Date: Fri, 01 Nov 1996 09:10:21 -0800 From: "Michael L. VanLoon -- HeadCandy.com" <michaelv@MindBender.serv.net> To: David Kelly <dkelly@hiwaay.net> Cc: Josef Grosch <jgrosch@superior.truenorth.org.headcandy.com>, current@freebsd.org, roberto@keltia.freenix.fr, jlemon@americantv.com, jgrosch@sirius.com Subject: Re: SCSI and IDE (was Re: 2.1.5r -> current upgrade) Message-ID: <199611011710.JAA12840@MindBender.serv.net> In-Reply-To: Your message of Fri, 01 Nov 96 01:12:00 -0600. <XFMail.961101013230.dkelly@hiwaay.net>
next in thread | previous in thread | raw e-mail | index | archive | help
>Speaking of SCSI, I was playing today with IDE and SCSI on my new
>AMD 586/133 PCI MB. The SCSI is on a 2940, bios rev 1.10 or so:
[...]
>On the IDE drive:
>PeeCee: {872} time iozone 32
>0.2u 10.8s 0:44.54 24.7% 69+750k 374+542io 0pf+0w
[...]
>Now on to the SCSI drive:
>0.2u 10.9s 0:18.17 61.5% 26+281k 363+533io 0pf+0w
[...]
>Notice how both took the same amount of system time?
>(nit pickers: SCSI took 0.1 second longer.)
>I'm disappointed. A bit.
[...]
>BTW, tried a 1542CF first thing after upgrading to the SNAP
>and upgrading the MB from a 486DX33 that wouldn't host a bus
>master card. Iozone reported thruput about the same as the IDE.
>Didn't think to do the "time" part. And I don't think I'm
>interested enough to take it apart and put the 1542CF back in.
You wouldn't want to. The 1542 is *significantly* slower than the
2940. It's possible your old Seagate drive, coupled with a 486 CPU,
isn't fast enough to show this, though.
Now, SCSI vs. IDE. It's quite possible that an IDE drive could be
faster in raw throughput than a SCSI drive. The drives themselves are
the same. Just sequentially writing, then sequentially reading a
large file, isn't going to show you anything that the SCSI interface
does better.
The problem is, the IDE drive dominates the CPU while it's working.
Meaning, your CPU can't be doing anything else while it's transfering
data to/from the IDE drive. Not so with the SCSI. Running your tests
on a totally idle system won't show this difference.
If you really want to see the difference, try running multiple bonnies
at the same time. Especially try this where you have multiple IDE and
SCSI drives. Try running a bonnie for each IDE drive simultaneously
(or to a ccd of multiple IDE drives). Then do the exact same test to
multiple SCSI drives.
Or, start a couple of kernel compiles in other windows, then do a
bonnie test, timing both the bonnie, and the kernel builds. I think
you will find, all of a sudden, the system is much less congested, and
is better able to keep all the various tasks busier. I suggest bonnie
instead of iozone, because it does a better assortment of tests.
-----------------------------------------------------------------------------
Michael L. VanLoon michaelv@MindBender.serv.net
--< Free your mind and your machine -- NetBSD free un*x >--
NetBSD working ports: 386+PC, Mac 68k, Amiga, Atari 68k, HP300, Sun3,
Sun4/4c/4m, DEC MIPS, DEC Alpha, PC532, VAX, MVME68k, arm32...
NetBSD ports in progress: PICA, others...
-----------------------------------------------------------------------------
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199611011710.JAA12840>