#ceph IRC Log

Index

IRC Log for 2012-05-07

Timestamps are in GMT/BST.

[0:13] * lofejndif (~lsqavnbok@04ZAAC2PR.tor-irc.dnsbl.oftc.net) has joined #ceph
[0:25] * pruby (~tim@leibniz.catalyst.net.nz) has joined #ceph
[0:31] * BManojlovic (~steki@212.200.243.246) Quit (Ping timeout: 480 seconds)
[1:33] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) Quit (Quit: Leaving)
[1:56] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) Quit (Ping timeout: 480 seconds)
[2:19] * lxo (~aoliva@lxo.user.oftc.net) Quit (Read error: Connection reset by peer)
[2:28] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[2:37] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[2:39] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[2:44] * Ryan_Lane (~Adium@c-98-210-205-93.hsd1.ca.comcast.net) has joined #ceph
[3:35] * lofejndif (~lsqavnbok@04ZAAC2PR.tor-irc.dnsbl.oftc.net) Quit (Quit: gone)
[3:57] * asadpanda (~asadpanda@67.231.236.80) Quit (Ping timeout: 480 seconds)
[4:14] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[6:28] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[6:43] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[8:04] * aa_ (~aa@r190-135-11-154.dialup.adsl.anteldata.net.uy) has joined #ceph
[8:05] * renzhi (~renzhi@180.169.73.90) has joined #ceph
[8:10] * andresambrois (~aa@r190-135-37-155.dialup.adsl.anteldata.net.uy) Quit (Ping timeout: 480 seconds)
[8:40] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) has joined #ceph
[9:15] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[9:28] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[9:33] * Theuni (~Theuni@195.62.106.100) has joined #ceph
[9:43] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[9:43] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[9:52] * verwilst (~verwilst@d5152FEFB.static.telenet.be) has joined #ceph
[10:00] * aa_ (~aa@r190-135-11-154.dialup.adsl.anteldata.net.uy) Quit (Ping timeout: 480 seconds)
[10:11] * s[X] (~sX]@49.178.1.51) has joined #ceph
[10:16] * s[X] (~sX]@49.178.1.51) Quit (Remote host closed the connection)
[10:28] * s[X]_ (~sX]@49.178.3.225) has joined #ceph
[10:33] * s[X]_ (~sX]@49.178.3.225) Quit (Remote host closed the connection)
[11:18] * Ryan_Lane (~Adium@c-98-210-205-93.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[11:32] * john_ (~john@p54A30B46.dip0.t-ipconnect.de) has joined #ceph
[11:32] <john_> hi
[11:33] * john_ is now known as S0NiC
[11:33] <S0NiC> so
[11:33] <S0NiC> ;)
[11:34] <S0NiC> http://ceph.com/docs/master/ops/install/mkcephfs/ i installed ceph descriped in the doku. but i got no response if i do ceph -k mycluster.keyring -c mycluster.conf health. i can ssh into all servers. any ideas?
[11:45] <S0NiC> i got it...forget to start service ;??(
[11:52] * oliver1 (~oliver@p4FFFE38D.dip.t-dialin.net) has joined #ceph
[12:01] * brambles (brambles@79.133.200.49) Quit (Quit: leaving)
[12:02] * brambles (brambles@79.133.200.49) has joined #ceph
[12:11] * Theuni (~Theuni@195.62.106.100) Quit (Ping timeout: 480 seconds)
[12:14] * Theuni (~Theuni@195.62.106.100) has joined #ceph
[12:35] * nhorman (~nhorman@99.127.245.201) has joined #ceph
[12:36] * s[X]_ (~sX]@60-241-151-10.tpgi.com.au) has joined #ceph
[12:36] * s[X]_ (~sX]@60-241-151-10.tpgi.com.au) Quit (Remote host closed the connection)
[12:48] * s[X]_ (~sX]@60-241-151-10.tpgi.com.au) has joined #ceph
[12:50] * s[X]_ (~sX]@60-241-151-10.tpgi.com.au) Quit (Remote host closed the connection)
[12:53] * s[X]_ (~sX]@60-241-151-10.tpgi.com.au) has joined #ceph
[13:16] * renzhi (~renzhi@180.169.73.90) Quit (Quit: Leaving)
[13:58] * jefferai (~quassel@quassel.jefferai.org) Quit (Read error: Connection reset by peer)
[13:58] * jefferai (~quassel@quassel.jefferai.org) has joined #ceph
[14:02] <nhm> grr, I wish I could sleep later.
[14:03] <nhm> anyway, good morning #ceph. :)
[14:06] * mtk (~mtk@ool-44c35967.dyn.optonline.net) has joined #ceph
[14:16] <S0NiC> good morning...
[14:43] * Theuni (~Theuni@195.62.106.100) Quit (Ping timeout: 480 seconds)
[14:55] * aliguori (~anthony@12.177.253.250) has joined #ceph
[14:57] * Theuni (~Theuni@195.62.106.110) has joined #ceph
[15:02] * aliguori (~anthony@12.177.253.250) Quit (Remote host closed the connection)
[15:19] * DLange is now known as Guest889
[15:19] * DLange (~DLange@dlange.user.oftc.net) has joined #ceph
[15:21] * Guest889 (~DLange@dlange.user.oftc.net) Quit (Ping timeout: 480 seconds)
[15:58] * Theuni (~Theuni@195.62.106.110) Quit (Quit: Leaving.)
[15:59] * Kioob (~kioob@luuna.daevel.fr) Quit (Remote host closed the connection)
[16:04] * BManojlovic (~steki@91.195.39.5) has joined #ceph
[16:29] * verwilst (~verwilst@d5152FEFB.static.telenet.be) Quit (Quit: Ex-Chat)
[16:30] * s[X]_ (~sX]@60-241-151-10.tpgi.com.au) Quit (Remote host closed the connection)
[16:30] * turtle (~turtle@213.61.32.212) has joined #ceph
[16:30] <turtle> hey folks
[16:31] <turtle> anyone knows how to mount cephfs via fstab?
[16:31] <turtle> with fuse?
[16:31] <turtle> ceph-fuse#10.10.0.11:6789:/ /cephfs fuse defaults 0 0
[16:31] <turtle> tells me
[16:32] <turtle> srv1:/# mount -a
[16:32] <turtle> ceph-fuse[15679]: starting ceph client
[16:32] <turtle> ceph-fuse[15679]: starting fuse
[16:32] <turtle> fuse: bad mount point `10.10.0.11:6789:/': No such file or directory
[16:32] <turtle> ceph-fuse[15679]: fuse finished with error 22
[16:32] <turtle> 2012-05-07 16:31:53.105858 7f5b68ac9780 -1 fuse_parse_cmdline failed.
[16:32] <turtle> ceph-fuse[15677]: mount failed: (22) Invalid argument
[16:32] <turtle> while mounting it over command line works fine
[16:33] <turtle> ceph-fuse -m 10.10.0.11:6789 /cephfs/
[16:33] <turtle> any ideas?
[16:56] * aliguori (~anthony@12.177.253.250) has joined #ceph
[17:04] * BManojlovic (~steki@91.195.39.5) Quit (Quit: Ja odoh a vi sta 'ocete...)
[17:23] * aliguori (~anthony@12.177.253.250) Quit (Remote host closed the connection)
[17:26] * oliver1 (~oliver@p4FFFE38D.dip.t-dialin.net) has left #ceph
[17:38] * bchrisman (~Adium@c-76-103-130-94.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[17:42] * aa_ (~aa@r190-135-11-154.dialup.adsl.anteldata.net.uy) has joined #ceph
[17:54] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) Quit (Ping timeout: 480 seconds)
[17:57] * Tv_ (~tv@aon.hq.newdream.net) has joined #ceph
[18:03] * Tv_ (~tv@aon.hq.newdream.net) Quit (Quit: Tv_)
[18:04] * Tv_ (~tv@aon.hq.newdream.net) has joined #ceph
[18:04] * BManojlovic (~steki@212.200.243.232) has joined #ceph
[18:04] * Tv_ (~tv@aon.hq.newdream.net) Quit ()
[18:07] * CristianDM (~CristianD@host217.190-230-240.telecom.net.ar) has joined #ceph
[18:07] <CristianDM> Hi. Any guide to use ceph form openstack?
[18:07] <CristianDM> I build a ceph cluster but I don??t know how use it from openstack
[18:11] * asadpanda (~asadpanda@67.231.236.80) has joined #ceph
[18:21] <yehudasa> CristianDM: as a block storage or as an object storage?
[18:23] * Tv_ (~tv@aon.hq.newdream.net) has joined #ceph
[18:26] * Theuni (~Theuni@46.253.59.219) has joined #ceph
[18:28] * aa_ (~aa@r190-135-11-154.dialup.adsl.anteldata.net.uy) Quit (Remote host closed the connection)
[18:28] <CristianDM> block storage. I need to use for store the vm
[18:46] * mgalkiewicz (~mgalkiewi@85.89.186.247) has joined #ceph
[18:47] <mgalkiewicz> sage: hi
[18:47] <mgalkiewicz> sagewk: hi
[18:47] <sagewk> hey
[18:47] <mgalkiewicz> I am not sure how to find core file
[18:48] <sagewk> usually in /?
[18:48] <sagewk> or not there at all.. ulimit -c is usually none by default
[18:49] <mgalkiewicz> I have it in /
[18:49] <mgalkiewicz> installing gdb
[18:49] <sagewk> if you're using ceph debs, install ceph-dbg too so you get debug symbols
[18:49] <sagewk> brb
[18:50] <mgalkiewicz> ceph-dbg installed as well
[18:53] <yehudasa> CristainDM: basically you need to create rbd image. I'm not too familiar with how the openstack integration works
[18:54] <yehudasa> Tv_: do you have some info about how to set up nova with rbd?
[18:56] <sagewk> mgalkiewicz: can you pastebin the bt when you get it?
[18:56] <mgalkiewicz> yes
[18:56] * bchrisman (~Adium@108.60.121.114) has joined #ceph
[18:58] <mgalkiewicz> http://pastie.org/3874340
[19:02] <sagewk> mgalkiewicz: is it reproducible?
[19:03] <sagewk> f 8
[19:03] <sagewk> p i
[19:04] <Tv_> yehuda: not really, sorry
[19:05] <Tv_> yehuda: josh is the guy who's had hands-on on the actual admin side; i've looked at the code but that doesn't mean i know how to use it ;)
[19:05] <mgalkiewicz> sagewk: I could not start this mon at all so I can reproduce this in my cluster
[19:06] <sagewk> mgalkiewicz: can you add debug paxos = 20 to your [mon] section and restart, and stick the logs somewhere
[19:07] <mgalkiewicz> sure
[19:07] * chutzpah (~chutz@216.174.109.254) has joined #ceph
[19:07] * joshd (~joshd@aon.hq.newdream.net) has joined #ceph
[19:08] <mgalkiewicz> http://pastie.org/3874405
[19:09] <sagewk> mgalkiewicz: ah, i see the problem.. thanks!
[19:10] <sagewk> as this cluster just upgraded?
[19:10] <sagewk> *was
[19:12] * dmick (~dmick@aon.hq.newdream.net) has joined #ceph
[19:13] <sagewk> mgalkiewicz: can you post output of find /path/to/mon/pgmap -ls ?
[19:13] <mgalkiewicz> sagewk: no only affected monitor was upgraded
[19:13] <mgalkiewicz> but it worked the same with older version 0.44
[19:17] * cattelan_away is now known as cattelan
[19:18] * favn (~avati@c-24-6-100-38.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[19:18] <mgalkiewicz> sagewk: https://gist.github.com/2629059
[19:21] * The_Bishop (~bishop@cable-86-56-102-91.cust.telecolumbus.net) Quit (Quit: Wer zum Teufel ist dieser Peer? Wenn ich den erwische dann werde ich ihm mal die Verbindung resetten!)
[19:22] <mgalkiewicz> sagewk: I will also really appreciate looking into http://tracker.newdream.net/issues/2346
[19:22] <mgalkiewicz> sagewk: it is a huge pain in the ass and caused data loss
[19:28] <sagewk> sure
[19:28] * favn (~avati@209.132.181.86) has joined #ceph
[19:30] <mgalkiewicz> thx
[19:31] <joshd> CristianDM: to use rbd with openstack, add 'volume_driver=nova.volume.driver.RBDDriver' to your nova.conf
[19:31] <sagewk> mgalkiewicz: what does last_committed, first_committed, last_consumed contain? and can you pastebin 'hexdump -C latest | head'?
[19:32] <mgalkiewicz> sec
[19:33] <joshd> CristianDM: if you're using cephx you can upload the secret to libvirt, then add nova settings for 'rbd_user', 'rbd_pool', and 'rbd_secret_uuid'
[19:36] <mgalkiewicz> sagewk: http://pastie.org/3874526
[19:37] * aa (~aa@r200-40-114-26.ae-static.anteldata.net.uy) has joined #ceph
[19:40] <sagewk> 'echo 1 > .../pgmap/slurping' should fix it. not clear to me how that was missed unless it is an upgrade issue
[19:42] * joshd (~joshd@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[19:42] <mgalkiewicz> it works
[19:43] <mgalkiewicz> The problem appeared some time after upgrade to 0.44 so I guess the upgrade was successful
[19:47] <mgalkiewicz> sagewk: thx!
[19:47] <sagewk> are you completely certain that that ceph-mon was up and healthy running v0.44 prior to it breaking? maybe it didn't start after the upgrade or something?
[19:48] <mgalkiewicz> I will check logs
[19:49] <mgalkiewicz> I dont have enough of them
[19:49] <mgalkiewicz> I am not 100% sure but I think that ceph was restarted after the upgrade
[19:53] * joshd (~joshd@p4FFFE38D.dip.t-dialin.net) has joined #ceph
[19:59] <CristianDM> Thanks.
[19:59] <CristianDM> I will tey
[19:59] <CristianDM> try
[20:00] <CristianDM> Another doubt. I build a cluster and kill all server last one.
[20:00] <CristianDM> I run ceph health
[20:02] * Ryan_Lane (~Adium@216.38.130.166) has joined #ceph
[20:03] * CristianDM (~CristianD@host217.190-230-240.telecom.net.ar) Quit (Read error: Connection reset by peer)
[20:03] * CristianDM (~CristianD@host217.190-230-240.telecom.net.ar) has joined #ceph
[20:06] <CristianDM> Any idea why? Is normal?
[20:07] * favn (~avati@209.132.181.86) Quit (Quit: leaving)
[20:07] <sagewk> mgalkiewicz: thanks. the slurping flag was added in 0.42; not seeing any way it would be broken :/
[20:08] <joshd> CristianDM: normally osds report each other as failed if they fail to send heartbeats. there's a longer timeout (I think 15 minutes by default) before the monitors will notice if all the osds are gone (since no osds are around to report everyone as faild)
[20:09] <joshd> failed, even
[20:09] <CristianDM> Ahh ok.
[20:09] <CristianDM> I run the command for hours but I don??t wait first 15 minutes.
[20:09] <CristianDM> I will run again and wait 1 hour
[20:11] <CristianDM> joshd, have any tutorial to setup openstack? How I can upload the secret to libvirt?
[20:12] <CristianDM> I check the docs http://ceph.com/docs/master/ops/manage/pool/ but I can??t find how create a pool
[20:14] <joshd> pool creation is the same as for the glance backend, described at the end of this section: http://glance.openstack.org/configuring.html#configuring-the-rbd-storage-backend
[20:16] <joshd> the keyring file is text, and will show you the secret you need to upload to libvirt
[20:16] <CristianDM> But first I need to create the pool in ceph?
[20:16] * The_Bishop (~bishop@p4FCDFDB1.dip.t-dialin.net) has joined #ceph
[20:16] <CristianDM> Or this is automatically created by openstack?
[20:17] <joshd> openstack doesn't do anything to ceph pools, you have to create them (or use the existing ones)
[20:21] <joshd> by default you'll already have an rbd pool
[20:21] <joshd> you can just create a rados user who can only access that pool
[20:28] <joshd> you create a secret in libvirt by doing 'virsh secret-define secret.xml', where secret.xml is something like http://pastie.org/3874729
[20:29] <joshd> it'll output the uuid of the secret
[20:30] <CristianDM> Thanks. I will try
[20:30] <joshd> then you can set the actual value to the secret from your rados user's keyring with 'virsh secret-set-value <uuid> <secret>'
[20:31] <CristianDM> And how view de default pool and secret of ceph?
[20:32] <joshd> 'rados lspools' and 'ceph auth list'
[20:32] <joshd> by default there are users for the daemons, and an admin user who has access to everything
[20:41] <CristianDM> The default is rbd ?
[20:41] <CristianDM> I have data, metadata and rbd
[20:43] <joshd> the default for the rbd command line tool is rbd
[20:47] <CristianDM> Yes, but for setup into openstack rbd_store_pool
[20:47] <CristianDM> I need to setup the store pool
[20:50] <CristianDM> joshd, can send DM?
[20:50] <joshd> sure
[20:58] <mgalkiewicz> sagewk: I dont have enough logs to be sure that mon was restarted.
[20:59] * mkampe (~markk@aon.hq.newdream.net) has joined #ceph
[21:17] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[21:26] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[21:32] <sagewk> mgalkiewicz: ok, thanks for checking!
[21:38] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[21:42] * Oliver1 (~oliver1@ip-176-199-58-77.unitymediagroup.de) has joined #ceph
[22:01] <mgalkiewicz> sagwk: np
[22:01] <mgalkiewicz> sagewk: np
[22:11] * nhorman (~nhorman@99.127.245.201) Quit (Quit: Leaving)
[22:16] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) Quit (Quit: Leaving)
[22:17] * The_Bishop (~bishop@p4FCDFDB1.dip.t-dialin.net) Quit (Ping timeout: 480 seconds)
[22:26] * The_Bishop (~bishop@p4FCDFC53.dip.t-dialin.net) has joined #ceph
[22:50] * LarsFronius (~LarsFroni@95-91-243-252-dynip.superkabel.de) has joined #ceph
[23:18] * Theuni (~Theuni@46.253.59.219) Quit (Quit: Leaving.)
[23:24] <Tv_> ceph really builds too slowly
[23:25] <Tv_> ... the amount of swordfighting i could have done today
[23:25] <dmick> it's a lot better in 12M :)
[23:25] <dmick> er, 12G
[23:25] <Tv_> dmick: damn you
[23:25] <dmick> did you follow up with Max, btw? I can, for you, if you like
[23:25] <Tv_> also, i'm waiting on a gitbuilder
[23:25] <Tv_> emailed
[23:26] <dmick> k
[23:26] <Tv_> i'm letting them (max & corp it) have a chance to sort it out, if not i will forcefeed them a newegg link or something
[23:26] <Tv_> largely because i'm out of town anyway
[23:27] <Tv_> and really my only task at the office for today was "redo all your steps in setting up ceph via chef"
[23:27] <Tv_> and i'm still not done
[23:27] <Tv_> because of silly little mistakes in the deb packaging changes, and this huge delay in getting the next round to try
[23:27] <dmick> yeah
[23:28] * LarsFronius (~LarsFroni@95-91-243-252-dynip.superkabel.de) Quit (Quit: LarsFronius)
[23:38] * s[X]_ (~sX]@eth589.qld.adsl.internode.on.net) has joined #ceph
[23:40] * LarsFronius (~LarsFroni@95-91-243-252-dynip.superkabel.de) has joined #ceph
[23:41] * cattelan is now known as cattelan_away
[23:47] * cattelan_away is now known as cattelan

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