Re: spinlock which can morph into a mutex

[Miquel van Smoorenburg]

On Fri, 2009-12-18 at 18:14 +0100, Thomas Gleixner wrote:
> On Fri, 18 Dec 2009, Miquel van Smoorenburg wrote:
>  I think I need a spinlock that can morph into a mutex ..
> 
> Is the writer frequency and the possible contention so high that you
> need a spinlock at all ?

Possibly - I don't want to degrade the performance of existing code
(which uses a spinlock).
 
> Test it :)

Good point.

> If the mutex is still to heavy weight for you, then you can solve it
> without implementing another weird concurrency control:
> 
>        	  wait_event_(un)interruptible(&hash_wq, !hash_update_active);
>
>        hash_update_active = 1;
>        ....
>        hash_update_active = 0;
>        wake_up(&hash_wq);

Ah, ofcourse. Thanks for pointing that out!

Thanks everybody for your input. I gained quite a bit of insight.

Mike.

--
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/