On Sat, 30 Aug 2008, Dâniel Fraga wrote:

On Fri, 29 Aug 2008 16:07:04 +0300 (EEST)
"Ilpo Järvinen" [off-list ref] wrote:

quoted

...as it would probably not be wise to make a full dump available (that it 
would contain every syscall). Alternatively, you can create one full dump 
for yourself and just grep the relevant parts. There may be need to strace
more than one process (all dovecot related).

	While waiting for a stall, I was thinking here: is there any
chance it could be a bug generated by gcc 4.3? I saw the date gcc 4.3.0
was released and it's just after 2.6.24 and before 2.6.25...

	I was using gcc 4.3.1 and now 4.3.2... but maybe I could try go
back to gcc 4.2.4 to test...

That's one option. If you do that, you could try catching two flies at the 
same time by selecting something else than tickless.

	Which version of gcc you developers are using?

I guess that on x86 most use some recent/semi-recent by default but there 
are some with old as well, while the non-x86 archs tend to have more often 
a bit older gccs I guess.

Anyway, if gcc did something wrong, it is still mostly correct, ie., 
there's just some race (which is likely non-corrupting even). And hitting 
that might not be very easy for some of the devs.

-- 
 i.