On Wed, 13 May 2020 11:19:06 +0200 Sven Schnelle <sv...@linux.ibm.com> wrote:
> Did you had a chance to look into this? I can easily reproduce this both on > x86 > and s390 by doing: > > cd /sys/kernel/tracing > cat /dev/zero >/dev/null & # generate some load > echo function >current_tracer > # wait a few seconds to fill the buffer > cat trace > > Usually it will print the warn after a few seconds. > > I haven't digged through all the ring buffer code yet, so i thought i might > ask > whether you have an idea what's going on. Can you send me the config for where you can reproduce it on x86? The iterator now doesn't stop the ring buffer when it iterates, and is doing so over a live buffer (but should be able to handle it). It's triggering something I thought wasn't suppose to happen (which must be happening). Perhaps with your config I'd be able to reproduce it. -- Steve