Re: recursive spinlocks. Shoot.

[Nikita Danilov]

Robert White writes:
 > This will, hopefully, be my out-comment on this thread.
 > 

[...]

 > 
 > 4) All locks (spin or otherwise) should obviously be held for the shortest
 > amount of time reasonably possible which still produces the correct result.
 > 
 > If this needs explaining...  8-)

It surely does.

Consider two loops:

(1)

spin_lock(&lock);
list_for_each_entry(item, ...) {
  do something with item;
}
spin_unlock(&lock);

versus

(2)

list_for_each_entry(item, ...) {
  spin_lock(&lock);
  do something with item;
  spin_unlock(&lock);
}

and suppose they both are equally correct. Now, in (2) total amount of
time &lock is held is smaller than in (1), but (2) will usually perform
worse on SMP, because:

. spin_lock() is an optimization barrier

. taking even un-contended spin lock is an expensive operation, because
of the cache coherency issues.

 > 

[...]

 > 
 > Rob.
 > 

Nikita.