On Sat, Jun 08, 2024 at 03:44:36PM +0200, Benjamin Block wrote:
> Making a small change like this to the profiling thread
>
> @@ -123,13 +123,11 @@ static void *idle_prof_thread_fn(void *data)
>
> /* exit if other threads failed to initialize */
> if (ipc.status == IDLE_PROF_STATUS_ABORT) {
> - pthread_mutex_unlock(&ipt->start_lock);
> goto do_exit;
> }
>
> v /* exit if we are doing calibration only */
> if (ipc.status == IDLE_PROF_STATUS_CALI_STOP) {
> - pthread_mutex_unlock(&ipt->start_lock);
> goto do_exit;
> }
>
> @@ -151,10 +149,9 @@ static void *idle_prof_thread_fn(void *data)
> idle_prof_done:
>
> ipt->loops = j + (double) k / page_size;
> +do_exit:
> ipt->state = TD_EXITED;
> pthread_mutex_unlock(&ipt->start_lock);
> -
> -do_exit:
> free_cpu_affinity(ipt);
> return NULL;
> }
>
> fixes the issue that `fio` doesn't exit in case a profiling thread
> aborts/exits before reaching their main loop.
Ah, this is also buggy :D
if (retval == -1) {
ipt->state = TD_EXITED;
pthread_mutex_unlock(&ipt->init_lock);
goto do_exit;
}
above uses the same label before having locked `ipt->start_lock`, but the idea
applies.
--
Best Regards, Benjamin Block / Linux on IBM Z Kernel Development
IBM Deutschland Research & Development GmbH / https://www.ibm.com/privacy
Vors. Aufs.-R.: Wolfgang Wendt / Gesch?ftsf?hrung: David Faller
Sitz der Ges.: B?blingen / Registergericht: AmtsG Stuttgart, HRB 243294
