http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From hch@xxxxxxx 2004-01-01 17:02 PDT -- Can you retry with 2.6.1-rc1? It has fixes to better reclaim inodes and dentries. -- Yo
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From sandeen@xxxxxxx 2003-22-11 19:05 PDT -- Any chance you can try this same test on a non-xfs box? Just to narrow down whether
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From condor-sgi@xxxxxxxxxxxxx 2003-22-11 20:03 PDT -- Sadly (:p), all my machines are XFS. I'll ask around and see if I can find
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From sandeen@xxxxxxx 2003-23-11 09:29 PDT -- No problem, I can test this on an ext3 box. Just figured if you had one handy you c
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From sandeen@xxxxxxx 2003-24-11 15:05 PDT -- Actually, what makes you certain that this is a leak, rather than normal caching, e
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From condor-sgi@xxxxxxxxxxxxx 2003-24-11 17:16 PDT -- Well, I think it's a leak largely because it eats non-buffer, non-cached R
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From sandeen@xxxxxxx 2003-22-11 19:05 PDT -- Any chance you can try this same test on a non-xfs box? Just to narrow down whether
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From condor-sgi@xxxxxxxxxxxxx 2003-22-11 20:03 PDT -- Sadly (:p), all my machines are XFS. I'll ask around and see if I can find
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From sandeen@xxxxxxx 2003-23-11 09:29 PDT -- No problem, I can test this on an ext3 box. Just figured if you had one handy you c
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From sandeen@xxxxxxx 2003-24-11 15:05 PDT -- Actually, what makes you certain that this is a leak, rather than normal caching, e
http://oss.sgi.com/bugzilla/show_bug.cgi?id=290 -- Additional Comments From condor-sgi@xxxxxxxxxxxxx 2003-24-11 17:16 PDT -- Well, I think it's a leak largely because it eats non-buffer, non-cached R