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.

weed/shell/command_collection_delete.go

@@ -35,7 +35,7 @@ func (c *commandCollectionDelete) HasTag(CommandTag) bool {
 func (c *commandCollectionDelete) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
 
 	colDeleteCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
-	collectionName := colDeleteCommand.String("collection", "", "collection to delete. Use '_default_' for the empty-named collection.")
+	collectionName := colDeleteCommand.String("collection", "", "collection to delete. Use '"+CollectionDefault+"' for the empty-named collection.")
 	applyBalancing := colDeleteCommand.Bool("apply", false, "apply the collection")
 	// TODO: remove this alias
 	applyBalancingAlias := colDeleteCommand.Bool("force", false, "apply the collection (alias for -apply)")
@@ -55,9 +55,13 @@ func (c *commandCollectionDelete) Do(args []string, commandEnv *CommandEnv, writ
 		return fmt.Errorf("empty collection name is not allowed")
 	}
 
-	if *collectionName == "_default_" {
+	// The legacy "_default_" spelling stays accepted for compatibility;
+	// CollectionDefault is the shared keyword every other -collection flag
+	// uses for the empty-named collection.
+	if *collectionName == CollectionDefault+"_" {
 		*collectionName = ""
 	}
+	*collectionName = resolveCollectionName(*collectionName)
 
 	if !*applyBalancing {
 		fmt.Fprintf(writer, "collection '%s' will be deleted. Use -apply to apply the change.\n", *collectionName)

weed/shell/command_ec_balance.go

@@ -7,6 +7,7 @@ import (
 	"github.com/seaweedfs/seaweedfs/weed/glog"
 	"github.com/seaweedfs/seaweedfs/weed/storage/needle"
 	"github.com/seaweedfs/seaweedfs/weed/storage/types"
+	"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
 )
 
 func init() {
@@ -42,7 +43,7 @@ func (c *commandEcBalance) HasTag(CommandTag) bool {
 
 func (c *commandEcBalance) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
 	balanceCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
-	collection := balanceCommand.String("collection", "EACH_COLLECTION", "collection name, or \"EACH_COLLECTION\" for each collection")
+	collection := balanceCommand.String("collection", string(wildcard.CollectionFilterEach), "comma-separated collection names, wildcards, or regex patterns, \""+CollectionDefault+"\" for the collection with no name, or \""+string(wildcard.CollectionFilterEach)+"\" for each collection")
 	dc := balanceCommand.String("dataCenter", "", "only apply the balancing for this dataCenter")
 	shardReplicaPlacement := balanceCommand.String("shardReplicaPlacement", "", "replica placement for EC shards, or master default if empty")
 	diskTypeStr := balanceCommand.String("diskType", "", "the disk type for EC shards (hdd, ssd, or empty for default hdd)")
@@ -71,14 +72,9 @@ func (c *commandEcBalance) Do(args []string, commandEnv *CommandEnv, writer io.W
 		return
 	}
 
-	var collections []string
-	if *collection == "EACH_COLLECTION" {
-		collections, err = ListCollectionNames(commandEnv, false, true)
-		if err != nil {
-			return err
-		}
-	} else {
-		collections = append(collections, *collection)
+	collections, err := resolveEcCollections(commandEnv, *collection)
+	if err != nil {
+		return err
 	}
 	glog.V(1).Infof("balanceEcVolumes collections %+v\n", len(collections))
 

weed/shell/command_ec_common.go

@@ -2,6 +2,7 @@ package shell
 
 import (
 	"context"
+	"fmt"
 	"strings"
 	"time"
 
@@ -142,13 +143,37 @@ func EcBalance(commandEnv *CommandEnv, collections []string, dc string, ecReplic
 	return ec.EcBalance(commandEnv.ecEnv(), collections, dc, ecReplicaPlacement, diskType, maxParallelization, ioBytePerSecond, applyBalancing, excludeNodes, volumeIds, nil)
 }
 
-// compileCollectionPattern compiles the -collection value shared by the ec and
-// tier commands: a comma-separated list of collection names, wildcards, and
-// regex patterns. An empty value matches the empty-named collection only, the
-// same as CollectionDefault.
+// compileCollectionPattern compiles the -collection value shared by commands
+// where an empty value means the collection with no name: a comma-separated
+// list of collection names, wildcards, and regex patterns, or CollectionDefault
+// for the empty-named collection.
 func compileCollectionPattern(pattern string) (*wildcard.CollectionMatcher, error) {
 	if strings.TrimSpace(pattern) == "" {
 		pattern = CollectionDefault
 	}
 	return wildcard.CompileCollectionMatcher(pattern)
 }
+
+// resolveEcCollections expands the ec commands' -collection value into
+// collection names. An empty value means the empty-named collection, the same
+// as CollectionDefault. Literal names pass through even when the master does
+// not list them — the listing only contains collections with registered
+// volumes, and ec.rebuild exists to bring back a collection whose volumes all
+// lost their index. Wildcard and regex entries resolve against the listing.
+func resolveEcCollections(commandEnv *CommandEnv, filter string) (collections []string, err error) {
+	if strings.TrimSpace(filter) == "" {
+		filter = CollectionDefault
+	}
+	names, err := ListCollectionNames(commandEnv, false, true)
+	if err != nil {
+		return nil, err
+	}
+	collections, err = wildcard.ExpandCollectionFilter(filter, names)
+	if err != nil {
+		return nil, fmt.Errorf("invalid collection pattern %q: %w", filter, err)
+	}
+	if len(collections) == 0 {
+		return nil, fmt.Errorf("no collections match %q", filter)
+	}
+	return collections, nil
+}

weed/shell/command_ec_common_test.go

@@ -14,7 +14,7 @@ func TestCompileCollectionPattern(t *testing.T) {
 		{pattern: CollectionDefault, matches: []string{""}, misses: []string{"pictures"}},
 		{pattern: "pictures", matches: []string{"pictures"}, misses: []string{"", "pictures-backup"}},
 		{pattern: "pictures,videos", matches: []string{"pictures", "videos"}, misses: []string{"", "clips"}},
-		{pattern: "pictures,_default", matches: []string{"pictures", ""}, misses: []string{"clips"}},
+		{pattern: "pictures," + CollectionDefault, matches: []string{"pictures", ""}, misses: []string{"clips"}},
 		{pattern: "pictures*", matches: []string{"pictures", "pictures-backup"}, misses: []string{"clips"}},
 		{pattern: "^pictures", matches: []string{"pictures", "pictures-backup"}, misses: []string{"clips"}},
 		{pattern: "*", matches: []string{"", "pictures"}},

weed/shell/command_ec_encode.go

@@ -62,7 +62,7 @@ func (c *commandEcEncode) Help() string {
 	  - Several collections: ec.encode -collection="mybucket,otherbucket"
 	  - Match by prefix: ec.encode -collection="bucket*"
 	  - Match all collections: ec.encode -collection="*"
-	  - The empty-named collection: ec.encode -collection="_default"
+	  - The empty-named collection: ec.encode -collection="` + CollectionDefault + `"
 
 	Options:
 	  -verbose: show detailed reasons why volumes are not selected for encoding

weed/shell/command_ec_rebuild.go

@@ -10,6 +10,7 @@ import (
 	"github.com/seaweedfs/seaweedfs/weed/ec"
 	"github.com/seaweedfs/seaweedfs/weed/storage/needle"
 	"github.com/seaweedfs/seaweedfs/weed/storage/types"
+	"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
 )
 
 func init() {
@@ -73,7 +74,7 @@ func (c *commandEcRebuild) HasTag(CommandTag) bool {
 func (c *commandEcRebuild) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
 
 	fixCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
-	collection := fixCommand.String("collection", "EACH_COLLECTION", "collection name, or \"EACH_COLLECTION\" for each collection")
+	collection := fixCommand.String("collection", string(wildcard.CollectionFilterEach), "comma-separated collection names, wildcards, or regex patterns, \""+CollectionDefault+"\" for the collection with no name, or \""+string(wildcard.CollectionFilterEach)+"\" for each collection")
 	volumeIdsStr := fixCommand.String("volumeIds", "", "optional comma-separated list of volume ID to process; defaults to all volumes in the collection")
 	maxParallelization := fixCommand.Int("maxParallelization", DefaultMaxParallelization, "run up to X tasks in parallel, whenever possible")
 	applyChanges := fixCommand.Bool("apply", false, "apply the changes")
@@ -98,14 +99,9 @@ func (c *commandEcRebuild) Do(args []string, commandEnv *CommandEnv, writer io.W
 		return err
 	}
 
-	var collections []string
-	if *collection == "EACH_COLLECTION" {
-		collections, err = ListCollectionNames(commandEnv, false, true)
-		if err != nil {
-			return err
-		}
-	} else {
-		collections = []string{*collection}
+	collections, err := resolveEcCollections(commandEnv, *collection)
+	if err != nil {
+		return err
 	}
 
 	var volumeIds []needle.VolumeId

weed/shell/command_fs_configure.go

@@ -90,6 +90,12 @@ func (c *commandFsConfigure) Do(args []string, commandEnv *CommandEnv, writer io
 
 	if *locationPrefix != "" {
 		infoAboutSimulationMode(writer, *apply, "-apply")
+		// A path rule cannot express "the collection with no name": an empty
+		// Collection means "unset" and merges as inherit, so the keyword would
+		// be silently ignored.
+		if *collection == CollectionDefault {
+			return fmt.Errorf("path rules cannot select the collection with no name; omit -collection to inherit")
+		}
 		locConf := &filer_pb.FilerConf_PathConf{
 			LocationPrefix:           *locationPrefix,
 			Collection:               *collection,

weed/shell/command_fs_merge_volumes.go

@@ -18,6 +18,7 @@ import (
 	"github.com/seaweedfs/seaweedfs/weed/filer"
 	"github.com/seaweedfs/seaweedfs/weed/security"
 	"github.com/seaweedfs/seaweedfs/weed/storage/needle"
+	"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
 	"github.com/seaweedfs/seaweedfs/weed/wdclient"
 	"golang.org/x/exp/maps"
 	"google.golang.org/protobuf/proto"
@@ -66,7 +67,7 @@ func (c *commandFsMergeVolumes) Do(args []string, commandEnv *CommandEnv, writer
 	dirArg := fsMergeVolumesCommand.String("dir", "/", "base directory to find and update files")
 	fromVolumeArg := fsMergeVolumesCommand.Uint("fromVolumeId", 0, "move chunks with this volume id")
 	toVolumeArg := fsMergeVolumesCommand.String("toVolumeId", "", "change chunks to this volume id, or distribute across a comma-separated list of volume ids")
-	collectionArg := fsMergeVolumesCommand.String("collection", "*", "Name of collection to merge")
+	collectionArg := fsMergeVolumesCommand.String("collection", "*", "comma-separated collection names, wildcards, or regex patterns; \""+CollectionDefault+"\" for the collection with no name")
 	apply := fsMergeVolumesCommand.Bool("apply", false, "applying the metadata changes")
 	if err = fsMergeVolumesCommand.Parse(args); err != nil {
 		return err
@@ -532,12 +533,17 @@ func parseTargetVolumeIds(arg string) ([]needle.VolumeId, error) {
 }
 
 func (c *commandFsMergeVolumes) createMergePlan(collection string, toVolumeIds []needle.VolumeId, fromVolumeId needle.VolumeId) (*mergePlan, error) {
+	collectionMatcher, err := compileCollectionPattern(collection)
+	if err != nil {
+		return nil, fmt.Errorf("invalid collection pattern %q: %w", collection, err)
+	}
+
 	// When the user names both endpoints, honor that exact direction. The
 	// heuristic below only ever merges a smaller volume into a larger one, so
 	// an explicit "merge larger into smaller" request would otherwise yield an
 	// empty plan and silently do nothing.
 	if fromVolumeId != 0 && len(toVolumeIds) > 0 {
-		return c.createDirectedMergePlan(collection, fromVolumeId, toVolumeIds)
+		return c.createDirectedMergePlan(collectionMatcher, collection, fromVolumeId, toVolumeIds)
 	}
 
 	plan := newMergePlan(c.volumeSizeLimit)
@@ -549,7 +555,7 @@ func (c *commandFsMergeVolumes) createMergePlan(collection string, toVolumeIds [
 	l := len(volumeIds)
 	for i := 0; i < l; i++ {
 		volume := c.volumes[volumeIds[i]]
-		if volume.GetReadOnly() || c.getVolumeSize(volume) == 0 || (collection != "*" && collection != volume.GetCollection()) {
+		if volume.GetReadOnly() || c.getVolumeSize(volume) == 0 || !collectionMatcher.Matches(volume.GetCollection()) {
 
 			if fromVolumeId != 0 && volumeIds[i] == fromVolumeId || slices.Contains(toVolumeIds, volumeIds[i]) {
 				if volume.GetReadOnly() {
@@ -607,7 +613,7 @@ func (c *commandFsMergeVolumes) createMergePlan(collection string, toVolumeIds [
 
 // createDirectedMergePlan honors the exact direction the user named, skipping
 // the heuristic planner's smaller-into-larger ordering.
-func (c *commandFsMergeVolumes) createDirectedMergePlan(collection string, from needle.VolumeId, toIds []needle.VolumeId) (*mergePlan, error) {
+func (c *commandFsMergeVolumes) createDirectedMergePlan(collectionMatcher *wildcard.CollectionMatcher, collection string, from needle.VolumeId, toIds []needle.VolumeId) (*mergePlan, error) {
 	if slices.Contains(toIds, from) {
 		return nil, fmt.Errorf("no volume id changes, %d is both source and target", from)
 	}
@@ -619,8 +625,8 @@ func (c *commandFsMergeVolumes) createDirectedMergePlan(collection string, from
 		if volume.GetReadOnly() {
 			return nil, fmt.Errorf("volume %d is readonly", vid)
 		}
-		if collection != "*" && collection != volume.GetCollection() {
-			return nil, fmt.Errorf("volume %d is not in collection %q", vid, collection)
+		if !collectionMatcher.Matches(volume.GetCollection()) {
+			return nil, fmt.Errorf("volume %d does not match collection filter %q", vid, collection)
 		}
 		// Merging into an empty target is valid (e.g. a freshly vacuumed
 		// volume); only an empty source has nothing to move.

weed/shell/command_fs_merge_volumes_test.go

@@ -108,7 +108,7 @@ func TestCreateMergePlan_DirectedRejectsIneligible(t *testing.T) {
 			from:    &master_pb.VolumeInformationMessage{Id: 87, Size: 100, Collection: "other"},
 			to:      &master_pb.VolumeInformationMessage{Id: 83, Size: 100, Collection: "other"},
 			coll:    "wanted",
-			wantErr: "volume 87 is not in collection",
+			wantErr: "volume 87 does not match collection filter",
 		},
 	}
 	for _, tc := range cases {
@@ -233,6 +233,54 @@ func TestParseTargetVolumeIds(t *testing.T) {
 	}
 }
 
+// The collection filter speaks the shared vocabulary: "_default" selects the
+// empty-named collection, a name or pattern only its matches, and "*" (or no
+// flag) every collection.
+func TestCreateMergePlan_CollectionFilter(t *testing.T) {
+	mb := uint64(1024 * 1024)
+	mk := func(id uint32, sizeMB uint64, collection string) *master_pb.VolumeInformationMessage {
+		return &master_pb.VolumeInformationMessage{Id: id, Size: sizeMB * mb, Collection: collection}
+	}
+	newCmd := func() *commandFsMergeVolumes {
+		return newMergeCmd(250000, mk(1, 10, ""), mk(2, 80, ""), mk(3, 10, "x"), mk(4, 80, "x"))
+	}
+
+	// "_default" merges only the unnamed-collection volumes.
+	plan, err := newCmd().createMergePlan(CollectionDefault, nil, 0)
+	if err != nil {
+		t.Fatalf("%s: %v", CollectionDefault, err)
+	}
+	if got := plan.targets[needle.VolumeId(1)]; len(got) != 1 || got[0] != needle.VolumeId(2) {
+		t.Fatalf("expected 1->2, got %v", plan.targets)
+	}
+	if plan.isSource(needle.VolumeId(3)) {
+		t.Fatalf("named-collection volume must not merge under _default, got %v", plan.targets)
+	}
+
+	// A literal name still selects its collection.
+	plan, err = newCmd().createMergePlan("x", nil, 0)
+	if err != nil {
+		t.Fatalf("x: %v", err)
+	}
+	if got := plan.targets[needle.VolumeId(3)]; len(got) != 1 || got[0] != needle.VolumeId(4) {
+		t.Fatalf("expected 3->4, got %v", plan.targets)
+	}
+	if plan.isSource(needle.VolumeId(1)) {
+		t.Fatalf("unnamed volume must not merge under x, got %v", plan.targets)
+	}
+
+	// "*" keeps covering every collection.
+	plan, err = newCmd().createMergePlan("*", nil, 0)
+	if err != nil {
+		t.Fatalf("*: %v", err)
+	}
+	for src, dest := range map[needle.VolumeId]needle.VolumeId{1: 2, 3: 4} {
+		if got := plan.targets[src]; len(got) != 1 || got[0] != dest {
+			t.Fatalf("expected %d->%d, got %v", src, dest, plan.targets)
+		}
+	}
+}
+
 // A volume reporting more deleted bytes than it holds must read as empty.
 func TestGetVolumeSize_ClampsDeletedOverSize(t *testing.T) {
 	c := newMergeCmd(250000)

weed/shell/command_mq_topic_compact.go

@@ -2,6 +2,7 @@ package shell
 
 import (
 	"flag"
+	"fmt"
 	"io"
 	"time"
 
@@ -55,6 +56,13 @@ func (c *commandMqTopicCompact) Do(args []string, commandEnv *CommandEnv, writer
 		return err
 	}
 
+	// The AssignVolumeRequest collection falls back to the path rule and the
+	// filer default when empty, so the empty-named collection cannot be
+	// requested explicitly.
+	if *collection == CollectionDefault {
+		return fmt.Errorf("%s is not a usable collection name here; omit -collection to inherit the configured collection", CollectionDefault)
+	}
+
 	storagePreference := &operation.StoragePreference{
 		Replication: *replication,
 		Collection:  *collection,

weed/shell/command_volume_fsck.go

@@ -34,6 +34,7 @@ import (
 	"github.com/seaweedfs/seaweedfs/weed/storage/types"
 	"github.com/seaweedfs/seaweedfs/weed/util"
 	util_http "github.com/seaweedfs/seaweedfs/weed/util/http"
+	"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
 	"golang.org/x/sync/errgroup"
 )
 
@@ -55,6 +56,8 @@ type commandVolumeFsck struct {
 	writer                    io.Writer
 	bucketsPath               string
 	collection                *string
+	collectionMatcher         *wildcard.CollectionMatcher
+	knownVolumeIds            map[uint32]bool
 	volumeIds                 map[uint32]bool
 	scopedFilerPath           string
 	tempFolder                string
@@ -109,7 +112,7 @@ func (c *commandVolumeFsck) Do(args []string, commandEnv *CommandEnv, writer io.
 	c.verbose = fsckCommand.Bool("v", false, "verbose mode")
 	c.skipEcVolumes = fsckCommand.Bool("skipEcVolumes", false, "skip erasure coded volumes")
 	c.findMissingChunksInFiler = fsckCommand.Bool("findMissingChunksInFiler", false, "see \"help volume.fsck\"")
-	c.collection = fsckCommand.String("collection", "", "the collection name")
+	c.collection = fsckCommand.String("collection", "", "comma-separated collection names, wildcards, or regex patterns; empty or \"*\" matches all, \""+CollectionDefault+"\" the collection with no name")
 	volumeIds := fsckCommand.String("volumeId", "", "comma separated the volume id")
 	applyPurging := fsckCommand.Bool("reallyDeleteFromVolume", false, "<expert only!> after detection, delete missing data from volumes / delete missing file entries from filer. Currently this only works with default filerGroup.")
 	c.forcePurging = fsckCommand.Bool("forcePurging", false, "delete missing data from volumes in one replica used together with applyPurging")
@@ -147,6 +150,10 @@ func (c *commandVolumeFsck) Do(args []string, commandEnv *CommandEnv, writer io.
 	c.env = commandEnv
 	c.writer = writer
 
+	if c.collectionMatcher, err = wildcard.CompileCollectionMatcher(*c.collection); err != nil {
+		return fmt.Errorf("invalid collection pattern %q: %w", *c.collection, err)
+	}
+
 	c.bucketsPath, err = readFilerBucketsPath(commandEnv)
 	if err != nil {
 		return fmt.Errorf("read filer buckets path: %w", err)
@@ -170,6 +177,16 @@ func (c *commandVolumeFsck) Do(args []string, commandEnv *CommandEnv, writer io.
 		return fmt.Errorf("failed to collect all volume locations: %w", err)
 	}
 
+	// Every volume the master knows about, before any filtering: a filer
+	// entry pointing at a volume that was filtered out of this run is
+	// excluded, not missing — it must never be reported or purged.
+	c.knownVolumeIds = make(map[uint32]bool)
+	for _, vidMap := range dataNodeVolumeIdToVInfo {
+		for vid := range vidMap {
+			c.knownVolumeIds[vid] = true
+		}
+	}
+
 	// If the operator specified -volumeId, reject unknown ids up front instead
 	// of silently filtering them out and reporting "no orphan data". A silent
 	// success on a missing volume looks identical to a clean volume and hides
@@ -222,7 +239,7 @@ func (c *commandVolumeFsck) Do(args []string, commandEnv *CommandEnv, writer io.
 						continue
 					}
 				}
-				if *c.collection != "" && vinfo.collection != *c.collection {
+				if !c.collectionMatcher.Matches(vinfo.collection) {
 					delete(volumeIdToVInfo, volumeId)
 					continue
 				}
@@ -375,6 +392,11 @@ func (c *commandVolumeFsck) collectFilerFileIdAndPaths(dataNodeVolumeIdToVInfo m
 							continue
 						}
 					}
+					// A volume the master knows but this run filtered out is not a
+					// missing volume: its files are healthy and stay untouched.
+					if c.knownVolumeIds[i.vid] {
+						continue
+					}
 					fmt.Fprintf(c.writer, "%d,%x%08x %s volume not found\n", i.vid, i.fileKey, i.cookie, i.path)
 					if purgeAbsent {
 						fmt.Fprintf(c.writer, "deleting path %s after volume not found\n", i.path)
@@ -966,7 +988,11 @@ func (c *commandVolumeFsck) getCollectFilerFilePath() string {
 
 func (c *commandVolumeFsck) resolveScopedFilerPath(dataNodeVolumeIdToVInfo map[string]map[uint32]VInfo) string {
 	if *c.collection != "" {
-		return fmt.Sprintf("%s/%s", c.bucketsPath, *c.collection)
+		// fs.configure can bind a collection to any path prefix, so files
+		// referencing the filtered volumes may live anywhere. A bucket-dir
+		// walk could miss them and report their live chunks as orphans;
+		// only a full walk is safe for a collection filter.
+		return "/"
 	}
 	if len(c.volumeIds) == 0 {
 		return "/"

weed/shell/command_volume_grow.go

@@ -39,7 +39,7 @@ func (c *commandGrow) Do(args []string, commandEnv *CommandEnv, writer io.Writer
 
 	volumeVacuumCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
 	growCount := volumeVacuumCommand.Uint("count", 2, "")
-	collection := volumeVacuumCommand.String("collection", "", "grow this collection")
+	collection := volumeVacuumCommand.String("collection", "", "grow this collection; \""+CollectionDefault+"\" for the collection with no name")
 	dataCenter := volumeVacuumCommand.String("dataCenter", "", "grow volumes only from the specified data center")
 	rack := volumeVacuumCommand.String("rack", "", "grow volumes only from the specified rack")
 	dataNode := volumeVacuumCommand.String("dataNode", "", "grow volumes only from the specified data node")
@@ -51,6 +51,7 @@ func (c *commandGrow) Do(args []string, commandEnv *CommandEnv, writer io.Writer
 	if *collection == "" {
 		return fmt.Errorf("collection option is required")
 	}
+	*collection = resolveCollectionName(*collection)
 	t, _, err := collectTopologyInfo(commandEnv, 0)
 	if err != nil {
 		return err

weed/shell/command_volume_mark.go

@@ -9,6 +9,7 @@ import (
 
 	"github.com/seaweedfs/seaweedfs/weed/pb"
 	"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
+	"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
 
 	"github.com/seaweedfs/seaweedfs/weed/storage/needle"
 )
@@ -47,7 +48,7 @@ func (c *commandVolumeMark) Do(args []string, commandEnv *CommandEnv, writer io.
 	volMarkCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
 	volumeIdInt := volMarkCommand.Int("volumeId", 0, "the volume id")
 	nodeStr := volMarkCommand.String("node", "", "the volume server <host>:<port>")
-	collection := volMarkCommand.String("collection", "", "the collection name")
+	collection := volMarkCommand.String("collection", "", "comma-separated collection names, wildcards, or regex patterns; \""+CollectionDefault+"\" for the collection with no name")
 	writable := volMarkCommand.Bool("writable", false, "volume mark writable")
 	readonly := volMarkCommand.Bool("readonly", false, "volume mark readonly")
 	readonlyCanDelete := volMarkCommand.Bool("readonlyCanDelete", false, "volume mark readonly but still accepting deletes")
@@ -137,11 +138,9 @@ func collectVolumeMarkTargetsByCollection(topoInfo *master_pb.TopologyInfo, coll
 	if collection == "" {
 		return nil, fmt.Errorf("collection is required")
 	}
-
-	// _default targets volumes that belong to no named collection.
-	matchCollection := collection
-	if matchCollection == CollectionDefault {
-		matchCollection = ""
+	collectionMatcher, err := wildcard.CompileCollectionMatcher(collection)
+	if err != nil {
+		return nil, fmt.Errorf("invalid collection pattern %q: %w", collection, err)
 	}
 
 	var targets []volumeMarkTarget
@@ -152,7 +151,7 @@ func collectVolumeMarkTargetsByCollection(topoInfo *master_pb.TopologyInfo, coll
 		sourceVolumeServer := pb.NewServerAddressFromDataNode(dn)
 		for _, diskInfo := range dn.GetDiskInfos() {
 			for _, v := range diskInfo.GetVolumeInfos() {
-				if v.GetCollection() == matchCollection {
+				if collectionMatcher.Matches(v.GetCollection()) {
 					targets = append(targets, volumeMarkTarget{
 						volumeId:           needle.VolumeId(v.GetId()),
 						sourceVolumeServer: sourceVolumeServer,
@@ -162,7 +161,7 @@ func collectVolumeMarkTargetsByCollection(topoInfo *master_pb.TopologyInfo, coll
 		}
 	})
 	if len(targets) == 0 {
-		return nil, fmt.Errorf("collection %s has no volumes", collection)
+		return nil, fmt.Errorf("no volumes match collection %s", collection)
 	}
 	return targets, nil
 }

weed/shell/command_volume_mark_test.go

@@ -122,7 +122,7 @@ func TestCollectVolumeMarkTargetsByCollectionRejectsEmptyCollection(t *testing.T
 
 func TestCollectVolumeMarkTargetsByCollectionReportsMissingCollection(t *testing.T) {
 	_, err := collectVolumeMarkTargetsByCollection(&master_pb.TopologyInfo{}, "missing")
-	if err == nil || !strings.Contains(err.Error(), "collection missing has no volumes") {
+	if err == nil || !strings.Contains(err.Error(), "no volumes match collection missing") {
 		t.Fatalf("expected missing collection error, got %v", err)
 	}
 }

weed/shell/command_volume_tier_compact.go

@@ -126,6 +126,39 @@ func (c *commandVolumeTierCompact) Do(args []string, commandEnv *CommandEnv, wri
 	return nil
 }
 
+// findVolumeCollection resolves the collection a volume actually lives in,
+// honoring the -collection filter: an empty pattern matches any collection, a
+// non-empty one compiles like the rest of the tier commands. The volume server
+// verifies the collection name on tier requests, so callers need the real
+// name, not the pattern.
+func findVolumeCollection(topoInfo *master_pb.TopologyInfo, vid needle.VolumeId, collectionPattern string) (collection string, found bool, err error) {
+	var matchesCollection func(string) bool
+	if collectionPattern != "" {
+		collectionMatcher, compileErr := compileCollectionPattern(collectionPattern)
+		if compileErr != nil {
+			return "", false, fmt.Errorf("invalid collection pattern '%s': %v", collectionPattern, compileErr)
+		}
+		matchesCollection = collectionMatcher.Matches
+	} else {
+		matchesCollection = func(string) bool { return true }
+	}
+
+	eachDataNode(topoInfo, func(dc DataCenterId, rack RackId, dn *master_pb.DataNodeInfo) {
+		if found {
+			return
+		}
+		for _, diskInfo := range dn.DiskInfos {
+			for _, v := range diskInfo.VolumeInfos {
+				if needle.VolumeId(v.Id) == vid && matchesCollection(v.Collection) {
+					collection, found = v.Collection, true
+					return
+				}
+			}
+		}
+	})
+	return
+}
+
 func findRemoteVolumeInTopology(topoInfo *master_pb.TopologyInfo, vid needle.VolumeId, collectionPattern string) (remoteVolumeInfo, bool, error) {
 	var matchesCollection func(string) bool
 	if collectionPattern != "" {

weed/shell/command_volume_tier_download.go

@@ -80,7 +80,7 @@ func (c *commandVolumeTierDownload) Do(args []string, commandEnv *CommandEnv, wr
 
 	// volumeId is provided
 	if vid != 0 {
-		return doVolumeTierDownload(commandEnv, writer, *collection, vid, *concurrency)
+		return doVolumeTierDownload(commandEnv, writer, topologyInfo, *collection, vid, *concurrency)
 	}
 
 	// apply to all volumes in the collection
@@ -91,7 +91,7 @@ func (c *commandVolumeTierDownload) Do(args []string, commandEnv *CommandEnv, wr
 	}
 	fmt.Printf("tier download volumes: %v\n", volumeIds)
 	for _, vid := range volumeIds {
-		if err = doVolumeTierDownload(commandEnv, writer, *collection, vid, *concurrency); err != nil {
+		if err = doVolumeTierDownload(commandEnv, writer, topologyInfo, *collection, vid, *concurrency); err != nil {
 			return err
 		}
 	}
@@ -124,13 +124,23 @@ func collectRemoteVolumes(topoInfo *master_pb.TopologyInfo, collectionPattern st
 	return
 }
 
-func doVolumeTierDownload(commandEnv *CommandEnv, writer io.Writer, collection string, vid needle.VolumeId, concurrency int) (err error) {
+func doVolumeTierDownload(commandEnv *CommandEnv, writer io.Writer, topoInfo *master_pb.TopologyInfo, collectionPattern string, vid needle.VolumeId, concurrency int) (err error) {
 	// find volume location
 	locations, found := commandEnv.MasterClient.GetLocationsClone(uint32(vid))
 	if !found {
 		return fmt.Errorf("volume %d not found", vid)
 	}
 
+	// 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 {
+		return fmt.Errorf("volume %d not found in collections matching %q", vid, collectionPattern)
+	}
+
 	// All replicas point at the same remote object; only the final download may delete
 	// it. Every earlier replica keeps it so the survivors are not left dangling.
 	// TODO parallelize this

weed/shell/command_volume_tier_move.go

@@ -67,7 +67,7 @@ func (c *commandVolumeTierMove) Help() string {
 
 	Note:
 		-collectionPattern is a comma-separated list of collection names, with "*" and "?"
-		wildcards, and regex patterns. Use "_default" to match only the default collection
+		wildcards, and regex patterns. Use "` + CollectionDefault + `" to match only the default collection
 		(volumes with no collection name). An empty pattern matches all collections.
 
 `

weed/shell/command_volume_tier_upload.go

@@ -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,

weed/shell/command_volume_vacuum.go

@@ -5,11 +5,18 @@ import (
 	"flag"
 	"fmt"
 	"io"
+	"slices"
 	"sort"
 	"strconv"
 	"strings"
+	"time"
 
+	"github.com/seaweedfs/seaweedfs/weed/operation"
+	"github.com/seaweedfs/seaweedfs/weed/pb"
 	"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
+	"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
+	"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
+	"google.golang.org/grpc"
 )
 
 func init() {
@@ -42,12 +49,17 @@ func (c *commandVacuum) Do(args []string, commandEnv *CommandEnv, writer io.Writ
 
 	volumeVacuumCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
 	garbageThreshold := volumeVacuumCommand.Float64("garbageThreshold", 0.3, "vacuum when garbage is more than this limit")
-	collection := volumeVacuumCommand.String("collection", "", "vacuum this collection")
+	collection := volumeVacuumCommand.String("collection", "", "comma-separated collection names, wildcards, or regex patterns; empty or \"*\" matches all, \""+CollectionDefault+"\" the collection with no name")
 	volumeIds := volumeVacuumCommand.String("volumeId", "", "comma-separated list of volume IDs")
 	if err = volumeVacuumCommand.Parse(args); err != nil {
 		return nil
 	}
 
+	collectionMatcher, err := wildcard.CompileCollectionMatcher(*collection)
+	if err != nil {
+		return fmt.Errorf("invalid collection pattern %q: %w", *collection, err)
+	}
+
 	if err = commandEnv.confirmIsLocked(args); err != nil {
 		return
 	}
@@ -107,19 +119,41 @@ func (c *commandVacuum) Do(args []string, commandEnv *CommandEnv, writer io.Writ
 	} else if topo != nil {
 		// The sweep says nothing about the volumes it leaves alone, so an
 		// operator on a full disk sees the command return and nothing change.
-		if skipped := readOnlyVolumesAboveThreshold(topo, *collection, *garbageThreshold); len(skipped) > 0 {
+		if skipped := readOnlyVolumesAboveThreshold(topo, collectionMatcher, *garbageThreshold); len(skipped) > 0 {
 			fmt.Fprintf(writer, "%d read-only volume(s) hold garbage above %g and are skipped by the sweep: %v\n", len(skipped), *garbageThreshold, skipped)
 			fmt.Fprintf(writer, "vacuum them explicitly with -volumeId\n")
 		}
 	}
 
-	for _, volumeId := range volumeIdInts {
-		err = commandEnv.MasterClient.WithClient(context.Background(), false, func(client master_pb.SeaweedClient) error {
-			_, err = client.VacuumVolume(context.Background(), &master_pb.VacuumVolumeRequest{
-				GarbageThreshold: float32(*garbageThreshold),
-				VolumeId:         volumeId,
-				Collection:       *collection,
+	// The VacuumVolume RPC takes one exact collection name per call and reads
+	// "" as "all collections", so a filter has to be resolved here: one request
+	// per matched named collection, and per-volume requests for the unnamed
+	// collection, which no Collection value selects on its own.
+	var requests []*master_pb.VacuumVolumeRequest
+	if collectionMatcher == nil {
+		for _, volumeId := range volumeIdInts {
+			requests = append(requests, &master_pb.VacuumVolumeRequest{
+				VolumeId: volumeId,
 			})
+		}
+	} else {
+		if topo == nil {
+			return fmt.Errorf("cannot resolve collection pattern %q: topology unavailable", *collection)
+		}
+		if *volumeIds != "" {
+			requests, err = vacuumRequestsForVolumeIds(topo, collectionMatcher, volumeIdInts)
+		} else {
+			requests, err = vacuumRequestsForPattern(commandEnv.option.GrpcDialOption, writer, topo, collectionMatcher)
+		}
+		if err != nil {
+			return err
+		}
+	}
+
+	for _, req := range requests {
+		req.GarbageThreshold = float32(*garbageThreshold)
+		err = commandEnv.MasterClient.WithClient(context.Background(), false, func(client master_pb.SeaweedClient) error {
+			_, err = client.VacuumVolume(context.Background(), req)
 			return err
 		})
 		if err != nil {
@@ -130,6 +164,139 @@ func (c *commandVacuum) Do(args []string, commandEnv *CommandEnv, writer io.Writ
 	return nil
 }
 
+// vidReplica pairs a volume replica's read-only state with the server that
+// reports it, so the unnamed-collection sweep can reproduce the master's
+// low-disk-space exception client-side.
+type vidReplica struct {
+	server   pb.ServerAddress
+	readOnly bool
+}
+
+// vacuumRequestsForPattern resolves a collection filter to the sweep requests
+// that cover it: one per matched named collection, which keeps the server's
+// read-only skip, plus per-volume requests for the unnamed collection — no
+// Collection value scopes the RPC to it alone.
+func vacuumRequestsForPattern(grpcDialOption grpc.DialOption, writer io.Writer, topo *master_pb.TopologyInfo, collectionMatcher *wildcard.CollectionMatcher) ([]*master_pb.VacuumVolumeRequest, error) {
+	collections := make(map[string]bool)
+	defaultReplicas := make(map[uint32][]vidReplica)
+	eachDataNode(topo, func(_ DataCenterId, _ RackId, dn *master_pb.DataNodeInfo) {
+		for _, disk := range dn.DiskInfos {
+			for _, v := range disk.VolumeInfos {
+				if !collectionMatcher.Matches(v.Collection) {
+					continue
+				}
+				collections[v.Collection] = true
+				if v.Collection == "" {
+					defaultReplicas[v.Id] = append(defaultReplicas[v.Id], vidReplica{
+						server:   pb.NewServerAddressFromDataNode(dn),
+						readOnly: v.ReadOnly,
+					})
+				}
+			}
+		}
+	})
+	if len(collections) == 0 {
+		return nil, fmt.Errorf("no volumes found in collections matching the filter")
+	}
+
+	var requests []*master_pb.VacuumVolumeRequest
+	for name := range collections {
+		if name != "" {
+			requests = append(requests, &master_pb.VacuumVolumeRequest{Collection: name})
+		}
+	}
+	// The unnamed collection has no scoping name, so each of its volumes gets
+	// a per-volume request — which also vacuums any other collection sharing
+	// the id. A volume whose every replica is read-only is skipped unless a
+	// replica reports low disk space, the sweep's own exception.
+	var defaultVids []uint32
+	for vid, replicas := range defaultReplicas {
+		writable := false
+		for _, r := range replicas {
+			if !r.readOnly {
+				writable = true
+				break
+			}
+		}
+		if !writable && !anyReplicaDiskSpaceLow(grpcDialOption, replicas, vid, writer) {
+			continue
+		}
+		defaultVids = append(defaultVids, vid)
+	}
+	sort.Slice(defaultVids, func(i, j int) bool { return defaultVids[i] < defaultVids[j] })
+	for _, vid := range defaultVids {
+		requests = append(requests, &master_pb.VacuumVolumeRequest{VolumeId: vid})
+	}
+	return requests, nil
+}
+
+// anyReplicaDiskSpaceLow probes read-only replicas for the low-disk condition
+// under which the master's sweep still vacuums a read-only volume.
+func anyReplicaDiskSpaceLow(grpcDialOption grpc.DialOption, replicas []vidReplica, vid uint32, writer io.Writer) bool {
+	for _, r := range replicas {
+		diskSpaceLow := false
+		err := operation.WithVolumeServerClient(false, r.server, grpcDialOption, func(client volume_server_pb.VolumeServerClient) error {
+			ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+			defer cancel()
+			resp, checkErr := client.VacuumVolumeCheck(ctx, &volume_server_pb.VacuumVolumeCheckRequest{VolumeId: vid})
+			if checkErr != nil {
+				return checkErr
+			}
+			diskSpaceLow = resp.DiskSpaceLow
+			return nil
+		})
+		if err != nil {
+			fmt.Fprintf(writer, "volume %d on %s: cannot check disk space: %v\n", vid, r.server, err)
+			continue
+		}
+		if diskSpaceLow {
+			return true
+		}
+	}
+	return false
+}
+
+// vacuumRequestsForVolumeIds scopes each requested volume to the collections
+// it lives in that the filter matches, so -volumeId and a pattern narrow each
+// other the same way the server narrows an exact -collection name.
+func vacuumRequestsForVolumeIds(topo *master_pb.TopologyInfo, collectionMatcher *wildcard.CollectionMatcher, volumeIdInts []uint32) ([]*master_pb.VacuumVolumeRequest, error) {
+	collectionsByVid := make(map[uint32]map[string]bool)
+	eachDataNode(topo, func(_ DataCenterId, _ RackId, dn *master_pb.DataNodeInfo) {
+		for _, disk := range dn.DiskInfos {
+			for _, v := range disk.VolumeInfos {
+				if collectionsByVid[v.Id] == nil {
+					collectionsByVid[v.Id] = make(map[string]bool)
+				}
+				collectionsByVid[v.Id][v.Collection] = true
+			}
+		}
+	})
+
+	var requests []*master_pb.VacuumVolumeRequest
+	for _, vid := range volumeIdInts {
+		var matched []string
+		for name := range collectionsByVid[vid] {
+			if collectionMatcher.Matches(name) {
+				matched = append(matched, name)
+			}
+		}
+		if len(matched) == 0 {
+			return nil, fmt.Errorf("volume %d is not in a collection matching the filter", vid)
+		}
+		// The unnamed collection has no scoping name; a volume-id-only request
+		// covers it (and any other collection the id is shared into).
+		if slices.Contains(matched, "") {
+			requests = append(requests, &master_pb.VacuumVolumeRequest{VolumeId: vid})
+			continue
+		}
+		sort.Strings(matched)
+		for _, name := range matched {
+			requests = append(requests, &master_pb.VacuumVolumeRequest{VolumeId: vid, Collection: name})
+		}
+	}
+	return requests, nil
+}
+
 // readOnlyVolumesAboveThreshold lists the volumes a sweep leaves alone: any
 // replica read-only (that is what the sweep checks), in the collection when one
 // is given, and some replica with a garbage ratio at or above the threshold.
@@ -138,13 +305,13 @@ func (c *commandVacuum) Do(args []string, commandEnv *CommandEnv, writer io.Writ
 // it can only understate, and a converted index that reports deletes without
 // their sizes is left out because its ratio is not knowable here. This is a
 // hint; the volume server's own check decides.
-func readOnlyVolumesAboveThreshold(topo *master_pb.TopologyInfo, collection string, garbageThreshold float64) []uint32 {
+func readOnlyVolumesAboveThreshold(topo *master_pb.TopologyInfo, collectionMatcher *wildcard.CollectionMatcher, garbageThreshold float64) []uint32 {
 	readOnly := make(map[uint32]bool)
 	garbage := make(map[uint32]float64) // the highest ratio any replica reports
 	eachDataNode(topo, func(_ DataCenterId, _ RackId, dn *master_pb.DataNodeInfo) {
 		for _, disk := range dn.DiskInfos {
 			for _, v := range disk.VolumeInfos {
-				if collection != "" && v.Collection != collection {
+				if !collectionMatcher.Matches(v.Collection) {
 					continue
 				}
 				if v.ReadOnly {

weed/shell/command_volume_vacuum_test.go

@@ -1,10 +1,12 @@
 package shell
 
 import (
+	"io"
 	"reflect"
 	"testing"
 
 	"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
+	"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
 )
 
 func vacuumTestTopology(nodes ...*master_pb.DataNodeInfo) *master_pb.TopologyInfo {
@@ -42,17 +44,115 @@ func TestReadOnlyVolumesAboveThreshold(t *testing.T) {
 		vacuumTestNode(readOnlyHalfGarbage, readOnlyOtherCollection, mixedWritableReplica),
 	)
 
-	got := readOnlyVolumesAboveThreshold(topo, "a", 0.3)
+	matcherA, err := wildcard.CompileCollectionMatcher("a")
+	if err != nil {
+		t.Fatalf("compile matcher: %v", err)
+	}
+
+	got := readOnlyVolumesAboveThreshold(topo, matcherA, 0.3)
 	if want := []uint32{1, 6, 7}; !reflect.DeepEqual(got, want) {
 		t.Fatalf("collection a, threshold 0.3: got %v, want %v", got, want)
 	}
 
-	got = readOnlyVolumesAboveThreshold(topo, "", 0.3)
+	got = readOnlyVolumesAboveThreshold(topo, nil, 0.3)
 	if want := []uint32{1, 4, 6, 7}; !reflect.DeepEqual(got, want) {
 		t.Fatalf("all collections, threshold 0.3: got %v, want %v", got, want)
 	}
 
-	if got := readOnlyVolumesAboveThreshold(topo, "a", 0.95); len(got) != 0 {
+	if got := readOnlyVolumesAboveThreshold(topo, matcherA, 0.95); len(got) != 0 {
 		t.Fatalf("threshold 0.95: got %v, want none", got)
 	}
 }
+
+func mustMatcher(t *testing.T, filter string) *wildcard.CollectionMatcher {
+	t.Helper()
+	m, err := wildcard.CompileCollectionMatcher(filter)
+	if err != nil {
+		t.Fatalf("compile %q: %v", filter, err)
+	}
+	return m
+}
+
+func TestVacuumRequestsForPattern(t *testing.T) {
+	node := vacuumTestNode(
+		&master_pb.VolumeInformationMessage{Id: 1, Collection: "a", Size: 100},
+		&master_pb.VolumeInformationMessage{Id: 2, Collection: "", Size: 100},
+		// read-only volumes stay out of the unnamed-collection sweep, the
+		// same as the server skips them on a named-collection sweep — the
+		// unreachable address keeps the low-disk probe a fast miss
+		&master_pb.VolumeInformationMessage{Id: 3, Collection: "", Size: 100, ReadOnly: true},
+		&master_pb.VolumeInformationMessage{Id: 4, Collection: "b", Size: 100},
+	)
+	node.Id = "localhost:1"
+	topo := vacuumTestTopology(node)
+
+	// A named collection sweeps as a single collection-scoped request.
+	reqs, err := vacuumRequestsForPattern(nil, io.Discard, topo, mustMatcher(t, "a"))
+	if err != nil {
+		t.Fatalf("pattern a: %v", err)
+	}
+	if len(reqs) != 1 || reqs[0].Collection != "a" || reqs[0].VolumeId != 0 {
+		t.Fatalf("pattern a: got %v, want one collection-a sweep request", reqs)
+	}
+
+	// Patterns cover several named collections.
+	reqs, err = vacuumRequestsForPattern(nil, io.Discard, topo, mustMatcher(t, "a,b"))
+	if err != nil {
+		t.Fatalf("pattern a,b: %v", err)
+	}
+	names := map[string]bool{}
+	for _, r := range reqs {
+		names[r.Collection] = true
+	}
+	if len(reqs) != 2 || !names["a"] || !names["b"] {
+		t.Fatalf("pattern a,b: got %v, want sweeps for a and b", reqs)
+	}
+
+	// The unnamed collection resolves to per-volume requests — no Collection
+	// value selects it alone, and the read-only volume is skipped because the
+	// probe cannot confirm low disk space.
+	reqs, err = vacuumRequestsForPattern(nil, io.Discard, topo, mustMatcher(t, CollectionDefault))
+	if err != nil {
+		t.Fatalf("%s: %v", CollectionDefault, err)
+	}
+	if len(reqs) != 1 || reqs[0].VolumeId != 2 || reqs[0].Collection != "" {
+		t.Fatalf("%s: got %v, want one per-volume request for volume 2", CollectionDefault, reqs)
+	}
+
+	// A filter hitting nothing is an error, not a silent no-op.
+	if _, err = vacuumRequestsForPattern(nil, io.Discard, topo, mustMatcher(t, "missing")); err == nil {
+		t.Fatal("expected an error for a filter matching no collection")
+	}
+}
+
+func TestVacuumRequestsForVolumeIds(t *testing.T) {
+	topo := vacuumTestTopology(
+		vacuumTestNode(
+			&master_pb.VolumeInformationMessage{Id: 1, Collection: "a"},
+			&master_pb.VolumeInformationMessage{Id: 2, Collection: ""},
+		),
+	)
+
+	// A matching name scopes the request to that collection.
+	reqs, err := vacuumRequestsForVolumeIds(topo, mustMatcher(t, "a"), []uint32{1})
+	if err != nil {
+		t.Fatalf("vid 1 in a: %v", err)
+	}
+	if len(reqs) != 1 || reqs[0].VolumeId != 1 || reqs[0].Collection != "a" {
+		t.Fatalf("vid 1 in a: got %v, want {VolumeId:1, Collection:a}", reqs)
+	}
+
+	// The unnamed collection sends a volume-id-only request.
+	reqs, err = vacuumRequestsForVolumeIds(topo, mustMatcher(t, CollectionDefault), []uint32{2})
+	if err != nil {
+		t.Fatalf("vid 2 in default: %v", err)
+	}
+	if len(reqs) != 1 || reqs[0].VolumeId != 2 || reqs[0].Collection != "" {
+		t.Fatalf("vid 2 in default: got %v, want {VolumeId:2}", reqs)
+	}
+
+	// A volume outside the filter is an error.
+	if _, err = vacuumRequestsForVolumeIds(topo, mustMatcher(t, "a"), []uint32{2}); err == nil {
+		t.Fatal("expected an error for a volume outside the filter")
+	}
+}

weed/shell/common.go

@@ -14,6 +14,16 @@ var (
 	CollectionDefault = wildcard.CollectionDefault
 )
 
+// resolveCollectionName maps the shared "_default" keyword to the empty-named
+// collection for commands whose -collection flag names one collection rather
+// than filtering by a pattern.
+func resolveCollectionName(name string) string {
+	if name == CollectionDefault {
+		return ""
+	}
+	return name
+}
+
 // ErrorWaitGroup lives in weed/util so packages outside the shell can share it.
 type ErrorWaitGroup = util.ErrorWaitGroup
 type ErrorWaitGroupTask = util.ErrorWaitGroupTask

weed/util/wildcard/collection_filter.go

@@ -211,6 +211,47 @@ func isRegexEntry(entry string) bool {
 	return false
 }
 
+// ExpandCollectionFilter resolves a collection_filter into concrete names
+// drawn from candidates — the same names CompileCollectionMatcher would
+// match — with one difference: a literal entry (no wildcard or regex syntax)
+// is returned even when absent from candidates, since a command may target a
+// collection the listing does not contain yet. CollectionDefault resolves to
+// the empty-named collection. Empty, "*", and the mode sentinels return all
+// candidates.
+func ExpandCollectionFilter(filter string, candidates []string) ([]string, error) {
+	trimmed := strings.TrimSpace(filter)
+	mode := CollectionFilterMode(trimmed)
+	if trimmed == "" || trimmed == "*" || mode == CollectionFilterAll || mode == CollectionFilterEach {
+		return candidates, nil
+	}
+	matcher, err := CompileCollectionMatcher(trimmed)
+	if err != nil {
+		return nil, err
+	}
+	seen := make(map[string]bool, len(candidates))
+	var out []string
+	add := func(name string) {
+		if !seen[name] {
+			seen[name] = true
+			out = append(out, name)
+		}
+	}
+	for _, entry := range splitCollectionEntries(trimmed) {
+		entry = strings.TrimSpace(entry)
+		if entry == CollectionDefault {
+			add("")
+		} else if !isRegexEntry(entry) && !strings.ContainsAny(entry, "*?") {
+			add(entry)
+		}
+	}
+	for _, name := range candidates {
+		if matcher.Matches(name) {
+			add(name)
+		}
+	}
+	return out, nil
+}
+
 // Matches reports whether a collection passes the filter. A nil matcher accepts everything.
 func (m *CollectionMatcher) Matches(collection string) bool {
 	if m == nil {

weed/util/wildcard/collection_filter_test.go

@@ -1,6 +1,9 @@
 package wildcard
 
-import "testing"
+import (
+	"reflect"
+	"testing"
+)
 
 func TestCompileCollectionMatcher(t *testing.T) {
 	cases := []struct {
@@ -72,3 +75,36 @@ func TestCompileCollectionMatcherInvalidEntry(t *testing.T) {
 		}
 	}
 }
+
+func TestExpandCollectionFilter(t *testing.T) {
+	listed := []string{"photos", "photos-backup", "videos"}
+	cases := []struct {
+		filter string
+		want   []string
+	}{
+		// Match-all forms return the candidates.
+		{"", listed},
+		{"*", listed},
+		{string(CollectionFilterEach), listed},
+		// A literal name passes through even when unlisted — the listing only
+		// covers collections with registered volumes.
+		{"photos", []string{"photos"}},
+		{"archived", []string{"archived"}},
+		{CollectionDefault, []string{""}},
+		{"photos," + CollectionDefault, []string{"photos", ""}},
+		// Patterns resolve only against listed names; a literal in the same
+		// list still passes through.
+		{"photos*", []string{"photos", "photos-backup"}},
+		{"photos*,archived", []string{"archived", "photos", "photos-backup"}},
+		{"^videos$", []string{"videos"}},
+	}
+	for _, c := range cases {
+		got, err := ExpandCollectionFilter(c.filter, listed)
+		if err != nil {
+			t.Fatalf("ExpandCollectionFilter(%q): %v", c.filter, err)
+		}
+		if !reflect.DeepEqual(got, c.want) {
+			t.Errorf("ExpandCollectionFilter(%q) = %v, want %v", c.filter, got, c.want)
+		}
+	}
+}