From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Jiri Olsa <jolsa@kernel.org>
Cc: lkml <linux-kernel@vger.kernel.org>,
Don Zickus <dzickus@redhat.com>, Joe Mario <jmario@redhat.com>,
Ingo Molnar <mingo@kernel.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Namhyung Kim <namhyung@kernel.org>,
David Ahern <dsahern@gmail.com>, Andi Kleen <andi@firstfloor.org>
Subject: Re: [PATCH 49/57] perf c2c report: Limit the cachelines table entries
Date: Mon, 10 Oct 2016 17:01:21 -0300 [thread overview]
Message-ID: <20161010200121.GN4809@kernel.org> (raw)
In-Reply-To: <1474558645-19956-50-git-send-email-jolsa@kernel.org>
Em Thu, Sep 22, 2016 at 05:37:17PM +0200, Jiri Olsa escreveu:
> Add a limit for entries number of the cachelines table
> entries. By default now it's the 0.0005% minimum of
> remote HITMs.
>
> Also display only cachelines with remote hitm or store data.
Humm, this made my test machine, which has just one CPU, to show nothing
:-\
I think we need to have a command line switch to control this?
I'm leaving this patch for later.
- Arnaldo
> Link: http://lkml.kernel.org/n/tip-inykbom2f19difvsu1e18avr@git.kernel.org
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
> tools/perf/builtin-c2c.c | 36 ++++++++++++++++++++++++++++++++++--
> tools/perf/util/hist.c | 1 +
> tools/perf/util/hist.h | 1 +
> 3 files changed, 36 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
> index 31e311959480..ff89c0b86c44 100644
> --- a/tools/perf/builtin-c2c.c
> +++ b/tools/perf/builtin-c2c.c
> @@ -1639,11 +1639,42 @@ static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
> return hpp_list__parse(&c2c_hists->list, output, sort);
> }
>
> -static int filter_cb(struct hist_entry *he __maybe_unused)
> +#define DISPLAY_LINE_LIMIT 0.0005
> +
> +static bool he__display(struct hist_entry *he, struct c2c_stats *stats)
> +{
> + struct c2c_hist_entry *c2c_he;
> + double ld_dist;
> +
> + c2c_he = container_of(he, struct c2c_hist_entry, he);
> +
> + if (stats->rmt_hitm) {
> + ld_dist = ((double)c2c_he->stats.rmt_hitm / stats->rmt_hitm);
> + if (ld_dist < DISPLAY_LINE_LIMIT)
> + he->filtered = HIST_FILTER__C2C;
> + } else {
> + he->filtered = HIST_FILTER__C2C;
> + }
> +
> + return he->filtered == 0;
> +}
> +
> +static inline int valid_hitm_or_store(struct hist_entry *he)
> +{
> + struct c2c_hist_entry *c2c_he;
> +
> + c2c_he = container_of(he, struct c2c_hist_entry, he);
> + return c2c_he->stats.rmt_hitm || c2c_he->stats.store;
> +}
> +
> +static int filter_cb(struct hist_entry *he)
> {
> if (c2c.show_src && !he->srcline)
> he->srcline = hist_entry__get_srcline(he);
>
> + if (!valid_hitm_or_store(he))
> + he->filtered = HIST_FILTER__C2C;
> +
> return 0;
> }
>
> @@ -1651,11 +1682,12 @@ static int resort_cl_cb(struct hist_entry *he)
> {
> struct c2c_hist_entry *c2c_he;
> struct c2c_hists *c2c_hists;
> + bool display = he__display(he, &c2c.hitm_stats);
>
> c2c_he = container_of(he, struct c2c_hist_entry, he);
> c2c_hists = c2c_he->hists;
>
> - if (c2c_hists) {
> + if (display && c2c_hists) {
> c2c_hists__reinit(c2c_hists,
> "percent_rmt_hitm,"
> "percent_lcl_hitm,"
> diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
> index b02992efb513..e1be4132054d 100644
> --- a/tools/perf/util/hist.c
> +++ b/tools/perf/util/hist.c
> @@ -1195,6 +1195,7 @@ static void hist_entry__check_and_remove_filter(struct hist_entry *he,
> case HIST_FILTER__GUEST:
> case HIST_FILTER__HOST:
> case HIST_FILTER__SOCKET:
> + case HIST_FILTER__C2C:
> default:
> return;
> }
> diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
> index 9928fed8bc59..d4b6514eeef5 100644
> --- a/tools/perf/util/hist.h
> +++ b/tools/perf/util/hist.h
> @@ -22,6 +22,7 @@ enum hist_filter {
> HIST_FILTER__GUEST,
> HIST_FILTER__HOST,
> HIST_FILTER__SOCKET,
> + HIST_FILTER__C2C,
> };
>
> enum hist_column {
> --
> 2.7.4
next prev parent reply other threads:[~2016-10-10 20:01 UTC|newest]
Thread overview: 107+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-22 15:36 [PATCHv4 00/57] perf c2c: Add new tool to analyze cacheline contention on NUMA systems Jiri Olsa
2016-09-22 15:36 ` [PATCH 01/57] perf tools: Add __hist_entry__snprintf function Jiri Olsa
2016-09-22 15:50 ` Arnaldo Carvalho de Melo
2016-09-23 5:28 ` [tip:perf/core] perf hists: " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 02/57] perf tools: Introduce c2c_decode_stats function Jiri Olsa
2016-10-22 8:31 ` [tip:perf/core] perf c2c: " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 03/57] perf tools: Introduce c2c_add_stats function Jiri Olsa
2016-10-22 8:31 ` [tip:perf/core] perf c2c: " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 04/57] perf tools: Make reset_dimensions global Jiri Olsa
2016-09-22 15:50 ` Arnaldo Carvalho de Melo
2016-09-23 5:29 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 05/57] perf tools: Make output_field_add and sort_dimension__add global Jiri Olsa
2016-09-22 15:50 ` Arnaldo Carvalho de Melo
2016-09-23 5:29 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 06/57] perf tools: Make several sorting functions global Jiri Olsa
2016-09-22 15:50 ` Arnaldo Carvalho de Melo
2016-09-23 5:29 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 07/57] perf tools: Make several display " Jiri Olsa
2016-09-22 15:50 ` Arnaldo Carvalho de Melo
2016-09-23 5:30 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 08/57] perf tools: Make __hist_entry__snprintf function global Jiri Olsa
2016-09-22 15:50 ` Arnaldo Carvalho de Melo
2016-09-23 5:30 ` [tip:perf/core] perf hists: " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 09/57] perf tools: Make hists__fprintf_headers " Jiri Olsa
2016-09-22 15:51 ` Arnaldo Carvalho de Melo
2016-09-23 5:31 ` [tip:perf/core] perf hists: " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 10/57] perf c2c: Add c2c command Jiri Olsa
2016-10-22 8:32 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 11/57] perf c2c: Add record subcommand Jiri Olsa
2016-10-22 8:32 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 12/57] perf c2c: Add report subcommand Jiri Olsa
2016-10-22 8:33 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 13/57] perf c2c report: Add dimension support Jiri Olsa
2016-10-22 8:33 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 14/57] perf c2c report: Add sort_entry " Jiri Olsa
2016-10-22 8:34 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 15/57] perf c2c report: Fallback to standard dimensions Jiri Olsa
2016-10-22 8:34 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 16/57] perf c2c report: Add sample processing Jiri Olsa
2016-10-22 8:35 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 17/57] perf c2c report: Add cacheline hists processing Jiri Olsa
2016-10-22 8:35 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 18/57] perf c2c report: Decode c2c_stats for hist entries Jiri Olsa
2016-10-22 8:36 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 19/57] perf c2c report: Add header macros Jiri Olsa
2016-10-22 8:36 ` [tip:perf/core] " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 20/57] perf c2c report: Add dcacheline dimension key Jiri Olsa
2016-10-04 16:50 ` Arnaldo Carvalho de Melo
2016-10-04 22:46 ` Jiri Olsa
2016-10-05 10:45 ` Arnaldo Carvalho de Melo
2016-10-05 10:50 ` Arnaldo Carvalho de Melo
2016-10-05 12:38 ` Jiri Olsa
2016-10-05 13:21 ` Arnaldo Carvalho de Melo
2016-10-05 11:01 ` Arnaldo Carvalho de Melo
2016-10-05 11:05 ` Arnaldo Carvalho de Melo
2016-10-05 12:45 ` Jiri Olsa
2016-10-05 13:09 ` Jiri Olsa
2016-10-05 13:26 ` Arnaldo Carvalho de Melo
2016-10-05 13:38 ` Jiri Olsa
2016-10-05 14:02 ` Jiri Olsa
2016-10-05 13:23 ` Arnaldo Carvalho de Melo
2016-10-22 8:37 ` [tip:perf/core] perf c2c report: Add 'dcacheline' " tip-bot for Jiri Olsa
2016-09-22 15:36 ` [PATCH 21/57] perf c2c report: Add offset " Jiri Olsa
2016-10-05 10:57 ` Arnaldo Carvalho de Melo
2016-10-05 12:11 ` Jiri Olsa
2016-09-22 15:36 ` [PATCH 22/57] perf c2c report: Add iaddr " Jiri Olsa
2016-09-22 15:36 ` [PATCH 23/57] perf c2c report: Add hitm related dimension keys Jiri Olsa
2016-09-22 15:36 ` [PATCH 24/57] perf c2c report: Add stores " Jiri Olsa
2016-09-22 15:36 ` [PATCH 25/57] perf c2c report: Add loads " Jiri Olsa
2016-09-22 15:36 ` [PATCH 26/57] perf c2c report: Add llc and remote " Jiri Olsa
2016-09-22 15:36 ` [PATCH 27/57] perf c2c report: Add llc load miss dimension key Jiri Olsa
2016-09-22 15:36 ` [PATCH 28/57] perf c2c report: Add total record sort key Jiri Olsa
2016-09-22 15:36 ` [PATCH 29/57] perf c2c report: Add total loads " Jiri Olsa
2016-09-22 15:36 ` [PATCH 30/57] perf c2c report: Add hitm percent " Jiri Olsa
2016-09-22 15:36 ` [PATCH 31/57] perf c2c report: Add hitm/store percent related sort keys Jiri Olsa
2016-09-22 15:37 ` [PATCH 32/57] perf c2c report: Add dram " Jiri Olsa
2016-09-22 15:37 ` [PATCH 33/57] perf c2c report: Add pid sort key Jiri Olsa
2016-09-22 15:37 ` [PATCH 34/57] perf c2c report: Add tid " Jiri Olsa
2016-09-22 15:37 ` [PATCH 35/57] perf c2c report: Add symbol and dso sort keys Jiri Olsa
2016-09-22 15:37 ` [PATCH 36/57] perf c2c report: Add node sort key Jiri Olsa
2016-09-22 15:37 ` [PATCH 37/57] perf c2c report: Add stats related sort keys Jiri Olsa
2016-09-22 15:37 ` [PATCH 38/57] perf c2c report: Add cpu cnt sort key Jiri Olsa
2016-09-22 15:37 ` [PATCH 39/57] perf c2c report: Add src line " Jiri Olsa
2016-10-10 16:47 ` Arnaldo Carvalho de Melo
2016-09-22 15:37 ` [PATCH 40/57] perf c2c report: Setup number of header lines for hists Jiri Olsa
2016-09-22 15:37 ` [PATCH 41/57] perf c2c report: Set final resort fields Jiri Olsa
2016-09-22 15:37 ` [PATCH 42/57] perf c2c report: Add stdio output support Jiri Olsa
2016-09-22 15:37 ` [PATCH 43/57] perf c2c report: Add main browser Jiri Olsa
2016-09-22 15:37 ` [PATCH 44/57] perf c2c report: Add cacheline browser Jiri Olsa
2016-09-22 15:37 ` [PATCH 45/57] perf c2c report: Add global stats stdio output Jiri Olsa
2016-09-22 15:37 ` [PATCH 46/57] perf c2c report: Add shared cachelines " Jiri Olsa
2016-09-22 15:37 ` [PATCH 47/57] perf c2c report: Add c2c related " Jiri Olsa
2016-09-22 15:37 ` [PATCH 48/57] perf c2c report: Allow to report callchains Jiri Olsa
2016-09-22 15:37 ` [PATCH 49/57] perf c2c report: Limit the cachelines table entries Jiri Olsa
2016-10-10 20:01 ` Arnaldo Carvalho de Melo [this message]
2016-10-11 9:22 ` Jiri Olsa
2016-09-22 15:37 ` [PATCH 50/57] perf c2c report: Add support to choose local HITMs Jiri Olsa
2016-09-22 15:37 ` [PATCH 51/57] perf c2c report: Allow to set cacheline sort fields Jiri Olsa
2016-09-22 15:37 ` [PATCH 52/57] perf c2c report: Recalc width of global sort entries Jiri Olsa
2016-09-22 15:37 ` [PATCH 53/57] perf c2c report: Add cacheline index entry Jiri Olsa
2016-09-22 15:37 ` [PATCH 54/57] perf c2c report: Add support to manage symbol name length Jiri Olsa
2016-09-22 15:37 ` [PATCH 55/57] perf c2c report: Iterate node display in browser Jiri Olsa
2016-09-22 15:37 ` [PATCH 56/57] perf c2c report: Add help windows Jiri Olsa
2016-09-22 15:37 ` [PATCH 57/57] perf c2c: Add man page and credits Jiri Olsa
2016-09-29 9:19 ` [PATCHv4 00/57] perf c2c: Add new tool to analyze cacheline contention on NUMA systems Peter Zijlstra
2016-09-29 14:54 ` Arnaldo Carvalho de Melo
2016-10-01 13:44 ` Joe Mario
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=20161010200121.GN4809@kernel.org \
--to=acme@kernel.org \
--cc=a.p.zijlstra@chello.nl \
--cc=andi@firstfloor.org \
--cc=dsahern@gmail.com \
--cc=dzickus@redhat.com \
--cc=jmario@redhat.com \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).