Return-Path: Delivered-To: apmail-db-derby-dev-archive@www.apache.org Received: (qmail 37372 invoked from network); 7 Sep 2004 21:43:43 -0000 Received: from hermes.apache.org (HELO mail.apache.org) (209.237.227.199) by minotaur-2.apache.org with SMTP; 7 Sep 2004 21:43:43 -0000 Received: (qmail 21614 invoked by uid 500); 7 Sep 2004 21:43:41 -0000 Delivered-To: apmail-db-derby-dev-archive@db.apache.org Received: (qmail 21569 invoked by uid 500); 7 Sep 2004 21:43:41 -0000 Mailing-List: contact derby-dev-help@db.apache.org; run by ezmlm Precedence: bulk list-help: list-unsubscribe: list-post: List-Id: "Derby Development" Reply-To: "Derby Development" Delivered-To: mailing list derby-dev@db.apache.org Received: (qmail 21552 invoked by uid 99); 7 Sep 2004 21:43:41 -0000 X-ASF-Spam-Status: No, hits=0.0 required=10.0 tests= X-Spam-Check-By: apache.org Received-SPF: pass (hermes.apache.org: local policy) Received: from [204.146.167.214] (HELO Boron.MeepZor.Com) (204.146.167.214) by apache.org (qpsmtpd/0.28) with ESMTP; Tue, 07 Sep 2004 14:43:40 -0700 Received: from [9.30.40.215] (dmz-firewall [206.199.198.4]) by Boron.MeepZor.Com (8.11.6/8.11.6) with ESMTP id i87LhTS21864 for ; Tue, 7 Sep 2004 17:43:29 -0400 Message-ID: <413E2AD2.8060000@Source-Zone.org> Date: Tue, 07 Sep 2004 14:40:34 -0700 From: Suresh Thalamati Reply-To: tsuresh@Source-Zone.org User-Agent: Mozilla Thunderbird 0.7.3 (Windows/20040803) X-Accept-Language: en-us, en MIME-Version: 1.0 To: Derby Development Subject: Re: java1.4.2 "rws" mode - log write performance - OSX numbers References: <52071FA1-0103-11D9-A502-000D93ADDBD4@serv.net> In-Reply-To: <52071FA1-0103-11D9-A502-000D93ADDBD4@serv.net> X-Enigmail-Version: 0.85.0.0 X-Enigmail-Supports: pgp-inline, pgp-mime Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Checked: Checked X-Spam-Rating: minotaur-2.apache.org 1.6.2 0/1000/N Joseph Grace wrote: > Suresh: > >> Does Mac OS has concept of write cache enabling ? Numbers below >> are with write cache enabled/disabled ? > > > Yes, OSX has write cache enabling. Presumably it's on by default > (though I admit to not knowing how to confirm that), so my numbers > include it. That's why I ran the test under a variety of > circumstances. Benchmarks are hard, and the numbers vary a lot, so I > flagged the variance. I'm not sure what all the factors are, but I > believe your (implied) suspicion that cache'ing is one such factor. > > = Joe = > Yes, trying to find out the write cache factor in "rws"/"rwd" performance numbers. What I observerd is on Win2k i when write cache is enabled "rws" mode does not seem to sync immediately to the disk unlike FileDescriptor.sync(); I think this is ok because user has chosen the write cache enabling option. When write cache is disabled on windows the "rws" mode write does seem to perform the sync.(Note: On JDK141 sycn does not happen this case also). I don't have much knoweledge of jvm internals , but if the expected behaviour jvm on MAC OS is similar to Windows, write performance numbers in "rws/rwd" mode won't be accurate when write cache is enabled. I also don't know how to disable the write cache on Mac. Can't really say "rws" does not sync for sure on Mac unless the write cache is disabled. -suresht