From owner-freebsd-questions Tue Dec 21 12:13:11 1999 Delivered-To: freebsd-questions@freebsd.org Received: from mail.rdc3.on.home.com (ha1.rdc3.on.home.com [24.2.9.68]) by hub.freebsd.org (Postfix) with ESMTP id A32D71500B for ; Tue, 21 Dec 1999 12:13:08 -0800 (PST) (envelope-from a.genkin@utoronto.ca) Received: from main.wgaf.net ([24.114.152.71]) by mail.rdc3.on.home.com (InterMail v4.01.01.02 201-229-111-106) with ESMTP id <19991221201100.POWI7552.mail.rdc3.on.home.com@main.wgaf.net> for ; Tue, 21 Dec 1999 12:11:00 -0800 Received: from antipode by main.wgaf.net with local (Exim 2.05 #1 (Debian)) id 120Ved-0000HK-00; Tue, 21 Dec 1999 15:13:07 -0500 To: freebsd-questions@freebsd.org Subject: One drive much slower than another X-Face: 0=A/O5-+sE[Tf%X>rYr?Y5LD4,:^'jaJ!4jC&UR*ZrrK2>^`g22Qeb]!:d;}2YJ|Hq"LHdF OX`jWX|AT-WVFQ(TPhFVak)0nt$aEdlOq=1~D,:\z5QlVOrZ2(H,mKg=Xr|'VlHA="r Organization: Wgaf From: Arcady Genkin Date: 21 Dec 1999 15:13:07 -0500 Message-ID: <87vh5s59yk.fsf@main.wgaf.net> Lines: 66 User-Agent: Gnus/5.0802 (Gnus v5.8.2) XEmacs/21.1 (Bryce Canyon) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG I run 3.4-R on a P166 box with 2 HDs: WD Caviar 22100 2.1G Rpm: 5400 Average Seek Time: sub 12 ms Quantum Bigfoot 19G Rpm: 4000 Average Seek Time: 10.5 ms I use the WD as a system drive, and the Quantum for data. Now it turns out that the 4000rpm Quantum works *much* faster than 5400rpm WD... I have softupdates enabled on both drives' partitions where I ran my tests. ,----- Here's relevant info from "dmesg": | wdc0 at 0x1f0-0x1f7 irq 14 flags 0xb0ffb0ff on isa | wdc0: unit 0 (wd0): , LBA, DMA, 32-bit, multi-block-16 | wd0: 2014MB (4124736 sectors), 1023 cyls, 64 heads, 63 S/T, 512 B/S | wdc1 at 0x170-0x177 irq 15 flags 0xb0ffb0ff on isa | wdc1: unit 0 (wd2): , LBA, DMA, 32-bit, multi-block-16 | wd2: 18366MB (37615536 sectors), 2341 cyls, 255 heads, 63 S/T, 512 B/S `----- ,----- Output from "mount": | door:~$ /sbin/mount | /dev/wd0s1a on / (ufs, local, writes: sync 15 async 48) | /dev/wd0s1f on /usr (ufs, local, soft-updates, writes: sync 2 async 31) | /dev/wd0s1e on /var (ufs, local, writes: sync 106 async 252) | /dev/wd2s1e on /mnt/data1 (ufs, local, soft-updates, writes: sync 2 async 0) | /dev/wd2s1f on /mnt/data2 (ufs, local, soft-updates, writes: sync 2 async 0) | /dev/wd2s1g on /mnt/data3 (ufs, local, soft-updates, writes: sync 2 async 0) | procfs on /proc (procfs, local) `----- As you can see, the two drives are on two separate controllers, and both controllers have exactly same flags. When I ran tests, outlined by Dale Hagglund, I found out that the Quantum writes at 10MB/s, whereas the WD -- only at 3MB/s. I did my tests in partitions, where softupdates are enabled: time dd if=/dev/zero of=100m bs=1m count=100 ,----- Test on Quantum: | door:/mnt/data3$ time dd if=/dev/zero of=100m bs=1m count=100 | 100+0 records in | 100+0 records out | 104857600 bytes transferred in 10.362510 secs (10118938 bytes/sec) | | real 0m10.529s | user 0m0.016s | sys 0m6.320s `----- ,----- Test on WD: | door:/usr/tmp$ time dd if=/dev/zero of=100m bs=1m count=100 | 100+0 records in | 100+0 records out | 104857600 bytes transferred in 28.097030 secs (3731982 bytes/sec) | | real 0m29.046s | user 0m0.001s | sys 0m5.391s `----- Has anyone got any ideas how I can improve performance of the WD? Thanks for any input! -- Arcady Genkin http://wgaf.dyndns.org "'What good is my pity? Is not the pity the cross upon which he who loves man is nailed?..'" (Zarathustra - F. Nietzsche) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message