Date: Wed, 11 Nov 1998 01:59:31 -0500 From: Drew Baxter <netmonger@genesis.ispace.com> To: Greg Lehey <grog@lemis.com>, john cooper <john@isi.co.jp>, hackers@FreeBSD.ORG, mike@smith.net.au, ticso@cicely.de Subject: Re: SCSI vs. DMA33.. Message-ID: <4.1.19981111015237.00ab3ee0@genesis.ispace.com> In-Reply-To: <19981111162000.O20374@freebie.lemis.com> References: <98Nov11.134648jst.21907@ns.isi.co.jp> <98Nov11.134648jst.21907@ns.isi.co.jp>
next in thread | previous in thread | raw e-mail | index | archive | help
At 04:20 PM 11/11/98 +1030, Greg Lehey wrote:
>On Wednesday, 11 November 1998 at 13:41:00 +0900, john cooper wrote:
>>
>> Hi,
>> Just wondering if anyone has any _objective_ opinion on
>> the performance of say wide SCSI2 vs. DMA33 IDE drives [running
>> on contemporary motherboards].
>
>Depends on what you mean by "objective".
>
>> The theoretical throughputs of 40MBs and 33MBs don't tell me a whole
>> lot. I know SCSI was the choice for performance in the past,
>> however I'm curious what others are seeing in actual usage these
>> days.
>
>SCSI is still the performance choice, but the field is closer now. I
>have five drives on my main machine:
>
>wd0: 1223MB (2504880 sectors), 2485 cyls, 16 heads, 63 S/T, 512 B/S
>wd2: 6197MB (12692736 sectors), 12592 cyls, 16 heads, 63 S/T, 512 B/S
>ide_pci: generic_dmainit 0170:1: warning, IDE controller timing not set
>wdc1: unit 1 (wd3): <IBM-DHEA-38451>, DMA, 32-bit, multi-block-16
>wd3: 8063MB (16514064 sectors), 16383 cyls, 16 heads, 63 S/T, 512 B/S
>ahc0: <Adaptec 2940 SCSI adapter> rev 0x03 int a irq 11 on pci0.9.0
>ahc0: aic7870 Single Channel A, SCSI Id=7, 16/255 SCBs
>da0 at ahc0 bus 0 target 0 lun 0
>da0: <IBM DORS-32160 WA0A> Fixed Direct Access SCSI2 device
>da0: 10.0MB/s transfers (10.0MHz, offset 15), Tagged Queueing Enabled
>da0: 2063MB (4226725 512 byte sectors: 64H 32S/T 2063C)
>da1 at ahc0 bus 0 target 2 lun 0
>da1: <CONNER CFP4207S 4.28GB 2847> Fixed Direct Access SCSI2 device
>da1: 3.300MB/s transfers, Tagged Queueing Enabled
>da1: 4096MB (8388608 512 byte sectors: 64H 32S/T 4096C)
>
>I'm running 3.0-CURRENT (post-RELEASE), and as you can see Ultra DMA
>is enabled on the IDE drives. Here's what I get transferring 32 MB
>from each raw device:
>
>$ dd if=/dev/rwd0c bs=32k count=1000 of=/dev/null
>32768000 bytes transferred in 6.938876 secs (4722379 bytes/sec)
>$ dd if=/dev/rwd2c bs=32k count=1000 of=/dev/null
>32768000 bytes transferred in 3.214075 secs (10195157 bytes/sec)
>$ dd if=/dev/rwd3c bs=32k count=1000 of=/dev/null
>32768000 bytes transferred in 3.278695 secs (9994220 bytes/sec)
>$ dd if=/dev/rda0c bs=32k count=1000 of=/dev/null
>32768000 bytes transferred in 5.734632 secs (5714055 bytes/sec)
>$ dd if=/dev/rsd1c bs=32k count=1000 of=/dev/null
>32768000 bytes transferred in 8.893227 secs (3684602 bytes/sec)
>
>Looks good for the IDE drives, doesn't it? They say, though, that
>SCSI drives work better with multiple requests outstanding...
>
>$ dd if=/dev/rsd0c bs=32k count=1000 of=/dev/null & dd if=/dev/rsd1c bs=32k
>count=1000 of=/dev/null
>[3] 20705
>32768000 bytes transferred in 9.940641 secs (3296367 bytes/sec)
>32768000 bytes transferred in 12.121225 secs (2703357 bytes/sec)
>$ dd if=/dev/rsd0c bs=32k count=1000 of=/dev/null & dd if=/dev/rsd1c bs=32k
>count=1000 of=/dev/null
>32768000 bytes transferred in 9.940080 secs (3296553 bytes/sec)
>32768000 bytes transferred in 12.080951 secs (2712369 bytes/sec)
>
>Well, that doesn't look spectacular. What about the IDE drives (both
>on the same controller, wdc1):
>
>$ dd if=/dev/rwd2c bs=32k count=1000 of=/dev/null & dd if=/dev/rwd3c bs=32k
>count=1000 of=/dev/null
>32768000 bytes transferred in 3.710713 secs (8830648 bytes/sec)
>32768000 bytes transferred in 3.711320 secs (8829204 bytes/sec)
>$ dd if=/dev/rwd2c bs=32k count=1000 of=/dev/null & dd if=/dev/rwd3c bs=32k
>count=1000 of=/dev/null
>32768000 bytes transferred in 3.737548 secs (8767245 bytes/sec)
>32768000 bytes transferred in 3.729290 secs (8786659 bytes/sec)
>
>I must say, I'm surprised. This makes it look like there's more of a
>performance hit with concurrent requests on SCSI than on IDE. Let's
>look at the performance hits as a percentage (there's some guesswork
>which is which, of course, but only a little):
>
> alone 2 together % drop
>wd2 10.2 8.8 14
>wd3 10.0 8.8 12
>da0 5.7 3.3 42
>da1 3.7 2.7 23
>
>OK, the controller I have isn't the newest, but there's not exactly a
>lot of data crossing: even with the two disks transferring by
>themselves, they're transferring less data than a single DHEA drive.
>Can anybody else think of a reason for this? I have a 2940 Ultra
>("ahc0: <Adaptec 2940 Ultra SCSI adapter> rev 0x00 int a irq 14 on
>pci0.17.0") in another machine. The disks aren't Ultra SCSI; is there
>any reason to think it will perform better?
>
>Greg
I have the 2940U card, I found the integrated AIC-7895 on my mainboard
(Dual UltraSCSI Wide) performed better for throughput. Since my
applications don't require much better than the UDMA drives anyway, I can't
say I'm taking advantage of it. Then again, I'm not taking advantage of
the 2 processors on the board (Windows 95's lack of SMP support).
Eventually I'll probably throw a dual-boot in for FreeBSD, but I have a
workhorse PII for that already.
I find minimum grind when doing network applications across the house on
either. My Fujitsu SCSI 4.3gig gets used mostly for the bootup and OS
operation, the UDMA drives are used for public file sharing and caching and
things like that.
The UDMA 7.0gig replaced a regular EIDE Maxtor 3.5 gig. I will say that
this is HANDS DOWN a faster drive. the 3.5 gig would not succeed in above
a 2X CD-R write (for caching according to CEQuadrat's SpeedOMeter) and
that's with an empty partition. The 7.0gig can be half full with thousands
of files, and it scores to be reliable up to and past 8x CD-R speeds. I'd
say all in all, UDMA33 is significantly better than the older EIDE drives.
Whether it is better than SCSI or not is yet to be seen. But my Fujitsu
was probably a good 400+ dollars, and my 7.0gig Maxtor was 197 (and then 30
bucks off rebate). I can't argue with a price like that, the speed is an
added bonus. My FreeBSD box uses an older BIOSTAR 8500TUD that doesn't
contain a UDMA chip. It performs incredibly well with a 2.7gig Maxtor
(EIDE) and a 1.6gig Samsung (EIDE). The thing is running 17 Vservs on a
PII-333, and experiences a peak load of probably .16, and that's rare.
It all depends on how you use it I guess. I do Photoshop on the WIN95
machine, and also video editing. Runs flawless using either the 2nd
partition of the 4.3, or any of the UDMA partitions..
---
Drew "Droobie" Baxter
Network Admin/Professional Computer Nerd(TM)
OneEX: The OneNetwork Exchange 207-942-0275
http://www.droo.orland.me.us
My Latest Kernel: FreeBSD 3.0-CURRENT (ONEEX) #14: Mon Oct 19 22:36:58 EDT 1998
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4.1.19981111015237.00ab3ee0>