Re: pgsql: Fix up misuse of "volatile" in contrib/xml2.
От | Michael Paquier |
---|---|
Тема | Re: pgsql: Fix up misuse of "volatile" in contrib/xml2. |
Дата | |
Msg-id | aG2qhGodemZfrxcn@paquier.xyz обсуждение исходный текст |
Ответ на | pgsql: Fix up misuse of "volatile" in contrib/xml2. (Tom Lane <tgl@sss.pgh.pa.us>) |
Ответы |
Re: pgsql: Fix up misuse of "volatile" in contrib/xml2.
|
Список | pgsql-committers |
On Tue, Jul 08, 2025 at 09:00:39PM +0000, Tom Lane wrote: > Fix up misuse of "volatile" in contrib/xml2. > > Also fix a number of places where variables that are assigned to > within a PG_TRY and then used after it were not initialized or > not marked as volatile. (A few buildfarm members were issuing > "may be used uninitialized" warnings about some of these variables, > which is what drew my attention to this area.) In most cases > these variables were being set as the last step within the PG_TRY > block, which might mean that we could get away without the "volatile" > marking. But doing that seems unsafe and is definitely not per our > coding conventions. > > These problems seem to have come in with 732061150, so no need > for back-patch. Oops, thanks. I was not aware of these reports, and the buildfarm was not showing any red, the CI looked fine and my machine did not complain with a rather new gcc. What were the buildfarm members impacted? Did these use a switch and/or a specific compiler that helped in detecting these problems? -- Michael
Вложения
В списке pgsql-committers по дате отправления: