Kon, Since CIFS is not completely stateless, something needs to maintain state. Ucarp doesn't do this which is why something like CTDB is more appropriate for CIFS failover. -Jacob -----Original Message----- From: gluster-users-bounces at gluster.org [mailto:gluster-users-bounces at gluster.org] On Behalf Of Kon Wilms Sent: Thursday, December 09, 2010 10:38 AM To: gluster-users at gluster.org Subject: 3.1.1 GFS + UCARP for simple CIFS HA? A little information on my configuration for this task: - I am deploying a gfs 3.1.1 cluster using 4 nodes in mirror mode. - Each pair is running ucarp to provide failover support. - The two ucarp ips are then made available to clients via dnsrr. - My access mode is read-only for CIFS with no credentials for file access. - I am not looking to do an active/active configuration; active/standby suits me fine. - I am also not looking to retain state on failover. If a file access fails, it will be retried by the client-side application. - Clients are running Win2k8r2 and mount the cifs share to a local volume for local server access. Given this scenario, is ucarp suitable for deployment? Or are there other potential unforeseen issues i.e. client-side drive disconnects on failover? My other option is to go to NFS on the Win2k8r2 servers. Which begs the question of performance of CIFS vs. NFS. Cheers Kon _______________________________________________ Gluster-users mailing list Gluster-users at gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
