On May 26, 2004 02:58 pm, Si Jones <si@xxxxxxxxxxxxxxxxx> wrote:
> >Date: Wed, 26 May 2004 13:02:45 -0500
> >From: Randy Kelsoe <randykel@xxxxxxxxxx>
> >Subject: Re: SATA Silicon Image Speed Issue
> >To: For users of Fedora Core releases <fedora-list@xxxxxxxxxx>
> >Message-ID: <40B4DBC5.8030406@xxxxxxxxxx>
> >Content-Type: text/plain; charset=us-ascii; format=flowed
> >
> >Si Jones wrote:
> >>When looking at the logs the driver seems to show that UDMA133 is max
> >>and the drive is configured to UDMA100.
> >>
> >>Am wondering why? under windows the drive shows as UDMA6 Mode /
>
> UDMA150
>
> >>so was wondering does anyone know how to get the driver to change
>
> mode,
>
> >>also native command queueing should be available but am unsure how to
> >>check this.... anyone any good with this?
> >
> >Are you running FC1 or FC2? With FC1 and a 2.4 kernel, the driver is
> >PATA and not SATA, so the drive will look like an ATA100. I'm not
> >running FC2, yet, so I don't know if libata for the SATA drives is
> >working, or set up.
>
> Am running FC2, kernel 2.6.6 and had the same issues on kernel 2.6.5, it
> is libata in the kernel and works fine but as said there seems to be
> very relaxed performance. Am not saying it is bad, but belive it could
> be better.
I just ran bonnie++ on my VIA chipset SATA controller (Athlon64 K8T800
Chipset) using the VIA driver (not libata) and I only got 54,000 KBps Read
and Write. (54,000/1024 ~ 52.73 MBps) The drive does not appear to run slowly
at all and those numbers are really good actually.
The write is faster than I was getting on that Raid 5 I tested on the SIL3114
though that isn't surprising because no checksum data is being calculated.
I probably should have manually set the block size as it seems a little
inflated.
--
Mark Lane, CET mailto:mark@xxxxxxxxxxxx
Hard Data Ltd. http://www.harddata.com
T: 01-780-456-9771 F: 01-780-456-9772
11060 - 166 Avenue Edmonton, AB, Canada, T5X 1Y3
--> Ask me about our Excellent 1U Systems! <--
Version 1.03 ------Sequential Output------ --Sequential Input- --Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP
skip.harddata.n 20G 42648 88 53946 22 25138 7 29504 50 54544 6 75.4 0
------Sequential Create------ --------Random Create--------
-Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP
10 2417 99 +++++ +++ +++++ +++ 2482 92 +++++ +++ 9089 66
skip.harddata.net,20G,42648,88,53946,22,25138,7,29504,50,54544,6,75.4,0,10,2417,99,+++++,+++,+++++,+++,2482,92,+++++,+++,9089,66
