#ceph IRC Log

Index

IRC Log for 2010-09-24

Timestamps are in GMT/BST.

[0:53] * Spudz76 (~spudz76@dc.gigenet.com) has joined #ceph
[0:54] <Spudz76> so I can't seem to get replication to work, I have a test setup with 3x 8GB OSDs and regardless what I try it always provides 24GB instead of 8GB triple mirrored
[0:54] <sagewk> the free space doesn't factor in replication
[0:54] <Spudz76> I saw some posts that seem to say data replication is off by default but how the heck to you turn it on
[0:54] <sagewk> you'll notice that 'used' will grow 3x as fast
[0:54] <Spudz76> ohh
[0:54] <sagewk> it's 2x by default
[0:54] <sagewk> er, grow 2x as fast :)
[0:54] <Spudz76> well then that makes more sense
[0:55] <Spudz76> too used to RAID and how it behaves
[0:56] <Spudz76> and then I don't see it moving data around after I change replication level but then again I didn't write anything to it either yet ;P
[0:57] <sagewk> that might explain it :)
[1:22] * jvasudeo (~Adium@70-35-37-146.static.wiline.com) has joined #ceph
[2:15] * jvasudeo (~Adium@70-35-37-146.static.wiline.com) Quit (Quit: Leaving.)
[2:29] * deksai (~deksai@96-35-100-192.dhcp.bycy.mi.charter.com) Quit (Ping timeout: 480 seconds)
[2:37] * greglap (~Adium@166.205.139.115) has joined #ceph
[2:54] * ptinsley (~ptinsley@99-0-36-187.lightspeed.mrbotn.sbcglobal.net) has joined #ceph
[2:58] * ptinsley (~ptinsley@99-0-36-187.lightspeed.mrbotn.sbcglobal.net) has left #ceph
[3:05] * greglap (~Adium@166.205.139.115) Quit (Ping timeout: 480 seconds)
[3:06] * greglap (~Adium@166.205.138.157) has joined #ceph
[3:26] * yehudasa_hm (~yehuda@adsl-69-225-137-176.dsl.irvnca.pacbell.net) Quit (Ping timeout: 480 seconds)
[3:27] * greglap (~Adium@166.205.138.157) Quit (Ping timeout: 480 seconds)
[3:32] * greglap (~Adium@cpe-76-90-74-194.socal.res.rr.com) has joined #ceph
[3:33] * greglap (~Adium@cpe-76-90-74-194.socal.res.rr.com) has left #ceph
[4:33] * deksai (~deksai@96-35-100-192.dhcp.bycy.mi.charter.com) has joined #ceph
[6:11] * jvasudeo (~Adium@adsl-69-236-160-101.dsl.pltn13.pacbell.net) has joined #ceph
[7:23] * jvasudeo (~Adium@adsl-69-236-160-101.dsl.pltn13.pacbell.net) Quit (Quit: Leaving.)
[7:29] * jvasudeo (~Adium@adsl-69-236-160-101.dsl.pltn13.pacbell.net) has joined #ceph
[7:35] * jvasudeo (~Adium@adsl-69-236-160-101.dsl.pltn13.pacbell.net) Quit (Quit: Leaving.)
[8:20] * lidongyang (~lidongyan@222.126.194.154) has joined #ceph
[8:33] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) has joined #ceph
[8:47] * allsystemsarego (~allsystem@188.27.166.252) has joined #ceph
[9:02] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)
[9:08] * MarkN1 (~nathan@mail.zomojo.com) Quit (Quit: Leaving.)
[10:55] * allsystemsarego (~allsystem@188.27.166.252) Quit (Quit: Leaving)
[11:13] * Yoric (~David@213.144.210.93) has joined #ceph
[12:54] * Yoric (~David@213.144.210.93) Quit (Remote host closed the connection)
[12:54] * Yoric (~David@213.144.210.93) has joined #ceph
[14:21] * deksai (~deksai@96-35-100-192.dhcp.bycy.mi.charter.com) Quit (Ping timeout: 480 seconds)
[14:32] * ghaskins_mobile (~ghaskins_@66-189-114-103.dhcp.oxfr.ma.charter.com) Quit (Quit: Leaving)
[14:53] * allsystemsarego (~allsystem@188.27.166.252) has joined #ceph
[16:00] * f4m8 is now known as f4m8_
[17:26] * deksai (~deksai@96-35-100-192.dhcp.bycy.mi.charter.com) has joined #ceph
[17:51] * Spudz76 (~spudz76@dc.gigenet.com) has left #ceph
[18:31] * jvasudeo (~Adium@70-35-37-146.static.wiline.com) has joined #ceph
[18:44] * jvasudeo (~Adium@70-35-37-146.static.wiline.com) has left #ceph
[18:49] * Yoric_ (~David@213.144.210.93) has joined #ceph
[18:49] * Yoric (~David@213.144.210.93) Quit (Read error: Connection reset by peer)
[18:49] * Yoric_ is now known as Yoric
[18:53] <wido> sagewk: you there yet?
[18:53] <sagewk> wido: yeah
[18:53] <wido> about the objects being 0 bytes in size, that's pretty weird
[18:53] <wido> are both the replicas 0 bytes or just one of them?
[18:53] <sagewk> yeah
[18:54] <sagewk> i assumed that was the only replica, but i didn't actually check
[18:55] <wido> Ok
[18:55] <sagewk> looking now
[18:57] <sagewk> btw it causes the recovery to stall, but restart the osd will get it going again (for a while) until it stalls again. doing that now so i can find another zeroed object
[18:58] <wido> The OSD's were restarted this morning since I build the latest unstable
[18:58] <sagewk> k
[19:02] <wido> i have to go afk for a while
[19:08] <sagewk> k
[20:36] * Yoric (~David@213.144.210.93) Quit (Quit: Yoric)
[20:58] * allsystemsarego (~allsystem@188.27.166.252) Quit (Quit: Leaving)
[22:00] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) has joined #ceph
[22:23] <wido> sagewk: just got a crash on osd7 in ReplicatedPG::sub_op_push(MOSDSubOp*), I assume this is due to the stalling objects?
[22:24] <wido> If so, i'll upload the cores etc to logger
[23:00] <sagewk> wido: pushed a fix
[23:04] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)
[23:08] <wido> sagewk: i'll try the fix this weekend and update the issue if something comes up
[23:08] <sagewk> k thanks
[23:16] <wido> sagewk: Just tested the fix, didn't work. Uploaded core.node08.16520 and core.node08.16052 to the logger machine
[23:17] <wido> i'm going afk
[23:17] <wido> tnx for now!
[23:18] <wido> i'll check if I can find some data corruption after these crashes
[23:18] <sagewk> ok thanks

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