[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [MIT-Scheme-devel] [commit f372dae] Don't call OS_free_pages after G
From: |
Joe Marshall |
Subject: |
Re: [MIT-Scheme-devel] [commit f372dae] Don't call OS_free_pages after GC flip. We don't resize the heap and we will be reusing it. |
Date: |
Fri, 7 Oct 2011 13:20:24 -0700 |
On Fri, Oct 7, 2011 at 12:29 PM, Taylor R Campbell <address@hidden> wrote:
> Date: Fri, 7 Oct 2011 12:08:09 -0700
> From: Joe Marshall <address@hidden>
>
> > On Wed, Oct 5, 2011 at 7:50 PM, Taylor R Campbell <address@hidden>
> wrote:
> > > Contrariwise, if I have six Scheme processes that have not freed
> their
> > > unused pages and the OS is constantly swapping, then the whole world
> > > gets much, much slower, especially at larger heap sizes.
>
> Were they all actively computing, or were some of the processes waiting for
> input?
>
> Some were waiting for input.
The unused pages in a waiting process may remain unused for some time,
in which case it would be a good idea to free up the pages (especially if a GC
just happened).
> The purpose of calling OS_free_pages is to make Scheme behave better
> as a citizen of OSland and avoid bogarting more physical memory than
> it needs, not necessarily to speed up Scheme computations.
Do you use the absolute minimum value for --heap that you can get away with?
--
~jrm