The often repeated recommendation to not exceed 8GB/25% of RAM for shared buffers in postgres is wrong. For pgbench scale 1500, on laptop with fast SSD and 32GB of RAM, parallelism of 16. s_b of 1GB, 8GB, 16GB, using huge pages. r/o: 115k, 100k, 185k r/w: 16300, 15100, 21500
-
-
IIRC the bigger improvements was the rate limiting of page cache dirtying a few years ago. Doesn't make a meaningful difference for the cases where our flushing logic is enabled, but when not it is a huge improvement. IIRC that was done after our own writeback control.
-
There were production cases were we saw stalls of *single* writes in the 1000s range. On rotational disks, obviously. Not fun for a database workload.
End of conversation
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.