Messages in this thread | | | Subject | Re: oom_killer crash linux system | From | "Figo.zhang" <> | Date | Mon, 18 Oct 2010 16:13:51 +0800 |
| |
i want to test the oom-killer. My desktop (Dell optiplex 780, i686 kernel)have 2GB ram, i turn off the swap partition, and open a huge pdf files and applications, and let the system eat huge ram.
in 2.6.35, i can use ram up to 1.75GB,
but in 2.6.36-rc8, i just use to 1.53GB ram , the system come very slow and crashed after some minutes , the DiskIO is very busy. i see the DiskIO read is up to 8MB/s, write just only 400KB/s, (see by conky).
what change between 2.6.35 to 2.6.36-rc8? is it low performance about page reclaim and page writeback in high press ram useage?
Best, Figo.zhang
On Mon, 2010-10-18 at 10:11 +0800, Wu Fengguang wrote: > On Mon, Oct 18, 2010 at 09:57:22AM +0800, KAMEZAWA Hiroyuki wrote: > > On Mon, 18 Oct 2010 09:47:39 +0800 > > "Figo.zhang" <zhangtianfei@leadcoretech.com> wrote: > > > > > hi all, > > > > > > i have a desktop run linux2.6.35 and have 2GB ram. i turn off the swap > > > partition, and i open huge applications , let the system eat more and > > > more memory. > > > when the system eat more than 1.7G ram, the system crashed. > > > > > > > 2.6.36-rc series has a completely new logic, please try. > > And the new logic should help this case. > > commit a63d83f427fbce97a6cea0db2e64b0eb8435cd10 > Author: David Rientjes <rientjes@google.com> > Date: Mon Aug 9 17:19:46 2010 -0700 > > oom: badness heuristic rewrite > ... > Instead of basing the heuristic on mm->total_vm for each task, the task's > rss and swap space is used instead. This is a better indication of the > amount of memory that will be freeable if the oom killed task is chosen > and subsequently exits. This helps specifically in cases where KDE or > GNOME is chosen for oom kill on desktop systems instead of a memory > hogging task. > ... > > Thanks, > Fengguang
| |