* Added a destructor to clean up TLS memory at thread shutdown
* Refactored the TLS code to have platform independent code and a small platform dependent core with a fallback to generic code if platform dependent functions fail.
* Fixed recursion issues with SDL_GetErrBuf()
This lets us change things like this...
if (Failed) {
SDL_SetError("We failed");
return -1;
}
...into this...
if (Failed) {
return SDL_SetError("We failed");
}
Fixes Bugzilla #1778.
It's a long-dead platform, and we don't have any way to build for, test, or
maintain it, so there's no sense in doing acrobatics to support it.
If you need Windows CE support, use SDL 1.2. If you need Windows Phone support,
send SDL 2.0 patches for the newer Windows Mobile platform.
Implemented thread priority as the 'nice' value on Linux. High priority threads require root permissions (you shouldn't give your game root permissions though!)
Patrick Baggett 2011-02-16 22:58:33 PST
This enhancement is for both x86/x64 Windows.
The SDL implementation of mutexes uses the Win32 API interprocess
synchronization primitive called a "Mutex". This implementation is subpar
because it has a much higher overhead than an intraprocess mutex. The exact
technical details are below, but my tests have shown that for reasonably high
contention (10 threads on 4 physical cores), it has 13x higher overhead than
the Win32 CriticalSection API.
If this enhancement is accepted, I will write a patch to implement SDL mutexes
using the critical section API, which should dramatically reduce overhead and
improve scalability.
-- Tech details --
Normally, Win32 Mutexes are used across process boundaries to synchronize
separate processes. In order to lock or unlock them, a user->kernel space
transition is necessary, even in the uncontented case on a single CPU machine.
Win32 CriticalSection objects can only be used within the same process virtual
address space and thus to lock one, does not require a user->kernel space
transition for the uncontended case, and additionally may spin a short while
before going into kernel wait. This small spin allows a thread to obtain the
lock if the mutex is released shortly after the thread starts spinning, in
effect bypassing the overhead of user->kernel space transition which has higher
overhead than the spinning itself.
