[Gluster-users] Behaviour of simple distributed volumes on failed bricks?

I had a question on the expected behaviour of simple distributed volumes when a brick fails for the following scenarios (as in, will the scenario succeed for fail) : - New file creation if that file name hashes to the failed brick - New file creation if that file name hashes to one of the remainin

Re: [Gluster-users] Replace replicate in single brick

This is the format which we have followed in this command . There could be a case when you want to keep the same bricks which you have added using IP address but now instead of IP address you want that all the bricks should have hostname. In this case you have to mention both the source as wel

Re: [Gluster-users] Replace replicate in single brick

On 11/01/2017 4:07 AM, Andrus, Brian Contractor wrote: He showed the syntax for ‘replace-brick’ not ‘reset-brick’, which, since I am on 3.8.5, hopefully works when a source-brick is missing…. Anyone know if that would be true? Or do I have to upgrade to 3.9 to be able to replace a completely

Re: [Gluster-users] Replace replicate in single brick

Gandalf, From what I see, it doesn’t: reset-brick He showed the syntax for ‘replace-brick’ not ‘reset-brick’, which, since I am on 3.8.5, hopefully works when a source-brick is missing…. Anyone know if that would be true? Or do I have to upgrade to 3.9 to be able to replace a completely unava

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Xavi, In this case it's the file creation which failed. So I provided the xattrs of the parent. Thanks and Regards, Ram -Original Message- From: Xavier Hernandez [mailto:xhernan...@datalab.es] Sent: Tuesday, January 10, 2017 9:10 AM To: Ankireddypalle Reddy; Gluster Devel (g

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Hi Ram, On 10/01/17 14:42, Ankireddypalle Reddy wrote: Attachments (2): 1 ec.txt

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Attachments (2): 1 ec.txt

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Hi Ram, the error is caused by an extended attribute that does not match on all 3 bricks of the disperse set. Most probable value is trusted.ec.version, but could be others. At first sight, I don't see any change from 3.7.8 that could have caused this. I'll check again. What kind of operat

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Xavi, Thanks. If you could please explain what to look for in the extended attributes then I will check and let you know if I find anything suspicious. Also we noticed that some of these operations would succeed if retried. Do you know of any communicated related errors that are being

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Hi Ram, On 10/01/17 13:14, Ankireddypalle Reddy wrote: Attachment (1): 1 ecxattrs.txt

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Attachment (1): 1 ecxattrs.txt

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Hi Ram, can you execute the following command on all bricks on a file that is giving EIO ? getfattr -m. -e hex -d Xavi On 10/01/17 12:41, Ankireddypalle Reddy wrote: Xavi, We have been running 3.7.8 on these servers. We upgraded to 3.7.18 yesterday. We upgraded all the servers

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Hi Ram, how did you upgrade gluster ? from which version ? Did you upgrade one server at a time and waited until self-heal finished before upgrading the next server ? Xavi On 10/01/17 11:39, Ankireddypalle Reddy wrote: Hi, We upgraded to GlusterFS 3.7.18 yesterday. We see lot of fai

Re: [Gluster-users] [Gluster-devel] Lot of EIO errors in disperse volume

Xavi, We have been running 3.7.8 on these servers. We upgraded to 3.7.18 yesterday. We upgraded all the servers at a time. The volume was brought down during upgrade. Thanks and Regards, Ram -Original Message- From: Xavier Hernandez [mailto:xhernan...@datalab.es] Sent: Tu

Re: [Gluster-users] Ganesha with Gluster transport RDMA does not work

On 09/01/17 16:27, Andreas Kurzac wrote: Hi Jiffin, i raised bug 1411281. If you could provide test-rpms i would be very happy to test them in our environment. Sorry If I missed in previous mail, which nfs-ganesha (2.3 or 2.4) version are u using ? -- Jiffin In the meantime i will sw

[Gluster-users] Lot of EIO errors in disperse volume

Hi, We upgraded to GlusterFS 3.7.18 yesterday. We see lot of failures in our applications. Most of the errors are EIO. The following log lines are commonly seen in the logs: The message "W [MSGID: 122056] [ec-combine.c:873:ec_combine_check] 0-StoragePool-disperse-4: Mismatching xdata in

Re: [Gluster-users] Replace replicate in single brick

Il 10 gen 2017 05:59, "Ravishankar N" ha scritto: If you are using glusterfs 3.9 and want to give the replaced brick the same name as the old one, there is the reset-brick command. The commit message in http://review.gluster.org/#/c/12250/ gives you some information on the steps to run. If you ar