mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-18 12:08:32 +02:00
shell: make every -collection flag parse the same way (#11794)
* shell: make every -collection flag parse the same way The filter vocabulary (comma-separated names, wildcards, regexes, "_default" for the empty-named collection) already existed in wildcard.CompileCollectionMatcher, but several commands still did their own exact-match comparison or sent the raw flag value to servers. fs.mergeVolumes used a literal string compare, so -collection=_default silently produced an empty merge plan; it now uses the shared matcher while keeping "*" as the match-all default. volume.fsck and volume.mark filter through the matcher too, and volume.vacuum resolves the filter client-side into per-collection and per-volume requests, since no Collection value scopes the VacuumVolume RPC to the unnamed collection alone. Commands that put one concrete collection name on the wire normalize "_default" to "" (volume.grow, fs.configure, mq.topic.compact, collection.delete, ec.rebuild, ec.balance), and the tier -volumeId commands resolve the volume's actual collection from topology first so patterns and named-collection requests pass the volume server's collection check. * shell: spell the default-collection keyword via CollectionDefault * shell: address review findings on collection filter handling volume.fsck keeps a set of every volume the master knows before any filtering, so a filer entry whose volume was excluded by -collection or -volumeId is skipped instead of reported "volume not found" and deleted by -reallyDeleteFilerEntries. The collection filter also no longer scopes the filer walk to /buckets/<collection>: fs.configure can bind a collection to any path prefix, and a narrower walk could mark live chunks as orphans under -reallyDeleteFromVolume. ec.rebuild and ec.balance resolve -collection through the new wildcard.ExpandCollectionFilter, which passes literal names through even when the master does not list them — ec.rebuild must be able to recover a collection whose shards all lost their index and never registered. fs.configure and mq.topic.compact now reject _default outright: an empty Collection means "unset" in both the path-rule merge and the filer's storage-option fallback chain, so the keyword would have been silently ignored. The unnamed-collection vacuum sweep keeps the master's low-disk-space exception: a volume whose every replica is read-only is probed with VacuumVolumeCheck and stays eligible when a replica reports DiskSpaceLow, instead of being dropped outright.
This commit is contained in:
1 parent
268424a5e1
commit
b0ab4c4e1e
23 files changed
+593
-71
No files matched your search
@@ -89,7 +89,7 @@ func (c *commandVolumeTierUpload) Do(args []string, commandEnv *CommandEnv, writ
|
||||
|
||||
tierCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
|
||||
volumeId := tierCommand.Int("volumeId", 0, "the volume id")
|
||||
collection := tierCommand.String("collection", "", "the collection name")
|
||||
collection := tierCommand.String("collection", "", "comma-separated collection names, wildcards, or regex patterns; empty matches the collection with no name")
|
||||
fullPercentage := tierCommand.Float64("fullPercent", 95, "the volume reaches the percentage of max volume size")
|
||||
quietPeriod := tierCommand.Duration("quietFor", 24*time.Hour, "select volumes without no writes for this period")
|
||||
dest := tierCommand.String("dest", "", "the target tier name")
|
||||
@@ -137,20 +137,30 @@ func (c *commandVolumeTierUpload) Do(args []string, commandEnv *CommandEnv, writ
|
||||
return nil
|
||||
}
|
||||
|
||||
func doVolumeTierUpload(commandEnv *CommandEnv, writer io.Writer, collection string, vid needle.VolumeId, dest string, keepLocalDatFile bool, concurrency int) (err error) {
|
||||
func doVolumeTierUpload(commandEnv *CommandEnv, writer io.Writer, collectionPattern string, vid needle.VolumeId, dest string, keepLocalDatFile bool, concurrency int) (err error) {
|
||||
// find volume location
|
||||
topoInfo, _, err := collectTopologyInfo(commandEnv, 0)
|
||||
if err != nil {
|
||||
return fmt.Errorf("collect topology info: %v", err)
|
||||
}
|
||||
|
||||
// The volume server verifies the request's collection against the volume's
|
||||
// own, so the pattern must resolve to the actual collection here.
|
||||
collection, found, err := findVolumeCollection(topoInfo, vid, collectionPattern)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if !found {
|
||||
if collectionPattern == "" {
|
||||
return fmt.Errorf("volume %d not found", vid)
|
||||
}
|
||||
return fmt.Errorf("volume %d not found in collections matching %s", vid, collectionPattern)
|
||||
}
|
||||
|
||||
existingLocations := collectVolumeTierUploadLocations(topoInfo, vid, collection, writer)
|
||||
|
||||
if len(existingLocations) == 0 {
|
||||
if collection == "" {
|
||||
return fmt.Errorf("volume %d not found", vid)
|
||||
}
|
||||
return fmt.Errorf("volume %d not found in collection %s", vid, collection)
|
||||
return fmt.Errorf("volume %d has no replicas in collection %s", vid, collection)
|
||||
}
|
||||
|
||||
_, err = markVolumeReplicasWritable(context.Background(), commandEnv.option.GrpcDialOption, vid, existingLocations, false, false)
|
||||
@@ -192,7 +202,7 @@ func collectVolumeTierUploadLocations(topoInfo *master_pb.TopologyInfo, vid need
|
||||
eachDataNode(topoInfo, func(dc DataCenterId, rack RackId, dn *master_pb.DataNodeInfo) {
|
||||
for _, disk := range dn.DiskInfos {
|
||||
for _, vi := range disk.VolumeInfos {
|
||||
if needle.VolumeId(vi.Id) == vid && (collection == "" || vi.Collection == collection) {
|
||||
if needle.VolumeId(vi.Id) == vid && vi.Collection == collection {
|
||||
fmt.Fprintf(writer, "find volume %d from Url:%s, GrpcPort:%d, DC:%s\n", vid, dn.Id, dn.GrpcPort, string(dc))
|
||||
loc := wdclient.Location{
|
||||
Url: dn.Id,
|
||||
|
||||
Reference in new issue
Block a user