[Format recovered--see http://www.lemis.com/email/email-format.html]
On Saturday, 21 August 1999 at 11:46:18 -0600, Chad David wrote:
> I just setup vinum for the first time on a brand new server,
> nd I am getting what I think are strange results in performance
> tests with rawio. My SCSI drives seem to be much slower that my
> IDE drives?
>
> wdc0 at 0x1f0-0x1f7 irq 14 flags 0xb0ffb0ff on isa
> wdc0: unit 0 (wd0): <IBM-DTTA-371440>, LBA, DMA, 32-bit, multi-block-16
> wd0: 13783MB (28229040 sectors), 1757 cyls, 255 heads, 63 S/T, 512 B/S
> wdc0: unit 1 (wd1): <IBM-DTTA-371440>, LBA, DMA, 32-bit, multi-block-16
> wd1: 13783MB (28229040 sectors), 1757 cyls, 255 heads, 63 S/T, 512 B/S
> wdc1 at 0x170-0x177 irq 15 flags 0xb0ffb0ff on isa
> wdc1: unit 0 (wd2): <IBM-DTTA-371440>, LBA, DMA, 32-bit, multi-block-16
> wd2: 13783MB (28229040 sectors), 1757 cyls, 255 heads, 63 S/T, 512 B/S
> wdc1: unit 1 (wd3): <IBM-DTTA-371440>, LBA, DMA, 32-bit, multi-block-16
> wd3: 13783MB (28229040 sectors), 1757 cyls, 255 heads, 63 S/T, 512 B/S
> da0 at ahc0 bus 0 target 3 lun 0
> da0: <IBM DNES-318350W SA30> Fixed Direct Access SCSI-3 device
> da0: 40.000MB/s transfers (20.000MHz, offset 8, 16bit), Tagged Queueing Enabled
> da0: 17501MB (35843670 512 byte sectors: 255H 63S/T 2231C)
> da1 at ahc0 bus 0 target 6 lun 0
> da1: <IBM DNES-318350W SA30> Fixed Direct Access SCSI-3 device
> da1: 40.000MB/s transfers (20.000MHz, offset 8, 16bit), Tagged Queueing Enabled
> da1: 17501MB (35843670 512 byte sectors: 255H 63S/T 2231C)
>
> ##########################################################################
>
> As you can see there are four 14.4 Gig IBM IDE drives, and 2
> 18Gig IBM SCSI drives.
>
> My vinum config is:
>
> drive scsi1 device /dev/da0e
> drive scsi2 device /dev/da1e
> drive ide1 device /dev/wd2e
> drive ide2 device /dev/wd3e
You'd get better performance spreading your volume across two IDE
controllers. Since you have a wd1 as well, you might consider
swapping wd1 and wd3.
> volume exporthome
> plex org concat
> sd length 0 drive scsi1
> sd length 0 drive scsi2
>
> volume backup
> plex org concat
> sd length 0 drive ide1
> sd length 0 drive ide2
>
> SCSI
> # rawio -a -v 1 /dev/vinum/rexporthome
> Test ID K/sec /sec %User %Sys %Total
> RR anon 1774.1 110 0.1 0.7 0.7 16384
> SR anon 14482.7 884 0.1 5.3 5.4 16384
> RW anon 1573.7 98 0.1 0.6 0.6 16384
> SW anon 1981.8 121 0.0 0.7 0.8 16384
>
> /dev/rda0 is one of the raw drives in exporthome..
> # rawio -a -v 1 /dev/rda0
> Test ID K/sec /sec %User %Sys %Total
> RR anon 2241.3 138 0.1 0.5 0.6 16384
> SR anon 19115.9 1167 0.1 4.5 4.5 16384
> RW anon 959.1 60 0.0 0.2 0.3 16384
> SW anon 2608.7 159 0.0 0.6 0.6 16384
>
>
> IDE
> # rawio -a -v 1 /dev/vinum/rbackup
> Test ID K/sec /sec %User %Sys %Total
> RR anon 1372.9 86 0.0 0.4 0.4 16384
> SR anon 28443.2 1736 0.4 7.5 7.8 16384
> RW anon 601.3 37 0.0 0.2 0.2 16384
> SW anon 12227.7 746 0.3 3.1 3.4 16384
>
> /dev/rwd1 is just a stand alone IDE drive.
> # rawio -a -v 1 /dev/rwd1
> Test ID K/sec /sec %User %Sys %Total
> RR anon 1610.0 100 0.0 0.2 0.3 16384
> SR anon 28828.8 1760 0.4 3.3 3.7 16384
> RW anon 1218.5 76 0.1 0.2 0.2 16384
> SW anon 11628.1 710 0.0 1.5 1.5 16384
>
> I could be wrong but shouldn't the SCSI system blow away the IDE system?
Not necessarily. This is a common fallacy. But the performance
figures you're getting there don't look very good. I wonder if the
SCSI drives have some problem. On the other hand, the serial
throughput on wd1 looks surprisingly high.
> On a side note, can you enable softupdates on a vinum fs?
Yes. Vinum is just a virtual disk.
Greg
--
See complete headers for address, home page and phone numbers
finger [EMAIL PROTECTED] for PGP public key
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
