#ceph IRC Log


IRC Log for 2012-03-29

Timestamps are in GMT/BST.

[0:27] * BManojlovic (~steki@ Quit (Quit: Ja odoh a vi sta 'ocete...)
[0:28] * verwilst (~verwilst@dD5769628.access.telenet.be) Quit (Quit: Ex-Chat)
[0:33] * perplexed (~ncampbell@ Quit (Quit: perplexed)
[0:41] * gregorg (~Greg@ has joined #ceph
[0:41] * `gregorg` (~Greg@ Quit (Read error: Connection reset by peer)
[1:28] * danieagle (~Daniel@ Quit (Quit: Inte+ :-) e Muito Obrigado Por Tudo!!! ^^)
[1:33] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) Quit (Ping timeout: 480 seconds)
[2:09] * lofejndif (~lsqavnbok@19NAAHPD4.tor-irc.dnsbl.oftc.net) Quit (Quit: Leaving)
[2:28] * bchrisman (~Adium@ Quit (Quit: Leaving.)
[2:32] * joao (~JL@ Quit (Remote host closed the connection)
[2:38] * imjustmatthew (~imjustmat@pool-96-228-59-130.rcmdva.fios.verizon.net) Quit (Read error: Connection reset by peer)
[2:48] * yoshi (~yoshi@p1062-ipngn1901marunouchi.tokyo.ocn.ne.jp) has joined #ceph
[3:48] * bchrisman (~Adium@c-76-103-130-94.hsd1.ca.comcast.net) has joined #ceph
[5:10] * joshd (~joshd@aon.hq.newdream.net) Quit (Quit: Leaving.)
[5:56] * dmick (~dmick@aon.hq.newdream.net) has left #ceph
[6:38] * f4m8_ is now known as f4m8
[7:26] <sage> elder: miklos' atomic-open patches seem to behave just fine. sent him an incremental patch to simplify/improve things further.. we'll see if al/christoph sign off on it
[7:27] <sage> also pushed to wip-atomic-open if we want to do further testing.. i suspect this will go in via miklos to al's tree tho
[8:35] * chutzpah (~chutz@ Quit (Quit: Leaving)
[9:02] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[9:27] * Kioob`Taff (~plug-oliv@local.plusdinfo.com) has joined #ceph
[10:20] * BManojlovic (~steki@ has joined #ceph
[10:24] * alexxy (~alexxy@ Quit (Ping timeout: 480 seconds)
[10:27] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) Quit (Read error: Connection reset by peer)
[10:28] * loicd (~loic@ has joined #ceph
[10:29] <loicd> Hi, I'm looking for paid support for ceph. Is there a company providing this ?
[10:34] * Theuni (~Theuni@dslb-088-066-108-233.pools.arcor-ip.net) has joined #ceph
[10:36] * Theuni (~Theuni@dslb-088-066-108-233.pools.arcor-ip.net) has left #ceph
[11:01] * LarsFronius (~LarsFroni@testing78.jimdo-server.com) has joined #ceph
[11:55] * f4m8 (f4m8@kudu.in-berlin.de) Quit (Remote host closed the connection)
[11:56] * f4m8 (f4m8@kudu.in-berlin.de) has joined #ceph
[12:02] * joao (~JL@ has joined #ceph
[12:11] * oliver1 (~oliver@p4FFFED61.dip.t-dialin.net) has joined #ceph
[12:11] * f4m8_ (f4m8@kudu.in-berlin.de) has joined #ceph
[12:11] * f4m8 (f4m8@kudu.in-berlin.de) Quit (Read error: Connection reset by peer)
[13:06] * Kioob`Taff (~plug-oliv@local.plusdinfo.com) Quit (Quit: Leaving.)
[13:06] * Kioob`Taff (~plug-oliv@local.plusdinfo.com) has joined #ceph
[13:20] * yoshi (~yoshi@p1062-ipngn1901marunouchi.tokyo.ocn.ne.jp) Quit (Remote host closed the connection)
[13:30] * alexxy (~alexxy@ has joined #ceph
[14:12] * ghaskins (~ghaskins@68-116-192-32.dhcp.oxfr.ma.charter.com) Quit (Read error: Connection reset by peer)
[14:13] * ghaskins (~ghaskins@68-116-192-32.dhcp.oxfr.ma.charter.com) has joined #ceph
[14:32] <elder> sage, OK, will do.
[15:29] <nhm> good morning all
[15:35] <joao> hi
[16:33] <joao> does the FileStore usually leak much memory?
[16:33] * oliver1 (~oliver@p4FFFED61.dip.t-dialin.net) has left #ceph
[16:42] <nhm> joao: that doesn't sound good
[16:43] <joao> nhm, I'm still looking into it, so don't read too much on what I just asked ;)
[16:46] <nhm> joao: good luck on your journey down the rabbit hole. ;)
[16:47] <joao> well, I might have jumped the gun here
[16:49] <joao> it appears to leak memory, but not that much
[16:49] <joao> and it's mainly in option parsing, I think
[17:04] * BManojlovic (~steki@ Quit (Quit: Ja odoh a vi sta 'ocete...)
[17:19] * lofejndif (~lsqavnbok@659AAA5Q5.tor-irc.dnsbl.oftc.net) has joined #ceph
[17:31] * bchrisman (~Adium@c-76-103-130-94.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[17:36] * kirby (~kfiles@pool-151-199-52-228.bos.east.verizon.net) has joined #ceph
[17:37] * aliguori (~anthony@cpe-70-123-132-139.austin.res.rr.com) Quit (Remote host closed the connection)
[17:38] <kirby> Is it possible for Ceph to participate in the VFS cache? I notice that no matter how many times I read a file, the reads are never cached in VFS.
[17:56] * danieagle (~Daniel@ has joined #ceph
[17:57] * joshd (~joshd@aon.hq.newdream.net) has joined #ceph
[18:06] * aliguori (~anthony@ has joined #ceph
[18:17] <sagewk> kirby: using the kernel fs client?
[18:19] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) Quit (Quit: Leaving.)
[18:38] * bchrisman (~Adium@ has joined #ceph
[18:39] * alexxy (~alexxy@ Quit (Remote host closed the connection)
[18:40] <gregaf> loicd: we're bootstrapping support now???if you want details you can email info@ceph.com
[18:42] * imjustmatthew (~imjustmat@pool-96-228-59-130.rcmdva.fios.verizon.net) has joined #ceph
[18:44] * alexxy (~alexxy@ has joined #ceph
[18:56] * BManojlovic (~steki@ has joined #ceph
[19:06] <wido> sagewk: For 2212, do you need logs of multiple OSD's?
[19:07] * chutzpah (~chutz@ has joined #ceph
[19:07] <joao> looks like the tracker is unresponsive again
[19:10] <nhm> joao: I got a message from Tommi about not being able to do vidyo, but I wasn't sure if he was referring to the standup meeting. Just FYI
[19:10] <gregaf> I think there's no standup today
[19:10] <joao> oh really?
[19:10] <joao> okay then
[19:11] <joao> let me know if plans change or if you postpone it to a later time
[19:13] <nhm> yay, localled archived non-scheduled teuthology-suite ftw
[19:14] <joao> oh boy, couldn't make any sense of what you just said :p
[19:14] <nhm> joao: I added some changes (back in) to teuthology-suite so that I can optionally run it in a way that lets me archive the results locally rather than as part of a nightly run.
[19:15] <loicd> gregaf: great news ;-)
[19:17] <elder> gregaf, why?
[19:24] <loicd> gregaf: mail sent to info@ceph.com . I'll be at the OpenStack summit in two weeks (representing Debian GNU/Linux and my company). Maybe it will be an opportunity to learn more about the support program ?
[19:24] * dmick (~dmick@aon.hq.newdream.net) has joined #ceph
[19:26] <joao> hey Dan :)
[19:26] <dmick> hey Joao
[19:31] <gregaf> elder: sorry, was afk ?????we're doing a trainingish thingy today in the office (well, not me...)
[19:31] <gregaf> loicd: I'm not sure who will be there yet, but my magic 8 ball says the odds are good
[19:31] <elder> Very well articulated.
[19:32] <loicd> :-D
[19:35] * jmlowe (~Adium@129-79-195-139.dhcp-bl.indiana.edu) has joined #ceph
[19:39] <kirby> sagewk: yes, I'm using the kernel client (3.2.0) and ceph 0.44 backend
[19:39] <jmlowe> I'm having some trouble with rbd and snapshots, I should be able to create a rbd device, mount it, take a snapshot, then mount the snapshot readonly without it sending everything into uninterruptible wait states right?
[19:47] <gregaf> jmlowe: probably? but you really want to freeze the filesystem before taking the snapshot
[19:54] <wido> joao: Is the tracker still down at your location?
[19:54] <joao> checking
[19:54] <jmlowe> hmm, don't know if a sync freed things up or I just waited long enough
[19:54] <joao> wido, looks like it
[19:55] <joao> yes, no response whatsoever
[19:55] <wido> ok, then it's not me. Just "Waiting for here"
[19:55] <wido> gregaf: You might poke somebody?
[19:55] <gregaf> I need to find out what Sage is doing/who he's poking
[19:56] <gregaf> but I'll look around
[19:57] <wido> thanks
[19:57] <gregaf> jmlowe: it wouldn't surprise me if snapshots were a bit slow, especially if the filesystem was still trying to do work while taking one
[19:57] <gregaf> theoretically it should be pretty quick, but if you back up even a few seconds worth of data and then it all needs to flush out to a small OSD cluster which needs to make copies of everything, it might not go as fast as one would like
[19:58] * loicd (~loic@ Quit (Quit: Leaving.)
[19:59] <jmlowe> gregaf: yeah, that's all it was, after a sync mount fails quickly with a recovery required write access unavailable cannot proceed
[19:59] <wido> btw, achieved record today I think. After 160 days of uptime I'm shutting down a RBD VM, going to 0.44.1 and there is a on-disk change, so mkcephfs is needed
[19:59] <wido> it survived a couple of OSDs dying, other cluster issues, but it's still alive and kicking
[19:59] <gregaf> jmlowe: huh?
[20:00] <jmlowe> gregaf: oxford commas would have made that clearer
[20:02] <jmlowe> gregaf: following a successful sync command, mount returns a failure quickly, predictably it can't mount because it wants to fix a copy of an ready mounted filesystem and can't do that with a readonly device
[20:02] <gregaf> ah, good then
[20:09] <dmick> gregaf: managed to get into the tracker machine
[20:09] <dmick> sage said yesterday there were typically two processes fighting, and he kills them both. looking.
[20:10] <gregaf> oh, good to know
[20:18] * LarsFronius (~LarsFroni@testing78.jimdo-server.com) Quit (Quit: LarsFronius)
[20:20] <joao> dmick, I believe it was redmine and git
[20:22] <dmick> yeah, I found the log with gregaf's help
[20:22] <dmick> restarting, but not up yet
[20:29] <dmick> looks like it's back
[20:30] <dmick> (tracker, that is....^wido ^joao)
[20:32] <sagewk> not sure why that keeps happening. i can disable the redmine's access to the git tree as a quick fix.. but it means the commit links won't work
[20:33] <dmick> didn't see the git processes
[20:33] <dmick> only killed two Ruby procs
[20:33] <dmick> and they needed -9
[20:37] * nhorman (~nhorman@99-127-245-201.lightspeed.rlghnc.sbcglobal.net) has joined #ceph
[20:44] * lofejndif (~lsqavnbok@659AAA5Q5.tor-irc.dnsbl.oftc.net) Quit (Ping timeout: 480 seconds)
[20:45] * LarsFronius (~LarsFroni@e176058108.adsl.alicedsl.de) has joined #ceph
[20:54] * lofejndif (~lsqavnbok@09GAAEFSS.tor-irc.dnsbl.oftc.net) has joined #ceph
[21:07] * BManojlovic (~steki@ Quit (Ping timeout: 480 seconds)
[21:07] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[21:09] * lofejndif (~lsqavnbok@09GAAEFSS.tor-irc.dnsbl.oftc.net) Quit (Ping timeout: 480 seconds)
[21:13] * Kioob (~kioob@luuna.daevel.fr) Quit (Quit: Leaving.)
[21:15] * Kioob (~kioob@luuna.daevel.fr) has joined #ceph
[21:18] * lofejndif (~lsqavnbok@9YYAAEYMC.tor-irc.dnsbl.oftc.net) has joined #ceph
[22:00] * lofejndif (~lsqavnbok@9YYAAEYMC.tor-irc.dnsbl.oftc.net) Quit (Quit: Leaving)
[22:15] * nhorman (~nhorman@99-127-245-201.lightspeed.rlghnc.sbcglobal.net) Quit (Quit: Leaving)
[22:22] * lofejndif (~lsqavnbok@659AAA52K.tor-irc.dnsbl.oftc.net) has joined #ceph
[22:25] * LarsFronius_ (~LarsFroni@e176058108.adsl.alicedsl.de) has joined #ceph
[22:25] * LarsFronius (~LarsFroni@e176058108.adsl.alicedsl.de) Quit (Read error: Connection reset by peer)
[22:25] * LarsFronius_ is now known as LarsFronius
[22:30] * LarsFronius (~LarsFroni@e176058108.adsl.alicedsl.de) Quit (Quit: LarsFronius)
[22:54] * jmlowe (~Adium@129-79-195-139.dhcp-bl.indiana.edu) Quit (Quit: Leaving.)
[23:33] * loicd (~loic@magenta.dachary.org) has joined #ceph
[23:36] * BManojlovic (~steki@ has joined #ceph
[23:44] * dmick (~dmick@aon.hq.newdream.net) Quit (Quit: Leaving.)
[23:48] * aliguori (~anthony@ Quit (Remote host closed the connection)

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