Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Wed, 23 Mar 2022 12:07:11 +0100
From:   Jiri Olsa <olsajiri@gmail.com>
To:     Thomas Richter <tmricht@linux.ibm.com>
Cc:     linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
        acme@kernel.org, namhyung@kernel.org, gor@linux.ibm.com,
        acme@redhat.com, svens@linux.ibm.com, sumanthk@linux.ibm.com,
        hca@linux.ibm.com
Subject: Re: [PATCH] perf/stat: Fix perf stat for forked applications
Message-ID: <Yjr/X+Cuunyo84S3@krava>
References: <20220317155346.577384-1-tmricht@linux.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20220317155346.577384-1-tmricht@linux.ibm.com>
Precedence: bulk

On Thu, Mar 17, 2022 at 04:53:46PM +0100, Thomas Richter wrote:
> I have run into the following issue:
> 
>  # perf stat -a -e new_pmu/INSTRUCTION_7/ --  mytest -c1 7
> 
>  Performance counter stats for 'system wide':
> 
>                  0      new_pmu/INSTRUCTION_7/
> 
>        0.000366428 seconds time elapsed
>  #
> 
> The new PMU for s390 counts the execution of certain CPU instructions.
> The root cause is the extremely small run time of the
> mytest program. It just executes some assembly instructions
> and then exits. In above invocation the instruction is executed
> exactly one time (-c1 option). The PMU is expected to report this one
> time execution by a counter value of one, but fails to do so
> in some cases, not all.
> 
> Debugging reveals the invocation of the child process is done
> *before* the counter events are installed and enabled. Tracing
> reveals that sometimes the child process starts and exits before
> the event is installed on all CPUs. The more CPUs the machine has,
> the more often this miscount happens.
> 
> Fix this by reversing the start of the work load after the events
> have been installed on the specified CPUs. Now the comment also
> matches the code.
> 
> Output after:
>  # perf stat -a -e new_pmu/INSTRUCTION_7/ --  mytest -c1 7
> 
>  Performance counter stats for 'system wide':
> 
>                  1      new_pmu/INSTRUCTION_7/
> 
>        0.000366428 seconds time elapsed
>  #
> 
> Now the correct result is reported rock solid all the time regardless
> how many CPUs are online.
> 
> Fixes:  acf2892270dc ("perf stat: Use perf_evlist__prepare/start_workload())
> 
> Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
> Acked-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
> Cc: Namhyung Kim <namhyung@kernel.org>
> ---
>  tools/perf/builtin-stat.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 3f98689dd687..60baa3dadc4b 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -955,10 +955,10 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
>  	 * Enable counters and exec the command:
>  	 */
>  	if (forks) {
> -		evlist__start_workload(evsel_list);
>  		err = enable_counters();
>  		if (err)
>  			return -1;
> +		evlist__start_workload(evsel_list);

right, without -a the event has enable_on_exec so the race does not
matter, but it's a problem for system wide with fork

Acked-by: Jiri Olsa <jolsa@kernel.org>

thanks,
jirka

>  
>  		t0 = rdclock();
>  		clock_gettime(CLOCK_MONOTONIC, &ref_time);
> -- 
> 2.35.1
>