On Wed, Oct 29, 2014 at 1:37 PM, Haomai Wang <haomaiwang@xxxxxxxxx> wrote: > maybe you can run it directly with debug_osd=20/20 and get ending logs > ceph-osd -i 1 -c /etc/ceph/ceph.conf -f > > On Wed, Oct 29, 2014 at 6:34 PM, Andrey Korolyov <andrey@xxxxxxx> wrote: >> On Wed, Oct 29, 2014 at 1:28 PM, Haomai Wang <haomaiwang@xxxxxxxxx> wrote: >>> Thanks! >>> >>> You mean osd.1 exited abrptly without ceph callback trace? >>> Anyone has some ideas about this log? @sage @gregory >>> >>> >>> On Wed, Oct 29, 2014 at 6:19 PM, Andrey Korolyov <andrey@xxxxxxx> wrote: >>>> On Wed, Oct 29, 2014 at 1:11 PM, Haomai Wang <haomaiwang@xxxxxxxxx> wrote: >>>>> Thanks for Andrey, >>>>> >>>>> The attachment OSD.1's log is only these lines? I really can't find >>>>> the detail infos from it? >>>>> >>>>> Maybe you need to improve debug_osd to 20/20? >>>>> >>>>> On Wed, Oct 29, 2014 at 5:25 PM, Andrey Korolyov <andrey@xxxxxxx> wrote: >>>>>> Hi Haomai, all. >>>>>> >>>>>> Today after unexpected power failure one of kv stores (placed on ext4 >>>>>> with default mount options) refused to work. I think that it may be >>>>>> interesting to revive it because it is almost first time among >>>>>> hundreds of power failures (and their simulations) when data store got >>>>>> broken. >>>>>> >>>>>> Strace: >>>>>> http://xdel.ru/downloads/osd1.strace.gz >>>>>> >>>>>> Debug output with 20-everything level: >>>>>> http://xdel.ru/downloads/osd1.out >>>>> >>>>> >>>>> >>>>> -- >>>>> Best Regards, >>>>> >>>>> Wheat >>>> >>>> >>>> Unfortunately that`s all I`ve got. Updated osd1.out to show an actual >>>> cli args and entire output - it ends abruptly without last newline and >>>> without any valuable output. >>> >>> >>> >>> -- >>> Best Regards, >>> >>> Wheat >> >> >> With log-file specified, it adds just following line at very end: >> >> 2014-10-29 13:29:57.437776 7ffa562c9840 -1 ** ERROR: osd init failed: >> (22) Invalid argument >> >> the stdout printing seems a bit broken and do not print this at all >> (and store output part is definitely is not detailed enough to make >> any conclusions, and even file a bug). CCing Sage/Greg. > > > > -- > Best Regards, > > Wheat -f does not print the last line to stderr either. Ok, it looks like very minor separate bug, but I remembering its appearance long before, so but as bug remains, probably it does not bother anyone - the stderr output is less usual for debugging purposes. _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |