diff options
| author | David Rowley <drowley@postgresql.org> | 2024-08-01 01:27:54 +1200 |
|---|---|---|
| committer | David Rowley <drowley@postgresql.org> | 2024-08-01 01:27:54 +1200 |
| commit | 51895d08b41a5e5ed7e7a477fb5aa36213347ea7 (patch) | |
| tree | 1724a623e66553feade04f89002aafb9a0e3ab42 /src/backend/commands/variable.c | |
| parent | 924a08b76f5d9f89b2569caed26113f0a020c644 (diff) | |
| download | postgresql-51895d08b41a5e5ed7e7a477fb5aa36213347ea7.tar.gz postgresql-51895d08b41a5e5ed7e7a477fb5aa36213347ea7.zip | |
Doc: mention executor memory usage for enable_partitionwise* GUCs
Prior to this commit, the docs for enable_partitionwise_aggregate and
enable_partitionwise_join mentioned the additional overheads enabling
these causes for the query planner, but they mentioned nothing about the
possible surge in work_mem-consuming executor nodes that could end up in
the final plan. Dimitrios reported the OOM killer intervened on his
query as a result of using enable_partitionwise_aggregate=on.
Here we adjust the docs to mention the possible increase in the number of
work_mem-consuming executor nodes that can appear in the final plan as a
result of enabling these GUCs.
Reported-by: Dimitrios Apostolou
Reviewed-by: Ashutosh Bapat
Discussion: https://postgr.es/m/3603c380-d094-136e-e333-610914fb3e80%40gmx.net
Discussion: https://postgr.es/m/CAApHDvoZ0_yqwPFEpb6h261L76BUpmh5GxBQq0LeRzQ5Jh3zzg@mail.gmail.com
Backpatch-through: 12, oldest supported version
Diffstat (limited to 'src/backend/commands/variable.c')
0 files changed, 0 insertions, 0 deletions