45 YEARS
RS
SERVING THE GLOBAL
FORTUNE
UNE 500
Mainframe Performance
& Optimization
Accessing Data Faster
Mainframe Performance & Optimization Solutions
WHAT AFFECTS PERFORMANCE THE MOST?
It’s all about how fast you can access your data—how fast the CPU can get the
data that it needs for processing. Or, more importantly, how long does it have
to WAIT for data?
Remember that all CPUs—regardless how powerful—wait at the same speed
WHAT LIMITS DATA ACCESS ACCESS?
• The number of I/O’s you need to process to get your data
• The efficiency of your data buffers
• The code path length required to get the data
50 Hines Road, Suite 240
Ottawa, ON, Canada © DataKinetics 2023
K2K 2M5
Mainframe Performance & Optimization Solutions
WHAT TO DO ABOUT EXCESSIVE I/O
What about I/O’s?
• Move processing to a cheaper platform
(but that’s only going to make sense to some people…)
• Database buffers and buffer pools significantly reduce
I/O usage
• But that may not be enough
OPTIMIZE BUFFER POOL PERFORMANCE
What about buffer optimization?
• Your experienced DBAs do a good job of this
• There are third-party buffer optimizer products that can
help with this as well
• Plus the new Db2 v12 features (FTBs, Contiguous Buffer
Pools, In-Memory Sort Processing, etc.)
• But that still may not be enough
50 Hines Road, Suite 240
Ottawa, ON, Canada © DataKinetics 2023
K2K 2M5
Mainframe Performance & Optimization Solutions
PATH LENGTH MAKES THE DIFFERENCE
What about the code path length?
• Here is a typical code path for accessing data from a database and its buffers:
Master DBM1 IRLM
Calling Application
SSAS RDS DM BM VSAM
Med Mgr
DASD
BSDS Logs SQL Parse SQL Opt Rec Map Index Mgr DSM Buffer Pools LRW IRLM
• While buffers are in memory, accessing data from them still requires
significant database overhead.
• This data access overhead adds up—especially for repetitive RO data
accesses—for example interest rates, customer codes, product codes, etc.
Can this be optimized?
50 Hines Road, Suite 240
Ottawa, ON, Canada © DataKinetics 2023
K2K 2M5
Mainframe Performance & Optimization Solutions
OPTIMIZING THE CODE PATH LENGTH
Your data’s code path length can be optimized.
Using high-performance in-memory technology, you can significantly reduce
the code path length for accessing your most often accessed data.
Master DBM1 IRLM
Calling Application
SSAS RDS DM BM VSAM
Med Mgr
DASD
BSDS Logs SQL Parse SQL Opt Rec Map Index Mgr DSM Buffer Pools LRW IRLM
Driver
High-performance In-memory Tables
• Your typical code path length for buffered data (top) consumes 10,000 to
100,000 CPU cycles.
• The optimized code path length (below) consumes about 400 CPU cycles.
50 Hines Road, Suite 240
Ottawa, ON, Canada © DataKinetics 2023
K2K 2M5
Mainframe Performance & Optimization Solutions
PERFORMANCE & OPTIMIZATION IS PAINLESS
High-performance in-memory technology does not require changes to your
mainframe datacenter:
• No changes to the database
(This technology augments the buffered DBMS; it does not replace it.)
• No application logic is changed
• You simply copy a small amount of data into in-memory tables
50 Hines Road, Suite 240
Ottawa, ON, Canada © DataKinetics 2023
K2K 2M5
Mainframe Performance & Optimization Solutions
BENEFITS OF PERFORMANCE & OPTIMIZATION
• Accelerates application processing, decreases CPU usage
• Resource usage will actually decrease, while processing performance increases
• Applications will run much faster
• Either reduced costs, or freed-up CPU that can be used for increased/new workloads
• A general improvement in system performance, application performance and database
performance.
Reduction in CPU
Utility
Health
Insurance
Government
Insurance
Finance 2
Finance 1
Services
0% 25% 50% 75% 100%
Before in-memory technology After in-memory technology
50 Hines Road, Suite 240
Ottawa, ON, Canada © DataKinetics 2023
K2K 2M5
THE NEXT STEP
Please contact us for more information—we can send you a more detailed white paper, or alternatively, you can
speak to one of our Professional Services staff to discuss your specific challenges. Use the contact information
shown above to get started.
ABOUT US
As the global leader in Data Access Performance and Optimization Solutions, the world’s largest banks, credit card,
brokerage, insurance, healthcare, retail and telecommunication organizations rely on DataKinetics to dramatically
improve their data throughput and processing.
Our comprehensive, world-renowned suite of solutions enables Fortune 500 companies to:
• Process over a billion mission-critical transactions every day
• Accelerate application processing by up to 98%
• Seamlessly integrate data on mainframe and distributed systems
+1.800.267.0730 | info@dkl.com
© DataKinetics 2023. All rights reserved. No part of this publication may be reproduced without the express written permission of DataKinetics.
DataKinetics and tableBASE are registered trademarks of DataKinetics. All other trademarks, registered trademarks, product names, and
company names and/or logos cited herein, if any, are the property of their respective holders.
