Re: [Jfs-discussion] performance probs - 2.4.28, jsf117, raid5
On Sun, 05 Dec 2004 18:40:58 +0100, Per Jessen wrote: >I do a find in a directory that contains 5-600,000 files - which just >about makes the box grind to a halt. The machine is not heavily loaded as >such, >but does write 2 new files/sec to the same filesystem. Or tries to. I need to add - at the same time kswapd is very, very busy, despite only about 1Gb of the 2Gb main core being used/active. /Per -- regards, Per Jessen, Zurich http://www.spamchek.com - let your spam stop here! ___ Jfs-discussion mailing list [EMAIL PROTECTED] http://www-124.ibm.com/developerworks/oss/mailman/listinfo/jfs-discussion
[Jfs-discussion] performance probs - 2.4.28, jsf117, raid5
Hi, I'm not certain JFS is the culprit here, but at least it's a suspect :-) I have a 150Gb filesystem on software RAID5 with JFS117, kernel 2.4.28. The box is a 4way 500MHz Xeon with 2Gb. I do a find in a directory that contains 5-600,000 files - which just about makes the box grind to a halt. The machine is not heavily loaded as such, but does write 2 new files/sec to the same filesystem. Or tries to. I fully appreciate that having that many files in a single directory is not exactly the most optimal, but as they are only accessed once a week for deletion (it's a trashcan), I haven't bothered with dividing into subdirs. Anyway, 1) am I right in suspecting JFS in this and 2) is it to be expected? thanks -- regards, Per Jessen, Zurich http://www.spamchek.com - let your spam stop here! ___ Jfs-discussion mailing list [EMAIL PROTECTED] http://www-124.ibm.com/developerworks/oss/mailman/listinfo/jfs-discussion
[Jfs-discussion] Filesystem performance with Linux 2.4 vs. 2.6
Hi all, I read an article in the German 'Linux Magazin' 11/04 about a comparision of the different FS. They tested Ext2, Ext3, JFS, XFS, ReiserFS, Reiser4 and Veritas. Detailed results can be found on http://www.linux-magazin.de/Service/Listings/2004/11/fs_bench. My question is: Why is the reading performance of every FS (available for both Linux versions) under 2.6 so bad compared to 2.4? 2.6 looses nearly 50%! The write performance is depending on the file size sometimes slightly higher or lower. Can you tell me in short words what changed from 2.4 to 2.6 that explains the difference? I thought that every major kernel release makes things better. So what is now so much better that is worth to loose 50% performance? Regards Michael ___ Jfs-discussion mailing list [EMAIL PROTECTED] http://www-124.ibm.com/developerworks/oss/mailman/listinfo/jfs-discussion