[lttng-dev] [PART 4/4] Re: ***UNCHECKED*** Re: Re: urcu workqueue thread uses 99% of cpu while workqueue is empty

2022-06-23 Thread Minlan Wang via lttng-dev
Hi, Mathieu, This is the last one. 0623_futex-20220623-112754.tar.bz2.ad Description: Binary data ___ lttng-dev mailing list lttng-dev@lists.lttng.org https://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev

Re: [lttng-dev] ***UNCHECKED*** Re: Re: urcu workqueue thread uses 99% of cpu while workqueue is empty

2022-06-23 Thread Minlan Wang via lttng-dev
On Wed, Jun 22, 2022 at 04:52:00PM -0400, Mathieu Desnoyers wrote: [...] > remote: https://review.lttng.org/c/userspace-rcu/+/8441 Fix: workqueue: > futex wait: handle spurious futex wakeups [NEW] I tried this patch in our environment, it worked fine, the issue does not appear anymore.

Re: [lttng-dev] ***UNCHECKED*** Re: Re: urcu workqueue thread uses 99% of cpu while workqueue is empty

2022-06-23 Thread Mathieu Desnoyers via lttng-dev
- On Jun 22, 2022, at 11:57 PM, Minlan Wang wangmin...@szsandstone.com wrote: > On Wed, Jun 22, 2022 at 11:45:28PM -0400, Minlan Wang wrote: >> The session output is in attachment: 0623_futex-20220623-112754.tar.bz2 > Hi, Mathieu, > There are several workqueues in the pr

Re: [lttng-dev] ***UNCHECKED*** Re: Re: urcu workqueue thread uses 99% of cpu while workqueue is empty

2022-06-23 Thread Minlan Wang via lttng-dev
On Thu, Jun 23, 2022 at 10:09:55AM -0400, Mathieu Desnoyers wrote: > > By looking at the trace, here is one problematic scenario which end up > emitting "workqueue:futex_wait_again": > > [23:33:48.060581417] (+0.06985) localhost.localdomain > workqueue:futex_no_wait: { cpu_id = 4 }, { vpid