Attempt to fix newly added Memoize regression test
Both drongo and fairywren seem not to like a new regression test added
by 2cca95e17. These machines show a different number of actual rows in
the EXPLAIN ANALYZE output. Since the number of actual rows is divided by
the number of loops, I suspec
Compare varnullingrels too in assign_param_for_var().
Oversight in 2489d76c4. Preliminary analysis suggests that the
problem may be unreachable --- but if we did have instances of
the same column with different varnullingrels, we'd surely need
to treat them as different Params.
Discussion: https
Compare varnullingrels too in assign_param_for_var().
Oversight in 2489d76c4. Preliminary analysis suggests that the
problem may be unreachable --- but if we did have instances of
the same column with different varnullingrels, we'd surely need
to treat them as different Params.
Discussion: https
Detect Julian-date overflow in timestamp[tz]_pl_interval.
We perform addition of the days field of an interval via
arithmetic on the Julian-date representation of the timestamp's date.
This step is subject to int32 overflow, and we also should not let
the Julian date become very negative, for fear
Detect Julian-date overflow in timestamp[tz]_pl_interval.
We perform addition of the days field of an interval via
arithmetic on the Julian-date representation of the timestamp's date.
This step is subject to int32 overflow, and we also should not let
the Julian date become very negative, for fear
Detect Julian-date overflow in timestamp[tz]_pl_interval.
We perform addition of the days field of an interval via
arithmetic on the Julian-date representation of the timestamp's date.
This step is subject to int32 overflow, and we also should not let
the Julian date become very negative, for fear
Detect Julian-date overflow in timestamp[tz]_pl_interval.
We perform addition of the days field of an interval via
arithmetic on the Julian-date representation of the timestamp's date.
This step is subject to int32 overflow, and we also should not let
the Julian date become very negative, for fear
Detect Julian-date overflow in timestamp[tz]_pl_interval.
We perform addition of the days field of an interval via
arithmetic on the Julian-date representation of the timestamp's date.
This step is subject to int32 overflow, and we also should not let
the Julian date become very negative, for fear
Detect Julian-date overflow in timestamp[tz]_pl_interval.
We perform addition of the days field of an interval via
arithmetic on the Julian-date representation of the timestamp's date.
This step is subject to int32 overflow, and we also should not let
the Julian date become very negative, for fear
Temporary patch to help debug pg_walsummary test failures.
The tests in 002_blocks.pl are failing in the buildfarm from time to
time, but we don't know how to reproduce the failure elsewhere. The
most obvious explanation seems to be the unexpected disappearance of a
WAL summary file, so bump up th
Combine FSM updates for prune and no-prune cases.
lazy_scan_prune() and lazy_scan_noprune() update the freespace map
with identical conditions; combine them. This consolidation is easier
now that cb970240f13df2b63f0410f81f452179a2b78d6f moved visibility map
updates into lazy_scan_prune().
While c
Split some code out from MergeAttributes()
- Separate function to merge a child attribute into matching inherited
attribute: The logic to merge a child attribute into matching
inherited attribute in MergeAttribute() is only applicable to
regular inheritance child. The code is isolated and c
Make spelling of cancelled/cancellation consistent
This fixes places where words derived from cancel were not using their
common en-US ugly^H^H^H^Hspelling.
Author: Jelte Fennema-Nio
Reported-by: Thomas Munro
Discussion:
https://postgr.es/m/ca+hukg+lrq+ty6ywxf5572qnq8kwxgwg5n4fseccuap685n...@m
MergeAttributes code deduplication
The code handling NOT NULL constraints is duplicated in blocks merging
the attribute definition incrementally. Deduplicate that code.
Author: Ashutosh Bapat
Discussion:
https://www.postgresql.org/message-id/flat/52a125e4-ff9a-95f5-9f61-b87cf447e...@eisentraut
Reindex toast before its main relation in reindex_relation()
This commit changes the order of reindex on a relation so as a toast
relation is processed before its main relation.
The original order, where a rebuild was first done for the indexes on
the main table, could be a problem in the event o
15 matches
Mail list logo
