milvus/internal/storage/sort_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

200 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 storage
import (
"testing"
"github.com/apache/arrow/go/v17/arrow/array"
"github.com/stretchr/testify/assert"
"github.com/milvus-io/milvus/pkg/v2/common"
)
func TestSort(t *testing.T) {
const batchSize = 64 * 1024 * 1024
getReaders := func() []RecordReader {
blobs, err := generateTestDataWithSeed(10, 3)
assert.NoError(t, err)
reader10 := newIterativeCompositeBinlogRecordReader(generateTestSchema(), nil, MakeBlobsReader(blobs))
blobs, err = generateTestDataWithSeed(20, 3)
assert.NoError(t, err)
reader20 := newIterativeCompositeBinlogRecordReader(generateTestSchema(), nil, MakeBlobsReader(blobs))
rr := []RecordReader{reader20, reader10}
return rr
}
lastPK := int64(-1)
rw := &MockRecordWriter{
writefn: func(r Record) error {
pk := r.Column(common.RowIDField).(*array.Int64).Value(0)
assert.Greater(t, pk, lastPK)
lastPK = pk
return nil
},
closefn: func() error {
lastPK = int64(-1)
return nil
},
}
t.Run("sort", func(t *testing.T) {
gotNumRows, err := Sort(batchSize, generateTestSchema(), getReaders(), rw, func(r Record, ri, i int) bool {
return true
}, []int64{common.RowIDField})
assert.NoError(t, err)
assert.Equal(t, 6, gotNumRows)
err = rw.Close()
assert.NoError(t, err)
})
t.Run("sort with predicate", func(t *testing.T) {
gotNumRows, err := Sort(batchSize, generateTestSchema(), getReaders(), rw, func(r Record, ri, i int) bool {
pk := r.Column(common.RowIDField).(*array.Int64).Value(i)
return pk >= 20
}, []int64{common.RowIDField})
assert.NoError(t, err)
assert.Equal(t, 3, gotNumRows)
err = rw.Close()
assert.NoError(t, err)
})
}
func TestMergeSort(t *testing.T) {
getReaders := func() []RecordReader {
blobs, err := generateTestDataWithSeed(1000, 5000)
assert.NoError(t, err)
reader10 := newIterativeCompositeBinlogRecordReader(generateTestSchema(), nil, MakeBlobsReader(blobs))
blobs, err = generateTestDataWithSeed(4000, 5000)
assert.NoError(t, err)
reader20 := newIterativeCompositeBinlogRecordReader(generateTestSchema(), nil, MakeBlobsReader(blobs))
rr := []RecordReader{reader20, reader10}
return rr
}
lastPK := int64(-1)
rw := &MockRecordWriter{
writefn: func(r Record) error {
pk := r.Column(common.RowIDField).(*array.Int64).Value(0)
assert.Greater(t, pk, lastPK)
lastPK = pk
return nil
},
closefn: func() error {
lastPK = int64(-1)
return nil
},
}
const batchSize = 64 * 1024 * 1024
t.Run("merge sort", func(t *testing.T) {
gotNumRows, err := MergeSort(batchSize, generateTestSchema(), getReaders(), rw, func(r Record, ri, i int) bool {
return true
}, []int64{common.RowIDField})
assert.NoError(t, err)
assert.Equal(t, 10000, gotNumRows)
err = rw.Close()
assert.NoError(t, err)
})
t.Run("merge sort with predicate", func(t *testing.T) {
gotNumRows, err := MergeSort(batchSize, generateTestSchema(), getReaders(), rw, func(r Record, ri, i int) bool {
pk := r.Column(common.RowIDField).(*array.Int64).Value(i)
// cover a single record (1024 rows) that is deleted, or the last data in the record is deleted
// index 1023 is deleted. records (1024-2048) and (5000-6023) are all deleted
return pk < 2000 || (pk >= 3050 && pk < 5000) || pk >= 7000
}, []int64{common.RowIDField})
assert.NoError(t, err)
assert.Equal(t, 5950, gotNumRows)
err = rw.Close()
assert.NoError(t, err)
})
}
// Benchmark sort
func BenchmarkSort(b *testing.B) {
batch := 500000
blobs, err := generateTestDataWithSeed(batch, batch)
assert.NoError(b, err)
reader10 := newIterativeCompositeBinlogRecordReader(generateTestSchema(), nil, MakeBlobsReader(blobs))
blobs, err = generateTestDataWithSeed(batch*2+1, batch)
assert.NoError(b, err)
reader20 := newIterativeCompositeBinlogRecordReader(generateTestSchema(), nil, MakeBlobsReader(blobs))
rr := []RecordReader{reader20, reader10}
rw := &MockRecordWriter{
writefn: func(r Record) error {
return nil
},
closefn: func() error {
return nil
},
}
const batchSize = 64 * 1024 * 1024
b.ResetTimer()
b.Run("sort", func(b *testing.B) {
for i := 0; i < b.N; i++ {
Sort(batchSize, generateTestSchema(), rr, rw, func(r Record, ri, i int) bool {
return true
}, []int64{common.RowIDField})
}
})
}
func TestSortByMoreThanOneField(t *testing.T) {
const batchSize = 10000
sortByFieldIDs := []int64{common.RowIDField, common.TimeStampField}
blobs, err := generateTestDataWithSeed(10, batchSize)
assert.NoError(t, err)
reader10 := newIterativeCompositeBinlogRecordReader(generateTestSchema(), nil, MakeBlobsReader(blobs))
blobs, err = generateTestDataWithSeed(20, batchSize)
assert.NoError(t, err)
reader20 := newIterativeCompositeBinlogRecordReader(generateTestSchema(), nil, MakeBlobsReader(blobs))
rr := []RecordReader{reader20, reader10}
lastPK := int64(-1)
lastTS := int64(-1)
rw := &MockRecordWriter{
writefn: func(r Record) error {
pk := r.Column(common.RowIDField).(*array.Int64).Value(0)
ts := r.Column(common.TimeStampField).(*array.Int64).Value(0)
assert.True(t, pk > lastPK || (pk == lastPK && ts > lastTS))
lastPK = pk
return nil
},
closefn: func() error {
lastPK = int64(-1)
return nil
},
}
gotNumRows, err := Sort(batchSize, generateTestSchema(), rr, rw, func(r Record, ri, i int) bool {
return true
}, sortByFieldIDs)
assert.NoError(t, err)
assert.Equal(t, batchSize*2, gotNumRows)
assert.NoError(t, rw.Close())
}