From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew W Elble Date: Fri, 16 Oct 2015 09:49:02 -0400 Subject: [Cluster-devel] [GFS2 PATCH v2 14/15] GFS2: Hold onto iopen glock longer when dinode creation fails In-Reply-To: <820524051.47443676.1445002403265.JavaMail.zimbra@redhat.com> (Bob Peterson's message of "Fri, 16 Oct 2015 09:33:23 -0400") References: <1444158168-23036-1-git-send-email-rpeterso@redhat.com> <1444158168-23036-15-git-send-email-rpeterso@redhat.com> <820524051.47443676.1445002403265.JavaMail.zimbra@redhat.com> Message-ID: List-Id: To: cluster-devel.redhat.com MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit > Hi Andy, > > Thanks. I'll investigate it. > > BTW, I haven't found any more blatant bugs during testing, however I'm > debugging another issue. It seems as if I still have a reference counter > issue somewhere because if I slam GFS2 hard enough, I can get it to > accumulate millions of glocks that are never freed (unless memory pressure > causes the glock shrinker to be called). Having the extra glocks is causing > undue strain on the dlm, to the point where dlm can't keep up. > So it seems likely that I'll do another revision here anyway. > I'll keep you posted. Bob, Would that resemble something like this? S glocks nondisk inode rgrp iopen flock quota j;rnl Total S --------- ------- -------- ------- ------- ------- ----- ---- -------- S Unlocked: 1 67677 304 0 0 460 0 68442 S Locked: 2 1638575 630 1637848 0 780 1 3277836 S Total: 3 1706252 934 1637848 0 1240 1 3346278 S S Held EX: 0 1 0 0 0 0 1 2 S Held SH: 1 1 0 1637847 0 0 0 1637849 S Held DF: 0 0 0 0 0 0 0 0 S G Waiting: 0 0 0 0 0 0 0 0 S P Waiting: 0 0 0 0 0 0 0 0 S DLM wait: 0 Thanks, Andy -- Andrew W. Elble aweits at discipline.rit.edu Infrastructure Engineer, Communications Technical Lead Rochester Institute of Technology PGP: BFAD 8461 4CCF DC95 DA2C B0EB 965B 082E 863E C912