Open ReganWz opened 5 months ago
- Milvus version:GPU 2.4.1 - Deployment mode(standalone or cluster):standalone - MQ type(rocksmq, pulsar or kafka): rocksmq - SDK version(e.g. pymilvus v2.0.0rc2): go 2.3.x - OS(Ubuntu or CentOS): CentOS - CPU/Memory: - GPU: A10 - Others:
单台milvus GPU A10 6卡 单milvus节点数据 4000w,一个collection,默认partition,并发100-150时崩溃,QPS 300-400 持续一段时间(大约10分钟)开始异常错误;
No response
milvus_error.log
none
Is there an existing issue for this?
Environment
Current Behavior
单台milvus GPU A10 6卡 单milvus节点数据 4000w,一个collection,默认partition,并发100-150时崩溃,QPS 300-400 持续一段时间(大约10分钟)开始异常错误;
Expected Behavior
No response
Steps To Reproduce
No response
Milvus Log
milvus_error.log
Anything else?
none