Re: [Gluster-users] add/replace brick corrupting data
On 17 May 2016 at 10:02, WK wrote: > That being said, when we lose a brick, we've traditionally just live > migrated those VMs off onto other clusters because we didn't want to take > the heal hit which at best slowed down our VMs at on the pickier ones cause > them to RO out. > > We have not yet upgraded to 3.7.x yet (still on 3.4 cuz it aint broke) and > are hoping that sharding solves that problem. But it seems everytime it > looks like things are 'safe' for 3.7.x, something comes up. Fortunately, we > like the fuse mount so maybe we are still ok. Unfortunately(?) I get much better performance out of the gfapi - seeing around 30-40% better reads and IOPs over the fuse client in VM's. -- Lindsay ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] add/replace brick corrupting data
That should be an important clue. That being said, when we lose a brick, we've traditionally just live migrated those VMs off onto other clusters because we didn't want to take the heal hit which at best slowed down our VMs at on the pickier ones cause them to RO out. We have not yet upgraded to 3.7.x yet (still on 3.4 cuz it aint broke) and are hoping that sharding solves that problem. But it seems everytime it looks like things are 'safe' for 3.7.x, something comes up. Fortunately, we like the fuse mount so maybe we are still ok. -wk On 5/16/2016 4:42 AM, Lindsay Mathieson wrote: Ok, this is probably an interesting data point. I was unable to reproduce the problem when using the fuse mount. Its late here so I might not have time to repeat with the gfapi, but I will tomorrow. On 16/05/2016 4:55 PM, Krutika Dhananjay wrote: Yes, that would probably be useful in terms of at least having access to the client logs. -Krutika On Mon, May 16, 2016 at 12:18 PM, Lindsay Mathieson wrote: On 16 May 2016 at 16:46, Krutika Dhananjay wrote: > Could you share the mount and glustershd logs for investigation? Can do, though its via gfapi rather than the fuse mount. If I can replicate the problem off the fuse mount would that be more useful? -- Lindsay -- Lindsay Mathieson ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] add/replace brick corrupting data
Ok, this is probably an interesting data point. I was unable to reproduce the problem when using the fuse mount. Its late here so I might not have time to repeat with the gfapi, but I will tomorrow. On 16/05/2016 4:55 PM, Krutika Dhananjay wrote: Yes, that would probably be useful in terms of at least having access to the client logs. -Krutika On Mon, May 16, 2016 at 12:18 PM, Lindsay Mathieson mailto:lindsay.mathie...@gmail.com>> wrote: On 16 May 2016 at 16:46, Krutika Dhananjay mailto:kdhan...@redhat.com>> wrote: > Could you share the mount and glustershd logs for investigation? Can do, though its via gfapi rather than the fuse mount. If I can replicate the problem off the fuse mount would that be more useful? -- Lindsay -- Lindsay Mathieson ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users