All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@redhat.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: acme@kernel.org, jolsa@kernel.org, linux-kernel@vger.kernel.org,
	Andi Kleen <ak@linux.intel.com>
Subject: Re: [PATCH v4 3/9] perf evlist: Maintain evlist->all_cpus
Date: Wed, 6 Nov 2019 17:34:07 +0100	[thread overview]
Message-ID: <20191106163407.GN30214@krava> (raw)
In-Reply-To: <20191105002522.83803-4-andi@firstfloor.org>

On Mon, Nov 04, 2019 at 04:25:16PM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Maintain a cpumap in the evlist that is the union of all the cpus
> of the events.
> 
> This needs a cpumap merge operation. To make the merge operation
> work efficiently maintain the cpumap in a sorted state.
> 
> The sorting is also needed for the affinity loop changes later.
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  tools/perf/lib/cpumap.c                  | 42 ++++++++++++++++++++++++
>  tools/perf/lib/evlist.c                  |  1 +
>  tools/perf/lib/include/internal/evlist.h |  1 +
>  tools/perf/lib/include/perf/cpumap.h     |  2 ++
>  4 files changed, 46 insertions(+)
> 
> diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c
> index 2ca1fafa620d..5ca26a9d318f 100644
> --- a/tools/perf/lib/cpumap.c
> +++ b/tools/perf/lib/cpumap.c
> @@ -68,6 +68,11 @@ static struct perf_cpu_map *cpu_map__default_new(void)
>  	return cpus;
>  }
>  
> +static int cmp_int(const void *a, const void *b)
> +{
> +	return *(const int *)a - *(const int*)b;
> +}
> +
>  static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
>  {
>  	size_t payload_size = nr_cpus * sizeof(int);
> @@ -76,6 +81,7 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
>  	if (cpus != NULL) {
>  		cpus->nr = nr_cpus;
>  		memcpy(cpus->map, tmp_cpus, payload_size);
> +		qsort(cpus->map, nr_cpus, sizeof(int), cmp_int);
>  		refcount_set(&cpus->refcnt, 1);
>  	}
 
please move the sort into separate change

>  
> @@ -272,3 +278,39 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
>  
>  	return max;
>  }
> +
> +struct perf_cpu_map *perf_cpu_map__update(struct perf_cpu_map *orig,
> +					  struct perf_cpu_map *other)
> +{

it's more like perf_cpu_map__merge, right?

> +	int *tmp_cpus;
> +	int tmp_len;
> +	int i, j, k;
> +	struct perf_cpu_map *merged;
> +
> +	if (!orig) {
> +		perf_cpu_map__get(other);
> +		return other;
> +	}
> +	if (orig->nr == other->nr &&
> +	    !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
> +		return orig;
> +	tmp_len = orig->nr + other->nr;
> +	tmp_cpus = malloc(tmp_len * sizeof(int));
> +	if (!tmp_cpus)
> +		return NULL;
> +	i = j = k = 0;
> +	while (i < orig->nr && j < other->nr) {
> +		if (orig->map[i] <= other->map[j])
> +			tmp_cpus[k++] = orig->map[i++];
> +		else
> +			tmp_cpus[k++] = other->map[j++];
> +	}
> +	while (i < orig->nr)
> +		tmp_cpus[k++] = orig->map[i++];
> +	while (j < other->nr)
> +		tmp_cpus[k++] = other->map[j++];
> +	assert(k < tmp_len);
> +	merged = cpu_map__trim_new(k, tmp_cpus);
> +	free(tmp_cpus);
> +	return merged;
> +}

this is great function for automated test, please add

thanks,
jirka


  reply	other threads:[~2019-11-06 16:34 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-05  0:25 Optimize perf stat for large number of events/cpus Andi Kleen
2019-11-05  0:25 ` [PATCH v4 1/9] perf pmu: Use file system cache to optimize sysfs access Andi Kleen
2019-11-05  0:25 ` [PATCH v4 2/9] perf affinity: Add infrastructure to save/restore affinity Andi Kleen
2019-11-05  0:25 ` [PATCH v4 3/9] perf evlist: Maintain evlist->all_cpus Andi Kleen
2019-11-06 16:34   ` Jiri Olsa [this message]
2019-11-05  0:25 ` [PATCH v4 4/9] perf evsel: Add iterator to iterate over events ordered by CPU Andi Kleen
2019-11-05  0:25 ` [PATCH v4 5/9] perf stat: Use affinity for closing file descriptors Andi Kleen
2019-11-06 16:33   ` Jiri Olsa
2019-11-06 16:34   ` Jiri Olsa
2019-11-05  0:25 ` [PATCH v4 6/9] perf stat: Factor out open error handling Andi Kleen
2019-11-06 16:33   ` Jiri Olsa
2019-11-05  0:25 ` [PATCH v4 7/9] perf stat: Use affinity for opening events Andi Kleen
2019-11-06 16:34   ` Jiri Olsa
2019-11-05  0:25 ` [PATCH v4 8/9] perf stat: Use affinity for reading Andi Kleen
2019-11-05  0:25 ` [PATCH v4 9/9] perf stat: Use affinity for enabling/disabling events Andi Kleen
2019-11-06 16:34   ` Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191106163407.GN30214@krava \
    --to=jolsa@redhat.com \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=andi@firstfloor.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.