milvus/internal/flushcommon/syncmgr/storage_serializer_test.go
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

253 lines
7.0 KiB
Go

// Licensed to the LF AI & Data foundation under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you 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 syncmgr
import (
"context"
"fmt"
"math/rand"
"testing"
"time"
"github.com/samber/lo"
"github.com/stretchr/testify/mock"
"github.com/stretchr/testify/suite"
"github.com/milvus-io/milvus-proto/go-api/v2/commonpb"
"github.com/milvus-io/milvus-proto/go-api/v2/msgpb"
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
"github.com/milvus-io/milvus/internal/allocator"
"github.com/milvus-io/milvus/internal/flushcommon/metacache"
"github.com/milvus-io/milvus/internal/flushcommon/metacache/pkoracle"
"github.com/milvus-io/milvus/internal/storage"
"github.com/milvus-io/milvus/pkg/v2/common"
"github.com/milvus-io/milvus/pkg/v2/proto/datapb"
"github.com/milvus-io/milvus/pkg/v2/util/paramtable"
"github.com/milvus-io/milvus/pkg/v2/util/tsoutil"
)
type StorageV1SerializerSuite struct {
suite.Suite
collectionID int64
partitionID int64
segmentID int64
channelName string
schema *schemapb.CollectionSchema
mockAllocator *allocator.MockAllocator
mockCache *metacache.MockMetaCache
mockMetaWriter *MockMetaWriter
serializer *storageV1Serializer
}
func (s *StorageV1SerializerSuite) SetupSuite() {
paramtable.Init()
s.collectionID = rand.Int63n(100) + 1000
s.partitionID = rand.Int63n(100) + 2000
s.segmentID = rand.Int63n(1000) + 10000
s.channelName = fmt.Sprintf("by-dev-rootcoord-dml_0_%dv0", s.collectionID)
s.schema = &schemapb.CollectionSchema{
Name: "serializer_v1_test_col",
Fields: []*schemapb.FieldSchema{
{FieldID: common.RowIDField, DataType: schemapb.DataType_Int64},
{FieldID: common.TimeStampField, DataType: schemapb.DataType_Int64},
{
FieldID: 100,
Name: "pk",
DataType: schemapb.DataType_Int64,
IsPrimaryKey: true,
},
{
FieldID: 101,
Name: "vector",
DataType: schemapb.DataType_FloatVector,
TypeParams: []*commonpb.KeyValuePair{
{Key: common.DimKey, Value: "128"},
},
},
},
}
s.mockAllocator = allocator.NewMockAllocator(s.T())
s.mockCache = metacache.NewMockMetaCache(s.T())
s.mockMetaWriter = NewMockMetaWriter(s.T())
}
func (s *StorageV1SerializerSuite) SetupTest() {
s.mockCache.EXPECT().GetSchema(mock.Anything).Return(s.schema).Maybe()
s.mockCache.EXPECT().Collection().Return(s.collectionID).Once()
var err error
s.serializer, err = NewStorageSerializer(s.mockCache, s.schema)
s.Require().NoError(err)
}
func (s *StorageV1SerializerSuite) getEmptyInsertBuffer() *storage.InsertData {
buf, err := storage.NewInsertData(s.schema)
s.Require().NoError(err)
return buf
}
func (s *StorageV1SerializerSuite) getInsertBuffer() *storage.InsertData {
buf := s.getEmptyInsertBuffer()
// generate data
for i := 0; i < 10; i++ {
data := make(map[storage.FieldID]any)
data[common.RowIDField] = int64(i + 1)
data[common.TimeStampField] = int64(i + 1)
data[100] = int64(i + 1)
vector := lo.RepeatBy(128, func(_ int) float32 {
return rand.Float32()
})
data[101] = vector
err := buf.Append(data)
s.Require().NoError(err)
}
return buf
}
func (s *StorageV1SerializerSuite) getDeleteBuffer() *storage.DeleteData {
buf := &storage.DeleteData{}
for i := 0; i < 10; i++ {
pk := storage.NewInt64PrimaryKey(int64(i + 1))
ts := tsoutil.ComposeTSByTime(time.Now(), 0)
buf.Append(pk, ts)
}
return buf
}
func (s *StorageV1SerializerSuite) getBasicPack() *SyncPack {
pack := &SyncPack{}
pack.WithCollectionID(s.collectionID).
WithPartitionID(s.partitionID).
WithSegmentID(s.segmentID).
WithChannelName(s.channelName).
WithCheckpoint(&msgpb.MsgPosition{
Timestamp: 1000,
ChannelName: s.channelName,
})
return pack
}
func (s *StorageV1SerializerSuite) getBfs() *pkoracle.BloomFilterSet {
bfs := pkoracle.NewBloomFilterSet()
fd, err := storage.NewFieldData(schemapb.DataType_Int64, &schemapb.FieldSchema{
FieldID: 101,
Name: "ID",
IsPrimaryKey: true,
DataType: schemapb.DataType_Int64,
}, 16)
s.Require().NoError(err)
ids := []int64{1, 2, 3, 4, 5, 6, 7}
for _, id := range ids {
err = fd.AppendRow(id)
s.Require().NoError(err)
}
bfs.UpdatePKRange(fd)
return bfs
}
func (s *StorageV1SerializerSuite) TestSerializeInsert() {
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
s.Run("without_data", func() {
pack := s.getBasicPack()
pack.WithTimeRange(50, 100)
pack.WithDrop()
_, err := s.serializer.serializeBinlog(ctx, pack)
s.NoError(err)
})
s.Run("with_empty_data", func() {
pack := s.getBasicPack()
pack.WithTimeRange(50, 100)
pack.WithInsertData([]*storage.InsertData{s.getEmptyInsertBuffer()}).WithBatchRows(0)
_, err := s.serializer.serializeBinlog(ctx, pack)
s.Error(err)
})
s.Run("with_normal_data", func() {
pack := s.getBasicPack()
pack.WithTimeRange(50, 100)
pack.WithInsertData([]*storage.InsertData{s.getInsertBuffer()}).WithBatchRows(10)
blobs, err := s.serializer.serializeBinlog(ctx, pack)
s.NoError(err)
s.Len(blobs, 4)
stats, blob, err := s.serializer.serializeStatslog(pack)
s.NoError(err)
s.NotNil(stats)
s.NotNil(blob)
})
s.Run("with_flush_segment_not_found", func() {
pack := s.getBasicPack()
pack.WithInsertData([]*storage.InsertData{s.getInsertBuffer()}).WithFlush()
s.mockCache.EXPECT().GetSegmentByID(s.segmentID).Return(nil, false).Once()
_, err := s.serializer.serializeMergedPkStats(pack)
s.Error(err)
})
s.Run("with_flush", func() {
pack := s.getBasicPack()
pack.WithTimeRange(50, 100)
pack.WithInsertData([]*storage.InsertData{s.getInsertBuffer()}).WithBatchRows(10)
pack.WithFlush()
bfs := s.getBfs()
segInfo := metacache.NewSegmentInfo(&datapb.SegmentInfo{}, bfs, nil)
metacache.UpdateNumOfRows(1000)(segInfo)
s.mockCache.EXPECT().GetSegmentByID(s.segmentID).Return(segInfo, true)
blobs, err := s.serializer.serializeBinlog(ctx, pack)
s.NoError(err)
s.Len(blobs, 4)
stats, blob, err := s.serializer.serializeStatslog(pack)
s.NoError(err)
s.NotNil(stats)
s.NotNil(blob)
action := metacache.RollStats(stats)
action(segInfo)
blob, err = s.serializer.serializeMergedPkStats(pack)
s.NoError(err)
s.NotNil(blob)
})
}
func (s *StorageV1SerializerSuite) TestBadSchema() {
mockCache := metacache.NewMockMetaCache(s.T())
_, err := NewStorageSerializer(mockCache, &schemapb.CollectionSchema{})
s.Error(err)
}
func TestStorageV1Serializer(t *testing.T) {
suite.Run(t, new(StorageV1SerializerSuite))
}