From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hans Reiser Subject: Re: A question: May Reiser4 be equivalent to Reiser3 with some flag/plugin ... Date: Wed, 18 Jan 2006 09:40:35 -0800 Message-ID: <43CE7D93.7090304@namesys.com> References: <13dbb67f0601070441q559b156ep@mail.gmail.com> <43C2A9D8.80103@namesys.com> <200601092001.17684.marcel@hilzinger.hu> <43CDFC25.90401@futuretg.com> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Return-path: list-help: list-unsubscribe: list-post: Errors-To: flx@namesys.com In-Reply-To: <43CDFC25.90401@futuretg.com> List-Id: Content-Type: text/plain; charset="us-ascii" To: "Giovanni A. Orlando" Cc: reiserfs-list@namesys.com Giovanni A. Orlando wrote: > Hi, > > Looking the http://linuxgazette.net/122/TWDT.html#piszcz article, I > see that > in some cases ReiserFS 3.X is better than Reiser4. > > Correct me if I am wrong. High numbers means poor, more delay. > > Now, because we plan to support both: Reiser3 and Reiser4 in our OS, > we plan to know if there are some system the Reiser3 performance > may become available for Reiser4. > > Reiser4 is superior but seems that with full security enabled > logically > the system may delay. > > Basically, my question may be re-posted like: "I know Reiser4 is > different than Reiser3, but may the Reiser4 performance may be > superior > all the time, doing some update? > > Thanks, > Giovanni. > Please understand that that benchmark was so poorly done that it will have to be repeated by us and fixed before it can have any diagnostic meaning at all. We may indeed learn things from it, but what we will learn we still have no idea of at this time. V3 is faster for highly synchronous workloads. V4 smokes it in pretty much all other measures. Given time, V4 will become fast at synchronous workloads. Hans