Re: [PATCH v2] Revert "eal/unix: fix thread creation"

[David Marchand <david.marchand@redhat.com>]

Hello Luca,

On Sat, Nov 2, 2024 at 11:09 AM David Marchand
<david.marchand@redhat.com> wrote:
>
> On Thu, Oct 31, 2024 at 9:46 PM Stephen Hemminger
> <stephen@networkplumber.org> wrote:
> >
> > On Thu, 31 Oct 2024 14:05:16 +0000
> > Luca Boccassi <luca.boccassi@gmail.com> wrote:
> >
> > > On Thu, 31 Oct 2024 at 13:04, David Marchand <david.marchand@redhat.com> wrote:
> > > >
> > > > On Thu, Oct 31, 2024 at 1:58 PM Luca Boccassi <luca.boccassi@gmail.com> wrote:
> > > > >
> > > > > On Thu, 31 Oct 2024 at 12:52, David Marchand <david.marchand@redhat.com> wrote:
> > > > > >
> > > > > > On Thu, Oct 31, 2024 at 1:47 PM David Marchand
> > > > > > <david.marchand@redhat.com> wrote:
> > > > > > > Could you share a backtrace when hitting this deadlock?
> > > > > >
> > > > > > If the backtrace is not possible, running with
> > > > > > --log-level=lib.eal:debug may help.
> > > > >
> > > > > I cannot get backtraces. This runs via "meson test", how can that
> > > > > option be passed in?
> > > >
> > > > # meson test -C build-debian --suite fast-tests --verbose -t 5
> > > > --test-args=--log-level=lib.eal:debug
> > >
> > > https://paste.debian.net/1334095/
> >
> > Could not repro this on Raspberry Pi 5. Main branch builds and runs
>
> There is no deadlock at play, as far as I can see.
>
> The mentionned commit slowed down thread instantiation (a lot, from
> what the timestamps seen in the paste link).
> The exact reason is not entirely clear to me, but it forced the thread
> creating children threads to wait for them to start running.
> Reverting this commit enhances the situation, but reintroduce a double
> free (if set affinity of the created thread fails, both the parent and
> the created thread will free ctx).
>
> I sent a patch, reintroducing use of pthread_attr_setaffinity_np like
> Tyler had first proposed.
> Let's see what the CI think of this.

The change has been merged and OBS is now all green.
You can disable the debug logs in your OBS package.

Thanks.


-- 
David Marchand