milvus/internal/storage/stats_collector_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

262 lines
7.4 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 storage
import (
"fmt"
"testing"
"github.com/apache/arrow/go/v17/arrow"
"github.com/apache/arrow/go/v17/arrow/array"
"github.com/apache/arrow/go/v17/arrow/memory"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
"github.com/milvus-io/milvus/internal/allocator"
"github.com/milvus-io/milvus/pkg/v2/common"
)
func TestPkStatsCollector(t *testing.T) {
collectionID := int64(1)
schema := &schemapb.CollectionSchema{
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,
},
},
}
t.Run("collect and digest int64 pk", func(t *testing.T) {
collector, err := NewPkStatsCollector(collectionID, schema, 100)
require.NoError(t, err)
require.NotNil(t, collector)
// Create test record
fields := []arrow.Field{
{Name: "pk", Type: arrow.PrimitiveTypes.Int64},
}
arrowSchema := arrow.NewSchema(fields, nil)
builder := array.NewRecordBuilder(memory.DefaultAllocator, arrowSchema)
defer builder.Release()
pkBuilder := builder.Field(0).(*array.Int64Builder)
for i := 0; i < 10; i++ {
pkBuilder.Append(int64(i))
}
rec := builder.NewRecord()
field2Col := map[FieldID]int{100: 0}
record := NewSimpleArrowRecord(rec, field2Col)
// Collect stats
err = collector.Collect(record)
assert.NoError(t, err)
// Digest stats
alloc := allocator.NewLocalAllocator(1, 100)
writer := func(blobs []*Blob) error { return nil }
resultMap, err := collector.Digest(collectionID, 1, 2, "/tmp", 10, alloc, writer)
assert.NoError(t, err)
assert.NotNil(t, resultMap)
assert.Len(t, resultMap, 1)
})
t.Run("varchar pk", func(t *testing.T) {
varcharSchema := &schemapb.CollectionSchema{
Fields: []*schemapb.FieldSchema{
{FieldID: common.RowIDField, DataType: schemapb.DataType_Int64},
{FieldID: common.TimeStampField, DataType: schemapb.DataType_Int64},
{
FieldID: 100,
Name: "pk",
DataType: schemapb.DataType_VarChar,
IsPrimaryKey: true,
},
},
}
collector, err := NewPkStatsCollector(collectionID, varcharSchema, 100)
require.NoError(t, err)
// Create test record with varchar pk
fields := []arrow.Field{
{Name: "pk", Type: arrow.BinaryTypes.String},
}
arrowSchema := arrow.NewSchema(fields, nil)
builder := array.NewRecordBuilder(memory.DefaultAllocator, arrowSchema)
defer builder.Release()
pkBuilder := builder.Field(0).(*array.StringBuilder)
for i := 0; i < 10; i++ {
pkBuilder.Append(fmt.Sprintf("key_%d", i))
}
rec := builder.NewRecord()
field2Col := map[FieldID]int{100: 0}
record := NewSimpleArrowRecord(rec, field2Col)
err = collector.Collect(record)
assert.NoError(t, err)
})
}
func TestBm25StatsCollector(t *testing.T) {
schema := &schemapb.CollectionSchema{
Fields: []*schemapb.FieldSchema{
{FieldID: common.RowIDField, DataType: schemapb.DataType_Int64},
{FieldID: common.TimeStampField, DataType: schemapb.DataType_Int64},
{
FieldID: 100,
Name: "text",
DataType: schemapb.DataType_VarChar,
},
},
Functions: []*schemapb.FunctionSchema{
{
Name: "bm25_function",
Type: schemapb.FunctionType_BM25,
InputFieldIds: []int64{100},
OutputFieldIds: []int64{101},
OutputFieldNames: []string{"bm25_field"},
},
},
}
t.Run("collect bm25 stats", func(t *testing.T) {
collector := NewBm25StatsCollector(schema)
assert.NotNil(t, collector)
assert.NotNil(t, collector.bm25Stats)
})
t.Run("digest with empty stats", func(t *testing.T) {
collector := NewBm25StatsCollector(schema)
alloc := allocator.NewLocalAllocator(1, 100)
writer := func(blobs []*Blob) error { return nil }
_, err := collector.Digest(1, 1, 2, "/tmp", 10, alloc, writer)
assert.NoError(t, err)
})
}
func TestNewPkStatsCollector_NoPkField(t *testing.T) {
schema := &schemapb.CollectionSchema{
Fields: []*schemapb.FieldSchema{
{FieldID: common.RowIDField, DataType: schemapb.DataType_Int64},
{FieldID: common.TimeStampField, DataType: schemapb.DataType_Int64},
},
}
collector, err := NewPkStatsCollector(1, schema, 100)
assert.Error(t, err)
assert.Nil(t, collector)
}
func TestPkStatsCollector_DigestEndToEnd(t *testing.T) {
collectionID := int64(1)
partitionID := int64(2)
segmentID := int64(3)
schema := &schemapb.CollectionSchema{
Fields: []*schemapb.FieldSchema{
{
FieldID: 100,
Name: "pk",
DataType: schemapb.DataType_Int64,
IsPrimaryKey: true,
},
},
}
collector, err := NewPkStatsCollector(collectionID, schema, 100)
require.NoError(t, err)
// Create test record
fields := []arrow.Field{
{Name: "pk", Type: arrow.PrimitiveTypes.Int64},
}
arrowSchema := arrow.NewSchema(fields, nil)
builder := array.NewRecordBuilder(memory.DefaultAllocator, arrowSchema)
defer builder.Release()
pkBuilder := builder.Field(0).(*array.Int64Builder)
for i := 0; i < 10; i++ {
pkBuilder.Append(int64(i))
}
rec := builder.NewRecord()
field2Col := map[FieldID]int{100: 0}
record := NewSimpleArrowRecord(rec, field2Col)
err = collector.Collect(record)
require.NoError(t, err)
alloc := allocator.NewLocalAllocator(1, 100)
var writtenBlobs []*Blob
writer := func(blobs []*Blob) error {
writtenBlobs = blobs
return nil
}
// Test Digest which includes writing
binlogMap, err := collector.Digest(collectionID, partitionID, segmentID,
"/tmp", 10, alloc, writer)
assert.NoError(t, err)
assert.NotNil(t, binlogMap)
assert.Len(t, binlogMap, 1)
binlog := binlogMap[100]
assert.NotNil(t, binlog)
assert.Equal(t, int64(100), binlog.FieldID)
assert.Len(t, binlog.Binlogs, 1)
assert.Contains(t, binlog.Binlogs[0].LogPath, "stats_log")
assert.NotNil(t, writtenBlobs)
assert.Len(t, writtenBlobs, 1)
}
func TestBm25StatsCollector_DigestEndToEnd(t *testing.T) {
schema := &schemapb.CollectionSchema{
Fields: []*schemapb.FieldSchema{
{FieldID: 100, Name: "text", DataType: schemapb.DataType_VarChar},
},
Functions: []*schemapb.FunctionSchema{
{
Name: "bm25_function",
Type: schemapb.FunctionType_BM25,
InputFieldIds: []int64{100},
OutputFieldIds: []int64{101},
OutputFieldNames: []string{"bm25_field"},
},
},
}
collector := NewBm25StatsCollector(schema)
alloc := allocator.NewLocalAllocator(1, 100)
writer := func(blobs []*Blob) error { return nil }
// Test with empty stats
_, err := collector.Digest(1, 2, 3, "/tmp", 10, alloc, writer)
assert.NoError(t, err)
}