#ceph IRC Log

Index

IRC Log for 2010-11-24

Timestamps are in GMT/BST.

[0:03] <jantje_> fyi, sagelap , dont know if you missed this
[0:03] <jantje_> 23:24 < jantje_> what's the issue? 13KB data on a new filesystem ?
[0:03] <jantje_> 23:27 < jantje_> I think I saw it before, and that it was replaying the journal when first started
[0:04] <jantje_> 23:27 < jantje_> or something like that
[0:05] <cmccabe> jantje: are you talking about issue #531 (Journaling Causes System Hang)
[0:14] * greglap (~Adium@ip-66-33-206-8.dreamhost.com) has joined #ceph
[0:14] * greglap1 (~Adium@ip-66-33-206-8.dreamhost.com) Quit (Read error: Connection reset by peer)
[0:16] * shdb (~shdb@217-162-231-62.dclient.hispeed.ch) has joined #ceph
[0:18] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)
[0:25] <gregaf> jantje: wido was talking about issue #538, and Sage's commit to fix it
[0:26] <gregaf> the small amount of data wasn't the problem :)
[0:27] <cmccabe> k
[0:39] * ajnelson (~Adium@soenat3.cse.ucsc.edu) has joined #ceph
[0:40] <jantje_> nevermind then :-)
[0:42] <gregaf> err, I meant 608, sorry, no idea how I got those backward
[0:42] <jantje_> for http://tracker.newdream.net/issues/584, i'm curious what results you get with iozone
[0:42] <jantje_> especially random read/write, both me and wido get MORE random WRITE than random read
[0:42] <jantje_> iozone -t 10 -s1G -i 0 -i 2 -i 8
[0:43] <jantje_> for example
[0:45] <gregaf> jantje_: that's a distinct possibility since random writes are usually caught up in the OSD journal (streaming writes instead of random writes), but reads have to go out to the main store (which makes random reads)
[0:45] * sagelap (~sage@ip-66-33-206-8.dreamhost.com) Quit (Quit: Leaving.)
[0:45] <jantje_> i see
[0:46] <jantje_> too bad my build performance is slower on 6 OSDs than on a single local harddisk :-)
[0:47] <jantje_> is there some way i can tell you guys where the bottleneck is?
[0:47] <jantje_> (except for the delay ofcoursE)
[0:48] <jantje_> anyway, i'm going to bed
[0:48] <jantje_> nite everyone
[1:01] * greglap1 (~Adium@ip-66-33-206-8.dreamhost.com) has joined #ceph
[1:01] * greglap (~Adium@ip-66-33-206-8.dreamhost.com) Quit (Read error: Connection reset by peer)
[1:07] * shdb (~shdb@217-162-231-62.dclient.hispeed.ch) Quit (Read error: Connection reset by peer)
[1:08] * shdb (~shdb@217-162-231-62.dclient.hispeed.ch) has joined #ceph
[1:17] * ajnelson (~Adium@soenat3.cse.ucsc.edu) Quit (Quit: Leaving.)
[1:19] * greglap1 (~Adium@ip-66-33-206-8.dreamhost.com) Quit (Quit: Leaving.)
[1:21] * allsystemsarego (~allsystem@188.26.32.15) Quit (Quit: Leaving)
[1:31] * pruby (~tim@leibniz.catalyst.net.nz) has joined #ceph
[1:38] * greglap (~Adium@166.205.138.242) has joined #ceph
[2:32] * greglap (~Adium@166.205.138.242) Quit (Read error: Connection reset by peer)
[2:43] * greglap (~Adium@cpe-76-90-74-194.socal.res.rr.com) has joined #ceph
[4:18] * lidongyang (~lidongyan@222.126.194.154) has joined #ceph
[5:56] * pruby (~tim@leibniz.catalyst.net.nz) Quit (Remote host closed the connection)
[6:42] * f4m8_ is now known as f4m8
[7:13] * lidongyang (~lidongyan@222.126.194.154) Quit (Remote host closed the connection)
[7:52] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) has joined #ceph
[8:52] * ajnelson (~Adium@dhcp-145-95.cruznetsecure.ucsc.edu) has joined #ceph
[9:10] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)
[9:34] * ajnelson (~Adium@dhcp-145-95.cruznetsecure.ucsc.edu) Quit (Quit: Leaving.)
[10:06] * eternaleye (~eternaley@195.215.30.181) Quit (synthon.oftc.net weber.oftc.net)
[10:06] * sage (~sage@dsl092-035-022.lax1.dsl.speakeasy.net) Quit (synthon.oftc.net weber.oftc.net)
[10:06] * gregaf (~Adium@ip-66-33-206-8.dreamhost.com) Quit (synthon.oftc.net weber.oftc.net)
[10:06] * NoahWatkins (~jayhawk@kyoto.soe.ucsc.edu) Quit (synthon.oftc.net weber.oftc.net)
[10:06] * LW_ (~jkreger@rrcs-98-101-117-50.midsouth.biz.rr.com) Quit (synthon.oftc.net weber.oftc.net)
[10:11] * eternaleye (~eternaley@195.215.30.181) has joined #ceph
[10:11] * sage (~sage@dsl092-035-022.lax1.dsl.speakeasy.net) has joined #ceph
[10:11] * gregaf (~Adium@ip-66-33-206-8.dreamhost.com) has joined #ceph
[10:11] * NoahWatkins (~jayhawk@kyoto.soe.ucsc.edu) has joined #ceph
[10:11] * LW_ (~jkreger@rrcs-98-101-117-50.midsouth.biz.rr.com) has joined #ceph
[10:19] * allsystemsarego (~allsystem@188.26.32.15) has joined #ceph
[10:57] * Yoric (~David@213.144.210.93) has joined #ceph
[11:57] * sig (~sig@c-67-169-42-1.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[12:28] * sig (~sig@c-67-169-42-1.hsd1.ca.comcast.net) has joined #ceph
[14:15] * sentinel_e86 (~sentinel_@188.226.51.71) has joined #ceph
[14:47] * hijacker (~hijacker@213.91.163.5) Quit (Quit: Leaving)
[15:15] * hijacker (~hijacker@213.91.163.5) has joined #ceph
[15:46] * f4m8 is now known as f4m8_
[15:53] * gregorg (~Greg@78.155.152.6) Quit (Read error: Connection reset by peer)
[15:53] * gregorg (~Greg@78.155.152.6) has joined #ceph
[16:24] * jantje_ (~jan@paranoid.nl) Quit (reticulum.oftc.net kinetic.oftc.net)
[16:24] * failboat (~stingray@stingr.net) Quit (reticulum.oftc.net kinetic.oftc.net)
[16:24] * jantje_ (~jan@paranoid.nl) has joined #ceph
[16:24] * failboat (~stingray@stingr.net) has joined #ceph
[17:31] * ajnelson (~Adium@dhcp-145-95.cruznetsecure.ucsc.edu) has joined #ceph
[17:31] * greglap (~Adium@cpe-76-90-74-194.socal.res.rr.com) Quit (Quit: Leaving.)
[17:34] * ajnelson (~Adium@dhcp-145-95.cruznetsecure.ucsc.edu) Quit ()
[17:51] * greglap (~Adium@166.205.136.178) has joined #ceph
[18:28] <greglap> wido: for #611, was this one of the osds that was down before the upgrade?
[18:30] <wido> greglap: No, not that I know, all OSD's were online this morning
[18:30] <wido> Oh no, I'm sure it was up
[18:30] <wido> I had some issues with recovering, thise morning only 3 objects were degraded
[18:30] <greglap> okay
[18:31] <wido> bummer? ;)
[18:31] <greglap> no, I'm just trying to get some context
[18:31] <wido> ok
[18:31] <greglap> Sage made some changes to how the messenger works in the OSDs that got merged yesterday, but I don't think it should have impacted this
[18:33] <wido> ok, if there is anything I can do, let me know!
[18:35] <greglap> I will :)
[18:37] * morse (~morse@supercomputing.univpm.it) Quit (Remote host closed the connection)
[18:48] * greglap (~Adium@166.205.136.178) Quit (Ping timeout: 480 seconds)
[18:55] * Yoric (~David@213.144.210.93) Quit (Quit: Yoric)
[18:56] * morse (~morse@supercomputing.univpm.it) has joined #ceph
[19:01] * greglap (~Adium@ip-66-33-206-8.dreamhost.com) has joined #ceph
[19:17] * greglap1 (~Adium@ip-66-33-206-8.dreamhost.com) has joined #ceph
[19:17] * greglap (~Adium@ip-66-33-206-8.dreamhost.com) Quit (Read error: Connection reset by peer)
[19:35] * sjust (~sam@ip-66-33-206-8.dreamhost.com) has joined #ceph
[19:57] * sagephone (~yaaic@32.173.163.156) has joined #ceph
[19:59] * sagephone (~yaaic@32.173.163.156) Quit ()
[20:57] <wido> is it correct that RBD's current version is 1.3?
[20:57] <wido> The Wiki still tells activate 1.2, but has 0.23.1 also RBD 1.3 or still 1.2?
[20:57] <wido> Wiki: http://ceph.newdream.net/wiki/Rbd#Loading_RBD
[20:58] <yehudasa> wido: I fixed a few issues with the class
[20:58] <yehudasa> and bumped up the version
[20:59] <yehudasa> you can still use v1.2, but it has some bugs with snapshots removal
[21:01] <wido> yehudasa: Ok, but the Wiki has to state 1.3 then? Just for the new people, who try to use RBD
[21:05] * greglap (~Adium@ip-66-33-206-8.dreamhost.com) has joined #ceph
[21:05] * greglap1 (~Adium@ip-66-33-206-8.dreamhost.com) Quit (Read error: Connection reset by peer)
[21:40] * pruby (~tim@leibniz.catalyst.net.nz) has joined #ceph
[22:06] * Meths_ (rift@91.106.141.66) has joined #ceph
[22:13] * Meths (rift@91.106.208.45) Quit (Ping timeout: 480 seconds)
[22:57] * greglap1 (~Adium@ip-66-33-206-8.dreamhost.com) has joined #ceph
[22:57] * greglap (~Adium@ip-66-33-206-8.dreamhost.com) Quit (Read error: Connection reset by peer)
[22:58] * greglap1 (~Adium@ip-66-33-206-8.dreamhost.com) Quit ()
[23:06] * allsystemsarego (~allsystem@188.26.32.15) Quit (Quit: Leaving)
[23:18] * ijuz__ (~ijuz@p4FFF7D59.dip.t-dialin.net) has joined #ceph
[23:19] * greglap (~Adium@166.205.139.47) has joined #ceph
[23:42] * Meths_ is now known as Meths
[23:54] <sig> Where does rbd come from? Was it created soley for ceph?
[23:55] <greglap> sig: rbd is a comparatively wrapper around RADOS
[23:56] <greglap> RADOS was built for Ceph
[23:56] <greglap> rbd was written since people seemed interested in it
[23:57] <sig> Interesting
[23:58] <sig> I will research rados. Looks like it made it upstream in >=2.6.37

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