* Add volume dir tags to topology Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add preferred tag config for EC Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Prioritize EC destinations by tags Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add EC placement planner tag tests Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Refactor EC placement tests to reuse buildActiveTopology Remove buildActiveTopologyWithDiskTags helper function and consolidate tag setup inline in test cases. Tests now use UpdateTopology to apply tags after topology creation, reusing the existing buildActiveTopology function rather than duplicating its logic. All tag scenario tests pass: - TestECPlacementPlannerPrefersTaggedDisks - TestECPlacementPlannerFallsBackWhenTagsInsufficient Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Consolidate normalizeTagList into shared util package Extract normalizeTagList from three locations (volume.go, detection.go, erasure_coding_handler.go) into new weed/util/tag.go as exported NormalizeTagList function. Replace all duplicate implementations with imports and calls to util.NormalizeTagList. This improves code reuse and maintainability by centralizing tag normalization logic. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add PreferredTags to EC config persistence Add preferred_tags field to ErasureCodingTaskConfig protobuf with field number 5. Update GetConfigSpec to include preferred_tags field in the UI configuration schema. Add PreferredTags to ToTaskPolicy to serialize config to protobuf. Add PreferredTags to FromTaskPolicy to deserialize from protobuf with defensive copy to prevent external mutation. This allows EC preferred tags to be persisted and restored across worker restarts. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add defensive copy for Tags slice in DiskLocation Copy the incoming tags slice in NewDiskLocation instead of storing by reference. This prevents external callers from mutating the DiskLocation.Tags slice after construction, improving encapsulation and preventing unexpected changes to disk metadata. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add doc comment to buildCandidateSets method Document the tiered candidate selection and fallback behavior. Explain that for a planner with preferredTags, it accumulates disks matching each tag in order into progressively larger tiers, emits a candidate set once a tier reaches shardsNeeded, and finally falls back to the full candidates set if preferred-tag tiers are insufficient. This clarifies the intended semantics for future maintainers. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Apply final PR review fixes 1. Update parseVolumeTags to replicate single tag entry to all folders instead of leaving some folders with nil tags. This prevents nil pointer dereferences when processing folders without explicit tags. 2. Add defensive copy in ToTaskPolicy for PreferredTags slice to match the pattern used in FromTaskPolicy, preventing external mutation of the returned TaskPolicy. 3. Add clarifying comment in buildCandidateSets explaining that the shardsNeeded <= 0 branch is a defensive check for direct callers, since selectDestinations guarantees shardsNeeded > 0. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix nil pointer dereference in parseVolumeTags Ensure all folder tags are initialized to either normalized tags or empty slices, not nil. When multiple tag entries are provided and there are more folders than entries, remaining folders now get empty slices instead of nil, preventing nil pointer dereference in downstream code. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix NormalizeTagList to return empty slice instead of nil Change NormalizeTagList to always return a non-nil slice. When all tags are empty or whitespace after normalization, return an empty slice instead of nil. This prevents nil pointer dereferences in downstream code that expects a valid (possibly empty) slice. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add nil safety check for v.tags pointer Add a safety check to handle the case where v.tags might be nil, preventing a nil pointer dereference. If v.tags is nil, use an empty string instead. This is defensive programming to prevent panics in edge cases. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add volume.tags flag to weed server and weed mini commands Add the volume.tags CLI option to both the 'weed server' and 'weed mini' commands. This allows users to specify disk tags when running the combined server modes, just like they can with 'weed volume'. The flag uses the same format and description as the volume command: comma-separated tag groups per data dir with ':' separators (e.g. fast:ssd,archive). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <copilot@github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
260 lines
7.0 KiB
Go
260 lines
7.0 KiB
Go
package storage
|
|
|
|
import (
|
|
"os"
|
|
"path/filepath"
|
|
"strconv"
|
|
"testing"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/needle"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/super_block"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/types"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
)
|
|
|
|
// newTestStore creates a test store with the specified number of directories
|
|
func newTestStore(t *testing.T, numDirs int) *Store {
|
|
tempDir := t.TempDir()
|
|
|
|
var dirs []string
|
|
var maxCounts []int32
|
|
var minFreeSpaces []util.MinFreeSpace
|
|
var diskTypes []types.DiskType
|
|
|
|
for i := 0; i < numDirs; i++ {
|
|
dir := filepath.Join(tempDir, "dir"+strconv.Itoa(i))
|
|
os.MkdirAll(dir, 0755)
|
|
dirs = append(dirs, dir)
|
|
maxCounts = append(maxCounts, 100) // high limit
|
|
minFreeSpaces = append(minFreeSpaces, util.MinFreeSpace{})
|
|
diskTypes = append(diskTypes, types.HardDriveType)
|
|
}
|
|
|
|
store := NewStore(nil, "localhost", 8080, 18080, "http://localhost:8080", "",
|
|
dirs, maxCounts, minFreeSpaces, "", NeedleMapInMemory, diskTypes, nil, 3)
|
|
|
|
// Consume channel messages to prevent blocking
|
|
done := make(chan bool)
|
|
go func() {
|
|
for {
|
|
select {
|
|
case <-store.NewVolumesChan:
|
|
case <-done:
|
|
return
|
|
}
|
|
}
|
|
}()
|
|
t.Cleanup(func() {
|
|
store.Close()
|
|
close(done)
|
|
})
|
|
|
|
return store
|
|
}
|
|
|
|
func TestLocalVolumesLen(t *testing.T) {
|
|
testCases := []struct {
|
|
name string
|
|
totalVolumes int
|
|
remoteVolumes int
|
|
expectedLocalCount int
|
|
}{
|
|
{
|
|
name: "all local volumes",
|
|
totalVolumes: 5,
|
|
remoteVolumes: 0,
|
|
expectedLocalCount: 5,
|
|
},
|
|
{
|
|
name: "all remote volumes",
|
|
totalVolumes: 5,
|
|
remoteVolumes: 5,
|
|
expectedLocalCount: 0,
|
|
},
|
|
{
|
|
name: "mixed local and remote",
|
|
totalVolumes: 10,
|
|
remoteVolumes: 3,
|
|
expectedLocalCount: 7,
|
|
},
|
|
{
|
|
name: "no volumes",
|
|
totalVolumes: 0,
|
|
remoteVolumes: 0,
|
|
expectedLocalCount: 0,
|
|
},
|
|
}
|
|
|
|
for _, tc := range testCases {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
diskLocation := &DiskLocation{
|
|
volumes: make(map[needle.VolumeId]*Volume),
|
|
}
|
|
|
|
// Add volumes
|
|
for i := 0; i < tc.totalVolumes; i++ {
|
|
vol := &Volume{
|
|
Id: needle.VolumeId(i + 1),
|
|
volumeInfo: &volume_server_pb.VolumeInfo{},
|
|
}
|
|
|
|
// Mark some as remote
|
|
if i < tc.remoteVolumes {
|
|
vol.hasRemoteFile = true
|
|
vol.volumeInfo.Files = []*volume_server_pb.RemoteFile{
|
|
{BackendType: "s3", BackendId: "test", Key: "test-key"},
|
|
}
|
|
}
|
|
|
|
diskLocation.volumes[vol.Id] = vol
|
|
}
|
|
|
|
result := diskLocation.LocalVolumesLen()
|
|
|
|
if result != tc.expectedLocalCount {
|
|
t.Errorf("Expected LocalVolumesLen() = %d; got %d (total: %d, remote: %d)",
|
|
tc.expectedLocalCount, result, tc.totalVolumes, tc.remoteVolumes)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestVolumeLoadBalancing(t *testing.T) {
|
|
testCases := []struct {
|
|
name string
|
|
locations []locationSetup
|
|
expectedLocations []int // which location index should get each volume
|
|
}{
|
|
{
|
|
name: "even distribution across empty locations",
|
|
locations: []locationSetup{
|
|
{localVolumes: 0, remoteVolumes: 0},
|
|
{localVolumes: 0, remoteVolumes: 0},
|
|
{localVolumes: 0, remoteVolumes: 0},
|
|
},
|
|
expectedLocations: []int{0, 1, 2, 0, 1, 2}, // round-robin
|
|
},
|
|
{
|
|
name: "prefers location with fewer local volumes",
|
|
locations: []locationSetup{
|
|
{localVolumes: 5, remoteVolumes: 0},
|
|
{localVolumes: 2, remoteVolumes: 0},
|
|
{localVolumes: 8, remoteVolumes: 0},
|
|
},
|
|
expectedLocations: []int{1, 1, 1}, // all go to location 1 (has fewest)
|
|
},
|
|
{
|
|
name: "ignores remote volumes in count",
|
|
locations: []locationSetup{
|
|
{localVolumes: 2, remoteVolumes: 10}, // 2 local, 10 remote
|
|
{localVolumes: 5, remoteVolumes: 0}, // 5 local
|
|
{localVolumes: 3, remoteVolumes: 0}, // 3 local
|
|
},
|
|
// expectedLocations: []int{0, 0, 2}
|
|
// Explanation:
|
|
// 1. Initial local counts: [2, 5, 3]. First volume goes to location 0 (2 local, ignoring 10 remote).
|
|
// 2. New local counts: [3, 5, 3]. Second volume goes to location 0 (first with min count 3).
|
|
// 3. New local counts: [4, 5, 3]. Third volume goes to location 2 (3 local < 4 local).
|
|
expectedLocations: []int{0, 0, 2},
|
|
},
|
|
{
|
|
name: "balances when some locations have remote volumes",
|
|
locations: []locationSetup{
|
|
{localVolumes: 1, remoteVolumes: 5},
|
|
{localVolumes: 1, remoteVolumes: 0},
|
|
{localVolumes: 0, remoteVolumes: 3},
|
|
},
|
|
// expectedLocations: []int{2, 0, 1}
|
|
// Explanation:
|
|
// 1. Initial local counts: [1, 1, 0]. First volume goes to location 2 (0 local).
|
|
// 2. New local counts: [1, 1, 1]. Second volume goes to location 0 (first with min count 1).
|
|
// 3. New local counts: [2, 1, 1]. Third volume goes to location 1 (next with min count 1).
|
|
expectedLocations: []int{2, 0, 1},
|
|
},
|
|
}
|
|
|
|
for _, tc := range testCases {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
// Create test store with multiple directories
|
|
store := newTestStore(t, len(tc.locations))
|
|
|
|
// Pre-populate locations with volumes
|
|
for locIdx, setup := range tc.locations {
|
|
location := store.Locations[locIdx]
|
|
vidCounter := 1000 + locIdx*100 // unique volume IDs per location
|
|
|
|
// Add local volumes
|
|
for i := 0; i < setup.localVolumes; i++ {
|
|
vol := createTestVolume(needle.VolumeId(vidCounter), false)
|
|
location.SetVolume(vol.Id, vol)
|
|
vidCounter++
|
|
}
|
|
|
|
// Add remote volumes
|
|
for i := 0; i < setup.remoteVolumes; i++ {
|
|
vol := createTestVolume(needle.VolumeId(vidCounter), true)
|
|
location.SetVolume(vol.Id, vol)
|
|
vidCounter++
|
|
}
|
|
}
|
|
|
|
// Create volumes and verify they go to expected locations
|
|
for i, expectedLoc := range tc.expectedLocations {
|
|
volumeId := needle.VolumeId(i + 1)
|
|
|
|
err := store.AddVolume(volumeId, "", NeedleMapInMemory, "000", "",
|
|
0, needle.GetCurrentVersion(), 0, types.HardDriveType, 3)
|
|
|
|
if err != nil {
|
|
t.Fatalf("Failed to add volume %d: %v", volumeId, err)
|
|
}
|
|
|
|
// Find which location got the volume
|
|
actualLoc := -1
|
|
for locIdx, location := range store.Locations {
|
|
if _, found := location.FindVolume(volumeId); found {
|
|
actualLoc = locIdx
|
|
break
|
|
}
|
|
}
|
|
|
|
if actualLoc != expectedLoc {
|
|
t.Errorf("Volume %d: expected location %d, got location %d",
|
|
volumeId, expectedLoc, actualLoc)
|
|
|
|
// Debug info
|
|
for locIdx, loc := range store.Locations {
|
|
localCount := loc.LocalVolumesLen()
|
|
totalCount := loc.VolumesLen()
|
|
t.Logf(" Location %d: %d local, %d total", locIdx, localCount, totalCount)
|
|
}
|
|
}
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
// Helper types and functions
|
|
type locationSetup struct {
|
|
localVolumes int
|
|
remoteVolumes int
|
|
}
|
|
|
|
func createTestVolume(vid needle.VolumeId, isRemote bool) *Volume {
|
|
vol := &Volume{
|
|
Id: vid,
|
|
SuperBlock: super_block.SuperBlock{},
|
|
volumeInfo: &volume_server_pb.VolumeInfo{},
|
|
}
|
|
|
|
if isRemote {
|
|
vol.hasRemoteFile = true
|
|
vol.volumeInfo.Files = []*volume_server_pb.RemoteFile{
|
|
{BackendType: "s3", BackendId: "test", Key: "remote-key-" + strconv.Itoa(int(vid))},
|
|
}
|
|
}
|
|
|
|
return vol
|
|
}
|