lkml.org 
[lkml]   [2008]   [Sep]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [Bug #11308] tbench regression on each kernel release from 2.6.22 -> 2.6.28
From
Date
On Sat, 2008-09-13 at 13:44 +0200, Mike Galbraith wrote:

> 2.6.27-rc6
> Throughput 1037.98 MB/sec 4 procs
>
> 16384 87380 1 1 60.00 80293.80
> 16384 87380 1 1 60.00 80266.60
> 16384 87380 1 1 60.00 80394.83
> 16384 87380 1 1 60.01 80397.27

<snip... sigh>

goes back to current real .27 config

Throughput 1022.52 MB/sec 4 procs

16384 87380 1 1 60.00 75941.95
16384 87380 1 1 60.01 76002.46
16384 87380 1 1 60.01 76367.55
16384 87380 1 1 60.00 76188.66

...

demodularizes seriously over-configured network

Throughput 750.175 MB/sec 4 procs

16384 87380 1 1 60.00 49270.35
16384 87380 1 1 60.01 49233.86
16384 87380 1 1 60.00 49265.72
16384 87380 1 1 60.00 49227.00

Very un-good thing to try. Stupid thing too?

-Mike



\
 
 \ /
  Last update: 2008-09-14 08:29    [W:0.330 / U:0.512 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site