Hi, 15.05.2013 05:22, Yuichi SEINO wrote: > Hi, > > I ran the test for about two days. > > Environment > > OS:RHEL 6.3 > pacemaker-1.1.9-devel (commit 138556cb0b375a490a96f35e7fbeccc576a22011) > corosync-2.3.0 > cluster-glue > latest+patch(detail:http://www.gossamer-threads.com/lists/linuxha/dev/85787) > libqb- 0.14.4 > > There may be a memory leak in crmd and lrmd. I regularly got rss of ps. > > start-up > crmd:5332 > lrmd:3625 > > interval(about 30h later) > crmd:7716 > lrmd:3744 > > ending(about 60h later) > crmd:8336 > lrmd:3780
Does SHR grow as well? I know that crmd allocated big enough QB buffer in shared memory (5 Mb or so), and consumes it until it becomes full, and all that time both RSS ans SHR grow synchronously. In my tests (several months ago, with 1.1.8) it took several days to reach that point on a static cluster. You may also look to differences in /proc/<pid>/smaps (just with diff) to see what exactly grows. Best, Vladislav _______________________________________________ Pacemaker mailing list: Pacemaker@oss.clusterlabs.org http://oss.clusterlabs.org/mailman/listinfo/pacemaker Project Home: http://www.clusterlabs.org Getting started: http://www.clusterlabs.org/doc/Cluster_from_Scratch.pdf Bugs: http://bugs.clusterlabs.org