| From: | David Steele <david(at)pgbackrest(dot)org> |
|---|---|
| To: | Michael Paquier <michael(at)paquier(dot)xyz>, Fujii Masao <masao(dot)fujii(at)gmail(dot)com> |
| Cc: | Nikolay Samokhvalov <nik(at)postgres(dot)ai>, pgsql-hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org> |
| Subject: | Re: recovery.signal not cleaned up when both signal files are present |
| Date: | 2026-02-13 00:55:15 |
| Message-ID: | d914df67-626c-41ee-9ebe-8015404885a0@pgbackrest.org |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On 2/10/26 11:52, Michael Paquier wrote:
> On Tue, Feb 10, 2026 at 12:26:36PM +0900, Fujii Masao wrote:
>> +1 to apply this change only to the master branch. Patch attached.
>
> It looks like something we should have a test for, at least..
+1 for a test.
> + /*
> + *
> + * If both signal files are present, standby signal file takes precedence.
> + * If neither is present then we won't enter archive recovery.
> + */
>
> This comment's format is incorrect.
Other than the comment the patch looks good overall.
Reluctantly I have to agree to not back patch this. I'm not sure how
this change would break existing recovery processes but experience tells
me that it probably would.
Instead -- I wonder if we could add a warning in the back branches?
Regards,
-David
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Henson Choi | 2026-02-13 01:14:26 | Re: Row pattern recognition |
| Previous Message | Andres Freund | 2026-02-13 00:51:18 | Re: Replace literal 0 values with the appropriate Invalid* constants |