Camelia, the Perl 6 bug

IRC log for #gluster, 2012-10-07

| Channels | #gluster index | Today | | Search | Google Search | Plain-Text | summary

All times shown according to UTC.

Time Nick Message
00:22 bullardo joined #gluster
00:37 jrist joined #gluster
03:16 hagarth joined #gluster
03:36 hagarth joined #gluster
05:02 bullardo joined #gluster
05:44 badone_home joined #gluster
06:47 badone_home joined #gluster
07:18 mo joined #gluster
07:47 Guest50094 .hi all..... trying to get  ctdb work with gluster, but I cannot get the share-locking area to perform good enough. Running gluster 3.3 from rpm for fc16... Ping_pong test runs fine on first host, but hangs when trying the next host
07:48 Guest50094 anyone got an idea how to tune this ?
07:52 cyberbootje joined #gluster
07:57 kore joined #gluster
08:30 badone_home joined #gluster
08:33 stickyboy joined #gluster
08:45 Guest50094 left #gluster
09:03 badone_home joined #gluster
09:22 gbrand_ joined #gluster
09:34 badone_home joined #gluster
10:04 badone_home joined #gluster
10:34 badone_home joined #gluster
10:43 nueces joined #gluster
10:49 badone_home joined #gluster
11:03 hagarth joined #gluster
11:12 badone_home joined #gluster
12:22 indivarnair joined #gluster
12:23 indivarnair Hi...
12:23 glusterbot indivarnair: Despite the fact that friendly greetings are nice, please ask your question. Carefully identify your problem in such a way that when a volunteer has a few minutes, they can offer you a potential solution. These are volunteers, so be patient. Answers may come in a few minutes, or may take hours. If you're still in the channel, someone will eventually offer an answer.
12:24 indivarnair Is the Switch Scheduler still available, or is it Obsolete?
12:41 stickyboy joined #gluster
14:05 bulde joined #gluster
14:20 bulde1 joined #gluster
15:49 ian__ joined #gluster
15:49 wushudoin joined #gluster
15:57 lico joined #gluster
16:37 bullardo joined #gluster
16:52 Nr18 joined #gluster
16:52 bulde joined #gluster
16:59 neofob joined #gluster
17:00 neofob a screenshot of my gluster healing powered by two cuboxes (Marvell Armada 510 @ 800Mhz) http://bit.ly/QNQX1u
17:10 elyograg joined #gluster
17:34 bulde joined #gluster
17:35 gbrand_ joined #gluster
18:22 JoeJulian indivarnair: The schedulers are only used in the unify translator. From what I can read in the source, it look like it still exists but since there's no way to make use of it through the cli you would have to manage vol files manually.
19:45 Guest986 joined #gluster
19:46 Guest986 hi all..... trying to get  ctdb work with gluster, but I cannot get the share-locking area to perform good enough. Running gluster 3.3 from rpm for fc16... Ping_pong test runs fine on first host, but hangs when trying the next host
19:46 Guest986 someone knows how to get this to work ?
19:51 Nr18 joined #gluster
19:52 wushudoin joined #gluster
19:57 JoeJulian Guest986: No idea what ctdb's doing that would cause that. Maybe run an strace and see what it's trying to do?
20:11 badone joined #gluster
20:15 Guest986 hi... it is using fcntl locking.... I will try to enable this feature on the volume
20:23 JoeJulian Guest986: sounds like ctdb is trying to lock files on each server. Since they're sharing the same files, they're locking each other out of them.
20:29 indivarnair joined #gluster
20:40 Azrael808 joined #gluster
20:55 gbrand_ joined #gluster
20:57 duerF joined #gluster
20:57 Guest986 JoeJulian: according to ctdb this is the way it is supposed to work... really struggling to get this working... but I can now also see that my simple replicated two node volume does not work if one node is down... so I will have to look into this further
21:02 andrewbogott_afk joined #gluster
21:03 andrewbogott_afk joined #gluster
21:04 gbrand_ joined #gluster
21:18 badone_home joined #gluster
21:19 Azrael808 joined #gluster
21:25 badone_home joined #gluster
21:51 hjmangalam joined #gluster
21:59 hjmangalam I have 4 gluster 3.3 servers (on Ubuntu 10.04) recovering from a power outage. 2 of them are not restarting their glusterfsd's with the result that the volume is being /partially/ exported AFAICT. clients can see the vol, but not all files. And some gluster utils say the volume is started, some say not. If I try to manually start the glusterfsd, it doesn't complain, but also doesn't stay up. The distributed gluster init scripts don't work
22:10 crashmag joined #gluster
23:00 dbanck joined #gluster
23:01 dbanck I'm running 2 glusterfs 3.3 servers with a lot of replicated volumes. If one of the servers fails and comes back up, do I have to do anything to start selfhealing?
23:29 JoeJulian hjmangalam: Check the brick logs on the servers that are failing to stay up.
23:30 JoeJulian dbanck: Depends on whether or not anything changed while one of the servers was down. It /should/ happen automatically though.
23:32 dbanck There will be changed files for sure, but if it happens automatically I'll just sit and check if everything works
23:38 JoeJulian "gluster volume heal $volname info" should show the files that need healed. Once it's empty, you should be all caught up.

| Channels | #gluster index | Today | | Search | Google Search | Plain-Text | summary