Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 12 Jan 2000 17:33:58 -0700
From:      "Kenneth D. Merry" <ken@kdm.org>
To:        Joerg Micheel <joerg@cs.waikato.ac.nz>
Cc:        sthaug@nethelp.no, grios@ddsecurity.com.br, ohoyer@fbwi.fh-wilhelmshaven.de, freebsd-hardware@freebsd.org
Subject:   Re: hardware
Message-ID:  <20000112173358.A93414@panzer.kdm.org>
In-Reply-To: <20000113132414.K5228@cs.waikato.ac.nz>; from joerg@cs.waikato.ac.nz on Thu, Jan 13, 2000 at 01:24:14PM %2B1300
References:  <387D0354.63159B8@ddsecurity.com.br> <72218.947717759@verdi.nethelp.no> <20000113124314.I5228@cs.waikato.ac.nz> <20000112165428.A93083@panzer.kdm.org> <20000113132414.K5228@cs.waikato.ac.nz>

next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Jan 13, 2000 at 13:24:14 +1300, Joerg Micheel wrote:
> On Wed, Jan 12, 2000 at 04:54:28PM -0700, Kenneth D. Merry wrote:
> > On Thu, Jan 13, 2000 at 12:43:14 +1300, Joerg Micheel wrote:
> > > FWIW, this is a 3.3-RELEASE system:
> > > 
> > > da0: <SEAGATE ST150176LW 0002> Fixed Direct Access SCSI-2 device 
> > > da0: 40.000MB/s transfers (20.000MHz, offset 8, 16bit), Tagged Queueing Enabled
> > > da0: 47702MB (97693755 512 byte sectors: 255H 63S/T 6081C)
> > > 
> > > 48 [negara] (root) benchmarks/rawio/work # rawio  /dev/rda0c
> > >            Random read  Sequential read    Random write Sequential write
> > > ID          K/sec  /sec    K/sec  /sec     K/sec  /sec     K/sec  /sec
> > > anon       3556.7   220   5227.6   319
> > > 
> > > I can't perform any write tests, this drive is in use.
> > 
> > 
> > That seems very low.  What happens with dd?  e.g.:
> > 
> > dd if=/dev/rda0c of=/dev/null bs=1m count=4096
> > 
> > At least for sequential reads, I would expect something in the
> > neighborhood of what Seagate claims, and their claim of 22.5MB/sec doesn't
> > seem out of line for a new drive with high media density like that one.
> 
> Hmm, still learning how to apply the tools properly ...
> 
> 50 [negara] (root) # dd if=/dev/rda0c of=/dev/null bs=1m count=4096
> 4096+0 records in
> 4096+0 records out
> 4294967296 bytes transferred in 178.795312 secs (24021700 bytes/sec)
> 
> 54 [negara] (root) # dd if=/dev/rda0c of=/dev/null bs=1m count=4096 skip=2047
> 4096+0 records in
> 4096+0 records out
> 4294967296 bytes transferred in 179.872815 secs (23877801 bytes/sec)

Those numbers are pretty close to what Seagate was claiming.

> dd refuses to skip more than 2GB, so I cannot continue here ... but:
> 
> 60 [negara] (root) # rawio -c 128 /dev/rda0c
>            Random read  Sequential read    Random write Sequential write
> ID          K/sec  /sec    K/sec  /sec     K/sec  /sec     K/sec  /sec
> anon       6790.6   103  14491.1   221
> 61 [negara] (root) # rawio -c 144 /dev/rda0c
>            Random read  Sequential read    Random write Sequential write
> ID          K/sec  /sec    K/sec  /sec     K/sec  /sec     K/sec  /sec
> anon       6777.9    92  13295.9   180
> 62 [negara] (root) # rawio -c 192 /dev/rda0c
>            Random read  Sequential read    Random write Sequential write
> ID          K/sec  /sec    K/sec  /sec     K/sec  /sec     K/sec  /sec
> anon       7163.9    73  14467.4   147
> 
> rawio -c 256 causes bad reads on the disk.

What do you mean it causes bad reads?  Are there any error message printed
out?

It may take careful tuning to get the same sorts of numbers out of rawio
that you got out of dd, above, if that is even possible.  (I haven't done
much with rawio.)

Ken
-- 
Kenneth Merry
ken@kdm.org


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hardware" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20000112173358.A93414>