8 Jun
2020
8 Jun
'20
3:37 p.m.
Hi Harald,
was this exact OSD suffering from "ceph_assert(h->file->fnode.ino != 1)"?
Could you please collect extended log with debug-bluefs set ot 20?
Thanks,
Igor
On 6/8/2020 4:48 PM, Harald Staub wrote:
> This is again about our bad cluster, with far too many objects. Now
> another OSD crashes immediately at startup:
>
> /build/ceph-14.2.8/src/os/bluestore/KernelDevice.cc: 944: FAILED
> ceph_assert(is_valid_io(off, len))
> 1: (ceph::__ceph_assert_fail(char const*, char const*, int, char
> const*)+0x152) [0x5601938e0e92]
> 2: (ceph::__ceph_assertf_fail(char const*, char const*, int, char
> const*, char const*, ...)+0) [0x5601938e106d]
> 3: (KernelDevice::read(unsigned long, unsigned long,
> ceph::buffer::v14_2_0::list*, IOContext*, bool)+0x8e0) [0x560193f2ae90]
> 4: (BlueFS::_read(BlueFS::FileReader*, BlueFS::FileReaderBuffer*,
> unsigned long, unsigned long, ceph::buffer::v14_2_0::list*,
> char*)+0x4f6) [0x560193ee0506]
> 5: (BlueFS::_replay(bool, bool)+0x489) [0x560193ee14e9]
> 6: (BlueFS::mount()+0x219) [0x560193ef4319]
> 7: (BlueStore::_open_bluefs(bool)+0x41) [0x560193de2281]
> 8: (BlueStore::_open_db(bool, bool, bool)+0x88c) [0x560193de347c]
> 9: (BlueStore::_open_db_and_around(bool)+0x44) [0x560193dfa134]
> 10: (BlueStore::_mount(bool, bool)+0x584) [0x560193e4a804]
> 11: (OSD::init()+0x3b7) [0x56019398f957]
> 12: (main()+0x3cdb) [0x5601938e85cb]
> 13: (__libc_start_main()+0xe7) [0x7f54cdf1bb97]
> 14: (_start()+0x2a) [0x56019391b08a]
>
> 2020-06-08 13:44:52.063 7f54d169ec00 -1 *** Caught signal (Aborted) **
> in thread 7f54d169ec00 thread_name:ceph-osd
>
> ceph version 14.2.8 (2d095e947a02261ce61424021bb43bd3022d35cb)
> nautilus (stable)
> 1: (()+0x12890) [0x7f54cf286890]
> 2: (gsignal()+0xc7) [0x7f54cdf38e97]
> 3: (abort()+0x141) [0x7f54cdf3a801]
> 4: (ceph::__ceph_assert_fail(char const*, char const*, int, char
> const*)+0x1a3) [0x5601938e0ee3]
> 5: (ceph::__ceph_assertf_fail(char const*, char const*, int, char
> const*, char const*, ...)+0) [0x5601938e106d]
> 6: (KernelDevice::read(unsigned long, unsigned long,
> ceph::buffer::v14_2_0::list*, IOContext*, bool)+0x8e0) [0x560193f2ae90]
> 7: (BlueFS::_read(BlueFS::FileReader*, BlueFS::FileReaderBuffer*,
> unsigned long, unsigned long, ceph::buffer::v14_2_0::list*,
> char*)+0x4f6) [0x560193ee0506]
> 8: (BlueFS::_replay(bool, bool)+0x489) [0x560193ee14e9]
> 9: (BlueFS::mount()+0x219) [0x560193ef4319]
> 10: (BlueStore::_open_bluefs(bool)+0x41) [0x560193de2281]
> 11: (BlueStore::_open_db(bool, bool, bool)+0x88c) [0x560193de347c]
> 12: (BlueStore::_open_db_and_around(bool)+0x44) [0x560193dfa134]
> 13: (BlueStore::_mount(bool, bool)+0x584) [0x560193e4a804]
> 14: (OSD::init()+0x3b7) [0x56019398f957]
> 15: (main()+0x3cdb) [0x5601938e85cb]
> 16: (__libc_start_main()+0xe7) [0x7f54cdf1bb97]
> 17: (_start()+0x2a) [0x56019391b08a]
> NOTE: a copy of the executable, or `objdump -rdS <executable>` is
> needed to interpret this.
>
> There was a preceding assert (earlier written about):
>
> /build/ceph-14.2.8/src/os/bluestore/BlueFS.cc: 2261: FAILED
> ceph_assert(h->file->fnode.ino != 1)
>
> Any ideas that I could try to save this OSDs?
>
> Cheers
> Harry
> _______________________________________________
> ceph-users mailing list -- ceph-users(a)ceph.io
> To unsubscribe send an email to ceph-users-leave(a)ceph.io