Re: [Bug #11308] tbench regression on each kernel release from 2.6.22 -> 2.6.28

[Mike Galbraith]

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

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/