-
Notifications
You must be signed in to change notification settings - Fork 409
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
Get correct cpu cores in k8s pod #6430
Conversation
[REVIEW NOTIFICATION] This pull request has been approved by:
To complete the pull request process, please ask the reviewers in the list to review by filling The full list of commands accepted by this bot can be found here. Reviewer can indicate their review by submitting an approval review. |
/run-build-arm64-release |
/run-build-arm64-release |
download tiflash binary(linux arm64) at http://fileserver.pingcap.net/download/builds/pingcap/test/tiflash/master/3608ae5daad64281f376563444418be8ec1c64b5/centos7/tiflash-linux-arm64.tar.gz |
/rebuild |
/cc @windtalker @SeaRise |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add test_infra tests to check?
/// Let's limit ourself to the number of physical cores. | ||
/// But if the number of logical cores is small - maybe it is a small machine | ||
/// or very limited cloud instance and it is reasonable to use all the cores. | ||
if (cpu_count >= 32) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A little weired here, this cpu_count = 32, its max stream will be 16, smaller than cpu_count = 24. That's machine with more cpus has smaller max_streams.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
can use the value in server info https://github.com/pingcap/tiflash/blob/master/dbms/src/Server/ServerInfo.h which is more accurate and compatible. |
values in ServerInfo is calculated by this function, so ServerInfo can't help us. |
no, actually it reuse the logic from tikv https://github.com/tikv/tikv/blob/master/components/tikv_util/src/sys/cgroup.rs, tiflash/dbms/src/Server/Server.cpp Lines 876 to 886 in 110bda2
|
|
max_streams of xxxxInputStream is determined by Context's max_threads which is initialized by |
@Lloyd-Pottiger: It seems you want to merge this PR, I will help you trigger all the tests: /run-all-tests You only need to trigger If you have any questions about the PR merge process, please refer to pr process. Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the ti-community-infra/tichi repository. |
This pull request has been accepted and is ready to merge. Commit hash: c2b73ff
|
@xzhangxian1008: Your PR was out of date, I have automatically updated it for you. If the CI test fails, you just re-trigger the test that failed and the bot will merge the PR for you after the CI passes. Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the ti-community-infra/tichi repository. |
/run-all-tests |
In response to a cherrypick label: new pull request created: #6449. |
Signed-off-by: ti-chi-bot <ti-community-prow-bot@tidb.io>
In response to a cherrypick label: new pull request created: #6450. |
In response to a cherrypick label: new pull request created: #6451. |
Signed-off-by: ti-chi-bot <ti-community-prow-bot@tidb.io>
In response to a cherrypick label: new pull request created: #6452. |
Signed-off-by: ti-chi-bot <ti-community-prow-bot@tidb.io>
In response to a cherrypick label: new pull request created: #6453. |
Signed-off-by: ti-chi-bot <ti-community-prow-bot@tidb.io>
In response to a cherrypick label: new pull request created: #6454. |
Signed-off-by: ti-chi-bot <ti-community-prow-bot@tidb.io>
Signed-off-by: ti-chi-bot <ti-community-prow-bot@tidb.io>
In response to a cherrypick label: new pull request created: #6455. |
What problem does this PR solve?
Issue Number: close #6434
Problem Summary:
max_streams of xxxxInputStream is determined by Context's max_threads which is initialized by
getNumberofPhysicalCPUCores()
. In x86 virtual environment, we get max_threads as 48 which is physical cpu cores while getting max_threads as 128 which is logical cpu cores in arm virtual environment. 128 is much larger than 48, so it will use more threads and exceed the limit more easily.What is changed and how it works?
Check List
Tests
Side effects
Documentation
Release note