|
Metric |
Target |
Status |
Comment |
|
Number of CPUs |
400 |
2163 |
More than 60 % of available CPU resources are
non-dedicated facilities. The Grid3 environment effectively
shares resources not directly owned by the participating experiments (ref: list of sites) |
|
Number of users |
> 10 |
102 |
About 10% of the users are application administrators who do the majority of the jobsubmissions.
However, more than 102 users are authorized to use the resources through their respective VOMS
services.
|
|
Number of applications |
> 4 |
10 |
Seven scientific applications including at least one from each of the five
GriPhyN-iVDGL-PPDG participating experiments are being run on Grid3. In
addition, three computer science demonstrators (instrumented gridftp, a
multi-site I/O generator, and health monitors the grid) are run periodically. (ref:applications page) |
|
Number of sites running concurent applications
|
> 10 |
17 |
This number is related to the number of Computational Service (CS,CSE) sites defined on the
catalog page and varies with application. |
|
Data transfers per day |
> 2-3 TB |
3 TB |
Metric met with the aid of the GridFTP-demo which runs concurently with scientific applications (ref:GridFTP statics page) |
|
Percentage of resources used |
up to 90% |
< 70% |
Problems with core software stability, particularly MDS and the GRAM interface to local batch systems
prevented us from reaching this target early. Heading into SC week these problems are
being solved.
|
|
Effeciency of job completion |
up to 75 % |
varies |
This varies depending on the application, and defintion of
failure. Generally speaking, for well-run Grid3 sites and stable applications
this figure exceeds 90%.
|
|
Peak number of concurent jobs |
up to 1000 |
>500 |
Achieved on 11/13/03.
|
|
Rate of faults/crashes |
< 1/hr |
varies |
We will continually study this figure and update during the
course of the major demonstration week. |
|
Operations support load |
< 2 FTEs |
Typically ~10 |
As of 11/14/03.
|