Robert Haas wrote:
>
> The biggest flaw in the benchmark by far has got to be that it was
> done with a ramdisk, so it's really only measuring CPU consumption.
> Measuring CPU consumption is interesting, but it doesn't have a lot to
> do with throughput in real-life situations.
>
... and memory access. Measuring these two in isolation from any
(real/usual) io system is interesting but perhaps only as a curiosity -
however, it would become much more interesting if we could see how the
results change when a disk based filesystem is used (or even raw for the
big O and innodb and filesystem for postgres...).
regards
Mark