Hi Dimitry, Can you please suggest me the trigger point for LMK. from which part of code the LMK is getting called as well as any variables responsible for the call.
About your question: Yes LMK doesnt take NR_FILE_PAGES in count because that's the downside left while making it. On Tuesday, November 22, 2011 7:53:48 PM UTC+5:30, Dmitry wrote: > > Hi, > > I'm trying to figure out how the low memory killer (kernel/staging/ > android/lowmemorykiller.c) is trying to clear some space. > In current version it checks only NR_FILE_PAGE count and ignores the > NR_FREE_PAGES at all. > In some heavy load tests it seem causing too aggressive process > killing which causes problems with apps. > > According to logs the system have a lot of free pages and very small > amount of file cache pages. > nr_free_pages 26659 > nr_file_pages 8822 > nr_shmem 2296 > > So the question is why NR_FREE_PAGES are not taken into account? I do > not know the exact meaning of NR_FILE_PAGES, but it seems to me that > it show the number of pages allocated for file mappings (and file > buffers most likely) but not the number of free pages of file cache . > So it is very strange to compare the limits of minfree with > NR_FILE_PAGES > > Dmitry > > -- -- unsubscribe: android-kernel+unsubscr...@googlegroups.com website: http://groups.google.com/group/android-kernel --- You received this message because you are subscribed to the Google Groups "Android Linux Kernel Development" group. To unsubscribe from this group and stop receiving emails from it, send an email to android-kernel+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/groups/opt_out.
