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
```
139 lines
3.3 KiB
Go
139 lines
3.3 KiB
Go
package erasure_coding
|
|
|
|
import (
|
|
"fmt"
|
|
"io"
|
|
"os"
|
|
"path"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/stats"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/needle"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/types"
|
|
)
|
|
|
|
type ShardId uint8
|
|
|
|
// Converts a slice of uint32s to ShardId.
|
|
func Uint32ToShardIds(ids []uint32) []ShardId {
|
|
res := make([]ShardId, len(ids))
|
|
for i, id := range ids {
|
|
res[i] = ShardId(id)
|
|
}
|
|
return res
|
|
}
|
|
|
|
// Converts a slice of ShardIds to uint32
|
|
func ShardIdsToUint32(ids []ShardId) []uint32 {
|
|
res := make([]uint32, len(ids))
|
|
for i, id := range ids {
|
|
res[i] = uint32(id)
|
|
}
|
|
return res
|
|
}
|
|
|
|
// Returns a slice of all possible ShardIds.
|
|
func AllShardIds() []ShardId {
|
|
res := make([]ShardId, TotalShardsCount)
|
|
for i := range res {
|
|
res[i] = ShardId(i)
|
|
}
|
|
return res
|
|
}
|
|
|
|
type EcVolumeShard struct {
|
|
VolumeId needle.VolumeId
|
|
ShardId ShardId
|
|
Collection string
|
|
dir string
|
|
ecdFile *os.File
|
|
ecdFileSize int64
|
|
DiskType types.DiskType
|
|
}
|
|
|
|
func NewEcVolumeShard(diskType types.DiskType, dirname string, collection string, id needle.VolumeId, shardId ShardId) (v *EcVolumeShard, e error) {
|
|
|
|
v = &EcVolumeShard{dir: dirname, Collection: collection, VolumeId: id, ShardId: shardId, DiskType: diskType}
|
|
|
|
baseFileName := v.FileName()
|
|
|
|
// open ecd file
|
|
if v.ecdFile, e = os.OpenFile(baseFileName+ToExt(int(shardId)), os.O_RDONLY, 0644); e != nil {
|
|
if e == os.ErrNotExist || strings.Contains(e.Error(), "no such file or directory") {
|
|
return nil, os.ErrNotExist
|
|
}
|
|
return nil, fmt.Errorf("cannot read ec volume shard %s%s: %v", baseFileName, ToExt(int(shardId)), e)
|
|
}
|
|
ecdFi, statErr := v.ecdFile.Stat()
|
|
if statErr != nil {
|
|
_ = v.ecdFile.Close()
|
|
return nil, fmt.Errorf("can not stat ec volume shard %s%s: %v", baseFileName, ToExt(int(shardId)), statErr)
|
|
}
|
|
v.ecdFileSize = ecdFi.Size()
|
|
|
|
v.Mount()
|
|
|
|
return
|
|
}
|
|
|
|
func (shard *EcVolumeShard) Mount() {
|
|
stats.VolumeServerVolumeGauge.WithLabelValues(shard.Collection, "ec_shards").Inc()
|
|
}
|
|
|
|
func (shard *EcVolumeShard) Unmount() {
|
|
stats.VolumeServerVolumeGauge.WithLabelValues(shard.Collection, "ec_shards").Dec()
|
|
}
|
|
|
|
func (shard *EcVolumeShard) Size() int64 {
|
|
return shard.ecdFileSize
|
|
}
|
|
|
|
func (shard *EcVolumeShard) String() string {
|
|
return fmt.Sprintf("ec shard %v:%v, dir:%s, Collection:%s", shard.VolumeId, shard.ShardId, shard.dir, shard.Collection)
|
|
}
|
|
|
|
func (shard *EcVolumeShard) FileName() (fileName string) {
|
|
return EcShardFileName(shard.Collection, shard.dir, int(shard.VolumeId))
|
|
}
|
|
|
|
func EcShardFileName(collection string, dir string, id int) (fileName string) {
|
|
idString := strconv.Itoa(id)
|
|
if collection == "" {
|
|
fileName = path.Join(dir, idString)
|
|
} else {
|
|
fileName = path.Join(dir, collection+"_"+idString)
|
|
}
|
|
return
|
|
}
|
|
|
|
func EcShardBaseFileName(collection string, id int) (baseFileName string) {
|
|
baseFileName = strconv.Itoa(id)
|
|
if collection != "" {
|
|
baseFileName = collection + "_" + baseFileName
|
|
}
|
|
return
|
|
}
|
|
|
|
func (shard *EcVolumeShard) Close() {
|
|
if shard.ecdFile != nil {
|
|
_ = shard.ecdFile.Close()
|
|
shard.ecdFile = nil
|
|
}
|
|
}
|
|
|
|
func (shard *EcVolumeShard) Destroy() {
|
|
shard.Unmount()
|
|
os.Remove(shard.FileName() + ToExt(int(shard.ShardId)))
|
|
}
|
|
|
|
func (shard *EcVolumeShard) ReadAt(buf []byte, offset int64) (int, error) {
|
|
|
|
n, err := shard.ecdFile.ReadAt(buf, offset)
|
|
if err == io.EOF && n == len(buf) {
|
|
err = nil
|
|
}
|
|
return n, err
|
|
|
|
}
|