Closed wangting0128 closed 1 year ago
/unassign
client argo tasks: fouramf-stnjq, fouramf-concurrent-q2phm
Steps To Reproduce
1、deploy Milvus Cluster
2、client:
1. create collection
2. build index of IVF_SQ8
3. insert 20m vectors
4. flush
5. rebuild IVF_SQ8 index
6. load
7. locust search <- concurrent
3、concurrent insert to the same collection
4、scale out queryNode from 4 to 5
5、concurrent search to the same collection and scale out queryNode from 5 to 6
6、concurrent 2 clients and the same as step 2, one collection set replica=2, dataset size=20m; another one set replica=3, dataset size=10m
7、The Milvus instance idles overnight 《- the memory of queryNode rises slowly
server:
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
fouramf-l2mgq-61-3057-etcd-0 1/1 Running 0 18h 10.104.23.124 4am-node27 <none> <none>
fouramf-l2mgq-61-3057-etcd-1 1/1 Running 0 18h 10.104.15.190 4am-node20 <none> <none>
fouramf-l2mgq-61-3057-etcd-2 1/1 Running 0 18h 10.104.16.143 4am-node21 <none> <none>
fouramf-l2mgq-61-3057-milvus-datacoord-756fd4fb99-2v5d8 1/1 Running 0 21h 10.104.21.77 4am-node24 <none> <none>
fouramf-l2mgq-61-3057-milvus-datanode-7c5fd9f69d-rjsdq 1/1 Running 1 (21h ago) 21h 10.104.21.78 4am-node24 <none> <none>
fouramf-l2mgq-61-3057-milvus-indexcoord-7b96f6d694-8xlzf 1/1 Running 1 (21h ago) 21h 10.104.15.153 4am-node20 <none> <none>
fouramf-l2mgq-61-3057-milvus-indexnode-54589b88f-twbvv 1/1 Running 0 21h 10.104.23.76 4am-node27 <none> <none>
fouramf-l2mgq-61-3057-milvus-proxy-7579976fd6-926pp 1/1 Running 1 (21h ago) 21h 10.104.21.76 4am-node24 <none> <none>
fouramf-l2mgq-61-3057-milvus-querycoord-7f6dd89cc7-p4bnb 1/1 Running 1 (21h ago) 21h 10.104.15.152 4am-node20 <none> <none>
fouramf-l2mgq-61-3057-milvus-querynode-5586c588dc-29v2j 1/1 Running 0 21h 10.104.9.123 4am-node14 <none> <none>
fouramf-l2mgq-61-3057-milvus-querynode-5586c588dc-c5kbq 1/1 Running 0 21h 10.104.17.89 4am-node23 <none> <none>
fouramf-l2mgq-61-3057-milvus-querynode-5586c588dc-dstqm 1/1 Running 0 21h 10.104.20.112 4am-node22 <none> <none>
fouramf-l2mgq-61-3057-milvus-querynode-5586c588dc-qpwsq 1/1 Running 0 18h 10.104.16.145 4am-node21 <none> <none>
fouramf-l2mgq-61-3057-milvus-querynode-5586c588dc-t88tb 1/1 Running 0 18h 10.104.15.188 4am-node20 <none> <none>
fouramf-l2mgq-61-3057-milvus-querynode-5586c588dc-x8k4g 1/1 Running 0 21h 10.104.18.80 4am-node25 <none> <none>
fouramf-l2mgq-61-3057-milvus-rootcoord-b58b4fc45-cvbgm 1/1 Running 0 21h 10.104.17.86 4am-node23 <none> <none>
fouramf-l2mgq-61-3057-minio-0 1/1 Running 0 21h 10.104.24.50 4am-node29 <none> <none>
fouramf-l2mgq-61-3057-minio-1 1/1 Running 0 21h 10.104.4.180 4am-node11 <none> <none>
fouramf-l2mgq-61-3057-minio-2 1/1 Running 0 21h 10.104.16.79 4am-node21 <none> <none>
fouramf-l2mgq-61-3057-minio-3 1/1 Running 0 21h 10.104.15.157 4am-node20 <none> <none>
fouramf-l2mgq-61-3057-pulsar-bookie-0 1/1 Running 0 21h 10.104.24.51 4am-node29 <none> <none>
fouramf-l2mgq-61-3057-pulsar-bookie-1 1/1 Running 0 21h 10.104.4.183 4am-node11 <none> <none>
fouramf-l2mgq-61-3057-pulsar-bookie-2 1/1 Running 0 21h 10.104.1.41 4am-node10 <none> <none>
fouramf-l2mgq-61-3057-pulsar-broker-0 1/1 Running 0 21h 10.104.5.55 4am-node12 <none> <none>
fouramf-l2mgq-61-3057-pulsar-proxy-0 1/1 Running 0 21h 10.104.5.54 4am-node12 <none> <none>
fouramf-l2mgq-61-3057-pulsar-recovery-0 1/1 Running 0 21h 10.104.23.77 4am-node27 <none> <none>
fouramf-l2mgq-61-3057-pulsar-zookeeper-0 1/1 Running 0 21h 10.104.16.82 4am-node21 <none> <none>
fouramf-l2mgq-61-3057-pulsar-zookeeper-1 1/1 Running 0 21h 10.104.15.159 4am-node20 <none> <none>
fouramf-l2mgq-61-3057-pulsar-zookeeper-2 1/1 Running 0 21h 10.104.19.109 4am-node28 <none> <none>
client:
server:
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
fouramf-k9c4t-71-7665-etcd-0 1/1 Running 0 37h 10.104.15.189 4am-node20 <none> <none>
fouramf-k9c4t-71-7665-etcd-1 1/1 Running 0 37h 10.104.20.139 4am-node22 <none> <none>
fouramf-k9c4t-71-7665-etcd-2 1/1 Running 0 37h 10.104.18.149 4am-node25 <none> <none>
fouramf-k9c4t-71-7665-milvus-datacoord-54bfb467c7-6ph67 1/1 Running 0 40h 10.104.15.145 4am-node20 <none> <none>
fouramf-k9c4t-71-7665-milvus-datanode-85db4d867b-gcgsr 1/1 Running 0 40h 10.104.24.39 4am-node29 <none> <none>
fouramf-k9c4t-71-7665-milvus-indexcoord-786495fb68-cdwrp 1/1 Running 0 40h 10.104.15.146 4am-node20 <none> <none>
fouramf-k9c4t-71-7665-milvus-indexnode-7c7f98c55-c4b5r 1/1 Running 0 40h 10.104.21.75 4am-node24 <none> <none>
fouramf-k9c4t-71-7665-milvus-proxy-567f975c76-fhwl5 1/1 Running 0 40h 10.104.20.107 4am-node22 <none> <none>
fouramf-k9c4t-71-7665-milvus-querycoord-548dc8895-cwzh5 1/1 Running 0 40h 10.104.21.74 4am-node24 <none> <none>
fouramf-k9c4t-71-7665-milvus-querynode-775467c8fc-hd4ch 1/1 Running 6 (13h ago) 40h 10.104.4.175 4am-node11 <none> <none>
fouramf-k9c4t-71-7665-milvus-querynode-775467c8fc-p2nlr 1/1 Running 0 37h 10.104.21.151 4am-node24 <none> <none>
fouramf-k9c4t-71-7665-milvus-querynode-775467c8fc-tf5nt 1/1 Running 0 37h 10.104.16.144 4am-node21 <none> <none>
fouramf-k9c4t-71-7665-milvus-rootcoord-c896646b7-5vxjm 1/1 Running 0 40h 10.104.17.81 4am-node23 <none> <none>
fouramf-k9c4t-71-7665-minio-0 1/1 Running 0 40h 10.104.15.151 4am-node20 <none> <none>
fouramf-k9c4t-71-7665-minio-1 1/1 Running 0 40h 10.104.24.42 4am-node29 <none> <none>
fouramf-k9c4t-71-7665-minio-2 1/1 Running 0 40h 10.104.18.77 4am-node25 <none> <none>
fouramf-k9c4t-71-7665-minio-3 1/1 Running 0 40h 10.104.17.83 4am-node23 <none> <none>
fouramf-k9c4t-71-7665-pulsar-bookie-0 1/1 Running 0 40h 10.104.23.75 4am-node27 <none> <none>
fouramf-k9c4t-71-7665-pulsar-bookie-1 1/1 Running 0 40h 10.104.18.79 4am-node25 <none> <none>
fouramf-k9c4t-71-7665-pulsar-bookie-2 1/1 Running 0 40h 10.104.24.44 4am-node29 <none> <none>
fouramf-k9c4t-71-7665-pulsar-broker-0 1/1 Running 0 40h 10.104.17.80 4am-node23 <none> <none>
fouramf-k9c4t-71-7665-pulsar-proxy-0 1/1 Running 0 40h 10.104.18.71 4am-node25 <none> <none>
fouramf-k9c4t-71-7665-pulsar-recovery-0 1/1 Running 0 40h 10.104.18.72 4am-node25 <none> <none>
fouramf-k9c4t-71-7665-pulsar-zookeeper-0 1/1 Running 0 40h 10.104.4.178 4am-node11 <none> <none>
fouramf-k9c4t-71-7665-pulsar-zookeeper-1 1/1 Running 0 40h 10.104.17.85 4am-node23 <none> <none>
fouramf-k9c4t-71-7665-pulsar-zookeeper-2 1/1 Running 0 40h 10.104.24.46 4am-node29 <none> <none>
memory rises ~5G
/assign
case : test_concurrent_locust_100m_ivf_sq8_ddl_dql_filter_replica2_cluster After running the test and waiting a few hours without doing anything, querynode memory rises.
server :
fouramf-stbsk-99-2262-etcd-0 1/1 Running 0 3m54s 10.104.16.14 4am-node21 <none> <none>
fouramf-stbsk-99-2262-etcd-1 1/1 Running 0 3m54s 10.104.24.70 4am-node29 <none> <none>
fouramf-stbsk-99-2262-etcd-2 1/1 Running 0 3m54s 10.104.21.94 4am-node24 <none> <none>
fouramf-stbsk-99-2262-milvus-datacoord-6c9dd7549d-2w2sz 1/1 Running 0 3m54s 10.104.22.195 4am-node26 <none> <none>
fouramf-stbsk-99-2262-milvus-datanode-76d869bff6-brgw6 1/1 Running 0 3m54s 10.104.22.193 4am-node26 <none> <none>
fouramf-stbsk-99-2262-milvus-indexcoord-8696cddfbf-s7zhr 1/1 Running 0 3m54s 10.104.22.189 4am-node26 <none> <none>
fouramf-stbsk-99-2262-milvus-indexnode-5d7b5fffbb-mhmfr 1/1 Running 0 3m54s 10.104.5.11 4am-node12 <none> <none>
fouramf-stbsk-99-2262-milvus-proxy-54bf8c597c-dxb8z 1/1 Running 0 3m54s 10.104.24.65 4am-node29 <none> <none>
fouramf-stbsk-99-2262-milvus-querycoord-658d8f4886-ckpkb 1/1 Running 0 3m54s 10.104.22.190 4am-node26 <none> <none>
fouramf-stbsk-99-2262-milvus-querynode-68fcc5985d-9k8hw 1/1 Running 0 3m54s 10.104.6.198 4am-node13 <none> <none>
fouramf-stbsk-99-2262-milvus-querynode-68fcc5985d-ftb4p 1/1 Running 0 3m54s 10.104.22.191 4am-node26 <none> <none>
fouramf-stbsk-99-2262-milvus-rootcoord-8dc7bd4fb-4sxnj 1/1 Running 0 3m54s 10.104.22.188 4am-node26 <none> <none>
fouramf-stbsk-99-2262-minio-0 1/1 Running 0 3m54s 10.104.21.91 4am-node24 <none> <none>
fouramf-stbsk-99-2262-minio-1 1/1 Running 0 3m54s 10.104.24.67 4am-node29 <none> <none>
fouramf-stbsk-99-2262-minio-2 1/1 Running 0 3m54s 10.104.4.137 4am-node11 <none> <none>
fouramf-stbsk-99-2262-minio-3 1/1 Running 0 3m54s 10.104.23.169 4am-node27 <none> <none>
fouramf-stbsk-99-2262-pulsar-bookie-0 1/1 Running 0 3m54s 10.104.16.17 4am-node21 <none> <none>
fouramf-stbsk-99-2262-pulsar-bookie-1 1/1 Running 0 3m54s 10.104.24.72 4am-node29 <none> <none>
fouramf-stbsk-99-2262-pulsar-bookie-2 1/1 Running 0 3m53s 10.104.4.140 4am-node11 <none> <none>
fouramf-stbsk-99-2262-pulsar-bookie-init-f48rh 0/1 Completed 0 3m54s 10.104.21.88 4am-node24 <none> <none>
fouramf-stbsk-99-2262-pulsar-broker-0 1/1 Running 0 3m54s 10.104.4.135 4am-node11 <none> <none>
fouramf-stbsk-99-2262-pulsar-proxy-0 1/1 Running 0 3m54s 10.104.24.64 4am-node29 <none> <none>
fouramf-stbsk-99-2262-pulsar-pulsar-init-98z8n 0/1 Completed 0 3m54s 10.104.22.187 4am-node26 <none> <none>
fouramf-stbsk-99-2262-pulsar-recovery-0 1/1 Running 0 3m54s 10.104.23.165 4am-node27 <none> <none>
fouramf-stbsk-99-2262-pulsar-zookeeper-0 1/1 Running 0 3m54s 10.104.21.92 4am-node24 <none> <none>
fouramf-stbsk-99-2262-pulsar-zookeeper-1 1/1 Running 0 3m15s 10.104.23.171 4am-node27 <none> <none>
fouramf-stbsk-99-2262-pulsar-zookeeper-2 1/1 Running 0 2m40s 10.104.16.21 4am-node21 <none> <none>
should a analysis on the weird increase
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Rotten issues close after 30d of inactivity. Reopen the issue with /reopen
.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Rotten issues close after 30d of inactivity. Reopen the issue with /reopen
.
keep an eye on it
case: test_concurrent_locust_100m_ivf_sq8_ddl_dql_filter_kafka_cluster image: master-20230905-fb0705df
querynode memory up at 28h
querynode memory went from 1.19g to 5.54g
server:
fouramf-9jq2k-13-8541-etcd-0 1/1 Running 0 2d3h 10.104.17.83 4am-node23 <none> <none>
fouramf-9jq2k-13-8541-etcd-1 1/1 Running 0 2d3h 10.104.24.33 4am-node29 <none> <none>
fouramf-9jq2k-13-8541-etcd-2 1/1 Running 1 2d3h 10.104.12.107 4am-node17 <none> <none>
fouramf-9jq2k-13-8541-kafka-0 1/1 Running 2 (2d3h ago) 2d3h 10.104.12.108 4am-node17 <none> <none>
fouramf-9jq2k-13-8541-kafka-1 1/1 Running 1 (2d3h ago) 2d3h 10.104.24.37 4am-node29 <none> <none>
fouramf-9jq2k-13-8541-kafka-2 1/1 Running 2 (2d3h ago) 2d3h 10.104.17.87 4am-node23 <none> <none>
fouramf-9jq2k-13-8541-milvus-datacoord-fcddf56f6-qmhxj 1/1 Running 0 2d3h 10.104.17.80 4am-node23 <none> <none>
fouramf-9jq2k-13-8541-milvus-datanode-76bb646c68-tb54f 1/1 Running 0 2d3h 10.104.4.102 4am-node11 <none> <none>
fouramf-9jq2k-13-8541-milvus-indexcoord-7f6d75795c-sknc7 1/1 Running 0 2d3h 10.104.17.78 4am-node23 <none> <none>
fouramf-9jq2k-13-8541-milvus-indexnode-5457c4f4b8-zlgtr 1/1 Running 0 2d3h 10.104.14.88 4am-node18 <none> <none>
fouramf-9jq2k-13-8541-milvus-proxy-8847b7bc5-95jzf 1/1 Running 0 2d3h 10.104.14.85 4am-node18 <none> <none>
fouramf-9jq2k-13-8541-milvus-querycoord-df8bf659d-ftr4h 1/1 Running 0 2d3h 10.104.4.100 4am-node11 <none> <none>
fouramf-9jq2k-13-8541-milvus-querynode-57d4f579bd-vvdmz 1/1 Running 0 2d3h 10.104.12.101 4am-node17 <none> <none>
fouramf-9jq2k-13-8541-milvus-rootcoord-858f9dc8c8-qs99s 1/1 Running 0 2d3h 10.104.4.101 4am-node11 <none> <none>
fouramf-9jq2k-13-8541-minio-0 1/1 Running 0 2d3h 10.104.24.31 4am-node29 <none> <none>
fouramf-9jq2k-13-8541-minio-1 1/1 Running 0 2d3h 10.104.17.93 4am-node23 <none> <none>
fouramf-9jq2k-13-8541-minio-2 1/1 Running 0 2d3h 10.104.9.76 4am-node14 <none> <none>
fouramf-9jq2k-13-8541-minio-3 1/1 Running 0 2d3h 10.104.1.173 4am-node10 <none> <none>
fouramf-9jq2k-13-8541-zookeeper-0 1/1 Running 0 2d3h 10.104.12.106 4am-node17 <none> <none>
fouramf-9jq2k-13-8541-zookeeper-1 1/1 Running 0 2d3h 10.104.17.86 4am-node23 <none> <none>
fouramf-9jq2k-13-8541-zookeeper-2 1/1 Running 0 2d3h 10.104.24.36 4am-node29 <none> <none>
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Rotten issues close after 30d of inactivity. Reopen the issue with /reopen
.
Is there an existing issue for this?
Environment
Current Behavior
client argo tasks: fouramf-87ghh,fouramf-concurrent-bzzrx
server:
the memory of queryNode rises slowly
client:
Expected Behavior
No response
Steps To Reproduce
Milvus Log
No response
Anything else?
No response