Re: Performance degradation seen after using one list for hot/cold pages.

[Christoph Lameter <cl@linux-foundation.org>]

On Tue, 23 Jun 2009, KAMEZAWA Hiroyuki wrote:

> > Ok, by the looks of things, all the aio_read() requests are due to readahead
> > as opposed to explicit AIO  requests from userspace. In this case, nothing
> > springs to mind that would avoid excessive requests for cold pages.
> >
> > It looks like the simpliest solution is to go with the patch I posted.
> > Does anyone see a better alternative that doesn't branch in rmqueue_bulk()
> > or add back the hot/cold PCP lists?
> >
> No objection.  But 2 questions...

Also no objections here. Readahead makes sense.

> 1. if (likely(coild == 0))
> 	"likely" is necessary ?

Would not think so. Code is sufficiently compact so that the
processor "readahead" will have both branches in cache.

> 2. Why moving pointer "list" rather than following ?
>
> 	if (cold)
> 		list_add(&page->lru, list);
> 	else
> 		list_add_tail(&page->lru, list);

Not sure what your point is here. Can you pickup the patch fix it up and
resubmit? Mel is out for now it seems.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>