#ceph IRC Log

Index

IRC Log for 2012-06-18

Timestamps are in GMT/BST.

[0:15] * MarkN (~nathan@142.208.70.115.static.exetel.com.au) has left #ceph
[0:26] * danieagle (~Daniel@177.43.213.15) Quit (Quit: Inte+ :-) e Muito Obrigado Por Tudo!!! ^^)
[1:12] * BManojlovic (~steki@212.200.243.183) Quit (Remote host closed the connection)
[1:36] * loicd (~loic@magenta.dachary.org) has joined #ceph
[2:05] * lofejndif (~lsqavnbok@9KCAAGDJP.tor-irc.dnsbl.oftc.net) has joined #ceph
[2:21] * lofejndif (~lsqavnbok@9KCAAGDJP.tor-irc.dnsbl.oftc.net) Quit (Quit: gone)
[2:34] * yoshi (~yoshi@p37158-ipngn3901marunouchi.tokyo.ocn.ne.jp) has joined #ceph
[4:45] * Ryan_Lane1 (~Adium@dslb-088-075-182-072.pools.arcor-ip.net) has joined #ceph
[4:52] * Ryan_Lane (~Adium@dslb-092-078-135-015.pools.arcor-ip.net) Quit (Ping timeout: 480 seconds)
[5:00] * elder (~elder@c-71-195-31-37.hsd1.mn.comcast.net) has joined #ceph
[5:07] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[5:08] * loicd (~loic@magenta.dachary.org) has joined #ceph
[6:04] * danieagle (~Daniel@177.43.213.15) has joined #ceph
[6:06] * Solver (~robert@atlas.opentrend.net) has joined #ceph
[6:13] * cattelan_away_away is now known as cattelan_away_away_away
[7:33] * danieagle (~Daniel@177.43.213.15) Quit (Quit: Inte+ :-) e Muito Obrigado Por Tudo!!! ^^)
[7:41] * gregorg (~Greg@78.155.152.6) Quit (Read error: Connection reset by peer)
[7:41] * gregorg (~Greg@78.155.152.6) has joined #ceph
[8:14] * joao (~JL@89.181.148.114) has joined #ceph
[8:16] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[8:20] * jluis (~JL@89-181-148-114.net.novis.pt) Quit (Ping timeout: 480 seconds)
[8:58] * The_Bishop (~bishop@2a01:198:2ee:0:8c74:688a:2042:ea1b) Quit (Ping timeout: 480 seconds)
[9:10] * s[X]_ (~sX]@ppp59-167-154-113.static.internode.on.net) Quit (Remote host closed the connection)
[9:10] * s[X] (~sX]@ppp59-167-154-113.static.internode.on.net) has joined #ceph
[9:13] * loicd (~loic@83.167.43.235) has joined #ceph
[9:18] * BManojlovic (~steki@91.195.39.5) has joined #ceph
[9:18] * s[X] (~sX]@ppp59-167-154-113.static.internode.on.net) Quit (Ping timeout: 480 seconds)
[9:20] * verwilst (~verwilst@d5152FEFB.static.telenet.be) has joined #ceph
[9:31] * BManojlovic (~steki@91.195.39.5) Quit (Quit: Ja odoh a vi sta 'ocete...)
[9:32] * BManojlovic (~steki@91.195.39.5) has joined #ceph
[9:33] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[10:01] * Ryan_Lane1 (~Adium@dslb-088-075-182-072.pools.arcor-ip.net) Quit (Quit: Leaving.)
[10:45] * hijacker (~hijacker@213.91.163.5) has joined #ceph
[10:50] * BManojlovic (~steki@91.195.39.5) Quit (Quit: Ja odoh a vi sta 'ocete...)
[10:51] * BManojlovic (~steki@91.195.39.5) has joined #ceph
[10:56] * Ryan_Lane1 (~Adium@p5DDC4B3B.dip.t-dialin.net) has joined #ceph
[11:04] * tpeb (~tdesaules@193.46.206.1) Quit (Quit: Lost terminal)
[11:05] * yoshi (~yoshi@p37158-ipngn3901marunouchi.tokyo.ocn.ne.jp) Quit (Remote host closed the connection)
[11:33] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[11:54] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[11:58] * loicd1 (~loic@83.167.43.235) has joined #ceph
[12:05] * loicd (~loic@83.167.43.235) Quit (Ping timeout: 480 seconds)
[12:10] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[12:29] * johnl (~johnl@2a02:1348:14c:1720:914b:154:1220:85e6) Quit (Remote host closed the connection)
[12:29] * johnl (~johnl@2a02:1348:14c:1720:1860:8443:35ed:e764) has joined #ceph
[12:36] * ninkotech (~duplo@89.177.137.231) Quit (Quit: Konversation terminated!)
[12:37] * ninkotech (~duplo@89.177.137.231) has joined #ceph
[13:07] * lofejndif (~lsqavnbok@9KCAAGDZ7.tor-irc.dnsbl.oftc.net) has joined #ceph
[13:18] * ninkotech (~duplo@89.177.137.231) Quit (Read error: Connection reset by peer)
[13:19] * ninkotech (~duplo@89.177.137.231) has joined #ceph
[13:21] * loicd (~loic@83.167.43.235) has joined #ceph
[13:21] * lofejndif (~lsqavnbok@9KCAAGDZ7.tor-irc.dnsbl.oftc.net) Quit (Quit: gone)
[13:21] * loicd1 (~loic@83.167.43.235) Quit (Read error: No route to host)
[13:33] * nhorman (~nhorman@hmsreliant.think-freely.org) has joined #ceph
[13:40] * mtk0 (m5XnCXf0bF@panix2.panix.com) Quit (Remote host closed the connection)
[13:40] * mtk0 (~mtk@ool-44c35bb4.dyn.optonline.net) has joined #ceph
[14:04] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[14:04] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Ping timeout: 480 seconds)
[14:10] * mtk0 (~mtk@ool-44c35bb4.dyn.optonline.net) Quit (Quit: Leaving)
[14:12] * mtk (~mtk@ool-44c35bb4.dyn.optonline.net) has joined #ceph
[14:39] * aliguori (~anthony@cpe-70-123-145-39.austin.res.rr.com) has joined #ceph
[14:39] * aliguori (~anthony@cpe-70-123-145-39.austin.res.rr.com) Quit (Remote host closed the connection)
[14:39] * aliguori (~anthony@cpe-70-123-145-39.austin.res.rr.com) has joined #ceph
[15:08] * mtk (~mtk@ool-44c35bb4.dyn.optonline.net) Quit (Remote host closed the connection)
[15:09] * mtk (~mtk@ool-44c35bb4.dyn.optonline.net) has joined #ceph
[15:28] * jluis (~JL@89-181-148-114.net.novis.pt) has joined #ceph
[15:34] * joao (~JL@89.181.148.114) Quit (Ping timeout: 480 seconds)
[15:37] * joao (~JL@89.181.148.21) has joined #ceph
[15:43] * jluis (~JL@89-181-148-114.net.novis.pt) Quit (Ping timeout: 480 seconds)
[15:50] * ninkotech (~duplo@89.177.137.231) Quit (Read error: Connection reset by peer)
[15:50] * ninkotech (~duplo@89.177.137.231) has joined #ceph
[17:12] * s[X] (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[17:13] * verwilst (~verwilst@d5152FEFB.static.telenet.be) Quit (Quit: Ex-Chat)
[17:21] * LarsFronius (~LarsFroni@testing78.jimdo-server.com) has joined #ceph
[17:22] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[17:24] * BManojlovic (~steki@91.195.39.5) Quit (Quit: Ja odoh a vi sta 'ocete...)
[17:30] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[17:37] * bchrisman (~Adium@c-76-103-130-94.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[17:41] * ninkotech (~duplo@89.177.137.231) Quit (Read error: Connection reset by peer)
[17:41] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[17:42] * BManojlovic (~steki@212.200.243.183) has joined #ceph
[17:44] * ninkotech (~duplo@89.177.137.231) has joined #ceph
[17:50] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[17:53] * Tv_ (~tv@2607:f298:a:607:b19a:507b:4b80:3233) has joined #ceph
[17:53] * Tv_ is now known as tv_
[17:59] * loicd (~loic@83.167.43.235) Quit (Ping timeout: 480 seconds)
[18:00] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[18:03] <sagewk> elder: oh, i see.. i switched around testing and master by accident
[18:03] <elder> Not a problem, I just wanted to make sure we both understood what happened.
[18:03] <elder> Do we?
[18:03] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) Quit (Ping timeout: 480 seconds)
[18:03] <sagewk> i was going to leave master against 3.3 so that it's easier for others to pull in. there is a (trivial) conflict with 3.4 because of the stupid unsigned -> unsigned int thing tho
[18:04] <sagewk> what do you think?
[18:04] <elder> The -next build had no complaints.
[18:04] <elder> And this even with my temporary SCSI fix at the top of the pile.
[18:04] <elder> So I suppose it's fine with master as-is, based on 3.5-rc1
[18:04] <sagewk> let's drop the scsi commit at least
[18:05] <elder> And in that case, we should update the testing branch to match master (+ the scsi commit after it's removed)
[18:05] <elder> The only thing I wanted to try is building that with a non-UML build to see if the scsi fix was needed or not.
[18:05] <sagewk> it makes me nervous having -rc1 in master.. it means its not a kernel someone should actually run
[18:05] * yehudasa (~yehudasa@aon.hq.newdream.net) has joined #ceph
[18:06] <elder> Hmm.
[18:06] <elder> Maybe....
[18:06] <elder> We should have stable branches!
[18:06] <sagewk> yeah, i guess so :)
[18:06] <sagewk> ok
[18:06] <elder> Let's talk about that next week.
[18:06] <sagewk> k
[18:06] <elder> For now let's just back up the one commit on master.
[18:06] <sagewk> both branches fixed
[18:06] <elder> OK.
[18:07] <elder> I'll update my local tree.
[18:07] <elder> I've added that to my growing agenda for next week.
[18:11] * loicd (~loic@magenta.dachary.org) has joined #ceph
[18:14] * mkampe (~markk@aon.hq.newdream.net) has joined #ceph
[18:18] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[18:27] * lofejndif (~lsqavnbok@9KCAAGEDU.tor-irc.dnsbl.oftc.net) has joined #ceph
[18:53] * bchrisman (~Adium@108.60.121.114) has joined #ceph
[18:54] * gregaf (~Adium@2607:f298:a:607:1dbd:59b6:79e3:4e20) Quit (Quit: Leaving.)
[18:55] * gregaf (~Adium@aon.hq.newdream.net) has joined #ceph
[18:57] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[19:00] * joshd (~joshd@2607:f298:a:607:221:70ff:fe33:3fe3) has joined #ceph
[19:03] * morse (~morse@supercomputing.univpm.it) Quit (Remote host closed the connection)
[19:07] * LarsFronius (~LarsFroni@testing78.jimdo-server.com) Quit (Remote host closed the connection)
[19:07] * LarsFronius (~LarsFroni@testing78.jimdo-server.com) has joined #ceph
[19:07] * morse (~morse@supercomputing.univpm.it) has joined #ceph
[19:15] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) Quit (Quit: Leaving.)
[19:15] * chutzpah (~chutz@216.174.109.254) has joined #ceph
[19:23] * LarsFronius (~LarsFroni@testing78.jimdo-server.com) Quit (Quit: LarsFronius)
[19:30] * mkampe (~markk@aon.hq.newdream.net) Quit (Remote host closed the connection)
[19:36] * mkampe (~markk@2607:f298:a:607:222:19ff:fe31:b5d3) has joined #ceph
[19:45] * chutzpah (~chutz@216.174.109.254) Quit (Read error: Operation timed out)
[20:02] * adjohn (~adjohn@69.170.166.146) has joined #ceph
[20:12] * chutzpah (~chutz@216.174.109.254) has joined #ceph
[20:15] * Dieter_be (~Dieterbe@dieter2.plaetinck.be) has joined #ceph
[20:16] <Dieter_be> hey, can you append to blobs that are stored in rados?
[20:22] <dmick_away> librados::ObjectWriteOperation::append
[20:22] <dmick_away> looks like! :)
[20:22] * dmick_away is now known as dmick
[20:23] <dmick> (there are a number of classes there, let me make sure that's the right API, I suspect I'm not quite right)
[20:24] <dmick> the C binding has rados_append()
[20:24] <dmick> (and rados_aio_append)
[20:25] <tv_> http://ceph.com/docs/master/api/librados/#rados_append
[20:25] <tv_> mmm prettah
[20:26] <dmick> *probably* more likely to use librados::IoCtx::append() from your C++ than ObjectWriteOperation::append, but ... yeah, does that answer your question Dieter_be?
[20:32] <Dieter_be> i'm not familiar with that C++ stuff, but, say we were to implement a ceph rados cluster and write node.js (javascript) bindings towards librados, then we would have append support, right?
[20:33] <Dieter_be> and with implement i meant more like "deploy"
[20:36] <dmick> librados definitely supplies the option, directly with C and C++; there are other bindings available as well (Python), so yes, I can't imagine that would be a problem
[20:37] <Dieter_be> ok thanks
[20:37] <sjust> binding to the C api would be the path of least resistance, so you would have access to any functionality exposed in the C bindings
[20:38] <Dieter_be> yeah, we would bind to the C api. i don't see how we would do it otherwise?
[20:39] <sjust> ok, so only path of non-infinite resistance :)
[20:39] <tv_> the other way would be using HTTP to radosgw
[20:39] <sjust> ah, true
[20:39] <Dieter_be> ugh :)
[20:39] <tv_> depending on *how* node.js you are, you might be more comfortable with that
[20:40] <Dieter_be> btw hi again tv_
[20:40] <tv_> Dieter_be: hello person i am currently lacking context for ;)
[20:40] <Dieter_be> I'm Dieter from Vimeo
[20:40] <tv_> ahhh
[20:40] <tv_> hi
[20:44] <tv_> lunch time in la...
[20:46] <nhm> Dieter_be: neat. :)
[20:54] * Ryan_Lane1 (~Adium@p5DDC4B3B.dip.t-dialin.net) Quit (Quit: Leaving.)
[21:00] * ninkotech (~duplo@89.177.137.231) Quit (Read error: Connection reset by peer)
[21:01] <Dieter_be> nhm: yeah ;)
[21:02] <jmlowe> nhm: you were testing xfs backed ceph?
[21:02] <nhm> jmlowe: yes, also ext4...
[21:02] <jmlowe> how did that go?
[21:03] * ninkotech (~duplo@89.177.137.231) has joined #ceph
[21:04] <nhm> jmlowe: For XFS: stable, lower performance than btrfs on a fresh filesystem. Higher performance at scale. Less performance degredation so when the FS was nearly full the perfromance was roughly the same as btrfs.
[21:05] <nhm> The "at scale" comment was for more OSDs per node and on SSDs.
[21:10] <jmlowe> ok, thanks, good to know, I'm again at the point where I'm ditching btrfs due to stability concerns
[21:12] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[21:13] * loicd (~loic@magenta.dachary.org) has joined #ceph
[21:28] <elder> tv_, sagewk, where is the top-level "nightly" run content defined? I see stuff in repository ceph-qa-suite, but that looks like the pieces, not the top-level-driver.
[21:28] <elder> The reason I ask is that I would like to run something like the nightly run on something other than the testing branch. If there is an easy way to do that I would love to know.
[21:30] <joshd> elder: look at schedule_suite.sh in the teuthology repo
[21:30] <elder> OK.
[21:30] <elder> Thank you.
[21:31] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[21:33] <nhm> jmlowe: I should say too, that during my tests btrfs was stable as well. We probably need much longer running tests to really push them.
[21:33] <nhm> jmlowe: I did make ext4 blow up though.
[21:33] <elder> Does a nightly run include suite "basic", "bench", or "thrash" (or some combination of them)?
[21:35] <joshd> it includes everything in the regression collection, which is all of those subdirectories
[21:35] <jmlowe> nhm: I was running the latest ubuntu stock kernel from kernel.ubuntu.com and I had compress=lzo, kept locking up and having the watchdog reboot which got me into a bad place
[21:36] <elder> Thanks joshd. I'll run them in that order (hopefully the order doesn't matter)
[21:36] <joshd> no, order doesn't matter
[21:36] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) Quit (Quit: Leaving.)
[21:41] <nhm> jmlowe: I've heard there are some fixes for btrfs in 3.5, but I haven't really looked into it much...
[21:47] * Ryan_Lane (~Adium@dslb-088-075-182-072.pools.arcor-ip.net) has joined #ceph
[22:07] * cattelan_away_away_away (~cattelan@2001:4978:267:0:21c:c0ff:febf:814b) Quit (Read error: Operation timed out)
[22:22] * querty (~querty@546B21DC.cm-12-4a.dynamic.ziggo.nl) has joined #ceph
[22:22] <querty> whazzup?
[22:24] * widodh_ (~widodh@minotaur.apache.org) Quit (Read error: Operation timed out)
[22:24] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has joined #ceph
[22:25] * nhorman (~nhorman@hmsreliant.think-freely.org) Quit (Quit: Leaving)
[22:25] * widodh (~widodh@minotaur.apache.org) has joined #ceph
[22:26] * querty (~querty@546B21DC.cm-12-4a.dynamic.ziggo.nl) Quit (Quit: Leaving)
[22:41] <gregaf> sagewk: finished reviewing wip-clsrbd again, left a few more comments on github
[22:47] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) has left #ceph
[23:01] <sagewk> gregaf: thanks, looking now
[23:01] * ninkotech (~duplo@89.177.137.231) Quit (Read error: Connection reset by peer)
[23:02] * ninkotech (~duplo@89.177.137.231) has joined #ceph
[23:02] <sagewk> gregaf: can you take a quick look at 2fc2cf03b30423ba302d243b2eba2b0afefb1790 ?
[23:08] <gregaf> sagewk: looks fine
[23:09] <jmlowe> nhm: hard to say what put it into a state where the watchdog timer went off, but btrfs is certainly suspect
[23:10] <jmlowe> nhm: actually btrfs compression is what's really suspect
[23:10] <gregaf> I don't think we've used compression at all, and I bet that's less tested than the non-compressed code paths are
[23:11] <jmlowe> gregaf: I was doing ok I think until I turned it on, really needed the space until I got an extra 36TB recently
[23:11] <dmick> storage is cheap unless you don't have any at hand right now
[23:12] <tv_> dmick: storage is cheap unless you suck at planning?-)
[23:13] <tv_> storage is weird these days.. i have something like 13TB on my desk at home, mostly unused
[23:13] <tv_> *available* and *fast* storage is not cheap ;)
[23:23] * s[X] (~sX]@ppp59-167-154-113.static.internode.on.net) has joined #ceph
[23:24] * s[X]_ (~sX]@ppp59-167-154-113.static.internode.on.net) has joined #ceph
[23:24] * s[X] (~sX]@ppp59-167-154-113.static.internode.on.net) Quit (Read error: Connection reset by peer)
[23:25] <sagewk> gregaf: repushed wip-clsrbd. didn't change unit test parent id, but otherwise fixed up
[23:26] <gregaf> cool
[23:26] <sagewk> oh, left check_exists().. imperative -> return 0, predicate(?) is_foo() -> true/false
[23:27] <sagewk> is predicate the right word?
[23:27] <gregaf> I have no idea, given your symbology :)
[23:28] <gregaf> if you're saying is_foo() is a logical predicate, but check_exists is???not, then I think "predicate" is correct
[23:29] <dmick> tv_: corollary: practically everyone sucks at planning
[23:38] <tv_> identifying network interfaces with just macs is a royal pain
[23:38] <tv_> the tools just aren't there
[23:38] <tv_> dropping in my 100-line python *again* just to do this one thing
[23:39] <tv_> ethernet macs ;)
[23:40] <tv_> i wouldn't try to do actually work on an os x machine :-p
[23:40] <dmick> lol
[23:44] <nhm> tv_: I wonder if they've fixed the linux vidyo client yet. That's the only thing keeping osx on my mac.
[23:44] <tv_> frankly, i don't understand why they chose vidyo
[23:45] <tv_> that's only a significant chunk of the user population
[23:45] <tv_> it's nice between the conference rooms, sure
[23:45] <gregaf> I'm pretty sure our team was the best at getting Skype to work
[23:45] <gregaf> and our percentage wasn't that great either
[23:45] <tv_> but DH/inktank are so linux-heavy
[23:45] <sjust> it actually worked fine on linux for me
[23:46] <dmick> a linux released in the last four years?
[23:46] <sjust> yeah, 11.10
[23:46] <nhm> sjust: vidyo?
[23:46] <sjust> yes
[23:46] <nhm> sjust: lucky you!
[23:46] <sjust> getting skype to work was a nightmare
[23:46] <sjust> by comparison
[23:47] <nhm> sjust: strange, that's the exact opposite experience for me. skype worked from the get-go while vidyo would randomly segfault, or disable the microphone, or do some other bizarre thing.
[23:48] <nhm> works fine under OSX though.
[23:48] <nhm> aside from the echo cancelation bit I guess.
[23:48] <gregaf> yeah, that's just incredibly disappointing

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