Actions
Bug #7613
closedmds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
Status:
Can't reproduce
Priority:
High
Assignee:
-
Category:
-
Target version:
-
% Done:
0%
Source:
Community (user)
Tags:
Backport:
Regression:
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(FS):
MDS
Labels (FS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
-2> 2014-03-05 07:05:36.312967 7f5abc599700 1 -- 172.28.130.222:7026/477344 <== client.10131 172.28.128.197:0/3610731943 49 ==== client_request(client.10131:310253922 create #1000267c7e3/esolorio@fwwatch.org.promoted RETRY=1) ==== 143+0+0 (2116337601 0 0) 0xfaa3c100 con 0x25a83700 -1> 2014-03-05 07:05:36.312985 7f5abc599700 4 mds.0.server handle_client_request client_request(client.10131:310253922 create #1000267c7e3/esolorio@fwwatch.org.promoted RETRY=1) 0> 2014-03-05 07:05:36.332955 7f5abc599700 -1 mds/MDCache.cc: In function 'void MDCache::add_inode(CInode*)' thread 7f5abc599700 time 2014-03-05 07:05:36.313099 mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0) ceph version 0.72.1 (4d923861868f6a15dcb33fef7f50f674997322de) 1: /usr/bin/ceph-mds() [0x62f0a6] 2: (Server::prepare_new_inode(MDRequest*, CDir*, inodeno_t, unsigned int, ceph_file_layout*)+0x1400) [0x5d0570] 3: (Server::handle_client_openc(MDRequest*)+0xc0d) [0x5ffdfd] 4: (Server::dispatch_client_request(MDRequest*)+0x1db) [0x60967b] 5: (Server::handle_client_request(MClientRequest*)+0x38b) [0x60de2b] 6: (Server::dispatch(Message*)+0x45b) [0x60ea3b] 7: (MDS::handle_deferrable_message(Message*)+0x950) [0x56c7b0] 8: (MDS::_dispatch(Message*)+0x1531) [0x57fe81] 9: (MDS::ms_dispatch(Message*)+0x1ab) [0x58050b] 10: (DispatchQueue::entry()+0x582) [0x8c4032] 11: (DispatchQueue::DispatchThread::entry()+0xd) [0x840eed] 12: /lib64/libpthread.so.0() [0x3bbd407851] 13: (clone()+0x6d) [0x3bbcce894d] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.
Files
Updated by Matthew Via about 10 years ago
Stopping the clients that were attempting to mount cephfs (by restarting them) appeared to let the mds start with no issues. Attached is the log in case pastee vanishes.
Updated by Matthew Via about 10 years ago
I shouldn't have said anything -- minutes later the problem is now happening again.
Updated by Zheng Yan about 10 years ago
can upload the core dump and ceph-mds binary to somewhere?
Updated by Sage Weil almost 10 years ago
- Status changed from 12 to Need More Info
Updated by Sage Weil over 9 years ago
- Status changed from Need More Info to Can't reproduce
Actions