On Tue, Sep 29, 2015 at 9:51 PM, Scottix <scot...@gmail.com> wrote: > I'm positive the client I sent you the log is 94. We do have one client > still on 87. > which version of kernel are you using? I found a kernel bug which can cause this issue in 4.1 and later kernels.
Regards Yan, Zheng > > On Tue, Sep 29, 2015, 6:42 AM John Spray <jsp...@redhat.com> wrote: > >> >> Hmm, so apparently a similar bug was fixed in 0.87: Scott, can you >> confirm that your *clients* were 0.94 (not just the servers)? >> >> Thanks, >> John >> >> On Tue, Sep 29, 2015 at 11:56 AM, John Spray <jsp...@redhat.com> wrote: >> >>> Ah, this is a nice clear log! >>> >>> I've described the bug here: >>> http://tracker.ceph.com/issues/13271 >>> >>> In the short term, you may be able to mitigate this by increasing >>> client_cache_size (on the client) if your RAM allows it. >>> >>> John >>> >>> On Tue, Sep 29, 2015 at 12:58 AM, Scottix <scot...@gmail.com> wrote: >>> >>>> I know this is an old one but I got a log in ceph-fuse for it. >>>> I got this on OpenSuse 12.1 >>>> 3.1.10-1.29-desktop >>>> >>>> Using ceph-fuse >>>> ceph version 0.94.3 (95cefea9fd9ab740263bf8bb4796fd864d9afe2b) >>>> >>>> I am running an rsync in the background and then doing a simple ls -la >>>> so the log is large. >>>> >>>> I am guessing this is the problem. The file is there and if I list the >>>> directory again it shows up properly. >>>> >>>> 2015-09-28 16:34:21.548631 7f372effd700 3 client.28239198 ll_lookup >>>> 0x7f370d1b1c50 data.2015-08-23_00-00-00.csv.bz2 >>>> 2015-09-28 16:34:21.548635 7f372effd700 10 client.28239198 _lookup >>>> concluded ENOENT locally for 100009d72a1.head(ref=4 ll_ref=5 cap_refs={} >>>> open={} mode=42775 size=0/0 mtime=2015-09-28 05:57:57.259306 >>>> caps=pAsLsXsFs(0=pAsLsXsFs) COMPLETE parents=0x7f3732ff97c0 0x7f370d1b1c50) >>>> dn 'data.2015-08-23_00-00-00.csv.bz2' >>>> >>>> >>>> [image: Selection_034.png] >>>> >>>> It seems to show up more if multiple things are access the ceph mount, >>>> just my observations. >>>> >>>> Best, >>>> Scott >>>> >>>> On Tue, Mar 3, 2015 at 3:05 PM Scottix <scot...@gmail.com> wrote: >>>> >>>>> Ya we are not at 0.87.1 yet, possibly tomorrow. I'll let you know if >>>>> it still reports the same. >>>>> >>>>> Thanks John, >>>>> --Scottie >>>>> >>>>> >>>>> On Tue, Mar 3, 2015 at 2:57 PM John Spray <john.sp...@redhat.com> >>>>> wrote: >>>>> >>>>>> On 03/03/2015 22:35, Scottix wrote: >>>>>> > I was testing a little bit more and decided to run the >>>>>> cephfs-journal-tool >>>>>> > >>>>>> > I ran across some errors >>>>>> > >>>>>> > $ cephfs-journal-tool journal inspect >>>>>> > 2015-03-03 14:18:54.453981 7f8e29f86780 -1 Bad entry start ptr >>>>>> > (0x2aeb0000f6) at 0x2aeb32279b >>>>>> > 2015-03-03 14:18:54.539060 7f8e29f86780 -1 Bad entry start ptr >>>>>> > (0x2aeb000733) at 0x2aeb322dd8 >>>>>> > 2015-03-03 14:18:54.584539 7f8e29f86780 -1 Bad entry start ptr >>>>>> > (0x2aeb000d70) at 0x2aeb323415 >>>>>> > 2015-03-03 14:18:54.669991 7f8e29f86780 -1 Bad entry start ptr >>>>>> > (0x2aeb0013ad) at 0x2aeb323a52 >>>>>> > 2015-03-03 14:18:54.707724 7f8e29f86780 -1 Bad entry start ptr >>>>>> > (0x2aeb0019ea) at 0x2aeb32408f >>>>>> > Overall journal integrity: DAMAGED >>>>>> >>>>>> I expect this is http://tracker.ceph.com/issues/9977, which is fixed >>>>>> in >>>>>> master. >>>>>> >>>>>> You are in *very* bleeding edge territory here, and I'd suggest using >>>>>> the latest development release if you want to experiment with the >>>>>> latest >>>>>> CephFS tooling. >>>>>> >>>>>> Cheers, >>>>>> John >>>>>> >>>>> >>> >> > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > >
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
