#ceph IRC Log

Index

IRC Log for 2015-04-18

Timestamps are in GMT/BST.

[0:09] * clarjon1 (~Pulec@5NZAABTHL.tor-irc.dnsbl.oftc.net) Quit ()
[0:09] * xcezzz1 (~Adium@pool-100-3-14-19.tampfl.fios.verizon.net) has joined #ceph
[0:09] * xcezzz (~Adium@pool-100-3-14-19.tampfl.fios.verizon.net) Quit (Read error: Connection reset by peer)
[0:09] * drupal (~Hidendra@TerokNor.tor-exit.network) has joined #ceph
[0:11] * wicope_ (~wicope@76.Red-83-60-55.dynamicIP.rima-tde.net) Quit (Read error: Connection reset by peer)
[0:16] * gregmark (~Adium@68.87.42.115) Quit (Quit: Leaving.)
[0:18] * LeaChim (~LeaChim@host86-143-18-67.range86-143.btcentralplus.com) Quit (Ping timeout: 480 seconds)
[0:23] * rastro (~rastro@68.140.239.132) Quit (Remote host closed the connection)
[0:27] * daniel2_ (~daniel@12.164.168.117) Quit (Ping timeout: 480 seconds)
[0:35] * tk12_ (~tk12@68.140.239.132) Quit (Quit: Leaving...)
[0:39] * drupal (~Hidendra@2WVAABQHG.tor-irc.dnsbl.oftc.net) Quit ()
[0:39] * blank (~Dragonsha@tor-relay-0.0xdeadce11.com) has joined #ceph
[0:43] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has joined #ceph
[0:43] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) Quit (Remote host closed the connection)
[0:44] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has left #ceph
[0:45] * dneary (~dneary@nat-pool-bos-u.redhat.com) Quit (Ping timeout: 480 seconds)
[0:48] * fsimonce (~simon@host178-188-dynamic.26-79-r.retail.telecomitalia.it) Quit (Quit: Coyote finally caught me)
[0:50] * PerlStalker (~PerlStalk@162.220.127.20) Quit (Quit: ...)
[0:50] * lcurtis (~lcurtis@47.19.105.250) Quit (Ping timeout: 480 seconds)
[0:54] * alram (~alram@cpe-172-250-2-46.socal.res.rr.com) has joined #ceph
[1:01] * BManojlovic (~steki@cable-89-216-238-140.dynamic.sbb.rs) Quit (Quit: Ja odoh a vi sta 'ocete...)
[1:01] * BManojlovic (~steki@cable-89-216-238-140.dynamic.sbb.rs) has joined #ceph
[1:07] * rendar (~I@host13-180-dynamic.23-79-r.retail.telecomitalia.it) Quit ()
[1:09] * blank (~Dragonsha@98EAABCZY.tor-irc.dnsbl.oftc.net) Quit ()
[1:09] * PuyoDead (~Swompie`@chomsky.torservers.net) has joined #ceph
[1:24] * oms101 (~oms101@p20030057EA395C00EEF4BBFFFE0F7062.dip0.t-ipconnect.de) Quit (Ping timeout: 480 seconds)
[1:28] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[1:28] * BManojlovic (~steki@cable-89-216-238-140.dynamic.sbb.rs) Quit (Quit: Ja odoh a vi sta 'ocete...)
[1:34] * oms101 (~oms101@p20030057EA2BAF00EEF4BBFFFE0F7062.dip0.t-ipconnect.de) has joined #ceph
[1:36] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[1:36] * mattrich (~Adium@38.108.161.130) has joined #ceph
[1:37] <mattrich> Nats_: thanks for your help yesterday, things are more stable now.
[1:39] * PuyoDead (~Swompie`@5NZAABTKG.tor-irc.dnsbl.oftc.net) Quit ()
[1:39] * uhtr5r (~PuyoDead@india012.server4you.net) has joined #ceph
[1:39] <mattrich> i have a new problem where some hosts are down (3). we have 3 racks, with crush selecting at the rack level. there are at least three hosts up on each rack. a few placement groups have 1 OSD acting, and many have only 2. any idea why crush isn't picking the up/in hosts on the other racks to fill out those placement groups?
[1:42] * winston-d_ (~zhithuang@58.33.47.14) has joined #ceph
[1:44] * dgurtner (~dgurtner@217-162-119-191.dynamic.hispeed.ch) has joined #ceph
[1:48] * fmanana is now known as fdmanana
[1:50] * winston-d_ (~zhithuang@58.33.47.14) Quit (Ping timeout: 480 seconds)
[2:00] * sjm (~sjm@pool-173-70-76-86.nwrknj.fios.verizon.net) Quit (Ping timeout: 480 seconds)
[2:05] <flaf> m0zes: sorry for my late reaction but you said that with min_size=1 and size=3 in a pool, ceph sends a ack to the client just after the writing of one copy of the object (in the primary OSD). Are you sure? For me, even if min_size=1, if all OSDs are OK, ceph will send a ack to the client when the object is written on each OSD (1,2,3).
[2:09] * uhtr5r (~PuyoDead@2WVAABQK1.tor-irc.dnsbl.oftc.net) Quit ()
[2:16] * dgurtner (~dgurtner@217-162-119-191.dynamic.hispeed.ch) Quit (Ping timeout: 480 seconds)
[2:28] * vjujjuri (~chatzilla@204.14.239.106) Quit (Ping timeout: 480 seconds)
[2:32] * alram (~alram@cpe-172-250-2-46.socal.res.rr.com) Quit (Quit: leaving)
[2:37] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[2:51] * segutier_ (~segutier@206.222.178.195) has joined #ceph
[2:56] * segutier_ (~segutier@206.222.178.195) Quit ()
[2:56] * segutier (~segutier@c-24-6-218-139.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[2:58] * winston-d_ (~zhithuang@58.33.47.14) has joined #ceph
[3:02] * mattrich (~Adium@38.108.161.130) Quit (Quit: Leaving.)
[3:05] * darkfaded (~floh@88.79.251.60) Quit (Ping timeout: 480 seconds)
[3:06] * winston-d_ (~zhithuang@58.33.47.14) Quit (Ping timeout: 480 seconds)
[3:08] * bandrus (~brian@128.sub-70-211-79.myvzw.com) Quit (Quit: Leaving.)
[3:09] * root (~root@pD9E9D140.dip0.t-ipconnect.de) has joined #ceph
[3:09] * shishi (~drdanick@ncc-1701-a.tor-exit.network) has joined #ceph
[3:10] * KevinPerks (~Adium@ip-64-134-99-56.public.wayport.net) has joined #ceph
[3:11] <flaf> http://ceph.com/docs/master/rados/operations/pools/#set-the-number-of-object-replicas => "This (min_size) ensures that no object in the data pool will receive I/O with fewer than min_size replicas."
[3:12] <flaf> For me it's different of "the ack of the I/O is sent after min_size replicas". But maybe I'm wrong.
[3:15] * root4 (~root@p57B2F81C.dip0.t-ipconnect.de) Quit (Ping timeout: 480 seconds)
[3:24] * daniel2_ (~daniel@156.39.10.45) has joined #ceph
[3:25] <jclm> flaf: No you're right
[3:27] <flaf> jclm: ah ok, thx. I have always a doubt on this point because I read often a different interpretation on IRC etc.
[3:32] <flaf> I change of topic but I have just discovered "ceph df detail" command (I knen "ceph df" but not "ceph df detail"). What is the meaning of the DIRTY column. In my cluster, the number in the OBJECTS column is equal to the number in the DIRTY column, for each pool.
[3:32] <flaf> Is it normal? Is my cluster dirty? ;)
[3:39] * shishi (~drdanick@2WVAABQNQ.tor-irc.dnsbl.oftc.net) Quit ()
[3:39] * Inverness (~Salamande@95.211.81.104) has joined #ceph
[3:41] * daniel2_ (~daniel@156.39.10.45) Quit (Ping timeout: 480 seconds)
[3:44] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) has joined #ceph
[3:46] * segutier (~segutier@c-24-6-218-139.hsd1.ca.comcast.net) has joined #ceph
[3:48] * ChrisHolcombe (~chris@pool-108-42-125-114.snfcca.fios.verizon.net) Quit (Quit: Leaving)
[3:52] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) Quit (Ping timeout: 480 seconds)
[4:03] * segutier (~segutier@c-24-6-218-139.hsd1.ca.comcast.net) Quit (Quit: segutier)
[4:09] <flaf> In fact, what is a "dirty" object?
[4:09] * Inverness (~Salamande@98EAABC29.tor-irc.dnsbl.oftc.net) Quit ()
[4:09] * puffy (~puffy@216.207.42.129) Quit (Ping timeout: 480 seconds)
[4:17] * jwilkins (~jwilkins@c-50-131-97-162.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[4:24] * winston-d_ (~zhithuang@58.33.47.14) has joined #ceph
[4:28] * winston-d_ (~zhithuang@58.33.47.14) Quit ()
[4:39] * Esvandiary (~LorenXo@digi00377.digicube.fr) has joined #ceph
[4:41] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[5:09] * Esvandiary (~LorenXo@5NZAABTR3.tor-irc.dnsbl.oftc.net) Quit ()
[5:11] * wushudoin (~wushudoin@209.132.181.86) Quit (Ping timeout: 480 seconds)
[5:18] * OutOfNoWhere (~rpb@199.68.195.102) has joined #ceph
[5:24] * Vacuum (~vovo@88.130.199.58) has joined #ceph
[5:31] * Vacuum_ (~vovo@88.130.200.73) Quit (Ping timeout: 480 seconds)
[5:39] * bildramer1 (~clarjon1@2.shulgin.nl.torexit.haema.co.uk) has joined #ceph
[5:55] * fmanana (~fdmanana@bl13-130-213.dsl.telepac.pt) has joined #ceph
[5:55] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) Quit (Quit: p66kumar)
[6:02] * fdmanana (~fdmanana@bl13-131-19.dsl.telepac.pt) Quit (Ping timeout: 480 seconds)
[6:09] * bildramer1 (~clarjon1@5NZAABTT5.tor-irc.dnsbl.oftc.net) Quit ()
[6:09] * straterra (~Xa@nx-01.tor-exit.network) has joined #ceph
[6:15] * sherlocked (~watson@14.139.82.6) has joined #ceph
[6:16] * sherlocked (~watson@14.139.82.6) Quit ()
[6:39] * straterra (~Xa@5NZAABTU4.tor-irc.dnsbl.oftc.net) Quit ()
[6:39] * AotC (~verbalins@5NZAABTV3.tor-irc.dnsbl.oftc.net) has joined #ceph
[6:45] * MACscr (~Adium@2601:d:c800:de3:f172:697:7fc7:ab8b) Quit (Quit: Leaving.)
[7:07] * mgolub (~Mikolaj@91.225.202.226) has joined #ceph
[7:09] * AotC (~verbalins@5NZAABTV3.tor-irc.dnsbl.oftc.net) Quit ()
[7:09] * Bonzaii (~Knuckx@intenstar.com) has joined #ceph
[7:20] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) has joined #ceph
[7:27] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) Quit (Quit: p66kumar)
[7:28] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) has joined #ceph
[7:30] * wschulze1 (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) Quit (Quit: Leaving.)
[7:30] * nathharp (~nathharp@90.200.89.199) has joined #ceph
[7:34] * nolan (~nolan@phong.sigbus.net) Quit (Quit: ZNC - http://znc.sourceforge.net)
[7:35] * nolan (~nolan@phong.sigbus.net) has joined #ceph
[7:39] * Bonzaii (~Knuckx@1GLAABF3S.tor-irc.dnsbl.oftc.net) Quit ()
[7:39] * Kottizen (~w2k@chomsky.torservers.net) has joined #ceph
[8:04] * janos_ (~messy@static-71-176-211-4.rcmdva.fios.verizon.net) has joined #ceph
[8:06] * lalatenduM (~lalatendu@122.172.131.42) has joined #ceph
[8:09] * Kottizen (~w2k@5NZAABTXT.tor-irc.dnsbl.oftc.net) Quit ()
[8:09] * Sami345 (~Plesioth@ncc-1701-a.tor-exit.network) has joined #ceph
[8:11] * janos (~messy@static-71-176-211-4.rcmdva.fios.verizon.net) Quit (Ping timeout: 480 seconds)
[8:15] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) Quit (Quit: p66kumar)
[8:15] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) has joined #ceph
[8:16] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) Quit ()
[8:18] * KevinPerks (~Adium@ip-64-134-99-56.public.wayport.net) Quit (Read error: Connection reset by peer)
[8:19] * KevinPerks (~Adium@ip-64-134-99-56.public.wayport.net) has joined #ceph
[8:23] * lalatenduM (~lalatendu@122.172.131.42) Quit (Ping timeout: 480 seconds)
[8:24] * subscope (~subscope@92-249-244-167.pool.digikabel.hu) has joined #ceph
[8:30] * Concubidated (~Adium@71.21.5.251) Quit (Quit: Leaving.)
[8:34] * rkarim (~rkarim@119.15.153.195) has joined #ceph
[8:34] <rkarim> hi
[8:35] <rkarim> is it feasible to use CEPH with CIFS gw for 4K video editing platform
[8:39] * Sami345 (~Plesioth@5NZAABTYK.tor-irc.dnsbl.oftc.net) Quit ()
[8:39] * n0x1d (~x303@176.10.99.200) has joined #ceph
[8:41] <florz> no clue, but my best guess would be that leaving out CIFS would give better performance?
[8:45] * lalatenduM (~lalatendu@122.171.124.143) has joined #ceph
[8:53] * ajazdzewski__ (~ajazdzews@p200300406E38DC00C4CEDD34BC4B9A93.dip0.t-ipconnect.de) has joined #ceph
[8:54] <rkarim> but my editing software runs on Windows, and CEPH does not have any native windows client
[8:54] <rkarim> I could export RBD OVER SCSI but in that case I can't use same RBD in multiple edit station
[8:55] <rkarim> currently we are using costly Quantum SNFS of ver ISCSI
[8:56] <rkarim> but it is costly and looking for alternative open source soluiton
[9:09] * n0x1d (~x303@5NZAABTY4.tor-irc.dnsbl.oftc.net) Quit ()
[9:09] * mollstam (~jakekosbe@india012.server4you.net) has joined #ceph
[9:12] * rendar (~I@host83-182-dynamic.37-79-r.retail.telecomitalia.it) has joined #ceph
[9:17] * darkfader (~floh@88.79.251.60) has joined #ceph
[9:19] * subscope (~subscope@92-249-244-167.pool.digikabel.hu) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[9:38] * KindOne (kindone@0001a7db.user.oftc.net) Quit (Quit: Hiring PHP developers does not contribute to the quota of employees with disabilities.)
[9:39] * mollstam (~jakekosbe@425AAAM6C.tor-irc.dnsbl.oftc.net) Quit ()
[9:39] * jakekosberg (~ain@98EAABDBB.tor-irc.dnsbl.oftc.net) has joined #ceph
[9:49] * KindOne (kindone@0001a7db.user.oftc.net) has joined #ceph
[9:58] * rotbart (~redbeard@aftr-95-222-27-149.unity-media.net) has joined #ceph
[9:59] * KindOne (kindone@0001a7db.user.oftc.net) Quit (Remote host closed the connection)
[10:00] * oro (~oro@89.248.140.14) has joined #ceph
[10:01] * YmrDtnJu (~YmrDtnJu@193.171.234.167) Quit (Remote host closed the connection)
[10:06] * KindOne (kindone@0001a7db.user.oftc.net) has joined #ceph
[10:09] * jakekosberg (~ain@98EAABDBB.tor-irc.dnsbl.oftc.net) Quit ()
[10:20] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) has joined #ceph
[10:24] * dopesong (~dopesong@78-60-74-130.static.zebra.lt) has joined #ceph
[10:28] * jclm (~jclm@ip24-253-45-236.lv.lv.cox.net) Quit (Quit: Leaving.)
[10:33] * rkarim (~rkarim@119.15.153.195) Quit (Quit: Leaving)
[10:34] * jclm (~jclm@ip24-253-45-236.lv.lv.cox.net) has joined #ceph
[10:39] * joao (~joao@193.137.142.2) has joined #ceph
[10:39] * DougalJacobs1 (~Silentspy@62-210-37-82.rev.poneytelecom.eu) has joined #ceph
[10:41] * sleinen (~Adium@84-72-160-233.dclient.hispeed.ch) has joined #ceph
[10:42] * sleinen1 (~Adium@2001:620:0:82::102) has joined #ceph
[10:49] * sleinen (~Adium@84-72-160-233.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[10:51] * qwebirc54434 (~oftc-webi@ec2-54-149-249-115.us-west-2.compute.amazonaws.com) Quit (Remote host closed the connection)
[11:09] * DougalJacobs1 (~Silentspy@5NZAABT2O.tor-irc.dnsbl.oftc.net) Quit ()
[11:39] * mollstam (~Zeis@95.128.43.164) has joined #ceph
[11:41] * Kioob (~Kioob@ALyon-651-1-58-69.w2-3.abo.wanadoo.fr) has joined #ceph
[11:42] * Sysadmin88 (~IceChat77@054527d3.skybroadband.com) has joined #ceph
[12:00] * joao (~joao@193.137.142.2) Quit (Quit: leaving)
[12:03] * RayTracer (~RayTracer@153.19.7.39) has joined #ceph
[12:04] * lalatenduM (~lalatendu@122.171.124.143) Quit (Quit: Leaving)
[12:08] * oro (~oro@89.248.140.14) Quit (Ping timeout: 480 seconds)
[12:09] * mollstam (~Zeis@98EAABDEC.tor-irc.dnsbl.oftc.net) Quit ()
[12:09] * Da_Pineapple (~smf68@orion.enn.lu) has joined #ceph
[12:16] * wicope (~wicope@0001fd8a.user.oftc.net) has joined #ceph
[12:18] * leseb_ (~leseb@81-64-215-19.rev.numericable.fr) Quit (Quit: ZNC - http://znc.in)
[12:18] * Kioob (~Kioob@ALyon-651-1-58-69.w2-3.abo.wanadoo.fr) Quit (Ping timeout: 480 seconds)
[12:20] * leseb_ (~leseb@81-64-215-19.rev.numericable.fr) has joined #ceph
[12:29] * dopesong (~dopesong@78-60-74-130.static.zebra.lt) Quit (Remote host closed the connection)
[12:36] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) has joined #ceph
[12:39] * Da_Pineapple (~smf68@98EAABDE5.tor-irc.dnsbl.oftc.net) Quit ()
[12:39] * Tumm (~darkid@176.10.99.202) has joined #ceph
[12:48] * Pablo (~pcaruana@ip-89-176-145-183.net.upcbroadband.cz) has joined #ceph
[13:02] * wicope (~wicope@0001fd8a.user.oftc.net) Quit (Read error: Connection reset by peer)
[13:09] * Tumm (~darkid@5NZAABT6W.tor-irc.dnsbl.oftc.net) Quit ()
[13:17] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[13:28] * tupper_ (~tcole@rtp-isp-nat1.cisco.com) Quit (Remote host closed the connection)
[13:31] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) Quit (Remote host closed the connection)
[13:39] * Kakeru (~KungFuHam@enjolras.gtor.org) has joined #ceph
[13:40] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has joined #ceph
[13:44] * tupper_ (~tcole@108-83-203-37.lightspeed.rlghnc.sbcglobal.net) has joined #ceph
[14:09] * Kakeru (~KungFuHam@5NZAABT85.tor-irc.dnsbl.oftc.net) Quit ()
[14:09] * lobstar (~clarjon1@anonymous6.sec.nl) has joined #ceph
[14:11] * darkfader (~floh@88.79.251.60) Quit (Read error: Connection reset by peer)
[14:12] * nathharp (~nathharp@90.200.89.199) Quit (Quit: nathharp)
[14:15] * darkfader (~floh@88.79.251.60) has joined #ceph
[14:26] * segutier (~segutier@c-24-6-218-139.hsd1.ca.comcast.net) has joined #ceph
[14:33] * segutier (~segutier@c-24-6-218-139.hsd1.ca.comcast.net) has left #ceph
[14:39] * lobstar (~clarjon1@5NZAABUAB.tor-irc.dnsbl.oftc.net) Quit ()
[14:40] * Bobby (~hassifa@nx-01.tor-exit.network) has joined #ceph
[15:09] * Bobby (~hassifa@2WVAABRBS.tor-irc.dnsbl.oftc.net) Quit ()
[15:10] * jschmid (~jxs@ip9234e338.dynamic.kabel-deutschland.de) has joined #ceph
[15:10] * Snowcat4 (~visored@hoenir.neoretro.net) has joined #ceph
[15:18] * ajazdzewski__ (~ajazdzews@p200300406E38DC00C4CEDD34BC4B9A93.dip0.t-ipconnect.de) Quit (Ping timeout: 480 seconds)
[15:29] * jschmid (~jxs@ip9234e338.dynamic.kabel-deutschland.de) Quit (Quit: Leaving)
[15:35] * haomaiwang (~haomaiwan@114.111.166.249) Quit (Remote host closed the connection)
[15:35] * dopesong (~dopesong@78-60-74-130.static.zebra.lt) has joined #ceph
[15:37] * dopesong (~dopesong@78-60-74-130.static.zebra.lt) Quit ()
[15:39] * Snowcat4 (~visored@5NZAABUCH.tor-irc.dnsbl.oftc.net) Quit ()
[15:39] * Deiz1 (~airsoftgl@2WVAABRDL.tor-irc.dnsbl.oftc.net) has joined #ceph
[15:40] * vjujjuri (~chatzilla@static-50-53-42-60.bvtn.or.frontiernet.net) has joined #ceph
[15:45] * pavera (~tomc@64-199-185-54.ip.mcleodusa.net) has joined #ceph
[15:47] <pavera> I???m seeing what appears to me to be abnormally high cpu usage on my mons, anyone know what might cause mons to use close to a full core of CPU consistently (75-95%)
[15:54] <pavera> additionally, ceph status has seemed to get very unresponsive in the last couple days, I don???t know if thats related or not.. nothing has really changed about the cluster except we???ve added a good amount of data
[15:54] <pavera> 30-40TB over the last few weeks, problems started cropping up about 2-3 days ago
[15:56] * wicope (~wicope@0001fd8a.user.oftc.net) has joined #ceph
[15:56] * wicope_ (~wicope@76.Red-83-60-55.dynamicIP.rima-tde.net) has joined #ceph
[16:08] <flaf> pavera: what the space used in the working dir of your monitor?
[16:09] <flaf> For the CPU, I don't know but I have seen in the ML someone who has latency with just a simple "ceph -s" command.
[16:09] * Deiz1 (~airsoftgl@2WVAABRDL.tor-irc.dnsbl.oftc.net) Quit ()
[16:09] <pavera> where is the working dir of the mon?
[16:10] <pavera> nevermind silly...
[16:10] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[16:10] <pavera> it has 4.6GB used
[16:11] <flaf> /var/lib/ceph/mon/$cluster-$id/
[16:11] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) has joined #ceph
[16:13] <flaf> pavera: for the example I said (of the ML), the user, after a "ceph tell mon.$i compact", hasn't no longer latency with "ceph -s"
[16:13] <flaf> Maybe you should try.
[16:13] <pavera> ok, I???ll try that
[16:14] <pavera> the $i is 0, 1, 2 I assume? not the host name?
[16:14] <flaf> For the user, before 2.6G for the working dir and latency with "ceph -s". After the "compact" command -> 461MB for the workdir and no latency.
[16:14] <flaf> yes: $id = 0, 1, 2 etc.
[16:15] <flaf> Maybe try with id =0
[16:15] <flaf> => du -sh /var/lib/ceph/mon/ceph-0/; ceph tell mon.0 compact; du -sh /var/lib/ceph/mon/ceph-0/
[16:16] <flaf> Can you see a difference of used space?
[16:16] <pavera> safer to run this on a non-leader first?
[16:17] <flaf> (4.6GB seems to me big)
[16:17] <pavera> its a production cluster,
[16:17] <pavera> yeah I agree
[16:17] <flaf> pavera: I must be honest with you
[16:17] <flaf> 1. I'm not a ceph expert and 2. I have never tested this command.
[16:17] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has left #ceph
[16:17] <flaf> pavera: just see that => http://www.mail-archive.com/ceph-users@lists.ceph.com/msg18441.html
[16:18] <flaf> In the thread, you can see that the command solved the problem for the PO.
[16:19] <pavera> yeah??? ok I???m running it on one of my mons now, it does take the mon down it looks like
[16:19] <pavera> so??? we???ll see
[16:20] <flaf> Here the principal message => http://www.mail-archive.com/ceph-users@lists.ceph.com/msg18459.html
[16:20] <flaf> It's hopeful ;)
[16:23] * wicope_ (~wicope@76.Red-83-60-55.dynamicIP.rima-tde.net) Quit (Quit: Leaving)
[16:24] <flaf> I noticed that the PO, like you, had pushed lot data in his cluster before to have the problem.
[16:25] <flaf> pavera: let me know if the command solve your problem. I'm interested. ;)
[16:25] * vjujjuri (~chatzilla@static-50-53-42-60.bvtn.or.frontiernet.net) Quit (Ping timeout: 480 seconds)
[16:26] <pavera> yeah, I will??? its still running on the first mon
[16:26] <pavera> the mon is unresponsive
[16:26] <pavera> the directory has grown from 4.6 to 7.1GB so far???
[16:27] <flaf> It seems to me logical because the leveldb is probably modified and optimized.
[16:28] <pavera> yeah
[16:28] * wschulze (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) has joined #ceph
[16:30] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) has joined #ceph
[16:38] * oro (~oro@80-219-254-208.dclient.hispeed.ch) has joined #ceph
[16:39] <pavera> did not seem to work...
[16:39] <pavera> the mon is still down
[16:39] * clusterfudge (~osuka_@5NZAABUFP.tor-irc.dnsbl.oftc.net) has joined #ceph
[16:39] <flaf> the "compact" command is finished ?
[16:39] <pavera> the directory size grew to 8.4GB, then shrank back to 4.6GB.. but now its grown again to 5.2GB
[16:39] <pavera> it says the compaction completed though
[16:40] <flaf> And if you restart the mon?
[16:43] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) Quit (Remote host closed the connection)
[16:47] <pavera> yeah.. no dice
[16:47] <pavera> it seems to have lost its key???
[16:47] <pavera> its now trying to create-keys?
[16:47] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) has joined #ceph
[16:48] <flaf> err?
[16:49] <flaf> does the file /var/lib/ceph/mon/ceph-0/keyring exist?
[16:52] <pavera> yes
[16:52] <flaf> So the monitor hasn't lost its key.
[16:55] <pavera> it doesn???t look like it??? Just tried stopping the mon with sudo stop ceph-mon-all, then started it again with sudo start ceph-mon-all and it is back in the same state??? ceph-create-keys
[16:55] <pavera> is running???
[16:56] <pavera> when I restarted it it did say in the log that it was ???cleaning up an inconsistent store???
[16:57] <pavera> then the leveldb shrunk to under 1GB??? it has since grown back to 1.2GB
[16:57] <pavera> but it hasn???t rejoined the cluster
[16:58] <flaf> Is the cluster was health_ok before trying to compact mon.0?
[16:58] <flaf> s/is//
[16:59] <pavera> yes
[16:59] <pavera> and I didn???t do mon.0
[16:59] <pavera> I did mon.2
[16:59] <pavera> cause I didn???t want to do it on the leader
[17:04] <flaf> I'm sorry, I have no idea. Maybe try to run ceph-mon in console with -d (debug mode) to see something.
[17:04] <flaf> => ceph-mon --cluster=ceph -i 2 -d
[17:07] <flaf> Which version of ceph?
[17:09] * clusterfudge (~osuka_@5NZAABUFP.tor-irc.dnsbl.oftc.net) Quit ()
[17:09] * Hidendra (~Dragonsha@lydia.hybridragon.net) has joined #ceph
[17:09] * vjujjuri (~chatzilla@static-50-53-42-60.bvtn.or.frontiernet.net) has joined #ceph
[17:09] <pavera> 0.80.7
[17:14] <litwol> Is it possible to see what configuration string ceph was compiled with from the binaries?
[17:15] <pavera> I can???t get it to rejoin
[17:15] <pavera> no clue
[17:16] <flaf> pavera: I'm sorry for my bad advice.
[17:16] <pavera> I don???t think it was bad advice
[17:17] <pavera> i do think the size of the level db is too large
[17:17] <flaf> The only way I see is to remove mon.2 and recreate a new mon.2 from scratch.
[17:17] <pavera> from things I???ve now read I think that is the cause of our latency and probably high cpu
[17:18] <flaf> Yes indeed. I think too.
[17:18] <pavera> but something has gone awry
[17:18] <pavera> anyway, thats software I???ll figure it out one way or another
[17:18] * rotbart (~redbeard@aftr-95-222-27-149.unity-media.net) Quit (Quit: Leaving)
[17:19] <flaf> Currently you have a quorum of mons, so it's easy to remove mon.2 from the cluster.
[17:19] <flaf> Maybe, after a new instance of the new mon.2, you will have a working dir not so big.
[17:21] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[17:21] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) has joined #ceph
[17:23] * oro (~oro@80-219-254-208.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[17:26] * lovejoy_ (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) has joined #ceph
[17:30] * RayTracer (~RayTracer@153.19.7.39) Quit (Remote host closed the connection)
[17:33] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) Quit (Ping timeout: 480 seconds)
[17:35] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) has joined #ceph
[17:38] * lovejoy (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) Quit ()
[17:39] * Hidendra (~Dragonsha@2WVAABRGF.tor-irc.dnsbl.oftc.net) Quit ()
[17:39] * cryptk (~Curt`@207.201.223.196) has joined #ceph
[17:40] * lovejoy_ (~lovejoy@cpc69388-oxfd28-2-0-cust415.4-3.cable.virginm.net) Quit (Ping timeout: 480 seconds)
[17:56] * danieagle (~Daniel@177.138.223.106) has joined #ceph
[18:09] * cryptk (~Curt`@5NZAABUHW.tor-irc.dnsbl.oftc.net) Quit ()
[18:09] * SaneSmith (~slowriot@2WVAABRH2.tor-irc.dnsbl.oftc.net) has joined #ceph
[18:13] * segutier (~segutier@mfb0436d0.tmodns.net) has joined #ceph
[18:16] * vjujjuri (~chatzilla@static-50-53-42-60.bvtn.or.frontiernet.net) Quit (Quit: ChatZilla 0.9.91.1 [Firefox 36.0.1/20150305021524])
[18:19] * vjujjuri (~chatzilla@static-50-53-42-60.bvtn.or.frontiernet.net) has joined #ceph
[18:19] * mattrich (~Adium@c-98-207-79-48.hsd1.ca.comcast.net) has joined #ceph
[18:19] * segutier (~segutier@mfb0436d0.tmodns.net) Quit (Read error: Connection reset by peer)
[18:20] * segutier (~segutier@mfb0436d0.tmodns.net) has joined #ceph
[18:22] * oro (~oro@80-219-254-208.dclient.hispeed.ch) has joined #ceph
[18:23] * haomaiwang (~haomaiwan@114.111.166.250) has joined #ceph
[18:28] * wushudoin (~wushudoin@209.132.181.86) has joined #ceph
[18:29] * wushudoin (~wushudoin@209.132.181.86) Quit ()
[18:31] * RayTracer (~RayTracer@public-gprs517328.centertel.pl) has joined #ceph
[18:34] * segutier (~segutier@mfb0436d0.tmodns.net) Quit (Read error: Connection reset by peer)
[18:35] * segutier (~segutier@mfb0436d0.tmodns.net) has joined #ceph
[18:35] * mattrich (~Adium@c-98-207-79-48.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[18:37] * RayTracer (~RayTracer@public-gprs517328.centertel.pl) Quit (Remote host closed the connection)
[18:39] * SaneSmith (~slowriot@2WVAABRH2.tor-irc.dnsbl.oftc.net) Quit ()
[18:39] * dontron (~Ralth@wannabe.torservers.net) has joined #ceph
[18:43] * oro (~oro@80-219-254-208.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[18:49] * Kioob (~Kioob@ALyon-651-1-58-69.w2-3.abo.wanadoo.fr) has joined #ceph
[18:53] * visbits (~textual@cpe-174-101-246-167.cinci.res.rr.com) has joined #ceph
[18:54] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) has joined #ceph
[18:55] <visbits> is there no options for auto repair in ceph.. its annoying having to repair pg once a week
[18:56] * segutier (~segutier@mfb0436d0.tmodns.net) Quit (Quit: segutier)
[18:59] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) has joined #ceph
[19:01] * jdillaman (~jdillaman@pool-173-66-110-250.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[19:09] * dontron (~Ralth@98EAABDPC.tor-irc.dnsbl.oftc.net) Quit ()
[19:09] * Xerati (~Kristophe@176.10.99.202) has joined #ceph
[19:25] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has joined #ceph
[19:26] * Aid2 (491aa3ec@107.161.19.109) has joined #ceph
[19:26] <Aid2> hey... has anyone ever used rbd for anything other than VMs?
[19:39] * Xerati (~Kristophe@1GLAABGL0.tor-irc.dnsbl.oftc.net) Quit ()
[19:42] * Aid2 (491aa3ec@107.161.19.109) Quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client)
[19:43] * danieagle (~Daniel@177.138.223.106) Quit (Quit: Obrigado por Tudo! :-) inte+ :-))
[19:46] * pavera (~tomc@64-199-185-54.ip.mcleodusa.net) Quit (Quit: pavera)
[19:55] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[19:56] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has left #ceph
[20:09] * offender (~Corti^car@5.9.158.75) has joined #ceph
[20:21] * wschulze (~wschulze@cpe-74-73-11-233.nyc.res.rr.com) has left #ceph
[20:24] * jschmid (~jxs@ip9234e338.dynamic.kabel-deutschland.de) has joined #ceph
[20:25] * jschmid (~jxs@ip9234e338.dynamic.kabel-deutschland.de) Quit (Remote host closed the connection)
[20:27] * jschmid (~jxs@ip9234e338.dynamic.kabel-deutschland.de) has joined #ceph
[20:27] * jschmid (~jxs@ip9234e338.dynamic.kabel-deutschland.de) Quit ()
[20:29] * oro (~oro@80-219-254-208.dclient.hispeed.ch) has joined #ceph
[20:39] * offender (~Corti^car@5NZAABUNI.tor-irc.dnsbl.oftc.net) Quit ()
[20:39] * Vale (~Morde@95.128.43.164) has joined #ceph
[20:41] * oro (~oro@80-219-254-208.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[20:43] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) Quit (Remote host closed the connection)
[20:44] * RayTracer (~RayTracer@host-81-190-2-156.gdynia.mm.pl) has joined #ceph
[20:44] * Kioob (~Kioob@ALyon-651-1-58-69.w2-3.abo.wanadoo.fr) Quit (Remote host closed the connection)
[20:45] * RayTracer (~RayTracer@host-81-190-2-156.gdynia.mm.pl) Quit ()
[20:45] * darkfader (~floh@88.79.251.60) Quit (Ping timeout: 480 seconds)
[20:50] * darkfader (~floh@88.79.251.60) has joined #ceph
[20:51] * mgolub (~Mikolaj@91.225.202.226) Quit (Ping timeout: 480 seconds)
[20:51] * mgolub (~Mikolaj@91.225.202.158) has joined #ceph
[21:01] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) has joined #ceph
[21:07] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) Quit (Quit: p66kumar)
[21:09] * Vale (~Morde@425AAANC3.tor-irc.dnsbl.oftc.net) Quit ()
[21:13] * vjujjuri (~chatzilla@static-50-53-42-60.bvtn.or.frontiernet.net) Quit (Ping timeout: 480 seconds)
[21:14] * tritonx1 (~FNugget@5NZAABUP5.tor-irc.dnsbl.oftc.net) has joined #ceph
[21:18] * rendar (~I@host83-182-dynamic.37-79-r.retail.telecomitalia.it) Quit (Ping timeout: 480 seconds)
[21:21] * rendar (~I@host83-182-dynamic.37-79-r.retail.telecomitalia.it) has joined #ceph
[21:24] * sherlocked (~watson@14.139.82.6) has joined #ceph
[21:25] * sherlocked (~watson@14.139.82.6) Quit ()
[21:31] * tupper_ (~tcole@108-83-203-37.lightspeed.rlghnc.sbcglobal.net) Quit (Ping timeout: 480 seconds)
[21:33] * mattrich (~Adium@67-207-118-226.static.wiline.com) has joined #ceph
[21:39] * brutuscat (~brutuscat@105.34.133.37.dynamic.jazztel.es) Quit (Remote host closed the connection)
[21:44] * tritonx1 (~FNugget@5NZAABUP5.tor-irc.dnsbl.oftc.net) Quit ()
[21:44] * Scaevolus (~Hidendra@digi00377.digicube.fr) has joined #ceph
[21:46] * Concubidated (~Adium@71.21.5.251) has joined #ceph
[22:06] * sjmtest (uid32746@id-32746.uxbridge.irccloud.com) has joined #ceph
[22:14] * Scaevolus (~Hidendra@2WVAABRPN.tor-irc.dnsbl.oftc.net) Quit ()
[22:15] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[22:19] * mattrich (~Adium@67-207-118-226.static.wiline.com) Quit (Quit: Leaving.)
[22:27] * B_Rake (~B_Rake@45.56.23.41) has joined #ceph
[22:29] * B_Rake (~B_Rake@45.56.23.41) Quit (Read error: Connection reset by peer)
[22:30] * B_Rake (~B_Rake@2605:a601:5b9:dd01:3984:bfd1:b3f6:ad2) has joined #ceph
[22:45] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) has joined #ceph
[22:59] * B_Rake (~B_Rake@2605:a601:5b9:dd01:3984:bfd1:b3f6:ad2) Quit (Remote host closed the connection)
[23:01] * mgolub (~Mikolaj@91.225.202.158) Quit (Quit: away)
[23:09] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Remote host closed the connection)
[23:10] * DV (~veillard@2001:41d0:1:d478::1) Quit (Ping timeout: 480 seconds)
[23:13] * DV (~veillard@2001:41d0:1:d478::1) has joined #ceph
[23:23] <litwol> Hmm
[23:24] <litwol> I've created brand new pool made of 4 nodes. 4 mons, 3 osds.
[23:24] <litwol> since the moment i launched it all i get is HEALTH_WARN with "64 active+undersized+degraded"
[23:25] <litwol> even though logs say 99% space availability
[23:31] <litwol> http://dpaste.com/0BK7Q33
[23:32] <litwol> Not sure what i can do here to bring cluster health to HEALTH_OK
[23:32] <litwol> :-\
[23:37] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) Quit (Quit: p66kumar)
[23:40] <litwol> need to better understand placement groups
[23:49] * K3NT1S_aw (~elt@179.43.152.247) has joined #ceph
[23:55] * p66kumar (~p66kumar@c-67-188-232-183.hsd1.ca.comcast.net) has joined #ceph

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