From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hans Reiser Subject: Re: Re: [STUPID TESTCASE] ext3 htree vs. reiserfs on 2.5.40-mm1 Date: Sat, 05 Oct 2002 02:27:20 +0400 Message-ID: <3D9E15C8.2060005@namesys.com> References: <200210042254.23978.Dieter.Nuetzel@hamburg.de> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: list-help: list-unsubscribe: list-post: Errors-To: flx@namesys.com List-Id: Content-Type: text/plain; charset="iso-8859-1"; format="flowed" To: =?ISO-8859-15?Q?Dieter_N=FCtzel?= Cc: ReiserFS List , Chris Mason , Paul P Komkoff Jr , Manuel Krause Dieter N=FCtzel wrote: >Am Mittwoch, 2. Oktober 2002 10:48 schrieb Paul P Komkoff Jr: > =20 > >>Replying to Andreas Dilger: >> =20 >> >>>Why do you think data=3Dwriteback is better than data=3Djournal? If the >>>files have no data then it should not make a difference. >>> =20 >>> >>It is better than default data=3Dordered I think :) >> >>Thanks for detailed explanation - it saved much time for me and >>accortind to yours directions I have recalculated my test. Now ext3 is >>better :) >> >>e3 >>create 2m49.545s 0m4.162s 2m20.766s >>delete 2m8.155s 0m3.614s 1m34.945s >> >>reiser >>create 3m13.577s 0m4.338s 2m54.026s >>delete 4m39.249s 0m3.968s 4m16.297s >> >>e3 >>create 2m50.766s 0m4.024s 2m21.197s >>delete 2m8.755s 0m3.501s 1m35.737s >> >>reiser >>create 3m13.015s 0m4.432s 2m53.412s >>delete 4m41.011s 0m3.893s 4m16.845s >> >> >>this is two typical runs. Now I creating ext3 with >>mke2fs -j -O dir_index -J size=3D192 -T news /dev/sda4 >> >>as you can see, this improves performance by 1/4 >> >>Unfortunately, there still one issue in ext3. It called "inode limit". >>Initially I wanted to run this test on 1000000 files but ... I hit >>inode limit and don't want to increase it artificially yet. >> >>Reiserfs worked fine because it don't have such kind of limit ... >> =20 >> > >Orange and apples, again? > >Try with latest ReiserFS data-logging and see what we get? >Chris do you have something for 2.5.40+ ready? > >2.5.40 is GREAT! > >Regards, > Dieter > =20 > So, I think that if you create enough files in your test to stress the=20 IO subsystem, then it will be a much more interesting test.=20 Unfortunately, you may need to increase the inode allocation to test=20 this for ext3. Once you start to get above a million files, you may=20 start to see reiser4 doing substantially better than ReiserFS because=20 reiser4 has better layout and better hashes based on things we learned. I would be curious to see your benchmark done for 3 million files. I=20 would be curious to see what happens if you umount in the middle of it.=20 I would not be surprised if interesting VFS/dcache performance issues=20 arise as you increase the number of files. Hans