lkml.org 
[lkml]   [1998]   [Dec]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: SCSI write caching (was: Dumb question: Which is "better" SCSI or IDE disks?)
On Wed, 9 Dec 1998, C S Hendrix wrote:

> Last night I ran some tests with bonnie.c on my system with a DPT
> 2044 controller and two Seagate Hawk fast-wide drives.
>
> The tests were actually faster with write cache turned off. I'm not
> sure I really expected it to be faster, but I was surprised that
> cache slowed things down.
>
> I'm talking too about a fairly significant different of nearly
> 2MB/sec on the block output test.
>
> Granted, bonnie and other benchmarks are not the best, but I think
> it is safe to at least say write-cache enabled was slower.

It is only slower in your particular load. When writing absurde
amounts of data having the write cache on can cause the disk to
have to make a few more seeks.

Under 'normal' load the write cache helps an awful lot since the
drive can simply hold back a write until it's either too old or
the driver passes the sector it wants to write and it can write
it cheaply.

In my experience write cache does indeed slow down benchmarks
but it really helps in real life performance...

cheers,

Rik -- the flu hits, the flu hits, the flu hits -- MORE
+-------------------------------------------------------------------+
| Linux memory management tour guide. H.H.vanRiel@phys.uu.nl |
| Scouting Vries cubscout leader. http://www.phys.uu.nl/~riel/ |
+-------------------------------------------------------------------+


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

\
 
 \ /
  Last update: 2005-03-22 13:46    [W:2.273 / U:0.008 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site