Transcript Handout

IBM zEnterprise System Innovation
Extending the innovation of the zEC12 to enterprises of all
sizes with the zBC12
© 2013 IBM Corporation
Trademarks
The following are trademarks of the International Business Machines Corporation in the United States and/or other countries.
AIX*
BladeCenter*
CICS*
Cognos*
DataPower*
DB2*
DFSMS
EASY Tier
FICON*
GDPS*
HiperSockets*
HyperSwap
IMS
InfiniBand*
Lotus*
MQSeries*
NetView*
OMEGAMON*
Parallel Sysplex*
POWER7*
PowerHA*
PR/SM
PureSystems
Rational*
RACF*
RMF
Smarter Planet*
Storwize*
System Storage*
System x*
System z*
System z10*
Tivoli*
WebSphere*
XIV*
zEnterprise*
z10
z10 EC
z/OS*
z/VM*
z/VSE*
* Registered trademarks of IBM Corporation
The following are trademarks or registered trademarks of other companies.
Adobe, the Adobe logo, PostScript, and the PostScript logo are either registered trademarks or trademarks of Adobe Systems Incorporated in the United States, and/or other countries.
Cell Broadband Engine is a trademark of Sony Computer Entertainment, Inc. in the United States, other countries, or both and is used under license therefrom.
Intel, Intel logo, Intel Inside, Intel Inside logo, Intel Centrino, Intel Centrino logo, Celeron, Intel Xeon, Intel SpeedStep, Itanium, and Pentium are trademarks or registered trademarks of Intel
Corporation or its subsidiaries in the United States and other countries.
IT Infrastructure Library is a registered trademark of the Central Computer and Telecommunications Agency which is now part of the Office of Government Commerce.
ITIL is a registered trademark, and a registered community trademark of the Office of Government Commerce, and is registered in the U.S. Patent and Trademark Office.
Java and all Java based trademarks and logos are trademarks or registered trademarks of Oracle and/or its affiliates.
Linear Tape-Open, LTO, the LTO Logo, Ultrium, and the Ultrium logo are trademarks of HP, IBM Corp. and Quantum in the U.S. and
Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both.
Microsoft, Windows, Windows NT, and the Windows logo are trademarks of Microsoft Corporation in the United States, other countries, or both.
OpenStack is a trademark of OpenStack LLC. The OpenStack trademark policy is available on the OpenStack website.
TEALEAF is a registered trademark of Tealeaf, an IBM Company.
Windows Server and the Windows logo are trademarks of the Microsoft group of countries.
Worklight is a trademark or registered trademark of Worklight, an IBM Company.
UNIX is a registered trademark of The Open Group in the United States and other countries.
* Other product and service names might be trademarks of IBM or other companies.
Notes:
Performance is in Internal Throughput Rate (ITR) ratio based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput 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 improvements equivalent to the performance ratios stated here.
IBM hardware products are manufactured from new parts, or new and serviceable used parts. Regardless, our warranty terms apply.
All customer examples cited or described in this presentation are presented as illustrations of the manner in which some customers have used IBM products and the results they may have achieved. Actual environmental
costs and performance characteristics will vary depending on individual customer configurations and conditions.
This publication was produced in the United States. IBM may not offer the products, services or features discussed in this document in other countries, and the information may be subject to change without notice. Consult
your local IBM business contact for information on the product or services available in your area.
All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
Information about non-IBM products is obtained from the manufacturers of those products or their published announcements. IBM has not tested those products and cannot confirm the performance, compatibility, or any
other claims related to non-IBM products. Questions on the capabilities of non-IBM products should be addressed to the suppliers of those products.
Prices subject to change without notice. Contact your IBM representative or Business Partner for the most current pricing in your geography.
This information provides only general descriptions of the types and portions of workloads that are eligible for execution on Specialty Engines (e.g, zIIPs, zAAPs, and IFLs) ("SEs"). IBM authorizes customers to use IBM
SE only to execute the processing of Eligible Workloads of specific Programs expressly authorized by IBM as specified in the “Authorized Use Table for IBM Machines” provided at
www.ibm.com/systems/support/machine_warranties/machine_code/aut.html (“AUT”). No other workload processing is authorized for execution on an SE. IBM offers SE at a lower price than General Processors/Central
Processors because customers are authorized to use SEs only to process certain types and/or amounts of workloads as specified by IBM in the AUT.
2
© 2013 IBM Corporation
Innovation too exciting not to share with a broader market
2012
AUG
IBM zEnterprise® EC12
(zEC12)
 Performance
 Availability
innovations
 Optimized for
data serving
 Boost
to software
IBM zEnterprise Unified
Resource Manager
(zManager) and
zEnterprise BladeCenter®
Extension (zBX) Mod 003
 Investment protection
 Hosts PS701 and HX5 blades
 Commitment to future of zBX
2013
DEC
System
Director
MAR
Enhancements
 Updates to
IBM zAware
 Enhancements
for provisioning  Updates to
DataPower ® XI50z
and image
 Top exit cabling for
management
zBX
on zBX
 2GB page
support for z/OS®
JUL
IBM Enterprise BC12 (zBC12)
 Right size without
compromise
 Start small and rapidly
grow with ease
 Secure foundation for
Cloud, Mobile & Data
zBX Model 003 & zManager
 Resource Management
 Availability Monitoring
zEC12 updates
 Data serving
 Secure
z/OS V2.1
 Optimized data storage
 Cloud like scale
 New Crypto as a Service
 Workload Optimization built in
z/VM® 6.3
 New scale opportunities with z/VM
support for 1TB of real memory
 HiperDispatch – more efficient
utilization of CPU resources
3
© 2013 IBM Corporation
zEnterprise EC12 satisfies the most robust enterprise requirements
Announced August 28, 2012
Up to
25%
Faster engines1
Up to
30%
Faster Linux engines1
Up to
50%
More total capacity1
Up to 101 configurable cores
60 subcapacity settings
Up to 3 TB RAIM memory
IFL, zIIP, zAAP, ICFs and optional SAPs
zEC12
Machine Type: 2827
Models: H20, H43, H66, H89, HA1
 Advanced Technology 5.5 GHz processor chip for
performance boost for all workloads
– Over 78,000 MIPS for large scale consolidation
 Processor chip optimized for software
performance
 Innovation to drive availability to superior levels
– IBM zAware offers snap-shot of the current state of your
business
– FLASH Express and pageable large pages to drive
availability and performance for critical workloads
 Trusted resilience is a zEnterprise standard
Environmental focus
– High speed cryptography integrated as part of the chip
Upgradeable from IBM zEnterprise 196 and IBM
System z10® Enterprise Class
– Enhanced functions with new Crypto Express4S
– PR/SM™ received EAL5+ certification
1 Based
on preliminary internal measurements and projections against a z196. Official performance data will be available upon announce and can be obtained online at LSPR (Large Systems Performance Reference)
website at: https://www.ibm.com/servers/resourcelink/lib03060.nsf/pages/lsprindex. Actual performance results may vary by customer based on individual workload, configuration and software levels.
4
© 2013 IBM Corporation
Introducing the new IBM zEnterprise BC12
Performance
Economics
36% performance boost per
core running at 4.2 GHz
Same low entry price as
the z114
58% more capacity for
traditional workloads
27% improvement in P/P
for specialty engines
62% more capacity for
Linux® workloads
Compression acceleration
(zEDC) for better resource usage
2X increase in
RAIM memory
20% increase
in granularity
Networking and Hybrid
Security and Availability
Reduced latency for server to
server communications with
z/OS V2.1 SMC-R and 10GbE
RoCE Express
Simplified TKE 7.3 workstation
Resource management
defined by business goals
and objectives
Investment Protection
Start Small and Grow with Ease
Upgrade from z10™ BC and z114
Upgrade into zEC12
Upgrade zBX Mod 002 to Mod 003
z/OS 2.1 Crypto as a service
IT analytics with IBM zAware to
improve availability
Flash Express helps reduce
downtime from application
availability lapses
* US prices, may vary by country
Increased performance and flexibility in lower cost package extending
the latest mainframe technology to organizations of all sizes
5
© 2013 IBM Corporation
Increased scale and flexibility provide room for growth
6
Model
Total
PUs
CPs
IFLs
zAAPs
zIIPs
ICFs
Std.
SAPs
Add' l
SAPs
Spares
IFP
H06
9
0-6
0-6
0-4*
0-4*
0-6
2
0-2
0
1
H13
18
0-6
0-13
0-8**
0-8**
0-13
2
0-2
2
1
Z01
Y01
X01
W01
V01
U01
T01
S01
R01
Q01
P01
O01
N01
M01
L01
K01
J01
I01
H01
G01
F01
E01
D01
C01
B01
A01
Z02
Y02
X02
W02
V02
U02
T02
S02
R02
Q02
P02
O02
N02
M02
L02
K02
J02
I02
H02
G02
F02
E02
D02
C02
B02
A02
Z03
Y03
X03
W03
V03
U03
T03
S03
R03
Q03
P03
O03
N03
M03
L03
K03
J03
I03
H03
G03
F03
E03
D03
C03
B03
A03
Z04
Y04
X04
W04
V04
U04
T04
S04
R04
Q04
P04
O04
N04
M04
L04
K04
J04
I04
H04
G04
F04
E04
D04
C04
B04
A04
Z05
Y05
X05
W05
V05
U05
T05
S05
R05
Q05
P05
O05
N05
M05
L05
K05
J05
I05
H05
G05
F05
E05
D05
C05
B05
A05
Z06
Y06
X06
W06
V06
U06
T06
S06
R06
Q06
P06
O06
N06
M06
L06
K06
J06
I06
H06
G06
F06
E06
D06
C06
B06
A06
1-way
2-way
3-way
4-way
5-way
6-way
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
* Max available with 2 CPs
** Max available with 4/5 CPs
zBC12
Machine Type: 2828 Models: H06, H13
 New 2:1 order ratio for zIIP and/or zAAP to CP
 New entry level – 50 MIPS at same z114 entry price
 Full uniprocessor running at over 1064 MIPS with total
capacity available over 4900 MIPS
 Increased granularity for right sizing -- 26 capacity levels x
6 CPs = 156 settings
‒ Complete capacity matrix available on both models
 Cloud ready solution ideal for Enterprise Linux Server
– Model H13 with up to 13 IFLs, up to 496 GB memory
and z/VM 6.3
 Great economics for standalone Coupling Facility
 Integrated firmware processor (IFP) used for infrastructure
management of new PCIe adapters
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
© 2013 IBM Corporation
Processor chip optimized for software performance
Exploited by Java, PL/I, compilers, DB2, more
 Our leadership in microprocessor design supports
a boost in performance for all workloads
 Larger caches to optimize data serving
environments
 Help for lockouts, reduction of Java™ overhead,
improvements to DB2® bufferpools and Java
heaps, complier improvements with decimal
format conversions facility
 Exploitation of HiperDispatch in z/VM V6.3
7
© 2013 IBM Corporation
Specialty Engines continue to offer excellent price/performance
for all clients
Continue investing
in Coupling:
IFLs and new Enterprise
Linux Server:
zAAPs and zIIPs:
 New efficiencies for
shared CF engines with
the potential to lower
acquisition costs
 In the future CF will use
Flash Express for a
cost effective, resilient
solution for overflow of
WebSphere MQ shared
queues in Coupling
Facility (SOD)*
 IT optimization and
cloud computing can
deliver enhanced
economics
 Helps bring on new workloads and applications
8
 z/VM virtualization
software priced per
processor
 Performance increase
for Linux workload with
each new generation
Internal Coupling
Facility (ICF)
Integrated Facility
for Linux (IFL)
1997
2000
 Enables better centralization of data on
the mainframe
 Workloads on zIIP can help connect, manage,
extend, and protect the data
 Helps minimize the need to maintain duplicate
copies of the data and provide better security
 zIIP can optimize Java and XML processing
 New 2:1 order ratio for zIIP and/or zAAP to CP
IBM System z® Application
Assist Processor (zAAP)
IBM System z Integrated
Information Processor (zIIP)
2004
* All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
2006
© 2013 IBM Corporation
New innovations available on zBC12 and zEC12
Data
Compression
Acceleration
High Speed
Communication
Fabric
Flash
Technology
Exploitation
Proactive
Systems Health
Analytics
Hybrid
Computing
Enhancements
Reduce CP
consumption,
free up storage
& speed cross
platform data
exchange
Optimize server to
server networking
with reduced
latency and lower
CPU overhead
Improve availability
and performance
during critical
workload transitions,
now with dynamic
reconfiguration;
Coupling Facility
exploitation (SOD)
Increase availability
by detecting unusual
application or system
behaviors for faster
problem resolution
before they disrupt
business
x86 blade resource
optimization; New
alert & notification for
blade virtual servers;
Latest x86 OS
support; Expanding
futures roadmap
zEDC
Express
10GbE
RoCE Express
IBM
Flash Express
IBM
zAware
zBX Mod 003;
zManager Automate;
Ensemble Availability
Manager; DataPower
Virtual appliance SoD
9
© 2013 IBM Corporation
zEnterprise Data Compression (zEDC) - can help to reduce CPU and storage
Every day 2.5 quintillion bytes of data are created
Compress your data
4X*
(efficient system data
compression)
Up to 118X reduction in
CPU and up to 24X
throughput improvement
when zlib uses zEDC **
Efficiently compress active data by providing a low CPU, high performance,
dedicated compression accelerator
Industry standard compliance compression for cross platform
data distribution **
Typical Client Use Cases:
Significant disk savings with trivial CPU cost for large
BSAM/QSAM sequential files ***
More efficiently store audit data in application logs
Reduce the amount of data needed for data migration
and backup/restore **
Transparent acceleration of Java compressed applications **
zEDC Express
Data Ready
10
z/VM 6.3 support
for guests***
* The amount of data sent to an SMF logstream can be reduced by up to 75% using zEDC compression – reducing logger overhead
** These results are based on projections and measurements completed in a controlled environment. Results may vary by customer based on individual
workload, configuration and software levels
*** All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
z/OS V2.1
zEDC
© 2013 IBM Corporation
Flash Express cuts away at availability lapses
19%
Reduction in total
dump time for 36 GB
standalone dump
10x
Faster response time and
37% increase in throughput
compared to disk for
morning transition
Up to
28%
Improvement in DB2
throughput leveraging Flash
Express with Pageable
Large Pages (PLP)
11
Innovative PCI-e storage-class memory
Enables the use of large 1 MB pageable pages
Typical Client Use Cases:
Improve availability and performance during workload
transition and spikes
Faster, less disruptive diagnostics
Cost effective, resilient solution for overflow of MQ
shared queues in Coupling Facility (SOD) *
Supported on
z/OS V1.13
or Higher **
Dynamic
Reconfiguration
for Flash Express
Flash Express
feature for zEC12
and zBC12
* All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only
** With the March 2013 RSM Enablement Offering Web deliverable.
© 2013 IBM Corporation
IBM zAware delivers smarter message monitoring capabilities
IT analytics to reduce service disruptions
Difficult or
unusual problems
can be found in
2 clicks
not hours
Leading edge pattern recognition can intercept application
and system problems before they cause future disruptions
Real-time, self-learning solution accurately represents your
environment – automatically
Ultimate in
Resiliency
New July 9, 2013:
OMEGAMON® XE
on z/OS support
12
Typical Client Use Cases:
Diagnose complex problems quickly and restore service faster
Accelerate problem determination across IT functions
Real-time, self-learning solution accurately represents your
environment – automatically
IBM zAware
firmware
Customized
analysis,
scoring
Supports long
distances
3500km
Supported on
z/OS V1.13
or higher
© 2013 IBM Corporation
Optimize server to server networking – transparently
“HiperSockets™-like” capability across systems
Up to 50% CPU savings
for FTP file transfers
across z/OS systems
versus standard TCP/IP **
zBC12
zEC12
Up to 48% reduction in
response time and
10% CPU savings for a
sample CICS workload
exploiting IPIC using
SMC-R versus TCP/IP ***
Up to 40% reduction in
overall transaction
response time for WAS
workload accessing
z/OS DB2 ****
Up to 3X increase in
WebSphere MQ messages
delivered across
z/OS systems *****
13
Shared Memory Communications (SMC-R):
Exploit RDMA over Converged Ethernet (RoCE) with qualities of
service support for dynamic failover to redundant hardware
Typical Client Use Cases:
Help to reduce both latency and CPU resource consumption over
traditional TCP/IP for communications across z/OS systems
Any z/OS TCP sockets based workload can seamlessly use
SMC-R without requiring any application changes
z/OS V2.1
SMC-R
z/VM 6.3 support
for guests*
10GbE RoCE
Express
* All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
** Based on internal IBM benchmarks in a controlled environment using z/OS V2R1 Communications Server FTP client and FTP server, transferring a 1.2GB binary file using SMC-R (10GbE RoCE Express feature) vs standard TCP/IP (10GbE
OSA Express4 feature). The actual CPU savings any user will experience may vary.
*** Based on internal IBM benchmarks using a modeled CICS workload driving a CICS transaction that performs 5 DPL (Distributed Program Link) calls to a CICS region on a remote z/OS system via CICS IP interconnectivity (IPIC), using 32K
input/output containers. Response times and CPU savings measured on z/OS system initiating the DPL calls. The actual response times and CPU savings any user will experience will vary.
**** Based on projections and measurements completed in a controlled environment. Results may vary by customer based on individual workload, configuration and software levels.
© 2013 IBM Corporation
***** Based on internal IBM benchmarks using a modeled WebSphere MQ for z/OS workload driving non-persistent messages across z/OS systems in a request/response pattern. The benchmarks included various data sizes and number of
channel pairs The actual throughput and CPU savings users will experience may vary based on the user workload and configurati on.
zBX and zManager – Proven hybrid computing environment
Support for multi-platform infrastructure with single resource management
 Investment protection Model 002 to Model 003
– zManager entitlements move at no-charge
zBX
Machine Type: 2458, Model: 003
 zBX opens cloud opportunities with its fit-for-purpose
strategy
What’s new?
For zManager
 Performance policy managing and load balancing for HX5
 Monitor and reporting to an availability policy
 Support for Microsoft Windows Server 2012 on HX5 blades
New networking connectivity option
 Layer-2 support between external data network and zBX*
In the Future
 With strategy for future including tightly integrated hardware
delivery, new compute node form factors, improved
virtualization capabilities **
Cloud Ready
14
* Some restrictions will apply
** All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
© 2013 IBM Corporation
zEnterprise System delivers a security ready infrastructure
Up to 52%
lower security administrator
efforts by using zSecure
with RACF1
Intrinsic platform
security and
privacy
 Cryptography built
into processor chip
and Crypto
Express4S
 Secure your critical
information assets (or
data) throughout their
life cycle
 Simplified setup and
management with
new TKE 7.3
Spanning
multiple
industries
 Enhanced digital
signature
cryptography
(PKCS#11) to protect
data
 Payment card
industry solutions
with EMV support for
credit and debit cards
Leveraging
operating system
security
System z
exclusive
cryptography
Total isolation
of workloads
and data
 Qualities needed by
enterprises adopting
cloud application
architectures
 Wide range of
cryptographic
primitives exploited by
operating system and
middleware to help
secure and accelerate
workloads
 z/OS V2.1 Crypto
as a service
 Blends the speed
of processor based
crypto with the
security of the
Crypto Express
coprocessor
 EAL5+ means the
highest levels of
protection on
commercial server
for secure isolation
of LPARs
 EAL4+ for z/OS
and z/VM
* Green indicates new for zEC12
New z/OS V2.1 ready to protect data, reduce risk and
strengthen customer trust
15
1
Based on input from a Financial Service Provider and ROI business value tools by IBM SWG
© 2013 IBM Corporation
Flexible connectivity
Improving bandwidth, granularity and options for connections
Clustering for
availability
Controlled and simplified
management
 HCA-3 InfiniBand®
Coupling Links
‒1x and 12x
 ISC-3
(peer mode only) 1
 STP
 IBM zAware partition managed
from Hardware Management
Console (HMC)
 Central management of
heterogeneous resources with
zManager
 Connectivity of zBX for Hybrid
Computing:
- Intraensemble data network
- Intranode management
network
Note: No ESCON support on zEC12 and zBC12
Efficient data
access
 zEDC Express
 Flash Express
 FICON Express8S
 Carry forward only FICON Express81,
FICON Express4S1,
FICON Express41
Linking up to
Speed Up
 10GbE RoCE Express
 OSA-Express5S
 OSA-Express4S
 OSA Express31
 10 GbE for connecting
a IBM PureSystems™
1 Carry
forward only
* Green indicates new for zEC12
Plus – High Performance FICON for System z (zHPF) is a performance and RAS
enhancement designed to help reduce FICON channel overhead
16
© 2013 IBM Corporation
A zEnterprise for everyone
“Right size” your mainframe to fit your needs
If you …
… want a hybrid computing environment
managed as a single system – including
z/OS, AIX®, Linux on IBM System x®,
Microsoft Windows on System x
… are looking for an entry level mainframe
with almost 100X growth options in
same footprint for traditional capacity
settings
… need a smaller mix of special engines
(*zAAP on zIIP great option here!)
… have smaller Coupling and/or I/O
attachment requirements
… need the lowest cost application
development environment
The zBC12 H06 may be the
perfect option.
17
… want the flexibility to manage across a
hybrid platform
… want the flexibility to manage across a
hybrid platform
… want to replace your z10 BC or z114
server with one that has more capacity
settings and more engines for IFLs,
zAAPs or zIIPs
… have a large mainframe capacity
requirement or desire for massive
consolidation – scale to over 78,000
MIPS in one footprint
… want to replace your standalone
coupling facility or Linux only server with
a machine that provides more engine,
memory and I/O scale out capabilities
… have a large disk installment so in turn
have large I/O requirements
… have future growth needs, but prefer
growth in smaller increments and want
to avoid disruptive outage during
upgrade
The zBC12 H13 is just
what you need.
… need new ways to address your ‘green’
requirements – like water cooling – or
need a non-raised floor environment
… have a large CBU requirement – and
like the control of having your disaster
recovery site right in your own shop
The enhanced zEC12 is right
for you.
© 2013 IBM Corporation
Extending the mainframe with new capabilities
 Energize your applications
through integration, improved
performance and networking innovations
 Save money
by rightsizing without compromise,
consolidation opportunities broadened
and compression acceleration
 Secure it all
with confidence on a trusted and
resilient infrastructure
An Integrated
Data & Analytics
Engine
18
Efficient, Agile
Cloud Computing
Foundation
Sophisticated
platform for
Mobile Computing
Ultimate in
Trusted Security
& Resiliency
© 2013 IBM Corporation
Thank You
19
© 2013 IBM Corporation
Removed for shortened roadshow
version of the deck
20
© 2013 IBM Corporation
System z and Storage Synergy
Designing, developing, and testing together
is key to unlocking true value
Midrange
offerings
Linux
offerings
New IBM System
Storage® DS8870
 zHPF and Extended Address Volumes
 GDPS®/PPRC HyperSwap™
 zDAC on z/OS for easy configuration
 Entry Level BC version



XIV® Storage Systems
 Popular with z/VSE®, z/VM and Linux
on System z








TS3500
 Attaches to multiple heterogeneous
systems
 Supports for all System z (via 3953)



TS7700 Virtualization
Engine
 z/OS, z/VM and z/VSE support



IBM FlashSystem 820
with SVC
 Couple with Enterprise Linux Server
(ELS) offering for a High Performance
Cloud Solution
Storwize® V7000
21
Large
enterprise
SVC
 Perfect for z/VSE, z/VM and Linux on
System z
TS1140
 Support for z/OS, Linux on System z,
z/VM, and z/VSE

© 2013 IBM Corporation
Operating systems focused on exploiting zEnterprise Innovation
z/OS
Version 2.1
& z/OSMF 2.1
z/VM
Version 6.3
z/VSE
Version 5.1
z/TPF
Version 1.1
Linux on
System z
 Availability and
scalability for cloud
 Support for more
virtual servers
 Reduced memory
constraints
 Improved cross
platform integration
 New virtualization
enhancements
 Ability to process
huge volumes of
data
 Improved
performance by
more efficient
utilization
 Wide portfolio using
Linux on System z
 Modernization
through SOA
enablement
 Securing critical
assets
 Enabled for
OpenStack® support
 Continued core
system usability
enhancements with
CICS® Explorer
 Protecting data,
reduce risk and
strength customer
trust
 Simplification for
configuring and
managing system
software
22
 Hybrid systems
connectivity
 Highly secure with
protection of data in
flight, at rest, and in
use
 Open development
environment
 Improvement in
diagnosing issues
and reducing
outages
 Faster
communications
with improved
networking
 Enhanced web
serving
performance
© 2013 IBM Corporation
Misc joint zBC12 and zEC12 charts
23
© 2013 IBM Corporation
IBM zEnterprise System
An optimized system
Java
Semiconductor
Technology
24
Microprocessor
Design
Systems
Design
Virtualization
& Operating
Systems
Compilers &
Java Virtual
Machine
Optimized
Middleware
© 2013 IBM Corporation
Parallel Sysplex® CFCC level 18
 Performance Improvements
– Elapsed time improvements when dynamically altering the size of a cache structure
– Throughput enhancements for parallel cache castout processing
– Storage class and castout class contention avoidance by breaking up individual storage class
and castout class queues to reduce storage class and castout class latch contention
 Coupling link characteristics reporting to z/OS
– Identifies underlying InfiniBand hardware characteristics for CIB CHPIDs to help with
Sysplex monitoring and tuning
– Enables RMF™ Monitor III to report additional information
• InfiniBand Link type and protocol: 12x IFB, 12x IFB3 and 1x IFB
• CHPID mapping to physical links – HCA IDs and port numbers
• Link fiber optic distance
• Fully functional or degraded status
 Resiliency Improvements
– Enhanced capabilities to non-disruptively capture and collect extended diagnostic structure
data from Coupling Facility structures that have encountered an error.
– Verification of local cache controls for a Coupling Facility cache structure connector
 Structure and CF Storage Sizing with CFCC level 18
– May increase storage requirements when moving from CF Level 17 (or below) to CF Level 18
– Use of the CF Sizer Tool is recommended: http://www.ibm.com/systems/z/cfsizer/
25
© 2013 IBM Corporation
zEnterprise Server Time Protocol Enhancements
 Broadband Security Improvements for STP
– Authenticates NTP servers when accessed by the HMC client through a firewall
– Authenticates NTP clients when the HMC is acting as an NTP server
– Provides symmetric key (NTP V3-V4) and Autokey (NTP V4) authentication
(Autokey is not supported if Network Address Translation is used)
– This is the highest level of NTP security available
 Improved NTP Commands panel on HMC/SE
– Shows command response details
 Telephone modem dial out to an STP time source is no longer supported
– All STP dial functions are still supported by broadband connectivity
– zEC12 HMC LIC no longer supports dial modems
(Fulfills the Statement of Direction in Letter 111-167, dated October 12, 2011)
26
© 2013 IBM Corporation
Redbooks
 IBM zEnterprise System Technical Introduction, SG24-8050-01
This book provides concepts, positioning, and a business value view of zEnterprise System capabilities,
hardware functions/features, and associated software support. It is intended for IT Managers,
consultants, IT Architects and Specialists, and anyone who wants to understand the basic elements of
the IBM zEnterprise EC12 (zEC12) and IBM zEnterprise EC12 (zBC12).
 IBM zEnterprise EC12 Technical Guide, SG24-8049-01
This book provides specific information about the zEC12 and its functions, features, and associated
software support. Greater detail is offered in areas relevant to technical planning. It is intended for
systems engineers, system programmers (IT Specialists), planners, and anyone wanting to understand
the zEC12 functions and plan for their usage.
 IBM zEnterprise BC12 Technical Guide, SG24-8138
This book provides specific information about the zBC12 and its functions, features, and associated
software support. Greater detail is offered in areas relevant to technical planning. It is intended for
systems engineers, system programmers (IT Specialists), planners, and anyone wanting to understand
the zBC12 functions and plan for their usage.
 IBM System z Connectivity Handbook, SG24-5444
This book highlights the hardware and software components, typical uses, coexistence, and relative
merits of the System z I/O features. It is intended for data center planners, IT Specialists, system
engineers, technical sales staff, and network planners who are involved in planning connectivity
solutions for System z servers.
 http://www.redbooks.ibm.com/Redbooks.nsf/pages/zEnterprise?Open
27
© 2013 IBM Corporation
Processor chip optimized for software performance
Exploited by Java, PL/I, compilers, DB2, more
 Our leadership in microprocessor design supports a
boost in performance for all workloads
– 5.5 GHz for zEC12 and 4.2 GHz for zBC12
– Second generation out of order execution design
– Multi-level branch prediction supports complex workloads
 zBC12 offers similar Single Chip Module (SCM) as
z114
 Larger caches to optimize data serving
environments
– Almost 2x on chip and 2x additional on book
 Transactional Execution, 2 GB page frames, decimal
format conversions facility – new hardware
functions optimized for software performance
– Help for lockouts, reduction of Java overhead, improvements
to DB2 bufferpools and Java heaps, complier improvements
with decimal format conversions facility
 Exploitation of HiperDispatch in z/VM V6.3
– Re-dispatch work to same processor it ran on last dispatch
28
© 2013 IBM Corporation
Enterprise COBOL for z/OS v5.1
The key to supercharging IBM System z Applications
 Advanced technology designed to optimize
COBOL programs and fully exploit System z
hardware
–
Delivers greater than 10% performance improvement
over Enterprise COBOL v4 for well structured, CPUintensive batch applications on System z1
–
Many numerically intensive programs have shown
performance increases greater than 20%1
–
Maintains compatibility with previous COBOL releases
 New programming and application
modernization capabilities.
–
Where Tradition Meets Innovation…
Modernize Applications to work
with web, cloud and mobile
infrastructures
Increase
Programmer
Productivity
Enables users to deliver enhancements to business
critical applications quicker with less cost and lower risk
Bolsters overall
benefits of
CICS, IMS™,
DB2
Increase Performance of
Business Critical
Applications
 Allows users, who implement sub-capacity
tracking, to reduce administrative overhead
 Supports the ecosystem of COBOL
development tools supplied by
"Our testing of COBOL V5
IBM and ISVs.
shows a significant performance improvement for math. As a financial
services company with a continually narrowing batch window, that improvement is very important to us. It
will help us meet our Service Level Agreements and reduce cost driven by CPU utilization.”
Michael A Todd, Software Architect
Multi-national financial services company
1
Results are based on an internal compute-intensive test suite.
Performance results from other applications may vary.
29
CUSTOMER VALUE
© 2013 IBM Corporation
Operating systems focused on exploiting zEnterprise value
z/OS
Version 2.1
& z/OSMF 2.1
 Handle huge volumes of
data with 100-way (SMP)
support in a single LPAR
on zEC12
 Reduce CPU load across
the board*….also up to
80% less CPU when
running VSAM RLS
against large catalogs*
 Shorten batch windows
with 40% shorter file recall
time
 Improve SAP workload
performance with 175x
faster zFS V5 directory
lookup
 Leverage Crypto-as-aservice for Linux to extend
System z’s reach as a
crypto hub
 Lower entry cost of
z/OSMF by up to 60% and
running cost by up to 25%
30
z/VM
Version 6.3
 Supports more virtual
servers than any other
platform in a single
footprint with support for
1TB of real memory,
 Support 4x more virtual
servers than previously
available
 Increased performance
for large VMs with a 4x
increase in memory
scalability while
maintaining greater
than 90% resource
utilization
 More efficient use of
CPU resources for
better price
performance
 Enabled for OpenStack
support
z/VSE
Version 5.1
 Special Linux on
System z offering for
V5 and zBC12 clients
 New 64-bit virtual
addressing for
exploiting larger
memory for Virtual
Storage Constraint
relief
 Gain visibility and
control into CICS with
CICS Explorer at no
extra chargeExploits full
range of IBM System
Storage
 More efficient
communications with
Linux Fast Path by
eliminating need for
TCP/IP stack
 Allows z/VSE
applications to access a
relational database on
System z or zBX
z/TPF
Version 1.1
 World’s most efficient
platform for real-time
reservations and credit
card authorizations
 Average 35%
performance
improvement on IBM
zEC12/BC12
 New adapter for ODM
improves cross
platform integration
 New business
eventing allows
integration with the
enterprise eventing
 Open development
environment to
leverage skills
commonly available
Linux on
System z
 Deploy from hundreds
(zBC12) to 1000’s
(zEC12) of virtual
servers in a single
footprint
 Secure isolation of
Logical Partitions with
highest level of security
certification (EAL5+)
 Balanced System
Design with up to 3TB
of memory (zEC12)
 Pre-Packaged Linux
only Server (ELS)
includes Hardware,
Hypervisor,
Maintenance
 Enterprise Linux Server
(ELS) for Analytics
 Support for Red Hat,
SUSE and OpenStack
© 2013 IBM Corporation
zBC12: The right-sized mainframe
IBM continues to redefine and extend the mainframe to deliver new
strategic capabilities and deeper client value
An Integrated
Data & Analytics
Engine
Efficient, Agile
Cloud Computing
Foundation
Sophisticated
platform for
Mobile Computing
Ultimate in
Trusted Security
& Resiliency
31
 Processor chip optimized for performance
 New z/OS support for compression acceleration and
memory to memory communication
 Business application availability
 Flexible connectivity
 Balanced performance and growth – cycle time
improvements, core counts, memory, bandwidth
 Hybrid computing expands application portfolio and allows
for improved integration and management
 Improved economies of scale on z/VM 6.3
 Enterprise connectivity
 System z security as enterprise standard
 WebSphere® MQ offers reliable mobile backbone
 Isolation of workloads and data for highest level of security
 Security for sending financial data for clients and vendors
 Digital signatures for smart cards
 Simplification for set up and support of security
© 2013 IBM Corporation
Misc zBC12 charts
32
© 2013 IBM Corporation
zBC12 continues the CMOS Mainframe heritage
5000
4500 4500
4000 4000
3500 3500
3000 3000
2500
MHz
2500
2000
2000
1500
1500 1000
1000
500
500 0
0
33
z800
180 nm SOI
625 MHz
Up to 4 CPs
Full 64-bit
architecture
2002
z890
130 nm SOI
1.0 GHz
4 CPs
Super-scalar
core
Modular SMP
z9 BC
90 nm SOI
1.4 GHz
4 CPs (7 IFLs)
2004
2006
z10 BC
65 nm SOI
3.5 GHz
5 CPs (10 IFLs)
High-freq core
3-level cache
2008
z114
45 nm SOI
3.8 GHz
5 CPs (10 IFL)
OOO core
zBX integration
2011
zBC12
32 nm SOI
4.2 GHz
6 CPs (13 IFL)
PCIe: zEDC
Express, 10GbE
RoCE Express,
Flash Express and
IBM zAware
2013
© 2013 IBM Corporation
zEnterprise BC12 (zBC12)
Increased scale and flexibility increase your options
zBC12
Machine Type: 2828
Models: H06, H13
 New 4.2 GHz processor chip for performance boost
for all workloads
– Full uniprocessor at over 1064 MIPS with total capacity
available almost 5000 MIPS
 Increased granularity for right sizing
– New entry level at 50 MIPS
– 26 capacity levels and 6 CPs = 156 settings
– Complete granularity matrix available on both models
 Up to 496 GB available RAIM memory
– Excellent for new workloads like Linux and WebSphere
Up to
36%
Faster engines1
Up to
58%
More total capacity1
Up to
62%
More capacity for Linux1
 Model H13 brings new options for growth
– 58% more total capacity than zEnterprise 114 (z114)1
– Combined with z/VM 6.3 – improved scale (up to 13 IFLs),
more memory and availability for cloud ready qualities of
service make it perfect for Linux only server (ELS)
– Economics are excellent for Coupling Facility only server
1 Based
on preliminary internal measurements and projections and compared to the z114 and/or z10 BC. Official performance data will be available upon announce. Results may vary by customer based on individual
workload, configuration and software levels. Visit LSPR website for more details at: https://www.ibm.com/servers/resourcelink/lib03060.nsf/pages/lsprindex?OpenDocument
34
© 2013 IBM Corporation
zBC12 Processor chip optimized for software performance
Exploited by Java, PL/I, compilers, DB2, more
 Similar Single Chip Module (SCM) as z114
 Our leadership in microprocessor design supports
a boost in performance for all workloads
– Second generation out of order execution design
 Larger caches to optimize data serving
environments
– Almost 2x on chip and 2x additional on drawer
 Fully utilized memory with single z/VM 6.3 system
plus HiperDispatch plus up to 13 IFLs = great
platform for ELS
 New hardware functions optimized for software
performance
– Help for lockouts, reduction of Java overhead,
improvements to DB2 bufferpools and Java heaps,
complier improvements with decimal format
conversions facility
35
© 2013 IBM Corporation
Systems Management for IBM zEnterprise BC12 (zBC12)
IBM Automation Control for z/OS provides comprehensive Application and
Resource Management capabilities for today’s multi architecture data centers
Visibility, Control, and Automation for
modern Data Center Management
Automation of Server Management
Simplify, automate, and improve service
quality thru Management of Blades and
Virtual Servers.
Control of zBX Management
IBM Automation Control for z/OS controls
local CPC, LPARs, Systems (incl. Linux
on System z), and BladeCenters/Blades
(incl. automated start/stop of Virtual
Servers).
Visibility
Dynamic Discovery of Virtual Servers
running on a Blade.
36
© 2013 IBM Corporation
zBC12 Functional Comparison to z114
Processor /
Memory
Virtualization and
Alternative
Processors




Uniprocessor Performance
System Capacity
Processor Design
Cache






Models
Processing cores
Granular Capacity
Memory
Fixed HSA
Data Compression
 Virtualization
 zEnterprise BladeCenter Extension
(zBX)
Connectivity




HiperSockets
FICON®
I/O subsystem
Internal I/O Bandwidth
 Coupling
 Cryptography
 RAS Focus
RAS
Environmentals
37
 Up to 36% performance improvement over z114 uniprocessor*
 Up to 58% general system capacity performance improvement over z114 (comparison of the
zBC12 z06 to the z114 z05)
 Up to 62% greater total system capacity over z114 (zBC12 13way compared to the z114
10way)
 New 4.2 GHz processor chip versus 3.82 GHz
 zBC12 has 33% more L2 cache, instruction and data (total 2 MB versus total 1.5 MB on z114),
100% more L3 cache (total 24 MB versus 12 MB on z114), 100% more L4 cache (192 MB
versus 96 on z114)
 Two models with up to 2 CPC drawers
 Up to 13 cores to configure, up to 10 on z114
 Up to 156 capacity settings versus 130 on the z114
 Up to 512 GB RAIM memory versus 256 GB on the z114
 16 GB fixed HSA versus 8 GB fixed on z114
 New zEDC Express
 zEnterprise Unified Resource Manager provides virtualization management for blades installed
in the zBX Mod 003.
 zEnterprise Unified Resource Manager has “resource workload awareness” where hybrid
resources can be managed and optimized across the zEnterprise.
 zEnterprise System is a truly integrated hardware platform that is able to span and intelligently
manage resources across mainframe and distributed technologies – including select
POWER7® and IBM System x blades
 Supported optimizer is IBM WebSphere DataPower XI50 V5.0 in the zBX Mod 003.
 zBX Model 003 (versus zBX Model 002 which attaches to z114)
 zBX has optional top exit I/O and power cabling
 Both zBC12 and z114 support of 32 HiperSockets
 New OSA-Express5S 10 GbE, GbE and 1000 BASE-T included in PCIe I/O infrastructure.
FICON Express8S, New 10 GbE RoCE Express for SMC-R
 zBC12 has industry standard 8 GBps PCIe supports high speed connectivity and high
bandwidth same on z114
 Coupling with HCA-3 InfiniBand Coupling Links same on z114
 Crypto Express4S enhanced with new FIPS 140-2 Level 4 cert and PKCS#11 support
 Elliptic Curve Cryptography (ECC)
 Availability
 New IBM zAware offers high speed analytics facilitates the ability to consume large quantities
of message logs for smarter monitoring
 zBC12 offers advanced memory enhancements (RAIM) and advanced power and thermal
optimization and management that can help to control heat / improve RAS
 PCIe New Flash Express on zBC12 to handle paging workload spikes and improve availability
– not available on z114
 Energy
 Cooling
 Optional Non Raised Floor and overhead cabling options for both I/O and Power
 More capacity but same environmentals as the z114
* LSPR mixed workload average running z/OS 1.13 – zBC12 Z01 versus z114 Z01
** Based on preliminary internal measurements and projections and compared to the z10BC. Official performance data will be available upon
announce. Results may vary by customer based on individual workload, configuration and software levels. Visit LSPR website for more details
© 2013 IBM Corporation
zBC12 Functional Comparison to z10 BC
Processor /
Memory










Virtualization and
Alternative
Processors
 Virtualization
Uniprocessor Performance
System Capacity
Processor Design
Cache
Models
Processing cores
Granular Capacity
Memory
Fixed HSA
Data Compression
 zEnterprise BladeCenter Extension
(zBX)
Connectivity




HiperSockets
FICON
I/O subsystem
Internal I/O Bandwidth
 Coupling
 Cryptography
RAS
Environmentals
38
 RAS Focus
 Almost 61% performance improvement over z10 BC uniprocessor*/**
 Up to 77% general system capacity performance improvement over z10 BC 10-way (zBC12
z06 compared to the z10 BC z05)**
 New 4.2 GHz processor chip versus 3.5 GHz on z10 BC
 zBC12 has more than 100% more cache than z10 BC
 zBC12 has two models and z10 BC has one model
 Up to 13 cores to configure, up to 10 on z10 BC
 Up to 156 capacity settings versus 130 on the z10 BC
 Up to 512 GB RAIM memory versus 256 GB on the z10 BC
 16 GB fixed HSA versus 8 GB fixed on z110 BC
 New zEDC Express
 zBC12 offers zEnterprise Unified Resource Manager provides virtualization management for
blades installed in the zBX Mod 003.
 zEnterprise Unified Resource Manager has “resource workload awareness” where hybrid
resources can be managed and optimized across the zEnterprise.
 zEnterprise System is a truly integrated hardware platform that is able to span and intelligently
manage resources across mainframe and distributed technologies – including select POWER7
and IBM System x blades
 Supported optimizer is IBM WebSphere DataPower XI50 V5.0 in the zBX Mod 003.
 zBX Model 003 versus N/A on z10 BC
 zBX has optional top exit I/O and power cabling
 Double HiperSockets – 32 on zBC12 and z10 BC supports of 16
 New OSA-Express5S 10 GbE, GbE and 1000 BASE-T included in PCIe I/O infrastructure.
FICON Express8S, New 10 GbE RoCE Express for SMC-R
 zBC12 has industry standard 8 GBps PCIe supports high speed connectivity and high
bandwidth and z114 6 GBps Infiniband support
 Coupling with HCA-2 InfiniBand Coupling Links
 Crypto Express4S enhanced with new FIPS 140-2 Level 4 cert and PKCS#11 support versus
Crypto Express2 on z10 BC
 Elliptic Curve Cryptography (ECC) on zB12 is not available on z10 BC
 Availability
 New IBM zAware offers high speed analytics facilitates the ability to consume large quantities
of message logs for smarter monitoring (not available on z10 BC)
 zBC12 offers advanced memory enhancements (RAIM) (no RAIM on z10 BC) and advanced
power and thermal optimization and management that can help to control heat / improve RAS
 PCIe New Flash Express on zBC12 to handle paging workload spikes and improve availability
– not available on z10 BC
 Energy
 Cooling
 zBC12 offers optional Non Raised Floor and overhead cabling options for both I/O and Power
(no overhead cabling options on z10 BC)
 More capacity but the same environmentals as the z114
* LSPR mixed workload average running z/OS 1.13 – zBC12 Z01 versus z10 BC Z01 z114 Z01
** Based on preliminary internal measurements and projections and compared to the z10BC. Official performance data will be available
upon announce. Results may vary by customer based on individual workload, configuration and software levels. Visit LSPR website for
more details
© 2013 IBM Corporation
Protecting your investment in IBM technology
 Designed to protect your investment
zBX
Mod 002
z114
z10 BC
– Offering upgrades from z10 BC and z114 to the
zBC12
– Upgrades from zBX Model 002 to
zBX Model 003
 The zEnterprise System offers full
upgradeability within the family
– zBC12 Model H13 upgraded to
zEC12 Model H20
– Upgrade from Model H06 to Model H13
will require a planned outage
zBC12
 On demand offerings offer temporary or
permanent growth when you need it
zEC12
39
zBX
Mod 003
© 2013 IBM Corporation
Misc zEC12 charts
40
© 2013 IBM Corporation
Processor chip optimized for software performance
Exploited by Java, PL/I, compilers, DB2, more
 Our leadership in microprocessor design supports a boost in performance for all workloads
– Second generation out of order execution design
– Multi-level branch prediction supports complex workloads
 Larger caches to optimize data serving environments
– Almost 2x on chip and 2x additional on book
 New hardware functions optimized for software
performance
– Transactional Execution Facility for parallelism and scale
– Runtime Instrumentation Facility is intended to help
reduce Java overhead
– 2 GB page frames are intended to offer performance
Improvements for DB2 buffer pools and Java heaps
– New IBM Enterprise PL/I compiler is planned to exploit and
get a performance boost from decimal format conversions
facility
– Up to 30% improvement in IMS™ throughput due to faster
CPU, cache and compliers1
Excellent Results:
Up to
45%
Improvement
in throughput
for Java
workloads1
Up to
32%
Improvement in
performance for IBM
Cognos Business
Intelligence V10.21
Up to
30%
Improvement in
throughput for
DB2 for z/OS
operational
analytics2
More than
30%
Improvement
in throughput
for SAP
workloads1
– Workloads leveraging Flash Express with Pageable Large Pages
can see up to a 8% price performance improvement3 over the z196
1 Based
2
3
41
on preliminary internal measurements and projections
As measured by the IBM 9700 Solution Integration Center. The measured operational BI workload consists of 56 concurrent users executing a fixed set of 160,860 Cognos reports . Compared DB2 v10 workload
running on IBM's z196 w/10 processors to an zEC12 w/10 processors
based on average 5% discount for zEC12 workloads under the AWLC pricing plus up to 3% more performance per MSU with Flash Express.
© 2013 IBM Corporation
zEnterprise: Enhancing our IBM Mainframe Platform
IBM continues to deliver enhancements that strengthen the role of the mainframe
Support for 50% more I/O
devices per FICON channel
New 10GbE RoCE
Express
Efficiencies provided for
shared CF engines
EP11 and digital
signatures - more
standards
Flash Express exploited
by Coupling Facility
Simplification and new
wizard on TKE 7.3
workstation
LPAR capacity
setting update
New Smart card with
stronger encryption
zManager enhancements
z/VM 6.3 support for
1TB real memory
zEDC Express for data
compression
Refresh OSA technology
with OSA-Express5S
Crypto as a Service
with z/OS V2.1
zEC12: Our Smarter Computing infrastructure that is Cloud Ready, Data Ready
and Security Ready, enabling a Smarter Planet® for today and tomorrow
42
© 2013 IBM Corporation
Systems Management for IBM zEnterprise EC12 (zEC12)
IBM System Automation for z/OS provides comprehensive Application and
Resource Management capabilities for today’s multi architecture data centers
Visibility, Control, and
Automation for modern Data
Center Management
Automation of Server Management
Simplify, automate, and improve service
quality thru Management of Blades and
Virtual Servers.
Control of zBX Management
IBM Automation Control for z/OS
controls CPCs, LPARs, Systems (incl.
Linux on System z), and
BladeCenters/Blades (incl. automated
start/stop of Virtual Servers).
Visibility
Dynamic Discovery of Virtual Servers
running on a Blade.
43
© 2013 IBM Corporation
Protecting your investment in IBM technology
zBX
Mod 002
z196
 Designed to protect your investment
– Offering upgrades from z10 EC™ and z196 to
the zEC12
– Upgrades from zBX Model 002 to zBX Model
003
z10 EC
zBC12
 The zEnterprise System offers full
upgradeability within the family
– zBC12 Model H13 upgraded to zEC12 Model
H20
– Upgrade to Model HA1 will require a planned
outage
 On demand offerings offer temporary or
permanent growth when you need it
zEC12
44
zBX
Mod 003
© 2013 IBM Corporation
Misc Cloud and Linux for
System z charts
45
© 2013 IBM Corporation
zEnterprise offers Linux support to match your business needs
Increased flexibility for your multi-architecture strategy
zEnterprise System
 Scalability and security in a smaller infrastructure
 Dynamic workload management and systems management to
help manage the life cycle of the z/VM hypervisors and the
virtual servers
 Provides a more manageable infrastructure for cloud computing
 Expanded ISV support for enterprise
applications
 Silo managed islands of computing
 Less dynamic than System z
virtualization
 Minimal resource sharing with
System z resources
 Broad availability of solutions
 No single point for Enterprise
management
Distributed Systems
(including Flex)
46
 Targeted for applications that
interact with mainframe data and
transactions
 Provisioned and managed by
System z
Select IBM x86 Blades in zBX
 Extreme consolidation of servers and
networking
 Superior levels of virtual server
provisioning, monitoring and workload
management
 Industry-best virtual I/O bandwidth and
reliability
 Fewer components and reduced
complexity
 System z qualities of dynamic resource
management and capacity-on-demand
 Seamless integration with z/OS
backup and disaster recovery solutions
Linux on z/VM
© 2013 IBM Corporation
Advantages of building your Private Cloud on IBM zEnterprise
Increased
Productivity
 Advanced workload
management that
provisions resources on
the fly
 U.S. Bank reduced
provisioning time from
45 days to 20 minutes
Higher
Utilization,
Scalability
 Up to 100% CPU
utilization
 “Shared everything”
architecture
 Manage up to 100,000
virtual servers
More Efficient Data
Center
 Up to 80% less energy
than existing distributed
servers
 Less floor space
 Fewer parts to manage
Greater Reliability,
Availability, Security
 Built-in hardware
redundancy
 Decades of RAS innovation
 Capacity and Backup
on Demand
 Highest security rating
EAL5+
The City and County of Honolulu implemented a cloud environment that reduced
database licensing costs by 68 percent and reduced time to deploy
applications from one week to a few hours
47
© 2013 IBM Corporation
zEnterprise Delivers an Open Cloud infrastructure
Integrate
IBM
Products
&
Offerings
 zEnterprise: zEC12, z196,
zBC12, z114
 Linux on System z
 z/VM 6.3
New
CSL Wave
 Provided by CSL International
ISV
 Hypervisor Manager
Solutions
 Cross marketing agreement to
market and promote product
IBM announced intention
to acquire
Open
Source
Options
48
Automate
Orchestrate
 Tivoli Provisioning Manager
 Cloud Ready for Linux on System z
 SmartCloud Entry
 SmartCloud Provisioning
 Tivoli Service Automation
Manager
 SmartCloud Orchestrator
System z support currently in development
zPRO
 Provided by Velocity Software
 Add-on feature to Velocity’s zVPS
product that provides performance
management
 Provides golden image creation,
cloning, and operational controls
APPLogic
 Provided by Computer Associates
 Manages both distributed and z/VM
environments.
MOAB
 Provided by Adaptive Computing
 Provides a policy based cloud
management based on xCAT
xCAT
 Extreme Cloud Administration Tool
 Now supported on z/VM through
services offering (GTS)
OpenStack
 Being enabled for z/VM first and eventually zManager
 Being used as a code base for SCE / SCP / SCO
© 2013 IBM Corporation
RHEL for System z Business Class Promotion
Benefit from the security, performance and scalability of both
technologies and save 50% on Red Hat Enterprise Linux on
IBM System z Business Class servers
 Consolidate workloads and save on software license costs
 Bring Data closer to the Application
 Explore Big Data and Analytics under Linux on System z
 Extra security with SELinux and platform independent Management with
RHN Satellite
Rules:
- Discount of 50% on MSRP
- Applicable for Business Class (BC) machines only
- New workloads* (Net New Customers)
- Limited to 28th February 2014
For more information - contact Red Hat’s local Alliance Manager or:
WW
US
EMEA
APAC
LATAM
BRAZIL
Filipe Miranda
Jennifer Miller
Sebastian Siegert
Norman Deery
Mariano Fernandez
Samuel Masini
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
*Not valid for renewals of regular Subscriptions
49
z114
zBC12
www.redhat.com/products/enterprise-linux/for-ibm-system-z/promotions/
© 2013 IBM Corporation
SUSE for System Business Class Promotion
SLES for System z Business Class
Multi-IFL Promotion (USD)
Basic Subscription:
Basic Subscription Pricing*
1 IFL
2-5 IFLs
6-11 IFLs
12+ IFLs
1 year
$6,000
$5,700
$5,600
$5,500
3 year
$16,200
$15,400
$15,100
$14,800
5 year
$24,000
$22,800
$22,400
$21,900
includes Code Maintenance,
such as patches, fixes and
security updates.
Can be combined with IBM
GTS services
Standard Subscription Pricing*
1 IFL
2-5 IFLs
6-11 IFLs
12+ IFLs
Standard Subscription:
1 year
$7,500
$7,200
$7,000
$6,900
3 year
$20,300
$19,300
$18,900
$18,500
5 year
$30,000
$28,500
$27,900
$27,300
$1
includes Basic Subscription
deliveries plus 12x5 Support
services delivered by SUSE
Technical Services
$1
$1
Priority Subscription Pricing*
1 IFL
2-5 IFLs
6-11 IFLs
12+ IFLs
1 year
$9,000
$8,600
$8,400
$8,200
3 year
$24,300
$23,100
$22,600
$22,200
5 year
$36,000
$34,200
$33,500
$32,800
Priority Subscription:
includes Basic Subscription
deliveries plus 24x7 Support
services delivered by SUSE
Technical Services
* Per IFL. Get more details on subscription and support service levels here !
ATTENTION:
 Offer is restricted to new System z Business Class purchases only
st
 Promotion Period: September 2013 (with availability of zBC12) through December 31 , 2014
 Get a 50% discount compared to regular Multi-IFL pricing – plus volume discount!
50
© 2013 IBM Corporation
IBM FlashSystem Solution
Combining IBM SVC & IBM FlashSystem™
Considerations for Linux on System z
 The extreme performance of IBM FlashSystem with IBM MicroLatency™ provides:
– I/O per sec 430k - Mixed 70/30% read/write (Model 820)
– Low entry price (4 TB on the Model 810)
– Very attractive match of incredible performance and price options - Model 820 12 TB
•
Include the San Volume Controller (SVC) at competitive pricing
– Delivers outstanding performance per gigabyte, can quickly uncover business insights using
traditional data analytics as well as new big-data technologies.
– Enterprise Class services with SVC
•
Business Continuity with Copy services, Flash Copy Back-up, Drive Storage
Efficiency with Easy Tier.. driving optimal Workload Availability
– When compared to equivalent disk systems, IBM flash storage solutions deliver 6.7 times
more capacity in a single rack, 19 times more cost efficiency in dollars/per IOPS, and are
115 times more energy efficient. (1)
Connect via Fiber Channel with
enterprise services using SVC
Thin Provisioning & Real Time Compression
Drive Storage Efficiency with Easy Tier
51
1 Flash Outperforms disk in IBM Almaden Research Lab Demonstration
© 2013 IBM Corporation
New IBM FlashSystem storage extends ELS offering
The new IBM SAN Volume Controller and IBM FlashSystem bundle offers an
economically priced storage solution for our Enterprise Linux Server clients.
Right combination of performance and function:
The extreme performance of IBM FlashSystem with IBM MicroLatency™
• Advanced storage functionality of IBM SVC
•
•
Thin Provisioning – allocate storage “just in time”
•
Easy Tier – storage efficiency
•
FlashCopy – point in time copies
•
Mirroring/Copy Services – data replication and protection
•
Real-Time Compression – up to 5X more data in the same physical space
An ability to cost effectively deploy quickly and realize
immediate results
IBM SAN Volume Controller (SVC) and IBM
FlashSystem bundle are support ‘out of the box’
by z/VM and Linux on System z.
52
© 2013 IBM Corporation
Backup charts on IBM zEDC
53
© 2013 IBM Corporation
Increasing Value with New Technology Innovations
NEW! zEDC
Express
NEW! 10GbE RoCE
Express with SMC-R
New! Flash Express
New! IBM zAware
Low latency, CPU
Efficient Data
Compression
Low latency, high
performance network
communications
Improved availability and Improve availability
performance during
through smarter problem
critical workload
determination
transitions
… available on both zEC12 and zBC12
54
© 2013 IBM Corporation
Explosive growth in data
Every day 2.5 quintillion bytes of data are created
Data needs to be shared
cross platform
Managing and storing data
can push expenses up for IT
Many types of compression
are used today
 Today’s modular business
applications are
heterogeneous
 While able to improve I/O
throughput and thus
performance, many compression
applications consume CPU
resources
 Many offerings for archive –
creating data that will be
infrequently accessed
 Batch workloads and some data
types can drive up compression
requirements
 Industry standard compression
offerings in market like zlib
 Applications need to be able to
efficiently share and process
large files
 Not being able to compress files
can contribute to added disk
expense
 Smaller files allowing for faster
network transfers
 IBM System z offers hardware
compression on all System z
processor chips
…. Still massive amounts of data are not being compressed and need a
different approach to compress more “active” data
55
© 2013 IBM Corporation
IBM zEnterprise Data Compression (zEDC)
New data compression offering that can reduce resource usage
What is it?
How is it different
 A combined software (z/OS V2.1) and
hardware (zEDC Express) solution designed
to help reduce resource consumption, disk
utilization and optimize cross platform
exchange of data
 Performance: Efficient alternative for
larger files. Reduced CPU overhead for
SMF jobs.
 Efficient: Optimized algorithms scan text to
locate the re-use of phrases and refers back
to earlier references
 Industry Standard: Compatible with open
zlib based compression – widely used
across all platforms
 Economical: Reduced DASD space
requirements and improved effective
bandwidth without significant CPU
overhead***
15% reduction in elapsed time for
SMF extraction with up to 40%
reduction for CPU time *
56
Logger overhead reduced by up to
30% **
* When running an SMF extraction/dump against an SMF logstream with records compressed by zEDC
** The amount of data sent to an SMF logstream can be reduced by up to 75% using zEDC compression – reducing logger overhead
*** SOD for BSAM/QSAM access methods
All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
© 2013 IBM Corporation
Use cases for zEDC
Target Market for zEDC
Use Cases
 Reduced logger overhead allows collection of
more SMF data
 Increase the amount of data you can keep
active by compressing more frequently
accessed data
 Enhance cross platform data exchange when
sending / receiving large data files
 SOD: Improve disk utilization and economics
of using flash for extended format
BSAM/QSAM
 SOD: Improve latency for Java applications
57
 Introductory Use with SMF Log Data: Clients
running SMF using logger that are looking to
reduce the logger overhead or collect
additional data
 Clients such as a clearing house, financial
institution or direct marketing agencies that are
sending and receiving large files
 SOD: Customers with large volumes of extended
format BSAM/QSAM sequential data
 SOD: Clients that have purchased flash on
DS8870 and want to use it more efficiently when
storing extended format BSAM/QSAM sequential
data
 SOD: Clients that use Java today where they
create a stream of compressed data
© 2013 IBM Corporation
zEDC Requirements
 Operating system requirements
– Requires z/OS 2.1 and new zEDC for z/OS feature
– z/OS V1.13 and V1.12 offer software decompression support only
– Easy to set up and use – transparent to application software
•
•
Use policy (DATACLASS) to set up compression.
No changes to access method
 Server requirements
– Exclusive to zEC12 (with Driver 15E) and zBC12
– New zEDC Express feature for PCIe I/O drawer (FC#0420)
•
•
One compression coprocessor per zEDC Express feature
Each feature can be shared across up to 15 LPARs
– Recommended minimum configuration per server is two features
•
Up to 8 features available on zEC12 or zBC12
– For best performance, feature is needed on all systems accessing the compressed data
 Planned exploitation:
– Hardware exploitation first for log files - SMF records (September 2013) reduced logger overhead
allows collection of more SMF data
– All systems sharing sequential BSAM/QSAM extended format (1Q’14)*
– SOD: Java using standard zlib compression library for compression services. Java applications
and middleware can be transparently accelerated by enabling Java for hardware compression
– SOD: DFSMS™ planned exploiters TBD
58
All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
© 2013 IBM Corporation
IBM Offers Multiple Compression Technologies for the
Mainframe
Type
Optimized for
Performance
Overhead
Supported data
Frequency of
access post
compression
CMPSC compression
on System z
processor chip
Optimal for DB2 or
select DFSMS files
On Chip, relatively little CPU
overhead and less I/O, Fast
• DB2 - Optimized for rowwise access to data is
required
• DFSMS files – for VSAM
and non-VSAM extended
format data sets
Often
Other software
compression (zlib, or
similar)
Most compression uses
industry std today.
Used by many file types
Higher CPU - software
instructions executed. Note: if
Java then eligible for zIIP (or
zAAP)
Any. De facto standard for
almost any type of data.
Often
Tape HW
compression
Tape compression –
optimized for use with
large files, archival
purposes
Performed by the tape
subsystem
Any.
Often – Rare (application
dependent)
Archival / Backup
Archive data and data
to backup/copy
CPU overhead, longer wall
clock time
DFSMShsm, DFSMSdss
Often – Rare (application
dependent)
Real time
compression
IBM NAS storage
No performance degradation
SVC
Designed for active
primary data.
zEDC Express
Active, for cross
platform data
exchange. Enables
compression of active
and inactive data
Processing on zEDC Expressexpect minimal CPU overhead,
low latency
•
•
•
•
Frequent access required.
Useful for files that
previously used software
compression as well
59
SMF though logger
zlib compatible
SOD – Java
SOD – BSAM/QSAM
Extended format
• SOD DFSMShsm /dss
• SOD Encryption Facility
© 2013 IBM Corporation
IBM System z Batch Network Analyzer and Compression
Helping determine if you have files that are candidates for zEDC
 IBM System z Batch Network Analyzer
– A free, “as is” tool to analyze batch windows
– Available to Customers, Business Partners and IBMers
– Replaces the old BWATOOL
– PC based, and provides graphical and text reports
• Including Gnatt charts and support for Alternate Processors
 Available from NA ATS CPSTools team
– http://w3-03.ibm.com/support/techdocs/atsmastr.nsf/WebIndex/PRS5126
 New news… zBNA will identify zEDC Compression Candidates
– Post-process customer provided SMF records, to identify jobs and data sets which are zEDC
compression candidates across a specified time window, typically a batch window
– Help estimate utilization of a zEDC feature and help size number of features needed
– Generate a list of data sets by job which already do hardware compression and may be candidates for
zEDC
– Generate a list of data sets by job which may be zEDC candidates but are not in extended format
– Target availability – 4Q 2013
60
© 2013 IBM Corporation
Backup charts on SMC-R and
10GbE RoCE Express
61
© 2013 IBM Corporation
Increasing Value with New Technology Innovations
NEW! zEDC Express NEW! 10GbE RoCE
Express with SMC-R
New! Flash Express
Low latency, CPU
Efficient Data
Compression
Improved availability and Improve availability
performance during
through smarter problem
critical workload
determination
transitions
Low latency, high
performance network
communications
New! IBM zAware
… available on both zEC12 and zBC12
62
© 2013 IBM Corporation
Network Performance Issues
Use of traditional TCP/IP technology is not optimal for some environments
 Many applications today use TCP/IP to communicate server to server
 Using traditional Ethernet technology, network latency and processor resource
consumption can be high.
– Network latency can be seen when sensitive transactional workloads such as
WebSphere are accessing a database using TCP/IP.
– The amount of CPU resource consumed for applications moving big data such as file
transfer programs, streaming workloads or some web based protocols can drive up
total cost of operations.
 These performance issues can be due TCP/IP communications being executed
in software.
– The amount of time needed for handshaking can propagate across the link and add to
latency in the transmission of information
63
© 2013 IBM Corporation
Optimize server to server networking - transparently
“HiperSockets-likes” capability
What is it?
How is it different
 Shared Memory Communications via Remote
Direct Memory Access (SMC-R) is a feature of
z/OS V2.1 and will exploit a new 10GbE RoCE
Express feature of zEC12 or zBC12
 The combination is designed to reduce latency
and improve wall clock time
 Can be server-to-server communication in a
multi-server environment or LPAR-to-LPAR
communication on a single system
Transaction
without SMC-R
Transaction
with SMC-R
Network
TCP
SMC-R
 Industry Standard: Exploits standard 10 Gb
Ethernet fiber optic links
 Transparent: z/OS TCP sockets based
applications can use seamlessly
 Secure: Preserves existing network security
model, IP topology, network administrative
and operational model
 Coexist: Coexists with HiperSockets
Network
TIME
Reduced latency,
CPU consumption and improved wall clock time
80%
Network latency reduced up to
for z/OS TCP/IP multi- tier OLTP workloads such
as web based claims and payment systems *
64
* Based on internal IBM benchmarks of modeled z/OS TCP sockets-based workloads with request/response traffic patterns using SMC-R vs TCP/IP. The
actual throughput that any user will experience will vary.
© 2013 IBM Corporation
Use cases for SMC-R and 10GbE RoCE Express for z/OS to
z/OS communications
Use Cases
 Application server such as CICS communicating (via TCP based communications) with a database
server such as DB2 – particularly when the application is network intensive and transaction
oriented
 Transactional workloads that exchange larger messages (e.g. web services such as WAS to DB2
or CICS) will see benefit.
 Streaming (or bulk) application workloads (e.g. FTP) communicating z/OS to z/OS TCP will see
improvements in both CPU and throughput
 Applications that use z/OS to z/OS TCP based communications using Sysplex Distributor
Plus … Transparent to application software – no changes required!
65
© 2013 IBM Corporation
SMC-R and 10GbE RoCE Express Requirements
 Operating system requirements
– Requires z/OS 2.1 which supports the SMC-R protocol
 Server requirements
– Exclusive to zEC12 (with Driver 15E) and zBC12
– New 10 GbE RoCE Express feature for PCIe I/O
drawer (FC#0411)
 Single port enabled for use by SMC-R
 Each feature must be dedicated to one LPAR
– Recommended minimum configuration two features
per LPAR for redundancy
 Up to 16 features supported
– OSA Express – either 1 GbE or 10 GbE
 Must be Layer 2 connection
 Does not need to be dedicated to the LPAR
– Standard 10GbE Switch or point to point configuration
supported
66
© 2013 IBM Corporation
Impact of SMC-R on real z/OS workloads – early benchmark results
WebSphere to DB2 communications using SMC-R
40% reduction in overall transaction response time
for WebSphere Application Server v8.5 Liberty profile
TradeLite workload accessing z/OS DB2 in another
system measured in internal benchmarks *
Linux on x
Workload Client
Simulator
(JIBE)
z/OS
SYSA
TCP/IP
HTTP/REST
WAS
Liberty
TradeLite
SMC-R
z/OS
SYSB
JDBC/DRDA
RoCE
DB2
File Transfers (FTP) using SMC-R
z/OS
SYSA
FTP Client
SMC-R
FTP
z/OS
SYSB
Up to 50% CPU savings for FTP binary file transfers
across z/OS systems when using SMC-R vs standard
TCP/IP **
FTP Server
RoCE
CICS to CICS IP Intercommunications (IPIC) using SMC-R
Up to 48% reduction in response time and up to 10% CPU
savings for CICS transactions using DPL (Distributed Program
Link) to invoke programs in remote CICS regions in another z/OS
system via CICS IP interconnectivity (IPIC) when using SMC-R vs
standard TCP/IP ***
z/OS
SYSA
CICS A
DPL calls
SMC-R
IPIC
RoCE
z/OS
SYSB
CICS B
Program X
* Based on projections and measurements completed in a controlled environment. Results may vary by customer based on individual workload, configuration and software levels.
** Based on internal IBM benchmarks in a controlled environment using z/OS V2R1 Communications Server FTP client and FTP server, transferring a 1.2GB binary file using SMC-R (10GbE
RoCE Express feature) vs standard TCP/IP (10GbE OSA Express4 feature). The actual CPU savings any user will experience may vary.
*** Based on internal IBM benchmarks using a modeled CICS workload driving a CICS transaction that performs 5 DPL calls to a CICS region on a remote z/OS system, using 32K input/output
containers. Response times and CPU savings measured on z/OS system initiating the DPL calls. The actual response times and CPU savings any user will experience will vary.
67
© 2013 IBM Corporation
Flash Express
68
© 2013 IBM Corporation
Increasing Value with New Technology Innovations
NEW! zEDC Express NEW! 10GbE RoCE
Express with SMC-R
New! Flash Express
Low Latency, CPU
Efficient Data
Compression
Improved availability and Improve availability
performance during
through smarter problem
critical workload
determination
transitions
Low latency, high
performance network
communications
New! IBM zAware
… available on both zEC12 and zBC12
69
© 2013 IBM Corporation
Flash Express
Problem
 Organizations must drive availability and consistently high
performance for workloads to meet stringent service levels
 All organizations run diagnostics that can be disruptive
causing work to stop
Today
 Many customers acquire enough real memory not to page
 But they still suffer from disruptions during key transition
periods (morning transition) and during dumps.
 Such delays impact SLAs, and can prevent other work
from processing
Flash access is much faster than disk
Goal
 Deliver improved availability and performance for
companies who cannot compromise on service
Companies will invest in improving availability
70
© 2013 IBM Corporation
Flash Express – Innovation to improve availability and performance
Drive increased availability and performance for business critical workloads
What is Flash Express?
How is it different?

An innovative PCI-e feature introduced
with zEnterprise designed to provide
improved performance and availability
 Performance: Significant improvement over
use of spinning disk. Use of pageable large
pages delivers CPU savings.

Enables the use of large 1MB pageable
pages which can improve performance of
middleware
 Transparent: no application code changes
needed.
 Secure: 128 bit AES encryption
 Resiliency: Designed for high availability and
failover, concurrent upgrade
 Virtualized: Virtualize Flash Express across
partitions
71
© 2013 IBM Corporation
IBM Flash Express
Notable Increases in Availability and Performance
What’s New?
 Dynamic Reconfiguration of Flash
Express memory
 In the future, Coupling Facility use of
Flash provides a cost effective, resilient
solution for overflow of MQ
shared queues in Coupling Facility
(SOD) *
 Support for DB2 11 use of Flash
planned for 2013, rollback of DB2 10
support via APAR
 Java SDK7 SR3 and middleware
exploiters are available
Proof Points
37% increase
in transaction throughput
during morning transition
Standalone Dump
19% reduction
in total elapsed time
SVC dump elapsed time
~25% less than
with DASD
28% improvement
in DB2 throughput
WAS Day Trader
8% performance improvement
72
* All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
© 2013 IBM Corporation
Use cases Flash Express
Target Market
 Traders, banks, FSIs or service centers
Flash Express Use Cases
(Summary)
 Any service bureau, host, cloud,
outsourcer that has non standard SLAs
Ideal during transition periods and for
smoothing paging spikes
Accelerates start of day processing –
batch to online
Reduces latency of page-ins from aux
storage
Enables faster diagnostics snapshots
Performance boost
 Companies with heavy development and
test activities
 Complements existing system availability
solutions – addresses significant
remaining application lapses
- Reduces page translations overhead
- Improves Java & DB2 performance
- Ideal for random read access & high
read/write ratios
73
© 2013 IBM Corporation
Flash Express Configuration
 FLASH Express
– Flash Express Feature Code is ordered
as a feature code, FC #0402
– Sold in card pairs, each card pair provides
1.4 TB storage; Maximum 4 card pairs (5.6 TB)
– Supported on z/OS V1.13 with web deliverable
EASY TO
SET UP
 Minimal configuration
– Uses 4 Flash Solid State Drives (SSDs) on the card
– Uses standard PCIe I/O drawer
MINIMAL
 Capacity Planning
– Sized to accommodate all paging
– No special planning needed
RESILIENT
PLANNING
SECURED
 Qualities of Service
– Error isolation, mirroring, diagnostics, failover
– Concurrent firmware update. Designed to handle
failover transparently
– NEW ! Dynamic reconfiguration of memory
 Secured Data
– Uses crypto hardware for secured data;
128 bit AES encryption
– Removal of card does not compromise data
74
© 2013 IBM Corporation
IBM zAware
75
© 2013 IBM Corporation
Increasing Value with New Technology Innovations
NEW! zEDC Express NEW! 10GbE RoCE
Express with SMC-R
New! Flash Express
Low Latency, CPU
Efficient Data
Compression
Improved availability and Improve availability
performance during
through smarter problem
critical workload
determination
transitions
Low latency, high
performance network
communications
New! IBM zAware
… available on both zEC12 and zBC12
76
© 2013 IBM Corporation
Improve Availability through smarter Problem Determination
Problem
 The complexity of today’s IT infrastructures stress operation’s
ability to resolve problems quickly and accurately.
Time to Recover from
Business Interruptions
Today
 The volume of messages is outpacing operation’s ability
to respond
– Staff cannot digest message rate of 200-300 per second
– Multiple systems concurrently issue messages which must be
interpreted together
 Today’s tools cannot effectively identify complex problems
Year
2010
Best in Class Companies
$60K
$101K
2012
– Tools cannot identify messages preceding a problem
– Many symptoms remain undetected for a long period of time
 Current problem solving techniques are inadequate
– Manual analysis of messages often requires collaboration
between multiple experts
– Brute force process of elimination method causes unnecessary
disruptions
Best in class companies still incur
expenses 60% greater
than in 2010
Goal:
 Improve the quality and speed of problem determination
to reduce IT operations cost and improve availability
Source Aberdeen Group Feb 2012
77
© 2013 IBM Corporation
IBM zAware
Improve z/OS Problem determination and time to repair with a self
contained firmware solution
How is it different?
What is it?
 IBM zAware is an integrated, self‐learning,
analytics solution for z/OS that helps
identify unusual system behavior in near
real time.
 Helps accelerate problem determination so
service is restored faster, improving
availability.
 Efficient : Needs no maintenance or integration, pre
integrated “appliance-like” form factor
 z/OS expertise: Understands System z message
patterns and can detect anomalies applying domain
knowledge
 Automated: No need to code rules to recognize
problems; supports integration with other products
 Scalable: can scale to monitor millions of messages
 Easy to use: Intuitive web based UI, easy to learn, use
Reduces time and effort to identify & diagnose problematic messages
Trends
Abnormalities
Unusual situations
78
© 2013 IBM Corporation
Lessons learned: Each Tool Has a Specific Role to Drive
Availability
Early Warning
Determination &
Diagnosis
Prevention
Early warning based on
existing metrics
Unusual, Unknown, or
Unexpected Problems
PFA
Gathering of diagnostic information
Problem Determination, unknown
problems based on messages
IBM zAware
Known
Problems or
characteristics
Remediation&
Automation
Automation-Remediation
Tivoli®
NetView/OM
Detect Trends, known problems
HealthChecker
Understand problems in context of
other issues
Little advanced warning
Diagnostics at time
of problem
RTD
Tivoli SA
Take Automated action
Capture diagnostic information
These tools provide several functions. They collectively help companies run operations
effectively and achieve higher availability. No one product does it all.
79
© 2013 IBM Corporation
Problem Determination in 2 clicks instead of Hours
Click on yellow bars to drill down on that interval
Each ten minute reporting
interval (2 minutes sampling) is
represented by a bar. Height
and color coding signal
potential anomalies
JES Spool full. This would
have caused a severe
disruption. When spool is
full you can't logon, batch
stops, a Severity 1 condition.
80
© 2013 IBM Corporation
Identify Problems That You Did Not Even Know You Have
VTAM messages were unusual and
not issued after previous IPLs.
The VTAM team made changes and
failed to remove an obsolete definition
from VTAM's node list.
IBM zAware caught this
An incorrect definition would have
been assigned somewhere causing
other problems
Undetermined how long before the
problem would have been discovered
manually
81
© 2013 IBM Corporation
IBM zAware helps precisely identify anomalies. It can reduce
time to time to diagnose problems from hours to minutes
Without IBM zAware
With IBM zAware
Problem
Problem
Decide
what to do
Business
Impact
Little
advanced
warning
Attempts to
Correct
Problem
are often
incorrect
shutdown
restart
Ineffective time spent in problem
determination and trial and error.
Reduce
Business
Impact
Achieve
Application
Steady State
More Precise
and Targeted
Corrective Action
Detect
early
shutdown
Time
82
Shorten
decision
time
Application
Steady State
restart
Time
More precise and early diagnosis can
shorten impact time and help you to
avoid a similar problem.
© 2013 IBM Corporation
Roles of Problem Determination Tools
Stage
Solutions Available:
Prevention
z/OS Health
Checker
•
•
•
•
Checks configurations
Programmatic, applies to IBM & ISV tools
Can escalate notifications
Part of z/OS
z/OS
Runtime
Diagnostics
• Real time diagnostics of specific z/OS
system issues
• Specific set of diagnostics
• Part of z/OS
Early Warning
of known
problems
z/OS PFA
• Trending analysis of z/OS system
resources
• Can invoke z/OS Runtime Diagnostics
• 6 types of analysis
• Part of z/OS
Post process
notification of
high alerts and
recommended
maintenance
Proactive
Log Analysis
(PLA)
• Tool filters for high alert areas / abends
• APAR/PTF recommendations offered
based on analysis
• If no fix exists, recommend opening of
RETAIN PMR or suggest gather more
data
• Services offering by GTS Germany
Detection and
identification
of unusual or
unknown
problems
IBM zAware
• Pattern-based message analysis
• Aid in diagnosing complex z/OS
problems including cross-sysplex
problems
• Resides in own partition
Diagnosis/
Capture
83
Rulesbased
Analytic /
Statistical
model
Examines
message
traffic
Self
Learning
Method
Screen for
conditions

Diagnostics
right after an
incident
Specific
IBM-defined
messages
back 1 hour


By count of
arrivals /
CPU

Filtering for
known
problems and
expert review
by SMEs
Examines
LOGREC
weekly or bimonthly


By message
patterns,
unusual
messages,
burst of
specific
message
Early
detection and
alerting

Diagnosis
useful before
or after an
incident
© 2013 IBM Corporation
IBM zAware Operating Requirements
 IBM zAware Server Host runs on zEC12 or zBC12
 Server requirements
– Exclusive to zEC12 and zBC12 hosts, orderable as a feature code (FC #0011)
– Self contained firmware stack in it’s own LPAR. Runs on IFL or general CPs.
– HiperSockets or OSA ports needed; need a dedicated IP address
– New specifications offer granular planning guidance to customers on memory DASD
– New! Feature code can be removed, see zEC12 installation guide GC28-6913-00
– Packaged as a firmware appliance
 IBM zAware Monitored Clients
– IBM zAware monitored clients are ordered as Feature codes #0101*
– Monitored clients can be on any System z Server running z/OS 1.13 + PTFs.
– New! 3500 km distance allowed between host and monitored clients – good for D/R sites
 Data
–
–
–
–
Reads OPERLOG data -- any system messages sent to OPERLOG
Prime with 90 days recommended syslog or OPERLOG data.
Use Bulk Load utility to prime- no need to wait 90 days
You can exclude specific dates from analysis
 User Interface
– Web based, intuitive UI (Mozilla Firefox ESR10, Microsoft IE 9)
* No charge for D/R FC #0102
84
© 2013 IBM Corporation
IBM zAware and Tivoli Service Management - A powerful
Combination
Get the more from the zAware feature by integrating with Tivoli Service
Management. Tivoli will utilize the IBM zAware API to integrate log analysis
with existing service management capabilities.
 Provide visibility into IBM zAware anomalies via Event Management
 Improve mean time to failure (MTTR) through integration with existing problem
determination and performance monitoring tools
 Identify system errors and eliminate subsequent occurrences thru automation and more
sophisticated analysis
IBM zAware is NOT a replacement for traditional performance and
availability monitoring tools. It’s just the opposite. When used in
conjunction with existing service management tools, it can provide
a VERY powerful combination to help achieve 24/7 uptime, improve
MTTR when problems occur and help avoid subsequent problems.
85
© 2013 IBM Corporation
IBM zAware – Log Analytics with Anomaly Detection





IBM zAware available on zEC12 and zBC12
Requires z/OS operlog (‘simple’ implementation)
Focus – Log Analytics – Anomaly detection
Customer - z/OS Enterprise customers
Customer Value – Save money by ensuring z/OS availability (decrease time to
perform problem determination and lower MTTR)
 Leverages IBM zAware through existing Service Management solutions
(NetView/OMEGAMON integration and event visibility (OMNIbus))
Event
Management
OMNIbus
Problem
Determination
NetView
CANZLOG
Performance
Monitoring
OMEGAMON
(NEW! July 9,
2013)
IBM zAware
Surface
Anomalies
86
© 2013 IBM Corporation
IBM zAware, Automation, Event Management and PD Tools
Operator, SME
Logger
zLinux
zLinux
zLinux
z/OS
ICF
z/OS
z/OS
z/VM
PR/SM
z CPU,ZMemory
and
IO
CPU, Memory and
IO
zLinux
zLinux
zLinux
SE
z/OS
 NetView samples provided to generate anomaly message and event(s) – Samples
are available for download from Service Management Connect
 NetView integration referenced from IBM zAware Redbook
http://www.redbooks.ibm.com/abstracts/sg248070.html?Open
 IBM Services (optional) available to install and configure IBM zAware and NetView
Virtual Machine
 Query IBM zAware (10 minute interval)
 If anomaly detected:
– Generate ‘anomaly’ message
– Generate Event
 SME can browse NetView CANZLOG to
perform problem determination
ICF
z/OS
z/OS
Netview processing
Virtual Machine
NetView
EC12
Virtual Machine
zAware
IBM
z/OS
Browse NetView CANZLOG
Perform PD for anomaly
z/OS
View event in Active Event List
Generate trouble ticket
z/VM
PR/SM
z CPU,ZMemory
and
IO
CPU, Memory and
IO
SE
87
© 2013 IBM Corporation
IBM zAware, Event Management and Traditional
Performance Monitoring
Operator, SME
Perform PD for anomaly using association
with traditional monitoring KPIs
zLinux
zLinux
z/OS
ICF
z/OS
z/OS
Virtual Machine
z/VM®
PR/SM
z CPU,ZMemory
and
IO
CPU, Memory and
IO
zLinux
zLinux
zLinux
ICF
z/OS
z/OS
SE
Virtual Machine
Processing …
 Query IBM zAware (10 minute interval)
 If anomaly detected
– Trigger situation to Generate Event
when anomaly is surfaced
 Include IBM zAware insights in
performance monitoring views
IBM zAware
OMEGAMON
Performance
Monitoring
zLinux
EC12
Logger
z/OS
z/OS
z/OS
View event in Active Event List
Generate trouble ticket
z/VM
PR/SM™
z CPU,ZMemory
and
IO
CPU, Memory and
IO
88
SE
© 2013 IBM Corporation
Hybrid computing
 IBM DB2 Analytics Accelerator
 zBX
 zManager
89
© 2013 IBM Corporation
zEnterprise delivers optimized fit for purpose Cloud
infrastructures
Over
240
Hybrid* units shipped since
inception
Up to
84%
Lower TCA with fit for
purpose cloud architectures
IBM zBX and zManager:
No charge migration to Model 003
Workload policy based performance management for
AIX, Linux on System x and Microsoft® Windows®
Continuous operations across the ensemble
with alert and notification for blade virtual servers
Up to
35%
Lower infrastructure
management costs
90
Support for Layer 2 communications
between intranet and zBX
Support for Microsoft Windows Server 2012
DataPower Virtual appliance SoD for x86 blades**
Futures roadmap
* Includes zEnterprise BladeCenter Extension and IBM DB2 Analytics Accelerator
** All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
© 2013 IBM Corporation
Why mission critical business
analytics on zEnterprise?
Mission critical =
zEnterprise
DB2 Analytics
Accelerator for z/OS
 C Level executives
treat business analytics
as mission critical
 Complex business
analytics queries will
run extremely fast
 Bullet proof security,
reliability, disaster
recovery, and
availability at 99.999%
 Reduces need for
distributed data marts
 High scalability to
support mixed workload
analytics, high volume
of users and requests
 Storage savings by
keeping DB2 z/OS
historical data in the
accelerator only
Co-residency
of data
True hybrid
computing platform
 Production data (70%
originates on System z)
and data in the
warehouse both reside
on the same platform
 High volume transaction
processing, batch, short
duration and complex
analytics queries all
running concurrently on
the same hybrid
platform
 Data in the warehouse
is much more current
 Reduces costs and risk
– no need to manage
and copy production
data into distributed
data warehouses data
marts
 Excellent platform for
consolidation of costly
distributed data
warehouses, data marts
and business analytics
tools
zEnterprise: The most optimal platform for mixed workloads, large user population,
heavy concurrency and high volumes of requests
91
© 2013 IBM Corporation
IBM DB2 Analytics Accelerator V3.1 - Highlights
Building on the Core Values
Fast
Complex queries run
up to 2000x faster while
retaining single record
lookup speed
Cost Saving
Eliminate costly query
tuning while offloading
complex query
processing
Appliance
No applications to
change, just plug it in,
load the data, and gain
the value
Reducing the Cost of High Speed Analytics
 Choice of historical data location – High Performance Storage Saver
–Reduces host data warehouse storage usage by over 95%
–Significantly reduces cost of host storage resources and administration
 Real time analytics – Incremental Update
–Data changes are propagated for high-speed use as they occur
–Current information is available for right-time decisions
–Extends the accelerator use to reporting on operational data
 Faster data refresh – Unload Lite
– Data available for analytics faster
• Refresh of tables or partitions is much faster and more efficient
• More optimized version of unloading data from DB2
 New capacity – Full range of Netezza® models supported
– Now expandable to 960 cores and 1.28 petabytes
 New queries
– More queries eligible for acceleration
92
© 2013 IBM Corporation
zBX Overview
2458-003
Fibre Channel
Disk Storage
93
 Machine Type/Model 2458-003
 Racks – Up to 4 (B, C, D and E)
– 42U Enterprise, (36u height reduction option)
– 4 maximum, 2 chassis/rack
– 2-4 power line cords/rack
– Non-acoustic doors as standard
– Optional Acoustic Doors
– Optional Rear Door Heat Exchanger (conditioned water
required)
 Chassis – Up to 2 per rack
– 9U BladeCenter
– Redundant Power, cooling and management modules
– Network Modules
– I/O Modules
 Blades (Maximum 112 single width blades in 4 racks)
– Customer supplied POWER7 Blades (0 to 112)
– Customer supplied IBM System x Blades (0 to 56)
– DataPower XI50z, M/T 2462-4BX (0 to 28 – double width)
 Management Firmware
– Unified Resource Manager
 Top of Rack (TOR) Switches - 4
– 1000BASE-T intranode management network (INMN)
– 10 GbE intraensemble data network (IEDN)
– GbE IEDN for customer network
 Network and I/O Modules in the BladeCenter
– 1000BASE-T and 10 GbE modules
– 8 Gb Fibre Channel (FC) connected to customer supplied disks
© 2013 IBM Corporation
zBX offers Flexibility for Workload Deployment and Integration
 zBX is built with integrated IBM certified components
– Standard parts – TOR switch, BladeCenter Chassis, Power Distribution
Units, Optional Acoustic Panels
– Optional optimizer - IBM WebSphere DataPower Integration Appliance
XI50 for zEnterprise (DataPower XI50z) ordered as a feature of zBX
IBM zEnterprise
BladeCenter Extension (zBX)
Machine Type: 2458 Mod 003
(for attachment to zEC12 and zBC12)
 Up to 112 blades are supported on zBX
– System x and POWER7 blades are acquired through existing channels
– IBM System x Blades – up to 56
• IBM BladeCenter HX5 (7873) dual-socket 16-core blades, four
supported memory configurations for zBX – 64 GB, 128 GB, 192
GB, 256 GB
– IBM POWER7 Blades – up to 112
• IBM BladeCenter PS701 Express - 8-core processor 3.0GHz,
three configurations supported in zBX - 32 GB, 64 GB, 128 GB
– Up to 28 DataPower XI50z blades (double wide)
– Ability to mix and match blades in the same chassis and number of
blades supported varies by type
 System z support – Blades assume System z warranty and
maintenance when installed in the zBX
 Investment protection
– Upgrade the Model 002 to Model 003
 Top Exit I/O and Power Cabling
94
© 2013 IBM Corporation
Operating System Environments extend application flexibility
 Operating Systems are customer acquired and installed
 Unified Resource Manager will install hypervisor on blades in
the zBX
– Integrated hypervisor (KVM-based) for System x blades
– PowerVM™ Enterprise Edition for POWER7 blades
zBX
Machine Type: 2458, Model: 003
 Support for Linux and Windows environments on System x
blades in zBX
– 64-bit version support only
– Linux: Red Hat RHEL 5.5 and up, 6.0 and up & SUSE Linux Enterprise
Server (SLES) 10 (SP4) and up and SLES 11 SP1 and up
– Microsoft Windows Server 2012, Microsoft Windows Server 2008 R2 and
Microsoft Windows Server 2008 (SP2) (Datacenter Edition recommended)
 Support of AIX environments on POWER7 blades in zBX
– AIX: AIX 5.3 Technology Level 12 or higher, AIX 6.1 Technology Level 5 or
higher, AIX 7.1
 Certifications inherited from blades
– SAP support for Linux and Windows on x86 blades in the zBX
 PowerHA™ SystemMirror Standard Edition for AIX supported for
the zBX with PS701 blades
 RMF XP – provides monitoring of workloads running across the
zEnterprise
– Gain a comprehensive end-to-end view of Enterprise performance data
– Resource Monitoring in IBM z/OSMF provides performance metrics from
connected Linux on System z, Linux on System x or AIX systems, along
with z/OS metrics
95
© 2013 IBM Corporation
System Director uses zManager APIs to improve zBX
management
 Ability to discover, inventory, and visualize
zBX resources under the Systems Director
umbrella
– AIX on POWER7 blades, and Microsoft Windows
and Linux on System x on HX5 blades
System Director
Standard Edition for System z
includes Director, Energy Management,
Virtual Image Management
96
Z CPU, Memory and IO
SE
SE
xHyp
xHyp
xHyp
xHyp
xHyp
POWER7
AIX
AIX
AIX AIX
AIX AIX
ICP AIX
AIX
AIX AIX
AIX AIX
AIX
AIX
ISS
ISS
DP
DataPower
DP XI50z
Cell
XI50z
DataPower
Cell
DWA
XI50z
DataPower
DWA
DataPower XI50z
PR/SM
x86
Linux
Linux
Linux
Linux
Linux
Linux
ICPLinux
Linux
Linux
Linux
Microsoft Windows
Linux
Linux
Linux on System x
Linux on System z
z/VM
Linux on System z
zOS
Virtual Machine
zOS
Virtual Machine
Virtual Machine
zOS
– Monitoring power usage and thresholds for
System z
– Managing power for System z – Power Savings
for zEC12 and for each zBX blade (Power only)
– Power capping for zEC12 and zBX blades (both
System x and Power)
z/VM MAP
 Energy Management of the zBX to lower
energy consumption and costs
HMC and zManager
– z/VM via z/VM MAP
– zBX via zManager
Linux on System z
 Image management provided for blades
with in a zBX to support provisioning of
new virtual servers
pHyp
pHyp
pHyp
pHyp
PowerVM
AMM
AMM
AMM
z Blade Extension
z Blade Extension
zEnterprise BladeCenter Extension (zBX)
© 2013 IBM Corporation
IBM POWER7 and System x Blades
General purpose processors under one management umbrella
How is it different?
What is it?
The zBX infrastructure can host select IBM
POWER7 and IBM System x blades. Each blade
comes with an installed hypervisor that offers the
possibility of running an application that spans
z/OS, Linux on System z, AIX on POWER®, Linux
or Microsoft Windows on System x but have it
under a single management umbrella.
 Complete management: Advanced management
brings operational control and cost benefits,
improved security, workload management based on
goals and policies.
 Virtualized and Optimized: Virtualization means
fewer resources are required to meet peak demands
with optimized interconnection. Multiple resources
(both blade types and optimizers) can reside in a
single zBX.
 Integrated: Integration with System z brings
heterogeneous resources together that can be
managed as one.
 Transparency: Applications certified to run on AIX
5.3, 6.1 or 7.1 on POWER7 blades and those
certified to run on supported releases of Linux on
System x or Windows on the System x blades will
run on those blades in a zBX. No changes to
deployed guest images.
 More applications: Brings larger application
portfolio to System z.
IBM BladeCenter PS701
97
IBM BladeCenter HX5 (7873)
© 2013 IBM Corporation
WebSphere DataPower Appliances are easy-to-deploy,
configurable, highly secure network devices
Purpose built hardware as part of hybrid computing
What are they?
These purpose-built appliances simplify, help
secure, accelerate and govern your XML, Web
services and messaging deployments, and extend
your SOA infrastructure in a heterogeneous
environments.
How is it different within the zBX?
 Security: Enforced isolation of network traffic with
secure private networks.
 Improved support: Monitoring of hardware with
“call home” for current/expected problems and
support by System z Service Support
Representative.
 System z packaging: Increased quality with pretesting of blade and zBX. Upgrade history
available to ease growth.
 Operational controls: Monitoring rolled into
System z environment from single console.
Consistent change management with Unified
Resource Manager.
 Centralized: Datacenter consolidation reduces
overall IT footprint and energy costs
98
© 2013 IBM Corporation
IBM WebSphere DataPower Integration Appliance XI50 for
zEnterprise Helps Extend the Value of zEnterprise
The DataPower XI50z can help simplify, govern, secure and integrate XML and IT
services by providing connectivity, gateway functions, data transformation, protocol
bridging, and intelligent load distribution.
 Decreased Operational Costs with multi-purpose integration capability
 Minimize expense of new applications – using DataPower to extend and modernize
legacy systems
 Reduce future expenses by redeploying
or reducing hardware requirements
 Reduce overall software maintenance costs
 Reduce IT costs by removing redundant
software and hardware products
 A Proven, “Hardened” and “Secured” Policy
Enforcement Point
DataPower
XI50z
 Reduce operational expenses by improving utilization of all computing resources
across one or more sites
99
© 2013 IBM Corporation
Management Stack
Building an architectural construct of hardware, software, services
Service
Management
Platform
Management
Hardware
Management
100









Visibility, Control and Automation for Applications, Transactions, Databases and Data Center Resources
End-to End Workload Management and Service Level Objectives aligning IT Mgmt with Business Goals
Common Usage and Accounting for business accounting
Dynamic/Centralized Management of Application Workloads based on Policies
Business Resilience for multi-site recovery
End-to-end Enterprise Security Multi-site Storage management and disaster recovery
High availability and disaster recovery for the cloud
Cloud provisioning and management
Asset and Change Management for physical and virtual resources
 Workload based Resource Allocation and
Extending with
Provisioning for zEnterprise
Unified Resource Manager
 Physical and Virtual Resource
Management (Server, Storage, Network)  Hypervisor management and creation of virtual
 Goal Oriented Resource Management of
networks
zEnterprise (Availability, Performance,
 Operational controls, service and support for
Energy, Security)
hardware / firmware
 Ensemble Network and Storage
Management
 Configuration management for
hardware / firmware
 Operational controls for the
hardware / firmware
 Service and Support for the
hardware / firmware
 Lifecycle management for the
platform’s virtual resources
 Network management of private and secure data
and support networks
 Energy monitoring and management
 Resource workload awareness and platform
performance management
 Virtualization management – single view of
virtualization across the platform
 Programmatic access to functions via APIs
© 2013 IBM Corporation
Unified Resource Manager (zManager) design points
Manage your mainframe and distributed environment as one
 Incorporate “hardware management / platform management” capabilities into robust
firmware to control each attached hardware component – mainframe to blade
–
–
–
–
Hypervisors managed as firmware
Network managed by firmware – improved access control
Single management point of control – the HMC - reduced complexity of day-to-day operations
Simplified installation - auto discovery and configuration of resources inserted into the zBX
 Deliver workload awareness to optimize the system resources in accordance with
understanding the policies assigned to that particular workload.
 System z service and support management for the server (zEC12, zBC12, z196 or z114)
AND the virtual machines and blades
–
Monitoring of heterogeneous architectures for problems, logging and analyzing of events, initiating
recovery procedures, call home and notifying the user – all with time stamps to maintain data and
transaction integrity
 zManager offers virtual server provisioning and management for Linux guests running
on z/VM
–
Simplified skill level needed to manage a Linux on z/VM environment
Manage your mainframe and distributed with the same
tools, same techniques, same practices
101
© 2013 IBM Corporation
zEnterprise Unified Resource Manager
Transforming the way resources are managed and deployed
What is it?
Unified Resource Manager provides
infrastructure awareness to optimize the
system resources in accordance with
understanding the policies assigned to
that particular workload.
Functions are grouped into suites of
tiered functionality that enable different
levels of capability – Manage, Advanced
Management and Automate.
How is it different?
 Heterogeneous management: Total systems management
across heterogeneous resources. APIs facilitate enterprise
wide management.
 Integration: Single point of control, common skills for
resources, reduced complexity of day to day operations..
 Monitoring. New dashboard for CPU resources and energy
management.
 Simplified installation: Auto discovery and configuration of
resources and workloads with single interface
 Secure: Improved network security with lower latency, less
hops and less complexity. Improved control of access due to
management of hypervisors as firmware.
 Service and support management: Virtual machines and
blades able to perform hardware problem detection, reporting
and call home
102
© 2013 IBM Corporation
Unified Resource Manager
Manage Firmware Suite
 Manage (DataPower XI50z, select POWER7 and System x blades)
– Monitor and trend reporting of CPU energy efficiency.
– New dashboard interface enabling a broader view of system resource consumption.
– Integrated hardware / asset management across all elements of the system.
– Private and physically isolated connections for secure support and data sharing.
– Management of network resources to assist with problem determination.
– Administrative simplification (wizard) for virtual server provisioning and enablement of
integrated storage and network across hypervisors.
– Sharing of resource information and metrics via APIs.
– Dynamic add of storage resources
103
© 2013 IBM Corporation
Unified Resource Manager – zBX Model 003
Automate Firmware Suite
 Automate (Select POWER7 blades and Select System x blades)
‒ Additional wizard function to set up resources associated with a workload and the
capability to associate those resources with a named business process.
‒ Ability to manage to a user defined performance service level policy and enable
performance monitoring, reporting and resource optimization.
‒ Load balancing to ensure that network traffic flows correctly.
‒ Availability Monitoring and reporting of virtual servers to satisfy a defined workload
policy
 Automate (Select POWER7 blades, Select System x blades and
DataPower XI50z)
‒ Energy management capabilities.
 Automate (Select POWER7 blades only)
‒ Static power savings.
104
© 2013 IBM Corporation
Tivoli’s Integrated Service Management Portfolio
Unifying layer for enterprise-wide integration
Service
Management

Tivoli Performance Monitoring – OMEGAMON, ITM, ITCAM
– End-to End Application Performance Monitoring
– zEnterprise Hybrid Application Management

Tivoli Financial & Asset Management, Usage & Accounting, Asset Discovery
– Common usage and accounting for business accounting
– Asset and Change Management for physical and virtual resources
VISIBILITY

Enterprise Security Portfolio – TAM, Tivoli Security Policy Manager, zSecure
– End-to-End Enterprise Security support, including RACF®

Tivoli Storage: TSM, TPC, Tivoli Advanced Storage portfolio
– Multi-site Storage management and disaster recovery

Smart Cloud Family – Provisioning, Orchestration, Monitoring
– Resource provisioning and management for Cloud on System z
CONTROL

Tivoli System Automation: NetView ®SA for z/OS, SA for Multiplatform and
Application Manager
– High availability, GDPS® and disaster recovery

AUTOMATION
Tivoli Workload Automation and Business Service Management – TWS, TBSM,
Netcool®/Omnibus
– Policy based dynamic/centralized management of Application Workloads
– End-to End Workload Automation and Service Level Objectives
105
© 2013 IBM Corporation
zEnterprise Unified Resource Manager – zBX Model 003
Hardware Management
Energy Management
Hypervisor Management
g Monitoring and trend reporting of CPU
g Integrated deployment and
energy efficiency
configuration of hypervisor
g Hypervisors (except z/VM) shipped and
serviced as firmware
g Management of ISO images
g Creation of virtual networks
Operational Controls
Auto-discovery and configuration
support for new resources (including
storage)
g Cross platform hardware problem
detection, reporting and call home
g Physical hardware configuration,
backup and restore
g Delivery of system activity using new
user interface
g Dynamic add of storage for POWER7
blades
g
HMC
Network Management
g Monitoring and collecting metrics of networking resources
g Management of virtual networks including access control
106
Key
g Manage suite
p Automate suite
© 2013 IBM Corporation
zEnterprise Unified Resource Manager – zBX Model 003
Platform Management
Energy Management
Hypervisor Management
p Static power savings
g Manage and control communication
p Ability to query maximum potential power
between virtual server operating
systems and the hypervisor
Resource Workload Awareness
and Platform Performance
Resource Workload
Awareness Availability
Monitoring and Reporting
g HMC provides a single consolidated and
consistent view of resources
p Wizard-driven set up of resources in
p Monitor and report availability
accordance with specified business
process
p Ability to monitor and report performance
p Load balance recommendations
p Manage to a performance policy
based on policy
p Provide availability status for
virtual servers associated with
a workload
HMC
Virtual Server Lifecycle Management
Key
g Manage suite
p Automate suite
107
g Single view of virtualization across platforms.
g Ability to deploy multiple, cross-platform virtual
servers within minutes
g Management of virtual networks including
access control
g Integration of HiperSockets network with IEDN
© 2013 IBM Corporation
zEnterprise Unified Resource Manager – zBX Model 003
Platform Management
Hypervisor Management
Manage and control communication between virtual
server operating systems and the hypervisor
g Integrated deployment and configuration of hypervisor
g Hypervisors (except z/VM) shipped and serviced as
firmware
g Management of ISO images
g Creation of virtual networks
g
Resource Workload
Awareness Availability
Monitoring and Reporting
p Monitor and report availability based
on policy
p Provide availability status for virtual
servers associated with a workload
Operational Controls
Auto-discovery and configuration support for new
resources (including storage)
g Cross platform hardware problem detection,
reporting and call home
HMC
g Physical hardware configuration, backup and restore
g Delivery of system activity using new user interface
g Dynamic add of storage for POWER7 blades
g
Network Management
g Monitoring and collecting metrics of networking resources
g Management of virtual networks including access control Key
g Manage suite
p Automate suite
108
Energy Management
p Monitoring and trend reporting of CPU
energy efficiency
p Static power savings
p Ability to query maximum potential power
Resource Workload Awareness
and Platform Performance
g HMC provides a single consolidated and
consistent view of resources
p Wizard-driven set up of resources in
accordance with specified business
process
p Ability to monitor and report performance
p Load balance recommendations
p Manage to a performance policy
Virtual Server Lifecycle Management
g Single view of virtualization across platforms.
g Ability to deploy multiple, cross-platform virtual
servers within minutes
g Management of virtual networks including
access control
g Integration of HiperSockets network with IEDN
© 2013 IBM Corporation
zEnterprise Unified Resource Manager
Management of zEnterprise from external tools
zManager Application
Programming Interface (API) is a
new implementation in the HMC
 Enabled via the Web Services
API on the HMC
 Network support available with
SSL for connection security
 Supports modern scripting
languages (e.g., Perl, Python)
that have HTTP supporting
libraries
 Fully documented and
supported for customer and
third-party use
 HMC UI remains in place,
supported and will continue to
be extended as Unified
Resource Manager evolves
 APIs are governed by the
functions they involve such as
‘Manage’ or ‘Automate’
109
API allows programmatic
access to the same functions
exploited by the HMC User
Interface (UI) – such as:
 List and get properties for core
(traditional) entities, ensemble,
workloads, virtual networks,
virtual hosts, virtual servers,
storage, zBX infrastructure (as
well as provide
start/stop/restart for many of
these also)
HMC
 Can provide service oriented
functions like metrics retrieval
and inventory
 Manage energy management
modes
 Help on recover actions of
virtual actions
 Access monitoring information
for mobile apps
 And more …
© 2013 IBM Corporation
zEnterprise Unified Resource Manager pricing strategy
Priced to value: Tiered functionality that scales
 Manage and Automate are ordered as features of the zBC12
– When placing an order for a zBC12, the default is ‘Manage’ FC#0019. If you want “Automate” you will
need to order FC#0020. The additional feature codes for these functions for the blades/optimizers will
automatically be generated for you based on the number of blades/optimizers that you order. To get
ensemble management and cables make sure that you also order FC#0025 on the zBC12.
Manage
Delivers Unified Resource Manager’s function for core operational controls,
installation and configuration, and energy monitoring.
Automate
Delivers workload definition and performance policy monitoring and reporting.
Delivers goal oriented monitoring and goal oriented management of resources and
energy management.
Manage –
per connection
Automate –
per connection
FC#0019 - N/C
FC#0020 - N/C
N/C
FC#0060 – Yes
POWER7 Blade
(zBX FC#0612)
FC#0065 – Yes
FC#0068 – Yes
DataPower Blade
(zBX FC#0611)
FC#0064 – Yes
FC#0067 – N/C
System x Blade
(zBX FC#0613)
FC#0066 – Yes
FC#0069 – Yes
zBC12 base hardware
configuration
IFL
110
© 2013 IBM Corporation
zEnterprise Unified Resource Manager pricing strategy
Priced to value: Tiered functionality that scales
 Manage, Advanced Management and Automate are ordered as features of the zEC12
– When placing an order for a zEC12, the default is ‘Manage’ FC#0019. If you want “Advanced Management /
Automate’ you will need to order FC#0020. The additional feature codes for these functions for the blades/optimizers
will automatically be generated for you based on the number of blades/optimizers that you order. To get ensemble
management and cables make sure that you also order FC#0025 on the zEC12.
Delivers Unified Resource Manager’s function for core operational controls, installation and
configuration, and energy monitoring
Advanced Management
Delivers workload definition and performance policy monitoring and reporting. Load
balancing capabilities
Automate **
Delivers workload definition and performance policy monitoring and reporting. Delivers goal
oriented monitoring and goal oriented management of resources and energy management.
Load balancing capabilities.
Manage –
per connection
Advanced Management –
per connection
Automate –
per connection **
FC#0019 - N/C
N/A
FC#0020 - N/C
N/C
N/A
FC#0054 – Yes
POWER7 Blade (zBX FC#0612)
FC#0048 – Yes
N/A
FC#0051 – Yes
DataPower Blade (zBX FC#0611)
FC#0047 – Yes
N/A
FC#0050 – N/C
System x Blade (zBX FC#0613)
FC#0049 – Yes
FC#0053 – Yes
Available on driver level 12
(September 2012) only
FC#0071 – Yes
Available on driver level 15
(September 2013) only
z196 or z114 base hardware configuration
IFL
** System x blades on earlier zEC12 servers will not have full Automate capabilities until they are upgraded to driver level 15. Prior to that level
they can only have Advanced Management functions including: automate capabilities for System x blades Wizard-driven set up of resources in
accordance with specified business process; ability to monitor and report performance ; Load balance recommendations
111
© 2013 IBM Corporation
Putting zEnterprise System to the Task
z/TPF Linux on Linux
on
System z
z/VSE®
System z
z/VM
Linux on
System x
Windows
on
System x
Blade
Virtualization
Blade
Virtualization
AIX on
POWER7
Optimizers
DataPower XI50z
z/OS®
Select IBM Blades
DataPower XI50z
System z Host
with Unified Resource Manager
System z Hardware Management Console (HMC)
Use the smarter solution to improve your application design
Blade
Virtualization
System z PR/SM™
z HW Resources
Blade HW Resources
Support Element
zBX
Private data network (IEDN)
Unified Resource
Manager
Customer Network
112
Private Management Network INMN
Private Management Network (information only)
Customer Network
Private High Speed Data Network IEDN
© 2013 IBM Corporation
IBM RD&T
113
© 2013 IBM Corporation
Rational Development and Test Environment for IBM System z v9
Reduce System z development costs with high fidelity off host development and test
 Exploit added zEnterprise capability for
increased mainframe compatibility
– New Parallel Sysplex support via the latest
System z coupling facility
Rational Development
and Test Environment for System z
RDz
– New zEnterprise EC12 platform support
– Better development and test coverage early
in the cycle for higher quality applications
delivered more quickly
 Improve hardware utilization and simplify
management
– New support for virtualization technologies,
including VMWare vSphere and IBM
zEnterprise BladeCenter Extension
 New, flexible licensing to support
automated testing and variable usage
patterns
RDz & ISPF
Open Lifecycle Integration and Services
Management Platform
It takes days for the mainframe staff to do a change request for CICS. If we are
doing something new, it may take many change requests and several weeks. With
RD&T, the developers can try the changes themselves in real-time until they get it
right. Then a change request can be submitted with correct configuration
parameters. This saved weeks.
Development Team Lead
Note: This Program is licensed only for development and test of applications that run on IBM z/OS. The Program may not be used to run production workloads of any kind, nor more
robust development workloads including without limitation production module builds, pre-production testing, stress testing, or performance testing.
114
© 2013 IBM Corporation
zEnterprise BladeCenter Extension (zBX) Support
 Provision RD&T onto HX5 blades integrated into zBX Model 3 using the IBM
zEnterprise Unified Resource Manager
 Benefits:
– Extend existing zEnterprise System management capabilities, automated provisioning,
and skills to handle your off host System z development and test environments
– Efficient System z data access via TCP/IP for mainframe application development and
testing activities using intraensemble data network (IEDN) connectivity
IBM zEnterprise Unified
Resource Manager
COBOL, PL/I, C++, Java, EGL, Batch,
Assembler, Debug Tool
IMS
DB2
CICS
WAS
RDz user
MQ
RDz user
z/OS
HX5 Blade
RDz user
ISPF user
RDz & ISPF user
115
© 2013 IBM Corporation
IBM Storage
116
© 2013 IBM Corporation
System z and Storage Synergy
Designing, developing, and testing together
is key to unlocking true value
Synergy with System z
Large
enterprise
Midrange
offerings
New IBM System
Storage® DS8870
 Integrated QoS management aligns server and storage resources with
application priorities
 Self optimizing performance and cost for hybrid computing
 Designed for near continuous availability
 Consolidated backup of mainframe and open
 3x Performance Boost for real-time and operational analytics
 zHPF and Extended
Address Volumes
 GDPS/PPRC HyperSwap
 zDAC on z/OS for easy
configuration
 Entry Level BC version


XIV® Storage
Systems
 Revolutionary high-end disk system designed for high availability, management
simplicity and low TCO
 Popular with z/VSE, z/VM
and Linux on System z


Storwize® V7000
 Midrange disk and virtualization
 External disk virtualization helps improve storage utilization
 Helps improve application availability
 Perfect for z/VSE, z/VM
and Linux on System z




• Attaches via SVC for
extreme performance of
up to 1.5M IOPs
SVC
IBM FlashSystem
820
(via SVC)
Extreme Performance with IBM MicroLatency
All Flash 20 TB RAIDed data capacity
Macro Efficiency 1U form factor
Variable Strip RAID and 2-D RAID for Enterprise Reliability



(Linux)
(Linux)


TS1140
 High perform (250 MBps) and high native capacity (4TB) for storage
consolidation
 Provides information security with support for encryption and key management
 Supports Write Once Read Many cartridges to help satisfy compliance
requirements
TS3500
 Scalable, automated data retention with up to 2.7 EB capacity with 3:1
compression
 Offers enhanced data availability and reliability with optional dual library
accessory
 Provides data security and regulatory compliance via support for tape drive
encryption and WORM cartridges
 Attaches to multiple
heterogeneous systems
 Supports for all System z
(via 3953)


TS7700
Virtualization
Engine
 Virtualization solution implements a fully integrated tiered storage hierarchy of
disk and tape
 Reduces batch processing time, total cost of ownership and management
overhead
 Disk-only models with up to 1.3 PB native tape volume cache
 Grid configurations for information availability and business continuity
 z/OS, z/VM and z/VSE
support


117
 Support for z/OS, Linux on
System z, z/VM, and
z/VSE
© 2013 IBM Corporation
DS8870 Business Class configuration
Entry-level storage for entry-level zBC12
 Single-frame model
– 2-core controller processors
– 16GB processor memory
• Supports up to 32GB
– 2.3TB raw disk capacity (single drawer of 146GB FDE 15k
drives)
• Supports up to 144 drives (intermix of SSD, Enterprise,
Nearline)
– Supports intermix of CKD and Open formatted data
– Includes Easy Tier™ and Full Disk Encryption drives
– Single or Three phase power options available
– Order with 2-core processor memory (Feature Code 4401)
Drive
enclosures
Management
Console
POWER 7
Controllers
 Concurrent upgrades available
– Advanced functions available after upgrading to 32GB or
Power
more of cache (e.g., copy services, I/O Priority
Supplies
Manager, PAV, Hyper PAV, zHPF, etc.)
(DC UPS)
– Upgradable to full DS8870 Enterprise Class
configurations
I/O drawers
Front view
(cover removed)
Optimized storage for System z at an entry-level price
118
© 2013 IBM Corporation
Advanced Function Meets Extreme Performance
SVC is designed to pool storage volumes into a reservoir of
capacity for centralized management. SVC helps to hide the
boundaries among disk systems, which simplify management and
enables customers to focus on managing storage as a resource to
meet business requirements and not as a set of boxes.
IBM FlashSystem™ delivers extreme performance driven by IBM
MicroLatency™ for quick response time and is a durable, high
reliability enterprise class family of flash storage systems that are easy
to integrate. FlashSystem leverages IBM patented Variable Stripe
RAID™ technology to maintain performance, protect data integrity as
well as usable storage capacity.
119
© 2013 IBM Corporation