Re: increasing page size

Alan Cox (alan@lxorguk.ukuu.org.uk)
Tue, 7 Jul 1998 11:17:33 +0100 (BST)


> I imagine a per-cpu hot list and aggressive forget-behind conspiring
> so that the kernel unmaps pages right after the program touches
> them, then reallocates those pages immediately, which causes the
> program to suffer a major fault when it goes back to touch the data.

The hot cache is for pages we have just freed, in the "really freed" sense.
Its actually bad to put user pages on the list since they will almost
certainly have been aged before freed and wont be in the cache, but
pages that are GFP_KERNEL or GFP_ATOMIC are different I suspect.

Alan

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu