From: Tomas Vondra [mailto:tomas.vondra@2ndquadrant.com]
> 0.7% may easily be just a noise, possibly due to differences in layout
> of the binary. How many runs? What was the variability of the results
> between runs? What hardware was this tested on?
3 runs, with the variability of about +-2%. Luckly, all those three runs (incidentally?) showed slight performance
decreasewith the patched version. The figures I wrote are the highest ones.
The hardware is, a very poor man's VM:
CPU: 4 core Intel(R) Xeon(R) CPU E7-4890 v2 @ 2.80GHz
RAM: 4GB
> FWIW I doubt tests with such small small schema are proving anything -
> the cache/lists are likely tiny. That's why I tested with much larger
> number of relations.
Yeah, it requires many relations to test the repeated catcache eviction and new entry creation, which would show the
needto increase catalog_cache_max_size for users. I tested with small number of relations to see the impact of
additionalprocessing while the catcache is not full -- memory accounting and catcache LRU chain maintenance.
Regards
Takayuki Tsunakawa