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

8
weed/server/volume_grpc_client_to_master.go
View File

@@ -237,8 +237,8 @@ func (vs *VolumeServer) doHeartbeatWithRetry(masterAddress pb.ServerAddress, grp
&ecShardMessage, // ecShardMessage is already a copy from the channel receive
},
}
glog.V(0).Infof("volume server %s:%d adds ec shard %d:%d", vs.store.Ip, vs.store.Port, ecShardMessage.Id,
erasure_coding.ShardBits(ecShardMessage.EcIndexBits).ShardIds())
si := erasure_coding.ShardsInfoFromVolumeEcShardInformationMessage(&ecShardMessage)
glog.V(0).Infof("volume server %s:%d adds ec shards to %d [%s]", vs.store.Ip, vs.store.Port, ecShardMessage.Id, si.String())
if err = stream.Send(deltaBeat); err != nil {
glog.V(0).Infof("Volume Server Failed to update to master %s: %v", masterAddress, err)
return "", err
@@ -268,8 +268,8 @@ func (vs *VolumeServer) doHeartbeatWithRetry(masterAddress pb.ServerAddress, grp
&ecShardMessage, // ecShardMessage is already a copy from the channel receive
},
}
glog.V(0).Infof("volume server %s:%d deletes ec shard %d:%d", vs.store.Ip, vs.store.Port, ecShardMessage.Id,
erasure_coding.ShardBits(ecShardMessage.EcIndexBits).ShardIds())
si := erasure_coding.ShardsInfoFromVolumeEcShardInformationMessage(&ecShardMessage)
glog.V(0).Infof("volume server %s:%d deletes ec shards from %d [%s]", vs.store.Ip, vs.store.Port, ecShardMessage.Id, si.String())
if err = stream.Send(deltaBeat); err != nil {
glog.V(0).Infof("Volume Server Failed to update to master %s: %v", masterAddress, err)
return "", err

7
weed/server/volume_grpc_erasure_coding.go
View File

@@ -548,11 +548,10 @@ func (vs *VolumeServer) VolumeEcShardsInfo(ctx context.Context, req *volume_serv
for _, location := range vs.store.Locations {
if v, found := location.FindEcVolume(needle.VolumeId(req.VolumeId)); found {
// Get shard details from the EC volume
shardDetails := v.ShardDetails()
for _, shardDetail := range shardDetails {
for _, si := range erasure_coding.ShardsInfoFromVolume(v).AsSlice() {
ecShardInfo := &volume_server_pb.EcShardInfo{
ShardId: uint32(shardDetail.ShardId),
Size: int64(shardDetail.Size),
ShardId: uint32(si.Id),
Size: int64(si.Size),
Collection: v.Collection,
}
ecShardInfos = append(ecShardInfos, ecShardInfo)