[Intel-gfx] [Piketon bisected]TIMEOUT when running gem_tiled_blits

Meng, Mengmeng mengmeng.meng at intel.com
Fri Feb 11 11:47:51 CET 2011


My machine does not made progress. There is no warnings over netconsole. MemTotal in Piketon is about 1.8G. It takes about 
5s when running gem_tiled_blits normally. Timeout means 90s,even exist in process continuously.

-----Original Message-----
From: Chris Wilson [mailto:chris at chris-wilson.co.uk] 
Sent: Friday, February 11, 2011 5:15 PM
To: Meng, Mengmeng; Intel-gfx at lists.freedesktop.org
Cc: Meng, Mengmeng
Subject: Re: [Intel-gfx] [Piketon bisected]TIMEOUT when running gem_tiled_blits

On Fri, 11 Feb 2011 16:02:45 +0800, "Meng, Mengmeng" <mengmeng.meng at intel.com> wrote:
> Hi,
> There is something wrong about gem_tiled_blits. Timeout when running Intel_gpu_tools/gem_tiled_blits.
> It's case regression. By bisected,371f87f2d825900484e34a8ec78272b9e62cbc02 is the first bad commit.

Takes around 30s to run the exercise on my i3. The fun part is that it
tries to allocate 3+ GiB of memory in order to cause the aperture
thrashing and so test evicting tiled buffers. If you don't have that much
memory available, then you get swap thrashing or even the dreaded OOM.

[I thought about limiting it to total available memory...]

Is your machine making any progress? Did the kernel send any warnings over
netconsole? How much memory do you have and what is your timeout?
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre



More information about the Intel-gfx mailing list