Re: [Gluster-users] add/replace brick corrupting data

2016-05-17 Thread William Kern
I believe some of the staff tested gfapi back in the 3.4 days and found that at least that version didn't make a perceptible difference though it tested about 10% faster. We stayed with Fuse because at that time gfapi was still newish and we had used fuse for quite awhile and understood it.

Re: [Gluster-users] add/replace brick corrupting data

2016-05-17 Thread Krutika Dhananjay
Hmm in that case, could you do the following: If you could recreate this issue again, could you record the extended attributes associated with the shards that you see being listed against the replaced-brick in heal-info. For example, assuming you replaced the brick on vng, once heal kicks in,

Re: [Gluster-users] add/replace brick corrupting data

2016-05-17 Thread Lindsay Mathieson
On 17/05/2016 7:56 PM, Krutika Dhananjay wrote: Would you know where the logs of individual vms are with proxmox? No i don't I'm afraid. Would they be a function of gluster or qemu? -- Lindsay Mathieson ___ Gluster-users mailing list

Re: [Gluster-users] add/replace brick corrupting data

2016-05-17 Thread Krutika Dhananjay
Would you know where the logs of individual vms are with proxmox? In those, do you see any libgfapi/gluster log messages? -Krutika On Tue, May 17, 2016 at 8:38 AM, Lindsay Mathieson < lindsay.mathie...@gmail.com> wrote: > On 17 May 2016 at 10:02, WK wrote: > > That being

Re: [Gluster-users] add/replace brick corrupting data

2016-05-16 Thread Lindsay Mathieson
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. >

Re: [Gluster-users] add/replace brick corrupting data

2016-05-16 Thread WK
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

Re: [Gluster-users] add/replace brick corrupting data

2016-05-16 Thread Lindsay Mathieson
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

Re: [Gluster-users] add/replace brick corrupting data

2016-05-16 Thread Krutika Dhananjay
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 < lindsay.mathie...@gmail.com> wrote: > On 16 May 2016 at 16:46, Krutika Dhananjay wrote: > > Could you share the mount

Re: [Gluster-users] add/replace brick corrupting data

2016-05-16 Thread Krutika Dhananjay
Hi, Could you share the mount and glustershd logs for investigation? -Krutika On Sun, May 15, 2016 at 12:22 PM, Lindsay Mathieson < lindsay.mathie...@gmail.com> wrote: > On 15/05/2016 12:45 AM, Lindsay Mathieson wrote: > > *First off I tried removing/adding a brick.* > > gluster v

Re: [Gluster-users] add/replace brick corrupting data

2016-05-15 Thread Lindsay Mathieson
On 15/05/2016 12:45 AM, Lindsay Mathieson wrote: *First off I tried removing/adding a brick.* gluster v remove-brick replica 2 vng.proxmox.softlog:/tank/vmdata/test1 force. That worked fine, VM's (on another node) kept running without a hiccup I deleted /tank/vmdata/test1, then