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]
Date:	Wed, 13 Jun 2012 21:44:37 +0200
From:	Guillaume Bouchard <guillaume.bouchard@...is.cnrs.fr>
To:	Eric Dumazet <eric.dumazet@...il.com>
Cc:	linux-kernel@...r.kernel.org
Subject: Re: PROBLEM: Keyboard/mouse freeze with high network usage (r8169/brcmsmac/broadcom-wl)

Hello,

On Tue, Jun 12, 2012 at 11:14 PM, Eric Dumazet <eric.dumazet@...il.com> wrote:
> If your script can trigger the freeze in less than 5 minutes, you could
> start a background job to check /proc/meminfo, it sounds there is a mem
> leak ?
>
> while :
> do
>  date
>  cat /proc/meminfo
>  cat /proc/slabinfo
>  sleep 10
> done

Today it tooks 55 minutes to freeze. Kind of an heisenbug.

I have the /proc/meminfo and slabinfo trace, but it is around 4Mo, so
I put them on a separate host

http://gobpower.free.fr/meminfo/

This directory contains the cat of meminfo/slabinfo
(dump_meminfo_slabinfo), and *commands* and *data.dat* files which are
gnuplot files to display the curve of meminfo values. (gnuplot > load
'commands' to display it).

I don't know what I'm supposed to look for, so I tried to get closer
look on different part of the graph but it does not really talk to me.

I included an image of the graph, the .png in the same directory.  X
axis is the time (in 10 seconds).

between 0 and 180 in x (0 to 1800 seconds), some curves are really
noisy, but it may coincide with the time I was using the computer and
tried to make it freeze.

The committed AS, inactive and inactive file are increasing through
time, and the so call "Mem Free" is decreasing.

Between 250 and 300 did the freeze happened. At approximately 300, I
noticed it and unload the psmouse module. We can notice some sharp cut
in some curves at this moment.

Sorry, I'm a bit lost to interpret those stuffs, all I can do for now
is following your advices, so if you find something in this log and
need more experimentations, I'll be happy to do them.

Thank you for your time.

-- 
Guillaume
--
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/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ