Lockless uidinfo.

[Pawel Jakub Dawidek]

On Tue, Aug 21, 2007 at 09:19:02PM +0200, Pawel Jakub Dawidek wrote:
> > Memory barriers on another CPU don't mean anything about the CPU thread 2 is 
> > on.  Memory barriers do not flush caches on other CPUs, etc.  Normally when 
> > objects are refcounted in a table, the table holds a reference on the object, 
> > but that doesn't seem to be the case here. [...]
> 
> But the memory barrier from 'mtx_lock(&uihashtbl_mtx)' above
> 'if (uip->ui_ref > 0)' would do the trick and I can safely avoid using
> atomic read in this if statement, right?
> 
> > [...] Have you tried doing something 
> > very simple in uifree():
> > 
> > {
> > 	mtx_lock(&uihashtbl_mtx);
> > 	if (refcount_release(...)) {
> > 		LIST_REMOVE();
> > 		mtx_unlock(&uihashtbl_mtx);
> > 		...
> > 		free();
> > 	} else
> > 		mtx_unlock(&uihashtbl_mtx);
> > }
> > 
> > I wouldn't use a more complex algo in uifree() unless the simple one is shown 
> > to perform badly.  Needless complexity is a hindrance to future maintenance.
> 
> Of coure we could do that, but I was trying really hard to remove
> contention in the common case. Before we used UIDINFO_LOCK() in the
> common case, now you suggesting using global lock here, and I'd really,
> really prefer using one atomic only.
> 
> > Also, even if you do go with the more complex route, I'd rather you reduce 
> > diffs with the current code by keeping the test as 'uip->ui_ref == 0' and 
> > keeping the removal code in the if-block.
> 
> Will do.
> 
> > In chgproccnt() you should use atomic_fetchadd_long() to avoid a race when 
> > reading ui_proccnt.
> > 
> > 
> > 	old = atomic_fetchadd_long(&uip->ui_proccnt, diff);
> > 	if (old + diff < 0)
> > 		printf("....");
> 
> I'm aware of this race, but I don't find closing it that much important.
> We won't generate false positive here. My vote is to leave it as it is,
> because atomic_fetchadd_long() is slower on some archs than
> atomic_add_long(), ie. it is implemented using atomic_cmpset_long()
> loop, and as I checked by running 8 processes on 8way machine with
> older code that used atomic_cmpset_long() loop in 'diff > 0' case,
> there is almost one extra loop on every call, which makes it about 6%
> slower.
> 
> > OTOH, atomic_fetchadd_long() doesn't yet exist, so you will need to fix that, 
> > or just always use an atomic_cmpset() loop.
> 
> I already implemented those.

New patch is here:

	http://people.freebsd.org/~pjd/patches/uidinfo_waitfree.patch

-- 
Pawel Jakub Dawidek                       http://www.wheel.pl
pjd at FreeBSD.org                           http://www.FreeBSD.org
FreeBSD committer                         Am I Evil? Yes, I Am!
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 187 bytes
Desc: not available
Url : http://lists.freebsd.org/pipermail/freebsd-arch/attachments/20070821/d80b2456/attachment.pgp