Lockless uidinfo.
Pawel Jakub Dawidek
pjd at FreeBSD.org
Tue Aug 21 12:20:11 PDT 2007
On Tue, Aug 21, 2007 at 02:03:28PM -0400, John Baldwin wrote:
> On Saturday 18 August 2007 12:14:49 pm Pawel Jakub Dawidek wrote:
> > On Sat, Aug 18, 2007 at 08:50:41AM -0700, Alfred Perlstein wrote:
> > > * Pawel Jakub Dawidek <pjd at FreeBSD.org> [070818 07:59] wrote:
> > > > Yes, to lookup uidinfo you need to hold uihashtbl_mtx mutex, so once you
> > > > hold it and ui_ref is 0, noone will be able to reference it, because it
> > > > has to wait to look it up.
> > >
> > > And the field doesn't need to be volatile to prevent cached/opportunitic
> > > reads?
> >
> > The only chance of something like this will be the scenario below:
> >
> > thread1 (uifind) thread2 (uifree)
> > ---------------- ----------------
> > refcount_release(&uip->ui_ref))
> > /* ui_ref == 0 */
> > mtx_lock(&uihashtbl_mtx);
> > refcount_acquire(&uip->ui_ref);
> > /* ui_ref == 1 */
> > mtx_unlock(&uihashtbl_mtx);
> > mtx_lock(&uihashtbl_mtx);
> > if (uip->ui_ref > 0) {
> > mtx_unlock(&uihashtbl_mtx);
> > return;
> > }
> >
> > Now, you suggest that ui_ref in 'if (uip->ui_ref > 0)' may still have
> > cached 0? I don't think it is possible, first refcount_acquire() uses
> > read memory bariers (but we may still need ui_ref to volatile for this
> > to make any difference) and second, think of ui_ref as a field protected
> > by uihashtbl_mtx mutex in this very case.
> >
> > Is my thinking correct?
>
> 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.
--
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/ad862d70/attachment.pgp
More information about the freebsd-arch
mailing list