Some additional tests run on my performance testing

[Bruce Evans]

On Thu, 28 Aug 2003, Sean Chittenden wrote:

> For the sake of eating my own advice and in an attempt to verify the
> numbers you suggest above, I loaded a DB with 8k and 16K blocks
> (translation: almost all write activities).
>
> With 8K blocks:
> 15.188u 3.404s 7:12.27 4.2%     209+340k 1251+0io 0pf+0w
> 14.867u 3.686s 7:32.54 4.0%     201+327k 1252+0io 0pf+0w
>
> avg wall clock sec to complete: 442
>
> With 16K blocks:
> 15.192u 3.312s 6:44.43 4.5%     198+322k 1253+0io 0pf+0w
> 15.120u 3.330s 6:51.43 4.4%     205+334k 1254+0io 0pf+0w
>
> avg wall clock sec to complete: 407
>
> Which is different than what your results suggest, but I'll take the
> 35sec/8% speedup any day of the week and twice on Sunday.  Granted

How much faster is it with smaller block sizes (same or smaller block
size for the filesystem in all cases)?  Large block sizes are unlikely
to be more efficient if they are much larger than the average transaction
size.

Bruce