congqixia f94b04e642
feat: [2.6] integrate Loon FFI for manifest-based segment loading and index building (#46076)
Cherry-pick from master
pr: #45061 #45488 #45803 #46017 #44991 #45132 #45723 #45726 #45798
#45897 #45918 #44998

This feature integrates the Storage V2 (Loon) FFI interface as a unified
storage layer for segment loading and index building in Milvus. It
enables
manifest-based data access, replacing the traditional binlog-based
approach
with a more efficient columnar storage format.

Key changes:

### Segment Self-Managed Loading Architecture
- Move segment loading orchestration from Go layer to C++ segcore
- Add NewSegmentWithLoadInfo() API for passing load info during segment
creation
- Implement SetLoadInfo() and Load() methods in SegmentInterface
- Support parallel loading of indexed and non-indexed fields
- Enable both sealed and growing segments to self-manage loading

### Storage V2 FFI Integration
- Integrate milvus-storage library's FFI interface for packed columnar
data
- Add manifest path support throughout the data path (SegmentInfo,
LoadInfo)
- Implement ManifestReader for generating manifests from binlogs
- Support zero-copy data exchange using Arrow C Data Interface
- Add ToCStorageConfig() for Go-to-C storage config conversion

### Manifest-Based Index Building
- Extend FileManagerContext to carry loon_ffi_properties
- Implement GetFieldDatasFromManifest() using Arrow C Stream interface
- Support manifest-based reading in DiskFileManagerImpl and
MemFileManagerImpl
- Add fallback to traditional segment insert files when manifest
unavailable

### Compaction Pipeline Updates
- Include manifest path in all compaction task builders (clustering, L0,
mix)
- Update BulkPackWriterV2 to return manifest path
- Propagate manifest metadata through compaction pipeline

### Configuration & Protocol
- Add common.storageV2.useLoonFFI config option (default: false)
- Add manifest_path field to SegmentLoadInfo and related proto messages
- Add manifest field to compaction segment messages

### Bug Fixes
- Fix mmap settings not applied during segment load (key typo fix)
- Populate index info after segment loading to prevent redundant load
tasks
- Fix memory corruption by removing premature transaction handle
destruction

Related issues: #44956, #45060, #39173

## Individual Cherry-Picked Commits

1. **e1c923b5cc** - fix: apply mmap settings correctly during segment
load (#46017)
2. **63b912370b** - enhance: use milvus-storage internal C++ Reader API
for Loon FFI (#45897)
3. **bfc192faa5** - enhance: Resolve issues integrating loon FFI
(#45918)
4. **fb18564631** - enhance: support manifest-based index building with
Loon FFI reader (#45726)
5. **b9ec2392b9** - enhance: integrate StorageV2 FFI interface for
manifest-based segment loading (#45798)
6. **66db3c32e6** - enhance: integrate Storage V2 FFI interface for
unified storage access (#45723)
7. **ae789273ac** - fix: populate index info after segment loading to
prevent redundant load tasks (#45803)
8. **49688b0be2** - enhance: Move segment loading logic from Go layer to
segcore for self-managed loading (#45488)
9. **5b2df88bac** - enhance: [StorageV2] Integrate FFI interface for
packed reader (#45132)
10. **91ff5706ac** - enhance: [StorageV2] add manifest path support for
FFI integration (#44991)
11. **2192bb4a85** - enhance: add NewSegmentWithLoadInfo API to support
segment self-managed loading (#45061)
12. **4296b01da0** - enhance: update delta log serialization APIs to
integrate storage V2 (#44998)

## Technical Details

### Architecture Changes
- **Before**: Go layer orchestrated segment loading, making multiple CGO
calls
- **After**: Segments autonomously manage loading in C++ layer with
single entry point

### Storage Access Pattern
- **Before**: Read individual binlog files through Go storage layer
- **After**: Read manifest file that references packed columnar data via
FFI

### Benefits
- Reduced cross-language call overhead
- Better resource management at C++ level
- Improved I/O performance through batched streaming reads
- Cleaner separation of concerns between Go and C++ layers
- Foundation for proactive schema evolution handling

---------

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
Co-authored-by: Ted Xu <ted.xu@zilliz.com>
2025-12-04 17:09:12 +08:00

164 lines
5.4 KiB
Go

package compactor
import (
"context"
"fmt"
"time"
"github.com/apache/arrow/go/v17/arrow/array"
"go.opentelemetry.io/otel"
"go.uber.org/zap"
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
"github.com/milvus-io/milvus/internal/allocator"
"github.com/milvus-io/milvus/internal/compaction"
"github.com/milvus-io/milvus/internal/flushcommon/io"
"github.com/milvus-io/milvus/internal/storage"
"github.com/milvus-io/milvus/pkg/v2/common"
"github.com/milvus-io/milvus/pkg/v2/log"
"github.com/milvus-io/milvus/pkg/v2/metrics"
"github.com/milvus-io/milvus/pkg/v2/proto/datapb"
"github.com/milvus-io/milvus/pkg/v2/util/timerecord"
"github.com/milvus-io/milvus/pkg/v2/util/typeutil"
)
func mergeSortMultipleSegments(ctx context.Context,
plan *datapb.CompactionPlan,
collectionID, partitionID, maxRows int64,
binlogIO io.BinlogIO,
binlogs []*datapb.CompactionSegmentBinlogs,
tr *timerecord.TimeRecorder,
currentTime time.Time,
collectionTtl int64,
compactionParams compaction.Params,
sortByFields []int64,
) ([]*datapb.CompactionSegment, error) {
_ = tr.RecordSpan()
ctx, span := otel.Tracer(typeutil.DataNodeRole).Start(ctx, "mergeSortMultipleSegments")
defer span.End()
log := log.With(zap.Int64("planID", plan.GetPlanID()))
segIDAlloc := allocator.NewLocalAllocator(plan.GetPreAllocatedSegmentIDs().GetBegin(), plan.GetPreAllocatedSegmentIDs().GetEnd())
logIDAlloc := allocator.NewLocalAllocator(plan.GetPreAllocatedLogIDs().GetBegin(), plan.GetPreAllocatedLogIDs().GetEnd())
compAlloc := NewCompactionAllocator(segIDAlloc, logIDAlloc)
writer, err := NewMultiSegmentWriter(ctx, binlogIO, compAlloc, plan.GetMaxSize(), plan.GetSchema(), compactionParams, maxRows, partitionID, collectionID, plan.GetChannel(), 4096,
storage.WithStorageConfig(compactionParams.StorageConfig),
storage.WithUseLoonFFI(compactionParams.UseLoonFFI))
if err != nil {
return nil, err
}
pkField, err := typeutil.GetPrimaryFieldSchema(plan.GetSchema())
if err != nil {
log.Warn("failed to get pk field from schema")
return nil, err
}
segmentReaders := make([]storage.RecordReader, len(binlogs))
segmentFilters := make([]compaction.EntityFilter, len(binlogs))
for i, s := range binlogs {
var reader storage.RecordReader
if s.GetManifest() != "" {
reader, err = storage.NewManifestRecordReader(ctx,
s.GetManifest(),
plan.GetSchema(),
storage.WithCollectionID(collectionID),
storage.WithDownloader(binlogIO.Download),
storage.WithVersion(s.StorageVersion),
storage.WithStorageConfig(compactionParams.StorageConfig),
)
} else {
reader, err = storage.NewBinlogRecordReader(ctx,
s.GetFieldBinlogs(),
plan.GetSchema(),
storage.WithCollectionID(collectionID),
storage.WithDownloader(binlogIO.Download),
storage.WithVersion(s.StorageVersion),
storage.WithStorageConfig(compactionParams.StorageConfig),
)
}
if err != nil {
return nil, err
}
segmentReaders[i] = reader
deltalogPaths := make([]string, 0)
for _, d := range s.GetDeltalogs() {
for _, l := range d.GetBinlogs() {
deltalogPaths = append(deltalogPaths, l.GetLogPath())
}
}
delta, err := compaction.ComposeDeleteFromDeltalogs(ctx, binlogIO, deltalogPaths)
if err != nil {
return nil, err
}
segmentFilters[i] = compaction.NewEntityFilter(delta, collectionTtl, currentTime)
}
defer func() {
for _, r := range segmentReaders {
r.Close()
}
}()
var predicate func(r storage.Record, ri, i int) bool
switch pkField.DataType {
case schemapb.DataType_Int64:
predicate = func(r storage.Record, ri, i int) bool {
pk := r.Column(pkField.FieldID).(*array.Int64).Value(i)
ts := r.Column(common.TimeStampField).(*array.Int64).Value(i)
return !segmentFilters[ri].Filtered(pk, uint64(ts))
}
case schemapb.DataType_VarChar:
predicate = func(r storage.Record, ri, i int) bool {
pk := r.Column(pkField.FieldID).(*array.String).Value(i)
ts := r.Column(common.TimeStampField).(*array.Int64).Value(i)
return !segmentFilters[ri].Filtered(pk, uint64(ts))
}
default:
log.Warn("compaction only support int64 and varchar pk field")
}
if _, err = storage.MergeSort(compactionParams.BinLogMaxSize, plan.GetSchema(), segmentReaders, writer, predicate, sortByFields); err != nil {
writer.Close()
return nil, err
}
if err := writer.Close(); err != nil {
log.Warn("compact wrong, failed to finish writer", zap.Error(err))
return nil, err
}
res := writer.GetCompactionSegments()
for _, seg := range res {
seg.IsSorted = true
}
var (
deletedRowCount int
expiredRowCount int
missingDeleteCount int
deltalogDeleteEntriesCount int
)
for _, filter := range segmentFilters {
deletedRowCount += filter.GetDeletedCount()
expiredRowCount += filter.GetExpiredCount()
missingDeleteCount += filter.GetMissingDeleteCount()
deltalogDeleteEntriesCount += filter.GetDeltalogDeleteCount()
}
totalElapse := tr.RecordSpan()
log.Info("compact mergeSortMultipleSegments end",
zap.Int("deleted row count", deletedRowCount),
zap.Int("expired entities", expiredRowCount),
zap.Int("missing deletes", missingDeleteCount),
zap.Duration("total elapse", totalElapse))
metrics.DataNodeCompactionDeleteCount.WithLabelValues(fmt.Sprint(collectionID)).Add(float64(deltalogDeleteEntriesCount))
metrics.DataNodeCompactionMissingDeleteCount.WithLabelValues(fmt.Sprint(collectionID)).Add(float64(missingDeleteCount))
return res, nil
}