Re: [PATCH] VM: Implements the swap-out page-clustering technique

["Hamid R. Jahanjou" <hamid.jahanjou@gmail.com>]

Andi Kleen wrote:
> "Hamid R. Jahanjou" <hamid.jahanjou@gmail.com> writes:
>
>   
>> From: Hamid R. Jahanjou
>>
>> Implements the idea of swap-out page clustering from *BSD for
>> Linux. Each time a candidate page is to be swapped out,
>> virtually-nearby pages are scanned to find eligible pages to be
>> swapped out too as a cluster. This technique increases the likelihood of
>> bringing in related data on a page fault and decreases swap space
>> fragmentation in the long run. Currently, Linux searches only
>> physically-nearby pages which is not optimal since, over time, physically-
>> adjacent pages may become unrelated.
>>
>> The code can be statically tuned. No benchmarks. I'm not sure whether
>> the added complexity is acceptable.
>>     
>
> Just some general comments:
>
> First I think virtual swap clustering is a great idea in theory and
> long overdue.  Hopefully the numbers will agree.
>
> In general the code would be much nicer if you didn't pass around 
> all that much in a structure (which is just a fancy way to have
> a function with lots of arguments) Perhaps try to restructure
> it a bit to make this smaller? Ideally clustering_info should disappear
> or at least get much smaller.
>   

Thanks for the review and the comments.
Do you consider the clustering_info struct to hurt the readability
of the code or there is some other technical reasons ?

> I didn't quite understand the "adjust the value of our search by
> the allocation order". The allocation order should be normally 0.
> I think having a tunable for the cluster sizes would be a good idea.
> At some point they might be even device dependent (e.g. on a flash
> device you would like to have them roughly erase block sized)
>   

The allocation order value is initially passed to the try_to_free_pages()
in __alloc_pages_internal() and its value can be well more than zero.
The clustering code adjusts the cluster size to the value of the allocation
order (in a non-linear fashion of course). In this sense the cluster
size is
not determined at compile time, but the parameters affecting it are.
Perhaps the term "statically-tunable" is appropriate here.

-- 
Hamid R. Jahanjou
(hamid.jahanjou@gmail.com)