[DRBD-user] write performance

[Leonardo Rodrigues de Mello]

Hi Anselm,

There is one important thing in your setup that can be affecting your performance. You have defined the syncer rate as 20MBytes/second. The maximum  theoretician performance that gigabit network can deliver is 125MBytes/second.

you must change this: 
syncer {
     rate 20M;
     al-extents 1024;
     group 1;
   }

to this :

syncer {
     rate 125M;
     al-extents 1024;
     group 1;
   }

see if you have some difference in your speed.

I would like to know more about what you are doing with lustre. are you documentating it ? can tell me more in private ? leonardo.mello at planejamento dot gov dot br 

I have some experience in gfs and ocfs2, and want to give lustre one try.

Best Regards
Leonardo Rodrigues de Mello

-----Original Message-----
From:	drbd-user-bounces at lists.linbit.com on behalf of Anselm Strauss
Sent:	qua 23/8/2006 06:20
To:	drbd-user at lists.linbit.com
Cc:	
Subject:	[DRBD-user] write performance


resource lustre1 {
   protocol C;
   disk {
     on-io-error detach;
   }
   net {
     max-buffers 8192;
     sndbuf-size 512k;
     max-epoch-size 8192;
   }
   syncer {
     rate 20M;
     al-extents 1024;
     group 1;
   }
   on tnode1 {
     device /dev/drbd0;
     disk /dev/sda9;
     address 10.0.0.5:7788;
     meta-disk internal;
   }
   on tnode2 {
     device /dev/drbd0;
     disk /dev/sda9;
     address 10.0.0.6:7788;
     meta-disk internal;
   }
}

It says sndbuf-size should not be set over 1M. Is it a problem if  
sndbuf-size aggregated over multiple sections is above 1M?

Cheers,
Anselm Strauss

_______________________________________________
drbd-user mailing list
drbd-user at lists.linbit.com
http://lists.linbit.com/mailman/listinfo/drbd-user



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.linbit.com/pipermail/drbd-user/attachments/20060823/0b79221a/attachment.htm>