Continue my quest to make 002_blocks.pl pass reliably.
The latest buildfarm failures show that after the insert, we don't
actually wait long enough for WAL summarization to catch up, apparently
because the on disk state gets updated before the in-memory state, and
so by checking the on disk state to see whether we're caught up and then
the in-memory state to see where exactly how far we've progressed, we
can, if unlucky, derive an older value of summarized_lsn, messing up
the rest of the test.
Attempt to fix this by using pg_available_wal_summaries() everywhere in
the test and pg_get_wal_summarizer_state() nowhere.
Per buildfarm.
Branch
------
master
Details
-------
https://git.postgresql.org/pg/commitdiff/19a829a3270fb083b3d6ae967cd3b3c02a170a38
Modified Files
--------------
src/bin/pg_walsummary/t/002_blocks.pl | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)