Remove small inefficiency in ExecARDeleteTriggers/ExecARUpdateTriggers.
Whilst poking at nodeModifyTable.c, I chanced to notice that while
its calls to ExecBR*Triggers and ExecIR*Triggers are protected by
tests to see if there are any relevant triggers to fire, its calls
to ExecAR*Triggers are not; the latter functions do the equivalent
tests themselves. This seems possibly reasonable given the more
complex conditions involved, but what's less reasonable is that
the ExecAR* functions aren't careful to do no work when there is
no work to be done. ExecARInsertTriggers gets this right, but the
other two will both force creation of a slot that the query may
have no use for. ExecARUpdateTriggers additionally performed a
usually-useless ExecClearTuple() on that slot. This is probably
all pretty microscopic in real workloads, but a cycle shaved is a
cycle earned.
Branch
------
master
Details
-------
https://git.postgresql.org/pg/commitdiff/65158f497a7d7523ad438b2034d01a560fafe6bd
Modified Files
--------------
src/backend/commands/trigger.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)