Marcin.Zukowski at cwi.nl
Tue Aug 2 16:58:59 CEST 2005
> Is it possible to look at the X100 source code or more detailed
> information right now?
As Peter mentioned, the open-source aspect of the X100 is not decided at
> ... One
> thing that I don't understand is whether the X100 scan retrieves
> vectors from _all_ participating BATs.
The Scan operator in one next() call delivers vectors from all the
relevant _columns_ (we don't have BATs anymore). Naturally, the scans
are buffered so the I/O granularity is much larger than a vector size.
> I'm also wondering how the size
> of the cache (and thus the size of the vector) is determined.
Currently there is no automatic tuning of the vector size. Usually we
use a size of ca.1k but for some queries and/or hardware platforms other
sizes would be better. We plan to do some work on this issue in the
future to make the system more complete.
To find the memory system characteristics we will most probably use a
"Calibrator" program developed by Stefan Manegold:
It is also a part of the MonetDB distribution and a module available in MIL.
Thanks for your interest in our work and good luck with your project.
More information about the developers-list