-
Notifications
You must be signed in to change notification settings - Fork 5.8k
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
A performance bottleneck when running TPCC workload the ARM servers #14380
Comments
We can see that it is stuck by
|
@SunRunAway Forgive me for the little knowledge, can you please tell me which version of tidb supports arm64 architecture? |
@alex-quan-001 Cloud you answer this question? |
I experience tests failures on Linux ARM64 even on latest |
The official website announces that it is supported, but we are currently only running it once before the release of the release branch. master branch is not yet integrated into ci cross-platform support. We are planning and requesting resources for master ci cross-platform support. |
@alex-quan-001 What CI system do you use ? |
oh okay, thanks @alex-quan-001 @SunRunAway for info.. |
You can ask new questions at https://ask.pingcap.com/ or https://asktug.com/ (Chinese). I will close this issue. If there are any updates, you can reopen it. |
Performance Questions
v3.0.7
We deploy 1 tidb-server and 3 tikv-server on each arm machine, and have 3 arm machines for test.
Then we use one TPCC client to perform workload on a fixed tidb-server, set 1000 warehouse and add terminals step by step to test the cluster's performance bottleneck. when the terminals was added to 1200 terminals, we found the qps was smaller than 1000 terminals, and what's more strange is that kv cmd OPS became smaller but kv cmd duration was greater than 1000 terminals.
The text was updated successfully, but these errors were encountered: