GitHub user lhotari added a comment to the discussion: Pulsar upgrade to 3.0.5 causes prometheus metrics timeouts on brokers
@justin-lathrop Do you know whether cgroup v1 or v2 is in use? I'm wondering that CPU requests of 200m doesn't result in the JVM assuming that there's 1 core to use. The workaround is described here: https://github.com/apache/pulsar/issues/17815#issuecomment-1268547528 . You can pass `-XX:ActiveProcessorCount=1` to the JVM arguments (in `PULSAR_MEM`, for example). GitHub link: https://github.com/apache/pulsar/discussions/22897#discussioncomment-9798023 ---- This is an automatically sent email for [email protected]. To unsubscribe, please send an email to: [email protected]
