-
Notifications
You must be signed in to change notification settings - Fork 3k
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]: Search latency increase from 3s to 30s after upgrading from v2.2.2 to 2.2.0-20230213-4e26d626 #22163
Comments
/assign @jaime0815 |
/assign @jiaoew1991 |
It was not caused by upgrading since the search latency would be that large if you run this test case for a new Milvus cluster with the image of 2.2.0 branch eg. 2.2.0-20230216-fa8a9224.
|
after downgrading knowhere to 1.3.7 it works fine. |
/assign @liliu-z Need to confirm and check why 1.x's CI didn't alert us on it. |
/assign @zhuwenxing |
verified and passed with 2.2.0-20230310-b2ece6a5
|
Is there an existing issue for this?
Environment
Current Behavior
nq=10000
topk=100
data size: 100M
before upgrade:
Expected Behavior
No response
Steps To Reproduce
No response
Milvus Log
collection name:sift_128_euclidean
failed job: https://qa-jenkins.milvus.io/blue/organizations/jenkins/deploy_test_kafka_for_release_cron/detail/deploy_test_kafka_for_release_cron/346/pipeline
log:
artifacts-kafka-cluster-upgrade-346-server-second-deployment-logs.tar.gz
artifacts-kafka-cluster-upgrade-346-server-first-deployment-logs.tar.gz
artifacts-kafka-cluster-upgrade-346-pytest-logs.tar.gz
Anything else?
It works well in
2.2.0-20230208-b83bbc04
passed job: https://qa-jenkins.milvus.io/blue/organizations/jenkins/deploy_test_for_release_cron/detail/deploy_test_for_release_cron/320/pipeline
The text was updated successfully, but these errors were encountered: