Large pages; page coloring

[Matthew Dillon]

DragonFly only uses large pages in-kernel and only for a few things.  They
do not extend to user-land.  The main reason is that to do it properly and
make large pages deterministic we would have to completely rewrite the
memory allocator, otherwise the benefit is not well realized.  FreeBSD
didn't and their large page allocations are relatively non-deterministic,
meaning it is hard to count on them happening all the time under normal
operating conditions.

DragonFly does have a shared page table optimization for common memory maps
which is useful for things like database servers (postgres, which forks
instead of threads).  This feature can be turned on with the
machdep.pmap_mmu_optimize sysctl.  It is considered experimental.
Basically what it does is recognize when two or more distinct processes
mmap() the same shared file or VM object (so it also works for any
fork-shared memory areas) and will simply have the processes MMU maps
access the same physical MMU directory page.  This has a big positive
effect on reducing VM page faults on heavily shared forked situations.

Big pages reduce TLB overheads but can wind up being pretty memory
inefficient.  Memory efficiency tends to be more important these days...
that is, servers are generally limited by memory and not limited by cpu.

--

If I recall, FreeBSD mostly removed page coloring from their VM page
allocation subsystem.  DragonFly kept it and integrated it into the
fine-grained-locked VM page allocator.  There's no advantage to
manipulating the parameters for two reasons.

First, all page coloring really does is try to avoid degenerate situations
in the cpu caches.  The cpu caches are already 4-way or 8-way
set-associative.  The page coloring improves this but frankly even the set
associativeness in the base cpu caches gets us most of the way there.  So
adjusting the page coloring algorithms will not yield any improvements.

Secondly, the L1 cache is a physical memory cache but it is also virtually
indexed.  This is a cpu hardware optimization that allows the cache lookup
to be initiated concurrent with the TLB lookup.  Because of this, physical
set associatively does not actually solve all the problems which can occur
with a virtually indexed cache.

So the userland memory allocator implements an offsetting feature for
allocations which attempts to address the virtually indexed cache issues.
This feature is just as important as the physical page coloring feature for
performance purposes.

-Matt


On Tue, Apr 14, 2015 at 10:10 AM, Alex Merritt <merritt.alex at gmail.com>
wrote:

> Hello!
>
> I am interested in learning whether Dragonfly supports large pages (2M and
> 1G), and secondly, what mechanisms exist for applications to have influence
> over the colors used to assign the physical pages backing their memory,
> specifically for private anonymous mmap'd regions. Regarding coloring, I'd
> like to be able to evaluate applications with a small number of colors
> (restricting their access to the last-level cache) and compare their
> performance to more/all colors available. I am initially looking to work in
> hacks to achieve this to perform some preliminary experiments, perhaps by
> way of a kernel module or something.
>
> A cursory search of the code showed no hints at support for large pages,
> but I did find there are more internal functions governing the allocation
> of pages based on colors, compared to FreeBSD (10.1). In FreeBSD it seems
> colors are only considered for regions which are added that are backed by a
> file, but I am not 100% certain.
>
> I appreciate any help!
>
> Thanks,
> Alex
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.dragonflybsd.org/pipermail/kernel/attachments/20150414/5f1bcea0/attachment-0002.html>