From owner-freebsd-questions Thu May 10 14:12:31 2001 Delivered-To: freebsd-questions@freebsd.org Received: from gandalf.vi.bravenet.com (gandalf.bravenet.com [139.142.105.50]) by hub.freebsd.org (Postfix) with SMTP id 4A64437B422 for ; Thu, 10 May 2001 14:12:27 -0700 (PDT) (envelope-from dphoenix@bravenet.com) Received: (qmail 23705 invoked by uid 1000); 10 May 2001 21:12:26 -0000 Received: from localhost (sendmail-bs@127.0.0.1) by localhost with SMTP; 10 May 2001 21:12:26 -0000 Date: Thu, 10 May 2001 14:12:26 -0700 (PDT) From: Dan Phoenix To: Greg Lehey Cc: Scott Mace , FreeBSD Questions Subject: Re: vinum on 2 ide drives? In-Reply-To: <20010510133425.K56501@wantadilla.lemis.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG [root@gorbag dphoenix]# rawio -a /dev/vinum/stripe Random read Sequential read Random write Sequential write ID K/sec /sec K/sec /sec K/sec /sec K/sec /sec stripe 2435.2 151 18504.8 1129 1920.9 119 2143.6 131 [root@gorbag dphoenix]# [root@gorbag dphoenix]#kldunload vinum.ko [root@gorbag dphoenix]# rawio -a /dev/ad1s1e Random read Sequential read Random write Sequential write ID K/sec /sec K/sec /sec K/sec /sec K/sec /sec ad1s1e 1543.4 95 1825.9 111 1294.0 80 1193.7 73 [root@gorbag dphoenix]# Here are your results as requested. Btw just noticed the -v 1 option from the man page...when i tested it quicky there really is not a Time field like man page suggests...just thought I'd let ya know. On Thu, 10 May 2001, Greg Lehey wrote: > Date: Thu, 10 May 2001 13:34:25 +0930 > From: Greg Lehey > To: Scott Mace > Cc: Dan Phoenix , > FreeBSD Questions > Subject: Re: vinum on 2 ide drives? > > On Wednesday, 9 May 2001 at 22:46:43 -0500, Scott Mace wrote: > > I'm seeing the same behaviour with a pair of IBM drives. I even made sure > > that > > write cache was enabled... I'm using 307030's > > > > This is on a regular non-vinum partition > > > > onix2# iozone 128 8192 > > > > IOZONE: Performance Test of Sequential File I/O -- V2.01 (10/21/94) > > > > IOZONE writes a 128 Megabyte sequential file consisting of > > 16384 records which are each 8192 bytes in length. > > It then reads the file. It prints the bytes-per-second > > rate at which the computer can read and write files. > > This is not really relevant to real-life access. But it might explain > Dan's issues: sequential access to a stripe will be slower than to a > concat plex such as you're using. > > > IOZONE performance measurements: > > 21746669 bytes/second for writing the file > > 29671622 bytes/second for reading the file > > > > This is on a vinum mirror. > > > > IOZONE performance measurements: > > 10784600 bytes/second for writing the file > > 24437936 bytes/second for reading the file > > It's difficult to guess what's going on here. Looking at your > configuration below, I'd guess that you're not comparing things > directly. > > > drive vinumdrive0 device /dev/ad0s1e > > drive vinumdrive2 device /dev/ad0s1f > > drive vinumdrive4 device /dev/ad0s1g > > drive vinumdrive1 device /dev/ad1s1e > > drive vinumdrive3 device /dev/ad1s1f > > drive vinumdrive5 device /dev/ad1s1g > > These are four drives too many. You don't want more than one drive > per spindle. > > Greg > -- > Finger grog@lemis.com for PGP public key > See complete headers for address and phone numbers > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message