Closed
Description
Is there an existing issue for this?
- I have searched the existing issues
Environment
- Milvus version: master-20250212-09888071-amd64
- Deployment mode(standalone or cluster):
- MQ type(rocksmq, pulsar or kafka):
- SDK version(e.g. pymilvus v2.0.0rc2):
- OS(Ubuntu or CentOS):
- CPU/Memory:
- GPU:
- Others:
Current Behavior
- create a collection -> insert 30m entities -> flush -> index -> load
- concurrent requests: insert + delete + search
- There are 11 L0 segments were left behind and the L0 compaction was not completed
Expected Behavior
No response
Steps To Reproduce
https://argo-workflows.zilliz.cc/archived-workflows/qa/4b7d61ca-efd0-408d-ae46-6be4eb0f3c15?nodeId=level-zero-stable-master-1739372400-1512316652
Milvus Log
pods:
level-master-insert-op-80-8499-milvus-datanode-747fc499c9-2j9fc 1/1 Running 0 20h 10.104.13.151 4am-node16 <none> <none>
level-master-insert-op-80-8499-milvus-indexnode-696b8c65bck9r6t 1/1 Running 0 20h 10.104.13.152 4am-node16 <none> <none>
level-master-insert-op-80-8499-milvus-indexnode-696b8c65bcwtcsd 1/1 Running 0 20h 10.104.6.48 4am-node13 <none> <none>
level-master-insert-op-80-8499-milvus-mixcoord-5b487f7d65-7h8dt 1/1 Running 0 20h 10.104.9.154 4am-node14 <none> <none>
level-master-insert-op-80-8499-milvus-proxy-5b949b979d-gqvvz 1/1 Running 0 20h 10.104.6.47 4am-node13 <none> <none>
level-master-insert-op-80-8499-milvus-querynode-0-5f98bbf4bthdp 1/1 Running 0 20h 10.104.24.213 4am-node29 <none> <none>
level-master-insert-op-80-8499-milvus-querynode-0-5f98bbf4mfxj8 1/1 Running 0 20h 10.104.16.82 4am-node21 <none> <none>
level-master-insert-op-80-8499-milvus-querynode-0-5f98bbf4ntx9x 1/1 Running 0 20h 10.104.14.8 4am-node18 <none> <none>
level-master-insert-op-80-8499-milvus-querynode-0-5f98bbf4pmr97 1/1 Running 0 20h 10.104.9.155 4am-node14 <none> <none>
Anything else?
No response