Re: recovery.signal not cleaned up when both signal files are present

From: Michael Paquier <michael(at)paquier(dot)xyz>
To: David Steele <david(at)pgbackrest(dot)org>
Cc: Fujii Masao <masao(dot)fujii(at)gmail(dot)com>, 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 02:31:12
Message-ID: aY6M8HwCq6Zvt00Y@paquier.xyz
Views: Whole Thread | Raw Message | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Fri, Feb 13, 2026 at 12:55:15AM +0000, David Steele wrote:
> 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?

I am not convinced that going down to that is really necessary based
on the lack of complaints, and it could even be qualified as
disturbing for existing cases as well? Let's leave that as a
HEAD-only change.
--
Michael

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message John Naylor 2026-02-13 02:32:29 Re: tuple radix sort
Previous Message Zhijie Hou (Fujitsu) 2026-02-13 02:24:50 RE: Improve pg_sync_replication_slots() to wait for primary to advance