54,7 +54,7 @@ var _PropertySourceNameToValueMap = map[string]PropertySource{
 	_PropertySourceName_2[0:4]:  8,
 	_PropertySourceName_3[0:9]:  16,
 	_PropertySourceName_4[0:8]:  32,
-	_PropertySourceName_5[0:3]:  18446744073709551615,
+	_PropertySourceName_5[0:3]:  4294967295,
 }
 
 // PropertySourceString retrieves an enum value from the enum constants string name.

zfs/zfs.go

@@ -7,6 +7,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"math"
 	"os"
 	"os/exec"
 	"regexp"
@@ -14,7 +15,6 @@ import (
 	"strconv"
 	"strings"
 	"sync"
-	"time"
 
 	"github.com/pkg/errors"
 	"github.com/prometheus/client_golang/prometheus"
@@ -26,11 +26,6 @@ import (
 	"github.com/zrepl/zrepl/zfs/zfscmd"
 )
 
-var (
-	ZFSSendPipeCapacityHint = int(envconst.Int64("ZFS_SEND_PIPE_CAPACITY_HINT", 1<<25))
-	ZFSRecvPipeCapacityHint = int(envconst.Int64("ZFS_RECV_PIPE_CAPACITY_HINT", 1<<25))
-)
-
 type DatasetPath struct {
 	comps []string
 }
@@ -328,8 +323,8 @@ func absVersion(fs string, v *ZFSSendArgVersion) (full string, err error) {
 }
 
 func pipeWithCapacityHint(capacity int) (r, w *os.File, err error) {
-	if capacity <= 0 {
-		panic(fmt.Sprintf("capacity must be positive %v", capacity))
+	if capacity < 0 {
+		panic(fmt.Sprintf("capacity must be non-negative, got %v", capacity))
 	}
 	stdoutReader, stdoutWriter, err := os.Pipe()
 	if err != nil {
@@ -339,60 +334,122 @@ func pipeWithCapacityHint(capacity int) (r, w *os.File, err error) {
 	return stdoutReader, stdoutWriter, nil
 }
 
+type sendStreamState int
+
+const (
+	sendStreamOpen sendStreamState = iota
+	sendStreamClosed
+)
+
 type SendStream struct {
 	cmd          *zfscmd.Cmd
 	kill         context.CancelFunc
-
-	closeMtx     sync.Mutex
-	stdoutReader *os.File
+	stdoutReader io.ReadCloser // not *os.File for mocking during platformtest
 	stderrBuf    *circlog.CircularLog
-	opErr        error
+
+	mtx     sync.Mutex
+	state   sendStreamState
+	exitErr *ZFSError
 }
 
-func (s *SendStream) Read(p []byte) (n int, err error) {
-	s.closeMtx.Lock()
-	opErr := s.opErr
-	s.closeMtx.Unlock()
-	if opErr != nil {
-		return 0, opErr
-	}
+func (s *SendStream) Read(p []byte) (n int, _ error) {
+	s.mtx.Lock()
+	defer s.mtx.Unlock()
 
-	n, err = s.stdoutReader.Read(p)
-	if err != nil {
-		debug("sendStream: read err: %T %s", err, err)
-		// TODO we assume here that any read error is permanent
-		// which is most likely the case for a local zfs send
-		kwerr := s.killAndWait(err)
-		debug("sendStream: killAndWait n=%v err= %T %s", n, kwerr, kwerr)
-		// TODO we assume here that any read error is permanent
-		return n, kwerr
+	switch s.state {
+	case sendStreamClosed:
+		return 0, os.ErrClosed
+
+	case sendStreamOpen:
+		n, readErr := s.stdoutReader.Read(p)
+		if readErr != nil {
+			debug("sendStream: read: readErr=%T %s", readErr, readErr)
+			if readErr == io.EOF {
+				// io.EOF must be bubbled up as is so that consumers can handle it properly.
+				return n, readErr
+			}
+			// Assume that the error is not retryable.
+			// Try to kill now so that we can return a nice *ZFSError with captured stderr.
+			// If the kill doesn't work, it doesn't matter because the caller must by contract call Close() anyways.
+			killErr := s.killAndWait()
+			debug("sendStream: read: killErr=%T %s", killErr, killErr)
+			if killErr == nil {
+				s.state = sendStreamClosed
+				return n, s.exitErr // return the nice error
+			} else {
+				// we remain open so that we retry
+				return n, readErr // return the normal error
+			}
+		}
+		return n, readErr
+
+	default:
+		panic("unreachable")
 	}
-	return n, err
 }
 
 func (s *SendStream) Close() error {
 	debug("sendStream: close called")
-	return s.killAndWait(nil)
+	s.mtx.Lock()
+	defer s.mtx.Unlock()
+
+	switch s.state {
+	case sendStreamOpen:
+		err := s.killAndWait()
+		if err != nil {
+			return err
+		} else {
+			s.state = sendStreamClosed
+			return nil
+		}
+	case sendStreamClosed:
+		return os.ErrClosed
+	default:
+		panic("unreachable")
+	}
 }
 
-func (s *SendStream) killAndWait(precedingReadErr error) error {
+// returns nil iff the child process is gone (has been successfully waited upon)
+// in that case, s.exitErr is set
+func (s *SendStream) killAndWait() error {
 
 	debug("sendStream: killAndWait enter")
 	defer debug("sendStream: killAndWait leave")
-	if precedingReadErr == io.EOF {
-		// give the zfs process a little bit of time to terminate itself
-		// if it holds this deadline, exitErr will be nil
-		time.AfterFunc(200*time.Millisecond, s.kill)
-	} else {
+
+	// send SIGKILL
 	s.kill()
+
+	// Close our read-end of the pipe.
+	//
+	// We must do this before .Wait() because in some (not all) versions/build configs of ZFS,
+	// `zfs send` uses a separate kernel thread (taskq) to write the send stream (function `dump_bytes`).
+	// The `zfs send` thread then waits uinterruptably for the taskq thread to finish the write.
+	// And signalling the `zfs send` thread doesn't propagate to the taskq thread.
+	// So we end up in a state where we .Wait() forever.
+	// (See https://github.com/openzfs/zfs/issues/12500 and
+	//  https://github.com/zrepl/zrepl/issues/495#issuecomment-902530043)
+	//
+	// By closing our read end of the pipe before .Wait(), we unblock the taskq thread if there is any.
+	// If there is no separate taskq thread, the SIGKILL to `zfs end` would suffice and be most precise,
+	// but due to the circumstances above, there is no other portable & robust way.
+	//
+	// However, the fallout from closing the pipe is that (in non-taskq builds) `zfs sends` will get a SIGPIPE.
+	// And on Linux, that SIGPIPE appears to win over the previously issued SIGKILL.
+	// And thus, on Linux, the `zfs send` will be killed by the default SIGPIPE handler.
+	// We can observe this in the WaitStatus below.
+	// This behavior is slightly annoying because the *exec.ExitError's message ("signal: broken pipe")
+	// isn't as clear as ("signal: killed").
+	// However, it seems like we just have to live with that. (covered by platformtest)
+	var closePipeErr error
+	if s.stdoutReader != nil {
+		closePipeErr = s.stdoutReader.Close()
+		if closePipeErr == nil {
+			// avoid double-closes in case waiting below doesn't work
+			// and someone attempts Close again
+			s.stdoutReader = nil
+		} else {
+			return closePipeErr
 		}
-
-	// allow async kills from Close(), that's why we only take the mutex here
-	s.closeMtx.Lock()
-	defer s.closeMtx.Unlock()
-
-	if s.opErr != nil {
-		return s.opErr
 	}
 
 	waitErr := s.cmd.Wait()
@@ -407,39 +464,30 @@ func (s *SendStream) killAndWait(precedingReadErr error) error {
 		}
 	}
 
-	// now, after we know the program exited do we close the pipe
-	var closePipeErr error
-	if s.stdoutReader != nil {
-		closePipeErr = s.stdoutReader.Close()
-		if closePipeErr == nil {
-			// avoid double-closes in case anything below doesn't work
-			// and someone calls Close again
-			s.stdoutReader = nil
-		} else {
-			return closePipeErr
-		}
-	}
+	// invariant: at this point, the child is gone and we cleaned up everything related to the SendStream
 
-	// we managed to tear things down, no let's give the user some pretty *ZFSError
 	if exitErr != nil {
-		s.opErr = &ZFSError{
+		// zfs send exited with an error or was killed by a signal.
+		s.exitErr = &ZFSError{
 			Stderr:  []byte(s.stderrBuf.String()),
 			WaitErr: exitErr,
 		}
 	} else {
-		s.opErr = precedingReadErr
+		// zfs send exited successfully (we know that since waitErr was either nil or wasn't an *exec.ExitError)
+		s.exitErr = nil
 	}
 
-	// detect the edge where we're called from s.Read
-	// after the pipe EOFed and zfs send exited without errors
-	// this is actually the "hot" / nice path
-	if exitErr == nil && precedingReadErr == io.EOF {
-		return precedingReadErr
+	return nil
 }
 
-	return s.opErr
+func (s *SendStream) TestOnly_ReplaceStdoutReader(f io.ReadCloser) (prev io.ReadCloser) {
+	prev = s.stdoutReader
+	s.stdoutReader = f
+	return prev
 }
 
+func (s *SendStream) TestOnly_ExitErr() *ZFSError { return s.exitErr }
+
 // NOTE: When updating this struct, make sure to update funcs Validate ValidateCorrespondsToResumeToken
 type ZFSSendArgVersion struct {
 	RelName string
@@ -858,7 +906,7 @@ func ZFSSend(ctx context.Context, sendArgs ZFSSendArgsValidated) (*SendStream, e
 	ctx, cancel := context.WithCancel(ctx)
 
 	// setup stdout with an os.Pipe to control pipe buffer size
-	stdoutReader, stdoutWriter, err := pipeWithCapacityHint(ZFSSendPipeCapacityHint)
+	stdoutReader, stdoutWriter, err := pipeWithCapacityHint(getPipeCapacityHint("ZFS_SEND_PIPE_CAPACITY_HINT"))
 	if err != nil {
 		cancel()
 		return nil, err
@@ -913,7 +961,7 @@ type DrySendInfo struct {
 	Type         DrySendType
 	Filesystem   string // parsed from To field
 	From, To     string // direct copy from ZFS output
-	SizeEstimate int64  // -1 if size estimate is not possible
+	SizeEstimate uint64 // 0 if size estimate is not possible
 }
 
 var (
@@ -986,11 +1034,10 @@ func (s *DrySendInfo) unmarshalInfoLine(l string) (regexMatched bool, err error)
 		// see https://github.com/zrepl/zrepl/issues/289
 		fields["size"] = "0"
 	}
-	s.SizeEstimate, err = strconv.ParseInt(fields["size"], 10, 64)
+	s.SizeEstimate, err = strconv.ParseUint(fields["size"], 10, 64)
 	if err != nil {
 		return true, fmt.Errorf("cannot not parse size: %s", err)
 	}
-
 	return true, nil
 }
 
@@ -1000,6 +1047,7 @@ func ZFSSendDry(ctx context.Context, sendArgs ZFSSendArgsValidated) (_ *DrySendI
 
 	if sendArgs.From != nil && strings.Contains(sendArgs.From.RelName, "#") {
 		/* TODO:
+		 * XXX feature check & support this as well
 		 * ZFS at the time of writing does not support dry-run send because size-estimation
 		 * uses fromSnap's deadlist. However, for a bookmark, that deadlist no longer exists.
 		 * Redacted send & recv will bring this functionality, see
@@ -1018,7 +1066,7 @@ func ZFSSendDry(ctx context.Context, sendArgs ZFSSendArgsValidated) (_ *DrySendI
 			Filesystem:   sendArgs.FS,
 			From:         fromAbs,
 			To:           toAbs,
-			SizeEstimate: -1}, nil
+			SizeEstimate: 0}, nil
 	}
 
 	args := make([]string, 0)
@@ -1038,6 +1086,19 @@ func ZFSSendDry(ctx context.Context, sendArgs ZFSSendArgsValidated) (_ *DrySendI
 	if err := si.unmarshalZFSOutput(output); err != nil {
 		return nil, fmt.Errorf("could not parse zfs send -n output: %s", err)
 	}
+
+	// There is a bug in OpenZFS where it estimates the size incorrectly.
+	// - zrepl: https://github.com/zrepl/zrepl/issues/463
+	// - resulting upstream bug: https://github.com/openzfs/zfs/issues/12265
+	//
+	// The wrong estimates are easy to detect because they are absurdly large.
+	// NB: we're doing the workaround for this late so that the test cases are not affected.
+	sizeEstimateThreshold := envconst.Uint64("ZREPL_ZFS_SEND_SIZE_ESTIMATE_INCORRECT_THRESHOLD", math.MaxInt64)
+	if sizeEstimateThreshold != 0 && si.SizeEstimate >= sizeEstimateThreshold {
+		debug("size estimate exceeds threshold %v, working around it: %#v %q", sizeEstimateThreshold, si, args)
+		si.SizeEstimate = 0
+	}
+
 	return &si, nil
 }
 
@@ -1160,7 +1221,7 @@ func ZFSRecv(ctx context.Context, fs string, v *ZFSSendArgVersion, stream io.Rea
 
 	stderr := bytes.NewBuffer(make([]byte, 0, RecvStderrBufSiz))
 
-	stdin, stdinWriter, err := pipeWithCapacityHint(ZFSRecvPipeCapacityHint)
+	stdin, stdinWriter, err := pipeWithCapacityHint(getPipeCapacityHint("ZFS_RECV_PIPE_CAPACITY_HINT"))
 	if err != nil {
 		return err
 	}
@@ -1446,7 +1507,7 @@ func tryDatasetDoesNotExist(expectPath string, stderr []byte) *DatasetDoesNotExi
 }
 
 //go:generate enumer -type=PropertySource -trimprefix=Source
-type PropertySource uint
+type PropertySource uint32
 
 const (
 	SourceLocal PropertySource = 1 << iota
@@ -1506,8 +1567,18 @@ func (s PropertySource) zfsGetSourceFieldPrefixes() []string {
 	return prefixes
 }
 
-func zfsGet(ctx context.Context, path string, props []string, allowedSources PropertySource) (*ZFSProperties, error) {
-	args := []string{"get", "-Hp", "-o", "property,value,source", strings.Join(props, ","), path}
+func zfsGetRecursive(ctx context.Context, path string, depth int, dstypes []string, props []string, allowedSources PropertySource) (map[string]*ZFSProperties, error) {
+	args := []string{"get", "-Hp", "-o", "name,property,value,source"}
+	if depth != 0 {
+		args = append(args, "-r")
+		if depth != -1 {
+			args = append(args, "-d", fmt.Sprintf("%d", depth))
+		}
+	}
+	if len(dstypes) > 0 {
+		args = append(args, "-t", strings.Join(dstypes, ","))
+	}
+	args = append(args, strings.Join(props, ","), path)
 	cmd := zfscmd.CommandContext(ctx, ZFS_BINARY, args...)
 	stdout, err := cmd.Output()
 	if err != nil {
@@ -1527,36 +1598,67 @@ func zfsGet(ctx context.Context, path string, props []string, allowedSources Pro
 	}
 	o := string(stdout)
 	lines := strings.Split(o, "\n")
-	if len(lines) < 1 || // account for newlines
-		len(lines)-1 != len(props) {
-		return nil, fmt.Errorf("zfs get did not return the number of expected property values")
-	}
-	res := &ZFSProperties{
-		make(map[string]PropertyValue, len(lines)),
-	}
+	propsByFS := make(map[string]*ZFSProperties)
 	allowedPrefixes := allowedSources.zfsGetSourceFieldPrefixes()
-	for _, line := range lines[:len(lines)-1] {
+	for _, line := range lines[:len(lines)-1] { // last line is an empty line due to how strings.Split works
 		fields := strings.FieldsFunc(line, func(r rune) bool {
 			return r == '\t'
 		})
-		if len(fields) != 3 {
-			return nil, fmt.Errorf("zfs get did not return property,value,source tuples")
+		if len(fields) != 4 {
+			return nil, fmt.Errorf("zfs get did not return name,property,value,source tuples")
 		}
 		for _, p := range allowedPrefixes {
 			// prefix-match so that SourceAny (= "") works
-			if strings.HasPrefix(fields[2], p) {
-				source, err := parsePropertySource(fields[2])
+			if strings.HasPrefix(fields[3], p) {
+				source, err := parsePropertySource(fields[3])
 				if err != nil {
 					return nil, errors.Wrap(err, "parse property source")
 				}
-				res.m[fields[0]] = PropertyValue{
-					Value:  fields[1],
+				fsProps, ok := propsByFS[fields[0]]
+				if !ok {
+					fsProps = &ZFSProperties{
+						make(map[string]PropertyValue),
+					}
+				}
+				if _, ok := fsProps.m[fields[1]]; ok {
+					return nil, errors.Errorf("duplicate property %q for dataset %q", fields[1], fields[0])
+				}
+				fsProps.m[fields[1]] = PropertyValue{
+					Value:  fields[2],
 					Source: source,
 				}
+				propsByFS[fields[0]] = fsProps
 				break
 			}
 		}
 	}
+	// validate we got expected output
+	for fs, fsProps := range propsByFS {
+		if len(fsProps.m) != len(props) {
+			return nil, errors.Errorf("zfs get did not return all requested values for dataset %q\noutput was:\n%s", fs, o)
+		}
+	}
+	return propsByFS, nil
+}
+
+func zfsGet(ctx context.Context, path string, props []string, allowedSources PropertySource) (*ZFSProperties, error) {
+	propMap, err := zfsGetRecursive(ctx, path, 0, nil, props, allowedSources)
+	if err != nil {
+		return nil, err
+	}
+	if len(propMap) == 0 {
+		// XXX callers expect to always get a result here
+		// They will observe props.Get("propname") == ""
+		// We should change .Get to return a tuple, or an error, or whatever.
+		return &ZFSProperties{make(map[string]PropertyValue)}, nil
+	}
+	if len(propMap) != 1 {
+		return nil, errors.Errorf("zfs get unexpectedly returned properties for multiple datasets")
+	}
+	res, ok := propMap[path]
+	if !ok {
+		return nil, errors.Errorf("zfs get returned properties for a different dataset that requested")
+	}
 	return res, nil
 }
 

zfs/zfs_pipe.go

@@ -1,3 +1,4 @@
+//go:build !linux
 // +build !linux
 
 package zfs
@@ -7,10 +8,14 @@ import (
 	"sync"
 )
 
+func getPipeCapacityHint(envvar string) int {
+	return 0 // not supported
+}
+
 var zfsPipeCapacityNotSupported sync.Once
 
 func trySetPipeCapacity(p *os.File, capacity int) {
-	if debugEnabled {
+	if debugEnabled && capacity != 0 {
 		zfsPipeCapacityNotSupported.Do(func() {
 			debug("trySetPipeCapacity error: OS does not support setting pipe capacity")
 		})

zfs/zfs_pipe_linux.go

@@ -3,11 +3,33 @@ package zfs
 import (
 	"errors"
 	"fmt"
+	"io/ioutil"
 	"os"
+	"strconv"
+	"strings"
 
 	"golang.org/x/sys/unix"
+
+	"github.com/zrepl/zrepl/util/envconst"
 )
 
+func getPipeCapacityHint(envvar string) int {
+	var capacity int64 = 1 << 25
+
+	// Work around a race condition in Linux >= 5.8 related to pipe resizing.
+	// https://github.com/zrepl/zrepl/issues/424#issuecomment-800370928
+	// https://bugzilla.kernel.org/show_bug.cgi?id=212295
+	if _, err := os.Stat("/proc/sys/fs/pipe-max-size"); err == nil {
+		if dat, err := ioutil.ReadFile("/proc/sys/fs/pipe-max-size"); err == nil {
+			if capacity, err = strconv.ParseInt(strings.TrimSpace(string(dat)), 10, 64); err != nil {
+				capacity = 1 << 25
+			}
+		}
+	}
+
+	return int(envconst.Int64(envvar, capacity))
+}
+
 func trySetPipeCapacity(p *os.File, capacity int) {
 	res, err := unix.FcntlInt(p.Fd(), unix.F_SETPIPE_SZ, capacity)
 	if err != nil {

zfs/zfscmd/zfscmd.go

@@ -209,3 +209,7 @@ func (c *Cmd) Runtime() time.Duration {
 	}
 	return c.waitReturnedAt.Sub(c.startedAt)
 }
+
+func (c *Cmd) TestOnly_ExecCmd() *exec.Cmd {
+	return c.cmd
+}