On Thu, 25 Mar 2021, Jonathan Schwender wrote:
> Move error handling for setting the affinity of the main pid
> into a separate function.
> This prevents duplicating the code in the next commit,
> where the main thread pid can be restricted to one of
> two bitmasks depending on the passed parameters.
>
> After feedback from John Kacur, the function is now
> located in src/lib/rt-numa.c.
> This allows other tests to reuse this, if they also
> prefer to warn if numa_sched_setaffinity fails.
>
> Signed-off-by: Jonathan Schwender <schwenderjonathan@xxxxxxxxx>
> ---
> src/cyclictest/cyclictest.c | 8 +-------
> src/include/rt-numa.h | 2 ++
> src/lib/rt-numa.c | 11 +++++++++++
> 3 files changed, 14 insertions(+), 7 deletions(-)
>
> diff --git a/src/cyclictest/cyclictest.c b/src/cyclictest/cyclictest.c
> index dca9610..460f6ae 100644
> --- a/src/cyclictest/cyclictest.c
> +++ b/src/cyclictest/cyclictest.c
> @@ -1791,13 +1791,7 @@ int main(int argc, char **argv)
>
> /* Restrict the main pid to the affinity specified by the user */
> if (affinity_mask != NULL) {
> - int res;
> -
> - errno = 0;
> - res = numa_sched_setaffinity(getpid(), affinity_mask);
> - if (res != 0)
> - warn("Couldn't setaffinity in main thread: %s\n", strerror(errno));
> -
> + try_numa_sched_setaffinity(getpid(), affinity_mask);
> if (verbose)
> printf("Using %u cpus.\n",
> numa_bitmask_weight(affinity_mask));
> diff --git a/src/include/rt-numa.h b/src/include/rt-numa.h
> index ca86a45..e9fa312 100644
> --- a/src/include/rt-numa.h
> +++ b/src/include/rt-numa.h
> @@ -18,4 +18,6 @@ int cpu_for_thread_ua(int thread_num, int max_cpus);
>
> int parse_cpumask(char *str, int max_cpus, struct bitmask **cpumask);
>
> +void try_numa_sched_setaffinity(__pid_t pid, struct bitmask *cpumask);
> +
> #endif
> diff --git a/src/lib/rt-numa.c b/src/lib/rt-numa.c
> index babcc63..9a81cfb 100644
> --- a/src/lib/rt-numa.c
> +++ b/src/lib/rt-numa.c
> @@ -138,3 +138,14 @@ int parse_cpumask(char *str, int max_cpus, struct bitmask **cpumask)
>
> return 0;
> }
> +
> +void try_numa_sched_setaffinity(pid_t pid, struct bitmask *cpumask)
> +{
> + int res;
> +
> + errno = 0;
> + res = numa_sched_setaffinity(pid, cpumask);
> + if (res != 0)
> + warn("Couldn't setaffinity for thread %d: %s\n", pid,
> + strerror(errno));
> +}
> --
> 2.30.2
>
>
Yuck. My bad, this is some pretty inelegant error code wrapped around a
numa call, I don't think it really warrents trying to make an API out of
it. That said, I might need to do this anyway, when I put back code that
can run when numa is not available on a target machine.
For now, can you just leave this inline and respin?
Thanks
John Kacur
