Обсуждение: pgsql: injection_points: Add injection_points_list()
injection_points: Add injection_points_list() This function can be used to retrieve the information about all the injection points attached to a cluster, providing coverage for InjectionPointList() introduced in 7b2eb72b1b8c. The original proposal turned around a system function, but that would not be backpatchable to stable branches. It was also a bit weird to have a system function that fails depending on if the build allows injection points or not. Reviewed-by: Aleksander Alekseev <aleksander@timescale.com> Reviewed-by: Rahila Syed <rahilasyed90@gmail.com> Discussion: https://postgr.es/m/Z_xYkA21KyLEHvWR@paquier.xyz Branch ------ master Details ------- https://git.postgresql.org/pg/commitdiff/4eca711bc991954613261b7a314b1e8f5963815c Modified Files -------------- .../injection_points/expected/injection_points.out | 16 +++++++++ .../injection_points/injection_points--1.0.sql | 12 +++++++ .../modules/injection_points/injection_points.c | 39 ++++++++++++++++++++++ .../injection_points/sql/injection_points.sql | 7 ++++ 4 files changed, 74 insertions(+)
Hi Michael, > injection_points: Add injection_points_list() > > This function can be used to retrieve the information about all the > injection points attached to a cluster, providing coverage for > InjectionPointList() introduced in 7b2eb72b1b8c. > > The original proposal turned around a system function, but that would > not be backpatchable to stable branches. It was also a bit weird to > have a system function that fails depending on if the build allows > injection points or not. In injection_points_list() isn't `memset(values, 0, sizeof(values))` redundant? Also perhaps we want to pfree inj_points. These are minor issues of course.
On Thu, Jul 10, 2025 at 01:24:48PM +0300, Aleksander Alekseev wrote: > In injection_points_list() isn't `memset(values, 0, sizeof(values))` > redundant? Yes, I'm just finding this to be a cleaner practice. > Also perhaps we want to pfree inj_points. This is freed with the memory context of the function, so any way is fine IMO. -- Michael