操作步驟

1. 進入實例配置頁面。

   1. 登錄阿里云Milvus控制臺。

   2. 在左側導航欄，單擊Milvus實例。

   3. 在頂部菜單欄處，根據實際情況選擇地域。

   4. 在Milvus實例頁面，單擊目標實例名稱。

   5. 單擊實例配置頁簽。

2. 在實例配置輸入框內輸入需要覆蓋默認配置的參數，然后單擊保存配置。

   參數格式為YAML格式，相關配置參數示例如下所示。

   # Related configuration of rootCoord, used to handle data definition language (DDL) and data control language (DCL) requests
   rootCoord:
     maxDatabaseNum: 64 # Maximum number of database
     maxPartitionNum: 4096 # Maximum number of partitions in a collection
     minSegmentSizeToEnableIndex: 1024 # It's a threshold. When the segment size is less than this value, the segment will not be indexed
     importTaskExpiration: 900 # (in seconds) Duration after which an import task will expire (be killed). Default 900 seconds (15 minutes).
     importTaskRetention: 86400 # (in seconds) Milvus will keep the record of import tasks for at least `importTaskRetention` seconds. Default 86400, seconds (24 hours).
     grpc:
       serverMaxSendSize: 536870912
       serverMaxRecvSize: 268435456
       clientMaxSendSize: 268435456
       clientMaxRecvSize: 536870912
       
   # Related configuration of proxy, used to validate client requests and reduce the returned results.
   proxy:
     timeTickInterval: 200 # ms, the interval that proxy synchronize the time tick
     healthCheckTimeout: 3000 # ms, the interval that to do component healthy check
     maxNameLength: 255 # Maximum length of name for a collection or alias
     # Maximum number of fields in a collection.
     # As of today (2.2.0 and after) it is strongly DISCOURAGED to set maxFieldNum >= 64.
     # So adjust at your risk!
     maxFieldNum: 64
     maxTaskNum: 1024 # max task number of proxy task queue
     grpc:
       serverMaxSendSize: 268435456
       serverMaxRecvSize: 67108864
       clientMaxSendSize: 268435456
       clientMaxRecvSize: 67108864
   
   # Related configuration of queryCoord, used to manage topology and load balancing for the query nodes, and handoff from growing segments to sealed segments.
   queryCoord:
     autoHandoff: true # Enable auto handoff
     autoBalance: true # Enable auto balance
     balancer: ScoreBasedBalancer # Balancer to use
     overloadedMemoryThresholdPercentage: 90 # The threshold percentage that memory overload
     balanceIntervalSeconds: 60
     memoryUsageMaxDifferencePercentage: 30
     checkInterval: 1000
     channelTaskTimeout: 60000 # 1 minute
     segmentTaskTimeout: 120000 # 2 minute
     distPullInterval: 500
     heartbeatAvailableInterval: 10000 # 10s, Only QueryNodes which fetched heartbeats within the duration are available
     loadTimeoutSeconds: 600
     checkHandoffInterval: 5000
     grpc:
       serverMaxSendSize: 536870912
       serverMaxRecvSize: 268435456
       clientMaxSendSize: 268435456
       clientMaxRecvSize: 536870912
   
   # Related configuration of queryNode, used to run hybrid search between vector and scalar data.
   queryNode:
     dataSync:
       flowGraph:
         maxQueueLength: 16 # Maximum length of task queue in flowgraph
         maxParallelism: 1024 # Maximum number of tasks executed in parallel in the flowgraph
     stats:
       publishInterval: 1000 # Interval for querynode to report node information (milliseconds)
     segcore:
       cgoPoolSizeRatio: 2.0 # cgo pool size ratio to max read concurrency
       knowhereThreadPoolNumRatio: 4
       # Use more threads to make better use of SSD throughput in disk index.
       # This parameter is only useful when enable-disk = true.
       # And this value should be a number greater than 1 and less than 32.
       chunkRows: 128 # The number of vectors in a chunk.
       exprEvalBatchSize: 8192 # The batch size for executor get next
       interimIndex: # build a vector temperate index for growing segment or binlog to accelerate search
         enableIndex: true
         nlist: 128 # segment index nlist
         nprobe: 16 # nprobe to search segment, based on your accuracy requirement, must smaller than nlist
         memExpansionRate: 1.15 # the ratio of building interim index memory usage to raw data
     loadMemoryUsageFactor: 1 # The multiply factor of calculating the memory usage while loading segments
     enableDisk: false # enable querynode load disk index, and search on disk index
     maxDiskUsagePercentage: 95
     grouping:
       enabled: true
       maxNQ: 1000
       topKMergeRatio: 20
     scheduler:
       receiveChanSize: 10240
       unsolvedQueueSize: 10240
       # maxReadConcurrentRatio is the concurrency ratio of read task (search task and query task).
       # Max read concurrency would be the value of runtime.NumCPU * maxReadConcurrentRatio.
       # It defaults to 2.0, which means max read concurrency would be the value of runtime.NumCPU * 2.
       # Max read concurrency must greater than or equal to 1, and less than or equal to runtime.NumCPU * 100.
       # (0, 100]
       maxReadConcurrentRatio: 1
       cpuRatio: 10 # ratio used to estimate read task cpu usage.
       maxTimestampLag: 86400
       # read task schedule policy: fifo(by default), user-task-polling.
       scheduleReadPolicy:
         # fifo: A FIFO queue support the schedule.
         # user-task-polling:
         #     The user's tasks will be polled one by one and scheduled.
         #     Scheduling is fair on task granularity.
         #     The policy is based on the username for authentication.
         #     And an empty username is considered the same user.
         #     When there are no multi-users, the policy decay into FIFO
         name: fifo
         maxPendingTask: 10240
         # user-task-polling configure:
         taskQueueExpire: 60 # 1 min by default, expire time of inner user task queue since queue is empty.
         enableCrossUserGrouping: false # false by default Enable Cross user grouping when using user-task-polling policy. (close it if task of any user can not merge others).
         maxPendingTaskPerUser: 1024 # 50 by default, max pending task in scheduler per user.
     grpc:
       serverMaxSendSize: 536870912
       serverMaxRecvSize: 268435456
       clientMaxSendSize: 268435456
       clientMaxRecvSize: 536870912
   
   indexCoord:
     bindIndexNodeMode:
       enable: false
       withCred: false
     segment:
       minSegmentNumRowsToEnableIndex: 1024 # It's a threshold. When the segment num rows is less than this value, the segment will not be indexed
   
   indexNode:
     scheduler:
       buildParallel: 1
     enableDisk: true # enable index node build disk vector index
     maxDiskUsagePercentage: 95
     grpc:
       serverMaxSendSize: 536870912
       serverMaxRecvSize: 268435456
       clientMaxSendSize: 268435456
       clientMaxRecvSize: 536870912
   
   dataCoord:
     channel:
       watchTimeoutInterval: 300 # Timeout on watching channels (in seconds). Datanode tickler update watch progress will reset timeout timer.
       balanceSilentDuration: 300 # The duration before the channelBalancer on datacoord to run
       balanceInterval: 360 #The interval for the channelBalancer on datacoord to check balance status
     segment:
       maxSize: 1024 # Maximum size of a segment in MB
       diskSegmentMaxSize: 2048 # Maximum size of a segment in MB for collection which has Disk index
       sealProportion: 0.12
       # The time of the assignment expiration in ms
       # Warning! this parameter is an expert variable and closely related to data integrity. Without specific
       # target and solid understanding of the scenarios, it should not be changed. If it's necessary to alter
       # this parameter, make sure that the newly changed value is larger than the previous value used before restart
       # otherwise there could be a large possibility of data loss
       assignmentExpiration: 2000
       maxLife: 86400 # The max lifetime of segment in seconds, 24*60*60
       # If a segment didn't accept dml records in maxIdleTime and the size of segment is greater than
       # minSizeFromIdleToSealed, Milvus will automatically seal it.
       # The max idle time of segment in seconds, 10*60.
       maxIdleTime: 600
       minSizeFromIdleToSealed: 16 # The min size in MB of segment which can be idle from sealed.
       # The max number of binlog file for one segment, the segment will be sealed if
       # the number of binlog file reaches to max value.
       maxBinlogFileNumber: 32
       smallProportion: 0.5 # The segment is considered as "small segment" when its # of rows is smaller than
       # (smallProportion * segment max # of rows).
       # A compaction will happen on small segments if the segment after compaction will have
       compactableProportion: 0.85
       # over (compactableProportion * segment max # of rows) rows.
       # MUST BE GREATER THAN OR EQUAL TO <smallProportion>!!!
       # During compaction, the size of segment # of rows is able to exceed segment max # of rows by (expansionRate-1) * 100%.
       expansionRate: 1.25
       # Whether to enable levelzero segment
       enableLevelZero: false
     enableCompaction: true # Enable data segment compaction
     compaction:
       enableAutoCompaction: true
       rpcTimeout: 10 # compaction rpc request timeout in seconds
       maxParallelTaskNum: 10 # max parallel compaction task number
       indexBasedCompaction: true
   
       levelzero:
         forceTrigger:
           minSize: 8 # The minmum size in MB to force trigger a LevelZero Compaction
           deltalogMinNum: 10 # the minimum number of deltalog files to force trigger a LevelZero Compaction
   
     enableGarbageCollection: true
     gc:
       interval: 3600 # gc interval in seconds
       missingTolerance: 3600 # file meta missing tolerance duration in seconds, 3600
       dropTolerance: 10800 # file belongs to dropped entity tolerance duration in seconds. 10800
     enableActiveStandby: false
     grpc:
       serverMaxSendSize: 536870912
       serverMaxRecvSize: 268435456
       clientMaxSendSize: 268435456
       clientMaxRecvSize: 536870912
   
   dataNode:
     dataSync:
       flowGraph:
         maxQueueLength: 16 # Maximum length of task queue in flowgraph
         maxParallelism: 1024 # Maximum number of tasks executed in parallel in the flowgraph
       maxParallelSyncMgrTasks: 256 #The max concurrent sync task number of datanode sync mgr globally 
       skipMode:
         # when there are only timetick msg in flowgraph for a while (longer than coldTime),
         # flowGraph will turn on skip mode to skip most timeticks to reduce cost, especially there are a lot of channels
         enable: true
         skipNum: 4
         coldTime: 60
     segment:
       insertBufSize: 16777216 # Max buffer size to flush for a single segment.
       deleteBufBytes: 67108864 # Max buffer size to flush del for a single channel
       syncPeriod: 600 # The period to sync segments if buffer is not empty.
     # can specify ip for example
     # ip: 127.0.0.1
     grpc:
       serverMaxSendSize: 536870912
       serverMaxRecvSize: 268435456
       clientMaxSendSize: 268435456
       clientMaxRecvSize: 536870912
     memory:
       forceSyncEnable: true # `true` to force sync if memory usage is too high
       forceSyncSegmentNum: 1 # number of segments to sync, segments with top largest buffer will be synced.
       watermarkStandalone: 0.2 # memory watermark for standalone, upon reaching this watermark, segments will be synced.
       watermarkCluster: 0.5 # memory watermark for cluster, upon reaching this watermark, segments will be synced.
     timetick:
       byRPC: true
     channel:
       # specify the size of global work pool of all channels
       # if this parameter <= 0, will set it as the maximum number of CPUs that can be executing
       # suggest to set it bigger on large collection numbers to avoid blocking
       workPoolSize: -1
       # specify the size of global work pool for channel checkpoint updating
       # if this parameter <= 0, will set it as 1000
       # suggest to set it bigger on large collection numbers to avoid blocking
       updateChannelCheckpointMaxParallel: 1000
   
   grpc:
     client:
       compressionEnabled: false
       dialTimeout: 200
       keepAliveTime: 10000
       keepAliveTimeout: 20000
       maxMaxAttempts: 10
       initialBackOff: 0.2 # seconds
       maxBackoff: 10 # seconds
       
   quotaAndLimits:
     enabled: true # `true` to enable quota and limits, `false` to disable.
     limits:
       maxCollectionNum: 65536
       maxCollectionNumPerDB: 65536
     # quotaCenterCollectInterval is the time interval that quotaCenter
     # collects metrics from Proxies, Query cluster and Data cluster.
     # seconds, (0 ~ 65536)
     quotaCenterCollectInterval: 3
     ddl:
       enabled: false
       collectionRate: -1 # qps, default no limit, rate for CreateCollection, DropCollection, LoadCollection, ReleaseCollection
       partitionRate: -1 # qps, default no limit, rate for CreatePartition, DropPartition, LoadPartition, ReleasePartition
     indexRate:
       enabled: false
       max: -1 # qps, default no limit, rate for CreateIndex, DropIndex
     flushRate:
       enabled: false
       max: -1 # qps, default no limit, rate for flush
     compactionRate:
       enabled: false
       max: -1 # qps, default no limit, rate for manualCompaction
     dml:
       # dml limit rates, default no limit.
       # The maximum rate will not be greater than max.
       enabled: false
       insertRate:
         collection:
           max: -1 # MB/s, default no limit
         max: -1 # MB/s, default no limit
       upsertRate:
         collection:
           max: -1 # MB/s, default no limit
         max: -1 # MB/s, default no limit
       deleteRate:
         collection:
           max: -1 # MB/s, default no limit
         max: -1 # MB/s, default no limit
       bulkLoadRate:
         collection:
           max: -1 # MB/s, default no limit, not support yet. TODO: limit bulkLoad rate
         max: -1 # MB/s, default no limit, not support yet. TODO: limit bulkLoad rate
     dql:
       # dql limit rates, default no limit.
       # The maximum rate will not be greater than max.
       enabled: false
       searchRate:
         collection:
           max: -1 # vps (vectors per second), default no limit
         max: -1 # vps (vectors per second), default no limit
       queryRate:
         collection:
           max: -1 # qps, default no limit
         max: -1 # qps, default no limit
     limitWriting:
       # forceDeny false means dml requests are allowed (except for some
       # specific conditions, such as memory of nodes to water marker), true means always reject all dml requests.
       forceDeny: false
       ttProtection:
         enabled: false
         # maxTimeTickDelay indicates the backpressure for DML Operations.
         # DML rates would be reduced according to the ratio of time tick delay to maxTimeTickDelay,
         # if time tick delay is greater than maxTimeTickDelay, all DML requests would be rejected.
         # seconds
         maxTimeTickDelay: 300
       memProtection:
         # When memory usage > memoryHighWaterLevel, all dml requests would be rejected;
         # When memoryLowWaterLevel < memory usage < memoryHighWaterLevel, reduce the dml rate;
         # When memory usage < memoryLowWaterLevel, no action.
         enabled: true
         dataNodeMemoryLowWaterLevel: 0.85 # (0, 1], memoryLowWaterLevel in DataNodes
         dataNodeMemoryHighWaterLevel: 0.95 # (0, 1], memoryHighWaterLevel in DataNodes
         queryNodeMemoryLowWaterLevel: 0.85 # (0, 1], memoryLowWaterLevel in QueryNodes
         queryNodeMemoryHighWaterLevel: 0.95 # (0, 1], memoryHighWaterLevel in QueryNodes
       growingSegmentsSizeProtection:
         # No action will be taken if the growing segments size is less than the low watermark.
         # When the growing segments size exceeds the low watermark, the dml rate will be reduced,
         # but the rate will not be lower than `minRateRatio * dmlRate`.
         enabled: false
         minRateRatio: 0.5
         lowWaterLevel: 0.2
         highWaterLevel: 0.4
       diskProtection:
         enabled: true # When the total file size of object storage is greater than `diskQuota`, all dml requests would be rejected;
         diskQuota: -1 # MB, (0, +inf), default no limit
         diskQuotaPerCollection: -1 # MB, (0, +inf), default no limit
     limitReading:
       # forceDeny false means dql requests are allowed (except for some
       # specific conditions, such as collection has been dropped), true means always reject all dql requests.
       forceDeny: false
       queueProtection:
         enabled: false
         # nqInQueueThreshold indicated that the system was under backpressure for Search/Query path.
         # If NQ in any QueryNode's queue is greater than nqInQueueThreshold, search&query rates would gradually cool off
         # until the NQ in queue no longer exceeds nqInQueueThreshold. We think of the NQ of query request as 1.
         # int, default no limit
         nqInQueueThreshold: -1
         # queueLatencyThreshold indicated that the system was under backpressure for Search/Query path.
         # If dql latency of queuing is greater than queueLatencyThreshold, search&query rates would gradually cool off
         # until the latency of queuing no longer exceeds queueLatencyThreshold.
         # The latency here refers to the averaged latency over a period of time.
         # milliseconds, default no limit
         queueLatencyThreshold: -1
       resultProtection:
         enabled: false
         # maxReadResultRate indicated that the system was under backpressure for Search/Query path.
         # If dql result rate is greater than maxReadResultRate, search&query rates would gradually cool off
         # until the read result rate no longer exceeds maxReadResultRate.
         # MB/s, default no limit
         maxReadResultRate: -1
       # colOffSpeed is the speed of search&query rates cool off.
       # (0, 1]
       coolOffSpeed: 0.9

3. 在彈出的提示對話框中，輸入變更原因，單擊確定。

   配置修改請求提交后，若所修改配置項需要重啟以生效，則在配置修改完成后將重啟實例。此時實例將進入升級中狀態，待配置更新完成后，集群將恢復至運行中狀態。