mirror of
https://gitee.com/milvus-io/milvus.git
synced 2025-12-07 01:28:27 +08:00
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>
229 lines
7.2 KiB
Go
229 lines
7.2 KiB
Go
package compactor
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"math"
|
|
"testing"
|
|
|
|
"github.com/apache/arrow/go/v17/arrow/array"
|
|
"github.com/stretchr/testify/mock"
|
|
"github.com/stretchr/testify/suite"
|
|
|
|
"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/metacache"
|
|
"github.com/milvus-io/milvus/internal/flushcommon/metacache/pkoracle"
|
|
"github.com/milvus-io/milvus/internal/flushcommon/syncmgr"
|
|
"github.com/milvus-io/milvus/internal/mocks/flushcommon/mock_util"
|
|
"github.com/milvus-io/milvus/internal/storage"
|
|
"github.com/milvus-io/milvus/internal/storagecommon"
|
|
"github.com/milvus-io/milvus/internal/storagev2/packed"
|
|
"github.com/milvus-io/milvus/internal/util/initcore"
|
|
"github.com/milvus-io/milvus/pkg/v2/common"
|
|
"github.com/milvus-io/milvus/pkg/v2/objectstorage"
|
|
"github.com/milvus-io/milvus/pkg/v2/proto/datapb"
|
|
"github.com/milvus-io/milvus/pkg/v2/proto/indexpb"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/paramtable"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/tsoutil"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/typeutil"
|
|
)
|
|
|
|
type NamespaceCompactorTestSuite struct {
|
|
suite.Suite
|
|
binlogIO *mock_util.MockBinlogIO
|
|
schema *schemapb.CollectionSchema
|
|
sortedSegments []*datapb.CompactionSegmentBinlogs
|
|
}
|
|
|
|
func (s *NamespaceCompactorTestSuite) SetupSuite() {
|
|
paramtable.Get().Init(paramtable.NewBaseTable())
|
|
paramtable.Get().Save("common.storageType", "local")
|
|
paramtable.Get().Save("common.storage.enableV2", "true")
|
|
initcore.InitStorageV2FileSystem(paramtable.Get())
|
|
|
|
s.binlogIO = mock_util.NewMockBinlogIO(s.T())
|
|
s.binlogIO.EXPECT().Upload(mock.Anything, mock.Anything).Return(nil)
|
|
s.schema = &schemapb.CollectionSchema{
|
|
Fields: []*schemapb.FieldSchema{
|
|
{
|
|
FieldID: common.RowIDField,
|
|
Name: "row_id",
|
|
DataType: schemapb.DataType_Int64,
|
|
},
|
|
{
|
|
FieldID: common.TimeStampField,
|
|
Name: "timestamp",
|
|
DataType: schemapb.DataType_Int64,
|
|
},
|
|
{
|
|
FieldID: 100,
|
|
Name: "pk",
|
|
DataType: schemapb.DataType_Int64,
|
|
IsPrimaryKey: true,
|
|
},
|
|
{
|
|
FieldID: 101,
|
|
Name: "namespace",
|
|
DataType: schemapb.DataType_Int64,
|
|
},
|
|
},
|
|
}
|
|
s.setupSortedSegments()
|
|
}
|
|
|
|
func (s *NamespaceCompactorTestSuite) setupSortedSegments() {
|
|
num := 3
|
|
rows := 10000
|
|
collectionID := int64(100)
|
|
partitionID := int64(100)
|
|
alloc := allocator.NewLocalAllocator(0, math.MaxInt64)
|
|
|
|
for i := 0; i < num; i++ {
|
|
data, err := storage.NewInsertData(s.schema)
|
|
s.Require().NoError(err)
|
|
for j := 0; j < rows; j++ {
|
|
v := map[int64]interface{}{
|
|
common.RowIDField: int64(j),
|
|
common.TimeStampField: int64(tsoutil.ComposeTSByTime(getMilvusBirthday(), 0)),
|
|
100: int64(j),
|
|
101: int64(j),
|
|
}
|
|
data.Append(v)
|
|
}
|
|
pack := new(syncmgr.SyncPack).WithCollectionID(collectionID).WithPartitionID(partitionID).WithSegmentID(int64(i)).WithChannelName(fmt.Sprintf("by-dev-rootcoord-dml_0_%dv0", collectionID)).WithInsertData([]*storage.InsertData{data})
|
|
rootPath := paramtable.Get().LocalStorageCfg.Path.GetValue()
|
|
cm := storage.NewLocalChunkManager(objectstorage.RootPath(rootPath))
|
|
bfs := pkoracle.NewBloomFilterSet()
|
|
seg := metacache.NewSegmentInfo(&datapb.SegmentInfo{}, bfs, nil)
|
|
metacache.UpdateNumOfRows(int64(rows))(seg)
|
|
mc := metacache.NewMockMetaCache(s.T())
|
|
mc.EXPECT().Collection().Return(collectionID).Maybe()
|
|
mc.EXPECT().GetSchema(mock.Anything).Return(s.schema).Maybe()
|
|
mc.EXPECT().GetSegmentByID(int64(i)).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()
|
|
fields := typeutil.GetAllFieldSchemas(s.schema)
|
|
columnGroups := storagecommon.SplitColumns(fields, map[int64]storagecommon.ColumnStats{}, storagecommon.NewSelectedDataTypePolicy(), storagecommon.NewRemanentShortPolicy(-1))
|
|
bw := syncmgr.NewBulkPackWriterV2(mc, s.schema, cm, alloc, packed.DefaultWriteBufferSize, 0, &indexpb.StorageConfig{
|
|
StorageType: "local",
|
|
RootPath: rootPath,
|
|
}, columnGroups)
|
|
inserts, _, _, _, _, _, err := bw.Write(context.Background(), pack)
|
|
s.Require().NoError(err)
|
|
s.sortedSegments = append(s.sortedSegments, &datapb.CompactionSegmentBinlogs{
|
|
SegmentID: int64(i),
|
|
FieldBinlogs: storage.SortFieldBinlogs(inserts),
|
|
Deltalogs: []*datapb.FieldBinlog{},
|
|
StorageVersion: storage.StorageV2,
|
|
IsSorted: true,
|
|
})
|
|
}
|
|
}
|
|
|
|
func (s *NamespaceCompactorTestSuite) TestCompactSorted() {
|
|
plan := &datapb.CompactionPlan{
|
|
SegmentBinlogs: s.sortedSegments,
|
|
Schema: s.schema,
|
|
PreAllocatedSegmentIDs: &datapb.IDRange{
|
|
Begin: 0,
|
|
End: math.MaxInt64,
|
|
},
|
|
PreAllocatedLogIDs: &datapb.IDRange{
|
|
Begin: 0,
|
|
End: math.MaxInt64,
|
|
},
|
|
MaxSize: 1024 * 1024 * 1024,
|
|
}
|
|
params := compaction.GenParams()
|
|
sortedByFieldIDs := []int64{101, 100}
|
|
|
|
c := NewNamespaceCompactor(context.Background(), plan, s.binlogIO, params, sortedByFieldIDs)
|
|
result, err := c.Compact()
|
|
|
|
s.Require().NoError(err)
|
|
s.Require().Equal(datapb.CompactionTaskState_completed, result.State)
|
|
for _, segment := range result.GetSegments() {
|
|
s.assertSorted(segment, sortedByFieldIDs)
|
|
}
|
|
}
|
|
|
|
func (s *NamespaceCompactorTestSuite) assertSorted(segment *datapb.CompactionSegment, sortedByFieldIDs []int64) {
|
|
reader, err := storage.NewBinlogRecordReader(context.Background(), segment.GetInsertLogs(), s.schema, storage.WithVersion(segment.GetStorageVersion()), storage.WithStorageConfig(&indexpb.StorageConfig{
|
|
StorageType: "local",
|
|
RootPath: paramtable.Get().LocalStorageCfg.Path.GetValue(),
|
|
}))
|
|
s.Require().NoError(err)
|
|
records := make([]storage.Record, 0)
|
|
for {
|
|
record, err := reader.Next()
|
|
if err != nil {
|
|
break
|
|
}
|
|
record.Retain()
|
|
records = append(records, record)
|
|
}
|
|
|
|
cmps := make([]func(ri, i, rj, j int) int, 0)
|
|
for _, fieldID := range sortedByFieldIDs {
|
|
field := typeutil.GetField(s.schema, fieldID)
|
|
switch field.DataType {
|
|
case schemapb.DataType_Int64:
|
|
cmps = append(cmps, func(ri, i, rj, j int) int {
|
|
vi := records[ri].Column(fieldID).(*array.Int64).Value(i)
|
|
vj := records[rj].Column(fieldID).(*array.Int64).Value(j)
|
|
if vi < vj {
|
|
return -1
|
|
}
|
|
if vi > vj {
|
|
return 1
|
|
}
|
|
return 0
|
|
})
|
|
case schemapb.DataType_String:
|
|
cmps = append(cmps, func(ri, i, rj, j int) int {
|
|
vi := records[ri].Column(fieldID).(*array.String).Value(i)
|
|
vj := records[rj].Column(fieldID).(*array.String).Value(j)
|
|
if vi < vj {
|
|
return -1
|
|
}
|
|
if vi > vj {
|
|
return 1
|
|
}
|
|
return 0
|
|
})
|
|
default:
|
|
panic("unsupported data type")
|
|
}
|
|
}
|
|
|
|
prevri := -1
|
|
previ := -1
|
|
|
|
for ri := 0; ri < len(records); ri++ {
|
|
for i := 0; i < records[ri].Len(); i++ {
|
|
if prevri == -1 {
|
|
prevri = ri
|
|
previ = i
|
|
continue
|
|
}
|
|
for _, cmp := range cmps {
|
|
c := cmp(prevri, previ, ri, i)
|
|
s.Require().True(c <= 0, "not sorted")
|
|
if c < 0 {
|
|
break
|
|
}
|
|
}
|
|
prevri = ri
|
|
previ = i
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestNamespaceCompactorTestSuite(t *testing.T) {
|
|
suite.Run(t, new(NamespaceCompactorTestSuite))
|
|
}
|