Hi Rik,
On Thu, 16 Nov 2000, Rik van Riel wrote:
> On 16 Nov 2000, Christoph Rohland wrote:
>> So in shm_swap_out I check if the page is already in the swap
>> cache. If not I put the page into it and note the swap entry in
>> the shadow pte of shm. Right?
>
> Exactly. And I'll change page_launder() to:
> 1. write dirty swap cache pages to disk
> 2. do some IO clustering (maybe) or rely on luck ;)
>
>> So does the page live all the time in the swap cache? This would
>> lead to a vastly increased swap usage since we would have to
>> preallocate the swap entries on page allocation.
>
> If the usage count of the swap entry is 1 (all users of the
> page have swapped it in and the swap cache is the only user),
> then we can free the page from swap and the swap cache.
Great. So what do we have to do to get this done? The shm stuff sounds
pretty easy.
Greetings
Christoph
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Nov 23 2000 - 21:00:11 EST