FWIW, I have experienced similar issue, but since I'm also running zfs which is still pretty experimental, I've blamed it on zfs. Unfortunately I had to reboot quickly without much time to investigate.
What I usually do is look at the slabs (cat /proc/slabinfo or use slabtop) and any hugepages (fgrep HugePages /proc/meminfo) that might be just sitting there. Unfortunately I didn't find the way to link slabs to the parts of the kernel that are alocating them, except when it isn't obvious from the name. Of course, it could be that the running processes have leaks or "leaks", I assume that you already used top and similar tools to figure out where the memory is going. regards, "JR Richardson" <jmr.richard...@gmail.com> writes: > Hi All, > > > > Ive been using OpenVZ for many years, was on a fairly old kernel for a > long time, VEs running great no issues. I recently upgraded to kernel > 2.6.32-openvz-042stab090.4-amd64, same VEs, after 75 days in production > the memory on the host node is maxed and Im seeing issues in the VEs > with MySQL database dips, slow responses and such. > > > > Any known issues with memory leaks with the newer kernels, should I try > upgrading to linux-source-2.6.32-openvz-042stab093.4-amd64 or downgrade to > another older version? > > > > Opinions very welcome. > > > > Thanks. > > > > JR > > JR Richardson > > Engineering for the Masses > > > > -------------------------------------------------------------------------- > > [1][IMG] This email is free from viruses and malware because [2]avast! > Antivirus protection is active. > > References > > Visible links > 1. http://www.avast.com/ > 2. http://www.avast.com/ > _______________________________________________ > Users mailing list > Users@openvz.org > https://lists.openvz.org/mailman/listinfo/users -- Ti si arogantan, prepotentan i peglaš vlastitu frustraciju. -- Ivan Tišljar, hr.comp.os.linux
_______________________________________________ Users mailing list Users@openvz.org https://lists.openvz.org/mailman/listinfo/users