mirror of
https://gitee.com/milvus-io/milvus.git
synced 2026-01-07 19:31:51 +08:00
issue: #44358 Implement complete snapshot management system including creation, deletion, listing, description, and restoration capabilities across all system components. Key features: - Create snapshots for entire collections - Drop snapshots by name with proper cleanup - List snapshots with collection filtering - Describe snapshot details and metadata Components added/modified: - Client SDK with full snapshot API support and options - DataCoord snapshot service with metadata management - Proxy layer with task-based snapshot operations - Protocol buffer definitions for snapshot RPCs - Comprehensive unit tests with mockey framework - Integration tests for end-to-end validation Technical implementation: - Snapshot metadata storage in etcd with proper indexing - File-based snapshot data persistence in object storage - Garbage collection integration for snapshot cleanup - Error handling and validation across all operations - Thread-safe operations with proper locking mechanisms <!-- This is an auto-generated comment: release notes by coderabbit.ai --> - Core invariant/assumption: snapshots are immutable point‑in‑time captures identified by (collection, snapshot name/ID); etcd snapshot metadata is authoritative for lifecycle (PENDING → COMMITTED → DELETING) and per‑segment manifests live in object storage (Avro / StorageV2). GC and restore logic must see snapshotRefIndex loaded (snapshotMeta.IsRefIndexLoaded) before reclaiming or relying on segment/index files. - New capability added: full end‑to‑end snapshot subsystem — client SDK APIs (Create/Drop/List/Describe/Restore + restore job queries), DataCoord SnapshotWriter/Reader (Avro + StorageV2 manifests), snapshotMeta in meta, SnapshotManager orchestration (create/drop/describe/list/restore), copy‑segment restore tasks/inspector/checker, proxy & RPC surface, GC integration, and docs/tests — enabling point‑in‑time collection snapshots persisted to object storage and restorations orchestrated across components. - Logic removed/simplified and why: duplicated recursive compaction/delta‑log traversal and ad‑hoc lookup code were consolidated behind two focused APIs/owners (Handler.GetDeltaLogFromCompactTo for delta traversal and SnapshotManager/SnapshotReader for snapshot I/O). MixCoord/coordinator broker paths were converted to thin RPC proxies. This eliminates multiple implementations of the same traversal/lookup, reducing divergence and simplifying responsibility boundaries. - Why this does NOT introduce data loss or regressions: snapshot create/drop use explicit two‑phase semantics (PENDING → COMMIT/DELETING) with SnapshotWriter writing manifests and metadata before commit; GC uses snapshotRefIndex guards and IsRefIndexLoaded/GetSnapshotBySegment/GetSnapshotByIndex checks to avoid removing referenced files; restore flow pre‑allocates job IDs, validates resources (partitions/indexes), performs rollback on failure (rollbackRestoreSnapshot), and converts/updates segment/index metadata only after successful copy tasks. Extensive unit and integration tests exercise pending/deleting/GC/restore/error paths to ensure idempotence and protection against premature deletion. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: Wei Liu <wei.liu@zilliz.com>
124 lines
4.3 KiB
Go
124 lines
4.3 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 (
|
|
"context"
|
|
"io"
|
|
|
|
"github.com/minio/minio-go/v7"
|
|
"go.uber.org/zap"
|
|
|
|
"github.com/milvus-io/milvus/pkg/v2/log"
|
|
"github.com/milvus-io/milvus/pkg/v2/objectstorage"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/paramtable"
|
|
)
|
|
|
|
var _ ObjectStorage = (*MinioObjectStorage)(nil)
|
|
|
|
type MinioObjectStorage struct {
|
|
*minio.Client
|
|
}
|
|
|
|
type ObjectReader struct {
|
|
*minio.Object
|
|
}
|
|
|
|
func (or *ObjectReader) Size() (int64, error) {
|
|
stat, err := or.Stat()
|
|
if err != nil {
|
|
return -1, err
|
|
}
|
|
return stat.Size, nil
|
|
}
|
|
|
|
func newMinioObjectStorageWithConfig(ctx context.Context, c *objectstorage.Config) (*MinioObjectStorage, error) {
|
|
minIOClient, err := objectstorage.NewMinioClient(ctx, c)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
return &MinioObjectStorage{minIOClient}, nil
|
|
}
|
|
|
|
func (minioObjectStorage *MinioObjectStorage) GetObject(ctx context.Context, bucketName, objectName string, offset int64, size int64) (FileReader, error) {
|
|
opts := minio.GetObjectOptions{}
|
|
if offset > 0 {
|
|
err := opts.SetRange(offset, offset+size-1)
|
|
if err != nil {
|
|
log.Warn("failed to set range", zap.String("bucket", bucketName), zap.String("path", objectName), zap.Error(err))
|
|
return nil, checkObjectStorageError(objectName, err)
|
|
}
|
|
}
|
|
object, err := minioObjectStorage.Client.GetObject(ctx, bucketName, objectName, opts)
|
|
if err != nil {
|
|
return nil, checkObjectStorageError(objectName, err)
|
|
}
|
|
return &ObjectReader{
|
|
Object: object,
|
|
}, nil
|
|
}
|
|
|
|
func (minioObjectStorage *MinioObjectStorage) PutObject(ctx context.Context, bucketName, objectName string, reader io.Reader, objectSize int64) error {
|
|
_, err := minioObjectStorage.Client.PutObject(ctx, bucketName, objectName, reader, objectSize, minio.PutObjectOptions{})
|
|
return checkObjectStorageError(objectName, err)
|
|
}
|
|
|
|
func (minioObjectStorage *MinioObjectStorage) StatObject(ctx context.Context, bucketName, objectName string) (int64, error) {
|
|
info, err := minioObjectStorage.Client.StatObject(ctx, bucketName, objectName, minio.StatObjectOptions{})
|
|
return info.Size, checkObjectStorageError(objectName, err)
|
|
}
|
|
|
|
func (minioObjectStorage *MinioObjectStorage) WalkWithObjects(ctx context.Context, bucketName string, prefix string, recursive bool, walkFunc ChunkObjectWalkFunc) (err error) {
|
|
// if minio has lots of objects under the provided path
|
|
// recursive = true may timeout during the recursive browsing the objects.
|
|
// See also: https://github.com/milvus-io/milvus/issues/19095
|
|
// So we can change the `ListObjectsMaxKeys` to limit the max keys by batch to avoid timeout.
|
|
in := minioObjectStorage.Client.ListObjects(ctx, bucketName, minio.ListObjectsOptions{
|
|
Prefix: prefix,
|
|
Recursive: recursive,
|
|
MaxKeys: paramtable.Get().MinioCfg.ListObjectsMaxKeys.GetAsInt(),
|
|
})
|
|
|
|
for object := range in {
|
|
if object.Err != nil {
|
|
return object.Err
|
|
}
|
|
if !walkFunc(&ChunkObjectInfo{FilePath: object.Key, ModifyTime: object.LastModified}) {
|
|
return nil
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (minioObjectStorage *MinioObjectStorage) RemoveObject(ctx context.Context, bucketName, objectName string) error {
|
|
err := minioObjectStorage.Client.RemoveObject(ctx, bucketName, objectName, minio.RemoveObjectOptions{})
|
|
return checkObjectStorageError(objectName, err)
|
|
}
|
|
|
|
func (minioObjectStorage *MinioObjectStorage) CopyObject(ctx context.Context, bucketName, srcObjectName, dstObjectName string) error {
|
|
srcOpts := minio.CopySrcOptions{
|
|
Bucket: bucketName,
|
|
Object: srcObjectName,
|
|
}
|
|
dstOpts := minio.CopyDestOptions{
|
|
Bucket: bucketName,
|
|
Object: dstObjectName,
|
|
}
|
|
_, err := minioObjectStorage.Client.CopyObject(ctx, dstOpts, srcOpts)
|
|
return checkObjectStorageError(dstObjectName, err)
|
|
}
|