Messages in this thread |  | | Date | Mon, 14 May 2001 21:57:16 -0300 (BRST) | From | Rik van Riel <> | Subject | Re: [PATCH] vmscan.c fixes |
| |
On Mon, 14 May 2001, Marcelo Tosatti wrote: > On Mon, 14 May 2001, Rik van Riel wrote: > > > + /* XXX: dynamic free target is complicated and may be wrong... */ > > int freetarget = freepages.high + inactive_target / 3; > > I think its better if we just remove " + inactive_target / 3" here --- > callers already account for the inactive_target when trying to > calculate the free target anyway.
Right, there's really only one thing this "+ inactive_target / 3" achieves ... more agressive flushing of dirty pages, by trying to keep a larger free target.
Whether this is good or not I really don't know; this basically boils down to the old "pre-flushing vs. delaying IO" thing.
regards,
Rik -- Linux MM bugzilla: http://linux-mm.org/bugzilla.shtml
Virtual memory is like a game you can't win; However, without VM there's truly nothing to lose...
http://www.surriel.com/ http://www.conectiva.com/ http://distro.conectiva.com/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
|  |