System z Performance &
Capacity Management using
TDSz and DB2 Analytics Accelerator:
UNIPOL customer experiences
manager of mainframe IT system environment, UNIPOL
zStack Advocate, zClient Architect, IBM Italy
Technical Sales, IBM Italy
IBM’s statements regarding its plans, directions, and intent are subject to change or withdrawal without notice at IBM’s sole
Information regarding potential future products is intended to outline our general product direction and it should not be relied
on in making a purchasing decision.
The information mentioned regarding potential future products is not a commitment, promise, or legal obligation to deliver any
material, code or functionality. Information about potential future products may not be incorporated into any contract.
The development, release, and timing of any future features or functionality described for our products remains at our sole
Performance is based on measurements and projections using standard IBM benchmarks in a controlled environment.
The actual throughput or performance that any user will experience will vary depending upon many factors, including
considerations such as the amount of multiprogramming in the user’s job stream, the I/O configuration, the storage
configuration, and the workload processed.
Therefore, no assurance can be given that an individual user will achieve results similar to those stated here.
“After introduction of DB2 Analytics Accelerator it became possible to improve BA and BI
solution on System z. One of the many possible exploitations is related to performance and
capacity data analysis, a very rich context of structured Big Data to deal with.
In the past, space and database response times limitations restricted the exploitation of this
solution. Both of them are now solved, having up to 192 TB of space and 96 parallel cores
available with IDAA.
We'll present how it's possible to start from SMF detailed data, collect them with TDSz in a
structured way and calculate on the fly performance/SLA enhanced COGNOS reports.
We'll also use SPSS BA tool to develop capacity forecasts based on historical data. Hours
of computation will now became minutes, minutes will become seconds. Isn't it an
System z Performance & Capacity Management using TDSz
and DB2 Analytics Accelerator: UNIPOL customer experiences
Introduction – IT capacity management1
The designed solution for UNIPOL5
Customer needs – Pain points4
Q&A - Closure8
IBM Capacity Management Analytics for zEnterprise2
Analytics in IT = Capacity Management
Definition from ITIL V3:
– ITIL Capacity Management aims to ensure that the capacity of IT services and
the IT infrastructure is able to deliver the agreed service level targets in a cost
effective and timely manner.
– Capacity Management considers all resources required to deliver the IT service,
and plans for short, medium and long term business requirements.
– Component Capacity Management
– Service Capacity Management
– Business Capacity Management
– Capacity Management Reporting
Why Capacity Management is important
Helps consolidate and reduce costs
– Reduces HW and labor costs
– Reduces number of physical servers required to run workloads
– Reduce number of required licenses
Helps ensure application availability
– Are any resources overloaded? When will physical resources reach their limits?
– Have there been any significant changes in my environment between two weeks?
– Ensure supply can meet demand
– Ensure business policies are met
Helps optimize resource utilization
– Right size virtual machines
– Identify trends for workload balancing
Questions Capacity Management can Answer…..
System/Workload Characteristics, Performance and Trending
• How is my environment performing overall?
– Which are my most used servers/LPARs for a given resource type?
– Are there any bottlenecks in my current environment and where?
– Am I reaching capacity on resources and which resource? When will I exhaust
– Which is my top resource consumers for a given resource type?
– Which are my least used servers/LPARs for a given resource type?
– Which are my bottom resource consumers for a given resource type?
– Do I have any outstanding abnormal behavior this week compared to last week
(other periods can be used)?
– Are my systems/workloads balanced or unbalanced?
Questions Capacity Management can Answer…..
System/Workload Estimation and Optimization
(optimize and keep optimized – what if)
– How many more VMs can I add to a cluster/server based on usage history?
– How much more resources do I need to add additional VMs to environment?
– How, where do I add capacity if existing systems are not enough for future growth
for optimized capacity usage?
– Where do I place new workloads? Do I really need to add more resources?
– How can I optimize the VM/LPARs placement to maximize usage and minimize
– How can I optimize the app placement to maximize usage and minimize costs?
IBM Capacity Management Analytics for zEnterprise
Manage the complete time
Problem Identification and Resolution
Capacity Forecasting & Real-time Analysis
Historical reporting of past performance
Forecasting future requirements
Real-time transaction monitoring
Jumpstart your time to
value & eases the path to
Built on IBM’s easy of use analytics
Includes prepackaged, interactive reports
Optional services and education
A single, integrated cost
What is IBM Capacity Management Analytics?
It’s everything necessary for the cost effective analysis of zEnterprise usage, service
objectives, resource utilization, system tuning, accounting, cost recovery, and more…..
IBM Capacity Management Analytics
Capacity Management Analytics: understand how current system is running
Complete reporting and dashboards
capabilities so all system managers &
executives can view, interact with and
personalize it in ways that support the
unique way they analyze performance
and make decisions
Problem Identification and
Delivers a top down view of zEnterprise
workloads with the ability to drill into
further detail, perform simple adhoc
analysis to get to the "why", create
system alerts or monitor performance in
near real-time to predict potential issues
before they impact the business.
Capacity Management Analytics : Understand why and how to fix it
Capacity Forecasting & Real-time
Forecast future capacity to ensure the
capacity is available that the business
needs, when they need it.
Real-time scoring of transactions as they
flow through the system enabling you to
compare with forecast.
Capacity Management Analytics: Build a plan and track against it
reportingA workspace with greater
power, intuitive navigation &
Seamlessly shift to more advanced
Communicate your analysis
using Microsoft Office
Analytics on the go with Mobile devices
and disconnected interaction
Built on IBM’s ease of use analytics solution
Optional: SCCM Optional: Distributed data feed
IBM CMA core architecture diagram
Cognos Business Intelligence
provides the range of analysis capabilities necessary for optimizing zEnterprise use by
confidently and simply compiling the information necessary to understand and manage
system activity while significantly improving the ability to identify potential issues and
pinpoint their cause.
A look under the covers: IBM Cognos BI on zEnterprise
A look under the covers: IBM SPSS Modeler for Linux on zEnterprise
SPSS Modeler with Scoring Adapter
can help you use predictive analytics to
forecast future requirements for zEnterprise
and ensure the capacity required is available
when the business needs it. The Scoring
Adapter provides real-time scoring of
transactions as they flow through the
system enabling you to compare actual
usage with expected and identify anomalies
before they can adversely affect the system.
A look under the covers: Tivoli Decision Support for z/OS
Tivoli Decision Support for z/OS
enables the data collection for the solution and builds the capacity warehouse in DB2 for
z/OS that Cognos Business Intelligence and SPSS Modeler access for reporting, analysis
and predictive modeling. Tivoli Decision Support for z/OS is also able to collect capacity and
performance data for virtually all platforms that are used in business today.
Chargeback & Accounting-
Service Level Reporting
IBM DB2 Analytics Accelerator : Providing faster analysis of your capacity requirements!
• What does it do?
– Base forecasts off larger samples of historical
SMF data to improve accuracy of predictive
– Dramatically accelerate the analysis of your
zEnterprise usage & performance data
– Significantly speed up complex queries of the
large volumes of data that are being created by
– Lower the cost of long-term storage of large
volumes of historical SMF data with a high-
performance storage saver feature
IBM DB2 Analytics Accelerator
What is it?
• A high performance appliance that speeds analysis, enabling you to base your projections on a larger
sample of historical data
IBM DB2 Analytics Accelerator : Query Execution Flow
DB2 for z/OS
IBM DB2 Analytics Accelerator
Queries executed with DB2 Analytics Accelerator
Queries executed without DB2 Analytics Accelerator
Heartbeat (DB2 Analytics Accelerator availability and performance indicators)
Query execution run-time for
queries that cannot be or should
not be off-loaded to IDAA
Faster Answers, Faster Reports
IBM DB2 Analytics Accelerator : High Performance Storage Saver
Reducing the cost of high speed storage
• Time-partitioned tables where:
– only the recent partitions are used in a transactional context
(frequent data changes, short running queries)
– the entire table is used for analytics (data intensive, complex
• DB2 partitions are deleted after the High Performance Storage
Saver are created on the accelerator
No longer present on DB2 Storage
• Customer needed a solution to control all resources required to
deliver the IT service, and plans for short, medium and long term
• Solution should follow cost reduction directive, so the consumption
of MIPS and use of storage should be reduced and kept as small as
• Improvement in the existing user interface should be provided,
allowing intuitive navigation and easy-to-use tools
An overview of UNIPOL solution architecture
Most recent data (2-8
days) <= 1TB
stored in HPSS
Most recent data
Physical 16 TB
(64 TB uncompressed)
The plan to realize the designed solution
• Phase 1: upgrade & reports
•environment upgrade (TDSz new features) and setup of Cognos report environment
• Phase 2: speed up & archives:
•setup and test of IDAA environment
•test of IDAA queries
•tables partitioning and archives with data compression
•Phase 3: ideas for new functions – to be verified and discussed
•use only TDSz detailed data with IDAA aggregations
•use of LOAD instead of INSERT in order to use Turboloader
•SPSS for forecasting
Phase 1: upgrade & reports
• TDSz: upgrade maintenance and installation of CICS feature
– maintenance update of PTS
– Installation of CICS feature
• COGNOS: setup and connection to TDSz DB2 database
– Migration of existing reports and definition of new ones
• installation of TDSz provided reports
• migration of existing reports to COGNOS
• development of new local reports to satisfy new requirements
• definition of users group in order to control access to database
– Reports scheduling and automatic distribution inside UNIPOL
• schedule of predefined reports with output in PDF format
• distribution of PDF reports to defined users
• output in PDF with graphs format or columnar data
Phase 2: speed up & archives 1/2
• Identification of environment to test solution
– Test environment with TDSz database or directly in production?
• Identification of TDSz queries
– Analysis on existing elapsed time/consumption data to define the list of queries
to be used for benchmarking
• TDSz queries measurements
– measurement forcing DB2 execution
• SET CURRENT QUERY ACCELERATION NONE;
– measurement forcing IDAA execution
• SET CURRENT QUERY ACCELERATION ALL;
Phase 2: speed up & archives 2/2
• Identification of TDSz tables for partitioning
– analysis based on TDSz queries
– list of tables to be modified
• Partitioning tables (partitioning based on time criteria)
– Alter + Reorg DB2 commands
– archiving tables
• Force the use of IDAA
– reduction of MIPS usage
– access to all data in tables
– we force the use of IDAA from the queries instead of forcing it from DB2, so DB2
administrator can globally select the databases to be under IDAA optimization
Queries on TDSz data: values we detected (Montpellier lab environment)
Space usage: compression rate we detected (Montpellier lab environment)
Using the average
A full rack model 2001
will store 273 TB
Next steps: ideas for the future we’re working on
• Use of IDAA v4
– performance improvements
– improvements in archive operation (automation of manual activities)
• Keep only detailed data in TDSz tables.
– All the depending data will be calculated on the fly by IDAA and only detailed data will be
stored in IDAA storage
• Use of SPSS to forecast resources requests
– SPSS can forecast future capacity to ensure the capacity is available that the business
needs, when they need it.
– Real-time scoring of transactions as they flow through the system will enable us to compare
• Evaluate with TDSz labs the possibility to use LOAD function instead of INSERT
– This in order to have performance data only on IDAA