Re: RAM Cache vs the Pageout Demon
Re: RAM Cache vs the Pageout Demon
- Subject: Re: RAM Cache vs the Pageout Demon
- From: Russ <email@hidden>
- Date: Fri, 20 Oct 2006 20:13:13 -0700 (PDT)
They can be based on disk data. The disk-based source data can come from any
number of file-reading libraries, so turning off caching on a per-file basis
isn't possible. It's certainly conceivable there could be a conflict between my
RAM cache and the system file cache. In general, given a choice between paging
out an apparently-inactive page from my process, or dropping a page from the
file cache for a file requested by my app, it has to drop the (read-once!) file
cache page 100% of the time.
--- Paul Ripke <email@hidden> wrote:
> On Fri, Oct 20, 2006 at 12:55:47PM -0700, Russ wrote:
> > My commercial app has a ram cache system for image sequence playback;
> images
> > can be tens of megabytes and there can be gigabytes of them. On OS X, when
> the
> > RAM cache is large, it looks like the darwin pageout demon is activating
> > prematurely, paging out part of the RAM cache preemptively to meet its
> > free-space target, even though there is no competing demand. Consequently,
> the
> > app thrashes catastrophically to its knees.
>
> I assume all these images are read in from disk - since you're doing
> your own caching, are you using F_NOCACHE with fcntl(2)? It may be
> that the aggressive file caching done by the kernel is fighting
> with your cache for RAM.
>
> Cheers,
> --
> Paul Ripke
> Unix/OpenVMS/TSM/DBA
> I love deadlines. I like the whooshing sound they make as they fly by.
> -- Douglas Adams
>
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
_______________________________________________
Do not post admin requests to the list. They will be ignored.
Darwin-dev mailing list (email@hidden)
Help/Unsubscribe/Update your Subscription:
This email sent to email@hidden