| Author |
RE: Performance: VUPS Procedure |
VolkerHalle
Member
Posts: 104
Location: Germany
Joined: 02.04.10 |
| Posted on May 04 2011 05:55 |
|
|
Rick,
it shouldn't matter, which version of the VUPS procedure is being used, they both contain the same basic algorithm and produce the same VUPS data.
The OpenVMS version is also a factor when running this procedure, as well as the other load on the system. Note that this is a single CPU performance test and does not take into account SMP processors.
V7.2-1 is known to be reporting relatively low VUPS data with this procedure. Try booting from an OpenVMS CD with another version and run the VUPS procedure again.
I try to run run these tests after booting MINIMUM, to reduce the influence of other processes.
Volker. |
 |
| Author |
RE: Performance: VUPS Procedure |
rickw
Member
Posts: 3
Joined: 03.05.11 |
| Posted on May 04 2011 08:09 |
|
|
Hi Volker,
Thanks for the information. That explains the rating differences.
I'll see if I can schedule system down time to do the CD boot minimum.
But, both the DS20 and the RX6600 systems are production systems at my work so I may not be able to do such "intrusive" testing.
Rick |
|
|
| Author |
RE: Performance: VUPS Procedure |
abrsvc
Member
Posts: 108
Joined: 12.03.10 |
| Posted on May 09 2011 01:28 |
|
|
The most recently posted script was used. Also, the DS10s were running V7.3-2. The SMP overhead may have a little to do with the differences as well, although I would not expect such a drastic difference. I have a few DS10L machines as well. I'll try running on those to get a few numbers.
Dan |
|
|
