Fix inconsistent quoting for some options in TAP tests
This commit addresses some inconsistencies with how the options of some
routines from PostgreSQL/Test/ are written, mainly for init() and
init_from_backup() in Cluster.pm. These are written as unquoted, except
in the locations updated here.
Apply more consistent style for command options in TAP tests
This commit reshapes the grammar of some commands to apply a more
consistent style across the board, following rules similar to
ce1b0f9da03e:
- Elimination of some pointless used-once variables.
- Use of long options, to self-document be
Revert "Add redo LSN to pgstats files"
This reverts commit b860848232aa, that was added as a prerequisite for
the support of pgstats data flush across checkpoints, linking a pgstats
file to a specific checkpoint redo LSN.
As reported, this is proving to be currently problematic when going
through
pg_dump, pg_dumpall, pg_restore: Add --no-policies option.
Add --no-policies option to control row level security policy handling
in dump and restore operations. When this option is used, both CREATE
POLICY commands and ALTER TABLE ... ENABLE ROW LEVEL SECURITY commands
are excluded from dumps and
contrib/isn: Make weak mode a GUC setting, and fix related functions.
isn's weak mode used to be a simple static variable, settable only
via the isn_weak(boolean) function. This wasn't optimal, as this
means it doesn't respect transactions nor respond to RESET ALL.
This patch makes isn.weak a GU
reindexdb: Fix the index-level REINDEX with multiple jobs
47f99a407d introduced a parallel index-level REINDEX. The code was written
assuming that running run_reindex_command() with 'async == true' can schedule
a number of queries for a connection. That's not true, and the second query
sent usin
reindexdb: Fix the index-level REINDEX with multiple jobs
47f99a407d introduced a parallel index-level REINDEX. The code was written
assuming that running run_reindex_command() with 'async == true' can schedule
a number of queries for a connection. That's not true, and the second query
sent usin
pg_createsubscriber: Remove some code bloat in the atexit() callback
This commit adjusts some code added by e117cfb2f6c6 in the atexit()
callback of pg_createsubscriber.c, in charge of performing post-failure
cleanup actions. The code loops over all the databases specified, and
it is changed here
