Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug]: GetRemoteCentroidsObjectPrefix function in KmeansClustering.h is missing ANALYZE_ROOT_PATH #39353

Open
1 task done
liorf95 opened this issue Jan 16, 2025 · 5 comments
Assignees
Labels
kind/bug Issues or changes related a bug triage/needs-information Indicates an issue needs more information in order to work on it.

Comments

@liorf95
Copy link

liorf95 commented Jan 16, 2025

Is there an existing issue for this?

  • I have searched the existing issues

Environment

- Milvus version: cloned on 25 Dec 
- Deployment mode(standalone or cluster): cluster
- MQ type(rocksmq, pulsar or kafka):    
- SDK version(e.g. pymilvus v2.0.0rc2):
- OS(Ubuntu or CentOS): Ubuntu 
- CPU/Memory: 
- GPU: 
- Others:

Current Behavior

Thus clustering compaction failed to find the centroid file under the analyze_stats folder.

Expected Behavior

No response

Steps To Reproduce

Milvus Log

No response

Anything else?

No response

@liorf95 liorf95 added kind/bug Issues or changes related a bug needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one. labels Jan 16, 2025
@yanliang567
Copy link
Contributor

@liorf95 could you please attach the completed milvus logs, and share the steps to reproduce the issue.
/unassign

@yanliang567 yanliang567 added triage/needs-information Indicates an issue needs more information in order to work on it. and removed needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one. labels Jan 17, 2025
@chasingegg
Copy link
Contributor

@liorf95 Thanks for alerting! This path was modified unintentionally, I will fix it. BTW, what is your use case to use clustering compaction on vectors

@liorf95
Copy link
Author

liorf95 commented Jan 19, 2025

@liorf95 could you please attach the completed milvus logs, and share the steps to reproduce the issue. /unassign

milvus3-milvus-datanode-6f64d58569-wdkxf_datanode.log

@liorf95
Copy link
Author

liorf95 commented Jan 19, 2025

@liorf95 Thanks for alerting! This path was modified unintentionally, I will fix it. BTW, what is your use case to use clustering compaction on vectors

milvus yaml:

# This is a sample to deploy a milvus cluster in milvus-operator's default configurations.
apiVersion: milvus.io/v1beta1
kind: Milvus
metadata:
  name: milvus3
  namespace: kioxia
  labels:
    app: milvus
spec:
  mode: cluster
  dependencies:
    etcd:
      inCluster:
        values:
          replicaCount: 1
          persistence:    
            storageClass: local-path
            size: 10Gi
            volumePermissions:
              enabled: true
    storage:      
      inCluster:
        values:
          # change to standalone if you dont have 3 nodes
          mode: standalone
          service:
            type: LoadBalancer
          consoleService:
            type: LoadBalancer
              
          replicas: 1
          persistence:    
            storageClass: local-path
            size: 1Ti       
            
    pulsar:      
      inCluster:
        values:     
          # disabled AntiAffinity
          affinity:
            anti_affinity: false
          # disable auto recovery
          components:
            autorecovery: false
            pulsar_manager: true
            
          zookeeper:
            replicaCount: 1
            volumes:
              data:
                size: 40Gi
          broker:
            replicaCount: 1
            resources:
              limits:
                cpu: 4
                memory: 4Gi   
            configData:                                                                                                                                 
              PULSAR_MEM: >                                                                                                                             
                -Xms128m -Xmx1024m -XX:MaxDirectMemorySize=1024m                                                    
              PULSAR_GC: >     
                -XX:+IgnoreUnrecognizedVMOptions                  
                -XX:+UseG1GC                                                                                                         
                -XX:MaxGCPauseMillis=10                                                                                                                   
                -Dio.netty.leakDetectionLevel=disabled                                                                                                    
                -Dio.netty.recycler.linkCapacity=1024                                                                                                   
                -XX:+ParallelRefProcEnabled                                                                                                             
                -XX:+UnlockExperimentalVMOptions                                                                  
                -XX:+DoEscapeAnalysis                                                          
                -XX:ParallelGCThreads=4                                                                                              
                -XX:ConcGCThreads=4                                                                                                                       
                -XX:G1NewSizePercent=50                                                                                                                   
                -XX:+DisableExplicitGC                                                                                                                  
                -XX:-ResizePLAB                                                                                                                         
                -XX:+ExitOnOutOfMemoryError                                                                       
                -XX:+PerfDisableSharedMem             
              managedLedgerDefaultAckQuorum: '1'
              managedLedgerDefaultEnsembleSize: '1'
              managedLedgerDefaultWriteQuorum: '1'                                                  
          bookkeeper:
            replicaCount: 1
            configData:                                                                                                                                   
              # we use `bin/pulsar` for starting bookie daemons                                                                                           
              PULSAR_MEM: >                                                                                                                             
                -Xms128m                                                                                                                                
                -Xmx1024m                                                                                                                                  
                -XX:MaxDirectMemorySize=1024m                                                                                                            
              PULSAR_GC: >        
                -XX:+IgnoreUnrecognizedVMOptions                  
                -XX:+UseG1GC                                                                                                         
                -XX:MaxGCPauseMillis=10                                                                                                                   
                -XX:+ParallelRefProcEnabled                                                                                                             
                -XX:+UnlockExperimentalVMOptions                                                                                                        
                -XX:+DoEscapeAnalysis                                                                                                                   
                -XX:ParallelGCThreads=4                                                                                                                 
                -XX:ConcGCThreads=4                                                                                                                     
                -XX:G1NewSizePercent=50                                                                                                                 
                -XX:+DisableExplicitGC                                                                                                                    
                -XX:-ResizePLAB                                                                                                                         
                -XX:+ExitOnOutOfMemoryError                                                                                                             
                -XX:+PerfDisableSharedMem                                                                                                               
                -verbosegc                                                                                                                              
                -Xloggc:/var/log/bookie-gc.log                                                                                       
                -XX:G1LogLevel=finest                               
            resources:
              limits:
                cpu: 4
                memory: 32Gi             
             
  components:
    proxy:
      replicas: 1
      serviceType: LoadBalancer
      image: 10.93.66.61:32610/milvus:v2.4.5-liorf4
    queryNode:
      replicas: 1
      image: 10.93.66.61:32610/milvus:v2.4.5-liorf4

env:

- name: MALLOC_CONF

value: "background_thread:true,prof:true,prof_leak:true,lg_prof_interval:30,lg_prof_sample:19,prof_final:true,stats_print:true,prof_prefix:/var/lib/milvus/data/jeprof"

      volumeMounts:
      - mountPath: /var/lib/milvus/data
        name: disk
      volumes:
      - name: disk
        hostPath:
          path: "/var/lib/milvus/data"
          type: DirectoryOrCreate
    indexNode:
      replicas: 1
      image: 10.93.66.61:32610/milvus:v2.4.5-liorf4
      env:
        - name: LOCAL_STORAGE_SIZE
          value: "300"
      volumeMounts:
      - mountPath: /var/lib/milvus/data
        name: disk
      volumes:
      - name: disk
        hostPath:
          path: "/var/lib/milvus/data"
          type: DirectoryOrCreate      
    dataCoord:
      image: 10.93.66.61:32610/milvus:v2.4.5-liorf4
      replicas: 1
    queryCoord:
      image: 10.93.66.61:32610/milvus:v2.4.5-liorf4
      replicas: 1          
    indexCoord:
      image: 10.93.66.61:32610/milvus:v2.4.5-liorf4
      replicas: 1
    dataNode:
      image: 10.93.66.61:32610/milvus:v2.4.5-liorf4
      replicas: 1
    rootCoord:
      image: 10.93.66.61:32610/milvus:v2.4.5-liorf4
      replicas: 1
      
  config:
    log:
      file:
        maxAge: 10
        maxBackups: 20
        maxSize: 100            
      format: text
      level: warn
    common:
      DiskIndex:
        BeamWidthRatio: 8
        BuildNumThreadsRatio: 1
        LoadNumThreadRatio: 8
        MaxDegree: 20
        PQCodeBudgetGBRatio: 0.04
        SearchCacheBudgetGBRatio: 0.0
        SearchListSize: 100
      useVectorAsClusteringKey: true
      enableVectorClusteringKey: true
    proxy:
      grpc:
        serverMaxRecvSize: 2147483648   # 2GB
        serverMaxSendSize: 2147483648
        clientMaxRecvSize: 2147483648
        clientMaxSendSize: 2147483648
    dataNode:
      import:
        maxConcurrentTaskNum: 64
        maxImportFileSizeInGB: 1024
    queryNode:
      segcore:
        knowhereThreadPoolNumRatio: 4
      scheduler:
        maxReadConcurrentRatio: 2
      enableSegmentPrune: true
      defaultSegmentFilterRatio: 1.5

    queryCoord:
      loadTimeoutSeconds: 6000
    dataCoord:
      import:
        maxImportFileNumPerReq: 100000
      statsTask:
        enable: false
      segment:
        maxSize: 1300
        diskSegmentMaxSize: 1300
        sealProportion: 0.8
        smallProportion: 0.5
      compaction:
        clustering:
          autoEnable: true
          enable: true
          maxInterval: 25920000
          minCentroidsNum: 5
          triggerInterval: 60
        rpcTimeout: 180
        timeout: 5600
        levelzero:
          forceTrigger:
            maxSize: 85899345920

@yanliang567
Copy link
Contributor

/assign @chasingegg

sre-ci-robot pushed a commit that referenced this issue Jan 20, 2025
sre-ci-robot pushed a commit that referenced this issue Jan 20, 2025
issue: #39353
The path was modified unintentionally, change it back.

Signed-off-by: chasingegg <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
kind/bug Issues or changes related a bug triage/needs-information Indicates an issue needs more information in order to work on it.
Projects
None yet
Development

No branches or pull requests

3 participants