<div>apologies, it is</div>
<div> </div>
<div>ocfs-2.4.21-EL-smp-1.0.14-1, the old version was still there by accident.</div>
<div> </div>
<div>Anyway, the 128K thing did the trick, copying speeds are great now.</div>
<div> </div>
<div>Thanks</div>
<div><br>Dave<br><br> </div>
<div><span class="gmail_quote">On 27/11/06, <b class="gmail_sendername">Sunil Mushran</b> <<a href="mailto:Sunil.Mushran@oracle.com">Sunil.Mushran@oracle.com</a>> wrote:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">ocfs-2.4.9-e-smp-1.0.12-1 is for AS2.1. Unsure how you can use that<br>on a RHEL3 box.<br><br>Other than that, ensure you have the latest coreutils.
<br><br>cp --o_direct=128K,0 /ocfs /ext3<br>It will read in 128K chunks.<br><br>Michael Aubertin wrote:<br>> Hi David,<br>><br>> It smell like some scsi driver congestion. First of all,<br>> you can try to set greater value (such 256) to both max and min readahead.
<br>> (see sysctl)<br>> One idea could be to set the elevator to "deadline" or "as" if SAS drive(i.e: Kernel append).<br>> Other could be to mount the ext3 with option such -o reservation,noatime,nodiratime
<br>><br>><br>> Good luck<br>><br>> Michael.<br>> <a href="mailto:michael.aubertin@gmail.com">michael.aubertin@gmail.com</a><br>><br>> Original message:<br>> ---------------<br>><br>> ****************************************************************************************************
<br>> 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.<br>> Toute utilisation, divulgation ou reproduction de son contenu sont strictement interdits.
<br>> Si vous avez recu ce message par erreur, merci de le notifier a son expediteur et d'en detruire toute copie.<br>> Le present message pouvant-etre altere a notre insu, le groupe ARES ne peut pas etre engage par son contenu.
<br>> <a href="http://www.ares.fr">www.ares.fr</a><br>> ****************************************************************************************************<br>><br>> Received:11/27/06 16:08<br>> From:David Sharples <
<a href="mailto:davidsharples@gmail.com">davidsharples@gmail.com</a>><br>> <a href="mailto:To:ocfs-users@oss.oracle.com">To:ocfs-users@oss.oracle.com</a><br>> Cc:<br>> Subject:[Ocfs-users] copying files from ocfs to ext3
<br>><br>> Hi, using ocfs-2.4.9-e-smp-1.0.12-1 on Redhat 3 U4<br>><br>> Trying to copy files from an ocfs volume to an ext3 volume is very very slow<br>> - talking a couple of minutes for a 100Mb file.<br>> same happens if I use o-direct or not, dd exhibits the same behaviour
<br>><br>> ocfs is in the updatedb.conf and both filesystems are in the PRUNEPATHS line<br>> in the same file (a reboot was done after the changes were made just to make<br>> sure)<br>><br>> Coping from ocfs to ocfs is very quick as is copying from ext3 to ext3
<br>><br>> Any ideas where I can look?<br>><br>> Thanks<br>><br>> Dave<br>><br>><br>> _______________________________________________<br>> Ocfs-users mailing list<br>> <a href="mailto:Ocfs-users@oss.oracle.com">
Ocfs-users@oss.oracle.com</a><br>> <a href="http://oss.oracle.com/mailman/listinfo/ocfs-users">http://oss.oracle.com/mailman/listinfo/ocfs-users</a><br>><br></blockquote></div><br>