From mboxrd@z Thu Jan 1 00:00:00 1970 From: Joel Soete Subject: Re: [parisc-linux] ext3 perf patch#4 Date: Mon, 28 Mar 2005 12:51:10 +0000 Message-ID: <4247FDBE.2010306@tiscali.be> References: <20050326103540.GA31557@colo.lackof.org> <20050327011849.GD9287@colo.lackof.org> <4246B9D2.7070906@tiscali.be> <20050328034838.GI30963@colo.lackof.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Cc: parisc-linux@lists.parisc-linux.org To: Grant Grundler Return-Path: In-Reply-To: <20050328034838.GI30963@colo.lackof.org> List-Id: parisc-linux developers list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: parisc-linux-bounces@lists.parisc-linux.org Grant Grundler wrote: > On Sun, Mar 27, 2005 at 01:49:06PM +0000, Joel Soete wrote: > ... > >># time rsync -a /Debian-apt/SRC/linux-2.6.12-rc1-pa4-050327 /Sources/CVS-tst >> >>real 3m34.512s >>user 1m0.730s >>sys 1m6.440s > > > Joel, > thanks for the data! > > But I don't know what it means. > Was the performance bad for that box before? > :-) No just looks like as before: # uname -a Linux hpalin 2.6.12-rc1-pa1-c110 #2 Sat Mar 19 23:36:05 CET 2005 parisc GNU/Linux # time rsync -a /Debian-apt/SRC/linux-2.6.12-rc1-pa4-050327 /Sources/CVS-tst real 3m44.365s user 1m0.350s sys 1m11.120s > >>I prefer simply tar and so: >># cd /Debian-apt/SRC >># time tar -cslpf /chroot/Develop/linux-2.6.12-rc1-pa4.tar2 >>linux-2.6.12-rc1-pa4-050327 >> >>real 0m38.487s >>user 0m3.690s >>sys 0m18.650s >> >>a sample iostat too :-) >>avg-cpu: %user %nice %sys %iowait %idle >> 15.70 0.00 47.00 37.30 0.00 >> >>Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrtn >>sda 2.50 0.00 19.60 0 196 >>sdb 297.30 5906.40 89.20 59064 892 >>sdc 15.10 0.00 7712.80 0 77128 > > ... > > That looks fine. > Yes, sorry for confusion (I would just show that it works and nothing was broken) ... > > I probably should have posted that speculation to the mailing list > instead of in the commit log...I was quite tired at that point. > Don't wory I would have to be disturbe or confused by the song of a bird in the garden ?-) (the 32bit bug has obviously nothing to do with that) > That could only be true if ext3 perf issue only shows up in 64-bit kernels. > I don't recall if anyone posted perf results for 32-bit kernels. > TBH, the 2 64bit system I have the oportunity to test (b2k up, n4k smp) are so confortable (well n4k ask many time for self test on reboot) from speed point of view that I never noticed ext[23] lack of perf ;-) Thanks, Joel _______________________________________________ parisc-linux mailing list parisc-linux@lists.parisc-linux.org http://lists.parisc-linux.org/mailman/listinfo/parisc-linux