On Thu, February 8, 2007 6:58 pm, Ariz Jacinto wrote: > look, you can't just tweak the filesystem on the other and then leave the > other on its default! you also have to disable the equivalent feature on > Ext3 (journalling). =D
i think he uses the same machine on his small benchmark. hmm disabling journaling on ext3 makes it ext2-like fs. i can't now see the fs advantages on it. > please do bother to state if both OS are loaded on the same or identical > machines. if you're only using a single machine, then they should have > at least identical disks (but not on multi boot), partitions, etc. you > should > also state the version of the OS (or kernel) that you're testing. > > i really don't care which FS performs better on your tests, as long as > you're going to do it properly. and please do bother to use the typical > micro and "real world" testing tools such as Bonnie++, IOZone, etc. no offense, but benchmarck proves nothing. real world testing tool is deploying it on the wild. > and you were reading the changelog of the release candidates =D imho that bugs is present on the latest stable before that release candidate. but good that they've fixed it. > seriously speaking, with the upstream development of the linux kernel, > the sysad who's after the stability instead of the new feature or improved > performance, usually waits for the x.x.2x.x or x.x.3x.x release versions. see. performance and features over stability. that's what fooler is trying to emphazise to us. i'm aware that his working environment is enough for a "real time benchmark". > not all filesystems does the same thing. each have their own design > and merit that can be applied best for a specific application or based > on the available resources. yes and i'm waiting for zfs on freebsd. > in benchmarking, test setups are done using the default configuration > and then using the optimized configuration. it is common to ask for > the expertise of product developers in order to do justice and to prevent > any bias. if you read one of the recent papers on Usenix, the researchers > also sought the expertise of the *BSD community on one of their FS > tests. yes, but imo all benchmarks done by these people are all micro benchmarks. there's no "real time benchmark" except in "real time deployment" and it takes a very long time and too much regressions to see the result. > > as of the moment, the most recent micro/real world benchmark > was presented on LK 2006 featuring various OS and filesystems: > http://bulk.fefe.de/lk2006/talk.pdf fefe actually is a linux guy. i remember that he asked on openbsd mailing list how to optimize the os after publishing his test result. cheers! _________________________________________________ Philippine Linux Users' Group (PLUG) Mailing List [email protected] (#PLUG @ irc.free.net.ph) Read the Guidelines: http://linux.org.ph/lists Searchable Archives: http://archives.free.net.ph
