Please #PostgreSQL hackers, we'd like to understand the significant performance difference between count(*) and count(1).https://twitter.com/lukaseder/status/1174621016187973632 …
So JIT is not in play in your test since the costs aren't high enough. How repeatable are your timings? Can you try the generate_series version?
-
-
I tried and tried again with an even larger set, couldn't find jit involved in explain planspic.twitter.com/2uNw1H7cd2
-
Did you compile with the --with-llvm option? (you can check via select setting from pg_config where name='CONFIGURE';) What are your actual timings for the generate_series version of the test?
- 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.