-
Notifications
You must be signed in to change notification settings - Fork 580
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
Segfault running rpk redpanda tune net #22856
Comments
Oh, I have the same problem. |
This is a known issue on systems with more obscure NIC setups like Azure, VMs and others. The actual segfault comes from hwloc-distrib (issue here) but the main problem is that the tuner fails to parse interrupt lines for the NICs. This needs custom handling for different platforms. |
It’s interesting that I have another redpanda cluster in the same environment and network tuning works there. It’s also not clear how much the cluster’s performance will deteriorate without network tuning? |
So, @StephanDollberg what would you suggest as a workaround for this? Not using |
Yeah just skip it for now. Hard to generalize perf impact of this as it quite heavily depends on the system. In many cases it can be negligible. In others it can have larger impact (many core servers) but that part isn't working correctly right now anyway for other reasons. |
Thanks a lot! 🙏 |
Version & Environment
Redpanda version: v24.2.2 (the same problem was observed in 23.1.11)
Operating System: Ubuntu 20.04.6 LTS (Focal Fossa)
5.4.0-192-generic #212-Ubuntu SMP Fri Jul 5 09:47:39 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux
What went wrong?
Verbose:
What should have happened instead?
Either error or correctly tuned.
How to reproduce the issue?
rpk redpanda mode prod
rpk redpanda tune net
JIRA Link: CORE-6865
The text was updated successfully, but these errors were encountered: