No, it depends totally on the application.  For financial and
physical inventory purposes where I have had occasion to use it,
the properties which were important were:

Hmmm. Probably I'm biased towards my compiler with an integer linear flavor field, where C-like "%" is always a pain, however you look at it.

I'm not sure of physical inventories with negative numbers though. In accounting, I thought that a negative number was a positive number with "debit" written above. In finance, no problem to get big deficits:-)

Now about the use case, I'm not sure that you would like to write your financial and physical inventory stuff within a pgbench test script, whereas in such a script I do expect when doing a modulo with the size of a table to have a positive result so that I can expect to find a tuple there, hence the desired "positive remainder" property for negative dividends.


Sent via pgsql-hackers mailing list (
To make changes to your subscription:

Reply via email to