Received-SPF: pass (google.com: domain of linux-kernel+bounces-206919-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Content-Type: text/plain;
	charset=utf-8
Precedence: bulk
Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3774.500.171.1.1\))
Subject: Re: [PATCH 1/3] tools/perf: Fix the nrcpus in perf bench futex to
 enable the run when all CPU's are not online
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
In-Reply-To: <CAP-5=fVCXW1FEBra5aFLJm48f0-b4a+oTugTZt+VYEv1EySBKg@mail.gmail.com>
Date: Sat, 8 Jun 2024 12:36:04 +0530
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
        Adrian Hunter <adrian.hunter@intel.com>,
        Namhyung Kim <namhyung@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>, linux-perf-users@vger.kernel.org,
        linuxppc-dev@lists.ozlabs.org, akanksha@linux.ibm.com,
        maddy@linux.ibm.com, kjain@linux.ibm.com, disgoel@linux.vnet.ibm.com
Content-Transfer-Encoding: quoted-printable
Message-Id: <8232BA2A-C7C5-4413-B174-6088EBF863C0@linux.vnet.ibm.com>
References: <20240607044354.82225-1-atrajeev@linux.vnet.ibm.com>
 <CAP-5=fVCXW1FEBra5aFLJm48f0-b4a+oTugTZt+VYEv1EySBKg@mail.gmail.com>
To: Ian Rogers <irogers@google.com>


> On 7 Jun 2024, at 10:53=E2=80=AFPM, Ian Rogers <irogers@google.com> =
wrote:
>=20
> On Thu, Jun 6, 2024 at 9:44=E2=80=AFPM Athira Rajeev
> <atrajeev@linux.vnet.ibm.com> wrote:
>>=20
>> Perf bench futex fails as below when attempted to run on
>> on a powerpc system:
>>=20
>> ./perf bench futex all
>> Running futex/hash benchmark...
>> Run summary [PID 626307]: 80 threads, each operating on 1024 =
[private] futexes for 10 secs.
>>=20
>> perf: pthread_create: No such file or directory
>>=20
>> In the setup where this perf bench was ran, difference was that
>> partition had 640 CPU's, but not all CPUs were online. 80 CPUs
>> were online. While blocking the threads with futex_wait, code
>> sets the affinity using cpumask. The cpumask size used is 80
>> which is picked from "nrcpus =3D perf_cpu_map__nr(cpu)". Here the
>> benchmark reports fail while setting affinity for cpu number which
>> is greater than 80 or higher, because it attempts to set a bit
>> position which is not allocated on the cpumask. Fix this by changing
>> the size of cpumask to number of possible cpus and not the number
>> of online cpus.
>>=20
>> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
>=20
> For the series:
> Reviewed-by: Ian Rogers <irogers@google.com>

Hi Ian

Thanks for the review=20

Athira
>=20
> Thanks,
> Ian
>=20
>> ---
>> tools/perf/bench/futex-hash.c          | 2 +-
>> tools/perf/bench/futex-lock-pi.c       | 2 +-
>> tools/perf/bench/futex-requeue.c       | 2 +-
>> tools/perf/bench/futex-wake-parallel.c | 2 +-
>> tools/perf/bench/futex-wake.c          | 2 +-
>> 5 files changed, 5 insertions(+), 5 deletions(-)
>>=20
>> diff --git a/tools/perf/bench/futex-hash.c =
b/tools/perf/bench/futex-hash.c
>> index 0c69d20efa32..b472eded521b 100644
>> --- a/tools/perf/bench/futex-hash.c
>> +++ b/tools/perf/bench/futex-hash.c
>> @@ -174,7 +174,7 @@ int bench_futex_hash(int argc, const char **argv)
>>        pthread_attr_init(&thread_attr);
>>        gettimeofday(&bench__start, NULL);
>>=20
>> -       nrcpus =3D perf_cpu_map__nr(cpu);
>> +       nrcpus =3D cpu__max_cpu().cpu;
>>        cpuset =3D CPU_ALLOC(nrcpus);
>>        BUG_ON(!cpuset);
>>        size =3D CPU_ALLOC_SIZE(nrcpus);
>> diff --git a/tools/perf/bench/futex-lock-pi.c =
b/tools/perf/bench/futex-lock-pi.c
>> index 7a4973346180..0416120c091b 100644
>> --- a/tools/perf/bench/futex-lock-pi.c
>> +++ b/tools/perf/bench/futex-lock-pi.c
>> @@ -122,7 +122,7 @@ static void create_threads(struct worker *w, =
struct perf_cpu_map *cpu)
>> {
>>        cpu_set_t *cpuset;
>>        unsigned int i;
>> -       int nrcpus =3D  perf_cpu_map__nr(cpu);
>> +       int nrcpus =3D  cpu__max_cpu().cpu;
>>        size_t size;
>>=20
>>        threads_starting =3D params.nthreads;
>> diff --git a/tools/perf/bench/futex-requeue.c =
b/tools/perf/bench/futex-requeue.c
>> index d9ad736c1a3e..aad5bfc4fe18 100644
>> --- a/tools/perf/bench/futex-requeue.c
>> +++ b/tools/perf/bench/futex-requeue.c
>> @@ -125,7 +125,7 @@ static void block_threads(pthread_t *w, struct =
perf_cpu_map *cpu)
>> {
>>        cpu_set_t *cpuset;
>>        unsigned int i;
>> -       int nrcpus =3D perf_cpu_map__nr(cpu);
>> +       int nrcpus =3D cpu__max_cpu().cpu;
>>        size_t size;
>>=20
>>        threads_starting =3D params.nthreads;
>> diff --git a/tools/perf/bench/futex-wake-parallel.c =
b/tools/perf/bench/futex-wake-parallel.c
>> index b66df553e561..90a5b91bf139 100644
>> --- a/tools/perf/bench/futex-wake-parallel.c
>> +++ b/tools/perf/bench/futex-wake-parallel.c
>> @@ -149,7 +149,7 @@ static void block_threads(pthread_t *w, struct =
perf_cpu_map *cpu)
>> {
>>        cpu_set_t *cpuset;
>>        unsigned int i;
>> -       int nrcpus =3D perf_cpu_map__nr(cpu);
>> +       int nrcpus =3D cpu__max_cpu().cpu;
>>        size_t size;
>>=20
>>        threads_starting =3D params.nthreads;
>> diff --git a/tools/perf/bench/futex-wake.c =
b/tools/perf/bench/futex-wake.c
>> index 690fd6d3da13..49b3c89b0b35 100644
>> --- a/tools/perf/bench/futex-wake.c
>> +++ b/tools/perf/bench/futex-wake.c
>> @@ -100,7 +100,7 @@ static void block_threads(pthread_t *w, struct =
perf_cpu_map *cpu)
>>        cpu_set_t *cpuset;
>>        unsigned int i;
>>        size_t size;
>> -       int nrcpus =3D perf_cpu_map__nr(cpu);
>> +       int nrcpus =3D cpu__max_cpu().cpu;
>>        threads_starting =3D params.nthreads;
>>=20
>>        cpuset =3D CPU_ALLOC(nrcpus);
>> --
>> 2.43.0