oyd
/
minio
6
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Automatically set goroutines based on shardSize (#5346)

Browse Source 
Update reedsolomon library to enable feature to automatically
set number of go-routines based on the input shard size,
since shard size is sort of a constant in Minio for
objects > 10MiB (default blocksize)

klauspost reported around 15-20% improvement in performance
numbers on older systems such as AVX and SSE3

```
name                  old speed      new speed      delta
Encode10x2x10000-8    5.45GB/s ± 1%  6.22GB/s ± 1%  +14.20%    (p=0.000 n=9+9)
Encode100x20x10000-8  1.44GB/s ± 1%  1.64GB/s ± 1%  +13.77%  (p=0.000 n=10+10)
Encode17x3x1M-8       10.0GB/s ± 5%  12.0GB/s ± 1%  +19.88%  (p=0.000 n=10+10)
Encode10x4x16M-8      7.81GB/s ± 5%  8.56GB/s ± 5%   +9.58%   (p=0.000 n=10+9)
Encode5x2x1M-8        15.3GB/s ± 2%  19.6GB/s ± 2%  +28.57%   (p=0.000 n=9+10)
Encode10x2x1M-8       12.2GB/s ± 5%  15.0GB/s ± 5%  +22.45%  (p=0.000 n=10+10)
Encode10x4x1M-8       7.84GB/s ± 1%  9.03GB/s ± 1%  +15.19%    (p=0.000 n=9+9)
Encode50x20x1M-8      1.73GB/s ± 4%  2.09GB/s ± 4%  +20.59%   (p=0.000 n=10+9)
Encode17x3x16M-8      10.6GB/s ± 1%  11.7GB/s ± 4%  +10.12%   (p=0.000 n=8+10)
```
master
Harshavardhana 7 years ago committed by kannappanr
parent b1fb550d5c
commit c0721164be
13 changed files with 151 additions and 47 deletions
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Show Stats Download Patch File Download Diff File
  1. 4
      cmd/erasure-createfile_test.go
  2. 2
      cmd/erasure-healfile_test.go
  3. 6
      cmd/erasure-readfile_test.go
  4. 5
      cmd/erasure.go
  5. 2
      cmd/erasure_test.go
  6. 2
      cmd/xl-v1-healing.go
  7. 2
      cmd/xl-v1-multipart.go
  8. 6
      cmd/xl-v1-object.go
  9. 4
      vendor/github.com/klauspost/reedsolomon/README.md
  10. 56
      vendor/github.com/klauspost/reedsolomon/galois_amd64.s
  11. 15
      vendor/github.com/klauspost/reedsolomon/options.go
  12. 34
      vendor/github.com/klauspost/reedsolomon/reedsolomon.go
  13. 60
      vendor/vendor.json

4
cmd/erasure-createfile_test.go
Unescape View File

@ -70,7 +70,7 @@ func TestErasureCreateFile(t *testing.T) {
if err != nil {
t.Fatalf("Test %d: failed to create test setup: %v", i, err)
}
storage, err := NewErasureStorage(setup.disks, test.dataBlocks, test.onDisks-test.dataBlocks)
storage, err := NewErasureStorage(setup.disks, test.dataBlocks, test.onDisks-test.dataBlocks, test.blocksize)
if err != nil {
setup.Remove()
t.Fatalf("Test %d: failed to create ErasureStorage: %v", i, err)
@ -125,7 +125,7 @@ func benchmarkErasureWrite(data, parity, dataDown, parityDown int, size int64, b
b.Fatalf("failed to create test setup: %v", err)
}
defer setup.Remove()
storage, err := NewErasureStorage(setup.disks, data, parity)
storage, err := NewErasureStorage(setup.disks, data, parity, blockSizeV1)
if err != nil {
b.Fatalf("failed to create ErasureStorage: %v", err)
}

2
cmd/erasure-healfile_test.go
Unescape View File

@ -74,7 +74,7 @@ func TestErasureHealFile(t *testing.T) {
if err != nil {
t.Fatalf("Test %d: failed to setup XL environment: %v", i, err)
}
storage, err := NewErasureStorage(setup.disks, test.dataBlocks, test.disks-test.dataBlocks)
storage, err := NewErasureStorage(setup.disks, test.dataBlocks, test.disks-test.dataBlocks, test.blocksize)
if err != nil {
setup.Remove()
t.Fatalf("Test %d: failed to create ErasureStorage: %v", i, err)

6
cmd/erasure-readfile_test.go
Unescape View File

@ -86,7 +86,7 @@ func TestErasureReadFile(t *testing.T) {
if err != nil {
t.Fatalf("Test %d: failed to create test setup: %v", i, err)
}
storage, err := NewErasureStorage(setup.disks, test.dataBlocks, test.onDisks-test.dataBlocks)
storage, err := NewErasureStorage(setup.disks, test.dataBlocks, test.onDisks-test.dataBlocks, test.blocksize)
if err != nil {
setup.Remove()
t.Fatalf("Test %d: failed to create ErasureStorage: %v", i, err)
@ -174,7 +174,7 @@ func TestErasureReadFileRandomOffsetLength(t *testing.T) {
}
defer setup.Remove()
storage, err := NewErasureStorage(setup.disks, dataBlocks, parityBlocks)
storage, err := NewErasureStorage(setup.disks, dataBlocks, parityBlocks, blockSize)
if err != nil {
t.Fatalf("failed to create ErasureStorage: %v", err)
}
@ -231,7 +231,7 @@ func benchmarkErasureRead(data, parity, dataDown, parityDown int, size int64, b
b.Fatalf("failed to create test setup: %v", err)
}
defer setup.Remove()
storage, err := NewErasureStorage(setup.disks, data, parity)
storage, err := NewErasureStorage(setup.disks, data, parity, blockSizeV1)
if err != nil {
b.Fatalf("failed to create ErasureStorage: %v", err)
}

5
cmd/erasure.go
Unescape View File

@ -44,8 +44,9 @@ type ErasureStorage struct {
// NewErasureStorage creates a new ErasureStorage. The storage erasure codes and protects all data written to
// the disks.
func NewErasureStorage(disks []StorageAPI, dataBlocks, parityBlocks int) (s ErasureStorage, err error) {
erasure, err := reedsolomon.New(dataBlocks, parityBlocks)
func NewErasureStorage(disks []StorageAPI, dataBlocks, parityBlocks int, blockSize int64) (s ErasureStorage, err error) {
shardsize := (int(blockSize) + dataBlocks - 1) / dataBlocks
erasure, err := reedsolomon.New(dataBlocks, parityBlocks, reedsolomon.WithAutoGoroutines(shardsize))
if err != nil {
return s, errors.Tracef("failed to create erasure coding: %v", err)
}

2
cmd/erasure_test.go
Unescape View File

@ -52,7 +52,7 @@ func TestErasureDecode(t *testing.T) {
copy(buffer, data)
disks := make([]StorageAPI, test.dataBlocks+test.parityBlocks)
storage, err := NewErasureStorage(disks, test.dataBlocks, test.parityBlocks)
storage, err := NewErasureStorage(disks, test.dataBlocks, test.parityBlocks, blockSizeV1)
if err != nil {
t.Fatalf("Test %d: failed to create erasure storage: %v", i, err)
}

2
cmd/xl-v1-healing.go
Unescape View File

@ -447,7 +447,7 @@ func healObject(storageDisks []StorageAPI, bucket, object string, quorum int) (i
// part to .minio/tmp/uuid/ which needs to be renamed later to
// the final location.
storage, err := NewErasureStorage(latestDisks,
latestMeta.Erasure.DataBlocks, latestMeta.Erasure.ParityBlocks)
latestMeta.Erasure.DataBlocks, latestMeta.Erasure.ParityBlocks, latestMeta.Erasure.BlockSize)
if err != nil {
return 0, 0, toObjectErr(err, bucket, object)
}

2
cmd/xl-v1-multipart.go
Unescape View File

@ -691,7 +691,7 @@ func (xl xlObjects) PutObjectPart(bucket, object, uploadID string, partID int, d
}
}
storage, err := NewErasureStorage(onlineDisks, xlMeta.Erasure.DataBlocks, xlMeta.Erasure.ParityBlocks)
storage, err := NewErasureStorage(onlineDisks, xlMeta.Erasure.DataBlocks, xlMeta.Erasure.ParityBlocks, xlMeta.Erasure.BlockSize)
if err != nil {
return pi, toObjectErr(err, bucket, object)
}

6
cmd/xl-v1-object.go
Unescape View File

@ -262,7 +262,7 @@ func (xl xlObjects) GetObject(bucket, object string, startOffset int64, length i
}
var totalBytesRead int64
storage, err := NewErasureStorage(onlineDisks, xlMeta.Erasure.DataBlocks, xlMeta.Erasure.ParityBlocks)
storage, err := NewErasureStorage(onlineDisks, xlMeta.Erasure.DataBlocks, xlMeta.Erasure.ParityBlocks, xlMeta.Erasure.BlockSize)
if err != nil {
return toObjectErr(err, bucket, object)
}
@ -535,13 +535,13 @@ func (xl xlObjects) PutObject(bucket string, object string, data *hash.Reader, m
// Total size of the written object
var sizeWritten int64
storage, err := NewErasureStorage(onlineDisks, xlMeta.Erasure.DataBlocks, xlMeta.Erasure.ParityBlocks)
storage, err := NewErasureStorage(onlineDisks, xlMeta.Erasure.DataBlocks, xlMeta.Erasure.ParityBlocks, xlMeta.Erasure.BlockSize)
if err != nil {
return ObjectInfo{}, toObjectErr(err, bucket, object)
}
// Alloc additional space for parity blocks created while erasure coding
buffer := make([]byte, partsMetadata[0].Erasure.BlockSize, 2*partsMetadata[0].Erasure.BlockSize)
buffer := make([]byte, xlMeta.Erasure.BlockSize, 2*xlMeta.Erasure.BlockSize)
// Read data and split into parts - similar to multipart mechanism
for partIdx := 1; ; partIdx++ {

4
vendor/github.com/klauspost/reedsolomon/README.md generated vendored
Unescape View File

@ -24,6 +24,10 @@ go get -u github.com/klauspost/reedsolomon
# Changes
## November 18, 2017
Added [WithAutoGoroutines](https://godoc.org/github.com/klauspost/reedsolomon#WithAutoGoroutines) which will attempt to calculate the optimal number of goroutines to use based on your expected shard size and detected CPU.
## October 1, 2017
* [Cauchy Matrix](https://godoc.org/github.com/klauspost/reedsolomon#WithCauchyMatrix) is now an option. Thanks to [templexxx](https://github.com/templexxx) for the basis of this.

56
vendor/github.com/klauspost/reedsolomon/galois_amd64.s generated vendored
Unescape View File

@ -19,8 +19,35 @@ TEXT ·galMulSSSE3Xor(SB), 7, $0
MOVQ out+72(FP), DX // DX: &out
PSHUFB X5, X8 // X8: lomask (unpacked)
SHRQ $4, R9 // len(in) / 16
MOVQ SI, AX
MOVQ DX, BX
ANDQ $15, AX
ANDQ $15, BX
CMPQ R9, $0
JEQ done_xor
ORQ AX, BX
CMPQ BX, $0
JNZ loopback_xor
loopback_xor_aligned:
MOVOA (SI), X0 // in[x]
MOVOA (DX), X4 // out[x]
MOVOA X0, X1 // in[x]
MOVOA X6, X2 // low copy
MOVOA X7, X3 // high copy
PSRLQ $4, X1 // X1: high input
PAND X8, X0 // X0: low input
PAND X8, X1 // X0: high input
PSHUFB X0, X2 // X2: mul low part
PSHUFB X1, X3 // X3: mul high part
PXOR X2, X3 // X3: Result
PXOR X4, X3 // X3: Result xor existing out
MOVOA X3, (DX) // Store
ADDQ $16, SI // in+=16
ADDQ $16, DX // out+=16
SUBQ $1, R9
JNZ loopback_xor_aligned
JMP done_xor
loopback_xor:
MOVOU (SI), X0 // in[x]
@ -57,15 +84,40 @@ TEXT ·galMulSSSE3(SB), 7, $0
MOVQ in_len+56(FP), R9 // R9: len(in)
MOVQ out+72(FP), DX // DX: &out
PSHUFB X5, X8 // X8: lomask (unpacked)
MOVQ SI, AX
MOVQ DX, BX
SHRQ $4, R9 // len(in) / 16
ANDQ $15, AX
ANDQ $15, BX
CMPQ R9, $0
JEQ done
ORQ AX, BX
CMPQ BX, $0
JNZ loopback
loopback_aligned:
MOVOA (SI), X0 // in[x]
MOVOA X0, X1 // in[x]
MOVOA X6, X2 // low copy
MOVOA X7, X3 // high copy
PSRLQ $4, X1 // X1: high input
PAND X8, X0 // X0: low input
PAND X8, X1 // X0: high input
PSHUFB X0, X2 // X2: mul low part
PSHUFB X1, X3 // X3: mul high part
PXOR X2, X3 // X3: Result
MOVOA X3, (DX) // Store
ADDQ $16, SI // in+=16
ADDQ $16, DX // out+=16
SUBQ $1, R9
JNZ loopback_aligned
JMP done
loopback:
MOVOU (SI), X0 // in[x]
MOVOU X0, X1 // in[x]
MOVOU X6, X2 // low copy
MOVOU X7, X3 // high copy
MOVOA X6, X2 // low copy
MOVOA X7, X3 // high copy
PSRLQ $4, X1 // X1: high input
PAND X8, X0 // X0: low input
PAND X8, X1 // X0: high input

15
vendor/github.com/klauspost/reedsolomon/options.go generated vendored
Unescape View File

@ -15,11 +15,12 @@ type options struct {
useAVX2, useSSSE3, useSSE2 bool
usePAR1Matrix bool
useCauchy bool
shardSize int
}
var defaultOptions = options{
maxGoroutines: 384,
minSplitSize: 512,
minSplitSize: 1024,
}
func init() {
@ -46,6 +47,18 @@ func WithMaxGoroutines(n int) Option {
}
}
// WithAutoGoroutines will adjust the number of goroutines for optimal speed with a
// specific shard size.
// Send in the shard size you expect to send. Other shard sizes will work, but may not
// run at the optimal speed.
// Overwrites WithMaxGoroutines.
// If shardSize <= 0, it is ignored.
func WithAutoGoroutines(shardSize int) Option {
return func(o *options) {
o.shardSize = shardSize
}
}
// WithMinSplitSize is the minimum encoding size in bytes per goroutine.
// See WithMaxGoroutines on how jobs are split.
// If n <= 0, it is ignored.

34
vendor/github.com/klauspost/reedsolomon/reedsolomon.go generated vendored
Unescape View File

@ -15,7 +15,10 @@ import (
"bytes"
"errors"
"io"
"runtime"
"sync"
"github.com/klauspost/cpuid"
)
// Encoder is an interface to encode Reed-Salomon parity sets for your data.
@ -239,6 +242,33 @@ func New(dataShards, parityShards int, opts ...Option) (Encoder, error) {
if err != nil {
return nil, err
}
if r.o.shardSize > 0 {
cacheSize := cpuid.CPU.Cache.L2
if cacheSize <= 0 {
// Set to 128K if undetectable.
cacheSize = 128 << 10
}
p := runtime.NumCPU()
// 1 input + parity must fit in cache, and we add one more to be safer.
shards := 1 + parityShards
g := (r.o.shardSize * shards) / (cacheSize - (cacheSize >> 4))
if cpuid.CPU.ThreadsPerCore > 1 {
// If multiple threads per core, make sure they don't contend for cache.
g *= cpuid.CPU.ThreadsPerCore
}
g *= 2
if g < p {
g = p
}
// Have g be multiple of p
g += p - 1
g -= g % p
r.o.maxGoroutines = g
}
// Inverted matrices are cached in a tree keyed by the indices
// of the invalid rows of the data to reconstruct.
@ -431,6 +461,8 @@ func (r reedSolomon) codeSomeShardsP(matrixRows, inputs, outputs [][]byte, outpu
if do < r.o.minSplitSize {
do = r.o.minSplitSize
}
// Make sizes divisible by 16
do = (do + 15) & (^15)
start := 0
for start < byteCount {
if start+do > byteCount {
@ -490,6 +522,8 @@ func (r reedSolomon) checkSomeShardsP(matrixRows, inputs, toCheck [][]byte, outp
if do < r.o.minSplitSize {
do = r.o.minSplitSize
}
// Make sizes divisible by 16
do = (do + 15) & (^15)
start := 0
for start < byteCount {
if start+do > byteCount {

60
vendor/vendor.json vendored
Unescape View File

@ -268,30 +268,6 @@
"revisionTime": "2016-01-19T13:13:26-08:00"
},
{
"checksumSHA1": "NYs0qvjZwsMZAXMtg2HRiED2cb4=",
"path": "github.com/joyent/triton-go",
"revision": "8365851ee7afcbb4cc1c7ba2e414b242ce0574f1",
"revisionTime": "2017-12-15T19:09:06Z"
},
{
"checksumSHA1": "Cth7NCLH/HaeKh9ZMRpQtudTEQQ=",
"path": "github.com/joyent/triton-go/authentication",
"revision": "8365851ee7afcbb4cc1c7ba2e414b242ce0574f1",
"revisionTime": "2017-12-15T19:09:06Z"
},
{
"checksumSHA1": "3ju04DVaxotpCKBF3Q/0vCSOlec=",
"path": "github.com/joyent/triton-go/client",
"revision": "8365851ee7afcbb4cc1c7ba2e414b242ce0574f1",
"revisionTime": "2017-12-15T19:09:06Z"
},
{
"checksumSHA1": "/WtyDZMgstGbBYtQ0f+ZfKMS4v8=",
"path": "github.com/joyent/triton-go/storage",
"revision": "8365851ee7afcbb4cc1c7ba2e414b242ce0574f1",
"revisionTime": "2017-12-15T19:09:06Z"
},
{
"checksumSHA1": "K6exl2ouL7d8cR2i378EzZOdRVI=",
"path": "github.com/howeyc/gopass",
"revision": "bf9dde6d0d2c004a008c27aaee91170c786f6db8",
@ -315,6 +291,30 @@
"revision": "8152e7eb6ccf8679a64582a66b78519688d156ad",
"revisionTime": "2016-01-12T19:33:35Z"
},
{
"checksumSHA1": "NYs0qvjZwsMZAXMtg2HRiED2cb4=",
"path": "github.com/joyent/triton-go",
"revision": "8365851ee7afcbb4cc1c7ba2e414b242ce0574f1",
"revisionTime": "2017-12-15T19:09:06Z"
},
{
"checksumSHA1": "Cth7NCLH/HaeKh9ZMRpQtudTEQQ=",
"path": "github.com/joyent/triton-go/authentication",
"revision": "8365851ee7afcbb4cc1c7ba2e414b242ce0574f1",
"revisionTime": "2017-12-15T19:09:06Z"
},
{
"checksumSHA1": "3ju04DVaxotpCKBF3Q/0vCSOlec=",
"path": "github.com/joyent/triton-go/client",
"revision": "8365851ee7afcbb4cc1c7ba2e414b242ce0574f1",
"revisionTime": "2017-12-15T19:09:06Z"
},
{
"checksumSHA1": "/WtyDZMgstGbBYtQ0f+ZfKMS4v8=",
"path": "github.com/joyent/triton-go/storage",
"revision": "8365851ee7afcbb4cc1c7ba2e414b242ce0574f1",
"revisionTime": "2017-12-15T19:09:06Z"
},
{
"path": "github.com/klauspost/cpuid",
"revision": "349c675778172472f5e8f3a3e0fe187e302e5a10",
@ -327,10 +327,10 @@
"revisionTime": "2016-10-16T15:41:25Z"
},
{
"checksumSHA1": "Nlhq327ZGeEh1gkPEBNPJKFlwds=",
"checksumSHA1": "ehsrWipiGIWqa4To8TmelIx06vI=",
"path": "github.com/klauspost/reedsolomon",
"revision": "e52c150f961e65ab9538bf1276b33bf469f919d8",
"revisionTime": "2017-11-18T15:17:31Z"
"revision": "0b30fa71cc8e4e9010c9aba6d0320e2e5b163b29",
"revisionTime": "2017-12-19T13:34:37Z"
},
{
"checksumSHA1": "dNYxHiBLalTqluak2/Z8c3RsSEM=",
@ -522,9 +522,9 @@
"checksumSHA1": "iqUXcP3VA+G1/gVLRpQpBUt/BuA=",
"path": "github.com/satori/uuid",
"revision": "5bf94b69c6b68ee1b541973bb8e1144db23a194b",
"revisionTime": "2017-03-21T23:07:31Z"
},
{
"revisionTime": "2017-03-21T23:07:31Z"
},
{
"checksumSHA1": "llmzhtIUy63V3Pl65RuEn18ck5g=",
"path": "github.com/segmentio/go-prompt",
"revision": "f0d19b6901ade831d5a3204edc0d6a7d6457fbb2",

Write Preview
Loading…
Cancel
Save