#ceph IRC Log


IRC Log for 2011-10-13

Timestamps are in GMT/BST.

[0:29] * maswan (maswan@kennedy.acc.umu.se) Quit (Ping timeout: 480 seconds)
[0:29] * maswan (maswan@kennedy.acc.umu.se) has joined #ceph
[0:42] <MattBenjamin> sagewk: sorry, got pulled away...all day. I'll do an updated push (we intend to have a different public repo actually) tomorrow or next.
[0:42] <Tv|work> sagewk: personally, i'd much rather wrap ssh / paramiko than add core code to ceph
[0:54] * jojy (~jojyvargh@75-54-231-2.lightspeed.sntcca.sbcglobal.net) Quit (Quit: jojy)
[1:01] * sjust (~sam@aon.hq.newdream.net) Quit (Read error: Connection reset by peer)
[1:29] * sjust (~sam@aon.hq.newdream.net) has joined #ceph
[1:33] * noahdesu (~nwatkins@kyoto.soe.ucsc.edu) Quit (Quit: Leaving)
[1:58] * cp (~cp@ Quit (Quit: cp)
[2:12] * cp (~cp@ has joined #ceph
[2:20] <MattBenjamin> Is it ok that Inode::get_first_parent() is returning begin() of a <set>?
[3:05] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) Quit (Quit: adjohn)
[3:07] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) has joined #ceph
[3:16] * cp (~cp@ Quit (Quit: cp)
[3:45] * joshd (~joshd@aon.hq.newdream.net) Quit (Quit: Leaving.)
[3:52] * jojy (~jojyvargh@75-54-231-2.lightspeed.sntcca.sbcglobal.net) has joined #ceph
[3:53] * jojy (~jojyvargh@75-54-231-2.lightspeed.sntcca.sbcglobal.net) Quit ()
[3:53] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) Quit (Quit: adjohn)
[3:57] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) has joined #ceph
[4:02] * yoshi (~yoshi@p9224-ipngn1601marunouchi.tokyo.ocn.ne.jp) has joined #ceph
[4:03] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) Quit (Quit: adjohn)
[4:04] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) has joined #ceph
[4:10] * yoshi (~yoshi@p9224-ipngn1601marunouchi.tokyo.ocn.ne.jp) Quit (Remote host closed the connection)
[4:17] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) Quit (Quit: adjohn)
[6:51] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) has joined #ceph
[7:00] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) Quit (Quit: adjohn)
[7:40] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) has joined #ceph
[8:07] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) Quit (Quit: adjohn)
[8:16] * Dantman (~dantman@S010600259c4d54ff.vs.shawcable.net) Quit (Remote host closed the connection)
[8:44] * Meths_ is now known as Meths
[8:47] * yoshi (~yoshi@p9224-ipngn1601marunouchi.tokyo.ocn.ne.jp) has joined #ceph
[9:52] * livemoon (~deadsun@ has joined #ceph
[9:52] <livemoon> Hi, all
[9:54] <livemoon> anyone use ceph with openstack?
[10:20] <livemoon> is anyone here?
[11:37] * gregorg (~Greg@ has joined #ceph
[11:37] * gregorg_taf (~Greg@ Quit (Read error: Connection reset by peer)
[11:48] * votz (~votz@pool-108-52-121-23.phlapa.fios.verizon.net) Quit (Quit: Leaving)
[11:49] * Kioob (~kioob@luuna.daevel.fr) Quit (Quit: Leaving.)
[12:03] * yoshi (~yoshi@p9224-ipngn1601marunouchi.tokyo.ocn.ne.jp) Quit (Remote host closed the connection)
[12:27] * livemoon (~deadsun@ Quit (Quit: leaving)
[13:02] * Hugh (~hughmacdo@soho-94-143-249-50.sohonet.co.uk) has joined #ceph
[14:21] * Nightdog (~karl@190.84-48-62.nextgentel.com) has joined #ceph
[14:44] * mtk (~mtk@ool-182c8e6c.dyn.optonline.net) Quit (Remote host closed the connection)
[14:50] * mtk (~mtk@ool-182c8e6c.dyn.optonline.net) has joined #ceph
[15:24] * cp (~cp@c-98-234-218-251.hsd1.ca.comcast.net) has joined #ceph
[15:31] * MK_FG (~MK_FG@ Quit (Quit: o//)
[15:31] * MK_FG (~MK_FG@ has joined #ceph
[16:39] * livemoon (~livemoon@ has joined #ceph
[16:39] <livemoon> hi,all
[16:39] <livemoon> anyone use ceph?
[16:53] * adjohn (~adjohn@50-0-92-177.dsl.dynamic.sonic.net) has joined #ceph
[16:57] * verwilst (~verwilst@dD576F86E.access.telenet.be) has joined #ceph
[16:58] * livemoon (~livemoon@ has left #ceph
[17:32] * MarkN (~nathan@ Quit (Read error: Operation timed out)
[17:37] <sagewk> MattBenjamin: it's returning *begin(), right? the first element
[17:42] * aliguori (~anthony@cpe-70-123-132-139.austin.res.rr.com) Quit (Remote host closed the connection)
[17:43] * MarkN (~nathan@ has joined #ceph
[17:44] * aliguori (~anthony@cpe-70-123-132-139.austin.res.rr.com) has joined #ceph
[17:53] * Dantman (~dantman@S010600259c4d54ff.vs.shawcable.net) has joined #ceph
[17:56] * bchrisman (~Adium@c-98-207-207-62.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[18:11] * MarkN (~nathan@ Quit (Ping timeout: 480 seconds)
[18:25] * aliguori (~anthony@cpe-70-123-132-139.austin.res.rr.com) Quit (Quit: Ex-Chat)
[18:25] * sjust (~sam@aon.hq.newdream.net) Quit (Quit: Leaving.)
[18:30] * sjust (~sam@aon.hq.newdream.net) has joined #ceph
[18:41] * joshd (~joshd@aon.hq.newdream.net) has joined #ceph
[18:53] * aliguori (~anthony@ has joined #ceph
[18:55] * jojy (~jojyvargh@ has joined #ceph
[19:33] * bchrisman (~Adium@ has joined #ceph
[19:38] <Tv|work> sometimes i feel like we should hire someone who speaks chinese to do support :-/
[19:41] * Kioob (~kioob@luuna.daevel.fr) has joined #ceph
[20:06] * stass (stas@ssh.deglitch.com) Quit (Ping timeout: 480 seconds)
[20:07] * stass (stas@ssh.deglitch.com) has joined #ceph
[20:19] * verwilst (~verwilst@dD576F86E.access.telenet.be) Quit (Quit: Ex-Chat)
[20:35] * bchrisman (~Adium@ Quit (Quit: Leaving.)
[20:45] <MattBenjamin> sagewk: any set has an order, is it the right one?
[20:46] <sagewk> doesn't really matter.. the method should probably be get_any_parent()
[20:46] <MattBenjamin> k, thanks
[20:53] * yehuda_hm (~yehuda@99-48-179-68.lightspeed.irvnca.sbcglobal.net) has joined #ceph
[21:04] * cp (~cp@c-98-234-218-251.hsd1.ca.comcast.net) Quit (Quit: cp)
[21:04] * cp (~cp@c-98-234-218-251.hsd1.ca.comcast.net) has joined #ceph
[21:21] * SpamapS_ (clint@xenclint.srihosting.com) has joined #ceph
[21:21] * SpamapS_ is now known as SpamapS
[21:31] * SpamapS waves hi from Ubuntu-land. :)
[21:32] <joshd> hello
[21:33] * bchrisman (~Adium@c-98-207-207-62.hsd1.ca.comcast.net) has joined #ceph
[21:33] * SpamapS wonders if he met anybody in here at the openstack summit last week
[21:34] <joshd> you might have met Tv|work
[21:35] <SpamapS> I'm working on a "juju charm" to do ceph deployment/scaling
[21:35] * cp (~cp@c-98-234-218-251.hsd1.ca.comcast.net) Quit (Quit: cp)
[21:36] <SpamapS> the sheer volume of options and ways to run make that.. somewhat challenging. :)
[21:39] <joshd> Tv|work has been working on chef recipes for that - looks like he's not around at the moment though
[21:40] <joshd> the initial pieces are at https://github.com/NewDreamNetwork/ceph-cookbooks/tree/wip-simple, and I think more complete ones will be pushed in the next few days
[21:41] <SpamapS> cool I might be able to just construct the charm around the chef stuff
[22:00] <Tv|work> SpamapS: yeah the charm & cookbooks should definitely use the same underlying mechanisms, the same way
[22:01] <Tv|work> SpamapS: i have my crowbar work from last week all in one uncommitted big pile, i'll work on getting it out; realistic schedule is next week
[22:07] <sagewk> ajm-: around?
[22:11] * cp (~cp@ has joined #ceph
[22:14] <SpamapS> Tv|work: cool. One thing that is challenging me is that one needs to decide where mds/mon/osd's live before mkcephfs (or the constituent steps anyway) ... there are two distinct modes... building system, and running system.
[22:14] <Tv|work> SpamapS: my cookbooks aren't using mkcephfs ;)
[22:15] <Tv|work> SpamapS: mkcephfs is best for small, fairly static clusters, and probably will get obsoleted by chef/juju/etc rather than them using it as a tool
[22:15] <SpamapS> right, thats what I'm thinking too..
[22:15] <Tv|work> SpamapS: i have dynamic osd deployment working in the cookbooks, i'll clean them up, commit & push in the next few days
[22:16] <SpamapS> but knowing when to go ahead and create the volumes is a bit challenging...
[22:17] <Tv|work> SpamapS: my thinking is more along the lines of.. hard drives "meant to be used by OSDs" are marked (mkfs & label "ceph-blank"), store nodes detect all those disks, allocate osd ids, re-label disks to "ceph-osd.42" etc, everything is dynamic
[22:17] <SpamapS> Tv|work: all the copying around of mon maps seems tricky too
[22:17] <Tv|work> SpamapS: i'm pushing to make the mon copying not needed, we'll see what we can do there ;)
[22:17] <SpamapS> Cool
[22:17] <Tv|work> SpamapS: right now my cookbooks limit themselves to single mon
[22:17] <SpamapS> the ceph charm I've written just puts mon/mds/osd on all nodes
[22:18] <Tv|work> yeah that's the non-challenging part of the challenge ;)
[22:18] <Tv|work> getting the services wired up, trust established, etc is the real meat
[22:18] <SpamapS> Tv|work: you're here in LA too right?
[22:18] <Tv|work> SpamapS: yup
[22:18] <Tv|work> Clint?
[22:18] <SpamapS> indeed!
[22:18] <SpamapS> sorry
[22:18] <Tv|work> SpamapS: we met at the summit ;)
[22:18] <SpamapS> indeed
[22:19] <SpamapS> Tv|work: once you've got that pile consumable, and I've had a poke at it.. it might be productive to get together for an afternoon of juju/chef mind melding.
[22:19] <Tv|work> SpamapS: once i've dealt with the 1.5 week backlog of email etc, i'll get back on track with the cookbooks; once i have a slightly better idea, we should probably do a half-day brainstorm on it, at our office
[22:20] <Tv|work> gaah
[22:20] <SpamapS> Yeah, no rush. :)
[22:20] * Tv|work grabs tinfoil hat
[22:20] <Tv|work> point that mindreading beam somewhere else
[22:20] <SpamapS> Its omnidirectional.. sorry
[22:32] <sagewk> spamaps: hi clint!
[22:32] <SpamapS> sagewk: hey, long time no chat :)
[22:33] <sagewk> spamaps: will you be at uds?
[22:38] <SpamapS> Yes, I arrive on Tuesday
[22:38] <ajm-> sagewk: yeah I am now
[22:38] <SpamapS> sagewk: There's a lot of buzz about ceph amongst the server focused people around Ubuntu.. quite exciting really.
[22:39] <sagewk> spamaps: yeah thats what i hear! should find out in the next few days if we'll be at uds or not. hopefully see you there
[22:40] <sagewk> ajm-: i have something pretty bloody that's just about ready for you to poke at. i have one more case to test, then a bit more hammering.
[22:40] <sagewk> should have a wip-unfound branch for you later today
[22:40] <ajm-> sagewk: i love you.
[22:40] <sagewk> let's wait until we know it doesn't eat your data :)
[22:41] <SpamapS> sagewk: the main thing it will do is help to solidify that ceph is something you guys want people to use.. being in main means our security team has to support you for 5 years, so its a big deal that upstream is on board. :)
[22:42] <SpamapS> sagewk: bring the family, go to Disneyworld after. ;)
[22:42] <sagewk> almost.. my wife is in orlando the following week for another conference.
[22:43] <SpamapS> I guess all the giant hotels figured out how to remain full during the mid-week
[22:43] <sagewk> ...but have to back here for the weekend.
[22:43] <sagewk> yeah really
[23:19] * MarkN (~nathan@ has joined #ceph
[23:48] * cp (~cp@ Quit (Quit: cp)

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