On 07/12/2013 05:51 AM, elvinas.piliponis at barclays.com wrote: >> The cluster seems to slow just slightly, but it kept on ticking. Great. > You are lucky then. Statements like this do not give me the warm fuzzies. Is Gluster safe to use in a production environment? > To avoid that I have changed fstab mount option to: errors=panic instead of default errors= remount-ro Noted. I will do the same then. >> File exists [2013-07-11 16:20:13.387819] I >> [server3_1-fops.c:1538:server_open_cbk] 0-bkupc1-server: 24283714: >> OPEN >> /BACKUPS/2013-07-10/cat/export/c/data/dir2/OLD/.dir.old.tar.gz.hdbx3z >> (0c079382-e88b-432c-83e3-79bd9f5b8bb9) ==> -1 (File exists) > Can you open the file from mount point? This particular file, yes. I can open with tar -ztvf and see it's contents just fine. However I have found other problems. One of the files listed by heal-failed is: 2013-07-11 16:07:53 /BACKUPS/2013-07-10/origo/export/a/home/flagon/src/matlab-r2012a/config/matlab-r2012a/opt/matlab-r2012a/toolbox/signal/signal/@dspdata/@groupdelay/schema.p When I try to access the file, I get: # ls -ald /BACKUPS/2013-07-10/origo/export/a/home/flagon/src/matlab-r2012a/config/matlab-r2012a/opt/matlab-r2012a/toolbox/signal/signal/@dspdata/@groupdelay/schema.p ls: cannot access /BACKUPS/2013-07-10/origo/export/a/home/flagon/src/matlab-r2012a/config/matlab-r2012a/opt/matlab-r2012a/toolbox/signal/signal/@dspdata/@groupdelay/schema.p: No such file or directory > >> The manual lists "volume heal <VOLUME> info heal-failed" as a command >> that I can check out, so I run that and get a list of files for which healing has >> failed. There's quite a bit of them. > Did you check output of "volume heal <VOLUME> info healed", maybe those files were eventually healed. Compare time stamps. Both of the above files are listed as having been healed. The first one is available, the second one returns an error. > You are using replicated or distributed replicated volume, am I right? Correct.
