#ceph IRC Log


IRC Log for 2012-07-28

Timestamps are in GMT/BST.

[0:07] * dspano (~dspano@rrcs-24-103-221-202.nys.biz.rr.com) Quit (Quit: Leaving)
[0:15] * Leseb (~Leseb@5ED01FAC.cm-7-1a.dynamic.ziggo.nl) Quit (Quit: Leseb)
[0:41] * kfogel (~Karl@74-92-190-113-Illinois.hfc.comcastbusiness.net) Quit (Quit: Off to the Big Room.)
[1:02] * andrewbogott (~andrewbog@c-76-113-214-220.hsd1.mn.comcast.net) Quit (Quit: andrewbogott)
[1:13] <ryann> when creating a rados pool, i would like to assign it to owner 0, like the rest of the cluster, however when executing 'rados mkpool SubPool1 0 0' and then i do a ceph osd getmap...and print it I see that that new pool's owner is this giant hash. Is this a big deal?
[1:21] <ryann> More Important: is there a trick in getting cephfs /mnt_pnt set_layout --pool 4 to work? All I get is "Error setting layout: Invalid argument"
[1:22] * deepsa (~deepsa@ Quit ()
[1:24] * tnt (~tnt@93.56-67-87.adsl-dyn.isp.belgacom.be) Quit (Ping timeout: 480 seconds)
[1:24] * BManojlovic (~steki@ Quit (Ping timeout: 480 seconds)
[1:24] <joshd> ryann: iirc you have to specify all the layout options with the cephfs tool, not just pool
[1:25] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[1:25] * loicd (~loic@magenta.dachary.org) has joined #ceph
[1:26] <ryann> joshd: Thanks. I'll try that.
[1:28] <joshd> I'm guessing the auid thing is a bug with the default value of -1 replacing 0
[1:29] <ryann> joshd: still the same error. The folder exists. I'm root. I'm not on any of the cluster hosts, I've mounted using a simple client with the kernal module.
[1:30] <joshd> what's the full command that you ran?
[1:36] <joshd> did you run 'ceph mds add_data_pool 4' already?
[1:37] <ryann> cephfs /media/ceph1/SCSI set_layout -p 4 -s 4194304 -u 4194304 -c 1 and no, I didn't know you had to run that command on the mds! Where do I find that?
[1:39] <joshd> I just found it in the test script for cephfs, but it should be in the docs
[1:40] <ryann> joshd: thanks for the auid info. I assumed it would be 0 but it's -1. cool. I haven't used the script. Not sure where it is in the docs. idk if it's there yet, as i don't see on manpages or the "control commands" area. still looking.
[1:40] <joshd> it's possible it's not there
[1:41] <joshd> since we haven't been focusing on the filesystem recently, its docs are less up to date
[1:42] <ryann> joshd: thanks. It's fine. The part that I needed working is working. I think :P
[1:43] <ryann> joshd: is there a mdsmap --print command like there is one for osdmap?
[1:44] <ryann> mdsmaptool i should say, or something like it?
[1:44] <joshd> there's ceph mds dump
[1:44] <joshd> I don't think there's a separate mdsmaptool though
[1:44] <joshd> same for pgmaps
[1:45] <ryann> i see.
[1:45] <joshd> but ceph (subsys) dump [version] shows you the map for mds, osd, and pg
[1:46] <joshd> and they can all have -f json too I think
[1:47] <ryann> joshd: you are a lifesaver!! It's working correctly now.
[1:48] <joshd> hooray!
[1:50] <ryann> Shoot! so is there an undocumented rados mv pool [oldname] [newname]? Yeah i just did that :-/
[1:50] <joshd> no, but there's a documented ceph osd pool rename <old> <new>
[1:51] <joshd> at least on the control commands page
[1:51] <ryann> joshd: HAHA! ok will that change the pool in any way that would screw my assignments?
[1:51] <joshd> no, it will just change the name
[1:52] <joshd> everything that actually uses pools uses the id internally
[1:52] <ryann> thx
[2:16] <mikeryan> ryann: how many pools do you have?
[3:35] * joshd (~joshd@2607:f298:a:607:221:70ff:fe33:3fe3) Quit (Quit: Leaving.)
[3:36] * mosu001 (~mosu001@en-439-0331-001.esc.auckland.ac.nz) Quit (Quit: Leaving)
[3:44] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[3:44] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Read error: Connection reset by peer)
[3:47] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[3:47] * loicd (~loic@magenta.dachary.org) has joined #ceph
[3:56] * chutzpah (~chutz@ Quit (Quit: Leaving)
[3:57] <ryann> mikeryan: I have 2; One is 4 nodes with about 12TB total (SATA) and other is SCSI-320 and is made up of 12 stripe OSD's. It's about 2TB. The Smaller is for Xen Block Storage. The larger is for filesystem storage and larger blocks.
[3:57] * duerF (~tommi@31-209-240-108.dsl.dynamic.simnet.is) Quit (Quit: Leaving)
[4:29] <mikeryan> ryann: interest, are you running rbd on it?
[4:29] <mikeryan> interesting*
[4:48] * Ryan_Lane (~Adium@ Quit (Quit: Leaving.)
[4:54] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[4:57] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[5:42] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[6:06] * lofejndif (~lsqavnbok@04ZAAEQVN.tor-irc.dnsbl.oftc.net) Quit (Quit: gone)
[6:17] <ryann> mikeryan: Trying to. I'm having issues getting the rbd create [imagename] --size [mb] to work. keep getting "librbd: failed to assign a block name for image"
[6:18] <ryann> Looks like it's a known bug. I've attempted to update ceph.conf with osd_class_dir = /usr/local/lib (my build prefix was /usr/local - personal preference mainly) but to no avail...
[6:19] <ryann> what i'm NOT sure of, is whether i need /usr/local/lib, or /usr/local/lib/rados-classes i can try both.
[6:23] <ryann> ...Nope still doesn't work :(
[6:24] <ryann> I even have a symlink created to the place it is expecting to find cls_rbd.so sigh...
[6:27] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[6:42] <mikeryan> ryann: not sure if that stuff's dlopen'd or what
[6:42] <mikeryan> you can try running ldconfig, slim chance it'll help
[6:43] <ryann> Yah. i have run ldconfig. I know it's pulled at runtime, due to its absence when listing required object via ldd. Still working on it...
[6:45] <ryann> The other thing i notice is that in rados-classes i have a libcls_rbd.so.1.0.0 not necessarily a cls_rbd.so. No sure if that's a typo in the docs or....
[6:48] <ryann> mikeryan: I'm out for the weekend. I'll work some more on Tuesday. Cheers!
[6:48] * ryann (~chatzilla@ has left #ceph
[7:10] * lxo (~aoliva@lxo.user.oftc.net) Quit (Read error: No route to host)
[9:43] * tnt (~tnt@93.56-67-87.adsl-dyn.isp.belgacom.be) has joined #ceph
[10:33] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[10:33] * loicd (~loic@magenta.dachary.org) has joined #ceph
[10:43] * Cube1 (~Adium@cpe-76-95-223-199.socal.res.rr.com) has joined #ceph
[10:45] * Cube (~Adium@cpe-76-95-223-199.socal.res.rr.com) Quit (Ping timeout: 480 seconds)
[11:01] * Cube1 (~Adium@cpe-76-95-223-199.socal.res.rr.com) Quit (Quit: Leaving.)
[12:53] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[12:53] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has left #ceph
[13:04] * tnt (~tnt@93.56-67-87.adsl-dyn.isp.belgacom.be) Quit (Ping timeout: 480 seconds)
[13:28] * BManojlovic (~steki@ has joined #ceph
[13:33] * EmilienM (~EmilienM@arc68-4-88-173-120-14.fbx.proxad.net) has joined #ceph
[13:44] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[13:44] * loicd (~loic@magenta.dachary.org) has joined #ceph
[14:12] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[14:12] * loicd (~loic@magenta.dachary.org) has joined #ceph
[15:04] * EmilienM (~EmilienM@arc68-4-88-173-120-14.fbx.proxad.net) has left #ceph
[15:30] * Leseb (~Leseb@5ED01FAC.cm-7-1a.dynamic.ziggo.nl) has joined #ceph
[15:47] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[15:47] * Leseb (~Leseb@5ED01FAC.cm-7-1a.dynamic.ziggo.nl) Quit (Quit: Leseb)
[15:59] * tnt (~tnt@ANancy-555-1-154-106.w92-161.abo.wanadoo.fr) has joined #ceph
[16:03] * Leseb (~Leseb@5ED01FAC.cm-7-1a.dynamic.ziggo.nl) has joined #ceph
[16:18] * sage (~sage@cpe-76-94-40-34.socal.res.rr.com) Quit (Quit: Leaving.)
[16:20] * sage (~sage@cpe-76-94-40-34.socal.res.rr.com) has joined #ceph
[16:20] * sage (~sage@cpe-76-94-40-34.socal.res.rr.com) Quit ()
[16:21] * Leseb (~Leseb@5ED01FAC.cm-7-1a.dynamic.ziggo.nl) Quit (Quit: Leseb)
[16:23] * sage (~sage@cpe-76-94-40-34.socal.res.rr.com) has joined #ceph
[16:29] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[17:00] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[17:01] * loicd (~loic@2a01:e35:2eba:db10:120b:a9ff:feb7:cce0) has joined #ceph
[17:49] * allsystemsarego (~allsystem@ has joined #ceph
[19:35] * loicd (~loic@2a01:e35:2eba:db10:120b:a9ff:feb7:cce0) Quit (Quit: Leaving.)
[19:36] * loicd (~loic@magenta.dachary.org) has joined #ceph
[20:34] * morse (~morse@supercomputing.univpm.it) Quit (Remote host closed the connection)
[20:35] * morse (~morse@supercomputing.univpm.it) has joined #ceph
[23:03] * imjustmatthew (~imjustmat@pool-96-228-59-186.rcmdva.fios.verizon.net) has joined #ceph

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