Meeting agenda
Friday, October 21, 2005
|
|
Session |
|
9:00 – 9:30 |
Breakfast,
Registration
|
|
9:30 – 10:00 |
Welcome and
Announcements |
|
10:00– 10:50 |
Bandwidth and Latency: Their Changing Impact on
Performance Bandwidth and latency are
familiar topics for IT. Both relate to
system performance, but in a different fashion; both have improved
significantly over the years, but at a very different pace. Their performance impact is also changing
as hardware and software technology progresses. We may have to update design strategies in
hardware, software, and protocols to cope.
This paper examines their impact to response time from a performance
analysis perspective and sheds some new light on how to manage the bandwidth
imbalance at different devices and imbalance between bandwidth and latency. Dr.
|
|
10:50 – 11:00 |
Break |
|
11:00 – 11:50 |
SAS – Meeting Sponsor
SAS IT Management
Solutions let you go beyond traditional IT performance management and
leverage the full potential of each IT resource across the enterprise. SAS IT
Management Solutions provide integrated and intuitive products for IT
management across the enterprise, sophisticated analytical reporting and data
visualization and reliable information on IT usage, resources, services and
costs.
Paul Bachteal, SAS |
|
11:50 – 13:00 |
Lunch |
|
13:00 – 13:50 |
A Practical View of Heavy-Tailed
Distributions and Their Effects on Computer and Network Performance
We first give a short
mathematical description of heavy-tailed distributions and then focus on the
subclass of Power-Tailed (PT) type (including the truncated variety, TPT). We
then show various places where they occur, e.g.: CPU times; file sizes; total
time taken by jobs with failure and RESTART; self-similar and bursty traffic;
and cache heirarchies. We discuss how a capacity planner/analyst can
recognize if PT behavior is present. The existence of PT distributions can
have an enormous effect on the performance of computer systems and network
routers. We present queueing and simulation models demonstrating each of
these, discussing what might go wrong with a model if it is not done properly.
We then discuss how a system can be modified when PT's are present to improve
performance. Dr. Lester Lipsky + Dr. Pierre M. Fiorini |
|
13:50 – 14:05 |
Break
|
|
14:05 – 14:55 |
Java
Performance On Z/OS: A Report From The Front Lines
Java is ten years old this
year and is being used more and more as the language of choice for mainframe
applications under WebSphere. But Java is not COBOL. It is important that
analysts understand the performance implications of this new world. This
paper will use actual front line application examples to illustrate some of
the performance issues involved with Java running under WebSphere on the
mainframe. Craig Hodgins, STROBE |
|
14:55 – 15:10 |
Break |
|
15:10 – 16:00 |
Improving Scalable Performance Using Clustered Caching
Cameron Purdy will discuss
applications development considerations for maximum scalable performance and
reliability in clustered J2EE environments.
He will focus on improving scalability and scalable performance of
applications through the use of clustered caching to reliably share live data
among clustered JVMs in the application tier and provide transparent
fail-over as a key element of uninterrupted operation and additionally reduce
the load on the database tier. Cameron Purdy, Tangosol |
|
16:00 – 16:10 |
Final Words
|