Thread (8 messages) 8 messages, 7 authors, 2009-08-27

Re: spin_is_locked() broken for uniprocessor?

From: Leon Woestenberg <hidden>
Date: 2009-08-19 11:16:49
Also in: lkml

Hello,

On Wed, Aug 19, 2009 at 12:53 PM, Alan Cox[off-list ref] wrote:
On Wed, 19 Aug 2009 10:38:06 +0100

in drivers because there is driver code that uses spin_is_locked() in
fairly sensible fashion when dealing with locking.
One use is to measure lock contention hits on a particular spin lock.


However I wonder if there are tracing capabilities to measure lock
contention on a particular lock?

Currently I have inserted code much like this to get a feeling on the
contention:

this_cpu = get_cpu();
put_cpu();
contention = spin_is_locked(&lock);
spin_lock*(&lock);
if (contention) {
  /* spin lock was contended, prev_cpu, this_cpu */
  /* no hard guarantee, as we had a possible race inbetween
is_locked() and lock(), but works for driver/irq spin lock */
}

/* critical section */

prev_cpu = this_cpu;
spin_unlock*(&lock);

Regards,
-- 
Leon
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help