On Sat, Oct 12, 2019 at 1:10 AM Kenneth Waegeman <kenneth.waege...@ugent.be>
wrote:
> Hi all,
>
> After solving some pg inconsistency problems, my fs is still in
> trouble. my mds's are crashing with this error:
>
>
> > -5> 2019-10-11 19:02:55.375 7f2d39f10700 1 mds.1.564276 rejoin_start
> > -4> 2019-10-11 19:02:55.385 7f2d3d717700 5 mds.beacon.mds01
> > received beacon reply up:rejoin seq 5 rtt 1.01
> > -3> 2019-10-11 19:02:55.495 7f2d39f10700 1 mds.1.564276
> > rejoin_joint_start
> > -2> 2019-10-11 19:02:55.505 7f2d39f10700 5 mds.mds01
> > handle_mds_map old map epoch 564279 <= 564279, discarding
> > -1> 2019-10-11 19:02:55.695 7f2d33f04700 -1
> >
> /home/jenkins-build/build/workspace/ceph-build/ARCH/x86_64/AVAILABLE_ARCH/x86_64/AVAILABLE_DIST/centos7/DIST/centos7/MACHINE_SIZE/huge/release/14.2.2/rpm/el7/BUILD/ceph-14.2.2/src/mds/mdstyp
> > es.h: In function 'static void
> > dentry_key_t::decode_helper(std::string_view, std::string&,
> > snapid_t&)' thread 7f2d33f04700 time 2019-10-11 19:02:55.703343
> >
> /home/jenkins-build/build/workspace/ceph-build/ARCH/x86_64/AVAILABLE_ARCH/x86_64/AVAILABLE_DIST/centos7/DIST/centos7/MACHINE_SIZE/huge/release/14.2.2/rpm/el7/BUILD/ceph-14.2.2/src/mds/mdstypes.h:
>
> > 1229: FAILED ceph_assert(i != string::npos
> > )
> >
> > ceph version 14.2.2 (4f8fa0a0024755aae7d95567c63f11d6862d55be)
> > nautilus (stable)
> > 1: (ceph::__ceph_assert_fail(char const*, char const*, int, char
> > const*)+0x14a) [0x7f2d43393046]
> > 2: (ceph::__ceph_assertf_fail(char const*, char const*, int, char
> > const*, char const*, ...)+0) [0x7f2d43393214]
> > 3: (CDir::_omap_fetched(ceph::buffer::v14_2_0::list&,
> > std::map<std::string, ceph::buffer::v14_2_0::list,
> > std::less<std::string>, std::allocator<std::pair<std::string const,
> > ceph::buffer::v14_2_0::list> > >&, bool, int)+0xa68) [0x556a17ec
> > baa8]
> > 4: (C_IO_Dir_OMAP_Fetched::finish(int)+0x54) [0x556a17ee0034]
> > 5: (MDSContext::complete(int)+0x70) [0x556a17f5e710]
> > 6: (MDSIOContextBase::complete(int)+0x16b) [0x556a17f5e9ab]
> > 7: (Finisher::finisher_thread_entry()+0x156) [0x7f2d433d8386]
> > 8: (()+0x7dd5) [0x7f2d41262dd5]
> > 9: (clone()+0x6d) [0x7f2d3ff1302d]
> >
> > 0> 2019-10-11 19:02:55.695 7f2d33f04700 -1 *** Caught signal
> > (Aborted) **
> > in thread 7f2d33f04700 thread_name:fn_anonymous
> >
> > ceph version 14.2.2 (4f8fa0a0024755aae7d95567c63f11d6862d55be)
> > nautilus (stable)
> > 1: (()+0xf5d0) [0x7f2d4126a5d0]
> > 2: (gsignal()+0x37) [0x7f2d3fe4b2c7]
> > 3: (abort()+0x148) [0x7f2d3fe4c9b8]
> > 4: (ceph::__ceph_assert_fail(char const*, char const*, int, char
> > const*)+0x199) [0x7f2d43393095]
> > 5: (ceph::__ceph_assertf_fail(char const*, char const*, int, char
> > const*, char const*, ...)+0) [0x7f2d43393214]
> > 6: (CDir::_omap_fetched(ceph::buffer::v14_2_0::list&,
> > std::map<std::string, ceph::buffer::v14_2_0::list,
> > std::less<std::string>, std::allocator<std::pair<std::string const,
> > ceph::buffer::v14_2_0::list> > >&, bool, int)+0xa68) [0x556a17ec
> > baa8]
> > 7: (C_IO_Dir_OMAP_Fetched::finish(int)+0x54) [0x556a17ee0034]
> > 8: (MDSContext::complete(int)+0x70) [0x556a17f5e710]
> > 9: (MDSIOContextBase::complete(int)+0x16b) [0x556a17f5e9ab]
> > 10: (Finisher::finisher_thread_entry()+0x156) [0x7f2d433d8386]
> > 11: (()+0x7dd5) [0x7f2d41262dd5]
> > 12: (clone()+0x6d) [0x7f2d3ff1302d]
> > NOTE: a copy of the executable, or `objdump -rdS <executable>` is
> > needed to interpret this.
> >
> > [root@mds02 ~]# ceph -s
> > cluster:
> > id: 92bfcf0a-1d39-43b3-b60f-44f01b630e47
> > health: HEALTH_WARN
> > 1 filesystem is degraded
> > insufficient standby MDS daemons available
> > 1 MDSs behind on trimming
> > 1 large omap objects
> >
> > services:
> > mon: 3 daemons, quorum mds01,mds02,mds03 (age 4d)
> > mgr: mds02(active, since 3w), standbys: mds01, mds03
> > mds: ceph_fs:2/2 {0=mds02=up:rejoin,1=mds01=up:rejoin(laggy or
> > crashed)}
> > osd: 535 osds: 533 up, 529 in
> >
> > data:
> > pools: 3 pools, 3328 pgs
> > objects: 376.32M objects, 673 TiB
> > usage: 1.0 PiB used, 2.2 PiB / 3.2 PiB avail
> > pgs: 3315 active+clean
> > 12 active+clean+scrubbing+deep
> > 1 active+clean+scrubbing
> >
> Someone an idea where to go from here ?☺
>
>
looks like omap for dirfrag is corrupted. please check mds log (debug_mds
= 10) to find which omap is corrupted. Basically all omap keys of dirfrag
should be in format xxxx_xxxx.
> Thanks!
>
> K
>
> _______________________________________________
> 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
