Bug #9428
mds: tight mon reconnect loop
Status:
Resolved
Priority:
Immediate
Assignee:
-
Category:
-
Target version:
-
% Done:
0%
Source:
Development
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(FS):
Labels (FS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
2014-09-10 22:08:14.055442 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 --> 10.214.133.104:6789/0 -- auth(proto 0 34 bytes epoch 5) v1 -- ?+0 0x35dfa6c0 con 0x989b02c0 2014-09-10 22:08:14.055448 7f2a1fc10700 5 mds.beacon.burnupi21 is_laggy 64.365890 > 15 since last acked beacon 2014-09-10 22:08:14.055451 7f2a1fc10700 5 mds.beacon.burnupi21 initiating monitor reconnect; maybe we're not the slow one 2014-09-10 22:08:14.055454 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 mark_down 0x989b02c0 -- 0x385f28c0 2014-09-10 22:08:14.055489 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 --> 10.214.133.114:6789/0 -- auth(proto 0 34 bytes epoch 5) v1 -- ?+0 0x35dfab40 con 0x24ca7160 2014-09-10 22:08:14.055495 7f2a1fc10700 5 mds.beacon.burnupi21 is_laggy 64.365937 > 15 since last acked beacon 2014-09-10 22:08:14.055498 7f2a1fc10700 5 mds.beacon.burnupi21 initiating monitor reconnect; maybe we're not the slow one 2014-09-10 22:08:14.055505 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 mark_down 0x24ca7160 -- 0x385f1b00 2014-09-10 22:08:14.055534 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 --> 10.214.133.104:6789/0 -- auth(proto 0 34 bytes epoch 5) v1 -- ?+0 0xa0a26000 con 0x24ca7000 2014-09-10 22:08:14.055540 7f2a1fc10700 5 mds.beacon.burnupi21 is_laggy 64.365982 > 15 since last acked beacon 2014-09-10 22:08:14.055543 7f2a1fc10700 5 mds.beacon.burnupi21 initiating monitor reconnect; maybe we're not the slow one 2014-09-10 22:08:14.055560 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 mark_down 0x24ca7000 -- 0x385f2b80 2014-09-10 22:08:14.055592 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 --> 10.214.133.134:6789/0 -- auth(proto 0 34 bytes epoch 5) v1 -- ?+0 0x65c1a480 con 0x24ca7420 2014-09-10 22:08:14.055599 7f2a1fc10700 5 mds.beacon.burnupi21 is_laggy 64.366040 > 15 since last acked beacon 2014-09-10 22:08:14.055602 7f2a1fc10700 5 mds.beacon.burnupi21 initiating monitor reconnect; maybe we're not the slow one 2014-09-10 22:08:14.055604 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 mark_down 0x24ca7420 -- 0x111f7b80 2014-09-10 22:08:14.055632 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 --> 10.214.133.104:6789/0 -- auth(proto 0 34 bytes epoch 5) v1 -- ?+0 0x65c1a240 con 0x24ca79a0 2014-09-10 22:08:14.055641 7f2a1fc10700 5 mds.beacon.burnupi21 is_laggy 64.366083 > 15 since last acked beacon 2014-09-10 22:08:14.055644 7f2a1fc10700 5 mds.beacon.burnupi21 initiating monitor reconnect; maybe we're not the slow one 2014-09-10 22:08:14.055646 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 mark_down 0x24ca79a0 -- 0x111f6000 2014-09-10 22:08:14.055673 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 --> 10.214.133.114:6789/0 -- auth(proto 0 34 bytes epoch 5) v1 -- ?+0 0x35dfa900 con 0x24ca76e0 2014-09-10 22:08:14.055679 7f2a1fc10700 5 mds.beacon.burnupi21 is_laggy 64.366121 > 15 since last acked beacon 2014-09-10 22:08:14.055682 7f2a1fc10700 5 mds.beacon.burnupi21 initiating monitor reconnect; maybe we're not the slow one 2014-09-10 22:08:14.055685 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 mark_down 0x24ca76e0 -- 0x53ab38c0 2014-09-10 22:08:14.055715 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 --> 10.214.133.104:6789/0 -- auth(proto 0 34 bytes epoch 5) v1 -- ?+0 0x35dfa480 con 0x24ca7b00 2014-09-10 22:08:14.055721 7f2a1fc10700 5 mds.beacon.burnupi21 is_laggy 64.366163 > 15 since last acked beacon 2014-09-10 22:08:14.055723 7f2a1fc10700 5 mds.beacon.burnupi21 initiating monitor reconnect; maybe we're not the slow one 2014-09-10 22:08:14.055726 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 mark_down 0x24ca7b00 -- 0x53ab2580 2014-09-10 22:08:14.055761 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 --> 10.214.133.114:6789/0 -- auth(proto 0 34 bytes epoch 5) v1 -- ?+0 0x35dfa6c0 con 0x6e1feb00 2014-09-10 22:08:14.055767 7f2a1fc10700 5 mds.beacon.burnupi21 is_laggy 64.366208 > 15 since last acked beacon 2014-09-10 22:08:14.055769 7f2a1fc10700 5 mds.beacon.burnupi21 initiating monitor reconnect; maybe we're not the slow one 2014-09-10 22:08:14.055791 7f2a1fc10700 1 -- 10.214.134.10:6801/40438 mark_down 0x6e1feb00 -- 0x4228f8c0
Associated revisions
mds/Beacon: do not reconnect to mon in quick succession
Wait at least one beacon interval between mon session resets.
Fixes: #9428
Signed-off-by: Sage Weil <sage@redhat.com>
History
#1 Updated by Sage Weil over 9 years ago
- Status changed from New to Resolved