Ok, confirmed. Letting dbench work on different subfolders makes it work fine.
In terms of log messages:
I would love to monitor for problems with gluster. Failing self heals in the 
logs might not really be a problem per-se, any suggestions of what else I could 
parse the logs for?

Cheers,
Marc

On 19.02.2013, at 23:32, Anand Avati <[email protected]> wrote:

> They were just self-heal double-checks performed in the lookup path, as we 
> perform the initial lookup unlocked for performance reasons. Those lines by 
> themselves do not indicate anything harmful (yet). I admit the log messages 
> could have been better though!
> 
> Avati
> 
> On Tue, Feb 19, 2013 at 2:20 PM, Marc Seeger <[email protected]> wrote:
> I'll give it a try. Isn't it somewhat concerning that this would heal to 
> missing gfids and failing self-heals though?
> 
> On 19.02.2013, at 21:22, Anand Avati <[email protected]> wrote:
> 
>> We run dbench in the pre-commit script for every patch. Looks like you are 
>> running dbench on the same directory from multiple clients. Is that even 
>> supposed to work? Did you instead lunch to run each dbench within their own 
>> subdirectory?
>> 
>> Avati
>> 
>> On Tue, Feb 19, 2013 at 12:07 PM, Marc Seeger <[email protected]> wrote:
>> To test gluster's behavior under heavy load, I'm currently doing this on two 
>> machines sharing a common /mnt/gfs gluster mount:
>> 
>> ssh bal-6.example.com apt-get install dbench && dbench 6 -t 60 -D /mnt/gfs
>> ssh bal-7.example.com apt-get install dbench && dbench 6 -t 60 -D /mnt/gfs
>> 
>> 
>> One of the processes usually dies pretty quickly like this:
>> 
>> [608] open /mnt/gfs/clients/client5/~dmtmp/PWRPNT/PCBENCHM.PPT failed for 
>> handle 10003 (No such file or directory)
>> (610) ERROR: handle 10003 was not found,
>> Child failed with status 1
>> 
>> 
>> And the logs are full of things like this (ignore the initial timestamp, 
>> that's from our logging):
>> 
>> [2013-02-19 14:38:38.714493] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  data missing-entry gfid self-heal failed on 
>> /clients/client5/~dmtmp/PM/MOVED.DOC, 
>> [2013-02-19 14:38:38.724494] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client3/~dmtmp, 
>> [2013-02-19 14:38:38.734495] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  data missing-entry gfid self-heal failed on 
>> /clients/client4/~dmtmp/PM/EVENTS.DOC, 
>> [2013-02-19 14:38:38.734495] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  data missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/PM/MOVED.DOC, 
>> [2013-02-19 14:38:38.734495] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  data missing-entry gfid self-heal failed on 
>> /clients/client1/~dmtmp/PM/MOVED.DOC, 
>> [2013-02-19 14:38:38.734495] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  data missing-entry gfid self-heal failed on 
>> /clients/client0/~dmtmp/PM/MOVED.DOC, 
>> [2013-02-19 14:38:38.734495] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client4/~dmtmp/PM,  [build-2 
>> system.rb:340], I,  
>> [2013-02-19T14:39:50.189970 #20802]  INFO -- : 
>> [2013-02-19 14:38:36.041890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /, 
>> [2013-02-19 14:38:36.041890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /, 
>> [2013-02-19 14:38:36.041890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /, 
>> [2013-02-19 14:38:36.041890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /, 
>> [2013-02-19 14:38:36.041890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /, 
>> [2013-02-19 14:38:36.051890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients, 
>> [2013-02-19 14:38:36.071890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2, 
>> [2013-02-19 14:38:36.071890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3, 
>> [2013-02-19 14:38:36.071890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client2, 
>> [2013-02-19 14:38:36.081890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client3, 
>> [2013-02-19 14:38:36.091890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp, 
>> [2013-02-19 14:38:36.091890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp, 
>> [2013-02-19 14:38:36.101890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client2/~dmtmp, 
>> [2013-02-19 14:38:36.101890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client3/~dmtmp, 
>> [2013-02-19 14:38:36.111890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/WORD, 
>> [2013-02-19 14:38:36.111890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/WORD, 
>> [2013-02-19 14:38:36.131890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client2/~dmtmp/WORD, 
>> [2013-02-19 14:38:36.141890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client3/~dmtmp/WORD, 
>> [2013-02-19 14:38:36.151890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/WORD/CHAP10.DOC, 
>> [2013-02-19 14:38:36.151890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/WORD/CHAP10.DOC, 
>> [2013-02-19 14:38:36.161890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/WORD/BASEMACH.DOC, 
>> [2013-02-19 14:38:36.161890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/WORD/BASEMACH.DOC, 
>> [2013-02-19 14:38:36.171890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entr [build-2 system.rb:340], I,  
>> [2013-02-19T14:39:50.189970 #20802]  INFO -- : y missing-entry gfid 
>> self-heal failed on /clients/client2/~dmtmp/WORD/FACTS.DOC, 
>> [2013-02-19 14:38:36.181890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/WORD/FACTS.DOC, 
>> [2013-02-19 14:38:36.201890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/EXCEL, 
>> [2013-02-19 14:38:36.201890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/EXCEL, 
>> [2013-02-19 14:38:36.201890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client2/~dmtmp/EXCEL, 
>> [2013-02-19 14:38:36.201890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client3/~dmtmp/EXCEL, 
>> [2013-02-19 14:38:36.211890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client0/~dmtmp, 
>> [2013-02-19 14:38:36.211890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/EXCEL/PCMAGCD.XLS, 
>> [2013-02-19 14:38:36.211890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/EXCEL/PCMAGCD.XLS, 
>> [2013-02-19 14:38:36.241890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/EXCEL/SALES.XLS, 
>> [2013-02-19 14:38:36.241890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/EXCEL/SALES.XLS, 
>> [2013-02-19 14:38:36.271890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/PWRPNT, 
>> [2013-02-19 14:38:36.271890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/PWRPNT, 
>> [2013-02-19 14:38:36.281890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client2/~dmtmp/PWRPNT, 
>> [2013-02-19 14:38:36.281890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  entry self-heal failed on /clients/client3/~dmtmp/PWRPNT, 
>> [2013-02-19 14:38:36.291890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/PWRPNT/PCBENCHM.PPT, 
>> [2013-02-19 14:38:36.311890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/PWRPNT/PCBENCHM.PPT, 
>> [2013-02-19 14:38:36.351890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/PWRPNT/ZD16.BMP, 
>> [2013-02-19 14:38:36.351890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client3/~dmtmp/PWRPNT/ZD16.BMP, 
>> [2013-02-19 14:38:36.381890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid self-heal failed on 
>> /clients/client2/~dmtmp/PWRPNT/PPTOOLS1.PPA, 
>> [2013-02-19 14:38:36.391890] E 
>> [afr-self-heal-common.c:2160:afr_self_heal_completion_cbk] 0-replicate0: 
>> background  meta-data data entry missing-entry gfid sel [build-2 
>> system.rb:340]
>> 
>> 
>> 
>> Any ideas? Can somebody confirm this happens for them too?
>> 
>> The setup is ubuntu lucid machines running 3.3.1 from this PPA: 
>> https://launchpad.net/~semiosis/+archive/ubuntu-glusterfs-3.3
>> 
>> 
>> _______________________________________________
>> Gluster-users mailing list
>> [email protected]
>> http://supercolony.gluster.org/mailman/listinfo/gluster-users
>> 
> 
> 

_______________________________________________
Gluster-users mailing list
[email protected]
http://supercolony.gluster.org/mailman/listinfo/gluster-users

Reply via email to