Red Hat Bugzilla – Bug 852821
sanity tests hung on replicate volume with rdma transport type
Last modified: 2016-09-17 08:20:09 EDT
+++ This bug was initially created as a clone of Bug #785157 +++ Created attachment 557854 [details] gluster fuse client log Description of problem: Was running sanity on a replicate volume with rdma transport. ltp test cases got hung for more than a day. Version-Release number of selected component (if applicable): git master with head at b02afc6d008f9959db28244eb2b9dd3b9ef92393 How reproducible: 1/1 Steps to Reproduce: 1. Create a replicated volume with rdma transport 2. Start the sanity tests (which includes ltp test cases) Actual results: ltp test cases in sanity tests hung for more than a day. Expected results: no test cases should hang. Additional info: I saw the following entries in statedumps of glusterfsd processes. [xlator.features.locks.hosdu-locks.inode] mandatory=0 entrylk-count=2 lock-dump.domain.domain=hosdu-replicate-0 xlator.feature.locks.lock-dump.domain.entrylk.entrylk[0](ACTIVE)= ENTRYLK_WRLCK on f4 pid = 18446744073686515360, owner=ff7effff247f0000, transport=0x7f19dd19ede0, granted at Thu Jan 26 03:05:37 2012 xlator.feature.locks.lock-dump.domain.entrylk.entrylk[1](BLOCKED)= ENTRYLK_WRLCK on f4 pid = 18446744073686459092, owner=ffffffff247f0000, transport=0x7f19dd1b5630, blocked at Thu Jan 26 03:05:38 2012 [xlator.features.locks.hosdu-locks.inode] mandatory=0 entrylk-count=2 lock-dump.domain.domain=hosdu-replicate-0 xlator.feature.locks.lock-dump.domain.entrylk.entrylk[0](ACTIVE)= ENTRYLK_WRLCK on f4 pid = 18446744073686448672, owner=207affff247f0000, transport=0x7f8d2401a2e0, granted at Wed Jan 25 00:21:16 2012 xlator.feature.locks.lock-dump.domain.entrylk.entrylk[1](BLOCKED)= ENTRYLK_WRLCK on f4 pid = 18446744073686463260, owner=1cffffff247f0000, transport=0x7f8d25127b00, blocked at Wed Jan 25 00:21:18 2012 I have attached the fuse client log and statedumps of both glusterfsds. --- Additional comment from msvbhat@redhat.com on 2012-01-27 08:30:47 EST --- Created attachment 557857 [details] glusterfsd statedump --- Additional comment from msvbhat@redhat.com on 2012-01-27 08:31:43 EST --- Created attachment 557858 [details] statedump of another glusterfsd --- Additional comment from msvbhat@redhat.com on 2012-01-27 08:32:22 EST --- Created attachment 557859 [details] statedump of client process
The product version of Red Hat Storage on which this issue was reported has reached End Of Life (EOL) [1], hence this bug report is being closed. If the issue is still observed on a current version of Red Hat Storage, please file a new bug report on the current version. [1] https://rhn.redhat.com/errata/RHSA-2014-0821.html