Re: Snapshots on HEAD

Amos Jeffries wrote:
> As some of you may have noticed there have been no snapshots on HEAD for
> about a week now. I'll stick my hand up for causing it. But in a good way.
>
> I've added a dependency on snapshots so they only generate when the
> TestBed gives the code a clean bill of health.
>
> This has brought to view several assertions which have been occurring in
> the IO and IP layers. I'd like to add this test layer to 3.1 also, which
> presently shows the errors but doesn't stop snapshots. The current issues
> need to be resolved first.
>
> I've spent some time this week trying to find fixes without much luck.
> It's open season on them if anyone can figure it out.
>
> The issues I'm aware of so far are:
>
> * errors in DiskIO when no module is available (NULL result from 'smart'
> module location).
>
> * unknown segfault in testUfs handling. possibly due to the above.

Finally tracked down these first two. It was the implicit declaration of
DiskIO modules not happening fast enough. Making an explicit +
deterministic trigger point seems to fix it.

Amos

-- 
Please be using
   Current Stable Squid 2.7.STABLE5 or 3.0.STABLE10
   Current Beta Squid 3.1.0.2