November 7, 2006
Marriott Courtyard Pleasanton

5059 Hopyard Road
Pleasanton, CA 
(925) 463-1414

  AGENDA

 

8:30 – 9:00           Registration and Continental Breakfast

 

9:00 – 10:00         Explosive Data Growth – How to Handle the Risks and Opportunities

            Speaker: David Bregman, Glasshouse Technologies Inc.

Over the course of the past three years, enterprises have worked hard to eliminate unnecessary costs in their storage environments and to protect and place value on their corporate information. The so-called ‘low hanging fruit’ projects have now all been completed and in general terms, there are not a lot of quick hits remaining to effect ongoing efficiency. Yet the Enterprise is still faced with massive data growth requirements and continued cost reduction demands. How can the Enterprise continue to meet data growth demands, new requirements from regulators and security advocates, and continued demands from distributed applications and workforces while simultaneously managing costs to maintain competitiveness? What efforts are underway in the industry leaders to address these challenges? What new technologies will play a key role? Is there any slowdown in the future or is this issue now perennial?

 

10:15 – 11:15      The Trilogy of DB2’s "Originating" Address Spaces – Mainframe DB2, DDF and Stored Procedures

            Speaker: Tom Halinski, Compuware

DB2 SQL executes using three main DB2 address spaces, SSAS, DBAS and IRLM.  To measure and see how it performs, we need to capture its activity from its “originating” address space.  This varies depending on the source of the SQL: Mainframe, Distributed or Stored Procedures - making a trilogy.  Let’s see what each is and how they work.  With a good methodology we can “tune” any of them.

 

11:20 – 12:20      Managing Financial Systems: The Peak Experience

                                Speaker: Jon Schmidt, Transaction Design Inc.

The impact of a capacity shortfall affecting financial systems can be very expensive. If a stock trading system fails to keep up with a

tumultuous day, or if a retail POS system can’t keep up over Christmas, the organization operating the system can lose thousands of dollars

from the bottom line for each minute that the system is down or degraded.

 

Jon’s presentation discusses how some organizations track the impact of peak business demand on their servers, and how they use this information to be prepared for the next surge in demand.

 

12:20 ‑ 1:30          NCCMG Business Meeting/Elections/Lunch

 

1:30 - 2:30            The Physics of I/O Performance with Practical Advice for Configuration Design

                                Speaker: Dave Fisk, ORtera

Storage I/O bottlenecks, meltdown conditions, constraints, and load imbalances are problems that enterprise organizations face on a daily basis.  Modeling I/O workloads to identify these potential problems can be a challenge a best, with less than reliable or accurate results.   Dave’s going to present a summary of results and examples from modeling I/O workloads and storage resource capabilities.  Included in this presentation will be a high level overview of the mathematical physics of storage performance as derived from Little’s Law - which leads to a handful of empirically based simple formulas that can be used to simplify and approximate I/O workload demand and storage resource capability required  for successful and accurate storage performance capacity planning.

 

2:45 – 3:45           Enterprise Extender Analysis for Dummies

            Speaker: Nalini Elkins, Insight Products Inc.

Many companies are implementing Enterprise Extender (EE).  Diagnosing problems for EE is a challenge!  There are over 8 headers involved with SNA, HPR, UDP, and IP.    We have seen companies with many RTP pipes unused for hours yet with overhead packets flowing.  Other issues include: retransmission, fragmentation and congestion on EE.  In this session, Nalini will discuss: EE trace headers; what impacts performance; Adaptive rate-based (ARB) headers and flow control; idle RTP pipes; SNA and HPR fragmentation and overhead.

 

 

Back to main page