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

[Zach Brown <zach.brown@oracle.com>]

>> - We would now have some measure of task_struct concurrency.  Read  
>> that twice,
>> it's scary.

> That's the one scaring me in fact ... Maybe it will end up being an  
> easy
> one but I don't feel too comfortable...

Indeed, that was my first reaction too.  I dismissed the idea for a  
good six months after initially realizing that it implied sharing  
journal_info, etc.

But when I finally sat down and started digging through the  
task_struct members and, after quickly dismissing involuntary  
preemption of the fibrils, it didn't seem so bad.  I haven't done an  
exhaustive audit yet (and I won't advocate merging until I have) but  
I haven't seen any train wrecks.

> we didn't create fibril-like
> things for threads, instead, we share PIDs between tasks. I wonder if
> the sane approach would be to actually create task structs (or have a
> pool of them pre-created sitting there for performances) and add a way
> to share the necessary bits so that syscalls can be run on those
> spin-offs.

Maybe, if it comes to that.  I have some hopes that sharing by  
default and explicitly marking the bits that we shouldn't share will  
be good enough.

- z