Commits on Nov 18, 2023

1. Fix producer sample so that it picks up usable defaults …

   The producer sample currently fails with this error:
   
   > `time=2023-11-18T13:37:05.945-08:00 level=ERROR msg=failed error="error inserting jobs: error inserting many jobs: ERROR: new row for relation \"river_job\" violates check constraint \"max_attempts_is_positive\" (SQLSTATE 23514)"`
   
   Digging into it, it turns out that this is because (1) batch insert's
   raw query uses `COPY FROM` so it's not allowed to have `coalesce` in it
   like the single insert, (2) defaults are added for bulk inserts by
   River's Go code, but at the client level and not the adapter level, and
   (3) the producer sample manually creates an adapter to insert jobs with.
   
   So it worked around the use of normal client inserts using an adapter
   instead, wasn't adding its own `MaxAttempts` and no default was provided,
   so it failed the on the positive check constraint.
   
   I could fix this by putting a `MaxAttempts` into the insert parameters,
   but I don't think this is the right way to go -- instead, the sample
   should just bulk insert through the client. There might be some nominal
   performance benefit to inserting through the adapter instead, but even
   if there is, I don't think it'd be that honest to use it in a benchmark
   because our users would be inserting through the client anyway. Using
   the client also simplifies the code quite a bit.

   

   brandur committed Nov 18, 2023
   Configuration menu

   • View commit details
   • Copy full SHA for 26bbdca
   • Browse repository at this point

   Copy the full SHA

   26bbdca View commit details

   Browse the repository at this point in the history