----- Original Message -----
> From: "Benjamin Smedberg" <benja...@smedbergs.us>
> To: "Bas Schouten" <bschou...@mozilla.com>, dev-tech-...@lists.mozilla.org
> Cc: "mozilla.dev.platform group" <dev-platform@lists.mozilla.org>
> Sent: Monday, May 19, 2014 1:01:28 PM
> Subject: Re: OMTC on Windows
>
> On 5/18/2014 3:16 AM, Bas Schouten wrote:
> > remove a lot of code that we've currently been duplicating. Furthermore it
> > puts us on track for enabling other features on desktop like APZ, off main
> > thread animations and other improvements.
>
> What is APZ?
Sorry, Asynz Pan Zoom. The ability to scroll without main thread involvement.
> Is OMTC turned on in all graphics setups, accelerated and not? Are we
> testing browser performance/responsiveness in these setups?
It's turned on (after I reland) on all Windows builds, and it's already turned
on on OS X. So we are doing all the testing we regularly do. Very soon it will
also be on on Linux, which will essentially mean it's on everywhere.
> > - Memory numbers will increase somewhat, this is unavoidable, there's
> > several steps which have to be taken when doing off main thread
> > compositing (like double-buffering), which inherently use more memory.
>
> I am concerned about this in general, because we know that OOM is a real
> problem for many of our users currently, and we have very poor metrics
> on memory usage in the wild. So I have a couple questions:
>
> * Is it a fair statement to say that the primary benefit of OMTC is in
> browser responsiveness and jank?
Yes. There's significant code complication as well, but perhaps that's more a
secondary benefit :). There's also advantages for e10s, which should be noted
has significant potential to reduce OOM.
> * Are there settings/knobs which which can reduce the memory usage of
> this feature (other than disabling OMTC completely)? If so, do we have a
> plan for tuning those knobs on beta before this hits release?
Not really, where you used to use 1x layer surface memory you now use 2x. It
should be noted that in every situation where this would cause a significant
> * How will we know whether OMTC is a net win for users on low-memory
> computers, where increased memory usage and paging might offset the
> responsiveness benefits?
Let's watch OOM rate's carefully.
> * Are there accurate about:memory reporters for OMTC buffers?
For CPU memory, yes, not for GPU memory, as always that's a little tricky.
However it should be noted in situations where the amount of layers is so large
that that forms a problem there's more significant issues to address. In the
area where gfx memory usage becomes large we're usually talking images. The
memory usage for this situation will not increase.. i.e. An okay situation of
20MB might go to 40MB.. a bad situation of 1000MB will also only increase to
1020MB.
Bas
_______________________________________________
dev-platform mailing list
dev-platform@lists.mozilla.org
https://lists.mozilla.org/listinfo/dev-platform
