Scribd
Upload
14 views8 pages

DataKinetics Data Performance Optimization

Uploaded by

SirousFekri
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
14 views8 pages

DataKinetics Data Performance Optimization

Uploaded by

SirousFekri
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

Mainframe Data Performance

& Optimization
Making the Mainframe More
Efficient, and Better at What
it Does Best
Mainframe Data Performance & Optimization Solutions

WHAT IS DATA PERFORMANCE?

Think of it as 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 PERFORMANCE?

• 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 2020
K2K 2M5
Mainframe Data 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 2020
K2K 2M5
Mainframe Data 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 2020
K2K 2M5
Mainframe Data 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 2020
K2K 2M5
Mainframe Data 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 2020
K2K 2M5
Mainframe Data 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 2020
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 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
• Enable increased control and flexibility in sub-capacity pricing and R4H soft capping environments

+1.800.267.0730 | [email protected]

© DataKinetics 2020. 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.

You might also like