build: bump minimum Go version to 1.18, as a dependency in ./tools requires it

https://app.circleci.com/pipelines/github/zrepl/zrepl/6085/workflows/bf5b11f2-8dc4-40a2-bb7a-fcf3cf8205d4/jobs/42340

  ...
  build github.com/golangci/golangci-lint/cmd/golangci-lint: cannot load io/fs: cannot find module providing package io/fs
  go install github.com/wadey/gocovmerge
  go: downloading github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad
  go: extracting github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad
  go install golang.org/x/tools/cmd/goimports
  # golang.org/x/mod/module
  ../../go/pkg/mod/golang.org/x/mod@v0.6.0/module/module.go:147:5: undefined: errors.As
  note: module requires Go 1.17
  go install golang.org/x/tools/cmd/stringer
  # golang.org/x/tools/go/internal/gcimporter
  ../../go/pkg/mod/golang.org/x/tools@v0.2.0/go/internal/gcimporter/iimport.go:520:9: undefined: constant.Make
  ../../go/pkg/mod/golang.org/x/tools@v0.2.0/go/internal/gcimporter/iimport.go:616:9: undefined: constant.Make
  note: module requires Go 1.18
  go install google.golang.org/grpc/cmd/protoc-gen-go-grpc
  go: downloading google.golang.org/grpc v1.46.2
  go: extracting google.golang.org/grpc v1.46.2
  go: downloading google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.1.0
  go: extracting google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.1.0
  go install google.golang.org/protobuf/cmd/protoc-gen-go

  Exited with code exit status 123

.circleci/config.yml

@@ -24,7 +24,12 @@ commands:
 
   apt-update-and-install-common-deps:
     steps:
-      - run: sudo apt update && sudo apt install gawk make
+      - run: sudo apt-get update
+      - run: sudo apt-get install -y gawk make
+      # CircleCI doesn't update its cimg/go images.
+      # So, need to update manually to get up-to-date trust chains.
+      # The need for this was required for cimg/go:1.12, but let's future proof this here and now.
+      - run: sudo apt-get install -y git ca-certificates
 
   restore-cache-gomod:
     steps:
@@ -150,7 +155,7 @@ parameters:
 
   release_docker_baseimage_tag:
     type: string
-    default: "1.17"
+    default: "1.19"
 
 workflows:
   version: 2
@@ -160,19 +165,19 @@ workflows:
     jobs:
       - quickcheck-docs
       - quickcheck-go: &quickcheck-go-smoketest
-          name: quickcheck-go-amd64-linux-1.17
-          goversion: &latest-go-release "1.17"
+          name: quickcheck-go-amd64-linux-1.19
+          goversion: &latest-go-release "1.19"
           goos: linux
           goarch: amd64
       - test-go-on-latest-go-release:
           goversion: *latest-go-release
       - quickcheck-go:
           requires:
-            - quickcheck-go-amd64-linux-1.17 #quickcheck-go-smoketest.name
+            - quickcheck-go-amd64-linux-1.19 #quickcheck-go-smoketest.name
           matrix: &quickcheck-go-matrix
             alias: quickcheck-go-matrix
             parameters:
-              goversion: [*latest-go-release, "1.12"]
+              goversion: [*latest-go-release, "1.18"]
               goos: ["linux", "freebsd"]
               goarch: ["amd64", "arm64"]
             exclude:
@@ -180,10 +185,6 @@ workflows:
               - goversion: *latest-go-release
                 goos: linux
                 goarch: amd64
-              # not supported by Go 1.12
-              - goversion: "1.12"
-                goos: freebsd
-                goarch: arm64
 
   release:
     when: << pipeline.parameters.do_release >>
@@ -249,7 +250,7 @@ jobs:
       goarch:
         type: string
     docker:
-      - image: circleci/golang:<<parameters.goversion>>
+      - image: cimg/go:<<parameters.goversion>>
     environment:
       GOOS: <<parameters.goos>>
       GOARCH: <<parameters.goarch>>
@@ -257,12 +258,13 @@ jobs:
     steps:
       - checkout
 
+      - install-godep
+
       - restore-cache-gomod
       - run: go mod download
       - run: cd build && go mod download
       - save-cache-gomod
 
-      - install-godep
       - run: make formatcheck
       - run: make generate-platform-test-list
       - run: make zrepl-bin test-platform-bin
@@ -286,7 +288,7 @@ jobs:
       goversion:
         type: string
     docker:
-      - image: circleci/golang:<<parameters.goversion>>
+      - image: cimg/go:<<parameters.goversion>>
     steps:
       - checkout
       - restore-cache-gomod

Makefile

@@ -28,7 +28,7 @@ GO_BUILDFLAGS := $(GO_MOD_READONLY) $(GO_EXTRA_BUILDFLAGS)
 GO_BUILD := $(GO_ENV_VARS) $(GO) build $(GO_BUILDFLAGS) -ldflags $(GO_LDFLAGS)
 GOLANGCI_LINT := golangci-lint
 GOCOVMERGE := gocovmerge
-RELEASE_DOCKER_BASEIMAGE_TAG ?= 1.17
+RELEASE_DOCKER_BASEIMAGE_TAG ?= 1.19
 RELEASE_DOCKER_BASEIMAGE ?= golang:$(RELEASE_DOCKER_BASEIMAGE_TAG)
 
 ifneq ($(GOARM),)
@@ -134,7 +134,13 @@ endif
 
 deb-docker:
 	docker build -t zrepl_debian_pkg --pull -f packaging/deb/Dockerfile .
+	# Use a small open file limit to make fakeroot work. If we don't
+	# specify it, docker daemon will use its file limit. I don't know
+	# what changed (Docker, its systemd service, its Go version). But I
+	# observed fakeroot iterating close(i) up to i > 1000000, which costs
+	# a good amount of CPU time and makes the build slow.
 	docker run --rm -i -v $(CURDIR):/build/src -u $$(id -u):$$(id -g) \
+		--ulimit nofile=1024:1024 \
 		zrepl_debian_pkg \
 		make deb GOOS=$(GOOS) GOARCH=$(GOARCH) GOARM=$(GOARM)
 

build/go.mod

@@ -4,13 +4,10 @@ go 1.12
 
 require (
 	github.com/alvaroloes/enumer v1.1.1
-	github.com/golangci/golangci-lint v1.35.2
-	github.com/golangci/misspell v0.3.4 // indirect
-	github.com/golangci/revgrep v0.0.0-20180812185044-276a5c0a1039 // indirect
-	github.com/spf13/afero v1.2.2 // indirect
+	github.com/golangci/golangci-lint v1.50.1
 	github.com/spf13/jwalterweatherman v1.1.0 // indirect
 	github.com/wadey/gocovmerge v0.0.0-20160331181800-b5bfa59ec0ad
-	golang.org/x/tools v0.0.0-20210105210202-9ed45478a130
+	golang.org/x/tools v0.2.0
 	google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.1.0 // indirect
-	google.golang.org/protobuf v1.25.0
+	google.golang.org/protobuf v1.28.0
 )

client/zfsabstractions.go

@@ -57,7 +57,7 @@ func (f *zabsFilterFlags) registerZabsFilterFlags(s *pflag.FlagSet, verb string)
 	for v := range endpoint.AbstractionTypesAll {
 		variants = append(variants, string(v))
 	}
-	variants = sort.StringSlice(variants)
+	sort.Strings(variants)
 	variantsJoined := strings.Join(variants, "|")
 	s.Var(&f.Types, "type", fmt.Sprintf("only %s holds of the specified type [default: all] [comma-separated list of %s]", verb, variantsJoined))
 

config/config.go

@@ -223,10 +223,11 @@ type SnapshottingEnum struct {
 }
 
 type SnapshottingPeriodic struct {
-	Type     string            `yaml:"type"`
-	Prefix   string            `yaml:"prefix"`
-	Interval *PositiveDuration `yaml:"interval"`
-	Hooks    HookList          `yaml:"hooks,optional"`
+	Type            string            `yaml:"type"`
+	Prefix          string            `yaml:"prefix"`
+	Interval        *PositiveDuration `yaml:"interval"`
+	Hooks           HookList          `yaml:"hooks,optional"`
+	TimestampFormat string            `yaml:"timestamp_format,optional,default=dense"`
 }
 
 type CronSpec struct {
@@ -255,10 +256,11 @@ func (s *CronSpec) UnmarshalYAML(unmarshal func(v interface{}, not_strict bool)
 }
 
 type SnapshottingCron struct {
-	Type   string   `yaml:"type"`
-	Prefix string   `yaml:"prefix"`
-	Cron   CronSpec `yaml:"cron"`
-	Hooks  HookList `yaml:"hooks,optional"`
+	Type            string   `yaml:"type"`
+	Prefix          string   `yaml:"prefix"`
+	Cron            CronSpec `yaml:"cron"`
+	Hooks           HookList `yaml:"hooks,optional"`
+	TimestampFormat string   `yaml:"timestamp_format,optional,default=dense"`
 }
 
 type SnapshottingManual struct {

config/config_snapshotting_test.go

@@ -35,8 +35,16 @@ jobs:
   snapshotting:
     type: periodic
     prefix: zrepl_
+    timestamp_format: dense
     interval: 10m
 `
+	cron := `
+  snapshotting:
+    type: cron
+    prefix: zrepl_
+    timestamp_format: human
+    cron: "10 * * * *"
+`
 
 	periodicDaily := `
   snapshotting:
@@ -91,6 +99,15 @@ jobs:
 		assert.Equal(t, "periodic", snp.Type)
 		assert.Equal(t, 24*time.Hour, snp.Interval.Duration())
 		assert.Equal(t, "zrepl_", snp.Prefix)
+		assert.Equal(t, "dense", snp.TimestampFormat)
+	})
+
+	t.Run("cron", func(t *testing.T) {
+		c = testValidConfig(t, fillSnapshotting(cron))
+		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingCron)
+		assert.Equal(t, "cron", snp.Type)
+		assert.Equal(t, "zrepl_", snp.Prefix)
+		assert.Equal(t, "human", snp.TimestampFormat)
 	})
 
 	t.Run("hooks", func(t *testing.T) {
@@ -103,3 +120,57 @@ jobs:
 	})
 
 }
+
+func TestSnapshottingTimestampDefaults(t *testing.T) {
+	tmpl := `
+jobs:
+- name: foo
+  type: push
+  connect:
+    type: local
+    listener_name: foo
+    client_identity: bar
+  filesystems: {"<": true}
+  %s
+  pruning:
+    keep_sender:
+    - type: last_n
+      count: 10
+    keep_receiver:
+    - type: last_n
+      count: 10
+`
+
+	periodic := `
+  snapshotting:
+    type: periodic
+    prefix: zrepl_
+    interval: 10m
+`
+	cron := `
+  snapshotting:
+    type: cron
+    prefix: zrepl_
+    cron: "10 * * * *"
+`
+
+	fillSnapshotting := func(s string) string { return fmt.Sprintf(tmpl, s) }
+	var c *Config
+
+	t.Run("periodic", func(t *testing.T) {
+		c = testValidConfig(t, fillSnapshotting(periodic))
+		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingPeriodic)
+		assert.Equal(t, "periodic", snp.Type)
+		assert.Equal(t, 10*time.Minute, snp.Interval.Duration())
+		assert.Equal(t, "zrepl_", snp.Prefix)
+		assert.Equal(t, "dense", snp.TimestampFormat) // default was set correctly
+	})
+
+	t.Run("cron", func(t *testing.T) {
+		c = testValidConfig(t, fillSnapshotting(cron))
+		snp := c.Jobs[0].Ret.(*PushJob).Snapshotting.Ret.(*SnapshottingCron)
+		assert.Equal(t, "cron", snp.Type)
+		assert.Equal(t, "zrepl_", snp.Prefix)
+		assert.Equal(t, "dense", snp.TimestampFormat) // default was set correctly
+	})
+}

config/config_test.go

@@ -44,7 +44,8 @@ func TestSampleConfigsAreParsedWithoutErrors(t *testing.T) {
 }
 
 // template must be a template/text template with a single '{{ . }}' as placeholder for val
-//nolint[:deadcode,unused]
+//
+//nolint:deadcode,unused
 func testValidConfigTemplate(t *testing.T, tmpl string, val string) *Config {
 	tmp, err := template.New("master").Parse(tmpl)
 	if err != nil {

daemon/hooks/hook_docs.go

@@ -5,7 +5,7 @@
 //
 // This package also provides all supported hook type implementations and abstractions around them.
 //
-// Use For Other Kinds Of ExpectStepReports
+// # Use For Other Kinds Of ExpectStepReports
 //
 // This package REQUIRES REFACTORING before it can be used for other activities than snapshots, e.g. pre- and post-replication:
 //
@@ -15,7 +15,7 @@
 // The hook implementations should move out of this package.
 // However, there is a lot of tight coupling which to untangle isn't worth it ATM.
 //
-// How This Package Is Used By Package Snapper
+// # How This Package Is Used By Package Snapper
 //
 // Deserialize a config.List using ListFromConfig().
 // Then it MUST filter the list to only contain hooks for a particular filesystem using
@@ -30,5 +30,4 @@
 // Command hooks make it available in the environment variable ZREPL_DRYRUN.
 //
 // Plan.Report() can be called while Plan.Run() is executing to give an overview of plan execution progress (future use in "zrepl status").
-//
 package hooks

daemon/hooks/hook_type_mysql_lock_tables.go

@@ -17,19 +17,22 @@ import (
 	"github.com/zrepl/zrepl/zfs"
 )
 
+// Hook to implement the following recommmendation from MySQL docs
 // https://dev.mysql.com/doc/mysql-backup-excerpt/5.7/en/backup-methods.html
 //
-// Making Backups Using a File System Snapshot:
+//	Making Backups Using a File System Snapshot:
 //
-//  If you are using a Veritas file system, you can make a backup like this:
+//	If you are using a Veritas file system, you can make a backup like this:
 //
-//    	From a client program, execute FLUSH TABLES WITH READ LOCK.
-//    	From another shell, execute mount vxfs snapshot.
-//    	From the first client, execute UNLOCK TABLES.
-//    	Copy files from the snapshot.
-//    	Unmount the snapshot.
+//	   	From a client program, execute FLUSH TABLES WITH READ LOCK.
+//	   	From another shell, execute mount vxfs snapshot.
+//	   	From the first client, execute UNLOCK TABLES.
+//	   	Copy files from the snapshot.
+//	   	Unmount the snapshot.
 //
-//	Similar snapshot capabilities may be available in other file systems, such as LVM or ZFS.
+//		Similar snapshot capabilities may be available in other file systems, such as LVM or ZFS.
+//
+
 type MySQLLockTables struct {
 	errIsFatal  bool
 	connector   sqldriver.Connector

daemon/job/snapjob.go

@@ -138,7 +138,7 @@ outer:
 // TODO:
 // This is a work-around for the current package daemon/pruner
 // and package pruning.Snapshot limitation: they require the
-//  `Replicated` getter method be present, but obviously,
+// `Replicated` getter method be present, but obviously,
 // a local job like SnapJob can't deliver on that.
 // But the pruner.Pruner gives up on an FS if no replication
 // cursor is present, which is why this pruner returns the

daemon/logging/trace/trace.go

@@ -1,6 +1,6 @@
 // package trace provides activity tracing via ctx through Tasks and Spans
 //
-// Basic Concepts
+// # Basic Concepts
 //
 // Tracing can be used to identify where a piece of code spends its time.
 //
@@ -10,51 +10,50 @@
 // to tech-savvy users (albeit not developers).
 //
 // This package provides the concept of Tasks and Spans to express what activity is happening within an application:
-//
-//  - Neither task nor span is really tangible but instead contained within the context.Context tree
-//  - Tasks represent concurrent activity (i.e. goroutines).
-//  - Spans represent a semantic stack trace within a task.
-//
+// - Neither task nor span is really tangible but instead contained within the context.Context tree
+// - Tasks represent concurrent activity (i.e. goroutines).
+// - Spans represent a semantic stack trace within a task.
 // As a consequence, whenever a context is propagated across goroutine boundary, you need to create a child task:
 //
-//   go func(ctx context.Context) {
-//     ctx, endTask = WithTask(ctx, "what-happens-inside-the-child-task")
-//     defer endTask()
-//     // ...
-//   }(ctx)
+//	go func(ctx context.Context) {
+//	  ctx, endTask = WithTask(ctx, "what-happens-inside-the-child-task")
+//	  defer endTask()
+//	  // ...
+//	}(ctx)
 //
 // Within the task, you can open up a hierarchy of spans.
 // In contrast to tasks, which have can multiple concurrently running child tasks,
 // spans must nest and not cross the goroutine boundary.
 //
-//  ctx, endSpan = WithSpan(ctx, "copy-dir")
-//  defer endSpan()
-//  for _, f := range dir.Files() {
-//    func() {
-//      ctx, endSpan := WithSpan(ctx, fmt.Sprintf("copy-file %q", f))
-//      defer endspan()
-//      b, _ := ioutil.ReadFile(f)
-//      _ = ioutil.WriteFile(f + ".copy", b, 0600)
-//    }()
-//  }
+//	ctx, endSpan = WithSpan(ctx, "copy-dir")
+//	defer endSpan()
+//	for _, f := range dir.Files() {
+//	  func() {
+//	    ctx, endSpan := WithSpan(ctx, fmt.Sprintf("copy-file %q", f))
+//	    defer endspan()
+//	    b, _ := ioutil.ReadFile(f)
+//	    _ = ioutil.WriteFile(f + ".copy", b, 0600)
+//	  }()
+//	}
 //
 // In combination:
-//  ctx, endTask = WithTask(ctx, "copy-dirs")
-//  defer endTask()
-//  for i := range dirs {
-//    go func(dir string) {
-//      ctx, endTask := WithTask(ctx, "copy-dir")
-//      defer endTask()
-//      for _, f := range filesIn(dir) {
-//        func() {
-//          ctx, endSpan := WithSpan(ctx, fmt.Sprintf("copy-file %q", f))
-//          defer endspan()
-//          b, _ := ioutil.ReadFile(f)
-//          _ = ioutil.WriteFile(f + ".copy", b, 0600)
-//        }()
-//      }
-//    }()
-//  }
+//
+//	ctx, endTask = WithTask(ctx, "copy-dirs")
+//	defer endTask()
+//	for i := range dirs {
+//	  go func(dir string) {
+//	    ctx, endTask := WithTask(ctx, "copy-dir")
+//	    defer endTask()
+//	    for _, f := range filesIn(dir) {
+//	      func() {
+//	        ctx, endSpan := WithSpan(ctx, fmt.Sprintf("copy-file %q", f))
+//	        defer endspan()
+//	        b, _ := ioutil.ReadFile(f)
+//	        _ = ioutil.WriteFile(f + ".copy", b, 0600)
+//	      }()
+//	    }
+//	  }()
+//	}
 //
 // Note that a span ends at the time you call endSpan - not before and not after that.
 // If you violate the stack-like nesting of spans by forgetting an endSpan() invocation,
@@ -65,8 +64,7 @@
 //
 // Recovering from endSpan() or endTask() panics will corrupt the trace stack and lead to corrupt tracefile output.
 //
-//
-// Best Practices For Naming Tasks And Spans
+// # Best Practices For Naming Tasks And Spans
 //
 // Tasks should always have string constants as names, and must not contain the `#` character. WHy?
 // First, the visualization by chrome://tracing draws a horizontal bar for each task in the trace.
@@ -74,8 +72,7 @@
 // Note that the `#NUM` suffix will be reused if a task has ended, in order to avoid an
 // infinite number of horizontal bars in the visualization.
 //
-//
-// Chrome-compatible Tracefile Support
+// # Chrome-compatible Tracefile Support
 //
 // The activity trace generated by usage of WithTask and WithSpan can be rendered to a JSON output file
 // that can be loaded into chrome://tracing .

daemon/logging/trace/trace_convenience.go

@@ -11,8 +11,6 @@ import (
 // use like this:
 //
 //	defer WithSpanFromStackUpdateCtx(&existingCtx)()
-//
-//
 func WithSpanFromStackUpdateCtx(ctx *context.Context) DoneFunc {
 	childSpanCtx, end := WithSpan(*ctx, getMyCallerOrPanic())
 	*ctx = childSpanCtx

daemon/snapper/cron.go

@@ -10,6 +10,7 @@ import (
 
 	"github.com/zrepl/zrepl/config"
 	"github.com/zrepl/zrepl/daemon/hooks"
+	"github.com/zrepl/zrepl/util/suspendresumesafetimer"
 	"github.com/zrepl/zrepl/zfs"
 )
 
@@ -20,8 +21,9 @@ func cronFromConfig(fsf zfs.DatasetFilter, in config.SnapshottingCron) (*Cron, e
 		return nil, errors.Wrap(err, "hook config error")
 	}
 	planArgs := planArgs{
-		prefix: in.Prefix,
-		hooks:  hooksList,
+		prefix:          in.Prefix,
+		timestampFormat: in.TimestampFormat,
+		hooks:           hooksList,
 	}
 	return &Cron{config: in, fsf: fsf, planArgs: planArgs}, nil
 }
@@ -42,67 +44,45 @@ type Cron struct {
 
 func (s *Cron) Run(ctx context.Context, snapshotsTaken chan<- struct{}) {
 
-	t := time.NewTimer(0)
-	defer func() {
-		if !t.Stop() {
-			select {
-			case <-t.C:
-			default:
-			}
-		}
-	}()
 	for {
 		now := time.Now()
 		s.mtx.Lock()
 		s.wakeupTime = s.config.Cron.Schedule.Next(now)
 		s.mtx.Unlock()
 
-		// Re-arm the timer.
-		// Need to Stop before Reset, see docs.
-		if !t.Stop() {
-			// Use non-blocking read from timer channel
-			// because, except for the first loop iteration,
-			// the channel is already drained
-			select {
-			case <-t.C:
-			default:
-			}
-		}
-		t.Reset(s.wakeupTime.Sub(now))
-
-		select {
-		case <-ctx.Done():
+		ctxDone := suspendresumesafetimer.SleepUntil(ctx, s.wakeupTime)
+		if ctxDone != nil {
 			return
-		case <-t.C:
-			getLogger(ctx).Debug("cron timer fired")
-			s.mtx.Lock()
-			if s.running {
-				getLogger(ctx).Warn("snapshotting triggered according to cron rules but previous snapshotting is not done; not taking a snapshot this time")
-				s.wakeupWhileRunningCount++
-				s.mtx.Unlock()
-				continue
-			}
-			s.lastError = nil
-			s.lastPlan = nil
-			s.wakeupWhileRunningCount = 0
-			s.running = true
-			s.mtx.Unlock()
-			go func() {
-				err := s.do(ctx)
-				s.mtx.Lock()
-				s.lastError = err
-				s.running = false
-				s.mtx.Unlock()
-
-				select {
-				case snapshotsTaken <- struct{}{}:
-				default:
-					if snapshotsTaken != nil {
-						getLogger(ctx).Warn("callback channel is full, discarding snapshot update event")
-					}
-				}
-			}()
 		}
+
+		getLogger(ctx).Debug("cron timer fired")
+		s.mtx.Lock()
+		if s.running {
+			getLogger(ctx).Warn("snapshotting triggered according to cron rules but previous snapshotting is not done; not taking a snapshot this time")
+			s.wakeupWhileRunningCount++
+			s.mtx.Unlock()
+			continue
+		}
+		s.lastError = nil
+		s.lastPlan = nil
+		s.wakeupWhileRunningCount = 0
+		s.running = true
+		s.mtx.Unlock()
+		go func() {
+			err := s.do(ctx)
+			s.mtx.Lock()
+			s.lastError = err
+			s.running = false
+			s.mtx.Unlock()
+
+			select {
+			case snapshotsTaken <- struct{}{}:
+			default:
+				if snapshotsTaken != nil {
+					getLogger(ctx).Warn("callback channel is full, discarding snapshot update event")
+				}
+			}
+		}()
 	}
 
 }

daemon/snapper/impl.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"sort"
+	"strconv"
 	"strings"
 	"time"
 
@@ -14,8 +15,9 @@ import (
 )
 
 type planArgs struct {
-	prefix string
-	hooks  *hooks.List
+	prefix          string
+	timestampFormat string
+	hooks           *hooks.List
 }
 
 type plan struct {
@@ -58,6 +60,21 @@ type snapProgress struct {
 	runResults hooks.PlanReport
 }
 
+func (plan *plan) formatNow(format string) string {
+	now := time.Now().UTC()
+	switch strings.ToLower(format) {
+	case "dense":
+		format = "20060102_150405_000"
+	case "human":
+		format = "2006-01-02_15:04:05"
+	case "iso-8601":
+		format = "2006-01-02T15:04:05.000Z"
+	case "unix-seconds":
+		return strconv.FormatInt(now.Unix(), 10)
+	}
+	return now.Format(format)
+}
+
 func (plan *plan) execute(ctx context.Context, dryRun bool) (ok bool) {
 
 	hookMatchCount := make(map[hooks.Hook]int, len(*plan.args.hooks))
@@ -68,7 +85,7 @@ func (plan *plan) execute(ctx context.Context, dryRun bool) (ok bool) {
 	anyFsHadErr := false
 	// TODO channel programs -> allow a little jitter?
 	for fs, progress := range plan.snaps {
-		suffix := time.Now().In(time.UTC).Format("20060102_150405_000")
+		suffix := plan.formatNow(plan.args.timestampFormat)
 		snapname := fmt.Sprintf("%s%s", plan.args.prefix, suffix)
 
 		ctx := logging.WithInjectedField(ctx, "fs", fs.ToString())

daemon/snapper/periodic.go

@@ -15,6 +15,7 @@ import (
 	"github.com/zrepl/zrepl/daemon/hooks"
 	"github.com/zrepl/zrepl/daemon/logging"
 	"github.com/zrepl/zrepl/util/envconst"
+	"github.com/zrepl/zrepl/util/suspendresumesafetimer"
 	"github.com/zrepl/zrepl/zfs"
 )
 
@@ -35,8 +36,9 @@ func periodicFromConfig(g *config.Global, fsf zfs.DatasetFilter, in *config.Snap
 		interval: in.Interval.Duration(),
 		fsf:      fsf,
 		planArgs: planArgs{
-			prefix: in.Prefix,
-			hooks:  hookList,
+			prefix:          in.Prefix,
+			timestampFormat: in.TimestampFormat,
+			hooks:           hookList,
 		},
 		// ctx and log is set in Run()
 	}
@@ -171,16 +173,13 @@ func periodicStateSyncUp(a periodicArgs, u updater) state {
 	u(func(s *Periodic) {
 		s.sleepUntil = syncPoint
 	})
-	t := time.NewTimer(time.Until(syncPoint))
-	defer t.Stop()
-	select {
-	case <-t.C:
-		return u(func(s *Periodic) {
-			s.state = Planning
-		}).sf()
-	case <-a.ctx.Done():
+	ctxDone := suspendresumesafetimer.SleepUntil(a.ctx, syncPoint)
+	if ctxDone != nil {
 		return onMainCtxDone(a.ctx, u)
 	}
+	return u(func(s *Periodic) {
+		s.state = Planning
+	}).sf()
 }
 
 func periodicStatePlan(a periodicArgs, u updater) state {
@@ -241,17 +240,13 @@ func periodicStateWait(a periodicArgs, u updater) state {
 		logFunc("enter wait-state after error")
 	})
 
-	t := time.NewTimer(time.Until(sleepUntil))
-	defer t.Stop()
-
-	select {
-	case <-t.C:
-		return u(func(snapper *Periodic) {
-			snapper.state = Planning
-		}).sf()
-	case <-a.ctx.Done():
+	ctxDone := suspendresumesafetimer.SleepUntil(a.ctx, sleepUntil)
+	if ctxDone != nil {
 		return onMainCtxDone(a.ctx, u)
 	}
+	return u(func(snapper *Periodic) {
+		snapper.state = Planning
+	}).sf()
 }
 
 func listFSes(ctx context.Context, mf zfs.DatasetFilter) (fss []*zfs.DatasetPath, err error) {

dist/grafana/grafana-prometheus-zrepl.json

@@ -1235,7 +1235,7 @@
         ]
     },
     "timezone": "",
-    "title": "zrepl 0.3",
+    "title": "zrepl",
     "uid": "etQuvBnGz",
-    "version": 7
+    "version": 8
 }

dist/systemd/zrepl.service

@@ -9,6 +9,9 @@ ExecStart=/usr/local/bin/zrepl --config /etc/zrepl/zrepl.yml daemon
 RuntimeDirectory=zrepl zrepl/stdinserver
 RuntimeDirectoryMode=0700
 
+# Make Go produce coredumps
+Environment=GOTRACEBACK='crash'
+
 ProtectSystem=strict
 #PrivateDevices=yes # TODO ZFS needs access to /dev/zfs, could we limit this?
 ProtectKernelTunables=yes
@@ -27,7 +30,8 @@ ProtectHome=read-only
 # SystemCallFilter
 #   ~@privileged doesn't work with Ubuntu 18.04 ssh
 SystemCallFilter=~ @mount @cpu-emulation @keyring @module @obsolete @raw-io @debug @clock @resources
-
+# Go1.19 added automatic RLIMIT_NOFILE changes, so, we need to allow that
+SystemCallFilter= setrlimit
 
 [Install]
 WantedBy=multi-user.target

docs/changelog.rst

@@ -16,13 +16,42 @@ Changelog
 The changelog summarizes bugfixes that are deemed relevant for users and package maintainers.
 Developers should consult the git commit log or GitHub issue tracker.
 
-0.6 (Unreleased)
-----------------
+Next Release
+------------
 
-* `Feature Wishlist on GitHub <https://github.com/zrepl/zrepl/discussions/547>`_
+The plan for the next release is to revisit how zrepl does snapshot management.
+High-level goals:
+
+- Make it easy to decouple snapshot management (snapshotting, pruning) from replication.
+- Ability to include/exclude snapshots from replication.
+  This is useful for aforementioned decoupling, e.g., separate snapshot prefixes for local & remote replication.
+  Also, it makes explicit that by default, zrepl replicates all snapshots, and that
+  replication has no concept of "zrepl-created snapshots", which is a common misconception.
+- Use of ``zfs snapshot`` comma syntax or channel programs to take snapshots of multiple
+  datasets atomically.
+- Provide an alternative to the ``grid`` pruning policy.
+  Most likely something based on hourly/daily/weekly/monthly "trains" plus a count.
+- Ability to prune at the granularity of the **group** of snapshots created at a given
+  time, as opposed to the individual snapshots within a dataset.
+  Maybe this will be addressed by the alternative to the ``grid`` pruning policy,
+  as it will likely be more predictable.
+
+Those changes will likely come with some breakage in the config.
+However, I want to avoid breaking **use cases** that are satisfied by the current design.
+There will be beta/RC releases to give users a chance to evaluate.
+
+0.6
+---
 
 * |feature| :ref:`Schedule-based snapshotting<job-snapshotting--cron>` using ``cron`` syntax instead of an interval.
-* |feature| Add ``ZREPL_DESTROY_MAX_BATCH_SIZE`` env var (default 0=unlimited).
+* |feature| Configurable initial replication policy.
+  When a filesystem is first replicated to a receiver, this control whether just the newest
+  snapshot will be replicated vs. all existing snapshots. Learn more :ref:`in the docs <conflict_resolution-initial_replication>`.
+* |feature| Configurable timestamp format for snapshot names via :ref:`timestamp_format<job-snapshotting-timestamp_format>`
+  (Thanks, `@ydylla <https://github.com/ydylla>`_).
+* |feature| Add ``ZREPL_DESTROY_MAX_BATCH_SIZE`` env var (default 0=unlimited)
+  (Thanks, `@3nprob <https://github.com/3nprob>`_).
+* |feature| Add ``zrepl configcheck --skip-cert-check`` flag (Thanks, `@cole-h <https://github.com/cole-h>`_).
 * |bugfix| Fix resuming from interrupted replications that use ``send.raw`` on unencrypted datasets.
 
   * The send options introduced in zrepl 0.4 allow users to specify additional zfs send flags for zrepl to use.
@@ -34,7 +63,7 @@ Developers should consult the git commit log or GitHub issue tracker.
   * However, this means that the ``zrepl status`` UI no longer indicates whether a replication step uses encrypted sends or not.
     The setting is still effective though.
 
-* |break| |feature| convert Prometheus metric ``zrepl_version_daemon`` to ``zrepl_start_time`` metric
+* |break| convert Prometheus metric ``zrepl_version_daemon`` to ``zrepl_start_time`` metric
 
   * The metric still reports the zrepl version in a label.
     But the metric *value* is now the Unix timestamp at the time the daemon was started.
@@ -43,6 +72,13 @@ Developers should consult the git commit log or GitHub issue tracker.
 * |bugfix| transient zrepl status error: ``Post "http://unix/status": EOF``
 * |bugfix| don't treat receive-side bookmarks as a replication conflict.
   This facilitates chaining of replication jobs. See :issue:`490`.
+* |bugfix| workaround for Go/gRPC problem on Illumos where zrepl would
+  crash when using the ``local`` transport type (:issue:`598`).
+* |bugfix| fix active child tasks panic that cold occur during replication plannig (:issue:`193abbe`)
+* |bugfix| ``zrepl status`` off-by-one error in display of completed step count (:commit:`ce6701f`)
+* |bugfix| Allow using day & week units for ``snapshotting.interval`` (:commit:`ffb1d89`)
+* |docs| ``docs/overview`` improvements (Thanks, `@jtagcat <https://github.com/jtagcat>`_).
+* |maint| Update to Go 1.19.
 
 0.5
 ---

docs/configuration/conflict_resolution.rst

@@ -15,7 +15,7 @@ Conflict Resolution Options
 
      ...
 
-.. _conflict_resolution-initial_replication-option-send_all_snapshots:
+.. _conflict_resolution-initial_replication:
 
 
 ``initial_replication`` option

docs/configuration/snapshotting.rst

@@ -62,6 +62,9 @@ The ``periodic`` and ``cron`` snapshotting types share some common options and b
        type: periodic
        prefix: zrepl_
        interval: 10m
+       # Timestamp format that is used as snapshot suffix.
+       # Can be any of "dense" (default), "human", "iso-8601", "unix-seconds" or a custom Go time format (see https://go.dev/src/time/format.go)
+       timestamp_format: dense
        hooks: ...
     pruning: ...
 
@@ -91,6 +94,9 @@ The snapshotter uses the ``prefix`` to identify which snapshots it created.
        # (second, optional) minute hour day-of-month month day-of-week
        # This example takes snapshots daily at 3:00.
        cron: "0 3 * * *"
+       # Timestamp format that is used as snapshot suffix.
+       # Can be any of "dense" (default), "human", "iso-8601", "unix-seconds" or a custom Go time format (see https://go.dev/src/time/format.go)
+       timestamp_format: dense
      pruning: ...
 
 In ``cron`` mode, the snapshotter takes snaphots at fixed points in time.
@@ -98,6 +104,21 @@ See https://en.wikipedia.org/wiki/Cron for details on the syntax.
 zrepl uses the ``the github.com/robfig/cron/v3`` Go package for parsing.
 An optional field for "seconds" is supported to take snapshots at sub-minute frequencies.
 
+.. _job-snapshotting-timestamp_format:
+
+Timestamp Format
+~~~~~~~~~~~~~~~~
+
+The ``cron`` and ``periodic`` snapshotter support configuring a custom timestamp format that is used as suffix for the snapshot name.
+It can be used by setting ``timestamp_format`` to any of the following values:
+
+* ``dense`` (default) looks like ``20060102_150405_000``
+* ``human`` looks like ``2006-01-02_15:04:05``
+* ``iso-8601`` looks like ``2006-01-02T15:04:05.000Z``
+* ``unix-seconds`` looks like ``1136214245``
+* Any custom Go time format accepted by `time.Time#Format <https://go.dev/src/time/format.go>`_.
+
+
 ``manual`` Snapshotting
 -----------------------
 

endpoint/endpoint.go

@@ -439,7 +439,7 @@ type FSMap interface { // FIXME unused
 }
 
 // NOTE: when adding members to this struct, remember
-//       to add them to `ReceiverConfig.copyIn()`
+// to add them to `ReceiverConfig.copyIn()`
 type ReceiverConfig struct {
 	JobID JobID
 

endpoint/endpoint_zfs_abstraction.go

@@ -168,7 +168,7 @@ func (s AbstractionTypeSet) String() string {
 	for i := range s {
 		sts = append(sts, string(i))
 	}
-	sts = sort.StringSlice(sts)
+	sort.Strings(sts)
 	return strings.Join(sts, ",")
 }
 

endpoint/endpoint_zfs_abstraction_replication_cursor.go

@@ -23,7 +23,7 @@ func replicationCursorBookmarkNameImpl(fs string, guid uint64, jobid string) (st
 
 var ErrV1ReplicationCursor = fmt.Errorf("bookmark name is a v1-replication cursor")
 
-//err != nil always means that the bookmark is not a valid replication bookmark
+// err != nil always means that the bookmark is not a valid replication bookmark
 //
 // Returns ErrV1ReplicationCursor as error if the bookmark is a v1 replication cursor
 func ParseReplicationCursorBookmarkName(fullname string) (uint64, JobID, error) {

replication/driver/replication_driver.go

@@ -797,7 +797,7 @@ func (a *attempt) errorReport() *errorReport {
 			r.byClass[class] = errs
 		}
 		for _, err := range r.flattened {
-			if neterr, ok := err.Err.(net.Error); ok && neterr.Temporary() {
+			if neterr, ok := err.Err.(net.Error); ok && neterr.Timeout() {
 				putClass(err, errorClassTemporaryConnectivityRelated)
 				continue
 			}

replication/driver/replication_driver_debug.go

@@ -13,7 +13,7 @@ func init() {
 	}
 }
 
-//nolint[:deadcode,unused]
+//nolint:deadcode,unused
 func debug(format string, args ...interface{}) {
 	if debugEnabled {
 		fmt.Fprintf(os.Stderr, "repl: driver: %s\n", fmt.Sprintf(format, args...))
@@ -22,7 +22,7 @@ func debug(format string, args ...interface{}) {
 
 type debugFunc func(format string, args ...interface{})
 
-//nolint[:deadcode,unused]
+//nolint:deadcode,unused
 func debugPrefix(prefixFormat string, prefixFormatArgs ...interface{}) debugFunc {
 	prefix := fmt.Sprintf(prefixFormat, prefixFormatArgs...)
 	return func(format string, args ...interface{}) {

rpc/dataconn/dataconn_debug.go

@@ -14,7 +14,7 @@ func init() {
 	}
 }
 
-//nolint[:deadcode,unused]
+//nolint:deadcode,unused
 func debug(format string, args ...interface{}) {
 	if debugEnabled {
 		fmt.Fprintf(os.Stderr, "rpc/dataconn: %s\n", fmt.Sprintf(format, args...))

rpc/dataconn/heartbeatconn/heartbeatconn.go

@@ -24,6 +24,9 @@ func (e HeartbeatTimeout) Error() string {
 	return "heartbeat timeout"
 }
 
+// This function is deprecated in net.Error and since this
+// function is not involved in .Accept() code path, nothing
+// really needs this method to be here.
 func (e HeartbeatTimeout) Temporary() bool { return true }
 
 func (e HeartbeatTimeout) Timeout() bool { return true }

rpc/dataconn/heartbeatconn/heartbeatconn_debug.go

@@ -13,7 +13,7 @@ func init() {
 	}
 }
 
-//nolint[:deadcode,unused]
+//nolint:deadcode,unused
 func debug(format string, args ...interface{}) {
 	if debugEnabled {
 		fmt.Fprintf(os.Stderr, "rpc/dataconn/heartbeatconn: %s\n", fmt.Sprintf(format, args...))

rpc/dataconn/heartbeatconn/integration_test_variablereceiverate/heartbeatconn_integration_variablereceiverate.go

@@ -6,12 +6,12 @@
 // In commit 082335df5d85e1b0b9faa35ff182c71886142d3e and earlier, heartbeatconn would fail
 // this benchmark with a writev I/O timeout (here the ss(8) output at the time of failure)
 //
-//  ESTAB        33369    0                                        127.0.0.1:12345                                                127.0.0.1:57282                    users:(("heartbeatconn_i",pid=25953,fd=5))
-//	 cubic wscale:7,7 rto:203 rtt:2.992/5.849 ato:162 mss:32768 pmtu:65535 rcvmss:32741 advmss:65483 cwnd:10 bytes_sent:48 bytes_acked:48 bytes_received:195401 segs_out:44 segs_in:57 data_segs_out:6 data_segs_in:34 send 876.1Mbps lastsnd:125 lastrcv:9390 lastack:125 pacing_rate 1752.0Mbps delivery_rate 6393.8Mbps delivered:7 app_limited busy:42ms rcv_rtt:1 rcv_space:65483 rcv_ssthresh:65483 minrtt:0.029
-//	 --
-//	 ESTAB        0        3956805                                  127.0.0.1:57282                                                127.0.0.1:12345                    users:(("heartbeatconn_i",pid=26100,fd=3))
-//		  cubic wscale:7,7 rto:211 backoff:5 rtt:10.38/16.937 ato:40 mss:32768 pmtu:65535 rcvmss:536 advmss:65483 cwnd:10 bytes_sent:195401 bytes_acked:195402 bytes_received:48 segs_out:57 segs_in:45 data_segs_out:34 data_segs_in:6 send 252.5Mbps lastsnd:9390 lastrcv:125 lastack:125 pacing_rate 505.1Mbps delivery_rate 1971.0Mbps delivered:35 busy:30127ms rwnd_limited:30086ms(99.9%) rcv_space:65495 rcv_ssthresh:65495 notsent:3956805 minrtt:0.007
-//	 panic: writev tcp 127.0.0.1:57282->127.0.0.1:12345: i/o timeout
+//	 ESTAB        33369    0                                        127.0.0.1:12345                                                127.0.0.1:57282                    users:(("heartbeatconn_i",pid=25953,fd=5))
+//		 cubic wscale:7,7 rto:203 rtt:2.992/5.849 ato:162 mss:32768 pmtu:65535 rcvmss:32741 advmss:65483 cwnd:10 bytes_sent:48 bytes_acked:48 bytes_received:195401 segs_out:44 segs_in:57 data_segs_out:6 data_segs_in:34 send 876.1Mbps lastsnd:125 lastrcv:9390 lastack:125 pacing_rate 1752.0Mbps delivery_rate 6393.8Mbps delivered:7 app_limited busy:42ms rcv_rtt:1 rcv_space:65483 rcv_ssthresh:65483 minrtt:0.029
+//		 --
+//		 ESTAB        0        3956805                                  127.0.0.1:57282                                                127.0.0.1:12345                    users:(("heartbeatconn_i",pid=26100,fd=3))
+//			  cubic wscale:7,7 rto:211 backoff:5 rtt:10.38/16.937 ato:40 mss:32768 pmtu:65535 rcvmss:536 advmss:65483 cwnd:10 bytes_sent:195401 bytes_acked:195402 bytes_received:48 segs_out:57 segs_in:45 data_segs_out:34 data_segs_in:6 send 252.5Mbps lastsnd:9390 lastrcv:125 lastack:125 pacing_rate 505.1Mbps delivery_rate 1971.0Mbps delivered:35 busy:30127ms rwnd_limited:30086ms(99.9%) rcv_space:65495 rcv_ssthresh:65495 notsent:3956805 minrtt:0.007
+//		 panic: writev tcp 127.0.0.1:57282->127.0.0.1:12345: i/o timeout
 //
 // The assumed reason for those writev timeouts is the following:
 // - Sporadic server stalls (sever data handling, usually I/O) cause TCP exponential backoff on the client for client->server
@@ -22,27 +22,23 @@
 // The fix contained in the commit this message was committed with resets the deadline whenever
 // a heartbeat is received from the server.
 //
-//
 // How to run this integration test:
 //
+//	Terminal 1:
+//	   $ ZREPL_RPC_DATACONN_HEARTBEATCONN_DEBUG=1 go run heartbeatconn_integration_variablereceiverate.go  -mode server -addr 127.0.0.1:12345
+//	   rpc/dataconn/heartbeatconn: send heartbeat
+//	   rpc/dataconn/heartbeatconn: send heartbeat
+//	   ...
 //
-//  Terminal 1:
-//     $ ZREPL_RPC_DATACONN_HEARTBEATCONN_DEBUG=1 go run heartbeatconn_integration_variablereceiverate.go  -mode server -addr 127.0.0.1:12345
-//     rpc/dataconn/heartbeatconn: send heartbeat
-//     rpc/dataconn/heartbeatconn: send heartbeat
-//     ...
-//
-//  Terminal 2:
-//     $ ZREPL_RPC_DATACONN_HEARTBEATCONN_DEBUG=1 go run heartbeatconn_integration_variablereceiverate.go  -mode  client -addr 127.0.0.1:12345
-//     rpc/dataconn/heartbeatconn: received heartbeat, resetting write timeout
-//     rpc/dataconn/heartbeatconn: renew frameconn write timeout returned errT=<nil> err=%!s(<nil>)
-//     rpc/dataconn/heartbeatconn: send heartbeat
-//     rpc/dataconn/heartbeatconn: received heartbeat, resetting write timeout
-//     rpc/dataconn/heartbeatconn: renew frameconn write timeout returned errT=<nil> err=%!s(<nil>)
-//     rpc/dataconn/heartbeatconn: received heartbeat, resetting write timeout
-//     ...
-//
-//  You should observe
+//	Terminal 2:
+//	   $ ZREPL_RPC_DATACONN_HEARTBEATCONN_DEBUG=1 go run heartbeatconn_integration_variablereceiverate.go  -mode  client -addr 127.0.0.1:12345
+//	   rpc/dataconn/heartbeatconn: received heartbeat, resetting write timeout
+//	   rpc/dataconn/heartbeatconn: renew frameconn write timeout returned errT=<nil> err=%!s(<nil>)
+//	   rpc/dataconn/heartbeatconn: send heartbeat
+//	   rpc/dataconn/heartbeatconn: received heartbeat, resetting write timeout
+//	   rpc/dataconn/heartbeatconn: renew frameconn write timeout returned errT=<nil> err=%!s(<nil>)
+//	   rpc/dataconn/heartbeatconn: received heartbeat, resetting write timeout
+//	   ...
 package main
 
 import (

rpc/dataconn/microbenchmark/microbenchmark.go

@@ -2,15 +2,13 @@
 //
 // With stdin / stdout on client and server, simulating zfs send|recv piping
 //
-//   ./microbenchmark -appmode server  | pv -r > /dev/null
-//   ./microbenchmark -appmode client -direction recv < /dev/zero
-//
+//	./microbenchmark -appmode server  | pv -r > /dev/null
+//	./microbenchmark -appmode client -direction recv < /dev/zero
 //
 // Without the overhead of pipes (just protocol performance, mostly useful with perf bc no bw measurement)
 //
-//   ./microbenchmark -appmode client -direction recv -devnoopWriter -devnoopReader
-//   ./microbenchmark -appmode server -devnoopReader -devnoopWriter
-//
+//	./microbenchmark -appmode client -direction recv -devnoopWriter -devnoopReader
+//	./microbenchmark -appmode server -devnoopReader -devnoopWriter
 package main
 
 import (

rpc/dataconn/stream/stream.go

@@ -29,7 +29,7 @@ func WithLogger(ctx context.Context, log Logger) context.Context {
 	return context.WithValue(ctx, contextKeyLogger, log)
 }
 
-//nolint[:deadcode,unused]
+//nolint:deadcode,unused
 func getLog(ctx context.Context) Logger {
 	log, ok := ctx.Value(contextKeyLogger).(Logger)
 	if !ok {
@@ -181,23 +181,19 @@ func (e *ReadStreamError) Error() string {
 
 var _ net.Error = &ReadStreamError{}
 
-func (e ReadStreamError) netErr() net.Error {
-	if netErr, ok := e.Err.(net.Error); ok {
-		return netErr
-	}
-	return nil
-}
-
 func (e ReadStreamError) Timeout() bool {
-	if netErr := e.netErr(); netErr != nil {
+	if netErr, ok := e.Err.(net.Error); ok {
 		return netErr.Timeout()
 	}
 	return false
 }
 
+// This function is deprecated in net.Error and since this
+// function is not involved in .Accept() code path, nothing
+// really needs this method to be here.
 func (e ReadStreamError) Temporary() bool {
-	if netErr := e.netErr(); netErr != nil {
-		return netErr.Temporary()
+	if te, ok := e.Err.(interface{ Temporary() bool }); ok {
+		return te.Temporary()
 	}
 	return false
 }

rpc/dataconn/stream/stream_conn.go

@@ -232,7 +232,12 @@ var _ net.Error = (*closeStateErrConnectionClosed)(nil)
 func (e *closeStateErrConnectionClosed) Error() string {
 	return "connection closed"
 }
-func (e *closeStateErrConnectionClosed) Timeout() bool   { return false }
+
+func (e *closeStateErrConnectionClosed) Timeout() bool { return false }
+
+// This function is deprecated in net.Error and since this
+// function is not involved in .Accept() code path, nothing
+// really needs this method to be here.
 func (e *closeStateErrConnectionClosed) Temporary() bool { return false }
 
 func (s *closeState) CloseEntry() error {

rpc/dataconn/stream/stream_debug.go

@@ -13,7 +13,7 @@ func init() {
 	}
 }
 
-//nolint[:deadcode,unused]
+//nolint:deadcode,unused
 func debug(format string, args ...interface{}) {
 	if debugEnabled {
 		fmt.Fprintf(os.Stderr, "rpc/dataconn/stream: %s\n", fmt.Sprintf(format, args...))

rpc/netadaptor/authlistener_netlistener_adaptor.go

@@ -1,25 +1,5 @@
 // Package netadaptor implements an adaptor from
 // transport.AuthenticatedListener to net.Listener.
-//
-// In contrast to transport.AuthenticatedListener,
-// net.Listener is commonly expected (e.g. by net/http.Server.Serve),
-// to return errors that fulfill the Temporary interface:
-//   interface Temporary { Temporary() bool }
-// Common behavior of packages consuming net.Listener is to return
-// from the serve-loop if an error returned by Accept is not Temporary,
-// i.e., does not implement the interface or is !net.Error.Temporary().
-//
-// The zrepl transport infrastructure was written with the
-// idea that Accept() may return any kind of error, and the consumer
-// would just log the error and continue calling Accept().
-// We have to adapt these listeners' behavior to the expectations
-// of net/http.Server.
-//
-// Hence, Listener does not return an error at all but blocks the
-// caller of Accept() until we get a (successfully authenticated)
-// connection without errors from the transport.
-// Accept errors returned from the transport are logged as errors
-// to the logger passed on initialization.
 package netadaptor
 
 import (

rpc/rpc_client.go

@@ -188,8 +188,8 @@ func (c *Client) WaitForConnectivity(ctx context.Context) error {
 			data, dataErr := c.dataClient.ReqPing(ctx, &req)
 			// dataClient uses transport.Connecter, which doesn't expose WaitForReady(true)
 			// => we need to mask dial timeouts
-			if err, ok := dataErr.(interface{ Temporary() bool }); ok && err.Temporary() {
-				// Rate-limit pings here in case Temporary() is a mis-classification
+			if err, ok := dataErr.(interface{ Timeout() bool }); ok && err.Timeout() {
+				// Rate-limit pings here in case Timeout() == true is a mis-classification
 				// or returns immediately (this is a tight loop in that case)
 				// TODO keep this in lockstep with controlClient
 				// 		=> don't use FailFast for control, but check that both control and data worked

rpc/rpc_debug.go

@@ -14,7 +14,7 @@ func init() {
 	}
 }
 
-//nolint[:deadcode,unused]
+//nolint:deadcode,unused
 func debug(format string, args ...interface{}) {
 	if debugEnabled {
 		fmt.Fprintf(os.Stderr, "rpc: %s\n", fmt.Sprintf(format, args...))

rpc/rpc_doc.go

@@ -3,7 +3,7 @@
 // The zrepl documentation refers to the client as the
 // `active side` and to the server as the `passive side`.
 //
-// Design Considerations
+// # Design Considerations
 //
 // zrepl has non-standard requirements to remote procedure calls (RPC):
 // whereas the coordination of replication (the planning phase) mostly
@@ -35,7 +35,7 @@
 //
 // Hence, this package attempts to combine the best of both worlds:
 //
-// GRPC for Coordination and Dataconn for Bulk Data Transfer
+// # GRPC for Coordination and Dataconn for Bulk Data Transfer
 //
 // This package's Client uses its transport.Connecter to maintain
 // separate control and data connections to the Server.
@@ -47,68 +47,66 @@
 // The following ASCII diagram gives an overview of how the individual
 // building blocks are glued together:
 //
-//                    +------------+
-//                    | rpc.Client |
-//                    +------------+
-//                      |         |
-//             +--------+         +------------+
-//             |                               |
-//   +---------v-----------+          +--------v------+
-//   |pdu.ReplicationClient|          |dataconn.Client|
-//   +---------------------+          +--------v------+
-//             | label:            label:      |
-//             | zrepl_control      zrepl_data |
-//             +--------+         +------------+
-//                      |         |
-//                   +--v---------v---+
-//                   |  transportmux  |
-//                   +-------+--------+
-//                           | uses
-//                   +-------v--------+
-//                   |versionhandshake|
-//                   +-------+--------+
-//                           | uses
-//                    +------v------+
-//                    |  transport  |
-//                    +------+------+
-//                           |
-//                        NETWORK
-//                           |
-//                    +------+------+
-//                    |  transport  |
-//                    +------^------+
-//                           | uses
-//                   +-------+--------+
-//                   |versionhandshake|
-//                   +-------^--------+
-//                           | uses
-//                   +-------+--------+
-//                   |  transportmux  |
-//                   +--^--------^----+
-//                      |        |
-//             +--------+        --------------+       ---
-//             |                               |        |
-//             | label:            label:      |        |
-//             | zrepl_control      zrepl_data |        |
-//       +-----+----+              +-----------+---+    |
-//       |netadaptor|              |dataconn.Server|    | rpc.Server
-//       |     +    |              +------+--------+    |
-//       |grpcclient|                     |             |
-//       |identity  |                     |             |
-//       +-----+----+                     |             |
-//             |                          |             |
-//   +---------v-----------+              |             |
-//   |pdu.ReplicationServer|              |             |
-//   +---------+-----------+              |             |
-//             |                          |            ---
-//             +----------+  +------------+
-//                        |  |
-//                    +---v--v-----+
-//                    |  Handler   |
-//                    +------------+
-//           (usually endpoint.{Sender,Receiver})
-//
-//
+//	                 +------------+
+//	                 | rpc.Client |
+//	                 +------------+
+//	                   |         |
+//	          +--------+         +------------+
+//	          |                               |
+//	+---------v-----------+          +--------v------+
+//	|pdu.ReplicationClient|          |dataconn.Client|
+//	+---------------------+          +--------v------+
+//	          | label:            label:      |
+//	          | zrepl_control      zrepl_data |
+//	          +--------+         +------------+
+//	                   |         |
+//	                +--v---------v---+
+//	                |  transportmux  |
+//	                +-------+--------+
+//	                        | uses
+//	                +-------v--------+
+//	                |versionhandshake|
+//	                +-------+--------+
+//	                        | uses
+//	                 +------v------+
+//	                 |  transport  |
+//	                 +------+------+
+//	                        |
+//	                     NETWORK
+//	                        |
+//	                 +------+------+
+//	                 |  transport  |
+//	                 +------^------+
+//	                        | uses
+//	                +-------+--------+
+//	                |versionhandshake|
+//	                +-------^--------+
+//	                        | uses
+//	                +-------+--------+
+//	                |  transportmux  |
+//	                +--^--------^----+
+//	                   |        |
+//	          +--------+        --------------+       ---
+//	          |                               |        |
+//	          | label:            label:      |        |
+//	          | zrepl_control      zrepl_data |        |
+//	    +-----+----+              +-----------+---+    |
+//	    |netadaptor|              |dataconn.Server|    | rpc.Server
+//	    |     +    |              +------+--------+    |
+//	    |grpcclient|                     |             |
+//	    |identity  |                     |             |
+//	    +-----+----+                     |             |
+//	          |                          |             |
+//	+---------v-----------+              |             |
+//	|pdu.ReplicationServer|              |             |
+//	+---------+-----------+              |             |
+//	          |                          |            ---
+//	          +----------+  +------------+
+//	                     |  |
+//	                 +---v--v-----+
+//	                 |  Handler   |
+//	                 +------------+
+//	        (usually endpoint.{Sender,Receiver})
 package rpc
 
 // edit trick for the ASCII art above:

rpc/rpc_logging.go

@@ -9,7 +9,7 @@ import (
 
 type Logger = logger.Logger
 
-/// All fields must be non-nil
+// All fields must be non-nil
 type Loggers struct {
 	General Logger
 	Control Logger

rpc/versionhandshake/versionhandshake.go

@@ -33,8 +33,47 @@ var _ net.Error = &HandshakeError{}
 
 func (e HandshakeError) Error() string { return e.msg }
 
-// Like with net.OpErr (Go issue 6163), a client failing to handshake
-// should be a temporary Accept error toward the Listener .
+// When a net.Listener.Accept() returns an error, the server must
+// decide whether to retry calling Accept() or not.
+// On some platforms (e.g., Linux), Accept() can return errors
+// related to the specific protocol connection that was supposed
+// to be returned as asocket FD. Obviously, we want to ignore,
+// maybe log, those errors and retry Accept() immediately to
+// serve other connections.
+// But there are also conditions where we get Accept() errors because
+// the process has run out of file descriptors. In that case, retrying
+// won't help. We need to close some file descriptor to make progress.
+// Note that there could be lots of open file descriptors because we
+// have accepted, and not yet closed, lots of connections in the past.
+// And then, of course there can be errors where we just want
+// to return, e.g., if there's a programming error and we're getting
+// an EBADFD or whatever.
+//
+// So, the serve loops in net/http.Server.Serve() or gRPC's server.Serve()
+// must inspect the error and decide what to do.
+// The vehicle for this is the
+//
+//	interface { Temporary() bool }
+//
+// Behavior in both of the aforementioned Serve() loops:
+//
+//   - if the error doesn't implement the interface, stop serving and return
+//   - `Temporary() == true`: retry with back-off
+//   - `Temporary() == false`: stop serving and return
+//
+// So, to make this package's HandshakeListener work with these
+// Serve() loops, we return Temporary() == true if the handshake fails.
+// In the aforementioned categories, that's the case of a per-connection
+// protocol error.
+//
+// Note: the net.Error interface has deprecated the Temporary() method
+// in go.dev/issue/45729, but there is no replacement for users of .Accept().
+// Existing users of .Accept() continue to check for the interface.
+// So, we need to continue supporting Temporary() until there's a different
+// mechanism for serve loops to decide whether to retry or not.
+// The following mailing list post proposes to eliminate the retries
+// completely, but it seems like the effort has stalled.
+// https://groups.google.com/g/golang-nuts/c/-JcZzOkyqYI/m/xwaZzjCgAwAJ
 func (e HandshakeError) Temporary() bool {
 	if e.isAcceptError {
 		return true

util/chainlock/chainlock.go

@@ -3,13 +3,12 @@
 //
 // Intended Usage
 //
-//   defer s.lock().unlock()
-//   // drop lock while waiting for wait group
-//   func() {
-//	     defer a.l.Unlock().Lock()
-//	     fssesDone.Wait()
-//	 }()
-//
+//	  defer s.lock().unlock()
+//	  // drop lock while waiting for wait group
+//	  func() {
+//		     defer a.l.Unlock().Lock()
+//		     fssesDone.Wait()
+//		 }()
 package chainlock
 
 import "sync"

util/nodefault/nodefault.go

@@ -7,26 +7,25 @@
 //
 // Example:
 //
-//  type Config struct {
-//      // This field must be set to a non-nil value,
-//      // forcing the caller to make their mind up
-//      // about this field.
-//      CriticalSetting   *nodefault.Bool
-//  }
+//	type Config struct {
+//	    // This field must be set to a non-nil value,
+//	    // forcing the caller to make their mind up
+//	    // about this field.
+//	    CriticalSetting   *nodefault.Bool
+//	}
 //
 // An function that takes such a Config should _not_ check for nil-ness:
 // and instead unconditionally dereference:
 //
-//  func f(c Config) {
-//      if (c.CriticalSetting) { }
-//  }
+//	func f(c Config) {
+//	    if (c.CriticalSetting) { }
+//	}
 //
 // If the caller of f forgot to specify the .CriticalSetting
 // field, the Go runtime will issue a nil-pointer deref panic
 // and it'll be clear that the caller did not read the docs of Config.
 //
-//  f(Config{}) // crashes
-//
-//  f Config{ CriticalSetting: &nodefault.Bool{B: false}} // doesn't crash
+//	f(Config{}) // crashes
 //
+//	f Config{ CriticalSetting: &nodefault.Bool{B: false}} // doesn't crash
 package nodefault

util/suspendresumesafetimer/suspendresumesafetimer.go

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

zfs/namecheck.go

@@ -53,7 +53,6 @@ var componentValidChar = regexp.MustCompile(`^[0-9a-zA-Z-_\.: ]+$`)
 // characters:
 //
 //	[-_.: ]
-//
 func ComponentNamecheck(datasetPathComponent string) error {
 	if len(datasetPathComponent) == 0 {
 		return fmt.Errorf("path component must not be empty")
@@ -91,8 +90,8 @@ func (e *PathValidationError) Error() string {
 
 // combines
 //
-//    lib/libzfs/libzfs_dataset.c: zfs_validate_name
-//    module/zcommon/zfs_namecheck.c: entity_namecheck
+//	lib/libzfs/libzfs_dataset.c: zfs_validate_name
+//	module/zcommon/zfs_namecheck.c: entity_namecheck
 //
 // The '%' character is not allowed because it's reserved for zfs-internal use
 func EntityNamecheck(path string, t EntityType) (err *PathValidationError) {

zfs/zfs.go

@@ -343,7 +343,6 @@ const (
 
 type SendStream struct {
 	cmd          *zfscmd.Cmd
-	kill         context.CancelFunc
 	stdoutReader io.ReadCloser // not *os.File for mocking during platformtest
 	stderrBuf    *circlog.CircularLog
 
@@ -416,8 +415,29 @@ func (s *SendStream) killAndWait() error {
 	debug("sendStream: killAndWait enter")
 	defer debug("sendStream: killAndWait leave")
 
+	// ensure this function is only called once
+	if s.state != sendStreamOpen {
+		panic(s.state)
+	}
+
 	// send SIGKILL
-	s.kill()
+	// In an earlier version, we used the starting context.Context's cancel function
+	// for this, but in Go > 1.19, doing so will cause .Wait() to return the
+	// context cancel error instead of the *exec.ExitError.
+	err := s.cmd.Process().Kill()
+	if err != nil {
+		if err == os.ErrProcessDone {
+			// This can happen if
+			// (1) the process has already been .Wait()ed, or
+			// (2) some other goroutine cancels the context, likely further up
+			//     the context tree.
+			// Case (1) can't happen to us because we only call
+			// this function in sendStreamOpen state.
+			// In Case (2), it's still our job to .Wait(), so, fallthrough.
+		} else {
+			return err
+		}
+	}
 
 	// Close our read-end of the pipe.
 	//
@@ -963,10 +983,10 @@ func ZFSSend(ctx context.Context, sendArgs ZFSSendArgsValidated) (*SendStream, e
 
 	stream := &SendStream{
 		cmd:          cmd,
-		kill:         cancel,
 		stdoutReader: stdoutReader,
 		stderrBuf:    stderrBuf,
 	}
+	_ = cancel // the SendStream.killAndWait() will kill the process
 
 	return stream, nil
 }
@@ -1022,8 +1042,10 @@ func (s *DrySendInfo) unmarshalZFSOutput(output []byte) (err error) {
 }
 
 // unmarshal info line, looks like this:
-//   full	zroot/test/a@1	5389768
-//   incremental	zroot/test/a@1	zroot/test/a@2	5383936
+//
+//	full	zroot/test/a@1	5389768
+//	incremental	zroot/test/a@1	zroot/test/a@2	5383936
+//
 // => see test cases
 func (s *DrySendInfo) unmarshalInfoLine(l string) (regexMatched bool, err error) {
 
@@ -1855,7 +1877,6 @@ var ErrBookmarkCloningNotSupported = fmt.Errorf("bookmark cloning feature is not
 // unless a bookmark with the name `bookmark` exists and has the same idenitty (zfs.FilesystemVersionEqualIdentity)
 //
 // v must be validated by the caller
-//
 func ZFSBookmark(ctx context.Context, fs string, v FilesystemVersion, bookmark string) (bm FilesystemVersion, err error) {
 
 	bm = FilesystemVersion{

zfs/zfs_debug.go

@@ -13,7 +13,7 @@ func init() {
 	}
 }
 
-//nolint[:deadcode,unused]
+//nolint:deadcode,unused
 func debug(format string, args ...interface{}) {
 	if debugEnabled {
 		fmt.Fprintf(os.Stderr, "zfs: %s\n", fmt.Sprintf(format, args...))