From: Heikki Linnakangas <hlinnaka@iki.fi>
To: Thomas Munro <thomas.munro@gmail.com>
Cc: Heikki Linnakangas <heikki.linnakangas@iki.fi>
Cc: pgsql-committers@lists.postgresql.org, Tom Lane <tgl@sss.pgh.pa.us>
Subject: Re: pgsql: Refactor libpq state machine for negotiating encryption
Date: Fri, 12 Apr 2024 19:57:02 +0300
Message-ID: <6a720823-d946-4f8e-a111-ee0998082b73@iki.fi> (raw)
In-Reply-To: <d28cb2c5-4ea8-406d-937a-9e292ebfd5d5@iki.fi>
References: <E1rtdlT-001383-HT@gemulon.postgresql.org>
<CA+hUKG+HRTtB+x+KKKj_cfX6sNhbeGuqmGxjGMwdVPG7YGFP8w@mail.gmail.com>
<32196.1712791542@sss.pgh.pa.us>
<CA+hUKGK5Ku5rH2aXEEcmGZEJmrxOskmk+HK-k2oSduPcgvNVkA@mail.gmail.com>
<d28cb2c5-4ea8-406d-937a-9e292ebfd5d5@iki.fi>
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@sss.pgh.pa.us> wrote:
>>> Thomas Munro <thomas.munro@gmail.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)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-committers@postgresql.org
Cc: hlinnaka@iki.fi, thomas.munro@gmail.com, heikki.linnakangas@iki.fi, tgl@sss.pgh.pa.us
Subject: Re: pgsql: Refactor libpq state machine for negotiating encryption
In-Reply-To: <6a720823-d946-4f8e-a111-ee0998082b73@iki.fi>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox