pgbench performance is lagging compared to Linux and DragonflyBSD?

[Garrett Cooper]

On Nov 6, 2012, at 8:55 AM, Wojciech Puchar <wojtek at wojtek.tensor.gdynia.pl> wrote:

>>> Tuning operating system for single benchmark is an example of that childish
>>> behaviour.
>> 
>> LOL. That's what "we" did several years ago :
>> http://people.freebsd.org/~kris/scaling/dfly.html
> 
> i've seen that page some time ago but i don't really care of it.
> i just wasn't interested.
> 
> Still - DOING such benchmark is good, as it can show general problems in used algorithms.
> 
> But working on software to make it better in some kind of synthetic benchmark is common in commercial software world. ("We have more performance per buck than company X")

"Synthetic benchmarks" as you put it shouldn't be the ultimate basis for a decision, but instead allow users to gauge whether or not a certain software or hardware configuration is suitable for their given workload. No more, no less. The fact that they're being used in this manner is a bit like a salesman selling snake oil as the results aren't necessarily the result of a "best" configuration for all competing platforms, but instead an unknown configuration in this case.

A similar statement about the importance of micro benchmarks can be made...

Thanks,
-Garrett