#ceph IRC Log

Index

IRC Log for 2012-01-04

Timestamps are in GMT/BST.

[0:00] * aliguori (~anthony@32.97.110.59) Quit (Read error: Operation timed out)
[0:04] * lx0 (~aoliva@lxo.user.oftc.net) Quit (Remote host closed the connection)
[0:04] * lx0 (~aoliva@lxo.user.oftc.net) has joined #ceph
[0:33] <nhm> hrm... seems some other people have gotten bus errors in git due to insane amounts of recursion blowing out the stack. Wonder if it could be something similar.
[0:34] <dwm_> nhm: Don't have this problem when the process is operating on bit-wise identical copies on an NFS mount or local disk.
[0:35] <nhm> dwm_: ah, just when git is on ceph?
[0:35] <dwm_> nhm: Yes.
[0:36] <dwm_> It's not just a `git gc` run, though that's a good test-case; I've had git fetches fail consistently, too.
[0:37] <nhm> dwm_: ok, so probably not a hardware problem either. un-aligned memory access?
[0:40] <nhm> hrm... mmap maybe?
[1:05] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) has joined #ceph
[1:54] * lx0 (~aoliva@lxo.user.oftc.net) Quit (Remote host closed the connection)
[1:59] * lx0 (~aoliva@lxo.user.oftc.net) has joined #ceph
[2:19] * jojy (~jvarghese@108.60.121.114) Quit (Quit: jojy)
[2:28] * lx0 (~aoliva@lxo.user.oftc.net) Quit (Remote host closed the connection)
[2:29] * lx0 (~aoliva@lxo.user.oftc.net) has joined #ceph
[2:47] * bchrisman (~Adium@108.60.121.114) Quit (Quit: Leaving.)
[3:05] * joshd (~joshd@aon.hq.newdream.net) Quit (Quit: Leaving.)
[4:04] * yoshi (~yoshi@p9224-ipngn1601marunouchi.tokyo.ocn.ne.jp) has joined #ceph
[5:39] * elder (~elder@c-71-193-71-178.hsd1.mn.comcast.net) Quit (Quit: Leaving)
[8:00] * bchrisman (~Adium@c-76-103-130-94.hsd1.ca.comcast.net) has joined #ceph
[8:13] * s[X] (~sX]@eth589.qld.adsl.internode.on.net) Quit (Remote host closed the connection)
[8:41] * tjikkun (~tjikkun@82-169-255-84.ip.telfort.nl) Quit (Remote host closed the connection)
[8:44] * tjikkun (~tjikkun@2001:7b8:356:0:225:22ff:fed2:9f1f) has joined #ceph
[9:11] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[9:19] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Ping timeout: 480 seconds)
[9:23] * BManojlovic (~steki@93-87-148-183.dynamic.isp.telekom.rs) has joined #ceph
[9:23] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[9:31] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Ping timeout: 480 seconds)
[9:35] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[10:02] * yoshi (~yoshi@p9224-ipngn1601marunouchi.tokyo.ocn.ne.jp) Quit (Remote host closed the connection)
[10:07] * fghaas (~florian@85-127-155-32.dynamic.xdsl-line.inode.at) has joined #ceph
[12:22] <dwm_> nhm: Just raising a new bug with some additional details for that `git gc` bus error test-case.
[12:22] <dwm_> (This time, I actually have non-default OSD logging enabled..)
[12:28] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[12:28] <dwm_> Okay, that's bug #1847. Should hopefully be pretty trivial to reproduce, assuming I'm not doing something odd or stupid.
[12:56] * BManojlovic (~steki@93-87-148-183.dynamic.isp.telekom.rs) Quit (Remote host closed the connection)
[13:11] * BManojlovic (~steki@93-87-148-183.dynamic.isp.telekom.rs) has joined #ceph
[14:08] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[14:09] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[14:27] <wonko_be> anyone willing to help me getting qemu-rbd up and running? I must be missing some obvious stuff here... (kvm is complaining about the type"network" in my disk definition)
[14:32] * lx0 (~aoliva@lxo.user.oftc.net) Quit (Remote host closed the connection)
[14:32] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[14:33] <wonko_be> never mind, my kvm setup is completely broken
[14:33] <wonko_be> let me get that back first
[14:33] * lx0 (~aoliva@lxo.user.oftc.net) has joined #ceph
[14:42] * elder (~elder@c-71-193-71-178.hsd1.mn.comcast.net) has joined #ceph
[15:00] * aliguori (~anthony@cpe-70-123-132-139.austin.res.rr.com) has joined #ceph
[16:27] <todin> wonko_be: you still have a prob with qemu-rbd?
[17:16] * bchrisman (~Adium@c-76-103-130-94.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[17:19] * bchrisman (~Adium@c-76-103-130-94.hsd1.ca.comcast.net) has joined #ceph
[17:21] <wido> is it still vacation in the US?
[17:22] <wido> wonko_be: Make sure you have a recent version of libvirt
[17:22] <wido> the network type is pretty new
[17:23] * aliguori (~anthony@cpe-70-123-132-139.austin.res.rr.com) Quit (Remote host closed the connection)
[17:36] * aliguori (~anthony@cpe-70-123-132-139.austin.res.rr.com) has joined #ceph
[17:39] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) has joined #ceph
[17:39] <wonko_be> yeah, got to the point that type="network" and friends are working
[17:40] <wonko_be> (was indeed an old version on the testbox)
[17:40] <wonko_be> i'll toy with either this evening or tomorrow
[17:41] <wonko_be> some real work first
[17:41] * bchrisman (~Adium@c-76-103-130-94.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[18:03] <nhm> wido: most people are off vacation now
[18:11] * BManojlovic (~steki@93-87-148-183.dynamic.isp.telekom.rs) Quit (Quit: Ja odoh a vi sta 'ocete...)
[18:24] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[18:24] * fronlius (~fronlius@testing78.jimdo-server.com) has joined #ceph
[18:28] * lx0 (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[18:30] <gregaf> wido: nhm: actually we're mostly back now, although sam and tv took some extra time
[18:33] <nhm> gregaf: oops, I meant we are no longer on vacation in the US. :)
[18:33] <nhm> gregaf: in the general sense...
[18:36] <lxo> learned the hard way last night that a set_layout on a symlink makes ceph.ko go kaboom. known issue?
[18:36] <lxo> (3.1.6)
[18:39] <gregaf> lxo: nope, not known
[18:41] <lxo> tks, will report
[18:43] <lxo> also, it seems like ceph.ko won't set times/ownership info on symlinks. as in, rsyncing -a symlinkpool/ /mnt/ceph.ko/ doesn't copy time info, whereas to /mnt/cfuse/ it does
[18:44] <gregaf> hrm, dunno
[18:44] <gregaf> they're independent code bases so it's possible
[18:52] * joshd (~joshd@aon.hq.newdream.net) has joined #ceph
[18:55] * bchrisman (~Adium@108.60.121.114) has joined #ceph
[19:50] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) Quit (Quit: Leaving)
[20:13] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) has joined #ceph
[20:32] * fronlius (~fronlius@testing78.jimdo-server.com) Quit (Quit: fronlius)
[21:13] * nhm_ (~nh@68.168.168.19) has joined #ceph
[21:13] * nhm (~nh@68.168.168.19) Quit (Read error: Connection reset by peer)
[21:14] * fronlius (~fronlius@d217032.adsl.hansenet.de) has joined #ceph
[21:17] <wonko_be> anyone has an example on how I should add the auth stuff in my libvirt .xml definitions?
[21:32] <wonko_be> or any idea why this pops up: qemu: could not open disk image rbd:data/timemachine:conf=/etc/ceph/ceph.conf:id=admin:secret=...
[21:33] <joshd> wonko_be: maybe a permissions issue with /etc/ceph/ceph.conf?
[21:34] <joshd> apparmor might be blocking qemu from reading it
[21:34] <wonko_be> its debian, no apparmor there, and the permissions look okay
[21:35] <joshd> what's the error at the end of 'could not open disk image'?
[21:36] <wonko_be> No such file or directory
[21:37] <wonko_be> some info on this: http://pastie.org/3127053
[21:37] <joshd> does 'rbd info data/timemachine' work?
[21:38] <wonko_be> ah, that doesnt work, without the "data/" it does however
[21:38] <wonko_be> let me give that a spin
[21:39] <wonko_be> nope, still the same
[21:39] <wonko_be> error: internal error process exited while connecting to monitor: qemu: could not open disk image rbd:timemachine:conf=/etc/ceph/ceph.conf:id=admin:secret=AQDk2AFPQBzBFBAArzUR8g2G8BDW+XH19vZBaA==: No such file or directory
[21:39] <joshd> the data/ bit specifies the pool
[21:40] <joshd> by default rbd images are in the 'rbd' pool
[21:40] <joshd> so rbd:rbd/timemachine... should work
[21:40] <wonko_be> ah, so rbd/timemachine should be the correct one
[21:40] <joshd> yeah
[21:41] <wonko_be> sorry, no go
[21:41] * jojy (~jvarghese@108.60.121.114) has joined #ceph
[21:41] <wonko_be> still the same
[21:42] <wonko_be> what should be on the kvm machine? i've put librados and librbd on it, installed libvirt and then git cloned the qemu-rbd repo from github
[21:42] <wonko_be> compiled it with --enable-rbd
[21:42] <joshd> that should be enough
[21:42] <wonko_be> do i need some other rbd-related tools on the kvm-machine?
[21:43] <wonko_be> can i test the image with qemu-img somehow?
[21:43] <joshd> try adding debug_auth=10:debug_objecter=10:debug_ms=1:log_to_stderr=true
[21:45] <joshd> you can try 'qemu-img info -f rbd rbd:rbd/timemachine...'
[21:46] <wonko_be> aha, qemu-img: invalid conf option secret
[21:47] <joshd> oh, right, I always get that confused too
[21:47] <joshd> should be key= instead
[21:47] <wonko_be> what should it be? pass? key?
[21:47] <wonko_be> okay
[21:47] <joshd> the xml way to do it has an example at http://libvirt.org/formatdomain.html#elementsDisks
[21:47] <wonko_be> aha, this is better: file format: rbd
[21:47] <wonko_be> virtual size: 5.0T (5497558138880 bytes)
[21:48] <wonko_be> lets try to spin up this machine
[21:48] <joshd> you have to add the secret to libvirt too (http://libvirt.org/formatsecret.html)
[21:51] <wonko_be> caramba, still no luck, let me read those links first
[21:53] <joshd> ah, here's a full example:http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/4674
[21:55] <wonko_be> ah, that is indeed a lot better for a kvm-noob like me
[21:59] <wonko_be> "error: XML error: unknown secret usage type ceph" - that would say "your libvirt version is too low?
[22:00] <joshd> yeah, needs at least 0.9.7
[22:01] <wonko_be> 0.9.2 here, let me get that fixed first
[22:23] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[22:36] * MarkN (~nathan@142.208.70.115.static.exetel.com.au) has joined #ceph
[22:36] * MarkN (~nathan@142.208.70.115.static.exetel.com.au) has left #ceph
[22:37] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[22:38] <wonko_be> joshd: thanks for the help, no luck yet (libvirt-bin is giving me issues), but it got me well on the way
[22:41] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Ping timeout: 480 seconds)
[22:41] <joshd> wonko_be: you're welcome :)
[22:42] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[23:04] * s[X] (~sX]@eth589.qld.adsl.internode.on.net) has joined #ceph
[23:07] <wido> wonko_be: feel free to contact me!
[23:47] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[23:57] * fghaas (~florian@85-127-155-32.dynamic.xdsl-line.inode.at) Quit (Ping timeout: 480 seconds)

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