protty

This trades memory usage for better latency (and maybe throughput) FWIW.

Are posix timers useful for the standard library? Userspace implementations of timers are almost always faster due to not having to go through syscalls to update the Timer state or...

I was more so trying to figure out a use case for posix timers, as I'm still not sure. Genuinely curious not only for justification purposes. The standard library is...

`undefined` is a poison value; Comparisons to `undefined` produce bools that are `undefined`. Branching on `undefined` is undefined behavior and the compiler can tell you if you try `if (undefined)`...

If this is upstream, it indicates that it needs adjustment but that the fields remain relatively the same https://android.googlesource.com/platform/bionic/+/40eabe2/libc/include/pthread.h#230

Yea, 1-5 can be simplified/updated to the following: 1) All types require only 1 word of storage (unlike stdlib which stores more state for poison detection). 2) Static initializers for...

Sorry it's been a while. `6)` looks like a duplicate of `5)`. Could it be removed?

* Has anyone looked into the condition variable darwin libpthread? Works with a futex-based api (ulock), uses 64bits of space, doesn't do extra wakes or require requeue, and is simpler...

Ah, fair point for the 10.7+ requirement. Does the new `Mutex` impl need timed wait? SRWLock and the [current API](https://doc.rust-lang.org/std/sync/struct.Mutex.html) don't support it.

Condvar's wait_timeout functions look like they always return the MutexGuard (excluding when poisoned). This implies that the mutex itself must be locked on return, hence no need for Mutex to...