管理快照Compatible with Milvus 3.0.x
在本指南中,您將學習如何建立和管理快照,包括
建立快照
在建立快照之前,建議您停止向目標集合寫入資料,並呼叫 `flush() ` 以避免可能的資料遺失。
呼叫 `flush() ` 並非強制要求,但強烈建議執行此步驟以避免資料遺失。若跳過此步驟,快照將僅包含已排空的資料。
為快照命名時,請使用清晰且具描述性的名稱,例如"daily_backup_20240101" 或"v2.1_production_release" ,並避免使用通用術語,例如"backup1" 和"test" 。請明智地使用快照名稱,以區分不同版本、環境和階段的快照。
以下程式碼範例假設您已經有一個名為my_collection 的集合。
from pymilvus import MilvusClient
client = MilvusClient(
uri="http://localhost:19530",
token="root:Milvus"
)
# Recommended: Flush data before creating snapshot to ensure all data is included
client.flush(collection_name="my_collection")
# Create snapshot for entire collection
client.create_snapshot(
collection_name="my_collection",
snapshot_name="backup_20240101",
description="Daily backup for January 1st, 2024"
)
// java
import (
"context"
"github.com/milvus-io/milvus/client/v2/milvusclient"
)
client, err := milvusclient.New(context.Background(), &milvusclient.ClientConfig{
Address: "localhost:19530",
Token: "root:Milvus",
})
// Recommended: Flush data before creating snapshot to ensure all data is included
err = client.Flush(context.Background(), milvusclient.NewFlushOption("my_collection"))
if err != nil {
log.Fatal(err)
}
// Create snapshot
createOpt := milvusclient.NewCreateSnapshotOption("backup_20240101", "my_collection").
WithDescription("Daily backup for January 1st, 2024")
err = client.CreateSnapshot(context.Background(), createOpt)
// node.js
# restful
列出快照
您可以列出現有快照的名稱。
# List all snapshots for a collection
snapshots = client.list_snapshots(
collection_name="my_collection"
)
// java
// List snapshots for collection
listOpt := milvusclient.NewListSnapshotsOption().
WithCollectionName("my_collection")
snapshots, err := client.ListSnapshots(context.Background(), listOpt)
// node.js
# bash
檢視快照詳細資訊
您可以取得特定快照的詳細資訊。
snapshot_info = client.describe_snapshot(
snapshot_name="backup_20240101",
include_collection_info=True
)
print(f"Snapshot ID: {snapshot_info.id}")
print(f"Collection: {snapshot_info.collection_name}")
print(f"Created: {snapshot_info.create_ts}")
print(f"Description: {snapshot_info.description}")
// java
describeOpt := milvusclient.NewDescribeSnapshotOption("backup_20240101")
resp, err := client.DescribeSnapshot(context.Background(), describeOpt)
fmt.Printf("Snapshot ID: %d\n", resp.GetSnapshotInfo().GetId())
fmt.Printf("Collection: %s\n", resp.GetSnapshotInfo().GetCollectionName())
// node.js
# restful
固定/解除固定快照資料
在還原過程中,您可以將快照固定,以暫時保護其底層資料免於被垃圾回收;亦可解除固定以釋放資料。
您亦可為固定操作設定有效期限 (TTL),以便在期限屆滿時釋放已固定的資料。
pin_id = client.pin_snapshot_data(
snapshot_name="backup_20240101",
collection_name="my_collection",
ttl_seconds=3600,
)
client.unpin_snapshot_data(
pin_id=pin_id
)
// java
pinID, err := client.PinSnapshotData(
context.Background(),
milvusclient.NewPinSnapshotDataOption("backup_20240101", "my_collection").WithTTL(3600),
)
if err != nil {
log.Fatal(err)
}
defer func() {
_ = client.UnpinSnapshotData(
context.Background(),
milvusclient.NewUnpinSnapshotDataOption(pinID),
)
}()
// Do work with pinned snapshot data.
// node.js
# restful
還原快照
您可以將快照還原至新的集合。此操作為非同步,並會傳回一個工作 ID 以供追蹤還原進度。
還原過程採用「複製區段」機制而非資料匯入,此方式更為高效,因為它
- 直接從快照儲存空間複製區段檔案(二進位日誌、增量日誌、索引檔案)
- 保留欄位 ID 和索引 ID,以確保與現有資料檔案的相容性
- 避免資料重寫與索引重建,從而顯著縮短還原時間,並
- 相較於傳統的備份與還原方法,效能提升 10 至 100 倍
要還原快照,請依下列步驟操作:
# Restore snapshot to new collection
job_id = client.restore_snapshot(
snapshot_name="backup_20240101",
collection_name="restored_collection",
)
// java
restoreOpt := milvusclient.NewRestoreSnapshotOption(
"backup_20240101",
"restored_collection"
)
jobID, err := client.RestoreSnapshot(context.Background(), restoreOpt)
if err != nil {
log.Fatal(err)
}
// node.js
# restful
有關監控還原工作進度的詳細資訊,請參閱「取得還原狀態」。
刪除快照
若快照已無使用需求,您可以刪除該快照。建議您定期刪除舊快照以節省儲存空間。
client.drop_snapshot(
snapshot_name="backup_20240101"
)
// java
dropOpt := milvusclient.NewDropSnapshotOption("backup_20240101")
err := client.DropSnapshot(context.Background(), dropOpt)
// node.js
# restful
列出還原工作
您可以使用此 API 取得已為目標集合建立的快照清單。
# List all restore jobs
jobs = client.list_restore_snapshot_jobs()
for job in jobs:
print(f"Job {job.job_id}: {job.snapshot_name} -> Collection {job.collection_id}")
print(f" State: {job.state}, Progress: {job.progress}%")
# List restore jobs for a specific collection
jobs = client.list_restore_snapshot_jobs(collection_name="my_collection")
// java
// List all restore jobs
listOpt := milvusclient.NewListRestoreSnapshotJobsOption()
jobs, err := client.ListRestoreSnapshotJobs(context.Background(), listOpt)
if err != nil {
log.Fatal(err)
}
for _, job := range jobs {
fmt.Printf("Job %d: %s -> Collection %d\n",
job.GetJobId(), job.GetSnapshotName(), job.GetCollectionId())
fmt.Printf(" State: %s, Progress: %d%%\n",
job.GetState(), job.GetProgress())
}
// List restore jobs for a specific collection
listOpt = milvusclient.NewListRestoreSnapshotJobsOption().
WithCollectionName("my_collection")
jobs, err = client.ListRestoreSnapshotJobs(context.Background(), listOpt)
// node.js
# restful
取得還原狀態
取得還原工作 ID 後,即可使用該 ID 查詢還原進度。
state = client.get_restore_snapshot_state(job_id=12345)
print(f"Job ID: {state.job_id}")
print(f"Snapshot Name: {state.snapshot_name}")
print(f"Collection ID: {state.collection_id}")
print(f"State: {state.state}")
print(f"Progress: {state.progress}%")
if state.state == "RestoreSnapshotFailed":
print(f"Failure Reason: {state.reason}")
print(f"Time Cost: {state.time_cost}ms")
// java
stateOpt := milvusclient.NewGetRestoreSnapshotStateOption(12345)
state, err := client.GetRestoreSnapshotState(context.Background(), stateOpt)
if err != nil {
log.Fatal(err)
}
fmt.Printf("Job ID: %d\n", state.GetJobId())
fmt.Printf("Snapshot Name: %s\n", state.GetSnapshotName())
fmt.Printf("Collection ID: %d\n", state.GetCollectionId())
fmt.Printf("State: %s\n", state.GetState())
fmt.Printf("Progress: %d%%\n", state.GetProgress())
if state.GetState() == milvuspb.RestoreSnapshotState_RestoreSnapshotFailed {
fmt.Printf("Failure Reason: %s\n", state.GetReason())
}
fmt.Printf("Time Cost: %dms\n", state.GetTimeCost())
// node.js
# restful