Re: [git pull] scheduler fixes

[Linus Torvalds]

On Tue, 13 May 2008, Ingo Molnar wrote:
> 
> hm, this sounds like damage that is inflicted on itself by the XFS code. 

No. You're confusing what a counting semaphore is.

> Why does it signal to its waiters that "resource is available", when in 
> reality that resource is not available but immediately serialized via a 
> lock? (even if the lock might technically be some _other_ object)

So you have 'n' resources available, and you use a counting semaphore for 
that resource counting.

But you'd still need a spinlock to actually protect the list of resources 
themselves. The spinlock protects a different thing than the semaphore. 
The semaphore isn't about mutual exclusion - it's about counting resources 
and waiting when there are too many things in flight.

And you seem to think that a counting semaphore is about mutual exclusion. 
It has nothing what-so-ever to do with that. 

			Linus
--
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/