Re: pgsql: Refactor libpq state machine for negotiating encryption

On 11/04/2024 20:07, Heikki Linnakangas wrote:
> On 11/04/2024 02:33, Thomas Munro wrote:
>> On Thu, Apr 11, 2024 at 11:25 AM Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> wrote:
>>> Thomas Munro <thomas(dot)munro(at)gmail(dot)com> writes:
>>>> If -Dssl=none and -Dgssapi=disabled, compilation of fe-connect.c
>>>> fails: call to undeclared function 'encryption_negotiation_failed'. I
>>>> didn't look too hard, but maybe ENABLE_GSS and USE_GSS are confused?
>>>
>>> For me, configure --with-gssapi fails like that, but the other three
>>> combinations of --with-openssl and --with-gssapi compile OK. I don't
>>> find it terribly surprising that the buildfarm isn't covering that
>>> combination ...
>>
>> Oops, right, correction to my report: it is indeed -Dssl=none
>> -Dgssapi=enabled that is broken, not the other combinations.
>
> Yes, I misspelled ENABLE_GSS as USE_GSS.
>
> After fixing that, the new tests are failing; the expected output for
> many of the cases is different when GSSAPI support is not compiled in. I
> think the test tables need to be rearranged some more to take that into
> account, or we will end up with a ridiculous amount of different
> expected outputs.
>
> I will take a closer look at that tomorrow. As a bandaid fix, we could
> temporarily disable the new tests with that combination of configure
> options, it's still better test coverage than not having the tests at
> all. But given that no buildfarm members are testing that combination I
> think it can wait a day.

Fixed the compilation with that combination, and the expected test
output. Thanks for the report!

--
Heikki Linnakangas
Neon (https://neon.tech)