Horton

Re: Partitioned tables and [un]loggedness

Michael Paquier <michael@paquier.xyz>

View thread View on postgr.es
From: Michael Paquier <michael@paquier.xyz>
To: Alvaro Herrera <alvherre@alvh.no-ip.org>
Cc: Nathan Bossart <nathandbossart@gmail.com>, "David G. Johnston" <david.g.johnston@gmail.com>, Postgres hackers <pgsql-hackers@lists.postgresql.org>
Date: 2024-09-24T00:06:40Z
Lists: pgsql-hackers 
On Fri, Sep 20, 2024 at 09:37:54AM +0900, Michael Paquier wrote:
> What do you think about adding a test with DETACH FINALIZE when
> attempting it on a normal table, its path being under a different
> subcommand than DETACH [CONCURRENTLY]?
> 
> There are no tests for normal tables with DETACH CONCURRENTLY, but as
> it is the same as DETACH under the AT_DetachPartition subcommand, that
> does not seem worth the extra cycles.

Added an extra test for the CONCURRENTLY case at the end, and applied
the simplification.

Hmm.  Should we replace the error messages in transformPartitionCmd()
with some assertions at this stage?  I don't see a high cost in
keeping these even now, and keeping errors is perhaps more useful for
some extension code that builds AT_AttachPartition or
AT_DetachPartition commands?
--
Michael

Commits

  1. psql: Remove PARTITION BY clause in tab completion for unlogged tables

  2. Remove support for unlogged on partitioned tables

  3. Remove ATT_TABLE for ALTER TABLE ... ATTACH/DETACH

  4. Introduce ATT_PARTITIONED_TABLE in tablecmds.c

  5. Refactor some code for ALTER TABLE SET LOGGED/UNLOGGED in tablecmds.c

  6. Remove tab completion for CREATE UNLOGGED MATERIALIZED VIEW.