From vger.rutgers.edu!owner-linux-raid-outgoing Mon Sep 13 21:49:11 1999 Return-Path: Received: from listserv.funet.fi(really [128.214.248.27]) by planet via smail with esmtp id for ; Mon, 13 Sep 1999 21:49:11 -0700 (PDT) (Smail-3.2.0.90 1996-Dec-4 #9 built 1996-Dec-8) Received: from vger.rutgers.edu ([128.6.190.2]:54325 "EHLO vger.rutgers.edu") by listserv.funet.fi with ESMTP id ; Tue, 14 Sep 1999 07:33:41 +0300 Received: by vger.rutgers.edu via listexpand id ; Tue, 14 Sep 1999 00:32:55 -0400 Received: by vger.rutgers.edu id ; Tue, 14 Sep 1999 00:32:39 -0400 Received: from proxy3.ba.best.com ([206.184.139.14]:2654 "EHLO proxy3.ba.best.com") by vger.rutgers.edu with ESMTP id ; Tue, 14 Sep 1999 00:32:32 -0400 Received: from bigfoot.com (IDENT:tim@dynamic23.pm08.mv.best.com [209.24.241.215]) by proxy3.ba.best.com (8.9.3/8.9.2/best.out) with ESMTP id VAA18970 for ; Mon, 13 Sep 1999 21:31:25 -0700 (PDT) Message-ID: <37DDD0BD.61E655E1@bigfoot.com> Date: Mon, 13 Sep 1999 21:36:13 -0700 From: Tim Moore Organization: Yoyodyne Propulsion Systems, Inc. X-Mailer: Mozilla 4.61 [en] (X11; U; Linux 2.0.38 i686) X-Accept-Language: en MIME-Version: 1.0 To: raid Subject: Re: IDE RAID0 hdparm benchmarks References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-linux-raid@vger.rutgers.edu Precedence: bulk X-Loop: majordomo@vger.rutgers.edu X-Orcpt: rfc822;linux-raid-outgoing Status: RO Coffee or no the addiction never goes away. 2 drives, ~2X. All timings are typical. /dev/md0: buffer-cache reads: 128 MB in 1.00 seconds =128.00 MB/sec buffered disk reads: 64 MB in 3.37 seconds =18.99 MB/sec and /dev/md0: buffer-cache reads: 64 MB in 0.66 seconds =96.97 MB/sec buffered disk reads: 32 MB in 1.71 seconds =18.71 MB/sec and /dev/hde3: buffer-cache reads: 128 MB in 1.01 seconds =126.73 MB/sec buffered disk reads: 64 MB in 6.69 seconds = 9.57 MB/sec /dev/hdg3: buffer-cache reads: 128 MB in 0.98 seconds =130.61 MB/sec buffered disk reads: 64 MB in 6.69 seconds = 9.57 MB/sec dd test: 33 MB in use, file size = memory size # time dd if=/dev/zero of=/raid/test bs=1k count=256k && \ ? time dd if=/raid/test of=/dev/null bs=1k && \ ? time rm -fv /raid/test && \ ? time sync 262144+0 records in 262144+0 records out 0.260u 7.680s 0:16.10 49.3% 0+0k 0+0io 95pf+0w 262144+0 records in 262144+0 records out 0.230u 5.840s 0:26.17 23.1% 0+0k 0+0io 65696pf+0w /raid/test 0.000u 0.140s 0:06.78 2.0% 0+0k 0+0io 111pf+0w 0.000u 0.010s 0:00.35 2.8% 0+0k 0+0io 85pf+0w [tim@asus tim]# echo 262144/16.10 | bc -q 16282 [tim@asus tim]# echo 262144/26.17 | bc -q 10016 machine: ASUS P3B-F, 256 MB, Celeron 300A (2.2v core, 472 MHz), PCI @35 MHz (6%). software: RH 5.2 base + 2.0.38 kernel, raidtools-0.50beta10-2. raid: read_ahead 8 sectors md0 : active raid0 hde3 hdg3 5221120 blocks 16k chunks /dev/md0: 1k block size w 1% reserve drives & controller: hde: IBM-DHEA-36481, 6197MB w/472kB Cache, CHS=12592/16/63, UDMA hdg: IBM-DHEA-36481, 6197MB w/472kB Cache, CHS=12592/16/63, UDMA Disk /dev/hde: 255 heads, 63 sectors, 790 cylinders Units = cylinders of 16065 * 512 bytes /dev/hde3 63 387 2610562+ 83 Linux native /dev/hdg3 63 387 2610562+ 83 Linux native ide: PDC20246 UDMA Bus Mastering Controller on PCI bus 0 function 80 ide: timings == 000003ee ide2: BM-DMA at 0xa400-0xa407 ide3: BM-DMA at 0xa408-0xa40f ide2 at 0xb800-0xb807,0xb406 on irq 3 ide3 at 0xb000-0xb007,0xa806 on irq 3 (shared with ide2) --