lkml.org 
[lkml]   [2018]   [Feb]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: Use higher-order pages in vmalloc
From
Date
On 02/21/2018 07:42 AM, Matthew Wilcox wrote:
> On Tue, Jan 23, 2018 at 01:55:32PM +0300, Konstantin Khlebnikov wrote:
>> Virtually mapped stack have two bonuses: it eats order-0 pages and
>> adds guard page at the end. But it slightly slower if system have
>> plenty free high-order pages.
>>
>> This patch adds option to use virtually bapped stack as fallback for
>> atomic allocation of traditional high-order page.
> This prompted me to write a patch I've been meaning to do for a while,
> allocating large pages if they're available to satisfy vmalloc. I thought
> it would save on touching multiple struct pages, but it turns out that
> the checking code we currently have in the free_pages path requires you
> to have initialised all of the tail pages (maybe we can make that code
> conditional ...)

What the concept here? If we can use high-order pages for vmalloc() at
the moment, we *should* use them?

One of the coolest things about vmalloc() is that it can do large
allocations without consuming large (high-order) pages, so it has very
few side-effects compared to doing a bunch of order-0 allocations. This
patch seems to propose removing that cool thing. Even trying the
high-order allocation could kick off a bunch of reclaim and compaction
that was not there previously.

If you could take this an only _opportunistically_ allocate large pages,
it could be a more universal win. You could try to make sure that no
compaction or reclaim is done for the large allocation. Or, maybe you
only try it if there are *only* high-order pages in the allocator that
would have been broken down into order-0 *anyway*.

I'm not sure it's worth it, though. I don't see a lot of folks
complaining about vmalloc()'s speed or TLB impact.

\
 
 \ /
  Last update: 2018-02-21 17:17    [W:0.065 / U:0.536 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site