From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hans Reiser Subject: Re: Linux Gazette benchmark Reiser 4 Date: Mon, 09 Jan 2006 10:22:16 -0800 Message-ID: <43C2A9D8.80103@namesys.com> References: <13dbb67f0601070441q559b156ep@mail.gmail.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: <13dbb67f0601070441q559b156ep@mail.gmail.com> List-Id: Content-Type: text/plain; charset="us-ascii" To: Andrea Gelmini , ReiserFS List Andrea Gelmini wrote: > > > 2006/1/6, Robert Hulme >: > > http://linuxgazette.net/122/TWDT.html#piszcz > > It seems to come off fairly badly in most of the tests. > > > I really did not understand this kind of benchmark. I don't care > which filesystem is faster creating 10.000 files (something I never > have to do). I care about which filesystem fits better with my > everyday use of my data. > Days ago I wrote a few script trying to simulate a tipical desktop > session, *my* tipical desktop session. With different filesystem I've > got difference of minutes. That's a benchmark that mean something to me. > Why I'm trying/looking at reiser4? > Because: > a) seeks are the real problem of hd (they kill performance); > b) journal in a fixed position creates a lot of seeks; > c) I love ext2, but my laptop crash a lot of time in a day (tests, > battery and so on). > > Testing reiser4 is giving to me a good feeling with wondering logs. > You know... less seek, less HD stress... so more responsiveness. > Well, it's too early to express an opinion about R4 (I'm using it > since last week), but the only way to test a FS is to use it for a > long time. > > Sorry for my bad english, > gelma > reiser4 is normally very fast in creating 10,000 files. I suspect that there was simply error in how he did the test, and when the guys get back i will have someone try to reproduce his results. Justin made so many errors, I suspect he got something wrong here also. I encourage you guys to run your own tests, and you will see that we do fairly well I think. Advice when benchmarking is: make sure your fileset is much larger than RAM make sure the benchmark takes a while to run create your tarballs on the same fs you use them to benchmark (readdir order matters) Assume a 3% noise level.