#ceph IRC Log

Index

IRC Log for 2014-02-28

Timestamps are in GMT/BST.

[0:00] * KevinPerks (~Adium@74.122.167.244) has joined #ceph
[0:00] * al (quassel@niel.cx) has joined #ceph
[0:01] * rturk-away is now known as rturk
[0:05] * garphy is now known as garphy`aw
[0:05] * JoeGruher (~JoeGruher@jfdmzpr01-ext.jf.intel.com) Quit (Remote host closed the connection)
[0:05] * Midnightmyth (~quassel@93-167-84-102-static.dk.customer.tdc.net) Quit (Ping timeout: 480 seconds)
[0:08] * markbby (~Adium@168.94.245.3) has joined #ceph
[0:11] * BManojlovic (~steki@fo-d-130.180.254.37.targo.rs) Quit (Quit: Ja odoh a vi sta 'ocete...)
[0:12] * ivotron (~ivotron@adsl-99-146-2-252.dsl.pltn13.sbcglobal.net) has joined #ceph
[0:13] * al (quassel@niel.cx) Quit ()
[0:13] * al (d@niel.cx) has joined #ceph
[0:15] * BillK (~BillK-OFT@124-171-229-29.dyn.iinet.net.au) has joined #ceph
[0:30] * markbby (~Adium@168.94.245.3) Quit (Ping timeout: 480 seconds)
[0:40] * jjgalvez (~jjgalvez@ip98-167-16-160.lv.lv.cox.net) Quit (Quit: Leaving.)
[0:47] * sarob (~sarob@mobile-166-137-185-054.mycingular.net) has joined #ceph
[0:47] <mo-> anybody know how I can check whether a "mon add soandso" has completed? because I should have 4/5 mons up now but ceph health still blocks
[0:55] * sarob (~sarob@mobile-166-137-185-054.mycingular.net) Quit (Ping timeout: 480 seconds)
[0:55] * jjgalvez (~jjgalvez@ip98-167-16-160.lv.lv.cox.net) has joined #ceph
[1:02] * carif (~mcarifio@pool-173-76-155-34.bstnma.fios.verizon.net) has joined #ceph
[1:04] * sjm (~sjm@gzac10-107-1.nje.twosigma.com) has left #ceph
[1:06] * sprachgenerator (~sprachgen@130.202.135.204) Quit (Quit: sprachgenerator)
[1:08] * Gamekiller77 (~Gamekille@2001:420:28c:1007:f889:d84:a530:e871) Quit (Quit: Leaving)
[1:08] * joef (~Adium@2620:79:0:131:c860:358a:ef42:4b77) has joined #ceph
[1:10] <dmick> with 4/5 up it shouldn't block
[1:10] <mo-> I thought so too. now I just found out an additional mon is blocking (not starting at all) like the other one that started all this
[1:10] <dmick> one thing you can check is: log into mon machine; ceph daemon <mon-name> mon_status
[1:10] <mo-> so thats 3/5, still no quorum
[1:10] <mo-> of a failing or running mon?
[1:10] * sarob (~sarob@207.114.197.199) has joined #ceph
[1:11] <dmick> actually either, but the failing is more interesting probably
[1:11] <mo-> well thats blocking just like ceph health does
[1:12] <mo-> only printing the fault messages
[1:12] <mo-> on both a failing and working mon
[1:12] <mo-> is that command eventually gonna complete even with the fault spam or could I wait til kingdom come for that?
[1:16] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[1:16] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[1:16] <mo-> hu? this is weird
[1:16] <mo-> the 3rd, running mon has faults connecting to itself
[1:17] * sarob (~sarob@207.114.197.199) Quit (Remote host closed the connection)
[1:18] <mo-> so.. I think im looking at a crash log in the log file now
[1:19] <mo-> 2014-02-28 00:11:48.861263 7f4728042700 -1 mon/Monitor.cc: In function 'void Monitor::sync_timeout(entity_inst_t&)' thread 7f4728042700 time 2014-02-28 00:11:48.782305 mon/Monitor.cc: 1099: FAILED assert(sync_state == SYNC_STATE_CHUNKS)
[1:20] * KevinPerks (~Adium@74.122.167.244) Quit (Quit: Leaving.)
[1:21] <mo-> ok, so that mon is now also blocking from starting. this apparantly isnt working
[1:21] <mo-> is it possible to add .61.9 mons to a .61.2 cluster?
[1:29] * Pedras (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[1:31] * via (~via@smtp2.matthewvia.info) has joined #ceph
[1:33] * valeech (~valeech@166.170.42.80) has joined #ceph
[1:33] <valeech> why does the ceph-deploy tool output a config file that looks nothing like anything referenced in the ceph documentation examples?
[1:35] * zerick (~eocrospom@190.187.21.53) Quit (Ping timeout: 480 seconds)
[1:38] * Pedras (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) has joined #ceph
[1:38] <athrift> I was wondering with the new "cache pools" will the OSD's in the cache pool still need a journal ? e.g. if I add two hosts with SSD's in to Pool-A and make it the cache pool for Pool-B will the SSD's in Pool-A still need a journal ?
[1:41] * banks (~banks@host86-154-234-37.range86-154.btcentralplus.com) Quit (Quit: banks)
[1:48] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[1:48] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[1:49] * andreask (~andreask@h081217067008.dyn.cm.kabsi.at) Quit (Ping timeout: 480 seconds)
[1:49] * zerick (~eocrospom@190.114.248.34) has joined #ceph
[1:51] * valeech (~valeech@166.170.42.80) Quit (Quit: valeech)
[1:52] <joshd2> athrift: yes, the journal is still required for transaction safety in a cache pool. in the future non-fs backends for osds may not require one
[1:55] * ircolle (~Adium@2601:1:8380:2d9:393c:5410:2aca:4e03) Quit (Quit: Leaving.)
[1:56] <athrift> joshd2: Thanks for the answer. I look forward to new non-fs backends :)
[2:00] * zerick (~eocrospom@190.114.248.34) Quit (Ping timeout: 480 seconds)
[2:00] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[2:00] * dereky (~derek@proxy00.umiacs.umd.edu) has joined #ceph
[2:03] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[2:13] * LeaChim (~LeaChim@host86-166-182-74.range86-166.btcentralplus.com) Quit (Ping timeout: 480 seconds)
[2:15] * mtanski (~mtanski@69.193.178.202) Quit (Ping timeout: 480 seconds)
[2:15] * yanzheng (~zhyan@134.134.139.72) has joined #ceph
[2:19] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[2:23] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[2:33] * glzhao (~glzhao@220.181.11.232) has joined #ceph
[2:39] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[2:40] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[2:47] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[2:50] * jskinner (~jskinner@69.170.148.179) Quit (Remote host closed the connection)
[2:50] * jskinner (~jskinner@69.170.148.179) has joined #ceph
[2:53] * jskinner_ (~jskinner@69.170.148.179) has joined #ceph
[2:53] * jskinner (~jskinner@69.170.148.179) Quit (Read error: Connection reset by peer)
[2:55] * xarses_ (~andreww@12.164.168.117) Quit (Ping timeout: 480 seconds)
[2:58] * markbby (~Adium@168.94.245.1) has joined #ceph
[2:59] * sjm (~sjm@pool-108-53-56-179.nwrknj.fios.verizon.net) has joined #ceph
[3:01] * jskinner_ (~jskinner@69.170.148.179) Quit (Ping timeout: 480 seconds)
[3:13] * shimo (~A13032@122x212x216x66.ap122.ftth.ucom.ne.jp) has joined #ceph
[3:14] * rturk is now known as rturk-away
[3:19] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[3:19] * erkules (~erkules@port-92-193-26-216.dynamic.qsc.de) has joined #ceph
[3:26] * erkules_ (~erkules@port-92-193-7-20.dynamic.qsc.de) Quit (Ping timeout: 480 seconds)
[3:27] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[3:39] * BillK (~BillK-OFT@124-171-229-29.dyn.iinet.net.au) Quit (Read error: Connection reset by peer)
[3:40] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) Quit (Quit: Leaving.)
[3:42] * haomaiwa_ (~haomaiwan@117.79.232.213) Quit (Remote host closed the connection)
[3:42] * haomaiwang (~haomaiwan@219-87-173-15.static.tfn.net.tw) has joined #ceph
[3:43] * carif (~mcarifio@pool-173-76-155-34.bstnma.fios.verizon.net) Quit (Quit: Ex-Chat)
[3:44] * BillK (~BillK-OFT@106-68-188-219.dyn.iinet.net.au) has joined #ceph
[3:50] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) has joined #ceph
[3:52] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) Quit ()
[3:59] * mtanski (~mtanski@cpe-72-229-51-156.nyc.res.rr.com) has joined #ceph
[3:59] * jjgalvez (~jjgalvez@ip98-167-16-160.lv.lv.cox.net) Quit (Quit: Leaving.)
[4:07] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[4:11] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) has joined #ceph
[4:12] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) Quit ()
[4:13] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[4:16] * rmoe (~quassel@12.164.168.117) Quit (Ping timeout: 480 seconds)
[4:17] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[4:18] * mtanski (~mtanski@cpe-72-229-51-156.nyc.res.rr.com) Quit (Quit: mtanski)
[4:23] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[4:27] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[4:28] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) has joined #ceph
[4:28] * markbby (~Adium@168.94.245.1) Quit (Remote host closed the connection)
[4:28] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) Quit ()
[4:32] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[4:32] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[4:37] * sputnik13 (~sputnik13@207.8.121.241) Quit (Ping timeout: 480 seconds)
[4:42] * rmoe (~quassel@173-228-89-134.dsl.static.sonic.net) has joined #ceph
[4:44] * xarses_ (~andreww@c-24-23-183-44.hsd1.ca.comcast.net) has joined #ceph
[4:46] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[4:48] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) has joined #ceph
[4:50] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) Quit ()
[4:51] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[4:52] * angdraug (~angdraug@12.164.168.117) Quit (Quit: Leaving)
[4:54] * dereky_ (~derek@pool-71-114-104-38.washdc.fios.verizon.net) has joined #ceph
[4:55] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[4:56] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[4:56] * jackhill (jackhill@pilot.trilug.org) Quit (Read error: Operation timed out)
[4:57] * jackhill (jackhill@pilot.trilug.org) has joined #ceph
[4:57] * dereky (~derek@proxy00.umiacs.umd.edu) Quit (Ping timeout: 480 seconds)
[4:57] * dereky_ is now known as dereky
[4:58] * Pedras (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[4:59] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) has joined #ceph
[5:01] * wschulze (~wschulze@cpe-72-229-37-201.nyc.res.rr.com) Quit (Quit: Leaving.)
[5:01] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[5:02] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[5:02] * KevinPerks (~Adium@cpe-066-026-252-218.triad.res.rr.com) has joined #ceph
[5:03] * sjusthm (~sam@24-205-43-60.dhcp.gldl.ca.charter.com) Quit ()
[5:05] * mtanski (~mtanski@cpe-72-229-51-156.nyc.res.rr.com) has joined #ceph
[5:05] * xmltok (~xmltok@cpe-76-90-130-65.socal.res.rr.com) Quit (Remote host closed the connection)
[5:07] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[5:08] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[5:13] * sprachgenerator (~sprachgen@c-67-167-211-254.hsd1.il.comcast.net) has joined #ceph
[5:20] * sarob (~sarob@2601:9:7080:13a:d36:988f:4b22:e386) has joined #ceph
[5:21] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[5:24] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[5:26] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) has joined #ceph
[5:28] * sarob (~sarob@2601:9:7080:13a:d36:988f:4b22:e386) Quit (Ping timeout: 480 seconds)
[5:28] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[5:28] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[5:31] * Vacum (~vovo@i59F7A979.versanet.de) has joined #ceph
[5:33] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[5:33] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has left #ceph
[5:35] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[5:38] * Vacum_ (~vovo@88.130.200.249) Quit (Ping timeout: 480 seconds)
[5:38] * mtanski (~mtanski@cpe-72-229-51-156.nyc.res.rr.com) Quit (Quit: mtanski)
[5:38] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[5:39] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[5:39] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[5:41] * bandrus (~Adium@adsl-75-5-250-121.dsl.scrm01.sbcglobal.net) Quit (Quit: Leaving.)
[5:42] * sprachgenerator (~sprachgen@c-67-167-211-254.hsd1.il.comcast.net) Quit (Quit: sprachgenerator)
[5:42] * bandrus (~Adium@adsl-75-5-250-121.dsl.scrm01.sbcglobal.net) has joined #ceph
[5:45] * bandrus (~Adium@adsl-75-5-250-121.dsl.scrm01.sbcglobal.net) Quit ()
[5:47] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[5:47] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[5:52] * sputnik13 (~sputnik13@wsip-68-105-248-60.sd.sd.cox.net) has joined #ceph
[6:03] * sputnik13 (~sputnik13@wsip-68-105-248-60.sd.sd.cox.net) Quit (Quit: My MacBook has gone to sleep. ZZZzzz???)
[6:06] * haomaiwa_ (~haomaiwan@117.79.232.213) has joined #ceph
[6:10] * wschulze (~wschulze@cpe-72-229-37-201.nyc.res.rr.com) has joined #ceph
[6:13] * haomaiwang (~haomaiwan@219-87-173-15.static.tfn.net.tw) Quit (Ping timeout: 480 seconds)
[6:17] * nwat (~textual@c-50-131-197-174.hsd1.ca.comcast.net) has joined #ceph
[6:19] * BillK (~BillK-OFT@106-68-188-219.dyn.iinet.net.au) Quit (Ping timeout: 480 seconds)
[6:21] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[6:21] * BillK (~BillK-OFT@106-69-38-223.dyn.iinet.net.au) has joined #ceph
[6:24] * wschulze (~wschulze@cpe-72-229-37-201.nyc.res.rr.com) Quit (Quit: Leaving.)
[6:29] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Ping timeout: 481 seconds)
[6:31] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[6:34] * nwat (~textual@c-50-131-197-174.hsd1.ca.comcast.net) Quit (Quit: My MacBook has gone to sleep. ZZZzzz???)
[6:39] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[6:47] * Siva (~sivat@generalnat.eglbp.corp.yahoo.com) has joined #ceph
[6:52] * jjgalvez (~jjgalvez@ip98-167-16-160.lv.lv.cox.net) has joined #ceph
[6:52] * Siva_ (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[6:53] * Siva_ (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit ()
[6:54] * Siva_ (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[6:55] * Siva (~sivat@generalnat.eglbp.corp.yahoo.com) Quit (Ping timeout: 480 seconds)
[6:55] * Siva_ is now known as Siva
[7:01] * hasues (~hazuez@108-236-232-243.lightspeed.knvltn.sbcglobal.net) Quit (Quit: Leaving.)
[7:07] * wschulze (~wschulze@cpe-72-229-37-201.nyc.res.rr.com) has joined #ceph
[7:21] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Quit: Siva)
[7:21] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[7:26] * themgt (~themgt@pc-188-95-160-190.cm.vtr.net) Quit (Quit: themgt)
[7:28] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Read error: Operation timed out)
[7:28] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[7:34] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[7:34] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[7:36] * sputnik13 (~sputnik13@wsip-68-105-248-60.sd.sd.cox.net) has joined #ceph
[7:37] * sputnik13 (~sputnik13@wsip-68-105-248-60.sd.sd.cox.net) Quit ()
[7:37] * sputnik13 (~sputnik13@wsip-68-105-248-60.sd.sd.cox.net) has joined #ceph
[7:41] * rotbeard (~redbeard@2a02:908:df10:6f00:76f0:6dff:fe3b:994d) Quit (Quit: Verlassend)
[7:41] * AfC (~andrew@2407:7800:400:1011:2ad2:44ff:fe08:a4c) Quit (Quit: Leaving.)
[7:47] * shimo (~A13032@122x212x216x66.ap122.ftth.ucom.ne.jp) Quit (Quit: shimo)
[7:47] * shimo (~A13032@122x212x216x66.ap122.ftth.ucom.ne.jp) has joined #ceph
[7:49] * wschulze (~wschulze@cpe-72-229-37-201.nyc.res.rr.com) Quit (Quit: Leaving.)
[7:54] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Remote host closed the connection)
[7:55] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[8:00] * fghaas (~florian@91-119-140-244.dynamic.xdsl-line.inode.at) has joined #ceph
[8:06] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[8:07] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[8:12] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Ping timeout: 480 seconds)
[8:16] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[8:18] * madkiss (~madkiss@chello062178057005.20.11.vie.surfer.at) has joined #ceph
[8:19] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[8:22] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[8:25] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[8:25] * fghaas (~florian@91-119-140-244.dynamic.xdsl-line.inode.at) Quit (Quit: Leaving.)
[8:27] * mattt (~textual@cpc9-rdng20-2-0-cust565.15-3.cable.virginm.net) has joined #ceph
[8:30] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[8:31] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[8:34] * rotbeard (~redbeard@b2b-94-79-138-170.unitymedia.biz) has joined #ceph
[8:37] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[8:40] * thb (~me@port-56562.pppoe.wtnet.de) has joined #ceph
[8:40] * ninkotech_ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[8:40] * thb is now known as Guest1705
[8:41] * Guest1705 is now known as thb
[8:44] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[8:46] * ninkotech__ (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[8:54] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[8:55] * fghaas (~florian@91-119-140-244.dynamic.xdsl-line.inode.at) has joined #ceph
[8:56] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[8:57] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[8:58] * KevinPerks (~Adium@cpe-066-026-252-218.triad.res.rr.com) Quit (Quit: Leaving.)
[9:03] * oro (~oro@2001:620:20:16:3df3:876d:8467:2eed) has joined #ceph
[9:06] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[9:08] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[9:09] * steki (~steki@91.195.39.5) has joined #ceph
[9:10] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[9:11] * Sysadmin88 (~IceChat77@176.254.32.31) Quit (Quit: Light travels faster then sound, which is why some people appear bright, until you hear them speak)
[9:11] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Remote host closed the connection)
[9:12] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[9:12] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Quit: Siva)
[9:19] * LeaChim (~LeaChim@host86-166-182-74.range86-166.btcentralplus.com) has joined #ceph
[9:19] * jbd_ (~jbd_@2001:41d0:52:a00::77) has joined #ceph
[9:22] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Ping timeout: 480 seconds)
[9:23] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[9:23] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[9:23] * andreask (~andreask@h081217067008.dyn.cm.kabsi.at) has joined #ceph
[9:23] * ChanServ sets mode +v andreask
[9:25] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[9:26] * hybrid512 (~walid@LPoitiers-156-86-25-85.w193-248.abo.wanadoo.fr) Quit (Ping timeout: 480 seconds)
[9:28] * piezo (~chatzilla@107-197-220-222.lightspeed.irvnca.sbcglobal.net) Quit (Quit: ChatZilla 0.9.90.1 [Firefox 27.0.1/20140212131424])
[9:28] * KevinPerks (~Adium@cpe-066-026-252-218.triad.res.rr.com) has joined #ceph
[9:30] * sleinen1 (~Adium@2001:620:0:26:d112:2b0c:f3a5:a7fc) has joined #ceph
[9:30] * ponyofdeath (~vladi@cpe-76-167-201-214.san.res.rr.com) Quit (Ping timeout: 480 seconds)
[9:31] * AfC (~andrew@2001:44b8:31cb:d400:6e88:14ff:fe33:2a9c) has joined #ceph
[9:31] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[9:34] * ponyofdeath (~vladi@cpe-76-167-201-214.san.res.rr.com) has joined #ceph
[9:34] * humbolt (~elias@93-82-44-212.adsl.highway.telekom.at) Quit (Quit: Leaving.)
[9:34] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Quit: Siva)
[9:37] * sleinen (~Adium@2001:620:0:46:15f5:4346:e461:6ce4) Quit (Ping timeout: 480 seconds)
[9:38] * hybrid512 (~walid@LPoitiers-156-86-25-85.w193-248.abo.wanadoo.fr) has joined #ceph
[9:38] * The_Bishop__ (~bishop@g229133036.adsl.alicedsl.de) has joined #ceph
[9:39] * thomnico (~thomnico@2a01:e35:8b41:120:495b:2f8e:f264:a01f) has joined #ceph
[9:40] * KevinPerks (~Adium@cpe-066-026-252-218.triad.res.rr.com) Quit (Ping timeout: 480 seconds)
[9:43] * The_Bishop_ (~bishop@f050145151.adsl.alicedsl.de) Quit (Ping timeout: 480 seconds)
[9:46] * AfC (~andrew@2001:44b8:31cb:d400:6e88:14ff:fe33:2a9c) Quit (Quit: Leaving.)
[9:54] * rendar (~s@host76-141-dynamic.59-82-r.retail.telecomitalia.it) has joined #ceph
[9:58] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[10:06] * Cataglottism (~Cataglott@dsl-087-195-030-184.solcon.nl) has joined #ceph
[10:17] * yanzheng (~zhyan@134.134.139.72) Quit (Quit: Leaving)
[10:20] * b0e (~aledermue@juniper1.netways.de) has joined #ceph
[10:20] * TMM (~hp@c97185.upc-c.chello.nl) Quit (Ping timeout: 480 seconds)
[10:23] * sarob (~sarob@2601:9:7080:13a:6c09:5900:86fb:82e2) has joined #ceph
[10:31] * sarob (~sarob@2601:9:7080:13a:6c09:5900:86fb:82e2) Quit (Ping timeout: 480 seconds)
[10:31] * banks (~banks@host86-154-234-37.range86-154.btcentralplus.com) has joined #ceph
[10:33] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[10:39] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Read error: Operation timed out)
[10:42] * Midnightmyth (~quassel@93-167-84-102-static.dk.customer.tdc.net) has joined #ceph
[10:43] * allsystemsarego (~allsystem@188.25.129.255) has joined #ceph
[10:47] * TMM (~hp@sams-office-nat.tomtomgroup.com) has joined #ceph
[10:57] * Cube (~Cube@66-87-64-73.pools.spcsdns.net) Quit (Quit: Leaving.)
[10:59] * mattt_ (~textual@92.52.76.140) has joined #ceph
[11:02] * mattt (~textual@cpc9-rdng20-2-0-cust565.15-3.cable.virginm.net) Quit (Ping timeout: 480 seconds)
[11:02] * mattt_ is now known as mattt
[11:04] <josef_> Is any talks from the ceph day at Frankfurt out?
[11:12] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Quit: Konversation terminated!)
[11:18] * gstaicu (~oftc-webi@remote-munich.teradata.com) has joined #ceph
[11:19] <gstaicu> ho
[11:19] <gstaicu> hi
[11:24] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[11:25] <gstaicu> I want to log a bug
[11:25] <gstaicu> for the documentation
[11:25] <gstaicu> on openstack+ceph
[11:26] <gstaicu> can someone please help me to verify if it qualify as a bug or not?
[11:27] * Cube (~Cube@66-87-64-73.pools.spcsdns.net) has joined #ceph
[11:32] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[11:34] <fghaas> josef_: madkiss' slides are here: http://www.hastexo.com/resources/presentations/openstack-ceph-perfect-match
[11:40] * Cube (~Cube@66-87-64-73.pools.spcsdns.net) Quit (Ping timeout: 480 seconds)
[11:48] * diegows (~diegows@190.190.5.238) has joined #ceph
[11:49] * JCL (~JCL@2601:9:5980:39b:8d82:b92f:d7f3:1bff) Quit (Quit: Leaving.)
[11:54] <gstaicu> fghaas thanks a lot for the presentation Florian
[11:54] <fghaas> not my presentation, it's martin's :)
[11:54] <gstaicu> than thanks to both of you
[11:54] <gstaicu> :)
[11:55] <gstaicu> great work
[11:55] <gstaicu> I saw it perfectly on chrome
[11:56] <gstaicu> but on firefox some slides to not show
[11:56] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Quit: Siva)
[12:02] <josef_> fghaas, nice!
[12:04] <josef_> Wanted to attend but couldn't make it :-( Hope to see some videos :)
[12:04] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[12:11] * cow (~cow@ip-2607-F298-0001-0100-0000-0000-0000-FFFF.dreamhost.com) has joined #ceph
[12:12] * cow is now known as cowbar
[12:12] * banks (~banks@host86-154-234-37.range86-154.btcentralplus.com) Quit (Quit: banks)
[12:19] <darkfader> the talk from the fujtisu guy was quite good, if you want some benchmark galore
[12:19] * yanzheng (~zhyan@jfdmzpr06-ext.jf.intel.com) has joined #ceph
[12:20] <darkfader> i think he upset a few people by calling "serious" raidcontrollers commodity hardware
[12:20] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Quit: Siva)
[12:21] <darkfader> and the big takeway was that ssd-only pools had little benefit
[12:22] <fghaas> darkfader: that last bit I'd disagree with, although I wasn't in Frankfurt so I don't know what he really said
[12:22] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[12:23] * Cataglottism (~Cataglott@dsl-087-195-030-184.solcon.nl) Quit (Quit: My Mac Pro has gone to sleep. ZZZzzz???)
[12:26] <josef_> fghaas: you mean that SSD-only pools are actually worth the effort? =)
[12:26] <fghaas> josef_: andreask will have additional input on that if he's around
[12:28] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Quit: Leaving.)
[12:30] <josef_> Since you don't want to run anything other than enterprise-grade Ceph, I'm guessing the tiering won't be in for another 6 months..?
[12:30] <josef_> As it's out in Firefly now and Dumpling is the current enterprise.
[12:30] * steki (~steki@91.195.39.5) Quit (Ping timeout: 480 seconds)
[12:31] <fghaas> josef_: firefly will be the next ICE, they're skipping emperor
[12:31] <josef_> woot :)
[12:32] <fghaas> but as for a release date for the next ICE, you need to talk to someone at inktank
[12:32] <josef_> maybe sage knows :)
[12:32] * AfC (~andrew@2001:44b8:31cb:d400:6e88:14ff:fe33:2a9c) has joined #ceph
[12:33] <fghaas> josef: possibly I know too, but I couldn't give you that info :)
[12:33] <josef_> Hypothetically.. :D
[12:34] <josef_> fghaas, I think you know everything about ceph. It seems that way anyhow ;)
[12:34] * sjm (~sjm@pool-108-53-56-179.nwrknj.fios.verizon.net) has left #ceph
[12:34] * schmee_ (~quassel@phobos.isoho.st) has joined #ceph
[12:34] <fghaas> josef_: far from it
[12:35] <josef_> btw, we're getting some new hardware soon, will be doing some pretty benchmarks! That'll be fun.
[12:35] <fghaas> btw, josef_, madkiss tells me that the talks were recorded, but obviously no word yet on whether they'll be on YT, and if so, when
[12:35] <fghaas> the Frankfurt talks, that is
[12:36] <josef_> Probably the video-editing guy not fond of just shipping videos.
[12:36] <josef_> They were released for the last one, so hopefully this one as well.
[12:37] * thomnico (~thomnico@2a01:e35:8b41:120:495b:2f8e:f264:a01f) Quit (Quit: Ex-Chat)
[12:38] * schmee (~quassel@phobos.isoho.st) Quit (Ping timeout: 480 seconds)
[12:38] * glzhao (~glzhao@220.181.11.232) Quit (Quit: leaving)
[12:42] * thomnico (~thomnico@2a01:e35:8b41:120:8d68:ccd5:8257:cbe6) has joined #ceph
[12:42] * BManojlovic (~steki@fo-d-130.180.254.37.targo.rs) has joined #ceph
[12:43] * nwf_ (~nwf@67.62.51.95) Quit (Ping timeout: 480 seconds)
[12:43] <darkfader> he had the sas pools running at 2GB/s per node and the ssd pools were like 2.05GB/s per node. he said it might be different if he had been using another extra set of pcie ssd for the journal, but ideally you'd be able to turn off the journal for that (which you can't)
[12:44] <darkfader> otherwise you also get bw problems
[12:44] <darkfader> network + write to journal + write to osds would add up to some 8GB/s if i get it right
[12:45] <darkfader> and yes i mean "B" = bytes
[12:49] * fdmanana (~fdmanana@bl5-78-108.dsl.telepac.pt) has joined #ceph
[12:50] <josef_> darkfader, 2GB/s per node with how many SSDs in it?
[12:53] * Koma (~Koma@0001c112.user.oftc.net) Quit (Ping timeout: 480 seconds)
[12:54] <darkfader> iirc one or two pcie
[12:54] <darkfader> lets check when the slides are online
[12:57] * BillK (~BillK-OFT@106-69-38-223.dyn.iinet.net.au) Quit (Ping timeout: 480 seconds)
[12:57] * i_m (~ivan.miro@deibp9eh1--blueice4n2.emea.ibm.com) has joined #ceph
[12:57] * Koma (~Koma@0001c112.user.oftc.net) has joined #ceph
[12:59] * BillK (~BillK-OFT@106-68-226-187.dyn.iinet.net.au) has joined #ceph
[13:00] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Quit: Siva)
[13:01] <fghaas> darkfader: "running" at that throughput? what does that mean, read or write or both?
[13:02] * yanzheng (~zhyan@jfdmzpr06-ext.jf.intel.com) Quit (Remote host closed the connection)
[13:03] * nwf_ (~nwf@67.62.51.95) has joined #ceph
[13:12] * ircuser-1 (~ircuser-1@35.222-62-69.ftth.swbr.surewest.net) Quit (Ping timeout: 480 seconds)
[13:16] * banks (~banks@host86-154-234-37.range86-154.btcentralplus.com) has joined #ceph
[13:16] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[13:21] * oro (~oro@2001:620:20:16:3df3:876d:8467:2eed) Quit (Ping timeout: 480 seconds)
[13:25] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[13:28] * zidarsk8 (~zidar@2001:1470:fffe:fe01:e2ca:94ff:fe34:7822) has joined #ceph
[13:33] * Cataglottism (~Cataglott@dsl-087-195-030-170.solcon.nl) has joined #ceph
[13:33] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[13:37] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Quit: Siva)
[13:38] * AfC (~andrew@2001:44b8:31cb:d400:6e88:14ff:fe33:2a9c) Quit (Quit: Leaving.)
[13:43] * mtk (~mtk@ool-44c35983.dyn.optonline.net) Quit (Read error: Connection reset by peer)
[13:44] * mtk (~mtk@ool-44c35983.dyn.optonline.net) has joined #ceph
[13:44] * BillK (~BillK-OFT@106-68-226-187.dyn.iinet.net.au) Quit (Ping timeout: 480 seconds)
[13:44] * jwillem (~jwillem@thuiscomputer.xs4all.nl) has joined #ceph
[13:46] * BillK (~BillK-OFT@106-68-65-143.dyn.iinet.net.au) has joined #ceph
[13:47] <jwillem> We get every hour files, for different sources called "lines".
[13:47] <jwillem> I have ceph working now. I understand that ceph has few builtin limit's. But want to know how you would organise ceph.
[13:47] <jwillem> We get every hour files, for different sources called "lines".
[13:48] <jwillem> we keep them several years. First years are important. Would like high avaliability
[13:49] <jwillem> later years are not so important, would like to change the redundancy of the pool
[13:50] <jwillem> I could create three pools and bring the data from one pool to the other
[13:50] <jwillem> i could create a lot of pools by month and lines, and change redundancy , and delete the pools in the end
[13:50] <fghaas> you want http://wiki.ceph.com/Planning/Blueprints/Dumpling/Erasure_encoding_as_a_storage_backend#2_.22tiered.22_storage ... but that's only happening in firefly
[13:51] <jwillem> Would working with a lot of pools (thousands) be stpud idea?
[13:51] <jwillem> yes i sure want erause coding !!!!
[13:54] * ircuser-1 (~ircuser-1@35.222-62-69.ftth.swbr.surewest.net) has joined #ceph
[13:58] <jwillem> "but that's only happening in firefly"-> i use 0.77-xx "quite new" -> if i want to test something like erasure coding. Where do i look for info
[13:58] <jwillem> i understand it is a plugin you need to use somehow
[13:59] * abique (~abique@time2market1.epfl.ch) Quit (Quit: Leaving)
[14:01] * zidarsk8 (~zidar@2001:1470:fffe:fe01:e2ca:94ff:fe34:7822) has left #ceph
[14:05] * t0rn (~ssullivan@2607:fad0:32:a02:d227:88ff:fe02:9896) has joined #ceph
[14:05] * abique (~abique@time2market1.epfl.ch) has joined #ceph
[14:09] * jcsp (~Adium@0001bf3a.user.oftc.net) Quit (Quit: Leaving.)
[14:10] * Cube (~Cube@66-87-64-73.pools.spcsdns.net) has joined #ceph
[14:11] * BillK (~BillK-OFT@106-68-65-143.dyn.iinet.net.au) Quit (Ping timeout: 480 seconds)
[14:14] * Cube (~Cube@66-87-64-73.pools.spcsdns.net) Quit (Read error: Connection reset by peer)
[14:15] * jcsp (~Adium@0001bf3a.user.oftc.net) has joined #ceph
[14:20] * andreask (~andreask@h081217067008.dyn.cm.kabsi.at) Quit (Quit: Leaving.)
[14:25] * schmee_ (~quassel@phobos.isoho.st) Quit (Quit: No Ping reply in 180 seconds.)
[14:26] * hybrid512 (~walid@LPoitiers-156-86-25-85.w193-248.abo.wanadoo.fr) Quit (Ping timeout: 480 seconds)
[14:26] * schmee (~quassel@phobos.isoho.st) has joined #ceph
[14:29] * themgt (~themgt@pc-188-95-160-190.cm.vtr.net) has joined #ceph
[14:36] * hybrid512 (~walid@LPoitiers-156-86-25-85.w193-248.abo.wanadoo.fr) has joined #ceph
[14:47] * KevinPerks (~Adium@cpe-066-026-252-218.triad.res.rr.com) has joined #ceph
[14:52] * i_m (~ivan.miro@deibp9eh1--blueice4n2.emea.ibm.com) Quit (Quit: Leaving.)
[14:58] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) Quit (Quit: dereky)
[14:58] * Cube (~Cube@66-87-64-73.pools.spcsdns.net) has joined #ceph
[14:59] * Cube (~Cube@66-87-64-73.pools.spcsdns.net) Quit ()
[14:59] * wschulze (~wschulze@cpe-72-229-37-201.nyc.res.rr.com) has joined #ceph
[15:00] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) has joined #ceph
[15:07] * jskinner (~jskinner@69.170.148.179) has joined #ceph
[15:07] * markbby (~Adium@168.94.245.3) has joined #ceph
[15:08] * oro (~oro@80-218-67-114.dclient.hispeed.ch) has joined #ceph
[15:08] * TMM (~hp@sams-office-nat.tomtomgroup.com) Quit (Quit: Ex-Chat)
[15:09] * alfredodeza (~alfredode@198.206.133.89) has joined #ceph
[15:10] * jskinner (~jskinner@69.170.148.179) Quit (Read error: No route to host)
[15:10] * jskinner (~jskinner@69.170.148.179) has joined #ceph
[15:16] <sage> josef_: fghaas: rough estimate is that the next ICE version will be out 1-2 months after firefly. it all depends on how things shake out though!
[15:17] <janos> what is ICE? longer-term stable platform?
[15:17] <fghaas> Inktank Ceph Enterprise
[15:17] <janos> ah
[15:17] <janos> ty
[15:17] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[15:17] <fghaas> pronounced "ice", not "eye cee ee"
[15:19] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[15:21] <josef_> Firefly needed some ice?
[15:22] <madkiss> hey sage
[15:22] <sage> madkiss: howdy
[15:22] <sage> josef_: :)
[15:22] <madkiss> sage: still in beautiful frankfurt? ;-)
[15:22] <sage> fghaas: as in, 'ice ice, baby'?
[15:23] <sage> madkiss: something like that
[15:23] <madkiss> sage: ouch :\
[15:23] * gregmark (~Adium@68.87.42.115) has joined #ceph
[15:23] <madkiss> ;-)
[15:23] <fghaas> sage: every time you make that reference, the FSM kills a kitten
[15:23] <madkiss> fsm?
[15:23] <madkiss> Frichard S. Mallman?
[15:24] <rotbeard> madkiss, _beautiful_ frankfurt? lets talk about that in may in berlin ;)
[15:25] <madkiss> rotbeard: actually I was being sarcastic.
[15:25] <rotbeard> i see
[15:27] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[15:33] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) Quit (Quit: dereky)
[15:34] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) has joined #ceph
[15:34] * Siva (~sivat@117.192.62.255) has joined #ceph
[15:34] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) Quit (Quit: Konversation terminated!)
[15:35] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[15:38] * Siva_ (~sivat@vpnnat.eglbp.corp.yahoo.com) has joined #ceph
[15:40] * dgbaley27 (~matt@c-76-120-64-12.hsd1.co.comcast.net) has joined #ceph
[15:41] * valeech (~valeech@166.170.42.80) has joined #ceph
[15:41] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) has joined #ceph
[15:41] * dgbaley27 (~matt@c-76-120-64-12.hsd1.co.comcast.net) Quit ()
[15:41] * dgbaley27 (~matt@c-76-120-64-12.hsd1.co.comcast.net) has joined #ceph
[15:42] * Siva (~sivat@117.192.62.255) Quit (Ping timeout: 480 seconds)
[15:42] * Siva_ is now known as Siva
[15:43] * sarob (~sarob@c-50-161-65-119.hsd1.ca.comcast.net) Quit (Remote host closed the connection)
[15:43] * sarob (~sarob@2601:9:7080:13a:c17a:ae09:c318:f7cb) has joined #ceph
[15:45] * alfredodeza (~alfredode@198.206.133.89) Quit (Read error: Connection reset by peer)
[15:45] * CSa (~christian@brln-4dba2709.pool.mediaWays.net) has joined #ceph
[15:46] <valeech> I'm looking for some advice on exposing rbd via iSCSI for vmware. I need to support 2 paths from vmware to the datastore. Since tgt does not support clustering, do I use LIO and setup two iSCSI gateways pointing to the same storage or do I use tgt, setup two gateways and use DRBD to replicate between two storage locations?
[15:47] <fghaas> no no no no no no no no no no NO!
[15:47] <fghaas> http://fghaas.wordpress.com/2011/11/29/dual-primary-drbd-iscsi-and-multipath-dont-do-that/
[15:47] * ninkotech (~duplo@static-84-242-87-186.net.upcbroadband.cz) has joined #ceph
[15:48] * sroy (~sroy@207.96.182.162) has joined #ceph
[15:48] * alfredodeza (~alfredode@198.206.133.89) has joined #ceph
[15:48] <valeech> fghaas: Thanks! digesting now
[15:51] * TMM (~hp@sams-office-nat.tomtomgroup.com) has joined #ceph
[15:51] * sarob (~sarob@2601:9:7080:13a:c17a:ae09:c318:f7cb) Quit (Ping timeout: 480 seconds)
[15:54] * mjeanson_ (~mjeanson@bell.multivax.ca) has joined #ceph
[15:56] * markbby (~Adium@168.94.245.3) Quit (Quit: Leaving.)
[15:58] * mjeanson (~mjeanson@00012705.user.oftc.net) Quit (Ping timeout: 480 seconds)
[16:00] * steki (~steki@91.195.39.5) has joined #ceph
[16:00] * mjeanson (~mjeanson@bell.multivax.ca) has joined #ceph
[16:01] * arbrandes (~arbrandes@189.78.56.95) has joined #ceph
[16:04] * nwat (~textual@c-50-131-197-174.hsd1.ca.comcast.net) has joined #ceph
[16:07] * markbby (~Adium@168.94.245.3) has joined #ceph
[16:07] * mjeanson_ (~mjeanson@bell.multivax.ca) Quit (Ping timeout: 480 seconds)
[16:15] <valeech> fghaas: ok so dual-primary drbd is not a good idea. Is the only way to get ha iscsi targets to use lio and pacemaker?
[16:20] * Cataglottism (~Cataglott@dsl-087-195-030-170.solcon.nl) Quit (Ping timeout: 480 seconds)
[16:22] * Cataglottism (~Cataglott@dsl-087-195-030-170.solcon.nl) has joined #ceph
[16:24] * erice (~erice@50.240.86.181) has joined #ceph
[16:25] * sprachgenerator (~sprachgen@130.202.135.176) has joined #ceph
[16:26] * JCL (~JCL@2601:9:5980:39b:cce9:d2ce:292f:35dd) has joined #ceph
[16:29] * bandrus (~Adium@adsl-75-5-250-121.dsl.scrm01.sbcglobal.net) has joined #ceph
[16:29] * BManojlovic (~steki@fo-d-130.180.254.37.targo.rs) Quit (Remote host closed the connection)
[16:29] * banks (~banks@host86-154-234-37.range86-154.btcentralplus.com) Quit (Quit: banks)
[16:31] <madkiss> valeech: Whats wrong with Ceph+tgt?
[16:31] <madkiss> You would still need Pacemaker to actually run the target somewhere, of course, but the storage backend part wouldn't be much of a concern anymore
[16:32] * banks (~banks@host86-154-234-37.range86-154.btcentralplus.com) has joined #ceph
[16:35] <valeech> madkiss: the problem is mostly my ignorance :) in all of my research so far I did not come across using pacemaker to cluster tgt as an option so the only real option I saw was to use 2 vms running lio to point to the same rbd.
[16:36] * zerick (~eocrospom@190.187.21.53) has joined #ceph
[16:41] * hasues (~hasues@kwfw01.scrippsnetworksinteractive.com) has joined #ceph
[16:45] * valeech (~valeech@166.170.42.80) Quit (Quit: valeech)
[16:47] * mtanski (~mtanski@69.193.178.202) has joined #ceph
[16:50] * wrencsok (~wrencsok@wsip-174-79-34-244.ph.ph.cox.net) Quit (Quit: Leaving.)
[16:54] <sage> madkiss: valeech: i think the main thing to watch out for with dual-tgt is fencing. i haven't looked at this closely, but i suspect that in order to do safe fail-over or multipathing there needs to be some integration with scsi reservations and/or rbd advisory locking
[16:54] <sage> (and fencing when rbd locks are broken during failover)
[16:55] * valeech (~valeech@64.191.222.117) has joined #ceph
[16:55] * elder (~elder@c-71-195-31-37.hsd1.mn.comcast.net) Quit (Quit: Leaving)
[16:56] <rotbeard> general question: ceph + tgt + vmware is production ready at all or isn't?
[16:57] <madkiss> sage: in the cluster context, fencing generally is a good idea :)
[16:58] * sputnik13 (~sputnik13@wsip-68-105-248-60.sd.sd.cox.net) Quit (Quit: Textual IRC Client: www.textualapp.com)
[16:59] * banks (~banks@host86-154-234-37.range86-154.btcentralplus.com) Quit (Quit: banks)
[16:59] * sjm (~sjm@gzac10-107-1.nje.twosigma.com) has joined #ceph
[17:00] <madkiss> rotbeard: To the best of my knowledge, librados support in tgt is still marked experimental, so no.
[17:01] <rotbeard> k, thanks
[17:01] <fghaas> s/librados/librbd/, but same thing :)
[17:01] <rotbeard> so there is no _really_ stable setup for using ceph as a storage backend for vmware?
[17:01] <madkiss> that is true.
[17:02] <madkiss> well
[17:02] <rotbeard> (they should support ceph at all)
[17:02] <madkiss> unless you go with some sort of Cluster manager that is running on "iSCSI gateway nodes"
[17:03] * mtk (~mtk@ool-44c35983.dyn.optonline.net) Quit (Read error: Connection reset by peer)
[17:04] * mtk (~mtk@ool-44c35983.dyn.optonline.net) has joined #ceph
[17:05] * Guest1743 (~astra@178.75.71.13) has joined #ceph
[17:05] * sleinen1 (~Adium@2001:620:0:26:d112:2b0c:f3a5:a7fc) has left #ceph
[17:06] <Guest1743> hi
[17:06] * sputnik13 (~sputnik13@wsip-68-105-248-60.sd.sd.cox.net) has joined #ceph
[17:07] * Guest1743 (~astra@178.75.71.13) Quit (Quit: ?????????? ?? ???? ?????? (xchat 2.4.5 ?????? ????????????))
[17:08] <rotbeard> madkiss, for example running tgt as a pacemaker cluster ressource?
[17:09] * jskinner (~jskinner@69.170.148.179) Quit (Quit: Leaving...)
[17:09] <madkiss> on a separate host on top of rbd.ko.
[17:10] * sputnik13 (~sputnik13@wsip-68-105-248-60.sd.sd.cox.net) Quit ()
[17:10] <rotbeard> ok, so our plan to buy some nodes (2 or 3) for the iscsi stuff only should do...
[17:10] * yanzheng (~zhyan@134.134.137.73) has joined #ceph
[17:10] * andreask (~andreask@h081217067008.dyn.cm.kabsi.at) has joined #ceph
[17:10] * ChanServ sets mode +v andreask
[17:10] <rotbeard> we are running ceph the first time btw ;)
[17:11] <valeech> rotbeard: we are in the same boat exactly today. Trying to determine best method to have ha iscsi with ceph for vmware
[17:11] <rotbeard> looks like ;)
[17:12] <valeech> looks like it will be a pacemaker cluster with tgt running active/standby.
[17:12] * CSa (~christian@brln-4dba2709.pool.mediaWays.net) Quit (Read error: Operation timed out)
[17:13] <fghaas> valeech: that sounds good modulo support issues (iirc, using the Inktank rbd packages will break your Red Hat tgt support, and I'm unsure of inktank's support policy regarding "extra" packages like their own tgt build)
[17:13] <rotbeard> our current fear is the bottleneck, that such a cluster could be.
[17:14] <fghaas> rotbeard: an iscsi cluster will *always* be a bottleneck versus a hundred clients being able to talk directly to OSDs, like with native rbd
[17:14] <valeech> fghaas: makes sense.
[17:15] <valeech> any sizing recommendations for the gateways? :)
[17:15] <rotbeard> of course, but for now we have no idea wether 2x 10gbits ethernet will do the job _good_ or maybe 4x 10gbits
[17:15] <fghaas> valeech: that being said, please don't take my work re inktank support policies; an inktank person will be much more qualified to give information on that
[17:15] * yanzheng (~zhyan@134.134.137.73) Quit (Remote host closed the connection)
[17:16] <valeech> fghaas: understood. thanks for the help.
[17:18] * thomnico (~thomnico@2a01:e35:8b41:120:8d68:ccd5:8257:cbe6) Quit (Quit: Ex-Chat)
[17:18] * thomnico (~thomnico@2a01:e35:8b41:120:8d68:ccd5:8257:cbe6) has joined #ceph
[17:19] <fghaas> I will say that if anyone needs help with pacemaker/rbd integration in a PS capacity, madkiss, andreask or myself are probably the right people to talk to :) ... but that's actually OT for this channel, so I'll say no more
[17:22] * oro (~oro@80-218-67-114.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[17:30] * thomnico (~thomnico@2a01:e35:8b41:120:8d68:ccd5:8257:cbe6) Quit (Quit: Ex-Chat)
[17:35] * Underbyte (~jerrad@pat-global.macpractice.net) Quit (Remote host closed the connection)
[17:37] * thomnico (~thomnico@2a01:e35:8b41:120:8d68:ccd5:8257:cbe6) has joined #ceph
[17:38] * Pedras (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) has joined #ceph
[17:39] * Underbyte (~jerrad@pat-global.macpractice.net) has joined #ceph
[17:41] * andreask (~andreask@h081217067008.dyn.cm.kabsi.at) has left #ceph
[17:43] * Underbyte (~jerrad@pat-global.macpractice.net) Quit ()
[17:43] * jharley (~jharley@76-10-151-146.dsl.teksavvy.com) has joined #ceph
[17:47] <bdonnahue2> im working on ceph deploy but having problems. I was able to get the monitors to reach quorum. the ceph deploy log say so.
[17:47] <bdonnahue2> but then when i log into a monitor i see
[17:47] <bdonnahue2> health HEALTH_ERR 192 pgs stuck inactive; 192 pgs stuck unclean; no osds; clock skew detected on mon.OS-004-OSD-002, mon.OS-004-OSD-003
[17:47] <bdonnahue2> monmap e1: 3 mons at {OS-004-OSD-001=50.4.50.101:6789/0,OS-004-OSD-002=50.4.50.102:6789/0,OS-004-OSD-003=50.4.50.103:6789/0}, election epoch 8, quorum 0,1,2 OS-004-OSD-001,OS-004-OSD-002,OS-004-OSD-003
[17:47] <bdonnahue2> (sorry for multiline paste)
[17:49] * ircolle (~Adium@2601:1:8380:2d9:2c52:e3a9:f209:4206) has joined #ceph
[17:51] <madkiss> OS-004 sounds like an Austrian Airlines flght number.
[17:51] <madkiss> *duck*
[17:51] * nwat_ (~textual@c-50-131-197-174.hsd1.ca.comcast.net) has joined #ceph
[17:53] * Siva (~sivat@vpnnat.eglbp.corp.yahoo.com) Quit (Quit: Siva)
[17:55] <kitz> bdonnahue2: make sure you're running ntp to sync the clocks.
[17:56] * ivotron (~ivotron@adsl-99-146-2-252.dsl.pltn13.sbcglobal.net) Quit (Remote host closed the connection)
[17:56] <kitz> ceph needs clocks synced within .05 seconds.
[17:56] * ivotron (~ivotron@adsl-99-146-2-252.dsl.pltn13.sbcglobal.net) has joined #ceph
[17:57] * sputnik13 (~sputnik13@207.8.121.241) has joined #ceph
[17:57] <Fetch> anyone happen to run ceph osd cohosted on nova compute nodes, and hitting openswitch falling down under i/o load?
[17:57] * neurodrone (~neurodron@static-108-30-171-7.nycmny.fios.verizon.net) Quit (Quit: neurodrone)
[17:57] <Fetch> I know it's a long shot, but the openvswitch bubs are quiet
[17:57] * neurodrone (~neurodron@static-108-30-171-7.nycmny.fios.verizon.net) has joined #ceph
[17:57] <bdonnahue2> ok ill figure out the ntp issue thanks kitz (i was hoping that would not be an issue)
[17:58] * nwat (~textual@c-50-131-197-174.hsd1.ca.comcast.net) Quit (Read error: Operation timed out)
[17:59] * orion195 (~oftc-webi@213.244.168.133) Quit (Quit: Page closed)
[18:01] * TMM (~hp@sams-office-nat.tomtomgroup.com) Quit (Quit: Ex-Chat)
[18:03] * b0e (~aledermue@juniper1.netways.de) Quit (Ping timeout: 480 seconds)
[18:03] * Underbyte (~jerrad@pat-global.macpractice.net) has joined #ceph
[18:04] * ivotron (~ivotron@adsl-99-146-2-252.dsl.pltn13.sbcglobal.net) Quit (Ping timeout: 480 seconds)
[18:06] * angdraug (~angdraug@12.164.168.117) has joined #ceph
[18:08] * nwat_ (~textual@c-50-131-197-174.hsd1.ca.comcast.net) Quit (Quit: My MacBook has gone to sleep. ZZZzzz???)
[18:10] * nwat (~textual@c-50-131-197-174.hsd1.ca.comcast.net) has joined #ceph
[18:10] * diegows (~diegows@190.190.5.238) Quit (Read error: Operation timed out)
[18:11] * rmoe (~quassel@173-228-89-134.dsl.static.sonic.net) Quit (Ping timeout: 480 seconds)
[18:15] * JoeGruher (~JoeGruher@134.134.139.76) has joined #ceph
[18:15] <JoeGruher> in the Kraken dashboard it shows "apply" and "commit" latencies for each OSD... what do those values represent, what's the difference between apply and commit?
[18:18] * japuzzo (~japuzzo@ool-4570886e.dyn.optonline.net) has joined #ceph
[18:18] * JoeGruher (~JoeGruher@134.134.139.76) Quit ()
[18:18] * andreask (~andreask@h081217067008.dyn.cm.kabsi.at) has joined #ceph
[18:18] * ChanServ sets mode +v andreask
[18:18] * JoeGruher (~JoeGruher@134.134.139.76) has joined #ceph
[18:18] * wrencsok (~wrencsok@wsip-174-79-34-244.ph.ph.cox.net) has joined #ceph
[18:20] * xarses_ (~andreww@c-24-23-183-44.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[18:26] * Cube (~Cube@66-87-64-198.pools.spcsdns.net) has joined #ceph
[18:28] * nwat (~textual@c-50-131-197-174.hsd1.ca.comcast.net) Quit (Quit: My MacBook has gone to sleep. ZZZzzz???)
[18:30] * mtanski_ (~mtanski@69.193.178.202) has joined #ceph
[18:31] * rmoe (~quassel@12.164.168.117) has joined #ceph
[18:34] * mtanski (~mtanski@69.193.178.202) Quit (Ping timeout: 480 seconds)
[18:34] * mtanski_ is now known as mtanski
[18:34] * nwat (~textual@c-50-131-197-174.hsd1.ca.comcast.net) has joined #ceph
[18:36] * dgbaley27 (~matt@c-76-120-64-12.hsd1.co.comcast.net) Quit (Quit: Leaving.)
[18:37] * JoeGruher (~JoeGruher@134.134.139.76) Quit ()
[18:38] * andreask (~andreask@h081217067008.dyn.cm.kabsi.at) has left #ceph
[18:38] * nwat (~textual@c-50-131-197-174.hsd1.ca.comcast.net) Quit (Read error: Operation timed out)
[18:39] * Kioob (~kioob@2a01:e34:ec0a:c0f0:21e:8cff:fe07:45b6) has joined #ceph
[18:42] * Pedras (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[18:43] * themgt (~themgt@pc-188-95-160-190.cm.vtr.net) Quit (Quit: Pogoapp - http://www.pogoapp.com)
[18:43] * Pedras (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) has joined #ceph
[18:46] * JeffK (~JeffK@38.99.52.10) Quit (Read error: Connection reset by peer)
[18:47] * JeffK (~JeffK@38.99.52.10) has joined #ceph
[18:51] * mtanski (~mtanski@69.193.178.202) Quit (Quit: mtanski)
[18:51] * mrabbitt (~matt@64.191.222.117) has joined #ceph
[18:54] <mrabbitt> I deployed an osd using ceph-deploy specifying that the journal should go to another disk(an ssd), should I see those journal partitions mounted?
[18:54] <mrabbitt> when I do a ceph-disk list, I see the mounts for the 4 osds I have on this node. But the ssd partitions (dev/sdf1, /dev/sdf2, etc.) just say other, there is no mount
[18:56] * dpippenger (~riven@cpe-198-72-157-189.socal.res.rr.com) Quit (Ping timeout: 480 seconds)
[18:56] * steki (~steki@91.195.39.5) Quit (Ping timeout: 480 seconds)
[18:58] * jharley (~jharley@76-10-151-146.dsl.teksavvy.com) Quit (Quit: jharley)
[18:59] * gregmark (~Adium@68.87.42.115) Quit (Quit: Leaving.)
[18:59] * Sysadmin88 (~IceChat77@176.254.32.31) has joined #ceph
[18:59] * gregmark (~Adium@68.87.42.115) has joined #ceph
[18:59] * dpippenger (~riven@172.56.31.115) has joined #ceph
[18:59] * thomnico (~thomnico@2a01:e35:8b41:120:8d68:ccd5:8257:cbe6) Quit (Quit: Ex-Chat)
[19:00] <joef> Is there an easy way to calculate usable space for different replica scenarios? In turn, determine what replica policy one might choose depending on the use case?
[19:02] * Sysadmin88 (~IceChat77@176.254.32.31) Quit ()
[19:02] * Sysadmin88 (~IceChat77@176.254.32.31) has joined #ceph
[19:05] * nwat (~textual@eduroam-230-236.ucsc.edu) has joined #ceph
[19:05] * mtk (~mtk@ool-44c35983.dyn.optonline.net) Quit (Read error: Connection reset by peer)
[19:07] * mtk (~mtk@ool-44c35983.dyn.optonline.net) has joined #ceph
[19:08] * dpippenger (~riven@172.56.31.115) Quit (Read error: Connection reset by peer)
[19:08] * mattt (~textual@92.52.76.140) Quit (Read error: Connection reset by peer)
[19:09] * dpippenger (~riven@172.56.31.115) has joined #ceph
[19:10] * fghaas (~florian@91-119-140-244.dynamic.xdsl-line.inode.at) has left #ceph
[19:15] * xarses_ (~andreww@12.164.168.117) has joined #ceph
[19:19] * neurodrone (~neurodron@static-108-30-171-7.nycmny.fios.verizon.net) Quit (Quit: neurodrone)
[19:20] * neurodrone (~neurodron@static-108-30-171-7.nycmny.fios.verizon.net) has joined #ceph
[19:29] * mtk (~mtk@ool-44c35983.dyn.optonline.net) Quit (Read error: Operation timed out)
[19:29] * sjm (~sjm@gzac10-107-1.nje.twosigma.com) Quit (Ping timeout: 480 seconds)
[19:31] * diegows (~diegows@190.190.5.238) has joined #ceph
[19:31] * rotbeard (~redbeard@b2b-94-79-138-170.unitymedia.biz) Quit (Quit: Leaving)
[19:34] * sputnik13 (~sputnik13@207.8.121.241) Quit (Ping timeout: 480 seconds)
[19:36] * sjm (~sjm@gzac10-107-1.nje.twosigma.com) has joined #ceph
[19:36] * CSa (~christian@brln-4dba2709.pool.mediaWays.net) has joined #ceph
[19:36] * sputnik13 (~sputnik13@207.8.121.241) has joined #ceph
[19:37] * jbd_ (~jbd_@2001:41d0:52:a00::77) has left #ceph
[19:37] * CSa (~christian@brln-4dba2709.pool.mediaWays.net) Quit (Read error: Connection reset by peer)
[19:39] * mtk (~mtk@ool-44c35983.dyn.optonline.net) has joined #ceph
[19:43] * owenmurr (~owenmurr@109.175.201.0) has joined #ceph
[19:46] * BManojlovic (~steki@fo-d-130.180.254.37.targo.rs) has joined #ceph
[19:47] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) Quit (Quit: dereky)
[19:47] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) has joined #ceph
[19:51] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) Quit ()
[19:51] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) has joined #ceph
[19:52] * keeperandy (~textual@c-71-200-84-53.hsd1.md.comcast.net) has joined #ceph
[19:54] * owenmurr (~owenmurr@109.175.201.0) Quit (Quit: Lost terminal)
[19:56] <cjh973> hey guys, I was looking at the nodirstat option. It says cat dirname for stats. What stats does it give you back?
[19:57] * dmsimard (~Adium@69.165.206.93) has joined #ceph
[20:03] * sjm (~sjm@gzac10-107-1.nje.twosigma.com) Quit (Quit: Leaving.)
[20:03] * sjm (~sjm@gzac10-107-1.nje.twosigma.com) has joined #ceph
[20:05] * gstaicu (~oftc-webi@remote-munich.teradata.com) Quit (Remote host closed the connection)
[20:05] * dmsimard1 (~Adium@108.163.152.66) has joined #ceph
[20:10] * dmsimard (~Adium@69.165.206.93) Quit (Read error: Operation timed out)
[20:11] * houkouonchi-home (~linux@houkouonchi-1-pt.tunnel.tserv15.lax1.ipv6.he.net) has joined #ceph
[20:15] * dmsimard1 is now known as dmsimard
[20:21] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) Quit (Quit: dereky)
[20:22] * sputnik13 (~sputnik13@207.8.121.241) Quit (Quit: My MacBook has gone to sleep. ZZZzzz???)
[20:23] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) has joined #ceph
[20:23] * sputnik13 (~sputnik13@207.8.121.241) has joined #ceph
[20:24] * jjgalvez (~jjgalvez@ip98-167-16-160.lv.lv.cox.net) Quit (Read error: Connection reset by peer)
[20:25] * ivotron (~ivotron@dhcp-59-219.cse.ucsc.edu) has joined #ceph
[20:30] * piezo (~chatzilla@107-197-220-222.lightspeed.irvnca.sbcglobal.net) has joined #ceph
[20:32] * janos (~messy@static-71-176-211-4.rcmdva.fios.verizon.net) Quit (Read error: Connection reset by peer)
[20:33] * gregsfortytwo1 (~Adium@2607:f298:a:607:7c6b:309a:af96:7699) has joined #ceph
[20:35] * jjgalvez (~jjgalvez@ip98-167-16-160.lv.lv.cox.net) has joined #ceph
[20:36] * rotbeard (~redbeard@2a02:908:df10:6f00:76f0:6dff:fe3b:994d) has joined #ceph
[20:38] * The_Bishop__ (~bishop@g229133036.adsl.alicedsl.de) Quit (Ping timeout: 480 seconds)
[20:39] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) Quit (Quit: dereky)
[20:39] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) has joined #ceph
[20:43] * thb (~me@0001bd58.user.oftc.net) Quit (Ping timeout: 480 seconds)
[20:43] * calcifer (~calcifer@h-873.lbcfree.net) has joined #ceph
[20:45] * dpippenger1 (~riven@cpe-198-72-157-189.socal.res.rr.com) has joined #ceph
[20:46] * goerk (~goerk@ip-176-198-112-20.unitymediagroup.de) has joined #ceph
[20:50] * dpippenger (~riven@172.56.31.115) Quit (Ping timeout: 480 seconds)
[20:52] * piezo (~chatzilla@107-197-220-222.lightspeed.irvnca.sbcglobal.net) Quit (Quit: ChatZilla 0.9.90.1 [Firefox 27.0.1/20140212131424])
[20:53] * piezo (~kvirc@107-197-220-222.lightspeed.irvnca.sbcglobal.net) has joined #ceph
[21:00] * mattt (~textual@cpc9-rdng20-2-0-cust565.15-3.cable.virginm.net) has joined #ceph
[21:01] <mo-> given a bog-standard minimal setup of 3 ceph nodes with 2 OSDs each and replica=1, would the cluster automatically distribute objects so that theyre spread across multiple IP addresses?
[21:02] <mo-> trying to evaluate whether itd be possible to down a node without losing access to any object
[21:06] <bandrus> mo-: with replica=1, you could not afford to lose a node.
[21:06] <bandrus> with replica=2, and min_size=1, you could
[21:07] <bandrus> default rep size is 2, btw, and by default, ceph will place copies on different nodes
[21:07] <mo-> thanks. wish I was in the loop how that system was set up. all of the ceph commands block so I cant even issue osd dump to check on those settings
[21:07] <mo-> also documentation says
[21:07] <mo-> By default, ceph Creates one replica of an object
[21:07] <darkfader> mo-: did you try the admin socket thing
[21:07] <darkfader> this should never block
[21:07] <mo-> I have not, great idea
[21:08] <bandrus> mo-: where in the documentation does it state that?
[21:08] <bandrus> oh - 1 replica yes
[21:08] <mo-> http://ceph.com/docs/master/rados/operations/pools/
[21:08] <mo-> at the very bottom
[21:08] <bandrus> apologies. 1 replica replica size=2
[21:08] <bandrus> I was thinking size=1
[21:09] <bandrus> so 1 replica would be size=2, and a the same data should not exist on the same node
[21:10] * mtk (~mtk@ool-44c35983.dyn.optonline.net) Quit (Read error: Connection reset by peer)
[21:10] <bandrus> so yes - you should be able to lose a node. Not saying it would be ideal for cluster health, but you should theoretically be able to access any object with the default settings in your configuration
[21:10] <mo-> ok great
[21:10] <bandrus> many other factors could come into play that would result in lost access, however
[21:11] <mo-> ima try the admin socket thing
[21:11] <bandrus> or rather, reduced access
[21:11] * mtk (~mtk@ool-44c35983.dyn.optonline.net) has joined #ceph
[21:13] <valeech> What type of performance should I expect from rados bench on a system with 3 nodes and 4 osds per node?
[21:14] <valeech> i have a single ssd handling journaling for the four osds
[21:15] <valeech> running 4th wd black drives, 7200 rpm. I am running radios bench on a server that is 10g connected to the mon and osds.
[21:15] <valeech> *4tb
[21:16] <mo-> im seeing min_rep 1. whats the replica setting called?
[21:18] <valeech> I am running the command 'rados bench -p rbd 100 write'. throughput starts out around 300MB/s but quickly degrades to around 75MB/s
[21:19] <bandrus> mo-: http://ceph.com/docs/master/rados/operations/pools/#set-pool-values
[21:21] <mo-> I was looking at that. the admin socket doesnt seem to offer osd * commands tho
[21:22] <mo-> theres only config show, which doesnt seem to contain pg/pool settings
[21:22] * yuriw (~Adium@c-71-202-126-141.hsd1.ca.comcast.net) Quit (Read error: Connection reset by peer)
[21:22] * yuriw (~Adium@c-71-202-126-141.hsd1.ca.comcast.net) has joined #ceph
[21:22] <mo-> "osd_pool_default_size": "2",
[21:22] <mo-> there it is
[21:23] * The_Bishop (~bishop@g229133036.adsl.alicedsl.de) has joined #ceph
[21:23] <mo-> I guess
[21:26] * arbrandes (~arbrandes@189.78.56.95) Quit (Quit: Leaving)
[21:26] * keeperandy (~textual@c-71-200-84-53.hsd1.md.comcast.net) Quit (Quit: Textual IRC Client: www.textualapp.com)
[21:29] * root (~root@176.28.50.139) has joined #ceph
[21:31] * root (~root@176.28.50.139) Quit ()
[21:31] * root (~root@176.28.50.139) has joined #ceph
[21:39] <mo-> so. trying to prepare for a node reboot. I assume I wont be able to "osd set noout" since quorum has been lost, right?
[21:42] * diegows (~diegows@190.190.5.238) Quit (Read error: Operation timed out)
[21:54] * gregsfortytwo1 (~Adium@2607:f298:a:607:7c6b:309a:af96:7699) Quit (Quit: Leaving.)
[22:02] <dmick> osd_pool_default_size affects new pool creation, not existing pools
[22:03] <mo-> yea but the guy said he didnt deviate from defaults
[22:03] <dmick> k
[22:03] <dmick> as long as you weren't thinking you could change it
[22:03] <mo-> nono, thats not it
[22:05] <dmick> but yes, you can't do much without a monitor quorum
[22:05] <mo-> my problem is that I cant risk restarting a node then, since the "cluster" would try to rebalance the data
[22:06] <mo-> and I would assume this would generate more data in the store.db of the alive mons
[22:07] <mo-> which would be likely to kill another mon that is close to hitting 95% disk utilization
[22:07] <dmick> I don't understand your full situation, but, why would the cluster start out without quorum before you take this administrative action?
[22:08] <dmick> and there are grace periods before the cluster takes action on missing OSDs
[22:09] <mo-> oh? thats great news.
[22:09] <mo-> I think im looking for this then? "The grace period in seconds before declaring unresponsive Ceph OSD Daemons down."
[22:09] <dmick> again, I don't understand where you're starting from; perhaps you could summarize?
[22:09] <mo-> ok will try
[22:10] <dmick> why don't yo0u have quorum now?
[22:10] <mo-> cluster of 3 nodes, 1 mon, 2 osd each. 2 mons died (disk space ran out), so it was decided to add another mon
[22:11] <dmick> I would think you'd want to fix one of the two dead mons
[22:11] <mo-> that mon never synced up correctly and greg said it might not ever be able to due to bugs in the used version. so its 2/4 mons now
[22:11] <mo-> I was able to free up some disk space to get mon 2 back, which is temporarily running. mon 3 does not start tho
[22:11] <mo-> its completely blocking, even in debug mode. a situation only a reboot would fix afaik
[22:12] * t0rn (~ssullivan@2607:fad0:32:a02:d227:88ff:fe02:9896) Quit (Quit: Leaving.)
[22:12] <dmick> you think a kernel reboot is going to help the mon start cleanly?
[22:12] <mo-> so mon 4 fails to sync up, and mon 3 is blocking
[22:12] <mo-> well in the past it has, I understand this doesnt make much sense
[22:12] <mo-> but Im dealing with a .61.2 cluster, which apparantly has lots of syncing bugs
[22:13] <dmick> personally, I would be finding out why that mon isn't booting, and very pessimistic about "host reboot" helping
[22:13] <mo-> appraciate the input so far
[22:14] <dmick> if it seems to have helped int he past tho and it doesn't take many minutes to reboot, it might be relatively safe to reboot
[22:14] <mo-> I dont know how finding that out would go tho
[22:14] <mo-> if I start the mon, the log will display the initial log line with the pid
[22:14] <mo-> and then NOTHING
[22:14] <mo-> not even in debug mode
[22:14] <mo-> I dont know how diagnose anything from that
[22:15] <dmick> what do you mean by "debug mode" exactly? just -d?
[22:15] <mo-> yea
[22:15] <dmick> there's a lot more debug you can enable in the mon
[22:15] * Underbyte (~jerrad@pat-global.macpractice.net) Quit (Quit: Linkinus - http://linkinus.com)
[22:15] <dmick> even without that, does the status from daemon mon_status never change on the one that fails to boot?
[22:16] <mo-> I can check that
[22:16] <mo-> the other debug thing I didnt know about. its the settings in the ceph conf youre refering to, right?
[22:18] <dmick> they can be there....but they can also be on cmdline
[22:19] <mo-> trying to find out how I could get mon_status via socket if possible since again.. no quorum, "ceph mon_status" just blocks
[22:19] <dmick> daemon
[22:20] <mo-> lets see
[22:21] <mo-> used "ceph daemon mon.c mon_status". its blocking also
[22:21] * markbby (~Adium@168.94.245.3) Quit (Quit: Leaving.)
[22:21] <dmick> is mon.c running at all?
[22:21] <dmick> I don't think I've ever seen that block
[22:21] <mo-> it does appear in ps -ef, yea
[22:21] <dmick> what about ceph daemon mon.c version?
[22:22] <mo-> only outputting faults trying to reach the mon
[22:23] <dmick> I am totally confused; faults are from normal mon commands
[22:23] <mo-> netstat tells me it hasnt opened the port, so it must be stuck before that
[22:23] <dmick> which this is not
[22:23] <dmick> can you pastebin the version invocation and its response?
[22:23] <mo-> yea
[22:24] <mo-> (waiting for say 4 fault messages before copying)
[22:25] <mo-> http://pastebin.com/kpqLUCdD
[22:26] <mo-> looks like its trying to contact the mon via network, which the mon isnt listening to yet
[22:26] <dmick> yeah
[22:26] * hasues (~hasues@kwfw01.scrippsnetworksinteractive.com) Quit (Quit: Leaving.)
[22:27] <dmick> try this instead: ceph --admin-daemon /var/run/ceph/mon.c.asok mon_status
[22:27] <dmick> (that mon.c.asok path element may not be completely correct...maybe ceph-mon.c.asok)
[22:28] <mo-> read only got 0 bytes of 4 expected for response length; invalid command?
[22:29] <dmick> same for version?
[22:29] <mo-> so this thing actually responds. I can see the help
[22:29] <dmick> ah, ok, so help works, but just not mon_status. sigh.
[22:29] <mo-> version outputs
[22:29] <dmick> I guess it's 'start up with CLI debug' then
[22:29] <dmick> try adding --debug_mon=30 to the args when you start the mon
[22:29] <mo-> again, appreciate you helpin me out
[22:30] <mo-> will do
[22:30] <dmick> and perhaps use -f
[22:30] <dmick> so it comes to the console
[22:30] <dmick> and can be ^c'ed
[22:31] <mo-> running
[22:31] <mo-> log says "needs conversion" and "obtain_monmap"... lets see where it stops
[22:31] <mo-> well.. it stops right there, nothing past that
[22:32] <mo-> so like... could I dump the monmap from a running mon (no quorum, so via socket only) and inject it into mon.c?
[22:33] <dmick> conceivably, but now this is past my knowledge
[22:33] <dmick> there may be some doc about this
[22:35] <mo-> ok so couple minutes later, log still only says that
[22:36] <dmick> http://ceph.com/docs/master/rados/operations/add-or-rm-mons/#changing-a-monitor-s-ip-address-the-messy-way is all the hints I can find; it's a different motivation, but has info about how monmaps can be manipulated/injected
[22:36] <dmick> I do doubt very much that host reboot will help tho
[22:37] <mo-> the link you gave starts off with "ceph mon getmap" tho :/
[22:37] <dmick> yeah
[22:37] <dmick> and I don't think that's easily extractable any other way, come to think of it, these days
[22:38] <mo-> ooooh
[22:38] <mo-> I may have just found it
[22:38] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) Quit (Quit: dereky)
[22:39] <mo-> I ran the daemon thing on mon.b for mon_status
[22:39] <mo-> and that outputs a monmap blob
[22:39] <mo-> not sure if thats what its supposed to look like tho
[22:39] <kraken> ???_???
[22:39] <dmick> if monmaptool can deal with it, or if you can sand it down so it can, that might work
[22:39] <kraken> http://i.imgur.com/hYdy4.gif
[22:40] <mo-> hm lets see
[22:40] <mo-> can you see how a monmap dump would have to look like? pondering how much I need to cut
[22:41] <dmick> mon getmap dumps a binary
[22:41] <mo-> damn
[22:42] <dmick> monmaptool --print shows it was
[22:42] * Lamuki (~Lamuki@46.120.134.250) has joined #ceph
[22:42] <dmick> epoch 1
[22:42] <dmick> fsid b0fd9daf-70d2-41f1-8870-fc0209ab30d6
[22:42] <dmick> last_changed 2014-02-18 12:17:01.834846
[22:42] <dmick> created 2014-02-18 12:17:01.834846
[22:42] <dmick> 0: 192.168.107.227:6789/0 mon.a
[22:42] <dmick> for a single-mon cluster, obviously
[22:42] <mo-> yea Im looking at something like that
[22:43] <dmick> but it looks like monmaptool is about editing with CLI switchesw
[22:43] <dmick> so, probably, just read it and invoke mmt with --add options
[22:43] * Lamuki (~Lamuki@46.120.134.250) has left #ceph
[22:44] <dmick> and then verify that it prints the same
[22:44] * allsystemsarego (~allsystem@188.25.129.255) Quit (Quit: Leaving)
[22:44] * The_Bishop (~bishop@g229133036.adsl.alicedsl.de) Quit (Ping timeout: 480 seconds)
[22:45] <mo-> ah you mean like --create and --add --add --add?
[22:45] <dmick> + --fsid
[22:46] <mo-> just making sure im not ruining anything, --create will really only just dump the map to file and nothing else, right?
[22:46] <dmick> right
[22:46] <dmick> monmaptool does not talk to the cluster or even try
[22:48] * The_Bishop (~bishop@g229133036.adsl.alicedsl.de) has joined #ceph
[22:51] <mo-> hu. okay so before running that I looked at the help
[22:51] <mo-> I guess its not create but rather --generate
[22:52] <mo-> or hm
[22:52] <mo-> the example lists --create --add. weird. will try that then
[22:55] <mo-> ok, so
[22:56] <mo-> epoch, last_changed and created are different. not sure about epoch, but the other 2 are obvious
[22:57] * rendar (~s@host76-141-dynamic.59-82-r.retail.telecomitalia.it) Quit ()
[22:57] * thb (~me@port-56562.pppoe.wtnet.de) has joined #ceph
[22:58] * thb is now known as Guest1760
[22:58] <mo-> so I now try to inject the mon.c with the monmap I just made
[22:58] <mo-> ?
[22:59] <mo-> hey now. mon.c actually made it past the monmap
[22:59] <mo-> just looked at the log again
[23:01] <mo-> neither mon_status nor sync_status output anything tho, they hang
[23:02] * keith4_ (~keith4@greed.cc.lehigh.edu) Quit (Quit: Client exiting)
[23:03] <mo-> mon.c@2(probing) e16 sync_start entity( mon.0 X.Y.Z.201:6789/0 )... could mon.c actually be syncing now? I can see the df output changing slightly
[23:05] <mo-> dmick: hope you dont mind the ping. I suppose I should be waiting and knocking on all the wood I can find nearby now?
[23:08] * erice (~erice@50.240.86.181) Quit (Ping timeout: 480 seconds)
[23:10] * dereky (~derek@pool-71-114-104-38.washdc.fios.verizon.net) has joined #ceph
[23:12] * danieagle (~Daniel@179.176.61.234.dynamic.adsl.gvt.net.br) has joined #ceph
[23:13] <kitz> What should I check if my reads are great (900MiBps+) but my writes are totally abysmal (41MiBps)?
[23:15] * erice (~erice@71-218-224-83.hlrn.qwest.net) has joined #ceph
[23:18] * nwat (~textual@eduroam-230-236.ucsc.edu) Quit (Quit: My MacBook has gone to sleep. ZZZzzz???)
[23:19] * gregmark (~Adium@68.87.42.115) Quit (Quit: Leaving.)
[23:20] <dmick> sorry
[23:20] <dmick> distracted
[23:21] <dmick> mo-: maybe strace the mon, see what it's up to
[23:21] <dmick> and/or --debug-mon=30 agai
[23:21] <mo-> its still running at debug 30
[23:21] <kraken> mo- might be talking about http://tracker.ceph.com/issues/30 [multimds: slave_request on getattr]
[23:21] <mo-> thats the output
[23:22] <dmick> does it respond to mon_status?
[23:22] * fatih (~fatih@208.72.139.54) has joined #ceph
[23:22] <mo-> apparantly not. nothing happens
[23:22] <mo-> log now says
[23:23] <mo-> mon.c@2(synchronizing sync( requester state start )) e16 tick
[23:23] <mo-> I am hopeful this guy is actually currently syncing
[23:26] <fatih> hi everyone
[23:28] * erice_ (~erice@71-208-244-192.hlrn.qwest.net) has joined #ceph
[23:28] <fatih> sometimes one of our machines just get stalled, I've tried to debug a little here, I'm not an expert our devops director knows better however I wanted to ask
[23:28] <fatih> http://glui.me/?i=k5hxgryx0b8hjwd/2014-02-28_at_2.25_PM.png/
[23:28] <fatih> here as you see, the "sync" command just wait
[23:28] <fatih> we have 20-25 machines, and currently 4 of them is in a situation where it's not usable anymore
[23:29] <fatih> and all those machines have processes like this
[23:29] <fatih> this is a ubuntu machine and the "sync" is called in /etc/init.d/sigsend
[23:29] * erice (~erice@71-218-224-83.hlrn.qwest.net) Quit (Ping timeout: 480 seconds)
[23:29] <fatih> can it be possible that something here: https://ceph.com/docs/master/rbd/rbd-config-ref/ needs to be changed or tweaked ?
[23:31] <dmick> no information in that ps list of what might actually be hanging or why
[23:32] <fatih> ok what can I provide you that it shows ?
[23:32] <fatih> I've looked into dmesg -T
[23:33] <fatih> I saw a lot of socket closed errors
[23:33] <fatih> this is the dmesg output before it's get stalled: http://glui.me/?i=a0nj2q388ulizpt/2014-02-28_at_2.32_PM.png/
[23:33] <fatih> I mean after the stalling nothing happens and the latest messages are these one
[23:34] <jhujhiti> is it safe to run a qemu built for bobtail against a newer version cluster? i'd like to upgrade the bobtail cluster but i can't reboot the running VMs
[23:35] <jhujhiti> i'm using the packages here: http://ceph.com/packages/qemu-kvm/
[23:43] * diegows (~diegows@190.190.5.238) has joined #ceph
[23:43] * marrusl (~mark@209-150-43-182.c3-0.wsd-ubr2.qens-wsd.ny.cable.rcn.com) Quit (Remote host closed the connection)
[23:44] * marrusl (~mark@209-150-43-182.c3-0.wsd-ubr2.qens-wsd.ny.cable.rcn.com) has joined #ceph
[23:45] * sroy (~sroy@207.96.182.162) Quit (Ping timeout: 480 seconds)
[23:45] * markl (~mark@knm.org) Quit (Quit: leaving)
[23:46] * calcifer (~calcifer@h-873.lbcfree.net) Quit (Ping timeout: 480 seconds)
[23:46] * markl (~mark@knm.org) has joined #ceph
[23:46] * markl (~mark@knm.org) Quit ()
[23:47] * markl (~mark@knm.org) has joined #ceph
[23:47] * dmsimard (~Adium@108.163.152.66) Quit (Quit: Leaving.)
[23:48] <kitz> How do I give a client access to an additional pool? I can't seem to figure out how to use `ceph auth`
[23:49] <bdonnahue2> earlier my ceph-deploy was thought to have failed due to out of sync system clocks on my monitors
[23:49] <bdonnahue2> i have now synced the monitors using ntpd
[23:49] <bdonnahue2> i was wondering how i can tell the ceph monitors to try to reach quorum again
[23:49] <kitz> has the clock skew message gone away?
[23:49] <bdonnahue2> currently they still complain about being out of sync
[23:49] <bdonnahue2> no
[23:51] <bdonnahue2> im watching the update and the offset is less than a second for 2 of the 3 nodes (running a test)
[23:51] <bdonnahue2> but the skew message still complains about two nodes
[23:53] <bdonnahue2> perhapse there is some backoff logic in play
[23:53] <kitz> it needs to be within 0.05 seconds
[23:53] <bdonnahue2> adjust time server 50.4.1.1 offset -0.000084 sec
[23:53] <kitz> okie
[23:54] * Pedras1 (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) has joined #ceph
[23:54] * Pedras (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) Quit (Read error: Connection reset by peer)
[23:54] <bdonnahue2> should i run the mon create initial command again?
[23:54] <kitz> When I set up my cluster the first time I didn't have ntpd running and it didn't sort itself out until overnight.
[23:54] <kitz> Now, I install ntpd before ceph and it seems to come right up the first time.
[23:56] <kitz> that's not much of an answer, i know. :/
[23:56] * Pedras1 (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) Quit (Read error: Connection reset by peer)
[23:57] * Pedras (~Adium@c-67-188-26-20.hsd1.ca.comcast.net) has joined #ceph
[23:57] <bdonnahue2> no worries. any help/experience is appreciated
[23:58] * markbby (~Adium@168.94.245.3) has joined #ceph

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