[PATCH xserver] FlushAllOutput: Only call FlushCallbacks when actually flushing data

[Keith Packard]

Adam Jackson <ajax at nwnk.net> writes:

> Here's an epoll branch rebased to master, with poll emulation for
> Windows, and a pair of proof-of-concept patches at the end to allow
> (force) testing on pollful systems:

So you're just emulating poll with select, which should work on
Windows. that seems like a good starting place; I'd encourage the
Windows hackers to refine that to handle arbitrary numbers of FDs.

> I tested this with 32 parallel x11perf -noop's on Linux, and while it
> does work, reliable numbers are a bit hard to come by. The x11perf
> processes take (wildly) varying amounts of time to complete, such that
> the last few runs to complete show inflated nop dispatch rates because
> they're competing with fewer clients. I don't know yet how much of that
> is X's scheduler and how much is the kernel's. 

I've been running many instances of 'plaid' in parallel as that doesn't
scale it's work based on the server performance.

Thanks for taking a stab at this; it looks good to me. I'd love for
someone to give it a spin on Windows and make sure it actually works.

-- 
-keith
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 810 bytes
Desc: not available
URL: <https://lists.x.org/archives/xorg-devel/attachments/20160712/d3dcd9a8/attachment.sig>