Rik van Riel <riel@conectiva.com.br> wrote:
> As long as there is enough _freeable_ memory around we must not
> kill anything with OOM. In fact, my OOM code doesn't kill anything
> as long as do_try_to_free_pages is able to free the pages it needs.
For in-kernel OOM, this makes sense. For a pro-active user-land
version, we would start warning at a low-water mark, and
killing at some high water mark.
> It is a very common situation that systems have no free memory but
> tons of easily _freeable_ memory, like cache or pages which are
> duplicated in both swap and memory. In that case it is just not
> acceptable to start killing processes.
Cache is not included in my VM measurement. It's just
pages currently allocated to processes.
> Also, how is your "90%" measure applicable to machines without
> swap?
90% of RAM is used.
(In case I haven't been clear, when I say ``X% of VM'' I
mean:
X% = (pages used by processes in MEM + pages used by processes in SWAP)
------------------------------------------------------------------ * 100
(total pages of MEM + total pages of SWAP)
Clear as mud?
-- Jason McMullan, Senior Linux Consultant, Linuxcare, Inc. 412.422.8077 tel, 412.656.3519 cell, 415.701.0792 fax jmcmullan@linuxcare.com, http://www.linuxcare.com/ Linuxcare. Support for the revolution.- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sat Jul 15 2000 - 21:00:20 EST