This paper describes the benchmark testing that was done with IBM Storwize V7000 storage system and Fidelity Information services in January 2012. To know more about the IBM Storwize V7000, visit http://ibm.co/TaLb6Q.

1. Fidelity Information Services and IBM
Storwize V7000
with IBM System Storage Easy Tier
IBM Systems and Technology Group ISV Enablement
March, 2012
© Copyright IBM Corporation, 2012

2. Table of contents
Abstract..................................................................................................................................... 1
Introduction .............................................................................................................................. 1
Fidelity Information Services and IBM ..................................................................................................... 2
IBM Storwize V7000: Introduction and product overview ...................................................... 3
Profile benchmark configuration .............................................................................................................. 4
Hardware and software components ....................................................................................................... 6
Environment topology............................................................................................................ 7
Application topology ................................................................................................................................. 9
Easy Tier testing results ........................................................................................................ 10
Results ................................................................................................................................................... 10
Summary ................................................................................................................................. 12
Resources ............................................................................................................................... 13
About the author .................................................................................................................... 13
Trademarks and special notices ........................................................................................... 14
© Copyright IBM Corporation, 2012

3. Abstract
This paper describes the benchmark testing that was done with IBM Storwize V7000 storage
system and Fidelity Information services in January 2012.
Introduction
This paper describes the profile benchmark conducted at the IBM® Innovation Center located in Waltham,
Massachusetts. The benchmark engagement was conducted over a period of three weeks (January 16
through February 3, 2012) and included the following activities.
• Hardware and network configuration
− IBM Power® 780 LPAR IBM Storwize® V7000 storage system
• Software deployment and installation
− Profile application
− Message Transaction Monitor (MTM), HTM and other external libraries
− Online Java™ load generator
• Profile databases building
− Benchmark directory configuration
− Building out of databases
− Database backups
• Benchmark testing, analysis, and data collection
The main objectives of the benchmark include:
• Evaluation of the profile’s online and batch performance and scalability on IBM AIX® and
the IBM POWER7® processor-based server with 1 million, 5 million, 10 million, 20 million,
and 50 million account databases.
• Evaluation of the profile’s scalability on an IBM AIX®/POWER7 configuration.
• Identification and tuning of the application, database, and system related bottlenecks to
the extent possible.
The profile benchmark test suite includes the following functions:
• Online
The online test simulates an online activity including monetary transactions (60%) and
account inquiries (40%). A Java load tool developed by Fidelity was used to generate the
online load. These transactions are passed to PROFILE servers on a back-end computer
through PROFILE’s MTM. The MTM is connected to the clients using a TCP/IP
connection. Transactions received by the servers are processed and responded with a
reply message.
• Batch Posting (Function QUE066)
General Batch Posting is a multithreaded process that processed 100,000 transaction
1

4. records supplied in a standard input table (TTX). An input file containing random accounts
was used.
• Interest Posting (Function QUE055)
Interest Posting - End of Day is a multithreaded batch process that processes transactions
to those accounts that are scheduled to post interest.
• Accruals (Function QUE039)
Accrual processing is a multithreaded batch process that accrues one day’s accrued
interest and updates the applicable fields for every account record in the database. This
information is summarized by currency code, product class, product group, product type,
G/L set code, and cost center. The summary information is one of the sources that feed
the general ledger. As every account record in the database is processed, this function
serves as a good yardstick to measure performance.
− IBM Storwize V7000 Configuration
• Software deployment and installation
− Profile application
− MTM, HTM and other external libraries
− Online Java load generator
• Building profile databases
− Benchmark directory configuration
− Building out of databases
− Database backups
• Benchmark testing, analysis and data collection
Fidelity Information Services and IBM
A strong collaboration between Fidelity Information Services (FIS) and IBM organization has allowed
continuous development of best practices collateral for ensuring successful deployments of new Fidelity
Information Services infrastructure at customer locations.
Both the organizations benefit from a shared approach to investigation of new server and storage
technologies, including participation in testing at IBM benchmark sites, and as-needed in place validation
of selected technologies, such as the review of the latest IBM midrange storage product, the
IBM Storwize V7000 system.
2

5. IBM Storwize V7000: Introduction and product
overview
The IBM Storwize V7000 storage system incorporates some of the IBM top technologies typically found
only in enterprise-class storage systems, raising the standard for storage efficiency in midrange disk
systems. This cutting-edge storage system extends the comprehensive storage portfolio from IBM and can
help change the way organizations address the ongoing information explosion.
Easy to use
The IBM Storwize V7000 system simplifies management with a groundbreaking GUI that is both powerful
and easy to use. This interface can help organizations improve storage performance, efficiency, and
utilization rates while improving storage administrator productivity. The IBM Storwize V7000 system
includes the following features for ease of use:
• Preinstalled software
• Simplified provisioning
• Online data migration
• Simplified application performance tuning
Fast
The IBM Storwize V7000 system helps organizations deploy solid-state storage confidently, effectively,
and economically. The IBM Storwize V7000 system provides the following performance features:
• IBM System Storage® Easy Tier™
• Performance management
• Multiple storage tiers
Efficient
The IBM Storwize V7000 system integrates some of the top IBM storage-efficiency technologies into a
modular design that simplifies the addition of more storage technologies. Greater efficiency translates into
increased storage utilization and reduced energy costs. The IBM Storwize V7000 system efficiency
includes the following highlights:
• Thin provisioning
• Space-efficient IBM Tivoli® Storage FlashCopy® Manager
• Easy Tier
Cost-effective
The IBM Storwize V7000 system has a dynamic, modular, and compact design that sets a new standard
for cost-effective midrange disk systems. The IBM Storwize V7000 system uses individual, modular
components that require less space but still provide customers with the flexibility to grow the storage
environment. Capacity and functionality can be added as required, with less disruption than with traditional
midrange disk systems.
3

6. Profile benchmark configuration
The following tables provide configuration information regarding database sizes, account sizes, and
transaction volumes.
Database configurations
Number of customer Number of account Number of history
Database configuration records records records
1 million 500,000 1,000,000 10,000,000
5 million 2,500,000 5,000,000 50,000,000
10 million 5,000,000 10,000,000 100,000,000
20 million 10,000,000 20,000,000 200,000,000
50 million 25,000,000 50,000,000 500,000,000
Table 1: ????
Database configuration Extract file names Extract file size (bytes)
1 million v70perf06_1m.bin 2,471,318,770
5 million v70perf06_5m.bin 12,005,489,199
10 million v70perf06_10m.bin 23,877,455,188
20 million v70perf06_20m.bin 47,604,662,527
Multiple extract files Total: 118 GB
ACN.bin 60,202,708,100
CIF.bin 10,617,100,220
DTX.bin 4,797,484,330
50 million HIST.bin 31,792,421,708
TMP.bin 18,099
TTX.bin 7,309,534
UBG.bin 3,474,394,556
XREF.bin 7,832,924,442
Table 2: Database extract (backup) file sizes
4

7. 1 million 5 million 10 million 20 million 50 million
DB DB DB DB DB
Class Group Type Percentage Number of Number Number of Number of Number of
distribution accounts of accounts accounts accounts
accounts
D CD 350 10% 100,000 500,000 1,000,000 2,000,000 5,000,000
D DDA 400 40% 400,000 2,000,000 4,000,000 8,000,000 20,000,000
D SAV 300 20% 200,000 1,000,000 2,000,000 4,000,000 10,000,000
L LN 500 10% 100,000 500,000 1,000,000 2,000,000 5,000,000
L MTG 700 10% 100,000 500,000 1,000,000 2,000,000 5,000,000
L RC 600 10% 100,000 500,000 1,000,000 2,000,000 5,000,000
Total 5,000,000
DB 1,000,000 10,000,000 20,000,000 50,000,000
Size
Table 3: Account product distribution by database configuration
Transaction Accrual
Batch transaction Online inclearing Interest processing
volumes transactions batch posing batch batch
Database configuration OLTP QUE06 QUE055 QUE039
1 million 400,000 100,000 300,000 1,000,000
5 million 800,000 100,000 1,500,000 5,000,000
10 million 1,200,000 100,000 3,000,000 10,000,000
20 million 1,200,000 100,000 6,000,000 20,000,000
50 million 1,200,000 100,000 15,000,000 50,000,000
Table 4: Transaction volumes
5

8. 1 million DB 5 million DB 10 million DB 20 million DB 50 million DB
Class Group Type TTX Number of Number of Number of Number of Number of
Entries Transactions Transactions Transactions Transactions Transactions
D CD 350
D DDA 400 80,000 80,000 80,000 80,000 80,000 80,000
D SAV 300 20,000 20,000 20,000 20,000 20,000 20,000
L LN 500
L MTG 700
L RC 600
Total
TTX 100,000 100,000 100,000 100,000 100,000
Entries
Table 5: Batch transaction entries for QUE066
1 million DB 5 million DB 10 million 20 million DB 50 million DB
DB
Class Group Type Percentage Number of Number of Number of Number of Number of
Posting Accounts Accounts Accounts Accounts Accounts
Interest
D CD 350 100% 100,000 500,000 1,000,000 2,000,000 5,000,000
D DDA 400
D SAV 300 100% 200,000 1,000,000 2,000,000 4,000,000 10,000,000
L LN 500
L MTG 700
L RC 600
Total INP 300,000 1,500,000 3,000,000 6,000,000 15,000,000
Entries
Table 6: Interest posting account entries for QUE055
Hardware and software components
6

9. Software Components
Servers and Storage
Profile
Mozilla 1.7.12
nmon64
IBM DS4800
AIX 5.3 ML04 64-bit jfs2
IBM pSeries p595 IBM DS8100
Application and
Database Server
Load Drivers and Workstations
ISV Tools
AIX Performance Toolbox
VNC
TightVNC
Adobe Acrobat Reader 5.09
Internet Explorer 6.0
Mozilla 1.7.12
Windows 2003 Server SP1 AIX 5.3 ML04 64-bit jfs2
x336 p185 Intellistation
Load Driver (6)
Unix workstation
IBM to provide and install software IBM to setup hardware ISV to install & Configure
ISV to configure
7

10. Environment topology
Environment Topology
Subnet: 172.27.21.192
Netmask:255.255.255.192
Gateway: 172.27.21.193 DS8700
DNS: 172.27.1.2
Domain: bow.iic.ihost.com
wp7801a1(172.27.21.195)
SAN
Wp7801b1 (172.27.21.196)
V7000
wx355040 (127.27.21.197)
wx355041 (127.27.21.198)
wx355042 (127.27.21.199)
wx355043 (127.27.21.200)
KVM System
1 Gbps Cisco Machine Room
IBM IIC Secure
Router Firewall
KVM Console
FIS Onsite Client
VPN
FIS Router / Firewall
KVM
zPro
10.3.10.23
p185 p185
ISV provided Laptop
DHCP Clients
10/100 mbps Cisco Porting Room
10.3.10.55
Gigabit Backbone Cisco Gigabit Switch
Core
KVM
10.3.10.66
Cisco Gigabit Switch
x33601
x33602
x33603
x33604
x33605
x33606
SAN
2Gb fibre
p59501
DS8100
Network Topology
FIS Remote Client
8

11. Application topology
•
Load Load Load Load Load Load
•
Driver Driver Driver Driver Driver Driver
Primary Application and Database
Server
Profile Application (6 MTMs)
GTM Database
GTM
Replication
Secondary Application and Database
Server
Profile Application
GTM Database
9

12. Easy Tier testing results
The IBM Storwize V7000 includes IBM System Storage Easy Tier, a function that responds to the
presence of solid-state drives (SSDs) in a storage pool that also contains hard disk drives (HDDs). The
system automatically and nondisruptively moves frequently accessed data from HDD managed disks
(MDisks) to SSD MDisks, thus placing such data in a faster tier of storage.
Easy Tier eliminates manual intervention when assigning highly active data on volumes to faster
responding storage. In this dynamically tiered environment, data movement is seamless to the host
application, regardless of the storage tier in which the data is available. Manual controls exist so that you
can change the default behavior, for example, turning off Easy Tier on storage pools that have both types
of MDisks.
Storwize V7000 supports the following tiers:
• Generic SSD tier
− The SSD tier exists when SSDs are in the storage pool. The SSDs provide
greater performance than HDDs.
• Generic HDD tier
− The HDD tier exists when HDDs are in the storage pool.
During the FIS / Storwize benchmark, three Easy Tier tests were conducted:
• SDD only (Easy Tier off)
• HDD only (Easy Tier off)
• SSDs and HDDs (Easy Tier on)
Results
This section summarizes the test performed and the corresponding results.
SSD only (Easy Tier off)
What was tested?
• Twelve 300 GB SSD
• Easy Tier disabled
• FIS online and batch processing
• Input/output operations per second (IOPS) average at 2,000 to 4000 IOPS spikes to
15,000 IOPS
What were the results?
• Drive utilization: 63%
• Response time: 0.2 ms
• Processor user: 0~80%
• Processor sys: less than 2%
• Processor wait: less than 2%
10

13. Storwize V7000 HDD
What was tested?
• Twenty four 300 GB HDDs
• Easy Tier disabled
• FIS online and batch processing
• IOPS average at 2,000 to 4000 IOPS spikes to 15,000 IOPS
What were the results?
• Drive utilization: 481%
• Response time: 60 second peaks
• User: 80%
• Sys: 100%
• Wait: 100%
• Significant slowdowns in online and batch processing time
Storwize V7000 Easy Tier
What was tested?
• Twenty four 300 GB HDDs
• Four 300 GB SDDs
• Easy Tier enabled
• FIS online and batch processing
• IOPS average at 2,000 to 4000 IOPS spikes to 15,000 IOPS
What were the results?
• Drive utilization: 47%
• Response time: 0.2 ms
• Processor user: 0 to 80%
• Processor sys: less than 1%
• Processor wait: less than 1%
• Easy Tier provided better drive utilization, response time, and processor (user, sys, and
wait) times than HDD only and SSD only tests.
11

14. Summary
The tests with Easy Tier activated provided the best overall performance and total cost of owner ship
results. The combination of HDD and SSD with Easy Tier activated resulted in the best drive utilization,
response time, and processor (user, sys, wait) times.
12

15. Resources
These websites provide useful references to supplement the information contained in this paper:
• IBM Systems on PartnerWorld
ibm.com/partnerworld/systems
• Virtual Loaner Program
ibm.com/systems/vlp
• IBM Power Systems Information Center
http://publib.boulder.ibm.com/infocenter/powersys/v3r1m5/index.jsp
• IBM i 7.1 Information Center
http://publib.boulder.ibm.com/infocenter/iseries/v7r1m0/index.jsp
• IBM i 6.1 Information Center
http://publib.boulder.ibm.com/infocenter/iseries/v6r1m0/index.jsp
• IBM AIX 7.1 Information Center
http://publib.boulder.ibm.com/infocenter/aix/v7r1/index.jsp
• IBM AIX 6.1 Information Center
http://publib.boulder.ibm.com/infocenter/pseries/index.jsp
• IBM Redbooks
ibm.com/redbooks
• IBM Publications Center
www.elink.ibmlink.ibm.com/public/applications/publications/cgibin/pbi.cgi?CTY=US
13

16. Trademarks and special notices
© Copyright IBM Corporation 2012.
References in this document to IBM products or services do not imply that IBM intends to make them
available in every country.
IBM, the IBM logo, and ibm.com are trademarks or registered trademarks of International Business
Machines Corporation in the United States, other countries, or both. If these and other IBM trademarked
terms are marked on their first occurrence in this information with a trademark symbol (® or ™), these
symbols indicate U.S. registered or common law trademarks owned by IBM at the time this information
was published. Such trademarks may also be registered or common law trademarks in other countries. A
current list of IBM trademarks is available on the Web at "Copyright and trademark information" at
www.ibm.com/legal/copytrade.shtml.
Java and all Java-based trademarks and logos are trademarks or registered trademarks of Oracle and/or
its affiliates.
Microsoft, Windows, Windows NT, and the Windows logo are trademarks of Microsoft Corporation in the
United States, other countries, or both.
Intel, Intel Inside (logos), MMX, and Pentium are trademarks of Intel Corporation in the United States,
other countries, or both.
UNIX is a registered trademark of The Open Group in the United States and other countries.
Linux is a trademark of Linus Torvalds in the United States, other countries, or both.
Other company, product, or service names may be trademarks or service marks of others.
Information is provided "AS IS" without warranty of any kind.
All customer examples described are presented as illustrations of how those customers have used IBM
products and the results they may have achieved. Actual environmental costs and performance
characteristics may vary by customer.
Information concerning non-IBM products was obtained from a supplier of these products, published
announcement material, or other publicly available sources and does not constitute an endorsement of
such products by IBM. Sources for non-IBM list prices and performance numbers are taken from publicly
available information, including vendor announcements and vendor worldwide homepages. IBM has not
tested these products and cannot confirm the accuracy of performance, capability, or any other claims
related to non-IBM products. Questions on the capability of non-IBM products should be addressed to the
supplier of those products.
All statements regarding IBM future direction and intent are subject to change or withdrawal without notice,
and represent goals and objectives only. Contact your local IBM office or IBM authorized reseller for the
full text of the specific Statement of Direction.
Some information addresses anticipated future capabilities. Such information is not intended as a definitive
statement of a commitment to specific levels of performance, function or delivery schedules with respect to
any future products. Such commitments are only made in IBM product announcements. The information is
14

17. presented here to communicate IBM's current investment and development activities as a good faith effort
to help with our customers' future planning.
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
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 throughput or performance improvements equivalent to the ratios stated here.
Photographs shown are of engineering prototypes. Changes may be incorporated in production models.
Any references in this information to non-IBM websites are provided for convenience only and do not in
any manner serve as an endorsement of those websites. The materials at those websites are not part of
the materials for this IBM product and use of those websites is at your own risk.
15