Perl 6 - the future is here, just unevenly distributed

IRC log for #gluster, 2015-04-08

| Channels | #gluster index | Today | | Search | Google Search | Plain-Text | summary

All times shown according to UTC.

Time Nick Message
00:14 halfinhalfout joined #gluster
00:16 T3 joined #gluster
00:39 MugginsM joined #gluster
00:56 T3 joined #gluster
01:05 bala joined #gluster
01:21 MugginsM joined #gluster
02:00 tdasilva joined #gluster
02:03 khanku joined #gluster
02:04 lezo joined #gluster
02:05 fyxim joined #gluster
02:06 sankarshan_away joined #gluster
02:07 JPaul joined #gluster
02:07 ultrabizweb joined #gluster
02:14 bharata-rao joined #gluster
02:43 kdhananjay joined #gluster
02:54 owlbot joined #gluster
02:59 nangthang joined #gluster
03:08 julim joined #gluster
03:29 Pupeno joined #gluster
03:31 kumar joined #gluster
03:44 lalatenduM joined #gluster
03:49 ira joined #gluster
03:58 hchiramm joined #gluster
03:58 kkeithley1 joined #gluster
03:59 purpleidea joined #gluster
04:03 kkeithley1 joined #gluster
04:06 sage joined #gluster
04:07 kanagaraj joined #gluster
04:10 RameshN joined #gluster
04:11 rafi joined #gluster
04:16 atinmu joined #gluster
04:18 nishanth joined #gluster
04:25 ppai joined #gluster
04:34 anoopcs joined #gluster
04:35 meghanam joined #gluster
04:36 jiffin joined #gluster
04:42 smohan joined #gluster
04:43 ndarshan joined #gluster
04:46 punit_ joined #gluster
04:53 punit_ glusterfs slower throughput
04:53 punit_ is there any way to tweak glusterfs for good performance ??
04:55 punit_ in my ENV all are SSD disk but the performance is slower then SATA disk
04:56 harish_ joined #gluster
04:56 punit_ JoeJulian: is there any way to improve the performance of glusterfs ??
04:56 nbalacha joined #gluster
05:03 hagarth joined #gluster
05:06 soumya_ joined #gluster
05:07 Guest55680 joined #gluster
05:13 nshaikh joined #gluster
05:14 schandra joined #gluster
05:15 thangnn_ joined #gluster
05:16 karnan joined #gluster
05:19 pppp joined #gluster
05:20 deepakcs joined #gluster
05:32 itisravi joined #gluster
05:33 T3 joined #gluster
05:38 Manikandan_ joined #gluster
05:40 glusterbot News from newglusterbugs: [Bug 1209729] Disperse volume: Fix memory leak in truncate calls <https://bugzilla.redhat.co​m/show_bug.cgi?id=1209729>
05:41 hchiramm_ joined #gluster
05:42 spandit joined #gluster
05:45 hagarth joined #gluster
05:47 poornimag joined #gluster
05:47 gem joined #gluster
05:47 lalatenduM joined #gluster
05:48 pppp joined #gluster
05:50 anil joined #gluster
05:50 dusmant joined #gluster
05:50 soumya_ joined #gluster
06:00 vimal joined #gluster
06:02 kdhananjay joined #gluster
06:12 punit_ is there any one can help me to improve performance of glusterfs ??
06:13 kshlm joined #gluster
06:17 _NiC joined #gluster
06:22 jtux joined #gluster
06:24 poornimag joined #gluster
06:24 punit_ kshlm: i am getting very slow performance....slower then SATA...is there any tweks to impreove it... ??
06:28 soumya_ joined #gluster
06:32 kshlm punit_, I'm not really familiar with performance tweaks for GlusterFS. Maybe someone else could help you.
06:33 T3 joined #gluster
06:37 overclk joined #gluster
06:43 atalur joined #gluster
06:45 punit_ kshlm:is it possible to let me know who can help me in this tweaking ??
06:46 Anjana joined #gluster
06:56 jotun joined #gluster
06:57 Pupeno joined #gluster
06:57 Pupeno joined #gluster
06:57 smohan_ joined #gluster
06:58 [Enrico] joined #gluster
07:00 poornimag joined #gluster
07:04 anrao joined #gluster
07:04 dusmant joined #gluster
07:04 DV joined #gluster
07:04 atinmu joined #gluster
07:15 nangthang joined #gluster
07:15 nbalacha joined #gluster
07:16 raghu joined #gluster
07:23 sas_ joined #gluster
07:23 RaSTar hagarth: This is the syncop patch I was talking about, http://review.gluster.org/#/c/9859/
07:24 RaSTar There are many patches in review which can cause this patch to rebase  again..
07:24 RaSTar can we merge this soon?
07:26 fsimonce joined #gluster
07:33 atinmu joined #gluster
07:34 dusmant joined #gluster
07:34 T3 joined #gluster
07:39 hagarth RaSTar: I tired doing that yesterday .. will do that in a bit
07:40 glusterbot News from newglusterbugs: [Bug 1209752] BitRot :- info about bitd is not shown in volume status <https://bugzilla.redhat.co​m/show_bug.cgi?id=1209752>
07:47 poornimag joined #gluster
07:54 smohan joined #gluster
08:09 purpleidea joined #gluster
08:09 purpleidea joined #gluster
08:09 pppp joined #gluster
08:11 liquidat joined #gluster
08:11 nbalacha joined #gluster
08:18 Slashman joined #gluster
08:24 ktosiek joined #gluster
08:31 owlbot joined #gluster
08:33 liquidat joined #gluster
08:34 [Enrico] joined #gluster
08:35 bene2 joined #gluster
08:35 T3 joined #gluster
08:38 soumya_ joined #gluster
08:41 glusterbot News from newglusterbugs: [Bug 1209790] DHT rebalance :Incorrect error handling <https://bugzilla.redhat.co​m/show_bug.cgi?id=1209790>
08:43 bala joined #gluster
08:48 LebedevRI joined #gluster
08:49 dusmant joined #gluster
08:50 jmarley joined #gluster
08:51 meghanam joined #gluster
08:51 poornimag joined #gluster
08:52 Anjana joined #gluster
08:58 _NiC joined #gluster
09:00 hagarth raghu: on #gluster-dev ?
09:00 ndarshan joined #gluster
09:02 DV joined #gluster
09:05 atinmu joined #gluster
09:08 Prilly joined #gluster
09:11 glusterbot News from newglusterbugs: [Bug 1209799] BitRot :- not able to reset 'scrub-throttle' and 'scrub-frequency' to defalut values using reset command <https://bugzilla.redhat.co​m/show_bug.cgi?id=1209799>
09:13 ctria joined #gluster
09:17 anil joined #gluster
09:18 anrao joined #gluster
09:21 _PiGreco_ left #gluster
09:27 purpleidea joined #gluster
09:32 dusmant joined #gluster
09:36 T3 joined #gluster
09:39 deniszh joined #gluster
09:41 glusterbot News from newglusterbugs: [Bug 1209818] BitRot :- volume info should not show 'features.scrub: resume' if scrub process is resumed <https://bugzilla.redhat.co​m/show_bug.cgi?id=1209818>
09:43 atalur joined #gluster
09:45 atinmu joined #gluster
09:47 hagarth joined #gluster
09:50 Pupeno joined #gluster
09:55 atalur joined #gluster
09:57 karnan joined #gluster
09:58 Prilly joined #gluster
10:04 T0aD joined #gluster
10:09 pppp joined #gluster
10:11 glusterbot News from newglusterbugs: [Bug 1209831] peer probe fails because of missing glusterd.info file <https://bugzilla.redhat.co​m/show_bug.cgi?id=1209831>
10:14 ghenry joined #gluster
10:19 soumya_ joined #gluster
10:22 poornimag joined #gluster
10:23 RameshN joined #gluster
10:36 T3 joined #gluster
10:41 harish_ joined #gluster
10:41 glusterbot News from newglusterbugs: [Bug 1209843] [Backup]: Crash observed when multiple sessions were created for the same volume <https://bugzilla.redhat.co​m/show_bug.cgi?id=1209843>
10:45 aravindavk joined #gluster
10:49 nbalacha joined #gluster
10:59 hchiramm_ kdhananjay++
10:59 glusterbot hchiramm_: kdhananjay's karma is now 1
10:59 hchiramm_ lalatenduM,++
10:59 glusterbot hchiramm_: lalatenduM,'s karma is now 1
10:59 hchiramm_ lalatenduM++
10:59 glusterbot hchiramm_: lalatenduM's karma is now 8
11:03 soumya_ joined #gluster
11:17 dusmant joined #gluster
11:31 Debloper joined #gluster
11:37 T3 joined #gluster
11:41 ndevos REMINDER: in 20 minutes from now, the weekly Gluster Community Meeting will start in #gluster-meeting
11:41 glusterbot News from newglusterbugs: [Bug 1209869] xdata in FOPs should always be valid and never junk <https://bugzilla.redhat.co​m/show_bug.cgi?id=1209869>
11:43 soumya_ joined #gluster
11:58 hagarth joined #gluster
12:00 ndevos REMINDER: the weekly Gluster Community Meeting starts now in #gluster-meeting
12:01 jdarcy joined #gluster
12:02 rjoseph joined #gluster
12:06 schandra joined #gluster
12:08 nshaikh joined #gluster
12:10 anoopcs joined #gluster
12:12 nshaikh left #gluster
12:27 jarrpa joined #gluster
12:38 T3 joined #gluster
12:43 rjoseph joined #gluster
12:45 wkf joined #gluster
12:47 Manikandan_ joined #gluster
12:49 _Bryan_ joined #gluster
12:50 jarrpa left #gluster
12:50 Prilly joined #gluster
12:54 DV__ joined #gluster
13:02 halfinhalfout joined #gluster
13:06 overclk joined #gluster
13:11 julim joined #gluster
13:17 raghu joined #gluster
13:22 Gill joined #gluster
13:27 klaas joined #gluster
13:29 Gill left #gluster
13:29 georgeh-LT2 joined #gluster
13:32 bene2 joined #gluster
13:37 dgandhi joined #gluster
13:39 T3 joined #gluster
13:41 plarsen joined #gluster
13:43 ctria joined #gluster
13:44 dusmant joined #gluster
13:51 gnudna joined #gluster
13:51 gnudna left #gluster
13:52 gnudna joined #gluster
13:53 halfinhalfout joined #gluster
13:56 hamiller joined #gluster
14:03 jobewan joined #gluster
14:04 hellomichibye joined #gluster
14:04 kdhananjay joined #gluster
14:04 hellomichibye when I run gluster peer probe the glusterd gets killed with this error : https://gist.github.com/micha​elwittig/a9e9aabccbe131e0c43b
14:06 anil joined #gluster
14:09 nbalacha joined #gluster
14:12 wushudoin joined #gluster
14:15 lid3213 joined #gluster
14:15 lid3213 hey, I am running gluster server 3.6.2 and everytime after reboot the node is in "peer rejected" state.
14:15 lid3213 running ubuntu 14.04 lts
14:19 _shaps_ joined #gluster
14:27 dusmant joined #gluster
14:27 deepakcs joined #gluster
14:31 deniszh joined #gluster
14:39 T3 joined #gluster
14:40 coredump joined #gluster
14:42 ipmango joined #gluster
14:42 bennyturns joined #gluster
14:47 lpabon joined #gluster
15:00 dbruhn joined #gluster
15:02 squizzi joined #gluster
15:03 lid3213 even worse, I get a peer rejected once i restart the glusterfs-server, I just realized
15:06 ipmango_ joined #gluster
15:08 virusuy joined #gluster
15:13 ipmango joined #gluster
15:14 T3 joined #gluster
15:18 liquidat joined #gluster
15:27 lexi2 joined #gluster
15:31 lexi2_ joined #gluster
15:38 maveric_amitc_ joined #gluster
15:39 eberg joined #gluster
15:43 corretico joined #gluster
15:45 DV__ joined #gluster
15:46 Manikandan joined #gluster
15:58 kshlm joined #gluster
16:18 soumya_ joined #gluster
16:45 hchiramm joined #gluster
16:54 julim joined #gluster
16:59 firemanxbr joined #gluster
17:00 firemanxbr joined #gluster
17:01 firemanxbr hey guys I'm have this problema with my gluster cluster
17:04 RameshN joined #gluster
17:04 hchiramm joined #gluster
17:06 firemanxbr http://ur1.ca/k4rlu
17:06 firemanxbr I can help me ?
17:12 chirino joined #gluster
17:14 JoeJulian firemanxbr: According to what you've shown us, you can help you by bringing up enough servers to regain quorum.
17:14 firemanxbr JoeJulian, humm its possible
17:15 firemanxbr JoeJulian, I have 4 gluster servers, but only one is online
17:15 firemanxbr JoeJulian, but I have one volume like this:
17:16 firemanxbr http://ur1.ca/k4ro6
17:17 hagarth firemanxbr: can you not bring up the other servers online?
17:18 firemanxbr I believed that only one server available this volume is ennough, but no
17:18 firemanxbr hagarth, I'm trying :D
17:19 hagarth firemanxbr: ok :)
17:19 firemanxbr energy fail in data center :) I hate this datacenter :D
17:19 JoeJulian firemanxbr: it *could* be ok, but your volume has server-quorum set.
17:19 alpha01_ joined #gluster
17:20 firemanxbr JoeJulian, I could remove this set ?
17:22 JoeJulian I do not think so. Changing the setting would fail because the CLI could not update all the servers.
17:24 Rapture joined #gluster
17:24 nbalacha joined #gluster
17:25 firemanxbr JoeJulian, I realized, I believed that a volume 1 x 4 replicated permitirme would return the service with only one server, but it seems that is not possible, right?
17:26 JoeJulian It is possible, but you have it configured to be not possible.
17:26 RameshN joined #gluster
17:28 firemanxbr JoeJulian, okay, I believed this config are necessary for oVirt volumes
17:28 firemanxbr JoeJulian, thnkz for tips :D
17:30 papamoose joined #gluster
17:32 papamoose What does everyone do to monitor glusterfs volumes?
17:32 JoeJulian I prefer reading tea leaves.
17:32 papamoose thats the sense i got from my internet searches this morning.
17:32 JoeJulian but seriously, the answer is as diverse as the people that use it.
17:33 JoeJulian I've used icinga and consul.
17:36 purpleidea joined #gluster
17:36 purpleidea joined #gluster
17:36 firemanxbr papamoose, I'm using Zabbix
17:36 * firemanxbr Zabbix great tool :D
17:40 hagarth there's also gluster-nagios
17:40 soumya joined #gluster
17:41 purpleidea joined #gluster
17:43 glusterbot News from newglusterbugs: [Bug 1210029] Error in QEMU logs of VM, while using QEMU's native driver for glusterfs <https://bugzilla.redhat.co​m/show_bug.cgi?id=1210029>
17:47 lalatenduM joined #gluster
17:48 vipulnayyar joined #gluster
17:58 cornus_ammonis joined #gluster
18:03 o5k_ joined #gluster
18:07 thisisdave joined #gluster
18:07 purpleidea joined #gluster
18:07 purpleidea joined #gluster
18:23 Rapture joined #gluster
18:27 halfinhalfout I use http://exchange.nagios.org/directory/Plugins/Sys​tem-Metrics/File-System/GlusterFS-checks/details for monitoring gluster volumes
18:28 papamoose halfinhalfout: i found that too. Would you recommend it?
18:29 papamoose and it seems i also found your git repo in that first comment.
18:30 halfinhalfout works well for us. I forked it at https://github.com/customink​/nagios-nrpe-check_glusterfs and integrated some patches from some other folks
18:32 anrao joined #gluster
18:35 halfinhalfout there are some pull requests there that I haven't yet taken the time to review, though
18:36 halfinhalfout so, you may find it requires little tweaks for you
18:36 papamoose is this still a thing: 'GlusterFs hooks present in /var/lib/glusterd/hooks/'
18:37 papamoose seems so: /var/lib/glusterd/hooks/1/gsync-create/post/S56glusterd-geo-rep-create-post.sh
18:37 papamoose that exists in my 3.6.2 install.
18:39 rotbeard joined #gluster
18:46 papamoose I guess I need to modify my original question about how people monitor glusterfs volumes... Does everything just come down to writing a script that parses 'gluster volume info' or is there a better way?
18:51 JoeJulian parsing "gluster volume status all detail", watching logs for ' C ', monitoring "gluster volume heal $vol info" (can't use "all" there unfortunately).
18:53 papamoose damn. i was hoping for some object oriented api like thing... gluster.volume.status(volname) or something similar.
18:54 JoeJulian You can add --xml to get xml output and parse that in your scripting language of preference.
18:59 mango left #gluster
18:59 papamoose thats seems pretty great, i'll check that out.
18:59 ipmango_ joined #gluster
18:59 ipmango_ left #gluster
19:00 papamoose cool, though the man page doesnt seem to mention it.
19:02 alpha01_ joined #gluster
19:04 ipmango_ joined #gluster
19:06 purpleidea joined #gluster
19:06 purpleidea joined #gluster
19:09 firemanxbr hey guys
19:09 firemanxbr my 4 servers go back
19:10 firemanxbr but my gluster have this error:
19:10 firemanxbr http://ur1.ca/k4s8g
19:10 firemanxbr I'm using CentOS 7.1 and Gluster glusterfs-server-3.6.2-1.el7.x86_64
19:11 firemanxbr anyone can help me ?
19:11 semiosis firemanxbr: you need to allow insecure ports.... see ,,(options)
19:11 glusterbot firemanxbr: See config options and their defaults with 'gluster volume set help'; you can see the current value of an option, if it has been modified, with 'gluster volume info'; see also this page about undocumented options: http://goo.gl/mIAe4E
19:12 semiosis gluster volume set VOL_NAME server.allow-insecure on
19:12 firemanxbr semiosis, humm I'm try set this option :D
19:12 semiosis add 'option rpc-auth-allow-insecure on' to /etc/glusterfs/glusterd.vol and restart glusterfs-server/glusterd
19:14 firemanxbr semiosis, I need run in all server or only one ?
19:14 Manikandan joined #gluster
19:15 semiosis all
19:15 firemanxbr semiosis, thnkz
19:15 semiosis yw
19:24 firemanxbr semiosis, don't run :(
19:24 victori joined #gluster
19:24 firemanxbr in my principal server this report for systemctl:
19:25 firemanxbr http://ur1.ca/k4sar
19:26 firemanxbr peer status and volume status:
19:26 firemanxbr http://ur1.ca/k4sax
19:26 semiosis firemanxbr: start your volume
19:28 firemanxbr semiosis, dont run: http://ur1.ca/k4sb4
19:28 semiosis firemanxbr: check brick logs to see why they are not starting
19:28 firemanxbr in second server this error:
19:28 firemanxbr volume start: vol-ctdb: failed: Locking failed on 10.0.126.10. Please check log file for details.
19:28 semiosis /var/log/glusterfs/bricks
19:29 semiosis interesting
19:29 _NiC joined #gluster
19:29 semiosis stop all glusterd then start all again?
19:29 firemanxbr yep
19:30 firemanxbr http://ur1.ca/k4sbh
19:30 firemanxbr very strange this error
19:30 semiosis [2015-04-08 19:21:55.682935] E [posix.c:5626:init] 0-vol-ctdb-posix: Extended attribute trusted.glusterfs.volume-id is absent
19:30 semiosis this suggests the underlying brick fs is missing.  is your disk mounted?
19:31 firemanxbr semiosis, no, this disk is up and access perfectly
19:31 semiosis well the volume-id xattr is missing
19:31 semiosis so the brick will not start
19:32 JoeJulian every time someone has told me that the brick was mounted and working perfectly, it wasn't.
19:33 semiosis or "the network is fiiiine!"
19:33 firemanxbr lol, exactly, I believed
19:34 purpleidea joined #gluster
19:34 purpleidea joined #gluster
19:34 firemanxbr exist any command for restaure this attributes ?
19:35 firemanxbr semiosis, but in this gluster peer status network result in Connected
19:36 firemanxbr semiosis, I believe this network not a problem
19:38 semiosis firemanxbr: check the ,,(extended attributes of all the brick roots in the volume
19:38 semiosis ,,(extended attributes)
19:38 glusterbot (#1) To read the extended attributes on the server: getfattr -m .  -d -e hex {filename}, or (#2) For more information on how GlusterFS uses extended attributes, see this article: http://pl.atyp.us/hekafs.org/index.php/​2011/04/glusterfs-extended-attributes/
19:38 JoeJulian firemanxbr: If you write an ,,(extended attribute) to a directory, how can you remove that attribute? Can it just disappear all on it's own?
19:38 glusterbot firemanxbr: To read the extended attributes on the server: getfattr -m .  -d -e hex {filename}
19:39 JoeJulian Assume it cannot just disappear. It MUST be somewhere. Where is it? It's either on the filesystem that's used as a brick, or it's on the filesystem on which the brick was *supposed* to be mounted.
19:39 firemanxbr semiosis, JoeJulian I restore this bricks for one tape loader
19:40 JoeJulian Aha.
19:40 firemanxbr I believe my backup make using tar
19:40 firemanxbr I try restore using xfsdump and xfsrestore
19:41 semiosis if you did not backup & restore the extended attributes, you will have problems
19:42 firemanxbr my dream that gluster store this atributes in log files or config files, simple backup and simple restore, but no problem I have more 16 hours for return this datas :(
19:43 firemanxbr semiosis, I have other backup using dd for all devices, but is very slow
19:43 semiosis that should work better
19:43 firemanxbr semiosis, I think yes :D
19:44 semiosis next time you use tar, preserve xattrs... http://www.cyberciti.biz/faq/linux-tar-​rsync-preserving-acls-selinux-contexts/
19:45 firemanxbr semiosis, very good thanks guys, too JoeJulian
19:46 semiosis yw
19:46 semiosis @next
19:46 glusterbot semiosis: Error: You must be registered to use this command. If you are already registered, you must either identify (using the identify command) or add a hostmask matching your current hostmask (using the "hostmask add" command).
19:46 semiosis ,,(next)
19:46 glusterbot Another satisfied customer... NEXT!
19:48 semiosis glusterbot: whoami
19:48 glusterbot semiosis: I don't recognize you. You can message me either of these two commands: "user identify <username> <password>" to log in or "user register <username> <password>" to register.
19:58 Prilly joined #gluster
20:02 halfinhalfout1 joined #gluster
20:04 halfinhalfout2 joined #gluster
20:05 purpleidea joined #gluster
20:08 virusuy joined #gluster
20:09 badone_ joined #gluster
20:11 chirino joined #gluster
20:28 DV joined #gluster
20:42 halfinhalfout joined #gluster
20:59 hchiramm joined #gluster
21:02 gnudna left #gluster
21:06 tg2 > I restore this bricks for one tape loader
21:06 tg2 sweet baby jesus
21:06 tg2 LTO life
21:26 bene2 joined #gluster
21:26 fubada purpleidea: hi, do you know how I could set the owner/group on the mount dir with puppet-gluster
21:27 dgandhi joined #gluster
21:27 fubada I cant have an external File resource on that path because gluster::mount manages the directory, and gluster::mount lacks user/group settings
21:32 hchiramm joined #gluster
21:39 wkf joined #gluster
21:41 bene2 joined #gluster
21:44 glusterbot News from newglusterbugs: [Bug 1195415] glusterfsd core dumps when cleanup and socket disconnect routines race <https://bugzilla.redhat.co​m/show_bug.cgi?id=1195415>
21:44 glusterbot News from newglusterbugs: [Bug 1210085] GlusterFS 4.0 <https://bugzilla.redhat.co​m/show_bug.cgi?id=1210085>
21:48 halfinhalfout1 joined #gluster
21:57 papamoose JoeJulian: do you know if there are any more options like '--xml'.
21:57 glusterbot papamoose: ''s karma is now -1
21:59 bene3 joined #gluster
22:10 Gill joined #gluster
22:20 T3 joined #gluster
22:47 MugginsM joined #gluster
22:51 T3 joined #gluster
22:54 JoeJulian papamoose: from: grep 'opt, "' cli/src/cli.c    http://ur1.ca/k4tyw
22:55 JoeJulian You can see more details about those options by reading through the cli_opt_parse function.
23:02 plarsen joined #gluster
23:13 gildub joined #gluster

| Channels | #gluster index | Today | | Search | Google Search | Plain-Text | summary