#ceph IRC Log

Index

IRC Log for 2015-04-02

Timestamps are in GMT/BST.

[0:01] * badone__ (~brad@CPE-121-215-241-179.static.qld.bigpond.net.au) has joined #ceph
[0:02] * fridim_ (~fridim@56-198-190-109.dsl.ovh.fr) Quit (Ping timeout: 480 seconds)
[0:03] * tk12_ (~tk12@68.140.239.132) has joined #ceph
[0:04] * vata (~vata@208.88.110.46) Quit (Quit: Leaving.)
[0:09] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[0:09] * tk12 (~tk12@68.140.239.132) Quit (Ping timeout: 480 seconds)
[0:10] * bandrus (~brian@100.sub-70-211-64.myvzw.com) has joined #ceph
[0:11] * reed (~reed@75-101-54-131.dsl.static.fusionbroadband.com) Quit (Quit: Ex-Chat)
[0:11] * reed (~reed@75-101-54-131.dsl.static.fusionbroadband.com) has joined #ceph
[0:14] * daniel2_ (~daniel2_@cpe-24-28-6-151.austin.res.rr.com) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[0:15] * angdraug (~angdraug@12.164.168.117) has joined #ceph
[0:18] * moore (~moore@64.202.160.88) Quit (Remote host closed the connection)
[0:18] * angdraug (~angdraug@12.164.168.117) Quit ()
[0:22] * tk12 (~tk12@68.140.239.132) has joined #ceph
[0:22] * tk12_ (~tk12@68.140.239.132) Quit (Read error: Connection reset by peer)
[0:23] <cetex> finally
[0:23] <cetex> ceph cluster up and running
[0:23] <cetex> :)
[0:23] <cetex> and i kinda understand how everything is fitting together
[0:23] <cetex> now i just need to figure out how to store something..
[0:24] * tk12_ (~tk12@68.140.239.132) has joined #ceph
[0:24] * tk12 (~tk12@68.140.239.132) Quit (Read error: Connection reset by peer)
[0:29] * Izanagi (~Azerothia@5NZAAA0FL.tor-irc.dnsbl.oftc.net) Quit ()
[0:30] * reed (~reed@75-101-54-131.dsl.static.fusionbroadband.com) Quit (Quit: Ex-Chat)
[0:30] * reed_ (~reed@75-101-54-131.dsl.static.fusionbroadband.com) has joined #ceph
[0:31] * ircolle (~Adium@c-71-229-136-109.hsd1.co.comcast.net) Quit (Quit: Leaving.)
[0:32] * fsimonce (~simon@host186-55-dynamic.21-79-r.retail.telecomitalia.it) Quit (Quit: Coyote finally caught me)
[0:33] * LeaChim (~LeaChim@host86-151-147-249.range86-151.btcentralplus.com) has joined #ceph
[0:33] * tk12_ (~tk12@68.140.239.132) Quit (Read error: Connection reset by peer)
[0:34] * lcurtis (~lcurtis@47.19.105.250) Quit (Ping timeout: 480 seconds)
[0:34] * daniel2_ (~daniel2_@cpe-24-28-6-151.austin.res.rr.com) has joined #ceph
[0:35] * oro (~oro@80-219-254-208.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[0:37] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has joined #ceph
[0:37] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has left #ceph
[0:38] * bandrus (~brian@100.sub-70-211-64.myvzw.com) Quit (Ping timeout: 480 seconds)
[0:39] * badone__ is now known as badone
[0:40] * moore (~moore@97-124-123-201.phnx.qwest.net) has joined #ceph
[0:51] * bandrus (~brian@189.sub-70-211-73.myvzw.com) has joined #ceph
[0:51] * jaank (~quassel@98.215.50.223) has joined #ceph
[0:52] * tk12 (~tk12@68.140.239.132) has joined #ceph
[0:52] * moore (~moore@97-124-123-201.phnx.qwest.net) Quit (Remote host closed the connection)
[0:54] * eoin (~eoin@89-93-153-201.hfc.dyn.abo.bbox.fr) Quit (Ping timeout: 480 seconds)
[0:55] * reed_ (~reed@75-101-54-131.dsl.static.fusionbroadband.com) Quit (Quit: Ex-Chat)
[0:55] * reed_ (~reed@75-101-54-131.dsl.static.fusionbroadband.com) has joined #ceph
[0:56] * reed_ (~reed@75-101-54-131.dsl.static.fusionbroadband.com) Quit ()
[0:57] * tk12_ (~tk12@68.140.239.132) has joined #ceph
[0:57] * tk12 (~tk12@68.140.239.132) Quit (Read error: Connection reset by peer)
[0:58] * tk12 (~tk12@68.140.239.132) has joined #ceph
[0:58] * tk12_ (~tk12@68.140.239.132) Quit (Read error: Connection reset by peer)
[0:59] * reed (~reed@75-101-54-131.dsl.static.fusionbroadband.com) has joined #ceph
[1:01] * LeaChim (~LeaChim@host86-151-147-249.range86-151.btcentralplus.com) Quit (Ping timeout: 480 seconds)
[1:01] * tk12 (~tk12@68.140.239.132) Quit (Read error: Connection reset by peer)
[1:03] * sbfox (~Adium@72.2.49.50) Quit (Quit: Leaving.)
[1:04] * saltlake (~saltlake@pool-71-96-110-5.dfw.dsl-w.verizon.net) has joined #ceph
[1:06] <cetex> rados bench - 350MB/sec, not too shabby over 18 cheap 7.2k rpm drives and (kinda) 2gbit networking.
[1:06] * bandrus (~brian@189.sub-70-211-73.myvzw.com) Quit (Ping timeout: 480 seconds)
[1:07] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) has joined #ceph
[1:07] <gregsfortytwo> uh, 2gbit networking can't go that fast (unless you've got some local nodes)
[1:08] * tupper_ (~tcole@rtp-isp-nat1.cisco.com) has joined #ceph
[1:09] <cetex> running 9 rados bench'es on 9 nodes also running osd's
[1:09] * rendar (~I@host45-128-dynamic.61-82-r.retail.telecomitalia.it) Quit ()
[1:09] * moore (~moore@wsip-68-14-250-18.ph.ph.cox.net) has joined #ceph
[1:09] <cetex> and are running LACP to the servers (1+1Gbit) so it's not exactly 2Gbit. one tcp session is tied to an interface.
[1:10] <cetex> will be better within a month or two when i have same setup but 10gbit :)
[1:11] * moore (~moore@wsip-68-14-250-18.ph.ph.cox.net) Quit (Remote host closed the connection)
[1:11] * LeaChim (~LeaChim@host86-151-147-249.range86-151.btcentralplus.com) has joined #ceph
[1:11] * moore (~moore@64.202.160.233) has joined #ceph
[1:12] * zack_dolby (~textual@pa3b3a1.tokynt01.ap.so-net.ne.jp) Quit (Quit: My MacBook has gone to sleep. ZZZzzz???)
[1:14] <cetex> each drive tops out at 145MB/s during sequential writes by dd. should be room for improvement.
[1:15] <gregsfortytwo> no, I meant 2 gigabit maxes out at ~250MB/s, so getting ~350MB/s is quite an accomplishment
[1:15] <gregsfortytwo> but if you've got a bunch of processes on different nodes, with some local writes, it might be possible :)
[1:17] * bandrus (~brian@99.sub-70-211-76.myvzw.com) has joined #ceph
[1:18] <cetex> well, the network is 2gbit*9nodes
[1:19] * masteroman (~ivan@93-139-172-20.adsl.net.t-com.hr) has joined #ceph
[1:19] <cetex> so in theory it should max out at ~18gbit for sending data evenly distributed between all nodes.
[1:19] <cetex> *to all nodes.
[1:21] * BrianBailey (~brianbail@137.152.169.135) has joined #ceph
[1:29] * BrianBailey (~brianbail@137.152.169.135) Quit ()
[1:35] * bandrus (~brian@99.sub-70-211-76.myvzw.com) Quit (Ping timeout: 480 seconds)
[1:42] * fghaas (~florian@91-119-140-224.dynamic.xdsl-line.inode.at) Quit (Quit: Leaving.)
[1:48] * bandrus (~brian@181.sub-70-211-75.myvzw.com) has joined #ceph
[1:51] * sjm (~sjm@pool-173-70-76-86.nwrknj.fios.verizon.net) has left #ceph
[1:53] * Concubidated (~Adium@71.21.5.251) Quit (Quit: Leaving.)
[1:57] * bandrus (~brian@181.sub-70-211-75.myvzw.com) Quit (Ping timeout: 480 seconds)
[1:57] * oms101 (~oms101@p20030057EA031100EEF4BBFFFE0F7062.dip0.t-ipconnect.de) Quit (Ping timeout: 480 seconds)
[1:59] * Scaevolus (~ZombieL@98EAAATOU.tor-irc.dnsbl.oftc.net) has joined #ceph
[2:00] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[2:01] * wschulze (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) Quit (Quit: Leaving.)
[2:07] * oms101 (~oms101@p20030057EA02A200EEF4BBFFFE0F7062.dip0.t-ipconnect.de) has joined #ceph
[2:11] * bandrus (~brian@95.sub-70-211-66.myvzw.com) has joined #ceph
[2:17] * zack_dolby (~textual@nfmv003184.uqw.ppp.infoweb.ne.jp) has joined #ceph
[2:22] * saltlake (~saltlake@pool-71-96-110-5.dfw.dsl-w.verizon.net) Quit (Ping timeout: 480 seconds)
[2:22] * mykola (~Mikolaj@91.225.203.59) Quit (Quit: away)
[2:25] * bandrus1 (~brian@95.sub-70-211-66.myvzw.com) has joined #ceph
[2:27] * LeaChim (~LeaChim@host86-151-147-249.range86-151.btcentralplus.com) Quit (Ping timeout: 480 seconds)
[2:27] * badone_ (~brad@CPE-121-215-241-179.static.qld.bigpond.net.au) has joined #ceph
[2:28] * shyu (~Shanzhi@119.254.196.66) has joined #ceph
[2:29] * Scaevolus (~ZombieL@98EAAATOU.tor-irc.dnsbl.oftc.net) Quit ()
[2:29] * shyu (~Shanzhi@119.254.196.66) Quit ()
[2:29] * shyu (~Shanzhi@119.254.196.66) has joined #ceph
[2:29] * bandrus (~brian@95.sub-70-211-66.myvzw.com) Quit (Ping timeout: 480 seconds)
[2:31] * badone (~brad@CPE-121-215-241-179.static.qld.bigpond.net.au) Quit (Ping timeout: 480 seconds)
[2:32] * badone__ (~brad@CPE-121-215-241-179.static.qld.bigpond.net.au) has joined #ceph
[2:37] * lucas1 (~Thunderbi@218.76.52.64) has joined #ceph
[2:37] * badone_ (~brad@CPE-121-215-241-179.static.qld.bigpond.net.au) Quit (Ping timeout: 480 seconds)
[2:40] * arbrandes (~arbrandes@177.45.222.57) Quit (Quit: Leaving)
[2:44] * badone__ is now known as badone
[2:44] * diegows (~diegows@190.190.5.238) has joined #ceph
[2:45] * xarses_ (~andreww@12.164.168.117) Quit (Ping timeout: 480 seconds)
[2:46] * jaank_ (~quassel@98.215.50.223) has joined #ceph
[2:46] * bandrus1 (~brian@95.sub-70-211-66.myvzw.com) Quit (Remote host closed the connection)
[2:51] * xarses_ (~andreww@12.164.168.117) has joined #ceph
[2:53] * jaank (~quassel@98.215.50.223) Quit (Ping timeout: 480 seconds)
[2:58] * moore (~moore@64.202.160.233) Quit (Remote host closed the connection)
[2:58] * mliang2 (~oftc-webi@12.22.22.11) Quit (Remote host closed the connection)
[2:59] * Lite (~Mousey@37.187.129.166) has joined #ceph
[2:59] * haigang (~haigang@180.166.129.186) has joined #ceph
[3:03] * xarses_ (~andreww@12.164.168.117) Quit (Ping timeout: 480 seconds)
[3:06] * yanzheng (~zhyan@125.71.108.214) has joined #ceph
[3:07] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) has joined #ceph
[3:09] * puffy (~puffy@216.207.42.129) Quit (Ping timeout: 480 seconds)
[3:20] * doppelgrau (~doppelgra@pd956d116.dip0.t-ipconnect.de) Quit (Quit: doppelgrau)
[3:23] * bkopilov (~bkopilov@bzq-79-183-28-54.red.bezeqint.net) Quit (Ping timeout: 480 seconds)
[3:24] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[3:29] * Lite (~Mousey@98EAAATRT.tor-irc.dnsbl.oftc.net) Quit ()
[3:43] * debian112 (~bcolbert@24.126.201.64) Quit (Quit: Leaving.)
[3:47] * root (~root@pD9E9D970.dip0.t-ipconnect.de) has joined #ceph
[3:49] * xarses_ (~andreww@c-76-126-112-92.hsd1.ca.comcast.net) has joined #ceph
[3:53] * root4 (~root@p57B2E33B.dip0.t-ipconnect.de) Quit (Ping timeout: 480 seconds)
[3:57] * zhaochao (~zhaochao@111.161.17.97) has joined #ceph
[4:05] * PingKuo (~ping@122.146.93.152) has joined #ceph
[4:08] * kefu (~kefu@58.33.105.104) has joined #ceph
[4:10] * macjack (~macjack@122.146.93.152) Quit (Ping timeout: 480 seconds)
[4:15] * haomaiwang (~haomaiwan@182.48.117.114) has joined #ceph
[4:22] * Mika_c (~quassel@125.227.22.217) has joined #ceph
[4:23] * macjack (~macjack@122.146.93.152) has joined #ceph
[4:29] * Pettis (~Grimmer@95.130.15.98) has joined #ceph
[4:33] * wschulze (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) has joined #ceph
[4:37] * rongze (~rongze@182.48.117.114) has joined #ceph
[4:38] * reed (~reed@75-101-54-131.dsl.static.fusionbroadband.com) Quit (Quit: Ex-Chat)
[4:51] * kefu (~kefu@58.33.105.104) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[4:53] * sigsegv (~sigsegv@188.25.121.203) has joined #ceph
[4:54] * fam_away is now known as fam
[4:55] * kefu (~kefu@58.33.105.104) has joined #ceph
[4:56] * Concubidated (~Adium@71.21.5.251) has joined #ceph
[4:59] * Pettis (~Grimmer@425AAAFO4.tor-irc.dnsbl.oftc.net) Quit ()
[4:59] * Freddy (~Crisco@exit1.telostor.ca) has joined #ceph
[5:11] * joef1 (~Adium@2601:9:280:f2e:7529:bdc6:30f8:1a84) has joined #ceph
[5:25] * sjmtest (uid32746@id-32746.uxbridge.irccloud.com) Quit (Quit: Connection closed for inactivity)
[5:29] * Freddy (~Crisco@425AAAFPL.tor-irc.dnsbl.oftc.net) Quit ()
[5:29] * RaidSoft (~Xa@chomsky.torservers.net) has joined #ceph
[5:29] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) has joined #ceph
[5:34] <jcsalem> I'm using Ceph via librados. Two questions: (1) Is there any way to list or retrieve old versions of objects? I know Radosgw is starting to support this, but I'd like to do it via librados. AND (2) Is there any way to list just a subset of the objects in a pool based on a name prefix? (i.e., something like 'ls foo*')
[5:38] * joef1 (~Adium@2601:9:280:f2e:7529:bdc6:30f8:1a84) has left #ceph
[5:39] * macjack (~macjack@122.146.93.152) has left #ceph
[5:42] * Vacuum (~vovo@i59F796EE.versanet.de) has joined #ceph
[5:42] * Vacuum_ (~vovo@88.130.206.129) Quit (Read error: Connection reset by peer)
[5:44] * fdmanana (~fdmanana@bl5-3-113.dsl.telepac.pt) Quit (Ping timeout: 480 seconds)
[5:47] * Concubidated (~Adium@71.21.5.251) Quit (Quit: Leaving.)
[5:54] * fdmanana (~fdmanana@bl13-136-166.dsl.telepac.pt) has joined #ceph
[5:55] * shang (~ShangWu@69.80.100.214) has joined #ceph
[5:59] * RaidSoft (~Xa@3OZAAARCB.tor-irc.dnsbl.oftc.net) Quit ()
[5:59] * SinZ|offline (~Wizeon@dreamatorium.badexample.net) has joined #ceph
[6:08] * wschulze (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) Quit (Quit: Leaving.)
[6:23] * kanagaraj (~kanagaraj@115.241.25.103) has joined #ceph
[6:29] * SinZ|offline (~Wizeon@5NZAAA00P.tor-irc.dnsbl.oftc.net) Quit ()
[6:30] * bkopilov (~bkopilov@nat-pool-tlv-t.redhat.com) has joined #ceph
[6:32] * amote (~amote@121.244.87.116) has joined #ceph
[6:33] * matx1 (~dotblank@bg.tor-exit.neelc.org) has joined #ceph
[6:35] * jclm (~jclm@ip24-253-45-236.lv.lv.cox.net) has joined #ceph
[6:41] * Mika_c (~quassel@125.227.22.217) Quit (Ping timeout: 480 seconds)
[6:42] * jcsalem1 (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) has joined #ceph
[6:43] * joef1 (~Adium@c-24-130-254-66.hsd1.ca.comcast.net) has joined #ceph
[6:47] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) Quit (Ping timeout: 480 seconds)
[6:50] * kefu (~kefu@58.33.105.104) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[7:01] * jcsalem1 (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) Quit (Quit: Leaving.)
[7:02] * shang (~ShangWu@69.80.100.214) Quit (Ping timeout: 480 seconds)
[7:03] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) has joined #ceph
[7:03] * matx1 (~dotblank@98EAAATZ0.tor-irc.dnsbl.oftc.net) Quit ()
[7:03] * Random (~MJXII@hessel0.torservers.net) has joined #ceph
[7:04] * shylesh (~shylesh@121.244.87.124) has joined #ceph
[7:08] * vbellur (~vijay@122.172.166.249) Quit (Ping timeout: 480 seconds)
[7:11] * shang (~ShangWu@175.41.48.77) has joined #ceph
[7:13] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) Quit (Quit: Leaving.)
[7:15] * lalatenduM (~lalatendu@121.244.87.117) has joined #ceph
[7:17] * kanagaraj (~kanagaraj@115.241.25.103) Quit (Ping timeout: 480 seconds)
[7:21] * eoin (~eoin@89-93-153-201.hfc.dyn.abo.bbox.fr) has joined #ceph
[7:23] * jeevan_ullas (~Deependra@114.143.38.114) has joined #ceph
[7:24] * kefu (~kefu@58.33.105.104) has joined #ceph
[7:24] * jeevan_ullas (~Deependra@114.143.38.114) Quit ()
[7:25] * jeevan_ullas (~Deependra@114.143.38.114) has joined #ceph
[7:26] * kanagaraj (~kanagaraj@115.242.248.31) has joined #ceph
[7:33] * Random (~MJXII@425AAAFSA.tor-irc.dnsbl.oftc.net) Quit ()
[7:33] * Hejt (~hoopy@madiba.guilhem.org) has joined #ceph
[7:38] * vbellur (~vijay@121.244.87.117) has joined #ceph
[7:42] * karnan (~karnan@121.244.87.117) has joined #ceph
[7:48] * kefu (~kefu@58.33.105.104) Quit (Max SendQ exceeded)
[7:48] * kefu (~kefu@58.33.105.104) has joined #ceph
[7:50] * Hemanth (~Hemanth@121.244.87.117) has joined #ceph
[7:53] * joshd1 (~jdurgin@68-119-140-18.dhcp.ahvl.nc.charter.com) has joined #ceph
[7:53] * joshd1 (~jdurgin@68-119-140-18.dhcp.ahvl.nc.charter.com) Quit ()
[7:59] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) has joined #ceph
[8:01] <Nats> versions are called 'snaps' at low level of ceph
[8:01] * rdas (~rdas@121.244.87.116) has joined #ceph
[8:02] <Nats> if u search for snap on http://ceph.com/docs/master/rados/api/librados/ you'll probably find what you want
[8:02] * Mika_c (~quassel@125.227.22.217) has joined #ceph
[8:02] * haigang (~haigang@180.166.129.186) Quit (Quit: This computer has gone to sleep)
[8:02] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) Quit ()
[8:03] * Hejt (~hoopy@98EAAAT2M.tor-irc.dnsbl.oftc.net) Quit ()
[8:03] * _s1gma (~yuastnav@195.169.125.226) has joined #ceph
[8:03] * overclk (~overclk@121.244.87.117) has joined #ceph
[8:06] * lalatenduM (~lalatendu@121.244.87.117) Quit (Quit: Leaving)
[8:10] * lalatenduM (~lalatendu@121.244.87.117) has joined #ceph
[8:10] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has joined #ceph
[8:10] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has left #ceph
[8:27] * joef1 (~Adium@c-24-130-254-66.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[8:28] * joef1 (~Adium@c-24-130-254-66.hsd1.ca.comcast.net) has joined #ceph
[8:29] * KevinPerks (~Adium@cpe-75-177-32-14.triad.res.rr.com) Quit (Quit: Leaving.)
[8:33] * _s1gma (~yuastnav@2WVAAAT6R.tor-irc.dnsbl.oftc.net) Quit ()
[8:36] * Nacer (~Nacer@203-206-190-109.dsl.ovh.fr) Quit (Remote host closed the connection)
[8:36] * eoin (~eoin@89-93-153-201.hfc.dyn.abo.bbox.fr) Quit (Remote host closed the connection)
[8:38] * joef1 (~Adium@c-24-130-254-66.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[8:40] * oro (~oro@80-219-254-208.dclient.hispeed.ch) has joined #ceph
[8:42] * BillyBobJohn (~cyphase@hessel0.torservers.net) has joined #ceph
[8:43] * eedten1 (~eedten@212.117.81.27) has joined #ceph
[8:44] * fam is now known as fam_away
[8:46] * dugravot6 (~dugravot6@nat-persul-montet.wifi.univ-lorraine.fr) has joined #ceph
[8:46] * Concubidated (~Adium@71.21.5.251) has joined #ceph
[8:49] * kanagaraj (~kanagaraj@115.242.248.31) Quit (Quit: Leaving)
[8:53] * capri_on (~capri@212.218.127.222) Quit (Quit: Leaving)
[8:54] * eedten1 (~eedten@212.117.81.27) Quit (Ping timeout: 480 seconds)
[8:54] * capri (~capri@212.218.127.222) has joined #ceph
[8:54] * eedten (~eedten@212.117.81.27) has joined #ceph
[9:01] * overclk (~overclk@121.244.87.117) Quit (Ping timeout: 480 seconds)
[9:02] * Sysadmin88 (~IceChat77@94.4.7.123) Quit (Quit: The early bird may get the worm, but the second mouse gets the cheese)
[9:03] * kefu (~kefu@58.33.105.104) Quit (Max SendQ exceeded)
[9:03] * kefu (~kefu@58.33.105.104) has joined #ceph
[9:04] * eedten1 (~eedten@212.117.81.27) has joined #ceph
[9:04] * eedten (~eedten@212.117.81.27) Quit (Read error: Connection reset by peer)
[9:04] * kanagaraj (~kanagaraj@117.205.224.115) has joined #ceph
[9:06] * kawa2014 (~kawa@89.184.114.246) has joined #ceph
[9:08] * rotbeard (~redbeard@2a02:908:df10:d300:76f0:6dff:fe3b:994d) Quit (Quit: Verlassend)
[9:11] * analbeard (~shw@support.memset.com) has joined #ceph
[9:12] * dugravot6 (~dugravot6@nat-persul-montet.wifi.univ-lorraine.fr) Quit (Quit: Leaving.)
[9:12] * BillyBobJohn (~cyphase@1GLAAAWEN.tor-irc.dnsbl.oftc.net) Quit ()
[9:12] * Diablodoct0r (~dug@spftor4e1.privacyfoundation.ch) has joined #ceph
[9:14] * jordanP (~jordan@213.215.2.194) has joined #ceph
[9:16] * fam_away is now known as fam
[9:19] * fridim_ (~fridim@56-198-190-109.dsl.ovh.fr) has joined #ceph
[9:19] * oro (~oro@80-219-254-208.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[9:24] * derjohn_mob (~aj@94.119.1.11) has joined #ceph
[9:24] * bigtoch (~bigtoch@41.189.169.250) has joined #ceph
[9:26] * bitserker (~toni@88.87.194.130) has joined #ceph
[9:27] * fsimonce (~simon@host186-55-dynamic.21-79-r.retail.telecomitalia.it) has joined #ceph
[9:28] * overclk (~overclk@121.244.87.117) has joined #ceph
[9:29] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) has joined #ceph
[9:32] * jeevan_ullas (~Deependra@114.143.38.114) Quit (Ping timeout: 480 seconds)
[9:34] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has joined #ceph
[9:34] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) Quit ()
[9:34] * thomnico (~thomnico@2a01:e35:8b41:120:287f:5e1f:458e:1b9a) has joined #ceph
[9:42] * Diablodoct0r (~dug@2WVAAAUBL.tor-irc.dnsbl.oftc.net) Quit ()
[9:42] * Frostshifter (~Corti^car@98EAAAT7W.tor-irc.dnsbl.oftc.net) has joined #ceph
[9:43] * zW (~wesley@spider.pfoe.be) Quit (Quit: leaving)
[9:43] * dgurtner (~dgurtner@178.197.231.228) has joined #ceph
[9:47] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[9:48] * TMM (~hp@sams-office-nat.tomtomgroup.com) has joined #ceph
[9:54] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) has joined #ceph
[9:57] * rendar (~I@host107-140-dynamic.59-82-r.retail.telecomitalia.it) has joined #ceph
[9:57] * Concubidated (~Adium@71.21.5.251) Quit (Quit: Leaving.)
[10:02] * haigang (~haigang@180.166.129.186) has joined #ceph
[10:02] * mattronix (~quassel@fw1.sdc.mattronix.nl) Quit (Remote host closed the connection)
[10:02] * jordanP (~jordan@213.215.2.194) Quit (Ping timeout: 480 seconds)
[10:03] * fghaas (~florian@91-119-140-224.dynamic.xdsl-line.inode.at) has joined #ceph
[10:04] * mattronix (~quassel@fw1.sdc.mattronix.nl) has joined #ceph
[10:05] * fridim_ (~fridim@56-198-190-109.dsl.ovh.fr) Quit (Quit: Leaving)
[10:12] * Frostshifter (~Corti^car@98EAAAT7W.tor-irc.dnsbl.oftc.net) Quit ()
[10:12] * brannmar (~W|ldCraze@torsrvu.snydernet.net) has joined #ceph
[10:16] * wicope (~wicope@0001fd8a.user.oftc.net) has joined #ceph
[10:18] * jnq (~jnq@0001b7cc.user.oftc.net) Quit (Quit: WeeChat 0.3.7)
[10:19] * oro (~oro@2001:620:20:16:94b7:d096:2be4:977b) has joined #ceph
[10:22] * alram (~alram@194.66.249.137) has joined #ceph
[10:24] * Be-El (~quassel@fb08-bcf-pc01.computational.bio.uni-giessen.de) has joined #ceph
[10:24] * haigang (~haigang@180.166.129.186) Quit (Ping timeout: 480 seconds)
[10:24] * haigang (~haigang@180.166.129.186) has joined #ceph
[10:25] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Remote host closed the connection)
[10:25] * derjohn_mob (~aj@94.119.1.11) Quit (Ping timeout: 480 seconds)
[10:26] * jnq (~jnq@95.85.22.50) has joined #ceph
[10:26] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has left #ceph
[10:26] <Be-El> hi
[10:31] * calvinx (~calvin@103.7.202.198) has joined #ceph
[10:36] * jordanP (~jordan@scality-jouf-2-194.fib.nerim.net) has joined #ceph
[10:36] * jordanP (~jordan@scality-jouf-2-194.fib.nerim.net) Quit (Read error: Connection reset by peer)
[10:36] * jordanP (~jordan@scality-jouf-2-194.fib.nerim.net) has joined #ceph
[10:38] * derjohn_mob (~aj@fw.gkh-setu.de) has joined #ceph
[10:39] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) has joined #ceph
[10:42] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) Quit ()
[10:42] * brannmar (~W|ldCraze@5NZAAA1C4.tor-irc.dnsbl.oftc.net) Quit ()
[10:42] * mollstam (~DJComet@luna115.startdedicated.net) has joined #ceph
[10:42] * LeaChim (~LeaChim@host86-151-147-249.range86-151.btcentralplus.com) has joined #ceph
[10:43] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[10:43] * alexm (~alexm@000128d2.user.oftc.net) has left #ceph
[10:44] <Mika_c> Hello, all. Have anyone know how to remove a host???
[10:45] * fghaas1 (~florian@91-119-140-224.dynamic.xdsl-line.inode.at) has joined #ceph
[10:46] * fghaas (~florian@91-119-140-224.dynamic.xdsl-line.inode.at) Quit (Ping timeout: 480 seconds)
[10:46] * bigtoch (~bigtoch@41.189.169.250) Quit (Read error: Connection reset by peer)
[10:46] * bigtoch (~bigtoch@41.189.169.250) has joined #ceph
[10:50] * b0e (~aledermue@213.95.25.82) has joined #ceph
[10:52] * ChrisNBlum (~ChrisNBlu@178.255.153.117) has joined #ceph
[10:54] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Remote host closed the connection)
[10:56] * bitserker (~toni@88.87.194.130) Quit (Ping timeout: 480 seconds)
[10:58] * sigsegv (~sigsegv@188.25.121.203) has left #ceph
[11:03] <anorak> hi
[11:06] * bitserker (~toni@85.238.9.126) has joined #ceph
[11:06] * kefu is now known as kefu|afk
[11:12] * mollstam (~DJComet@2WVAAAUH0.tor-irc.dnsbl.oftc.net) Quit ()
[11:12] * spate (~raindog@kbtr2ce.tor-relay.me) has joined #ceph
[11:16] * chasmo77 (~chas77@158.183-62-69.ftth.swbr.surewest.net) Quit (Ping timeout: 480 seconds)
[11:16] <sugoruyo> Mika_c: what exactly are you trying to do?
[11:18] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[11:21] * calvinx (~calvin@103.7.202.198) Quit (Quit: calvinx)
[11:21] * zack_dolby (~textual@nfmv003184.uqw.ppp.infoweb.ne.jp) Quit (Quit: My MacBook has gone to sleep. ZZZzzz???)
[11:21] * chasmo77 (~chas77@158.183-62-69.ftth.swbr.surewest.net) has joined #ceph
[11:21] * calvinx (~calvin@103.7.202.198) has joined #ceph
[11:23] * kefu|afk (~kefu@58.33.105.104) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[11:24] * haigang (~haigang@180.166.129.186) Quit (Quit: This computer has gone to sleep)
[11:29] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[11:34] * calvinx (~calvin@103.7.202.198) Quit (Quit: calvinx)
[11:40] * haigang (~haigang@180.166.129.186) has joined #ceph
[11:40] * ngoswami (~ngoswami@121.244.87.116) has joined #ceph
[11:40] * badone (~brad@CPE-121-215-241-179.static.qld.bigpond.net.au) Quit (Quit: WeeChat 1.1.1)
[11:40] * kanagaraj_ (~kanagaraj@117.223.191.62) has joined #ceph
[11:40] * MACscr (~Adium@2601:d:c800:de3:d943:265e:a5d6:a9c4) Quit (Quit: Leaving.)
[11:41] <sugoruyo> Mika_c: OK, so you want to remove an entire host, with (assuming) a number of OSDs running on it?
[11:41] * kanagaraj (~kanagaraj@117.205.224.115) Quit (Ping timeout: 480 seconds)
[11:41] <Mika_c> Hello ,all. Hope someone can give me some idea.
[11:41] <Mika_c> My cluster have 3 host. And one host totaly dead. Right now my procedure is out the dead osd, crush remove dead osd, auth del dead osd and rm dead osd.
[11:41] <Mika_c> In the end, remove the dead host from crushmap.
[11:42] <sugoruyo> what's the problem?
[11:42] * spate (~raindog@98EAAAUBF.tor-irc.dnsbl.oftc.net) Quit ()
[11:44] <Mika_c> hummm... I want to sure the procedure is right.
[11:46] <sugoruyo> Mika_c: seems right to me
[11:46] <sugoruyo> if you have a single entry for each OSD on your ceph.conf file you should probably remove those too
[11:47] <sugoruyo> other than that I don't see how you could do it differently given a host died
[11:47] * visored (~Bj_o_rn@tor.nullbyte.me) has joined #ceph
[11:47] <sugoruyo> you could script it so it does the steps automatically
[11:50] <Mika_c> NP. Because the host deployed by "ceph-deploy". So the osds are not write into ceph.conf. Thank you again.
[11:50] * Mika_c (~quassel@125.227.22.217) Quit (Remote host closed the connection)
[11:50] * Mika_c (~quassel@125.227.22.217) has joined #ceph
[11:53] * branto (~branto@nat-pool-brq-t.redhat.com) has joined #ceph
[11:53] * Mika_c (~quassel@125.227.22.217) Quit (Remote host closed the connection)
[11:58] * ddiss (~ddiss@charybdis-ext.suse.de) has joined #ceph
[12:02] * PingKuo (~ping@122.146.93.152) Quit (Quit: Konversation terminated!)
[12:13] * wicope (~wicope@0001fd8a.user.oftc.net) Quit (Read error: Connection reset by peer)
[12:15] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Remote host closed the connection)
[12:15] * eedten1 (~eedten@212.117.81.27) Quit (Ping timeout: 480 seconds)
[12:17] * visored (~Bj_o_rn@425AAAFWU.tor-irc.dnsbl.oftc.net) Quit ()
[12:17] * AotC (~Zombiekil@tor-exit1.arbitrary.ch) has joined #ceph
[12:17] * wicope (~wicope@0001fd8a.user.oftc.net) has joined #ceph
[12:37] * haomaiwang (~haomaiwan@182.48.117.114) Quit (Remote host closed the connection)
[12:41] * shyu (~Shanzhi@119.254.196.66) Quit (Remote host closed the connection)
[12:43] * shang (~ShangWu@175.41.48.77) Quit (Quit: Ex-Chat)
[12:43] * chasmo77 (~chas77@158.183-62-69.ftth.swbr.surewest.net) Quit (Ping timeout: 480 seconds)
[12:44] * chasmo77 (~chas77@158.183-62-69.ftth.swbr.surewest.net) has joined #ceph
[12:47] * AotC (~Zombiekil@5NZAAA1HN.tor-irc.dnsbl.oftc.net) Quit ()
[12:48] * kanagaraj__ (~kanagaraj@117.213.131.96) has joined #ceph
[12:48] * kanagaraj_ (~kanagaraj@117.223.191.62) Quit (Ping timeout: 480 seconds)
[12:49] * kanagaraj__ (~kanagaraj@117.213.131.96) Quit ()
[12:49] * kanagaraj (~kanagaraj@117.213.131.96) has joined #ceph
[12:50] * bilco105 is now known as bilco105_
[12:52] * bilco105_ is now known as bilco105
[12:55] * haigang (~haigang@180.166.129.186) Quit (Quit: This computer has gone to sleep)
[12:55] * karnan (~karnan@121.244.87.117) Quit (Remote host closed the connection)
[13:02] <pmatulis_> i used to have to put "public network" in ceph.conf to be able to add monitors later. is that still required?
[13:02] * lmb (~lmb@2a02:8109:8100:1d2c:e0ef:70a9:f84c:c8ca) has joined #ceph
[13:09] * eedten (~eedten@212.117.81.27) has joined #ceph
[13:17] * Sami345 (~Xerati@tor-exit.server9.tvdw.eu) has joined #ceph
[13:26] * kanagaraj (~kanagaraj@117.213.131.96) Quit (Ping timeout: 480 seconds)
[13:28] * kanagaraj (~kanagaraj@117.216.102.45) has joined #ceph
[13:29] * kanagaraj (~kanagaraj@117.216.102.45) Quit ()
[13:29] * kanagaraj (~kanagaraj@117.216.102.45) has joined #ceph
[13:34] * shylesh (~shylesh@121.244.87.124) Quit (Remote host closed the connection)
[13:35] * vbellur (~vijay@121.244.87.117) Quit (Ping timeout: 480 seconds)
[13:39] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[13:42] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) Quit (Remote host closed the connection)
[13:42] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) has joined #ceph
[13:44] * evilrob00 (~evilrob00@cpe-72-179-3-209.austin.res.rr.com) Quit (Remote host closed the connection)
[13:45] * KevinPerks (~Adium@cpe-75-177-32-14.triad.res.rr.com) has joined #ceph
[13:47] * Sami345 (~Xerati@2WVAAAUSD.tor-irc.dnsbl.oftc.net) Quit ()
[13:47] * QuantumBeep (~Arfed@50.7.205.130) has joined #ceph
[13:49] * Hemanth (~Hemanth@121.244.87.117) Quit (Ping timeout: 480 seconds)
[13:49] * MACscr (~Adium@2601:d:c800:de3:1529:8e7c:1f9c:9cfa) has joined #ceph
[14:00] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) has joined #ceph
[14:00] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) Quit (Quit: Leaving.)
[14:01] * lx0 (~aoliva@lxo.user.oftc.net) has joined #ceph
[14:01] * rongze (~rongze@182.48.117.114) Quit (Remote host closed the connection)
[14:03] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) has joined #ceph
[14:07] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[14:07] * kefu (~kefu@58.33.105.104) has joined #ceph
[14:12] * c4tech (~c4tech@199.91.185.156) Quit (Ping timeout: 480 seconds)
[14:12] * linjan (~linjan@195.110.41.9) has joined #ceph
[14:13] * jcsalem (~Jim@pool-108-49-214-102.bstnma.fios.verizon.net) Quit (Quit: Leaving.)
[14:15] * kefu (~kefu@58.33.105.104) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[14:15] * shaunm (~shaunm@74.215.76.114) Quit (Ping timeout: 480 seconds)
[14:15] * c4tech (~c4tech@199.91.185.156) has joined #ceph
[14:17] * QuantumBeep (~Arfed@98EAAAUF6.tor-irc.dnsbl.oftc.net) Quit ()
[14:17] * OODavo (~ahmeni@h-213.61.149.100.host.de.colt.net) has joined #ceph
[14:18] * bkopilov (~bkopilov@nat-pool-tlv-t.redhat.com) Quit (Ping timeout: 480 seconds)
[14:23] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) has joined #ceph
[14:24] * kefu (~kefu@58.33.105.104) has joined #ceph
[14:26] * haomaiwang (~haomaiwan@114.111.166.250) has joined #ceph
[14:28] * c4tech (~c4tech@199.91.185.156) Quit (Ping timeout: 480 seconds)
[14:29] * linjan (~linjan@195.110.41.9) Quit (Ping timeout: 480 seconds)
[14:32] * bilco105 is now known as bilco105_
[14:33] * kefu (~kefu@58.33.105.104) Quit (Max SendQ exceeded)
[14:34] * kefu (~kefu@58.33.105.104) has joined #ceph
[14:34] * kanagaraj_ (~kanagaraj@117.216.98.75) has joined #ceph
[14:36] * shaunm (~shaunm@172.56.12.34) has joined #ceph
[14:41] * tupper_ (~tcole@rtp-isp-nat1.cisco.com) Quit (Read error: Connection reset by peer)
[14:41] * kanagaraj (~kanagaraj@117.216.102.45) Quit (Ping timeout: 480 seconds)
[14:42] * hetz (~oftc-webi@bzq-79-183-211-186.red.bezeqint.net) has joined #ceph
[14:42] * kefu (~kefu@58.33.105.104) Quit (Max SendQ exceeded)
[14:42] * kefu (~kefu@58.33.105.104) has joined #ceph
[14:43] <hetz> Hi. I got the new book to learn about ceph and I'm following the instructions, but when I try create mon on other ceph nodes, it fails
[14:44] * sjm (~sjm@pool-173-70-76-86.nwrknj.fios.verizon.net) has joined #ceph
[14:44] <hetz> This happens on the other 2 members (node2, node3): [ceph-node3][ERROR ] admin_socket: exception getting command descriptions: [Errno 2] No such file or directory
[14:45] * kefu (~kefu@58.33.105.104) Quit (Max SendQ exceeded)
[14:45] * kefu (~kefu@58.33.105.104) has joined #ceph
[14:47] * OODavo (~ahmeni@2WVAAAUV7.tor-irc.dnsbl.oftc.net) Quit ()
[14:47] * hellertime (~Adium@a23-79-238-10.deploy.static.akamaitechnologies.com) has joined #ceph
[14:49] * karnan (~karnan@106.51.240.32) has joined #ceph
[14:51] * bilco105_ is now known as bilco105
[14:55] * vbellur (~vijay@122.172.166.249) has joined #ceph
[14:55] * hetz (~oftc-webi@bzq-79-183-211-186.red.bezeqint.net) Quit (Remote host closed the connection)
[14:56] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[14:57] * wschulze (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) has joined #ceph
[14:58] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Remote host closed the connection)
[14:58] * kefu (~kefu@58.33.105.104) Quit (Max SendQ exceeded)
[14:59] * _prime_ (~oftc-webi@199.168.44.192) has joined #ceph
[15:03] * kefu (~kefu@58.33.105.104) has joined #ceph
[15:05] * DV (~veillard@2001:41d0:1:d478::1) Quit (Ping timeout: 480 seconds)
[15:06] * kefu (~kefu@58.33.105.104) Quit (Max SendQ exceeded)
[15:08] * kefu (~kefu@58.33.105.104) has joined #ceph
[15:12] * vpol (~vpol@000131a0.user.oftc.net) has joined #ceph
[15:12] * RayTracer (~RayTracer@153.19.7.39) has joined #ceph
[15:12] <anorak> hetz: how are you creating the monitor nodes?
[15:13] * ksingh (~Adium@2001:708:10:10:f160:3fb1:cc96:a88a) has joined #ceph
[15:14] * DV (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[15:14] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[15:15] * georgem (~Adium@fwnat.oicr.on.ca) has joined #ceph
[15:16] <ksingh> monitor not able to form quorum , and all the monitors are down , cluster unreachable http://paste.ubuntu.com/10723915/
[15:16] <ksingh> any idea why monitors are flapping http://paste.ubuntu.com/10723915/
[15:17] * CobraKhan007 (~curtis864@tor-exit.server9.tvdw.eu) has joined #ceph
[15:19] <anorak> ksingh: I assume network is stable. Correct?
[15:19] * harold (~hamiller@71-94-227-66.dhcp.mdfd.or.charter.com) has joined #ceph
[15:21] * yanzheng (~zhyan@125.71.108.214) Quit (Quit: This computer has gone to sleep)
[15:21] * lucas1 (~Thunderbi@218.76.52.64) Quit (Remote host closed the connection)
[15:21] * yanzheng (~zhyan@125.71.108.214) has joined #ceph
[15:22] * karnan (~karnan@106.51.240.32) Quit (Ping timeout: 480 seconds)
[15:23] * tupper_ (~tcole@2001:420:2280:1272:8900:f9b8:3b49:567e) has joined #ceph
[15:25] <ksingh> anorak: yes no problem with network / firewall
[15:26] <ksingh> this problem came when i marked an osd LOST
[15:26] <ksingh> now all the 3 monitors are out of quorum , cluster unreachable
[15:26] * bdonnahue (~James@24-148-51-171.c3-0.mart-ubr1.chi-mart.il.cable.rcn.com) has left #ceph
[15:26] <anorak> ksingh: I dont think marking the OSD as LOST should make the monitors unstable unless both the problematic storage node and OSD share something in common
[15:27] <anorak> problematic storage node and mon* node share
[15:29] <anorak> ksingh: I had this problem once. What I did were the following steps. I disabled the interface on which the mon nodes communicate
[15:29] <anorak> ksingh: then i rebooted the mon nodes. Once they were up and running
[15:29] <anorak> ksingh: I would verify that the network comm b/w storage and mon are OK and without any packet loss
[15:30] <anorak> ksingh: then I would enable the interface one by one giving each node atleast 5 minutes
[15:30] <anorak> ksingh: That solved my problem. You could give it a try this way. Hope this helps!
[15:31] * linuxkidd (~linuxkidd@166.170.53.210) has joined #ceph
[15:36] <ksingh> anorak: thanks i will try this
[15:38] * zigo (quasselcor@ipv6-ftp.gplhost.com) Quit (Remote host closed the connection)
[15:41] * zigo_ is now known as zigo
[15:44] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) Quit (Remote host closed the connection)
[15:45] * i_m (~ivan.miro@deibp9eh1--blueice2n2.emea.ibm.com) has joined #ceph
[15:46] * rdas (~rdas@121.244.87.116) Quit (Quit: Leaving)
[15:47] * CobraKhan007 (~curtis864@2WVAAAU04.tor-irc.dnsbl.oftc.net) Quit ()
[15:48] * yanzheng (~zhyan@125.71.108.214) Quit (Quit: This computer has gone to sleep)
[15:50] * scuttle|afk is now known as scuttlemonkey
[15:51] * kanagaraj_ (~kanagaraj@117.216.98.75) Quit (Quit: Leaving)
[15:53] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) has joined #ceph
[15:54] * rongze (~rongze@124.126.237.197) has joined #ceph
[15:56] * diegows (~diegows@190.190.5.238) Quit (Ping timeout: 480 seconds)
[15:57] * ddiss (~ddiss@charybdis-ext.suse.de) Quit (Remote host closed the connection)
[16:02] * ircolle (~Adium@c-71-229-136-109.hsd1.co.comcast.net) has joined #ceph
[16:03] * overclk (~overclk@121.244.87.117) Quit (Ping timeout: 480 seconds)
[16:05] * ksingh (~Adium@2001:708:10:10:f160:3fb1:cc96:a88a) has left #ceph
[16:07] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[16:07] * debian112 (~bcolbert@24.126.201.64) has joined #ceph
[16:08] * Be-El (~quassel@fb08-bcf-pc01.computational.bio.uni-giessen.de) Quit (Remote host closed the connection)
[16:08] * masterom1 (~ivan@93-139-205-154.adsl.net.t-com.hr) has joined #ceph
[16:08] * sankarshan (~sankarsha@121.244.87.117) Quit (Quit: Are you sure you want to quit this channel (Cancel/Ok) ?)
[16:11] * kefu (~kefu@58.33.105.104) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[16:11] * vata (~vata@208.88.110.46) has joined #ceph
[16:14] * bkopilov (~bkopilov@bzq-109-66-174-12.red.bezeqint.net) has joined #ceph
[16:15] * masteroman (~ivan@93-139-172-20.adsl.net.t-com.hr) Quit (Ping timeout: 480 seconds)
[16:16] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Remote host closed the connection)
[16:17] * Misacorp (~Frymaster@hessel2.torservers.net) has joined #ceph
[16:18] * evilrob00 (~evilrob00@cpe-24-28-12-195.austin.res.rr.com) has joined #ceph
[16:22] * eedten (~eedten@212.117.81.27) Quit (Quit: Leaving)
[16:26] * daniel2_ (~daniel2_@cpe-24-28-6-151.austin.res.rr.com) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[16:27] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[16:27] * vbellur (~vijay@122.172.166.249) Quit (Ping timeout: 480 seconds)
[16:29] * danieljh (~daniel@0001b4e9.user.oftc.net) has joined #ceph
[16:37] * bigtoch (~bigtoch@41.189.169.250) Quit (Remote host closed the connection)
[16:37] * kefu (~kefu@58.33.105.104) has joined #ceph
[16:38] * bkopilov (~bkopilov@bzq-109-66-174-12.red.bezeqint.net) Quit (Ping timeout: 480 seconds)
[16:38] * vbellur (~vijay@122.172.54.162) has joined #ceph
[16:39] * DV_ (~veillard@2001:41d0:1:d478::1) has joined #ceph
[16:39] * lalatenduM (~lalatendu@121.244.87.117) Quit (Quit: Leaving)
[16:45] * DV (~veillard@2001:41d0:a:f29f::1) Quit (Ping timeout: 480 seconds)
[16:47] * Misacorp (~Frymaster@425AAAFZ9.tor-irc.dnsbl.oftc.net) Quit ()
[16:47] * mLegion (~Enikma@62-210-170-27.rev.poneytelecom.eu) has joined #ceph
[16:50] * xcezzz1 (~Adium@pool-100-3-14-19.tampfl.fios.verizon.net) has joined #ceph
[16:50] * xcezzz (~Adium@pool-100-3-14-19.tampfl.fios.verizon.net) Quit (Read error: Connection reset by peer)
[16:51] * saltlake (~saltlake@12.250.199.170) has joined #ceph
[16:56] * lpabon (~quassel@24-151-54-34.dhcp.nwtn.ct.charter.com) has joined #ceph
[16:56] * wushudoin (~wushudoin@209.132.181.86) has joined #ceph
[16:57] * ircolle is now known as ircolle-afk
[16:57] * branto (~branto@nat-pool-brq-t.redhat.com) has left #ceph
[16:57] * bene (~ben@nat-pool-bos-t.redhat.com) has joined #ceph
[16:59] * scuttlemonkey is now known as scuttle|afk
[17:03] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) Quit (Remote host closed the connection)
[17:03] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) has joined #ceph
[17:04] * DV_ (~veillard@2001:41d0:1:d478::1) Quit (Ping timeout: 480 seconds)
[17:05] * analbeard (~shw@support.memset.com) Quit (Quit: Leaving.)
[17:06] * thomnico (~thomnico@2a01:e35:8b41:120:287f:5e1f:458e:1b9a) Quit (Quit: Ex-Chat)
[17:06] * thomnico (~thomnico@2a01:e35:8b41:120:287f:5e1f:458e:1b9a) has joined #ceph
[17:12] * DV_ (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[17:13] * xoritor (~xoritor@cpe-72-177-85-116.austin.res.rr.com) Quit (Remote host closed the connection)
[17:13] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[17:16] * evilrob00 (~evilrob00@cpe-24-28-12-195.austin.res.rr.com) Quit (Remote host closed the connection)
[17:17] * mLegion (~Enikma@5NZAAA1SE.tor-irc.dnsbl.oftc.net) Quit ()
[17:17] * sixofour (~JamesHarr@chulak.enn.lu) has joined #ceph
[17:22] * nils______ (~nils@doomstreet.collins.kg) Quit (Quit: This computer has gone to sleep)
[17:24] * RayTracer (~RayTracer@153.19.7.39) Quit (Remote host closed the connection)
[17:25] * evilrob00 (~evilrob00@cpe-72-179-3-209.austin.res.rr.com) has joined #ceph
[17:26] * vbellur (~vijay@122.172.54.162) Quit (Ping timeout: 480 seconds)
[17:27] * daniel2_ (~daniel2_@209.163.140.194) has joined #ceph
[17:29] * thomnico (~thomnico@2a01:e35:8b41:120:287f:5e1f:458e:1b9a) Quit (Quit: Ex-Chat)
[17:32] * joshd1 (~jdurgin@68-119-140-18.dhcp.ahvl.nc.charter.com) has joined #ceph
[17:35] * ircolle-afk is now known as ircolle
[17:35] * xarses_ (~andreww@c-76-126-112-92.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[17:35] * moore (~moore@64.202.160.88) has joined #ceph
[17:36] * sugoruyo (~georgev@paarthurnax.esc.rl.ac.uk) Quit (Quit: I'm going home!)
[17:39] * alram (~alram@194.66.249.137) Quit (Quit: leaving)
[17:40] * vbellur (~vijay@122.171.77.26) has joined #ceph
[17:46] * oro (~oro@2001:620:20:16:94b7:d096:2be4:977b) Quit (Ping timeout: 480 seconds)
[17:47] * sixofour (~JamesHarr@425AAAF0T.tor-irc.dnsbl.oftc.net) Quit ()
[17:48] * alram (~alram@194.66.249.137) has joined #ceph
[17:48] * zack_dolby (~textual@pa3b3a1.tokynt01.ap.so-net.ne.jp) has joined #ceph
[17:49] * yanzheng (~zhyan@125.71.108.214) has joined #ceph
[17:50] * angdraug (~angdraug@c-50-174-102-105.hsd1.ca.comcast.net) has joined #ceph
[17:50] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) Quit (Remote host closed the connection)
[17:52] * Sysadmin88 (~IceChat77@94.4.7.123) has joined #ceph
[17:54] * shaunm (~shaunm@172.56.12.34) Quit (Ping timeout: 480 seconds)
[17:54] * jcsp1 (~Adium@82-71-16-249.dsl.in-addr.zen.co.uk) has left #ceph
[17:55] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) has joined #ceph
[17:57] * harold (~hamiller@71-94-227-66.dhcp.mdfd.or.charter.com) Quit (Quit: Leaving)
[17:59] * bandrus (~brian@95.sub-70-211-66.myvzw.com) has joined #ceph
[17:59] <visbits> i just restarted the OSD that were having block requested and were back to health OK, what causes blocked requests in the first place?
[18:01] * lpabon (~quassel@24-151-54-34.dhcp.nwtn.ct.charter.com) Quit (Remote host closed the connection)
[18:02] * b0e (~aledermue@213.95.25.82) Quit (Quit: Leaving.)
[18:02] * wschulze (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) Quit (Quit: Leaving.)
[18:03] * vpol (~vpol@000131a0.user.oftc.net) Quit (Quit: vpol)
[18:03] * Meths_ (~meths@2.25.223.121) has joined #ceph
[18:04] * hellertime (~Adium@a23-79-238-10.deploy.static.akamaitechnologies.com) Quit (Read error: Connection reset by peer)
[18:04] * hellertime (~Adium@72.246.0.14) has joined #ceph
[18:05] * derjohn_mob (~aj@fw.gkh-setu.de) Quit (Ping timeout: 480 seconds)
[18:08] * karnan (~karnan@106.51.240.32) has joined #ceph
[18:09] * Meths (~meths@2.27.87.77) Quit (Ping timeout: 480 seconds)
[18:09] * yanzheng (~zhyan@125.71.108.214) Quit (Quit: This computer has gone to sleep)
[18:12] * xarses_ (~andreww@12.164.168.117) has joined #ceph
[18:13] * kefu (~kefu@58.33.105.104) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[18:14] <visbits> is Giant considered *stable*? or is firefly stable
[18:14] <m0zes> giant is a stable, not an LTS.
[18:15] <visbits> ive broken giant many times now it seems
[18:15] <m0zes> firefly is the previous LTS. hammer (hopefully being release soon) is the new LTS.
[18:15] <visbits> lots of fixes and performance improvements with hammer?
[18:16] <m0zes> supposedly. I'm deploying giant atm. will move to hammer as soon as it is a proper release.
[18:19] * wschulze (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) has joined #ceph
[18:20] <visbits> im seeing really inconsistent performance with my giant cluster
[18:20] <visbits> ive had to restart my OSDs twice to fix it
[18:21] * borourke (~borourke@0001ff66.user.oftc.net) Quit (Ping timeout: 480 seconds)
[18:22] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Ping timeout: 480 seconds)
[18:22] * DV_ (~veillard@2001:41d0:a:f29f::1) Quit (Remote host closed the connection)
[18:23] * DV (~veillard@2001:41d0:1:d478::1) has joined #ceph
[18:24] * lalatenduM (~lalatendu@122.172.96.54) has joined #ceph
[18:26] * RayTracer (~RayTracer@host-81-190-2-156.gdynia.mm.pl) has joined #ceph
[18:29] * lcurtis (~lcurtis@47.19.105.250) has joined #ceph
[18:30] * vbellur (~vijay@122.171.77.26) Quit (Ping timeout: 480 seconds)
[18:30] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) Quit (Read error: Connection reset by peer)
[18:30] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) has joined #ceph
[18:31] <lcurtis> Hello all...we are getting expected performance from ceph cluster and rados bench looks okay, but extremely low performance from radosgw in .93 hammer...have tried apache fastcgi, nginx, tengine with same results
[18:32] <lcurtis> trying to build a 5pb cluster that will house 37 billion objects eventually
[18:33] * Sysadmin88 (~IceChat77@94.4.7.123) Quit (Quit: Friends help you move. Real friends help you move bodies.)
[18:34] <lcurtis> any ideas or anyone have rgw experience?
[18:34] <visbits> jesus what are you storing lol
[18:35] <bstillwell> What metric are you using to measure performance?
[18:35] <lcurtis> cosbench
[18:35] <bstillwell> Latency? Throughput?
[18:35] <lcurtis> both...
[18:35] <lcurtis> iperf looks okay
[18:35] <lcurtis> not network related
[18:36] <bstillwell> It's been a while since I've used rgw (switched jobs and now doing mostly rbd), but I remember you needed to do most things in parallel to get good perf.
[18:37] <bstillwell> I was looking at around the same number of objects too... Image hosting site? :)
[18:37] <lcurtis> cloud type storage
[18:37] <m0zes> 5pb of data? probably movies.
[18:37] <bstillwell> Also what is your HDD to SSD ratio for journals?
[18:38] * glzhao (~glzhao@203.90.249.185) Quit (Ping timeout: 480 seconds)
[18:38] <bstillwell> not movies with 37 billion objects
[18:38] <lcurtis> seeing response times of 2500 ms and like 3MB/s
[18:38] <bstillwell> That's not right
[18:38] <bstillwell> Is the cluster healthy?
[18:38] <lcurtis> no, i thought so
[18:38] * zedle (~oftc-webi@47.19.105.250) has joined #ceph
[18:38] <lcurtis> cluster healthy and looks good on rados side
[18:39] <lcurtis> just rgw non performant
[18:39] <lcurtis> wondering if something in .93 or some hidden gotcha
[18:39] <bstillwell> Are you co-locating the journals on the drives or using SSDs?
[18:39] <visbits> lcurtis how many osds are in your cluster right now
[18:39] <lcurtis> using ssd's
[18:39] <lcurtis> 180 osds
[18:39] <bstillwell> What's the ratio of spinners to SSDs?
[18:39] <lcurtis> just as a test
[18:40] <lcurtis> 30 spinners to 6 ssds
[18:40] * vbellur (~vijay@122.171.91.36) has joined #ceph
[18:41] <bstillwell> 5:1 is a little high, but should only affect writes and recovery operations.
[18:41] * joshd1 (~jdurgin@68-119-140-18.dhcp.ahvl.nc.charter.com) Quit (Quit: Leaving.)
[18:41] <bstillwell> Are those response times for reads or writes?
[18:41] <lcurtis> <bstillwell> yes...this is for testing purposes
[18:41] <lcurtis> those response times are for writes
[18:41] <lcurtis> again...fine on rados
[18:41] <lcurtis> radosbench
[18:41] <lcurtis> but just through rgw
[18:42] <lcurtis> we're looking to get very high write throughput
[18:42] <bstillwell> I don't have any ideas right now, but you should write up an email describing your setup and results and send it to the ceph-users list.
[18:43] <lcurtis> <bstillwell> thanks...was just discussing that with a colleague and that will be my next step
[18:43] <lcurtis> <bstillwell> thanks for your reply and affirmation...will get started on that email
[18:43] <visbits> the ceph-users list is broken for me
[18:43] <bstillwell> Good luck, I'll be interested to see what others have to say.
[18:43] <visbits> i email it and never get anything back
[18:44] <bstillwell> You won't get your own emails back
[18:44] <bstillwell> just responses
[18:44] <visbits> i dont get any emails from the userlist at all
[18:44] <visbits> lol
[18:44] <bstillwell> I get like 30/day
[18:44] <bstillwell> sometimes more
[18:45] * bkopilov (~bkopilov@bzq-79-178-113-254.red.bezeqint.net) has joined #ceph
[18:46] * kawa2014 (~kawa@89.184.114.246) Quit (Quit: Leaving)
[18:46] * gregmark (~Adium@68.87.42.115) has joined #ceph
[18:47] <bstillwell> lcurtis: When I was doing a 100 million object test I ran into a few issues that might interest you.
[18:47] * CoMa (~WedTM@98EAAAURV.tor-irc.dnsbl.oftc.net) has joined #ceph
[18:47] <lcurtis> bstillwell for sure
[18:47] <bstillwell> objects per container was a big one
[18:47] <bstillwell> once you go over 1 million objects/container it really starts slowing down.
[18:48] <bstillwell> So you'll need to evenly distribute objects across at least 37,000 containers, probably more
[18:49] <lcurtis> interesting...we ran into that problem with swift...did not realize ceph had similar phenomenon
[18:49] <lcurtis> objects/container limitation
[18:49] <bstillwell> Another problem was with XFS and small objects. I think my average file size was around 60KiB, so you may not have the problem with your 150KiB objects, but XFS was reporting a full condition when the drive was 70% full.
[18:50] <bstillwell> Which caused a cascading failure for me in my testing. Once the first OSD hit ~70% it was kicked out of the cluster, then the recovery operations started doing that to the rest of the OSDs until it was quite a mess.
[18:51] <lcurtis> ouch...but you are now running in prod?
[18:52] * rongze (~rongze@124.126.237.197) Quit (Remote host closed the connection)
[18:52] <bstillwell> nope, couldn't convince the higher powers to use ceph (former traditional storage guys). So I switched jobs and am now doing ceph on a large private cloud for block storage.
[18:53] * mykola (~Mikolaj@91.225.203.59) has joined #ceph
[18:54] <lcurtis> very cool
[18:56] * RayTracer (~RayTracer@host-81-190-2-156.gdynia.mm.pl) Quit (Remote host closed the connection)
[18:56] * jordanP (~jordan@scality-jouf-2-194.fib.nerim.net) Quit (Quit: Leaving)
[18:57] * glzhao (~glzhao@203.90.249.185) has joined #ceph
[18:58] <theanalyst> bstillwell: what sort of tools did you use to populate around 150 mill objects?
[18:59] * lalatenduM (~lalatendu@122.172.96.54) Quit (Quit: Leaving)
[19:00] <bstillwell> theanalyst: I think I used the python api, but it's been about a year. Maybe gnu parallel and curl.
[19:01] <theanalyst> bstillwell: ah fine.. planning to do something like that for our cluster as well
[19:02] * i_m (~ivan.miro@deibp9eh1--blueice2n2.emea.ibm.com) Quit (Ping timeout: 480 seconds)
[19:03] <bstillwell> Re-using connections and not spanning lots of processes is good advice.
[19:03] <bstillwell> spawning...
[19:04] * derjohn_mob (~aj@88.128.80.66) has joined #ceph
[19:04] <theanalyst> hmm sure
[19:06] * hellertime (~Adium@72.246.0.14) Quit (Quit: Leaving.)
[19:08] * shaunm (~shaunm@172.56.12.216) has joined #ceph
[19:08] * kawa2014 (~kawa@89.184.114.246) has joined #ceph
[19:08] * shaunm (~shaunm@172.56.12.216) Quit (Remote host closed the connection)
[19:08] * kawa2014 (~kawa@89.184.114.246) Quit ()
[19:08] * shaunm (~shaunm@172.56.12.216) has joined #ceph
[19:09] * hellertime (~Adium@23.79.238.10) has joined #ceph
[19:10] * lcurtis (~lcurtis@47.19.105.250) Quit (Ping timeout: 480 seconds)
[19:10] * dupont-y (~dupont-y@2a01:e34:ec92:8070:353b:4f62:aa4c:134b) has joined #ceph
[19:11] * bitserker (~toni@85.238.9.126) Quit (Ping timeout: 480 seconds)
[19:16] * sbfox (~Adium@72.2.49.50) has joined #ceph
[19:17] * CoMa (~WedTM@98EAAAURV.tor-irc.dnsbl.oftc.net) Quit ()
[19:21] * basicxman (~jakekosbe@tor-exit1.arbitrary.ch) has joined #ceph
[19:23] * karnan (~karnan@106.51.240.32) Quit (Ping timeout: 480 seconds)
[19:24] * zedle (~oftc-webi@47.19.105.250) Quit (Remote host closed the connection)
[19:24] * oro (~oro@80-219-254-208.dclient.hispeed.ch) has joined #ceph
[19:28] * Meths_ is now known as Meths
[19:29] * sbfox (~Adium@72.2.49.50) Quit (Quit: Leaving.)
[19:30] * rongze (~rongze@124.126.237.197) has joined #ceph
[19:31] * lx0 (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[19:31] * Concubidated (~Adium@2607:f298:b:635:5cc4:a00a:f0aa:8199) has joined #ceph
[19:33] * sbfox (~Adium@72.2.49.50) has joined #ceph
[19:37] * derjohn_mob (~aj@88.128.80.66) Quit (Ping timeout: 480 seconds)
[19:50] * brutuscat (~brutuscat@93.Red-88-1-121.dynamicIP.rima-tde.net) Quit (Remote host closed the connection)
[19:51] * basicxman (~jakekosbe@98EAAAUS9.tor-irc.dnsbl.oftc.net) Quit ()
[19:53] * linjan (~linjan@80.179.241.26) has joined #ceph
[19:56] * PeterRabbit (~BlS@tor-exit.server7.tvdw.eu) has joined #ceph
[19:59] * Kioob (~Kioob@2a01:e34:ec0a:c0f0:7e7a:91ff:fe3c:6865) has joined #ceph
[20:01] * rongze (~rongze@124.126.237.197) Quit (Remote host closed the connection)
[20:02] * angdraug (~angdraug@c-50-174-102-105.hsd1.ca.comcast.net) Quit (Quit: Leaving)
[20:02] * puffy (~puffy@216.207.42.129) has joined #ceph
[20:09] * DV (~veillard@2001:41d0:1:d478::1) Quit (Remote host closed the connection)
[20:09] * DV (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[20:11] * jrankin (~jrankin@d53-64-170-236.nap.wideopenwest.com) has joined #ceph
[20:14] * RayTracer (~RayTracer@host-81-190-2-156.gdynia.mm.pl) has joined #ceph
[20:20] * RayTracer (~RayTracer@host-81-190-2-156.gdynia.mm.pl) Quit (Remote host closed the connection)
[20:22] * sherlocked (~watson@14.139.82.6) has joined #ceph
[20:23] * sherlocked (~watson@14.139.82.6) Quit ()
[20:24] <cetex> so.. we're looking at creating our own s3-like service with ceph. average file size is 500-600kb, we write around 600 files per second, and need to store at least one weeks worth of data. 362M objects over a week.
[20:25] <cetex> do we need to split this between "buckets"? what about leveldb?
[20:26] * PeterRabbit (~BlS@5NZAAA10H.tor-irc.dnsbl.oftc.net) Quit ()
[20:26] * raindog (~Keiya@dreamatorium.badexample.net) has joined #ceph
[20:26] * TMM (~hp@sams-office-nat.tomtomgroup.com) Quit (Quit: Ex-Chat)
[20:29] * linjan (~linjan@80.179.241.26) Quit (Ping timeout: 480 seconds)
[20:30] * JayJ (~jayj@157.130.21.226) has joined #ceph
[20:30] <bstillwell> cetex: from my experience you don't want to do much over 1M objects per container, but I don't know if that has changed in the last year.
[20:31] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[20:31] <bstillwell> I can't answer the leveldb question. Using it with KeyValueStore to replace FileStore seems promising to me, but haven't played with it.
[20:33] <cetex> hm.. yeah.
[20:33] <cetex> i'll need to read up on that.
[20:33] <JayJ> Hello - We have millions of smaller (less than a MB) files. I was wondering whether HDFS interface is better or the CephFS for the usecase? Anybody have ideas?
[20:35] <cetex> but i guess that size doesn't matter much
[20:35] <visbits> JayJ cephfs isnt production ready
[20:35] <visbits> and its not fast
[20:37] <JayJ> cetex: visbits: Thanks - what would be an optimal solution for a need, that would you guys suggest?
[20:38] <visbits> do they need to be on a filesystem? you can use ceph objects
[20:39] <JayJ> Ceph objects - you mean as in rados objects?
[20:39] <visbits> yea
[20:39] <visbits> s3/swift gateway
[20:39] * ngoswami (~ngoswami@121.244.87.116) Quit (Quit: Leaving)
[20:40] <JayJ> What about HDFS interface?
[20:40] <JayJ> Does HDFS interface require CephFS?
[20:41] <m0zes> it requires a specific version of hadoop fwict. don't think it is cephfs underneath , pretty sure it is rbd.
[20:41] <m0zes> 1.1.x from the docs.
[20:41] * vbellur (~vijay@122.171.91.36) Quit (Ping timeout: 480 seconds)
[20:43] * oro (~oro@80-219-254-208.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[20:44] * bkopilov (~bkopilov@bzq-79-178-113-254.red.bezeqint.net) Quit (Ping timeout: 480 seconds)
[20:50] * bkopilov (~bkopilov@bzq-109-64-142-55.red.bezeqint.net) has joined #ceph
[20:51] <JayJ> For such a usecase, what would be a solution outside of Ceph that you guys suggest (I know this is a Ceph channel :)
[20:52] * mykola (~Mikolaj@91.225.203.59) Quit (Remote host closed the connection)
[20:53] <m0zes> JayJ: what usecase? you've not mentioned how the files need to be accessed? do you need a posix(ish) filesystem, or can the reads/writes happen in the application layer to an api?
[20:54] * vbellur (~vijay@122.172.215.177) has joined #ceph
[20:55] <m0zes> do your objects need replication?
[20:56] <m0zes> performance requirements?
[20:56] * raindog (~Keiya@2WVAAAVSE.tor-irc.dnsbl.oftc.net) Quit ()
[20:56] * Sigma (~FNugget@jaures.gtor.org) has joined #ceph
[20:58] * DV (~veillard@2001:41d0:a:f29f::1) Quit (Remote host closed the connection)
[20:58] * DV (~veillard@2001:41d0:1:d478::1) has joined #ceph
[21:00] * scuttle|afk is now known as scuttlemonkey
[21:00] <cetex> in my case i want 3 copies. performance wise it needs to be able to handle 600 simultaneous new objects / 300MB per second.
[21:01] <cetex> i also need to handle deletes of data older than 7days, but i guess that's not heavy on performance?
[21:01] <JayJ> m0zes: Posix fiesystem is not required, object storage is good enough. We have realtime log processing for 1000s of end points. These are log files which are coming in are processed by Spark streaming/map reduce.
[21:02] * rongze (~rongze@124.126.237.197) has joined #ceph
[21:02] <JayJ> Performance - no data yet as this is somethng we are still builing ..
[21:04] <m0zes> JayJ: hdfs proper is not something you'd want, ceph with rgw could work for you, then. I've no experience with it, but I've heard good things.
[21:04] * dgurtner (~dgurtner@178.197.231.228) Quit (Ping timeout: 480 seconds)
[21:05] <JayJ> We are using rgw with Ceph and so far happy with it. Spoiled by success, we are seeing what else is out there that we can use.
[21:05] * georgem (~Adium@fwnat.oicr.on.ca) Quit (Quit: Leaving.)
[21:06] <JayJ> CephFS - I'm aware that its not prod ready but I really don't know what it means! Like whether there are bugs or just the code is not stable or is it the perf? We have another 6 months before we go production. So we are ready to take some risk
[21:06] * BManojlovic (~steki@cable-89-216-234-193.dynamic.sbb.rs) has joined #ceph
[21:08] <m0zes> basically not as performant, and it is currently missing an fsck tool.
[21:09] <bstillwell> JayJ: The multiple MDS support is only active/passive right now too I believe. So none of that fancy splitting the directory structure up AFAIK.
[21:10] * rongze (~rongze@124.126.237.197) Quit (Ping timeout: 480 seconds)
[21:11] <cetex> anyone knows how s3 does it? :)
[21:11] <bstillwell> JayJ: I've also given up on believing any kind of timeline of when it will be stable. Seems like it's been a few months out for a couple years.
[21:11] <JayJ> bstillwell: True.. I'm CephFS is in mostly the same state for months now
[21:12] * Nacer (~Nacer@203-206-190-109.dsl.ovh.fr) has joined #ceph
[21:12] <bstillwell> That being said, I've been using it at home for two years now.
[21:13] <bstillwell> Only problem I had was some corruption initially which was caused by an out of date kernel (I was using Ubuntu 12.04 at first)
[21:13] <bstillwell> The ceph-fuse driver has worked well since I switched, but it is slow.
[21:14] <cetex> so.. what parts of ceph are considered stable? :)
[21:14] <cetex> and fast
[21:14] <cetex> and such?
[21:15] <visbits> none
[21:15] <visbits> lol
[21:15] <visbits> LOL
[21:15] <cetex> or look at it the other way around.. what parts should i avoid if i'm looking for as high performance as possible and stability?
[21:17] * bandrus (~brian@95.sub-70-211-66.myvzw.com) Quit (Ping timeout: 480 seconds)
[21:18] * dupont-y (~dupont-y@2a01:e34:ec92:8070:353b:4f62:aa4c:134b) Quit (Quit: Ex-Chat)
[21:18] * dupont-y (~dupont-y@2a01:e34:ec92:8070:353b:4f62:aa4c:134b) has joined #ceph
[21:18] * bandrus (~brian@142.sub-70-211-87.myvzw.com) has joined #ceph
[21:19] <JayJ> We started with Ceph for OpenStack to save and run images (boot from volume). It just did not cut the performance. Now we are usign Ceph mostly for backups and use RadosGW for customer data storage (redundency)
[21:19] <cetex> what was the performance issue?
[21:20] * bandrus (~brian@142.sub-70-211-87.myvzw.com) Quit ()
[21:20] * bandrus (~brian@142.sub-70-211-87.myvzw.com) has joined #ceph
[21:20] <cetex> slow reads? transfers? network inefficiency?
[21:21] * alram (~alram@194.66.249.137) Quit (Quit: leaving)
[21:21] * linjan (~linjan@213.8.240.146) has joined #ceph
[21:22] <JayJ> Mostly the expectation setting from mgmt. Linux side of the world was happy but our production wokloads run on Windows. Simple SQL benchmark numbers were way apart. However, rados performance tests suggested we were doing better than average (that's the feedback from this channel) :)
[21:22] * linuxkidd (~linuxkidd@166.170.53.210) Quit (Ping timeout: 480 seconds)
[21:22] * omar_m (~omar_m@209.163.140.194) has joined #ceph
[21:23] * bdonnahue (~James@24-148-51-171.c3-0.mart-ubr1.chi-mart.il.cable.rcn.com) has joined #ceph
[21:23] <bdonnahue> Hello. if i make a change to ceph.conf on a ceph node will that change be copied to other nodes or do i need to change each node individually
[21:23] <cetex> ah, right. so you used ceph rbd as boot drives
[21:24] * sbfox (~Adium@72.2.49.50) Quit (Quit: Leaving.)
[21:26] <omar_m> yup, but what change are you making?
[21:26] * Sigma (~FNugget@2WVAAAVVE.tor-irc.dnsbl.oftc.net) Quit ()
[21:26] * Behedwin (~sixofour@enjolras.gtor.org) has joined #ceph
[21:26] * sjmtest (uid32746@id-32746.uxbridge.irccloud.com) has joined #ceph
[21:27] * linjan (~linjan@213.8.240.146) Quit (Remote host closed the connection)
[21:29] <cetex> JayJ: what was limiting performance for you? mds? osd? mon? network? disk iops?
[21:29] <bstillwell> cetex: RBD and RGW are considered stable
[21:29] <bstillwell> The performance depends a lot on how you build it.
[21:29] * linjan (~linjan@213.8.240.146) has joined #ceph
[21:30] <bdonnahue> omar_m: was that yup for me?
[21:30] <bstillwell> Some big names are building products based on ceph too:
[21:30] <bstillwell> http://www.fujitsu.com/global/products/computing/storage/eternus-cd/
[21:30] <bstillwell> http://www.sandisk.com/enterprise/infiniflash/
[21:32] * RayTracer (~RayTracer@host-81-190-2-156.gdynia.mm.pl) has joined #ceph
[21:32] * RayTracer (~RayTracer@host-81-190-2-156.gdynia.mm.pl) Quit (Remote host closed the connection)
[21:33] <cetex> bstillwell: yeah. i'm trying to figure that out..
[21:35] <cetex> the performance .. :)
[21:36] <cetex> but we got 200-350MB on 18 osd's yesterday when i did some testing. i'm guessing it's network limitations due to replication.
[21:36] <bstillwell> There are a lot of knobs for sure.
[21:36] <omar_m> @bdonnahue yes, excerpt from docs - Each process or daemon looks for a ceph.conf file that provides its configuration settings.
[21:36] <cephalobot> omar_m: Error: "bdonnahue" is not a valid command.
[21:36] * oro (~oro@80-219-254-208.dclient.hispeed.ch) has joined #ceph
[21:36] <bdonnahue> omar_m: i want to change the private network setting
[21:37] <bdonnahue> i figured i would edit a file and restart a daemon and the changes would not replicated out to the rest of the cluster but i would need to manually depoy the new setting to each nodes
[21:38] <bstillwell> cetex: You can acknowledge writes before all replicas are confirmed to disk.
[21:39] * RayTrace_ (~RayTracer@host-81-190-2-156.gdynia.mm.pl) has joined #ceph
[21:39] * ksingh (~Adium@a91-156-75-252.elisa-laajakaista.fi) has joined #ceph
[21:40] <cetex> ok. default is to ack after all replicas are written?
[21:40] <bstillwell> cetex: I'm not sure what the default is.
[21:40] <cetex> ok. :)
[21:41] * lcurtis (~lcurtis@47.19.105.250) has joined #ceph
[21:42] <bstillwell> cetex: Looks at 'osd pool default size' and 'osd pool default min size'
[21:42] * bandrus (~brian@142.sub-70-211-87.myvzw.com) Quit (Read error: Connection reset by peer)
[21:42] * derjohn_mob (~aj@tmo-110-30.customers.d1-online.com) has joined #ceph
[21:42] * ksingh1 (~Adium@a-v6-0003.vpn.csc.fi) has joined #ceph
[21:42] <lcurtis> hello all....is there a way to disable o_direct writes in ceph?
[21:43] * georgem (~Adium@207.164.79.57) has joined #ceph
[21:43] <lcurtis> journal aio true?
[21:43] <bstillwell> I believe that's only used by the journals.
[21:44] * linuxkidd (~linuxkidd@166.170.53.210) has joined #ceph
[21:44] <bstillwell> I'm not sure disabling it would be a good idea.
[21:45] * red_ (~red@chello084112110034.11.11.vie.surfer.at) Quit (Read error: Connection reset by peer)
[21:45] * red_ (~red@chello084112110034.11.11.vie.surfer.at) has joined #ceph
[21:45] * georgem (~Adium@207.164.79.57) Quit ()
[21:45] <lcurtis> no...just for testing low throughput
[21:45] <lcurtis> or to mitigate rather
[21:46] * Sysadmin88 (~IceChat77@94.4.7.123) has joined #ceph
[21:46] * Lyncos (~lyncos@208.71.184.41) has left #ceph
[21:47] <cetex> ah. min_size = 2, size = 3
[21:47] * bandrus1 (~brian@7.sub-70-211-80.myvzw.com) has joined #ceph
[21:47] <cetex> so it makes sure it's written to two osd's before acking.
[21:47] * dgurtner (~dgurtner@217-162-119-191.dynamic.hispeed.ch) has joined #ceph
[21:47] * ksingh (~Adium@a91-156-75-252.elisa-laajakaista.fi) Quit (Ping timeout: 480 seconds)
[21:48] <bstillwell> yep
[21:48] <cetex> so set min_size to 1 and it will ack faster.
[21:48] <cetex> :)
[21:49] <bstillwell> It should
[21:49] <bstillwell> But that'll increase your risk of data loss.
[21:49] * saltlake (~saltlake@12.250.199.170) Quit (Ping timeout: 480 seconds)
[21:49] <lcurtis> yes yes
[21:50] <omar_m> lol no point if you set it to 1
[21:50] <lcurtis> this is just to test
[21:50] <lcurtis> is this journal aio size parameter
[21:50] <lcurtis> ?
[21:51] * rendar (~I@host107-140-dynamic.59-82-r.retail.telecomitalia.it) Quit (Ping timeout: 480 seconds)
[21:53] * rendar (~I@host107-140-dynamic.59-82-r.retail.telecomitalia.it) has joined #ceph
[21:55] <cetex> yeah. if we go the path of ceph we'll have nodes do writes to two ceph clusters in parallel
[21:55] * puffy (~puffy@216.207.42.129) Quit (Ping timeout: 480 seconds)
[21:55] <cetex> in different datacenters
[21:55] * B_Rake (~B_Rake@69-195-66-67.unifiedlayer.com) Quit (Ping timeout: 480 seconds)
[21:55] <cetex> and then do opportunistic get requests. it will basically just try to ask both of them for data and see who answers first.
[21:56] * Behedwin (~sixofour@5NZAAA147.tor-irc.dnsbl.oftc.net) Quit ()
[21:58] * B_Rake (~B_Rake@69-195-66-67.unifiedlayer.com) has joined #ceph
[22:00] * jrankin (~jrankin@d53-64-170-236.nap.wideopenwest.com) Quit (Quit: Leaving)
[22:00] * Rosenbluth (~Hideous@98EAAAU1Y.tor-irc.dnsbl.oftc.net) has joined #ceph
[22:00] * puffy (~puffy@216.207.42.144) has joined #ceph
[22:02] * bandrus1 (~brian@7.sub-70-211-80.myvzw.com) Quit (Ping timeout: 480 seconds)
[22:02] * RayTrace_ (~RayTracer@host-81-190-2-156.gdynia.mm.pl) Quit (Quit: Leaving...)
[22:02] * rongze (~rongze@124.126.237.197) has joined #ceph
[22:03] <cetex> at least that's my plan :)
[22:08] <lcurtis> so does ceph not do sync writes to osd's?
[22:10] <cetex> you mean syncronized writes to multiple osd's? or synced to disk?
[22:10] * rongze (~rongze@124.126.237.197) Quit (Ping timeout: 480 seconds)
[22:11] <lcurtis> synced to disk
[22:11] <lcurtis> once write is flushed to ssd
[22:11] <lcurtis> or journal
[22:13] * bene (~ben@nat-pool-bos-t.redhat.com) Quit (Quit: Konversation terminated!)
[22:14] * bandrus (~brian@83.sub-70-211-80.myvzw.com) has joined #ceph
[22:15] <cetex> i believe first osd writes to journal
[22:15] <cetex> not sure if it's sending it to second while writing to journal, or if it's sending to secondary after it's written to journal
[22:15] <cetex> sounds more reasonable to send it while it's receiving the data.
[22:17] * DV (~veillard@2001:41d0:1:d478::1) Quit (Ping timeout: 480 seconds)
[22:19] * sjm (~sjm@pool-173-70-76-86.nwrknj.fios.verizon.net) has left #ceph
[22:21] * bandrus1 (~brian@117.sub-70-211-78.myvzw.com) has joined #ceph
[22:22] * bandrus (~brian@83.sub-70-211-80.myvzw.com) Quit (Ping timeout: 480 seconds)
[22:28] * DV (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[22:30] * Rosenbluth (~Hideous@98EAAAU1Y.tor-irc.dnsbl.oftc.net) Quit ()
[22:32] * xoritor (~xoritor@cpe-72-177-85-116.austin.res.rr.com) has joined #ceph
[22:35] * lcurtis (~lcurtis@47.19.105.250) Quit (Ping timeout: 480 seconds)
[22:38] * puffy (~puffy@216.207.42.144) Quit (Quit: Leaving.)
[22:45] * hellertime (~Adium@23.79.238.10) Quit (Ping timeout: 480 seconds)
[22:47] * lcurtis (~lcurtis@47.19.105.250) has joined #ceph
[22:50] * sbfox (~Adium@72.2.49.50) has joined #ceph
[22:51] * ChrisNBlum (~ChrisNBlu@178.255.153.117) Quit (Quit: Goodbye)
[22:52] * jclm (~jclm@ip24-253-45-236.lv.lv.cox.net) Quit (Quit: Leaving.)
[22:52] * BManojlovic (~steki@cable-89-216-234-193.dynamic.sbb.rs) Quit (Quit: Ja odoh a vi sta 'ocete...)
[22:52] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has joined #ceph
[22:53] * BManojlovic (~steki@cable-89-216-234-193.dynamic.sbb.rs) has joined #ceph
[22:53] * jclm (~jclm@ip24-253-45-236.lv.lv.cox.net) has joined #ceph
[22:54] * dupont-y (~dupont-y@2a01:e34:ec92:8070:353b:4f62:aa4c:134b) Quit (Quit: Ex-Chat)
[22:54] * linuxkidd (~linuxkidd@166.170.53.210) Quit (Quit: Leaving)
[22:55] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has left #ceph
[22:59] * vpol (~vpol@000131a0.user.oftc.net) has joined #ceph
[23:00] * daniel2_ (~daniel2_@209.163.140.194) Quit (Quit: Textual IRC Client: www.textualapp.com)
[23:02] * lpabon (~quassel@24-151-54-34.dhcp.nwtn.ct.charter.com) has joined #ceph
[23:03] * lcurtis (~lcurtis@47.19.105.250) Quit (Ping timeout: 480 seconds)
[23:03] * rongze (~rongze@124.126.237.197) has joined #ceph
[23:04] * Archeron (~wade@wk.ws.ok.ubc.ca) has joined #ceph
[23:08] * _prime_ (~oftc-webi@199.168.44.192) Quit (Quit: Page closed)
[23:10] <Archeron> Ceph seems to be great for big stuff, but is it worth considering using RBD in a small (4 node, 8 disk) deployment to aggregate discs across the cluster?
[23:11] * rongze (~rongze@124.126.237.197) Quit (Ping timeout: 480 seconds)
[23:15] <cetex> lcurtis: http://www.sebastien-han.fr/blog/2014/02/10/ceph-io-patterns-the-good/
[23:15] <cetex> http://www.sebastien-han.fr/blog/2014/02/17/ceph-io-patterns-the-bad/
[23:15] <cetex> hm..
[23:15] <cetex> not online anymore.
[23:19] <bstillwell> they work for me
[23:19] * haomaiwang (~haomaiwan@114.111.166.250) Quit (Ping timeout: 480 seconds)
[23:19] <bstillwell> oh, lcurtis...
[23:19] * shaunm (~shaunm@172.56.12.216) Quit (Ping timeout: 480 seconds)
[23:21] * vpol (~vpol@000131a0.user.oftc.net) Quit (Quit: vpol)
[23:26] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[23:28] * oro (~oro@80-219-254-208.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[23:30] * MatthewH12 (~skney@manning1.torservers.net) has joined #ceph
[23:32] * ksingh1 (~Adium@a-v6-0003.vpn.csc.fi) Quit (Read error: Connection reset by peer)
[23:33] * ksingh (~Adium@a-v6-0003.vpn.csc.fi) has joined #ceph
[23:37] * haomaiwang (~haomaiwan@114.111.166.250) has joined #ceph
[23:41] * dneary (~dneary@nat-pool-bos-u.redhat.com) Quit (Ping timeout: 480 seconds)
[23:42] * fghaas1 (~florian@91-119-140-224.dynamic.xdsl-line.inode.at) has left #ceph
[23:45] * lpabon (~quassel@24-151-54-34.dhcp.nwtn.ct.charter.com) Quit (Ping timeout: 480 seconds)
[23:49] * wicope (~wicope@0001fd8a.user.oftc.net) Quit (Remote host closed the connection)

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