#ceph IRC Log

Index

IRC Log for 2015-06-25

Timestamps are in GMT/BST.

[0:00] * bobrik_ (~bobrik@83.243.64.45) Quit (Quit: (null))
[0:01] * jwilkins (~jwilkins@2600:1010:b000:3840:ea2a:eaff:fe08:3f1d) has joined #ceph
[0:02] <TheSov> but dont you guys think its uncool to see your cluster size shrink as you delete osds?
[0:03] * sleinen1 (~Adium@2001:620:0:82::104) Quit (Ping timeout: 480 seconds)
[0:06] <TheSov> hmmm in that case i may just have to setup a script that will auto-delete an osd if it goes down. and if it clocks more than 3 or 4 down sends me an email with the osd numbers
[0:10] * dneary (~dneary@64.251.112.55) Quit (Ping timeout: 480 seconds)
[0:14] <doppelgrau> TheSov: in the end it is also a question what is cheaper, the higher labour costs if you replace every failed drive immediately or the (small) ???safety margin??? of additional servers/osds
[0:14] * dneary (~dneary@64.251.112.55) has joined #ceph
[0:16] * vata (~vata@cable-21.246.173-197.electronicbox.net) has joined #ceph
[0:20] <doppelgrau> TheSov: if the servers are on the same floor as the office and have hot-swapable trays the results are usually different compared to a 2-3hour drive to the datacenter ???
[0:24] <monsted> i'd probably have my alerting system keep track of number of OSDs vs. number of expected drives
[0:25] * dneary (~dneary@64.251.112.55) Quit (Ping timeout: 480 seconds)
[0:26] * TheSov (~TheSov@cip-248.trustwave.com) Quit (Ping timeout: 480 seconds)
[0:29] * fdmanana__ (~fdmanana@bl13-155-180.dsl.telepac.pt) Quit (Ping timeout: 480 seconds)
[0:30] * gregmark (~Adium@68.87.42.115) Quit (Quit: Leaving.)
[0:30] * srk (~srk@32.97.110.57) Quit (Quit: Leaving)
[0:33] * jdillaman (~jdillaman@pool-108-18-97-82.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[0:33] * jdillaman (~jdillaman@pool-108-18-97-82.washdc.fios.verizon.net) has joined #ceph
[0:34] * TheSov (~TheSov@cip-248.trustwave.com) has joined #ceph
[0:36] <ska> So I have a public network and a private one. How do I get the OSD data to flow on the private? How does Mon data flow on public?
[0:37] <ska> Should My hosts/node names point to the public numbers?
[0:38] <doppelgrau> ska: you simply configure the networks on the right interfaces
[0:39] * arbrandes (~arbrandes@189.78.72.151) Quit (Quit: Leaving)
[0:40] * xarses (~xarses@12.164.168.117) Quit (Ping timeout: 480 seconds)
[0:41] <ska> I don't know what that is though.. For example I had my Mon's set to listen on the public numbers, but the hostnames were only that of the private ones.
[0:42] * lupine (~lupine@ur.gs) has joined #ceph
[0:42] <ska> the "host" parameter was set to the hostname, but those resolve to the private addrs.
[0:44] * elder (~elder@104.135.1.105) Quit (Ping timeout: 480 seconds)
[0:45] <ska> Looks like net reference suggests that Mon and MDS live on public network only
[0:46] * spate (~homosaur@9S0AABIR1.tor-irc.dnsbl.oftc.net) has joined #ceph
[0:47] * rotbeard (~redbeard@2a02:908:df10:d300:76f0:6dff:fe3b:994d) Quit (Ping timeout: 480 seconds)
[0:52] * linjan (~linjan@80.179.241.26) has joined #ceph
[0:53] * elder (~elder@104.135.1.105) has joined #ceph
[0:55] <monsted> my understanding is that the cluster network is for OSDs only
[0:55] <monsted> everything else works on the public network
[0:58] <TheSov> monsted, yes thats correct
[0:58] <TheSov> only osd servers should have a cluster network
[0:58] <TheSov> goodnight guys
[0:58] * lcurtis (~lcurtis@47.19.105.250) Quit (Remote host closed the connection)
[0:58] * TheSov (~TheSov@cip-248.trustwave.com) Quit (Read error: Connection reset by peer)
[0:58] * jdillaman (~jdillaman@pool-108-18-97-82.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[0:59] <ska> My hosts files addresses were on the Cluster net.. I think that was confusing some things.
[0:59] * DV_ (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[1:00] * jdillaman (~jdillaman@pool-108-18-97-82.washdc.fios.verizon.net) has joined #ceph
[1:00] * elder (~elder@104.135.1.105) Quit (Read error: Connection reset by peer)
[1:01] * DV_ (~veillard@2001:41d0:a:f29f::1) Quit (Remote host closed the connection)
[1:06] * debian112 (~bcolbert@24.126.201.64) Quit (Quit: Leaving.)
[1:07] * _Tassadar (~tassadar@D57DEE42.static.ziggozakelijk.nl) Quit (Ping timeout: 480 seconds)
[1:08] * jwilkins (~jwilkins@2600:1010:b000:3840:ea2a:eaff:fe08:3f1d) Quit (Ping timeout: 480 seconds)
[1:10] * jdillaman (~jdillaman@pool-108-18-97-82.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[1:14] * segutier (~segutier@c-24-6-218-139.hsd1.ca.comcast.net) Quit (Quit: segutier)
[1:16] * spate (~homosaur@9S0AABIR1.tor-irc.dnsbl.oftc.net) Quit ()
[1:16] * DV_ (~veillard@2001:41d0:1:d478::1) has joined #ceph
[1:16] * DV_ (~veillard@2001:41d0:1:d478::1) Quit (Remote host closed the connection)
[1:18] * jwilkins (~jwilkins@2601:644:4100:bfef:ea2a:eaff:fe08:3f1d) has joined #ceph
[1:19] * DV_ (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[1:21] * _Tassadar (~tassadar@D57DEE42.static.ziggozakelijk.nl) has joined #ceph
[1:21] * DV_ (~veillard@2001:41d0:a:f29f::1) Quit (Remote host closed the connection)
[1:23] * ingslovak (~peto@188-167-237-207.dynamic.chello.sk) Quit (Ping timeout: 480 seconds)
[1:23] * danieagle (~Daniel@187.35.206.135) Quit (Quit: Obrigado por Tudo! :-) inte+ :-))
[1:24] * DV_ (~veillard@2001:41d0:1:d478::1) has joined #ceph
[1:25] * snakamoto (~Adium@192.16.26.2) has joined #ceph
[1:25] * DV_ (~veillard@2001:41d0:1:d478::1) Quit (Remote host closed the connection)
[1:27] * DV_ (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[1:29] * DV_ (~veillard@2001:41d0:a:f29f::1) Quit (Remote host closed the connection)
[1:31] * Nats_ (~natscogs@114.31.195.238) Quit (Read error: Connection reset by peer)
[1:32] * Nats_ (~natscogs@114.31.195.238) has joined #ceph
[1:34] * DV_ (~veillard@2001:41d0:1:d478::1) has joined #ceph
[1:35] * DV_ (~veillard@2001:41d0:1:d478::1) Quit (Remote host closed the connection)
[1:35] * ingslovak (~peto@cloud.vps.websupport.sk) has joined #ceph
[1:36] * xarses (~xarses@173-164-194-206-SFBA.hfc.comcastbusiness.net) has joined #ceph
[1:37] * DV_ (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[1:37] * DV_ (~veillard@2001:41d0:a:f29f::1) Quit (Remote host closed the connection)
[1:46] * nhm (~nhm@50-201-39-35-static.hfc.comcastbusiness.net) has joined #ceph
[1:46] * ChanServ sets mode +o nhm
[1:47] * oms101 (~oms101@p20030057EA061400C6D987FFFE4339A1.dip0.t-ipconnect.de) Quit (Ping timeout: 480 seconds)
[1:51] * ngoswami (~ngoswami@14.97.235.203) Quit (Quit: Leaving)
[1:51] * moore (~moore@64.202.160.88) Quit (Remote host closed the connection)
[1:55] * oms101 (~oms101@p20030057EA056200C6D987FFFE4339A1.dip0.t-ipconnect.de) has joined #ceph
[1:57] * doppelgrau (~doppelgra@pd956d116.dip0.t-ipconnect.de) Quit (Quit: doppelgrau)
[1:58] * DV_ (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[2:00] * daviddcc (~dcasier@84.197.151.77.rev.sfr.net) Quit (Ping timeout: 480 seconds)
[2:16] * ingslovak (~peto@cloud.vps.websupport.sk) Quit (Quit: Leaving.)
[2:19] * vbellur (~vijay@64.251.112.55) has joined #ceph
[2:20] * CAPSLOCK2000 (~oftc@2001:984:3be3:1::8) Quit (Ping timeout: 480 seconds)
[2:27] * lucas (~Thunderbi@218.76.52.64) has joined #ceph
[2:29] * linjan (~linjan@80.179.241.26) Quit (Ping timeout: 480 seconds)
[2:33] * alram (~alram@cpe-172-250-2-46.socal.res.rr.com) Quit (Quit: leaving)
[2:37] * wushudoin (~wushudoin@38.140.108.2) Quit (Quit: Leaving)
[2:41] * cholcombe (~chris@c-73-180-29-35.hsd1.or.comcast.net) Quit (Ping timeout: 480 seconds)
[3:02] * bobrik_ (~bobrik@83.243.64.45) has joined #ceph
[3:02] * snakamoto (~Adium@192.16.26.2) Quit (Quit: Leaving.)
[3:03] <snerd> would currently murder to have the aws-enable-static-website option for radosgw
[3:03] <snerd> to serve up a normal html index of gw bucket stuff
[3:05] <lurbs> I wouldn't go beyond maiming, personally.
[3:10] * shohn1 (~shohn@dslb-178-008-169-040.178.008.pools.vodafone-ip.de) has joined #ceph
[3:10] * bobrik_ (~bobrik@83.243.64.45) Quit (Ping timeout: 480 seconds)
[3:10] * xarses (~xarses@173-164-194-206-SFBA.hfc.comcastbusiness.net) Quit (Ping timeout: 480 seconds)
[3:12] * vbellur (~vijay@64.251.112.55) Quit (Ping timeout: 480 seconds)
[3:15] * kefu (~kefu@114.92.100.239) has joined #ceph
[3:16] * shohn (~shohn@dslb-088-072-078-092.088.072.pools.vodafone-ip.de) Quit (Ping timeout: 480 seconds)
[3:17] * daviddcc (~dcasier@84.197.151.77.rev.sfr.net) has joined #ceph
[3:24] <snerd> lurbs: a little light maiming
[3:24] <snerd> I have a lot of files stored in rgw that my consumers are only interested in grabbing if they can wget them from a directory tree
[3:24] <snerd> ye old apache style
[3:24] * yanzheng (~zhyan@182.139.20.134) has joined #ceph
[3:24] <snerd> you'd think this'd be simple but wow
[3:25] <snerd> currently using an s3fs mount with a apache index on it and it's hella slow
[3:28] * Sysadmin88 (~IceChat77@2.124.164.69) has joined #ceph
[3:35] * Debesis_ (0x@238.160.140.82.mobile.mezon.lt) Quit (Ping timeout: 480 seconds)
[3:39] * shang (~ShangWu@175.41.48.77) has joined #ceph
[3:41] * shyu (~Shanzhi@119.254.120.66) has joined #ceph
[3:42] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[3:43] * kefu (~kefu@114.92.100.239) has joined #ceph
[3:47] * snakamoto (~Adium@192.16.26.2) has joined #ceph
[3:47] * snakamoto (~Adium@192.16.26.2) Quit ()
[3:49] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[3:50] * kefu (~kefu@114.92.100.239) has joined #ceph
[3:57] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[3:57] * kefu (~kefu@114.92.100.239) has joined #ceph
[4:03] * Concubidated (~Adium@192.170.161.35) Quit (Quit: Leaving.)
[4:05] * ira (~ira@c-71-233-225-22.hsd1.ma.comcast.net) Quit (Quit: Leaving)
[4:11] * kefu (~kefu@114.92.100.239) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[4:13] * kefu (~kefu@114.92.100.239) has joined #ceph
[4:18] * yguang11 (~yguang11@nat-dip30-wl-d.cfw-a-gci.corp.yahoo.com) Quit (Remote host closed the connection)
[4:18] * yguang11 (~yguang11@nat-dip30-wl-d.cfw-a-gci.corp.yahoo.com) has joined #ceph
[4:20] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[4:20] * rlrevell (~leer@184.52.129.221) has joined #ceph
[4:23] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[4:23] * rlrevell (~leer@184.52.129.221) Quit (Read error: Connection reset by peer)
[4:24] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[4:25] * kefu (~kefu@114.92.100.239) has joined #ceph
[4:26] * yguang11 (~yguang11@nat-dip30-wl-d.cfw-a-gci.corp.yahoo.com) Quit (Ping timeout: 480 seconds)
[4:27] * Concubidated (~Adium@23.91.33.7) has joined #ceph
[4:29] * reed (~reed@75-101-54-131.dsl.static.fusionbroadband.com) Quit (Quit: Ex-Chat)
[4:29] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[4:30] * kefu (~kefu@114.92.100.239) has joined #ceph
[4:34] * sankarshan (~sankarsha@121.244.87.116) has joined #ceph
[4:35] * flisky (~Thunderbi@106.39.60.34) has joined #ceph
[4:36] * bkopilov (~bkopilov@bzq-109-64-160-158.red.bezeqint.net) Quit (Ping timeout: 480 seconds)
[4:40] * calvinx (~calvin@101.100.172.246) has joined #ceph
[4:40] * vbellur (~vijay@50-206-204-8-static.hfc.comcastbusiness.net) has joined #ceph
[4:45] * xarses (~xarses@c-73-202-191-48.hsd1.ca.comcast.net) has joined #ceph
[4:56] * zhaochao (~zhaochao@125.39.8.229) has joined #ceph
[4:59] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[5:00] * kefu (~kefu@114.92.100.239) has joined #ceph
[5:10] * adeel_ (~adeel@fw1.ridgeway.scc-zip.net) has joined #ceph
[5:11] * jclm (~jclm@50-206-204-8-static.hfc.comcastbusiness.net) has joined #ceph
[5:16] * adeel (~adeel@fw1.ridgeway.scc-zip.net) Quit (Ping timeout: 480 seconds)
[5:29] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[5:30] * macjack (~macjack@122.146.93.152) has joined #ceph
[5:30] * kefu (~kefu@114.92.100.239) has joined #ceph
[5:35] * squ (~Thunderbi@46.109.36.167) has joined #ceph
[5:36] * Vacuum_ (~Vacuum@88.130.195.130) has joined #ceph
[5:43] * Vacuum__ (~Vacuum@i59F79096.versanet.de) Quit (Ping timeout: 480 seconds)
[5:51] * dyasny (~dyasny@104.158.34.71) has joined #ceph
[5:54] * bkopilov (~bkopilov@nat-pool-tlv-t.redhat.com) has joined #ceph
[6:05] * shang (~ShangWu@175.41.48.77) Quit (Ping timeout: 480 seconds)
[6:11] * vbellur (~vijay@50-206-204-8-static.hfc.comcastbusiness.net) Quit (Ping timeout: 480 seconds)
[6:30] * wschulze (~wschulze@cpe-69-206-240-164.nyc.res.rr.com) has joined #ceph
[6:30] * sleinen (~Adium@84-72-160-233.dclient.hispeed.ch) has joined #ceph
[6:32] * sleinen1 (~Adium@2001:620:0:82::101) has joined #ceph
[6:38] * sleinen (~Adium@84-72-160-233.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[6:42] * yguang11 (~yguang11@12.31.82.125) has joined #ceph
[6:43] * shang (~ShangWu@175.41.48.77) has joined #ceph
[6:49] * yguang11_ (~yguang11@2001:4998:effd:7804::1018) has joined #ceph
[6:55] * yguang11 (~yguang11@12.31.82.125) Quit (Ping timeout: 480 seconds)
[6:57] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[6:58] * kefu (~kefu@114.92.100.239) has joined #ceph
[7:08] * dopesong (~dopesong@lb1.mailer.data.lt) has joined #ceph
[7:17] * dyasny (~dyasny@104.158.34.71) Quit (Ping timeout: 480 seconds)
[7:20] * bbby (~bibby@2601:204:c600:8a2e:e4d5:76ac:9b97:4190) Quit (Ping timeout: 480 seconds)
[7:28] * danieagle (~Daniel@187.35.206.135) has joined #ceph
[7:32] * kefu (~kefu@114.92.100.239) Quit (Ping timeout: 480 seconds)
[7:32] * jameskassemi (~james@75-173-111-208.albq.qwest.net) has joined #ceph
[7:38] * yguang11_ (~yguang11@2001:4998:effd:7804::1018) Quit (Ping timeout: 480 seconds)
[7:38] * nhm (~nhm@50-201-39-35-static.hfc.comcastbusiness.net) Quit (Ping timeout: 480 seconds)
[7:48] <nigwil> is there an easy fix for the 0.80.10 debian dependency problem?
[7:50] * dopesong (~dopesong@lb1.mailer.data.lt) Quit (Remote host closed the connection)
[7:50] * tganguly (~tganguly@121.244.87.117) has joined #ceph
[7:53] * zaitcev (~zaitcev@2001:558:6001:10:61d7:f51f:def8:4b0f) Quit (Quit: Bye)
[7:57] * kefu (~kefu@114.92.100.239) has joined #ceph
[7:57] * rdas (~rdas@106.221.132.232) has joined #ceph
[7:59] * danieagle (~Daniel@187.35.206.135) Quit (Quit: Obrigado por Tudo! :-) inte+ :-))
[8:01] * Hemanth (~Hemanth@121.244.87.117) has joined #ceph
[8:07] * overclk (~overclk@121.244.87.117) has joined #ceph
[8:09] * nsoffer (~nsoffer@bzq-84-111-112-230.red.bezeqint.net) has joined #ceph
[8:09] * sleinen1 (~Adium@2001:620:0:82::101) Quit (Ping timeout: 480 seconds)
[8:14] * dopesong (~dopesong@lb1.mailer.data.lt) has joined #ceph
[8:18] * shohn (~shohn@dslb-146-060-206-092.146.060.pools.vodafone-ip.de) has joined #ceph
[8:23] * shohn1 (~shohn@dslb-178-008-169-040.178.008.pools.vodafone-ip.de) Quit (Ping timeout: 480 seconds)
[8:31] * danieagle (~Daniel@187.35.206.135) has joined #ceph
[8:36] * Hemanth (~Hemanth@121.244.87.117) Quit (Ping timeout: 480 seconds)
[8:37] * tganguly (~tganguly@121.244.87.117) Quit (Ping timeout: 480 seconds)
[8:37] * Sysadmin88 (~IceChat77@2.124.164.69) Quit (Quit: Say What?)
[8:38] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[8:40] * capri (~capri@212.218.127.222) has joined #ceph
[8:42] * T1w (~jens@node3.survey-it.dk) has joined #ceph
[8:44] * dugravot6 (~dugravot6@dn-infra-04.lionnois.univ-lorraine.fr) has joined #ceph
[8:45] * tganguly (~tganguly@121.244.87.117) has joined #ceph
[8:51] * wschulze (~wschulze@cpe-69-206-240-164.nyc.res.rr.com) Quit (Quit: Leaving.)
[8:54] * kawa2014 (~kawa@89.184.114.246) has joined #ceph
[8:56] * rotbeard (~redbeard@185.32.80.238) has joined #ceph
[8:59] * Hemanth (~Hemanth@121.244.87.117) has joined #ceph
[8:59] * oro (~oro@84-72-180-62.dclient.hispeed.ch) has joined #ceph
[9:00] * rdas (~rdas@106.221.132.232) Quit (Quit: Leaving)
[9:03] * derjohn_mob (~aj@p578b6aa1.dip0.t-ipconnect.de) Quit (Ping timeout: 480 seconds)
[9:04] * linjan (~linjan@213.8.240.146) has joined #ceph
[9:04] * dgurtner (~dgurtner@178.197.231.10) has joined #ceph
[9:04] * CAPSLOCK2000 (~oftc@2001:984:3be3:1::8) has joined #ceph
[9:06] * rotbeard (~redbeard@185.32.80.238) Quit (Quit: Leaving)
[9:06] * linjan (~linjan@213.8.240.146) Quit (Remote host closed the connection)
[9:07] * jameskassemi (~james@75-173-111-208.albq.qwest.net) Quit (Quit: jameskassemi)
[9:08] * Nacer (~Nacer@203-206-190-109.dsl.ovh.fr) Quit (Remote host closed the connection)
[9:10] * linjan (~linjan@213.8.240.146) has joined #ceph
[9:10] * shohn1 (~shohn@dslb-092-078-030-072.092.078.pools.vodafone-ip.de) has joined #ceph
[9:10] * wesbell_ (~wesbell@vpngac.ccur.com) has joined #ceph
[9:14] * shohn (~shohn@dslb-146-060-206-092.146.060.pools.vodafone-ip.de) Quit (Ping timeout: 480 seconds)
[9:14] * fxmulder (~fxmulder@cpe-24-55-6-128.austin.res.rr.com) Quit (Ping timeout: 480 seconds)
[9:15] * wesbell__ (~wesbell@vpngac.ccur.com) Quit (Ping timeout: 480 seconds)
[9:18] <sep> rkeene, sorry i was dragged away yesterday. when you say osd, do you mean the osd process for a single disk in a server, or do you mean the server hosting the osd's ... so when performance is dependant on osd's i'd assume it was more servers = better, and more disks (osd's?) in a server is not better, just more space.
[9:20] * lucas (~Thunderbi@218.76.52.64) Quit (Quit: lucas)
[9:21] * fridim_ (~fridim@56-198-190-109.dsl.ovh.fr) has joined #ceph
[9:27] * fxmulder (~fxmulder@cpe-24-55-6-128.austin.res.rr.com) has joined #ceph
[9:28] * bitserker (~toni@88.87.194.130) has joined #ceph
[9:29] * derjohn_mob (~aj@fw.gkh-setu.de) has joined #ceph
[9:29] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[9:36] <Kioob`Taff> nigwil: with which version of Debian ?
[9:37] <Kioob`Taff> in Debian 7, I didn't see any dependency problem
[9:42] * jordanP (~jordan@213.215.2.194) has joined #ceph
[9:43] <nigwil> Kioob`Taff: Trusty
[9:43] <Kioob`Taff> ok, so, Ubuntu, not Debian.
[9:43] <nigwil> Ubuntu (sorry I said Debian above)
[9:44] <Kioob`Taff> there is an issue opened for Ubuntu Precise too : http://tracker.ceph.com/issues/12156
[9:44] <nigwil> yes, it is affecting Trusty too
[9:44] <Kioob`Taff> You sould probably add a comment about Trusty
[9:44] <nigwil> ok
[9:45] * tganguly (~tganguly@121.244.87.117) Quit (Ping timeout: 480 seconds)
[9:46] * Hemanth (~Hemanth@121.244.87.117) Quit (Ping timeout: 480 seconds)
[9:46] * oro (~oro@84-72-180-62.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[9:47] * sleinen (~Adium@2001:620:0:82::108) has joined #ceph
[9:50] * Be-El (~quassel@fb08-bcf-pc01.computational.bio.uni-giessen.de) has joined #ceph
[9:50] <Be-El> hi
[9:53] * sim_ is now known as sim
[9:56] * tganguly (~tganguly@121.244.87.117) has joined #ceph
[9:58] * gaveen (~gaveen@123.231.112.221) has joined #ceph
[10:00] * nils_ (~nils@doomstreet.collins.kg) has joined #ceph
[10:07] * lucas (~Thunderbi@218.76.52.64) has joined #ceph
[10:09] * daviddcc (~dcasier@84.197.151.77.rev.sfr.net) Quit (Ping timeout: 480 seconds)
[10:11] * branto (~branto@nat-pool-brq-t.redhat.com) has joined #ceph
[10:15] * oro (~oro@2001:620:20:16:749b:4710:c54f:d03c) has joined #ceph
[10:15] * oro_ (~oro@2001:620:20:16:749b:4710:c54f:d03c) has joined #ceph
[10:16] * rdas (~rdas@121.244.87.116) has joined #ceph
[10:16] * TMM (~hp@sams-office-nat.tomtomgroup.com) has joined #ceph
[10:19] * nardial (~ls@dslb-178-011-179-229.178.011.pools.vodafone-ip.de) has joined #ceph
[10:21] * bobrik_ (~bobrik@83.243.64.45) has joined #ceph
[10:26] * ramonskie (ab15507e@107.161.19.109) has joined #ceph
[10:26] <ramonskie> HELP!!! the update to 0.94.2 on precise removed ceph on my monitor
[10:26] <ramonskie> and i only had one monitor
[10:26] <ramonskie> :S
[10:29] * sleinen1 (~Adium@194.191.86.3) has joined #ceph
[10:29] * sleinen1 (~Adium@194.191.86.3) Quit ()
[10:31] * sleinen (~Adium@2001:620:0:82::108) Quit (Ping timeout: 480 seconds)
[10:32] * sleinen (~Adium@194.191.86.3) has joined #ceph
[10:33] * sleinen1 (~Adium@2001:620:0:82::100) has joined #ceph
[10:34] * bobrik_ (~bobrik@83.243.64.45) Quit (Ping timeout: 480 seconds)
[10:34] <frickler> ramonskie: yes, current release is broken, see http://tracker.ceph.com/issues/12129
[10:35] <ramonskie> i'm now upgrading to 14.04
[10:35] <ramonskie> in the hope that i can fix my monitor
[10:35] <frickler> ramonskie: the previous packages are still available in the pool, though, so you can manually install them
[10:35] <ramonskie> and revive it
[10:35] <ramonskie> it didnt want to install because of dependencies that where not met
[10:36] <ramonskie> i tried to look which dependencies but there where allot
[10:36] <frickler> you would have to download all the packages manually and install with dpkg, like http://ceph.com/debian-hammer/pool/main/c/ceph/ceph_0.94-1precise_amd64.deb
[10:37] <ramonskie> do you think i can still save my cluster?
[10:37] <frickler> ramonskie: I think you should, the config should still be there
[10:37] * sleinen (~Adium@194.191.86.3) Quit (Read error: Connection reset by peer)
[10:39] * jrocha (~jrocha@vagabond.cern.ch) has joined #ceph
[10:39] * bitserker1 (~toni@88.87.194.130) has joined #ceph
[10:40] <ramonskie> any idea how?
[10:42] * danieagle (~Daniel@187.35.206.135) Quit (Quit: Obrigado por Tudo! :-) inte+ :-))
[10:43] <frickler> ramonskie: download all the 0.94.1 versions of the packages that got removed, install them manually with dpkg. remove the repo from /etc/apt/sources.d until it is fixed.
[10:43] <ramonskie> okay
[10:44] <Be-El> ramonskie: make a backup of your mon data directory first...
[10:44] * kefu (~kefu@114.92.100.239) Quit (Read error: Connection reset by peer)
[10:45] * kefu (~kefu@114.92.100.239) has joined #ceph
[10:45] * sleinen1 (~Adium@2001:620:0:82::100) Quit (Ping timeout: 480 seconds)
[10:45] * bitserker (~toni@88.87.194.130) Quit (Ping timeout: 480 seconds)
[10:45] <ramonskie> and where is that
[10:46] * xinze (~xinze@120.35.11.138) has joined #ceph
[10:47] <ramonskie> sorry i'm a bit stressed and in panic right now
[10:49] * xinze (~xinze@120.35.11.138) has left #ceph
[10:53] <ramonskie> in /var/lib/ceph/mon it seems
[10:53] <jrocha> who can I talk to get this pull request reviewed? https://github.com/ceph/ceph/pull/4869
[10:53] <lathiat_> you might be able to try apt-get install ceph=0.94-1precise
[10:54] <lathiat_> depending on if the older version is in the package list or not
[10:55] <joao> ramonskie, as long as /var/lib/ceph/mon/ceph-FOO is still populated (or maybe living in an autonomous disk/partition) you should be able to just get it working again
[10:56] <joao> jrocha, for some reason, noah comes to mind
[10:56] * Nacer_ (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[10:56] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Read error: Connection reset by peer)
[10:56] <joao> he's not available right now though
[10:56] <joao> I'll assign it to him and let him decide if someone else should look into it
[10:57] * fdmanana__ (~fdmanana@bl13-155-180.dsl.telepac.pt) has joined #ceph
[11:00] <jrocha> jrocha, I've seen it. Thanks a lot!
[11:00] * sleinen (~Adium@194.191.86.3) has joined #ceph
[11:02] * sleinen1 (~Adium@2001:620:0:82::105) has joined #ceph
[11:02] <ramonskie> i upgraded to 14.04
[11:03] <ramonskie> and install ceph package again and started monitor
[11:03] <ramonskie> and i now get a health ok again
[11:03] <ramonskie> pfewww
[11:03] <lathiat_> ramonskie: congrats
[11:04] <lathiat_> non-fun situation
[11:05] <boolman> ramonskie: tip of the day: get 2 more mon's :)
[11:06] <ramonskie> yes the only thing that i'm working on for the past month
[11:06] <ramonskie> and noboday seems to be able to help me
[11:06] <ramonskie> posted it several times on mailing list but no answers
[11:07] * RomeroJnr (~h0m3r@hosd.leaseweb.net) Quit ()
[11:07] <ramonskie> when adding a monitor i get these erros in the monitor logs ephx: verify_authorizer could not decrypt ticket info: error: NSS AES final round failed: -8190
[11:08] * RomeroJnr (~h0m3r@hosd.leaseweb.net) has joined #ceph
[11:08] * sleinen (~Adium@194.191.86.3) Quit (Ping timeout: 480 seconds)
[11:09] * oro_ (~oro@2001:620:20:16:749b:4710:c54f:d03c) Quit (Ping timeout: 480 seconds)
[11:11] * oro (~oro@2001:620:20:16:749b:4710:c54f:d03c) Quit (Ping timeout: 480 seconds)
[11:11] * Nacer_ (~Nacer@252-87-190-213.intermediasud.com) Quit (Ping timeout: 480 seconds)
[11:13] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[11:15] * kefu (~kefu@114.92.100.239) has joined #ceph
[11:17] * oro_ (~oro@2001:620:20:64:749b:4710:c54f:d03c) has joined #ceph
[11:19] * oro (~oro@2001:620:20:64:749b:4710:c54f:d03c) has joined #ceph
[11:20] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[11:20] * kefu (~kefu@114.92.100.239) has joined #ceph
[11:21] * daviddcc (~dcasier@LAubervilliers-656-1-16-164.w217-128.abo.wanadoo.fr) has joined #ceph
[11:25] <ramonskie> so can maby someone try to help me by solving the strange error that i have when adding a monitor
[11:28] * bobrik (~bobrik@83.243.64.45) has joined #ceph
[11:28] <lathiat_> ramonskie: did you check that the clocks matched?
[11:29] <lathiat_> otherwise the auth keys might be bad in some way
[11:29] <lathiat_> but you probably know that already i guess
[11:29] <lathiat_> i'm pretty new to ceph so likely not helpful :-)
[11:30] * vpol (~vpol@000131a0.user.oftc.net) has joined #ceph
[11:32] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[11:33] <ramonskie> yes clocks match
[11:34] <ramonskie> and now i have again bigger issue i added the new mon
[11:34] <ramonskie> and now my current mon is doint notihing anymroe
[11:35] * oro (~oro@2001:620:20:64:749b:4710:c54f:d03c) Quit (Ping timeout: 480 seconds)
[11:35] * oro_ (~oro@2001:620:20:64:749b:4710:c54f:d03c) Quit (Ping timeout: 480 seconds)
[11:35] * kefu (~kefu@114.92.100.239) has joined #ceph
[11:37] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[11:38] * vpol (~vpol@000131a0.user.oftc.net) Quit (Ping timeout: 480 seconds)
[11:40] * kefu (~kefu@114.92.100.239) has joined #ceph
[11:42] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[11:43] * kefu (~kefu@114.92.100.239) has joined #ceph
[11:44] * doppelgrau (~doppelgra@pd956d116.dip0.t-ipconnect.de) has joined #ceph
[11:46] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[11:47] * tganguly (~tganguly@121.244.87.117) Quit (Ping timeout: 480 seconds)
[11:49] * kefu (~kefu@114.92.100.239) has joined #ceph
[11:51] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[11:51] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[11:52] <joao> jrocha, np
[11:52] * kefu (~kefu@114.92.100.239) has joined #ceph
[11:53] * oro (~oro@2001:620:20:16:749b:4710:c54f:d03c) has joined #ceph
[11:54] * oro_ (~oro@2001:620:20:16:749b:4710:c54f:d03c) has joined #ceph
[11:54] * sleinen (~Adium@194.191.86.3) has joined #ceph
[11:56] * sleinen2 (~Adium@2001:620:0:69::100) has joined #ceph
[11:56] * sleinen1 (~Adium@2001:620:0:82::105) Quit (Ping timeout: 480 seconds)
[11:56] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[11:57] * bitserker1 (~toni@88.87.194.130) Quit (Remote host closed the connection)
[11:58] * kefu (~kefu@114.92.100.239) has joined #ceph
[12:02] * sleinen (~Adium@194.191.86.3) Quit (Ping timeout: 480 seconds)
[12:03] * Debesis_ (0x@238.160.140.82.mobile.mezon.lt) has joined #ceph
[12:04] * daviddcc (~dcasier@LAubervilliers-656-1-16-164.w217-128.abo.wanadoo.fr) Quit (Ping timeout: 480 seconds)
[12:05] * jcsp1 (~Adium@82-71-16-249.dsl.in-addr.zen.co.uk) Quit (Quit: Leaving.)
[12:05] * jcsp (~Adium@0001bf3a.user.oftc.net) has joined #ceph
[12:05] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[12:06] * shyu (~Shanzhi@119.254.120.66) Quit (Remote host closed the connection)
[12:09] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[12:11] * kefu (~kefu@114.92.100.239) has joined #ceph
[12:13] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[12:14] * kefu (~kefu@114.92.100.239) has joined #ceph
[12:17] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[12:18] * kefu (~kefu@114.92.100.239) has joined #ceph
[12:22] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[12:25] * nsoffer (~nsoffer@bzq-84-111-112-230.red.bezeqint.net) Quit (Ping timeout: 480 seconds)
[12:26] * kefu (~kefu@114.92.100.239) has joined #ceph
[12:28] * sleinen2 (~Adium@2001:620:0:69::100) Quit (Ping timeout: 480 seconds)
[12:30] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[12:31] * mxmln (~mxmln@212.79.49.65) has joined #ceph
[12:32] * kefu (~kefu@114.92.100.239) has joined #ceph
[12:34] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[12:35] * kefu (~kefu@114.92.100.239) has joined #ceph
[12:36] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Remote host closed the connection)
[12:41] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[12:42] * dgurtner (~dgurtner@178.197.231.10) Quit (Ping timeout: 480 seconds)
[12:43] * kefu (~kefu@114.92.100.239) has joined #ceph
[12:48] * ramonskie (ab15507e@107.161.19.109) Quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client)
[12:56] * peem (~piotr@office.forlinux.co.uk) Quit (Quit: Konversation terminated!)
[13:00] * cok (~chk@test.roskilde-festival.dk) has joined #ceph
[13:00] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[13:02] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[13:03] * lucas (~Thunderbi@218.76.52.64) Quit (Quit: lucas)
[13:04] * vbellur (~vijay@50-206-204-8-static.hfc.comcastbusiness.net) has joined #ceph
[13:07] * nhm (~nhm@50-201-39-35-static.hfc.comcastbusiness.net) has joined #ceph
[13:07] * ChanServ sets mode +o nhm
[13:08] * Be-El (~quassel@fb08-bcf-pc01.computational.bio.uni-giessen.de) Quit (Remote host closed the connection)
[13:11] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[13:11] * kefu (~kefu@114.92.100.239) has joined #ceph
[13:12] * dgurtner (~dgurtner@178.197.231.10) has joined #ceph
[13:13] * ngoswami (~ngoswami@121.244.87.116) has joined #ceph
[13:17] * vbellur (~vijay@50-206-204-8-static.hfc.comcastbusiness.net) Quit (Ping timeout: 480 seconds)
[13:17] * daviddcc (~dcasier@LAubervilliers-656-1-16-164.w217-128.abo.wanadoo.fr) has joined #ceph
[13:19] * rlrevell (~leer@184.52.129.221) has joined #ceph
[13:21] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[13:22] * rlrevell (~leer@184.52.129.221) Quit (Read error: Connection reset by peer)
[13:23] * kefu (~kefu@114.92.100.239) has joined #ceph
[13:24] * nsoffer (~nsoffer@nat-pool-tlv-t.redhat.com) has joined #ceph
[13:30] * cok (~chk@test.roskilde-festival.dk) Quit (Ping timeout: 480 seconds)
[13:31] * mxmln (~mxmln@212.79.49.65) Quit (Quit: mxmln)
[13:31] * oro (~oro@2001:620:20:16:749b:4710:c54f:d03c) Quit (Ping timeout: 480 seconds)
[13:31] * oro_ (~oro@2001:620:20:16:749b:4710:c54f:d03c) Quit (Ping timeout: 480 seconds)
[13:32] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[13:33] * kefu (~kefu@114.92.100.239) has joined #ceph
[13:35] * vata (~vata@cable-21.246.173-197.electronicbox.net) Quit (Quit: Leaving.)
[13:35] * mxmln (~mxmln@212.79.49.65) has joined #ceph
[13:36] * tmrz (~quassel@198-84-192-38.cpe.teksavvy.com) Quit (Remote host closed the connection)
[13:37] * tmrz (~quassel@198-84-192-38.cpe.teksavvy.com) has joined #ceph
[13:37] * ganders (~root@190.2.42.21) has joined #ceph
[13:38] * rlrevell (~leer@vbo1.inmotionhosting.com) has joined #ceph
[13:40] * ingslovak (~peto@office.websupport.sk) has joined #ceph
[13:40] * oro_ (~oro@2001:620:20:16:749b:4710:c54f:d03c) has joined #ceph
[13:41] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[13:42] * oro (~oro@2001:620:20:16:749b:4710:c54f:d03c) has joined #ceph
[13:42] * kefu (~kefu@114.92.100.239) has joined #ceph
[13:43] * sankarshan (~sankarsha@121.244.87.116) Quit (Ping timeout: 480 seconds)
[13:45] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[13:45] * kefu (~kefu@114.92.100.239) has joined #ceph
[13:48] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[13:50] * kefu (~kefu@114.92.100.239) has joined #ceph
[13:51] * mxmln (~mxmln@212.79.49.65) Quit (Quit: mxmln)
[13:51] * mxmln (~mxmln@212.79.49.65) has joined #ceph
[13:52] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[13:52] * i_m (~ivan.miro@deibp9eh1--blueice3n2.emea.ibm.com) has joined #ceph
[13:53] * kefu (~kefu@114.92.100.239) has joined #ceph
[13:55] * ira (~ira@c-71-233-225-22.hsd1.ma.comcast.net) has joined #ceph
[13:56] * cooldharma06 (~chatzilla@14.139.180.40) has joined #ceph
[13:56] * alfredodeza (~alfredode@198.206.133.89) has joined #ceph
[13:56] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[13:58] <ska> Is there a way to get remote information (via API or other) from a Ceph Cluster?
[13:59] * zhaochao (~zhaochao@125.39.8.229) Quit (Quit: ChatZilla 0.9.91.1 [Iceweasel 38.0.1/20150526223604])
[13:59] * dugravot61 (~dugravot6@nat-persul-plg.wifi.univ-lorraine.fr) has joined #ceph
[14:02] * rlrevell (~leer@vbo1.inmotionhosting.com) Quit (Ping timeout: 480 seconds)
[14:04] * kefu (~kefu@114.92.100.239) has joined #ceph
[14:05] * dugravot6 (~dugravot6@dn-infra-04.lionnois.univ-lorraine.fr) Quit (Ping timeout: 480 seconds)
[14:06] <Kioob`Taff> ska: there is an "admin socket" on each daemon
[14:06] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[14:07] * kefu (~kefu@114.92.100.239) has joined #ceph
[14:08] <Kioob`Taff> ska, for example, I use this small script to wrap the result to a Zabbix server http://pastebin.com/Tqep82B5
[14:08] * sleinen (~Adium@2001:620:0:2d:7ed1:c3ff:fedc:3223) has joined #ceph
[14:11] * sleinen (~Adium@2001:620:0:2d:7ed1:c3ff:fedc:3223) Quit ()
[14:11] * tmrz (~quassel@198-84-192-38.cpe.teksavvy.com) Quit (Read error: Connection reset by peer)
[14:12] <jcsp> ska: you have three options ??? calamari, ceph-rest-api, or installing ceph client packages on your remote machine
[14:12] <jcsp> assuming that by "information" you mean status etc
[14:12] * rlrevell (~leer@184.52.129.221) has joined #ceph
[14:13] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[14:13] * rlrevell (~leer@184.52.129.221) Quit (Read error: Connection reset by peer)
[14:14] * flisky (~Thunderbi@106.39.60.34) Quit (Read error: Connection reset by peer)
[14:14] * mxmln (~mxmln@212.79.49.65) Quit (Quit: mxmln)
[14:15] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Remote host closed the connection)
[14:15] * sleinen (~Adium@130.59.94.50) has joined #ceph
[14:15] * Nacer (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[14:15] * tmrz (~quassel@198-84-192-38.cpe.teksavvy.com) has joined #ceph
[14:16] * sleinen1 (~Adium@2001:620:0:82::109) has joined #ceph
[14:16] <ska> jcsp: It looks like ceph-rest-api is our only choice. We can't easily install any 3rd party goods on our monitors..
[14:17] <ska> We have most of the python requirements though.
[14:18] * kefu (~kefu@136.0.17.243) has joined #ceph
[14:19] <ska> jcsp: Looks like the ceph-rest-api has no non-standard python dependencies so is ideal. Yea we only need status (GET call) type of info.
[14:19] * mxmln (~mxmln@212.79.49.65) has joined #ceph
[14:20] <jcsp> just bear in mind that if you want any security around that interface, it's up to you to implement it
[14:21] * badone (~brad@CPE-121-215-241-179.static.qld.bigpond.net.au) Quit (Ping timeout: 480 seconds)
[14:22] * calvinx (~calvin@101.100.172.246) Quit (Quit: calvinx)
[14:23] <ska> jcsp: right so that is on the cluster side.. We're creating some monitoring tools for it, but all we can do is make recommendations for the cluster operators.. (Ie. we don't/can't manage the clusters).
[14:23] * sleinen (~Adium@130.59.94.50) Quit (Ping timeout: 480 seconds)
[14:23] * tmrz (~quassel@198-84-192-38.cpe.teksavvy.com) Quit (Read error: Connection reset by peer)
[14:24] * kefu (~kefu@136.0.17.243) Quit (Max SendQ exceeded)
[14:24] * tmrz (~quassel@198-84-192-38.cpe.teksavvy.com) has joined #ceph
[14:24] * kefu (~kefu@136.0.17.243) has joined #ceph
[14:25] * t0rn (~ssullivan@2607:fad0:32:a02:56ee:75ff:fe48:3bd3) has joined #ceph
[14:25] * t0rn (~ssullivan@2607:fad0:32:a02:56ee:75ff:fe48:3bd3) has left #ceph
[14:26] * vata (~vata@207.96.182.162) has joined #ceph
[14:28] * kefu (~kefu@136.0.17.243) Quit (Max SendQ exceeded)
[14:28] * Nacer_ (~Nacer@252-87-190-213.intermediasud.com) has joined #ceph
[14:28] * hoonetorg (~hoonetorg@firewall.netconomy.net) has joined #ceph
[14:28] * kefu (~kefu@136.0.17.243) has joined #ceph
[14:28] <hoonetorg> hi, were using opennebula 4.12.1 + ceph 0.94.1 on centos 7.1
[14:29] <hoonetorg> (i know, i need to upgrade )
[14:29] <hoonetorg> we want to backup our machines
[14:29] * Nacer (~Nacer@252-87-190-213.intermediasud.com) Quit (Read error: Connection reset by peer)
[14:29] <rkeene> We're doing the same thing, except with newer software.
[14:29] <hoonetorg> a snapshot in opennebula uses "rbd cp"
[14:30] <hoonetorg> as far as i know that means i should freeze the fs in the vm during the snapshot, don't I
[14:30] <hoonetorg> ?
[14:31] <hoonetorg> rkeene: qu. 1 newer software?
[14:31] <hoonetorg> rkeene: qu. 2 how exactly do you do the backups?
[14:32] * rlrevell (~leer@vbo1.inmotionhosting.com) has joined #ceph
[14:33] <rkeene> hoonetorg, 1. Yes, CentOS 7.1 ships with old software, pretty much everything from the kernel to glibc to coreutils I'm running is newer
[14:34] <hoonetorg> rkeene: ok, but opennebula 4.12.1 and ceph 0.94.1 is relatively up to date (except ceph 0.94.2)
[14:34] <hoonetorg> ?
[14:35] <hoonetorg> rkeene: to ask further: if I snapshot a large disk in opennebula it takes extremely long, due to the fact that it uses "rbd cp"
[14:35] <rkeene> hoonetorg, 2. We have an OpenNebula Attribute called SNAPSHOT_SCHEDULE which contains the number of snapshots to hold at what interval (yearly, monthly, weekly, daily, hourly -- if you've ever used NetApp it's a real similar format); Periodically (every 1 minute) a daemon reads all the SNAPSHOT_SCHEDULE attributes from all the VMs and then takes snapshots as required to maintain that schedule
[14:36] * bkopilov (~bkopilov@nat-pool-tlv-t.redhat.com) Quit (Ping timeout: 480 seconds)
[14:37] <rkeene> The reason it does a "cp" is that the snapshot it creates is an independant image in OpenNebula
[14:37] <rkeene> RBD snapshots are: 1. Read-only; and 2. Attached to the original image
[14:37] * jclm (~jclm@50-206-204-8-static.hfc.comcastbusiness.net) Quit (Quit: Leaving.)
[14:37] * fam is now known as fam_away
[14:38] * branto (~branto@nat-pool-brq-t.redhat.com) has left #ceph
[14:39] * kefu_ (~kefu@114.92.100.239) has joined #ceph
[14:39] <hoonetorg> rkeene: if I do such a snapshot which takes 30min. and the machine runs on (without fsfreeze) and is a db server, won't the backup be inconsistent?
[14:39] <rkeene> So you can't delete the original image without first deleting the snapshot -- but since the snapshot in OpenNebula is just like any other image, so it needs to be writable and persist if you delete the original VM
[14:40] <rkeene> I'm pretty sure rbd cp is point-in-time consistent
[14:40] <rkeene> I'm checking now
[14:41] <hoonetorg> rkeene: thy, where can this be checked?
[14:41] * kefu_ (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[14:42] * jdillaman (~jdillaman@pool-108-18-97-82.washdc.fios.verizon.net) has joined #ceph
[14:43] * kefu (~kefu@136.0.17.243) Quit (Ping timeout: 480 seconds)
[14:43] <rkeene> I think I'm just going to have to test it
[14:43] * kefu (~kefu@114.92.100.239) has joined #ceph
[14:44] * brad_mssw (~brad@66.129.88.50) has joined #ceph
[14:45] * squ (~Thunderbi@46.109.36.167) Quit (Quit: https://youtu.be/PjeKA_ttPMU)
[14:45] * gaveen (~gaveen@123.231.112.221) Quit (Remote host closed the connection)
[14:46] <ska> Yesterday I had to use this to install using ceph-deploy: "ceph-deploy install --no-adjust-repos ceph-01" because of an apt-key issue.
[14:46] <ska> Am I missing a key in my installation?
[14:46] <hoonetorg> rkeene: only that i understand correct: you mean when i do an "rbd cp ..." at 2015-08-01 15:00 CEST the target image is the copy of the source image with the exact content of the source image at 2015-08-01 15:00 CEST
[14:46] <hoonetorg> ?
[14:48] <rkeene> Right, that should be true
[14:49] <rkeene> Checking now
[14:49] <ska> I'm on debian: when I do apt-key list <ceph-key> I get a valid key output.
[14:49] <alfredodeza> ska: would you mind pasting the complete output somewhere so I can take a look?
[14:49] <alfredodeza> output of ceph-deploy that is
[14:49] <alfredodeza> trying to install normally
[14:50] * amote (~amote@121.244.87.116) Quit (Quit: Leaving)
[14:51] <ska> alfredodeza: sure. but I've just realized that my wget is somehoe broken..
[14:51] <ska> When I do a manual wget on my terminal, it get nothing
[14:51] <alfredodeza> that sounds odd
[14:52] <ska> If i do it on another system I get right results.
[14:52] <ska> wget -q -O- 'https://ceph.com/git/?p=ceph.git;a=blob_plain;f=keys/release.asc' (blank response)
[14:52] * sankarshan (~sankarsha@183.87.39.242) has joined #ceph
[14:54] <hoonetorg> rkeene: thy very much, in the meantime i hv a look at this SNAPSHOT_SCHEDULE thing of opennebula
[14:54] <ska> I think wget is damaged?
[14:55] <alfredodeza> ska: a paste of the whole output would really be useful, from ceph-deploy
[14:56] <alfredodeza> ska: what happens if you use double quotes
[14:56] <alfredodeza> wget -q -O- "https://git.ceph.com/?p=ceph.git;a=blob_plain;f=keys/release.asc"
[14:58] <rkeene> hoonetorg, It's not something OpenNebula does
[14:58] <hoonetorg> k
[14:58] <rkeene> I just store use the VM attribute to keep the information
[14:58] <hoonetorg> ok, i'm a bit new to opennebula (runs since two weeks or so)
[14:59] * vbellur (~vijay@64.251.112.55) has joined #ceph
[14:59] <hoonetorg> migrating first machines and trying to implement a simple backup to nfs-share
[14:59] <hoonetorg> (of running machines)
[15:00] * timi (~timi@ip4-89-238-218-34.euroweb.ro) Quit ()
[15:00] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[15:01] <ska> alfredodeza: http://paste.debian.net/261159/ =
[15:01] <ska> alfredodeza: I have a broken key or untrusted key.
[15:02] <alfredodeza> aha!
[15:02] <alfredodeza> I wonder why or what causes that though
[15:02] <alfredodeza> maybe we should remove the -q flag
[15:02] <ska> alfredodeza: yea, same result with double-quotes.
[15:02] * kefu (~kefu@192.154.200.66) has joined #ceph
[15:02] <ska> That may cause another error in the key process
[15:04] <hoonetorg> rkeene: so your daemon reads this attribute out of onevm list, onevm show --csv (f.e) and then uses ...? onevm disk-snapshot <id> <diskid> <attribute-content-as-snapshot-name>?
[15:04] <alfredodeza> ska: what happens if you use curl? same thing?
[15:04] <rkeene> hoonetorg, Testing it looks like it will *NOT* be point-in-time consistent
[15:05] <ska> no.. curl is happy, but its the ceph-deploy that uses wget internally.
[15:05] <ska> I can possibly replace that part, but I'd like ot fix the key
[15:05] <alfredodeza> I understand, just trying to narrow the issue :)
[15:05] <hoonetorg> rkeene: uuuoooooooouuuhhhh
[15:05] <rkeene> So you'll want to modify OpenNebula to snapshot, clone, then flatten
[15:05] * kefu (~kefu@192.154.200.66) Quit (Max SendQ exceeded)
[15:06] <rkeene> Which will be the same thing as "rbd cp", in time, just consistent
[15:06] <ska> alfredodeza: I'm using hammer I think.. Maybe that is too new for the keys installed on debian 7?
[15:06] <hoonetorg> rkeene: with modify opennebula you mean me programming ruby or c/c++?
[15:07] <rkeene> No, the transfer manager for Ceph is written in bash
[15:07] <hoonetorg> rkeene: puh, with that I'm better :)
[15:08] <hoonetorg> do you know path of it in installed system?
[15:08] * kefu (~kefu@192.154.200.66) has joined #ceph
[15:08] <rkeene> Hang on, still doing testing
[15:09] <rkeene> I'm able to completely verify that it will become inconsistent
[15:10] * kefu (~kefu@192.154.200.66) Quit (Max SendQ exceeded)
[15:10] <ska> alfredodeza: Im missing something essential on my system..
[15:10] <alfredodeza> ska: what is Debian 7's codename?
[15:11] <alfredodeza> wheezy
[15:11] * kefu (~kefu@192.154.200.66) has joined #ceph
[15:14] * dugravot61 (~dugravot6@nat-persul-plg.wifi.univ-lorraine.fr) Quit (Quit: Leaving.)
[15:14] <hoonetorg> rkeene: shhhh....
[15:15] * kawa2014 (~kawa@89.184.114.246) Quit (Ping timeout: 480 seconds)
[15:15] * dugravot6 (~dugravot6@dn-infra-04.lionnois.univ-lorraine.fr) has joined #ceph
[15:16] * dugravot6 (~dugravot6@dn-infra-04.lionnois.univ-lorraine.fr) Quit ()
[15:16] <rkeene> hoonetorg, http://www.rkeene.org/viewer/tmp/ceph-rbd-cp-not-consistent.txt.htm
[15:16] * kefu (~kefu@192.154.200.66) Quit (Max SendQ exceeded)
[15:16] * dugravot6 (~dugravot6@dn-infra-04.lionnois.univ-lorraine.fr) has joined #ceph
[15:17] * yanzheng (~zhyan@182.139.20.134) Quit (Quit: This computer has gone to sleep)
[15:17] * dugravot6 (~dugravot6@dn-infra-04.lionnois.univ-lorraine.fr) Quit ()
[15:17] * squizzi (~squizzi@nat-pool-rdu-t.redhat.com) Quit (Remote host closed the connection)
[15:17] <ska> wheezy
[15:18] * yanzheng (~zhyan@182.139.20.134) has joined #ceph
[15:18] * kefu (~kefu@192.154.200.66) has joined #ceph
[15:18] <ska> apt-key list shows the key ok. but apt-key update does not process that key.
[15:21] <hoonetorg> rkeene: at point 2 were already lost, point 3 is the proof
[15:21] * sugoruyo (~georgev@paarthurnax.esc.rl.ac.uk) has joined #ceph
[15:21] * georgem (~Adium@fwnat.oicr.on.ca) has joined #ceph
[15:21] <hoonetorg> rkeene: but how to do it correctly manually
[15:22] <hoonetorg> 1. rbd snapshot
[15:22] <rkeene> rbd snapshot; rbd clone; rbd flatten (which unlinks the clone from the snapshot)
[15:22] <hoonetorg> rkeene: ok got it
[15:23] <rkeene> Look at /var/lib/one/remotes/tm/ceph/cpds at the end
[15:23] * rdas (~rdas@121.244.87.116) Quit (Quit: Leaving)
[15:24] <rkeene> Also /var/lib/one/remotes/datastore/ceph/cp has an "rbd copy", but only if you are using image format 1... which presumably doesn't support snapshots ?
[15:24] * joshd (~jdurgin@63.138.96.6) has joined #ceph
[15:24] <rkeene> Image format 1 seems to support snapshots to me
[15:25] * RomeroJnr (~h0m3r@hosd.leaseweb.net) Quit ()
[15:25] <joshd> format 1 supports snapshots, but not clones
[15:25] <rkeene> Ah
[15:25] <hoonetorg> but I use image format 2
[15:25] <rkeene> So you really only need to worry about "cpds"
[15:26] * kawa2014 (~kawa@89.184.114.246) has joined #ceph
[15:27] <hoonetorg> so you mean replacing the copy with snapshot clone flatten and some error handling should do the trick?
[15:27] <ska> alfredodeza: I was able to get around some of it with: ceph-deploy install --no-adjust-repos ceph-01 ...
[15:27] * dugravot6 (~dugravot6@dn-infra-04.lionnois.univ-lorraine.fr) has joined #ceph
[15:27] <ska> But I'm sure some other things are broken.
[15:28] * kefu (~kefu@192.154.200.66) Quit (Read error: Connection reset by peer)
[15:28] <doppelgrau> Anyone an idea why ???e2fsck -f -E discard /dev/rbdx??? frees space on a rbd-image but fstrim on the mounted iMAGE not? (ext3, kernel 4.1)
[15:28] <hoonetorg> rkeene: so you mean replacing the copy with snapshot clone flatten and some error handling should do the trick?
[15:28] <hoonetorg> rkeene: in script /var/lib/one/remotes/tm/ceph/cpds
[15:30] <alfredodeza> ska: yeah not sure what is going on, however, I think we might want to remove that -q flag so that errors are a bit more obvious
[15:33] * harold (~hamiller@71-94-227-123.dhcp.mdfd.or.charter.com) has joined #ceph
[15:33] * harold (~hamiller@71-94-227-123.dhcp.mdfd.or.charter.com) Quit ()
[15:35] <rkeene> hoonetorg, Yeah
[15:36] <rkeene> I'll verify and add a bug to OpenNebula
[15:36] * kefu (~kefu@114.92.100.239) has joined #ceph
[15:36] <ska> alfredodeza: I verified that my apt-setup is ok.. Maybe I can bypass wget's authentication somehow.
[15:36] * arbrandes (~arbrandes@189.78.72.151) has joined #ceph
[15:37] <hoonetorg> rkeene: will test changes in /var/lib/one/remotes/tm/ceph/* on my test system
[15:37] * sleinen1 (~Adium@2001:620:0:82::109) Quit (Ping timeout: 480 seconds)
[15:37] * kefu (~kefu@114.92.100.239) Quit ()
[15:38] <ska> alfredodeza: changing https to http works ok.
[15:38] <hoonetorg> rkeene: your fb email of your domain still working?
[15:38] <rkeene> Then you need to onehost sync --force
[15:38] <rkeene> fb email ?
[15:38] <hoonetorg> found feedback on /oss/ of your domain
[15:39] <hoonetorg> "let us know"
[15:39] <hoonetorg> (don't like writing direct emails in irc channels)
[15:39] <hoonetorg> rkeene: i would send you what i implemented
[15:40] <rkeene> hoonetorg, That email is probably valid... But I never check that... Anything @rkeene.org will reach me
[15:40] <hoonetorg> cool
[15:40] <rkeene> opennebula@rkeene.org or ceph@rkeene.org are fine examples
[15:40] <hoonetorg> then i will probably write to postmaster
[15:40] * peem (~piotr@office.forlinux.co.uk) has joined #ceph
[15:40] <hoonetorg> sry
[15:41] <hoonetorg> rkeene: take one of your suggestions
[15:41] <peem> How I can make rgw work with inkscope ? Or should I rather go for calimari instead.
[15:42] <hoonetorg> rkeene: thx very much so far
[15:43] * kawa2014 (~kawa@89.184.114.246) Quit (Quit: Leaving)
[15:44] * kawa2014 (~kawa@89.184.114.246) has joined #ceph
[15:46] <ska> alfredodeza: I need to find a solution for now because that wget call is used throughout ceph-deploy..
[15:47] <alfredodeza> ska: there are a couple of things you can do
[15:48] <alfredodeza> ska: you can set the key to "http" in your configuration file
[15:48] <alfredodeza> that is documented here http://ceph.com/ceph-deploy/docs/conf.html#ceph-deploy-configuration
[15:48] <alfredodeza> and you can set the repository info to default that way you can just install without any flags
[15:49] <ska> check_certificate = off in /etc/wgetrc
[15:49] <ska> cool.. ty
[15:49] <alfredodeza> with the ceph-deploy configuration changes you don't need to change that globally for every server you install ceph, which sounds unsafe
[15:49] <ska> ok.
[15:51] * vbellur (~vijay@64.251.112.55) Quit (Ping timeout: 480 seconds)
[15:54] <ska> http://paste.debian.net/261192/ same errors..
[15:56] * shang (~ShangWu@175.41.48.77) Quit (Quit: Ex-Chat)
[15:58] * dyasny (~dyasny@104.158.34.71) has joined #ceph
[15:58] <ska> http://paste.debian.net/261195/
[16:01] * T1w (~jens@node3.survey-it.dk) Quit (Ping timeout: 480 seconds)
[16:02] * bkopilov (~bkopilov@109.64.160.158) has joined #ceph
[16:02] * sleinen (~Adium@2001:620:0:2d:7ed1:c3ff:fedc:3223) has joined #ceph
[16:03] * sep (~sep@2a04:2740:1:0:52e5:49ff:feeb:32) Quit (Ping timeout: 480 seconds)
[16:04] * sleinen (~Adium@2001:620:0:2d:7ed1:c3ff:fedc:3223) Quit ()
[16:05] <alfredodeza> ska: you are not configuring a repo, you just changed one setting in one and left everything else commented out
[16:06] <alfredodeza> your repo section should look like one of the commented out ones, and include a `default = True` so you aren't required to specify it
[16:06] <alfredodeza> e.g. baseurl cannot be commented out
[16:09] <ska> ok..
[16:10] * derjohn_mob (~aj@fw.gkh-setu.de) Quit (Ping timeout: 480 seconds)
[16:10] * yanzheng (~zhyan@182.139.20.134) Quit (Quit: This computer has gone to sleep)
[16:11] <ska> I don't know what to put into those values though.. baseurl points to nothing.
[16:12] * TMM (~hp@sams-office-nat.tomtomgroup.com) Quit (Quit: Ex-Chat)
[16:12] * sleinen (~Adium@130.59.94.50) has joined #ceph
[16:12] * sep (~sep@95.62-50-191.enivest.net) has joined #ceph
[16:13] <ska> alfredodeza: did I do something wrong to have this much trouble? What is the root problem of my approach?
[16:13] * kefu (~kefu@114.92.100.239) has joined #ceph
[16:13] * sleinen1 (~Adium@2001:620:0:82::104) has joined #ceph
[16:14] <alfredodeza> ska: look at what your repo file looks like in your server that failed installation
[16:14] <alfredodeza> I don't know why the key is having those issues
[16:14] * vbellur (~vijay@64.251.112.55) has joined #ceph
[16:15] <ska> Could it be that I'm using hammer instead of something else? I don't recall doing anythingh different.
[16:15] <ska> Than the instructions.
[16:16] * TMM (~hp@sams-office-nat.tomtomgroup.com) has joined #ceph
[16:17] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[16:17] * kefu (~kefu@114.92.100.239) has joined #ceph
[16:18] * wschulze (~wschulze@cpe-69-206-240-164.nyc.res.rr.com) has joined #ceph
[16:20] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[16:20] * sleinen (~Adium@130.59.94.50) Quit (Ping timeout: 480 seconds)
[16:21] <hoonetorg> rkeene: http://dev.opennebula.org/issues/3782
[16:21] * kefu (~kefu@114.92.100.239) has joined #ceph
[16:24] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[16:25] * debian112 (~bcolbert@24.126.201.64) has joined #ceph
[16:25] * kefu (~kefu@114.92.100.239) has joined #ceph
[16:27] * p3t3rparker (~oftc-webi@43.224.129.29) has joined #ceph
[16:28] <doppelgrau> After playing around my fstrim/ext3 problem is not rbd-specifik, works with ext4-Images, so something in the used fstrim-Version or the kernel is the problem
[16:33] * derjohn_mob (~aj@p578b6aa1.dip0.t-ipconnect.de) has joined #ceph
[16:33] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[16:33] <p3t3rparker> i have a 4 node cluster with 3 osd each with default_pool_size as 3 and i have pg and pgp set as 512 (12*100/3) still it shows [too few PGs per OSD (16 < min 30)] .The real issue is a power failure restarted all 4 servers and now its in peering,stuck inactive,unclean state.I dont have any data in this cluster but still its not recovering.Can any one help me with this please
[16:33] * sleinen (~Adium@macsb.switch.ch) has joined #ceph
[16:34] * Concubidated (~Adium@23.91.33.7) Quit (Quit: Leaving.)
[16:34] <p3t3rparker> using hammer on centos 7
[16:35] * kefu (~kefu@114.92.100.239) has joined #ceph
[16:40] * sleinen1 (~Adium@2001:620:0:82::104) Quit (Ping timeout: 480 seconds)
[16:43] <burley> are all of your OSDs online?
[16:47] * bbby (~bibby@2601:204:c600:8a2e:e4d5:76ac:9b97:4190) has joined #ceph
[16:48] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[16:49] * kefu (~kefu@114.92.100.239) has joined #ceph
[16:51] <p3t3rparker> burley yes http://pastebin.com/H46a7f6H
[16:51] <p3t3rparker> luckily after rebooting all the servers its back online :)
[16:51] * kefu (~kefu@114.92.100.239) Quit (Max SendQ exceeded)
[16:52] * kefu (~kefu@114.92.100.239) has joined #ceph
[16:53] <p3t3rparker> any idea what will be the ideal PG and PGP value for single rbd pool (number of osd*100/pool size gives 512) but still it shows too few pgs per osd
[16:53] <burley> so I'd do a ceph health detail, to list those that are peering
[16:53] <burley> and then a 'ceph pg $PG query' to get some more details
[16:53] <burley> assumign your comment above isn't that you rebooted everything and the problem is now resolved
[16:54] * rlrevell (~leer@vbo1.inmotionhosting.com) Quit (Ping timeout: 480 seconds)
[16:55] <burley> per: http://ceph.com/docs/master/rados/operations/placement-groups/ "Between 10 and 50 OSDs set pg_num to 4096"
[16:56] * nardial (~ls@dslb-178-011-179-229.178.011.pools.vodafone-ip.de) Quit (Quit: Leaving)
[16:58] * rlrevell (~leer@184.52.129.221) has joined #ceph
[16:58] * rlrevell (~leer@184.52.129.221) Quit ()
[16:59] * rlrevell (~leer@184.52.129.221) has joined #ceph
[16:59] * mxmln (~mxmln@212.79.49.65) Quit (Quit: mxmln)
[16:59] * TheSov (~TheSov@cip-248.trustwave.com) has joined #ceph
[16:59] * rlrevell (~leer@184.52.129.221) Quit (Read error: Connection reset by peer)
[17:01] * overclk (~overclk@121.244.87.117) Quit (Quit: Leaving)
[17:02] * gregmark (~Adium@68.87.42.115) has joined #ceph
[17:04] * Kioob`Taff (~plug-oliv@2a01:e35:2e8a:1e0::42:10) Quit (Quit: Leaving.)
[17:04] * dyasny_ (~dyasny@104.158.34.71) has joined #ceph
[17:05] <TheSov> how does one evacuate an osd?
[17:05] * lpabon (~quassel@24-151-54-34.dhcp.nwtn.ct.charter.com) has joined #ceph
[17:07] <p3t3rparker> burley : thanks i will save your messages for real issues for now everything is back online after rebooting all 4 servers ,i will also try new pg_num
[17:09] <burley> thesov: "ceph osd out $osd"
[17:09] <TheSov> that will evacuate it?
[17:09] <burley> for one definition of evacuate
[17:09] <TheSov> i would still have to delete it afterwards correct?
[17:09] <burley> yes, that merely make the cluster rebalance its data
[17:10] <TheSov> i ask because my boss wants me to get to the knitty gritty before we try a "backups" environment
[17:11] <burley> if you use ceph-disk, there's a zap command i believe, I usually just remove the OSD entirely and then reformat manually if necessary, etc.
[17:11] <burley> http://ceph.com/docs/master/rados/operations/add-or-rm-osds/#removing-osds-manual
[17:11] <burley> http://ceph.com/docs/master/rados/deployment/ceph-deploy-osd/#zap-disks
[17:11] <TheSov> when an osd dies, do you find that its best to just delete it from the cluster and get to it when you can?
[17:11] * dyasny (~dyasny@104.158.34.71) Quit (Ping timeout: 480 seconds)
[17:13] <burley> we leave it in place (but marked out), until we replace the disk, at which point we follow the manual removal process and then let our automation add the new disk in its place
[17:13] <peem> I have 5 servers running osds, just powered one off for testing and whole cluster seems unresponsive... Is that normal behaviour ?
[17:13] <burley> peem: no :)
[17:13] <TheSov> if your monitor is on the same server yes,
[17:14] <peem> Ah.... ok one of two monitor was ..
[17:14] <TheSov> when a monitor goes down theres like 2 second lag on the cluster
[17:14] <TheSov> unless its the only monitor in which case, you have no cluster
[17:14] <burley> if you only have 2 monitors, then you have an issue
[17:14] <peem> TheSov: more like 15 minutes for me....
[17:14] <burley> since you wouldn't be able to get to a quorum
[17:14] <TheSov> then something else is wrong
[17:14] <burley> you need an odd number
[17:15] <TheSov> where are your monitors?
[17:15] <peem> burley: that's test environment...
[17:15] <TheSov> yes you need an odd number( preferably greater than 1)
[17:15] <burley> if you have 2 monitors, and one goes down, you have no quorum
[17:15] <burley> cluster is dead
[17:15] <peem> TheSov: burley already explained why it is down...
[17:15] * dugravot6 (~dugravot6@dn-infra-04.lionnois.univ-lorraine.fr) Quit (Quit: Leaving.)
[17:16] <peem> Would adding monitors now help ?
[17:16] <burley> if you have 3 monitors and one goes down, you still have a majority up and your cluster will survive
[17:16] <TheSov> you could, but you would have to copy the keys to it first
[17:16] <burley> you probably need to bring the one you downed back online, then add the third
[17:17] <TheSov> you should also run your monitors on dedicated hardware
[17:17] <TheSov> even for a test IMHO
[17:17] * MentalRay (~MRay@MTRLPQ42-1176054809.sdsl.bell.ca) has joined #ceph
[17:17] <peem> TheSov: I should ...
[17:18] <TheSov> root@ceph-mon-01:/home/ceph# ceph status
[17:18] <TheSov> cluster 16f67b32-6489-4a41-a494-33b118e636cb
[17:18] <TheSov> health HEALTH_OK
[17:18] <TheSov> monmap e1: 3 mons at {ceph-mon-01=10.70.114.11:6789/0,ceph-mon-02=10.70.114.12:6789/0,ceph-mon-03=10.70.114.13:6789/0}
[17:18] <TheSov> election epoch 16, quorum 0,1,2 ceph-mon-01,ceph-mon-02,ceph-mon-03
[17:18] <TheSov> osdmap e25: 4 osds: 4 up, 4 in
[17:18] <TheSov> pgmap v78: 128 pgs, 2 pools, 133 bytes data, 2 objects
[17:18] <TheSov> 20616 MB used, 873 GB / 893 GB avail
[17:18] * rlrevell (~leer@vbo1.inmotionhosting.com) has joined #ceph
[17:18] <TheSov> 128 active+clean
[17:18] <TheSov> root@ceph-mon-01:/home/ceph#
[17:18] <TheSov> my test!
[17:19] * oro (~oro@2001:620:20:16:749b:4710:c54f:d03c) Quit (Ping timeout: 480 seconds)
[17:19] <TheSov> 3 monitors and 4 osd servers
[17:19] * oro_ (~oro@2001:620:20:16:749b:4710:c54f:d03c) Quit (Ping timeout: 480 seconds)
[17:27] * madkiss (~madkiss@chello080108036100.31.11.vie.surfer.at) has joined #ceph
[17:28] * elder (~elder@104.135.1.105) has joined #ceph
[17:29] <peem> TheSov: one option would be to have monitor on each osd server. Should work fine for test environment.
[17:30] * angdraug (~angdraug@c-50-174-102-105.hsd1.ca.comcast.net) has joined #ceph
[17:33] * moore (~moore@64.202.160.88) has joined #ceph
[17:34] * yanzheng (~zhyan@182.139.20.134) has joined #ceph
[17:35] * yguang11 (~yguang11@nat-dip30-wl-d.cfw-a-gci.corp.yahoo.com) has joined #ceph
[17:37] * joshd (~jdurgin@63.138.96.6) Quit (Quit: Leaving.)
[17:37] * Guest2769 is now known as n8
[17:37] * n8 is now known as networkn8
[17:41] * kefu_ (~kefu@114.92.96.246) has joined #ceph
[17:41] * bitserker (~toni@88.87.194.130) has joined #ceph
[17:42] * TMM (~hp@sams-office-nat.tomtomgroup.com) Quit (Quit: Ex-Chat)
[17:43] * kefu_ (~kefu@114.92.96.246) Quit ()
[17:44] * cooldharma06 (~chatzilla@14.139.180.40) Quit (Quit: ChatZilla 0.9.91.1 [Iceweasel 21.0/20130515140136])
[17:46] * kefu (~kefu@114.92.100.239) Quit (Ping timeout: 480 seconds)
[17:49] * Lyncos (~lyncos@208.71.184.41) has left #ceph
[17:50] * dneary (~dneary@64.251.112.55) has joined #ceph
[17:54] * oro (~oro@84-72-180-62.dclient.hispeed.ch) has joined #ceph
[17:58] <TheSov> peem, but i have 7...
[17:59] * alram (~alram@cpe-172-250-2-46.socal.res.rr.com) has joined #ceph
[18:01] * kawa2014 (~kawa@89.184.114.246) Quit (Quit: Leaving)
[18:02] * xarses_ (~xarses@c-73-202-191-48.hsd1.ca.comcast.net) has joined #ceph
[18:02] * madkiss (~madkiss@chello080108036100.31.11.vie.surfer.at) Quit (Quit: Leaving.)
[18:03] * Nacer_ (~Nacer@252-87-190-213.intermediasud.com) Quit (Ping timeout: 480 seconds)
[18:04] * cholcombe (~chris@c-73-180-29-35.hsd1.or.comcast.net) has joined #ceph
[18:05] * lcurtis (~lcurtis@47.19.105.250) has joined #ceph
[18:05] * vbellur (~vijay@64.251.112.55) Quit (Ping timeout: 480 seconds)
[18:05] * starcoder (~Kidlvr@tor-exit-node.7by7.de) has joined #ceph
[18:10] * dneary (~dneary@64.251.112.55) Quit (Ping timeout: 480 seconds)
[18:15] * mykola (~Mikolaj@91.225.202.121) has joined #ceph
[18:15] <ganders> hi cephers, one quick question, is best to had a OSD server with a mix of SSD and SATA disks or to had only SATA disks and put the SSD on a cache tier?
[18:16] * jordanP (~jordan@213.215.2.194) Quit (Remote host closed the connection)
[18:17] <ska> I finally got some OSD's up. Somehow it lists my mon node as an OSD : http://git.io/vtO3C
[18:17] <doppelgrau> ganders: depends on the workload, but usually ssd for journals is better
[18:17] <ska> ceph health doesnt give me the green light.
[18:17] <burley> ganders: We have 3 classes of ceph nodes: mons, spinner OSDs and SSD OSDs
[18:17] <burley> the spinner OSDs use spinners for data, and ssd's for journaling
[18:17] <burley> the SSDs just have SSD drives
[18:18] <burley> and we use crush rules to ensure pools use the right set of disks
[18:18] <ganders> burley: so the best way to go would be spinner OSD's, journal SSD and cache SSD? since i had more ssds than spinner disks
[18:18] <burley> if you want to tier, you certainly can, but its not required
[18:18] <ganders> since i've the osd servers with 4x 3TB disks and 8 SSD disks
[18:19] <doppelgrau> ganders: in that case i would think of ssd for primary copy for fast reads
[18:19] <ska> My ceph.conf only has a global section.
[18:19] <doppelgrau> ganders: in addition to ssd-journals
[18:19] <ganders> doppelgrau: and what about the spinner disks?
[18:20] <doppelgrau> other copies with ssd journal
[18:20] <doppelgrau> bbl
[18:21] <ganders> with primary copy you mean a cache pool infront of the 'regular' hdd disks right?
[18:23] <ganders> also, is there any problem to mix OSD servers with different type of cpu's?
[18:24] <ska> Do I need to run Ceph-mds to get my OSD repaired?
[18:26] * jameskassemi (~james@216.243.114.238) has joined #ceph
[18:27] * yanzheng (~zhyan@182.139.20.134) Quit (Quit: This computer has gone to sleep)
[18:28] <ska> I have osd pool default size = 2, but it seems like its still stuck.
[18:29] <ska> Should I remove my non-osd node from the osd's?
[18:29] * yanzheng (~zhyan@182.139.20.134) has joined #ceph
[18:31] * perpetualrabbit (~perpetual@asselijn.lorentz.leidenuniv.nl) Quit (Quit: Leaving)
[18:31] * yanzheng (~zhyan@182.139.20.134) Quit ()
[18:32] * Rickus (~Rickus@office.protected.ca) has joined #ceph
[18:33] <ska> Actually for some reason, it has one osd on node2 and 2 on node3
[18:35] * starcoder (~Kidlvr@5NZAAEB6N.tor-irc.dnsbl.oftc.net) Quit ()
[18:35] * Concubidated (~Adium@23.91.33.7) has joined #ceph
[18:45] * snakamoto (~Adium@192.16.26.2) has joined #ceph
[18:46] <doppelgrau> ganders: no, I mean a crush-map where the first copy is put on a ssd and the other (size - 1) copies are put on platter sith ssd-journal
[18:46] * dopesong (~dopesong@lb1.mailer.data.lt) Quit (Ping timeout: 480 seconds)
[18:46] * ingslovak (~peto@office.websupport.sk) Quit (Quit: Leaving.)
[18:46] * sugoruyo (~georgev@paarthurnax.esc.rl.ac.uk) Quit (Quit: I'm going home!)
[18:48] * arbrandes (~arbrandes@189.78.72.151) Quit (Remote host closed the connection)
[18:55] * bitserker (~toni@88.87.194.130) Quit (Ping timeout: 480 seconds)
[18:59] * sankarshan (~sankarsha@183.87.39.242) Quit (Quit: Are you sure you want to quit this channel (Cancel/Ok) ?)
[19:01] * xarses_ (~xarses@c-73-202-191-48.hsd1.ca.comcast.net) Quit (Quit: Leaving)
[19:01] <qhartman> So I've been working on reducing the iowait on a heavily loaded cluster that is serving VM images to openstack
[19:01] * xarses (~xarses@c-73-202-191-48.hsd1.ca.comcast.net) Quit (Remote host closed the connection)
[19:01] * dopesong (~dopesong@78-60-74-130.static.zebra.lt) has joined #ceph
[19:01] * xarses (~xarses@c-73-202-191-48.hsd1.ca.comcast.net) has joined #ceph
[19:01] <qhartman> last night while doing some work to add another pool to the setup, I accidentally removed the permissions that allowed the currently running VMs to access ceph
[19:02] <qhartman> This forced me to reboot essentially all the VMs on the cluster
[19:02] * nils_ (~nils@doomstreet.collins.kg) Quit (Quit: This computer has gone to sleep)
[19:02] <qhartman> and now my iowait is reduced by about 50% from where it was across the cluster
[19:03] <qhartman> my only explanation is that either there were some VMs that were in some sort of weird pathological state that caused them to create more IO than they should have, and rebooting stopped that
[19:04] <qhartman> OR (and I think this is more likely) the restarted VMs are running with a newer qemu and/or librbd than they had been, which is behaving better
[19:04] <qhartman> I did update ceph to 0.87.1 recently, but I don't recall if that was before or after this fleet of VMs was started.
[19:06] <qhartman> but as far as I can tell the same amount of work is being done by the VMs as was before, but the IO stats are looking much better. Queues are reduced, responsiveness is improved, every measurable metric is better.
[19:07] <p3t3rparker> sorry to ask this basic question ,in ceph.conf pg_num, pgp_num was 512 and later i changed to 4096 and i did a reboot of all 4servers but still ceph -s shows [too few pgs 16 < 30] whats the relation between this and pg_num
[19:08] * irccloud1228 (uid94503@id-94503.ealing.irccloud.com) Quit (Quit: Connection closed for inactivity)
[19:08] * segutier (~segutier@173-13-189-142-sfba.hfc.comcastbusiness.net) has joined #ceph
[19:08] <qhartman> you have to actually make the change in the pool itself, the value in the conf is just the default new pools will be created with
[19:08] * Sysadmin88 (~IceChat77@2.124.164.69) has joined #ceph
[19:09] <qhartman> so you need to issue a command like "ceph osd $pool set pg_num 4096".
[19:09] <qhartman> (that syntax probably isn't right, but the spirit is there)
[19:09] * segutier (~segutier@173-13-189-142-sfba.hfc.comcastbusiness.net) Quit ()
[19:09] <qhartman> also, you will probably need to increase the pg num in small steps to get to your deisred number
[19:10] <qhartman> and ultimately make sure your pgp num is updated as well.
[19:11] <doppelgrau> qhartman: bad behaving VMs could be swapping? lots of IO and stops when rebooting ???
[19:11] <qhartman> doppelgrau, I run them w/o swap to prevent that very thing
[19:12] <qhartman> in our environment having something OOM killed is prefereable to the IO load of using swap.
[19:12] * sleinen (~Adium@macsb.switch.ch) Quit (Ping timeout: 480 seconds)
[19:16] * TheSov3 (~TheSov@38.106.143.234) has joined #ceph
[19:17] * Concubidated (~Adium@23.91.33.7) Quit (Quit: Leaving.)
[19:18] * i_m (~ivan.miro@deibp9eh1--blueice3n2.emea.ibm.com) Quit (Ping timeout: 480 seconds)
[19:20] * angdraug (~angdraug@c-50-174-102-105.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[19:22] * daviddcc (~dcasier@LAubervilliers-656-1-16-164.w217-128.abo.wanadoo.fr) Quit (Ping timeout: 480 seconds)
[19:22] <doppelgrau> qhartman: ok, then you see in a few days if the IO increases with the runtime or the newer versions had helped
[19:23] * TheSov (~TheSov@cip-248.trustwave.com) Quit (Ping timeout: 480 seconds)
[19:23] <qhartman> yup
[19:24] <qhartman> Jsut thought it was interesting so I'd mention it in here for posterity
[19:24] <ganders> doppelgrau: got you, also the mix of cpu's on the osd servers is possible or is not recommended?
[19:25] <doppelgrau> ganders: I see no disadvantage as long the cpus are fast enough. And use the faster one for SSDs
[19:28] * reed (~reed@75-101-54-131.dsl.static.fusionbroadband.com) has joined #ceph
[19:30] * dgurtner (~dgurtner@178.197.231.10) Quit (Ping timeout: 480 seconds)
[19:37] * xarses (~xarses@c-73-202-191-48.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[19:52] * xarses (~xarses@12.164.168.117) has joined #ceph
[19:52] * xarses (~xarses@12.164.168.117) Quit (Remote host closed the connection)
[19:53] * xarses (~xarses@12.164.168.117) has joined #ceph
[19:54] * TheSov (~TheSov@cip-248.trustwave.com) has joined #ceph
[19:56] * Concubidated (~Adium@192.170.161.35) has joined #ceph
[19:59] * ngoswami (~ngoswami@121.244.87.116) Quit (Quit: Leaving)
[20:00] * daviddcc (~dcasier@84.197.151.77.rev.sfr.net) has joined #ceph
[20:01] * bbby (~bibby@2601:204:c600:8a2e:e4d5:76ac:9b97:4190) Quit (Quit: Leaving.)
[20:01] * TheSov3 (~TheSov@38.106.143.234) Quit (Ping timeout: 480 seconds)
[20:02] * bbby (~bibby@2601:204:c600:8a2e:c54b:d8db:a54c:b489) has joined #ceph
[20:08] * t0rn (~ssullivan@2607:fad0:32:a02:56ee:75ff:fe48:3bd3) has joined #ceph
[20:08] * t0rn (~ssullivan@2607:fad0:32:a02:56ee:75ff:fe48:3bd3) has left #ceph
[20:09] <p3t3rparker> thanks qhartman it works :)
[20:11] * MentalRay (~MRay@MTRLPQ42-1176054809.sdsl.bell.ca) Quit (Quit: This computer has gone to sleep)
[20:13] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[20:13] * dyasny_ is now known as dyasny
[20:17] * bbby (~bibby@2601:204:c600:8a2e:c54b:d8db:a54c:b489) Quit (Ping timeout: 480 seconds)
[20:18] <ska> Is there a large difference between the ceph-rest-api and the calamari api?
[20:19] <off_rhoden> ska: I thik gmeno in #ceph-devel can answer that best
[20:23] <TheSov> ok i got something odd to report, when i first connect to an rbd and do an hdparm test, it goes a good speed like 200megabytes per second, but once i mount and write to it any data, it goes half of that what gives?
[20:23] <TheSov> is that just a shitty os?
[20:27] <ira> OS?
[20:28] * bbby (~bibby@2601:204:c600:8a2e:c54b:d8db:a54c:b489) has joined #ceph
[20:28] * jameskassemi (~james@216.243.114.238) Quit (Quit: jameskassemi)
[20:30] <TheSov> operating system
[20:31] * sleinen (~Adium@84-72-160-233.dclient.hispeed.ch) has joined #ceph
[20:33] * sleinen1 (~Adium@2001:620:0:82::105) has joined #ceph
[20:39] * sleinen (~Adium@84-72-160-233.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[20:42] * dupont-y (~dupont-y@familledupont.org) has joined #ceph
[20:46] <rkeene> hoonetorg, I'm in #OpenNebula too FWIW
[20:48] * p3t3rparker (~oftc-webi@43.224.129.29) Quit (Quit: Page closed)
[20:51] * bbby (~bibby@2601:204:c600:8a2e:c54b:d8db:a54c:b489) Quit (Ping timeout: 480 seconds)
[20:54] * jameskassemi (~james@75-173-111-208.albq.qwest.net) has joined #ceph
[20:57] <ganders> i need to power-off a OSD server to replace a memory, is there any procedure out-there?
[20:58] <ganders> or just mark all the osd's that belong to that OSD server with the noout set option?
[20:58] <burley> assuming you have suitable replication and don't want data to move, 'ceph osd set noout'
[20:58] <burley> then power it down and replace the chip
[20:59] <burley> then 'ceph osd unset noout'
[20:59] <ganders> burley: excellent, thanks a lot!
[21:01] <burley> alternately, set the 'mon osd down out interval' value high enough that you can do such maintenance without setting noout
[21:02] * MentalRay (~MRay@MTRLPQ42-1176054809.sdsl.bell.ca) has joined #ceph
[21:07] <georgem> ganders: I don't think you can mark just some osd with "noout", it's a cluster wide setting
[21:10] <ganders> georgem: you are right, i express my self wrong :D
[21:10] * DV (~veillard@2001:41d0:a:f29f::1) Quit (Remote host closed the connection)
[21:11] * DV (~veillard@2001:41d0:a:f29f::1) has joined #ceph
[21:12] * rotbeard (~redbeard@2a02:908:df10:d300:6267:20ff:feb7:c20) has joined #ceph
[21:22] * marrusl (~mark@cpe-67-247-9-253.nyc.res.rr.com) Quit (Quit: bye!)
[21:24] * joshd (~jdurgin@64.251.112.55) has joined #ceph
[21:28] * jameskassemi (~james@75-173-111-208.albq.qwest.net) Quit (Quit: jameskassemi)
[21:29] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[21:30] * jameskassemi (~james@75-173-111-208.albq.qwest.net) has joined #ceph
[21:34] * snakamoto (~Adium@192.16.26.2) Quit (Quit: Leaving.)
[21:40] * joshd (~jdurgin@64.251.112.55) Quit (Ping timeout: 480 seconds)
[21:43] * marrusl (~mark@cpe-67-247-9-253.nyc.res.rr.com) has joined #ceph
[21:51] * branto (~branto@178.253.154.66) has joined #ceph
[21:51] * branto (~branto@178.253.154.66) Quit ()
[21:54] * visbits (~textual@8.29.138.28) Quit (Ping timeout: 480 seconds)
[21:57] <TheSov> are there any guides to perf tuning rbd's?
[22:09] * TMM (~hp@178-84-46-106.dynamic.upc.nl) has joined #ceph
[22:10] * fdmanana__ (~fdmanana@bl13-155-180.dsl.telepac.pt) Quit (Ping timeout: 480 seconds)
[22:17] * DV_ (~veillard@2001:41d0:a:f29f::1) Quit (Ping timeout: 480 seconds)
[22:18] * DV (~veillard@2001:41d0:a:f29f::1) Quit (Ping timeout: 480 seconds)
[22:27] * DV (~veillard@2001:41d0:1:d478::1) has joined #ceph
[22:28] * DV_ (~veillard@2001:41d0:1:d478::1) has joined #ceph
[22:28] * dopesong_ (~dopesong@lb1.mailer.data.lt) has joined #ceph
[22:31] * bitserker (~toni@77.231.154.146) has joined #ceph
[22:31] * ganders (~root@190.2.42.21) Quit (Quit: WeeChat 0.4.2)
[22:32] * Rickus (~Rickus@office.protected.ca) Quit (Read error: Connection reset by peer)
[22:34] * dopesong (~dopesong@78-60-74-130.static.zebra.lt) Quit (Ping timeout: 480 seconds)
[22:36] * MentalRay (~MRay@MTRLPQ42-1176054809.sdsl.bell.ca) Quit (Quit: This computer has gone to sleep)
[22:40] * MentalRay (~MRay@MTRLPQ42-1176054809.sdsl.bell.ca) has joined #ceph
[22:41] * fridim_ (~fridim@56-198-190-109.dsl.ovh.fr) Quit (Ping timeout: 480 seconds)
[22:46] * georgem (~Adium@fwnat.oicr.on.ca) Quit (Quit: Leaving.)
[22:51] * jameskassemi (~james@75-173-111-208.albq.qwest.net) Quit (Quit: jameskassemi)
[22:51] * mykola (~Mikolaj@91.225.202.121) Quit (Quit: away)
[22:52] * jameskassemi (~james@75-173-111-208.albq.qwest.net) has joined #ceph
[22:53] * jameskassemi (~james@75-173-111-208.albq.qwest.net) Quit ()
[22:58] * oro (~oro@84-72-180-62.dclient.hispeed.ch) Quit (Ping timeout: 480 seconds)
[23:00] <ska> Can I run "ceph-deploy admin node_i" on each host sequentially? ( like in a loop)
[23:02] * Rickus (~Rickus@office.protected.ca) has joined #ceph
[23:05] * snakamoto (~Adium@192.16.26.2) has joined #ceph
[23:06] * jameskassemi (~james@75-173-111-208.albq.qwest.net) has joined #ceph
[23:09] * dopesong_ (~dopesong@lb1.mailer.data.lt) Quit (Remote host closed the connection)
[23:13] * rlrevell (~leer@vbo1.inmotionhosting.com) Quit (Ping timeout: 480 seconds)
[23:24] * dupont-y (~dupont-y@familledupont.org) Quit (Quit: Ex-Chat)
[23:25] * badone (~brad@CPE-121-215-241-179.static.qld.bigpond.net.au) has joined #ceph
[23:26] * TheSov (~TheSov@cip-248.trustwave.com) Quit (Read error: Connection reset by peer)
[23:26] * TMM (~hp@178-84-46-106.dynamic.upc.nl) Quit (Quit: Ex-Chat)
[23:28] <ska> http://paste.debian.net/261428/ missing rados service in debian7.
[23:30] <ska> Its named /etc/init.d/radosgw ...
[23:35] * mattrich (~Adium@38.108.161.130) has joined #ceph
[23:37] <ska> http://paste.debian.net/261429/ full log
[23:41] <mattrich> I get a compile error with gcc version 4.6.3 (ubuntu 12.04) in src/test/librbd/test_librbd.cc about a variable length array of non-POD element type. Would you take a patch for that or is that not a compiler version you care to support?
[23:41] * TMM (~hp@178-84-46-106.dynamic.upc.nl) has joined #ceph
[23:43] * newbie (~kvirc@c-73-6-205-85.hsd1.tx.comcast.net) has joined #ceph
[23:43] * rlrevell (~leer@184.52.129.221) has joined #ceph
[23:47] * jdillaman (~jdillaman@pool-108-18-97-82.washdc.fios.verizon.net) Quit (Quit: jdillaman)
[23:48] * rlrevell (~leer@184.52.129.221) Quit (Read error: Connection reset by peer)
[23:52] * vata (~vata@207.96.182.162) Quit (Quit: Leaving.)
[23:57] * fdmanana__ (~fdmanana@bl13-155-180.dsl.telepac.pt) has joined #ceph

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