mirror of
https://gitee.com/milvus-io/milvus.git
synced 2025-12-06 17:18:35 +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>
84 lines
2.6 KiB
Go
84 lines
2.6 KiB
Go
package storage
|
|
|
|
import (
|
|
"fmt"
|
|
"strconv"
|
|
|
|
"github.com/apache/arrow/go/v17/arrow"
|
|
|
|
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
|
|
"github.com/milvus-io/milvus/internal/storagev2/packed"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/merr"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/typeutil"
|
|
)
|
|
|
|
func ConvertToArrowSchema(schema *schemapb.CollectionSchema, useFieldID bool) (*arrow.Schema, error) {
|
|
fieldCount := typeutil.GetTotalFieldsNum(schema)
|
|
arrowFields := make([]arrow.Field, 0, fieldCount)
|
|
appendArrowField := func(field *schemapb.FieldSchema) error {
|
|
if serdeMap[field.DataType].arrowType == nil {
|
|
return merr.WrapErrParameterInvalidMsg("unknown field data type [%s] for field [%s]", field.DataType, field.GetName())
|
|
}
|
|
var dim int
|
|
switch field.DataType {
|
|
case schemapb.DataType_BinaryVector, schemapb.DataType_Float16Vector, schemapb.DataType_BFloat16Vector,
|
|
schemapb.DataType_Int8Vector, schemapb.DataType_FloatVector, schemapb.DataType_ArrayOfVector:
|
|
var err error
|
|
dim, err = GetDimFromParams(field.TypeParams)
|
|
if err != nil {
|
|
return merr.WrapErrParameterInvalidMsg("dim not found in field [%s] params", field.GetName())
|
|
}
|
|
default:
|
|
dim = 0
|
|
}
|
|
|
|
elementType := schemapb.DataType_None
|
|
if field.DataType == schemapb.DataType_ArrayOfVector {
|
|
elementType = field.GetElementType()
|
|
}
|
|
|
|
arrowType := serdeMap[field.DataType].arrowType(dim, elementType)
|
|
arrowField := ConvertToArrowField(field, arrowType, useFieldID)
|
|
|
|
// Add extra metadata for ArrayOfVector
|
|
if field.DataType == schemapb.DataType_ArrayOfVector {
|
|
arrowField.Metadata = arrow.NewMetadata(
|
|
[]string{packed.ArrowFieldIdMetadataKey, "elementType", "dim"},
|
|
[]string{strconv.Itoa(int(field.GetFieldID())), strconv.Itoa(int(elementType)), strconv.Itoa(dim)},
|
|
)
|
|
}
|
|
|
|
arrowFields = append(arrowFields, arrowField)
|
|
return nil
|
|
}
|
|
for _, field := range schema.GetFields() {
|
|
if err := appendArrowField(field); err != nil {
|
|
return nil, err
|
|
}
|
|
}
|
|
|
|
for _, structField := range schema.GetStructArrayFields() {
|
|
for _, field := range structField.GetFields() {
|
|
if err := appendArrowField(field); err != nil {
|
|
return nil, err
|
|
}
|
|
}
|
|
}
|
|
|
|
return arrow.NewSchema(arrowFields, nil), nil
|
|
}
|
|
|
|
func ConvertToArrowField(field *schemapb.FieldSchema, dataType arrow.DataType, useFieldID bool) arrow.Field {
|
|
f := arrow.Field{
|
|
Type: dataType,
|
|
Metadata: arrow.NewMetadata([]string{packed.ArrowFieldIdMetadataKey}, []string{strconv.Itoa(int(field.GetFieldID()))}),
|
|
Nullable: field.GetNullable(),
|
|
}
|
|
if useFieldID { // use fieldID as name when specified
|
|
f.Name = fmt.Sprintf("%d", field.GetFieldID())
|
|
} else {
|
|
f.Name = field.GetName()
|
|
}
|
|
return f
|
|
}
|