linux-kernel - Re: [PATCH] perf report: Add a simple GTK2-based 'perf report' browser

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

Date:	Thu, 23 Feb 2012 15:37:43 -0200
From:	Arnaldo Carvalho de Melo <acme@...stprotocols.net>
To:	Pekka Enberg <penberg@...nel.org>
Cc:	linux-kernel@...r.kernel.org,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Paul Mackerras <paulus@...ba.org>, Ingo Molnar <mingo@...e.hu>
Subject: Re: [PATCH] perf report: Add a simple GTK2-based 'perf report'
 browser

Em Thu, Feb 23, 2012 at 07:10:48PM +0200, Pekka Enberg escreveu:
> On Thu, Feb 23, 2012 at 6:53 PM, Arnaldo Carvalho de Melo <acme@...stprotocols.net> wrote:
> > Em Thu, Feb 23, 2012 at 02:47:39PM -0200, Arnaldo Carvalho de Melo escreveu:
> >> Em Thu, Feb 23, 2012 at 06:45:04PM +0200, Pekka Enberg escreveu:
> >> > How big files are we talking about here?
> >>
> >> 5 MB ones, say.
> >
> > Nah:
> >
> > [root@...icio linux]# perf record -a -F 10000 sleep 5m
> > [ perf record: Woken up 166 times to write data ]
> > [ perf record: Captured and wrote 42.104 MB perf.data (~1839573 samples)
> > ]
> > [root@...icio linux]#
> > [root@...icio linux]#
> > [root@...icio linux]# perf report --gtk
> >
> >  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
> > 10618 root      20   0  408m 170m  49m S  0.0  2.2   0:04.71 perf
> >
> > [root@...icio linux]# perf report --tui
> >
> > 10633 root      20   0  379m 165m  45m S  0.0  2.1   0:01.15 perf
> 
> Sorry, I don't understand how to interpret your numbers.

I was just gauging how much overhead --gtk had over --tui, for this
specific file VIRT was "just" 29 MB more, which for todays standards is
almost nothing :-)

So just for really, really big files this will make a difference.
 
> I used the same "perf record" command here which generated a 26 MB
> perf.data file. "perf report --gtk" starts up almost instantly here.

Yeah, seems to be OK for most cases, for the ones where it may get in
the way, we can use --tui or --stdio or revisit the providing a callback
for GTK to ask for just the lines it wants rendered.

One thing I saw was that it now defaults to --stdio and then doesn't
setup the pager, i.e. just build it with newt-devel, gtk2-devel
installed and don't specify --gtk to see what I mean.

- Arnaldo
--
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/