Hi Amar, Thanks for your reply and the information regarding the ha translator. That solved the problem so we will use rr dns instead. Gluster is a great product and has been a very nice experience so far! Samba export is the only problem we need to solve to able to be able to implement gluster in a production environment (40TB total). However, 1 problem persists: - 1 single read through samba re-export goes fine, around 60MB/s - When doing 2 concurrent reads through samba, total throughput drops to half of that, 30MB/s Is this a known issue, or is it expected to be solved by using the gluster patched fuse? Kind regards, Ate On Fri, May 8, 2009 at 1:40 AM, Amar Tumballi <amar at gluster.com> wrote: > Hi Ate, > Please see inlined response. > >> >>> And the following errors shows up in the logs: >>> >>> 2009-05-01 16:31:25 E [fuse-bridge.c:2332:fuse_getlk_cbk] glusterfs-fuse: >>> 73272: ERR => -1 (Transport endpoint is not connected) >>> 2009-05-01 16:31:25 E [fuse-bridge.c:2332:fuse_getlk_cbk] glusterfs-fuse: >>> 73289: ERR => -1 (Transport endpoint is not connected) >>> 2009-05-01 16:31:25 E [fuse-bridge.c:2332:fuse_getlk_cbk] glusterfs-fuse: >>> 73306: ERR => -1 (Transport endpoint is not connected) >>> 2009-05-01 16:31:25 E [fuse-bridge.c:2332:fuse_getlk_cbk] glusterfs-fuse: >>> 73323: ERR => -1 (Transport endpoint is not connected) >>> >>> I hope someone can provide any pointers on how to solve this. Vol files >>> can be found below. >> >> >>> volume ha1 >>> type /testing/cluster/ha >>> subvolumes brick1_51 brick1_101 >>> end-volume >>> >> > This problem is because the 'testing/cluster/ha' translator doesn't > implement lk() calls properly. It should be done soon. We will move ha out > of 'testing/' once lk() fop is complete. > > Regards, > > > -- > Amar Tumballi > > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://zresearch.com/pipermail/gluster-users/attachments/20090508/92e45f97/attachment.htm>
