On Wed, Jan 17, 2018 at 2:20 AM, Nikos Kormpakis <nkorb@xxxxxxxxxxxx> wrote: > On 01/16/2018 12:53 AM, Brad Hubbard wrote: >> On Tue, Jan 16, 2018 at 1:35 AM, Alexander Peters <apeters@xxxxxxxxx> wrote: >>> i created the dump output but it looks very cryptic to me so i can't really make much sense of it. is there anything to look for in particular? >> >> Yes, basically we are looking for any line that ends in "= 34". You >> might also find piping it through c++filt helps. >> >> Something like... >> >> $ c++filt </tmp/ltrace.out|grep "= 34" > > Hello, > we're facing the exact same issue. I added some more info about > our cluster and output from ltrace in [1]. Unfortunately, the strlen lines in that output are expected. Is it possible for me to access the ltrace output file somehow (you could email it directly or use ceph-post-file perhaps)? > > Best regards, > Nikos. > > [1] http://tracker.ceph.com/issues/22351 > >>> >>> i think i am going to read up on how interpret ltrace output... >>> >>> BR >>> Alex >>> >>> ----- Ursprüngliche Mail ----- >>> Von: "Brad Hubbard" <bhubbard@xxxxxxxxxx> >>> An: "Alexander Peters" <alexander.peters@xxxxxxxxx> >>> CC: "Ceph Users" <ceph-users@xxxxxxxxxxxxxx> >>> Gesendet: Montag, 15. Januar 2018 03:09:53 >>> Betreff: Re: radosgw fails with "ERROR: failed to initialize watch: (34) Numerical result out of range" >>> >>> On Mon, Jan 15, 2018 at 11:38 AM, Brad Hubbard <bhubbard@xxxxxxxxxx> wrote: >>>> On Mon, Jan 15, 2018 at 10:38 AM, Alexander Peters >>>> <alexander.peters@xxxxxxxxx> wrote: >>>>> Thanks for the reply - unfortunatly the link you send is behind a paywall so >>>>> at least for now i can’t read it. >>>> >>>> That's why I provided the cause as laid out in that article (pgp num > pg num). >>>> >>>> Do you have any settings in ceph.conf related to pg_num or pgp_num? >>>> >>>> If not, please add your details to http://tracker.ceph.com/issues/22351 >>> >>> Rados can return ERANGE (34) in multiple places so identifying where >>> might be a big step towards working this out. >>> >>> $ ltrace -fo /tmp/ltrace.out /usr/bin/radosgw --cluster ceph --name >>> client.radosgw.ctrl02 --setuser ceph --setgroup ceph -f -d >>> >>> The objective is to find which function(s) return 34. >>> >>>> >>>>> >>>>> output of ceph osd dump shows that pgp num == pg num: >>>>> >>>>> [root@ctrl01 ~]# ceph osd dump >>>>> epoch 142 >>>>> fsid 0e2d841f-68fd-4629-9813-ab083e8c0f10 >>>>> created 2017-12-20 23:04:59.781525 >>>>> modified 2018-01-14 21:30:57.528682 >>>>> flags sortbitwise,recovery_deletes,purged_snapdirs >>>>> crush_version 6 >>>>> full_ratio 0.95 >>>>> backfillfull_ratio 0.9 >>>>> nearfull_ratio 0.85 >>>>> require_min_compat_client jewel >>>>> min_compat_client jewel >>>>> require_osd_release luminous >>>>> pool 1 'glance' replicated size 3 min_size 2 crush_rule 0 object_hash >>>>> rjenkins pg_num 64 pgp_num 64 last_change 119 flags hashpspool stripe_width >>>>> 0 application rbd >>>>> removed_snaps [1~3] >>>>> pool 2 'cinder-2' replicated size 3 min_size 2 crush_rule 0 object_hash >>>>> rjenkins pg_num 64 pgp_num 64 last_change 120 flags hashpspool stripe_width >>>>> 0 application rbd >>>>> removed_snaps [1~3] >>>>> pool 3 'cinder-3' replicated size 3 min_size 2 crush_rule 0 object_hash >>>>> rjenkins pg_num 64 pgp_num 64 last_change 121 flags hashpspool stripe_width >>>>> 0 application rbd >>>>> removed_snaps [1~3] >>>>> pool 4 '.rgw.root' replicated size 3 min_size 2 crush_rule 0 object_hash >>>>> rjenkins pg_num 8 pgp_num 8 last_change 94 owner 18446744073709551615 flags >>>>> hashpspool stripe_width 0 application rgw >>>>> max_osd 3 >>>>> osd.0 up in weight 1 up_from 82 up_thru 140 down_at 79 >>>>> last_clean_interval [23,78) 10.16.0.11:6800/1795 10.16.0.11:6801/1795 >>>>> 10.16.0.11:6802/1795 10.16.0.11:6803/1795 exists,up >>>>> abe33844-6d98-4ede-81a8-a8bdc92dada8 >>>>> osd.1 up in weight 1 up_from 73 up_thru 140 down_at 71 >>>>> last_clean_interval [55,72) 10.16.0.13:6800/1756 10.16.0.13:6804/1001756 >>>>> 10.16.0.13:6805/1001756 10.16.0.13:6806/1001756 exists,up >>>>> 0dab9372-6ffe-4a23-a8b7-4edca3745a2a >>>>> osd.2 up in weight 1 up_from 140 up_thru 140 down_at 133 >>>>> last_clean_interval [31,132) 10.16.0.12:6800/1749 10.16.0.12:6801/1749 >>>>> 10.16.0.12:6802/1749 10.16.0.12:6803/1749 exists,up >>>>> 220bba17-8119-4035-9e43-5b8eaa27562f >>>>> >>>>> >>>>> Am 15.01.2018 um 01:33 schrieb Brad Hubbard <bhubbard@xxxxxxxxxx>: >>>>> >>>>> On Mon, Jan 15, 2018 at 8:34 AM, Alexander Peters >>>>> <alexander.peters@xxxxxxxxx> wrote: >>>>> >>>>> Hello >>>>> >>>>> I am currently experiencing a strange issue with my radosgw. It Fails to >>>>> start and all tit says is: >>>>> [root@ctrl02 ~]# /usr/bin/radosgw --cluster ceph --name >>>>> client.radosgw.ctrl02 --setuser ceph --setgroup ceph -f -d >>>>> 2018-01-14 21:30:57.132007 7f44ddd18e00 0 deferred set uid:gid to 167:167 >>>>> (ceph:ceph) >>>>> 2018-01-14 21:30:57.132161 7f44ddd18e00 0 ceph version 12.2.2 >>>>> (cf0baeeeeba3b47f9427c6c97e2144b094b7e5ba) luminous (stable), process >>>>> (unknown), pid 13928 >>>>> 2018-01-14 21:30:57.556672 7f44ddd18e00 -1 ERROR: failed to initialize >>>>> watch: (34) Numerical result out of range >>>>> 2018-01-14 21:30:57.558752 7f44ddd18e00 -1 Couldn't init storage provider >>>>> (RADOS) >>>>> >>>>> (when started via systemctl it writes the same lines to the logfile) >>>>> >>>>> strange thing is that it is working on an other env that was installed with >>>>> the same set of ansible playbooks. >>>>> OS is CentOS Linux release 7.4.1708 (Core) >>>>> >>>>> Ceph is up and running ( I am currently using it for storing volumes and >>>>> images form Openstack ) >>>>> >>>>> Does anyone have an idea how to debug this? >>>>> >>>>> >>>>> According to https://access.redhat.com/solutions/2778161 this can >>>>> happen if your pgp num is higher than the pg num. >>>>> >>>>> Check "ceph osd dump" output for that possibility. >>>>> >>>>> >>>>> Best Regards >>>>> Alexander >>>>> >>>>> _______________________________________________ >>>>> ceph-users mailing list >>>>> ceph-users@xxxxxxxxxxxxxx >>>>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >>>>> >>>>> >>>>> >>>>> >>>>> -- >>>>> Cheers, >>>>> Brad >>>>> >>>>> >>>> >>>> >>>> >>>> -- >>>> Cheers, >>>> Brad >>> >>> >>> >>> -- >>> Cheers, >>> Brad >> >> >> > > > -- > Nikos Kormpakis - nkorb@xxxxxxxxxxxx > Network Operations Center, Greek Research & Technology Network > Tel: +30 210 7475712 - http://www.grnet.gr > 7, Kifisias Av., 115 23 Athens, Greece > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -- Cheers, Brad _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |