Perl 6 - the future is here, just unevenly distributed

IRC log for #gluster, 2015-07-25

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

All times shown according to UTC.

Time Nick Message
00:18 nangthang joined #gluster
00:18 calavera joined #gluster
00:21 ct joined #gluster
00:22 calavera joined #gluster
00:36 calavera joined #gluster
00:41 calavera joined #gluster
00:54 dgandhi joined #gluster
01:03 wushudoin| joined #gluster
01:33 shyam joined #gluster
01:36 ct The issue mentioned in https://bugzilla.redhat.com/show_bug.cgi?id=1188064 was fixed in 3.6.3, but I'm seeing the same problem with 3.7.2
01:36 glusterbot Bug 1188064: unspecified, unspecified, 3.6.3, bugs, MODIFIED , log files get flooded when removexattr() can't find a specified key or value
01:41 JoeJulian ct: that fix was in the 3.7 branch as of commit bd592f8b8379087604f35c3b377f6e94b9e1697d
01:47 jcastill1 joined #gluster
01:52 shyam joined #gluster
01:52 jcastillo joined #gluster
01:58 harish joined #gluster
01:59 ct JoeJulian: I'm get log entries from client-rpc-fops.c:1300:client3_3_removexattr_cbk when I touch a non existent file
02:08 JoeJulian ct:
02:08 JoeJulian https://github.com/gluster/glusterfs/blob/master/xlators/protocol/client/src/client-rpc-fops.c#L1284-L1294
02:09 JoeJulian oops, that's master.
02:10 JoeJulian https://github.com/gluster/glusterfs/blob/v3.7.2/xlators/protocol/client/src/client-rpc-fops.c#L1291-L1301
02:11 JoeJulian Which says it's a debug if the error is "ENODATA or ENOATTR" otherwise it's warning. So the possibilities are, you're not running 3.7.2 (wrong version installed or you upgraded but didn't restart the bricks) or it's a different problem.
02:11 JoeJulian Or... you have log-level=DEBUG.
02:17 ct JoeJulian: This is a new install for 3.7.2.  I have diagnostics.brick-log-level and diagnostics.client-log-level set to ERROR
02:23 JoeJulian As you can see, an error level log isn't even an option.
02:23 JoeJulian Please show me one entire line of output.
02:25 ct [2015-07-25 02:06:11.206465]  [MSGID: 114031] [client-rpc-fops.c:1300:client3_3_removexattr_cbk] 0-gv0-client-0: remote operation failed: No data available [No data available]
02:28 dgandhi joined #gluster
02:32 plarsen joined #gluster
02:36 JoeJulian ct: hrm... bug
02:37 JoeJulian It's fixed in master but...
02:37 JoeJulian For some reason someone set loglevel=0 which is supposed to be GF_LOG_NONE which one would think means, don't log it.
02:38 JoeJulian Unfortunately that's never tested for and a log level of 0 means: always log this no matter what!
02:47 ct JoeJulian: OK thanks, I'll log a bug report
03:11 TheSeven joined #gluster
03:29 pppp joined #gluster
03:34 nishanth joined #gluster
03:52 spalai joined #gluster
03:52 spalai left #gluster
03:57 jobewan joined #gluster
04:22 anrao joined #gluster
04:31 jiffin joined #gluster
04:33 shyam left #gluster
05:15 glusterbot News from newglusterbugs: [Bug 1246728] Log files get flooded <https://bugzilla.redhat.com/show_bug.cgi?id=1246728>
05:17 harish joined #gluster
05:39 Intensity joined #gluster
05:45 spalai joined #gluster
05:45 spalai left #gluster
06:19 krink joined #gluster
06:37 deniszh joined #gluster
06:38 jwd joined #gluster
06:41 anoopcs akay1, Sorry. this bug fix https://bugzilla.redhat.com/show_bug.cgi?id=1237375 will not be present in 3.7.3. Most probably you can expect the fix in one of the upcoming 3.7.x release.
06:41 glusterbot Bug 1237375: medium, urgent, ---, achiraya, ASSIGNED , Trashcan broken on Distribute-Replicate volume
06:52 ekuric joined #gluster
07:11 haomaiwang joined #gluster
07:22 haomaiwang joined #gluster
07:42 kovshenin joined #gluster
08:42 ekuric joined #gluster
08:42 akay1 thanks, anoopcs
09:29 pppp joined #gluster
09:29 hgowtham joined #gluster
09:32 DV joined #gluster
09:40 anrao joined #gluster
09:53 stultus joined #gluster
09:54 stultus left #gluster
09:54 LebedevRI joined #gluster
10:03 spalai joined #gluster
10:03 spalai left #gluster
10:19 Lee1092 joined #gluster
10:30 kotreshhr joined #gluster
10:34 cleong joined #gluster
10:45 dgandhi joined #gluster
10:50 matclayton joined #gluster
11:08 nishanth joined #gluster
11:17 kotreshhr joined #gluster
11:32 deniszh1 joined #gluster
12:35 TrincaTwik joined #gluster
12:41 hagarth joined #gluster
12:43 kotreshhr left #gluster
12:57 ali_ joined #gluster
13:12 skoduri joined #gluster
13:15 plarsen joined #gluster
13:18 krink joined #gluster
13:22 vikumar joined #gluster
13:23 gem joined #gluster
13:31 edwardm61 joined #gluster
13:34 plarsen joined #gluster
14:22 spalai joined #gluster
14:28 kotreshhr joined #gluster
14:41 liewegas joined #gluster
14:46 liewegas joined #gluster
14:50 liewegas joined #gluster
14:55 liewegas joined #gluster
14:58 mlhess Any tips for increasing performance of reading lots and lots of small files.
14:59 liewegas joined #gluster
15:02 nsoffer joined #gluster
15:04 liewegas joined #gluster
15:05 rp_ joined #gluster
15:09 liewegas joined #gluster
15:11 uebera|| joined #gluster
15:13 rp_ joined #gluster
15:14 liewegas joined #gluster
15:18 liewegas joined #gluster
15:23 liewegas joined #gluster
15:52 matclayton joined #gluster
15:57 harish joined #gluster
16:01 PatNarciso_ mlhess, are you connecting via the nfs client, or the gluster client?   try the nfs client.
16:04 calisto joined #gluster
16:19 side_control joined #gluster
16:36 mlhess PatNarciso if I use the NFS client, I lose the redundancy.
16:39 cholcombe joined #gluster
16:42 TrincaTwik joined #gluster
16:50 smohan joined #gluster
16:56 PatNarciso_ mlhess, I believe JoeJulian has a blog post related to increasing small file performance.
17:02 jcastill1 joined #gluster
17:04 JoeJulian @php
17:04 glusterbot JoeJulian: (#1) php calls the stat() system call for every include. This triggers a self-heal check which makes most php software slow as they include hundreds of small files. See http://joejulian.name/blog/optimizing-web-performance-with-glusterfs/ for details., or (#2) It could also be worth mounting fuse with glusterfs --attribute-timeout=HIGH --entry-timeout=HIGH --negative-timeout=HIGH --fopen-keep-cache
17:04 JoeJulian Also a lot of work was done in 3.7 toward that end.
17:07 jcastillo joined #gluster
17:21 TrincaTwik joined #gluster
17:22 maveric_amitc_ joined #gluster
17:32 PatNarciso_ whats the ideal way to human read a brick changelog?
17:35 tquinn joined #gluster
17:35 spcmastertim joined #gluster
17:57 patnarciso_ joined #gluster
17:59 pppp joined #gluster
18:10 PatNarciso_ yah... I'm having trouble searching for the right term here... 'changelog' is related to the advancement of each version of gluster...
18:13 bennyturns joined #gluster
18:17 JoeJulian PatNarciso_: the changelog translator is used for geo-replication to keep track of which files need re-rsynced. The changes within a replica are tracked with ,,(extended attributes).
18:17 glusterbot PatNarciso_: (#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/
18:18 matclayton joined #gluster
18:19 JoeJulian There's no versioning of changes or journaling, except in new-style-replication which I'm not sure is even something that can be enabled yet.
18:25 anrao joined #gluster
18:34 * PatNarciso_ is attempting to... 'repair' a broken volume.  looking for clues in an old volume where gfid-labeled, attribute-cleared files belong.
18:36 PatNarciso_ thanks for the references.  at this point, everything helps.
18:37 PatNarciso_ when I'm done with my current process -- I'll have a handful of files that I dunno there destination path... and, grep'n thru the changelog's with the gfid may provide a clue.
18:48 glusterbot News from newglusterbugs: [Bug 1246782] marker: fix memory freeing order <https://bugzilla.redhat.com/show_bug.cgi?id=1246782>
18:58 bennyturns joined #gluster
19:07 vimal joined #gluster
19:21 smohan joined #gluster
19:24 nsoffer joined #gluster
19:26 TrincaTwik joined #gluster
19:47 kotreshhr left #gluster
19:55 aaronott joined #gluster
20:08 free_amitc_ joined #gluster
20:10 DV joined #gluster
20:19 cleong joined #gluster
20:34 side_control joined #gluster
20:38 julim joined #gluster
21:10 JoeJulian (for me) file a bug
21:10 glusterbot https://bugzilla.redhat.com/enter_bug.cgi?product=GlusterFS
21:20 glusterbot News from newglusterbugs: [Bug 1246794] GF_LOG_NONE logs always <https://bugzilla.redhat.com/show_bug.cgi?id=1246794>
22:51 cholcombe joined #gluster
23:08 RedW joined #gluster
23:10 BeerLover joined #gluster
23:10 BeerLover hello
23:10 glusterbot BeerLover: Despite the fact that friendly greetings are nice, please ask your question. Carefully identify your problem in such a way that when a volunteer has a few minutes, they can offer you a potential solution. These are volunteers, so be patient. Answers may come in a few minutes, or may take hours. If you're still in the channel, someone will eventually offer an answer.
23:44 twisted` joined #gluster
23:55 jcastill1 joined #gluster

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