Re: [PATCH v10 05/24] perf record: Introduce thread local variable

[Jiri Olsa <jolsa@redhat.com>]

On Mon, Jul 12, 2021 at 09:46:05AM +0300, Alexey Bayduraev wrote:
> Introduce thread local variable and use it for threaded trace streaming.
> Use thread affinity mask instead or record affinity mask in affinity
> modes.
> 
> Acked-by: Andi Kleen <ak@linux.intel.com>
> Acked-by: Namhyung Kim <namhyung@gmail.com>
> Signed-off-by: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
> ---
>  tools/perf/builtin-record.c | 139 ++++++++++++++++++++++++------------
>  1 file changed, 93 insertions(+), 46 deletions(-)
> 
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index a25b23affc43..dfc5db24e037 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -110,6 +110,8 @@ struct record_thread {
>  	unsigned long		waking;
>  };
>  
> +static __thread struct record_thread *thread;
> +
>  struct record {
>  	struct perf_tool	tool;
>  	struct record_opts	opts;
> @@ -132,7 +134,6 @@ struct record {
>  	bool			timestamp_boundary;
>  	struct switch_output	switch_output;
>  	unsigned long long	samples;
> -	struct mmap_cpu_mask	affinity_mask;
>  	unsigned long		output_max_size;	/* = 0: unlimited */
>  	int			nr_threads;
>  	struct thread_mask	*thread_masks;
> @@ -574,7 +575,7 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
>  		bf   = map->data;
>  	}
>  
> -	rec->samples++;
> +	thread->samples++;
>  	return record__write(rec, map, bf, size);
>  }
>  
> @@ -1317,19 +1318,29 @@ static struct perf_event_header finished_round_event = {
>  	.type = PERF_RECORD_FINISHED_ROUND,
>  };
>  
> -static void record__adjust_affinity(struct record *rec, struct mmap *map)
> +static int record__adjust_affinity(struct record *rec, struct mmap *map)

hm, why changing the return value if the caller does not check it?

jirka

>  {
> +	int ret = 0;
> +
>  	if (rec->opts.affinity != PERF_AFFINITY_SYS &&
> -	    !bitmap_equal(rec->affinity_mask.bits, map->affinity_mask.bits,
> -			  rec->affinity_mask.nbits)) {
> -		bitmap_zero(rec->affinity_mask.bits, rec->affinity_mask.nbits);
> -		bitmap_or(rec->affinity_mask.bits, rec->affinity_mask.bits,
> -			  map->affinity_mask.bits, rec->affinity_mask.nbits);
> -		sched_setaffinity(0, MMAP_CPU_MASK_BYTES(&rec->affinity_mask),
> -				  (cpu_set_t *)rec->affinity_mask.bits);
> -		if (verbose == 2)
> -			mmap_cpu_mask__scnprintf(&rec->affinity_mask, "thread");
> +	    !bitmap_equal(thread->mask->affinity.bits, map->affinity_mask.bits,
> +			  thread->mask->affinity.nbits)) {
> +		bitmap_zero(thread->mask->affinity.bits, thread->mask->affinity.nbits);
> +		bitmap_or(thread->mask->affinity.bits, thread->mask->affinity.bits,
> +			  map->affinity_mask.bits, thread->mask->affinity.nbits);
> +		ret = sched_setaffinity(0, MMAP_CPU_MASK_BYTES(&thread->mask->affinity),
> +					(cpu_set_t *)thread->mask->affinity.bits);
> +		if (ret)
> +			pr_err("threads[%d]: sched_setaffinity() call failed: %s\n",
> +			       thread->tid, strerror(errno));
> +		if (verbose == 2) {
> +			pr_debug("threads[%d]: addr=", thread->tid);
> +			mmap_cpu_mask__scnprintf(&thread->mask->affinity, "thread");
> +			pr_debug("threads[%d]: on cpu=%d\n", thread->tid, sched_getcpu());
> +		}
>  	}
> +
> +	return ret;
>  }

SNIP