* refactor: add ECContext structure to encapsulate EC parameters
- Create ec_context.go with ECContext struct
- NewDefaultECContext() creates context with default 10+4 configuration
- Helper methods: CreateEncoder(), ToExt(), String()
- Foundation for cleaner function signatures
- No behavior change, still uses hardcoded 10+4
* refactor: update ec_encoder.go to use ECContext
- Add WriteEcFilesWithContext() and RebuildEcFilesWithContext() functions
- Keep old functions for backward compatibility (call new versions)
- Update all internal functions to accept ECContext parameter
- Use ctx.DataShards, ctx.ParityShards, ctx.TotalShards consistently
- Use ctx.CreateEncoder() instead of hardcoded reedsolomon.New()
- Use ctx.ToExt() for shard file extensions
- No behavior change, still uses default 10+4 configuration
* refactor: update ec_volume.go to use ECContext
- Add ECContext field to EcVolume struct
- Initialize ECContext with default configuration in NewEcVolume()
- Update LocateEcShardNeedleInterval() to use ECContext.DataShards
- Phase 1: Always uses default 10+4 configuration
- No behavior change
* refactor: add EC shard count fields to VolumeInfo protobuf
- Add data_shards_count field (field 8) to VolumeInfo message
- Add parity_shards_count field (field 9) to VolumeInfo message
- Fields are optional, 0 means use default (10+4)
- Backward compatible: fields added at end
- Phase 1: Foundation for future customization
* refactor: regenerate protobuf Go files with EC shard count fields
- Regenerated volume_server_pb/*.go with new EC fields
- DataShardsCount and ParityShardsCount accessors added to VolumeInfo
- No behavior change, fields not yet used
* refactor: update VolumeEcShardsGenerate to use ECContext
- Create ECContext with default configuration in VolumeEcShardsGenerate
- Use ecCtx.TotalShards and ecCtx.ToExt() in cleanup
- Call WriteEcFilesWithContext() instead of WriteEcFiles()
- Save EC configuration (DataShardsCount, ParityShardsCount) to VolumeInfo
- Log EC context being used
- Phase 1: Always uses default 10+4 configuration
- No behavior change
* fmt
* refactor: update ec_test.go to use ECContext
- Update TestEncodingDecoding to create and use ECContext
- Update validateFiles() to accept ECContext parameter
- Update removeGeneratedFiles() to use ctx.TotalShards and ctx.ToExt()
- Test passes with default 10+4 configuration
* refactor: use EcShardConfig message instead of separate fields
* optimize: pre-calculate row sizes in EC encoding loop
* refactor: replace TotalShards field with Total() method
- Remove TotalShards field from ECContext to avoid field drift
- Add Total() method that computes DataShards + ParityShards
- Update all references to use ctx.Total() instead of ctx.TotalShards
- Read EC config from VolumeInfo when loading EC volumes
- Read data shard count from .vif in VolumeEcShardsToVolume
- Use >= instead of > for exact boundary handling in encoding loops
* optimize: simplify VolumeEcShardsToVolume to use existing EC context
- Remove redundant CollectEcShards call
- Remove redundant .vif file loading
- Use v.ECContext.DataShards directly (already loaded by NewEcVolume)
- Slice tempShards instead of collecting again
* refactor: rename MaxShardId to MaxShardCount for clarity
- Change from MaxShardId=31 to MaxShardCount=32
- Eliminates confusing +1 arithmetic (MaxShardId+1)
- More intuitive: MaxShardCount directly represents the limit
fix: support custom EC ratios beyond 14 shards in VolumeEcShardsToVolume
- Add MaxShardId constant (31, since ShardBits is uint32)
- Use MaxShardId+1 (32) instead of TotalShardsCount (14) for tempShards buffer
- Prevents panic when slicing for volumes with >14 total shards
- Critical fix for custom EC configurations like 20+10
* fix: add validation for EC shard counts from VolumeInfo
- Validate DataShards/ParityShards are positive and within MaxShardCount
- Prevent zero or invalid values that could cause divide-by-zero
- Fallback to defaults if validation fails, with warning log
- VolumeEcShardsGenerate now preserves existing EC config when regenerating
- Critical safety fix for corrupted or legacy .vif files
* fix: RebuildEcFiles now loads EC config from .vif file
- Critical: RebuildEcFiles was always using default 10+4 config
- Now loads actual EC config from .vif file when rebuilding shards
- Validates config before use (positive shards, within MaxShardCount)
- Falls back to default if .vif missing or invalid
- Prevents data corruption when rebuilding custom EC volumes
* add: defensive validation for dataShards in VolumeEcShardsToVolume
- Validate dataShards > 0 and <= MaxShardCount before use
- Prevents panic from corrupted or uninitialized ECContext
- Returns clear error message instead of panic
- Defense-in-depth: validates even though upstream should catch issues
* fix: replace TotalShardsCount with MaxShardCount for custom EC ratio support
Critical fixes to support custom EC ratios > 14 shards:
disk_location_ec.go:
- validateEcVolume: Check shards 0-31 instead of 0-13 during validation
- removeEcVolumeFiles: Remove shards 0-31 instead of 0-13 during cleanup
ec_volume_info.go ShardBits methods:
- ShardIds(): Iterate up to MaxShardCount (32) instead of TotalShardsCount (14)
- ToUint32Slice(): Iterate up to MaxShardCount (32)
- IndexToShardId(): Iterate up to MaxShardCount (32)
- MinusParityShards(): Remove shards 10-31 instead of 10-13 (added note about Phase 2)
- Minus() shard size copy: Iterate up to MaxShardCount (32)
- resizeShardSizes(): Iterate up to MaxShardCount (32)
Without these changes:
- Custom EC ratios > 14 total shards would fail validation on startup
- Shards 14-31 would never be discovered or cleaned up
- ShardBits operations would miss shards >= 14
These changes are backward compatible - MaxShardCount (32) includes
the default TotalShardsCount (14), so existing 10+4 volumes work as before.
* fix: replace TotalShardsCount with MaxShardCount in critical data structures
Critical fixes for buffer allocations and loops that must support
custom EC ratios up to 32 shards:
Data Structures:
- store_ec.go:354: Buffer allocation for shard recovery (bufs array)
- topology_ec.go:14: EcShardLocations.Locations fixed array size
- command_ec_rebuild.go:268: EC shard map allocation
- command_ec_common.go:626: Shard-to-locations map allocation
Shard Discovery Loops:
- ec_task.go:378: Loop to find generated shard files
- ec_shard_management.go: All 8 loops that check/count EC shards
These changes are critical because:
1. Buffer allocations sized to 14 would cause index-out-of-bounds panics
when accessing shards 14-31
2. Fixed arrays sized to 14 would truncate shard location data
3. Loops limited to 0-13 would never discover/manage shards 14-31
Note: command_ec_encode.go:208 intentionally NOT changed - it creates
shard IDs to mount after encoding. In Phase 1 we always generate 14
shards, so this remains TotalShardsCount and will be made dynamic in
Phase 2 based on actual EC context.
Without these fixes, custom EC ratios > 14 total shards would cause:
- Runtime panics (array index out of bounds)
- Data loss (shards 14-31 never discovered/tracked)
- Incomplete shard management (missing shards not detected)
* refactor: move MaxShardCount constant to ec_encoder.go
Moved MaxShardCount from ec_volume_info.go to ec_encoder.go to group it
with other shard count constants (DataShardsCount, ParityShardsCount,
TotalShardsCount). This improves code organization and makes it easier
to understand the relationship between these constants.
Location: ec_encoder.go line 22, between TotalShardsCount and MinTotalDisks
* improve: add defensive programming and better error messages for EC
Code review improvements from CodeRabbit:
1. ShardBits Guardrails (ec_volume_info.go):
- AddShardId, RemoveShardId: Reject shard IDs >= MaxShardCount
- HasShardId: Return false for out-of-range shard IDs
- Prevents silent no-ops from bit shifts with invalid IDs
2. Future-Proof Regex (disk_location_ec.go):
- Updated regex from \.ec[0-9][0-9] to \.ec\d{2,3}
- Now matches .ec00 through .ec999 (currently .ec00-.ec31 used)
- Supports future increases to MaxShardCount beyond 99
3. Better Error Messages (volume_grpc_erasure_coding.go):
- Include valid range (1..32) in dataShards validation error
- Helps operators quickly identify the problem
4. Validation Before Save (volume_grpc_erasure_coding.go):
- Validate ECContext (DataShards > 0, ParityShards > 0, Total <= MaxShardCount)
- Log EC config being saved to .vif for debugging
- Prevents writing invalid configs to disk
These changes improve robustness and debuggability without changing
core functionality.
* fmt
* fix: critical bugs from code review + clean up comments
Critical bug fixes:
1. command_ec_rebuild.go: Fixed indentation causing compilation error
- Properly nested if/for blocks in registerEcNode
2. ec_shard_management.go: Fixed isComplete logic incorrectly using MaxShardCount
- Changed from MaxShardCount (32) back to TotalShardsCount (14)
- Default 10+4 volumes were being incorrectly reported as incomplete
- Missing shards 14-31 were being incorrectly reported as missing
- Fixed in 4 locations: volume completeness checks and getMissingShards
3. ec_volume_info.go: Fixed MinusParityShards removing too many shards
- Changed from MaxShardCount (32) back to TotalShardsCount (14)
- Was incorrectly removing shard IDs 10-31 instead of just 10-13
Comment cleanup:
- Removed Phase 1/Phase 2 references (development plan context)
- Replaced with clear statements about default 10+4 configuration
- SeaweedFS repo uses fixed 10+4 EC ratio, no phases needed
Root cause: Over-aggressive replacement of TotalShardsCount with MaxShardCount.
MaxShardCount (32) is the limit for buffer allocations and shard ID loops,
but TotalShardsCount (14) must be used for default EC configuration logic.
* fix: add defensive bounds checks and compute actual shard counts
Critical fixes from code review:
1. topology_ec.go: Add defensive bounds checks to AddShard/DeleteShard
- Prevent panic when shardId >= MaxShardCount (32)
- Return false instead of crashing on out-of-range shard IDs
2. command_ec_common.go: Fix doBalanceEcShardsAcrossRacks
- Was using hardcoded TotalShardsCount (14) for all volumes
- Now computes actual totalShardsForVolume from rackToShardCount
- Fixes incorrect rebalancing for volumes with custom EC ratios
- Example: 5+2=7 shards would incorrectly use 14 as average
These fixes improve robustness and prepare for future custom EC ratios
without changing current behavior for default 10+4 volumes.
Note: MinusParityShards and ec_task.go intentionally NOT changed for
seaweedfs repo - these will be enhanced in seaweed-enterprise repo
where custom EC ratio configuration is added.
* fmt
* style: make MaxShardCount type casting explicit in loops
Improved code clarity by explicitly casting MaxShardCount to the
appropriate type when used in loop comparisons:
- ShardId comparisons: Cast to ShardId(MaxShardCount)
- uint32 comparisons: Cast to uint32(MaxShardCount)
Changed in 5 locations:
- Minus() loop (line 90)
- ShardIds() loop (line 143)
- ToUint32Slice() loop (line 152)
- IndexToShardId() loop (line 219)
- resizeShardSizes() loop (line 248)
This makes the intent explicit and improves type safety readability.
No functional changes - purely a style improvement.
351 lines
10 KiB
Go
351 lines
10 KiB
Go
package erasure_coding
|
|
|
|
import (
|
|
"fmt"
|
|
"io"
|
|
"os"
|
|
|
|
"github.com/klauspost/reedsolomon"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/idx"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/needle_map"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/types"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/volume_info"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
)
|
|
|
|
const (
|
|
DataShardsCount = 10
|
|
ParityShardsCount = 4
|
|
TotalShardsCount = DataShardsCount + ParityShardsCount
|
|
MaxShardCount = 32 // Maximum number of shards since ShardBits is uint32 (bits 0-31)
|
|
MinTotalDisks = TotalShardsCount/ParityShardsCount + 1
|
|
ErasureCodingLargeBlockSize = 1024 * 1024 * 1024 // 1GB
|
|
ErasureCodingSmallBlockSize = 1024 * 1024 // 1MB
|
|
)
|
|
|
|
// WriteSortedFileFromIdx generates .ecx file from existing .idx file
|
|
// all keys are sorted in ascending order
|
|
func WriteSortedFileFromIdx(baseFileName string, ext string) (e error) {
|
|
|
|
nm, err := readNeedleMap(baseFileName)
|
|
if nm != nil {
|
|
defer nm.Close()
|
|
}
|
|
if err != nil {
|
|
return fmt.Errorf("readNeedleMap: %w", err)
|
|
}
|
|
|
|
ecxFile, err := os.OpenFile(baseFileName+ext, os.O_TRUNC|os.O_CREATE|os.O_WRONLY, 0644)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to open ecx file: %w", err)
|
|
}
|
|
defer ecxFile.Close()
|
|
|
|
err = nm.AscendingVisit(func(value needle_map.NeedleValue) error {
|
|
bytes := value.ToBytes()
|
|
_, writeErr := ecxFile.Write(bytes)
|
|
return writeErr
|
|
})
|
|
|
|
if err != nil {
|
|
return fmt.Errorf("failed to visit idx file: %w", err)
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
// WriteEcFiles generates .ec00 ~ .ec13 files using default EC context
|
|
func WriteEcFiles(baseFileName string) error {
|
|
ctx := NewDefaultECContext("", 0)
|
|
return WriteEcFilesWithContext(baseFileName, ctx)
|
|
}
|
|
|
|
// WriteEcFilesWithContext generates EC files using the provided context
|
|
func WriteEcFilesWithContext(baseFileName string, ctx *ECContext) error {
|
|
return generateEcFiles(baseFileName, 256*1024, ErasureCodingLargeBlockSize, ErasureCodingSmallBlockSize, ctx)
|
|
}
|
|
|
|
func RebuildEcFiles(baseFileName string) ([]uint32, error) {
|
|
// Attempt to load EC config from .vif file to preserve original configuration
|
|
var ctx *ECContext
|
|
if volumeInfo, _, found, _ := volume_info.MaybeLoadVolumeInfo(baseFileName + ".vif"); found && volumeInfo.EcShardConfig != nil {
|
|
ds := int(volumeInfo.EcShardConfig.DataShards)
|
|
ps := int(volumeInfo.EcShardConfig.ParityShards)
|
|
|
|
// Validate EC config before using it
|
|
if ds > 0 && ps > 0 && ds+ps <= MaxShardCount {
|
|
ctx = &ECContext{
|
|
DataShards: ds,
|
|
ParityShards: ps,
|
|
}
|
|
glog.V(0).Infof("Rebuilding EC files for %s with config from .vif: %s", baseFileName, ctx.String())
|
|
} else {
|
|
glog.Warningf("Invalid EC config in .vif for %s (data=%d, parity=%d), using default", baseFileName, ds, ps)
|
|
ctx = NewDefaultECContext("", 0)
|
|
}
|
|
} else {
|
|
glog.V(0).Infof("Rebuilding EC files for %s with default config", baseFileName)
|
|
ctx = NewDefaultECContext("", 0)
|
|
}
|
|
|
|
return RebuildEcFilesWithContext(baseFileName, ctx)
|
|
}
|
|
|
|
// RebuildEcFilesWithContext rebuilds missing EC files using the provided context
|
|
func RebuildEcFilesWithContext(baseFileName string, ctx *ECContext) ([]uint32, error) {
|
|
return generateMissingEcFiles(baseFileName, 256*1024, ErasureCodingLargeBlockSize, ErasureCodingSmallBlockSize, ctx)
|
|
}
|
|
|
|
func ToExt(ecIndex int) string {
|
|
return fmt.Sprintf(".ec%02d", ecIndex)
|
|
}
|
|
|
|
func generateEcFiles(baseFileName string, bufferSize int, largeBlockSize int64, smallBlockSize int64, ctx *ECContext) error {
|
|
file, err := os.OpenFile(baseFileName+".dat", os.O_RDONLY, 0)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to open dat file: %w", err)
|
|
}
|
|
defer file.Close()
|
|
|
|
fi, err := file.Stat()
|
|
if err != nil {
|
|
return fmt.Errorf("failed to stat dat file: %w", err)
|
|
}
|
|
|
|
glog.V(0).Infof("encodeDatFile %s.dat size:%d with EC context %s", baseFileName, fi.Size(), ctx.String())
|
|
err = encodeDatFile(fi.Size(), baseFileName, bufferSize, largeBlockSize, file, smallBlockSize, ctx)
|
|
if err != nil {
|
|
return fmt.Errorf("encodeDatFile: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func generateMissingEcFiles(baseFileName string, bufferSize int, largeBlockSize int64, smallBlockSize int64, ctx *ECContext) (generatedShardIds []uint32, err error) {
|
|
|
|
shardHasData := make([]bool, ctx.Total())
|
|
inputFiles := make([]*os.File, ctx.Total())
|
|
outputFiles := make([]*os.File, ctx.Total())
|
|
for shardId := 0; shardId < ctx.Total(); shardId++ {
|
|
shardFileName := baseFileName + ctx.ToExt(shardId)
|
|
if util.FileExists(shardFileName) {
|
|
shardHasData[shardId] = true
|
|
inputFiles[shardId], err = os.OpenFile(shardFileName, os.O_RDONLY, 0)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer inputFiles[shardId].Close()
|
|
} else {
|
|
outputFiles[shardId], err = os.OpenFile(shardFileName, os.O_TRUNC|os.O_WRONLY|os.O_CREATE, 0644)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer outputFiles[shardId].Close()
|
|
generatedShardIds = append(generatedShardIds, uint32(shardId))
|
|
}
|
|
}
|
|
|
|
err = rebuildEcFiles(shardHasData, inputFiles, outputFiles, ctx)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("rebuildEcFiles: %w", err)
|
|
}
|
|
return
|
|
}
|
|
|
|
func encodeData(file *os.File, enc reedsolomon.Encoder, startOffset, blockSize int64, buffers [][]byte, outputs []*os.File, ctx *ECContext) error {
|
|
|
|
bufferSize := int64(len(buffers[0]))
|
|
if bufferSize == 0 {
|
|
glog.Fatal("unexpected zero buffer size")
|
|
}
|
|
|
|
batchCount := blockSize / bufferSize
|
|
if blockSize%bufferSize != 0 {
|
|
glog.Fatalf("unexpected block size %d buffer size %d", blockSize, bufferSize)
|
|
}
|
|
|
|
for b := int64(0); b < batchCount; b++ {
|
|
err := encodeDataOneBatch(file, enc, startOffset+b*bufferSize, blockSize, buffers, outputs, ctx)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func openEcFiles(baseFileName string, forRead bool, ctx *ECContext) (files []*os.File, err error) {
|
|
for i := 0; i < ctx.Total(); i++ {
|
|
fname := baseFileName + ctx.ToExt(i)
|
|
openOption := os.O_TRUNC | os.O_CREATE | os.O_WRONLY
|
|
if forRead {
|
|
openOption = os.O_RDONLY
|
|
}
|
|
f, err := os.OpenFile(fname, openOption, 0644)
|
|
if err != nil {
|
|
return files, fmt.Errorf("failed to open file %s: %v", fname, err)
|
|
}
|
|
files = append(files, f)
|
|
}
|
|
return
|
|
}
|
|
|
|
func closeEcFiles(files []*os.File) {
|
|
for _, f := range files {
|
|
if f != nil {
|
|
f.Close()
|
|
}
|
|
}
|
|
}
|
|
|
|
func encodeDataOneBatch(file *os.File, enc reedsolomon.Encoder, startOffset, blockSize int64, buffers [][]byte, outputs []*os.File, ctx *ECContext) error {
|
|
|
|
// read data into buffers
|
|
for i := 0; i < ctx.DataShards; i++ {
|
|
n, err := file.ReadAt(buffers[i], startOffset+blockSize*int64(i))
|
|
if err != nil {
|
|
if err != io.EOF {
|
|
return err
|
|
}
|
|
}
|
|
if n < len(buffers[i]) {
|
|
for t := len(buffers[i]) - 1; t >= n; t-- {
|
|
buffers[i][t] = 0
|
|
}
|
|
}
|
|
}
|
|
|
|
err := enc.Encode(buffers)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
for i := 0; i < ctx.Total(); i++ {
|
|
_, err := outputs[i].Write(buffers[i])
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func encodeDatFile(remainingSize int64, baseFileName string, bufferSize int, largeBlockSize int64, file *os.File, smallBlockSize int64, ctx *ECContext) error {
|
|
|
|
var processedSize int64
|
|
|
|
enc, err := ctx.CreateEncoder()
|
|
if err != nil {
|
|
return fmt.Errorf("failed to create encoder: %w", err)
|
|
}
|
|
|
|
buffers := make([][]byte, ctx.Total())
|
|
for i := range buffers {
|
|
buffers[i] = make([]byte, bufferSize)
|
|
}
|
|
|
|
outputs, err := openEcFiles(baseFileName, false, ctx)
|
|
defer closeEcFiles(outputs)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to open ec files %s: %v", baseFileName, err)
|
|
}
|
|
|
|
// Pre-calculate row sizes to avoid redundant calculations in loops
|
|
largeRowSize := largeBlockSize * int64(ctx.DataShards)
|
|
smallRowSize := smallBlockSize * int64(ctx.DataShards)
|
|
|
|
for remainingSize >= largeRowSize {
|
|
err = encodeData(file, enc, processedSize, largeBlockSize, buffers, outputs, ctx)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to encode large chunk data: %w", err)
|
|
}
|
|
remainingSize -= largeRowSize
|
|
processedSize += largeRowSize
|
|
}
|
|
for remainingSize > 0 {
|
|
err = encodeData(file, enc, processedSize, smallBlockSize, buffers, outputs, ctx)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to encode small chunk data: %w", err)
|
|
}
|
|
remainingSize -= smallRowSize
|
|
processedSize += smallRowSize
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func rebuildEcFiles(shardHasData []bool, inputFiles []*os.File, outputFiles []*os.File, ctx *ECContext) error {
|
|
|
|
enc, err := ctx.CreateEncoder()
|
|
if err != nil {
|
|
return fmt.Errorf("failed to create encoder: %w", err)
|
|
}
|
|
|
|
buffers := make([][]byte, ctx.Total())
|
|
for i := range buffers {
|
|
if shardHasData[i] {
|
|
buffers[i] = make([]byte, ErasureCodingSmallBlockSize)
|
|
}
|
|
}
|
|
|
|
var startOffset int64
|
|
var inputBufferDataSize int
|
|
for {
|
|
|
|
// read the input data from files
|
|
for i := 0; i < ctx.Total(); i++ {
|
|
if shardHasData[i] {
|
|
n, _ := inputFiles[i].ReadAt(buffers[i], startOffset)
|
|
if n == 0 {
|
|
return nil
|
|
}
|
|
if inputBufferDataSize == 0 {
|
|
inputBufferDataSize = n
|
|
}
|
|
if inputBufferDataSize != n {
|
|
return fmt.Errorf("ec shard size expected %d actual %d", inputBufferDataSize, n)
|
|
}
|
|
} else {
|
|
buffers[i] = nil
|
|
}
|
|
}
|
|
|
|
// encode the data
|
|
err = enc.Reconstruct(buffers)
|
|
if err != nil {
|
|
return fmt.Errorf("reconstruct: %w", err)
|
|
}
|
|
|
|
// write the data to output files
|
|
for i := 0; i < ctx.Total(); i++ {
|
|
if !shardHasData[i] {
|
|
n, _ := outputFiles[i].WriteAt(buffers[i][:inputBufferDataSize], startOffset)
|
|
if inputBufferDataSize != n {
|
|
return fmt.Errorf("fail to write to %s", outputFiles[i].Name())
|
|
}
|
|
}
|
|
}
|
|
startOffset += int64(inputBufferDataSize)
|
|
}
|
|
|
|
}
|
|
|
|
func readNeedleMap(baseFileName string) (*needle_map.MemDb, error) {
|
|
indexFile, err := os.OpenFile(baseFileName+".idx", os.O_RDONLY, 0644)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("cannot read Volume Index %s.idx: %v", baseFileName, err)
|
|
}
|
|
defer indexFile.Close()
|
|
|
|
cm := needle_map.NewMemDb()
|
|
err = idx.WalkIndexFile(indexFile, 0, func(key types.NeedleId, offset types.Offset, size types.Size) error {
|
|
if !offset.IsZero() && !size.IsDeleted() {
|
|
cm.Set(key, offset, size)
|
|
} else {
|
|
cm.Delete(key)
|
|
}
|
|
return nil
|
|
})
|
|
return cm, err
|
|
}
|