feat: add collection pattern to delete empty volumes (#10129)

* feat: add collection pattern to delete empty volumes

Co-authored-by: Codex <noreply@openai.com>

* shell: match collection pattern with wildcard matcher

Use wildcard.MatchesWildcard in the shared collection-pattern helper,
matching command_volume_fix_replication's matchCollectionPattern. The
flag only advertises '*' and '?', which is exactly what the matcher
supports.

---------

Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Chris Lu <chris.lu@gmail.com>

weed/shell/command_volume_delete_empty.go

@@ -27,6 +27,7 @@ func (c *commandVolumeDeleteEmpty) Help() string {
 	return `delete empty volumes from all volume servers
 
 	volume.deleteEmpty -quietFor=24h -apply
+	volume.deleteEmpty -collectionPattern=important* -quietFor=24h -apply
 
 	This command deletes all empty volumes from one volume server.
 
@@ -41,6 +42,7 @@ func (c *commandVolumeDeleteEmpty) Do(args []string, commandEnv *CommandEnv, wri
 
 	volDeleteCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
 	quietPeriod := volDeleteCommand.Duration("quietFor", 24*time.Hour, "select empty volumes with no recent writes, avoid newly created ones")
+	collectionPattern := volDeleteCommand.String("collectionPattern", "", "match with wildcard characters '*' and '?'")
 	applyBalancing := volDeleteCommand.Bool("apply", false, "apply to delete empty volumes")
 	// TODO: remove this alias
 	applyBalancingAlias := volDeleteCommand.Bool("force", false, "apply to delete empty volumes (alias for -apply)")
@@ -67,7 +69,7 @@ func (c *commandVolumeDeleteEmpty) Do(args []string, commandEnv *CommandEnv, wri
 	eachDataNode(topologyInfo, func(dc DataCenterId, rack RackId, dn *master_pb.DataNodeInfo) {
 		for _, diskInfo := range dn.DiskInfos {
 			for _, v := range diskInfo.VolumeInfos {
-				if v.Size <= super_block.SuperBlockSize && v.ModifiedAtSecond > 0 && v.ModifiedAtSecond+quietSeconds < nowUnixSeconds {
+				if isEmptyVolumeDeleteCandidate(v, quietSeconds, nowUnixSeconds, *collectionPattern) {
 					if *applyBalancing {
 						log.Printf("deleting empty volume %d from %s", v.Id, dn.Id)
 						if deleteErr := deleteVolume(commandEnv.option.GrpcDialOption, needle.VolumeId(v.Id),
@@ -85,3 +87,10 @@ func (c *commandVolumeDeleteEmpty) Do(args []string, commandEnv *CommandEnv, wri
 
 	return
 }
+
+func isEmptyVolumeDeleteCandidate(v *master_pb.VolumeInformationMessage, quietSeconds, nowUnixSeconds int64, collectionPattern string) bool {
+	return matchesVolumeCollectionPattern(collectionPattern, v.Collection) &&
+		v.Size <= super_block.SuperBlockSize &&
+		v.ModifiedAtSecond > 0 &&
+		v.ModifiedAtSecond+quietSeconds < nowUnixSeconds
+}

weed/shell/command_volume_delete_empty_test.go

@@ -0,0 +1,41 @@
+package shell
+
+import (
+	"testing"
+
+	"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
+)
+
+func TestIsEmptyVolumeDeleteCandidateCollectionPattern(t *testing.T) {
+	now := int64(1000)
+	quietSeconds := int64(100)
+	quietEmptyVolume := &master_pb.VolumeInformationMessage{
+		Size:             0,
+		ModifiedAtSecond: now - quietSeconds - 1,
+		Collection:       "important-logs",
+	}
+
+	tests := []struct {
+		name       string
+		pattern    string
+		collection string
+		want       bool
+	}{
+		{name: "empty pattern matches named collection", pattern: "", collection: "important-logs", want: true},
+		{name: "wildcard matches collection", pattern: "important*", collection: "important-logs", want: true},
+		{name: "wildcard rejects collection", pattern: "important*", collection: "other-logs", want: false},
+		{name: "default pattern matches empty collection", pattern: CollectionDefault, collection: "", want: true},
+		{name: "default pattern rejects named collection", pattern: CollectionDefault, collection: "important-logs", want: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			v := *quietEmptyVolume
+			v.Collection = tt.collection
+			if got := isEmptyVolumeDeleteCandidate(&v, quietSeconds, now, tt.pattern); got != tt.want {
+				t.Fatalf("isEmptyVolumeDeleteCandidate(collection=%q, pattern=%q) = %v, want %v",
+					tt.collection, tt.pattern, got, tt.want)
+			}
+		})
+	}
+}

weed/shell/command_volume_list.go

@@ -4,7 +4,6 @@ import (
 	"bytes"
 	"flag"
 	"fmt"
-	"path/filepath"
 	"slices"
 	"sort"
 	"strings"
@@ -15,6 +14,7 @@ import (
 	"github.com/seaweedfs/seaweedfs/weed/storage/erasure_coding"
 	"github.com/seaweedfs/seaweedfs/weed/storage/types"
 	"github.com/seaweedfs/seaweedfs/weed/util"
+	"github.com/seaweedfs/seaweedfs/weed/util/wildcard"
 
 	"io"
 )
@@ -319,16 +319,8 @@ func (c *commandVolumeList) isNotMatchDiskInfo(readOnly bool, collection string,
 	if *c.writable && (readOnly || volumeSize == -1 || (c.volumeSizeLimitMb > 0 && uint64(volumeSize) >= c.volumeSizeLimitMb*util.MiByte)) {
 		return true
 	}
-	if *c.collectionPattern != "" {
-		var matched bool
-		if *c.collectionPattern == CollectionDefault {
-			matched = (collection == "")
-		} else {
-			matched, _ = filepath.Match(*c.collectionPattern, collection)
-		}
-		if !matched {
-			return true
-		}
+	if !matchesVolumeCollectionPattern(*c.collectionPattern, collection) {
+		return true
 	}
 	if *c.volumeId > 0 && *c.volumeId != uint64(volumeId) {
 		return true
@@ -336,6 +328,16 @@ func (c *commandVolumeList) isNotMatchDiskInfo(readOnly bool, collection string,
 	return false
 }
 
+func matchesVolumeCollectionPattern(pattern, collection string) bool {
+	if pattern == "" {
+		return true
+	}
+	if pattern == CollectionDefault {
+		return collection == ""
+	}
+	return wildcard.MatchesWildcard(pattern, collection)
+}
+
 func (c *commandVolumeList) writeDiskInfo(writer io.Writer, t *master_pb.DiskInfo, verbosityLevel int, outNodeInfo func()) statistics {
 	var s statistics
 	diskType := t.Type