Hi David,
It smell like some scsi driver congestion. First of all,
you can try to set greater value (such 256) to both max and min readahead.
(see sysctl)
One idea could be to set the elevator to "deadline" or "as"
if SAS drive(i.e: Kernel append).
Other could be to mount the ext3 with option such -o
reservation,noatime,nodiratime
Good luck
Michael.
michael.aubertin@gmail.com
Original message:
---------------
****************************************************************************************************
Ce message ou ses pieces jointes peuvent contenir des informations
confidentielles a l'intention exclusive de son destinataire et est couvert
par le secret professionnel.
Toute utilisation, divulgation ou reproduction de son contenu sont strictement
interdits.
Si vous avez recu ce message par erreur, merci de le notifier a son expediteur
et d'en detruire toute copie.
Le present message pouvant-etre altere a notre insu, le groupe ARES ne peut pas
etre engage par son contenu.
www.ares.fr
****************************************************************************************************
Received:11/27/06 16:08
From:David Sharples <davidsharples@gmail.com>
To:ocfs-users@oss.oracle.com
Cc:
Subject:[Ocfs-users] copying files from ocfs to ext3
Hi, using ocfs-2.4.9-e-smp-1.0.12-1 on Redhat 3 U4
Trying to copy files from an ocfs volume to an ext3 volume is very very slow
- talking a couple of minutes for a 100Mb file.
same happens if I use o-direct or not, dd exhibits the same behaviour
ocfs is in the updatedb.conf and both filesystems are in the PRUNEPATHS line
in the same file (a reboot was done after the changes were made just to make
sure)
Coping from ocfs to ocfs is very quick as is copying from ext3 to ext3
Any ideas where I can look?
Thanks
Dave