linux-kernel - Re: [PATCH 1/2] perf report: Add --percent-limit option

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-prev] [day] [month] [year] [list]

Message-ID: <87hai65qhn.fsf@sejong.aot.lge.com>
Date:	Tue, 14 May 2013 09:56:04 +0900
From:	Namhyung Kim <namhyung@...nel.org>
To:	Andi Kleen <andi@...stfloor.org>
Cc:	Arnaldo Carvalho de Melo <acme@...stprotocols.net>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Paul Mackerras <paulus@...ba.org>,
	Ingo Molnar <mingo@...nel.org>,
	Namhyung Kim <namhyung.kim@....com>,
	LKML <linux-kernel@...r.kernel.org>,
	Jiri Olsa <jolsa@...hat.com>, David Ahern <dsahern@...il.com>,
	Stephane Eranian <eranian@...gle.com>
Subject: Re: [PATCH 1/2] perf report: Add --percent-limit option

Hi Andi,

On Mon, 13 May 2013 16:11:17 +0200, Andi Kleen wrote:
> On Mon, May 13, 2013 at 05:41:42PM +0900, Namhyung Kim wrote:
>> From: Namhyung Kim <namhyung.kim@....com>
>> 
>> The --percent-limit option is for not showing small overheaded entries
>> in the output.  Maybe we want to set a certain default value like 0.1.
>> 
>> Cc: Andi Kleen <andi@...stfloor.org>
>
> I like the option, but 0 is not a good default.
> Make it 1 or something.

Thanks.  I just wanted to reserve same behavior since I didn't know
what's the reasonable default value.  We might use a config variable for
this to customize the default value.

>
> Perhaps a better heuristic would be 
> percent < threshold || samples < sample-threshold
> with sample-threshold being several hundred at least.
>
> A very small number of hits on something is usually quite much useless,
> unless your original event was extremly rare in the beginning
> (but then it's unclear if the profile is any useful)

Looks reasonable, but I know there's also some users who use the perf
tools lightly.  A several hundreds sample-threshold looks too harsh to
them IMHO.  In addition, it should handle tracepoints.

Thanks,
Namhyung
--
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/