#ceph IRC Log

Index

IRC Log for 2010-07-18

Timestamps are in GMT/BST.

[0:02] * sakib (~sakib@94.153.116.52) has left #ceph
[0:08] * Guest59 (~bbigras@bas11-montreal02-1128530979.dsl.bell.ca) Quit (Ping timeout: 480 seconds)
[0:24] <todinini> now I get this 10.0.0.2:0/1756 >> 10.0.0.2:6789/0 pipe(0x1809810 sd=-1 pgs=0 cs=0 l=0).fault first fault
[0:27] <darkfader> oh, i had that a few times now
[0:27] <darkfader> one thinggy has broken
[0:27] <darkfader> mds or mon
[0:28] <todinini> thats form the mon, how did you get rid of it?
[0:30] <wido> hi
[0:31] <wido> IRC logs: http://irclogs.ceph.widodh.nl/
[0:31] <darkfader> i did kill all mds/mon and then they restarted all happily
[0:31] <wido> todinini: your mon's are down
[0:32] <wido> that's when you get that fault
[0:32] <darkfader> wido: why does a aptitude remove ceph also remove the btrfs-tools?
[0:32] <wido> don't know?
[0:32] <darkfader> ok :)
[0:32] <wido> it shouldn't
[0:32] <wido> well, i might know
[0:32] <darkfader> very confusing stuff
[0:32] <wido> since you did a install for Ceph, it depended on btrfs-tools
[0:33] * allsystemsarego (~allsystem@188.27.164.220) Quit (Quit: Leaving)
[0:33] <darkfader> ahh! and then it remembers that during uninstall? thats not so bad :)
[0:33] <wido> when you remove it, there is no longer a need for btrfs-tools, so aptitude removes it? apt-get only gives a warning
[0:33] <wido> you have to do apt-get autoremove to then remove packages which are no longer needed
[0:33] <darkfader> yeah it did, and not reinstall when i re-installed ceph
[0:33] <wido> ok
[0:33] <wido> i'm afk
[0:33] <wido> ttyl
[0:34] <darkfader> laters :)
[0:49] <darkfader> my fs is now smaller ^^
[0:49] <darkfader> the journal should not use space "inside" the fs, should it?
[0:53] * eternaleye (~quassel@184-76-53-210.war.clearwire-wmx.net) has joined #ceph
[1:01] <darkfader> i now also get the lease expire
[1:01] <darkfader> will have to check their clocks
[1:02] <darkfader> the vm's run on different hosts, so yeah, maybe they're off
[1:02] <darkfader> uh oh.
[1:02] <darkfader> they are.
[1:16] * seb_ (~seb@gut75-4-82-235-160-49.fbx.proxad.net) Quit (Remote host closed the connection)
[1:40] * greglap1 (~Adium@cpe-76-90-74-194.socal.res.rr.com) has joined #ceph
[1:42] <darkfader> 19037MB data from my rsync in the fs now and it's still eating
[1:42] <darkfader> i'm happy
[1:47] * greglap (~Adium@cpe-76-90-74-194.socal.res.rr.com) Quit (Ping timeout: 480 seconds)
[5:30] * bbigras (~bbigras@bas11-montreal02-1128535472.dsl.bell.ca) has joined #ceph
[5:31] * bbigras is now known as Guest126
[8:27] * allsystemsarego (~allsystem@188.27.164.220) has joined #ceph
[8:27] * Osso (osso@AMontsouris-755-1-9-31.w90-46.abo.wanadoo.fr) Quit (Quit: Osso)
[12:41] <todinini> if I do a /etc/init.d/ceph -a stop the script says it stops the mon's and mds's but they are still running, knows anybody this behaviour?
[12:44] <darkfader> yes!
[12:45] <darkfader> i made a script that i can use to do a full restart
[12:45] <darkfader> it does stop, pkill, wait, start i think
[12:46] <todinini> darkfader: ok, but I think the orignal script should do that
[12:46] <darkfader> yes
[12:46] <darkfader> and i think one of us needs to make a patch
[12:46] <darkfader> and i'm lazy ;p
[12:48] <darkfader> it has to do it, and also needs to avoid double starting the processes when run twice
[12:48] <darkfader> pid file handling is also very bad
[12:48] <darkfader> anyway, i need a break
[13:43] <darkfader> ah in the script it says "no pid file, daemon not running" *smile*
[13:43] <darkfader> but it's quite large
[16:54] * Osso_ (osso@AMontsouris-755-1-9-31.w90-46.abo.wanadoo.fr) has joined #ceph
[22:54] * allsystemsarego (~allsystem@188.27.164.220) Quit (Quit: Leaving)

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