On Tue, 26 Feb 2008 22:18:38 +0100 Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:I think it doesn't make sense for fairness. IMHO, this functionality is an unfair one in nature. While someone is reclaiming pages, other processes can get a newly reclaimed page without calling try_to_free_page. For high-priority processes, 1. avoiding diving into try_to_free_pages if it's congested. 2. just waiting for that someone relcaim pages and grab it ASAP maybe good for quick work. Thanks, -Kame --
| Peter Zijlstra | Re: Quad core CPUs loaded at only 50% when running a CPU and mmap intensive multi-... |
| Satyam Sharma | [-mm patchset] War on warnings |
| Izik Eidus | [PATCH 0/4] ksm - dynamic page sharing driver for linux |
| Renato S. Yamane | Error -71 on device descriptor read/all |
git: | |
| Martin Langhoff | Handling large files with GIT |
| Wincent Colaiuta | Rebase/cherry-picking idea |
| Linus Torvalds | People unaware of the importance of "git gc"? |
| Joe Fiorini | Undo git-rm without commit? |
| Christian Weisgerber | Re: libiconv problem |
| Peter | OpenBSD as Virtualbox guest |
| Brandon Lee | DELL PERC 5iR slow performance |
| Martin Toft | Trying to compile cwm on Linux |
| Alexey Dobriyan | [PATCH 01/53] xfrm: initialise xfrm_policy_gc_work statically |
| Arjan van de Ven | Printing the driver name as part of the netdev watchdog message |
| Dushan Tcholich | Re: ksoftirqd high cpu load on kernels 2.6.24 to 2.6.27-rc1-mm1 |
| Inaky Perez-Gonzalez | [PATCH 03/39] wimax: constants and definitions to interact with user space |
