Date: Mon, 4 Aug 2008 20:55:44 +0100 (BST)
From: Hugh Dickins <hugh@veritas.com>
To: Keith Packard <keithp@keithp.com>
cc: Nick Piggin <nickpiggin@yahoo.com.au>,
       Christoph Hellwig <hch@infradead.org>, Eric Anholt <eric@anholt.net>,
       linux-kernel@vger.kernel.org
Subject: Re: [PATCH] Export shmem_file_setup and shmem_getpage for DRM-GEM
In-Reply-To: <1217877645.24714.87.camel@koto.keithp.com>
Message-ID: <Pine.LNX.4.64.0808042055240.17041@blonde.site>
References: <1217573919-7496-1-git-send-email-eric@anholt.net> 
 <200808041902.23970.nickpiggin@yahoo.com.au>  <1217845590.24714.45.camel@koto.keithp.com>
  <200808042043.46710.nickpiggin@yahoo.com.au>  <1217850352.24714.66.camel@koto.keithp.com>
  <Pine.LNX.4.64.0808041720500.25617@blonde.site>  <1217870748.24714.79.camel@koto.keithp.com>
  <Pine.LNX.4.64.0808041855050.5717@blonde.site> <1217877645.24714.87.camel@koto.keithp.com>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1380
Lines: 28

On Mon, 4 Aug 2008, Keith Packard wrote:
> On Mon, 2008-08-04 at 19:39 +0100, Hugh Dickins wrote:
> > For how long are these objects' pages pinned in memory like this?
> 
> Forever? The only reason an object would get unpinned would be on
> eviction from the GTT, and objects will only be evicted if we fill the
> aperture with other stuff. When we add a register_shrinker callback,
> we'll also unpin pages at that point.
> 
> A busy system should have the GTT entirely full, and that will be
> somewhere between 256MB and 1GB.

Okay, thanks for the warning.  It sounds like the shrinker will be
important, but we'll also need to mark those pages as unevictable
while they're unshrunk.  (Usually when drivers grab a large number
of pages, they're not on any LRU to begin with: you're being nice
by choosing swappable LRU pages - in the tmpfs case - but enough
to upset the balance while they're not swappable.)  Offhand I can't
say what will be the appropriate way to do that, it's something we
need to revisit later (from your point of view it should amount to
one function call or flag set somewhere, not any grand redesign).

Hugh
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/