Date: Fri, 1 Nov 1996 03:12:23 -0800 (PST) From: "Jonathan M. Bresler" <jmb> To: dkelly@hiwaay.net (David Kelly) Cc: jgrosch@superior.truenorth.org, current@FreeBSD.org, roberto@keltia.freenix.fr, jlemon@americantv.com, jgrosch@sirius.com, michaelv@MindBender.serv.net Subject: Re: SCSI and IDE (was Re: 2.1.5r -> current upgrade) Message-ID: <199611011112.DAA18626@freefall.freebsd.org> In-Reply-To: <XFMail.961101013230.dkelly@hiwaay.net> from "David Kelly" at Nov 1, 96 01:12:00 am
next in thread | previous in thread | raw e-mail | index | archive | help
David Kelly wrote:
>
> 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:
>
> (ahc0:0:0): "SEAGATE ST3610N 9290" type 0 fixed SCSI 2
> sd0(ahc0:0:0): Direct-Access 510MB (1046206 512 byte sectors)
>
> The IDE is an old mode 0 drive on the MB EIDE controller:
>
> wdc0: unit 0 (wd0): <Conner Peripherals 510MB - CP3541>
> wd0: 486MB (996912 sectors), 989 cyls, 16 heads, 63 S/T, 512 B/S
>
> The system has 32M of memory, its supposed to have 512k of cache
> but the BIOS only reports 256k (I suspect "WRITE BACK CACHE" on
> the MB is fake so I added a 256k cache to the cache socket).
>
> On the IDE drive:
> PeeCee: {872} time iozone 32
> [snip]
> IOZONE performance measurements:
> 1188424 bytes/second for writing the file
> 2111586 bytes/second for reading the file
> 0.2u 10.8s 0:44.54 24.7% 69+750k 374+542io 0pf+0w
>
> Now on to the SCSI drive:
> PeeCee: {873} cd /usr1
> PeeCee: {874} time iozone 32
> [snip]
> IOZONE performance measurements:
> 3455323 bytes/second for writing the file
> 4149726 bytes/second for reading the file
> 0.2u 10.9s 0:18.17 61.5% 26+281k 363+533io 0pf+0w
> ^^^^ this is the interesting part.
it is interesting that the system time is the same.
how full are the disks?
IOzone is sensitive to how full the disk is.
Filesystem 1K-blocks Used Avail Capacity Mounted on
/dev/sd1a 38991 24083 11789 67% /
/dev/sd1e 297423 243942 29688 89% /usr
/dev/sd1f 656010 541051 62479 90% /home
/dev/sd2f 424591 95490 295134 24% /usr/obj
/dev/sd2g 230345 177118 34800 84% /usr/src
procfs 4 4 0 100% /proc
Aspen:[2] cd /home/jmb/tmp
Aspen:[3] time /home/jmb/BenchMarks/iozone-2.01/iozone 32
[snip]
IOZONE performance measurements:
1539966 bytes/second for writing the file
1915685 bytes/second for reading the file
0.5u 16.8s 0:40.24 43.1% 25+287k 1060+1049io 6pf+0w
Aspen:[4] cd /usr/src
Aspen:[5] time /home/jmb/BenchMarks/iozone-2.01/iozone 32
IOZONE performance measurements:
1678377 bytes/second for writing the file
2340581 bytes/second for reading the file
0.6u 16.2s 0:34.93 48.4% 25+285k 670+676io 0pf+0w
Aspen:[6] cd /usr/obj
Aspen:[7] time /home/jmb/BenchMarks/iozone-2.01/iozone 32
IOZONE performance measurements:
2499980 bytes/second for writing the file
4177983 bytes/second for reading the file
0.5u 18.1s 0:22.19 84.3% 26+286k 534+540io 0pf+0w
2 iozone's running on the same filesystems at the same time:
Aspen:[8] time /home/jmb/BenchMarks/iozone-2.01/iozone 32 &; \
( cd foo; time /home/jmb/BenchMarks/iozone-2.01/iozone 32 &) &
IOZONE performance measurements:
1184165 bytes/second for writing the file
1701651 bytes/second for reading the file
0.5u 17.5s 0:50.20 36.0% 26+290k 514+570io 0pf+0w
IOZONE performance measurements:
1120523 bytes/second for writing the file
1727661 bytes/second for reading the file
0.4u 17.4s 0:49.32 36.3% 25+283k 514+551io 1pf+0w
aggregate thruput is somewhat less, system time for each iozone run is
less (more done per interrupt), clock time is somewhat more than double
a single iozone
backgrounding may actually speed up disk transfers !! :)
look ath the clock time below...hmmm..
Aspen:[9] time /home/jmb/BenchMarks/iozone-2.01/iozone 32 &
IOZONE performance measurements:
2476913 bytes/second for writing the file
4387096 bytes/second for reading the file
0.5u 17.7s 0:21.85 83.5% 26+288k 479+535io 0pf+0w
machine is a 486dx2-66, asus sp3g, pci sc-200 (ncr53c810), 16mb,
256 kb write-back, disks are "FUJITSU M1606S-512 6234" type 0 fixed SCSI 2
jmb
--
Jonathan M. Bresler FreeBSD Postmaster jmb@FreeBSD.ORG
FreeBSD--4.4BSD Unix for PC clones, source included. http://www.freebsd.org/
PGP 2.6.2 Fingerprint: 31 57 41 56 06 C1 40 13 C5 1C E3 E5 DC 62 0E FB
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199611011112.DAA18626>