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]: "rootcoord send tt to all channels too slowly #26279
Comments
@ronghuaihai could you please attach the 2 kinds of logs so that we could compare the different time cost between two search to address the issue? please refer this doc to export the whole Milvus logs. /assign @ronghuaihai |
the querycoord and rootcoord logs as follows: |
we can find such logs
There is reasonable suspicion that the pulsar didn't work well at that time. Also query nodes fetch lots of log from pulsar after restarted, may lead to high load on pulsar. We recently release v2.2.14, it is recommended that you use the latest version.Refer to v2.2.x release notes, we made lots of efforts about mq and pulsar after 2.2.8, like |
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. |
Is there an existing issue for this?
Environment
Current Behavior
I have install milvus cluster(2.2.8) on k8s . After running normally two month, I modify the memory limit of queryNode,like this
use commands as follows to upgrade the milvus cluster:
helm upgrade my-release . --set metrics.serviceMonitor.enabled=true -f values.yaml
than we find all collections load again ,warning logs begin appear in the milvus rootcoord logs , the insert rate and search rate all become very slowly.
Expected Behavior
when i increase the memory limits of querynode or increate the numbers of querynodes.the performance should become better .but the performance become worser .
Steps To Reproduce
3.use follow command to upgrade milvus cluster :
helm upgrade my-release . --set metrics.serviceMonitor.enabled=true -f values.yaml
4.all collecions reload again ,and run hellow_milvus.py ,insert rate takes too long time until timeout
The text was updated successfully, but these errors were encountered: