minio/cmd/erasure-heal.go
Klaus Post 4a007e3767
Prefer local disks when fetching data blocks (#9563)
If the requested server is part of the set this will always read 
from the local disk, even if the disk contains a parity shard. 
In default setup there is a 50% chance that at least 
one shard that otherwise would have been fetched remotely 
will be read locally instead.

It basically trades RPC call overhead for reed-solomon. 
On distributed localhost this seems to be fairly break-even, 
with a very small gain in throughput and latency. 
However on networked servers this should be a bigger

1MB objects, before:

```
Operation: GET. Concurrency: 32. Hosts: 4.

Requests considered: 76257:
 * Avg: 25ms 50%: 24ms 90%: 32ms 99%: 42ms Fastest: 7ms Slowest: 67ms
 * First Byte: Average: 23ms, Median: 22ms, Best: 5ms, Worst: 65ms

Throughput:
* Average: 1213.68 MiB/s, 1272.63 obj/s (59.948s, starting 14:45:44 CEST)
```

After:
```
Operation: GET. Concurrency: 32. Hosts: 4.

Requests considered: 78845:
 * Avg: 24ms 50%: 24ms 90%: 31ms 99%: 39ms Fastest: 8ms Slowest: 62ms
 * First Byte: Average: 22ms, Median: 21ms, Best: 6ms, Worst: 57ms

Throughput:
* Average: 1255.11 MiB/s, 1316.08 obj/s (59.938s, starting 14:43:58 CEST)
```

Bonus fix: Only ask for heal once on an object.
2020-05-26 16:47:23 -07:00

49 lines
1.4 KiB
Go

/*
* MinIO Cloud Storage, (C) 2016 MinIO, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package cmd
import (
"context"
"io"
"github.com/minio/minio/cmd/logger"
)
// Heal heals the shard files on non-nil writers. Note that the quorum passed is 1
// as healing should continue even if it has been successful healing only one shard file.
func (e Erasure) Heal(ctx context.Context, readers []io.ReaderAt, writers []io.Writer, size int64) error {
r, w := io.Pipe()
go func() {
if err := e.Decode(ctx, w, readers, 0, size, size, nil); err != nil {
w.CloseWithError(err)
return
}
w.Close()
}()
buf := make([]byte, e.blockSize)
// quorum is 1 because CreateFile should continue writing as long as we are writing to even 1 disk.
n, err := e.Encode(ctx, r, writers, buf, 1)
if err != nil {
return err
}
if n != size {
logger.LogIf(ctx, errLessData)
return errLessData
}
return nil
}