Re: Wrong checksumming function chosen

On Sunday September 22, sarek@uliweb.de wrote:

Hi!

It seems as my computer (Athlon XP 2000+) chooses the wrong checksumming
function.

The kernel output is as follows:

raid5: measuring checksumming speed
   8regs     :  2564.000 MB/sec
   32regs    :  2260.000 MB/sec
   pIII_sse  :  4748.400 MB/sec
   pII_mmx   :  3921.200 MB/sec
   p5_mmx    :  5022.400 MB/sec
raid5: using function: pIII_sse (4748.400 MB/sec)

I hope I can help the developers with this piece of information.
And I also hope I mailed at the right address.

The only problem here is that the message is misleading.

pIII_sse is deliberately chosen despite appearing not to be so fast
because it avoid the level-1 cache which is appropriate for this data
which is only used by the CPU once.

NeilBrown

Greets,
-- 
Sebastian Schäfer
E-Mail: sarek@uliweb.de || http://www.uliweb.de
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html