From owner-freebsd-current Thu Nov 9 11:00:09 1995 Return-Path: owner-current Received: (from root@localhost) by freefall.freebsd.org (8.6.12/8.6.6) id LAA01356 for current-outgoing; Thu, 9 Nov 1995 11:00:09 -0800 Received: from devnull.mpd.tandem.com ([131.124.4.29]) by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id LAA01341 for ; Thu, 9 Nov 1995 11:00:05 -0800 Received: from olympus by devnull.mpd.tandem.com (8.6.8/8.6.6) id MAA04032; Thu, 9 Nov 1995 12:58:42 -0600 Received: by olympus (4.1/TSS2.1) id AA27364; Thu, 9 Nov 95 12:58:51 CST From: faulkner@mpd.tandem.com (Boyd Faulkner) Message-Id: <9511091858.AA27364@olympus> Subject: Re: iozone and mount -o async To: bde@zeta.org.au (Bruce Evans) Date: Thu, 9 Nov 1995 12:58:50 -0600 (CST) Cc: current@freebsd.org, faulkner@devnull In-Reply-To: <199511090011.LAA16890@godzilla.zeta.org.au> from "Bruce Evans" at Nov 9, 95 11:11:21 am X-Mailer: ELM [version 2.4 PL17] Content-Type: text Content-Length: 1115 Sender: owner-current@freebsd.org Precedence: bulk > > >Can you test the fs mounted async with iozone? I am getting a slowdown > >mounted async! > > This is normal. Mounting async disables the pessimization of doing > async (but ASAP) writes for full buffers. This pessimization is > actually an optimization for stupid benchmarks such as iozone. It > forces the physical i/o to be done ASAP instead of later when iozone > does an fsync(). Most applications don't do fsync()s so their i/o > gets done when the system thinks best. It might be useful to have > an fadvise() syscall (like madvise() but working :-). Applications > that do large sequential i/o's could use it to suggest write-through. > > Bruce > So how can I test my performance? iozone is no good. dd is no better. cp and cat file1 > file2 don't do as well either. It is because I am doing these things to a big file vs. a lot of smaller files? Thanks again, Boyd -- _______________________________________________________________________ Boyd Faulkner - faulkner@isd.tandem.com - http://cactus.org/~faulkner _______________________________________________________________________