linux-kernel - [PATCH 0/4][RFC] perf bench: prepare framework for parallel oriented benchmarking

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <1272808519-4743-1-git-send-email-mitake@dcl.info.waseda.ac.jp>
Date:	Sun,  2 May 2010 22:55:15 +0900
From:	Hitoshi Mitake <mitake@....info.waseda.ac.jp>
To:	Ingo Molnar <mingo@...e.hu>
Cc:	linux-kernel@...r.kernel.org, mitake@....info.waseda.ac.jp,
	h.mitake@...il.com, Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Paul Mackerras <paulus@...ba.org>,
	Arnaldo Carvalho de Melo <acme@...hat.com>,
	Frederic Weisbecker <fweisbec@...il.com>
Subject: [PATCH 0/4][RFC] perf bench: prepare framework for parallel oriented benchmarking

Hi Ingo,

I made a change on "perf bench" and made patch series
for parallel oriented benchmarking.

Previous perf bench provided only least
framework for each benchmark programs,
but I felt this was not enough.

Because it seems that lots of today's performance issue
is found by multi thread/process programs.

So I made perf bench to provide the framework
for easy parallel benchmark writing.

And this is a preparation for "perf bench syscall".
Because each benchmarks of system call
will be required parallel workloads,
but parallel frameworks for each benchmarks will be fat code.

Request for comments!

Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Paul Mackerras <paulus@...ba.org>
Cc: Arnaldo Carvalho de Melo <acme@...hat.com>
Cc: Frederic Weisbecker <fweisbec@...il.com>

Hitoshi Mitake (4):
  perf bench: add "sample" subsystem and "sample" suite as sample
    benchmark program
  perf bench: fix "mem" subsystem to adopt new style of perf bench
  perf bench: fix "sched" subsystem to adopt new style of perf bench
  perf bench: improve perf bench for parallel oriented benchmarking

 tools/perf/Makefile                |    5 +
 tools/perf/bench/bench.h           |   32 ++
 tools/perf/bench/mem-memcpy.c      |  182 ++++--------
 tools/perf/bench/mem.h             |    4 +
 tools/perf/bench/sample-sample.c   |   98 +++++++
 tools/perf/bench/sample.h          |    4 +
 tools/perf/bench/sched-messaging.c |  553 ++++++++++++++++++++----------------
 tools/perf/bench/sched-pipe.c      |  146 +++++-----
 tools/perf/bench/sched.h           |    8 +
 tools/perf/builtin-bench.c         |  227 +++++++++++----
 10 files changed, 762 insertions(+), 497 deletions(-)
 create mode 100644 tools/perf/bench/mem.h
 create mode 100644 tools/perf/bench/sample-sample.c
 create mode 100644 tools/perf/bench/sample.h
 create mode 100644 tools/perf/bench/sched.h

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/