endpoint: refactor, fix stale holds on initial replication, holds release subcmds

- endpoint abstractions now share an interface `Abstraction`
- pkg endpoint now has a query facitilty (`ListAbstractions`) which is
  used to find on-disk
    - step holds and bookmarks
    - replication cursors (v1, v2)
    - last-received-holds
- the `zrepl holds list` command consumes endpoint.ListAbstractions
- the new `zrepl holds release-{all,stale}` commands can be used
  to remove abstractions of package endpoint

Co-authored-by: InsanePrawn <insane.prawny@gmail.com>

supersedes #282
fixes #280
fixes #278
This commit is contained in:
Christian Schwarz
2020-03-26 23:43:17 +01:00
parent 44bd354eae
commit f3734ed0d4
28 changed files with 1854 additions and 1168 deletions
+52 -36
View File
@@ -113,25 +113,40 @@ func (p *Sender) HintMostRecentCommonAncestor(ctx context.Context, r *pdu.HintMo
var err error
fs := r.GetFilesystem()
mostRecent, err := sendArgsFromPDUAndValidateExists(ctx, fs, r.GetSenderVersion())
log := getLogger(ctx).WithField("fs", fs).WithField("hinted_most_recent", fmt.Sprintf("%#v", r.GetSenderVersion()))
// FIXME check if fs exists AND IS PERMITTED by p.filesystems
log.WithField("full_hint", r).Debug("full hint")
if r.GetSenderVersion() == nil {
// no common ancestor found, likely due to failed prior replication attempt
// => release stale step holds to prevent them from accumulating
// (they can accumulate on initial replication because each inital replication step might hold a different `to`)
// => replication cursors cannot accumulate because we always _move_ the replication cursor
log.Debug("releasing all step holds on the filesystem")
TryReleaseStepStaleFS(ctx, fs, p.jobId)
return &pdu.HintMostRecentCommonAncestorRes{}, nil
}
// we were hinted a specific common ancestor
mostRecentVersion, err := sendArgsFromPDUAndValidateExistsAndGetVersion(ctx, fs, r.GetSenderVersion())
if err != nil {
msg := "HintMostRecentCommonAncestor rpc with nonexistent most recent version"
getLogger(ctx).WithField("fs", fs).WithField("hinted_most_recent", fmt.Sprintf("%#v", mostRecent)).
Warn(msg)
log.Warn(msg)
return nil, errors.Wrap(err, msg)
}
// move replication cursor to this position
_, err = MoveReplicationCursor(ctx, fs, mostRecent, p.jobId)
_, err = MoveReplicationCursor(ctx, fs, mostRecentVersion, p.jobId)
if err == zfs.ErrBookmarkCloningNotSupported {
getLogger(ctx).Debug("not creating replication cursor from bookmark because ZFS does not support it")
log.Debug("not creating replication cursor from bookmark because ZFS does not support it")
// fallthrough
} else if err != nil {
return nil, errors.Wrap(err, "cannot set replication cursor to hinted version")
}
// cleanup previous steps
if err := ReleaseStepAll(ctx, fs, mostRecent, p.jobId); err != nil {
if err := ReleaseStepCummulativeInclusive(ctx, fs, mostRecentVersion, p.jobId); err != nil {
return nil, errors.Wrap(err, "cannot cleanup prior invocation's step holds and bookmarks")
}
@@ -147,15 +162,16 @@ func uncheckedSendArgsFromPDU(fsv *pdu.FilesystemVersion) *zfs.ZFSSendArgVersion
return &zfs.ZFSSendArgVersion{RelName: fsv.GetRelName(), GUID: fsv.Guid}
}
func sendArgsFromPDUAndValidateExists(ctx context.Context, fs string, fsv *pdu.FilesystemVersion) (*zfs.ZFSSendArgVersion, error) {
v := uncheckedSendArgsFromPDU(fsv)
if v == nil {
return nil, errors.New("must not be nil")
func sendArgsFromPDUAndValidateExistsAndGetVersion(ctx context.Context, fs string, fsv *pdu.FilesystemVersion) (v zfs.FilesystemVersion, err error) {
sendArgs := uncheckedSendArgsFromPDU(fsv)
if sendArgs == nil {
return v, errors.New("must not be nil")
}
if err := v.ValidateExists(ctx, fs); err != nil {
return nil, err
version, err := sendArgs.ValidateExistsAndGetVersion(ctx, fs)
if err != nil {
return v, err
}
return v, nil
return version, nil
}
func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, zfs.StreamCopier, error) {
@@ -182,7 +198,7 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, zfs.St
return nil, nil, fmt.Errorf("unknown pdu.Tri variant %q", r.Encrypted)
}
sendArgs := zfs.ZFSSendArgs{
sendArgsUnvalidated := zfs.ZFSSendArgsUnvalidated{
FS: r.Filesystem,
From: uncheckedSendArgsFromPDU(r.GetFrom()), // validated by zfs.ZFSSendDry / zfs.ZFSSend
To: uncheckedSendArgsFromPDU(r.GetTo()), // validated by zfs.ZFSSendDry / zfs.ZFSSend
@@ -190,6 +206,11 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, zfs.St
ResumeToken: r.ResumeToken, // nil or not nil, depending on decoding success
}
sendArgs, err := sendArgsUnvalidated.Validate(ctx)
if err != nil {
return nil, nil, errors.Wrap(err, "validate send arguments")
}
getLogger(ctx).Debug("acquire concurrent send semaphore")
// TODO use try-acquire and fail with resource-exhaustion rpc status
// => would require handling on the client-side
@@ -224,7 +245,7 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, zfs.St
// update replication cursor
if sendArgs.From != nil {
// For all but the first replication, this should always be a no-op because SendCompleted already moved the cursor
_, err = MoveReplicationCursor(ctx, sendArgs.FS, sendArgs.From, s.jobId)
_, err = MoveReplicationCursor(ctx, sendArgs.FS, sendArgs.FromVersion, s.jobId)
if err == zfs.ErrBookmarkCloningNotSupported {
getLogger(ctx).Debug("not creating replication cursor from bookmark because ZFS does not support it")
// fallthrough
@@ -235,18 +256,18 @@ func (s *Sender) Send(ctx context.Context, r *pdu.SendReq) (*pdu.SendRes, zfs.St
// make sure `From` doesn't go away in order to make this step resumable
if sendArgs.From != nil {
err := HoldStep(ctx, sendArgs.FS, sendArgs.From, s.jobId)
err := HoldStep(ctx, sendArgs.FS, *sendArgs.FromVersion, s.jobId)
if err == zfs.ErrBookmarkCloningNotSupported {
getLogger(ctx).Debug("not creating step bookmark because ZFS does not support it")
// fallthrough
} else if err != nil {
return nil, nil, errors.Wrap(err, "cannot create step bookmark")
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
err = HoldStep(ctx, sendArgs.FS, sendArgs.To, s.jobId)
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.To.RelName)
return nil, nil, errors.Wrapf(err, "cannot hold `to` version %q before starting send", sendArgs.ToVersion)
}
// step holds & replication cursor released / moved forward in s.SendCompleted => s.moveCursorAndReleaseSendHolds
@@ -263,23 +284,24 @@ func (p *Sender) SendCompleted(ctx context.Context, r *pdu.SendCompletedReq) (*p
fs := orig.GetFilesystem()
var err error
var from *zfs.ZFSSendArgVersion
var from *zfs.FilesystemVersion
if orig.GetFrom() != nil {
from, err = sendArgsFromPDUAndValidateExists(ctx, fs, orig.GetFrom()) // no shadow
f, err := sendArgsFromPDUAndValidateExistsAndGetVersion(ctx, fs, orig.GetFrom()) // no shadow
if err != nil {
return nil, errors.Wrap(err, "validate `from` exists")
}
from = &f
}
to, err := sendArgsFromPDUAndValidateExists(ctx, fs, orig.GetTo())
to, err := sendArgsFromPDUAndValidateExistsAndGetVersion(ctx, fs, orig.GetTo())
if err != nil {
return nil, errors.Wrap(err, "validate `to` exists")
}
log := getLogger(ctx).WithField("to_guid", to.GUID).
log := getLogger(ctx).WithField("to_guid", to.Guid).
WithField("fs", fs).
WithField("to", to.RelName)
if from != nil {
log = log.WithField("from", from.RelName).WithField("from_guid", from.GUID)
log = log.WithField("from", from.RelName).WithField("from_guid", from.Guid)
}
log.Debug("move replication cursor to most recent common version")
@@ -320,18 +342,14 @@ func (p *Sender) SendCompleted(ctx context.Context, r *pdu.SendCompletedReq) (*p
return
}
log.Debug("release step-hold of or step-bookmark on `from`")
err := ReleaseStep(ctx, fs, from, p.jobId)
err := ReleaseStep(ctx, fs, *from, p.jobId)
if err != nil {
if dne, ok := err.(*zfs.DatasetDoesNotExist); ok {
// If bookmark cloning is not supported, `from` might be the old replication cursor
// and thus have already been destroyed by MoveReplicationCursor above
// In that case, nonexistence of `from` is not an error, otherwise it is.
fsp, err := zfs.NewDatasetPath(fs)
if err != nil {
panic(err) // fs has been validated multiple times above
}
for _, fsv := range destroyedCursors {
if fsv.ToAbsPath(fsp) == dne.Path {
for _, c := range destroyedCursors {
if c.GetFullPath() == dne.Path {
log.Info("`from` was a replication cursor and has already been destroyed")
return
}
@@ -610,9 +628,6 @@ func (s *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, receive zfs
if to == nil {
return nil, errors.New("`To` must not be nil")
}
if err := to.ValidateInMemory(lp.ToString()); err != nil {
return nil, errors.Wrap(err, "`To` invalid")
}
if !to.IsSnapshot() {
return nil, errors.New("`To` must be a snapshot")
}
@@ -725,7 +740,8 @@ func (s *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, receive zfs
}
// validate that we actually received what the sender claimed
if err := to.ValidateExists(ctx, lp.ToString()); err != nil {
toRecvd, err := to.ValidateExistsAndGetVersion(ctx, lp.ToString())
if err != nil {
msg := "receive request's `To` version does not match what we received in the stream"
getLogger(ctx).WithError(err).WithField("snap", snapFullPath).Error(msg)
getLogger(ctx).Error("aborting recv request, but keeping received snapshot for inspection")
@@ -734,7 +750,7 @@ func (s *Receiver) Receive(ctx context.Context, req *pdu.ReceiveReq, receive zfs
if s.conf.UpdateLastReceivedHold {
getLogger(ctx).Debug("move last-received-hold")
if err := MoveLastReceivedHold(ctx, lp.ToString(), *to, s.conf.JobID); err != nil {
if err := MoveLastReceivedHold(ctx, lp.ToString(), toRecvd, s.conf.JobID); err != nil {
return nil, errors.Wrap(err, "cannot move last-received-hold")
}
}
-503
View File
@@ -1,503 +0,0 @@
package endpoint
import (
"context"
"fmt"
"regexp"
"sort"
"github.com/kr/pretty"
"github.com/pkg/errors"
"github.com/zrepl/zrepl/zfs"
)
var stepHoldTagRE = regexp.MustCompile("^zrepl_STEP_J_(.+)")
func StepHoldTag(jobid JobID) (string, error) {
return stepHoldTagImpl(jobid.String())
}
func stepHoldTagImpl(jobid string) (string, error) {
t := fmt.Sprintf("zrepl_STEP_J_%s", jobid)
if err := zfs.ValidHoldTag(t); err != nil {
return "", err
}
return t, nil
}
// err != nil always means that the bookmark is not a step bookmark
func ParseStepHoldTag(tag string) (JobID, error) {
match := stepHoldTagRE.FindStringSubmatch(tag)
if match == nil {
return JobID{}, fmt.Errorf("parse hold tag: match regex %q", stepHoldTagRE)
}
jobID, err := MakeJobID(match[1])
if err != nil {
return JobID{}, errors.Wrap(err, "parse hold tag: invalid job id field")
}
return jobID, nil
}
const stepBookmarkNamePrefix = "zrepl_STEP"
// v must be validated by caller
func StepBookmarkName(fs string, guid uint64, id JobID) (string, error) {
return stepBookmarkNameImpl(fs, guid, id.String())
}
func stepBookmarkNameImpl(fs string, guid uint64, jobid string) (string, error) {
return makeJobAndGuidBookmarkName(stepBookmarkNamePrefix, fs, guid, jobid)
}
// name is the full bookmark name, including dataset path
//
// err != nil always means that the bookmark is not a step bookmark
func ParseStepBookmarkName(fullname string) (guid uint64, jobID JobID, err error) {
guid, jobID, err = parseJobAndGuidBookmarkName(fullname, stepBookmarkNamePrefix)
if err != nil {
err = errors.Wrap(err, "parse step bookmark name") // no shadow!
}
return guid, jobID, err
}
const replicationCursorBookmarkNamePrefix = "zrepl_CURSOR"
func ReplicationCursorBookmarkName(fs string, guid uint64, id JobID) (string, error) {
return replicationCursorBookmarkNameImpl(fs, guid, id.String())
}
func replicationCursorBookmarkNameImpl(fs string, guid uint64, jobid string) (string, error) {
return makeJobAndGuidBookmarkName(replicationCursorBookmarkNamePrefix, fs, guid, jobid)
}
var ErrV1ReplicationCursor = fmt.Errorf("bookmark name is a v1-replication cursor")
//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) {
// check for legacy cursors
{
if err := zfs.EntityNamecheck(fullname, zfs.EntityTypeBookmark); err != nil {
return 0, JobID{}, errors.Wrap(err, "parse replication cursor bookmark name")
}
_, _, name, err := zfs.DecomposeVersionString(fullname)
if err != nil {
return 0, JobID{}, errors.Wrap(err, "parse replication cursor bookmark name: decompose version string")
}
const V1ReplicationCursorBookmarkName = "zrepl_replication_cursor"
if name == V1ReplicationCursorBookmarkName {
return 0, JobID{}, ErrV1ReplicationCursor
}
}
guid, jobID, err := parseJobAndGuidBookmarkName(fullname, replicationCursorBookmarkNamePrefix)
if err != nil {
err = errors.Wrap(err, "parse replication cursor bookmark name") // no shadow
}
return guid, jobID, err
}
// may return nil for both values, indicating there is no cursor
func GetMostRecentReplicationCursorOfJob(ctx context.Context, fs string, jobID JobID) (*zfs.FilesystemVersion, error) {
fsp, err := zfs.NewDatasetPath(fs)
if err != nil {
return nil, err
}
candidates, err := GetReplicationCursors(ctx, fsp, jobID)
if err != nil || len(candidates) == 0 {
return nil, err
}
sort.Slice(candidates, func(i, j int) bool {
return candidates[i].CreateTXG < candidates[j].CreateTXG
})
mostRecent := candidates[len(candidates)-1]
return &mostRecent, nil
}
func GetReplicationCursors(ctx context.Context, fs *zfs.DatasetPath, jobID JobID) ([]zfs.FilesystemVersion, error) {
listOut := &ListHoldsAndBookmarksOutput{}
if err := listZFSHoldsAndBookmarksImplFS(ctx, listOut, fs); err != nil {
return nil, errors.Wrap(err, "get replication cursor: list bookmarks and holds")
}
if len(listOut.V1ReplicationCursors) > 0 {
getLogger(ctx).WithField("bookmark", pretty.Sprint(listOut.V1ReplicationCursors)).
Warn("found v1-replication cursor bookmarks, consider running migration 'replication-cursor:v1-v2' after successful replication with this zrepl version")
}
candidates := make([]zfs.FilesystemVersion, 0)
for _, v := range listOut.ReplicationCursorBookmarks {
zv := zfs.ZFSSendArgVersion{
RelName: "#" + v.Name,
GUID: v.Guid,
}
if err := zv.ValidateExists(ctx, v.FS); err != nil {
getLogger(ctx).WithError(err).WithField("bookmark", zv.FullPath(v.FS)).
Error("found invalid replication cursor bookmark")
continue
}
candidates = append(candidates, v.v)
}
return candidates, nil
}
// `target` is validated before replication cursor is set. if validation fails, the cursor is not moved.
//
// returns ErrBookmarkCloningNotSupported if version is a bookmark and bookmarking bookmarks is not supported by ZFS
func MoveReplicationCursor(ctx context.Context, fs string, target *zfs.ZFSSendArgVersion, jobID JobID) (destroyedCursors []zfs.FilesystemVersion, err error) {
if !target.IsSnapshot() {
return nil, zfs.ErrBookmarkCloningNotSupported
}
snapProps, err := target.ValidateExistsAndGetCheckedProps(ctx, fs)
if err != nil {
return nil, errors.Wrapf(err, "invalid replication cursor target %q (guid=%v)", target.RelName, target.GUID)
}
bookmarkname, err := ReplicationCursorBookmarkName(fs, snapProps.Guid, jobID)
if err != nil {
return nil, errors.Wrap(err, "determine replication cursor name")
}
// idempotently create bookmark (guid is encoded in it, hence we'll most likely add a new one
// cleanup the old one afterwards
err = zfs.ZFSBookmark(fs, *target, bookmarkname)
if err != nil {
if err == zfs.ErrBookmarkCloningNotSupported {
return nil, err // TODO go1.13 use wrapping
}
return nil, errors.Wrapf(err, "cannot create bookmark")
}
destroyedCursors, err = DestroyObsoleteReplicationCursors(ctx, fs, target, jobID)
if err != nil {
return nil, errors.Wrap(err, "destroy obsolete replication cursors")
}
return destroyedCursors, nil
}
func DestroyObsoleteReplicationCursors(ctx context.Context, fs string, target *zfs.ZFSSendArgVersion, jobID JobID) (destroyed []zfs.FilesystemVersion, err error) {
return destroyBookmarksOlderThan(ctx, fs, target, jobID, func(shortname string) (accept bool) {
_, parsedID, err := ParseReplicationCursorBookmarkName(fs + "#" + shortname)
return err == nil && parsedID == jobID
})
}
// idempotently hold / step-bookmark `version`
//
// returns ErrBookmarkCloningNotSupported if version is a bookmark and bookmarking bookmarks is not supported by ZFS
func HoldStep(ctx context.Context, fs string, v *zfs.ZFSSendArgVersion, jobID JobID) error {
if err := v.ValidateExists(ctx, fs); err != nil {
return err
}
if v.IsSnapshot() {
tag, err := StepHoldTag(jobID)
if err != nil {
return errors.Wrap(err, "step hold tag")
}
if err := zfs.ZFSHold(ctx, fs, *v, tag); err != nil {
return errors.Wrap(err, "step hold: zfs")
}
return nil
}
v.MustBeBookmark()
bmname, err := StepBookmarkName(fs, v.GUID, jobID)
if err != nil {
return errors.Wrap(err, "create step bookmark: determine bookmark name")
}
// idempotently create bookmark
err = zfs.ZFSBookmark(fs, *v, bmname)
if err != nil {
if err == zfs.ErrBookmarkCloningNotSupported {
// TODO we could actually try to find a local snapshot that has the requested GUID
// however, the replication algorithm prefers snapshots anyways, so this quest
// is most likely not going to be successful. Also, there's the possibility that
// the caller might want to filter what snapshots are eligible, and this would
// complicate things even further.
return err // TODO go1.13 use wrapping
}
return errors.Wrap(err, "create step bookmark: zfs")
}
return nil
}
// idempotently release the step-hold on v if v is a snapshot
// or idempotently destroy the step-bookmark of v if v is a bookmark
//
// note that this operation leaves v itself untouched, unless v is the step-bookmark itself, in which case v is destroyed
//
// returns an instance of *zfs.DatasetDoesNotExist if `v` does not exist
func ReleaseStep(ctx context.Context, fs string, v *zfs.ZFSSendArgVersion, jobID JobID) error {
if err := v.ValidateExists(ctx, fs); err != nil {
return err
}
if v.IsSnapshot() {
tag, err := StepHoldTag(jobID)
if err != nil {
return errors.Wrap(err, "step release tag")
}
if err := zfs.ZFSRelease(ctx, tag, v.FullPath(fs)); err != nil {
return errors.Wrap(err, "step release: zfs")
}
return nil
}
v.MustBeBookmark()
bmname, err := StepBookmarkName(fs, v.GUID, jobID)
if err != nil {
return errors.Wrap(err, "step release: determine bookmark name")
}
// idempotently destroy bookmark
if err := zfs.ZFSDestroyIdempotent(bmname); err != nil {
return errors.Wrap(err, "step release: bookmark destroy: zfs")
}
return nil
}
// release {step holds, step bookmarks} earlier and including `mostRecent`
func ReleaseStepAll(ctx context.Context, fs string, mostRecent *zfs.ZFSSendArgVersion, jobID JobID) error {
if err := mostRecent.ValidateInMemory(fs); err != nil {
return err
}
tag, err := StepHoldTag(jobID)
if err != nil {
return errors.Wrap(err, "step release all: tag")
}
err = zfs.ZFSReleaseAllOlderAndIncludingGUID(ctx, fs, mostRecent.GUID, tag)
if err != nil {
return errors.Wrapf(err, "step release all: release holds older and including %q", mostRecent.FullPath(fs))
}
_, err = destroyBookmarksOlderThan(ctx, fs, mostRecent, jobID, func(shortname string) bool {
_, parsedId, parseErr := ParseStepBookmarkName(fs + "#" + shortname)
return parseErr == nil && parsedId == jobID
})
if err != nil {
return errors.Wrapf(err, "step release all: destroy bookmarks older than %q", mostRecent.FullPath(fs))
}
return nil
}
var lastReceivedHoldTagRE = regexp.MustCompile("^zrepl_last_received_J_(.+)$")
// err != nil always means that the bookmark is not a step bookmark
func ParseLastReceivedHoldTag(tag string) (JobID, error) {
match := lastReceivedHoldTagRE.FindStringSubmatch(tag)
if match == nil {
return JobID{}, errors.Errorf("parse last-received-hold tag: does not match regex %s", lastReceivedHoldTagRE.String())
}
jobId, err := MakeJobID(match[1])
if err != nil {
return JobID{}, errors.Wrap(err, "parse last-received-hold tag: invalid job id field")
}
return jobId, nil
}
func LastReceivedHoldTag(jobID JobID) (string, error) {
return lastReceivedHoldImpl(jobID.String())
}
func lastReceivedHoldImpl(jobid string) (string, error) {
tag := fmt.Sprintf("zrepl_last_received_J_%s", jobid)
if err := zfs.ValidHoldTag(tag); err != nil {
return "", err
}
return tag, nil
}
func MoveLastReceivedHold(ctx context.Context, fs string, to zfs.ZFSSendArgVersion, jobID JobID) error {
if err := to.ValidateExists(ctx, fs); err != nil {
return err
}
if err := zfs.EntityNamecheck(to.FullPath(fs), zfs.EntityTypeSnapshot); err != nil {
return err
}
tag, err := LastReceivedHoldTag(jobID)
if err != nil {
return errors.Wrap(err, "last-received-hold: hold tag")
}
// we never want to be without a hold
// => hold new one before releasing old hold
err = zfs.ZFSHold(ctx, fs, to, tag)
if err != nil {
return errors.Wrap(err, "last-received-hold: hold newly received")
}
err = zfs.ZFSReleaseAllOlderThanGUID(ctx, fs, to.GUID, tag)
if err != nil {
return errors.Wrap(err, "last-received-hold: release older holds")
}
return nil
}
type ListHoldsAndBookmarksOutputBookmarkV1ReplicationCursor struct {
FS string
Name string
}
type ListHoldsAndBookmarksOutput struct {
StepBookmarks []*ListHoldsAndBookmarksOutputBookmark
StepHolds []*ListHoldsAndBookmarksOutputHold
ReplicationCursorBookmarks []*ListHoldsAndBookmarksOutputBookmark
V1ReplicationCursors []*ListHoldsAndBookmarksOutputBookmarkV1ReplicationCursor
LastReceivedHolds []*ListHoldsAndBookmarksOutputHold
}
type ListHoldsAndBookmarksOutputBookmark struct {
FS, Name string
Guid uint64
JobID JobID
v zfs.FilesystemVersion
}
type ListHoldsAndBookmarksOutputHold struct {
FS string
Snap string
SnapGuid uint64
SnapCreateTXG uint64
Tag string
JobID JobID
}
// List all holds and bookmarks managed by endpoint
func ListZFSHoldsAndBookmarks(ctx context.Context, fsfilter zfs.DatasetFilter) (*ListHoldsAndBookmarksOutput, error) {
// initialize all fields so that JSON serialization of output looks pretty (see client/holds.go)
// however, listZFSHoldsAndBookmarksImplFS shouldn't rely on it
out := &ListHoldsAndBookmarksOutput{
StepBookmarks: make([]*ListHoldsAndBookmarksOutputBookmark, 0),
StepHolds: make([]*ListHoldsAndBookmarksOutputHold, 0),
ReplicationCursorBookmarks: make([]*ListHoldsAndBookmarksOutputBookmark, 0),
V1ReplicationCursors: make([]*ListHoldsAndBookmarksOutputBookmarkV1ReplicationCursor, 0),
LastReceivedHolds: make([]*ListHoldsAndBookmarksOutputHold, 0),
}
fss, err := zfs.ZFSListMapping(ctx, fsfilter)
if err != nil {
return nil, errors.Wrap(err, "list filesystems")
}
for _, fs := range fss {
err := listZFSHoldsAndBookmarksImplFS(ctx, out, fs)
if err != nil {
return nil, errors.Wrapf(err, "list holds and bookmarks on %q", fs.ToString())
}
}
return out, nil
}
func listZFSHoldsAndBookmarksImplFS(ctx context.Context, out *ListHoldsAndBookmarksOutput, fs *zfs.DatasetPath) error {
fsvs, err := zfs.ZFSListFilesystemVersions(fs, nil)
if err != nil {
return errors.Wrapf(err, "list filesystem versions of %q", fs)
}
for _, v := range fsvs {
switch v.Type {
case zfs.Bookmark:
listZFSHoldsAndBookmarksImplTryParseBookmark(ctx, out, fs, v)
case zfs.Snapshot:
holds, err := zfs.ZFSHolds(ctx, fs.ToString(), v.Name)
if err != nil {
return errors.Wrapf(err, "get holds of %q", v.ToAbsPath(fs))
}
for _, tag := range holds {
listZFSHoldsAndBookmarksImplSnapshotTryParseHold(ctx, out, fs, v, tag)
}
default:
continue
}
}
return nil
}
// pure function, err != nil always indicates parsing error
func listZFSHoldsAndBookmarksImplTryParseBookmark(ctx context.Context, out *ListHoldsAndBookmarksOutput, fs *zfs.DatasetPath, v zfs.FilesystemVersion) {
var err error
if v.Type != zfs.Bookmark {
panic("impl error")
}
fullname := v.ToAbsPath(fs)
bm := &ListHoldsAndBookmarksOutputBookmark{
FS: fs.ToString(), Name: v.Name, v: v,
}
bm.Guid, bm.JobID, err = ParseStepBookmarkName(fullname)
if err == nil {
out.StepBookmarks = append(out.StepBookmarks, bm)
return
}
bm.Guid, bm.JobID, err = ParseReplicationCursorBookmarkName(fullname)
if err == nil {
out.ReplicationCursorBookmarks = append(out.ReplicationCursorBookmarks, bm)
return
} else if err == ErrV1ReplicationCursor {
v1rc := &ListHoldsAndBookmarksOutputBookmarkV1ReplicationCursor{
FS: fs.ToString(), Name: v.Name,
}
out.V1ReplicationCursors = append(out.V1ReplicationCursors, v1rc)
return
}
}
// pure function, err != nil always indicates parsing error
func listZFSHoldsAndBookmarksImplSnapshotTryParseHold(ctx context.Context, out *ListHoldsAndBookmarksOutput, fs *zfs.DatasetPath, v zfs.FilesystemVersion, holdTag string) {
var err error
if v.Type != zfs.Snapshot {
panic("impl error")
}
hold := &ListHoldsAndBookmarksOutputHold{
FS: fs.ToString(),
Snap: v.Name,
SnapGuid: v.Guid,
SnapCreateTXG: v.CreateTXG,
Tag: holdTag,
}
hold.JobID, err = ParseStepHoldTag(holdTag)
if err == nil {
out.StepHolds = append(out.StepHolds, hold)
return
}
hold.JobID, err = ParseLastReceivedHoldTag(holdTag)
if err == nil {
out.LastReceivedHolds = append(out.LastReceivedHolds, hold)
return
}
}
+530
View File
@@ -0,0 +1,530 @@
package endpoint
import (
"context"
"encoding/json"
"fmt"
"sort"
"strings"
"github.com/pkg/errors"
"github.com/zrepl/zrepl/util/envconst"
"github.com/zrepl/zrepl/zfs"
)
type AbstractionType string
// Implementation note:
// There are a lot of exhaustive switches on AbstractionType in the code base.
// When adding a new abstraction type, make sure to search and update them!
const (
AbstractionStepBookmark AbstractionType = "step-bookmark"
AbstractionStepHold AbstractionType = "step-hold"
AbstractionLastReceivedHold AbstractionType = "last-received-hold"
AbstractionReplicationCursorBookmarkV1 AbstractionType = "replication-cursor-bookmark-v1"
AbstractionReplicationCursorBookmarkV2 AbstractionType = "replication-cursor-bookmark-v2"
)
var AbstractionTypesAll = map[AbstractionType]bool{
AbstractionStepBookmark: true,
AbstractionStepHold: true,
AbstractionLastReceivedHold: true,
AbstractionReplicationCursorBookmarkV1: true,
AbstractionReplicationCursorBookmarkV2: true,
}
// Implementation Note:
// Whenever you add a new accessor, adjust AbstractionJSON.MarshalJSON accordingly
type Abstraction interface {
GetType() AbstractionType
GetFS() string
GetName() string
GetFullPath() string
GetJobID() *JobID // may return nil if the abstraction does not have a JobID
GetCreateTXG() uint64
GetFilesystemVersion() zfs.FilesystemVersion
String() string
// destroy the abstraction: either releases the hold or destroys the bookmark
Destroy(context.Context) error
json.Marshaler
}
func (t AbstractionType) Validate() error {
switch t {
case AbstractionStepBookmark:
return nil
case AbstractionStepHold:
return nil
case AbstractionLastReceivedHold:
return nil
case AbstractionReplicationCursorBookmarkV1:
return nil
case AbstractionReplicationCursorBookmarkV2:
return nil
default:
return errors.Errorf("unknown abstraction type %q", t)
}
}
func (t AbstractionType) MustValidate() error {
if err := t.Validate(); err != nil {
panic(err)
}
return nil
}
// Number of instances of this abstraction type that are live (not stale)
// per (FS,JobID). -1 for infinity.
func (t AbstractionType) NumLivePerFsAndJob() int {
switch t {
case AbstractionStepBookmark:
return 2
case AbstractionStepHold:
return 2
case AbstractionLastReceivedHold:
return 1
case AbstractionReplicationCursorBookmarkV1:
return -1
case AbstractionReplicationCursorBookmarkV2:
return 1
default:
panic(t)
}
}
type AbstractionJSON struct{ Abstraction }
var _ json.Marshaler = (*AbstractionJSON)(nil)
func (a AbstractionJSON) MarshalJSON() ([]byte, error) {
type S struct {
Type AbstractionType
FS string
Name string
FullPath string
JobID *JobID // may return nil if the abstraction does not have a JobID
CreateTXG uint64
FilesystemVersion zfs.FilesystemVersion
String string
}
v := S{
Type: a.Abstraction.GetType(),
FS: a.Abstraction.GetFS(),
Name: a.Abstraction.GetName(),
FullPath: a.Abstraction.GetFullPath(),
JobID: a.Abstraction.GetJobID(),
CreateTXG: a.Abstraction.GetCreateTXG(),
FilesystemVersion: a.Abstraction.GetFilesystemVersion(),
String: a.Abstraction.String(),
}
return json.Marshal(v)
}
type AbstractionTypeSet map[AbstractionType]bool
func AbstractionTypeSetFromStrings(sts []string) (AbstractionTypeSet, error) {
ats := make(map[AbstractionType]bool, len(sts))
for i, t := range sts {
at := AbstractionType(t)
if err := at.Validate(); err != nil {
return nil, errors.Wrapf(err, "invalid abstraction type #%d %q", i+1, t)
}
ats[at] = true
}
return ats, nil
}
func (s AbstractionTypeSet) String() string {
sts := make([]string, 0, len(s))
for i := range s {
sts = append(sts, string(i))
}
sts = sort.StringSlice(sts)
return strings.Join(sts, ",")
}
func (s AbstractionTypeSet) Validate() error {
for k := range s {
if err := k.Validate(); err != nil {
return err
}
}
return nil
}
type BookmarkExtractor func(fs *zfs.DatasetPath, v zfs.FilesystemVersion) Abstraction
// returns nil if the abstraction type is not bookmark-based
func (t AbstractionType) BookmarkExtractor() BookmarkExtractor {
switch t {
case AbstractionStepBookmark:
return StepBookmarkExtractor
case AbstractionReplicationCursorBookmarkV1:
return ReplicationCursorV1Extractor
case AbstractionReplicationCursorBookmarkV2:
return ReplicationCursorV2Extractor
case AbstractionStepHold:
return nil
case AbstractionLastReceivedHold:
return nil
default:
panic(fmt.Sprintf("unimpl: %q", t))
}
}
type HoldExtractor = func(fs *zfs.DatasetPath, v zfs.FilesystemVersion, tag string) Abstraction
// returns nil if the abstraction type is not hold-based
func (t AbstractionType) HoldExtractor() HoldExtractor {
switch t {
case AbstractionStepBookmark:
return nil
case AbstractionReplicationCursorBookmarkV1:
return nil
case AbstractionReplicationCursorBookmarkV2:
return nil
case AbstractionStepHold:
return StepHoldExtractor
case AbstractionLastReceivedHold:
return LastReceivedHoldExtractor
default:
panic(fmt.Sprintf("unimpl: %q", t))
}
}
type ListZFSHoldsAndBookmarksQuery struct {
FS ListZFSHoldsAndBookmarksQueryFilesystemFilter
// What abstraction types should match (any contained in the set)
What AbstractionTypeSet
// The output for the query must satisfy _all_ (AND) requirements of all fields in this query struct.
// if not nil: JobID of the hold or bookmark in question must be equal
// else: JobID of the hold or bookmark can be any value
JobID *JobID
// if not nil: The hold's snapshot or the bookmark's createtxg must be less than (or equal) Until
// else: CreateTXG of the hold or bookmark can be any value
Until *InclusiveExclusiveCreateTXG
// TODO
// Concurrent: uint > 0
}
type InclusiveExclusiveCreateTXG struct {
CreateTXG uint64
Inclusive *zfs.NilBool // must not be nil
}
// FS == nil XOR Filter == nil
type ListZFSHoldsAndBookmarksQueryFilesystemFilter struct {
FS *string
Filter zfs.DatasetFilter
}
func (q *ListZFSHoldsAndBookmarksQuery) Validate() error {
if err := q.FS.Validate(); err != nil {
return errors.Wrap(err, "FS")
}
if q.JobID != nil {
q.JobID.MustValidate() // FIXME
}
if q.Until != nil {
if err := q.Until.Validate(); err != nil {
return errors.Wrap(err, "Until")
}
}
if err := q.What.Validate(); err != nil {
return err
}
return nil
}
var zreplEndpointListAbstractionsQueryCreatetxg0Allowed = envconst.Bool("ZREPL_ENDPOINT_LIST_ABSTRACTIONS_QUERY_CREATETXG_0_ALLOWED", false)
func (i *InclusiveExclusiveCreateTXG) Validate() error {
if err := i.Inclusive.Validate(); err != nil {
return errors.Wrap(err, "Inclusive")
}
if i.CreateTXG == 0 && !zreplEndpointListAbstractionsQueryCreatetxg0Allowed {
return errors.New("CreateTXG must be non-zero")
}
return nil
}
func (f *ListZFSHoldsAndBookmarksQueryFilesystemFilter) Validate() error {
if f == nil {
return nil
}
fsSet := f.FS != nil
filterSet := f.Filter != nil
if fsSet && filterSet || !fsSet && !filterSet {
return fmt.Errorf("must set FS or Filter field, but fsIsSet=%v and filterIsSet=%v", fsSet, filterSet)
}
if fsSet {
if err := zfs.EntityNamecheck(*f.FS, zfs.EntityTypeFilesystem); err != nil {
return errors.Wrap(err, "FS invalid")
}
}
return nil
}
func (f *ListZFSHoldsAndBookmarksQueryFilesystemFilter) Filesystems(ctx context.Context) ([]string, error) {
if err := f.Validate(); err != nil {
panic(err)
}
if f.FS != nil {
return []string{*f.FS}, nil
}
if f.Filter != nil {
dps, err := zfs.ZFSListMapping(ctx, f.Filter)
if err != nil {
return nil, err
}
fss := make([]string, len(dps))
for i, dp := range dps {
fss[i] = dp.ToString()
}
return fss, nil
}
panic("unreachable")
}
type ListAbstractionsError struct {
FS string
Snap string
What string
Err error
}
func (e ListAbstractionsError) Error() string {
if e.FS == "" {
return fmt.Sprintf("list endpoint abstractions: %s: %s", e.What, e.Err)
} else {
v := e.FS
if e.Snap != "" {
v = fmt.Sprintf("%s@%s", e.FS, e.Snap)
}
return fmt.Sprintf("list endpoint abstractions on %q: %s: %s", v, e.What, e.Err)
}
}
type putListAbstractionErr func(err error, fs string, what string)
type putListAbstraction func(a Abstraction)
type ListAbstractionsErrors []ListAbstractionsError
func (e ListAbstractionsErrors) Error() string {
if len(e) == 0 {
panic(e)
}
if len(e) == 1 {
return fmt.Sprintf("list endpoint abstractions: %s", e[0])
}
msgs := make([]string, len(e))
for i := range e {
msgs[i] = e.Error()
}
return fmt.Sprintf("list endpoint abstractions: multiple errors:\n%s", strings.Join(msgs, "\n"))
}
func ListAbstractions(ctx context.Context, query ListZFSHoldsAndBookmarksQuery) (out []Abstraction, outErrs []ListAbstractionsError, err error) {
// impl note: structure the query processing in such a way that
// a minimum amount of zfs shell-outs needs to be done
if err := query.Validate(); err != nil {
return nil, nil, errors.Wrap(err, "validate query")
}
fss, err := query.FS.Filesystems(ctx)
if err != nil {
return nil, nil, errors.Wrap(err, "list filesystems")
}
errCb := func(err error, fs string, what string) {
outErrs = append(outErrs, ListAbstractionsError{Err: err, FS: fs, What: what})
}
emitAbstraction := func(a Abstraction) {
jobIdMatches := query.JobID == nil || a.GetJobID() == nil || *a.GetJobID() == *query.JobID
untilMatches := query.Until == nil
if query.Until != nil {
if query.Until.Inclusive.B {
untilMatches = a.GetCreateTXG() <= query.Until.CreateTXG
} else {
untilMatches = a.GetCreateTXG() < query.Until.CreateTXG
}
}
if jobIdMatches && untilMatches {
out = append(out, a)
}
}
for _, fs := range fss {
listAbstractionsImplFS(ctx, fs, &query, emitAbstraction, errCb)
}
return out, outErrs, nil
}
func listAbstractionsImplFS(ctx context.Context, fs string, query *ListZFSHoldsAndBookmarksQuery, emitCandidate putListAbstraction, errCb putListAbstractionErr) {
fsp, err := zfs.NewDatasetPath(fs)
if err != nil {
panic(err)
}
if len(query.What) == 0 {
return
}
// we need filesystem versions for any abstraction type
fsvs, err := zfs.ZFSListFilesystemVersions(fsp, nil)
if err != nil {
errCb(err, fs, "list filesystem versions")
return
}
for at := range query.What {
bmE := at.BookmarkExtractor()
holdE := at.HoldExtractor()
if bmE == nil && holdE == nil || bmE != nil && holdE != nil {
panic("implementation error: extractors misconfigured for " + at)
}
for _, v := range fsvs {
var a Abstraction
if v.Type == zfs.Bookmark && bmE != nil {
a = bmE(fsp, v)
}
if v.Type == zfs.Snapshot && holdE != nil {
holds, err := zfs.ZFSHolds(ctx, fsp.ToString(), v.Name)
if err != nil {
errCb(err, v.ToAbsPath(fsp), "get hold on snap")
continue
}
for _, tag := range holds {
a = holdE(fsp, v, tag)
}
}
if a != nil {
emitCandidate(a)
}
}
}
}
type BatchDestroyResult struct {
Abstraction
DestroyErr error
}
var _ json.Marshaler = (*BatchDestroyResult)(nil)
func (r BatchDestroyResult) MarshalJSON() ([]byte, error) {
err := ""
if r.DestroyErr != nil {
err = r.DestroyErr.Error()
}
s := struct {
Abstraction AbstractionJSON
DestroyErr string
}{
AbstractionJSON{r.Abstraction},
err,
}
return json.Marshal(s)
}
func BatchDestroy(ctx context.Context, abs []Abstraction) <-chan BatchDestroyResult {
// hold-based batching: per snapshot
// bookmark-based batching: none possible via CLI
// => not worth the trouble for now, will be worth it once we start using channel programs
// => TODO: actual batching using channel programs
res := make(chan BatchDestroyResult, len(abs))
go func() {
for _, a := range abs {
res <- BatchDestroyResult{
a,
a.Destroy(ctx),
}
}
close(res)
}()
return res
}
type StalenessInfo struct {
ConstructedWithQuery ListZFSHoldsAndBookmarksQuery
All []Abstraction
Live []Abstraction
Stale []Abstraction
}
func ListStale(ctx context.Context, q ListZFSHoldsAndBookmarksQuery) (*StalenessInfo, error) {
if q.Until != nil {
// we must determine the most recent step per FS, can't allow that
return nil, errors.New("ListStale cannot have Until != nil set on query")
}
abs, absErr, err := ListAbstractions(ctx, q)
if err != nil {
return nil, err
}
if len(absErr) > 0 {
// can't go on here because we can't determine the most recent step
return nil, ListAbstractionsErrors(absErr)
}
si := listStaleFiltering(abs)
si.ConstructedWithQuery = q
return si, nil
}
// The last AbstractionType.NumLive() step holds per (FS,Job,AbstractionType) are live
// others are stale.
//
// the returned StalenessInfo.ConstructedWithQuery is not set
func listStaleFiltering(abs []Abstraction) *StalenessInfo {
type fsAjobAtype struct {
FS string
Job JobID
Type AbstractionType
}
var noJobId []Abstraction
by := make(map[fsAjobAtype][]Abstraction)
for _, a := range abs {
if a.GetJobID() == nil {
noJobId = append(noJobId, a)
continue
}
faj := fsAjobAtype{a.GetFS(), *a.GetJobID(), a.GetType()}
l := by[faj]
l = append(l, a)
by[faj] = l
}
ret := &StalenessInfo{
All: abs,
Live: noJobId,
Stale: []Abstraction{},
}
// sort descending (highest createtxg first), then cut off
for k := range by {
l := by[k]
sort.Slice(l, func(i, j int) bool {
return l[i].GetCreateTXG() > l[j].GetCreateTXG()
})
cutoff := k.Type.NumLivePerFsAndJob()
if cutoff == -1 || len(l) <= cutoff {
ret.Live = append(ret.Live, l...)
} else {
ret.Live = append(ret.Live, l[0:cutoff]...)
ret.Stale = append(ret.Stale, l[cutoff:]...)
}
}
return ret
}
@@ -0,0 +1,377 @@
package endpoint
import (
"context"
"encoding/json"
"fmt"
"regexp"
"sort"
"github.com/kr/pretty"
"github.com/pkg/errors"
"github.com/zrepl/zrepl/util/errorarray"
"github.com/zrepl/zrepl/zfs"
)
const replicationCursorBookmarkNamePrefix = "zrepl_CURSOR"
func ReplicationCursorBookmarkName(fs string, guid uint64, id JobID) (string, error) {
return replicationCursorBookmarkNameImpl(fs, guid, id.String())
}
func replicationCursorBookmarkNameImpl(fs string, guid uint64, jobid string) (string, error) {
return makeJobAndGuidBookmarkName(replicationCursorBookmarkNamePrefix, fs, guid, jobid)
}
var ErrV1ReplicationCursor = fmt.Errorf("bookmark name is a v1-replication cursor")
//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) {
// check for legacy cursors
{
if err := zfs.EntityNamecheck(fullname, zfs.EntityTypeBookmark); err != nil {
return 0, JobID{}, errors.Wrap(err, "parse replication cursor bookmark name")
}
_, _, name, err := zfs.DecomposeVersionString(fullname)
if err != nil {
return 0, JobID{}, errors.Wrap(err, "parse replication cursor bookmark name: decompose version string")
}
const V1ReplicationCursorBookmarkName = "zrepl_replication_cursor"
if name == V1ReplicationCursorBookmarkName {
return 0, JobID{}, ErrV1ReplicationCursor
}
// fallthrough to main parser
}
guid, jobID, err := parseJobAndGuidBookmarkName(fullname, replicationCursorBookmarkNamePrefix)
if err != nil {
err = errors.Wrap(err, "parse replication cursor bookmark name") // no shadow
}
return guid, jobID, err
}
// may return nil for both values, indicating there is no cursor
func GetMostRecentReplicationCursorOfJob(ctx context.Context, fs string, jobID JobID) (*zfs.FilesystemVersion, error) {
fsp, err := zfs.NewDatasetPath(fs)
if err != nil {
return nil, err
}
candidates, err := GetReplicationCursors(ctx, fsp, jobID)
if err != nil || len(candidates) == 0 {
return nil, err
}
sort.Slice(candidates, func(i, j int) bool {
return candidates[i].CreateTXG < candidates[j].CreateTXG
})
mostRecent := candidates[len(candidates)-1]
return &mostRecent, nil
}
func GetReplicationCursors(ctx context.Context, dp *zfs.DatasetPath, jobID JobID) ([]zfs.FilesystemVersion, error) {
fs := dp.ToString()
q := ListZFSHoldsAndBookmarksQuery{
FS: ListZFSHoldsAndBookmarksQueryFilesystemFilter{FS: &fs},
What: map[AbstractionType]bool{
AbstractionReplicationCursorBookmarkV1: true,
AbstractionReplicationCursorBookmarkV2: true,
},
JobID: &jobID,
Until: nil,
}
abs, absErr, err := ListAbstractions(ctx, q)
if err != nil {
return nil, errors.Wrap(err, "get replication cursor: list bookmarks and holds")
}
if len(absErr) > 0 {
return nil, ListAbstractionsErrors(absErr)
}
var v1, v2 []Abstraction
for _, a := range abs {
switch a.GetType() {
case AbstractionReplicationCursorBookmarkV1:
v1 = append(v1, a)
case AbstractionReplicationCursorBookmarkV2:
v2 = append(v2, a)
default:
panic("unexpected abstraction: " + a.GetType())
}
}
if len(v1) > 0 {
getLogger(ctx).WithField("bookmark", pretty.Sprint(v1)).
Warn("found v1-replication cursor bookmarks, consider running migration 'replication-cursor:v1-v2' after successful replication with this zrepl version")
}
candidates := make([]zfs.FilesystemVersion, 0)
for _, v := range v2 {
candidates = append(candidates, v.GetFilesystemVersion())
}
return candidates, nil
}
type ReplicationCursorTarget interface {
IsSnapshot() bool
GetGuid() uint64
GetCreateTXG() uint64
ToSendArgVersion() zfs.ZFSSendArgVersion
}
// `target` is validated before replication cursor is set. if validation fails, the cursor is not moved.
//
// returns ErrBookmarkCloningNotSupported if version is a bookmark and bookmarking bookmarks is not supported by ZFS
func MoveReplicationCursor(ctx context.Context, fs string, target ReplicationCursorTarget, jobID JobID) (destroyedCursors []Abstraction, err error) {
if !target.IsSnapshot() {
return nil, zfs.ErrBookmarkCloningNotSupported
}
bookmarkname, err := ReplicationCursorBookmarkName(fs, target.GetGuid(), jobID)
if err != nil {
return nil, errors.Wrap(err, "determine replication cursor name")
}
// idempotently create bookmark (guid is encoded in it, hence we'll most likely add a new one
// cleanup the old one afterwards
err = zfs.ZFSBookmark(fs, target.ToSendArgVersion(), bookmarkname)
if err != nil {
if err == zfs.ErrBookmarkCloningNotSupported {
return nil, err // TODO go1.13 use wrapping
}
return nil, errors.Wrapf(err, "cannot create bookmark")
}
destroyedCursors, err = DestroyObsoleteReplicationCursors(ctx, fs, target, jobID)
if err != nil {
return nil, errors.Wrap(err, "destroy obsolete replication cursors")
}
return destroyedCursors, nil
}
type ReplicationCursor interface {
GetCreateTXG() uint64
}
func DestroyObsoleteReplicationCursors(ctx context.Context, fs string, current ReplicationCursor, jobID JobID) (_ []Abstraction, err error) {
q := ListZFSHoldsAndBookmarksQuery{
FS: ListZFSHoldsAndBookmarksQueryFilesystemFilter{
FS: &fs,
},
What: AbstractionTypeSet{
AbstractionReplicationCursorBookmarkV2: true,
},
JobID: &jobID,
Until: &InclusiveExclusiveCreateTXG{
CreateTXG: current.GetCreateTXG(),
Inclusive: &zfs.NilBool{B: false},
},
}
abs, absErr, err := ListAbstractions(ctx, q)
if err != nil {
return nil, errors.Wrap(err, "list abstractions")
}
if len(absErr) > 0 {
return nil, errors.Wrap(ListAbstractionsErrors(absErr), "list abstractions")
}
var destroyed []Abstraction
var errs []error
for res := range BatchDestroy(ctx, abs) {
log := getLogger(ctx).
WithField("replication_cursor_bookmark", res.Abstraction)
if res.DestroyErr != nil {
errs = append(errs, res.DestroyErr)
log.WithError(err).
Error("cannot destroy obsolete replication cursor bookmark")
} else {
destroyed = append(destroyed, res.Abstraction)
log.Info("destroyed obsolete replication cursor bookmark")
}
}
if len(errs) == 0 {
return destroyed, nil
} else {
return destroyed, errorarray.Wrap(errs, "destroy obsolete replication cursor")
}
}
var lastReceivedHoldTagRE = regexp.MustCompile("^zrepl_last_received_J_(.+)$")
// err != nil always means that the bookmark is not a step bookmark
func ParseLastReceivedHoldTag(tag string) (JobID, error) {
match := lastReceivedHoldTagRE.FindStringSubmatch(tag)
if match == nil {
return JobID{}, errors.Errorf("parse last-received-hold tag: does not match regex %s", lastReceivedHoldTagRE.String())
}
jobId, err := MakeJobID(match[1])
if err != nil {
return JobID{}, errors.Wrap(err, "parse last-received-hold tag: invalid job id field")
}
return jobId, nil
}
func LastReceivedHoldTag(jobID JobID) (string, error) {
return lastReceivedHoldImpl(jobID.String())
}
func lastReceivedHoldImpl(jobid string) (string, error) {
tag := fmt.Sprintf("zrepl_last_received_J_%s", jobid)
if err := zfs.ValidHoldTag(tag); err != nil {
return "", err
}
return tag, nil
}
func MoveLastReceivedHold(ctx context.Context, fs string, to zfs.FilesystemVersion, jobID JobID) error {
if to.IsSnapshot() {
return errors.Errorf("last-received-hold: target must be a snapshot: %s", to.FullPath(fs))
}
tag, err := LastReceivedHoldTag(jobID)
if err != nil {
return errors.Wrap(err, "last-received-hold: hold tag")
}
// we never want to be without a hold
// => hold new one before releasing old hold
err = zfs.ZFSHold(ctx, fs, to, tag)
if err != nil {
return errors.Wrap(err, "last-received-hold: hold newly received")
}
q := ListZFSHoldsAndBookmarksQuery{
What: AbstractionTypeSet{
AbstractionLastReceivedHold: true,
},
FS: ListZFSHoldsAndBookmarksQueryFilesystemFilter{
FS: &fs,
},
JobID: &jobID,
Until: &InclusiveExclusiveCreateTXG{
CreateTXG: to.GetCreateTXG(),
Inclusive: &zfs.NilBool{B: false},
},
}
abs, absErrs, err := ListAbstractions(ctx, q)
if err != nil {
return errors.Wrap(err, "last-received-hold: list")
}
if len(absErrs) > 0 {
return errors.Wrap(ListAbstractionsErrors(absErrs), "last-received-hold: list")
}
getLogger(ctx).WithField("last-received-holds", fmt.Sprintf("%s", abs)).Debug("releasing last-received-holds")
var errs []error
for res := range BatchDestroy(ctx, abs) {
log := getLogger(ctx).
WithField("last-received-hold", res.Abstraction)
if res.DestroyErr != nil {
errs = append(errs, res.DestroyErr)
log.WithError(err).
Error("cannot release last-received-hold")
} else {
log.Info("released last-received-hold")
}
}
if len(errs) == 0 {
return nil
} else {
return errorarray.Wrap(errs, "last-received-hold: release")
}
}
func ReplicationCursorV2Extractor(fs *zfs.DatasetPath, v zfs.FilesystemVersion) (_ Abstraction) {
if v.Type != zfs.Bookmark {
panic("impl error")
}
fullname := v.ToAbsPath(fs)
guid, jobid, err := ParseReplicationCursorBookmarkName(fullname)
if err == nil {
if guid != v.Guid {
// TODO log this possibly tinkered-with bookmark
return nil
}
return &ListHoldsAndBookmarksOutputBookmark{
Type: AbstractionReplicationCursorBookmarkV2,
FS: fs.ToString(),
FilesystemVersion: v,
JobID: jobid,
}
}
return nil
}
func ReplicationCursorV1Extractor(fs *zfs.DatasetPath, v zfs.FilesystemVersion) (_ Abstraction) {
if v.Type != zfs.Bookmark {
panic("impl error")
}
fullname := v.ToAbsPath(fs)
_, _, err := ParseReplicationCursorBookmarkName(fullname)
if err == ErrV1ReplicationCursor {
return &ReplicationCursorV1{
Type: AbstractionReplicationCursorBookmarkV1,
FS: fs.ToString(),
FilesystemVersion: v,
}
}
return nil
}
var _ HoldExtractor = LastReceivedHoldExtractor
func LastReceivedHoldExtractor(fs *zfs.DatasetPath, v zfs.FilesystemVersion, holdTag string) Abstraction {
var err error
if v.Type != zfs.Snapshot {
panic("impl error")
}
jobID, err := ParseLastReceivedHoldTag(holdTag)
if err == nil {
return &ListHoldsAndBookmarksOutputHold{
Type: AbstractionLastReceivedHold,
FS: fs.ToString(),
FilesystemVersion: v,
Tag: holdTag,
JobID: jobID,
}
}
return nil
}
type ReplicationCursorV1 struct {
Type AbstractionType
FS string
zfs.FilesystemVersion
}
func (c ReplicationCursorV1) GetType() AbstractionType { return c.Type }
func (c ReplicationCursorV1) GetFS() string { return c.FS }
func (c ReplicationCursorV1) GetFullPath() string { return fmt.Sprintf("%s#%s", c.FS, c.GetName()) }
func (c ReplicationCursorV1) GetJobID() *JobID { return nil }
func (c ReplicationCursorV1) GetFilesystemVersion() zfs.FilesystemVersion { return c.FilesystemVersion }
func (c ReplicationCursorV1) MarshalJSON() ([]byte, error) {
return json.Marshal(AbstractionJSON{c})
}
func (c ReplicationCursorV1) String() string {
return fmt.Sprintf("%s %s", c.Type, c.GetFullPath())
}
func (c ReplicationCursorV1) Destroy(ctx context.Context) error {
if err := zfs.ZFSDestroyIdempotent(c.GetFullPath()); err != nil {
return errors.Wrapf(err, "destroy %s %s: zfs", c.Type, c.GetFullPath())
}
return nil
}
+266
View File
@@ -0,0 +1,266 @@
package endpoint
import (
"context"
"fmt"
"regexp"
"github.com/pkg/errors"
"github.com/zrepl/zrepl/util/errorarray"
"github.com/zrepl/zrepl/zfs"
)
var stepHoldTagRE = regexp.MustCompile("^zrepl_STEP_J_(.+)")
func StepHoldTag(jobid JobID) (string, error) {
return stepHoldTagImpl(jobid.String())
}
func stepHoldTagImpl(jobid string) (string, error) {
t := fmt.Sprintf("zrepl_STEP_J_%s", jobid)
if err := zfs.ValidHoldTag(t); err != nil {
return "", err
}
return t, nil
}
// err != nil always means that the bookmark is not a step bookmark
func ParseStepHoldTag(tag string) (JobID, error) {
match := stepHoldTagRE.FindStringSubmatch(tag)
if match == nil {
return JobID{}, fmt.Errorf("parse hold tag: match regex %q", stepHoldTagRE)
}
jobID, err := MakeJobID(match[1])
if err != nil {
return JobID{}, errors.Wrap(err, "parse hold tag: invalid job id field")
}
return jobID, nil
}
const stepBookmarkNamePrefix = "zrepl_STEP"
// v must be validated by caller
func StepBookmarkName(fs string, guid uint64, id JobID) (string, error) {
return stepBookmarkNameImpl(fs, guid, id.String())
}
func stepBookmarkNameImpl(fs string, guid uint64, jobid string) (string, error) {
return makeJobAndGuidBookmarkName(stepBookmarkNamePrefix, fs, guid, jobid)
}
// name is the full bookmark name, including dataset path
//
// err != nil always means that the bookmark is not a step bookmark
func ParseStepBookmarkName(fullname string) (guid uint64, jobID JobID, err error) {
guid, jobID, err = parseJobAndGuidBookmarkName(fullname, stepBookmarkNamePrefix)
if err != nil {
err = errors.Wrap(err, "parse step bookmark name") // no shadow!
}
return guid, jobID, err
}
// idempotently hold / step-bookmark `version`
//
// returns ErrBookmarkCloningNotSupported if version is a bookmark and bookmarking bookmarks is not supported by ZFS
func HoldStep(ctx context.Context, fs string, v zfs.FilesystemVersion, jobID JobID) error {
if v.IsSnapshot() {
tag, err := StepHoldTag(jobID)
if err != nil {
return errors.Wrap(err, "step hold tag")
}
if err := zfs.ZFSHold(ctx, fs, v, tag); err != nil {
return errors.Wrap(err, "step hold: zfs")
}
return nil
}
if !v.IsBookmark() {
panic(fmt.Sprintf("version must bei either snapshot or bookmark, got %#v", v))
}
bmname, err := StepBookmarkName(fs, v.Guid, jobID)
if err != nil {
return errors.Wrap(err, "create step bookmark: determine bookmark name")
}
// idempotently create bookmark
err = zfs.ZFSBookmark(fs, v.ToSendArgVersion(), bmname)
if err != nil {
if err == zfs.ErrBookmarkCloningNotSupported {
// TODO we could actually try to find a local snapshot that has the requested GUID
// however, the replication algorithm prefers snapshots anyways, so this quest
// is most likely not going to be successful. Also, there's the possibility that
// the caller might want to filter what snapshots are eligibile, and this would
// complicate things even further.
return err // TODO go1.13 use wrapping
}
return errors.Wrap(err, "create step bookmark: zfs")
}
return nil
}
// idempotently release the step-hold on v if v is a snapshot
// or idempotently destroy the step-bookmark of v if v is a bookmark
//
// note that this operation leaves v itself untouched, unless v is the step-bookmark itself, in which case v is destroyed
//
// returns an instance of *zfs.DatasetDoesNotExist if `v` does not exist
func ReleaseStep(ctx context.Context, fs string, v zfs.FilesystemVersion, jobID JobID) error {
if v.IsSnapshot() {
tag, err := StepHoldTag(jobID)
if err != nil {
return errors.Wrap(err, "step release tag")
}
if err := zfs.ZFSRelease(ctx, tag, v.FullPath(fs)); err != nil {
return errors.Wrap(err, "step release: zfs")
}
return nil
}
if !v.IsBookmark() {
panic(fmt.Sprintf("impl error: expecting version to be a bookmark, got %#v", v))
}
bmname, err := StepBookmarkName(fs, v.Guid, jobID)
if err != nil {
return errors.Wrap(err, "step release: determine bookmark name")
}
// idempotently destroy bookmark
if err := zfs.ZFSDestroyIdempotent(bmname); err != nil {
return errors.Wrap(err, "step release: bookmark destroy: zfs")
}
return nil
}
// release {step holds, step bookmarks} earlier and including `mostRecent`
func ReleaseStepCummulativeInclusive(ctx context.Context, fs string, mostRecent zfs.FilesystemVersion, jobID JobID) error {
q := ListZFSHoldsAndBookmarksQuery{
What: AbstractionTypeSet{
AbstractionStepHold: true,
AbstractionStepBookmark: true,
},
FS: ListZFSHoldsAndBookmarksQueryFilesystemFilter{
FS: &fs,
},
JobID: &jobID,
Until: &InclusiveExclusiveCreateTXG{
CreateTXG: mostRecent.CreateTXG,
Inclusive: &zfs.NilBool{B: true},
},
}
abs, absErrs, err := ListAbstractions(ctx, q)
if err != nil {
return errors.Wrap(err, "step release cummulative: list")
}
if len(absErrs) > 0 {
return errors.Wrap(ListAbstractionsErrors(absErrs), "step release cummulative: list")
}
getLogger(ctx).WithField("step_holds_and_bookmarks", fmt.Sprintf("%s", abs)).Debug("releasing step holds and bookmarks")
var errs []error
for res := range BatchDestroy(ctx, abs) {
log := getLogger(ctx).
WithField("step_hold_or_bookmark", res.Abstraction)
if res.DestroyErr != nil {
errs = append(errs, res.DestroyErr)
log.WithError(err).
Error("cannot release step hold or bookmark")
} else {
log.Info("released step hold or bookmark")
}
}
if len(errs) == 0 {
return nil
} else {
return errorarray.Wrap(errs, "step release cummulative: release")
}
}
func TryReleaseStepStaleFS(ctx context.Context, fs string, jobID JobID) {
q := ListZFSHoldsAndBookmarksQuery{
FS: ListZFSHoldsAndBookmarksQueryFilesystemFilter{
FS: &fs,
},
JobID: &jobID,
What: AbstractionTypeSet{
AbstractionStepHold: true,
AbstractionStepBookmark: true,
},
}
staleness, err := ListStale(ctx, q)
if err != nil {
getLogger(ctx).WithError(err).Error("cannot list stale step holds and bookmarks")
return
}
for _, s := range staleness.Stale {
getLogger(ctx).WithField("stale_step_hold_or_bookmark", s).Info("batch-destroying stale step hold or bookmark")
}
for res := range BatchDestroy(ctx, staleness.Stale) {
if res.DestroyErr != nil {
getLogger(ctx).
WithField("stale_step_hold_or_bookmark", res.Abstraction).
WithError(res.DestroyErr).
Error("cannot destroy stale step-hold or bookmark")
} else {
getLogger(ctx).
WithField("stale_step_hold_or_bookmark", res.Abstraction).
WithError(res.DestroyErr).
Info("destroyed stale step-hold or bookmark")
}
}
}
var _ BookmarkExtractor = StepBookmarkExtractor
func StepBookmarkExtractor(fs *zfs.DatasetPath, v zfs.FilesystemVersion) (_ Abstraction) {
if v.Type != zfs.Bookmark {
panic("impl error")
}
fullname := v.ToAbsPath(fs)
guid, jobid, err := ParseStepBookmarkName(fullname)
if guid != v.Guid {
// TODO log this possibly tinkered-with bookmark
return nil
}
if err == nil {
bm := &ListHoldsAndBookmarksOutputBookmark{
Type: AbstractionStepBookmark,
FS: fs.ToString(),
FilesystemVersion: v,
JobID: jobid,
}
return bm
}
return nil
}
var _ HoldExtractor = StepHoldExtractor
func StepHoldExtractor(fs *zfs.DatasetPath, v zfs.FilesystemVersion, holdTag string) Abstraction {
if v.Type != zfs.Snapshot {
panic("impl error")
}
jobID, err := ParseStepHoldTag(holdTag)
if err == nil {
return &ListHoldsAndBookmarksOutputHold{
Type: AbstractionStepHold,
FS: fs.ToString(),
Tag: holdTag,
FilesystemVersion: v,
JobID: jobID,
}
}
return nil
}
@@ -1,7 +1,6 @@
package endpoint
import (
"context"
"fmt"
"regexp"
"strconv"
@@ -57,53 +56,3 @@ func parseJobAndGuidBookmarkName(fullname string, prefix string) (guid uint64, j
return guid, jobID, nil
}
func destroyBookmarksOlderThan(ctx context.Context, fs string, mostRecent *zfs.ZFSSendArgVersion, jobID JobID, filter func(shortname string) (accept bool)) (destroyed []zfs.FilesystemVersion, err error) {
if filter == nil {
panic(filter)
}
fsp, err := zfs.NewDatasetPath(fs)
if err != nil {
return nil, errors.Wrap(err, "invalid filesystem path")
}
mostRecentProps, err := mostRecent.ValidateExistsAndGetCheckedProps(ctx, fs)
if err != nil {
return nil, errors.Wrap(err, "validate most recent version argument")
}
stepBookmarks, err := zfs.ZFSListFilesystemVersions(fsp, zfs.FilterFromClosure(
func(t zfs.VersionType, name string) (accept bool, err error) {
if t != zfs.Bookmark {
return false, nil
}
return filter(name), nil
}))
if err != nil {
return nil, errors.Wrap(err, "list bookmarks")
}
// cut off all bookmarks prior to mostRecent's CreateTXG
var destroy []zfs.FilesystemVersion
for _, v := range stepBookmarks {
if v.Type != zfs.Bookmark {
panic("implementation error")
}
if !filter(v.Name) {
panic("inconsistent filter result")
}
if v.CreateTXG < mostRecentProps.CreateTXG {
destroy = append(destroy, v)
}
}
// FIXME use batch destroy, must adopt code to handle bookmarks
for _, v := range destroy {
if err := zfs.ZFSDestroyIdempotent(v.ToAbsPath(fsp)); err != nil {
return nil, errors.Wrap(err, "destroy bookmark")
}
}
return destroy, nil
}
+73
View File
@@ -0,0 +1,73 @@
package endpoint
import (
"context"
"encoding/json"
"fmt"
"github.com/pkg/errors"
"github.com/zrepl/zrepl/zfs"
)
type ListHoldsAndBookmarksOutputBookmark struct {
Type AbstractionType
FS string
zfs.FilesystemVersion
JobID JobID
}
func (b ListHoldsAndBookmarksOutputBookmark) GetType() AbstractionType { return b.Type }
func (b ListHoldsAndBookmarksOutputBookmark) GetFS() string { return b.FS }
func (b ListHoldsAndBookmarksOutputBookmark) GetJobID() *JobID { return &b.JobID }
func (b ListHoldsAndBookmarksOutputBookmark) GetFullPath() string {
return fmt.Sprintf("%s#%s", b.FS, b.Name) // TODO use zfs.FilesystemVersion.ToAbsPath
}
func (b ListHoldsAndBookmarksOutputBookmark) MarshalJSON() ([]byte, error) {
return json.Marshal(AbstractionJSON{b})
}
func (b ListHoldsAndBookmarksOutputBookmark) String() string {
return fmt.Sprintf("%s %s", b.Type, b.GetFullPath())
}
func (b ListHoldsAndBookmarksOutputBookmark) GetFilesystemVersion() zfs.FilesystemVersion {
return b.FilesystemVersion
}
func (b ListHoldsAndBookmarksOutputBookmark) Destroy(ctx context.Context) error {
if err := zfs.ZFSDestroyIdempotent(b.GetFullPath()); err != nil {
return errors.Wrapf(err, "destroy %s: zfs", b)
}
return nil
}
type ListHoldsAndBookmarksOutputHold struct {
Type AbstractionType
FS string
zfs.FilesystemVersion
Tag string
JobID JobID
}
func (h ListHoldsAndBookmarksOutputHold) GetType() AbstractionType { return h.Type }
func (h ListHoldsAndBookmarksOutputHold) GetFS() string { return h.FS }
func (h ListHoldsAndBookmarksOutputHold) GetJobID() *JobID { return &h.JobID }
func (h ListHoldsAndBookmarksOutputHold) GetFullPath() string {
return fmt.Sprintf("%s@%s", h.FS, h.GetName()) // TODO use zfs.FilesystemVersion.ToAbsPath
}
func (h ListHoldsAndBookmarksOutputHold) MarshalJSON() ([]byte, error) {
return json.Marshal(AbstractionJSON{h})
}
func (h ListHoldsAndBookmarksOutputHold) String() string {
return fmt.Sprintf("%s %q on %s", h.Type, h.Tag, h.GetFullPath())
}
func (h ListHoldsAndBookmarksOutputHold) GetFilesystemVersion() zfs.FilesystemVersion {
return h.FilesystemVersion
}
func (h ListHoldsAndBookmarksOutputHold) Destroy(ctx context.Context) error {
if err := zfs.ZFSRelease(ctx, h.Tag, h.GetFullPath()); err != nil {
return errors.Wrapf(err, "release %s: zfs", h)
}
return nil
}