Date: Wed, 4 Dec 1996 15:47:24 +1100 From: Bruce Evans <bde@zeta.org.au> To: nick@grayphics.com, roberto@keltia.freenix.fr Cc: freebsd-scsi@freebsd.org Subject: Re: 2940UW Adaptec SCSI Controler Message-ID: <199612040447.PAA27047@godzilla.zeta.org.au>
next in thread | raw e-mail | index | archive | help
>This is on a slightly fragmented partition. Keep in mind that these are
>older 4500rpm drives. I don't know the RPMs of the drives you are using,
>but they are likely to be 7200. I use one of these mechanisms in our
>Indy and it runs no faster, so I suspect this is roughly at the
>sustainable transfer rate of the mechanism. They are 2.9GB Seagate
>Elites, I don't remember the model number offhand though.
>
>On Tue, 3 Dec 1996, Ollivier Robert wrote:
>
>> How full/fragmented is the partition you ran iozone on ?
>>
>> I was getting more than 4.5 MB/s r/w on a Conner CFP1080S and got 5.5 MB/s
>> r/w out of my new (2 months) IBM DORS Ultrastar/ES 32160, both narrow.
>> Using an EISA Buslogic BT-747S under 2.2-CURRENT.
Any new drive on a Pentium PCI system should get > 5MB/sec on its inner
tracks. The DORS is not a high end drive. Relevant specs:
Rpm Media transfer rate (Mbps) Seek Time (Typical Read)
5400 47.4(inner) 71.6(outer) 3/8.5/15 ms track-to-track/avg/full
It is only a few percent faster than a new Quantum Fireball TM211A EIDE
drive. The Fireball TM is not a high end drive. Specs:
4500 36.0(inner) 55.2(outer) 3/10.5/22 ms
For the EIDE drive configured with 16 sectors/interrupt, 32-bit i/o and PIO
mode 4, on a P5/133 on an ASUS P55TP4XE (Triton 1) motherboard with the
onboard EIDE controller, on the same empty partion at offset 320MB and size
1024MB:
bonnie.ext2fs-under-freebsd-current (fs block size 4K)
-----------------------------------
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
see above 512 3786 71.8 5220 18.7 1556 9.1 3904 70.7 5204 14.5 47.6 2.8
bonnie.ext2fs-under-linux-2.0.20 (fs block size 4K)
--------------------------------
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
same 512 3836 96.2 4517 25.0 2500 35.0 3488 91.2 5156 19.8 44.8 2.0
bonnie.ufs-under-freebsd-current (fs block/frag size 8K/1K)
--------------------------------
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
same 512 3543 70.9 4627 19.1 1459 8.1 3891 70.5 4875 13.4 45.0 2.6
The SCSI drive gets about the same speed through the file system on the
inner tracks but is slightly faster on the middle tracks and at seeking.
Bruce
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199612040447.PAA27047>