milvus/internal/flushcommon/syncmgr/pack_writer_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

190 lines
6.1 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"
"reflect"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/mock"
"github.com/milvus-io/milvus-proto/go-api/v2/commonpb"
"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/mocks"
"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"
)
func TestNextID(t *testing.T) {
al := allocator.NewMockGIDAllocator()
i := int64(0)
al.AllocF = func(count uint32) (int64, int64, error) {
rt := i
i += int64(count)
return rt, int64(count), nil
}
al.AllocOneF = func() (allocator.UniqueID, error) {
rt := i
i++
return rt, nil
}
bw := NewBulkPackWriter(nil, nil, nil, al)
bw.prefetchIDs(new(SyncPack).WithFlush())
t.Run("normal_next", func(t *testing.T) {
id := bw.nextID()
assert.Equal(t, int64(0), id)
})
t.Run("id_exhausted", func(t *testing.T) {
assert.Panics(t, func() {
bw.nextID()
})
})
}
func TestBulkPackWriter_Write(t *testing.T) {
paramtable.Get().Init(paramtable.NewBaseTable())
seg := metacache.NewSegmentInfo(&datapb.SegmentInfo{}, nil, nil)
metacache.UpdateNumOfRows(1000)(seg)
collectionID := int64(123)
partitionID := int64(456)
segmentID := int64(789)
channelName := fmt.Sprintf("by-dev-rootcoord-dml_0_%dv0", collectionID)
schema := &schemapb.CollectionSchema{
Name: "sync_task_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"},
},
},
},
}
mc := metacache.NewMockMetaCache(t)
mc.EXPECT().Collection().Return(collectionID).Maybe()
mc.EXPECT().GetSchema(mock.Anything).Return(schema).Maybe()
mc.EXPECT().GetSegmentByID(segmentID).Return(seg, true).Maybe()
mc.EXPECT().GetSegmentsBy(mock.Anything, mock.Anything).Return([]*metacache.SegmentInfo{seg}).Maybe()
mc.EXPECT().UpdateSegments(mock.Anything, mock.Anything).Run(func(action metacache.SegmentAction, filters ...metacache.SegmentFilter) {
action(seg)
}).Return().Maybe()
cm := mocks.NewChunkManager(t)
cm.EXPECT().RootPath().Return("files").Maybe()
cm.EXPECT().Write(mock.Anything, mock.Anything, mock.Anything).Return(nil).Maybe()
deletes := &storage.DeleteData{}
for i := 0; i < 10; i++ {
pk := storage.NewInt64PrimaryKey(int64(i + 1))
ts := uint64(100 + i)
deletes.Append(pk, ts)
}
bw := &BulkPackWriter{
metaCache: mc,
schema: schema,
chunkManager: cm,
allocator: allocator.NewLocalAllocator(10000, 100000),
}
tests := []struct {
name string
pack *SyncPack
wantInserts map[int64]*datapb.FieldBinlog
wantDeltas *datapb.FieldBinlog
wantStats map[int64]*datapb.FieldBinlog
wantBm25Stats map[int64]*datapb.FieldBinlog
wantSize int64
wantErr error
}{
{
name: "empty",
pack: new(SyncPack).WithCollectionID(collectionID).WithPartitionID(partitionID).WithSegmentID(segmentID).WithChannelName(channelName),
wantInserts: map[int64]*datapb.FieldBinlog{},
wantDeltas: &datapb.FieldBinlog{},
wantStats: map[int64]*datapb.FieldBinlog{},
wantBm25Stats: map[int64]*datapb.FieldBinlog{},
wantSize: 0,
wantErr: nil,
},
{
name: "with delete",
pack: new(SyncPack).WithCollectionID(collectionID).WithPartitionID(partitionID).WithSegmentID(segmentID).WithChannelName(channelName).WithDeleteData(deletes),
wantInserts: map[int64]*datapb.FieldBinlog{},
wantDeltas: &datapb.FieldBinlog{
FieldID: 100,
Binlogs: []*datapb.Binlog{
{
EntriesNum: 10,
LogPath: "files/delta_log/123/456/789/10000",
LogSize: 60,
MemorySize: 240,
},
},
},
wantStats: map[int64]*datapb.FieldBinlog{},
wantBm25Stats: map[int64]*datapb.FieldBinlog{},
wantSize: 60,
wantErr: nil,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
gotInserts, gotDeltas, gotStats, gotBm25Stats, gotSize, err := bw.Write(context.Background(), tt.pack)
if err != tt.wantErr {
t.Errorf("BulkPackWriter.Write() error = %v, wantErr %v", err, tt.wantErr)
return
}
if !reflect.DeepEqual(gotInserts, tt.wantInserts) {
t.Errorf("BulkPackWriter.Write() gotInserts = %v, want %v", gotInserts, tt.wantInserts)
}
if !reflect.DeepEqual(gotDeltas, tt.wantDeltas) {
t.Errorf("BulkPackWriter.Write() gotDeltas = %v, want %v", gotDeltas, tt.wantDeltas)
}
if !reflect.DeepEqual(gotStats, tt.wantStats) {
t.Errorf("BulkPackWriter.Write() gotStats = %v, want %v", gotStats, tt.wantStats)
}
if !reflect.DeepEqual(gotBm25Stats, tt.wantBm25Stats) {
t.Errorf("BulkPackWriter.Write() gotBm25Stats = %v, want %v", gotBm25Stats, tt.wantBm25Stats)
}
if gotSize != tt.wantSize {
t.Errorf("BulkPackWriter.Write() gotSize = %v, want %v", gotSize, tt.wantSize)
}
})
}
}