#ceph IRC Log

Index

IRC Log for 2010-09-22

Timestamps are in GMT/BST.

[2:17] <yehudasa> wido: I updated the btrfs module on node08, there were two separate bugs there, seems to work better now
[2:17] <yehudasa> you can copy that module (from /lib/modules/..) to the rest of the nodes
[2:33] * monrad (~mmk@domitian.tdx.dk) has joined #ceph
[2:34] * monrad-51468 (~mmk@domitian.tdx.dk) Quit (Read error: Network is unreachable)
[2:53] * lidongyang (~lidongyan@222.126.194.154) Quit (Read error: Connection reset by peer)
[2:53] * lidongyang (~lidongyan@222.126.194.154) has joined #ceph
[3:11] * monrad (~mmk@domitian.tdx.dk) Quit (Quit: bla)
[3:12] * monrad-51468 (~mmk@domitian.tdx.dk) has joined #ceph
[3:14] * todinini (tuxadero@kudu.in-berlin.de) Quit (Remote host closed the connection)
[3:14] * todinini (tuxadero@kudu.in-berlin.de) has joined #ceph
[3:14] * darkfader (~floh@host-82-135-62-109.customer.m-online.net) Quit (Remote host closed the connection)
[3:19] * deksai (~deksai@96.35.100.192) Quit (Ping timeout: 480 seconds)
[3:30] * darkfader (~floh@host-82-135-62-109.customer.m-online.net) has joined #ceph
[5:17] * deksai (~deksai@96-35-100-192.dhcp.bycy.mi.charter.com) has joined #ceph
[5:48] * MarkN1 (~nathan@mail.zomojo.com) has joined #ceph
[5:48] * MarkN (~nathan@59.167.240.178) Quit (Read error: Connection reset by peer)
[6:09] * deksai (~deksai@96-35-100-192.dhcp.bycy.mi.charter.com) Quit (Ping timeout: 480 seconds)
[7:44] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) has joined #ceph
[7:51] * allsystemsarego (~allsystem@188.27.166.252) has joined #ceph
[8:05] * s15y (~s15y@sac91-2-88-163-166-69.fbx.proxad.net) Quit (Remote host closed the connection)
[8:05] * s15y (~s15y@sac91-2-88-163-166-69.fbx.proxad.net) has joined #ceph
[9:05] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)
[9:17] * f4m8_ is now known as f4m8
[10:04] * Yoric (~David@213.144.210.93) has joined #ceph
[15:06] * Yoric_ (~David@213.144.210.93) has joined #ceph
[15:06] * Yoric (~David@213.144.210.93) Quit (Read error: Connection reset by peer)
[15:06] * Yoric_ is now known as Yoric
[15:12] * Yoric (~David@213.144.210.93) Quit (Read error: Connection reset by peer)
[15:16] * Yoric (~David@213.144.210.93) has joined #ceph
[16:07] * f4m8 is now known as f4m8_
[17:08] <wido> yehudasa: thanks! Almost got all the OSD's back again
[17:35] * deksai (~deksai@dsl093-003-018.det1.dsl.speakeasy.net) has joined #ceph
[17:38] * deksai (~deksai@dsl093-003-018.det1.dsl.speakeasy.net) Quit (Remote host closed the connection)
[17:40] * deksai (~deksai@dsl093-003-018.det1.dsl.speakeasy.net) has joined #ceph
[17:43] * hijacker (~hijacker@213.91.163.5) Quit (Remote host closed the connection)
[17:49] * greglap (~Adium@166.205.137.103) has joined #ceph
[17:52] * deksai (~deksai@dsl093-003-018.det1.dsl.speakeasy.net) Quit (Ping timeout: 480 seconds)
[18:37] * greglap (~Adium@166.205.137.103) Quit (Quit: Leaving.)
[19:09] * deksai (~deksai@dsl093-003-018.det1.dsl.speakeasy.net) has joined #ceph
[19:32] * Yoric (~David@213.144.210.93) Quit (Quit: Yoric)
[19:48] * nolan (~nolan@phong.sigbus.net) Quit (Ping timeout: 480 seconds)
[20:09] * nolan (~nolan@phong.sigbus.net) has joined #ceph
[20:36] * cockroach (~stefan@dhcp-130-92-99-103.vpn.unibe.ch) has joined #ceph
[20:38] <cockroach> hey, small question: we're currently running lustre on a linux cluster and we'd like to get rid of it, thus i'm wondering, is ceph in a state where it would be a reasonably good idea to deploy it for non-mission-critical (but not entirely unimportant) data?
[20:41] <iggy> I think the answer is still no, but close
[20:42] <sagewk> yeah
[20:42] <iggy> iirc, sage said something about end of year target for having a release with some definition of stable
[20:42] <cockroach> hmm, how close?
[20:42] <cockroach> sweet
[20:43] <cockroach> in its current state, is there a risk of data loss? or just general instability?
[20:43] <sagewk> both, although we haven't seen much (any?) data loss of late.
[20:45] <cockroach> what about stability in a basic-things-don't-change way? could i create a ceph installation now and expect it to keep working once things get more evolved?
[20:46] <sagewk> yep!
[20:47] <iggy> there aren't going to be any more backward incompatible changes?
[20:47] <cockroach> nice. thanks for the answers, i guess it's going to take a couple of weeks/months until the new storage stuff is fully running anyway, so i guess we'll go with ceph and hope for the best :)
[20:48] <sagewk> iggy: none planned. so far everything has rolled forward (although no rolling backward!)
[20:48] <iggy> I will say this, sage and the guys are very responsive to issues
[21:06] <wido> I'm playing around with RADOS much more lately then with Ceph, had no data loss whatsoever
[21:07] <wido> some objects might be unavailable for a while when two OSD's crash (which both have a replica of the object)
[21:08] <wido> So you won't loose data, but it might be unavailable for some time
[21:12] <cockroach> ok, that sounds acceptable
[21:12] <iggy> make sure you're using the latest versions of stuff
[21:13] <iggy> wido found a btrfs bug that had already been fixed
[21:13] <cockroach> certainly. i saw that there are debian packages so it should be trivial to keep stuff updated.
[21:14] <iggy> kernel is important too
[21:14] <cockroach> hrm, so i guess debian stable (the upcoming one) is a bad idea?
[21:15] <iggy> unless all the btrfs stuff is being backported, you'll want something newer than 32
[21:15] <sagewk> cockroach: they picked an old kernel for squeeze :(
[21:15] <cockroach> (our cluster is a mixed gentoo/debian one, so we'll just use gentoo on those systems then)
[21:16] <iggy> I'm surprised more fixes aren't going back to 32... it's in ubuntu LTS, rhel6, squeeze, etc
[21:16] <iggy> it's going to be the new 2.6.18
[21:16] <cockroach> yep, the decision for .32 was a little ... unfortunate.
[22:15] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) has joined #ceph
[22:32] * nolan (~nolan@phong.sigbus.net) Quit (Ping timeout: 480 seconds)
[22:36] * nolan (~nolan@phong.sigbus.net) has joined #ceph
[22:43] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)
[22:44] * allsystemsarego (~allsystem@188.27.166.252) Quit (Quit: Leaving)
[23:35] * eternaleye (~eternaley@195.190.31.135) Quit (Quit: eternaleye)

These logs were automatically created by CephLogBot on irc.oftc.net using the Java IRC LogBot.