mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-10 16:40:46 +02:00
Chris Lu
b3be2f5449
* filer.backup: key the checkpoint by source path and sink destination The checkpoint id hashed only sink name + directory, so two backups to different buckets or endpoints sharing a directory layout advanced one checkpoint: whichever job was running pushed the shared offset forward, and a stopped or failing job later resumed from the other's position, silently skipping changes. Backups of different source paths to the same destination shared a checkpoint the same way. Each sink now reports a destination identity (endpoint or account, bucket or container, directory) and the checkpoint is keyed by the source path plus that identity. Reads fall back to the historical name+directory key when the new key has no value, so existing backups resume where they left off; writes go only to the new key. * filer.sync: include the target path in the offset key The offset stored on the target filer was keyed by source path and source filer signature only, so two syncs from the same source cluster and path to different directories on the same target cluster advanced one shared checkpoint, and the slower one could resume past events it never applied. The target path now participates in the key; "/" keeps the historical form, and a sync with a non-root target path falls back to the historical key once when its own key has no value yet. * join checkpoint key fields with NUL so they cannot alias A path or configuration value spelling out the separator could concatenate two different field tuples to the same checkpoint key. NUL cannot appear in a CLI path argument or any sane configuration value, making the encoding injective.
38 lines
1.6 KiB
Go
38 lines
1.6 KiB
Go
package sink
|
|
|
|
import (
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/replication/source"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
)
|
|
|
|
type ReplicationSink interface {
|
|
GetName() string
|
|
Initialize(configuration util.Configuration, prefix string) error
|
|
DeleteEntry(key string, isDirectory, deleteIncludeChunks bool, signatures []int32) error
|
|
CreateEntry(key string, entry *filer_pb.Entry, signatures []int32) error
|
|
UpdateEntry(key string, oldEntry *filer_pb.Entry, newParentPath string, newEntry *filer_pb.Entry, deleteIncludeChunks bool, signatures []int32) (foundExistingEntry bool, err error)
|
|
GetSinkToDirectory() string
|
|
// GetDestinationIdentity distinguishes this sink's write destination from
|
|
// any other destination the same sink type could write to: endpoint or
|
|
// account, bucket or container, and directory. filer.backup keys its resume
|
|
// checkpoint on it, so two configurations writing to different places must
|
|
// not share a value.
|
|
GetDestinationIdentity() string
|
|
SetSourceFiler(s *source.FilerSource)
|
|
IsIncremental() bool
|
|
}
|
|
|
|
// EntryMover is an optional capability for sinks that can relocate an entry
|
|
// natively, in one atomic step, instead of create-then-delete. Drivers prefer
|
|
// it for a rename so a failed copy can never leave the source deleted with no
|
|
// committed destination, a directory move never deletes descendants before they
|
|
// are recreated, and the entry's chunks are neither re-copied nor leaked.
|
|
type EntryMover interface {
|
|
MoveEntry(oldKey, newKey string, newEntry *filer_pb.Entry, signatures []int32) error
|
|
}
|
|
|
|
var (
|
|
Sinks []ReplicationSink
|
|
)
|