[lkml]   [2009]   [Apr]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 0/3] compressed in-memory swapping take5
On Thu, Apr 2, 2009 at 7:39 AM, Christoph Lameter <> wrote:
> On Thu, 2 Apr 2009, Nitin Gupta wrote:
>> Justification for this custom allocator is present in xvmalloc changelog
>> itself. It gives reason for not using SLUB and SLOB. During review
>> cycle, I never got any arguments against that justification.
> The use of highmem is pretty unique. But that restrict the usefulness to
> 32 bit processors with too much RAM.

I would again like to mention that apart from highmem, xvmalloc is O(1)
and is very memory efficient too. Sometime in future I hope to present
it as replacement for funny SLOB allocator. For this I will require lot of
data which is another major work....

For now, I will rename xvmalloc to rzmalloc and move it to
drivers/block/ramzswap. As for data to justify ramzswap inclusion
-- its going to be hard. It just 'feels' lot more responsive with compression
but not sure how to quantify this. Maybe I will get some data
by next release.

Thanks to you all for your reviews and suggestions.


 \ /
  Last update: 2009-04-02 05:35    [W:0.056 / U:0.024 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site