gsh-digital-services/seaweedFS
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix reporting of EC shard sizes from nodes to masters. (#7835)

Browse Source 
SeaweedFS tracks EC shard sizes on topology data stuctures, but this information is never
relayed to master servers :( The end result is that commands reporting disk usage, such
as `volume.list` and `cluster.status`, yield incorrect figures when EC shards are present.

As an example for a simple 5-node test cluster, before...

```
> volume.list
Topology volumeSizeLimit:30000 MB hdd(volume:6/40 active:6 free:33 remote:0)
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9001 hdd(volume:1/8 active:1 free:7 remote:0)
        Disk hdd(volume:1/8 active:1 free:7 remote:0) id:0
          volume id:3  size:88967096  file_count:172  replica_placement:2  version:3  modified_at_second:1766349617
          ec volume id:1 collection: shards:[1 5]
        Disk hdd total size:88967096 file_count:172
      DataNode 192.168.10.111:9001 total size:88967096 file_count:172
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9002 hdd(volume:2/8 active:2 free:6 remote:0)
        Disk hdd(volume:2/8 active:2 free:6 remote:0) id:0
          volume id:2  size:77267536  file_count:166  replica_placement:2  version:3  modified_at_second:1766349617
          volume id:3  size:88967096  file_count:172  replica_placement:2  version:3  modified_at_second:1766349617
          ec volume id:1 collection: shards:[0 4]
        Disk hdd total size:166234632 file_count:338
      DataNode 192.168.10.111:9002 total size:166234632 file_count:338
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9003 hdd(volume:1/8 active:1 free:7 remote:0)
        Disk hdd(volume:1/8 active:1 free:7 remote:0) id:0
          volume id:2  size:77267536  file_count:166  replica_placement:2  version:3  modified_at_second:1766349617
          ec volume id:1 collection: shards:[2 6]
        Disk hdd total size:77267536 file_count:166
      DataNode 192.168.10.111:9003 total size:77267536 file_count:166
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9004 hdd(volume:2/8 active:2 free:6 remote:0)
        Disk hdd(volume:2/8 active:2 free:6 remote:0) id:0
          volume id:2  size:77267536  file_count:166  replica_placement:2  version:3  modified_at_second:1766349617
          volume id:3  size:88967096  file_count:172  replica_placement:2  version:3  modified_at_second:1766349617
          ec volume id:1 collection: shards:[3 7]
        Disk hdd total size:166234632 file_count:338
      DataNode 192.168.10.111:9004 total size:166234632 file_count:338
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9005 hdd(volume:0/8 active:0 free:8 remote:0)
        Disk hdd(volume:0/8 active:0 free:8 remote:0) id:0
          ec volume id:1 collection: shards:[8 9 10 11 12 13]
        Disk hdd total size:0 file_count:0
    Rack DefaultRack total size:498703896 file_count:1014
  DataCenter DefaultDataCenter total size:498703896 file_count:1014
total size:498703896 file_count:1014
```

...and after:

```
> volume.list
Topology volumeSizeLimit:30000 MB hdd(volume:6/40 active:6 free:33 remote:0)
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9001 hdd(volume:1/8 active:1 free:7 remote:0)
        Disk hdd(volume:1/8 active:1 free:7 remote:0) id:0
          volume id:2  size:81761800  file_count:161  replica_placement:2  version:3  modified_at_second:1766349495
          ec volume id:1 collection: shards:[1 5 9] sizes:[1:8.00 MiB 5:8.00 MiB 9:8.00 MiB] total:24.00 MiB
        Disk hdd total size:81761800 file_count:161
      DataNode 192.168.10.111:9001 total size:81761800 file_count:161
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9002 hdd(volume:1/8 active:1 free:7 remote:0)
        Disk hdd(volume:1/8 active:1 free:7 remote:0) id:0
          volume id:3  size:88678712  file_count:170  replica_placement:2  version:3  modified_at_second:1766349495
          ec volume id:1 collection: shards:[11 12 13] sizes:[11:8.00 MiB 12:8.00 MiB 13:8.00 MiB] total:24.00 MiB
        Disk hdd total size:88678712 file_count:170
      DataNode 192.168.10.111:9002 total size:88678712 file_count:170
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9003 hdd(volume:2/8 active:2 free:6 remote:0)
        Disk hdd(volume:2/8 active:2 free:6 remote:0) id:0
          volume id:2  size:81761800  file_count:161  replica_placement:2  version:3  modified_at_second:1766349495
          volume id:3  size:88678712  file_count:170  replica_placement:2  version:3  modified_at_second:1766349495
          ec volume id:1 collection: shards:[0 4 8] sizes:[0:8.00 MiB 4:8.00 MiB 8:8.00 MiB] total:24.00 MiB
        Disk hdd total size:170440512 file_count:331
      DataNode 192.168.10.111:9003 total size:170440512 file_count:331
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9004 hdd(volume:2/8 active:2 free:6 remote:0)
        Disk hdd(volume:2/8 active:2 free:6 remote:0) id:0
          volume id:2  size:81761800  file_count:161  replica_placement:2  version:3  modified_at_second:1766349495
          volume id:3  size:88678712  file_count:170  replica_placement:2  version:3  modified_at_second:1766349495
          ec volume id:1 collection: shards:[2 6 10] sizes:[2:8.00 MiB 6:8.00 MiB 10:8.00 MiB] total:24.00 MiB
        Disk hdd total size:170440512 file_count:331
      DataNode 192.168.10.111:9004 total size:170440512 file_count:331
  DataCenter DefaultDataCenter hdd(volume:6/40 active:6 free:33 remote:0)
    Rack DefaultRack hdd(volume:6/40 active:6 free:33 remote:0)
      DataNode 192.168.10.111:9005 hdd(volume:0/8 active:0 free:8 remote:0)
        Disk hdd(volume:0/8 active:0 free:8 remote:0) id:0
          ec volume id:1 collection: shards:[3 7] sizes:[3:8.00 MiB 7:8.00 MiB] total:16.00 MiB
        Disk hdd total size:0 file_count:0
    Rack DefaultRack total size:511321536 file_count:993
  DataCenter DefaultDataCenter total size:511321536 file_count:993
total size:511321536 file_count:993
```
This commit is contained in:
Lisandro Pin
2025-12-29 04:30:42 +01:00
committed by GitHub
parent 2b529e310d
commit 6b98b52acc
28 changed files with 801 additions and 773 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
weed/shell/command_ec_rebuild.go
View File

@@ -149,8 +149,7 @@ func (erb *ecRebuilder) countLocalShards(node *EcNode, collection string, volume
for _, diskInfo := range node.info.DiskInfos {
for _, ecShardInfo := range diskInfo.EcShardInfos {
if ecShardInfo.Collection == collection && needle.VolumeId(ecShardInfo.Id) == volumeId {
shardBits := erasure_coding.ShardBits(ecShardInfo.EcIndexBits)
return len(shardBits.ShardIds())
return erasure_coding.ShardsCountFromVolumeEcShardInformationMessage(ecShardInfo)
}
}
}
@@ -266,7 +265,7 @@ func (erb *ecRebuilder) rebuildOneEcVolume(collection string, volumeId needle.Vo
fmt.Printf("rebuildOneEcVolume %s %d\n", collection, volumeId)
// collect shard files to rebuilder local disk
var generatedShardIds []uint32
var generatedShardIds []erasure_coding.ShardId
copiedShardIds, _, err := erb.prepareDataToRecover(rebuilder, collection, volumeId, locations)
if err != nil {
return err
@@ -306,7 +305,7 @@ func (erb *ecRebuilder) rebuildOneEcVolume(collection string, volumeId needle.Vo
return nil
}
func (erb *ecRebuilder) generateMissingShards(collection string, volumeId needle.VolumeId, sourceLocation pb.ServerAddress) (rebuiltShardIds []uint32, err error) {
func (erb *ecRebuilder) generateMissingShards(collection string, volumeId needle.VolumeId, sourceLocation pb.ServerAddress) (rebuiltShardIds []erasure_coding.ShardId, err error) {
err = operation.WithVolumeServerClient(false, sourceLocation, erb.commandEnv.option.GrpcDialOption, func(volumeServerClient volume_server_pb.VolumeServerClient) error {
resp, rebuildErr := volumeServerClient.VolumeEcShardsRebuild(context.Background(), &volume_server_pb.VolumeEcShardsRebuildRequest{
@@ -314,34 +313,35 @@ func (erb *ecRebuilder) generateMissingShards(collection string, volumeId needle
Collection: collection,
})
if rebuildErr == nil {
rebuiltShardIds = resp.RebuiltShardIds
rebuiltShardIds = erasure_coding.Uint32ToShardIds(resp.RebuiltShardIds)
}
return rebuildErr
})
return
}
func (erb *ecRebuilder) prepareDataToRecover(rebuilder *EcNode, collection string, volumeId needle.VolumeId, locations EcShardLocations) (copiedShardIds []uint32, localShardIds []uint32, err error) {
func (erb *ecRebuilder) prepareDataToRecover(rebuilder *EcNode, collection string, volumeId needle.VolumeId, locations EcShardLocations) (copiedShardIds []erasure_coding.ShardId, localShardIds []erasure_coding.ShardId, err error) {
needEcxFile := true
var localShardBits erasure_coding.ShardBits
localShardsInfo := erasure_coding.NewShardsInfo()
for _, diskInfo := range rebuilder.info.DiskInfos {
for _, ecShardInfo := range diskInfo.EcShardInfos {
if ecShardInfo.Collection == collection && needle.VolumeId(ecShardInfo.Id) == volumeId {
needEcxFile = false
localShardBits = erasure_coding.ShardBits(ecShardInfo.EcIndexBits)
localShardsInfo = erasure_coding.ShardsInfoFromVolumeEcShardInformationMessage(ecShardInfo)
}
}
}
for shardId, ecNodes := range locations {
for i, ecNodes := range locations {
shardId := erasure_coding.ShardId(i)
if len(ecNodes) == 0 {
erb.write("missing shard %d.%d\n", volumeId, shardId)
continue
}
if localShardBits.HasShardId(erasure_coding.ShardId(shardId)) {
localShardIds = append(localShardIds, uint32(shardId))
if localShardsInfo.Has(shardId) {
localShardIds = append(localShardIds, shardId)
erb.write("use existing shard %d.%d\n", volumeId, shardId)
continue
}
@@ -368,7 +368,7 @@ func (erb *ecRebuilder) prepareDataToRecover(rebuilder *EcNode, collection strin
erb.write("%s failed to copy %d.%d from %s: %v\n", rebuilder.info.Id, volumeId, shardId, ecNodes[0].info.Id, copyErr)
} else {
erb.write("%s copied %d.%d from %s\n", rebuilder.info.Id, volumeId, shardId, ecNodes[0].info.Id)
copiedShardIds = append(copiedShardIds, uint32(shardId))
copiedShardIds = append(copiedShardIds, shardId)
}
}
@@ -394,7 +394,7 @@ func (ecShardMap EcShardMap) registerEcNode(ecNode *EcNode, collection string) {
existing = make([][]*EcNode, erasure_coding.MaxShardCount)
ecShardMap[needle.VolumeId(shardInfo.Id)] = existing
}
for _, shardId := range erasure_coding.ShardBits(shardInfo.EcIndexBits).ShardIds() {
for _, shardId := range erasure_coding.ShardsInfoFromVolumeEcShardInformationMessage(shardInfo).Ids() {
existing[shardId] = append(existing[shardId], ecNode)
}
}