doc: fixup 0.3 changelog 05f1237a6d

refs #219
fixes #329

.github/FUNDING.yml

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

README.md

@@ -2,7 +2,8 @@
 [![Language: Go](https://img.shields.io/badge/language-Go-6ad7e5.svg)](https://golang.org/)
 [![User Docs](https://img.shields.io/badge/docs-web-blue.svg)](https://zrepl.github.io)
 [![Donate via Patreon](https://img.shields.io/endpoint.svg?url=https%3A%2F%2Fshieldsio-patreon.herokuapp.com%2Fzrepl%2Fpledges&style=flat&color=yellow)](https://www.patreon.com/zrepl)
-[![Donate via Liberapay](https://img.shields.io/liberapay/receives/zrepl.svg?logo=liberapay)](https://liberapay.com/zrepl/donate)
+[![Donate via 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)
 

config/config.go

@@ -76,7 +76,12 @@ type SnapJob struct {
 }
 
 type SendOptions struct {
-	Encrypted bool `yaml:"encrypted"`
+	Encrypted bool                 `yaml:"encrypted"`
+	StepHolds SendOptionsStepHolds `yaml:"step_holds,optional"`
+}
+
+type SendOptionsStepHolds struct {
+	DisableIncremental bool `yaml:"disable_incremental,optional"`
 }
 
 var _ yaml.Defaulter = (*SendOptions)(nil)
@@ -309,11 +314,6 @@ type PruneKeepNotReplicated struct {
 	KeepSnapshotAtCursor bool   `yaml:"keep_snapshot_at_cursor,optional,default=true"`
 }
 
-type PruneKeepStepHolds struct {
-	Type             string   `yaml:"type"`
-	AdditionalJobIds []string `yaml:"additional_job_ids,optional"`
-}
-
 type PruneKeepLastN struct {
 	Type  string `yaml:"type"`
 	Count int    `yaml:"count"`
@@ -485,7 +485,6 @@ func (t *ServeEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
 
 func (t *PruningEnum) UnmarshalYAML(u func(interface{}, bool) error) (err error) {
 	t.Ret, err = enumUnmarshal(u, map[string]interface{}{
-		"step_holds":     &PruneKeepStepHolds{},
 		"not_replicated": &PruneKeepNotReplicated{},
 		"last_n":         &PruneKeepLastN{},
 		"grid":           &PruneGrid{},

config/samples/quickstart_backup_to_external_disk.yml

@@ -0,0 +1,85 @@
+# This config serves as an example for a local zrepl installation that
+# backups the entire zpool `system` to `backuppool/zrepl/sink`
+#
+# The requirements covered by this setup are described in the zrepl documentation's
+# quick start section which inlines this example.
+#
+# CUSTOMIZATIONS YOU WILL LIKELY WANT TO APPLY:
+# - adjust the name of the production pool `system` in the `filesystems` filter of jobs `snapjob` and `push_to_derive`
+# - adjust the name of the backup pool `backuppool` in the `backuppool_sink` job
+# - adjust the occurences of `myhostname` to the name of the system you are backing up (cannot be easily changed once you start replicating)
+# - make sure the `zrepl_` prefix is not being used by any other zfs tools you might have installed (it likely isn't)
+
+jobs:
+
+# this job takes care of snapshot creation + pruning
+- name: snapjob
+  type: snap
+  filesystems: {
+      "system<": true,
+  }
+  # create snapshots with prefix `zrepl_` every 15 minutes
+  snapshotting:
+    type: periodic
+    interval: 15m
+    prefix: zrepl_
+  pruning:
+    keep:
+    # fade-out scheme for snapshots starting with `zrepl_`
+    # - keep all created in the last hour
+    # - then destroy snapshots such that we keep 24 each 1 hour apart
+    # - then destroy snapshots such that we keep 14 each 1 day apart
+    # - then destroy all older snapshots
+    - type: grid
+      grid: 1x1h(keep=all) | 24x1h | 14x1d
+      regex: "^zrepl_.*"
+    # keep all snapshots that don't have the `zrepl_` prefix
+    - type: regex
+      negate: true
+      regex: "^zrepl_.*"
+
+# This job pushes to the local sink defined in job `backuppool_sink`.
+# We trigger replication manually from the command line / udev rules using
+#  `zrepl signal wakeup push_to_drive`
+- type: push
+  name: push_to_drive
+  connect:
+    type: local
+    listener_name: backuppool_sink
+    client_identity: myhostname
+  filesystems: {
+      "system<": true
+  }
+  send:
+    encrypted: true
+    # disable incremental step holds so that
+    # - we can yank out the backup drive during replication
+    # - thereby sacrificing resumability
+    # - in exchange for the replicating snapshot not sticking around until we reconnect the backup drive
+    step_holds:
+      disable_incremental: true
+  snapshotting:
+    type: manual
+  pruning:
+    # no-op prune rule on sender (keep all snapshots), job `snapshot` takes care of this
+    keep_sender:
+    - type: regex
+      regex: ".*"
+    # retain 
+    keep_receiver:
+    # longer retention on the backup drive, we have more space there
+    - type: grid
+      grid: 1x1h(keep=all) | 24x1h | 360x1d
+      regex: "^zrepl_.*"
+    # retain all non-zrepl snapshots on the backup drive
+    - type: regex
+      negate: true
+      regex: "^zrepl_.*"
+
+# This job receives from job `push_to_drive` into `backuppool/zrepl/sink/myhostname`
+- type: sink
+  name: backuppool_sink
+  root_fs: "backuppool/zrepl/sink"
+  serve:
+    type: local
+    listener_name: backuppool_sink

config/samples/quickstart_continuous_server_backup_receiver.yml

@@ -0,0 +1,12 @@
+jobs:
+- name: sink
+  type: sink
+  serve:
+      type: tls
+      listen: ":8888"
+      ca: "/etc/zrepl/prod.crt"
+      cert: "/etc/zrepl/backups.crt"
+      key: "/etc/zrepl/backups.key"
+      client_cns:
+        - "prod"
+  root_fs: "storage/zrepl/sink"

config/samples/quickstart_continuous_server_backup_sender.yml

@@ -0,0 +1,28 @@
+jobs:
+- name: prod_to_backups
+  type: push
+  connect:
+    type: tls
+    address: "backups.example.com:8888"
+    ca: /etc/zrepl/backups.crt
+    cert: /etc/zrepl/prod.crt
+    key:  /etc/zrepl/prod.key
+    server_cn: "backups"
+  filesystems: {
+    "zroot/var/db": true,
+    "zroot/usr/home<": true,
+    "zroot/usr/home/paranoid": false
+  }
+  snapshotting:
+    type: periodic
+    prefix: zrepl_
+    interval: 10m
+  pruning:
+    keep_sender:
+    - type: not_replicated
+    - type: last_n
+      count: 10
+    keep_receiver:
+    - type: grid
+      grid: 1x1h(keep=all) | 24x1h | 30x1d | 6x30d
+      regex: "^zrepl_"

daemon/control.go

@@ -120,7 +120,13 @@ func (j *controlJob) Run(ctx context.Context) {
 		jsonResponder{log, func() (interface{}, error) {
 			jobs := j.jobs.status()
 			globalZFS := zfscmd.GetReport()
-			s := Status{Jobs: jobs, Global: GlobalStatus{ZFSCmds: globalZFS}}
+			envconstReport := envconst.GetReport()
+			s := Status{
+				Jobs: jobs,
+				Global: GlobalStatus{
+					ZFSCmds:  globalZFS,
+					Envconst: envconstReport,
+				}}
 			return s, nil
 		}})
 

daemon/daemon.go

@@ -14,6 +14,7 @@ import (
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/zrepl/zrepl/daemon/logging/trace"
 	"github.com/zrepl/zrepl/endpoint"
+	"github.com/zrepl/zrepl/util/envconst"
 
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/job"
@@ -94,6 +95,7 @@ func Run(ctx context.Context, conf *config.Config) error {
 	}
 
 	// register global (=non job-local) metrics
+	version.PrometheusRegister(prometheus.DefaultRegisterer)
 	zfscmd.RegisterMetrics(prometheus.DefaultRegisterer)
 	trace.RegisterMetrics(prometheus.DefaultRegisterer)
 	endpoint.RegisterMetrics(prometheus.DefaultRegisterer)
@@ -150,7 +152,8 @@ type Status struct {
 }
 
 type GlobalStatus struct {
-	ZFSCmds *zfscmd.Report
+	ZFSCmds  *zfscmd.Report
+	Envconst *envconst.Report
 }
 
 func (s *jobs) status() map[string]*job.Status {

daemon/job/active.go

@@ -152,9 +152,10 @@ func modePushFromConfig(g *config.Global, in *config.PushJob, jobID endpoint.Job
 	}
 
 	m.senderConfig = &endpoint.SenderConfig{
-		FSF:     fsf,
-		Encrypt: &zfs.NilBool{B: in.Send.Encrypted},
-		JobID:   jobID,
+		FSF:                         fsf,
+		Encrypt:                     &zfs.NilBool{B: in.Send.Encrypted},
+		DisableIncrementalStepHolds: in.Send.StepHolds.DisableIncremental,
+		JobID:                       jobID,
 	}
 	m.plannerPolicy = &logic.PlannerPolicy{
 		EncryptedSend: logic.TriFromBool(in.Send.Encrypted),

daemon/job/passive.go

@@ -79,9 +79,10 @@ func modeSourceFromConfig(g *config.Global, in *config.SourceJob, jobID endpoint
 		return nil, errors.Wrap(err, "cannot build filesystem filter")
 	}
 	m.senderConfig = &endpoint.SenderConfig{
-		FSF:     fsf,
-		Encrypt: &zfs.NilBool{B: in.Send.Encrypted},
-		JobID:   jobID,
+		FSF:                         fsf,
+		Encrypt:                     &zfs.NilBool{B: in.Send.Encrypted},
+		DisableIncrementalStepHolds: in.Send.StepHolds.DisableIncremental,
+		JobID:                       jobID,
 	}
 
 	if m.snapper, err = snapper.FromConfig(g, fsf, in.Snapshotting); err != nil {

daemon/job/snapjob.go

@@ -175,6 +175,8 @@ func (j *SnapJob) doPrune(ctx context.Context) {
 		FSF:   j.fsfilter,
 		// FIXME encryption setting is irrelevant for SnapJob because the endpoint is only used as pruner.Target
 		Encrypt: &zfs.NilBool{B: true},
+		// FIXME DisableIncrementalStepHolds setting is irrelevant for SnapJob because the endpoint is only used as pruner.Target
+		DisableIncrementalStepHolds: false,
 	})
 	j.pruner = j.prunerFactory.BuildLocalPruner(ctx, sender, alwaysUpToDateReplicationCursorHistory{sender})
 	log.Info("start pruning")

daemon/pruner.v2/fsstate_enumer.go

@@ -1,72 +0,0 @@
-// Code generated by "enumer -type=FSState -json"; DO NOT EDIT.
-
-//
-package pruner
-
-import (
-	"encoding/json"
-	"fmt"
-)
-
-const _FSStateName = "FSStateInitializedFSStatePlanningFSStatePlanErrFSStateExecutingFSStateExecuteErrFSStateExecuteSuccess"
-
-var _FSStateIndex = [...]uint8{0, 18, 33, 47, 63, 80, 101}
-
-func (i FSState) String() string {
-	if i < 0 || i >= FSState(len(_FSStateIndex)-1) {
-		return fmt.Sprintf("FSState(%d)", i)
-	}
-	return _FSStateName[_FSStateIndex[i]:_FSStateIndex[i+1]]
-}
-
-var _FSStateValues = []FSState{0, 1, 2, 3, 4, 5}
-
-var _FSStateNameToValueMap = map[string]FSState{
-	_FSStateName[0:18]:   0,
-	_FSStateName[18:33]:  1,
-	_FSStateName[33:47]:  2,
-	_FSStateName[47:63]:  3,
-	_FSStateName[63:80]:  4,
-	_FSStateName[80:101]: 5,
-}
-
-// FSStateString retrieves an enum value from the enum constants string name.
-// Throws an error if the param is not part of the enum.
-func FSStateString(s string) (FSState, error) {
-	if val, ok := _FSStateNameToValueMap[s]; ok {
-		return val, nil
-	}
-	return 0, fmt.Errorf("%s does not belong to FSState values", s)
-}
-
-// FSStateValues returns all values of the enum
-func FSStateValues() []FSState {
-	return _FSStateValues
-}
-
-// IsAFSState returns "true" if the value is listed in the enum definition. "false" otherwise
-func (i FSState) IsAFSState() bool {
-	for _, v := range _FSStateValues {
-		if i == v {
-			return true
-		}
-	}
-	return false
-}
-
-// MarshalJSON implements the json.Marshaler interface for FSState
-func (i FSState) MarshalJSON() ([]byte, error) {
-	return json.Marshal(i.String())
-}
-
-// UnmarshalJSON implements the json.Unmarshaler interface for FSState
-func (i *FSState) UnmarshalJSON(data []byte) error {
-	var s string
-	if err := json.Unmarshal(data, &s); err != nil {
-		return fmt.Errorf("FSState should be a string, got %s", data)
-	}
-
-	var err error
-	*i, err = FSStateString(s)
-	return err
-}

daemon/pruner.v2/pruner.go

@@ -1,454 +0,0 @@
-package pruner
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"os"
-
-	"github.com/pkg/errors"
-	"github.com/zrepl/zrepl/daemon/logging"
-	"github.com/zrepl/zrepl/daemon/logging/trace"
-	"github.com/zrepl/zrepl/endpoint"
-	"github.com/zrepl/zrepl/pruning"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-type Pruner struct {
-	fsfilter  endpoint.FSFilter
-	jid       endpoint.JobID
-	side      Side
-	keepRules []pruning.KeepRule
-
-	// all channels consumed by the run loop
-	reportReqs chan reportRequest
-	stopReqs   chan stopRequest
-	done       chan struct{}
-	fsListRes  chan fsListRes
-
-	state State
-
-	listFilesystemsError error       // only in state StateListFilesystemsError
-	fsPruners            []*FSPruner // only in state StateFanOutFilesystems
-}
-
-//go:generate enumer -type=State -json
-type State int
-
-const (
-	StateInitialized State = iota
-	StateListFilesystems
-	StateListFilesystemsError
-	StateFanOutFilesystems
-	StateDone
-)
-
-type Report struct {
-	State                State
-	ListFilesystemsError error       // only valid in StateListFilesystemsError
-	Filesystems          []*FSReport // valid from StateFanOutFilesystems
-}
-
-type reportRequest struct {
-	ctx   context.Context
-	reply chan *Report
-}
-
-type runRequest struct {
-	complete chan struct{}
-}
-
-type stopRequest struct {
-	complete chan struct{}
-}
-
-type fsListRes struct {
-	filesystems []*zfs.DatasetPath
-	err         error
-}
-
-type Side interface {
-	// may return both nil, indicating there is no replication position
-	GetReplicationPosition(ctx context.Context, fs string) (*zfs.FilesystemVersion, error)
-	isSide() Side
-}
-
-func NewPruner(fsfilter endpoint.FSFilter, jid endpoint.JobID, side Side, keepRules []pruning.KeepRule) *Pruner {
-	return &Pruner{
-		fsfilter,
-		jid,
-		side,
-		keepRules,
-		make(chan reportRequest),
-		make(chan stopRequest),
-		make(chan struct{}),
-		make(chan fsListRes),
-		StateInitialized,
-		nil,
-		nil,
-	}
-}
-
-func (p *Pruner) Run(ctx context.Context) *Report {
-
-	ctx, cancel := context.WithCancel(ctx)
-	defer cancel()
-
-	if p.state != StateInitialized {
-		panic("Run can onl[y be called once")
-	}
-
-	go func() {
-		fss, err := zfs.ZFSListMapping(ctx, p.fsfilter)
-		p.fsListRes <- fsListRes{fss, err}
-	}()
-
-	for {
-		select {
-		case res := <-p.fsListRes:
-			if res.err != nil {
-				p.state = StateListFilesystemsError
-				p.listFilesystemsError = res.err
-				close(p.done)
-				continue
-			}
-
-			p.state = StateFanOutFilesystems
-
-			p.fsPruners = make([]*FSPruner, len(res.filesystems))
-			_, add, end := trace.WithTaskGroup(ctx, "pruner-fan-out-fs")
-			for i, fs := range res.filesystems {
-				p.fsPruners[i] = NewFSPruner(p.jid, p.side, p.keepRules, fs)
-				add(func(ctx context.Context) {
-					p.fsPruners[i].Run(ctx)
-				})
-			}
-			go func() {
-				end()
-				close(p.done)
-			}()
-
-		case req := <-p.stopReqs:
-			cancel()
-			go func() {
-				<-p.done
-				close(req.complete)
-			}()
-		case req := <-p.reportReqs:
-			req.reply <- p.report(req.ctx)
-		case <-p.done:
-			p.state = StateDone
-			return p.report(ctx)
-		}
-	}
-}
-
-func (p *Pruner) Report(ctx context.Context) *Report {
-	req := reportRequest{
-		ctx:   ctx,
-		reply: make(chan *Report, 1),
-	}
-	select {
-	case p.reportReqs <- req:
-		return <-req.reply
-	case <-ctx.Done():
-		return nil
-	case <-p.done:
-		return nil
-	}
-}
-
-func (p *Pruner) report(ctx context.Context) *Report {
-	fsreports := make([]*FSReport, len(p.fsPruners))
-	for i := range fsreports {
-		fsreports[i] = p.fsPruners[i].report()
-	}
-	return &Report{
-		State:                p.state,
-		ListFilesystemsError: p.listFilesystemsError,
-		Filesystems:          fsreports,
-	}
-}
-
-// implements pruning.Snapshot
-type snapshot struct {
-	replicated bool
-	stepHolds  []pruning.StepHold
-	zfs.FilesystemVersion
-
-	state     SnapState
-	destroyOp *zfs.DestroySnapOp
-}
-
-//go:generate enumer -type=SnapState -json
-type SnapState int
-
-const (
-	SnapStateInitialized SnapState = iota
-	SnapStateKeeping
-	SnapStateDeletePending
-	SnapStateDeleteAttempted
-)
-
-// implements pruning.StepHold
-type stepHold struct {
-	endpoint.Abstraction
-}
-
-func (s snapshot) Replicated() bool              { return s.replicated }
-func (s snapshot) StepHolds() []pruning.StepHold { return s.stepHolds }
-
-func (s stepHold) GetJobID() endpoint.JobID { return *s.Abstraction.GetJobID() }
-
-type FSPruner struct {
-	jid       endpoint.JobID
-	side      Side
-	keepRules []pruning.KeepRule
-	fsp       *zfs.DatasetPath
-
-	state FSState
-
-	// all channels consumed by the run loop
-	planned    chan fsPlanRes
-	executed   chan fsExecuteRes
-	done       chan struct{}
-	reportReqs chan fsReportReq
-
-	keepList    []*snapshot // valid in FSStateExecuting and forward
-	destroyList []*snapshot // valid in FSStateExecuting and forward, field .destroyOp is invalid until FSStateExecuting is left
-
-}
-
-type fsPlanRes struct {
-	keepList    []*snapshot
-	destroyList []*snapshot
-	err         error
-}
-
-type fsExecuteRes struct {
-	completedDestroyOps []*zfs.DestroySnapOp // same len() as FSPruner.destroyList
-}
-
-type fsReportReq struct {
-	res chan *FSReport
-}
-
-type FSReport struct {
-	State    FSState
-	KeepList []*SnapReport
-	Destroy  []*SnapReport
-}
-
-type SnapReport struct {
-	State         SnapState
-	Name          string
-	Replicated    bool
-	StepHoldCount int
-	DestroyError  error
-}
-
-//go:generate enumer -type=FSState -json
-type FSState int
-
-const (
-	FSStateInitialized FSState = iota
-	FSStatePlanning
-	FSStatePlanErr
-	FSStateExecuting
-	FSStateExecuteErr
-	FSStateExecuteSuccess
-)
-
-func (s FSState) IsTerminal() bool {
-	return s == FSStatePlanErr || s == FSStateExecuteErr || s == FSStateExecuteSuccess
-}
-
-func NewFSPruner(jid endpoint.JobID, side Side, keepRules []pruning.KeepRule, fsp *zfs.DatasetPath) *FSPruner {
-	return &FSPruner{
-		jid, side, keepRules, fsp,
-		FSStateInitialized,
-		make(chan fsPlanRes),
-		make(chan fsExecuteRes),
-		make(chan struct{}),
-		make(chan fsReportReq),
-		nil, nil,
-	}
-}
-
-func (p *FSPruner) Run(ctx context.Context) *FSReport {
-
-	defer func() {
-	}()
-
-	p.state = FSStatePlanning
-
-	go func() { p.planned <- p.plan(ctx) }()
-
-out:
-	for !p.state.IsTerminal() {
-		select {
-		case res := <-p.planned:
-
-			if res.err != nil {
-				p.state = FSStatePlanErr
-				continue
-			}
-			p.state = FSStateExecuting
-			p.keepList = res.keepList
-			p.destroyList = res.destroyList
-
-			go func() { p.executed <- p.execute(ctx, p.destroyList) }()
-
-		case res := <-p.executed:
-
-			if len(res.completedDestroyOps) != len(p.destroyList) {
-				panic("impl error: completedDestroyOps is a vector corresponding to entries in p.destroyList")
-			}
-
-			var erronous []*zfs.DestroySnapOp
-			for i, op := range res.completedDestroyOps {
-				if *op.ErrOut != nil {
-					erronous = append(erronous, op)
-				}
-				p.destroyList[i].destroyOp = op
-				p.destroyList[i].state = SnapStateDeleteAttempted
-			}
-			if len(erronous) > 0 {
-				p.state = FSStateExecuteErr
-			} else {
-				p.state = FSStateExecuteSuccess
-			}
-
-			close(p.done)
-
-		case <-p.reportReqs:
-			panic("unimp")
-		case <-p.done:
-			break out
-		}
-	}
-
-	// TODO render last FS report
-	return nil
-}
-
-func (p *FSPruner) plan(ctx context.Context) fsPlanRes {
-	fs := p.fsp.ToString()
-	vs, err := zfs.ZFSListFilesystemVersions(ctx, p.fsp, zfs.ListFilesystemVersionsOptions{})
-	if err != nil {
-		return fsPlanRes{err: errors.Wrap(err, "list filesystem versions")}
-	}
-
-	allJobsStepHolds, absErrs, err := endpoint.ListAbstractions(ctx, endpoint.ListZFSHoldsAndBookmarksQuery{
-		FS: endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter{
-			FS: &fs,
-		},
-		What: endpoint.AbstractionTypeSet{
-			endpoint.AbstractionStepHold: true,
-		},
-		Concurrency: 1,
-	})
-	if err != nil {
-		return fsPlanRes{err: errors.Wrap(err, "list abstractions")}
-	}
-	if len(absErrs) > 0 {
-		logging.GetLogger(ctx, logging.SubsysPruning).WithError(endpoint.ListAbstractionsErrors(absErrs)).
-			Error("error listing some step holds, prune attempt might fail with 'dataset is busy' errors")
-	}
-
-	repPos, err := p.side.GetReplicationPosition(ctx, p.fsp.ToString())
-	if err != nil {
-		return fsPlanRes{err: errors.Wrap(err, "get replication position")}
-	}
-
-	vsAsSnaps := make([]pruning.Snapshot, len(vs))
-	for i := range vs {
-		var repPosCreateTxgOrZero uint64
-		if repPos != nil {
-			repPosCreateTxgOrZero = repPos.GetCreateTXG()
-		}
-		s := &snapshot{
-			state:             SnapStateInitialized,
-			FilesystemVersion: vs[i],
-			replicated:        vs[i].GetCreateTXG() <= repPosCreateTxgOrZero,
-		}
-		for _, h := range allJobsStepHolds {
-			if zfs.FilesystemVersionEqualIdentity(vs[i], h.GetFilesystemVersion()) {
-				s.stepHolds = append(s.stepHolds, stepHold{h})
-			}
-		}
-		vsAsSnaps[i] = s
-	}
-
-	downcastToSnapshots := func(l []pruning.Snapshot) (r []*snapshot) {
-		r = make([]*snapshot, len(l))
-		for i, e := range l {
-			r[i] = e.(*snapshot)
-		}
-		return r
-	}
-	pruningResult := pruning.PruneSnapshots(vsAsSnaps, p.keepRules)
-	remove, keep := downcastToSnapshots(pruningResult.Remove), downcastToSnapshots(pruningResult.Keep)
-	if len(remove)+len(keep) != len(vsAsSnaps) {
-		for _, s := range vsAsSnaps {
-			r, _ := json.MarshalIndent(s.(*snapshot).report(), "", "  ")
-			fmt.Fprintf(os.Stderr, "%s\n", string(r))
-		}
-		panic("indecisive")
-	}
-
-	for _, s := range remove {
-		s.state = SnapStateDeletePending
-	}
-	for _, s := range keep {
-		s.state = SnapStateKeeping
-	}
-
-	return fsPlanRes{keepList: keep, destroyList: remove, err: nil}
-}
-
-func (p *FSPruner) execute(ctx context.Context, destroyList []*snapshot) fsExecuteRes {
-	ops := make([]*zfs.DestroySnapOp, len(destroyList))
-	for i, fsv := range p.destroyList {
-		ops[i] = &zfs.DestroySnapOp{
-			Filesystem: p.fsp.ToString(),
-			Name:       fsv.GetName(),
-			ErrOut:     new(error),
-		}
-	}
-	zfs.ZFSDestroyFilesystemVersions(ctx, ops)
-
-	return fsExecuteRes{completedDestroyOps: ops}
-}
-
-func (p *FSPruner) report() *FSReport {
-	return &FSReport{
-		State:    p.state,
-		KeepList: p.reportRenderSnapReports(p.keepList),
-		Destroy:  p.reportRenderSnapReports(p.destroyList),
-	}
-}
-
-func (p *FSPruner) reportRenderSnapReports(l []*snapshot) (r []*SnapReport) {
-	r = make([]*SnapReport, len(l))
-	for i := range l {
-		r[i] = l[i].report()
-	}
-	return r
-}
-
-func (s *snapshot) report() *SnapReport {
-	var snapErr error
-	if s.state == SnapStateDeleteAttempted {
-		if *s.destroyOp.ErrOut != nil {
-			snapErr = (*s.destroyOp.ErrOut)
-		}
-	}
-	return &SnapReport{
-		State:         s.state,
-		Name:          s.Name,
-		Replicated:    s.Replicated(),
-		StepHoldCount: len(s.stepHolds),
-		DestroyError:  snapErr,
-	}
-}

daemon/pruner.v2/pruner_side.go

@@ -1,27 +0,0 @@
-package pruner
-
-import (
-	"context"
-
-	"github.com/zrepl/zrepl/endpoint"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-type SideSender struct {
-	jobID endpoint.JobID
-}
-
-func NewSideSender(jid endpoint.JobID) *SideSender {
-	return &SideSender{jid}
-}
-
-func (s *SideSender) isSide() Side { return nil }
-
-var _ Side = (*SideSender)(nil)
-
-func (s *SideSender) GetReplicationPosition(ctx context.Context, fs string) (*zfs.FilesystemVersion, error) {
-	if fs == "" {
-		panic("must not pass zero value for fs")
-	}
-	return endpoint.GetMostRecentReplicationCursorOfJob(ctx, fs, s.jobID)
-}

daemon/pruner.v2/snapstate_enumer.go

@@ -1,70 +0,0 @@
-// Code generated by "enumer -type=SnapState -json"; DO NOT EDIT.
-
-//
-package pruner
-
-import (
-	"encoding/json"
-	"fmt"
-)
-
-const _SnapStateName = "SnapStateInitializedSnapStateKeepingSnapStateDeletePendingSnapStateDeleteAttempted"
-
-var _SnapStateIndex = [...]uint8{0, 20, 36, 58, 82}
-
-func (i SnapState) String() string {
-	if i < 0 || i >= SnapState(len(_SnapStateIndex)-1) {
-		return fmt.Sprintf("SnapState(%d)", i)
-	}
-	return _SnapStateName[_SnapStateIndex[i]:_SnapStateIndex[i+1]]
-}
-
-var _SnapStateValues = []SnapState{0, 1, 2, 3}
-
-var _SnapStateNameToValueMap = map[string]SnapState{
-	_SnapStateName[0:20]:  0,
-	_SnapStateName[20:36]: 1,
-	_SnapStateName[36:58]: 2,
-	_SnapStateName[58:82]: 3,
-}
-
-// SnapStateString retrieves an enum value from the enum constants string name.
-// Throws an error if the param is not part of the enum.
-func SnapStateString(s string) (SnapState, error) {
-	if val, ok := _SnapStateNameToValueMap[s]; ok {
-		return val, nil
-	}
-	return 0, fmt.Errorf("%s does not belong to SnapState values", s)
-}
-
-// SnapStateValues returns all values of the enum
-func SnapStateValues() []SnapState {
-	return _SnapStateValues
-}
-
-// IsASnapState returns "true" if the value is listed in the enum definition. "false" otherwise
-func (i SnapState) IsASnapState() bool {
-	for _, v := range _SnapStateValues {
-		if i == v {
-			return true
-		}
-	}
-	return false
-}
-
-// MarshalJSON implements the json.Marshaler interface for SnapState
-func (i SnapState) MarshalJSON() ([]byte, error) {
-	return json.Marshal(i.String())
-}
-
-// UnmarshalJSON implements the json.Unmarshaler interface for SnapState
-func (i *SnapState) UnmarshalJSON(data []byte) error {
-	var s string
-	if err := json.Unmarshal(data, &s); err != nil {
-		return fmt.Errorf("SnapState should be a string, got %s", data)
-	}
-
-	var err error
-	*i, err = SnapStateString(s)
-	return err
-}

daemon/pruner.v2/state_enumer.go

@@ -1,71 +0,0 @@
-// Code generated by "enumer -type=State -json"; DO NOT EDIT.
-
-//
-package pruner
-
-import (
-	"encoding/json"
-	"fmt"
-)
-
-const _StateName = "StateInitializedStateListFilesystemsStateListFilesystemsErrorStateFanOutFilesystemsStateDone"
-
-var _StateIndex = [...]uint8{0, 16, 36, 61, 83, 92}
-
-func (i State) String() string {
-	if i < 0 || i >= State(len(_StateIndex)-1) {
-		return fmt.Sprintf("State(%d)", i)
-	}
-	return _StateName[_StateIndex[i]:_StateIndex[i+1]]
-}
-
-var _StateValues = []State{0, 1, 2, 3, 4}
-
-var _StateNameToValueMap = map[string]State{
-	_StateName[0:16]:  0,
-	_StateName[16:36]: 1,
-	_StateName[36:61]: 2,
-	_StateName[61:83]: 3,
-	_StateName[83:92]: 4,
-}
-
-// StateString retrieves an enum value from the enum constants string name.
-// Throws an error if the param is not part of the enum.
-func StateString(s string) (State, error) {
-	if val, ok := _StateNameToValueMap[s]; ok {
-		return val, nil
-	}
-	return 0, fmt.Errorf("%s does not belong to State values", s)
-}
-
-// StateValues returns all values of the enum
-func StateValues() []State {
-	return _StateValues
-}
-
-// IsAState returns "true" if the value is listed in the enum definition. "false" otherwise
-func (i State) IsAState() bool {
-	for _, v := range _StateValues {
-		if i == v {
-			return true
-		}
-	}
-	return false
-}
-
-// MarshalJSON implements the json.Marshaler interface for State
-func (i State) MarshalJSON() ([]byte, error) {
-	return json.Marshal(i.String())
-}
-
-// UnmarshalJSON implements the json.Unmarshaler interface for State
-func (i *State) UnmarshalJSON(data []byte) error {
-	var s string
-	if err := json.Unmarshal(data, &s); err != nil {
-		return fmt.Errorf("State should be a string, got %s", data)
-	}
-
-	var err error
-	*i, err = StateString(s)
-	return err
-}

daemon/pruner/pruner.go

@@ -20,14 +20,15 @@ import (
 )
 
 // Try to keep it compatible with github.com/zrepl/zrepl/endpoint.Endpoint
-type Endpoint interface {
+type History interface {
+	ReplicationCursor(ctx context.Context, req *pdu.ReplicationCursorReq) (*pdu.ReplicationCursorRes, error)
 	ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error)
-	ListFilesystemVersions(ctx context.Context, req *pdu.ListFilesystemVersionsReq) (*pdu.ListFilesystemVersionsRes, error)
 }
 
 // Try to keep it compatible with github.com/zrepl/zrepl/endpoint.Endpoint
 type Target interface {
-	Endpoint
+	ListFilesystems(ctx context.Context, req *pdu.ListFilesystemReq) (*pdu.ListFilesystemRes, error)
+	ListFilesystemVersions(ctx context.Context, req *pdu.ListFilesystemVersionsReq) (*pdu.ListFilesystemVersionsRes, error)
 	DestroySnapshots(ctx context.Context, req *pdu.DestroySnapshotsReq) (*pdu.DestroySnapshotsRes, error)
 }
 
@@ -45,14 +46,13 @@ func GetLogger(ctx context.Context) Logger {
 }
 
 type args struct {
-	ctx                              context.Context
-	target                           Target
-	sender, receiver                 Endpoint
-	rules                            []pruning.KeepRule
-	retryWait                        time.Duration
-	considerSnapAtCursorReplicated   bool
-	convertAnyStepHoldToStepBookmark bool
-	promPruneSecs                    prometheus.Observer
+	ctx                            context.Context
+	target                         Target
+	receiver                       History
+	rules                          []pruning.KeepRule
+	retryWait                      time.Duration
+	considerSnapAtCursorReplicated bool
+	promPruneSecs                  prometheus.Observer
 }
 
 type Pruner struct {
@@ -70,12 +70,11 @@ type Pruner struct {
 }
 
 type PrunerFactory struct {
-	senderRules                      []pruning.KeepRule
-	receiverRules                    []pruning.KeepRule
-	retryWait                        time.Duration
-	considerSnapAtCursorReplicated   bool
-	convertAnyStepHoldToStepBookmark bool
-	promPruneSecs                    *prometheus.HistogramVec
+	senderRules                    []pruning.KeepRule
+	receiverRules                  []pruning.KeepRule
+	retryWait                      time.Duration
+	considerSnapAtCursorReplicated bool
+	promPruneSecs                  *prometheus.HistogramVec
 }
 
 type LocalPrunerFactory struct {
@@ -123,35 +122,25 @@ func NewPrunerFactory(in config.PruningSenderReceiver, promPruneSecs *prometheus
 		}
 		considerSnapAtCursorReplicated = considerSnapAtCursorReplicated || !knr.KeepSnapshotAtCursor
 	}
-
-	convertAnyStepHoldToStepBookmark := false
-	for _, r := range in.KeepSender {
-		_, ok := r.Ret.(*config.PruneKeepStepHolds)
-		convertAnyStepHoldToStepBookmark = convertAnyStepHoldToStepBookmark || ok
-	}
-
 	f := &PrunerFactory{
-		senderRules:                      keepRulesSender,
-		receiverRules:                    keepRulesReceiver,
-		retryWait:                        envconst.Duration("ZREPL_PRUNER_RETRY_INTERVAL", 10*time.Second),
-		considerSnapAtCursorReplicated:   considerSnapAtCursorReplicated,
-		convertAnyStepHoldToStepBookmark: convertAnyStepHoldToStepBookmark,
-		promPruneSecs:                    promPruneSecs,
+		senderRules:                    keepRulesSender,
+		receiverRules:                  keepRulesReceiver,
+		retryWait:                      envconst.Duration("ZREPL_PRUNER_RETRY_INTERVAL", 10*time.Second),
+		considerSnapAtCursorReplicated: considerSnapAtCursorReplicated,
+		promPruneSecs:                  promPruneSecs,
 	}
 	return f, nil
 }
 
-func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, sender Target, receiver Endpoint) *Pruner {
+func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, receiver History) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "sender"),
-			sender,
-			sender,
+			target,
 			receiver,
 			f.senderRules,
 			f.retryWait,
 			f.considerSnapAtCursorReplicated,
-			f.convertAnyStepHoldToStepBookmark,
 			f.promPruneSecs.WithLabelValues("sender"),
 		},
 		state: Plan,
@@ -159,17 +148,15 @@ func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, sender Target, re
 	return p
 }
 
-func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, receiver Target, sender Endpoint) *Pruner {
+func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target, receiver History) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "receiver"),
-			receiver,
-			sender,
+			target,
 			receiver,
 			f.receiverRules,
 			f.retryWait,
 			false, // senseless here anyways
-			false, // senseless here anyways
 			f.promPruneSecs.WithLabelValues("receiver"),
 		},
 		state: Plan,
@@ -177,17 +164,15 @@ func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, receiver Target
 	return p
 }
 
-func (f *LocalPrunerFactory) BuildLocalPruner(ctx context.Context, target Target) *Pruner {
+func (f *LocalPrunerFactory) BuildLocalPruner(ctx context.Context, target Target, receiver History) *Pruner {
 	p := &Pruner{
 		args: args{
 			context.WithValue(ctx, contextKeyPruneSide, "local"),
 			target,
-			target,
-			target,
+			receiver,
 			f.keepRules,
 			f.retryWait,
 			false, // considerSnapAtCursorReplicated is not relevant for local pruning
-			false, // convertAnyStepHoldToStepBookmark is not relevant for local pruning
 			f.promPruneSecs.WithLabelValues("local"),
 		},
 		state: Plan,
@@ -356,13 +341,11 @@ func (s snapshot) Replicated() bool { return s.replicated }
 
 func (s snapshot) Date() time.Time { return s.date }
 
-func (s snapshot) CreateTXG() uint64 { return s.fsv.GetCreateTXG() }
-
 func doOneAttempt(a *args, u updater) {
 
-	ctx, sender, receiver, target := a.ctx, a.sender, a.receiver, a.target
+	ctx, target, receiver := a.ctx, a.target, a.receiver
 
-	sfssres, err := sender.ListFilesystems(ctx, &pdu.ListFilesystemReq{})
+	sfssres, err := receiver.ListFilesystems(ctx, &pdu.ListFilesystemReq{})
 	if err != nil {
 		u(func(p *Pruner) {
 			p.state = PlanErr
@@ -424,10 +407,6 @@ tfss_loop:
 
 		pfs.snaps = make([]pruning.Snapshot, 0, len(tfsvs))
 
-		receiver.ListFilesystemVersions(ctx, &pdu.ListFilesystemVersionsReq{
-			Filesystem: tfs.Path,
-		})
-
 		rcReq := &pdu.ReplicationCursorReq{
 			Filesystem: tfs.Path,
 		}
@@ -436,7 +415,6 @@ tfss_loop:
 			pfsPlanErrAndLog(err, "cannot get replication cursor bookmark")
 			continue tfss_loop
 		}
-
 		if rc.GetNotexist() {
 			err := errors.New("replication cursor bookmark does not exist (one successful replication is required before pruning works)")
 			pfsPlanErrAndLog(err, "")

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

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

docs/changelog.rst

@@ -35,18 +35,23 @@ This is a big one! Headlining features:
 * **Resumable Send & Recv Support**
   No knobs required, automatically used where supported.
 * **Hold-Protected Send & Recv**
-  Automatic ZFS holds to ensure that we can always resume a replication step.
-* **Encrypted Send & Recv Support** for OpenZFS native encryption.
-  :ref:`Configurable <job-send-options>` at the job level, i.e., for all filesystems a job is responsible for.
+  Automatic ZFS holds to ensure that we can always use resumable send&recv for a replication step.
+* **Encrypted Send & Recv Support** for OpenZFS native encryption,
+  :ref:`configurable <job-send-options>` at the job level, i.e., for all filesystems a job is responsible for.
 * **Receive-side hold on last received dataset**
   The counterpart to the replication cursor bookmark on the send-side.
   Ensures that incremental replication will always be possible between a sender and receiver.
 
-Actual changelog:
+.. TIP::
 
-* |break_config| **more restrictive job names than in prior zrepl versions**
-  Starting with this version, job names are going to be embedded into ZFS holds and bookmark names.
+   We highly recommend studying the :ref:`overview section of the configuration chapter <overview-how-replication-works>` to understand how replication works.
 
+Additional changelog:
+
+* |break| |break_config| **more restrictive job names than in prior zrepl versions**
+  Starting with this version, job names are going to be embedded into ZFS holds and bookmark names (see :ref:`here<replication-cursor-and-last-received-hold>` and :ref:`here<step-holds-and-bookmarks>`).
+  Therefore you might need to adjust your job names.
+  **Note that jobs** :issue:`cannot be renamed easily` **once you start using zrepl 0.3.**
 * |break| |mig| replication cursor representation changed
 
   * zrepl now manages the :ref:`replication cursor bookmark <replication-cursor-and-last-received-hold>` per job-filesystem tuple instead of a single replication cursor per filesystem.
@@ -56,16 +61,29 @@ Actual changelog:
   * Run ``zrepl migrate replication-cursor:v1-v2`` to safely destroy old-format cursors.
     The migration will ensure that only those old-format cursors are destroyed that have been superseeded by new-format cursors.
 
+* |feature| New option ``listen_freebind`` (tcp, tls, prometheus listener)
+* |feature| :issue:`265` transport/tcp: support for CIDR masks in client IP whitelist
+* |feature| documented subcommand to generate ``bash`` and ``zsh`` completions
+* |feature| :issue:`307` ``chrome://trace`` -compatible activity tracing of zrepl daemon activity
+* |feature| logging: trace IDs for better log entry correlation with concurrent replication jobs
+* |feature| experimental environment variable for parallel replication (see :issue:`306` )
 * |bugfix| missing logger context vars in control connection handlers
 * |bugfix| improved error messages on ``zfs send`` errors
-* |feature| New option ``listen_freebind`` (tcp, tls, prometheus listener)
 * |bugfix| |docs| snapshotting: clarify sync-up behavior and warn about filesystems
+* |bugfix| transport/ssh: do not leak zombie ssh process on connection failures
   that will not be snapshotted until the sync-up phase is over
+* |docs| Installation: :ref:`FreeBSD jail with iocage <installation-freebsd-jail-with-iocage>`
 * |docs| Document new replication features in the :ref:`config overview <overview-how-replication-works>` and :repomasterlink:`replication/design.md`.
-* |feature| documented subcommand to generate ``bash`` and ``zsh`` completions
 * **[MAINTAINER NOTICE]** New platform tests in this version, please make sure you run them for your distro!
 * **[MAINTAINER NOTICE]** Please add the shell completions to the zrepl packages.
 
+.. NOTE::
+   |  zrepl is a spare-time project primarily developed by `Christian Schwarz <https://cschwarz.com>`_.
+   |  You can support maintenance and feature development through one of the following services:
+   |  |Donate via Patreon| |Donate via 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>`_.
+
 0.2.1
 -----
 
@@ -102,14 +120,6 @@ Actual changelog:
   The pool name ``zreplplatformtest`` is reserved for this use case.
   Only run ``make platformtest`` on test systems, e.g. a FreeBSD VM image.
 
-.. NOTE::
-   |  zrepl is a spare-time project primarily developed by `Christian Schwarz <https://cschwarz.com>`_.
-   |  You can support maintenance and feature development through one of the following services:
-   |  |Donate via Patreon| |Donate via Liberapay| |Donate via PayPal|
-   |  Note that PayPal processing fees are relatively high for small donations.
-   |  For SEPA wire transfer and **commercial support**, please `contact Christian directly <https://cschwarz.com>`_.
-
-
 0.1.1
 -----
 

docs/configuration/jobs.rst

@@ -19,7 +19,7 @@ Job Type ``push``
     * - ``type``
       - = ``push``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``connect``
       - |connect-transport|
     * - ``filesystems``
@@ -47,7 +47,7 @@ Job Type ``sink``
     * - ``type``
       - = ``sink``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``serve``
       - |serve-transport|
     * - ``root_fs``
@@ -70,7 +70,7 @@ Job Type ``pull``
     * - ``type``
       - = ``pull``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``connect``
       - |connect-transport|
     * - ``root_fs``
@@ -98,7 +98,7 @@ Job Type ``source``
     * - ``type``
       - = ``source``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``serve``
       - |serve-transport|
     * - ``filesystems``
@@ -137,7 +137,7 @@ Job type that only takes snapshots and performs pruning on the local machine.
     * - ``type``
       - = ``snap``
     * - ``name``
-      - unique name of the job
+      - unique name of the job :issue:`(must not change)<327>`
     * - ``filesystems``
       - |filter-spec| for filesystems to be snapshotted
     * - ``snapshotting``

docs/configuration/overview.rst

@@ -12,7 +12,7 @@ The following paths are considered:
 The ``zrepl configcheck`` subcommand can be used to validate the configuration.
 The command will output nothing and exit with zero status code if the configuration is valid.
 The error messages vary in quality and usefulness: please report confusing config errors to the tracking :issue:`155`.
-Full example configs such as in the :ref:`tutorial` or the :sampleconf:`/` directory might also be helpful.
+Full example configs such as in the :ref:`quick-start guides <quickstart-toc>` or the :sampleconf:`/` directory might also be helpful.
 However, copy-pasting examples is no substitute for reading documentation!
 
 Config File Structure
@@ -39,6 +39,10 @@ A *job* is the unit of activity tracked by the zrepl daemon.
 The ``type`` of a job determines its role in a replication setup and in snapshot management.
 Jobs are identified by their ``name``, both in log files and the ``zrepl status`` command.
 
+.. NOTE::
+   The job name is persisted in several places on disk and thus :issue:`cannot be changed easily<327>`.
+
+
 Replication always happens between a pair of jobs: one is the **active side**, and one the **passive side**.
 The active side connects to the passive side using a :ref:`transport <transport>` and starts executing the replication logic.
 The passive side responds to requests from the active side after checking its permissions.
@@ -99,7 +103,7 @@ One of the major design goals of the replication module is to avoid any duplicat
 As such, the code works on abstract senders and receiver **endpoints**, where typically one will be implemented by a local program object and the other is an RPC client instance.
 Regardless of push- or pull-style setup, the logic executes on the active side, i.e. in the ``push`` or ``pull`` job.
 
-The following steps take place during replication and can be monitored using the ``zrepl status`` subcommand:
+The following high-level steps take place during replication and can be monitored using the ``zrepl status`` subcommand:
 
 * Plan the replication:
 
@@ -107,9 +111,9 @@ The following steps take place during replication and can be monitored using the
   * Build the **replication plan**
 
     * Per filesystem, compute a diff between sender and receiver snapshots
-    * Build a list of replication steps
+    * Build a list of **replication steps**
 
-      * If possible, use incremental and resumable sends (``zfs send -i``)
+      * If possible, use incremental and resumable sends
       * Otherwise, use full send of most recent snapshot on sender
 
   * Retry on errors that are likely temporary (i.e. network failures).
@@ -128,16 +132,8 @@ The following steps take place during replication and can be monitored using the
    
 The idea behind the execution order of replication steps is that if the sender snapshots all filesystems simultaneously at fixed intervals, the receiver will have all filesystems snapshotted at time ``T1`` before the first snapshot at ``T2 = T1 + $interval`` is replicated.
 
-.. _replication-cursor-and-last-received-hold:
-
-**Replication cursor** bookmark and **last-received-hold** are managed by zrepl to ensure that future replications can always be done incrementally:
-the replication cursor is a send-side bookmark of the most recent successfully replicated snapshot,
-and the last-received-hold is a hold of that snapshot on the receiving side.
-The replication cursor has the format ``#zrepl_CUSOR_G_<GUID>_J_<JOBNAME>``.
-The last-received-hold tag has the format ``#zrepl_last_received_J_<JOBNAME>``.
-Encoding the job name in the names ensures that multiple sending jobs can replicate the same filesystem to different receivers without interference.
-The ``zrepl holds list`` provides a listing of all bookmarks and holds managed by zrepl.
-
+Placeholder Filesystems
+^^^^^^^^^^^^^^^^^^^^^^^
 .. _replication-placeholder-property:
 
 **Placeholder filesystems** on the receiving side are regular ZFS filesystems with the placeholder property ``zrepl:placeholder=on``.
@@ -148,16 +144,83 @@ Thus, zrepl creates the parent filesystems as placeholders on the receiving side
 If at some point ``S/H`` and ``S`` shall be replicated, the receiving side invalidates the placeholder flag automatically.
 The ``zrepl test placeholder`` command can be used to check whether a filesystem is a placeholder.
 
+ZFS Background Knowledge
+^^^^^^^^^^^^^^^^^^^^^^^^
+
+This section gives some background knowledge about ZFS features that zrepl uses to guarantee that
+**incremental replication is always possible and that started replication steps can always be resumed if they are interrupted.**
+
+**ZFS Send Modes & Bookmarks**
+ZFS supports full sends (``zfs send fs@to``) and incremental sends (``zfs send -i @from fs@to``).
+Full sends are used to create a new filesystem on the receiver with the send-side state of ``fs@to``.
+Incremental sends only transfer the delta between ``@from`` and ``@to``.
+Incremental sends require that ``@from`` be present on the receiving side when receiving the incremental stream.
+Incremental sends can also use a ZFS bookmark as *from* on the sending side (``zfs send -i #bm_from fs@to``), where ``#bm_from`` was created using ``zfs bookmark fs@from fs#bm_from``.
+The receiving side must always have the actual snapshot ``@from``, regardless of whether the sending side uses ``@from`` or a bookmark of it.
+
+**Resumable Send & Recv**
+The ``-s`` flag for ``zfs recv`` tells zfs to save the partially received send stream in case it is interrupted.
+To resume the replication, the receiving side filesystem's ``receive_resume_token`` must be passed to a new ``zfs send -t <value> | zfs recv`` command.
+A full send can only be resumed if ``@to`` still exists.
+An incremental send can only be resumed if ``@to`` still exists *and* either ``@from`` still exists *or* a bookmark ``#fbm`` of ``@from`` still exists.
+
+**ZFS Holds**
+ZFS holds prevent a snapshot from being deleted through ``zfs destroy``, letting the destroy fail with a ``datset is busy`` error.
+Holds are created and referred to by a user-defined *tag*. They can be thought of as a named, persistent lock on the snapshot.
+
+.. _replication-cursor-and-last-received-hold:
+
+Guaranteeing That Incremental Sends Are Always Possible
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+**Replication cursor** bookmark and **last-received-hold** are managed by zrepl to ensure that future replications can always be done incrementally.
+The replication cursor is a send-side bookmark of the most recent successfully replicated snapshot,
+and the last-received-hold is a hold of that snapshot on the receiving side.
+Both are moved aomically after the receiving side has confirmed that a replication step is complete.
+
+The replication cursor has the format ``#zrepl_CUSOR_G_<GUID>_J_<JOBNAME>``.
+The last-received-hold tag has the format ``zrepl_last_received_J_<JOBNAME>``.
+Encoding the job name in the names ensures that multiple sending jobs can replicate the same filesystem to different receivers without interference.
+
+The ``zrepl zfs-abstraction list`` command provides a listing of all bookmarks and holds managed by zrepl.
+
+.. _step-holds-and-bookmarks:
+
+Guaranteeing That Sends Are Always Resumable
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+**Step holds** are zfs holds managed by zrepl to ensure that a replication step can always be resumed if it is interrupted, e.g., due to network outage.
+zrepl creates step holds before it attempts a replication step and releases them after the receiver confirms that the replication step is complete.
+For an initial replication ``full @initial_snap``, zrepl puts a zfs hold on ``@initial_snap``.
+For an incremental send ``@from -> @to``, zrepl puts a zfs hold on both ``@from`` and ``@to``.
+Note that ``@from`` is not strictly necessary for resumability -- a bookmark on the sending side would be sufficient --, but size-estimation in currently used OpenZFS versions only works if ``@from`` is a snapshot.
+
+The hold tag has the format ``zrepl_STEP_J_<JOBNAME>``.
+A job only ever has one active send per filesystem.
+Thus, there are never more than two step holds for a given pair of ``(job,filesystem)``.
+
+**Step bookmarks** are zrepl's equivalent for holds on bookmarks (ZFS does not support putting holds on bookmarks).
+They are intended for a situation where a replication step uses a bookmark ``#bm`` as incremental ``from`` that is not managed by zrepl.
+To ensure resumability, zrepl copies ``#bm`` to step bookmark ``#zrepl_STEP_G_<GUID>_J_<JOBNAME>``.
+If the replication is interrupted and ``#bm`` is deleted by the user, the step bookmark remains as an incremental source for the resumable send.
+Note that zrepl does not yet support creating step bookmarks because the `corresponding ZFS feature for copying bookmarks <https://github.com/openzfs/zfs/pull/9571>`_ is not yet widely available .
+Subscribe to zrepl :issue:`326` for details.
+
+The ``zrepl zfs-abstraction list`` command provides a listing of all bookmarks and holds managed by zrepl.
+
+.. NOTE::
+
+    More details can be found in the design document :repomasterlink:`replication/design.md`.
+
+Limitations
+^^^^^^^^^^^
+
 .. ATTENTION::
 
     Currently, zrepl does not replicate filesystem properties.
     When receiving a filesystem, it is never mounted (`-u` flag)  and `mountpoint=none` is set.
     This is temporary and being worked on :issue:`24`.
 
-.. NOTE::
-
-    More details can be found in the design document :repomasterlink:`replication/design.md`.
-
 
 .. _jobs-multiple-jobs:
 
@@ -177,7 +240,7 @@ Multiple Jobs & More than 2 Machines
 If you would like to see improvements to multi-job setups, please `open an issue on GitHub <https://github.com/zrepl/zrepl/issues/new>`_.
 
 No Overlapping
-~~~~~~~~~~~~~~
+^^^^^^^^^^^^^^
 
 Jobs run independently of each other.
 If two jobs match the same filesystem with their ``filesystems`` filter, they will operate on that filesystem independently and potentially in parallel.
@@ -185,14 +248,14 @@ For example, if job A prunes snapshots that job B is planning to replicate, the
 However, the next replication attempt will re-examine the situation from scratch and should work.
 
 N push jobs to 1 sink
-~~~~~~~~~~~~~~~~~~~~~
+^^^^^^^^^^^^^^^^^^^^^
 
 The :ref:`sink job <job-sink>` namespaces by client identity.
 It is thus safe to push to one sink job with different client identities.
 If the push jobs have the same client identity, the filesystems matched by the push jobs must be disjoint to avoid races.
 
 N pull jobs from 1 source
-~~~~~~~~~~~~~~~~~~~~~~~~~
+^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Multiple pull jobs pulling from the same source have potential for race conditions during pruning:
 each pull job prunes the source side independently, causing replication-prune and prune-prune races.

docs/configuration/sendrecvoptions.rst

@@ -16,6 +16,8 @@ Send Options
      filesystems: ...
      send:
        encrypted: true
+       step_holds:
+         disable_incremental: false
      ...
 
 :ref:`Source<job-source>` and :ref:`push<job-push>` jobs have an optional ``send`` configuration section.
@@ -34,6 +36,24 @@ Filesystems matched by ``filesystems`` that are not encrypted are not sent and w
 
 If ``encryption=false``, zrepl expects that filesystems matching ``filesystems`` are not encrypted or have loaded encryption keys.
 
+.. _job-send-option-step-holds-disable-incremental:
+
+``step_holds.disable_incremental`` option
+-----------------------------------------
+
+The ``step_holds.disable_incremental`` variable controls whether the creation of :ref:`step holds <step-holds-and-bookmarks>` should be disabled for incremental replication.
+The default value is ``false``.
+
+Disabling step holds has the disadvantage that steps :ref:`might not be resumable <step-holds-and-bookmarks>` if interrupted.
+Non-resumability means that replication progress is no longer monotonic which might result in a replication setup that never makes progress if mid-step interruptions are too frequent (e.g. frequent network outages).
+
+However, the advantage and :issue:`reason for existence <288>` of this flag is that it allows the pruner to delete snapshots of interrupted replication steps
+which is useful if replication happens so rarely (or fails so frequently) that the amount of disk space exclusively referenced by the step's snapshots becomes intolerable.
+
+.. NOTE::
+
+   When setting this flag to ``true``, existing step holds for the job will be destroyed on the next replication attempt.
+
 .. _job-recv-options:
 
 Recv Options

docs/gen-sphinx-versioning-flags.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+
+import subprocess
+import re
+
+output = subprocess.run(["git", "tag", "-l"], capture_output=True, check=True, text=True)
+tagRE = re.compile(r"^v(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(-rc(?P<rc>\d+))?$")
+class Tag:
+    orig: str
+    major: int
+    minor: int
+    patch: int
+    rc: int
+
+    def __str__(self):
+        return self.orig
+
+    def __repr__(self):
+        return self.orig
+
+tags = []
+for line in output.stdout.split("\n"):
+    m = tagRE.match(line)
+    if not m:
+        continue
+    m = m.groupdict()
+
+    t = Tag()
+    t.orig = line
+    t.major = int(m["major"])   
+    t.minor = int(m["minor"])   
+    t.patch = int(m["patch"])
+    t.rc = int(m["rc"] if m["rc"] is not None else 0)
+
+    tags.append(t)
+
+by_major_minor = {}
+
+for tag in tags:
+    key = (tag.major, tag.minor)
+    l = by_major_minor.get(key, [])
+    l.append(tag)
+    by_major_minor[key] = l
+
+latest_by_major_minor = []
+for (mm, l) in by_major_minor.items():
+    # sort ascending by patch-level (rc's weigh less)
+    l.sort(key=lambda tag: (tag.patch, int(tag.rc == 0), tag.rc))
+    latest_by_major_minor.append(l[-1])
+latest_by_major_minor.sort(key=lambda tag: (tag.major, tag.minor))
+
+# print(by_major_minor)
+# print(latest_by_major_minor)
+
+cmdline = []
+
+for latest_patch in latest_by_major_minor:
+    cmdline.append("--whitelist-tags")
+    cmdline.append(f"^{re.escape(latest_patch.orig)}$")
+
+# we want to render the latest non-rc version as the default page
+# (latest_by_major_minor is already sorted)
+default_version = latest_by_major_minor[-1]
+for tag in reversed(latest_by_major_minor):
+    if tag.rc == 0:
+        default_version = tag
+        break
+
+cmdline.extend(["--root-ref", f"{default_version}"])
+cmdline.extend(["--banner-main-ref", f"{default_version}"])
+cmdline.extend(["--show-banner"])
+cmdline.extend(["--sort", "semver"])
+
+cmdline.extend(["--whitelist-branches", "master"])
+
+print(" ".join(cmdline))

docs/global.rst.inc

@@ -11,10 +11,12 @@
    :target: https://zrepl.github.io
 .. |Donate via PayPal| image:: https://img.shields.io/badge/donate-paypal-yellow.svg
    :target: https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=R5QSXJVYHGX96
-.. |Donate via Liberapay| image:: https://img.shields.io/liberapay/receives/zrepl.svg?logo=liberapay
+.. |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/endpoint.svg?url=https%3A%2F%2Fshieldsio-patreon.herokuapp.com%2Fzrepl%2Fpledges&style=flat&color=yellow
    :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
 
@@ -25,4 +27,8 @@
 .. |recv-options| replace:: :ref:`recv options<job-recv-options>`
 .. |snapshotting-spec| replace:: :ref:`snapshotting specification <job-snapshotting-spec>`
 .. |pruning-spec| replace:: :ref:`pruning specification <prune>`
-.. |filter-spec| replace:: :ref:`filter specification<pattern-filter>`
+.. |filter-spec| replace:: :ref:`filter specification<pattern-filter>`
+
+.. |br| raw:: html
+
+   <br/>

docs/index.rst

@@ -5,7 +5,7 @@
 
 .. include:: global.rst.inc
 
-|GitHub license| |Language: Go| |Twitter| |Donate via Patreon| |Donate via Liberapay| |Donate via PayPal| 
+|GitHub license| |Language: Go| |Twitter| |Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal|
 
 
 zrepl - ZFS replication
@@ -44,7 +44,7 @@ zrepl - ZFS replication
 Getting started
 ~~~~~~~~~~~~~~~
 
-The :ref:`10 minutes tutorial setup <tutorial>` gives you a first impression.
+The :ref:`10 minute quick-start guides <quickstart-toc>` give you a first impression.
 
 Main Features
 ~~~~~~~~~~~~~
@@ -125,7 +125,7 @@ Table of Contents
    :maxdepth: 2
    :caption: Contents:
 
-   tutorial
+   quickstart
    installation
    configuration
    usage

docs/installation.rst

@@ -7,7 +7,7 @@ Installation
 
 .. TIP::
 
-    Note: check out the :ref:`tutorial` if you want a first impression of zrepl.
+    Note: check out the :ref:`quick-start guides <quickstart-toc>` if you want a first impression of zrepl.
 
 .. toctree::
 

docs/installation/compile-from-source.rst

@@ -42,4 +42,4 @@ Either way, all build results are located in the ``artifacts/`` directory.
 .. NOTE::
 
     It is your job to install the appropriate binary in the zrepl users's ``$PATH``, e.g. ``/usr/local/bin/zrepl``.
-    Otherwise, the examples in the :ref:`tutorial` may need to be adjusted.
+    Otherwise, the examples in the :ref:`quick-start guides <quickstart-toc>` may need to be adjusted.

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

@@ -126,7 +126,7 @@ Modify the ``/usr/local/etc/zrepl/zrepl.yml`` configuration file.
 
 .. TIP::
 
-    Note: check out the :ref:`tutorial` for examples of a ``sink`` job.
+    Note: check out the :ref:`quick-start guides <quickstart-toc>` for examples of a ``sink`` job.
 
 Now ``zrepl`` can be started.
 

docs/installation/what-next.rst

@@ -5,4 +5,4 @@ What next?
 
 Read the :ref:`configuration chapter<configuration_toc>` and then continue with the :ref:`usage chapter<usage>`.
 
-**Reminder**: If you want a quick introduction, please read the :ref:`tutorial`.
+**Reminder**: If you want a quick introduction, please read the :ref:`quick-start guides <quickstart-toc>`.

docs/publish.sh

@@ -51,11 +51,10 @@ git rm -rf .
 popd
 
 echo "building site"
+
 set -e
 sphinx-versioning build \
-   --show-banner \
-   --whitelist-branches '^master$' \
-   --whitelist-tags '(v)?\d+\.[1-9][0-9]*.\d+$' \
+   $(python3 gen-sphinx-versioning-flags.py) \
    docs ./public_git \
    -- -c sphinxconf # older conf.py throw errors because they used
                     # version = subprocess.show_output(["git", "describe"])

docs/quickstart.rst

@@ -0,0 +1,87 @@
+.. include:: global.rst.inc
+
+.. _quickstart-toc:
+
+***********************
+Quick Start by Use Case
+***********************
+
+The goal of this quick-start guide is to give you an impression of how zrepl can accomodate your use case.
+
+Install zrepl
+=============
+
+Follow the :ref:`OS-specific installation instructions <installation_toc>` and come back here.
+
+Overview Of How zrepl Works
+============================
+
+Check out the :ref:`overview section <job-overview>` to get a rough idea of what you are going to configure in the next step, then come back here.
+
+Configuration Examples
+======================
+
+zrepl is configured through a YAML configuration file in ``/etc/zrepl/zrepl.yml``.
+We have prepared example use cases that show-case typical deployments and different functionality of zrepl.
+We encourage you to read through all of the examples to get an idea of what zrepl has to offer, and how you can mix-and-match configurations for your use case.
+Keep the :ref:`full config documentation <configuration_toc>` handy if a config snippet is unclear.
+
+**Example Use Cases**
+
+.. toctree::
+   :titlesonly:
+
+   quickstart/continuous_server_backup
+   quickstart/backup_to_external_disk
+
+Use ``zrepl configcheck`` to validate your configuration.
+No output indicates that everything is fine.
+
+.. NOTE::
+
+   Please open an issue on GitHub if your use case for zrepl is significantly different from those listed above.
+   Or even better, write it up in the same style as above and open a PR!
+
+.. _quickstart-apply-config:
+
+Apply Configuration Changes
+===========================
+
+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``.
+
+Watch it Work
+=============
+
+Run ``zrepl status`` on the active side of the replication setup to monitor snaphotting, replication and pruning activity.
+To re-trigger replication (snapshots are separate!), use ``zrepl signal wakeup JOBNAME``.
+(refer to the example use case document if you are uncertain which job you want to wake up).
+
+You can also use basic UNIX tools to inspect see what's going on.
+If you like tmux, here is a handy script that works on FreeBSD: ::
+
+    pkg install gnu-watch tmux
+    tmux new -s zrepl -d
+    tmux split-window -t zrepl "tail -f /var/log/messages"
+    tmux split-window -t zrepl "gnu-watch 'zfs list -t snapshot -o name,creation -s creation'"
+    tmux split-window -t zrepl "zrepl status"
+    tmux select-layout -t zrepl tiled
+    tmux attach -t zrepl
+
+The Linux equivalent might look like this: ::
+
+    # make sure tmux is installed & let's assume you use systemd + journald
+    tmux new -s zrepl -d
+    tmux split-window -t zrepl  "journalctl -f -u zrepl.service"
+    tmux split-window -t zrepl "watch 'zfs list -t snapshot -o name,creation -s creation'"
+    tmux split-window -t zrepl "zrepl status"
+    tmux select-layout -t zrepl tiled
+    tmux attach -t zrepl
+
+What Next?
+==========
+
+* Read more about :ref:`configuration format, options & job types <configuration_toc>`
+* Configure :ref:`logging <logging>` \& :ref:`monitoring <monitoring>`.
+

docs/quickstart/backup_to_external_disk.rst

@@ -0,0 +1,36 @@
+.. include:: ../global.rst.inc
+
+.. _quickstart-backup-to-external-disk:
+
+Local Snapshots + Offline Backup to an External Disk
+====================================================
+
+This config example shows how we can use zrepl to make periodic snapshots of our local workstation and back it up to a zpool on an external disk which we occassionally connect.
+
+The local snapshots should be taken every 15 minutes for pain-free recovery from CLI disasters (``rm -rf /`` and the like).
+However, we do not want to keep the snapshots around for very long because our workstation is a little tight on disk space.
+Thus, we only keep one hour worth of high-resolution snapshots, then fade them out to one per hour for a day (24 hours), then one per day for 14 days.
+
+At the end of each work day, we connect our external disk that serves as our workstation's local offline backup.
+We want zrepl to inspect the filesystems and snapshots on the external pool, figure out which snapshots were created since the last time we connected the external disk, and use incremental replication to efficiently mirror our workstation to our backup disk.
+Afterwards, we want to clean up old snapshots on the backup pool: we want to keep all snapshots younger than one hour, 24 for each hor of the first day, then 360 daily backups.
+
+A few additional requirements:
+
+* Snapshot creation and pruning on our workstation should happen in the background, without interaction from our side.
+* However, we want to explicitly trigger replication via the command line.
+* We want to use OpenZFS native encryption to protect our data on the external disk.
+  It is absolutely critical that only encrypted data leaves our workstation.
+  **zrepl should provide an easy config knob for this and prevent replication of unencrypted datasets to the external disk.**
+* We want to be able to put off the backups for more than three weeks, i.e., longer than the lifetime of the automatically created snapshots on our workstation.
+  **zrepl should use bookmarks and holds to achieve this goal**.
+* When we yank out the drive during replication and go on a long vacation, we do *not* want the partially replicated snapshot to stick around as it would hold on to too much disk space over time.
+  Therefore, we want zrepl to deviate from its :ref:`default step-hold behavior <step-holds-and-bookmarks>` and sacrifice resumability, but nonetheless retain the ability to do incremental replication once we return from our vacation.
+  **zrepl should provide an easy config knob to disable step holds for incremental replication**.
+
+The following config snippet implements the setup described above.
+You will likely want to customize some aspects mentioned in the top comment in the file.
+
+.. literalinclude:: ../../config/samples/quickstart_backup_to_external_disk.yml
+
+:ref:`Click here <quickstart-apply-config>` to go back to the quickstart guide.

docs/quickstart/continuous_server_backup.rst

@@ -0,0 +1,97 @@
+.. include:: ../global.rst.inc
+
+.. _quickstart-continuous-replication:
+
+Continuous Backup of a Server
+=============================
+
+This config example shows how we can backup our ZFS-based server to another machine using a zrepl push job.
+
+* 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
+
+* Backup server ``backups`` with
+
+  * Filesystem ``storage/zrepl/sink/prod`` + children dedicated to backups of ``prod``
+
+Our backup solution should fulfill the following requirements:
+
+* Periodically snapshot the filesystems on ``prod`` *every 10 minutes*
+* Incrementally replicate these snapshots to ``storage/zrepl/sink/prod/*`` on ``backups``
+* Keep only very few snapshots on ``prod`` to save disk space
+* Keep a fading history (24 hourly, 30 daily, 6 monthly) of snapshots on ``backups``
+* The network is untrusted - zrepl should use TLS to protect its communication and our data.
+
+Analysis
+--------
+
+We can model this situation as two jobs:
+
+* A **push job** on ``prod``
+
+  * Creates the snapshots
+  * Keeps a short history of local snapshots to enable incremental replication to ``backups``
+  * Connects to the ``zrepl daemon`` process on ``backups``
+  * Pushes snapshots ``backups``
+  * Prunes snapshots on ``backups`` after replication is complete
+
+* A **sink job** on ``backups``
+
+  * Accepts connections & responds to requests from ``prod``
+  * Limits client ``prod`` access to filesystem sub-tree ``storage/zrepl/sink/prod``
+
+Generate TLS Certificates
+-------------------------
+
+We use the :ref:`TLS client authentication transport <transport-tcp+tlsclientauth>` to protect our data on the wire.
+To get things going quickly, we skip setting up a CA and generate two self-signed certificates as described :ref:`here <transport-tcp+tlsclientauth-2machineopenssl>`.
+For convenience, we generate the key pairs on our local machine and distribute them using ssh:
+
+.. code-block:: bash
+   :emphasize-lines: 6,13
+
+   openssl req -x509 -sha256 -nodes \
+      -newkey rsa:4096 \
+      -days 365 \
+      -keyout backups.key \
+      -out backups.crt
+   # ... and use "backups" as Common Name (CN)
+
+   openssl req -x509 -sha256 -nodes \
+      -newkey rsa:4096 \
+      -days 365 \
+      -keyout prod.key \
+      -out prod.crt
+   # ... and use "prod" as Common Name (CN)
+
+   ssh root@backups "mkdir /etc/zrepl"
+   scp  backups.key backups.crt prod.crt root@backups:/etc/zrepl
+
+   ssh root@prod "mkdir /etc/zrepl"
+   scp  prod.key prod.crt backups.crt root@prod:/etc/zrepl
+
+Note that alternative transports exist, e.g. via :ref:`TCP without TLS <transport-tcp>` or :ref:`ssh <transport-ssh+stdinserver>`.
+
+Configure server ``prod``
+-------------------------
+
+We define a **push job** named ``prod_to_backups`` in ``/etc/zrepl/zrepl.yml`` on host ``prod`` :
+
+.. literalinclude:: ../../config/samples/quickstart_continuous_server_backup_sender.yml
+
+.. _tutorial-configure-prod:
+
+Configure server ``backups``
+----------------------------
+
+We define a corresponding **sink job** named ``sink`` in ``/etc/zrepl/zrepl.yml`` on host ``backups`` :
+
+.. literalinclude:: ../../config/samples/quickstart_continuous_server_backup_receiver.yml
+
+Go Back To Quickstart Guide
+---------------------------
+
+:ref:`Click here <quickstart-apply-config>` to go back to the quickstart guide.

docs/supporters.rst

@@ -2,7 +2,7 @@
 
 .. _supporters:
 
-|Donate via Patreon| |Donate via Liberapay| |Donate via PayPal|
+|Donate via Patreon| |Donate via GitHub Sponsors| |Donate via Liberapay| |Donate via PayPal|
 
 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 services listed above.

docs/tutorial.rst

@@ -1,177 +0,0 @@
-.. include:: global.rst.inc
-
-.. _tutorial:
-
-Tutorial
-========
-
-
-This tutorial shows how zrepl can be used to implement a ZFS-based push backup.
-We assume the following scenario:
-
-* 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
-
-* Backup server ``backups`` with
-
-  * Filesystem ``storage/zrepl/sink/prod`` + children dedicated to backups of ``prod``
-
-Our backup solution should fulfill the following requirements:
-
-* Periodically snapshot the filesystems on ``prod`` *every 10 minutes*
-* Incrementally replicate these snapshots to ``storage/zrepl/sink/prod/*`` on ``backups``
-* Keep only very few snapshots on ``prod`` to save disk space
-* Keep a fading history (24 hourly, 30 daily, 6 monthly) of snapshots on ``backups``
-
-Analysis
---------
-
-We can model this situation as two jobs:
-
-* A **push job** on ``prod``
-
-  * Creates the snapshots
-  * Keeps a short history of local snapshots to enable incremental replication to ``backups``
-  * Connects to the ``zrepl daemon`` process on ``backups``
-  * Pushes snapshots ``backups``
-  * Prunes snapshots on ``backups`` after replication is complete
-
-* A **sink job** on ``backups``
-
-  * Accepts connections & responds to requests from ``prod``
-  * Limits client ``prod`` access to filesystem sub-tree ``storage/zrepl/sink/prod``
-
-Install zrepl
--------------
-
-Follow the :ref:`OS-specific installation instructions <installation_toc>` and come back here.
-
-Generate TLS Certificates
--------------------------
-
-We use the :ref:`TLS client authentication transport <transport-tcp+tlsclientauth>` to protect our data on the wire.
-To get things going quickly, we skip setting up a CA and generate two self-signed certificates as described :ref:`here <transport-tcp+tlsclientauth-2machineopenssl>`.
-For convenience, we generate the key pairs on our local machine and distribute them using ssh:
-
-.. code-block:: bash
-   :emphasize-lines: 6,13
-
-   openssl req -x509 -sha256 -nodes \
-      -newkey rsa:4096 \
-      -days 365 \
-      -keyout backups.key \
-      -out backups.crt
-   # ... and use "backups" as Common Name (CN)
-
-   openssl req -x509 -sha256 -nodes \
-      -newkey rsa:4096 \
-      -days 365 \
-      -keyout prod.key \
-      -out prod.crt
-   # ... and use "prod" as Common Name (CN)
-
-   ssh root@backups "mkdir /etc/zrepl"
-   scp  backups.key backups.crt prod.crt root@backups:/etc/zrepl
-
-   ssh root@prod "mkdir /etc/zrepl"
-   scp  prod.key prod.crt backups.crt root@prod:/etc/zrepl
-
-
-Configure server ``prod``
--------------------------
-
-We define a **push job** named ``prod_to_backups`` in ``/etc/zrepl/zrepl.yml`` on host ``prod`` : ::
-
-    jobs:
-    - name: prod_to_backups
-      type: push 
-      connect:
-        type: tls
-        address: "backups.example.com:8888"
-        ca: /etc/zrepl/backups.crt
-        cert: /etc/zrepl/prod.crt
-        key:  /etc/zrepl/prod.key
-        server_cn: "backups"
-      filesystems: {
-        "zroot/var/db": true,
-        "zroot/usr/home<": true,
-        "zroot/usr/home/paranoid": false
-      }
-      snapshotting:
-        type: periodic
-        prefix: zrepl_
-        interval: 10m
-      pruning:
-        keep_sender:
-        - type: not_replicated
-        - type: last_n
-          count: 10
-        keep_receiver:
-        - type: grid
-          grid: 1x1h(keep=all) | 24x1h | 30x1d | 6x30d
-          regex: "^zrepl_"
-
-.. _tutorial-configure-prod:
-
-Configure server ``backups``
-----------------------------
-
-We define a corresponding **sink job** named ``sink`` in ``/etc/zrepl/zrepl.yml`` on host ``backups`` : ::
-
-    jobs:
-    - name: sink
-      type: sink 
-      serve:
-         type: tls
-         listen: ":8888"
-         ca: "/etc/zrepl/prod.crt"
-         cert: "/etc/zrepl/backups.crt"
-         key: "/etc/zrepl/backups.key"
-         client_cns:
-           - "prod"
-      root_fs: "storage/zrepl/sink"
-
-
-Apply Configuration Changes
----------------------------
-
-We use ``zrepl configcheck`` to catch any configuration errors: no output indicates that everything is fine.
-If that is the case, restart the zrepl daemon on **both** ``prod`` and ``backups`` using ``service zrepl restart`` or ``systemctl restart zrepl``.
-
-
-Watch it Work
--------------
-
-Run ``zrepl status`` on ``prod`` to monitor the replication and pruning activity.
-To re-trigger replication (snapshots are separate!), use ``zrepl signal wakeup prod_to_backups`` on ``prod``.
-
-If you like tmux, here is a handy script that works on FreeBSD: ::
-
-    pkg install gnu-watch tmux
-    tmux new -s zrepl -d
-    tmux split-window -t zrepl "tail -f /var/log/messages"
-    tmux split-window -t zrepl "gnu-watch 'zfs list -t snapshot -o name,creation -s creation | grep zrepl_'"
-    tmux split-window -t zrepl "zrepl status"
-    tmux select-layout -t zrepl tiled
-    tmux attach -t zrepl
-
-The Linux equivalent might look like this: ::
-
-    # make sure tmux is installed & let's assume you use systemd + journald
-    tmux new -s zrepl -d
-    tmux split-window -t zrepl  "journalctl -f -u zrepl.service"
-    tmux split-window -t zrepl "watch 'zfs list -t snapshot -o name,creation -s creation | grep zrepl_'"
-    tmux split-window -t zrepl "zrepl status"
-    tmux select-layout -t zrepl tiled
-    tmux attach -t zrepl
-
-Summary
--------
-
-Congratulations, you have a working push backup. Where to go next?
-
-* Read more about :ref:`configuration format, options & job types <configuration_toc>`
-* Configure :ref:`logging <logging>` \& :ref:`monitoring <monitoring>`.

docs/usage.rst

@@ -38,7 +38,7 @@ CLI Overview
     * - ``zrepl migrate``
       - | perform on-disk state / ZFS property migrations
         | (see :ref:`changelog <changelog>` for details)
-    * - ``zrepl zfs-abstractions``
+    * - ``zrepl zfs-abstraction``
       - list and remove zrepl's abstractions on top of ZFS, e.g. holds and step bookmarks (see :ref:`overview <replication-cursor-and-last-received-hold>` )
 
 .. _usage-zrepl-daemon:

endpoint/endpoint.go

@@ -21,9 +21,10 @@ import (
 )
 
 type SenderConfig struct {
-	FSF     zfs.DatasetFilter
-	Encrypt *zfs.NilBool
-	JobID   JobID
+	FSF                         zfs.DatasetFilter
+	Encrypt                     *zfs.NilBool
+	DisableIncrementalStepHolds bool
+	JobID                       JobID
 }
 
 func (c *SenderConfig) Validate() error {
@@ -39,9 +40,10 @@ func (c *SenderConfig) Validate() error {
 
 // Sender implements replication.ReplicationEndpoint for a sending side
 type Sender struct {
-	FSFilter zfs.DatasetFilter
-	encrypt  *zfs.NilBool
-	jobId    JobID
+	FSFilter                    zfs.DatasetFilter
+	encrypt                     *zfs.NilBool
+	disableIncrementalStepHolds bool
+	jobId                       JobID
 }
 
 func NewSender(conf SenderConfig) *Sender {
@@ -49,9 +51,10 @@ func NewSender(conf SenderConfig) *Sender {
 		panic("invalid config" + err.Error())
 	}
 	return &Sender{
-		FSFilter: conf.FSF,
-		encrypt:  conf.Encrypt,
-		jobId:    conf.JobID,
+		FSFilter:                    conf.FSF,
+		encrypt:                     conf.Encrypt,
+		disableIncrementalStepHolds: conf.DisableIncrementalStepHolds,
+		jobId:                       conf.JobID,
 	}
 }
 
@@ -112,13 +115,6 @@ func (s *Sender) ListFilesystemVersions(ctx context.Context, r *pdu.ListFilesyst
 	for i := range fsvs {
 		rfsvs[i] = pdu.FilesystemVersionFromZFS(&fsvs[i])
 	}
-
-	sendAbstractions := sendAbstractionsCacheSingleton.GetByFS(ctx, lp.ToString())
-	rSabsInfo := make([]*pdu.SendAbstraction, len(sendAbstractions))
-	for i := range rSabsInfo {
-		rSabsInfo[i] = SendAbstractionToPDU(sendAbstractions[i])
-	}
-
 	res := &pdu.ListFilesystemVersionsRes{Versions: rfsvs}
 	return res, nil
 
@@ -228,9 +224,11 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 		}
 	}
 
+	takeStepHolds := sendArgs.FromVersion == nil || !s.disableIncrementalStepHolds
+
 	var fromHold, toHold Abstraction
 	// make sure `From` doesn't go away in order to make this step resumable
-	if sendArgs.From != nil {
+	if sendArgs.From != nil && takeStepHolds {
 		fromHold, err = HoldStep(ctx, sendArgs.FS, *sendArgs.FromVersion, s.jobId) // no shadow
 		if err == zfs.ErrBookmarkCloningNotSupported {
 			getLogger(ctx).Debug("not creating step bookmark because ZFS does not support it")
@@ -239,10 +237,12 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 			return nil, nil, errors.Wrapf(err, "cannot hold `from` version %q before starting send", *sendArgs.FromVersion)
 		}
 	}
-	// make sure `To` doesn't go away in order to make this step resumable
-	toHold, err = HoldStep(ctx, sendArgs.FS, sendArgs.ToVersion, s.jobId)
-	if err != nil {
-		return nil, nil, errors.Wrapf(err, "cannot hold `to` version %q before starting send", sendArgs.ToVersion)
+	if takeStepHolds {
+		// make sure `To` doesn't go away in order to make this step resumable
+		toHold, err = HoldStep(ctx, sendArgs.FS, sendArgs.ToVersion, s.jobId)
+		if err != nil {
+			return nil, nil, errors.Wrapf(err, "cannot hold `to` version %q before starting send", sendArgs.ToVersion)
+		}
 	}
 
 	// cleanup the mess that _this function_ might have created in prior failed attempts:
@@ -261,11 +261,11 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 	//
 	// Note further that a resuming send, due to the idempotent nature of func CreateReplicationCursor and HoldStep,
 	// will never lose its step holds because we just (idempotently re-)created them above, before attempting the cleanup.
+	liveAbs := []Abstraction{fromHold, toHold, fromReplicationCursor}
 	func() {
 		ctx, endSpan := trace.WithSpan(ctx, "cleanup-stale-abstractions")
 		defer endSpan()
 
-		liveAbs := []Abstraction{fromHold, toHold, fromReplicationCursor}
 		keep := func(a Abstraction) (keep bool) {
 			keep = false
 			for _, k := range liveAbs {
@@ -282,7 +282,10 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 			}
 			for _, staleVersion := range obsoleteAbs {
 				for _, mustLiveVersion := range mustLiveVersions {
-					if zfs.FilesystemVersionEqualIdentity(mustLiveVersion, staleVersion.GetFilesystemVersion()) {
+					isSendArg := zfs.FilesystemVersionEqualIdentity(mustLiveVersion, staleVersion.GetFilesystemVersion())
+					isStepHoldWeMightHaveCreatedWithCurrentValueOf_takeStepHolds :=
+						takeStepHolds && staleVersion.GetType() == AbstractionStepHold
+					if isSendArg && isStepHoldWeMightHaveCreatedWithCurrentValueOf_takeStepHolds {
 						panic(fmt.Sprintf("impl error: %q would be destroyed because it is considered stale but it is part of of sendArgs=%s", mustLiveVersion.String(), pretty.Sprint(sendArgs)))
 					}
 				}
@@ -290,13 +293,11 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, io.Rea
 		}
 		sendAbstractionsCacheSingleton.TryBatchDestroy(ctx, s.jobId, sendArgs.FS, keep, check)
 	}()
-
-	if fromHold != nil {
-		sendAbstractionsCacheSingleton.Put(fromHold)
-	}
-	sendAbstractionsCacheSingleton.Put(toHold)
-	if fromReplicationCursor != nil {
-		sendAbstractionsCacheSingleton.Put(fromReplicationCursor)
+	// now add the newly created abstractions to the cleaned-up cache
+	for _, a := range liveAbs {
+		if a != nil {
+			sendAbstractionsCacheSingleton.Put(a)
+		}
 	}
 
 	sendStream, err := zfs.ZFSSend(ctx, sendArgs)
@@ -353,6 +354,7 @@ func (p *Sender) SendCompleted(ctx context.Context, r *pdu.SendCompletedReq) (*p
 			return &pdu.SendCompletedRes{}, err
 		}
 	} else {
+		sendAbstractionsCacheSingleton.Put(toReplicationCursor)
 		log(ctx).WithField("to_cursor", toReplicationCursor.String()).Info("successfully created `to` replication cursor")
 	}
 

endpoint/endpoint_send_abstractions_cache.go

@@ -82,29 +82,11 @@ func (s *sendAbstractionsCache) InvalidateFSCache(fs string) {
 
 }
 
-func (s *sendAbstractionsCache) GetByFS(ctx context.Context, fs string) (ret []Abstraction) {
-	defer s.mtx.Lock().Unlock()
-	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
-	if fs == "" {
-		panic("must not pass zero-value fs")
-	}
-
-	s.tryLoadOnDiskSendAbstractions(ctx, fs)
-
-	for _, a := range s.abstractions {
-		if a.GetFS() == fs {
-			ret = append(ret, a)
-		}
-	}
-
-	return ret
-}
-
 // - logs errors in getting on-disk abstractions
 // - only fetches on-disk abstractions once, but every time from the in-memory store
 //
 // That means that for precise results, all abstractions created by the endpoint must be .Put into this cache.
-func (s *sendAbstractionsCache) GetAndDeleteByJobIDAndFS(ctx context.Context, jobID JobID, fs string) (ret []Abstraction) {
+func (s *sendAbstractionsCache) GetAndDeleteByJobIDAndFS(ctx context.Context, jobID JobID, fs string, keep func(a Abstraction) bool) (ret []Abstraction) {
 	defer s.mtx.Lock().Unlock()
 	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
 	var zeroJobId JobID
@@ -122,7 +104,7 @@ func (s *sendAbstractionsCache) GetAndDeleteByJobIDAndFS(ctx context.Context, jo
 	for _, a := range s.abstractions {
 		aJobId := *a.GetJobID()
 		aFS := a.GetFS()
-		if aJobId == jobID && aFS == fs {
+		if aJobId == jobID && aFS == fs && !keep(a) {
 			ret = append(ret, a)
 		} else {
 			remaining = append(remaining, a)
@@ -198,14 +180,7 @@ func (s *sendAbstractionsCache) TryBatchDestroy(ctx context.Context, jobId JobID
 
 	defer trace.WithSpanFromStackUpdateCtx(&ctx)()
 
-	allSendStepAbstractions := s.GetAndDeleteByJobIDAndFS(ctx, jobId, fs)
-
-	var obsoleteAbs []Abstraction
-	for _, a := range allSendStepAbstractions {
-		if !keep(a) {
-			obsoleteAbs = append(obsoleteAbs, a)
-		}
-	}
+	obsoleteAbs := s.GetAndDeleteByJobIDAndFS(ctx, jobId, fs, keep)
 
 	if check != nil {
 		check(obsoleteAbs)

endpoint/endpoint_zfs_abstraction_pdu.go

@@ -1,28 +0,0 @@
-package endpoint
-
-import "github.com/zrepl/zrepl/replication/logic/pdu"
-
-func SendAbstractionToPDU(a Abstraction) *pdu.SendAbstraction {
-	var ty pdu.SendAbstraction_SendAbstractionType
-	switch a.GetType() {
-	case AbstractionLastReceivedHold:
-		panic(a)
-	case AbstractionReplicationCursorBookmarkV1:
-		panic(a)
-	case AbstractionReplicationCursorBookmarkV2:
-		ty = pdu.SendAbstraction_ReplicationCursorV2
-	case AbstractionStepHold:
-		ty = pdu.SendAbstraction_StepHold
-	case AbstractionStepBookmark:
-		ty = pdu.SendAbstraction_StepBookmark
-	default:
-		panic(a)
-	}
-
-	version := a.GetFilesystemVersion()
-	return &pdu.SendAbstraction{
-		Type:    ty,
-		JobID:   (*a.GetJobID()).String(),
-		Version: pdu.FilesystemVersionFromZFS(&version),
-	}
-}

go.mod

@@ -22,7 +22,7 @@ require (
 	github.com/onsi/gomega v1.7.0 // indirect
 	github.com/pkg/errors v0.8.1
 	github.com/pkg/profile v1.2.1
-	github.com/problame/go-netssh v0.0.0-20191209123953-18d8aa6923c7
+	github.com/problame/go-netssh v0.0.0-20200601114649-26439f9f0dc5
 	github.com/prometheus/client_golang v1.2.1
 	github.com/prometheus/common v0.7.0
 	github.com/sergi/go-diff v1.0.1-0.20180205163309-da645544ed44 // go1.12 thinks it needs this

go.sum

@@ -212,6 +212,8 @@ github.com/problame/go-netssh v0.0.0-20191026123024-f34099f4f6b1 h1:HH8yzlaZq/A8
 github.com/problame/go-netssh v0.0.0-20191026123024-f34099f4f6b1/go.mod h1:JRs3nyBjvOv/9YHC+Vlw9z1Jfzl5s5t0BNnTzmclj1c=
 github.com/problame/go-netssh v0.0.0-20191209123953-18d8aa6923c7 h1:Oik8tLrLhoMq4fduDRuNNOAQ+q0M0dXkjAYLUf4+mAc=
 github.com/problame/go-netssh v0.0.0-20191209123953-18d8aa6923c7/go.mod h1:Ba6RaFpK1+IHWs1wLZ6sCBuXkt4iAVLeOG5GinXHusM=
+github.com/problame/go-netssh v0.0.0-20200601114649-26439f9f0dc5 h1:1eSrO2WAeSXjMol8WRKW9LekL1252VIMaKQwWkmEdvs=
+github.com/problame/go-netssh v0.0.0-20200601114649-26439f9f0dc5/go.mod h1:Ba6RaFpK1+IHWs1wLZ6sCBuXkt4iAVLeOG5GinXHusM=
 github.com/prometheus/client_golang v0.0.0-20180410130117-e11c6ff8170b/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
 github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
 github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo=

platformtest/tests/batchDestroy.go

@@ -2,9 +2,8 @@ package tests
 
 import (
 	"fmt"
+	"strings"
 
-	"github.com/kr/pretty"
-	"github.com/stretchr/testify/require"
 	"github.com/zrepl/zrepl/platformtest"
 	"github.com/zrepl/zrepl/zfs"
 )
@@ -18,9 +17,7 @@ func BatchDestroy(ctx *platformtest.Context) {
 		+  "foo bar@1"
 		+  "foo bar@2"
 		+  "foo bar@3"
-		+  "foo bar@4"
 		R  zfs hold zrepl_platformtest "${ROOTDS}/foo bar@2"
-		R  zfs hold zrepl_platformtest "${ROOTDS}/foo bar@4"
 	`)
 
 	reqs := []*zfs.DestroySnapOp{
@@ -34,40 +31,24 @@ func BatchDestroy(ctx *platformtest.Context) {
 			Filesystem: fmt.Sprintf("%s/foo bar", ctx.RootDataset),
 			Name:       "2",
 		},
-		&zfs.DestroySnapOp{
-			ErrOut:     new(error),
-			Filesystem: fmt.Sprintf("%s/foo bar", ctx.RootDataset),
-			Name:       "non existent",
-		},
-		&zfs.DestroySnapOp{
-			ErrOut:     new(error),
-			Filesystem: fmt.Sprintf("%s/foo bar", ctx.RootDataset),
-			Name:       "4",
-		},
 	}
 	zfs.ZFSDestroyFilesystemVersions(ctx, reqs)
-
-	pretty.Println(reqs)
-
 	if *reqs[0].ErrOut != nil {
 		panic("expecting no error")
 	}
-
-	eBusy, ok := (*reqs[1].ErrOut).(*zfs.ErrDestroySnapshotDatasetIsBusy)
-	require.True(ctx, ok)
-	require.Equal(ctx, reqs[1].Name, eBusy.Name)
-
-	require.Nil(ctx, *reqs[2].ErrOut, "destroying non-existent snap is not an error (idempotence)")
-
-	eBusy, ok = (*reqs[3].ErrOut).(*zfs.ErrDestroySnapshotDatasetIsBusy)
-	require.True(ctx, ok)
-	require.Equal(ctx, reqs[3].Name, eBusy.Name)
+	err := (*reqs[1].ErrOut).Error()
+	if !strings.Contains(err, fmt.Sprintf("%s/foo bar@2", ctx.RootDataset)) {
+		panic(fmt.Sprintf("expecting error about being unable to destroy @2: %T\n%s", err, err))
+	}
 
 	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
 	!N "foo bar@3"
 	!E "foo bar@1"
 	!E "foo bar@2"
-	!E "foo bar@4"
+	R zfs release zrepl_platformtest "${ROOTDS}/foo bar@2"
+	-  "foo bar@2"
+	-  "foo bar@1"
+	-  "foo bar"
 	`)
 
 }

platformtest/tests/generated_cases.go

@@ -14,13 +14,14 @@ var Cases = []Case{BatchDestroy,
 	ListFilesystemVersionsUserrefs,
 	ListFilesystemVersionsZeroExistIsNotAnError,
 	ListFilesystemsNoFilter,
-	Pruner2NotReplicated,
 	ReceiveForceIntoEncryptedErr,
 	ReceiveForceRollbackWorksUnencrypted,
 	ReplicationIncrementalCleansUpStaleAbstractionsWithCacheOnSecondReplication,
 	ReplicationIncrementalCleansUpStaleAbstractionsWithoutCacheOnSecondReplication,
+	ReplicationIncrementalDestroysStepHoldsIffIncrementalStepHoldsAreDisabledButStepHoldsExist,
 	ReplicationIncrementalIsPossibleIfCommonSnapshotIsDestroyed,
-	ReplicationIsResumableFullSend,
+	ReplicationIsResumableFullSend__DisableIncrementalStepHolds_False,
+	ReplicationIsResumableFullSend__DisableIncrementalStepHolds_True,
 	ResumableRecvAndTokenHandling,
 	ResumeTokenParsing,
 	SendArgsValidationEncryptedSendOfUnencryptedDatasetForbidden,

platformtest/tests/pruner.go.deact

@@ -1,331 +0,0 @@
-package tests
-
-import (
-	"encoding/json"
-	"fmt"
-	"time"
-
-	"github.com/prometheus/client_golang/prometheus"
-	"github.com/stretchr/testify/require"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/filters"
-	"github.com/zrepl/zrepl/daemon/pruner"
-	"github.com/zrepl/zrepl/endpoint"
-	"github.com/zrepl/zrepl/platformtest"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-func PrunerNotReplicated(ctx *platformtest.Context) {
-
-	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
-        DESTROYROOT
-        CREATEROOT
-        +  "foo bar"
-        +  "foo bar@1"
-        +  "foo bar@2"
-        +  "foo bar@3"
-        +  "foo bar@4"
-        +  "foo bar@5"
-    `)
-
-	c, err := config.ParseConfigBytes([]byte(fmt.Sprintf(`
-jobs:
-- name: prunetest
-  type: push
-  filesystems: {
-      "%s/foo bar<": true
-  }
-  connect:
-    type: tcp
-    address: 255.255.255.255:255
-  snapshotting:
-    type: manual
-  pruning:
-    keep_sender:
-    - type: not_replicated
-    - type: last_n
-      count: 1
-    keep_receiver:
-    - type: last_n
-      count: 2
-    `, ctx.RootDataset)))
-	require.NoError(ctx, err)
-
-	pushJob := c.Jobs[0].Ret.(*config.PushJob)
-
-	dummyHistVec := prometheus.NewHistogramVec(prometheus.HistogramOpts{
-		Namespace: "foo",
-		Subsystem: "foo",
-		Name:      "foo",
-		Help:      "foo",
-	}, []string{"foo"})
-
-	prunerFactory, err := pruner.NewPrunerFactory(pushJob.Pruning, dummyHistVec)
-	require.NoError(ctx, err)
-
-	senderJid := endpoint.MustMakeJobID("sender-job")
-
-	fsfilter, err := filters.DatasetMapFilterFromConfig(pushJob.Filesystems)
-	require.NoError(ctx, err)
-
-	sender := endpoint.NewSender(endpoint.SenderConfig{
-		FSF: fsfilter,
-		Encrypt: &zfs.NilBool{
-			B: false,
-		},
-		JobID: senderJid,
-	})
-
-	fs := ctx.RootDataset + "/foo bar"
-
-	// create a replication cursor to make pruning work at all
-	_, err = endpoint.CreateReplicationCursor(ctx, fs, fsversion(ctx, fs, "@2"), senderJid)
-	require.NoError(ctx, err)
-
-	p := prunerFactory.BuildSenderPruner(ctx, sender, sender)
-
-	p.Prune()
-
-	report := p.Report()
-
-	reportJSON, err := json.MarshalIndent(report, "", "  ")
-	require.NoError(ctx, err)
-	ctx.Logf("%s\n", string(reportJSON))
-
-	require.Equal(ctx, pruner.Done.String(), report.State)
-	require.Len(ctx, report.Completed, 1)
-	fsReport := report.Completed[0]
-	require.Equal(ctx, fs, fsReport.Filesystem)
-	require.Empty(ctx, fsReport.SkipReason)
-	require.Empty(ctx, fsReport.LastError)
-	require.Len(ctx, fsReport.DestroyList, 1)
-	require.Equal(ctx, fsReport.DestroyList[0], pruner.SnapshotReport{
-		Name:       "1",
-		Replicated: true,
-		Date:       fsReport.DestroyList[0].Date,
-	})
-
-}
-
-func PrunerNoKeepNotReplicatedNoKeepStepHoldConvertsAnyStepHoldToBookmark(ctx *platformtest.Context) {
-
-	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
-        DESTROYROOT
-        CREATEROOT
-        +  "foo bar"
-        +  "foo bar@1"
-        +  "foo bar@2"
-        +  "foo bar@3"
-        +  "foo bar@4"
-        +  "foo bar@5"
-    `)
-
-	c, err := config.ParseConfigBytes([]byte(fmt.Sprintf(`
-jobs:
-- name: prunetest
-  type: push
-  filesystems: {
-      "%s/foo bar<": true
-  }
-  connect:
-    type: tcp
-    address: 255.255.255.255:255
-  snapshotting:
-    type: manual
-  pruning:
-    keep_sender:
-    - type: last_n
-      count: 1
-    keep_receiver:
-    - type: last_n
-      count: 2
-    `, ctx.RootDataset)))
-	require.NoError(ctx, err)
-
-	pushJob := c.Jobs[0].Ret.(*config.PushJob)
-
-	dummyHistVec := prometheus.NewHistogramVec(prometheus.HistogramOpts{
-		Namespace: "foo",
-		Subsystem: "foo",
-		Name:      "foo",
-		Help:      "foo",
-	}, []string{"foo"})
-
-	prunerFactory, err := pruner.NewPrunerFactory(pushJob.Pruning, dummyHistVec)
-	require.NoError(ctx, err)
-
-	senderJid := endpoint.MustMakeJobID("sender-job")
-
-	fsfilter, err := filters.DatasetMapFilterFromConfig(pushJob.Filesystems)
-	require.NoError(ctx, err)
-
-	sender := endpoint.NewSender(endpoint.SenderConfig{
-		FSF: fsfilter,
-		Encrypt: &zfs.NilBool{
-			B: false,
-		},
-        JobID: senderJid,
-	})
-
-	fs := ctx.RootDataset + "/foo bar"
-
-	// create a replication cursor to make pruning work at all
-	_, err = endpoint.CreateReplicationCursor(ctx, fs, fsversion(ctx, fs, "@2"), senderJid)
-	require.NoError(ctx, err)
-
-	// create step holds for the incremental @2->@3
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@2"), senderJid)
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@3"), senderJid)
-	// create step holds for another job
-	otherJid := endpoint.MustMakeJobID("other-job")
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@2"), otherJid)
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@3"), otherJid)
-
-	p := prunerFactory.BuildSenderPruner(ctx, sender, sender)
-
-	p.Prune()
-
-	report := p.Report()
-
-	reportJSON, err := json.MarshalIndent(report, "", "  ")
-	require.NoError(ctx, err)
-	ctx.Logf("%s\n", string(reportJSON))
-
-	require.Equal(ctx, pruner.Done.String(), report.State)
-	require.Len(ctx, report.Completed, 1)
-	fsReport := report.Completed[0]
-	require.Equal(ctx, fs, fsReport.Filesystem)
-	require.Empty(ctx, fsReport.SkipReason)
-	require.Empty(ctx, fsReport.LastError)
-	expectDestroyList := []pruner.SnapshotReport{
-		{
-			Name:       "1",
-			Replicated: true,
-		},
-		{
-			Name:       "2",
-			Replicated: true,
-		},
-		{
-			Name:       "3",
-			Replicated: true,
-		},
-		{
-			Name:       "4",
-			Replicated: true,
-		},
-	}
-	for _, d := range fsReport.DestroyList {
-		d.Date = time.Time{}
-	}
-	require.Subset(ctx, fsReport.DestroyList, expectDestroyList)
-}
-
-
-
-func PrunerNoKeepNotReplicatedButKeepStepHold(ctx *platformtest.Context) {
-
-	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
-        DESTROYROOT
-        CREATEROOT
-        +  "foo bar"
-        +  "foo bar@1"
-        +  "foo bar@2"
-        +  "foo bar@3"
-        +  "foo bar@4"
-        +  "foo bar@5"
-    `)
-
-	c, err := config.ParseConfigBytes([]byte(fmt.Sprintf(`
-jobs:
-- name: prunetest
-  type: push
-  filesystems: {
-      "%s/foo bar<": true
-  }
-  connect:
-    type: tcp
-    address: 255.255.255.255:255
-  snapshotting:
-    type: manual
-  pruning:
-    keep_sender:
-    - type: step_holds
-    - type: last_n
-      count: 1
-    keep_receiver:
-    - type: last_n
-      count: 2
-    `, ctx.RootDataset)))
-	require.NoError(ctx, err)
-
-	pushJob := c.Jobs[0].Ret.(*config.PushJob)
-
-	dummyHistVec := prometheus.NewHistogramVec(prometheus.HistogramOpts{
-		Namespace: "foo",
-		Subsystem: "foo",
-		Name:      "foo",
-		Help:      "foo",
-	}, []string{"foo"})
-
-	prunerFactory, err := pruner.NewPrunerFactory(pushJob.Pruning, dummyHistVec)
-	require.NoError(ctx, err)
-
-	senderJid := endpoint.MustMakeJobID("sender-job")
-
-	fsfilter, err := filters.DatasetMapFilterFromConfig(pushJob.Filesystems)
-	require.NoError(ctx, err)
-
-	sender := endpoint.NewSender(endpoint.SenderConfig{
-		FSF: fsfilter,
-		Encrypt: &zfs.NilBool{
-			B: false,
-		},
-        JobID: senderJid,
-	})
-
-	fs := ctx.RootDataset + "/foo bar"
-
-	// create a replication cursor to make pruning work at all
-	_, err = endpoint.CreateReplicationCursor(ctx, fs, fsversion(ctx, fs, "@2"), senderJid)
-	require.NoError(ctx, err)
-
-	// create step holds for the incremental @2->@3
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@2"), senderJid)
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@3"), senderJid)
-	// create step holds for another job
-	otherJid := endpoint.MustMakeJobID("other-job")
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@2"), otherJid)
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@3"), otherJid)
-
-	p := prunerFactory.BuildSenderPruner(ctx, sender, sender)
-
-	p.Prune()
-
-	report := p.Report()
-
-	reportJSON, err := json.MarshalIndent(report, "", "  ")
-	require.NoError(ctx, err)
-	ctx.Logf("%s\n", string(reportJSON))
-
-	require.Equal(ctx, pruner.Done.String(), report.State)
-	require.Len(ctx, report.Completed, 1)
-	fsReport := report.Completed[0]
-	require.Equal(ctx, fs, fsReport.Filesystem)
-	require.Empty(ctx, fsReport.SkipReason)
-	require.Empty(ctx, fsReport.LastError)
-	expectDestroyList := []pruner.SnapshotReport{
-		{
-			Name:       "1",
-			Replicated: true,
-		},
-		{
-			Name:       "4",
-			Replicated: true,
-		},
-	}
-	for _, d := range fsReport.DestroyList {
-		d.Date = time.Time{}
-	}
-	require.Subset(ctx, fsReport.DestroyList, expectDestroyList)
-}

platformtest/tests/pruner.v2.go

@@ -1,137 +0,0 @@
-package tests
-
-import (
-	"encoding/json"
-	"fmt"
-	"time"
-
-	"github.com/kr/pretty"
-	"github.com/stretchr/testify/require"
-	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/daemon/filters"
-	"github.com/zrepl/zrepl/daemon/pruner.v2"
-	"github.com/zrepl/zrepl/endpoint"
-	"github.com/zrepl/zrepl/platformtest"
-	"github.com/zrepl/zrepl/pruning"
-	"github.com/zrepl/zrepl/zfs"
-)
-
-func Pruner2NotReplicated(ctx *platformtest.Context) {
-
-	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
-        DESTROYROOT
-        CREATEROOT
-        +  "foo bar"
-        +  "foo bar@1"
-        +  "foo bar@2"
-        +  "foo bar@3"
-        +  "foo bar@4"
-        +  "foo bar@5"
-	`)
-
-	fs := ctx.RootDataset + "/foo bar"
-	senderJid := endpoint.MustMakeJobID("sender-job")
-	otherJid1 := endpoint.MustMakeJobID("other-job-1")
-	otherJid2 := endpoint.MustMakeJobID("other-job-2")
-
-
-	// create step holds for the incremental @2->@3
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@2"), senderJid)
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@3"), senderJid)
-	// create step holds for other-job-1 @2 -> @3
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@2"), otherJid1)
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@3"), otherJid1)
-	// create step hold for other-job-2 @1 (will be pruned)
-	endpoint.HoldStep(ctx, fs, fsversion(ctx, fs, "@1"), otherJid2)
-
-	c, err := config.ParseConfigBytes([]byte(fmt.Sprintf(`
-jobs:
-- name: prunetest
-  type: push
-  filesystems: {
-      "%s/foo bar": true
-  }
-  connect:
-    type: tcp
-    address: 255.255.255.255:255
-  snapshotting:
-    type: manual
-  pruning:
-    keep_sender:
-    #- type: not_replicated
-    - type: step_holds
-    - type: last_n
-      count: 1
-    keep_receiver:
-    - type: last_n
-      count: 2
-    `, ctx.RootDataset)))
-	require.NoError(ctx, err)
-
-	pushJob := c.Jobs[0].Ret.(*config.PushJob)
-
-	require.NoError(ctx, err)
-
-	fsfilter, err := filters.DatasetMapFilterFromConfig(pushJob.Filesystems)
-	require.NoError(ctx, err)
-
-	matchedFilesystems, err := zfs.ZFSListMapping(ctx, fsfilter)
-	ctx.Logf("%s", pretty.Sprint(matchedFilesystems))
-	require.NoError(ctx, err)
-	require.Len(ctx, matchedFilesystems, 1)
-
-	sideSender := pruner.NewSideSender(senderJid)
-
-	keepRules, err := pruning.RulesFromConfig(senderJid, pushJob.Pruning.KeepSender)
-	require.NoError(ctx, err)
-	p := pruner.NewPruner(fsfilter, senderJid, sideSender, keepRules)
-
-	runDone := make(chan *pruner.Report)
-	go func() {
-		runDone <- p.Run(ctx)
-	}()
-
-	var report *pruner.Report
-	// concurrency stress
-out:
-	for {
-		select {
-		case <-time.After(10 * time.Millisecond):
-			p.Report(ctx)
-		case report = <-runDone:
-			break out
-		}
-	}
-	ctx.Logf("%s\n", pretty.Sprint(report))
-
-	reportJSON, err := json.MarshalIndent(report, "", "  ")
-	require.NoError(ctx, err)
-	ctx.Logf("%s\n", string(reportJSON))
-
-	ctx.FailNow()
-	// fs := ctx.RootDataset + "/foo bar"
-
-	// // create a replication cursor to make pruning work at all
-	// _, err = endpoint.CreateReplicationCursor(ctx, fs, fsversion(ctx, fs, "@2"), senderJid)
-	// require.NoError(ctx, err)
-
-	// p := prunerFactory.BuildSenderPruner(ctx, sender, sender)
-
-	// p.Prune()
-
-	// report := p.Report()
-
-	// require.Equal(ctx, pruner.Done.String(), report.State)
-	// require.Len(ctx, report.Completed, 1)
-	// fsReport := report.Completed[0]
-	// require.Equal(ctx, fs, fsReport.Filesystem)
-	// require.Empty(ctx, fsReport.SkipReason)
-	// require.Empty(ctx, fsReport.LastError)
-	// require.Len(ctx, fsReport.DestroyList, 1)
-	// require.Equal(ctx, fsReport.DestroyList[0], pruner.SnapshotReport{
-	// 	Name:       "1",
-	// 	Replicated: true,
-	// 	Date:       fsReport.DestroyList[0].Date,
-	// })
-
-}

platformtest/tests/replication.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"io"
 	"path"
+	"sort"
 
 	"github.com/kr/pretty"
 	"github.com/stretchr/testify/require"
@@ -26,10 +27,11 @@ import (
 // of a new sender and receiver instance and one blocking invocation
 // of the replication engine without encryption
 type replicationInvocation struct {
-	sjid, rjid      endpoint.JobID
-	sfs             string
-	rfsRoot         string
-	interceptSender func(e *endpoint.Sender) logic.Sender
+	sjid, rjid                  endpoint.JobID
+	sfs                         string
+	rfsRoot                     string
+	interceptSender             func(e *endpoint.Sender) logic.Sender
+	disableIncrementalStepHolds bool
 }
 
 func (i replicationInvocation) Do(ctx *platformtest.Context) *report.Report {
@@ -42,9 +44,10 @@ func (i replicationInvocation) Do(ctx *platformtest.Context) *report.Report {
 	err := sfilter.Add(i.sfs, "ok")
 	require.NoError(ctx, err)
 	sender := i.interceptSender(endpoint.NewSender(endpoint.SenderConfig{
-		FSF:     sfilter.AsFilter(),
-		Encrypt: &zfs.NilBool{B: false},
-		JobID:   i.sjid,
+		FSF:                         sfilter.AsFilter(),
+		Encrypt:                     &zfs.NilBool{B: false},
+		DisableIncrementalStepHolds: i.disableIncrementalStepHolds,
+		JobID:                       i.sjid,
 	}))
 	receiver := endpoint.NewReceiver(endpoint.ReceiverConfig{
 		JobID:                      i.rjid,
@@ -86,10 +89,11 @@ func ReplicationIncrementalIsPossibleIfCommonSnapshotIsDestroyed(ctx *platformte
 	snap1 := fsversion(ctx, sfs, "@1")
 
 	rep := replicationInvocation{
-		sjid:    sjid,
-		rjid:    rjid,
-		sfs:     sfs,
-		rfsRoot: rfsRoot,
+		sjid:                        sjid,
+		rjid:                        rjid,
+		sfs:                         sfs,
+		rfsRoot:                     rfsRoot,
+		disableIncrementalStepHolds: false,
 	}
 	rfs := rep.ReceiveSideFilesystem()
 
@@ -149,10 +153,11 @@ func implReplicationIncrementalCleansUpStaleAbstractions(ctx *platformtest.Conte
 	rfsRoot := ctx.RootDataset + "/receiver"
 
 	rep := replicationInvocation{
-		sjid:    sjid,
-		rjid:    rjid,
-		sfs:     sfs,
-		rfsRoot: rfsRoot,
+		sjid:                        sjid,
+		rjid:                        rjid,
+		sfs:                         sfs,
+		rfsRoot:                     rfsRoot,
+		disableIncrementalStepHolds: false,
 	}
 	rfs := rep.ReceiveSideFilesystem()
 
@@ -178,7 +183,7 @@ func implReplicationIncrementalCleansUpStaleAbstractions(ctx *platformtest.Conte
 	require.NoError(ctx, err)
 	require.Contains(ctx, holds, expectRjidHoldTag)
 
-	// create artifical stale replication cursors
+	// create artifical stale replication cursors & step holds
 	createArtificalStaleAbstractions := func(jobId endpoint.JobID) []endpoint.Abstraction {
 		snap2Cursor, err := endpoint.CreateReplicationCursor(ctx, sfs, snap2, jobId) // no shadow
 		require.NoError(ctx, err)
@@ -322,7 +327,15 @@ func (s *PartialSender) Send(ctx context.Context, r *pdu.SendReq) (r1 *pdu.SendR
 	return r1, r2, r3
 }
 
-func ReplicationIsResumableFullSend(ctx *platformtest.Context) {
+func ReplicationIsResumableFullSend__DisableIncrementalStepHolds_False(ctx *platformtest.Context) {
+	implReplicationIsResumableFullSend(ctx, false)
+}
+
+func ReplicationIsResumableFullSend__DisableIncrementalStepHolds_True(ctx *platformtest.Context) {
+	implReplicationIsResumableFullSend(ctx, true)
+}
+
+func implReplicationIsResumableFullSend(ctx *platformtest.Context, disableIncrementalStepHolds bool) {
 
 	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
 		CREATEROOT
@@ -353,6 +366,7 @@ func ReplicationIsResumableFullSend(ctx *platformtest.Context) {
 		interceptSender: func(e *endpoint.Sender) logic.Sender {
 			return &PartialSender{Sender: e, failAfterByteCount: 1 << 20}
 		},
+		disableIncrementalStepHolds: disableIncrementalStepHolds,
 	}
 	rfs := rep.ReceiveSideFilesystem()
 
@@ -394,3 +408,146 @@ func ReplicationIsResumableFullSend(ctx *platformtest.Context) {
 	_ = fsversion(ctx, rfs, "@3")
 
 }
+
+func ReplicationIncrementalDestroysStepHoldsIffIncrementalStepHoldsAreDisabledButStepHoldsExist(ctx *platformtest.Context) {
+
+	platformtest.Run(ctx, platformtest.PanicErr, ctx.RootDataset, `
+		CREATEROOT
+		+  "sender"
+		+  "receiver"
+		R  zfs create -p "${ROOTDS}/receiver/${ROOTDS}"
+	`)
+
+	sjid := endpoint.MustMakeJobID("sender-job")
+	rjid := endpoint.MustMakeJobID("receiver-job")
+
+	sfs := ctx.RootDataset + "/sender"
+	rfsRoot := ctx.RootDataset + "/receiver"
+
+	// fully replicate snapshots @1
+	{
+		mustSnapshot(ctx, sfs+"@1")
+		rep := replicationInvocation{
+			sjid:                        sjid,
+			rjid:                        rjid,
+			sfs:                         sfs,
+			rfsRoot:                     rfsRoot,
+			disableIncrementalStepHolds: false,
+		}
+		rfs := rep.ReceiveSideFilesystem()
+		report := rep.Do(ctx)
+		ctx.Logf("\n%s", pretty.Sprint(report))
+		// assert this worked (not the main subject of the test)
+		_ = fsversion(ctx, rfs, "@1")
+	}
+
+	// create a large snapshot @2
+	{
+		sfsmp, err := zfs.ZFSGetMountpoint(ctx, sfs)
+		require.NoError(ctx, err)
+		require.True(ctx, sfsmp.Mounted)
+		writeDummyData(path.Join(sfsmp.Mountpoint, "dummy.data"), 1<<22)
+		mustSnapshot(ctx, sfs+"@2")
+	}
+	snap2sfs := fsversion(ctx, sfs, "@2")
+
+	// partially replicate snapshots @2 with step holds enabled
+	// to effect a step-holds situation
+	{
+		rep := replicationInvocation{
+			sjid:                        sjid,
+			rjid:                        rjid,
+			sfs:                         sfs,
+			rfsRoot:                     rfsRoot,
+			disableIncrementalStepHolds: false, // !
+			interceptSender: func(e *endpoint.Sender) logic.Sender {
+				return &PartialSender{Sender: e, failAfterByteCount: 1 << 20}
+			},
+		}
+		rfs := rep.ReceiveSideFilesystem()
+		report := rep.Do(ctx)
+		ctx.Logf("\n%s", pretty.Sprint(report))
+		// assert this partial receive worked
+		_, err := zfs.ZFSGetFilesystemVersion(ctx, rfs+"@2")
+		ctx.Logf("%T %s", err, err)
+		_, notFullyReceived := err.(*zfs.DatasetDoesNotExist)
+		require.True(ctx, notFullyReceived)
+		// assert step holds are in place
+		abs, absErrs, err := endpoint.ListAbstractions(ctx, endpoint.ListZFSHoldsAndBookmarksQuery{
+			FS: endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter{
+				FS: &sfs,
+			},
+			Concurrency: 1,
+			JobID:       &sjid,
+			What:        endpoint.AbstractionTypeSet{endpoint.AbstractionStepHold: true},
+		})
+		require.NoError(ctx, err)
+		require.Empty(ctx, absErrs)
+		require.Len(ctx, abs, 2)
+		sort.Slice(abs, func(i, j int) bool {
+			return abs[i].GetCreateTXG() < abs[j].GetCreateTXG()
+		})
+		require.True(ctx, zfs.FilesystemVersionEqualIdentity(abs[0].GetFilesystemVersion(), fsversion(ctx, sfs, "@1")))
+		require.True(ctx, zfs.FilesystemVersionEqualIdentity(abs[1].GetFilesystemVersion(), fsversion(ctx, sfs, "@2")))
+	}
+
+	//
+	// end of test setup
+	//
+
+	// retry replication with incremental step holds disabled
+	// - replication should not fail due to holds-related stuff
+	// - replication should fail intermittently due to partial sender being fully read
+	// - the partial sender is 1/4th the length of the stream, thus expect
+	//   successful replication after 5 more attempts
+	rep := replicationInvocation{
+		sjid:                        sjid,
+		rjid:                        rjid,
+		sfs:                         sfs,
+		rfsRoot:                     rfsRoot,
+		disableIncrementalStepHolds: true, // !
+		interceptSender: func(e *endpoint.Sender) logic.Sender {
+			return &PartialSender{Sender: e, failAfterByteCount: 1 << 20}
+		},
+	}
+	rfs := rep.ReceiveSideFilesystem()
+	for i := 0; ; i++ {
+		require.True(ctx, i < 5)
+		report := rep.Do(ctx)
+		ctx.Logf("retry run=%v\n%s", i, pretty.Sprint(report))
+		_, err := zfs.ZFSGetFilesystemVersion(ctx, rfs+"@2")
+		if err == nil {
+			break
+		}
+	}
+
+	// assert replication worked
+	fsversion(ctx, rfs, "@2")
+
+	// assert no step holds exist
+	abs, absErrs, err := endpoint.ListAbstractions(ctx, endpoint.ListZFSHoldsAndBookmarksQuery{
+		FS: endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter{
+			FS: &sfs,
+		},
+		Concurrency: 1,
+		JobID:       &sjid,
+		What:        endpoint.AbstractionTypeSet{endpoint.AbstractionStepHold: true},
+	})
+	require.NoError(ctx, err)
+	require.Empty(ctx, absErrs)
+	require.Len(ctx, abs, 0)
+
+	// assert that the replication cursor bookmark exists
+	abs, absErrs, err = endpoint.ListAbstractions(ctx, endpoint.ListZFSHoldsAndBookmarksQuery{
+		FS: endpoint.ListZFSHoldsAndBookmarksQueryFilesystemFilter{
+			FS: &sfs,
+		},
+		Concurrency: 1,
+		JobID:       &sjid,
+		What:        endpoint.AbstractionTypeSet{endpoint.AbstractionReplicationCursorBookmarkV2: true},
+	})
+	require.NoError(ctx, err)
+	require.Empty(ctx, absErrs)
+	require.Len(ctx, abs, 1)
+	require.True(ctx, zfs.FilesystemVersionEqualIdentity(abs[0].GetFilesystemVersion(), snap2sfs))
+}

platformtest/tests/undestroyableSnapshotParsing.go

@@ -17,12 +17,10 @@ func UndestroyableSnapshotParsing(t *platformtest.Context) {
 		+  "foo bar@1 2 3"
 		+  "foo bar@4 5 6"
 		+  "foo bar@7 8 9"
-		+  "foo bar@10 11 12"
 		R  zfs hold zrepl_platformtest "${ROOTDS}/foo bar@4 5 6"
-		R  zfs hold zrepl_platformtest "${ROOTDS}/foo bar@7 8 9"
 	`)
 
-	err := zfs.ZFSDestroy(t, fmt.Sprintf("%s/foo bar@1 2 3,4 5 6,7 8 9,10 11 12", t.RootDataset))
+	err := zfs.ZFSDestroy(t, fmt.Sprintf("%s/foo bar@1 2 3,4 5 6,7 8 9", t.RootDataset))
 	if err == nil {
 		panic("expecting destroy error due to hold")
 	}
@@ -32,9 +30,8 @@ func UndestroyableSnapshotParsing(t *platformtest.Context) {
 		if dse.Filesystem != fmt.Sprintf("%s/foo bar", t.RootDataset) {
 			panic(dse.Filesystem)
 		}
-		expectUndestroyable := []string{"4 5 6", "7 8 9"}
-		require.Len(t, dse.Undestroyable, len(expectUndestroyable))
-		require.Subset(t, dse.Undestroyable, expectUndestroyable)
+		require.Equal(t, []string{"4 5 6"}, dse.Undestroyable)
+		require.Equal(t, []string{"dataset is busy"}, dse.Reason)
 	}
 
 }

pruning/keep_grid.go

@@ -66,26 +66,24 @@ type retentionGridAdaptor struct {
 	Snapshot
 }
 
-func (a retentionGridAdaptor) Date() time.Time { return a.Snapshot.GetCreation() }
-
 func (a retentionGridAdaptor) LessThan(b retentiongrid.Entry) bool {
 	return a.Date().Before(b.Date())
 }
 
 // Prune filters snapshots with the retention grid.
-func (p *KeepGrid) KeepRule(snaps []Snapshot) PruneSnapshotsResult {
+func (p *KeepGrid) KeepRule(snaps []Snapshot) (destroyList []Snapshot) {
 
-	reCandidates := partitionSnapList(snaps, func(snapshot Snapshot) bool {
-		return p.re.MatchString(snapshot.GetName())
+	snaps = filterSnapList(snaps, func(snapshot Snapshot) bool {
+		return p.re.MatchString(snapshot.Name())
 	})
-	if len(reCandidates.Remove) == 0 {
-		return reCandidates
+	if len(snaps) == 0 {
+		return nil
 	}
 
 	// Build adaptors for retention grid
 	adaptors := make([]retentiongrid.Entry, 0)
 	for i := range snaps {
-		adaptors = append(adaptors, retentionGridAdaptor{reCandidates.Remove[i]})
+		adaptors = append(adaptors, retentionGridAdaptor{snaps[i]})
 	}
 
 	// determine 'now' edge
@@ -95,17 +93,12 @@ func (p *KeepGrid) KeepRule(snaps []Snapshot) PruneSnapshotsResult {
 	now := adaptors[len(adaptors)-1].Date()
 
 	// Evaluate retention grid
-	keepa, removea := p.retentionGrid.FitEntries(now, adaptors)
+	_, removea := p.retentionGrid.FitEntries(now, adaptors)
 
 	// Revert adaptors
-	destroyList := make([]Snapshot, len(removea))
+	destroyList = make([]Snapshot, len(removea))
 	for i := range removea {
 		destroyList[i] = removea[i].(retentionGridAdaptor).Snapshot
 	}
-	for _, a := range keepa {
-		reCandidates.Keep = append(reCandidates.Keep, a.(retentionGridAdaptor))
-	}
-	reCandidates.Remove = destroyList
-
-	return reCandidates
+	return destroyList
 }

pruning/keep_helpers.go

@@ -1,13 +1,10 @@
 package pruning
 
-func partitionSnapList(snaps []Snapshot, remove func(Snapshot) bool) (r PruneSnapshotsResult) {
-	r.Keep = make([]Snapshot, 0, len(snaps))
-	r.Remove = make([]Snapshot, 0, len(snaps))
+func filterSnapList(snaps []Snapshot, predicate func(Snapshot) bool) []Snapshot {
+	r := make([]Snapshot, 0, len(snaps))
 	for i := range snaps {
-		if remove(snaps[i]) {
-			r.Remove = append(r.Remove, snaps[i])
-		} else {
-			r.Keep = append(r.Keep, snaps[i])
+		if predicate(snaps[i]) {
+			r = append(r, snaps[i])
 		}
 	}
 	return r

pruning/keep_last_n.go

@@ -17,17 +17,17 @@ func NewKeepLastN(n int) (*KeepLastN, error) {
 	return &KeepLastN{n}, nil
 }
 
-func (k KeepLastN) KeepRule(snaps []Snapshot) PruneSnapshotsResult {
+func (k KeepLastN) KeepRule(snaps []Snapshot) (destroyList []Snapshot) {
 
 	if k.n > len(snaps) {
-		return PruneSnapshotsResult{Keep: snaps}
+		return []Snapshot{}
 	}
 
 	res := shallowCopySnapList(snaps)
 
 	sort.Slice(res, func(i, j int) bool {
-		return res[i].GetCreateTXG() > res[j].GetCreateTXG()
+		return res[i].Date().After(res[j].Date())
 	})
 
-	return PruneSnapshotsResult{Remove: res[k.n:], Keep: res[:k.n]}
+	return res[k.n:]
 }

pruning/keep_not_replicated.go

@@ -2,8 +2,8 @@ package pruning
 
 type KeepNotReplicated struct{}
 
-func (*KeepNotReplicated) KeepRule(snaps []Snapshot) PruneSnapshotsResult {
-	return partitionSnapList(snaps, func(snapshot Snapshot) bool {
+func (*KeepNotReplicated) KeepRule(snaps []Snapshot) (destroyList []Snapshot) {
+	return filterSnapList(snaps, func(snapshot Snapshot) bool {
 		return snapshot.Replicated()
 	})
 }

pruning/keep_regex.go

@@ -27,12 +27,12 @@ func MustKeepRegex(expr string, negate bool) *KeepRegex {
 	return k
 }
 
-func (k *KeepRegex) KeepRule(snaps []Snapshot) PruneSnapshotsResult {
-	return partitionSnapList(snaps, func(s Snapshot) bool {
+func (k *KeepRegex) KeepRule(snaps []Snapshot) []Snapshot {
+	return filterSnapList(snaps, func(s Snapshot) bool {
 		if k.negate {
-			return k.expr.FindStringIndex(s.GetName()) != nil
+			return k.expr.FindStringIndex(s.Name()) != nil
 		} else {
-			return k.expr.FindStringIndex(s.GetName()) == nil
+			return k.expr.FindStringIndex(s.Name()) == nil
 		}
 	})
 }

pruning/keep_step_holds.go

@@ -1,44 +0,0 @@
-package pruning
-
-import (
-	"github.com/pkg/errors"
-	"github.com/zrepl/zrepl/endpoint"
-)
-
-type KeepStepHolds struct {
-	keepJobIDs map[endpoint.JobID]bool
-}
-
-var _ KeepRule = (*KeepStepHolds)(nil)
-
-func NewKeepStepHolds(mainJobId endpoint.JobID, additionalJobIdsStrings []string) (_ *KeepStepHolds, err error) {
-	additionalJobIds := make(map[endpoint.JobID]bool, len(additionalJobIdsStrings))
-
-	mainJobId.MustValidate()
-	additionalJobIds[mainJobId] = true
-
-	for i := range additionalJobIdsStrings {
-		ajid, err := endpoint.MakeJobID(additionalJobIdsStrings[i])
-		if err != nil {
-			return nil, errors.WithMessagef(err, "cannot parse job id %q: %s", additionalJobIdsStrings[i])
-		}
-		if additionalJobIds[ajid] == true {
-			return nil, errors.Errorf("duplicate job id %q", ajid)
-		}
-	}
-	return &KeepStepHolds{additionalJobIds}, nil
-}
-
-func (h *KeepStepHolds) KeepRule(snaps []Snapshot) PruneSnapshotsResult {
-	return partitionSnapList(snaps, func(s Snapshot) bool {
-		holdingJobIDs := make(map[endpoint.JobID]bool)
-		for _, h := range s.StepHolds() {
-			holdingJobIDs[h.GetJobID()] = true
-		}
-		oneOrMoreOfOurJobIDsHoldsSnap := false
-		for kjid := range h.keepJobIDs {
-			oneOrMoreOfOurJobIDsHoldsSnap = oneOrMoreOfOurJobIDsHoldsSnap || holdingJobIDs[kjid]
-		}
-		return !oneOrMoreOfOurJobIDsHoldsSnap
-	})
-}

pruning/pruning.go

@@ -7,93 +7,47 @@ import (
 	"github.com/pkg/errors"
 
 	"github.com/zrepl/zrepl/config"
-	"github.com/zrepl/zrepl/endpoint"
 )
 
 type KeepRule interface {
-	KeepRule(snaps []Snapshot) PruneSnapshotsResult
+	KeepRule(snaps []Snapshot) (destroyList []Snapshot)
 }
 
 type Snapshot interface {
-	GetName() string
+	Name() string
 	Replicated() bool
-	GetCreation() time.Time
-	GetCreateTXG() uint64
-	StepHolds() []StepHold
+	Date() time.Time
 }
 
-type StepHold interface {
-	GetJobID() endpoint.JobID
-}
-
-type PruneSnapshotsResult struct {
-	Remove, Keep []Snapshot
-}
-
-// The returned snapshot results are a partition of the snaps argument.
-// That means than len(Remove) + len(Keep) == len(snaps)
-func PruneSnapshots(snapsI []Snapshot, keepRules []KeepRule) PruneSnapshotsResult {
+// The returned snapshot list is guaranteed to only contains elements of input parameter snaps
+func PruneSnapshots(snaps []Snapshot, keepRules []KeepRule) []Snapshot {
 
 	if len(keepRules) == 0 {
-		return PruneSnapshotsResult{Remove: nil, Keep: snapsI}
-	}
-
-	type snapshot struct {
-		Snapshot
-		keepCount, removeCount int
-	}
-
-	// project down to snapshot
-	snaps := make([]Snapshot, len(snapsI))
-	for i := range snaps {
-		snaps[i] = &snapshot{snapsI[i], 0, 0}
+		return []Snapshot{}
 	}
 
+	remCount := make(map[Snapshot]int, len(snaps))
 	for _, r := range keepRules {
-
-		ruleImplCheckSet := make(map[Snapshot]int, len(snaps))
-		for _, s := range snaps {
-			ruleImplCheckSet[s] = ruleImplCheckSet[s] + 1
-		}
-
-		ruleResults := r.KeepRule(snaps)
-
-		for _, s := range snaps {
-			ruleImplCheckSet[s] = ruleImplCheckSet[s] - 1
-		}
-		for _, n := range ruleImplCheckSet {
-			if n != 0 {
-				panic(fmt.Sprintf("incorrect rule implementation: %T", r))
-			}
-		}
-
-		for _, s := range ruleResults.Remove {
-			s.(*snapshot).removeCount++
-		}
-		for _, s := range ruleResults.Keep {
-			s.(*snapshot).keepCount++
+		ruleRems := r.KeepRule(snaps)
+		for _, ruleRem := range ruleRems {
+			remCount[ruleRem]++
 		}
 	}
 
 	remove := make([]Snapshot, 0, len(snaps))
-	keep := make([]Snapshot, 0, len(snaps))
-	for _, sI := range snaps {
-		s := sI.(*snapshot)
-		if s.removeCount == len(keepRules) {
-			// all keep rules agree to remove the snap
-			remove = append(remove, s.Snapshot)
-		} else {
-			keep = append(keep, s.Snapshot)
+	for snap, rc := range remCount {
+		if rc == len(keepRules) {
+			remove = append(remove, snap)
 		}
 	}
 
-	return PruneSnapshotsResult{Remove: remove, Keep: keep}
+	return remove
 }
 
-func RulesFromConfig(mainJobId endpoint.JobID, in []config.PruningEnum) (rules []KeepRule, err error) {
+func RulesFromConfig(in []config.PruningEnum) (rules []KeepRule, err error) {
 	rules = make([]KeepRule, len(in))
 	for i := range in {
-		rules[i], err = RuleFromConfig(mainJobId, in[i])
+		rules[i], err = RuleFromConfig(in[i])
 		if err != nil {
 			return nil, errors.Wrapf(err, "cannot build rule #%d", i)
 		}
@@ -101,7 +55,7 @@ func RulesFromConfig(mainJobId endpoint.JobID, in []config.PruningEnum) (rules [
 	return rules, nil
 }
 
-func RuleFromConfig(mainJobId endpoint.JobID, in config.PruningEnum) (KeepRule, error) {
+func RuleFromConfig(in config.PruningEnum) (KeepRule, error) {
 	switch v := in.Ret.(type) {
 	case *config.PruneKeepNotReplicated:
 		return NewKeepNotReplicated(), nil
@@ -111,8 +65,6 @@ func RuleFromConfig(mainJobId endpoint.JobID, in config.PruningEnum) (KeepRule,
 		return NewKeepRegex(v.Regex, v.Negate)
 	case *config.PruneGrid:
 		return NewKeepGrid(v)
-	case *config.PruneKeepStepHolds:
-		return NewKeepStepHolds(mainJobId, v.AdditionalJobIds)
 	default:
 		return nil, fmt.Errorf("unknown keep rule type %T", v)
 	}

replication/logic/pdu/pdu.pb.go

@@ -46,36 +46,7 @@ func (x Tri) String() string {
 	return proto.EnumName(Tri_name, int32(x))
 }
 func (Tri) EnumDescriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{0}
-}
-
-type SendAbstraction_SendAbstractionType int32
-
-const (
-	SendAbstraction_Undefined           SendAbstraction_SendAbstractionType = 0
-	SendAbstraction_ReplicationCursorV2 SendAbstraction_SendAbstractionType = 1
-	SendAbstraction_StepHold            SendAbstraction_SendAbstractionType = 2
-	SendAbstraction_StepBookmark        SendAbstraction_SendAbstractionType = 3
-)
-
-var SendAbstraction_SendAbstractionType_name = map[int32]string{
-	0: "Undefined",
-	1: "ReplicationCursorV2",
-	2: "StepHold",
-	3: "StepBookmark",
-}
-var SendAbstraction_SendAbstractionType_value = map[string]int32{
-	"Undefined":           0,
-	"ReplicationCursorV2": 1,
-	"StepHold":            2,
-	"StepBookmark":        3,
-}
-
-func (x SendAbstraction_SendAbstractionType) String() string {
-	return proto.EnumName(SendAbstraction_SendAbstractionType_name, int32(x))
-}
-func (SendAbstraction_SendAbstractionType) EnumDescriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{5, 0}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{0}
 }
 
 type FilesystemVersion_VersionType int32
@@ -98,7 +69,7 @@ func (x FilesystemVersion_VersionType) String() string {
 	return proto.EnumName(FilesystemVersion_VersionType_name, int32(x))
 }
 func (FilesystemVersion_VersionType) EnumDescriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{6, 0}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{5, 0}
 }
 
 type ListFilesystemReq struct {
@@ -111,7 +82,7 @@ func (m *ListFilesystemReq) Reset()         { *m = ListFilesystemReq{} }
 func (m *ListFilesystemReq) String() string { return proto.CompactTextString(m) }
 func (*ListFilesystemReq) ProtoMessage()    {}
 func (*ListFilesystemReq) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{0}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{0}
 }
 func (m *ListFilesystemReq) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_ListFilesystemReq.Unmarshal(m, b)
@@ -142,7 +113,7 @@ func (m *ListFilesystemRes) Reset()         { *m = ListFilesystemRes{} }
 func (m *ListFilesystemRes) String() string { return proto.CompactTextString(m) }
 func (*ListFilesystemRes) ProtoMessage()    {}
 func (*ListFilesystemRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{1}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{1}
 }
 func (m *ListFilesystemRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_ListFilesystemRes.Unmarshal(m, b)
@@ -183,7 +154,7 @@ func (m *Filesystem) Reset()         { *m = Filesystem{} }
 func (m *Filesystem) String() string { return proto.CompactTextString(m) }
 func (*Filesystem) ProtoMessage()    {}
 func (*Filesystem) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{2}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{2}
 }
 func (m *Filesystem) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_Filesystem.Unmarshal(m, b)
@@ -242,7 +213,7 @@ func (m *ListFilesystemVersionsReq) Reset()         { *m = ListFilesystemVersion
 func (m *ListFilesystemVersionsReq) String() string { return proto.CompactTextString(m) }
 func (*ListFilesystemVersionsReq) ProtoMessage()    {}
 func (*ListFilesystemVersionsReq) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{3}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{3}
 }
 func (m *ListFilesystemVersionsReq) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_ListFilesystemVersionsReq.Unmarshal(m, b)
@@ -271,7 +242,6 @@ func (m *ListFilesystemVersionsReq) GetFilesystem() string {
 
 type ListFilesystemVersionsRes struct {
 	Versions             []*FilesystemVersion `protobuf:"bytes,1,rep,name=Versions,proto3" json:"Versions,omitempty"`
-	SendAbstractions     []*SendAbstraction   `protobuf:"bytes,2,rep,name=SendAbstractions,proto3" json:"SendAbstractions,omitempty"`
 	XXX_NoUnkeyedLiteral struct{}             `json:"-"`
 	XXX_unrecognized     []byte               `json:"-"`
 	XXX_sizecache        int32                `json:"-"`
@@ -281,7 +251,7 @@ func (m *ListFilesystemVersionsRes) Reset()         { *m = ListFilesystemVersion
 func (m *ListFilesystemVersionsRes) String() string { return proto.CompactTextString(m) }
 func (*ListFilesystemVersionsRes) ProtoMessage()    {}
 func (*ListFilesystemVersionsRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{4}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{4}
 }
 func (m *ListFilesystemVersionsRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_ListFilesystemVersionsRes.Unmarshal(m, b)
@@ -308,67 +278,6 @@ func (m *ListFilesystemVersionsRes) GetVersions() []*FilesystemVersion {
 	return nil
 }
 
-func (m *ListFilesystemVersionsRes) GetSendAbstractions() []*SendAbstraction {
-	if m != nil {
-		return m.SendAbstractions
-	}
-	return nil
-}
-
-type SendAbstraction struct {
-	Type                 SendAbstraction_SendAbstractionType `protobuf:"varint,1,opt,name=Type,proto3,enum=SendAbstraction_SendAbstractionType" json:"Type,omitempty"`
-	JobID                string                              `protobuf:"bytes,2,opt,name=JobID,proto3" json:"JobID,omitempty"`
-	Version              *FilesystemVersion                  `protobuf:"bytes,3,opt,name=Version,proto3" json:"Version,omitempty"`
-	XXX_NoUnkeyedLiteral struct{}                            `json:"-"`
-	XXX_unrecognized     []byte                              `json:"-"`
-	XXX_sizecache        int32                               `json:"-"`
-}
-
-func (m *SendAbstraction) Reset()         { *m = SendAbstraction{} }
-func (m *SendAbstraction) String() string { return proto.CompactTextString(m) }
-func (*SendAbstraction) ProtoMessage()    {}
-func (*SendAbstraction) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{5}
-}
-func (m *SendAbstraction) XXX_Unmarshal(b []byte) error {
-	return xxx_messageInfo_SendAbstraction.Unmarshal(m, b)
-}
-func (m *SendAbstraction) XXX_Marshal(b []byte, deterministic bool) ([]byte, error) {
-	return xxx_messageInfo_SendAbstraction.Marshal(b, m, deterministic)
-}
-func (dst *SendAbstraction) XXX_Merge(src proto.Message) {
-	xxx_messageInfo_SendAbstraction.Merge(dst, src)
-}
-func (m *SendAbstraction) XXX_Size() int {
-	return xxx_messageInfo_SendAbstraction.Size(m)
-}
-func (m *SendAbstraction) XXX_DiscardUnknown() {
-	xxx_messageInfo_SendAbstraction.DiscardUnknown(m)
-}
-
-var xxx_messageInfo_SendAbstraction proto.InternalMessageInfo
-
-func (m *SendAbstraction) GetType() SendAbstraction_SendAbstractionType {
-	if m != nil {
-		return m.Type
-	}
-	return SendAbstraction_Undefined
-}
-
-func (m *SendAbstraction) GetJobID() string {
-	if m != nil {
-		return m.JobID
-	}
-	return ""
-}
-
-func (m *SendAbstraction) GetVersion() *FilesystemVersion {
-	if m != nil {
-		return m.Version
-	}
-	return nil
-}
-
 type FilesystemVersion struct {
 	Type                 FilesystemVersion_VersionType `protobuf:"varint,1,opt,name=Type,proto3,enum=FilesystemVersion_VersionType" json:"Type,omitempty"`
 	Name                 string                        `protobuf:"bytes,2,opt,name=Name,proto3" json:"Name,omitempty"`
@@ -384,7 +293,7 @@ func (m *FilesystemVersion) Reset()         { *m = FilesystemVersion{} }
 func (m *FilesystemVersion) String() string { return proto.CompactTextString(m) }
 func (*FilesystemVersion) ProtoMessage()    {}
 func (*FilesystemVersion) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{6}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{5}
 }
 func (m *FilesystemVersion) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_FilesystemVersion.Unmarshal(m, b)
@@ -462,7 +371,7 @@ func (m *SendReq) Reset()         { *m = SendReq{} }
 func (m *SendReq) String() string { return proto.CompactTextString(m) }
 func (*SendReq) ProtoMessage()    {}
 func (*SendReq) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{7}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{6}
 }
 func (m *SendReq) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_SendReq.Unmarshal(m, b)
@@ -536,7 +445,7 @@ func (m *Property) Reset()         { *m = Property{} }
 func (m *Property) String() string { return proto.CompactTextString(m) }
 func (*Property) ProtoMessage()    {}
 func (*Property) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{8}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{7}
 }
 func (m *Property) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_Property.Unmarshal(m, b)
@@ -587,7 +496,7 @@ func (m *SendRes) Reset()         { *m = SendRes{} }
 func (m *SendRes) String() string { return proto.CompactTextString(m) }
 func (*SendRes) ProtoMessage()    {}
 func (*SendRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{9}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{8}
 }
 func (m *SendRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_SendRes.Unmarshal(m, b)
@@ -639,7 +548,7 @@ func (m *SendCompletedReq) Reset()         { *m = SendCompletedReq{} }
 func (m *SendCompletedReq) String() string { return proto.CompactTextString(m) }
 func (*SendCompletedReq) ProtoMessage()    {}
 func (*SendCompletedReq) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{10}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{9}
 }
 func (m *SendCompletedReq) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_SendCompletedReq.Unmarshal(m, b)
@@ -676,7 +585,7 @@ func (m *SendCompletedRes) Reset()         { *m = SendCompletedRes{} }
 func (m *SendCompletedRes) String() string { return proto.CompactTextString(m) }
 func (*SendCompletedRes) ProtoMessage()    {}
 func (*SendCompletedRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{11}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{10}
 }
 func (m *SendCompletedRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_SendCompletedRes.Unmarshal(m, b)
@@ -711,7 +620,7 @@ func (m *ReceiveReq) Reset()         { *m = ReceiveReq{} }
 func (m *ReceiveReq) String() string { return proto.CompactTextString(m) }
 func (*ReceiveReq) ProtoMessage()    {}
 func (*ReceiveReq) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{12}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{11}
 }
 func (m *ReceiveReq) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_ReceiveReq.Unmarshal(m, b)
@@ -762,7 +671,7 @@ func (m *ReceiveRes) Reset()         { *m = ReceiveRes{} }
 func (m *ReceiveRes) String() string { return proto.CompactTextString(m) }
 func (*ReceiveRes) ProtoMessage()    {}
 func (*ReceiveRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{13}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{12}
 }
 func (m *ReceiveRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_ReceiveRes.Unmarshal(m, b)
@@ -795,7 +704,7 @@ func (m *DestroySnapshotsReq) Reset()         { *m = DestroySnapshotsReq{} }
 func (m *DestroySnapshotsReq) String() string { return proto.CompactTextString(m) }
 func (*DestroySnapshotsReq) ProtoMessage()    {}
 func (*DestroySnapshotsReq) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{14}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{13}
 }
 func (m *DestroySnapshotsReq) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_DestroySnapshotsReq.Unmarshal(m, b)
@@ -841,7 +750,7 @@ func (m *DestroySnapshotRes) Reset()         { *m = DestroySnapshotRes{} }
 func (m *DestroySnapshotRes) String() string { return proto.CompactTextString(m) }
 func (*DestroySnapshotRes) ProtoMessage()    {}
 func (*DestroySnapshotRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{15}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{14}
 }
 func (m *DestroySnapshotRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_DestroySnapshotRes.Unmarshal(m, b)
@@ -886,7 +795,7 @@ func (m *DestroySnapshotsRes) Reset()         { *m = DestroySnapshotsRes{} }
 func (m *DestroySnapshotsRes) String() string { return proto.CompactTextString(m) }
 func (*DestroySnapshotsRes) ProtoMessage()    {}
 func (*DestroySnapshotsRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{16}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{15}
 }
 func (m *DestroySnapshotsRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_DestroySnapshotsRes.Unmarshal(m, b)
@@ -924,7 +833,7 @@ func (m *ReplicationCursorReq) Reset()         { *m = ReplicationCursorReq{} }
 func (m *ReplicationCursorReq) String() string { return proto.CompactTextString(m) }
 func (*ReplicationCursorReq) ProtoMessage()    {}
 func (*ReplicationCursorReq) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{17}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{16}
 }
 func (m *ReplicationCursorReq) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_ReplicationCursorReq.Unmarshal(m, b)
@@ -965,7 +874,7 @@ func (m *ReplicationCursorRes) Reset()         { *m = ReplicationCursorRes{} }
 func (m *ReplicationCursorRes) String() string { return proto.CompactTextString(m) }
 func (*ReplicationCursorRes) ProtoMessage()    {}
 func (*ReplicationCursorRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{18}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{17}
 }
 func (m *ReplicationCursorRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_ReplicationCursorRes.Unmarshal(m, b)
@@ -1101,7 +1010,7 @@ func (m *PingReq) Reset()         { *m = PingReq{} }
 func (m *PingReq) String() string { return proto.CompactTextString(m) }
 func (*PingReq) ProtoMessage()    {}
 func (*PingReq) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{19}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{18}
 }
 func (m *PingReq) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_PingReq.Unmarshal(m, b)
@@ -1140,7 +1049,7 @@ func (m *PingRes) Reset()         { *m = PingRes{} }
 func (m *PingRes) String() string { return proto.CompactTextString(m) }
 func (*PingRes) ProtoMessage()    {}
 func (*PingRes) Descriptor() ([]byte, []int) {
-	return fileDescriptor_pdu_2d84e8d7d278a80d, []int{20}
+	return fileDescriptor_pdu_483c6918b7b3d747, []int{19}
 }
 func (m *PingRes) XXX_Unmarshal(b []byte) error {
 	return xxx_messageInfo_PingRes.Unmarshal(m, b)
@@ -1173,7 +1082,6 @@ func init() {
 	proto.RegisterType((*Filesystem)(nil), "Filesystem")
 	proto.RegisterType((*ListFilesystemVersionsReq)(nil), "ListFilesystemVersionsReq")
 	proto.RegisterType((*ListFilesystemVersionsRes)(nil), "ListFilesystemVersionsRes")
-	proto.RegisterType((*SendAbstraction)(nil), "SendAbstraction")
 	proto.RegisterType((*FilesystemVersion)(nil), "FilesystemVersion")
 	proto.RegisterType((*SendReq)(nil), "SendReq")
 	proto.RegisterType((*Property)(nil), "Property")
@@ -1190,7 +1098,6 @@ func init() {
 	proto.RegisterType((*PingReq)(nil), "PingReq")
 	proto.RegisterType((*PingRes)(nil), "PingRes")
 	proto.RegisterEnum("Tri", Tri_name, Tri_value)
-	proto.RegisterEnum("SendAbstraction_SendAbstractionType", SendAbstraction_SendAbstractionType_name, SendAbstraction_SendAbstractionType_value)
 	proto.RegisterEnum("FilesystemVersion_VersionType", FilesystemVersion_VersionType_name, FilesystemVersion_VersionType_value)
 }
 
@@ -1431,67 +1338,61 @@ var _Replication_serviceDesc = grpc.ServiceDesc{
 	Metadata: "pdu.proto",
 }
 
-func init() { proto.RegisterFile("pdu.proto", fileDescriptor_pdu_2d84e8d7d278a80d) }
+func init() { proto.RegisterFile("pdu.proto", fileDescriptor_pdu_483c6918b7b3d747) }
 
-var fileDescriptor_pdu_2d84e8d7d278a80d = []byte{
-	// 940 bytes of a gzipped FileDescriptorProto
-	0x1f, 0x8b, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0xff, 0x8c, 0x56, 0x6d, 0x6f, 0xe3, 0xc4,
-	0x13, 0xaf, 0x13, 0xa7, 0x75, 0x26, 0xed, 0xbf, 0xee, 0x24, 0xff, 0x23, 0x44, 0x70, 0xaa, 0x96,
-	0x13, 0xca, 0x55, 0x60, 0xa1, 0xf0, 0x20, 0x10, 0xe8, 0xa4, 0x6b, 0xd2, 0x5e, 0x8b, 0xe0, 0x88,
-	0xb6, 0xb9, 0x0a, 0x9d, 0xc4, 0x0b, 0x37, 0x1e, 0x5a, 0xab, 0x8e, 0xd7, 0xdd, 0x75, 0xd0, 0x05,
-	0xf1, 0x8a, 0x77, 0xf0, 0xf5, 0xe0, 0x73, 0x20, 0x3e, 0x02, 0xf2, 0xc6, 0x4e, 0x1c, 0xdb, 0x3d,
-	0xf5, 0x55, 0x76, 0x7e, 0x33, 0xe3, 0x9d, 0xc7, 0xdf, 0x06, 0x9a, 0x91, 0x37, 0x77, 0x22, 0x29,
-	0x62, 0xc1, 0xda, 0x70, 0xf0, 0x9d, 0xaf, 0xe2, 0x53, 0x3f, 0x20, 0xb5, 0x50, 0x31, 0xcd, 0x38,
-	0xdd, 0xb1, 0xe3, 0x32, 0xa8, 0xf0, 0x63, 0x68, 0xad, 0x01, 0xd5, 0x35, 0x0e, 0xeb, 0xfd, 0xd6,
-	0xa0, 0xe5, 0xe4, 0x8c, 0xf2, 0x7a, 0xf6, 0xa7, 0x01, 0xb0, 0x96, 0x11, 0xc1, 0x1c, 0xbb, 0xf1,
-	0x4d, 0xd7, 0x38, 0x34, 0xfa, 0x4d, 0xae, 0xcf, 0x78, 0x08, 0x2d, 0x4e, 0x6a, 0x3e, 0xa3, 0x89,
-	0xb8, 0xa5, 0xb0, 0x5b, 0xd3, 0xaa, 0x3c, 0x84, 0x4f, 0x60, 0xef, 0x5c, 0x8d, 0x03, 0x77, 0x4a,
-	0x37, 0x22, 0xf0, 0x48, 0x76, 0xeb, 0x87, 0x46, 0xdf, 0xe2, 0x9b, 0x60, 0xf2, 0x9d, 0x73, 0x75,
-	0x12, 0x4e, 0xe5, 0x22, 0x8a, 0xc9, 0xeb, 0x9a, 0xda, 0x26, 0x0f, 0xb1, 0xaf, 0xe1, 0xdd, 0xcd,
-	0x84, 0x2e, 0x49, 0x2a, 0x5f, 0x84, 0x8a, 0xd3, 0x1d, 0x3e, 0xce, 0x07, 0x9a, 0x06, 0x98, 0x43,
-	0xd8, 0x1f, 0xc6, 0xfd, 0xde, 0x0a, 0x1d, 0xb0, 0x32, 0x31, 0xad, 0x09, 0x3a, 0x25, 0x4b, 0xbe,
-	0xb2, 0xc1, 0x6f, 0xc0, 0xbe, 0xa0, 0xd0, 0x7b, 0x7e, 0xa5, 0x62, 0xe9, 0x4e, 0x63, 0xed, 0x57,
-	0xd3, 0x7e, 0xb6, 0x53, 0x50, 0xf0, 0x92, 0x25, 0xfb, 0xc7, 0x80, 0xfd, 0x02, 0x88, 0x5f, 0x82,
-	0x39, 0x59, 0x44, 0xa4, 0x23, 0xff, 0xdf, 0xe0, 0x49, 0xf1, 0x2b, 0x45, 0x39, 0xb1, 0xe5, 0xda,
-	0x03, 0x3b, 0xd0, 0xf8, 0x56, 0x5c, 0x9d, 0x8f, 0xd2, 0xd2, 0x2f, 0x05, 0xfc, 0x08, 0x76, 0xd2,
-	0x68, 0x75, 0xb9, 0xab, 0x13, 0xca, 0x4c, 0xd8, 0x4f, 0xd0, 0xae, 0xb8, 0x00, 0xf7, 0xa0, 0xf9,
-	0x2a, 0xf4, 0xe8, 0x67, 0x3f, 0x24, 0xcf, 0xde, 0xc2, 0x77, 0xa0, 0xcd, 0x29, 0x0a, 0xfc, 0xa9,
-	0x9b, 0x58, 0x0c, 0xe7, 0x52, 0x09, 0x79, 0x39, 0xb0, 0x0d, 0xdc, 0x05, 0xeb, 0x22, 0xa6, 0xe8,
-	0x4c, 0x04, 0x9e, 0x5d, 0x43, 0x1b, 0x76, 0x13, 0xe9, 0x58, 0x88, 0xdb, 0x99, 0x2b, 0x6f, 0xed,
-	0x3a, 0xfb, 0xdb, 0x80, 0x83, 0xd2, 0xed, 0x38, 0xd8, 0x48, 0xf9, 0x71, 0x39, 0x3e, 0x27, 0xfd,
-	0xcd, 0x25, 0x8b, 0x60, 0xbe, 0x74, 0x67, 0x94, 0xe6, 0xaa, 0xcf, 0x09, 0xf6, 0x62, 0xee, 0x7b,
-	0x3a, 0x4f, 0x93, 0xeb, 0x33, 0xbe, 0x07, 0xcd, 0xa1, 0x24, 0x37, 0xa6, 0xc9, 0x8f, 0x2f, 0xf4,
-	0x2c, 0x99, 0x7c, 0x0d, 0x60, 0x0f, 0x2c, 0x2d, 0x24, 0xd5, 0x69, 0xe8, 0x2f, 0xad, 0x64, 0xf6,
-	0x14, 0x5a, 0xb9, 0x6b, 0x75, 0x6a, 0xa1, 0x1b, 0xa9, 0x1b, 0x11, 0xdb, 0x5b, 0x89, 0xb4, 0x4a,
-	0xcb, 0x60, 0x7f, 0x19, 0xb0, 0x93, 0x94, 0xed, 0x01, 0xf3, 0x87, 0x1f, 0x82, 0x79, 0x2a, 0xc5,
-	0x4c, 0x07, 0x5e, 0xdd, 0x0c, 0xad, 0x47, 0x06, 0xb5, 0x89, 0x78, 0x4b, 0xcb, 0x6a, 0x13, 0x51,
-	0x5c, 0x39, 0xb3, 0xbc, 0x72, 0x0c, 0x9a, 0xeb, 0x55, 0x6a, 0xe8, 0xfa, 0x9a, 0xce, 0x44, 0xfa,
-	0x7c, 0x0d, 0xe3, 0x23, 0xd8, 0x1e, 0xc9, 0x05, 0x9f, 0x87, 0xdd, 0x6d, 0xbd, 0x6b, 0xa9, 0xc4,
-	0x3e, 0x03, 0x6b, 0x2c, 0x45, 0x44, 0x32, 0x5e, 0xac, 0xca, 0x6d, 0xe4, 0xca, 0xdd, 0x81, 0xc6,
-	0xa5, 0x1b, 0xcc, 0xb3, 0x1e, 0x2c, 0x05, 0xf6, 0xfb, 0xaa, 0x16, 0x0a, 0xfb, 0xb0, 0xff, 0x4a,
-	0x91, 0x57, 0xa4, 0x05, 0x8b, 0x17, 0x61, 0x64, 0xb0, 0x7b, 0xf2, 0x26, 0xa2, 0x69, 0x4c, 0xde,
-	0x85, 0xff, 0x2b, 0xe9, 0xbc, 0xeb, 0x7c, 0x03, 0xc3, 0xa7, 0x00, 0x69, 0x3c, 0x3e, 0xa9, 0xae,
-	0xa9, 0xb7, 0xac, 0xe9, 0x64, 0x21, 0xf2, 0x9c, 0x92, 0x3d, 0x5b, 0xae, 0xe5, 0x50, 0xcc, 0xa2,
-	0x80, 0x62, 0xd2, 0x8d, 0x39, 0x82, 0xd6, 0x0f, 0xd2, 0xbf, 0xf6, 0x43, 0x37, 0xe0, 0x74, 0x97,
-	0xd6, 0xdf, 0x72, 0xd2, 0xbe, 0xf1, 0xbc, 0x92, 0x61, 0xc9, 0x5f, 0xb1, 0xdf, 0x00, 0x38, 0x4d,
-	0xc9, 0xff, 0x85, 0x1e, 0xd2, 0xe6, 0x65, 0xfb, 0x6a, 0x6f, 0x6d, 0xdf, 0x11, 0xd8, 0xc3, 0x80,
-	0x5c, 0x99, 0xaf, 0xcf, 0x92, 0x12, 0x4b, 0x38, 0xdb, 0xcd, 0xdd, 0xae, 0xd8, 0x35, 0xb4, 0x47,
-	0xa4, 0x62, 0x29, 0x16, 0xd9, 0x4c, 0x3e, 0x84, 0xfb, 0xf0, 0x13, 0x68, 0xae, 0xec, 0x53, 0x9a,
-	0xaa, 0x8a, 0x6d, 0x6d, 0xc4, 0x5e, 0x03, 0x16, 0x2e, 0x4a, 0x59, 0x32, 0x13, 0xf5, 0x2d, 0xf7,
-	0xb0, 0x64, 0x66, 0x93, 0x4c, 0xca, 0x89, 0x94, 0x42, 0x66, 0x93, 0xa2, 0x05, 0x36, 0xaa, 0x4a,
-	0x22, 0x79, 0x99, 0x76, 0x92, 0xc4, 0x83, 0x38, 0x63, 0xe0, 0xb6, 0x53, 0x0e, 0x81, 0x67, 0x36,
-	0xec, 0x0b, 0xe8, 0x94, 0xb8, 0xe8, 0x21, 0xef, 0xc0, 0xa4, 0xd2, 0x4f, 0x61, 0x27, 0x25, 0x91,
-	0xc4, 0xc3, 0x3c, 0xdb, 0x5a, 0xd1, 0x88, 0xf5, 0x52, 0xc4, 0xf4, 0xc6, 0x57, 0xf1, 0x72, 0x84,
-	0xcf, 0xb6, 0xf8, 0x0a, 0x39, 0xb6, 0x60, 0x7b, 0x19, 0x0e, 0xfb, 0x00, 0x76, 0xc6, 0x7e, 0x78,
-	0x9d, 0x04, 0xd0, 0x85, 0x9d, 0xef, 0x49, 0x29, 0xf7, 0x3a, 0xdb, 0x9a, 0x4c, 0x64, 0xef, 0x67,
-	0x46, 0x2a, 0xd9, 0xab, 0x93, 0xe9, 0x8d, 0xc8, 0xf6, 0x2a, 0x39, 0x1f, 0xf5, 0xa1, 0x3e, 0x91,
-	0x7e, 0x42, 0x31, 0x23, 0x11, 0xc6, 0x43, 0x57, 0x92, 0xbd, 0x85, 0x4d, 0x68, 0x9c, 0xba, 0x81,
-	0x22, 0xdb, 0x40, 0x0b, 0xcc, 0x89, 0x9c, 0x93, 0x5d, 0x1b, 0xfc, 0x5b, 0x4b, 0x08, 0x60, 0x95,
-	0x04, 0xf6, 0xc0, 0x4c, 0x3e, 0x8c, 0x96, 0x93, 0x06, 0xd1, 0xcb, 0x4e, 0x0a, 0xbf, 0x82, 0xfd,
-	0xcd, 0x67, 0x4f, 0x21, 0x3a, 0xa5, 0x3f, 0x0b, 0xbd, 0x32, 0xa6, 0x70, 0x0c, 0x8f, 0xaa, 0x5f,
-	0x4c, 0xec, 0x39, 0xf7, 0x3e, 0xc4, 0xbd, 0xfb, 0x75, 0x0a, 0x9f, 0x81, 0x5d, 0x6c, 0x3d, 0x76,
-	0x9c, 0x8a, 0x91, 0xee, 0x55, 0xa1, 0x0a, 0x9f, 0xc3, 0x41, 0xa9, 0x79, 0xf8, 0x7f, 0xa7, 0x6a,
-	0x10, 0x7a, 0x95, 0xb0, 0xc2, 0xcf, 0x61, 0x6f, 0x63, 0xc5, 0xf1, 0xc0, 0x29, 0x52, 0x46, 0xaf,
-	0x04, 0xa9, 0xe3, 0xc6, 0xeb, 0x7a, 0xe4, 0xcd, 0xaf, 0xb6, 0xf5, 0xff, 0xad, 0x4f, 0xff, 0x0b,
-	0x00, 0x00, 0xff, 0xff, 0x0a, 0xa0, 0x3f, 0xc2, 0x7c, 0x09, 0x00, 0x00,
+var fileDescriptor_pdu_483c6918b7b3d747 = []byte{
+	// 833 bytes of a gzipped FileDescriptorProto
+	0x1f, 0x8b, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0xff, 0x8c, 0x56, 0x5f, 0x6f, 0xe3, 0x44,
+	0x10, 0xaf, 0x13, 0xa7, 0x75, 0x26, 0x3d, 0x2e, 0x9d, 0x96, 0x93, 0xb1, 0xe0, 0x54, 0x2d, 0x08,
+	0xe5, 0x2a, 0x61, 0xa1, 0xf2, 0x47, 0x42, 0x48, 0x27, 0xd1, 0xb4, 0xbd, 0x3b, 0x01, 0x47, 0xb4,
+	0x35, 0x27, 0x74, 0x6f, 0x26, 0x19, 0xb5, 0x56, 0x1d, 0xaf, 0xbb, 0xe3, 0xa0, 0x0b, 0xe2, 0x89,
+	0x47, 0xbe, 0x1e, 0x7c, 0x10, 0x3e, 0x02, 0xf2, 0xc6, 0x4e, 0x9c, 0xd8, 0x41, 0x79, 0xca, 0xce,
+	0x6f, 0x66, 0x77, 0x67, 0x7f, 0xf3, 0x9b, 0x71, 0xa0, 0x9b, 0x4e, 0x66, 0x7e, 0xaa, 0x55, 0xa6,
+	0xc4, 0x31, 0x1c, 0xfd, 0x10, 0x71, 0x76, 0x1d, 0xc5, 0xc4, 0x73, 0xce, 0x68, 0x2a, 0xe9, 0x41,
+	0x5c, 0xd4, 0x41, 0xc6, 0xcf, 0xa0, 0xb7, 0x02, 0xd8, 0xb5, 0x4e, 0xdb, 0x83, 0xde, 0x79, 0xcf,
+	0xaf, 0x04, 0x55, 0xfd, 0xe2, 0x2f, 0x0b, 0x60, 0x65, 0x23, 0x82, 0x3d, 0x0a, 0xb3, 0x3b, 0xd7,
+	0x3a, 0xb5, 0x06, 0x5d, 0x69, 0xd6, 0x78, 0x0a, 0x3d, 0x49, 0x3c, 0x9b, 0x52, 0xa0, 0xee, 0x29,
+	0x71, 0x5b, 0xc6, 0x55, 0x85, 0xf0, 0x13, 0x78, 0xf4, 0x8a, 0x47, 0x71, 0x38, 0xa6, 0x3b, 0x15,
+	0x4f, 0x48, 0xbb, 0xed, 0x53, 0x6b, 0xe0, 0xc8, 0x75, 0x30, 0x3f, 0xe7, 0x15, 0x5f, 0x25, 0x63,
+	0x3d, 0x4f, 0x33, 0x9a, 0xb8, 0xb6, 0x89, 0xa9, 0x42, 0xe2, 0x5b, 0xf8, 0x60, 0xfd, 0x41, 0x6f,
+	0x48, 0x73, 0xa4, 0x12, 0x96, 0xf4, 0x80, 0x4f, 0xab, 0x89, 0x16, 0x09, 0x56, 0x10, 0xf1, 0xfd,
+	0xf6, 0xcd, 0x8c, 0x3e, 0x38, 0xa5, 0x59, 0x50, 0x82, 0x7e, 0x2d, 0x52, 0x2e, 0x63, 0xc4, 0x3f,
+	0x16, 0x1c, 0xd5, 0xfc, 0x78, 0x0e, 0x76, 0x30, 0x4f, 0xc9, 0x5c, 0xfe, 0xde, 0xf9, 0xd3, 0xfa,
+	0x09, 0x7e, 0xf1, 0x9b, 0x47, 0x49, 0x13, 0x9b, 0x33, 0xfa, 0x3a, 0x9c, 0x52, 0x41, 0x9b, 0x59,
+	0xe7, 0xd8, 0x8b, 0x59, 0x34, 0x31, 0x34, 0xd9, 0xd2, 0xac, 0xf1, 0x43, 0xe8, 0x0e, 0x35, 0x85,
+	0x19, 0x05, 0xbf, 0xbc, 0x30, 0xdc, 0xd8, 0x72, 0x05, 0xa0, 0x07, 0x8e, 0x31, 0x22, 0x95, 0xb8,
+	0x1d, 0x73, 0xd2, 0xd2, 0x16, 0xcf, 0xa0, 0x57, 0xb9, 0x16, 0x0f, 0xc1, 0xb9, 0x49, 0xc2, 0x94,
+	0xef, 0x54, 0xd6, 0xdf, 0xcb, 0xad, 0x0b, 0xa5, 0xee, 0xa7, 0xa1, 0xbe, 0xef, 0x5b, 0xe2, 0x6f,
+	0x0b, 0x0e, 0x6e, 0x28, 0x99, 0xec, 0xc0, 0x27, 0x7e, 0x0a, 0xf6, 0xb5, 0x56, 0x53, 0x93, 0x78,
+	0x33, 0x5d, 0xc6, 0x8f, 0x02, 0x5a, 0x81, 0x32, 0x4f, 0x69, 0x8e, 0x6a, 0x05, 0x6a, 0x53, 0x42,
+	0x76, 0x5d, 0x42, 0x02, 0xba, 0x2b, 0x69, 0x74, 0x0c, 0xbf, 0xb6, 0x1f, 0xe8, 0x48, 0xae, 0x60,
+	0x7c, 0x02, 0xfb, 0x97, 0x7a, 0x2e, 0x67, 0x89, 0xbb, 0x6f, 0xb4, 0x53, 0x58, 0xe2, 0x4b, 0x70,
+	0x46, 0x5a, 0xa5, 0xa4, 0xb3, 0xf9, 0x92, 0x6e, 0xab, 0x42, 0xf7, 0x09, 0x74, 0xde, 0x84, 0xf1,
+	0xac, 0xac, 0xc1, 0xc2, 0x10, 0x7f, 0x2e, 0xb9, 0x60, 0x1c, 0xc0, 0xe3, 0x9f, 0x99, 0x26, 0x9b,
+	0x32, 0x77, 0xe4, 0x26, 0x8c, 0x02, 0x0e, 0xaf, 0xde, 0xa5, 0x34, 0xce, 0x68, 0x72, 0x13, 0xfd,
+	0x4e, 0xe6, 0xdd, 0x6d, 0xb9, 0x86, 0xe1, 0x33, 0x80, 0x22, 0x9f, 0x88, 0xd8, 0xb5, 0x8d, 0xdc,
+	0xba, 0x7e, 0x99, 0xa2, 0xac, 0x38, 0xc5, 0x73, 0xe8, 0xe7, 0x39, 0x0c, 0xd5, 0x34, 0x8d, 0x29,
+	0x23, 0x53, 0x98, 0x33, 0xe8, 0xfd, 0xa4, 0xa3, 0xdb, 0x28, 0x09, 0x63, 0x49, 0x0f, 0x05, 0xff,
+	0x8e, 0x5f, 0xd4, 0x4d, 0x56, 0x9d, 0x02, 0x6b, 0xfb, 0x59, 0xfc, 0x01, 0x20, 0x69, 0x4c, 0xd1,
+	0x6f, 0xb4, 0x4b, 0x99, 0x17, 0xe5, 0x6b, 0xfd, 0x6f, 0xf9, 0xce, 0xa0, 0x3f, 0x8c, 0x29, 0xd4,
+	0x55, 0x7e, 0x16, 0x2d, 0x5e, 0xc3, 0xc5, 0x61, 0xe5, 0x76, 0x16, 0xb7, 0x70, 0x7c, 0x49, 0x9c,
+	0x69, 0x35, 0x2f, 0x35, 0xb9, 0x4b, 0x2f, 0xe3, 0xe7, 0xd0, 0x5d, 0xc6, 0xbb, 0xad, 0xad, 0xfd,
+	0xba, 0x0a, 0x12, 0x6f, 0x01, 0x37, 0x2e, 0x2a, 0xda, 0xbe, 0x34, 0xcd, 0x2d, 0x5b, 0xda, 0xbe,
+	0x8c, 0xc9, 0x95, 0x72, 0xa5, 0xb5, 0xd2, 0xa5, 0x52, 0x8c, 0x21, 0x2e, 0x9b, 0x1e, 0x91, 0x4f,
+	0xda, 0x83, 0xfc, 0xe1, 0x71, 0x56, 0x8e, 0x94, 0x63, 0xbf, 0x9e, 0x82, 0x2c, 0x63, 0xc4, 0xd7,
+	0x70, 0x22, 0x29, 0x8d, 0xa3, 0xb1, 0xe9, 0xda, 0xe1, 0x4c, 0xb3, 0xd2, 0xbb, 0xcc, 0xb5, 0xa0,
+	0x71, 0x1f, 0xe3, 0x49, 0x31, 0x44, 0xf2, 0x1d, 0xf6, 0xcb, 0xbd, 0xe5, 0x18, 0x71, 0x5e, 0xab,
+	0x8c, 0xde, 0x45, 0x9c, 0x2d, 0x24, 0xfc, 0x72, 0x4f, 0x2e, 0x91, 0x0b, 0x07, 0xf6, 0x17, 0xe9,
+	0x88, 0x8f, 0xe1, 0x60, 0x14, 0x25, 0xb7, 0x79, 0x02, 0x2e, 0x1c, 0xfc, 0x48, 0xcc, 0xe1, 0x6d,
+	0xd9, 0x35, 0xa5, 0x29, 0x3e, 0x2a, 0x83, 0x38, 0xef, 0xab, 0xab, 0xf1, 0x9d, 0x2a, 0xfb, 0x2a,
+	0x5f, 0x9f, 0x0d, 0xa0, 0x1d, 0xe8, 0x28, 0x1f, 0x31, 0x97, 0x2a, 0xc9, 0x86, 0xa1, 0xa6, 0xfe,
+	0x1e, 0x76, 0xa1, 0x73, 0x1d, 0xc6, 0x4c, 0x7d, 0x0b, 0x1d, 0xb0, 0x03, 0x3d, 0xa3, 0x7e, 0xeb,
+	0xfc, 0xdf, 0x56, 0x3e, 0x00, 0x96, 0x8f, 0x40, 0x0f, 0xec, 0xfc, 0x60, 0x74, 0xfc, 0x22, 0x09,
+	0xaf, 0x5c, 0x31, 0x7e, 0x03, 0x8f, 0xd7, 0xe7, 0x38, 0x23, 0xfa, 0xb5, 0x8f, 0x9f, 0x57, 0xc7,
+	0x18, 0x47, 0xf0, 0xa4, 0xf9, 0x13, 0x80, 0x9e, 0xbf, 0xf5, 0xc3, 0xe2, 0x6d, 0xf7, 0x31, 0x3e,
+	0x87, 0xfe, 0x66, 0xe9, 0xf1, 0xc4, 0x6f, 0x90, 0xb4, 0xd7, 0x84, 0x32, 0x7e, 0x07, 0x47, 0xb5,
+	0xe2, 0xe1, 0xfb, 0x7e, 0x93, 0x10, 0xbc, 0x46, 0x98, 0xf1, 0x2b, 0x78, 0xb4, 0xd6, 0xe2, 0x78,
+	0xe4, 0x6f, 0x8e, 0x0c, 0xaf, 0x06, 0xf1, 0x45, 0xe7, 0x6d, 0x3b, 0x9d, 0xcc, 0x7e, 0xdd, 0x37,
+	0xff, 0x1f, 0xbe, 0xf8, 0x2f, 0x00, 0x00, 0xff, 0xff, 0x27, 0x95, 0xc1, 0x78, 0x4c, 0x08, 0x00,
+	0x00,
 }

replication/logic/pdu/pdu.proto

@@ -25,22 +25,7 @@ message Filesystem {
 
 message ListFilesystemVersionsReq { string Filesystem = 1; }
 
-message ListFilesystemVersionsRes {
-  repeated FilesystemVersion Versions = 1;
-  repeated SendAbstraction SendAbstractions = 2;
-}
-
-message SendAbstraction {
-  enum SendAbstractionType {
-    Undefined = 0;
-    ReplicationCursorV2 = 1;
-    StepHold = 2;
-    StepBookmark = 3;
-  };
-  SendAbstractionType Type = 1;
-  string JobID = 2;
-  FilesystemVersion Version = 3;
-}
+message ListFilesystemVersionsRes { repeated FilesystemVersion Versions = 1; }
 
 message FilesystemVersion {
   enum VersionType {
@@ -95,7 +80,9 @@ message SendRes {
   repeated Property Properties = 4;
 }
 
-message SendCompletedReq { SendReq OriginalReq = 2; }
+message SendCompletedReq {
+  SendReq OriginalReq = 2;
+}
 
 message SendCompletedRes {}
 
@@ -111,7 +98,7 @@ message ReceiveReq {
 message ReceiveRes {}
 
 message DestroySnapshotsReq {
-string Filesystem = 1;
+  string Filesystem = 1;
   // Path to filesystem, snapshot or bookmark to be destroyed
   repeated FilesystemVersion Snapshots = 2;
 }

util/envconst/envconst.go

@@ -12,84 +12,100 @@ import (
 
 var cache sync.Map
 
-func Duration(varname string, def time.Duration) time.Duration {
+func Reset() {
+	cache.Range(func(key, _ interface{}) bool {
+		cache.Delete(key)
+		return true
+	})
+}
+
+func Duration(varname string, def time.Duration) (d time.Duration) {
+	var err error
 	if v, ok := cache.Load(varname); ok {
 		return v.(time.Duration)
 	}
 	e := os.Getenv(varname)
 	if e == "" {
-		return def
-	}
-	d, err := time.ParseDuration(e)
-	if err != nil {
-		panic(err)
+		d = def
+	} else {
+		d, err = time.ParseDuration(e)
+		if err != nil {
+			panic(err)
+		}
 	}
 	cache.Store(varname, d)
 	return d
 }
 
-func Int(varname string, def int) int {
+func Int(varname string, def int) (d int) {
 	if v, ok := cache.Load(varname); ok {
 		return v.(int)
 	}
 	e := os.Getenv(varname)
 	if e == "" {
-		return def
+		d = def
+	} else {
+		d64, err := strconv.ParseInt(e, 10, strconv.IntSize)
+		if err != nil {
+			panic(err)
+		}
+		d = int(d64)
 	}
-	d64, err := strconv.ParseInt(e, 10, strconv.IntSize)
-	if err != nil {
-		panic(err)
-	}
-	d := int(d64)
 	cache.Store(varname, d)
 	return d
 }
 
-func Int64(varname string, def int64) int64 {
+func Int64(varname string, def int64) (d int64) {
+	var err error
 	if v, ok := cache.Load(varname); ok {
 		return v.(int64)
 	}
 	e := os.Getenv(varname)
 	if e == "" {
-		return def
-	}
-	d, err := strconv.ParseInt(e, 10, 64)
-	if err != nil {
-		panic(err)
+		d = def
+	} else {
+		d, err = strconv.ParseInt(e, 10, 64)
+		if err != nil {
+			panic(err)
+		}
 	}
 	cache.Store(varname, d)
 	return d
 }
 
-func Bool(varname string, def bool) bool {
+func Bool(varname string, def bool) (d bool) {
+	var err error
 	if v, ok := cache.Load(varname); ok {
 		return v.(bool)
 	}
 	e := os.Getenv(varname)
 	if e == "" {
-		return def
-	}
-	d, err := strconv.ParseBool(e)
-	if err != nil {
-		panic(err)
+		d = def
+	} else {
+		d, err = strconv.ParseBool(e)
+		if err != nil {
+			panic(err)
+		}
 	}
 	cache.Store(varname, d)
 	return d
 }
 
-func String(varname string, def string) string {
+func String(varname string, def string) (d string) {
 	if v, ok := cache.Load(varname); ok {
 		return v.(string)
 	}
 	e := os.Getenv(varname)
 	if e == "" {
-		return def
+		d = def
+	} else {
+		d = e
 	}
-	cache.Store(varname, e)
-	return e
+	cache.Store(varname, d)
+	return d
 }
 
-func Var(varname string, def flag.Value) interface{} {
+func Var(varname string, def flag.Value) (d interface{}) {
 
 	// use def's type to instantiate a new object of that same type
 	// and call flag.Value.Set() on it
@@ -100,19 +116,43 @@ func Var(varname string, def flag.Value) interface{} {
 	defElemType := defType.Elem()
 
 	if v, ok := cache.Load(varname); ok {
-		return v.(string)
+		return v
 	}
+
 	e := os.Getenv(varname)
 	if e == "" {
-		return def
+		d = def
+	} else {
+		newInstance := reflect.New(defElemType)
+		if err := newInstance.Interface().(flag.Value).Set(e); err != nil {
+			panic(err)
+		}
+		d = newInstance.Interface()
 	}
 
-	newInstance := reflect.New(defElemType)
-	if err := newInstance.Interface().(flag.Value).Set(e); err != nil {
-		panic(err)
-	}
-
-	res := newInstance.Interface()
-	cache.Store(varname, res)
-	return res
+	cache.Store(varname, d)
+	return d
+}
+
+type Report struct {
+	Entries []EntryReport
+}
+
+type EntryReport struct {
+	Var         string
+	Value       string
+	ValueGoType string
+}
+
+func GetReport() *Report {
+	var r Report
+	cache.Range(func(key, value interface{}) bool {
+		r.Entries = append(r.Entries, EntryReport{
+			Var:         key.(string),
+			Value:       fmt.Sprintf("%v", value),
+			ValueGoType: fmt.Sprintf("%T", value),
+		})
+		return true
+	})
+	return &r
 }

util/envconst/envconst_test.go

@@ -32,19 +32,27 @@ func (m *ExampleVarType) Set(s string) error {
 
 const EnvVarName = "ZREPL_ENVCONST_UNIT_TEST_VAR"
 
-func TestVar(t *testing.T) {
+func TestVarDefaultValue(t *testing.T) {
+	envconst.Reset()
 	_, set := os.LookupEnv(EnvVarName)
 	require.False(t, set)
 	defer os.Unsetenv(EnvVarName)
 
 	val := envconst.Var(EnvVarName, &Var1)
 	if &Var1 != val {
-		t.Errorf("default value shut be same address")
+		t.Errorf("default value should be same address")
 	}
+}
+
+func TestVarOverriddenValue(t *testing.T) {
+	envconst.Reset()
+	_, set := os.LookupEnv(EnvVarName)
+	require.False(t, set)
+	defer os.Unsetenv(EnvVarName)
 
 	err := os.Setenv(EnvVarName, "var2")
 	require.NoError(t, err)
 
-	val = envconst.Var(EnvVarName, &Var1)
+	val := envconst.Var(EnvVarName, &Var1)
 	require.Equal(t, &Var2, val, "only structural identity is required for non-default vars")
 }

version/version.go

@@ -3,6 +3,8 @@ package version
 import (
 	"fmt"
 	"runtime"
+
+	"github.com/prometheus/client_golang/prometheus"
 )
 
 var (
@@ -29,3 +31,21 @@ func (i *ZreplVersionInformation) String() string {
 	return fmt.Sprintf("zrepl version=%s GOOS=%s GOARCH=%s Compiler=%s",
 		i.Version, i.RuntimeGOOS, i.RuntimeGOARCH, i.RUNTIMECompiler)
 }
+
+var prometheusMetric = prometheus.NewUntypedFunc(
+	prometheus.UntypedOpts{
+		Namespace: "zrepl",
+		Subsystem: "version",
+		Name:      "daemon",
+		Help:      "zrepl daemon version",
+		ConstLabels: map[string]string{
+			"raw":          zreplVersion,
+			"version_info": NewZreplVersionInformation().String(),
+		},
+	},
+	func() float64 { return 1 },
+)
+
+func PrometheusRegister(r prometheus.Registerer) {
+	r.MustRegister(prometheusMetric)
+}

zfs/versions.go

@@ -115,8 +115,6 @@ func (v FilesystemVersion) RelName() string {
 }
 func (v FilesystemVersion) String() string { return v.RelName() }
 
-func (v FilesystemVersion) GetCreation() time.Time { return v.Creation }
-
 // Only takes into account those attributes of FilesystemVersion that
 // are immutable over time in ZFS.
 func FilesystemVersionEqualIdentity(a, b FilesystemVersion) bool {

zfs/zfs.go

@@ -1500,30 +1500,6 @@ func tryParseDestroySnapshotsError(arg string, stderr []byte) *DestroySnapshotsE
 	}
 }
 
-type ErrDestroySnapshotDatasetIsBusy struct {
-	*DestroySnapshotsError
-	Name string
-}
-
-var _ error = (*ErrDestroySnapshotDatasetIsBusy)(nil)
-
-func tryErrDestroySnapshotDatasetIsBusy(arg string, stderr []byte) *ErrDestroySnapshotDatasetIsBusy {
-	dsne := tryParseDestroySnapshotsError(arg, stderr)
-	if dsne == nil {
-		return nil
-	}
-	if len(dsne.Reason) != 1 {
-		return nil
-	}
-	if dsne.Reason[0] == "dataset is busy" {
-		return &ErrDestroySnapshotDatasetIsBusy{
-			DestroySnapshotsError: dsne,
-			Name:                  dsne.Undestroyable[0],
-		}
-	}
-	return nil
-}
-
 func ZFSDestroy(ctx context.Context, arg string) (err error) {
 
 	var dstype, filesystem string
@@ -1557,8 +1533,6 @@ func ZFSDestroy(ctx context.Context, arg string) (err error) {
 			err = &DatasetDoesNotExist{arg}
 		} else if dsNotExistErr := tryDatasetDoesNotExist(filesystem, stdio); dsNotExistErr != nil {
 			err = dsNotExistErr
-		} else if dsBusy := tryErrDestroySnapshotDatasetIsBusy(arg, stdio); dsBusy != nil {
-			err = dsBusy
 		} else if dserr := tryParseDestroySnapshotsError(arg, stdio); dserr != nil {
 			err = dserr
 		}