Re: [PATCH 0 of 4] Generic AIO by scheduling stacks

[Zach Brown]

> Take FPU state: memory copies and RAID xor functions use MMX/SSE and
> require that the full task state be saved and restored.

Sure, that much is obvious.  I was hoping to see what FPU state  
juggling actually requires.  I'm operating under the assumption that  
it won't be *terrible*.

> Task priority is another.  POSIX AIO lets you specify request  
> priority, and
> it really is needed for realtime workloads where things like keepalive
> must be processed at a higher priority.

Yeah.  A first-pass approximation might be to have threads with asys  
system calls grouped by priority.  Leaving all that priority handling  
to the *task* scheduler, instead of the dirt-stupid fibril  
"scheduler", would be great.  If we can get away with it.  I don't  
have a good feeling for what portion of the world actually cares  
about this, or to what degree.

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