On Tue, Jul 26, 2011 at 05:05:15PM -0400, Tom Lane wrote:
> Noah Misch <noah@2ndQuadrant.com> writes:
> > That's the theoretical risk I wished to illustrate. Though this appears
> > possible on an abstract x86_64 system, I think it's unrealistic to suppose that
> > a dirty cache line could persist *throughout* the issuance of more than 10^9
> > invalidation messages on a concrete implementation.
>
> Dirty cache line, maybe not, but what if the assembly code commands the
> CPU to load those variables into CPU registers before doing the
> comparison? If they're loaded with maxMsgNum coming in last (or at
> least after resetState), I think you can have the problem without any
> assumptions about cache line behavior at all. You just need the process
> to lose the CPU at the right time.
True. If the compiler places the resetState load first, you could hit the
anomaly by "merely" setting a breakpoint on the next instruction, waiting for
exactly MSGNUMWRAPAROUND messages to enqueue, and letting the backend continue.
I think, though, we should either plug that _and_ the cache incoherency case or
worry about neither.
--
Noah Misch http://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Training & Services