Actions
Bug #3049
closedmds: startup+suicide failure, MDLog::handle_journaler_write_error
% Done:
0%
Source:
Development
Tags:
Backport:
Regression:
Severity:
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
0> 2012-08-25 21:38:18.087785 7fba8c9a4700 -1 common/Thread.cc: In function 'int Thread::join(void**)' thread 7fba8c9a4700 time 2012-08-25 21:38:18.084887 common/Thread.cc: 122: FAILED assert(status == 0) ceph version 0.50-383-gaa91cf8 (commit:aa91cf81af548463ae583872e319316871771e94) 1: (Thread::detach()+0) [0x8abee0] 2: (Finisher::stop()+0x197) [0x951957] 3: (MonClient::shutdown()+0xbc) [0x86503c] 4: (MDS::suicide()+0x137) [0x4c63e7] 5: (MDLog::handle_journaler_write_error(int)+0x1b5) [0x7a78c5] 6: (MDLog::C_MDL_WriteError::finish(int)+0x15) [0x7b0485] 7: (Journaler::handle_write_error(int)+0x77) [0x7b4a47] 8: (Journaler::_finish_write_head(int, Journaler::Header&, Context*)+0x404) [0x7b5794] 9: (Journaler::C_WriteHead::finish(int)+0x1d) [0x7bfdbd] 10: (Context::complete(int)+0x12) [0x4b7032] 11: (Objecter::C_Op_Map_Latest::finish(int)+0x160) [0x7d0f90] 12: (Context::complete(int)+0x12) [0x4b7032] 13: (C_IsLatestMap::finish(int)+0x27) [0x8719b7] 14: (Finisher::finisher_thread_entry()+0x3ad) [0x95291d] 15: (Finisher::FinisherThread::entry()+0x15) [0x871bf5] 16: (Thread::_entry_func(void*)+0x12) [0x8abb52] 17: (()+0x7e9a) [0x7fba92710e9a] 18: (clone()+0x6d) [0x7fba90cb84bd] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this. ubuntu@teuthology:/a/teuthology-2012-08-25_19:00:04-regression-master-testing-gcov/8818 for a reasonably useful log this looks like it's related to the msgr failure injection, which seems to be enough to break mds startup
Updated by Sage Weil over 11 years ago
- Category changed from 1 to Objecter
- Status changed from 12 to Fix Under Review
was able to reproduce after a few attempts with
./stop.sh ; CEPH_NUM_MDS=15 CEPH_NUM_MON=1 ./vstart.sh -d -n -x -o 'debug monc = 20' -o 'debug objecter = 20' -o 'ms inject socket failures = 250'
see fix in wip-monc-latest
Updated by Sage Weil over 11 years ago
- Status changed from Fix Under Review to 7
Actions