#ceph IRC Log

Index

IRC Log for 2016-07-10

Timestamps are in GMT/BST.

[0:06] * noahw (~noahw@eduroam-169-233-236-117.ucsc.edu) Quit (Ping timeout: 480 seconds)
[0:11] * TomasCZ (~TomasCZ@yes.tenlab.net) Quit (Remote host closed the connection)
[0:11] * TomasCZ (~TomasCZ@yes.tenlab.net) has joined #ceph
[0:19] * Jeffrey4l_ (~Jeffrey@119.251.140.246) has joined #ceph
[0:22] * n0x1d (~ggg@tsn109-201-154-210.dyn.nltelcom.net) has joined #ceph
[0:32] * Jeffrey4l_ (~Jeffrey@119.251.140.246) Quit (Ping timeout: 480 seconds)
[0:49] * newbie (~kvirc@host217-114-156-249.pppoe.mark-itt.net) Quit (Ping timeout: 480 seconds)
[0:52] * n0x1d (~ggg@tsn109-201-154-210.dyn.nltelcom.net) Quit ()
[0:52] * penguinRaider (~KiKo@23.27.206.118) Quit (Ping timeout: 480 seconds)
[0:55] * MentalRay (~MentalRay@107.171.161.165) has joined #ceph
[0:55] * MentalRay (~MentalRay@107.171.161.165) Quit ()
[0:57] <jiffe> how can I tell which directory each osd is mapped to?
[0:58] <neurodrone_> jiffe: What do you mean? They should all be in /var/lib/ceph/osd/* with the OSD id.
[1:02] * penguinRaider (~KiKo@23.27.206.118) has joined #ceph
[1:03] <jiffe> ah cool that works
[1:05] * owasserm (~owasserm@2001:984:d3f7:1:5ec5:d4ff:fee0:f6dc) Quit (Ping timeout: 480 seconds)
[1:08] * MentalRay (~MentalRay@107.171.161.165) has joined #ceph
[1:10] * Atomizer (~Cue@176.31.7.241) has joined #ceph
[1:11] * owasserm (~owasserm@2001:984:d3f7:1:5ec5:d4ff:fee0:f6dc) has joined #ceph
[1:15] * jdillaman_ (~jdillaman@pool-108-18-97-95.washdc.fios.verizon.net) Quit (Quit: jdillaman_)
[1:18] * rendar (~I@host107-182-dynamic.247-95-r.retail.telecomitalia.it) Quit (Quit: std::lower_bound + std::less_equal *works* with a vector without duplicates!)
[1:21] * MentalRay (~MentalRay@107.171.161.165) Quit (Quit: My Mac has gone to sleep. ZZZzzz???)
[1:22] * MentalRay (~MentalRay@107.171.161.165) has joined #ceph
[1:22] * MentalRay (~MentalRay@107.171.161.165) Quit ()
[1:40] * Atomizer (~Cue@7EXAAAB5C.tor-irc.dnsbl.oftc.net) Quit ()
[1:41] * noahw (~noahw@eduroam-169-233-236-117.ucsc.edu) has joined #ceph
[1:45] * fdmanana (~fdmanana@2001:8a0:6e0c:6601:80fe:bd46:5d83:1f20) has joined #ceph
[1:49] * Vale (~dusti@tor2r.ins.tor.net.eu.org) has joined #ceph
[2:00] * fdmanana (~fdmanana@2001:8a0:6e0c:6601:80fe:bd46:5d83:1f20) Quit (Ping timeout: 480 seconds)
[2:15] * noahw (~noahw@eduroam-169-233-236-117.ucsc.edu) Quit (Ping timeout: 480 seconds)
[2:19] * Vale (~dusti@4PRAAADD8.tor-irc.dnsbl.oftc.net) Quit ()
[2:24] * legion (~Sun7zu@61TAAAD13.tor-irc.dnsbl.oftc.net) has joined #ceph
[2:25] * Concubidated (~cube@122.103.163.63.ap.gmobb-fix.jp) has joined #ceph
[2:26] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) Quit (Quit: neurodrone_)
[2:39] * Discovery (~Discovery@109.235.52.5) Quit (Ping timeout: 480 seconds)
[2:53] * legion (~Sun7zu@61TAAAD13.tor-irc.dnsbl.oftc.net) Quit ()
[2:54] * dneary (~dneary@rrcs-69-193-7-218.nys.biz.rr.com) has joined #ceph
[3:03] * dneary (~dneary@rrcs-69-193-7-218.nys.biz.rr.com) Quit (Ping timeout: 480 seconds)
[3:19] * penguinRaider (~KiKo@23.27.206.118) Quit (Ping timeout: 480 seconds)
[3:30] * acctor (~acctor@c-73-170-8-35.hsd1.ca.comcast.net) has joined #ceph
[3:33] * penguinRaider (~KiKo@23.27.206.118) has joined #ceph
[3:37] <jiffe> so I used reweight-by-utilization and it reduced the weight of a single osd, it remapped some things but afterwards it is still using the same amount of space
[3:37] * ZyTer_ (~ZyTer@ghostbusters.apinnet.fr) Quit (Read error: Connection reset by peer)
[3:40] <jiffe> it seems to be going up and down so there must be some kind of cleanup going on
[3:40] * sebastian-w_ (~quassel@212.218.8.139) has joined #ceph
[3:43] * sebastian-w (~quassel@212.218.8.139) Quit (Read error: Connection reset by peer)
[3:54] <Psi-Jack> What does min_size really do? Insures that there's a minimum of 2 replicas?
[3:54] * aj__ (~aj@x4db06a39.dyn.telefonica.de) has joined #ceph
[4:02] * derjohn_mobi (~aj@x590c1b50.dyn.telefonica.de) Quit (Ping timeout: 480 seconds)
[4:03] <Psi-Jack> Heh. wow. First time since my Ceph migration that it's actually been HEALTH_OK, and not HEALTH_WARN! Finally. :D
[4:11] * acctor (~acctor@c-73-170-8-35.hsd1.ca.comcast.net) Quit (Quit: acctor)
[4:41] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) has joined #ceph
[5:13] * Vacuum__ (~Vacuum@88.130.193.226) has joined #ceph
[5:20] * Vacuum_ (~Vacuum@i59F7961C.versanet.de) Quit (Ping timeout: 480 seconds)
[5:36] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[5:52] * Chaos_Llama (~Xerati@tor.ohundred.com) has joined #ceph
[5:53] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) Quit (Quit: neurodrone_)
[5:57] * acctor (~acctor@c-73-170-8-35.hsd1.ca.comcast.net) has joined #ceph
[5:59] * [0x4A6F]_ (~ident@p4FC266DD.dip0.t-ipconnect.de) has joined #ceph
[6:02] * [0x4A6F] (~ident@0x4a6f.user.oftc.net) Quit (Ping timeout: 480 seconds)
[6:02] * [0x4A6F]_ is now known as [0x4A6F]
[6:12] * shyu (~Frank@180.173.197.145) has joined #ceph
[6:15] * ircolle (~Adium@173-19-51-71.client.mchsi.com) has joined #ceph
[6:22] * Chaos_Llama (~Xerati@61TAAAD54.tor-irc.dnsbl.oftc.net) Quit ()
[6:23] * ircolle (~Adium@173-19-51-71.client.mchsi.com) Quit (Ping timeout: 480 seconds)
[6:28] * acctor (~acctor@c-73-170-8-35.hsd1.ca.comcast.net) Quit (Quit: acctor)
[6:29] * shyu (~Frank@180.173.197.145) Quit (Ping timeout: 480 seconds)
[6:30] * acctor (~acctor@c-73-170-8-35.hsd1.ca.comcast.net) has joined #ceph
[6:32] * EinstCrazy (~EinstCraz@61.165.253.133) has joined #ceph
[6:37] * hroussea (~hroussea@000200d7.user.oftc.net) Quit (Read error: Connection reset by peer)
[6:38] * acctor (~acctor@c-73-170-8-35.hsd1.ca.comcast.net) Quit (Quit: acctor)
[6:41] * acctor (~acctor@c-73-170-8-35.hsd1.ca.comcast.net) has joined #ceph
[6:56] * Jeffrey4l_ (~Jeffrey@221.192.178.17) has joined #ceph
[6:57] * EinstCrazy (~EinstCraz@61.165.253.133) Quit (Remote host closed the connection)
[7:28] * Jeffrey4l_ (~Jeffrey@221.192.178.17) Quit (Ping timeout: 480 seconds)
[8:07] * jidar (~jidar@r2d2.fap.me) Quit (Quit: stuff.)
[8:08] * jidar (~jidar@r2d2.fap.me) has joined #ceph
[8:11] * praveen (~praveen@122.172.37.2) has joined #ceph
[8:11] * Jeffrey4l_ (~Jeffrey@221.192.178.17) has joined #ceph
[8:12] * Jeffrey4l_ (~Jeffrey@221.192.178.17) Quit ()
[8:19] * praveen (~praveen@122.172.37.2) Quit (Ping timeout: 480 seconds)
[8:37] * oliveiradan (~doliveira@137.65.133.10) Quit (Ping timeout: 480 seconds)
[8:56] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[9:00] * itamarl is now known as Guest2450
[9:00] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[9:04] * Guest2450 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[9:07] * arbrandes (~arbrandes@54.172.54.135) Quit (Ping timeout: 480 seconds)
[9:08] * itamarl is now known as Guest2451
[9:08] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[9:09] * Cue (~Joppe4899@213.61.149.100) has joined #ceph
[9:10] * arbrandes (~arbrandes@ec2-54-172-54-135.compute-1.amazonaws.com) has joined #ceph
[9:10] * Guest2451 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[9:24] * itamarl is now known as Guest2452
[9:24] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[9:25] * rendar (~I@host104-158-dynamic.44-79-r.retail.telecomitalia.it) has joined #ceph
[9:29] * itamarl is now known as Guest2453
[9:29] * Guest2452 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[9:29] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[9:32] * Guest2453 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[9:39] * Cue (~Joppe4899@7EXAAACCL.tor-irc.dnsbl.oftc.net) Quit ()
[9:39] * rwheeler (~rwheeler@bzq-82-81-161-51.red.bezeqint.net) has joined #ceph
[9:42] * swami1 (~swami@27.7.165.149) has joined #ceph
[9:45] * itamarl is now known as Guest2454
[9:45] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[9:46] * praveen (~praveen@122.172.37.2) has joined #ceph
[9:49] * Guest2454 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[9:52] * ircuser-1 (~Johnny@69.62.183.158) Quit (Quit: because)
[9:53] * itamarl is now known as Guest2455
[9:53] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[9:56] * Guest2455 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[9:57] * Coe|work (~Lunk2@nl3x.mullvad.net) has joined #ceph
[10:01] * John341 (~ceph@118.200.221.105) has joined #ceph
[10:02] <John341> When I try to bring up my osd.8, /etc/init.d/ceph start osd.8 on centos7/hammer, I get this large error in syslog. http://pastebin.ca/3656813
[10:02] <John341> can anyone advice on how to repair my osd?
[10:13] * efirs1 (~firs@c-50-185-70-125.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[10:15] * itamarl (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[10:18] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[10:25] * itamarl is now known as Guest2456
[10:26] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[10:27] * Coe|work (~Lunk2@7EXAAACC0.tor-irc.dnsbl.oftc.net) Quit ()
[10:28] * Guest2456 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[10:35] <badone> John341: there's a problem with your storage/hw/fw/driver stack
[10:35] <badone> $ sg_decode_sense 70 00 05 00 00 00 00 0a 00 00 00 00 20 00 01 cf 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[10:35] <badone> Fixed format, current; Sense key: Illegal Request
[10:35] <badone> Additional sense: Invalid command operation code
[10:35] <badone> Field replaceable unit code: 1
[10:35] <badone> Sense Key Specific: Error in Command: byte 0 bit 7
[10:35] <badone> something in the stack is reporting an Illegal Request
[10:43] * itamarl is now known as Guest2458
[10:43] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[10:46] <John341> badone: I'm not sure why I get this, it is just a ssd-partition for journaling, and osd is a complete sas drive.
[10:46] * Guest2458 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[10:46] <John341> badone: everything was working until I had to do a hard reset on the machine because it became inaccessiable
[10:49] * itamarl is now known as Guest2459
[10:50] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[10:53] * Guest2459 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[10:56] * itamarl is now known as Guest2461
[10:57] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[11:00] * Guest2461 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[11:03] * itamarl is now known as Guest2462
[11:03] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[11:07] * Guest2462 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[11:11] * toMeloos (~toMeloos@53568B3D.cm-6-7c.dynamic.ziggo.nl) has joined #ceph
[11:12] <badone> John341: is it running the same kernel it was running before the reboot?
[11:13] <badone> I've seen it before, the kernel gets upgraded but then the machine doesn't get rebooted for months and when it does, all of a sudden it's running a different kernel and things go pear shaped
[11:14] <badone> so it could be that, could be hw, could be some other component or config that got changed
[11:14] * itamarl is now known as Guest2464
[11:15] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[11:19] * itamarl is now known as Guest2465
[11:19] * Guest2464 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[11:19] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[11:20] <John341> badone: on half of my servers, 18osds and 4 journals, I see that drive ordering sometimes get scrambled for some strange reason. It seems to be more evident where hwraid and PERC has been used to do a RAID1 for OS. Maybe I should avoid using the hwraid and just to a MD-raid during installations?
[11:20] <John341> Its extremely annoying when device namings change
[11:21] <badone> John341: is you raid just for the OS disk?
[11:21] <badone> You don't *need* it for OSD or journal disks
[11:21] <badone> although some people still use it..
[11:22] <John341> badone: just for the OS yes. not for OSD.
[11:23] <badone> 'k, fair enough
[11:23] * Guest2465 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[11:23] <John341> I don't understand how centos7, device names can get scrambled tho
[11:23] <John341> the device indexing changes.
[11:23] <badone> John341: you can use UUID instead of the device name
[11:24] <badone> John341: I think it depends in what order the kernel finds the devices
[11:24] * Discovery (~Discovery@109.235.52.8) has joined #ceph
[11:25] <John341> how do I do a disk zap, prepare activate etc, with uuid?
[11:25] <badone> you can specify a device by device name, LABEL, UUID, ... and I think there is another but I can't rememer what it is right now
[11:25] <badone> John341: you don't. Ceph shouldn't care if a device name changes
[11:25] <badone> it detects which is which
[11:26] <badone> John341: ceph-disk list should identify what device belongs where
[11:26] * swami1 (~swami@27.7.165.149) Quit (Ping timeout: 480 seconds)
[11:26] <badone> John341: but if something else tries to use the same device all bets are off
[11:27] * itamarl is now known as Guest2466
[11:27] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[11:30] <John341> badone: osd.8 was down and I've tried to redeploy it. the osd was /dev/sdp1, I've zapped sdp. the journal in /var/lib/ceph/osd/ceph-8/journal was pointing as /dev/sdc1 which you can tell here is not one of my 4 paritioned-journals, http://pastebin.ca/3656840
[11:31] * Guest2466 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[11:31] <John341> badone: sdc here in this disk list is a 1.8T journal which is not how the drives were initially configured
[11:33] <John341> badone: sda1-5,sdb1-5,sdc1,sdd1-5 should had been the initially prepared and activated journal paritions
[11:33] <badone> John341: I don't understand your set-up and am heading off for the night but comparing "ceph-disk-list" with current device listings and historical data should help you work out what is going on
[11:33] * itamarl is now known as Guest2467
[11:33] <badone> you really need to fix Illegal Request errors before you do anything
[11:34] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[11:35] <badone> John341: anyway, good luck with it
[11:35] <John341> badone: okay, no worries. I will try to zap the drive, and rebuild with prepare and activate
[11:36] <John341> badone: thx
[11:36] <badone> John341: don't forget to try and track down those errors, I doubt very much they'll fix themselves
[11:37] * Guest2467 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[11:41] * EinstCrazy (~EinstCraz@61.165.253.133) has joined #ceph
[11:44] * EinstCrazy (~EinstCraz@61.165.253.133) Quit (Remote host closed the connection)
[11:46] * jargonmonk (jargonmonk@triton.blinkenshell.org) has joined #ceph
[11:52] * fdmanana (~fdmanana@2001:8a0:6e0c:6601:80fe:bd46:5d83:1f20) has joined #ceph
[11:54] * jargonmonk (jargonmonk@triton.blinkenshell.org) Quit (Quit: WeeChat 1.4)
[11:58] * itamarl is now known as Guest2468
[11:58] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:02] * itamarl is now known as Guest2469
[12:02] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:03] * Guest2468 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:03] * newbie (~kvirc@host217-114-156-249.pppoe.mark-itt.net) has joined #ceph
[12:04] * praveen (~praveen@122.172.37.2) Quit (Read error: Connection reset by peer)
[12:04] * EinstCrazy (~EinstCraz@61.165.253.133) has joined #ceph
[12:06] * Guest2469 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:07] * itamarl is now known as Guest2470
[12:07] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:10] * Guest2470 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:12] * EinstCra_ (~EinstCraz@61.165.253.133) has joined #ceph
[12:12] * EinstCrazy (~EinstCraz@61.165.253.133) Quit (Read error: Connection reset by peer)
[12:15] * itamarl is now known as Guest2471
[12:15] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:17] * Guest2471 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:18] * Mraedis (~dontron@safersocial5.lax.webair.com) has joined #ceph
[12:19] * praveen (~praveen@122.172.37.2) has joined #ceph
[12:20] * jargonmonk (jargonmonk@triton.blinkenshell.org) has joined #ceph
[12:21] * itamarl is now known as Guest2472
[12:21] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:23] * jargonmonk (jargonmonk@triton.blinkenshell.org) Quit (Quit: WeeChat 1.4)
[12:23] * fdmanana (~fdmanana@2001:8a0:6e0c:6601:80fe:bd46:5d83:1f20) Quit (Ping timeout: 480 seconds)
[12:24] * Guest2472 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:25] * EinstCra_ (~EinstCraz@61.165.253.133) Quit (Ping timeout: 480 seconds)
[12:27] * itamarl is now known as Guest2473
[12:27] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:29] * Guest2473 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:32] * itamarl is now known as Guest2474
[12:33] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:35] * Guest2474 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:37] * itamarl is now known as Guest2475
[12:37] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:41] * Guest2475 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:41] * itamarl is now known as Guest2476
[12:41] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:44] * rwheeler (~rwheeler@bzq-82-81-161-51.red.bezeqint.net) Quit (Quit: Leaving)
[12:45] * Guest2476 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:45] * jargonmonk (jargonmonk@triton.blinkenshell.org) has joined #ceph
[12:45] * itamarl is now known as Guest2477
[12:45] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:48] * Mraedis (~dontron@7EXAAACEE.tor-irc.dnsbl.oftc.net) Quit ()
[12:49] * Guest2477 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:51] * itamarl is now known as Guest2478
[12:51] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[12:53] * Guest2478 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[12:57] * itamarl is now known as Guest2479
[12:57] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:01] * itamarl is now known as Guest2480
[13:01] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:01] * Guest2479 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:05] * Guest2480 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:08] * itamarl is now known as Guest2482
[13:09] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:12] * Guest2482 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:12] * praveen (~praveen@122.172.37.2) Quit (Read error: Connection reset by peer)
[13:12] * itamarl is now known as Guest2483
[13:13] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:17] * Guest2483 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:20] * itamarl is now known as Guest2484
[13:20] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:23] * Guest2484 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:24] * itamarl is now known as Guest2485
[13:24] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:27] * jargonmonk (jargonmonk@triton.blinkenshell.org) Quit (Quit: WeeChat 1.4)
[13:28] * Guest2485 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:28] * ccourtaut (~ccourtaut@157.173.31.93.rev.sfr.net) Quit (Quit: I'll be back!)
[13:30] * ccourtaut (~ccourtaut@93.31.173.157) has joined #ceph
[13:33] * itamarl is now known as Guest2487
[13:33] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:37] * itamarl is now known as Guest2488
[13:37] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:38] * Guest2487 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:41] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[13:41] * Guest2488 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:44] * fdmanana (~fdmanana@2001:8a0:6e0c:6601:80fe:bd46:5d83:1f20) has joined #ceph
[13:47] * jargonmonk (jargonmonk@triton.blinkenshell.org) has joined #ceph
[13:47] * praveen (~praveen@122.172.37.2) has joined #ceph
[13:51] * itamarl is now known as Guest2489
[13:51] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[13:53] * EinstCrazy (~EinstCraz@61.165.253.133) has joined #ceph
[13:56] * Guest2489 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[13:59] * itamarl is now known as Guest2491
[13:59] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[14:04] * fdmanana (~fdmanana@2001:8a0:6e0c:6601:80fe:bd46:5d83:1f20) Quit (Ping timeout: 480 seconds)
[14:04] * Guest2491 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[14:04] * itamarl is now known as Guest2492
[14:05] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[14:07] * yanzheng (~zhyan@125.70.22.67) has joined #ceph
[14:09] * Guest2492 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[14:09] * toMeloos (~toMeloos@53568B3D.cm-6-7c.dynamic.ziggo.nl) Quit (Ping timeout: 480 seconds)
[14:14] * Concubidated1 (~cube@122.103.163.63.ap.gmobb-fix.jp) has joined #ceph
[14:14] * Concubidated (~cube@122.103.163.63.ap.gmobb-fix.jp) Quit (Read error: Connection reset by peer)
[14:17] * EinstCrazy (~EinstCraz@61.165.253.133) Quit (Remote host closed the connection)
[14:23] * jargonmonk (jargonmonk@triton.blinkenshell.org) Quit (Quit: WeeChat 1.4)
[14:25] * jargonmonk (jargonmonk@triton.blinkenshell.org) has joined #ceph
[14:28] * itamarl is now known as Guest2495
[14:29] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[14:29] * jargonmonk (jargonmonk@triton.blinkenshell.org) Quit ()
[14:30] * jargonmonk (jargonmonk@triton.blinkenshell.org) has joined #ceph
[14:31] * Guest2495 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[14:33] * jargonmonk (jargonmonk@triton.blinkenshell.org) Quit ()
[14:34] * Concubidated (~cube@ai126251021121.23.access-internet.ne.jp) has joined #ceph
[14:35] * jargonmonk (jargonmonk@triton.blinkenshell.org) has joined #ceph
[14:37] * jargonmonk (jargonmonk@triton.blinkenshell.org) Quit ()
[14:37] * yanzheng (~zhyan@125.70.22.67) Quit (Quit: This computer has gone to sleep)
[14:38] * jargonmonk (jargonmonk@triton.blinkenshell.org) has joined #ceph
[14:39] * yanzheng (~zhyan@125.70.22.67) has joined #ceph
[14:41] * Concubidated1 (~cube@122.103.163.63.ap.gmobb-fix.jp) Quit (Ping timeout: 480 seconds)
[14:41] * kuku (~kuku@112.203.51.69) has joined #ceph
[14:42] * kuku (~kuku@112.203.51.69) Quit (Remote host closed the connection)
[14:42] * praveen (~praveen@122.172.37.2) Quit (Read error: Connection reset by peer)
[14:43] * kuku (~kuku@112.203.51.69) has joined #ceph
[14:48] * itamarl is now known as Guest2497
[14:49] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[14:49] * yanzheng (~zhyan@125.70.22.67) Quit (Quit: This computer has gone to sleep)
[14:53] * Guest2497 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[14:54] * jargonmonk (jargonmonk@00022354.user.oftc.net) Quit (Quit: WeeChat 1.4)
[14:55] * jargonmonk (jargonmonk@00022354.user.oftc.net) has joined #ceph
[14:57] * yanzheng (~zhyan@125.70.22.67) has joined #ceph
[14:59] * kuku (~kuku@112.203.51.69) Quit (Remote host closed the connection)
[15:00] * kuku (~kuku@112.203.51.69) has joined #ceph
[15:01] * itamarl is now known as Guest2498
[15:01] * itamarl (~itamarl@194.90.7.244) has joined #ceph
[15:01] * itamarl (~itamarl@194.90.7.244) Quit ()
[15:03] * Guest2498 (~itamarl@194.90.7.244) Quit (Ping timeout: 480 seconds)
[15:06] * praveen (~praveen@122.172.37.2) has joined #ceph
[15:14] * karnan (~karnan@106.51.138.205) has joined #ceph
[15:15] <John341> I try to add an OSD manually, and when I do sudo mkfs -t xfs -f -i size=2048 /dev/sdm1 I get, mkfs.xfs: /dev/sdm1 contains a mounted filesystem. How do I fix this?
[15:16] <John341> I've checked mount, and /proc/mounts , and /etc/mtab, but there's no /dev/sdm mounted.
[15:16] <John341> Not sure why it complains about the device being mounted.
[15:18] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) has joined #ceph
[15:24] * karnan (~karnan@106.51.138.205) Quit (Quit: Leaving)
[15:24] * kuku (~kuku@112.203.51.69) Quit (Read error: Connection reset by peer)
[15:25] * kuku (~kuku@112.203.51.69) has joined #ceph
[15:29] * markl (~mark@knm.org) has joined #ceph
[15:44] * newbie (~kvirc@host217-114-156-249.pppoe.mark-itt.net) Quit (Ping timeout: 480 seconds)
[15:48] * ylmson (~Kealper@46.166.190.226) has joined #ceph
[15:51] * swami1 (~swami@27.7.165.149) has joined #ceph
[15:52] * penguinRaider (~KiKo@23.27.206.118) Quit (Ping timeout: 480 seconds)
[16:01] * penguinRaider (~KiKo@23.27.206.118) has joined #ceph
[16:12] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) Quit (Quit: neurodrone_)
[16:17] * praveen (~praveen@122.172.37.2) Quit (Read error: Connection reset by peer)
[16:18] * ylmson (~Kealper@46.166.190.226) Quit ()
[16:24] * kuku (~kuku@112.203.51.69) Quit (Remote host closed the connection)
[16:31] * yanzheng (~zhyan@125.70.22.67) Quit (Quit: This computer has gone to sleep)
[16:33] * penguinRaider (~KiKo@23.27.206.118) Quit (Ping timeout: 480 seconds)
[16:33] * praveen (~praveen@122.172.37.2) has joined #ceph
[16:38] * xarses_ (~xarses@c-73-202-191-48.hsd1.ca.comcast.net) has joined #ceph
[16:45] * xarses (~xarses@c-73-202-191-48.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[16:50] * penguinRaider (~KiKo@23.27.206.118) has joined #ceph
[17:12] * zc00gii (~poller@server1.dxxmail.com) has joined #ceph
[17:42] * zc00gii (~poller@61TAAAEE9.tor-irc.dnsbl.oftc.net) Quit ()
[17:45] * fdmanana (~fdmanana@2001:8a0:6e0c:6601:80fe:bd46:5d83:1f20) has joined #ceph
[17:47] * danieagle (~Daniel@191.205.90.5) has joined #ceph
[17:55] * kalleeen (~Tarazed@85.248.227.165) has joined #ceph
[18:03] * Discovery (~Discovery@109.235.52.8) Quit (Read error: Connection reset by peer)
[18:03] * mustafam (~mustafa@37.239.255.254) has joined #ceph
[18:04] <mustafam> Hi All, after upgrading to 10.2.2, I lost access to rbd
[18:04] * penguinRaider (~KiKo@23.27.206.118) Quit (Ping timeout: 480 seconds)
[18:04] <mustafam> I use mirror cache in front of ec pools
[18:13] * newbie (~kvirc@host217-114-156-249.pppoe.mark-itt.net) has joined #ceph
[18:13] * shaunm (~shaunm@74.83.215.100) Quit (Read error: Connection reset by peer)
[18:18] * penguinRaider (~KiKo@23.27.206.118) has joined #ceph
[18:19] * Concubidated (~cube@ai126251021121.23.access-internet.ne.jp) Quit (Quit: Leaving.)
[18:24] * fdmanana (~fdmanana@2001:8a0:6e0c:6601:80fe:bd46:5d83:1f20) Quit (Ping timeout: 480 seconds)
[18:25] * kalleeen (~Tarazed@61TAAAEF4.tor-irc.dnsbl.oftc.net) Quit ()
[18:29] * praveen (~praveen@122.172.37.2) Quit (Read error: Connection reset by peer)
[18:30] * toMeloos (~toMeloos@53568B3D.cm-6-7c.dynamic.ziggo.nl) has joined #ceph
[18:37] * rotbeard (~redbeard@2a02:908:df13:bb00:24c4:6857:4097:491) has joined #ceph
[18:47] * penguinRaider (~KiKo@23.27.206.118) Quit (Ping timeout: 480 seconds)
[18:56] * penguinRaider (~KiKo@23.27.206.118) has joined #ceph
[18:58] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Quit: Leaving.)
[18:58] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) has joined #ceph
[19:06] * praveen (~praveen@122.172.37.2) has joined #ceph
[19:13] * danieagle (~Daniel@191.205.90.5) Quit (Quit: Obrigado por Tudo! :-) inte+ :-))
[19:17] * stiopa (~stiopa@cpc73832-dals21-2-0-cust453.20-2.cable.virginm.net) has joined #ceph
[19:23] * praveen (~praveen@122.172.37.2) Quit (Ping timeout: 480 seconds)
[19:26] * ircuser-1 (~Johnny@158.183-62-69.ftth.swbr.surewest.net) has joined #ceph
[19:34] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) has joined #ceph
[19:35] * mustafam (~mustafa@37.239.255.254) Quit (Ping timeout: 480 seconds)
[19:37] * Jamana (~Zombiekil@37.203.209.10) has joined #ceph
[19:38] * jargonmonk (jargonmonk@00022354.user.oftc.net) Quit (Quit: WeeChat 1.4)
[19:38] * praveen (~praveen@122.171.110.99) has joined #ceph
[19:38] * swami1 (~swami@27.7.165.149) Quit (Quit: Leaving.)
[19:40] * jargonmonk (jargonmonk@00022354.user.oftc.net) has joined #ceph
[19:41] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) Quit (Quit: neurodrone_)
[20:07] * Jamana (~Zombiekil@37.203.209.10) Quit ()
[20:07] * kazer (~kazer@2601:643:8104:ba60:eea8:6bff:fef8:449) Quit (Read error: Connection reset by peer)
[20:07] * Xylios (~Quackie@justus.impium.de) has joined #ceph
[20:09] * voxadam (~adam@2601:1c2:1300:f91e:68e4:b11c:d102:8198) has joined #ceph
[20:37] * Xylios (~Quackie@7EXAAACKQ.tor-irc.dnsbl.oftc.net) Quit ()
[20:37] * Jebula (~BillyBobJ@tor-exit-4.all.de) has joined #ceph
[20:38] * i_m (~ivan.miro@nat-5-carp.hcn-strela.ru) Quit (Ping timeout: 480 seconds)
[21:07] * Jebula (~BillyBobJ@4PRAAADVN.tor-irc.dnsbl.oftc.net) Quit ()
[21:10] * noahw (~noahw@eduroam-169-233-233-213.ucsc.edu) has joined #ceph
[21:15] <Psi-Jack> Hmmmm.. So now, it's time for me to figure out how to move my OSD journals to SSD. heh
[21:19] <Psi-Jack> Hmmm. Wow.. pveceph setup 5GB journals for each OSD. heh
[21:25] * penguinRaider (~KiKo@23.27.206.118) Quit (Ping timeout: 480 seconds)
[21:30] * GeoTracer (~Geoffrey@41.77.153.99) Quit (Ping timeout: 480 seconds)
[21:31] * GeoTracer (~Geoffrey@41.77.153.99) has joined #ceph
[21:31] * rendar (~I@host104-158-dynamic.44-79-r.retail.telecomitalia.it) Quit (Ping timeout: 480 seconds)
[21:33] * acctor (~acctor@c-73-170-8-35.hsd1.ca.comcast.net) Quit (Quit: acctor)
[21:35] * penguinRaider (~KiKo@23.27.206.118) has joined #ceph
[21:39] * kuku (~kuku@112.203.51.69) has joined #ceph
[21:40] * kuku (~kuku@112.203.51.69) Quit ()
[21:40] <The_Ball> Should the pgmap version constantly be going upwards?
[21:40] <The_Ball> I'm almost at v5m
[21:41] * kuku (~kuku@112.203.51.69) has joined #ceph
[21:41] <The_Ball> I thought it would only be when the placement groups actually change, by reweights or OSDs going in/out or stuff like that
[21:41] * rotbeard (~redbeard@2a02:908:df13:bb00:24c4:6857:4097:491) Quit (Quit: Leaving)
[21:42] * CobraKhan007 (~MonkeyJam@64.ip-37-187-176.eu) has joined #ceph
[21:43] * kuku (~kuku@112.203.51.69) Quit (Remote host closed the connection)
[21:46] <Psi-Jack> Hmm, according to this http://lists.ceph.com/pipermail/ceph-users-ceph.com/2014-August/042085.html -- I shouldn't need to dd the old journal to the new journal disk? Just set the osd to noout, stop it, flush it, point it to the new one, link it, and mkjournal, then bring it back up?
[21:46] <The_Ball> Psi-Jack, yeah, done that many times
[21:46] <Psi-Jack> Heh, cool.
[21:47] <Psi-Jack> Then I could resize my HDD's to regain that 5GB that was put on the disk for journals. heh
[21:47] <The_Ball> here's what I do when switching over to SSD journal: http://pastebin.com/N8zBC7Je
[21:47] * praveen (~praveen@122.171.110.99) Quit (Read error: Connection reset by peer)
[21:48] <Psi-Jack> Cool. Thanks. :)
[21:48] <The_Ball> you must be hardpressed for space? I've left the partition there in case I need to use it stand-alone... for flexibility
[21:48] * moon (~moon@tunnel.greenhost.nl) has joined #ceph
[21:48] <Psi-Jack> Hmmm, you're using actual systemd to manage ceph stuff eh? My systems are using the lsb-init wrapper like base install of proxmox ve does. Which is annoying because they use annoying unit-names that look generated.
[21:49] <Psi-Jack> Eh, I have 10TB total amongst all drives, so not bad, but still, I expect little to no growth except replacement drives.
[21:49] <Psi-Jack> But, that is a good point still. In case the SSD does die.
[21:50] <The_Ball> I'm running on centos which uses systemd
[21:50] * Psi-Jack nods.
[21:51] <Psi-Jack> Yeah. Proxmox VE is based on Debian, and I'm running Ceph along-side Proxmox VE on the same hosts. It's not /perfect/ but it works.
[21:51] <Psi-Jack> Allows me better HA than I had before at the very least.
[21:51] <The_Ball> as long as you're having fun :)
[21:51] <Psi-Jack> Yeah. :)
[21:51] <Psi-Jack> And better disk distribution, so I'm not limited to running certain VMs only on certain physical hosts.
[21:53] <Psi-Jack> Though, I'm thinking of re-doing the ceph init stuff to utilize systemd and disabling the ceph init.d script. Because it just makes more sense.
[21:54] <Psi-Jack> I had a ceph cluster before that used systemd, so that was pretty awesome. :)
[21:54] <Psi-Jack> Though, I'll wait for my cluster to finish repairing. Re-upped my MDS data volume from a size 1 back to a size 2 now that I have full allocation of sisks.
[21:54] <Psi-Jack> disks*
[21:55] <Psi-Jack> Migration from LVM+GlusterFS (Gluster wasn't really much used anymore because it was unreliable), was a VERY slow process.
[21:56] <Psi-Jack> And then.. During the process, I thought I'd try various things with different RBD pools, that ended up shooting myself in the foot.
[21:56] <Psi-Jack> And over-utilized too many pgs.
[21:57] * rendar (~I@host104-158-dynamic.44-79-r.retail.telecomitalia.it) has joined #ceph
[21:58] * bjornar_ (~bjornar@ti0099a430-0410.bb.online.no) has joined #ceph
[22:00] <Psi-Jack> And just a note, you should avoid using variable names as UPPERCASE. :)
[22:09] <Psi-Jack> The_Ball: This is what I made of your script, to allow input, with minimal validation: https://paste.linux-help.org/view/3e8de88f
[22:09] <Psi-Jack> :)
[22:10] <The_Ball> cool bananas
[22:11] <Psi-Jack> I made one change to the lvcreate, which I recommend, -Cy for contiguous.
[22:12] * CobraKhan007 (~MonkeyJam@61TAAAEJ6.tor-irc.dnsbl.oftc.net) Quit ()
[22:12] * Maza1 (~Peaced@7EXAAACNR.tor-irc.dnsbl.oftc.net) has joined #ceph
[22:15] <Psi-Jack> Heh, one more thing I hate about Debian. They brought systemd, but only just barely.
[22:15] * bjornar_ (~bjornar@ti0099a430-0410.bb.online.no) Quit (Ping timeout: 480 seconds)
[22:17] * praveen (~praveen@122.171.110.99) has joined #ceph
[22:17] * pdrakeweb (~pdrakeweb@cpe-71-74-153-111.neo.res.rr.com) has joined #ceph
[22:19] <The_Ball> -Cy is good yes, but doesn't really matter for SSD
[22:19] <Psi-Jack> Hmmm, I suppose. :)
[22:22] * pdrakewe_ (~pdrakeweb@cpe-71-74-153-111.neo.res.rr.com) Quit (Ping timeout: 480 seconds)
[22:28] <Psi-Jack> Heh, well, I created all my systemd units and targets...
[22:31] <Psi-Jack> Hmmm.
[22:31] <Psi-Jack> What does the ceph-disk@.service do?
[22:32] <Psi-Jack> Ahh, that's from something later than hammer, re-looking at the branches. :)
[22:40] <The_Ball> Haven't seen that service
[22:40] <Psi-Jack> Yeah. Uses ceph-disk with the descrition: Ceph disk activation %f.. I just don't know what %f is intended to be.
[22:41] <Psi-Jack> ExecStart=/bin/sh -c 'flock /var/lock/ceph-disk /usr/sbin/ceph-disk --verbose --log-stdout trigger --sync %f'
[22:42] * Maza1 (~Peaced@7EXAAACNR.tor-irc.dnsbl.oftc.net) Quit ()
[22:43] <Psi-Jack> The problem is, it doesn't seem to use a ceph-disk "command", at all. I'm guessing in later versions than hammer, it doesn't need to. According to the manpage, it prepares a disk or drive for a ceph OSD, creates a GPT parition, etyc.
[22:43] <Psi-Jack> ceph-disk itself that is.
[22:44] <T1> afaik it for auto setup/teardown of disks for the OSDs on the node
[22:44] <T1> its even
[22:44] * Psi-Jack nods.
[22:44] * dnunez (~dnunez@c-73-38-0-185.hsd1.ma.comcast.net) has joined #ceph
[22:44] <Psi-Jack> So in my case, not really needed to convert from lsb-init to systemd init.
[22:45] <Psi-Jack> I took all the .target's, and @.service's though, and cloned them to fit my setup, and can eventually switch to it.
[22:46] <T1> there are a lot of automation tools and scripts available - some are used by all, while some are real "niche" tools
[22:46] <Psi-Jack> Heh
[22:46] <Psi-Jack> I'm actually kind of wodnering how Proxmox VE's pveceph makes the OSD's mounted at boot. I see nothing about it.
[22:47] <T1> in a large setup with more OSDs can you can count to on your fingers in a few minutes there if probably a need for udev to trigger all sorts of stuff to happen
[22:47] <T1> there is even
[22:47] <T1> (dammit I cant write properly tonight)
[22:47] * moon (~moon@tunnel.greenhost.nl) Quit (Ping timeout: 480 seconds)
[22:48] <Psi-Jack> Ahh, the ceph init script itself handles actual mounting it seems.
[22:48] <Psi-Jack> Somehow...
[22:48] <T1> yes, the sysv init script does all sorts of strage stuff
[22:48] <T1> strange even
[22:48] <T1> ffs..
[22:49] <Psi-Jack> heh
[22:52] <Psi-Jack> Welp, when my cephfs recovery is complete, I will start changing things to systemd, and move my journal to ssd.
[22:53] <Psi-Jack> Still have 20% degradation, 17% misplaced, from changing my cephfs_data pool to size 2 (from 1).
[22:54] <Psi-Jack> Until then. Thanks. Off to destroy the lawn in this horrible summer hell. :)
[22:57] <T1> well.. that should be expected from effectivly doubbling your data and requirering everything to be copied and written to new OSDs in whatever your CRUSH map says.. :)
[23:01] <Hatsjoe> Does anyone know how exactly the crush weight is calculated when using 'ceph-deploy create'? When adding an OSD manually, you have to provide a value yourself, but there is no documentation available as to how it is calculated.
[23:02] <T1> sorry, no idea
[23:02] * bjornar_ (~bjornar@ti0099a430-0410.bb.online.no) has joined #ceph
[23:07] * praveen (~praveen@122.171.110.99) Quit (Read error: Connection reset by peer)
[23:12] * djidis__ (~Maza@7EXAAACPC.tor-irc.dnsbl.oftc.net) has joined #ceph
[23:22] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) has joined #ceph
[23:29] * bjornar_ (~bjornar@ti0099a430-0410.bb.online.no) Quit (Ping timeout: 480 seconds)
[23:42] * djidis__ (~Maza@7EXAAACPC.tor-irc.dnsbl.oftc.net) Quit ()
[23:46] * praveen (~praveen@122.171.110.99) has joined #ceph
[23:49] * efirs (~firs@c-50-185-70-125.hsd1.ca.comcast.net) has joined #ceph
[23:53] * neurodrone_ (~neurodron@pool-100-35-225-168.nwrknj.fios.verizon.net) Quit (Quit: neurodrone_)
[23:58] * newbie (~kvirc@host217-114-156-249.pppoe.mark-itt.net) Quit (Ping timeout: 480 seconds)

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