FW: What we need to log during experiments

["Douglas Olson" <dlolson@lbl.gov>]

-----Original Message-----
From: asim@lbl.gov [mailto:asim@lbl.gov] 
Sent: Tuesday, September 29, 1998 9:18 AM
To: Henrik Nordberg
Cc: Arie Shoshani; Luis M. Bernardo; Doug Olson
Subject: Re: What we need to log during experiments


Henrik Nordberg wrote:
> 
> Some things I think we need to log when we run our experiments:
>         ______                ________                 _______
>        |      |       A      |        |       B       |       |
>        | HPSS |--------------| RMDS03 |---------------| Linux |
>        |______|              |________|               |_______|
> 
>                                 CPU
> Log:
> 
> At startup:
> * cache size (CM)
> * queries (QE?)
> * SII's parameters

Cache Size is set in gc.config.
QUeries, Dave Malon is alo logging, and QE can do it also.
SII logs query, elapsed time for each retrieved file, processing time,
and retrieved file ID.

> 
> At runtime:
> * A's transfer rate, both our part and other possible parts (we should
> be alone) (CM + system (perfmon?))
> * B's transfer rate (system)
> * CPU usage on RMDS03 for our and other components (system)
> * file size (CM)
> * cache utilization (how full it is) (CM)

As far as I know, CM does check file size and cache utilization each
time there is a stage request from QM. So, just little more modification
on CM will do the better job...


> 
> Any more suggestions?
>         - Henrik
> _________________________________________
> Henrik Nordberg       <hnordberg@lbl.gov>
> Scientific Data Management Research Group
> Lawrence Berkeley National Laboratory


-- 
Alex Sim                        
MS 50B-3238                      http://sim.lbl.gov
DM, NERSC, LBNL                        ASim@lbl.gov
1 Cyclotron Road             office: (510) 495-2290
Berkeley, CA 94720              FAX: (510) 486-4004