mirror of
https://gitee.com/milvus-io/milvus.git
synced 2025-12-06 17:18:35 +08:00
Related #44956 This commit integrates the Storage V2 FFI (Foreign Function Interface) interface throughout the Milvus codebase, enabling unified storage access through the Loon FFI layer. This is a significant step towards standardizing storage operations across different storage versions. 1. Configuration Support - **configs/milvus.yaml**: Added `useLoonFFI` configuration flag under `common.storage.file.splitByAvgSize` section - Allows runtime toggle between traditional binlog readers and new FFI-based manifest readers - Default: `false` (maintains backward compatibility) 2. Core FFI Infrastructure Enhanced Utilities (internal/core/src/storage/loon_ffi/util.cpp/h) - **ToCStorageConfig()**: Converts Go's `StorageConfig` to C's `CStorageConfig` struct for FFI calls - **GetManifest()**: Parses manifest JSON and retrieves latest column groups using FFI - Accepts manifest path with `base_path` and `ver` fields - Calls `get_latest_column_groups()` FFI function - Returns column group information as string - Comprehensive error handling for JSON parsing and FFI errors 3. Dependency Updates - **internal/core/thirdparty/milvus-storage/CMakeLists.txt**: - Updated milvus-storage version from `0883026` to `302143c` - Ensures compatibility with latest FFI interfaces 4. Data Coordinator Changes All compaction task builders now include manifest path in segment binlogs: - **compaction_task_clustering.go**: Added `Manifest: segInfo.GetManifestPath()` to segment binlogs - **compaction_task_l0.go**: Added manifest path to both L0 segment selection and compaction plan building - **compaction_task_mix.go**: Added manifest path to mixed compaction segment binlogs - **meta.go**: Updated metadata completion logic: - `completeClusterCompactionMutation()`: Set `ManifestPath` in new segment info - `completeMixCompactionMutation()`: Preserve manifest path in compacted segments - `completeSortCompactionMutation()`: Include manifest path in sorted segments 5. Data Node Compactor Enhancements All compactors updated to support dual-mode reading (binlog vs manifest): 6. Flush & Sync Manager Updates Pack Writer V2 (pack_writer_v2.go) - **BulkPackWriterV2.Write()**: Extended return signature to include `manifest string` - Implementation: - Generate manifest path: `path.Join(pack.segmentID, "manifest.json")` - Write packed data using FFI-based writer - Return manifest path along with binlogs, deltas, and stats Task Handling (task.go) - Updated all sync task result handling to accommodate new manifest return value - Ensured backward compatibility for callers not using manifest 7. Go Storage Layer Integration New Interfaces and Implementations - **record_reader.go**: Interface for unified record reading across storage versions - **record_writer.go**: Interface for unified record writing across storage versions - **binlog_record_writer.go**: Concrete implementation for traditional binlog-based writing Enhanced Schema Support (schema.go, schema_test.go) - Schema conversion utilities to support FFI-based storage operations - Ensures proper Arrow schema mapping for V2 storage Serialization Updates - **serde.go, serde_events.go, serde_events_v2.go**: Updated to work with new reader/writer interfaces - Test files updated to validate dual-mode serialization 8. Storage V2 Packed Format FFI Common (storagev2/packed/ffi_common.go) - Common FFI utilities and type conversions for packed storage format Packed Writer FFI (storagev2/packed/packed_writer_ffi.go) - FFI-based implementation of packed writer - Integrates with Loon storage layer for efficient columnar writes Packed Reader FFI (storagev2/packed/packed_reader_ffi.go) - Already existed, now complemented by writer implementation 9. Protocol Buffer Updates data_coord.proto & datapb/data_coord.pb.go - Added `manifest` field to compaction segment messages - Enables passing manifest metadata through compaction pipeline worker.proto & workerpb/worker.pb.go - Added compaction parameter for `useLoonFFI` flag - Allows workers to receive FFI configuration from coordinator 10. Parameter Configuration component_param.go - Added `UseLoonFFI` parameter to compaction configuration - Reads from `common.storage.file.useLoonFFI` config path - Default: `false` for safe rollout 11. Test Updates - **clustering_compactor_storage_v2_test.go**: Updated signatures to handle manifest return value - **mix_compactor_storage_v2_test.go**: Updated test helpers for manifest support - **namespace_compactor_test.go**: Adjusted writer calls to expect manifest - **pack_writer_v2_test.go**: Validated manifest generation in pack writing This integration follows a **dual-mode approach**: 1. **Legacy Path**: Traditional binlog-based reading/writing (when `useLoonFFI=false` or no manifest) 2. **FFI Path**: Manifest-based reading/writing through Loon FFI (when `useLoonFFI=true` and manifest exists) --------- Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
83 lines
2.6 KiB
Go
83 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{
|
|
Name: field.GetName(),
|
|
Type: dataType,
|
|
Metadata: arrow.NewMetadata([]string{packed.ArrowFieldIdMetadataKey}, []string{strconv.Itoa(int(field.GetFieldID()))}),
|
|
Nullable: field.GetNullable(),
|
|
}
|
|
if useFieldID {
|
|
field.Name = fmt.Sprintf("%d", field.GetFieldID())
|
|
}
|
|
return f
|
|
}
|