From owner-freebsd-hackers Sat Feb 11 00:17:26 1995 Return-Path: hackers-owner Received: (from root@localhost) by freefall.cdrom.com (8.6.9/8.6.6) id AAA02089 for hackers-outgoing; Sat, 11 Feb 1995 00:17:26 -0800 Received: from wcarchive.cdrom.com (wcarchive.cdrom.com [192.216.191.11]) by freefall.cdrom.com (8.6.9/8.6.6) with ESMTP id AAA02082 for ; Sat, 11 Feb 1995 00:17:25 -0800 Received: from netcom14.netcom.com (root@netcom14.netcom.com [192.100.81.126]) by wcarchive.cdrom.com (8.6.8/8.6.6) with ESMTP id AAA21890 for ; Sat, 11 Feb 1995 00:17:13 -0800 Received: by netcom14.netcom.com (8.6.9/Netcom) id AAA23129; Sat, 11 Feb 1995 00:11:54 -0800 Date: Sat, 11 Feb 1995 00:11:54 -0800 From: hasty@netcom.com (Amancio Hasty Jr) Message-Id: <199502110811.AAA23129@netcom14.netcom.com> To: hasty@netcom.com, julian@tfs.com Subject: Re: My iozone results Cc: FreeBSD-hackers@wcarchive.cdrom.com Sender: hackers-owner@FreeBSD.org Precedence: bulk Well, here is quick and simple disklabel: bettina# disklabel -r sd1 # /dev/rsd1c: type: SCSI disk: label: MBR based label flags: bytes/sector: 512 sectors/track: 4096 tracks/cylinder: 1 sectors/cylinder: 4096 cylinders: 1013 rpm: 5400 interleave: 1 trackskew: 0 cylinderskew: 0 headswitch: 0 # milliseconds track-to-track seek: 0 # milliseconds drivedata: 0 8 partitions: # size offset fstype [fsize bsize bps/cpg] a: 122880 0 4.2BSD 1024 8192 16 # (Cyl. 0 - 29) b: 81920 122880 swap # (Cyl. 30 - 49) c: 4108600 0 4.2BSD 1024 8192 16 # (Cyl. 0 - 1003*) d: 4108600 0 unused 0 0 # (Cyl. 0 - 1003*) e: 122880 204800 4.2BSD 1024 8192 16 # (Cyl. 50 - 79) f: 3780608 327680 4.2BSD 1024 8192 16 # (Cyl. 80 - 1002) The iozone results are for partition "a": IOZONE: auto-test mode MB reclen bytes/sec written bytes/sec read 1 512 2064888 3728270 1 1024 3355443 4473924 1 2048 3834792 4473924 1 4096 3947580 4793490 1 8192 4067203 4628197 2 512 2711469 3728270 2 1024 3627506 4628197 2 2048 4260880 4793490 2 4096 4473924 4793490 2 8192 4473924 4880644 4 512 2840586 3754342 4 1024 3754342 4836674 4 2048 4511520 5017485 4 4096 4793490 5017485 4 8192 4836674 5064819 8 512 2848121 2878664 8 1024 3848537 4925421 8 2048 4648233 5088823 8 4096 4948119 5113056 8 8192 5017485 5113056 16 512 2844349 3940336 16 1024 3747789 4982560 16 2048 4628197 5149840 16 4096 5064819 5149840 16 8192 5088823 5149840 Completed series of tests Now if I can only get double of that performance... Amancio