Re: [PATCH] rwsem: reduce spinlock contention in wakeup code path

[Peter Zijlstra]

On Sat, Sep 28, 2013 at 12:33:36PM -0700, Linus Torvalds wrote:
> The old rwlock's really have been a disappointment - they are slower
> than spinlocks, and seldom/never end up scaling any better.  Their
> main advantage was literally the irq behavior - allowing readers to
> happen without the expense of worrying about irq's.

So in part that is fundamental to the whole rw-spinlock concept.

Typically lock hold times should be short for spinlock type locks and if
your hold times are short, the lock acquisition times are significant.

And a read acquisition is still a RMW operation on the lock, thus read
locks are still entirely bound by the cacheline transfer of the lock
itself.
--
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/