diff options
author | Álvaro Herrera <alvherre@kurilemu.de> | 2025-09-26 16:21:28 +0200 |
---|---|---|
committer | Álvaro Herrera <alvherre@kurilemu.de> | 2025-09-26 16:21:28 +0200 |
commit | c4067383cb2c155c4cfea2351036709e2ebb3535 (patch) | |
tree | a67bccf518b9d4cbce6f43f63c8e7b5ea10b7663 /src/tutorial | |
parent | dbf8cfb4f02eb9ec5525de1761675f9babfd30e3 (diff) |
Split vacuumdb to create vacuuming.c/h
This allows these routines to be reused by a future utility heavily
based on vacuumdb.
I made a few relatively minor changes from the original, most notably:
- objfilter was declared as an enum but the values are bit-or'ed, and
individual bits are tested throughout the code. We've discussed this
coding pattern in other contexts and stayed away from it, on the
grounds that the values so generated aren't really true values of the
enum. This commit changes it to be a bits32 with a few #defines for
the flag definitions, the way we do elsewhere. Also, instead of being
a global variable, it's now in the vacuumingOptions struct.
- Two booleans, analyze_only (in vacuumingOptions) and analyze_in_stages
(passed around as a separate boolean argument), are really determining
what "mode" the program runs in -- it's either vacuum, or one of those
two modes. I have three adjectives for them: inconsistent,
unergonomic, unorthodox. Removing these and replacing them with a
mode enum to be kept in vacuumingOptions makes the code structure easier
to understand in a couple of places, and it'll be useful for the new
mode we add next, so do that.
Reviewed-by: Antonin Houska <ah@cybertec.at>
Discussion: https://postgr.es/m/202508301750.cbohxyy2pcce@alvherre.pgsql
Diffstat (limited to 'src/tutorial')
0 files changed, 0 insertions, 0 deletions