IBM Z 890 User Manual

Download

IBM ^ zSeries 890 and z/OS Reference Guide

January 2005

Table of Contents

z/Architecture page 5

IBM ~ zSeries 990 page 6

z890 Family Models page 10

z890 and z900 Performance Comparison page 13

z890 I/O SubSystem page 14

z890 Channels and I/O Connectivity page 16

Fibre Channel Connectivity page 18

A New Generation for SANs – FICON Express2 page 22

A New Generation of zSeries LAN Adapters

Open Systems Adapter-Express2 page 24

Open Systems Adapter-Express Features

(OSA-Express) page 27

HiperSockets page 31

Cryptography page 33

Availability page 38

Advanced Availability Functions page 40

Parallel Sysplex Cluster Technology page 41

z890 Support for Linux page 53

zSeries 890 Family Conﬁ guration Detail page 58

Physical Characteristics page 60

Coupling Facility - CF Level of Support page 60

z/OS page 62

z/VM page 83

VSE/ESA page 92

To Learn More page 93

zSeries Overview

Technology has always accelerated the pace of change.

New technologies enable new ways of doing business,

shifting markets, changing customer expectations, redeﬁ n-

ing business models. Each major enhancement to technol-

ogy presents opportunities. Companies that understand

and prepare for changes can gain advantage over com-

petitors and lead their industries.

Customers of every size, in every industry are looking for

ways to make their businesses more resilient in the face of

change and uncertainty. They want the ability to react to

rapidly changing market conditions, manage risk, outpace

their competitors with new capabilities and deliver clear

returns on investments.

Welcome to the on demand era, the next phase of

e-business, in which companies move beyond simply

integrating their processes to actually being able to sense

and respond to ﬂ uctuating market conditions and provide

products and services to customers on demand. While

the former notion of on demand as an e-utility capability

is a key component, on demand companies have much

broader capabilities.

What does an on demand company look like?

• Responsive: It can sense and respond in real time to the changing needs of customers, employees, suppliers and partners

• Variable: It must be capable of employing variable cost structures to do business at high levels of productivity,

cost control, capital efﬁ ciency and ﬁ nancial predictability.

• Focused: It concentrates on its core competencies – areas where it has a differentiating advantage – and draws on the skills of strategic partners to manage needs outside of these competencies.

• Resilient: It can handle the ups and downs of the global market, and manage changes and threats with consistent availability, security and privacy – around the world, around the clock.

To support an on demand business, the IT infrastructure

must evolve to support it. At its heart the data center must

change to reﬂ ect these needs, the data center must be

responsive to changing demands, it must be variable to

support the diverse environment, it must be ﬂ exible so that

applications can run on the optimal resources at any point

in time, and it must be resilient to support an always open

for business environment.

The on demand era plays to the strengths of the IBM

zSeries®. The IBM ^ zSeries 900

(z900) was launched in 2000 and was the ﬁ rst IBM server

‘designed from the ground up for e-business.’ The latest

member of the family, the IBM ^ zSeries 890

(z890), brings enriched functions that are required for the

on demand data center to a larger audience.

The ‘responsive’ data center needs to have systems that

are managed to the quality of service goals of the business

they need systems that can be upgraded transparently

to the user and they must be adaptable to the changing

requirements of the business. With the zSeries you have a

server with high levels of reliability and a balanced design

to enable high levels of utilization and consistently high

service to the user. The capacity on demand features

continue to evolve, helping to ensure that upgrading the

servers is timely and meets the needs of your business. It’s

not just the capacity of the servers that can be changed

on demand, but the mix of workload and the allocation of

resources can be changed to reﬂ ect the evolving needs

and priorities of the business.

The variable data center needs to be able to respond to

the ever changing demands that occur when you sup-

port multiple diverse workloads as a single entity. It must

respond to maintain the quality of service required and the

cost of utilizing the resources must reﬂ ect the changing

environment. The zSeries Intelligent Resource director

(IRD), which combines three key zSeries technologies,

Workload Manager (WLM), Logical Partitioning

z/OS

and Parallel Sysplex

technology helps enable your most

important workloads to get the resources they need

and constantly manages the resources according to the

changing priorities of the business. With workload license

charging, as the resources required by different applica-

tions, middleware and operating systems change over

time, the software costs change to reﬂ ect this. In addition,

new virtual Linux

servers can be added in just minutes

with zSeries virtualization technology to respond rapidly to

huge increases in user activity.

The ﬂ exible data center must be adaptable to support

change and ease integration. This is achieved through

a combination of Open and industry standards along

with the adaptability to direct resources where they are

required. The zSeries along with other IBM servers have

been investing in standards for years. Key is the support

™

for Linux, but let’s not forget Java

and XML and industry

standard technologies, such as FCP, Ethernet and SCSI.

Finally the on demand data center must be designed to be

resilient. The zSeries has been renowned for reliability and

availability. The zSeries platform will help protect from both

scheduled and unscheduled outages, and GDPS

auto-

mates site reconﬁ guration for both planned and unplanned

outages.

The New zSeries from IBM

IBM’s ongoing investment in zSeries technology produced

a re-invention of the zSeries server — the z990 which was

developed at a cost in excess of $1 Billion. The new tech-

nology introduced a host of new beneﬁ ts to meet today’s

on demand business.

The z890 takes advantage of the new z990 technology in a

package that helps deliver excellent price/performance for

those customers requiring a lower capacity entry point and

more granularity of upgrades than offered with the z990

but still delivering the ability to add incremental capacity

as it is required in an on demand world.

And IBM’s investment in zSeries doesn’t stop here. To

solidify the commitment to zSeries, IBM introduced the

“Mainframe Charter” that provides a framework for future

investment and a statement of IBM’s dedication to deliver

ongoing value to zSeries customers in their transformation

to on demand business.

Tools for Managing e-business

The IBM ^ product line is backed by a compre-

hensive suite of offerings and resources that provide value

at every stage of IT implementation. These tools can help

customers test possible solutions, obtain ﬁ nancing, plan

and implement applications and middleware, manage

capacity and availability, improve performance and obtain

technical support across the entire infrastructure. The

result is an easier way to handle the complexities and

rapid growth of e-business. In addition, IBM Global Ser-

vices experts can help with business and IT consulting,

business transformation and total systems management

services, as well as customized e-business solutions.

z/Architecture

The zSeries is based on the z/Architecture™, which is

designed to reduce bottlenecks associated with the lack of

addressable memory and automatically directs resources

to priority work through Intelligent Resource Director (IRD).

The z/Architecture is a 64-bit superset of ESA/390.

z/Architecture is implemented on the z890 to allow full 64-

bit real and virtual storage support. A maximum 32 GB of

real storage is available on z890 servers. z890 can deﬁ ne

any LPAR as having 31-bit or 64-bit addressability.

z/Architecture has:

• 64-bit general registers.

• New 64-bit integer instructions. Most ESA/390 architecture instructions with 32-bit operands have new 64-bit and 32- to 64-bit analogs.

• 64-bit addressing is supported for both operands and instructions for both real addressing and virtual addressing.

• 64-bit address generation. z/Architecture provides 64-bit virtual addressing in an address space, and 64-bit real addressing.

• 64-bit control registers. z/Architecture control registers can specify regions, segments, or can force virtual addresses to be treated as real addresses.

• The preﬁ x area is expanded from 4K to 8K bytes.

New instructions provide quad-word storage consis-

•

tency.

• The 64-bit I/O architecture allows CCW indirect data addressing to designate data addresses above 2 GB for both format-0 and format-1 CCWs.

• IEEE Floating Point architecture adds twelve new instructions for 64-bit integer conversion.

• The 64-bit SIE architecture allows a z/Architecture server to support both ESA/390 (31-bit) and z/Architecture (64bit) guests. Zone Relocation is expanded to 64-bit for

LPAR and z/VM

• 64-bit operands and general registers are used for all Cryptographic instructions

• The implementation of 64-bit z/Architecture can help reduce problems associated with lack of addressable memory by making the addressing capability virtually unlimited (16 Exabytes).

z/Architecture Operating System Support

The z/Architecture is a tri-modal architecture capable of

executing in 24-bit, 31-bit, or 64-bit addressing modes.

Operating systems and middleware products have been

modiﬁ ed to exploit the new capabilities of the z/Architecture

Immediate beneﬁ t can be realized by the elimination of the

overhead of Central Storage to Expanded Storage page

movement and the relief provided for those constrained by

the 2 GB real storage limit of ESA/390. Application programs

can run unmodiﬁ ed on the zSeries family of servers.

Expanded Storage (ES) is still supported for operating sys-

tems running in ESA/390 mode (31-bit). For z/Architecture

mode (64-bit), ES is supported by z/VM. ES is not supported

by z/OS in z/Architecture mode.

Although z/OS and z/OS.e do not support Expanded Stor-

age when running under the new architecture, all of the

™

Hiperspace

and VIO APIs, as well as the Move Page

(MVPG) instruction, continue to operate in a compatible

manner. There is no need to change products that use

Hiperspaces.

Some of the exploiters of z/Architecture for z/OS include:

• DB2 Universal Database™ Server for z/OS

™

• IMS

• Virtual Storage Access Method (VSAM)

• Remote Dual Copy (XRC)

• Tape and DASD access method

IBM

zSeries 890

Operating System ESA/390 z/Arch Compati Exploita (31-bit) (64-bit) bility tion

OS/390® 2.10 (support ended) Yes Yes Yes3 No

z/OS 1.2 (support ended) No Yes Yes

z/OS and z/OS.e 1.3 No Yes Yes

z/OS and z/OS.e 1.4 No Yes Yes

z/OS and z/OS.e 1.5, 1.6 No Yes Included

Linux for S/390

Linux for zSeries No Yes Yes Yes

z/VM 3.1 Yes Yes Yes No

z/VM 4.3 Yes Yes Yes No

z/VM 4.4 Yes Yes Included Included

z/VM 5.1 No Yes Included Included

VSE/ESA

z/VSE* 3.1 Yes No Yes Yes

TPF 4.1 Yes No Yes No

z/TPF 1.1 No Yes Yes No

1 – TPF and zTPF use LCSS-0 only, but more than 15 LPARs are permitted. See APAR PJ29309 (included in z/TPF). 2 – VSE 2.7 exploits Thin Interrupts with 4Q04 SPE 3 – Web Deliverable for Secure Crypto

* – z/VSE can execute in 31-bit mode only. It does not implement z/Architecture, and speciﬁ cally does not implement 64-bit mode capabilities

Yes No Yes Yes

™

2.6, 2.7 Yes No Yes No

Yes

Included

IBM ^ zSeries is the enterprise class e-business

server optimized for integration, transactions and data

of the next generation e-business world. In implement-

ing the z/Architecture with new technology solutions, the

zSeries models are designed to facilitate the IT business

transformation and reduce the stress of business-to-busi-

ness and business-to-customer growth pressure. The

zSeries represents an advanced generation of servers

that feature enhanced performance, support for zSeries

Parallel Sysplex clustering, improved hardware man-

agement controls and innovative functions to address

e-business processing.

The z890 server, the latest addition to the zSeries family,

takes advantage of the design enhancements and new

technology of the z990 in a package that helps deliver

excellent price/performance for those customers requiring

a lower capacity entry point than that offered by the z990.

With a new superscalar microprocessor and the CMOS 9S-

SOI technology, the z890 is designed to further extend and

integrate key platform characteristics such as dynamic

ﬂ exible partitioning and resource management in mixed

and unpredictable workload environments, providing tra-

ditional zSeries Quality of Service to emerging e-business

applications such as WebSphere

, Java and Linux.

The IBM ^ zSeries Application Assist Processor

(zAAP), available on the IBM ^ zSeries 990 (z990)

and zSeries 890 (z890) servers, is an attractively priced

specialized processing unit that provides strategic z/OS

Java execution environment for customers who desire the

powerful integration advantages and traditional Qualities

of Service of the zSeries platform.

When conﬁ gured with general purpose Central

Processors (CPs) within logical partitions running z/OS,

zAAPs can help you to extend the value of your existing

zSeries investments and strategically integrate and run

e-business Java workloads on the same server as your

database, helping to simplify and reduce the infrastructure

required for Web applications while helping to lower your

overall total cost of ownership.

zAAPs are designed to operate asynchronously with the

general purpose CPs to execute Java programming under

control of the IBM Java Virtual Machine (JVM). This can

help reduce the demands and capacity requirements on

general purpose CPs which may then be available for real-

location to other zSeries workloads. The amount of general

purpose CP savings may vary based on the amount of

Java application code executed by zAAP(s). And best

of all, IBM JVM processing cycles can be executed on

the conﬁ gured zAAPs with no anticipated modiﬁ cations

to the Java application(s). Execution of the JVM process-

ing cycles on a zAAP is a function of the IBM Software

Developer’s Kit (SDK) for z/OS Java 2 Technology Edition,

z/OS 1.6 (or z/OS.e 1.6) and the innovative Processor

™

Resource/Systems Manager

(PR/SM™).

Notably, execution of the Java applications on zAAPs,

within the same z/OS SMP LPAR as their associated

database subsystems, can also help simplify the server

infrastructures and improve operational efﬁ ciencies. For

example, use of zAAPs to strategically integrate Java

Web applications with backend databases could reduce

the number of TCP/IP programming stacks, ﬁ rewalls, and

physical interconnections (and their associated process-

ing) that might otherwise be required when the application

servers and their database servers are deployed on sepa-

rate physical server platforms.

Essentially, zAAPs allow customers to purchase additional

processing power exclusively for z/OS Java application

execution without affecting the total MSU rating or machine

model designation. Conceptually, zAAPs are very similar to

a System Assist Processor (SAP); they cannot execute an

Initial Program Load and only assist the general purpose

CPs for the execution of Java programming. Moreover,

IBM does not impose software charges on zAAP capacity.

Additional IBM software charges will apply when additional

general purpose CP capacity is used.

Customers are encouraged to contact their speciﬁ c ISVs/

USVs directly to determine if their charges will be affected.

z890 has a single model, the A04, and will support a wide

performance range from sub uni models through to a 4-

way multiprocessor. There will be a total of 28 capacity

settings which will offer outstanding granularity for custom-

ers' workload and cost management. The A04 model will

provide up to four processor units (PUs) that can be char-

acterized as either Central Processors (CPs), Integrated

Facility for Linux (IFLs), Internal Coupling Facilities (ICFs)

or zAAPs. This model will be offered as a new build and as

upgrades from designated models of the z800.

With the introduction of the z890 customers can expect to

see the following performance improvements with z/OS 1.4:

Number of CPs Base Estimated Ratio

1 z800 2.0

2 z800 2.1

3 z800 2.1

4 z800 2.1

The Large System Performance Reference (LSPR) should

be referenced when considering performance on the z890.

Visit: ibm.com/servers/eserver/zseries/lspr/ for more infor-

mation on LSPR.

As with the z990, an improvement to the I/O subsystem

has been introduced on the z890 to “break the barrier”

of the 256 CHPIDs per Channel Subsystem. Horizontal

growth is provided by allowing the deﬁ nition of two Logical

Channel SubSystems (LCSSs) each capable of supporting

up to 256 CHPIDs, giving a total of 512 CHPIDs per z890

server. The z890 can support up to 30 Logical Partitions

(LPARs). There is still a 256 CHPID limit per operating

system. (Note: The lowest Capacity Setting 110 can sup-

port up to 240 CHPIDs, dependent on channel type, and

up to a maximum of 15 LPARs.)

These are some of the signiﬁ cant enhancements in the

zSeries 890 server that bring improved performance, avail-

ability and function to the platform. The following sections

highlight the functions and features of the server.

z890 Design and Technology

The z890 is designed to provide balanced system perfor-

mance. From server to the storage to the system’s I/O and

network channels, end-to-end bandwidth is provided and

designed to deliver data where and when it is needed. The

z890 is a scaled down version of the z990 using one of

the most advanced chip and packaging technology in the

industry. The z890 has more technology similarities to the

z990 than the z800 does to the z900. Both the z890 and

z990 use the latest MCM packaging and book package.

The z890 compared to the z800 provides a signiﬁ cant

increase in system scalability and opportunity for server

consolidation by providing improved model granularity

while scaling to 2X the performance of the z800. The

z890’s processor cycle time has been improved to 1.0 ns

from the 1.6 ns of the z800. All z890’s have a single Mul-

tiChip Module (MCM) that is nearly identical to the z990’s

MultiChip module. The differences are minor. With fewer

functional processors and a slower cycle time less power

is required for the z890 MCM enabling air cooling. The

air cooled z890 MCM uses approximately 450 Watts

compared to the liquid cooled z990 MCM which requires

approximately 650 Watts. The z890 MCM can deliver 1 to

4-way conﬁ gurations with a variety of engine sizes. The

z890 MCM, which measures approximately 95 x 95 mil-

limeters, is about 42% smaller than the z900’s 127 mm

x 127 mm MCM. The z890 MCM contains 5 Processor

Unit (PU) chips, four Storage Data (Level 2 cache) chips,

a Level 2 Cache Storage Controller chip and two main

Memory Storage Controller (MSC) chips which control the

main memory or Level 3 storage. The MCM contains 101

glass ceramic layers of which 23 layers are to provide

interconnection between the chips and the off-module

environment. In total, there are approximately 378 meters

of internal copper wiring on both the z890 and z990 MCMs

compared to the 997 meters of internal wiring needed

for the MCMs in the z900 190 and 290 models. The new

smaller MCM packaging delivers an MCM with many

shorter paths. The z890 MCM is 40% smaller than the

z900 MCM. It has over 20% more I/O connections and

over a 130% I/O density improvement compared to the

z900 MCM.

The z890’s MCM provides support for 5 PUs and 32 MB

level 2 cache which can be shared by all PUs. Each PU

chip contains approximately 122 million transistors and

measures 14.1 mm x 18.9 mm. The design of the MCM

technology on the z890 provides the ﬂ exibility to conﬁ g-

ure the PUs for different uses. One of the PUs is reserved

for use as dedicated I/O Processor (IOP), commonly

referred to as a System Assist Processor (SAP) enabling

the Central Processor to avoid the burden of I/O set

ups and operations. Any unused PUs can be utilized as

spares. The inactive PUs on the MCM are available to be

characterized as either Central Processors (CPs), Internal

Coupling Facility (ICF) processors for Coupling Facility

applications, Integrated Facility Linux (IFL) for Linux appli-

cations, or as IBM ^ zSeries Application Assist

Processor (zAAP) engines, providing enterprises with tre-

mendous ﬂ exibility in conﬁ guring the best system for run-

ning applications. Each model of the z890 must always be

ordered with at least one CP, IFL or ICF.

The PU, which uses the latest chip technology from IBM

semiconductor laboratories, is built on CMOS 9S-SOI with

copper interconnections. The 14.1 mm x 18.9 mm chip

has a cycle time of 1.0 nanoseconds and is identical to the

z990 PU except for the cycle time. Implemented on this

chip are leading edge functions as the z/Architecture with

its 64-bit capabilities including instructions, 64-bit General

Purpose Registers, SuperScalar function, translation facili-

ties, ability to use long displacement operations and on

board Cryptographic Assist functions.

The z890 is a single book design. The book can support

up to 32 GB of memory on a single memory card and 8

Self-Timed Interconnects (STIs) for I/O Connectivity. The

memory which can be purchased in 8 GB increments, is

delivered on 8 GB, 16 GB or 32 GB cards. The minimum

memory is 8 GB. The book has a 2 Memory Bus Adapters

(MBAs) and each MBA supports 4 STIs.

(CUoD), Customer Initiated Upgrades (CIU), and the ability

to add CPs, ICFs, IFLs and zAAPs dynamically provid-

ing nondisruptive upgrade of processing capability. Also,

the ability to add CPs lets a z890 with spare PU capacity

become a backup for other systems in the enterprise;

expanding the z890 system to meet an emergency outage

situation. This is called Capacity BackUp (CBU).

The I/O SubSystem has been enhanced to support two

Logical Channel SubSystems (LCSSs) which provide the

capability to deﬁ ne up to 512 CHPIDs (256 CHPIDs per

operating system image). I/O improvements in the Parallel

Sysplex Coupling Link architecture and technology sup-

port faster and more efﬁ cient transmission between the

™

Coupling Facility and production systems. HiperSockets

provides high-speed capability to communicate among

virtual servers and Logical Partitions; this is based on

high-speed TCP/IP memory speed transfers and provides

value in allowing applications running in one partition to

communicate with applications running in another without

dependency on an external network. Industry standard

and openness are design objectives for I/O in z890. The

improved I/O subsystem is delivering new horizons in I/O

capability and has eliminated the 256 limit to I/O attach-

ments for a mainframe.

The z890 supports LPAR mode only (basic mode is no

longer supported).

The MultiChip Module (MCM) is the technology corner-

stone for ﬂ exible PU deployment in the z890 models. For

most models, the ability of the MCM to have inactive PUs

allows such features as Capacity Upgrade on Demand

z890 Family Models

The z890 offers a single model, the A04 and supports a

wide performance range from sub uni models up to a 4-

way multiprocessor. The z890 offers 7 general purpose CP

sizes (1 full performance plus 6 sub uni's). Each engine

size is available in 2-way, 3-way and 4-way multiproces-

sors. Seven engine sizes across 4 engines gives outstand-

ing capacity granularity over the 28 capacity settings.

The new model provides 1-4 conﬁ gurable processor units

which can be characterized as either CPs, IFLs, ICFs, or

zAAPs.

A new easy-to-enable ability to “turn off” capacity is avail-

able on z890. The objective is to allow customers to pur-

chase capacity for future use with virtually no impact on

software billing. An MES feature will enable the capacity

for use where the customer requires the increased capacity.

There are a wide range of upgrade options available which

are indicated in the z890 Models chart. The introduction of

the capacity setting allows capacity upgrades and down-

grades between capacity settings independent of the CP

quantity.

Unlike other zSeries server offerings, it is no longer pos-

sible to tell by the hardware model A04, the number of PUs

or the capacity of the server that is being used as CPs.

The capacity setting is in the form xy0, where the X repre-

sents the number of CPs and Y represents the sub-capacity,

from 7 (most capacity) to 1 (least capacity). All IFL and ICF

conﬁ gurations are software model 070. The capacity set-

ting will be returned by the Store System Information (STSI)

instruction for software billing purposes.

z890 Performance Comparison

Capacity

110 120 130 140 150 160 170 210 220 230 240 250 260 270 310 320 330 340 350 360 370 410 420 430 440 450 460 470

Settings*

Uni's

2-ways 4-ways (full capacity engines)

* Capacity Setting refers to number of installed CPs and capacity. Reported by STSI instruction. Note: For MSU values, refer to: ibm.com/servers/eserver/zseries/library/swpriceinfo/

3-ways

Model A04

IBM ^ On/Off Capacity on Demand for z890

IBM ^ On/Off Capacity on Demand (On/Off CoD)

is offered with z890 processors to provide a temporary

increase in capacity to help meet customers' peak work-

load requirement.

On/Off CoD is designed to temporarily turn on Central

Processors (CPs), Internal Coupling Facilities (ICFs), Inte-

grated Facilities for Linux (IFLs), zSeries Application Assist

Processors (zAAPs), previously unassigned Processor

Units (not assigned as a CP, ICF, IFL, or zAAP), and, for

z890, unassigned CPs and unassigned IFLs, that are avail-

able within the current model conﬁ guration. Temporary use

of CFs, memory and channels is not supported.

This is achieved by either increasing CP capacity through

changing the Capacity Setting of the CPs to a new Model

Capacity Indicator or by using unassigned/unowned PUs

available for use as CPs, IFLs, ICFs, or zAAPs. With On/Off

CoD, temporary capacity for CPs, cannot exceed more

than double the permanent CP capacity of the z890. IFL

and ICF capacity additions can only be done if an existing

IFL or ICF is installed on the permanent machine with the

restrictions that a) additional engines, of each type, cannot

exceed the number of installed permanent engines of

that same type and b) adding engines cannot exceed the

physical limit of the installed machine.

The maximum number of On/Off CoD zAAPs available for

z890 cannot exceed the number of zAAPs, with the addi-

tional restriction that the sum of zAAPs and On/Off CoD

zAAPs cannot exceed the number of CPs.

For example, capacity setting 110 is eligible for On/Off

CoD upgrades to only capacity settings 120 and 210. All

other target capacity settings would result in more than

two times the base capacity.

You will be billed for associated usage through one or

more of the following features: On/Off CoD Active CP-Day

(#9897), On/Off CoD Active IFL Day (#9888), On/Off Active

ICF-Day (#9889), or On/Off CoD Active zAAP-Day (#9893).

You will be billed for each On/Off CoD Active engine

turned on in any given 24-hour period, continuing until

such On/Off CoD Active engine is turned off. Each

month your bill will be calculated for the sum of all orders

installed within the prior month. Monitoring will occur

through the server call home facility and a bill will be gen-

erated if the hardware capacity has been enabled for any

given month. You will continue to be billed for the use of

temporary capacity until you return the server to its original

state. After concurrently returning to the original state, you

may choose to activate a new On/Off CoD upgrade, which

can be different from the previous upgrade. When you

dispose of the server, or decide that you want to disable

future temporary upgrades, you are required to remove the

enablement feature, On/Off CoD Enablement (#9896).

Although the hardware upgrade does not need a POR/

IML if there is a change in engine size, a z/OS IPL will be

required.

On/Off CoD is delivered through the Customer Initiated

Upgrade (CIU) facility. To participate in this offering,

customers must install CIU Enablement and On/Off CoD

Enablement, and must agree to speciﬁ c terms and condi-

tions which govern the use of temporary capacity.

For z890, you may request and concurrently install tem-

porary capacity through the CIU application on Resource

™

, and use that additional capacity for as long as

Link

needed. Using this facility, you may increase a machine’s

capacity setting and add a quantity of temporary IFLs

and ICFs, up to the machine’s current capacity setting or

the number of IFLs and ICFs, respectively, on the same

machine. You may similarly request and concurrently

install a quantity of temporary zAAPs up to the quantity of

permanent zAAPs, with the limitation that the combined

quantity of temporary zAAPs plus permanent zAAPs may

not exceed the combined quantity of temporary CPs plus

permanent CPs. You will be billed for associated usage

through one or more of the following features: On/Off CoD

Use Days, (one of #6121 through #6471), On/Off CoD

Active IFL-Day (#9888), On/Off Active ICF-Day (#9889), or

On/Off CoD Active zAAP-Days (#9893).

Typically, On/Off Capacity on Demand will be ordered

through CIU, however there will be an RPQ available if no

RSF connection is present.

Although Capacity BackUp (CBU) and On/Off Capacity

on Demand can both reside on the server, the activation

of On/Off Capacity on Demand is mutually exclusive with

CBU and no physical hardware upgrade will be supported

while On/Off Capacity on Demand is active.

This important function for zSeries gives customers greater

control and ability to add capacity to meet the require-

ments of an unpredictable on demand application environ-

ment. On/Off CoD extends zSeries capacity on demand

offerings to the next level of ﬂ exibility. It is designed to

help customers match cost with capacity utilization and

manage periodic business spikes. On/Off Capacity on

Demand is designed to provide a low risk way to deploy

new pilot applications, and it is designed to enable a cus-

tomer to grow capacity smartly and proportionately with

market demand.

Customers can also take advantage of the Capacity

Upgrade on Demand (CUoD), Customer Initiated Upgrade

(CIU), and Capacity BackUp (CBU) which are described

later in the document.

On/Off CoD Test

IBM continues to enhance On/Off CoD to be more respon-

sive to your on demand business requirements. On/Off

CoD has been enhanced to allow for a no-charge test.

No IBM charges are assessed for the test, including IBM

charges associated with temporary hardware capacity,

IBM software, or IBM maintenance. This test can be used

to validate the processes to download, activate, and deac-

tivate On/Off CoD capacity nondisruptively. Each On/Off

CoD-enabled server is entitled to one no-charge test, per

contract. This test may last up to a maximum duration of

24 hours commencing with the download and activation of

an On/Off CoD order. On/Off CoD tests which do exceed

24 hours in duration will be treated in their entirety as bill-

able On/Off CoD upgrades. In addition to validating the

On/Off CoD function within your environment, you may

choose to use this test as a training session for your per-

sonnel who are authorized to activate On/Off CoD.

On/Off CoD no-charge test can be requested and down-

loaded from the Web at Resource Link. Refer to: ibm.com/

servers/resourcelink.

On/Off CoD test is exclusive to z890 and z990.

The z890 is designed to offer an efﬁ cient I/O structure

using the same I/O cages as the z990. The single I/O cage

z890, has the capability of plugging up to 28 I/O cards

which would support a maximum of 420 ESCON

chan-

nels. Seven of the eight available STIs on the z890 are

required to support the 28 channel slots in the I/O cage.

The following chart shows the upgrade paths from z800 to

z890 and from z890 to z990. The z800 Models 0X2, 0A2,

002, 003 and 004 can be upgraded to any capacity z890.

Any z890 with more than 220 MIPS can be upgraded to a

z990 Model A08. There are no upgrades from 9672 G5/G6

or z900 server.

z800 to z890 and z890 Model Upgrades

e-Config will default to the next closest

z800 z890

To Any Capacity Setting

0X2 0A2 002 003 004

A04

capacity setting models, but the user may change to any capacity setting desired.

z800 z890

z890 Performance Comparisons

The IBM z890 is the latest member of the zSeries family.

The design of the z890 is a continuation of the major

change in the direction of the zSeries platform started with

the IBM ^ zSeries 990. The implementation of the

superscalar microprocessor provides for improvements

in the performance of new workloads as well as maintain-

ing excellent performance for traditional workloads. The

z890 provides a lower capacity entry point as compared to

the z800, an increase in total system capacity almost 2.1

times that of the z800 Model 004, doubling the number of

CHPIDs, doubling the number of LPARs, quadrupling the

number of HiperSockets, and increasing the number of

ESCON channels by 75%, the number of FICON

channels

by 25%, the number of ISC-3s by 100% and the number of

OSA-Express Network connections by 67%. This server is

designed to provide you with the ability to improve applica-

tion performance, increase the number of users supported,

support more transactions, increase scalability, and con-

solidate workloads beyond what is available on a z800.

performance levels, z890 offers from 1-4 Central Proces-

sors each with 7 different “dial points” (28 choices in all)

esource management within the system, it is expected

and r

that there will be a large performance variability than has

been previously seen by our traditional customer set. The

z890 supports an estimated performance range of 0.14 to

7.40 compared to a z800 Model 001. This variability may be

observed in several ways. The range of performance rat-

ings across the individual LSPR workloads is likely to have a

larger spread than past processors. There will also be more

performance variation of individual LPAR partitions as the

impact of ﬂ uctuating resource requirements of other parti-

tions can be more pronounced with the increased number

of partitions available on the z890. The customer impact of

this increased variability will be seen as increased devia-

tions of workloads from single-number-metric based factors

such as MIPS, MSUs and CPU time chargeback algorithms.

It is important to realize the z890 has been optimized to run

many workloads at high utilization rates.

The performance design of the z/Architecture enables

the entire server to support a new standard of perfor-

mance for all applications through expanding upon a bal-

anced system approach. As CMOS technology has been

enhanced to support not only additional processing power,

but also more engines, the entire server is modiﬁ ed to sup-

port the increase in processing power. The I/O subsystem

supports a great amount of bandwidth through internal

changes, thus providing for larger and quicker data move-

ment into and out of the server. Support of larger amounts

of data within the server required improved management

of storage conﬁ gurations made available through integra-

tion of the software operating system and hardware sup-

port of 64-bit addressing. The combined balanced system

effect allows for increases in performance across a broad

spectrum of work. However, due to the wide range of

It is also important to notice that the LSPR workloads for

z890 and z990 have been updated to reﬂ ect more closely

our customers’ current and growth workloads. The tradi-

tional TSO LSPR workload is replaced by a new, heavy

Java technology-based online workload referred to as

Trade2-EJB (a stock trading application). The traditional

/DB2® LSPR online workload has been updated to

CICS

have a Web-frontend which then connects to CICS. This

updated workload is referred to as WEB/CICS/DB2 and

is representative of customers who Web-enable access

to their legacy applications. Continuing in the LSPR for

z890/ z990 will be the legacy online workload, IMS, and

two legacy batch workloads CB84 and CBW2. The z890/

z990 LSPR will provide performance ratios for individual

workloads as well as a “default mixed workload” which is

used to establish single-number-metrics such as MIPS,

z890 I/O Subsystem

MSUs and SRM constants. The z990 default mixed work-

load will be composed of equal amounts of ﬁ ve workloads,

Trade2-EJB, WEB/CICS/DB2, IMS, CB84 and CBW2. Addi-

tionally, the z890/z990 LSPR will rate all z/Architecture pro-

cessors running in LPAR mode and 64-bit mode. The existing

z900 processors have all been re-measured using the new

workloads – all running in LPAR mode and 64-bit mode.

Using the new LSPR ‘default mixed workload' for z/OS

1.4, and with all processors executing in 64-bit and LPAR

mode, the following results have been achieved:

• Comparing a one-way z800 Model 001 to a one-way

z890 Model A04 170, it is estimated that the z890 model

has 2.0 times the capacity of z800 Model 001.

• Comparing a two-way z800 Model 002 to a two-way

z890 Model A04 270, it is estimated that the z890 model

has 2.1 times the capacity of z800 Model 002.

• Comparing a three-way z800 Model 003 to a three-way

z890 Model A04 370, it is estimated that the z890 model

has 2.1 times the capacity of z800 Model 003.

• Comparing a four-way z800 Model 004 to a four-way

z890 Model A04 470, it is estimated that the z890 model

has 2.1 times the capacity of z800 Model 004.

The z890 contains an I/O subsystem infrastructure which

uses an I/O cage that provides 28 I/O slots. Each I/O

cage has seven I/O domains with four features in each I/O

domain, and each domain has one STI for connectivity to

support each I/O cage. ESCON, FICON Express, FICON

Express2, OSA-Express, OSA-Express2 and Crypto

Express2 features plug into the z890 I/O cage along with

any ISC-3s and STI-3 distribution cards, and PCICA and

PCIXCC cryptographic features. All I/O cards and their

support cards can be hot-plugged in the I/O cage. The

z890 provides approximately a 78 percent increase in I/O

bandwidth provided by the STIs when compared to the

z800.

z890 Cage Layout

A-Frame

CEC

z890's Positioning in the zSeries Family

z990

z900 and z990

z890

z800

MP3000

MP 2000

MIPs

Note: Expected performance improvements are based on hardware changes. Additional performance beneﬁ ts may be obtained as the z/Architecture is fully exploited.

z900

9672

> 2550 MIPs

I/O

Cage

z890 Logical Channel SubSystems (LCSSs) and support for

Greater than 15 Logical Partitions (LPARs)

The z890 I/O subsystem is a breakthrough in connectivity

by providing up to 2 LCSS per server, and each LCSS can

support up to 256 CHPIDs when exploitation software is

installed. As the z890 is a single I/O cage conﬁ guration it

will support up to a maximum of 512 CHPIDs of which up

to 420 CHPIDs can be ESCON channels. This support is

provided in such a way that is transparent to the programs

operating in the Logical Partition (LP). Each Logical Chan-

nel SubSystem may have from 1 to 256 CHPIDs and may

in turn be conﬁ gured with 1 to 15 Logical Partitions. Each

Logical Partition runs under a single LCSS. As with previ-

ous zSeries servers, Multiple Image Facility (MIF) channel

sharing as well as all other channel subsystem features

are available to each Logical Partition conﬁ gured to each

Logical Channel SubSystem. The z890 supports up to 30

Logical Partitions. (Note: The lowest Capacity Setting 110

can support up to 240 CHPIDs and up to a maximum of 15

LPARs.)

feature in the I/O cage. CHPID numbers are no longer pre-

assigned and it is now a customer responsibility to do this

assignment via IOCP/HCD. CHPID assignment is done by

associating a CHPID number with a physical location, the

PCHID. It is important to note that although it is possible

to have 2 LCSSs, there is still a single IOCDS to deﬁ ne the

I/O subsystem, each LCSS can support CHPID 00-FF, and

the CHPID must be unique within the LCSS. There is a new

CHPID mapping tool available to aid in the mapping of

CHPIDs to PCHIDs. The CHPID Mapping tool is available

from Resource Link at: ibm.com/servers/resourcelink.

IOCP - IOCDS

Partitions

LCSS0 LCSS1

CHPIDs CHPIDs

12 52 EF4F 12 2F EF00 02

Partitions

Up to 30 Logical Partitions

Up to 256

LCSS0 LCSS1

CHPIDs

Up to 256

CHPIDs

Physical Channel IDs (PCHIDs) SubSystem

In order to accommodate the support for up to a maximum

of 512 CHPIDs on z890 with the Logical Channel SubSys-

tem (LCSS) a new Physical Channel ID (PCHID) is avail-

able. The PCHID represents the physical location of an I/O

HCD - HSA or IOCDS - HSA

102 103 104 110 200 201 202 2B0 2C5

Physical Channels (PCHIDs)

Note: Crypto no longer requires a CHPID

Logical Channel SubSystem (LCSS) Spanning

The concept of spanning channels provides the ability for

a channel to be conﬁ gured to multiple Logical Channel

SubSystems and therefore they may be transparently

shared by any/all of the logical partitions in those LCSSs.

z890 Channels and I/O Connectivity

Normal Multiple Image Facility (MIF) sharing of a chan-

nel is conﬁ ned to a single LCSS. The z890 supports the

spanning of the channels types: IC, HiperSockets, FICON

Express, FICON Express2, OSA-Express, OSA-Express2,

ISC-3s and ICBs (ICB-3 and ICB-4). Note: Spanning of

ESCON channels is not supported.

Channel Spanning

ZOS2 ZOS3 ZOS4 ZOS5 LNX1ZOS1

HiperSockets

CHPID 22 CHPID 22

LCSS0 LCSS1

A z890 has a total of 28 I/O slots in one I/O cage. These

slots can be plugged with a mixture of cards providing

the I/O connectivity, networking connectivity, coupling and

cryptographic capability of the server.

Up to 420 ESCON Channels

The high density ESCON feature has 16 ports, 15 of which

can be activated for customer use. One port is always

reserved as a spare which is activated in the event of a

failure of one of the other ports. For high availability the ini-

tial order of ESCON features will deliver two cards and the

active ports will be distributed across those cards. After

the initial install the ESCON features are installed in incre-

ments of one. ESCON channels are available in four-port

increments and are activated using IBM Licensed Internal

Code, Conﬁ guration Control (LIC CC). There is a 75%

increase in ESCON connectivity over z800.

Up to 40 FICON Express Channels

The z890 supports up to 40 FICON Express channels. It

offers a 25% increase in FICON Express channels over the

z800. FICON Express is available in long wavelength (LX)

and short wavelength (SX) features. Each FICON Express

feature has two independent ports which support two

channels per card. The LX and SX cannot be intermixed on

a single feature. The maximum number of FICON Express

features which can be installed in the I/O cage is 20.

The z890 supports up to 40 FCP channels for attach-

ment to Small Computer System Interface (SCSI) disks in

a Linux environment. The same two-port FICON Express

feature card used for FICON Express channels can also

be used for Fibre Channel Protocol (FCP) channels. FCP

channels are enabled on these existing features via a

Licensed Internal Code (LIC) with a unique mode of

operation and CHPID deﬁ nition (FCP). FCP is available in

long wavelength (LX) and short wavelength (SX) features,

though the LX and SX cannot be intermixed on a single

feature. Note, the maximum quantity of FICON Express,

OSA-Express, PCICA, and PCIXCC features in combina-

tion cannot exceed 20 features per server.

Up to 80 FICON Express2 Channels

Up to 80 FICON Express2 channels are supported on the

z890. This offers a 100% increase in FICON channels over

the z800. FICON Express2 is available in long wave

(LX) and short wavelength (SX) features. Each FICON

Express2 feature has four independent ports which support

four channels per card. The LX and SX cannot be intermixed

on a single feature. The maximum number of FICON Express2

features that can be installed in the I/O cage is 20.

The z890 supports up to 80 FCP channels for attachment

to Small Computer System Interface (SCSI) disks in a Linux

environment. The same four-port FICON Express2 feature

card used for FICON Express2 channels can also be used

for Fibre Channel Protocol (FCP) channels. FCP channels

are enabled on these existing features via a Licensed Inter-

nal Code (LIC) with a unique mode of operation and CHPID

deﬁ nition (FCP). FCP is available in long wavelength (LX)

and short wavelength (SX) features, though the LX and SX

cannot be intermixed on a single feature. Note, the maxi-

mum quantity of FICON Express, FICON Express2, OSA-

Express, OSA-Express2, PCICA, and PCIXCC features in

combination cannot exceed 20 features per server.

length

peer mode up to an unrepeated distance of 10 km (6.2 miles).

The mode is selected for each link via the CHPID type in the

IOCDS. ISC-3 links are ordered in increments of one. It is rec-

ommended that an initial order for ISC-3 include two links.

ISC-3 links in Compatibility Mode must be used for connec-

tivity to 9672s (ICB-2 links are not supported on the z890).

An RPQ card (8P2197) is available to allow ISC-3 dis-

tances up to 20 km. This card runs in Peer Mode at 1

Gbps and/or Compatibility Mode at 1 Gbps. A unique

daughter card with two links per card is shipped.

Integrated Cluster Bus-3 (ICB-3)

The ICB-3 feature is a coupling link used to provide high-

speed communication between z990 and z890 servers

and z900 and z800 General Purpose Servers and Cou-

pling Facilities over a short distance (less than 7 meters).

The ICB-3 is supported via an STI-3 card which resides in

the I/O cage and converts the 2.0 GBps input into two 1

GBps ICB-3s.

Integrated Cluster Bus-4 (ICB-4)

The ICB-4 feature is a coupling link used to provide

high-speed communication between a z990 and/or z890

servers over a short distance (less than 7 meters). The

ICB-4 consists of one link that attaches directly to a 2.0

GBps STI port on the server and does not require connec-

tivity to an I/O cage.

InterSystem Channel-3 (ISC-3)

A four link ISC-3 feature is provided on the z890 family of

servers. It consists of a mother card with two daughter cards

each with two links. Each link is capable of operating 1 giga-

bits per second (Gbps) in Compatibility Mode or 2 Gbps in

Internal Coupling Channel (IC)

IC links emulate the coupling links between images within

a single server. IC links are deﬁ ned in the IOCP. There is no

physical channel involved. A z/OS image can connect to a

Coupling Facility on the same server using IC capabilities.

Fibre Channel Connectivity

The on demand operating environment requires fast data

access, continuous data availability, and improved ﬂ exibil-

ity all with lower cost of ownership. zSeries Fibre Channel

Connectivity can help you achieve these goals.

Native FICON Channels

Native FICON channels and devices can help to reduce

bandwidth constraints and channel contention to enable

easier server consolidation, new application growth,

large business intelligence queries and exploitation of

e-business.

Currently, the IBM Enterprise Storage Server

(ESS)

models F20 and 800 have two host adapters to support

native FICON. These host adapters each have one port

per card and can either be FC 3021 for long wavelength

or FC 3032 for short wavelength on the F10/F20 or FC

3024 for long wavelength and 3025 for short wavelength

on the 800. All three models can support up to 16 FICON

ports per ESS. The Model 800 is 2 Gb link capable. The

IBM TotalStorage

Enterprise Tape Controller 3590 Model

A60 provides up to two FICON interfaces which can coex-

ist with ESCON on the same box. The IBM TotalStorage

Enterprise Tape Controller 3592-J70 which provides up to

four FICON interfaces which can exist with ESCON on the

same box. The 3592-J70 is designed to provide up to 1.5

times the throuput of the Model A60. Customers can utilize

IBM’s highest capacity, highest performance tape drive to

support their new business models.

Many Fibre Channel directors provide dynamic connec-

tivity to native FICON control units. The IBM 2032 models

001, 064 and 140 (resell of the McDATA ED-5000, and

Intrepid 6000 Series Directors) are 32-, 64- and 140-port

high availability directors. The IBM 2042 models 001, 128

and 256 (resell of the CNT (FC/9000 Directors) are 64-,

128- and 256-port high availability directors. All have fea-

tures that provide interface support to allow the unit to be

managed by System Automation for OS/390. The McDATA

Intrepid 6000 Series Directors and CNT (FC/9000 Direc-

tors) FC/9000-001/-128/-256 support 2 Gbps links as well.

The FICON Express features support attachment to the

IBM M12 Director (2109-M12). The IBM M12 Director sup-

ports attachment of FICON Express channels on the z890

via native FICON (FC CHPID type) and Fibre Channel

Protocol (FCP CHPID type) supporting attachment to SCSI

devices in Linux environments.

Wave Division Multiplexor and Optical Ampliﬁ ers that sup-

port 2 Gbps FICON Express links are: Cisco Systems ONS

15530 and 15540 ESP (LX, SX) and optical ampliﬁ er (LX,

SX), Nortel Networks Optera Metro 5100, 5200 and 5300E

and optical ampliﬁ er, ADVA Fiber Service Platform (FSP)

2000 system, and the IBM 2029 Fiber Saver.

The raw bandwidth and distance capabilities that native

FICON end-to-end connectivity has to offer makes them of

interest for anyone with a need for high performance, large

data transfers or enhanced multi-site solutions.

FICON CTC function

Native FICON channels support CTC on the z990, z900,

z890 and z800. G5 and G6 servers can connect to a

zSeries FICON CTC as well. This FICON CTC connectivity

will increase bandwidth between G5, G6, z990, z900, z890

and z800 systems.

Because the FICON CTC function is included as part

of the native FICON (FC) mode of operation on zSeries,

FICON CTC is not limited to intersystem connectivity (as

is the case with ESCON), but will also support multiple

device deﬁ nitions. For example, ESCON channels that are

dedicated as CTC cannot communicate with any other

device, whereas native FICON (FC) channels are not dedi-

cated to CTC only. Native can support both device and

CTC mode deﬁ nition concurrently, allowing for greater con-

nectivity ﬂ exibility.

FICON Connectivity

FICON Bridge

ESCD

9032

Model 5

FICON Bridge

ESCON

ESS

F10, F20, 800

high availability, extended distance connectivity, and (par-

ticularly with the implementation of 2 Gbps Inter Switch

Links), has the potential for ﬁ ber infrastructure cost sav-

ings by reducing the number of channels for interconnect-

ing the 2 sites.

FICON cascaded directors have the added value of high

integrity connectivity. New integrity features introduced

within the FICON Express channel and the FICON cas-

caded switch fabric to aid in the detection and reporting of

any miscabling actions occurring within the fabric during

and helps prevent data from being delivered to the wrong

end point.

FICON cascaded directors is offered in conjunction with

IBM, CNT, and McDATA Directors.

All FICON Channels =

100MB/s

= LX ONLY

= LX or SX

2032

2042

32, 64 or 140

64, 128 or 256

PORT

ESS

F10, F20, 800

Enterprise

Tape

Controller

3590 A60

Enterprise

Tape

Controller

3590 A60

FICON Support for Cascaded Directors

Native FICON (FC) channels support cascaded directors.

This support is for a single hop conﬁ guration only. This

means that a Native FICON (FC) channel or a FICON CTC

can connect a server to a device or other server via two

(same vendor) FICON Directors in between. This type of

cascaded support is important for disaster recovery and

business continuity solutions because it can help provide

IBM

Two site non-cascaded director

topology. Each CEC connects to

directors in both sites.

With Inter Switch Links (ISLs),

less fiber cabling may be needed

for cross-site connectivity

topology. Each CEC connects to

IBM

Two Site cascaded director

local directors only.

FCP Channels

zSeries supports FCP channels, switches and FCP/SCSI

devices with full fabric connectivity under Linux on zSeries

and z/VM Version 4 Release 3 and later. Support for FCP

devices means that zSeries servers will be capable of

attaching to select FCP/SCSI devices and may access

these devices from Linux on zSeries. This expanded

attachability means that customers have more choices

for new storage solutions, or may have the ability to use

existing storage devices, thus helping to leverage exist-

ing investments and lower total cost of ownership for their

Linux implementation.

For details of supported FICON and FCP attachments

access Resource Link at: ibm.com/servers/resourcelink

and in the Planning section go to z890/z990 I/O Connec-

tion information.

The support for FCP channels is for Linux and z/VM 4.3

and later. Linux may be the native operating system on the

zSeries server (note z890 runs LPAR mode only), or it can

be in LPAR mode or, operating as a guest under z/VM 4.3

or later. The z890 provides support for IPL of Linux guest

images from appropriate FCP attached devices.

Now, z/VM V5.1, support for SCSI FCP disks enables the

deployment of a Linux server farm running under VM con-

ﬁ gured only with SCSI disks. With this support you can

install, IPL, and operate z/VM from SCSI disks.

resources and infrastructure. Further savings may be real-

ized in the reduction of the number of ﬁ ber optic cabling

and director ports.

When conﬁ gured as FCP CHPID type, the z890 FICON

Express features support the industry standard interface

for Storage Area Network (SAN) managment tools.

FCP

Device

FCP

Device

Fibre Channel

Directors

FCP

Device

FCP

Device

FCP

Device

FCP

Device

FCP

Device

FCP

Device

FCP

Device

FCP

Device

FCP

Device

FCP

Device

FICON Express enhancements for Storage Area Networks

Preview - FCP LUN Access Control

The 2 Gbps capability on the FICON Express channel

cards means that 2 Gbps link data rates are available for

FCP channels as well.

FCP Full fabric connectivity

FCP full fabric support means that any number of (single

vendor) FCP directors/ switches can be placed between

the server and FCP/ SCSI device thereby allowing many

“hops” through a storage network for I/O connectivity. This

support along with 2 Gbps link capability is being deliv-

ered together with IBM and directors from IBM, CNT, and

McDATA. FCP full fabric connectivity enables multiple FCP

switches/ directors on a fabric to share links and there-

fore provide improved utilization of inter-site connected

IBM zSeries is previewing Fibre Channel Protocol (FCP)

Logical Unit Number (LUN) Access Control which is

designed to provide host-based control of access to storage

controllers and their devices as identiﬁ ed by their logical unit

numbers (LUNs). It will allow read-only sharing of FCP SCSI

devices among multiple operating system images.

If a host channel is shared among multiple operating

system images, the access control mechanism would pro-

vide for either none or all of these images to have access

to a particular storage controller or device (logical unit).

FCP LUN Access Control will allow you to deﬁ ne, via an

access control table, individual access rights to storage

controller ports and devices for each operating system

image. A system conﬁ guration using FCP LUN Access

Control may signiﬁ cantly reduce the number of FCP chan-

nels (FICON Express features) that are needed to provide

controlled access to the data on FCP SCSI devices. FCP

LUN Access Control complements the zoning and LUN

masking schemes that exist in open storage environments.

All of these types of access control can be used together.

FCP LUN Access Control will allow read-only sharing

of FCP SCSI devices among multiple operating system

images via a shared FCP Channel. A device to be used in

shared read-only mode must be deﬁ ned accordingly in the

access control table.

Conﬁ guration Utility: The Conﬁ guration Utility for FCP LUN

Access Control is expected to be a Linux user space

application which will be used to conﬁ gure the FCP LUN

Access Control.

To deﬁ ne and activate LUN Access Control, you would

create an access control table that describes the access

rights in XML format. In this table, you would deﬁ ne access

rights to storage controllers and devices in the SAN and

identify devices to be shared in read-only mode.

It is expected that the Conﬁ guration Utility will be pro-

vided for download by registered users via Resource Link:

ibm.com/servers/resourcelink/.

When available, FCP LUN Access Control will be sup-

ported by the FICON Express2 features when conﬁ gured

as CHPID type FCP, will be exclusive to z890 and z990,

and is planned to be available in the z/VM and Linux on

zSeries environments. This statement represents IBM’s

current intentions. IBM development plans are subject to

change or withdrawal without further notice.

IBM zSeries is interested in obtaining customers to par-

ticpate in an Early Support Program. We encourage you to

contact your IBM representative.

FICON purge path extended

The new purge path extended function provides enhanced

capability for FICON problem determination.

FICON purge path error-recovery function is extended so

that it transfers error-related data and statistics between

the channel and entry switch, and the control unit and its

entry switch to the host operating system.

The Conﬁ guration Utility for FCP LUN Access Control is

required to process the access control table, verify proper

speciﬁ cation of the rules, and activate the access control

functions in the FCP channel.

The Conﬁ guration Utility for FCP LUN Access Control is

a package consisting of user documentation and sample

ﬁ les with a skeleton to help you generate an XML-format

access control table, and the utility program itself. The

program is intended to provide a command line interface

(CLI) and be supported by Linux on zSeries.

z/OS 1.6 can now record this information so that it can

be used to more quickly isolate the source of link-related

errors by both channel and control unit ﬁ eld personnel.

FICON purge path extended applies to the FICON

Express2 features when conﬁ gured as CHPID type FC

(native FICON), is exclusive to z890 and z990, and is sup-

ported by z/OS and z/OS.e. Refer to the Hardware and

Software requirements sections for further information.

A New Generation for SANs – FICON Express2

FICON Express2 offers new packaging with increased

connectivity in the same amount of physical space.

Increased performance is also possible with FICON

Express2. This refresh of technology can help to satisfy

your server consolidation connectivity requirements, and

may help to reduce the number of I/O features required for

consolidation. At the same time, you may be able to realize

a performance advantage.

FICON Express2 Doubles the Channel Capacity

As zSeries has increased its maximum number of I/O

features, so has FICON increased its channel maximums

to meet the ever increasing demands of Storage Area

Networks (SANs). You can now install up to a maximum of

80 channels on z890 (when all are FICON Express2). The

maximum number of FICON features per server (any com-

bination of FICON Express2 and FICON Express) remains

at up to 20 on z890. Each FICON Express2 offers 4 ports

per feature – a 100% increase in channels per feature in

the same amount of physical space.

On the smallest sub-uni the maximum quantity cannot

exceed 16 features per server.

FICON Express2 SX (short wavelength) (#3320) and

FICON Express2 LX (long wavelength) (#3319) occupy

a single I/O slot, utilizing one CHPID per channel (four

CHPIDs per feature). Each of the four independent ports/

channels is capable of 1 gigabit per second (1 Gbps) or

2 Gbps depending upon the capability of the attached

switch or device. The link speed is auto-negotiated, point-

to-point, and is transparent to users and applications. The

FICON Express2 feature does not support FICON Bridge

(CHPID type FCV).

FICON Express2 LX

• The unrepeated distance between FICON Express2 LX channels is limited to 10 kilometers (6.2 miles). If greater distances are desired, an RPQ request should be submitted.

• If reusing existing 50 or 62.5 micron ﬁ ber optic cabling with a pair of MCP cables, the unrepeated distance between FICON Express2 channels cannot exceed 550 meters (1804 feet). MCP cables are only supported at 1 Gbps link data rates.

FICON Express2 SX

• When supporting a link data rate of 1 Gbps and using 50 micron multimode ﬁ ber, the unrepeated distance between FICON SX channels is limited to 500 meters (1640 feet).

• When supporting a link data rate of 2 Gbps and using 50 micron multimode ﬁ ber, the unrepeated distance between FICON SX channels is limited to 300 meters (984 feet).

• When supporting a link data rate of 1 Gbps and using

62.5 micron multimode ﬁ ber, the unrepeated distance between FICON SX channels is limited to 250 meters (820 feet).

• When supporting a link data rate of 2 Gbps and using

62.5 micron multimode ﬁ ber, the unrepeated distance between FICON SX channels is limited to 120 meters (394 feet). If greater distances are desired, an RPQ request should be submitted.

Performance Increase

Your enterprise may beneﬁ t from FICON Express2 with:

• Increased data transfer rates (bandwidth)

• Improved performance

• Increased number of start I/Os

• Reduced backup windows

• Channel aggregation to help reduce infrastructure costs

Concurrent Update

The FICON Express2 SX and LX features may be added

to an existing z890 concurrently. This concurrent update

capability allows you to continue to run workloads through

other channels while the new FICON Express2 features are

being added. This applies to CHPID types FC and FCP.

FICON Express2 Replaces FICON Express on z890

FICON Express2 SX and LX (#3320, #3319) replace the

FICON Express SX and LX features (#2320, #2319) cur-

rently offered on z890. When the FICON Express2 features

become available, the FICON Express features will no

longer be orderable.

Continued Support of Spanned Channels and LPARs

The FICON Express2, both FICON and FCP (CHPID types

FC and FCP) channel types, can be deﬁ ned as a spanned

channel and can be shared among LPARs within and

across LCSSs.

Modes of Operation

There are two modes of operation supported by FICON

Express2 SX and LX. These modes are conﬁ gured on a

channel-by-channel basis – each of the four channels can

be conﬁ gured in either of two supported modes.

• Fibre Channel (CHPID type FC), which is native FICON or FICON Channel-To-Channel (server-to-server)

• Fibre Channel Protocol (CHPID type FCP), which supports attachment to SCSI devices via Fibre Channel switches or directors in z/VM and Linux on zSeries environments

Cascading

The FICON Express2 features also support cascading

(the connection of two FICON Directors in succession) to

minimize the number of cross-site connections and reduce

implementation costs for disaster recovery, business conti-

nuity, GDPS, and remote copy solutions.

CHPID Type FCV Not Supported on FICON Express2

FICON Bridge (CHPID type FCV) is not supported on

FICON Express2. CHPID type FCV was designed to be

used with the bridge feature in the ESCON Director Model

5, which was withdrawn from marketing December 31,

2004. If your customers continue to have a requirement

for CHPID type FCV, then they may wish to add FICON

Express2 for growth, supporting CHPID types FC and FCP,

and use FICON Express, supporting CHPID type FCV, for

connectivity to ESCON control units.

When the FICON Express2 features become available,

the FICON Express features are no longer orderable. For

customers requiring additional FICON Express features to

support CHPID type FCV an RPQ 8P2295 is available. For

existing infrastructures using FCV, FICON Express will con-

tinue to be supported on the z890.

The FICON Express2 features are exclusive to z990 and

z890, and are supported by z/OS, z/OS.e, z/VM, VSE/ESA,

TPF, and Linux on zSeries.

FICON Express2 is planned to be available on January 28,

2005 and June 30, 2005 in Argentina and Venezuela.

A New Generation of zSeries LAN Adapters Open Systems Adapter-Express2

A new generation of zSeries LAN adapters is being deliv-

ered, as well as a 10 Gigabit Ethernet feature. This update of

technology, referred to as OSA-Express2, can help to satisfy

the bandwidth demands of your applications. Like their pre-

decessors, the OSA-Express2 features continue to be hot-

pluggable, support the Multiple Image Facility (MIF) – sharing

of channels across logical partitions (LPARs), and can be

deﬁ ned as a spanned channel to be shared among LPARs

within and across LCSSs. The maximum combined number

of OSA-Express and OSA-Express2 features supported per

server is 20 on the z890 and 24 features on the z990.

Both OSA-Express2 Gigabit Ethernet (GbE) and 10 Gigabit

Ethernet (10 GbE) support the Queued Direct Input/Out

(QDIO) mode, carrying TCP/IP trafﬁ c only. QDIO continues

to be the preferred architecture on zSeries for high-speed

communication, helping to reduce host interruptions and

improve response time.

Also like the predecessor features, OSA-Express2 GbE and

10 GbE support the direct SNMP subagent, all of the SNMP

enhancements previously announced, Virtual Local Area Net-

works3 (VLANs), Internet Protocol Version 4 (IPv4), IPv6 and

all of the functions previously announced for QDIO mode.

The OSA-Express2 GbE and 10 GbE features support

Checksum Ofﬂ oad and have the connector type, LC Duplex,

like the current OSA-Express Gigabit Ethernet features.

OSA-Express2 Gigabit Ethernet

The third generation of Gigabit Ethernet features is

designed to deliver improved latency and throughput up

to line speed – 1 Gbps in each direction or 2 Gbps full

duplex and support the following functions:

• 640 TCP/IP stacks per CHPID

• Large send, for TCP/IP trafﬁ c and CPU efﬁ ciency, ofﬂ oading the TCP segmentation processing from the host TCP/IP stack

• Concurrent LIC update

• Layer 2

OSA-Express2 Gigabit Ethernet (GbE) operates in QDIO

mode only, supports full duplex operation, and jumbo

frames (8992 byte frame size).

The improved latency is expected to support additional

Ethernet connections per second compared to the OSA-

Express GbE features and the improved throughput is

designed to support line speed in each direction up to 2

Gbps full duplex.

The new OSA-Express2 GbE features continue to be dual-

port features occupying a single I/O slot and utilize one

CHPID per port; two CHPIDs per feature. The new OSA-

Express2 Gigabit Ethernet SX and LX features are offered

on new builds and replace the current OSA-Express Giga-

bit Ethernet features currently offered on z890 and z990.

The OSA-Express2 GbE features are exclusive to z890 and

z990, require the October 2004 level of Licensed Internal

Code.

OSA-Express2 10 Gigabit Ethernet LR

The newest member of the OSA-Express2 family is the

OSA-Express2 10 Gigabit Ethernet long reach (LR).

It can

be use in an enterprise backbone, between campuses, to

consolidate ﬁ le servers and to connect server farms with

zSeries 890 and 990 servers. The OSA-Express2 10 GbE

LR supports:

• Queued Direct Input/Output (QDIO)

• One port per feature

• A link data rate of 10 Gbps

• Full duplex mode

• Jumbo frames (8992 byte frame size)

• Checksum ofﬂ oad

• Layer 2 support

• 640 TCP/IP stacks

• Concurrent LIC update

• SC Duplex connector

• Single mode ﬁ ber (9 micron)

• An unrepeated distance of up to 10 km (6.2 miles)

Checksum Ofﬂ oad is supported in the z/OS, z/OS.e and

Linux on zSeries environments.

The 10 Gigabit Ethernet (10 GbE) feature does not support

auto-negotiation to any other speed. The 10 GbE supports

64B/66B coding, whereas GbE supports 8B/10B coding.

The OSA-Express2 10 GbE feature is exclusive to the z890

and z990, and requires the October 2004 level of Licensed

Internal Code.

New functions in OSA-Express2

In a continuing effort to enhance the functions of the Open

Systems Adapters and respond to customer requirements,

IBM zSeries has enhanced the OSA-Express2 over OSA-

Express features with the following improvements:

Large send for TCP/IP trafﬁ c

Large send, also referred to as TCP segmentation ofﬂ oad,

is designed to improve performance by ofﬂ oading TCP

packet processing from the z890 and z990 servers to the

OSA-Express2 features. This ofﬂ oad allows the zSeries

server to send large blocks of data (64 kilobytes), instead

of 1492 byte packets, to the OSA-Express2 feature. The

OSA-Express2 features then separate the 64 KB block into

standard Ethernet packets (1492 bytes) to be sent out on

the LAN. This applies only to outbound trafﬁ c, IPv4 or IPv6,

and to unicasts. Large send support can help reduce host

processor utilization, returning CPU cycles for other appli-

cation use, while increasing network efﬁ ciencies.

Large send support is exclusive to z890 and z990 servers

with the OSA-Express2 features, when in QDIO mode, and

is supported on Linux for zSeries (requires the October

2004 level of Licensed Internal Code).

OSA-Express2 large send for the z/OS environment –

preview

Previewing large send for TCP/IP trafﬁ c

Improved virtualization – now 640 TCP/IP stacks

If you have a need to host more Linux images, increasing

the number of TCP/IP stacks may be a solution. The OSA-

Express2 features support up to 640 connections (TCP/IP

stacks) per logical partition (LPAR) per dedicated CHPID,

or up to 640 total stacks across multiple LPARs using a

shared or spanned CHPID. This is 4 times the number of

connections that could be supported on the previous OSA-

Express features which were limited to 160 total stacks.

This support is exclusive on z890 and z990 servers and

the OSA-Express2 features in QDIO mode. This support

requires the October 2004 level of Licensed Internal Code

and is supported by z/OS, z/OS.e, z/VM and Linux on

zSeries environments.

z/OS Communications Server plans to exploit OSA-

Express2 large send (also referred to as TCP segmenta-

tion ofﬂ oad). Large send can improve performance by

ofﬂ oading outbound TCP segmentation processing from

the host to OSA-Express2 by employing a more efﬁ cient

memory transfer into OSA-Express2. The z/OS Communi-

cations Server support is planned for TCP/IP IPv4 trafﬁ c

only and z/OS and z/OS.e 1.7. In addition, a z/OS and

z/OS.e 1.6 PTF is planned to be provided.

Large send support applies to the OSA-Express2 features

(Gigabit Ethernet SX and LX, 10 Gigabit Ethernet LR), sup-

ports QDIO mode only (CHPID type OSD), and is exclu-

sive to z990 and z890. Large send support was previously

announced for the Linux on zSeries environment.

OSA-Express2 concurrent LIC update – an availability

enhancement

The OSA-Express2 features have increased memory

in comparison to the OSA-Express features and are

designed to be able to facilitate concurrent application of

Licensed Internal Code (LIC) updates, allowing the appli-

cation of LIC updates without requiring a conﬁ guration

off/on of the features. This can help minimize the disruption

to network trafﬁ c during the update.

For example, applying a patch could have up to x minutes

of impact on the network trafﬁ c for the affected adapters

prior to this enhancement.

OSA-Express2 concurrent LIC update is exclusive to the

z890 and z990 with the October 2004 level of Licensed

Internal Code and requires the OSA-Express2 features.

Layer 2 support – ideal for server consolidation

The OSA-Express26 Ethernet features with the Layer 2

support in z/VM for Linux images can be protocol inde-

pendence and simplify the communication with different

platforms when using IPX, NetBIOS, SNA, IPv4, or IPv6

protocols. In combination with the OSA-Express2 Ethernet

features, Layer 2 can assist in reducing: the effort to set

up Linux images in a guest LAN environment, the number

of router guests providing connection between guest

LANs and OSA, and the CPU consumption of these router

guests.

VLAN identiﬁ cation

, and/or the Ethernet destination MAC

address. This ﬁ ltering can help reduce both the amount of

inbound trafﬁ c being processed by the operating system,

and z890 or z990 CPU requirements.

Another mechanism for reducing z890 or z990 CPU utiliza-

tion with the OSA-Express2 features and the Layer 2 sup-

port is the z/VM Virtual Switch (VSWITCH). The VSWITCH

can eliminate the requirement for router virtual machines.

With z/VM 5.1, VSWITCH exploits the Layer 2 support

within the z/VM Control Program. The z/VM Control Pro-

gram owns the connection to the OSA-Express2 feature

and manages the MAC addresses and VLAN connectivity

of the attached guests. Linux on zSeries can exploit the

Layer 2 support and the z/VM VSWITCH in z/VM 5.1.

Layer 2 support, reducing CPU consumption for non-IP

workloads, is exclusive to z890 and z990, requires the

May 2004 level of Licensed Internal Code with the October

2004 maintenance levels, and is supported by z/VM and

Linux on zSeries. It is available on the OSA-Express2

Eth-

ernet features supporting QDIO mode only.

With the Layer 2 interface, packet forwarding decisions

can be based upon Link Layer (Layer 2) information,

instead of Network Layer (Layer 3) information. Each oper-

ating system attached to the Layer 2 interface uses its own

Medium Access Control (MAC) address. Therefore trafﬁ c

can be either IP (IPv4 or IPv6) or non-IP trafﬁ c such as

IPX, NetBIOS, or SNA. Also, datagrams can be ﬁ ltered by

Open Systems Adapter-Express Features (OSA-Express)

With the introduction of the z890, the OSA-Express

Adapter family of Local Area Network (LAN) features is

offering a maximum of 20 features per system, versus

the maximum of 12 features per system on prior genera-

tions, expanding the z890 balanced solution to increase

throughput and responsiveness in an on demand oper-

ating environment. These features combined with z/OS

and z/OS.e, or OS/390, z/VM, Linux on zSeries, TPF, and

VSE/ESA can help deliver a balanced system solution to

increase throughput and decrease host interrupts to con-

tinue to help satisfy your business goals.

Each of the OSA-Express features offers two ports for con-

nectivity delivered in a single I/O slot, with up to a maxi-

mum of 40 ports per z890. Each port uses a single CHPID

and can be separately conﬁ gured. For a new z890 build,

you can choose any combination of OSA-Express fea-

tures: the new OSA-Express Gigabit Ethernet LX or SX, the

new OSA-Express 1000BASE-T Ethernet or OSA-Express

Token-Ring. The prior OSA-Express Gigabit LX and SX, the

OSA-Express Fast Ethernet, and the OSA-Express Token-

Ring can be carried forward on an upgrade from z890.

TCP/IP stack utilization improvement for OSA-Express

The OSA-Express features support 480 devices and 160

TCP/IP stacks (480 devices / 3 = 160 stacks). Now the

OSA-Express features will allow a single LPAR to contain

all 160 stacks. Previously, in order to use all 160 stacks,

the CHPID had to be shared by multiple LPARs as the

number of stacks per LPAR was limited to 84.

This improvement is exclusive to the z890 and z990,

requires the May 2004 level of Licensed Internal Code,

is supported by z/OS and z/VM, and applies to the OSA-

Express features when in QDIO mode: GbE, 1000BASE-T

Ethernet, Fast Ethernet and Token-Ring.

z890 OSA-Express 1000BASE-T Ethernet

The new OSA-Express 1000BASE-T Ethernet feature

replaces the current Fast Ethernet (10/100 Mbps) feature.

This new feature is capable of operating at 10,100 or 1000

Mbps (1 Gbps) using the same copper cabling infrastructure

as Fast Ethernet, making the transition to this higher speed

Ethernet feature a straightforward process. It is designed to

support Auto-negotiation, QDIO and non-QDIO environments

on each port allowing you to make the most of your TCP/IP and

SNA/APPN® and HPR environments at up to gigabit speeds.

When this adapter is operating at gigabit Ethernet speed

it runs full duplex only. It also can support standard (1492

byte) and jumbo (8992 byte) frames.

non-QDIO mode SNA Passthru TCP/IP Passthru HPDT MPC

10/100/1000 Mbps Ethernet (copper)

Switch/

Hub/

Router

Server

IP WAN Intranet

DLSw

Router

10/100 Mbps

Ethernet

Server

10/100 Mbps

Ethernet

DLSw Router

Remote Office

4/16 Mbps

Token-Ring

SNA DLSw TCP/IP Native SNA

10/100/1000

IP Router

Server

10/100/1000 Mbps

Ethernet (copper)

Mbps

Ethernet

Server

IP WAN Intranet

10/100 Mbps

Ethernet

QDIO Mode - TCP/IP

IBM ^ pSeries®,

IBM ^ xSeries®,

RS/6000

Netfinity

Switch/

Hub/

Router

10/100 Mbps

Ethernet

IP Router

Internet or

extranet

Remote Office

4/16 Mbps

Token-Ring

TCP/IP applications TN3270 browser access to SNA applications Enterprise Extender for SNA end points

The new Checksum ofﬂ oad support on the 1000BASE-T

Ethernet feature, when operating in QDIO mode at gigabit

speed, is designed to ofﬂ oad z/OS 1.5 and Linux TCP/IP

stack processing of Checksum packet headers for TCP/IP

and UDP.

OSA-Integrated Console Controller

The new Open Systems Adapter Integrated Console

Controller function (OSA-ICC) which is exclusive on the

IBM z890 and z990 servers since it is based on the OSA-

Express feature, supports the attachment of non-SNA 3270

terminals for operator console operations. Now, 3270 emu-

lation for console session connections is integrated as part

of the OSA-Express 1000BASE-T Ethernet feature of the

zSeries and can help eliminate the requirement for external

console controllers (2074, 3174) helping to reducing cost

and complexity. The OSA-ICC can use one or both ports

on an OSA-Express 1000BASE-T Ethernet feature with the

appropriate Licensed Internal Code (LIC). The OSA-ICC is

enabled using CHPID type OSC.

The OSA-ICC is designed to support up to 120 client con-

sole LAN attached sessions either locally or remotely.

Support for this new feature will be available for z/VM

Version 4 Release 4 with a PTF, z/OS 1.3, VSE/ESA 2.6

onwards and TPF.

Queued Direct Input/Output (QDIO)

The OSA-Express Gigabit Ethernet, 1000BASE-T Ethernet

and Token-Ring features support QDIO. QDIO was ﬁ rst

introduced to the world on the z900, in Communication

Server for OS/390 2.7.

Queued Direct Input/Output (QDIO), a highly efﬁ cient data

transfer architecture, allows an OSA-Express feature to

directly communicate with the server’s communications

program through the use of data queues in memory. QDIO

eliminates the use of channel programs and channel con-

trol words (CCWs), helping to reduce host interrupts and

accelerate TCP/IP packet transmission.

TCP/IP connectivity is increased with the capability to

allow up to a maximum of 160 IP stacks per OSA-Express

port and 480 devices. This support is applicable to all the

OSA-Express features available on the z890 and is pro-

vided through the Licensed Code (LIC).

Full Virtual Local Area Network (VLAN) support is available

on z890 in z/OS and z/OS.e 1.5 Communications Server

(CS) for the OSA-Express 1000BASE-T Ethernet, Fast

Ethernet and Gigabit Ethernet features when conﬁ gured

in QDIO mode. Full VLAN support in a Linux on zSeries

environment was delivered for QDIO mode in April 2002

for z800 and z900.

z890 OSA-Express Gigabit Ethernet

The new OSA-Express Gigabit Ethernet LX and Gigabit

Ethernet SX features introduced on the z990 replace the

z900/z800 Gigabit Ethernet features for new build z890.

The new OSA-Express GbE features have a new connector

type, LC Duplex, replacing the current SC Duplex connec-

tors used on the prior z900/z800 Gigabit Ethernet features.

Switch /

Router

Server

Gigabit

Ethernet

Gigabit Ethernet (fiber or copper)

Gigabit Ethernet

(fiber or copper)

Server

IP WAN Intranet

4/16/100 Mbps

Token-Ring

10/100 Mbps

Ethernet

QDIO Mode - TCP/IP

pSeries, RS/6000

xSeries, Netfinity

Server

IP Router

Internet or

extranet

z890 OSA-Express Token-Ring

The same OSA-Express Token-Ring feature is supported

on z890, z800, z990 and z900. This Token-Ring supports

a range of speed including 4, 16 and 100 Mbps, and can

operate in both QDIO and non-QDIO modes.

Note: Statement of Direction

OSA-Express Token-Ring not to be offered: The zSeries 890

and 990 are expected to be the last zSeries servers to offer

a Token-Ring feature. It is intended that the OSA-Express

Token-Ring feature will not be available for ordering on a

new build or upgraded server, or for carrying forward on

an upgrade. A migration from a Token-Ring to an Ethernet

environment should be a part of all strategic LAN planning.

TCP/IP applications TN3270 browser access to SNA appls. Enterprise Extender for SNA end points

4/16 Mbps

Token-Ring

IP Router

Server

Remote Office

10/100 Mbps

Ethernet

The new Checksum ofﬂ oad support on these z890 features

is designed to ofﬂ oad z/OS 1.5 and Linux TCP/IP stack pro-

cessing of Checksum packet headers for TCP, IP and UDP.

NON-QDIO operational mode

The OSA-Express 1000BASE-T Ethernet, Fast Ethernet and

Token-Ring also support the non-QDIO mode of operation.

The adapter can only be set (via the CHPID type parameter)

to one mode at a time. The non-QDIO mode does not pro-

vide the beneﬁ ts of QDIO. This support includes native SNA/

APPN, High Performance Routing, TCP/IP passthrough, and

HPDT MPC. The new OSA-Express 1000BASE-T Ethernet

provides support for TCP/IP and SNA/APPN/HPR up to 1

gigabit per second over the copper wiring infrastructure.

All statements regarding IBM’s plans, directions, and intent

are subject to change or withdrawal without notice.

non-QDIO mode SNA Passthru TCP/IP Passthru HPDT MPC

Switch/

Hub/

Router

Server

4/16 Mbps

Token-Ring

Server

DSLw

Router

IP WAN Intranet

10/100 Mbps

Ethernet

4/16 Mbps

Token-Ring

Switch/

Hub/

Router

16/100 Mbps

Token-Ring

Remote Office

4/16 Mbps

Token-Ring

SNA DLSw TCP/IP Native SNA

100 Mbps

Token-Ring

Backbone

4/16 Mbps

Token-Ring

Switch/

Hub/

Router

4/16/100 Mbps

Token-Ring

Backbone

IP WAN

Intranet

10/100 Mbps

Ethernet

QDIO Mode - TCP/IP

Server

100 Mbps

Token-Ring

4/16 Mbps

Token-Ring

Server

IP Router

Internet or

extranet

Remote Office

4/16 Mbps

Token-Ring

TN3270 browser access to SNA appls. Enterprise Extender for SNA end points TCP/IP applications

Note: OSA-Express 155 ATM and OSA-2 FDDI are no

longer supported. If ATM or FDDI support are still required,

a multiprotocol switch or router with the appropriate net-

work interface for example, 1000BASE-T Ethernet, GbE LX

or GbE SX can be used to provide connectivity between

the LAN and the ATM network or FDDI LAN.

Server to User connections

A key strength of OSA-Express and associated Com-

munications Server protocol support is the ability to

accommodate the customer’s attachment requirements,

spanning combinations of TCP/IP and SNA applications

and devices. Customers can use TCP/IP connections from

the remote site to either their TCP/IP or SNA applications

on zSeries and S/390 by conﬁ guring OSA-Express with

QDIO and using either direct TCP/IP access or appropriate

SNA to IP integration technologies, such as TN3270 Server

and Enterprise Extender for access to SNA applications.

Customers who require the use of native SNA-based con-

nections from the remote site can use a TCP/IP or SNA

transport to the data center and then connect into zSeries

and S/390 using appropriate SNA support on OSA-Express

features conﬁ gured in non-QDIO mode.

LPAR Support of OSA-Express

For z890 customers or customers who use the Processor

Resource/Systems Manager (PR/SM) capabilities of the z800,

z900 and the S/390 servers, IBM offers the Multiple Image

Facility (MIF), allowing the sharing of physical channels by

any number of LPARs. Since a port on an OSA-Express fea-

ture operates as a channel, sharing of an OSA-Express port

is done using MIF. The LPARs are deﬁ ned in the Hardware

Conﬁ guration Deﬁ nition (HCD). Depending upon the feature,

and how it is deﬁ ned, SNA/APPN/HPR and TCP/IP trafﬁ c can

ﬂ ow simultaneously through any given port.

IPv6 Support

IPv6 requires the use of an OSA-Express adapter running

in QDIO mode and is supported only on OSA-Express

features on zSeries at driver level 3G or above. IPv6 is

supported on OSA-Express for zSeries Fast Ethernet,

1000BASE-T Ethernet and Gigabit Ethernet when running

with Linux on zSeries, z/VM 5.1, and z/OS 1.4 and later.

Performance enhancements for virtual servers

Two important networking technology advancements are

announced in z/VM 4.4 and Linux on z990.

• The high performance adapter interrupt handling ﬁ rst

introduced with HiperSockets is now available for OSA-

Express/OSA-Express2 in QDIO mode (CHPID=OSD)

and FICON Express/FICON Express2 (CHPID=FCP).

This advancement provides a more efﬁ cient technique

for I/O interruptions designed to reduce path lengths

and overhead in both the host operating system and in

the adapter. This beneﬁ ts OSA-

Express TCP/IP support in

both Linux for zSeries and z/VM.

• z990/z890 support of virtual machine technology has

been enhanced to include a new performance assist

for virtualization of adapter interruptions. This new z890/

z990 performance assist is available to V=V guests

(pageable guests) that support QDIO on z/VM 4.4 and

later. The deployment of adapter interruptions improves

efﬁ ciency and performance by reducing z/VM Control

Program overhead.

OSA-Express2 large send for the z/OS environment –

preview

Previewing large send for TCP/IP trafﬁ c

z/OS Communications Server plans to exploit OSA-

Express2 large send (also referred to as TCP segmentation

HiperSockets

ofﬂ oad). Large send can improve performance by ofﬂ oad-

ing outbound TCP segmentation processing from the host

to OSA-Express2 by employing a more efﬁ cient memory

transfer into OSA-Express2. The z/OS Communications

Server support is planned for TCP/IP IPv4 trafﬁ c only and

z/OS and z/OS.e 1.7. In addition, a z/OS and z/OS.e 1.6

PTF is planned to be provided.

Large send support applies to the OSA-Express2 features

(Gigabit Ethernet SX and LX, 10 Gigabit Ethernet LR), sup-

ports QDIO mode only (CHPID type OSD), and is exclu-

sive to z990 and z890. Large send support was previously

announced for the Linux on zSeries environment.

HiperSockets, a feature unique to the zSeries, provides a

“TCP/IP network in the server” that allows high-speed any-

to-any connectivity among virtual servers (TCP/IP images)

and LPARs within a zSeries system without any physical

cabling. HiperSockets decreases network latency and

increases bandwidth between combinations of Linux, z/OS

and z/VM virtual servers. These OS images can be ﬁ rst

level (directly under an LPAR), or second level images

(virtual servers under z/VM).

With new support for up to 16 HiperSockets, the z890 and

z990 provides four times more HiperSockets, and up to

4,096 TCP/IP images (stack) connections, which is also

four times more capacity than the z800 and z900. The

increased HiperSockets capacity and expanded con-

nectivity provides additional ﬂ exibility in designing the

networking to accommodate consolidated and multiple

partitioned systems. HiperSockets can be divided among

Logical Channel SubSystems for separation between vari-

ous LPARs, while at the same time a single LPAR could

have access to all 16 HiperSockets if the HiperSockets all

are assigned to the same LCSS.

A HiperSockets channel also supports spanned channels

in order to communicate between LPARs connected to

different LCSSs. HiperSockets (IQD CHPID type) can be

conﬁ gured to Channel SubSystems and transparently

shared by any or all conﬁ gured LPARs without regard to

the LCSS to which the LPAR is conﬁ gured. This means

one HiperSockets could be common to all 30 z890 or

z990 LPARs. This support is exclusive to z890 and z990.

Different HiperSockets can be used for security (separa-

tion of trafﬁ c, no external wire-tapping, monitoring) and

performance and management reasons (separate sysplex

trafﬁ c Linux or non-sysplex LPAR trafﬁ c).

z/VM

LPAR 1

z/OS

LPAR

LCSS0 LCSS1

z/VM

LPAR

Linux

LPAR

LinuxLinux

LPAR

This support gives the user the ﬂ exibility to optimize and

tune each HiperSockets to the predominant trafﬁ c proﬁ le,

for example to distinguish between “high bandwidth”

workloads such as FTP versus lower bandwidth interactive

workloads.

MIF-1 MIF-2 MIF-F MIF-1 MIF-2 MIF-3 MIF-F

CHPID00CHPID

CHPID

PCHID

010B

PCHID

010D

010C

HiperSockets CHPID 03

CHPID

PCHID

020A

CHPID

SPAN

CHPID

PCHID

0245

HiperSockets CHPID 05

CHPID

PCHID

0246

CHPID

PCHID

0248

PCHID

0249

HiperSockets CHPID 04

HiperSockets does not use an external network, therefore,

it can free up system and network resources, helping to

reduce attachment cost while improving availability and

performance. HiperSockets can have signiﬁ cant value in

server consolidation, for example, by connecting multiple

Linux virtual servers under z/VM to z/OS LPARs within the

same z890. Furthermore, HiperSockets can be utilized by

TCP/IP in place of XCF for sysplex connectivity between

images which exist in the same server, thus z/OS TCP/IP

uses HiperSockets for connectivity between sysplex

images in the same server and uses XCF for connectiv-

ity between

images in different servers. Management and

administration cost reductions over existing conﬁ gurations

are possible.

HiperSockets acts like any other TCP/IP network interface,

so TCP/IP features like IP Security (IPSec) in Virtual Private

Networks (VPN) and Secure Sockets layer (SSL) can be

used to provide heightened security for ﬂ ows within the

same CHPID. HiperSockets supports multiple frame sizes,

which is conﬁ gured on a per HiperSockets CHPID basis.

The HiperSockets function provides many possibilities for

improved integration between workloads in different LPARs,

bound only by the combinations of operating systems and

their respective applications. HiperSockets is intended to

provide the fastest zSeries connection between e-business

and Enterprise Resource Planning (ERP) solutions sharing

information while running on the same server. WebSphere

http and Web Application Servers or Apache http servers

can be running in a Linux image (LPAR or z/VM guest) and

will be able to use HiperSockets for very fast TCP/IP trafﬁ c

transfer to a DB2 database server running in a z/OS LPAR.

System performance is optimized because this allows you to

keep your Web and transaction application environments in

close proximity to your data and helps eliminate any expo-

sure to network related outages, thus improving availability.

The z/OS HiperSockets Accelerator function can help

improve performance and cost efﬁ ciencies when attach-

ing a high number of TCP/IP images via HiperSockets to a

“front end” z/OS system for shared access to a set of OSA-

Express adapters.

HiperSockets VLAN support in a Linux environment: Virtual

Local Area Networks (VLANs), IEEE standard 802.1q, is now

being offered for HiperSockets in a Linux for zSeries environ-

ment. VLANs can help reduce overhead by allowing networks

to be organized for optimum trafﬁ c ﬂ ow; the network is orga-

nized by trafﬁ c patterns rather than physical location. This

enhancement permits trafﬁ c to ﬂ ow on a VLAN connection

between applications over HiperSockets and between appli-

cations on HiperSockets connecting to an OSA-Express Giga-

bit Ethernet, 1000BASE-T Ethernet, or Fast Ethernet feature.

Cryptography

HiperSockets broadcast support for IPv4 packets – Linux,

z/OS, z/VM: Internet Protocol Version 4 (IPv4) broadcast

packets are now supported over HiperSockets internal LANs.

TCP/IP applications that support IPv4 broadcast, such

as z/OS OMPROUTE when running Routing Information

Protocol Version 1 (RIPv1), can send and receive broad-

cast packets over HiperSockets interfaces. This support is

exclusive to z890 and z990. Broadcast for IPv4 packets is

supported by Linux for zSeries. Support is available in z/OS

1.5. Support is also offered in z/VM 4.4 and later.

HiperSockets Network Concentrator

HiperSockets Network Concentrator support, exclusive to

z890 and z990, can simplify network addressing between

HiperSockets and OSA-Express. You can now integrate

HiperSockets-connected operating systems into external

networks, without requiring intervening network routing

overhead, thus helping to increase performance and sim-

plify conﬁ guration. With the HiperSockets Network Con-

centrator support, you can conﬁ gure a special purpose

Linux operating system instance, which can transparently

bridge trafﬁ c between a HiperSockets internal LAN and an

external OSA-Express network attachment, similar to a real

Layer 2 switch which bridges between different network

segments. This support can

network address connection

nected to the external network.

make the internal HiperSockets

appear as if it were directly con-

In the on demand era, security will be a strong require-

ment. The zSeries products will continue to address secu-

rity with announcements and deliveries of products and

features.

The main focus in cryptography will continue to be very

high and scalable performance for SSL algorithms, sec-

ondly, to provide security-rich, symmetric performance for

ﬁ nancial and banking applications using PIN/POS type

encryption. As in the past zSeries will be designed to

deliver seamless integration of the cryptography facilities

through use of ICSF. Use of ICSF will enable applications

to be designed to work without change regardless of how

and where the cryptographic functions are implemented,

and also assure that the cryptography work to be load bal-

anced across the hardware resources. Finally we will be

focused on required certiﬁ cations and open standards.

The existing PCICA card feature will continue to be avail-

able on the z890 and z990 – for SSL acceleration / clear

key operations. To support the increased number of LPARs

available on z890 and z990, the conﬁ guration options

for the crypto PCICA adapter – introduced with the z900

– will be extended to allow sharing of a PCICA over the

whole range of LPARs with a max of 16 LPARs sharing one

PCICA adapter.

In addition to the PCICA, a new crypto adapter (PCIXCC)

is introduced as a functional replacement for the CMOS

Cryptographic Coprocessor and the PCI Cryptographic

Coprocessor. The PCIXCC adapter design introduces

a breakthrough concept which supports high security

demanding applications requiring a FIPS 140-2 level 4

tiﬁ ed crypto module, and also as an execution environment

for customer written programs and a high performance

for Public Key / SSL operations. The PCIXCC hardware

cer-

path

and microcode design will support almost all of the past

Cryptographic functions that were provided on the zSeries

800 and 900 via the CMOS Cryptographic Coprocessor

(CCF) and the PCI Cryptographic Coprocessor (PCICC).

At the system software level the SSL-related operations will

be directed to the PCICA adapter and the Secure Crypto

operations to the PCIXCC adapter.

a method for key identiﬁ cation, exchange, separation,

update, backup, and management. The TKE workstation

and 4.0 code level are designed to provide a security-rich,

remote, and ﬂ exible method of providing Master Key Entry

and to remotely manage PCIX Cryptographic Coprocessors.

zSeries Security Certiﬁ cation

The zSeries cryptography is further advanced with the

introduction of the Cryptographic Assist Architecture

implemented on every z890 and z990 processor (CPU).

With enhanced scalability and data rates the z890 and

z990 processor is designed to provide a set of symmetric

cryptographic functions, synchronously executed, which

enormously enhance the performance of the en/decrypt

function of SSL, VPN (Virtual-Private-Network) and data

storing applications which do not require FIPS 140-2 level

4 security. The on-processor crypto functions run at z890

or z990 processor speed, an order of magnitude faster

than the CMOS Crypto Coprocessor in the zSeries 800 or

900. As these crypto functions are implemented in each

and every CPU the afﬁ nity problem of pre-z990/z890 sys-

tems (which had only two CMOS Crypto Coprocessors) is

virtually eliminated. The Crypto Assist Architecture includes

DES and T-DES data en/decryption, MAC message authen-

tication and SHA-1 secure hashing; all of these functions

are directly available to application programs (zSeries

Architecture instructions) and so will help reduce program-

ming overhead. To conﬁ rm with US Export and Import

Regulations of other countries, an SE panel is provided for

proper enable/disable of ‘strong’ cryptographic functions.

Cryptography

• z890/z990 PCIXCC:

– Designed for FIPS 140-2 level 4 certiﬁ cation

• Logical Partitions

– z900 and z800 servers are the ﬁ rst and only to

receive Common Criteria certiﬁ cation at EAL5

• Operating Systems Common Criteria Certiﬁ cation

– SUSE LINUX on zSeries

– SUSE SLES 8 has been certiﬁ ed at Controlled

Access Protection Proﬁ le (CAPP) EAL3+

• z/OS 1.6

– z/OS 1.6 is under evaluation for Controlled Access

Protection Proﬁ le (CAPP) EAL3+ and Labeled Security Protection Proﬁ le (LSPP) EAL3+

• z/VM

– IBM has applied for Common Criteria Controlled

(ISO/IEC 15408) certiﬁ cation of z/VM V5.1 with the

RACF

for z/VM optional feature against the Con trolled Access Protection Proﬁ le (CAPP) and the Labeled Security Protection Proﬁ le (LSPP), both at the EAL3+ assurance level

The Trusted Key Entry (TKE) 4.1 code level workstation

is an optional feature that can provide a basic key man-

agement system and Operational Key Entry support. The

key management system allows an authorized person

A third generation Cryptographic feature – Crypto Express2

Crypto Express2 features support for on demand business

in a security-rich environment.

Crypto Express2 provides the functions of PCICA and

PCIXCC in a single feature that is expected to provide

improved secure key and system throughput. Like its prede-

cessors, the Crypto Express2 feature has been designed to

satisfy the security requirements of an enterprise server.

The Integrated Cryptographic Service Facility (ICSF),

a component of z/OS, is designed to transparently use

the available cryptographic functions, the CP Assist for

Cryptographic Function (CPACF) as well as the PCICA,

PCIXCC, and Crypto Express2 features to balance the

workload and satisfy the requirements of the applications.

The Crypto Express2 feature is designed for Federal Infor-

mation Processing Standard (FIPS) 140-2 Level 4 Certiﬁ ca-

tion and has two coprocessors per feature for improved

system throughput. A performance beneﬁ t is expected

with multitasking applications. A performance beneﬁ t may

not be realized with single-threaded applications, which

can utilize only one of the two coprocessors.

The Crypto Express2 feature supports the following:

• Consolidation and simpliﬁ cation via a single crypto coprocessor feature on z890 and z990

• Compute-intensive public key cryptographic functions designed to help reduce CP utilization and increase system throughput

• Card Validation Value (CVV) generation and veriﬁ cation services for 19-digit Personal Account Number (PANs)

• Enabling use of less than 512-bit keys for clear key RSA operations

• 2048-bit key RSA management capability

• Functions previously supported by the PCICA and PCIXCC features offered on z890 and z990 including: – Compute-intensive public key cryptographic func-

tions to help reduce CP usage and increase system throughput

– Hardware acceleration for Secure Sockets Layer (SSL)

and Transport Layer Security (TLS) protocols to help support security-rich on demand business applications and transactions

– SSL performance equivalent to the PCICA feature

– The functional enhancements announced in April

2004, namely: PKE MRP support, PKD zero pad support, TDES DUKPT, and EMV2000

User Deﬁ ned Extension (UDX) Service Offering – pro-

–

grammable to deploy standard functions and algorithms

• Up to a maximum of eight features per server

– The combined maximum number of Crypto Express2,

PCICA, and PCIXCC features on a z890 and z990 cannot exceed eight features per server

– The z890 and z990 can support up to eight Crypto

Express2 features (16 coprocessors)

– The z890 and z990 can support up to six PCICA

features (12 accelerators)

– The z890 and z990 can support up to four PCIXCC

features (four coprocessors)

– With Crypto Express2, both the z890 and z990 can

have up to sixteen secure key coprocessors in comparison to the four coprocessors with the PCIXCC features. This is expected to translate into increased secure key and system throughput.

– With Crypto Express2, both the z890 and z990 servers

can utilize up to sixteen cryptographic coprocessors for clear key SSL acceleration in comparison to twelve accelerators with the PCICA features. The number of SSL handshakes per second in a 16 CP z990 is expected to remain at over 11,000 when running the z/OS operating system*.

– A mixture of both secure and clear key applications

can run on the same Crypto Express2 feature

– Based on the increased throughput, the ability to con-

solidate both secure key and clear key crypto workloads and I/O slots on the same feature

* The SSL rate was achieved with a z990 with 16 proces-

sors and 6 PCICA features (12 accelerator cards). These

measurements are examples of the maximum transactions/

second achieved in a lab environment with no other pro-

cessing occurring and do not represent actual ﬁ eld mea-

surements. Details available upon request.

All logical partitions (LPARs) in all Logical Channel Sub-

Systems (LCSSs) have access to the Crypto Express2

feature, up to 30 LPARs per feature.

Enabling use of less than 512-bit keys for clear key RSA

operations

The Crypto Express2 and PCIXCC features will now sup-

port applications that require clear key RSA operations

using keys less than 512-bits, including ICSF Callable

services and their corresponding verbs: Digital Signature

Verify (CSNDDSV), Public Key Encrypt (CSNDPKE), and

Public Key Decrypt (CSNDPKD). All other ICSF Callable

services that require a Crypto Express2 or PCIXCC feature

continue to require keys of more than 511-bits.

Enabling the lower limit for clear key RSA operations may

allow the migration of some additional cryptographic appli-

cations to z890 and z990 servers without requiring the

applications to be rewritten.

The Crypto Express2 feature is exclusive to z890 and

z990, requires the October 2004 level of Licensed Internal

Code, and is supported by z/OS, z/OS.e, z/VM, VSE/ESA,

and Linux on zSeries. z/VM, VSE/ESA and Linux on zSeries

offer support for clear key SSL transactions only.

Cryptographic support for 19-digit PANs

Crypto Express2 and PCIXCC now offer CVV generation

and veriﬁ cation services for 19-digit PANs. Industry prac-

tices for use of Card Validation Value (CVV) are moving to

base CVV computations on a 19-digit PAN instead of the

13-digit and 16-digit PANs currently in use and supported

by ICSF and the PCIXCC feature. ICSF, Crypto Express2,

and PCIXCC now support use of the 19-digit PAN in the

CVV generation and veriﬁ cation services (CSNBCSG and

CSNBCSV, respectively).

Support of CVV generation and veriﬁ cation services for

19-digit PANs, an anti-fraud security feature, is supported

by the Crypto Express2 and PCIXCC features on the z890

and z990 and by z/OS and z/OS.e.

Support of applications that require clear key RSA operations

using keys less than 512-bits applies to the Crypto Express2

and PCIXCC features, is exclusive to z890 and z990, and is

supported by z/OS, z/OS.e, and z/VM. Refer to the Hardware

and Software requirements sections for more information.

2048-bit key RSA management for PCICC on z800, z900

2048-bit key (clear and secure) RSA management capabil-

ity for z800 and z900 servers, in support of new Automated

Teller Machine (ATM) standards, will be available via the

2048-bit key RSA management for PCICC (#0867) feature.

1024-bit key RSA management is available today via a

Functional Control Vector (FCV) on the PCI Cryptographic

Coprocessor (PCICC) Enablement diskette (#0865). This

capability is unique to PCICC and does not apply to the

CMOS Cryptographic Coprocessor Facility (CCF).

The 2048-bit functional control vector (FCV) will support

four ICSF services: Public Key Decrypt (PKD), Symmetric

Key Import (SYI), Symmetric Key Export (SYX) and Sym-

metric Key Generate (SYG). Applications that require 2048-

bit key RSA management will be able to migrate with ease.

2048-bit key RSA management support for the PCICC fea-

tures on z800 and z900 is transparent to the hardware and

is supported by z/OS, z/OS.e, z/VM, and Linux on zSeries.

z/VM and Linux on zSeries offer support for clear key oper-

ations only. Refer to the Software requirements section for

further information. This is an integrated capability on the

Crypto Express2 and PCIXCC features on z890 and z990.

There is no unique feature.

TKE 4.2 and Smart Card Reader Support

The Trusted Key Entry (TKE) capability is an optional

feature of zSeries that provides a basic security key man-

agement system. The key management system provides

authorized persons a method of security key identiﬁ cation,

exchange, separation, update, and management. TKE 4.2

with optional smart card reader allows access to and use

of conﬁ dential data on the smart card protected by a user

deﬁ ned personal identiﬁ cation number (PIN) code provid-

ing storage, access, transport and entry of master and

operational key parts into the TKE workstation in a secu-

rity-rich environment.

For example, the smart card is able to store one or more

4758 PCI Cryptographic Coprocessor master key parts.

The parts are stored in the “clear” on the smart card. The

master key parts are generated by the 4758 PCI Crypto-

graphic Coprocessor card within the TKE workstation and

are transferred to the smart card for storage and later read

back to the 4758 PCI Cryptographic Coprocessor card

for processing. The master key parts are encrypted, for

added security, during transport between the smart card

and the 4758 PCI Cryptographic Coprocessor card.

The TKE 4.2 Smart Card Reader supports all of the mech-

anisms available in the current TKE LIC. That is, with the

smart card support, it is still possible to store key parts on

diskettes, paper, or to use a TKE authority key stored on a

diskette, and to logon to the 4758 using a pass phrase.

The optional features associated with the TKE 4.2 Smart

Card Reader support are:

• TKE 4.2 code

• TKE 4.2 Smart Card Reader

• TKE 4.2 additional Smart Cards

Support for an optional Smart Card Reader attached to

the TKE 4.2 workstation allows access to and use of conﬁ -

dential data on the smart card protected by a user deﬁ ned

personal identiﬁ cation number (PIN) code providing

secure storage, access, transport and entry of master and

operational key parts into the TKE workstation.

TKE 4.2 with Smart Card Reader and smart card has four

major functions:

• Storing ICSF key parts, speciﬁ cally, master and operational key parts

• Storing 4758 PCI Cryptographic Coprocessor master key parts

• Generating, storing, and using a TKE authority signature key pair

• Generating, storing, and using a 4758 logon key pair

The optional Smart Card Reader, which can be attached to

a TKE workstation is available on the S/390 G6 servers as

well as zSeries z800, z900, z890 and z990.

TKE 4.2 code

The TKE 4.2 code is designed to provide a security-rich

local and remote method to enter operational and master

keys. The TKE 4.2 code also includes support for the

Smart Card Reader and provides support for crypto-

graphic hardware features available with S/390 G6 and

the zSeries 800, z900, z890 and z990 servers. Currently

installed TKE workstations can be upgraded to the TKE

4.2 code.

Availability

z890 Capacity Upgrade on Demand (CUoD)

Capacity Upgrade on Demand allows for the nondisruptive

addition of additional Central Processor (CP) Capacity,

Internal Coupling Facilities (ICFs), Integrated Facility for

Linux (IFLs) and/or IBM ^ zSeries Application

Assist Processor (zAAP). Capacity Upgrade on Demand

can quickly add processors up to the maximum number

of available inactive engines. This provides customers

with the capacity for much needed dynamic growth in an

unpredictable e-business world. The Capacity Upgrade

on Demand function, combined with Parallel Sysplex tech-

nology, can enable virtually unlimited capacity upgrade

capability.

The CUoD functions are:

• Nondisruptive CP, ICF, IFL, and zAAP upgrades within minutes

• Dynamic upgrade of all I/O cards in the I/O Cage

• Dynamic upgrade of spare installed memory (24 - 32 GB only)

• Plan Ahead and Concurrent Conditioning

Plan Ahead and Concurrent Conditioning

Concurrent Conditioning conﬁ gures a system for hot

plugging of I/O based on a future speciﬁ ed target con-

ﬁ guration. Concurrent Conditioning of the zSeries I/O is

minimized by the fact that all I/O cards plugging into the

zSeries I/O cage are hot pluggable. This means that the

only I/O to be conditioned is the I/O cage itself. The ques-

tion of whether or not to concurrently condition a cage is

a very important consideration, especially with the rapid

change in the IT environment (e-business) as well as the

technology. Migration to FICON Express/FICON Express2

or additional OSA-Express/OSA-Express2 networking is

exceptionally easy and nondisruptive with the appropriate

microcode load and if the cage space is available.

The z890 supports concurrent memory upgrade. This capa-

bility will allow a processor’s memory to be increased without

disrupting the processor operation. To take advantage of this

capability, a customer should not plan processor storage

on the 8 or 16 GB increments. A customer with a Model A04

with 24 GB of storage will be able to concurrently upgrade

to 32 GB as there is spare memory capacity on the card.

However, for a customer with 8 or 16 GB of memory installed

getting to the next increment would be disruptive.

The Plan Ahead process can easily identify the customer

conﬁ guration that is required to meet future needs. The

result of concurrent conditioning is a ﬂ exible IT infrastruc-

ture that can accommodate unpredictable growth in a low

risk, nondisruptive way. Depending on the required Con-

current Conditioning, there should be minimal cost associ-

ated with dormant z890 capacity. This creates an attractive

option for businesses to quickly respond to changing

environments, bringing new applications online or growing

existing applications without disrupting users.

z890 Server Capacity BackUp (CBU)

Capacity BackUp (CBU) is offered with the z890 servers

to provide reserved emergency backup CPU capacity for

situations where customers have lost capacity in another

part of their establishment and want to recover by adding

reserved capacity on a designated z890 server. A CBU

system normally operates with a “base” CP conﬁ guration

and with a preconﬁ gured number of additional Processor

Units (PUs) reserved for activation in case of an emergency

The z890 technology is suited for providing capacity backup.

The reserved CBU processing units are on the same technol-

ogy building block, the MCM, as the regular CPs.

The “base” CBU conﬁ guration must have sufﬁ cient

memory and channels to accommodate the potential

needs of the larger CBU target machine. When capacity is

needed in an emergency, the primary operation performed

is activating the emergency CBU conﬁ guration with the

reserved PUs added into the conﬁ guration as CPs.

Customers who have an active Remote Support Facility

connection can perform a CBU upgrade automatically and

within a matter of minutes, right from their CBU machine’s

Hardware Management Console. For more information

on how a CBU upgrade can be activated automatically,

please refer to the

found on IBM Resource Link.

The z890 supports concurrent CBU downgrade. This func-

tion enables a Capacity BackUp server to be returned to

its normal conﬁ guration without an outage (i.e. PowerOn

Reset).

z890 Capacity Backup Users Guide

Automatic Enablement of CBU for GDPS

The intent of GDPS support for CBU is to enable auto-

matic management of the reserved PUs provided by the

CBU feature in the event of a processor failure and/or a

site failure. Upon detection of a processor failure or site

failure, GDPS will activate CBU to dynamically add PUs

to the processors in the takeover site to acquire process-

ing power required to restart mission-critical production

workloads. GDPS-CBU management helps to minimize

manual customer intervention and the potential for errors,

thereby reducing the outage time for critical workloads

from hours to minutes. Similarly, GDPS-CBU management

can also automate the process of dynamically returning

the reserved CPs when the temporary period has expired.

z890 Customer Initiated Upgrade (CIU)

Customer Initiated Upgrade (CIU) is the capability to initi-

ate a processor and/or memory upgrade when spare PUs

installed unused memory are available via the Web using

IBM Resource Link. Customers will be able to download

and apply the upgrade using functions on the Hardware

Management Console via the Remote Support Facility.

This unique and important function for zSeries gives the

customer greater control and ability in adding capacity to

the system to meet resource requirements for unpredictable

e-business workloads and for applications which are dif-

ﬁ cult to size. CIU is a low-risk, well tested-and-tried facility

for ordering capacity on demand.

On/Off CoD Testing

On/Off CoD has been enhanced to allow for a test at

no charge for temporary IBM hardware capacity, IBM

software, or IBM maintenance. This test can be used to

validate the processes to download, activate, and deac-

tivate On/Off CoD capacity nondisruptively. One free test

per serial number can have a maximum duration of 24

hours commencing with the download and activation of an

On/Off CoD order. This test can also be used as a train-

ing session for personnel who are authorized to activate

On/Off CoD. IBM continues to enhance On/Off CoD to help

enable customers to become more adaptive to their on

demand business requirements.

Order Staging for CIU-Express and On/Off CoD

All CIU-Express and On/Off CoD orders may now be

staged for greater than 30 days. In fact, the orders may be

staged for an extended period of time, unless one of the

following conditions occurs:

• Order is canceled by customer

• Machine is no longer under warranty or IBM Maintenance Service Agreement

• Permanent PU and/or memory conﬁ gurations is changed outside of CIU process

Advanced Availability Functions

Transparent Sparing

z890 offers a 5 PU MCM in the case of processor failure. If

there is a spare PU available it will be used for transparent

sparing. Note this can only be achieved on 1-way, 2-way

and 3-way models.

Enhanced Dynamic Memory Sparing

The z890 has enhanced this robust recovery design with

16 times more chips available for sparing. This will virtually

eliminate the need to replace a memory card due to DRAM

failure.

Enhanced Storage Protect Keys: z890 has enhanced the

memory storage protect key design by adding a third key

array to each memory card. The arrays are parity checked

and employ a Triple Voting strategy to assure accuracy.

This will reduce the need for memory card replacement

due to key array failure.

ESCON Port Sparing: The ESCON 16-port I/O card is

delivered with one unused port dedicated for sparing in

the event of a port failure on that card. Other unused ports

are available for nondisruptive growth of ESCON channels.

• Cryptographic Cards: The PCIXCC and PCICA cards

plug in the I/O cage and can be added or replaced

concurrently with system operation.

• Redundant Cage Controllers: The Power and Service

Control Network features redundant Cage Controllers for

Logic and Power control. This design enables nondis-

ruptive service to the controllers and virtually eliminates

customer scheduled outage.

• Auto-Switchover for Service Element: The z890 has two

Service Elements. In the event of failure on the Primary

SE, the switchover to the backup is handled automati-

cally. There is no need for any intervention by the cus-

tomer or Service Representative.

Concurrent Capacity BackUp Downgrade (CBU Undo)

This function allows the customer to downgrade the disas-

ter backup machine to its normal conﬁ guration without

requiring the PowerOn Reset (POR).

Fault Tolerant Interconnect Design: The memory design of

the z890 provides a fault tolerant dual interconnect fabric.

The z890 is designed to prevent a single failure within the

fabric from disrupting full memory access.

Concurrent Maintenance

• Concurrent Service for I/O Cards: All the cards which

plug into the new I/O Cage are able to be added and

replaced concurrent with system operation. This virtually

eliminates any need to schedule outage to service or

upgrade the I/O subsystem on this cage.

• Upgrade for Coupling Links: z890 has concurrent main-

tenance for the ISC-3 adapter card. Also, Coupling links

can be added concurrently. This virtually eliminates a

need for scheduled downtime in the demanding sysplex

environment.

Concurrent Capacity Upgrade: A z890 can be upgraded

via the concurrent addition of additional Processor Units

(PUs) and I/O and limited memory upgrades (24 Gb to 32

Gb increment) with no disruption to current operations.

However, while capacity upgrades to the processor itself

are concurrent, your software may not be able to take

advantage of the increased capacity without performing

an Initial Programming Load (IPL).

Parallel Sysplex Cluster Technology

Sparing for Storage Protect Keys: The robust conﬁ guration

of the Storage Protect Keys has been enhanced with chip

sparing. Already a triple-array with parity protection and

voting, the Key structure for z890 has added sparing, simi-

lar to Main Memory chip sparing, to further enhance the

availability of this critical function.

Failure Containment for the Memory Bus Adapter (MBA):

Memory Bus Adapters are designed to provide the critical

link between the z890 Processor Units and the I/O subsys-

tem. The Model A04 has two MBAs. In the unlikely event of

a catastrophic failure of an MBA chip, the z890 is designed

to isolate the failure of that chip such that the remaining

MBA chips continue to operate. This helps minimize the

impact of a failure and allows for scheduling maintenance.

Enhanced Firmware Simulation: The z890 process for

design, development, and test of Licensed Internal Code

(LIC) has been signiﬁ cantly enhanced with the use of

simulation to improve quality and early availability. Virtu-

ally every action/reaction of the code can be tested with

the simulated hardware/code of the rest of the server. The

result is to discover and correct design errors much earlier

in the process.

These new features, together with legacy features such

as high levels of recovery, concurrent processor upgrade,

concurrent memory upgrade, concurrent I/O upgrade, and

concurrent maintenance for hardware and LIC give the

z890 a very impressive RAS structure.

Parallel Sysplex clustering was designed to bring the

power of parallel processing to business-critical zSeries

and S/390 applications. A Parallel Sysplex cluster consists

of up to 32 z/OS and/or OS/390 images coupled to one or

more Coupling Facilities (CFs or ICFs) using high-speed

specialized links for communication. The Coupling Facili-

ties, at the heart of the Parallel Sysplex cluster, enable

high speed, read/write data sharing and resource sharing

among all the z/OS and OS/390 images in a cluster. All

images are also connected to a Sysplex Timer

time synchronization.

to address

Parallel Sysplex Resource Sharing enables multiple

system resources to be managed as a single logical

resource shared among all of the images. Some examples

of resource sharing include JES2 Checkpoint, GRS “star,”

and Enhanced Catalog Sharing; all of which provide sim-

pliﬁ ed systems management, increased performance

and/or scalability. For more detail, please see

of Resource Sharing White Paper

Parallel Sysplex home page at ibm.com/servers/eserver/

zseries/pso.

– GF22-5115 on the

S/390 Value

Although there is a signiﬁ cant value in a single footprint

and multi-footprint environment with resource sharing,

those customers looking for high availability must move

on to a database data sharing conﬁ guration. With the

Parallel Sysplex environment, combined with the Workload

Manager and CICS TS or IMS TM, incoming work can

be dynamically routed to the z/OS image most capable

of handling the work. This dynamic workload balancing,

along with the capability to have read/write access data

from anywhere in the Parallel Sysplex cluster, provides the

scalability and availability that businesses demand today.

When conﬁ gured properly, a Parallel Sysplex cluster has

no single point of failure and can provide customers with

near continuous application availability over planned and

unplanned outages. For detailed information on IBM’s

Parallel Sysplex technology, visit our Parallel Sysplex home

page at ibm.com/servers/eserver/zseries/pso.

Coupling Facility Conﬁ guration Alternatives

IBM offers different options for conﬁ guring a functioning

Coupling Facility:

• Standalone Coupling Facility: z900 Model 100 and z800 Model 0CF servers provide a physically isolated, totally independent CF environment. Like the z990, there is no unique standalone coupling facility model offered with the z890. Customers can achieve the same physically

isolated environment as on prior mainframe families by ordering a z890 or z990 with PUs characterized as ICFs and general purpose PUs. There are no software charges associated with such conﬁ guration. An ICF or CF partition sharing a server with any operating system images not in the sysplex acts like a logical standalone CF.

• Internal Coupling Facility (ICF): Customers considering clustering technology can get started with Parallel Sysplex technology at a lower cost by using an ICF instead of purchasing a standalone Coupling Facility.

An ICF feature is a processor that can only run Coupling Facility Control Code (CFCC) in a partition. Since CF LPARs on ICFs are restricted to running only CFCC, there are no IBM software charges associated with ICFs. ICFs are ideal for Intelligent Resource Director and resource sharing environments as well as for data sharing environments where System-Managed CF Structure Duplexing is exploited.

• Coupling Facility partition on a zSeries server using standard LPAR: A CF can be conﬁ gured to run in either a dedicated or shared CP partition. IBM software charges apply. This may be a good alternative for test conﬁ gurations that require very little CF processing resource or for providing hot-standby CF backup using the Dynamic Coupling Facility Dispatching function.

A Coupling Facility can be conﬁ gured to take advantage of

a combination of different Parallel Sysplex capabilities:

• Dynamic CF Dispatch: Prior to the availability of the Dynamic CF Dispatch algorithm, shared CF partitions could only use the “active wait” algorithm. With active wait, a CF partition uses all of its allotted time-slice, whether it has any requests to service or not. The optional Dynamic CF Dispatch algorithm puts a CF partition to “sleep” when there are no requests to service and the longer there are no requests, the longer the partition sleeps. Although less responsive than the active wait algorithm, Dynamic CF Dispatch will conserve CP or ICF resources when a CF partition has no work to process and will make the resources available to other partitions sharing the resource. Dynamic CF Dispatch can be used for test CFs and also for creating a hot-standby partition to back up an active CF.

• Dynamic ICF Expansion: Dynamic ICF expansion provides value by providing extra CF capacity when there are unexpected peaks in the workload or in case of loss of CF capacity in the cluster.

– ICF Expansion into shared CPs. A CF partition running

with dedicated ICFs needing processing capacity beyond what is available with the dedicated CP ICFs, can “grow” into the shared pool of application CPs being used to execute zSeries applications on the same server.

– ICF Expansion into shared ICFs. A CF partition run-

ning with dedicated ICFs can “grow” into the shared pool of ICFs in case the dedicated ICF capacity is not sufﬁ cient. The resulting partition, an “L-shaped” LPAR, will be composed of both shared ICF and dedicated ICF processors, enabling more efﬁ cient utilization of ICF resources across the various CF LPARs.

System-Managed CF Structure Duplexing

System-Managed Coupling Facility (CF) Structure Duplex-

ing provides a general purpose, hardware-assisted, easy-

to-exploit mechanism for duplexing CF structure data. This

provides a robust recovery mechanism for failures such as

loss of a single structure or CF or loss of connectivity to a

single CF, through rapid failover to the backup instance of

the duplexed structure pair.

• Reliability

A common framework provides less effort on behalf of the exploiters, resulting in more reliable subsystem code.

• Cost Beneﬁ ts

Facilitates the use of non-standalone CFs (e.g. ICFs) for

data sharing environments in addition to resource sharing environments.

• Flexibility

The diagram below represents creation of a duplexed

copy of the structure within a System-Managed CF Duplexing Conﬁ guration server using standard LPAR. A CF can be conﬁ gured to run in either a dedicated or shared CP partition. IBM software charges apply. This may be a good alternative for test conﬁ gurations that require very little CF processing resource or for providing hot-standby CF backup

Facility Dispatching function.

using the Dynamic Coupling

ICF z/OSz/OS ICF

Beneﬁ ts of System-Managed CF Structure Duplexing

include:

• Availability

Faster recovery of structures by having the data already

there in the second CF dramatically reducing the time and processing required for structure rebuilds. SystemManaged Duplexing also provides basic recovery for many structures that have no simple means to recover data for failed structures, failed CFs, and losses of CF connectivity.

• Manageability and Usability

A consistent procedure to duplexing does not “set

up” structures and manage structures across multiple exploiters.

z800/z890/z900/z990/G5/G6

A robust failure recovery capability

z800/z890/z900/z990/G5/G6

Note: An example of two systems in a Parallel Sysplex with

CF Duplexing

Customers who are interested in testing and/or deploying

System-Managed CF Structure Duplexing in their sysplex,

please review GM13-0103,

ture Duplexing

at ibm.com/server/eserver/zseries/pso

System-Managed CF Struc-

or ibm.com/server/eserver/zseries/library/techpapers/

gm130103.html to understand the performance and other

considerations of using this feature.

Parallel Sysplex Coupling Connectivity

CPC CPC

D W D M

Route A

Route B

ETR

CLO

9037

1 ETR link

per CPC

hut with

amplifiers

1ETR

link per

CPC

1ETR link per

CPC

2CLO

links

40 km max 40 km nom

up to

100 km

Site 1 Site 2

Note: Midspan 9037 can also be located within 40 km of site 2 or on Route B.

All ETR and CLO links are provisioned as 1 channel per wavelength.

The Coupling Facilities communicate with z/OS images

in the Parallel Sysplex environment over specialized

high-speed links. For availability purposes, it is recom-

mended that there be at least two links connecting each

z/OS image to each CF in a Parallel Sysplex cluster. As

processor performance increases, it is important to also

use faster links so that link performance does not become

constrained. The performance, availability and distance

requirements of a Parallel Sysplex environment are the key

factors that will identify the appropriate connectivity option

for a given conﬁ guration.

Parallel Sysplex Coupling Links on the zSeries have been

enhanced with the introduction of Peer Mode. When con-

necting between zSeries servers, the links can be conﬁ g-

ured to operate in Peer Mode. This allows for higher data

transfer rates to and from the Coupling Facilities. In Peer

Mode, the ﬁ ber optic single mode coupling link (ISC-3)

provides 200 Gbps capacity, up to 12 km, 100 Gbps up

to 20 km, the ICB-3 link with 1 GB/s peak capacity, the

ICB-4 supported on z890s and z990s connection at 2.0

GBps, and the IC-3 link with 3.5 GBps capacity. Additional

Peer Mode beneﬁ ts are obtained by enabling the link to

be MIFed between z/OS (or OS/390) and CF LPARs. The

peer link acts simultaneously as both a CF Sender and

CF Receiver link, reducing the number of links required.

Larger and more data buffers and improved protocols

also improve long distance performance. For connectiv-

ity to 9672s, zSeries ISC-3 CF links can be conﬁ gured to

run in Compatibility Mode with the same characteristics

as links on the 9672 of 100 Gbps. The ICB coupling link

speeds described above are theoretical maximums. Note:

The z890 does not support ICB-2 links for connectivity to

9672s. ISC-3 links in compatibility mode must be used.

GDPS/PPRC Cross Site Parallel Sysplex distance Extended to

100 km

When using a Dense Wave Division Multiplexer (DWDM),

it will be possible via an RPQ to conﬁ gure GDPS/PPRC or

a multi-site Parallel Sysplex with up to 100 km between

the two sites. The immediate advantage of this extended

distance is to potentially decrease the risk that the same

disaster will affect both sites, thus providing the ability

for customers to recover their production applications at

another site. Support for the External Timer Reference

(ETR) links and the Inter System Channel (ISC-3) links

has been increased from the current capability of 50 km

to an extended capability of up to 100 km. The extended

distance support for ETR and ISC-3 links is now consis-

tent with other cross site technologies that already sup-

port 100 km (such as FICON, Peer-to-Peer Remote Copy

(PPRC), and Peer-to-Peer Virtual Tape Server (PtP VTS)).

It should be noted that the maximum distance between a

pair of 9037 Sysplex Timers in an Expanded Availability

conﬁ guration remains at 40 km. Therefore, to achieve the

extended distance of 100 km between the two sites, one of

the options to be considered is locating one of the Sysplex

Timers in an intermediary site that is less than 40 km

from one of the two sites (as can be seen in the diagram

below). Other potential options can be evaluated when the

RPQ is ordered.

Connectivity

Options

G5/G6 ISC

z800/z900 ISC-3

z890/z990 ISC-3

G5/G6 ICB n/a n/a n/a

z900 ICB-2 n/a n/a n/a

z990 ICB-2 n/a n/a n/a

z900 ICB-3 n/a

z890/z990 ICB-3 n/a

z890/z990 ICB-4 n/a n/a

z890 ISC-3 z890 ICB-3 z890 ICB-4

1 Gbps

Compatibility

2 Gbps

Peer Mode

2 Gbps

Peer Mode

n/a n/a

1 GBps

Peer Mode

1 GBps Peer Mode

Recommendation

use ICB-4s

n/a

2 GBps

Peer Mode

z890 and z990 Theoretical Maximum Coupling Link Speed

• ISC-3. InterSystem Coupling Facility-3 channels provide the connectivity required for resource or data sharing between the Coupling Facility and the systems directly attached to it.

• ISC-3 channels are point-to-point connections that require a unique channel deﬁ nition at each end of the channel. ISC-3 channels operating in Peer Mode provide connection between zSeries (z800/z890/z900/z990) general purpose models and zSeries Coupling Facilities. ISC-3 channels operating in Compatibility Mode provide connection between zSeries and HiPerLink (ISC-2) channels on 9672 G5 and G6 and the 9674 R06 Models. A four port ISC-3 card structure is provided on the z890 processors. It consists of a mother card with two daughter cards which have 2 ports each. Each daughter card is capable of operation at 1 Gbps in Compatibility Mode or 2 Gbps in peer mode up to a distance of 10 km. From 10 to 20 km, an RPQ card which comes in 2 port increments is available which runs at 1 Gbps in both Peer and Compatibility Modes. The mode is selected for each port via CHPID type in the IOCDS. The ports

are activated in one port increments. The z890 supports a maximum of 48 links (12 features, 4 links per feature). Note: A maximum of 32 ISC-3s can be deﬁ ned in Compatibility Mode.

• ISC-2. HiPerLinks. HiPerLinks, based on single-mode CF links, are available on 9672s (G3 - G6) and 9674s only. ISC-3s replace HiPerLinks on zSeries 800, 900, 890 and 990 models.

• ICB-2. The Integrated Cluster Bus-2 is used to provide high-speed coupling communication between a zSeries server or CF and a 9672 G5/G6 server or CF over short distances (~7 meters). For longer distances, ISC links must be used. The z990 features the STI-2 card which resides in an I/O cage and provides 2 ICB-2 ports each capable of up to 333 MBps. The ports are activated in one port increments. Up to 4 STI-2 cards, 8 ICB-2 links are available on the z990. ICB-2 is not offered on the z890.

• ICB-3. The Integrated Cluster Bus-3 is used to provide high-speed coupling communication between a z990 server or CF and a z800/z900 server or CF or between two z800/z900s over short distances (~7 meters). For longer distances, ISC-3 links must be used. The z890/ z990 features the STI-3 card which resides in an I/O cage and provides 2 ICB-3 ports each capable of up to 1 GBps. The ports are activated in one port increments. Up to 8 STI-3 cards, 16 ICB-3 links are available on the z890. ICB-3 links operate in “peer mode.”

• ICB-4. The Integrated Coupling Bus-4 is a “native” coupling connection available for connecting a z890/z990 server or CF to another z890/ z990 server or CF over short distances. Capable of up to 2.0 GBps, the ICB-4 is the fast external coupling connection available for the z890/z990. The ICB-4 connection consists of one link that directly attaches to an STI port on the system and does not require connectivity to a card in the I/O cage. One feature is required for each end of the link. Up to 8 ICB-4 features can be conﬁ gured on a z890.

•

IC. The Internal Coupling channel emulates the Coupling

links providing connectivity between images within a single server. No hardware is required, however a minimum of 2 CHPID numbers must be deﬁ ned in the IOCDS. IC links provide the fastest Parallel Sysplex connectivity. The z890 supports up to a maximum of 32 ICs.

IRD has three major functions: LPAR CPU Management,

Dynamic Channel Path Management, and Channel Sub-

system Priority Queuing.

zSeries IRD Scope

Intelligent Resource Director

Exclusive to IBM’s z/Architecture is Intelligent Resource

Director (IRD), a function that optimizes processor and

channel resource utilization across Logical Partitions

(LPARs) based on workload priorities. IRD combines the

strengths of the zSeries LPARs, Parallel Sysplex clustering,

and z/OS Workload Manager.

s / B

g a

T S

C /O I

3 IT S

I T

X U M

I T S

T S

MUX

STI

4 x 2.0 GBps

STIs

STI-3 MUX

I/O Cage

ICB-4 (2.0 GBps)

ICB-3 (1 GBps)

z990 z890

z900 z800

Intelligent Resource Director uses the concept of an LPAR

cluster, the subset of z/OS systems in a Parallel Sysplex

cluster that are running as LPARs on the same zSeries

server. On a z890/ z990, systems that are part of the same

LPAR cluster may be in different LCSSs. In a Parallel

Sysplex environment, Workload Manager directs work to

the appropriate resources based on business policy. With

IRD, resources are directed to the priority work. Together,

Parallel Sysplex technology and IRD provide the ﬂ exibility

and responsiveness to on demand e-business workloads

unrivaled in the industry.

LPAR Cluster

z/OS

Linux

OS/390

ICF

LPAR CPU Management

LPAR CPU Management allows WLM working in goal

mode to manage the processor weighting and logical

processors across an LPAR cluster. CPU resources are

automatically moved toward LPARs with the greatest need

by adjusting the partition’s weight. WLM also manages the

available processors by adjusting the number of logical

CPs in each LPAR. This optimizes the processor speed

and multiprogramming level for each workload, helps

reduce MP overhead, and helps give z/OS more control

over how CP resources are distributed to help meet your

business goals.

z/OS 1.2 enhances the LPAR CPU management capa-

bilities and will allow the dynamic assignment of CPU

resources to non-z/OS partitions outside the z/OS LPAR

cluster such as Linux or z/VM.

Dynamic Channel Path Management

In the past, and on other architectures, I/O paths are

deﬁ ned with a ﬁ xed relationship between processors and

devices. With z/OS and the zSeries, paths may be dynami-

cally assigned to control units to reﬂ ect the I/O load. For

example, in an environment where an installation normally

requires four channels to several control units, but occa-

sionally needs as many as six, system programmers must

currently deﬁ ne all six channels to each control unit that

may require them. With Dynamic Channel Path Manage-

ment (DCM), the system programmer need only deﬁ ne the

four channels to the control units, and indicate that DCM

may add an additional two. As the control unit becomes

more heavily used, DCM may assign channels from a pool

of managed channels, identiﬁ ed by the system program-

mer, to the control unit. If the work shifts to other control

units, DCM will unassign them from lesser utilized control

units and assign them to what are now the more heavily

used ones. DCM is for ESCON and FICON Bridge chan-

nels can help reduce the number of channels required to

effectively run a workload. DCM can also help reduce the

cost of the ﬁ ber infrastructure required for connectivity

between multiple data centers. On a z890/z990 with Logi-

cal Channel SubSystems (LCSSs), the scope of DCM man-

agement is within a Logical Channel SubSystem. Although

an LPAR cluster can span LCSSs, when DCM is used it will

only consider systems in the same LPAR cluster and the

same LCSS.

Channel Subsystem Priority Queuing

The notion of I/O Priority Queuing is not new; it has been in

place in OS/390 for many years. With IRD, this capability

is extended into the I/O channel subsystem. Now, when

higher priority workloads are running in an LPAR cluster,

their I/Os will be given higher priority and will be sent to

the attached I/O devices (normally disk but also tape and

network devices) ahead of I/O for lower priority workloads.

LPAR priorities are managed by WLM in goal mode.

Channel Subsystem Priority Queuing provides two advan-

tages. First, customers who did not share I/O connectivity

via MIF (Multiple Image Facility) out of concern that a

lower priority I/O intensive workload might preempt the I/O

of higher priority workloads, can now share the channels

and reduce costs. Second, high priority workloads may

even beneﬁ t with improved performance if there were I/O

contention with lower priority workloads. Initially, Channel

Subsystem Priority Queuing is implemented for Parallel

OEMI and ESCON, FICON Bridge and native FICON

channels.

On a z890/z990, the scope of Channel Subsystem I/O

Priority Queuing is a Logical Channel SubSystem.

Channel Subsystem Priority Queuing complements the

IBM Enterprise Storage Server capability to manage I/O

priority across CECs.

With IRD, the combination of z/OS and zSeries working in

synergy extends the world-class workload management

tradition of S/390 and OS/390 so that the most important

work on a server meets its goals, to increase the efﬁ ciency

of existing hardware, and to reduce the amount of inter-

vention in a constantly changing environment.

Parallel Sysplex Professional Services

IBM provides extensive services to assist customers

with migrating their environments and applications to

beneﬁ t from Parallel Sysplex clustering. A basic set of

IBM services is designed to help address planning and

early implementation requirements. These services can

help you reduce the time and costs of planning a Parallel

Sysplex environment and moving it into production. An

advanced optional package of services is also available

and includes data sharing application enablement, project

management and business consultation through advanced

capacity planning and application stress testing. For more

information on Parallel Sysplex Professional Services, visit

IBM’s Web site at ibm.com/servers/eserver/zseries/pso/

services.html.

GDPS

GDPS supports both the synchronous Peer-to-Peer

Remote Copy (PPRC) as well as the asynchronous

Extended Remote Copy (XRC) forms of remote copy.

The GDPS solution, based on Peer-to-Peer Remote Copy

(PPRC), referred to as GDPS/PPRC, is designed with the

attributes of a continuously availability solution. PPRC is a

hardware solution that is designed to synchronously mirror

data residing on a set of disk volumes, called the primary

volumes in site 1, to secondary disk volumes on a second

system in site 2. Only when the primary storage subsystem

receives “write complete” from the secondary storage sub-

system is the application I/O signaled completed. GDPS/

PPRC complements a multisite Parallel Sysplex environment

by providing a single, automated solution to dynamically

manage disk and tape storage subsystem mirroring, pro-

cessors, and network resources designed to allow a busi-

ness to attain “continuous availability” and near transparent

business continuity/disaster recovery without data loss.

GDPS/PPRC provides the ability to perform a controlled

site switch for both planned and unplanned site outages,

while maintaining data integrity across multiple storage

subsystems. GDPS/PPRC is designed to be application

independent and therefore is expected to be able to cover

the customer’s complete application environment. GDPS/

PPRC is designed to allow a customer to meet a Recovery

Time Objective (RTO) of less than an hour, a Recovery Point

Objective (RPO) of no data loss, and protects against met-

ropolitan area disasters (up to 40 km between sites). On the

other hand, the GDPS solution based on Extended Remote

Copy (XRC), referred to as GDPS/XRC, has the attributes

of a Disaster Recovery solution. XRC is a combined hard-

ware and software asynchronous remote copy solution.

The application I/O is signaled completed when the data

update to the primary storage is completed. Subsequently,

™

a DFSMSdfp

component called System Data Mover (SDM),

typically running in site 2, is designed to asynchronously

ofﬂ oad data from the primary storage subsystem’s cache

and updates the secondary disk volumes.

In GDPS/XRC, the production system(s) located in site 1

can be a single system, multiple systems sharing disk, or

a base or Parallel Sysplex cluster. GDPS/XRC is designed

to provide a single, automated solution to dynamically

manage storage subsystem mirroring (disk and tape)

to allow a business to attain “near transparent” disaster

recovery with minimal data loss. GDPS/XRC is designed to

provide the ability to perform a controlled site switch for an

unplanned site outage, maintaining data integrity across

multiple volumes and storage subsystems. GDPS/XRC is

designed to allow a customer to meet a RTO of one to two

hours, an RPO of less than a minute, and helps protect

against metropolitan as well as regional disasters, since

the distance between sites is unlimited. XRC can use

either common communication links and channel extender

technology or dark ﬁ ber as the connectivity between sites.

GDPS/XRC is designed to be application independent and

therefore is capable of covering the customer’s complete

application environment.

GDPS requires Tivoli

NetView® for z/OS, Tivoli System

Automation for z/OS, and remote copy technologies.

Note: Dark ﬁ ber refers to dedicated strands of ﬁ ber optic

cable with no electronics between the ends (source and

destination).

GPDS/PPRC HyperSwap

™

The GDPS/PPRC HyperSwap function is designed to

broaden the continuous availability attributes of GDPS/

PPRC by extending the Parallel Sysplex redundancy to

disk subsystems. The HyperSwap function is enabled to

mask planned and unplanned disk and site reconﬁ gura-

tions by transparently switching to use the secondary

PPRC volumes. The HyperSwap function is designed to be

controlled by complete automation, allowing all aspects

of the site switch to be controlled via GDPS. Large con-

ﬁ gurations can be supported, as HyperSwap has been

designed to provide capacity and capability to swap large

numbers of disk devices very quickly. The important ability

to re-synchronize incremental disk data changes, in both

directions, between primary/secondary PPRC disks is pro-

vided as part of this function.

The planned HyperSwap function provides the ability to

transparently switch all primary PPRC disk subsystems

with the secondary PPRC disk subsystems for a planned

switch conﬁ guration. It enables disk conﬁ guration mainte-

nance and planned site maintenance without requiring any

applications to be quiesced. The unplanned HyperSwap

function contains additional function designed to transpar-

ently switch to use secondary PPRC disk subsystems, in

the event of unplanned outages of the primary PPRC disk

subsystems or a failure of the site containing the primary

PPRC disk subsystems. With unplanned HyperSwap func-

tion, disk subsystem failures no longer constitute a single

point of failure for an entire sysplex. If applications are

cloned and exploiting data sharing across the two sites,

the GDPS/PPRC unplanned HyperSwap capability, lays

the foundation for continuous availability, even in the event

of a complete site failure. In the event of a complete failure

of the site where the primary disk resides, the systems in

the site with the secondary disks can continue to remain

active even though workload running on these systems

needs to be restarted. An improvement in the Recovery

Time Objective (RTO) can be accomplished.

With the release of GDPS/PPRC V3.2, the HyperSwap

function was enhanced to exploit the PPRC Failover/

Failback function. For planned reconﬁ gurations, PPRC

Failover/Failback can help reduce the overall elapsed time

to switch the disk subsystems, which can then reduce the

time that applications may not be available to users. For

unplanned reconﬁ gurations, PPRC Failover/Failback allows

the secondary disks to be conﬁ gured in the suspended

state after the switch, thus eliminating the need to per-

form a full copy of the data when reestablishing the PPRC

mirror in the reverse direction. The window during which

critical data is left without PPRC protection following an

unplanned reconﬁ guration is thereby minimized.

GDPS/PPRC management for open systems LUNs (Logi-

cal Unit Numbers): GDPS/PPRC technology has been

extended to manage a heterogeneous environment of

z/OS and open systems data. If installations share their

disk subsystems between the z/OS and open systems

platforms, GDPS/PPRC, running in a z/OS system, can

manage the PPRC status of devices that belong to the

other platforms and are not even deﬁ ned to the z/OS

platform. GDPS/PPRC can also provide data consistency

across both z/OS and open systems data.

GDPS supports PPRC over Fiber Channel links: GDPS/

PPRC supports Enterprise Storage Server (ESS) PPRC

over Fiber Channel Protocol (FCP). It is expected that the

distance between sites can be increased while maintain-

ing acceptable application performance, since PPRC over

FCP requires only one protocol exchange compared to

two or three exchanges when using PPRC over ESCON.

The efﬁ ciency of the FCP protocol is also expected to help

lower the total cost of ownership, since two PPRC FCP

links are considered sufﬁ cient for most workloads, which

can allow a reduction in cross-site connectivity.

GDPS/PPRC and GDPS/XRC FlashCopy Support

FlashCopy is a point-in-time copy technology that allows

point-in-time copies of disk volumes to be made very

quickly, with the copies immediately available for read

or write access. FlashCopy can operate in either of two

modes, the COPY mode which runs a background copy

process and the NOCOPY mode that suppresses the

background copy. Previously GDPS/PPRC and GDPS/XRC

have provided support for both COPY and NOCOPY. With

the release of GDPS/PPRC V3.2 and GDPS/XRC V3.2,

an enhancement now available, called NOCOPY2COPY,

allows changing an existing FlashCopy relationship from

NOCOPY to COPY. This allows you the option of always

selecting the NOCOPY option of FlashCopy and then con-

verting it to the COPY option when you want to create a full

copy of the data in the background at a non-peak time.

LSS to a target in a different LSS within the same disk sub-

system. This new ﬂ exibility can help simplify administration

and capacity planning for FlashCopy.

GDPS/PPRC Multiplatform Resiliency for zSeries

GDPS/PPRC has been enhanced to include a new func-

tion: GDPS/PPRC Multiplatform Resiliency for zSeries.

This function is especially valuable for customers who

share data and storage subsystems between z/OS and

Linux on zSeries – for example, a SAP application server

running on Linux on zSeries and a SAP DB server running

on z/OS. With a multi-tiered architecture, there is a need to

provide a coordinated Disaster Recovery solution for both

z/OS and Linux on zSeries. GDPS/PPRC can now provide

that.

Another enhancement now available with GDPS V3.2

is support for Incremental FlashCopy. This provides the

capability to refresh a volume in a FlashCopy relationship

and reduce background copy time when only a subset

of data has changed. With Incremental FlashCopy, the

initial relationship between a source and target is main-

tained after the background copy is complete. When a

subsequent FlashCopy establish is initiated, only the data

updated on the source since the last FlashCopy is copied

to the target. This reduces the time needed to create a

tertiary copy thus giving customers the option to perform a

FlashCopy on a more frequent basis.

In 2003, IBM TotalStorage Enterprise Storage Server

announced support of FlashCopy V2. Refer to Hardware

Announcement 103-141, dated May 13, 2003. Prior to this

announcement, both source and target volumes had to

reside on the same LSS within the disk subsystem. Since

this constraint has been removed with FlashCopy V2,

GDPS can now allow a FlashCopy from a source in one

z/VM 5.1 provides a new HyperSwap function so that

the virtual device associated with one real disk can be

swapped transparently to another. HyperSwap can be

used to switch to secondary disk storage subsystems mir-

rored by Peer-to-Peer Remote Copy (PPRC). HyperSwap

can also be helpful in data migration scenarios to allow

applications to use new disk volumes without requiring

them to be quiesced.

GDPS/PPRC can provide the reconﬁ guration capabili-

ties for the Linux on zSeries servers and data in the same

manner as for z/OS systems and data. To support planned

and unplanned outages, GDPS is designed to provide the

following recovery actions:

• Re-IPL in place of failing operating system images

• Site takeover/failover of a complete production site

• Coordinated planned and unplanned HyperSwap of storage subsystems transparently to the operating system images and applications using the storage

This innovative disaster recovery solution requires GDPS,

IBM Tivoli System Automation for Multiplatforms, Linux on

zSeries, and z/VM 5.1 and is designed to help anticipate

and rapidly respond to business objectives and technical

requirements while maintaining high system availability.

Performance enhancements for GDPS/PPRC and GDPS/XRC

conﬁ gurations

• Concurrent activation of Capacity Backup Upgrade (CBU) can now be performed in parallel across multiple servers, which may result in an improved RTO. This improvement may apply to both the GDPS/PPRC and GDPS/XRC conﬁ gurations.

• In a GDPS/XRC conﬁ guration, it is often necessary to have multiple System Data Movers (SDMs). The number of SDMs is based on many factors, such as the number of volumes being copied and the I/O rate. Functions are now capable of being executed in parallel across multiple SDMs, thus helping to provide improved scalability for a coupled SDM conﬁ guration.

• Analysis has shown that PPRC commands issued by GDPS will generate a large number of Write to Operator messages (WTOs) that may cause WTO buffer shortages and temporarily adversely impact system performance. The Message Flooding Automation function is expected to substantially reduce the WTO message trafﬁ c and improve system performance by suppressing redundant WTOs.

GDPS/Global Mirror – preview

IBM Global Services plans to make available a new

service, GDPS/Global Mirror, to support the recently

announced IBM TotalStorage Enterprise Storage Server

(ESS) remote copy function called IBM TotalStorage Global

Mirror. Global Mirror is included in Peer to Peer Remote

Copy (PPRC) Version 2, and is designed to enable a two-

site disaster recovery and backup solution for the zSeries

and open systems environments.

Using asynchronous technology, Global Mirror operates

over high-speed communication links and is designed to

maintain a consistent and restartable copy of the data at a

recovery site that can be located at virtually unlimited dis-

tance from the application site.

GDPS/Global Mirror executes in both the application and

the recovery sites. It manages the Global Mirror remote

copy function, and automates the restart of the workload

in the recovery site in case of a disaster in the application

site. GDPS/Global Mirror has the capability of managing

multiple Global Mirror sessions. The multiple sessions

could be the data mirroring of multiple sysplexes or Open

systems or even single image z/OS systems.

The initial delivery of GDPS/Global Mirror will support

zSeries data. A future release will provide support for open

systems data.

These GDPS enhancements are applicable to z800, z900,

z890, and z990. For a complete list of other supported

hardware platforms and software prerequisites, refer to

the GDPS executive summary white paper, available at:

ibm.com/server/eserver/zseries/pso.

Automatic Enablement of CBU for GDPS

The intent of the GDPS (CBU) is to enable automatic man-

agement of the reserved PUs provided by the CBU feature

in the event of a processor failure and/or a site failure.

Upon detection of a site failure, GDPS will dynamically add

PUs to the conﬁ guration in the takeover site to restore pro-

cessing power for mission-critical production workloads.

GDPS-CBU management helps to minimize manual cus-

tomer intervention and the potential for errors, thereby

helping to reduce the outage time for critical workloads

from hours to minutes. Similarly, GDPS-CBU management

can also automate the process of dynamically returning

the reserved CPs when the temporary period has expired.

GDPS is discussed in a white paper available at ibm.com/

server/eserver/zseries/pso/library.html. GDPS is a service

offering of IBM Global Services. For IBM Installation Ser-

vices for GDPS, refer to the IBM Web site.

Message Time Ordering (Sysplex Timer Connectivity to Coupling

Facilities)

As processor and Coupling Facility link technologies have

improved over the years, the requirement for time synchro-

nization tolerance between systems in a Parallel Sysplex

environment has become ever more rigorous. In order to

enable that any exchanges of timestamped information

between systems in a sysplex involving the Coupling Facil-

ity observe the correct time ordering, time stamps are now

included in the message-transfer protocol between the sys-

tems and the Coupling Facility. Therefore, when a Coupling

Facility is conﬁ gured as an ICF on any z890, z990 or z900

Models 2C1 through 216, the Coupling Facility will require

connectivity to the same 9037 Sysplex Timer that the sys-

tems in its Parallel Sysplex cluster are using for time syn-

chronization. If the ICF is on the same server as a member

of its Parallel Sysplex environment, no additional connectiv-

ity is required, since the server already has connectivity to

the Sysplex Timer. However, when an ICF is conﬁ gured on

any z890, z990 or z900 Models 2C1 through 216 which do

not host any systems in the same Parallel Sysplex cluster, it

is necessary to attach the server to the 9037 Sysplex Timer.

z900 Turbo or z890/z990 Model with ICF

and non-Parallel Sysplex LPARs

CF01

ICF

ICB-3 / ICB-4/ ISC-3

ICB-3/ ICB-4 / ISC-3

IBM ^ z900

or z890/z990

Sysplex LPARs

z/OS

CF02

ICF

New Connection to Sysplex Timer

Non-Sysplex

LPARs

2 3

z/OS

11 10 9 8

IBM ^ z900

or z890/z990

Sysplex

z/OS

New Connection to Sysplex Timer

LPARs

Continuous Availability Recommended Conﬁ guration for Parallel

Sysplex

Dedicated (External)

z890 or

Coupling Facility

z990 with CFs only,

z900 Model 100

9674, 9672 R06,

or z800 Model 0CF

Internal Coupling

ICF

Facility

z/OSz/OS

Sysplex Timers

ESCON/FICON Express Channels

Note: z890/z990 will attach to 9037-001 or 9037-002. Ser-

vice for 9037-001 discontinued end of 2003.

Components and assumptions

• Two Coupling Facilities; at least one external or else using System-Managed CF Structure Duplexing

• Two Sysplex Timers

• Two z/OS or OS/390 servers with redundant backup capacity

• Two links from each CF to each image

• Two hardware management consoles

• Two ESCON or FICON Directors with cross-connected disks

• Dual electrical power grids

• Cloned OS/390 images, latest available software levels

• Automation capabilities for recovery/restart

• Critical data on RAID and/or mirrored disks

z890 Support for Linux

Key attributes can include

• No single point of failure

• Fast, automatic recovery

– CF: rebuild in surviving CF

– CEC, z/OS, OS/390: restart subsystems on surviving

image

– TM/DBMS: restart in place

• Surviving components absorb new work

• No service loss for planned or unplanned outages

• Near unlimited, plug-and-play growth capacity

Linux on zSeries

Linux and zSeries are a great team. Linux has the same

appearance and application programming interfaces no

matter what platform it is running on, since it is designed

to be platform-independent. When Linux is run on a

zSeries server it inherits the legendary qualities of service

that businesses world-wide rely on for hosting their most

important workloads. Linux is open standards-based, sup-

porting rapid application portability and can be adapted

to suit changing business needs. The ﬂ exibility and open-

ness of Linux make it very popular with developers, whose

contributions endow Linux with an extensive and diverse

application portfolio. zSeries servers enable massive scal-

ability within a single server, either horizontally or vertically.

Hundreds of Linux images can run simultaneously, provid-

ing unique server consolidation capabilities while aiding in

reducing both cost and complexity.

Of course, no matter which Linux applications are brought

to the zSeries platform, they can all beneﬁ t from high-

speed access to the applications and corporate data that

reside on zSeries.

IBM developed the code that enables Linux to run on

zSeries servers, and made it available to the Open Source

community. The term used to describe this enabling code

is “patches.”

To help eliminate the need for an external 2074 Console

controller and associated consoles, an administrator may

utilize the Hardware Management Console (HMC) func-

tions “Integrated 3270 Console Support” for operating

z/VM images, and “Integrated ASCII Console Support” to

operate Linux images.

The support is implemented using an internal commu

tions method – SCLP – which enables the operating

nica-

system

to communicate with the HMC. The software support was

made available in z/VM Version 4 Release 4. An update

for Linux will be made available to IBM Linux Distribution

Partners.

Linux on zSeries supports the 64-bit architecture available

on zSeries processors. z/Architecture eliminates the exist-

ing main storage limitation of 2 GB. Linux on zSeries pro-

vides full exploitation of the architecture in both real and

virtual modes. Linux on zSeries is based on the Linux 2.4

kernel. Linux on S/390 is also able to execute on zSeries

and S/390 in 32-bit mode:

IBM Middleware

• Connectors

– DB2 Connect

™

Version 8.1

– DB2 Connect Enterprise Edition Version 7.2

– DB2 Connect Unlimited Edition Version 7.2

– CICS Transaction Gateway Version 5.0

– IMS Connect Version 1.1 and 1.2

• WebSphere Family

– WebSphere Application Server Version 5.0

– WebSphere Application Server for Developers

Version 5.0

– WebSphere Application Server Network Deployment

Version 5.0

– WebSphere Application Server Advanced Edition 4.0

– WebSphere Application Server Advanced Single

Server Edition Version 4.0

– WebSphere Application Server Advanced Developer

Edition Version 4.0

– WebSphere Application Server Advanced Edition

Version 3.5

– WebSphere Commerce Business Edition Version 5.4

– WebSphere Host On-Demand Version 7.0 and 6.0

– WebSphere MQ Everyplace Version 2.0 and 1.2

– WebSphere MQ Version 5.3

– WebSphere Personalization Server for Multiplatforms

Version 4.0

– WebSphere Personalization Server Version 3.5

– WebSphere Portal Server for Multiplatforms Version

4.1 and 4.2

• Data Management

– DB2 Universal Database Enterprise Server Edition

Version 8.1

– DB2 Universal Developers Edition Version 8.1

– DB2 Personal Developers Edition Version 8.1

– DB2 Net.Data

Version 8.1

– DB2 Runtime Client Version 8.1

– DB2 Spatial Extender Version 8.1

™

– DB2 Intelligent Miner

Modeling Version 8.1

– DB2 Intelligent Miner Scoring Version 8.1

– DB2 Intelligent Miner Visualization Version 8.1

– DB2 Net Search Extender Version 8.1

DB2 Universal Database Enterprise Edition Version 7.2

–

DB2 Universal Database Developers Edition Version 7.2

– DB2 Intelligent Miner Scoring Version 7.1

– DB2 Net Search Extender Version 7.2

• Tivoli

Tivoli Access Manager for e-business Versions 3.9

–

and 4.1

–

Tivoli Access Manager for Operating Systems Version 4.1

– Tivoli Conﬁ guration Manager Version 4.2

– Tivoli Decision Support for OS/390 Version 1.5.1

– Tivoli Distributed Monitoring Version 4.1

– Tivoli Enterprise Console Version 3.8 and 3.7.1

– Tivoli Identity Manager Version 1.1

Tivoli Monitoring for Transaction Performance Version 5.1

–

– Tivoli Monitoring Version 5.1.1 and 5.1

– Tivoli NetView for z/OS Version 5.1

– Tivoli Remote Control Version 3.8

– Tivoli Risk Manager Version 4.1 and 3.8

– Tivoli Software Distribution Version 4.0

™

– Tivoli Storage Manager

Versions 5.1.5 and 5.1

– Tivoli Storage Manager Client Version 4.2

– Tivoli Switch Analyzer Version 1.2

– Tivoli User Admin Version 3.8

– Tivoli Workload Scheduler Version 8.1

• Informix

– Informix C-ISAM

• U2

– IBM UniData Version 5.2x

• Other IBM Software Products

– IBM Application Workload Modeler Version 1.1 and

Release 1

– IBM Developer Kit Versions 1.4 and 1.3.1

– IBM Directory Integrator Version 5.1

– IBM Directory Server Versions 5.1 and 4.1

– IBM HTTP Server Version 1.3.19.3

– IBM Object RE90 Version 2.2

– IBM Screen Customizer Versions 2.0.7 and 2.0.6

Linux Distribution Partners

• SUSE LINUX

Product Information at suse.de/en/produkte/susesoft/S390/

• Turbolinux

Product Information at turbolinux.com/products/s390

• Red Hat Linux

Product Information at redhat.com/software/S390

z/VM Version 4 and Version 5

z/VM supports Linux on the mainframe. Within the VM

environment, Linux images beneﬁ t from the ability to

share hardware and software resources and use internal

high-speed communications. While beneﬁ ting from the

reliability, availability and serviceability of IBM ^

zSeries servers, both z/VM V4 and V5 offers an ideal

platform for consolidating Linux workloads on a single

physical server which allows you to run tens to hundreds

of Linux images. z/VM V4 is priced on a per-engine basis

(one-time charge) and supports IBM Integrated Facility for

Linux (IFL) processor features for Linux based workloads,

as well as standard engines for all other zSeries and S/390

workloads. Engine-based Value Unit Pricing for z/VM V5.1

is replacing the pricing model available with z/VM V4.

Engine-based Value Unit Pricing is designed to provide a

lower entry point and a decreasing price curve which will

help provide improved price/performance as hardware

capacities and workload grow. Value Unit Pricing helps

you to add capacity and workload with an incremental

and improved price and the ability to aggregate licenses

acquired across machines that are part of your enterprise.

Integrated Facility for Linux (IFL)

The Integrated Facility for Linux feature of the zSeries

servers provides a way to add processing capacity, exclu-

sively for Linux workloads, with minimal or no effect on the

model designation. Operating systems like z/OS, TPF, and

VSE/ESA will not execute on Integrated Facility for Linux

engines. Consequently, these engines will not necessarily

affect the software charges for workload running on the

other engines in the system.

OSA-Express Ethernet for Linux

Driver support is provided for the functions of the new

OSA-Express Gigabit Ethernet and 1000BASE-T Ethernet

features.

OSA-Express Enhancements for Linux

A new function, Checksum Ofﬂ oad, offered for the new

OSA-Express GbE and 1000BASE-T Ethernet features,

is being introduced for the Linux on zSeries and z/OS

environments. Checksum Ofﬂ oad provides the capability

of calculating the Transmission Control Protocol (TCP),

User Datagram Protocol (UDP), and Internet Protocol (IP)

header checksums. Checksum veriﬁ es the correctness of

ﬁ les. By moving the checksum calculations to a Gigabit

or 1000BASE-T Ethernet feature, host CPU cycles are

reduced and performance is improved. When checksum

is ofﬂ oaded, the OSA-Express feature performs the check-

sum calculations for Internet Protocol Version 4 (IPv4)

packets.

Two important networking technology advancements are

announced in z/VM 4.4 and Linux on z990:

• The high performance adapter interrupt handling ﬁ rst

introduced with HiperSockets is now available for OSA-

Express/OSA-Express2 in QDIO mode (CHPID=IQD)

and FICON Express/FICON Express2 (CHPID=FCP).

This advancement provides a more efﬁ cient technique

for I/O interruptions designed to reduce path lengths

and overhead in both the host operating system and in

the adapter. This beneﬁ ts OSA-

Express TCP/IP support in

both Linux for zSeries and z/VM.

• The z990’s support of virtual machine technology has

been enhanced to include a new performance assist

for virtualization of adapter interruptions. This new

z990 performance assist is available to V=V guests

(pageable guests) that support QDIO on z/VM 4.4. The

deployment of adapter interruptions improves efﬁ ciency

and performance by reducing z/VM Control Program

overhead when handling Linux guest virtual servers.

HiperSockets

HiperSockets can be used for communication between

Linux images and Linux or z/OS images, whether Linux is

running in an IFL LPAR, natively or under z/VM.

Virtual Local Area Networks (VLANs), IEEE standard

802.1q, is now being offered for HiperSockets in a Linux

on zSeries environment. VLANs can reduce overhead

by allowing networks to be organized for optimum trafﬁ c

ﬂ ow; the network is organized by trafﬁ c patterns rather

than physical location. This enhancement permits trafﬁ c

to ﬂ ow on a VLAN connection both over HiperSockets

and between HiperSockets and an OSA-Express GbE,

1000BASE-T Ethernet, or Fast Ethernet feature.

Internet Protocol Version 4 (IPv4) broadcast packets are

now supported over HiperSockets. TCP/IP applications

that support IPv4 broadcast, such as OMPROUTE when

running Routing Information Protocol Version 1 (RIPv1),

can send and receive broadcast packets over HiperSockets

interfaces. This support is exclusive to z990.

You can now transparently bridge trafﬁ c between a

HiperSockets and an external OSA-Express network

attachment. New Linux Layer 2 Switch (Linux L2S)

support can help simplify network addressing between

HiperSockets and OSA-Express. You can now seamlessly

integrate HiperSockets-connected operating systems into

external networks, without requiring intervening network

routing overhead, thus increasing performance and simpli-

fying conﬁ guration.

The currently available distributions; SUSE SLES 7, SUSE

SLES 8, Red Hat 7.1 and Red Hat 7.2 support z990

compatibility and exploitation of 30 LPARs and 2 Logical

Channel SubSystems. Support to further exploit z990 func-

tions will be delivered as an Open Source Contribution

via www.software.ibm.com/developerworks/opensource/

linux390/index.shtm. IBM is working with its distribution

partners to provide these functions in future distribution

releases.

Fibre Channel Protocol (FCP channel) Support for Linux

Support for FCP channels enables zSeries servers to

connect to select Fibre Channel Switches and FCP/SCSI

devices under Linux on zSeries. This expanded attachabil-

ity provides a larger selection of storage solutions for Linux

implementations.

Cryptographic Support for Linux

Linux on zSeries running on standard z990, z900, and

z800 engines is capable of exploiting the hardware cryp-

tographic feature provided by the PCICA feature (PCI

Cryptographic Accelerator). This enables customers

implementing e-business applications on Linux on zSeries

to utilize this enhanced hardware security.

Network devices

• Virtual CTC

• ESCON CTC

•

OSA-Express (Gigabit Ethernet, 1000BASE-T Ethernet, Fast Ethernet, Token-Ring) up to 24 features/48 ports on z990

• HiperSockets (up to 4096 TCP/IP stacks on up to 16 HiperSockets on z990)

• 3172

• IUCV

• Character devices

• 3215 console

• Integrated console

Additional information is available at ibm.com/linux/ and at

ibm.com/zseries/linux/.

Linux Support

Environment

• z990, z900, z800 or z890 single image

• zSeries LPAR

• z/VM guest

Block devices

• VM minidisks

• ECKD

™

3380 or 3390 DASDs

• VM virtual disk in storage

zSeries 890 Family Conﬁ guration Detail

Maximum of 512 CHPIDs; One I/O cages: 28 I/O slots

Per System

Feature Minimum Maximum Maximum Ports/ Purchase Features I/O Slots Connections Channels/ Increments used by Increments Features per Feature

ESCON, 0

16 port channels channels

FICON 0 Express2

STI-35 0 8 N/A 2 outputs N/A ICB-3 link 0

1 204

ICB-4 link 01 N/A7 8 links6 N/A 1 link

ISC-3 0

OSA- 0 204 40 2 1 feature Express

OSA- 0 20 Express2 ports GbE has 1)

Crypto 0 16 Express2 coprocessors coprocessors

PCICA

0 24 4 accelerator 2 accelerator 1 feature

cards cards

010

PCIXCC coprocessor coprocessor

1) A minimum of one I/O feature (ESCON, FICON Express/FICON Express2) or one Coupling Link (ICB, ISC-3) is required.

2) Each ESCON feature has 16 channels of which 15 channels may be activated. One channel is always reserved as a spare.

3) ESCON channels are purchased in increments of four and are activated via Licensed Internal Code, Conﬁ guration Control (LIC CC). Channels are activated equally across all installed 16-port ESCON features for high availability.

4) The maximum quantity of FICON Express, FICON Express2, OSAExpress, OSA-Express2, PCICA, and PCIXCC in combination cannot exceed 20 features per server. When the FICON Express2 feature becomes available, the FICON Express (feature codes 2319 and 2320) will no longer be orderable.

5) Each STI-3 distribution card, which supports the ICB-3s, resides in the I/O cage, occupying one I/O slot.

6) The maximum number of Coupling Links combined (ICs, ICB-3s, ICB-4s, and active ISC-3 links) cannot exceed 64 per server.

7) ICB-4s do not require connectivity to a card in the I/O cage. ICB-4s are not included in the maximum feature count for I/O slots.

8) A maximum of 32 ISC-3s can be deﬁ ned in compatibility mode (operating at 1 Gbps, instead of 2 Gbps).

9) It is recommended that an initial order for ISC-3 include two links. When two links are purchased, two ISC-3 features are shipped and activated links are balanced across ISC-3 features for high availability.

10) PCIXCC feature increments are 0, 2, 3, or 4.

Note: The Capacity Model 110 has an I/O cage with 16 I/O slots maximum

which will support up to 240 channels which can be any mix of the following as long as it does not exceed 240 channels — maximum of 240 ESCON channels, 32 FICON Express channels, 24 OSA-Express ports.

28 420 16 4

80 4 1 feature

channels

N/A 16 links6 N/A 1 link

12 48 links

6, 8

4 links 1 link

ports ports

2, 4

40 2 or 1 (10 1 feature

2, 4

16 2 1 feature

44 4 1 1 feature

Processor Unit Assignments

Model Total PUs Characterized PUs* SAP Standard Spares A04***

1-way** 5 1 1 3

2-way** 5 2 1 2

3-way** 5 3 1 1

4-way** 5 4 1 0

*PU can be characterized as CP, IFL, ICF, or zAAP **These values are for all machines including the sub-uni, sub 2-way models, etc. ***Customer will be required to purchase at least one CP, IFL, ICF or zAAP

Processor Memory

z890 Model Minimum Maximum

A04 8 GB 32 GB

Single memory card. Memory cards 8 GB, 16 GB or 32 GB. Memory increments 8 GB.

Channels

Model ESCON Min **ESCON Max *FICON Min *FICON Max

A04 0 420 0 40

*FICON Express and FCP conﬁ gured on the same FICON Express features. Max FICON Express channels total 40, max FICON Express2 channels total 80. **ESCON increments of 4 channels

Coupling Links

Links IC ICB-3* ICB-4 ISC-3 Max Links

0-32 0-16 0-8 0-48 Max combined IC, ICB-3, ICB-4, active ISC-3 = 64

*requires STI-3 card

Note: At least one I/O channel (FICON, ESCON) or one coupling link (ISC, ICB) must be present.

Cryptographic Features

PCICA

Minimum 0 0

Maximum 23 4

1. Max two PCICA features per system

2. Max eight PCICA and PCIXCC features per system

3. Two accelerator cards per PCICA feature

4. One coprocessor per PCIXCC feature (minimum orderable 2 features)

1, 2

PCIXCC2

OSA-Express Features

OSA-Express* Features

Minimum 0

Maximum 20

*Any combination of GbE LX, GbE SX, 1000BASE-T Ethernet, Token-Ring

z890 Frame and I/O Conﬁ guration Content: Planning for I/O

The following diagrams show the capability and ﬂ exibility

built into the I/O subsystem. All machines are shipped with

a single frame, the A-Frame has a single I/O cage with 28

I/O slots.

A-Frame

Single

CEC

I/O

Cage

I/O cage

General Information:

• ESCON conﬁ gured in 4-port increments. Up to 28 channels in 2 cards, 60 channels in 4 cards, 88 channels in 6 cards, etc. up to a maximum 420 channels on 28 cards

• OSA-Express/OSA-Express2 can be Gigabit Ethernet, 1000BASE-T Ethernet or Token-Ring

• Total number of PCIXCC / PCICA is 8 per system

• If ICB-3 are required on the system, these will use up a single I/O slot for each ICB-3 to accommodate the STI-3 cards. The ﬁ rst ICB-3 required a slot. The second to the fourth required another slot. The ﬁ fth to the sixth required another slot. (STI-3 cards each provide two ICBs)

Channels and channel adapters no longer supported on z890

The following channels and/or channel adapters are no

longer supported:

• Parallel channels - an ESCON converter is required; IBM 9034 or Optica 34600 FXBT

• OSA-2 adapters - use equivalent OSA-Express adapters, for FDDI migrate to Ethernet as soon as possible

• OSA-Express ATM - use 1000BASE-T or Gigabit Ethernet with appropriate multi-protocol switch or router

• 4 Port ESCON cards - will be replaced with 16-port ESCON cards during upgrade

• PCICC - replaced with PCIXCC for most functions

• ICB-2 - replace with ISC-3 links in compatibility mode.

I/O Feature Type Features Maximum

ESCON 28 cards 420 channels

FICON Express 20 40 channels

FICON Express2 20 80 channels

OSA-Express 20 40 ports

OSA-Express2 20 40 ports

PCIXCC 4 4 ports

PCICA 2 4 ports

Maximum combined FICON Express, OSA-Express, PCICA/PCIXCC features is 20

Physical Characteristics

Coupling Facility — CF Level of Support

z890 Power/Heating/Cooling

System Power Consumption (50/60 Hz, KVA)

Model / Conﬁ g 1 I/O Cage

A04 1.5 - 4.7

Note: Assumes 60 amp cords

System Cooling (Air Flow Rate - CFM)

Model / Conﬁ g 1 I/O Cage

A04 640

Note: Assumes chilled underﬂ oor temperature of 24OC

Heat Output (kBTU/hr)

Model / Conﬁ g 1 I/O Cage

A04 5.12 - 16.06

z890 Dimensions

z890

# of Frames 1 Frame IBF contained within the single frame

Height (w/ covers) 194.1 cm / 76.4 in (40 EIA) Width (w/ covers) 78.5 cm / 30.9 in Depth (w/ covers) 157.7 cm / 62.1 in

Height Reduction 178.5 cm / 70.3 in (38 EIA) Width Reduction None

Machine Area 1.24 sq. meters / 13.31 sq. feet Service Clearance 3.03 sq. meters / 32.61 sq. feet (IBF contained within the frame)

CF Level Function

14 Contains modiﬁ cations to the CF dispatcher and internal serialization mechanisms to better

manage coupled workloads in all environments. CFCC Level 14 with CFCC Dispatcher Modiﬁ ca tions is exclusive to z890 and z990

13 Parallel Sysplex performance enhancements for DB2 castout processing and receives the beneﬁ ts of CFCC enhanced patch apply

12 64-bit support for Coupling Facility, CF Duplexing Toleration for >15 LPAR ID on z990, z890 Enhanced Storage Protect DB2 Performance Message Time Ordering

11 9672 G5/G6 CF Duplexing Toleration for >15 LPAR ID on z990, z890

10 z900 GA2 support

9 MQSeries

shared message queues WLM Multi-system Enclave Support Intelligent Resource Director** IC-3/ISC-3/ICB-3 Peer Mode**

8 Dynamic ICF expansion into shared ICF pool Systems-Managed Rebuild

7 Shared ICF partitions on server models DB2 Delete Name optimization

6 ICB & IC TPF support

5 DB2 cache structure duplexing DB2 castout performance improvement Dynamic ICF expansion into shared CP pool*

4 Performance optimization for IMS & VSAM RLS Dynamic CF Dispatching Internal Coupling Facility* IMS shared message queue extensions

3 IMS shared message queue base

2 DB2 performance VSAM RLS 255 Connectors/1023 structures for IMS Batch DL1 (non-BMP)

1 Dynamic Alter support CICS temporary storage queues System Logger

Notes: –

G5 base CF level code is CF Level 6 and can be upgraded to CF Level 11

–

G6 base CF level code is CF Level 8 and can be upgraded to CF Level 11 – z900 base CF level code is CF Level 9 – z800, z890 and z990 base CF level code is CF Level 12 –

Detailed information regarding CF Levels can be found in Coupling Facility Level (CF LEVEL) Considerations at ibm.com/s390/pso/cftable.html

*G3, G4, G5 and G6 only **zSeries required

Please note that although a particular back level machine may be updated to a more current CFCC level, NOT all the functions of that CFCC level may be able to run on that hardware platform, i.e., G3/G4 can be upgraded to CF Level 8 but it cannot use dynamic ICF expansion into shared ICF pool.

Fiber-Optic Cabling and System Connectivity

In the world of open systems and Storage Area Networks

(SANs), the changing requirements for ﬁ ber-optic cabling

are directly related to the system hardware conﬁ guration.

As industry-standard protocols and higher data rates

continue to be embraced in these environments, the ﬁ ber-

optic cabling options can become numerous and complex.

Today’s marketplace is evolving towards new Small Form

Factor (SFF) ﬁ ber-optic connectors, short wavelength (SX)

and long wavelength (LX) laser transceivers, and increas-

ing link speeds from one gigabit per second (Gbps) to 10

Gbps. New industry-standard SFF ﬁ ber-optic connectors

and transceivers are utilized on the zSeries ESCON and

FICON Express features, on the ISC-3 feature, and on the

zSeries ETR feature. These new features must coexist with

the current infrastructure that utilizes a different “family” of

ﬁ ber-optic connectors and transceivers.

As a result of this complex and continually changing land-

scape, IBM is providing you with multiple ﬁ ber cabling

services options to provide ﬂ exibility in meeting your ﬁ ber

cabling needs.

IBM Network Integration and Deployment Services for

zSeries ﬁ ber cabling (zSeries ﬁ ber cabling services)

enables businesses to choose the zSeries conﬁ guration

that best matches their computing environment without

having to worry about planning and implementing the

ﬁ ber-optic cabling. By teaming with IBM, businesses can

receive a world class solution for their zSeries ﬁ ber con-

nectivity requirements, including consulting and project

management, as well as the ﬁ ber-optic jumper cables and

installation to complete the zSeries integration.

zSeries ﬁ ber cabling now offers three options to address

a solution for your ﬁ ber cable installation. Enterprise ﬁ ber

cabling offers two additional options to help meet your

structured (trunking) environments requirements.

zSeries ﬁ ber cabling options:

• Fiber-optic jumper cabling package

will analyze your zSeries channel conﬁ guration and your

existing ﬁ ber-optic cabling to determine the appropriate ﬁ ber-optic jumper cables required, then supply, label and install the ﬁ ber-optic jumper cables and complete the installation with a detailed connection report.

• Fiber-optic jumper migration and reuse for a zSeries

upgrade will plan, organize, re-label, re-route and replug your existing ﬁ ber-optic jumper cables for reuse with the upgraded zSeries server

• Fiber-optic jumper cables and installation

will supply the ﬁ ber-optic jumper cables you specify,

then label and install the ﬁ ber-optic jumper cables.

Enterprise ﬁ ber cabling options

• zSeries ﬁ ber-optic trunk cabling package

will analyze your zSeries channel conﬁ guration and your

existing ﬁ ber-optic infrastructure to determine the appropriate ﬁ ber-optic harnesses, ﬁ ber-optic trunk cables and the ﬁ ber optic patch panel boxes required, then supply, label and install the ﬁ ber-optic components to connect your new zSeries server to your existing structured ﬁ ber cabling infrastructure.

• Enterprise ﬁ ber cabling package

will analyze your entire data center conﬁ guration and

existing ﬁ ber-optic infrastructure to determine the appropriate end-to-end enterprise solution for connectivity. This is a customized offering that includes trunk cables, zone cabinets, patch panels and direct attach harnesses for servers, directors and storage devices.

These tailored zSeries ﬁ ber cabling options use the same

planning and implementation methodologies as IBM’s cus-

tomized enterprise ﬁ ber cabling services, only focused on

your zSeries ﬁ ber cabling needs.

z/OS

Fiber Quick Connect (FQC): FQC, a zSeries conﬁ guration

option, helps reduce the cable bulk associated with the

installation of potentially 240 (z800) to 256 (z900) to 420

(z890/z990) ESCON channels in one I/O cage. Fiber har-

nesses, which are factory-installed, enable connection

to IBM’s Fiber Transport System (FTS) direct-attach ﬁ ber

trunk cables. Each trunk can have up to 72 ﬁ ber pairs.

Four trunks can displace the 240 to 256 ﬁ ber optic cables

on the z800 or z900.

In planning for zSeries systems, refer to Planning for:

S/390 Fiber Optic Links (ESCON, FICON, Coupling Links,

and Open System Adapters), GA23-0367, and the Installa-

tion Manual Physical Planning (IMPP) manual. Refer to the

services section of Resource Link for further details on the

zSeries Fiber Cabling Service options and the Fiber Quick

Connect conﬁ guration option.

Access Resource Link at ibm.com/servers/resourcelink.

While zSeries servers are supported by a number of dif-

ferent operating systems, their most advanced features

are powered by z/OS. z/OS is the foundation for the future

of zSeries, an integral part of the z/Architecture designed

and developed to quickly respond to the demanding qual-

ity of service requirements for on demand businesses.

z/OS is the ﬂ agship mainframe operating system based

on the 64-bit z/Architecture. It is designed to deliver the

highest qualities of service for enterprise transactions

and

data, and extends these qualities to new applications using

the latest software technologies. It provides a highly secure,

scalable, high-performance base on which to deploy Inter-

net and Java technology-enabled applications, providing a

comprehensive and diverse application execution environ-

ment. z/OS takes advantage of the latest software technolo-

gies: new object-oriented programming models that permit

the rapid design, development and deployment of applica-

tions essential to on demand businesses. It helps protect

your investment in your present mainframe applications

by providing options for modernizing existing applications

and integrating them with new on demand applications,

all within a single image of z/OS. It provides a solid base

for applications, supporting new technologies such as

™

Enterprise JavaBeans

, XML, HTML, and Unicode, Parallel

Sysplex clustering, highly available TCP/IP networking and

dynamic workload and resource balancing.

Integrated system services

z/OS helps make critical data and processing functions

accessible to end users regardless of their location in the

heterogeneous on demand world. The z/OS base includes

z/OS Communications Server, which enables world class

TCP/IP and SNA networking support, including mainframe

dependability, performance, and scalability; highly secure

connectivity; support for multiple protocols; and efﬁ cient

use of networking assets.

This integrated set of system services in z/OS can help a

customer to focus on extracting the maximum business

value from the z/OS installation. The system manages the

workload, program libraries and I/O devices. Complexities

are designed to be minimized and problem determina-

tion is facilitated with the sophisticated recovery, reporting

and debug facilities of z/OS. The z/OS operating system

combines many features that change the playing ﬁ eld of IT

infrastructure design:

• Support for zSeries Application Assist Processors (zAAP), an attractively priced special processing unit that provides an economical z/OS Java language-based execution environment

• Intelligent Resource Director expands the capabilities of z/OS Workload Manager to react to changing conditions and prioritize critical business workloads

•

Support for 64-bit real memory and 64-bit virtual storage

• A new installation and conﬁ guration infrastructure that simpliﬁ es the installation and conﬁ guration of z/OS and related products

• Software pricing models designed to support on demand reality

• z/OS 1.6 is the ﬁ rst release of z/OS that requires the z/Architecture. This release will only run on zSeries servers (z890, z990, z800, z990) or equivalent servers.

z/OS.e

z/OS.e unique for the z890 and z800 providing select func-

tion at an exceptional price. z/OS.e is intended to help

customers exploit the fast growing world of on demand

business by making the deployment of new application

workloads on the z890 and z800 very attractively priced.

z/OS.e uses the same code base as z/OS with custom

parameters and invokes an operating environment that is

comparable to z/OS in service, management, reporting,

and reliability. In addition, z/OS.e invokes zSeries hard-

ware functionality just as z/OS does. No new z/OS skills

and service procedures are required for z/OS.e.

z/OS.e is speciﬁ cally for Java, Enterprise Java, C/C++,

and Web-based data transaction processing applications,

giving these workloads a price/performance customers

expect. z/OS.e disables traditional workloads. z/OS.e will

not execute CICS, IMS, COBOL, or FORTRAN applica-

tions. However, precompiled COBOL DB2 stored proce-

dures and other precompiled COBOL applications using

the Language Environment

preinitialization interface

(CEEPIPI) are supported. You cannot use the following

compilers: COBOL, PL/I, VisualAge

PL/I, and FORTRAN.

However, z/OS.e supports execution of precompiled PL/I

and VisualAge PL/I applications.

At only a fraction of the cost of z/OS, z/OS.e makes the

decision to run new workloads on the mainframe easy

due to its reduced total cost of ownership and exceptional

robustness and functionality. z/OS.e and z890 or z800

server help reduce the total cost of ownership of hardware,

software, people, and environments, making the combina-

tion very cost-effective for new applications.

With very few exceptions, z/OS.e has the same features

and functionality as z/OS. As a result, unless otherwise

speciﬁ ed, z/OS features described herein are applicable

to z/OS.e running on a z890 or z800 server.

Intelligent Resource Director

Intelligent Resource Director (IRD) is a key feature of the

z/Architecture which extends the Workload Manager to

work with PR/SM on zSeries servers to dynamically manage

resources across an LPAR cluster. An LPAR cluster is the

subset of the z/OS systems that are running as LPARs on the

same CEC in the same Parallel Sysplex. Based on business

goals, WLM can adjust processor capacity, channel paths,

and I/O requests across LPARs without human intervention.

IRD assigns resources to the application; the applica-

tion is not assigned to the resource. This capability of a

system to dynamically direct resources to respond to the

needs of individual components within the system is an

evolutionary step. It enables the system to continuously

allocate resources for different applications, and this helps

to reduce the total cost of ownership of the system. IRD is

made up of three parts that work together to help optimize

the utilization of zSeries resources:

• LPAR CPU Management

• Dynamic Channel Path Management

• Channel Subsystem Priority Queuing

The z/OS Intelligent Resource Director (IRD) Planning

Wizard helps to plan your IRD implementation by asking

questions about your enterprise setup, and produces a

worksheet that describes the issues on each of your systems

that you must consider before you can implement IRD. The

z/OS IRD Planning Wizard supports z/OS 1.2 and higher.

zSeries Application Assist Processor

The IBM ^ zSeries Application Assist Processor

(zAAP), available on the z990 and z890 servers, is an

attractively priced specialized processing unit that pro-

vides an economical Java execution environment for z/OS

for customers who desire the traditional qualities of service

and the integration advantages of the zSeries platform.

When conﬁ gured with general purpose processors within

logical partitions running z/OS, zAAPs may help increase

general purpose processor productivity and may contrib-

ute to lowering the overall cost of computing for z/OS Java

technology-based applications. zAAPs are designed to

operate asynchronously with the general processors to

execute Java programming under control of the IBM Java

Virtual Machine (JVM). This can help reduce the demands

and capacity requirements on general purpose proces-

sors which may then be available for reallocation to other

zSeries workloads.

The IBM JVM processing cycles can be executed on the

conﬁ gured zAAPs with no anticipated modiﬁ cations to

the Java application(s). Execution of the JVM processing

cycles on a zAAP is a function of the Software Developer’s

Kit (SDK) 1.4.1 for zSeries, z/OS 1.6, and the Processor

Resource/Systems Manager (PR/SM).

z/OS Scalability

z/OS is a highly scalable operating system that can sup-

port the integration of new applications with existing

mainframe applications and data. z/OS can scale up in a

single logical partition, or scale out in a Parallel Sysplex for

higher availability. With z/OS V1.6, up to 24 processors are

supported in a single logical partition on the z990 server.

In previous releases, z/OS supported up to 16 processors.

In a Parallel Sysplex, up to 32 z/OS images can be conﬁ g-

ured in single-image cluster, with access to shared data.

64-bit Support

z/OS scale is extended with support for 64-bit real and

virtual storage on zSeries servers, while continuing to sup-

port 24-bit and 31-bit applications.

The 64-bit real support is intended to eliminate expanded

storage, helps eliminate paging and may allow you to

consolidate your current systems into fewer LPARs or to

a single native image. z/OS 1.5 delivers 64-bit shared

memory support to allow middleware to share large

amounts of 64-bit virtual storage among multiple address

spaces. This is expected to provide a signiﬁ cant capacity

enhancement for relieving shared virtual storage constraints.

Applications that can be written to 64-bit virtual storage

have signiﬁ cantly larger addressability to data. With z/OS

1.2, assembler programs can obtain virtual storage above

2 GB for storing and manipulating data. This 64-bit support

is used by DB2 V8 and other middleware. z/OS 1.6 includes

C/C++ support for the development of 64-bit applications,

including debug and runtime support. In addition, the Java

SDK 1.4.1 is also available with 64-bit support.

Automation Support

z/OS Managed System Infrastructure for Operations (msys

for Operations) provides automation for single system and

sysplex operations to help simplify operations and improve

availability. msys for Operations plays an important role in

outage avoidance.

Functions msys for operations provides control and

manage both hardware and software resources making

fully automated solutions possible. The focus is on simpli-

fying complicated operator interaction, detecting failure

situations and reacting to them quickly and precisely. This

is achieved through panel driven operator dialogs and

automated recovery routines that run in the background.

Simpliﬁ ed Conﬁ guration z/OS Managed System Infrastruc-

ture for Setup (msys for setup) is the strategic solution for

product installation, conﬁ guration and function enable-

ment. msys for Setup allows usage of consistent interfaces

with wizard-like conﬁ guration dialogs. In z/OS 1.4, the

msys for Setup Framework was enhanced to provide multi-

user capability and improved multisystem support.

Also, with z/OS 1.5 msys for Setup can use the IBM Direc-

tory Server, OpenLDAP, on any IBM platform including

OpenLDAP on z/OS UNIX

System Services. This can sim-

plify the initialization of msys for setup, and can make the

Management Directory virtually transparent to the user.

The following functions can be conﬁ gured using msys for

Setup: Parallel Sysplex clustering, TCP/IP, UNIX System

Service, Language Environment, LDAP, RMF, ISPF, FTP,

and DB2 UDB for z/OS V8.

System Services

z/OS Version 1 Release 6 base elements

Base Control Program (BCP)

JES2 ESCON Director Support MICR/OCR Support Bulk Data Transfer base DFSMSdfp EREP/MVS High Level Assembler ICKDSF ISPF

TSO/E 3270 PC File Transfer Program V1R1 FFST™/ESA TIOC

z/OS Version 1 Release 6 optional priced features

DFSMSdss DFSMShsm DFSMSrmm DFSMStvs JES3 Bulk Data Transfer (BDT) File to File Bulk Data Transfer SNA NJE

1. Disabled on z/OS.e

2. Not licensed on z/OS.e

3. TSO usage is limited to 8 concurrent users on z/OS.e

4. z/OS.e only supports the latest JES that ships with the product

™

The msys for setup dialogs use defaults and best practices

values whenever possible and derive low-level values from

answers to high-level questions. After the conﬁ guration param-

eters have been speciﬁ ed, msys for Setup can automatically

update the system conﬁ guration directly. The user can see in

detail what the changes will be before they are made.

The backbone of the z/OS system is the Base Control

Program (BCP) with JES2 or JES3. These provide the

essential services that make z/OS the system of choice

when workloads must be processed reliably, securely,

with complete data integrity and without interruption. The

BCP includes the I/O conﬁ guration program (IOCP), the

workload manager (WLM), systems management facilities

(SMF), the z/OS UNIX Systems Services kernel, and sup-

port for Unicode.

Sense and Respond with Workload Manager

Workload Manager (WLM) addresses the need for manag-

ing mixed workload distribution, load balancing and the

distribution of computing resources to competing work-

loads. It does this while providing fewer, simpler system

externals. Performance management goals are expressed

in Service Level Agreement terms. All this is done with a

single policy that can be used across the sysplex to pro-

vide a single control point, eliminating the need to manage

each individual image.

Dynamic balancing of JES2 batch initiators across a sys-

plex has been enhanced in z/OS 1.4 to provide better utili-

zation of processor resources. WLM is designed to check

every 10 seconds to see if re-balancing is required. WLM

is more aggressive in reducing initiators on constrained

systems and starting new ones on less utilized systems

helping to ensure that processors are more evenly utilized.

Data Management with DFSMS

DFSMS comprises a suite of related data and storage

management functions for the z/OS system. DFSMSdfp is

a base element of z/OS which performs the essential data,

storage and device management functions of z/OS. One

function of DFSMSdfp is the Storage Management Subsys-

tem (SMS). SMS helps automate and centralize the man-

agement of storage based on the customer’s policies for

availability, performance, space, and security. Using SMS,

the storage administrator deﬁ nes policies that can auto-

mate the management of storage and hardware devices.

These policies describe data allocation characteristics,

performance and availability goals, backup and retention

requirements, and storage requirements for the system.

The other elements of DFSMS – DFSMSdss, DFSMShsm,

DFSMSrmm, and DFSMStvs, complement DFSMSdfp to

provide a comprehensive approach to data and storage

management. In a system-managed storage environment,

DFSMS can automate and centralize storage manage-

ment based on the policies that your installation deﬁ nes for

availability, performance, space, and security. With these

optional features enabled, you can take full advantage of

all the functions that DFSMS offers.

WLM Improvements for WebSphere

z/OS 1.5 can simplify WLM control for WebSphere.

Customers now have the choice to manually deﬁ ne

WebSphere application environments for WLM or have

WebSphere deﬁ ne them as and when required.

Performance block reporting for enclaves and multi-period

classes are designed to provide improved workload bal-

ancing for middleware applications such as WebSphere.

WLM Enqueue Management establishes a new interface to

allow reporting of resource contention. The priority of the

task holding the enqueue can be increased to allow the

resource to be released more quickly.

DFSMShsm can perform space management functions

along with disaster recovery functions such as Advanced

Copy Services and aggregate backup and recovery sup-

port (ABARS). DFSMSdss can provide backup, restore

and copy services. DFSMSrmm provides tape manage-

ment services. Finally, DFSMStvs can provide coordinated

updates to multiple VSAM data sets at a transaction level,

providing high availability for CICS/VSAM by allowing con-

current access by batch applications.

z/OS 1.5 can help signiﬁ cantly enhance application

backup with enhancements to DFSMShsm to utilize

volume level fast replication. The fast backup is designed

to exploit FlashCopy and the virtual concurrent copy capa-

bility of IBM TotalStorage Enterprise Storage Server and

IBM RAMAC Virtual Array (RVA) respectively. DFSMShsm

Fast Replication in z/OS 1.5 is also intended to provide a

fast, easy to use point-in-time backup and recovery solu-

tion speciﬁ cally designed for DB2 Universal Database

(UDB) for z/OS V8. It is designed to allow fast, nondisrup-

tive backups to be taken at appropriate events when there

is minimum activity at the application level or when a fast

point-in-time backup is desired.

Parallel Sysplex

zSeries Parallel Sysplex technology provides world-class

availability by allowing z/OS workloads to be balanced

across multiple servers to provide near continuous avail-

ability. This form of clustering, known as single system

image, also provides tremendous scale. Up to 32 zSeries

servers with z/OS can appear as a single image for

data sharing applications (see previous section, Parallel

Sysplex Clustering Technology).

CICS/VSAM enabled for 24x7 availability

DFSMS Transactional VSAM Services (DFSMStvs) allows

you to share VSAM data sets across CICS, batch, and

object-oriented applications on z/OS or distributed sys-

tems. DFSMStvs can enable concurrent shared updates

of recoverable VSAM data sets by CICS transactions and

multiple batch applications and 24-hour availability of

CICS and batch applications. DFSMStvs is built on top of

VSAM record-level sharing (RLS), which permits sharing of

recoverable VSAM data sets at the record level.

System-Managed CF Structure Duplexing

System-Managed Coupling Facility (CF) Structure Duplex-

ing is designed to signiﬁ cantly enhance Parallel Sysplex

availability. It can provide a robust failure recovery capa-

bility via CF structure redundancy, and it can enhance

Parallel Sysplex ease of use by helping to reduce the

complexity of CF structure recovery. These beneﬁ ts can

be achieved by creating a duplicate (or duplexed) copy

of a CF structure and then maintaining the two struc-

ture instances in a synchronized state during normal CF

operation. In the event of a CF related failure (or even a

planned outage of a CF), failover to the remaining copy of

the duplexed structures can be initiated and quickly com-

pleted transparent to the CF structure user and without

manual intervention.

JES2 and JES3

JES2 and JES3 handle the submission of work and the

distribution of output for the Base Control Program. JES2

exercises independent control over its job processing

functions, whereas JES3 exercises centralized control.

• In z/OS 1.2, JES2 and JES3 allow an installation to have up to 999,999 jobs managed at any single point in time. In addition, both provide the installation the ability to obtain (spinoff) their JESlog data sets prior to job completion.

• The JES2 Health monitor, in z/OS 1.4, provides improved diagnostics. Even when JES2 is not responding to commands, the JES2 monitor, running in a separate address space, will be able to provide information about JES2’s status. JES2 also provides enhanced recovery from corrupted checkpoint data to prevent multisystem outages

• In z/OS 1.4, JES3 provides additional tolerance for initialization errors and the MAINPROC refresh function which enables the dynamic addition of systems to the sysplex

System Management Services

z/OS Version 1 Release 6 base elements and components

HCD SMP/E V3 Managed System Infrastructure for Setup Managed System Infrastructure for Operations

z/OS Version 1 Release 6 optional priced features

RMF SDSF HCM

z/OS provides systems management functions and fea-

tures to manage not only host resources, but also distrib-

uted systems resources. These capabilities have a long,

successful history of usage by S/390 customers. z/OS has

enhanced many of these systems management functions

and features to provide more robust control and automa-

tion of the basic processes of z/OS.

Console Enhancements

z/OS 1.5 includes consoles enhancements which are

designed to improve system availability by enhancing

the capacity and reliability of message delivery. Major

changes to the message production and consumption

ﬂ ow can help reduce the possibility of bottlenecks which

can cause a backlog of undelivered messages. These

enhancements are available with z/OS 1.4 as an optional

no-charge Console Enhancements Feature. msys for Setup

has been enhanced in z/OS 1.4 to allow multiple users

to log on and work concurrently from different worksta-

tions. Furthermore, as part of the user enrollment process,

the msys for Setup user administrator can control which

msys for Setup workplace functions a user can access.

The graphical user interface (msys for Setup workplace)

has been redesigned and is now easier to learn and use.

These valuable ease-of-use enhancements make working

with msys for Setup more intuitive.

z/OS msys for Operations is a base element in z/OS 1.2

that incorporates automation technology into z/OS. It pro-

vides self-healing attributes for some critical system and

sysplex resources and can simplify the day-to-day opera-

tion of a single z/OS image or of a Parallel Sysplex cluster.

msys for Operations enhancements in z/OS 1.3 include

automation to handle enqueue contention and auxiliary

storage shortages. msys for Operations can also interface

with the Hardware Management Console (HMC) to provide

hardware functions such as deactivating LPARs.

RMF

RMF is IBM’s strategic product for z/OS performance mea-

surement and management. It is the base product to col-

lect performance data for z/OS and sysplex environments

to monitor systems’ performance behavior and allows

customers to optimally tune and conﬁ gure their system

according to business needs. RMF provides its beneﬁ ts

through the operation of Postprocessing and Online Moni-

toring functions. They are based on a set of data gatherers

and data services which enable access to all performance

relevant data in a z/OS environment. The four components

are RMF Data Gatherer, RMF Sysplex Data Services, His-

torical Data Reporting and Online Monitoring with RMF.

Enhancements

• RMF can show the contention for Cryptographic Coprocessors, including a description of which workloads are using or are delayed in access to the cryptographic coprocessors

• Application State Recording, a new feature of z/OS 1.4 provides more granular performance reporting for middleware such as WebSphere

• In z/OS 1.5, RMF Monitor II and Monitor III performance data is now RACF protected

SMP/E

Security Services

SMP/E provides the ability to install software products

and service either from DASD or tape, or directly from a

network source, such as the Internet. By installing directly

from a network source, SMP/E is enabling a more seam-

less integration of electronic software delivery and instal-

lation.

Advanced System Automation

The unique and rich functions of IBM Tivoli System Auto-

mation for OS/390 (SA OS/390) Version 2.2 (separately

orderable) can ease z/OS management, help reduce

costs, and increase application availability. SA OS/390

automates I/O, processor, and system operations, and

includes “canned” automation for IMS, CICS, Tivoli OPC,

and DB2. Its focus is on Parallel Sysplex automation,

including multi- and single-system conﬁ gurations, and on

integration with end-to-end Tivoli enterprise solutions. With

the new patented manager/agent design, it is now pos-

sible to automate applications distributed over a sysplex

by virtually removing system boundaries for automation.

System Services beneﬁ ts can include:

• Increased system availability

• Improved productivity of system programmers

• A more consistent approach for conﬁ guring z/OS components or products

• System setup and automation using best practices which can greatly improve availability

z/OS Version 1 Release 6 base elements and components

Integrated Security Services include:

- Public Key Infrastructure Services

- DCE Security Server

- Open Cryptographic Enhanced Plug-ins

- Firewall Technologies

- LDAP Services

- Network Authentiﬁ cation Service

- Enterprise Identity Mapping

Cryptographic Services:

Integrated Cryptographic Service Facility

- System SSL

- Open Cryptographic Services Facility

z/OS Version 1 Release 6 optional priced features

Security Server includes:

- RACF

z/OS Version 1 Release 6 optional no-charge features

z/OS Security Level 3 which includes:

- LDAP Security Level 3

- Network Authentication Service Level 3

- System SSL Security Level 3

- Open Cryptographic Services Facility Security Level 3

z/OS extends its robust mainframe security features to

address the demands of on demand enterprises. Tech-

nologies such as LDAP, Secure Sockets Layer (SSL),

Kerberos V5, Public Key Infrastructure, and exploitation of

zSeries cryptographic features are available in z/OS.

RACF

Resource Access Control Facility (RACF) provides the

functions of authentication and access control for z/OS

resources and data, including the ability to control access

to DB2 objects using RACF proﬁ les. Using an entity known

as the RACF user ID, RACF can identify users requesting

access to the system. The RACF user password (or valid

substitute, such as a RACF PassTicket or a digital certiﬁ -

cate) authenticates the RACF user ID.

Once a user is authenticated, RACF and the resource

managers control the interaction between that user

and the objects it tries to gain access to. These objects

include: commands, datasets, programs, tape volumes,

terminals and objects that you deﬁ ne. RACF supports ﬂ ex-

ibility in auditing access attempts and changes to security

controls. To audit security-relevant events, you can use the

RACF system management unload utility and a variety of

reporting tools.

With one command, a security administrator can update

remote RACF databases without logging on to remote sys-

tems. Throughout the enterprise, RACF commands can be

sent automatically to synchronize multiple databases. In

addition, RACF can automatically propagate RACF data-

base updates made by applications. With RACF, users can

keep passwords synchronized for speciﬁ c user IDs. When

you change one password, RACF can change passwords

for your user ID on different systems and for several user

IDs on the same system. Also, passwords can be changed

automatically for the same user ID on different systems.

This way, several RACF databases can be kept synchro-

nized with the same password information.

• RACF facilitates enterprise password synchronization through RACF password enveloping and notiﬁ cation of password changes using z/OS LDAP

• Improved user accountability through RACF’s enforcement of unique z/OS UNIX UIDs and GIDs

• Improved access control ﬂ exibility and granularity for z/OS UNIX ﬁ les with access control lists

• Multilevel security support

Multilevel Security

z/OS 1.5 is the ﬁ rst and only IBM operating system to pro-

vide multilevel security. This technology can help improve

the way government agencies and other organizations

share critical classiﬁ ed information. Combined with IBM’s

DB2 UDB for z/OS Version 8, z/OS provides multilevel

security on the zSeries mainframe to help meet the strin-

gent security requirements of government agencies and

ﬁ nancial institutions, and can help open up new hosting

opportunities. Multilevel security technology allows IT

administrators to give users access to information based on

their need to know, or clearance level. It is designed to pre-

vent individuals from accessing unauthorized information

and to prevent individuals from declassifying information.

RACF enhancements:

• Digital Certiﬁ cates can be automatically authenticated without administrator action

• Administrative enhancements enable deﬁ nition of proﬁ les granting partial authority. Handling of new passwords and removal of class authority are simpliﬁ ed.

• On demand applications require a way to associate more users under a RACF Group deﬁ nition, so RACF allows the creation of a new kind of Group that can contain an unlimited number of users

• RACF now allows you to perform RACF installation class

updates without an IPL, which can help improve availability

With multilevel security support in IBM’s z/OS 1.5 and DB2

V8, customers can enable a single repository of data to

be managed at the row level and accessed by individuals

based on their need to know.

SSL

Secure Socket Layer (SSL) is a public key cryptography-

based extension to TCP/IP networking which helps to

enable private communications between parties on the

Internet. z/OS provides fast and highly secure SSL sup-

port, with increased performance when coupled with

zSeries server cryptographic capabilities.

z/OS SSL support includes the ability for applications to

create multiple SSL environments within a single process.

An application can now modify environment attributes

without terminating any SSL sessions already underway.

• IPv6 Support: This support allows System SSL to be used in an IPv6 network conﬁ guration. It also enables System SSL to support both IPv4 and IPv6 Internet protocol addresses.

• Performance is improved with CRL Caching: Today, SSL supports certiﬁ cate revocation lists (CRLs) stored in an LDAP server. Each time a certiﬁ cate needs to be validated, a request is made to the LDAP server to get the list of CRLs. CRL Caching enables applications to request that the retrieved list of CRLs be cached for a deﬁ ned length of time.

• Support for the AES Symmetric Cipher for SSL V3 and TLS Connections: System SSL supports the Advanced Encryption Standard (AES), which provides data encryption using 128-bit or 256-bit keys for SSL V3.0 and TLS V1.0 connections.

Support for DSS (Digital Signature Standard) Certiﬁ cates:

•

System SSL has been enhanced to support Digital Signature Standard certiﬁ cates deﬁ ned by the FIPS (Federal Information Processing Standard) 186-1 Standard.

• System SSL of RSA Private Keys Stored in ICSF: With z/OS 1.4, support is introduced that is designed to allow a certiﬁ cate’s private key to reside in ICSF thus lifting a restriction where the private key had to reside in the RACF database.

• Failover LDAP provides greater availability: You can now specify a list of Security Server-LDAP servers to be used for storing certiﬁ cate revocation lists (CRLs). When certiﬁ cate validation is being performed, this list will be used to determine which LDAP server to connect to for the CRL information.

• Simpliﬁ ed administration with the ability to export and import certiﬁ cate chains using PKCS#7 format ﬁ les

LDAP

z/OS provides industry-standard Lightweight Directory Pro-

tocol (LDAP) services supporting thousands of concurrent

clients. Client access to information in multiple directories

is supported with the LDAP protocol. The LDAP server

supports thousands of concurrent clients, increasing the

maximum number of concurrently connected clients by an

order of magnitude.

Enhancements:

• Mandatory Authentication Methods (required by IETF RFC 2829) are supported in z/OS 1.4: The CRAM-MD5 and DIGEST-MD5 authentication methods have been added. The methods avoid ﬂ owing the user’s password over the connection to the server. The LDAP Server, the C/C++ APIs, and the utilities are updated with this support. Interoperability is improved for any applications that make use of these methods.

• TLS: z/OS LDAP now provides support for TLS (Transport Layer Security) as deﬁ ned in IETF RFC 2830 as an alternative to SSL support. It also provides support, via an LDAP extended operation, that allows applications to selectively activate TLS for certain LDAP operations at the application’s discretion.

• Support for IPv6 and 64-bit addressing

• Peer-to-peer replication provides failover support for server availability. If a primary

master server fails, there

is now a backup master to which LDAP operations can be directed.

• Large group support helps improve LDAP server performance when maintaining large access groups containing many members.

ICSF

Integrated Cryptographic Service Facility (ICSF) is a part

of z/OS which provides cryptographic functions for data

security, data integrity, personal identiﬁ cation, digital

signatures, and the management of cryptographic keys.

These functions are provided via APIs intended to deliver

the highly scalable and available security features of z/OS

and the zSeries servers. Together with cryptography

features of the IBM zSeries servers, z/OS is designed to

provide high performance SSL, which can beneﬁ t applica-

tions that use System SSL, such as the z/OS HTTP Server

and WebSphere, TN3270, and CICS Transaction Gateway

server.

ICSF provides support for the z990 and z890 PCIX Cryp-

tographic Coprocessor (PCIXCC), a replacement for the

PCICC and the CMOS Cryptographic Coprocessor Facility

that were found on the z900 and z800. All of the equivalent

PCICC functions offered on the PCIXCC are expected to

be implemented with higher performance. In addition,

PCIXCC implements the functions on the CMOS Crypto-

graphic Coprocessor Facility used by known applications.

PCIXCC supports secure cryptographic functions, use of

secure encrypted key values and user-deﬁ ned extensions.

PKI Services

PKI Services is a z/OS component that provides a com-

plete Certiﬁ cate Authority (CA) package for full certiﬁ cate

life cycle management. Customers can be their own Cer-

tiﬁ cate Authority, with the scale and availability provided by

z/OS. This can result in signiﬁ cant savings over third party

options.

• User request driven via customizable Web pages for browser or server certiﬁ cates

• Automatic or administrator approval process administered via same Web interface

• End user / administrator revocation process

• Certiﬁ cate validation service for z/OS applications

Firewall

• Firewall Technologies provide sysplex-wide Security Association Support: This function is designed to enable VPN (virtual private network) security associations to be dynamically reestablished on a backup processor in a sysplex when a Dynamic Virtual IP Address (DVIPA) takeover occurs. When the Dynamic Virtual IP Address give-back occurs, the security association is designed to be reestablished on the original processor in the sysplex. When used in conjunction with z/OS Communications Server’s TCP/IP DVIPA takeover/give-back capability, this function provides customers with improved availability of IPSec security associations.

Network Authentication Service

• Network Authentication Services, provide authentication, delegation and data conﬁ dentiality services that are interoperable with other industry implementations based on the MIT Kerberos V5 reference implementation. Network Authentication Service, administered with RACF commands, supports both the native Kerberos API functions as well as the GSS-API Kerberos security mechanism and does not require DCE.

• IPv6 supported by Kerberos with z/OS 1.4 for improved network security scalability

• Kerberos in z/OS 1.4 provides an alternative database to RACF by offering support for its own registry database using the UNIX System Services NDBM (New Database Manager) support. NDBM provides full Kerberos administration support.

Application Enablement Services

z/OS Version 1 Release 6 base elements

Language Environment Run-Time Library Extensions

z/OS Version 1 Release 6 optional priced features

C/C++ without Debug Tool DFSORT GDDM®-PGF V2R1.3 GDDM-RE90 V3R2 HLASM Toolkit V1R4

1. Disabled on z/OS.e

2. z/OS.e only supports the latest Language Environment that ships with this product. See LE limitations for z/OS.e.

z/OS provides a solid infrastructure on which you can build

new applications, extend existing applications, and run

existing transactional and batch processes.

• Enhanced ASCII support provides the ability to produce code that contains ASCII string literals and character constants. This allows ASCII dependent logic to continue working on ASCII platforms, thus eliminating the need to ﬁ nd all such places in the code and converting

hem to EBCDIC when porting UNIX applications to z/OS.

•

Performance enhancements: A new higher optimization level, OPTIMIZE(3), provides the compiler’s highest and most aggressive level of optimization. OPTIMIZE(3) is suggested when the desire for run-time improvement outweighs the concern for minimizing compilation resources.

• DB2 preprocessor integration: The C/C++ compiler has been enhanced to integrate the functionality of the DB2 precompiler. A new SQL compiler option enables the compiler to process embedded SQL statements.

Language Environment

Language Environment is a base element of z/OS and

provides the run-time environment for programs generated

with C, C++, COBOL, Fortan, and PL/1.

C/C++

• Extra Performance Linkage (XPLINK) is provided in z/OS

1.2 -

A C or C++ application has overhead associated with

each function call. The more highly functionalized a program, the more overhead. XPLINK helps cut down on the overhead associated with these function calls and can improve the performance of these applications. In order to exploit the bulk of “high-performance linkage” customers must recompile their C and C++ programs under the new XPLINK environment. The new IBM SDK for z/OS Java 2 Technology Edition 1.4 has been rewritten to take advantage of this unique z/OS function, which can result in performance improvements.

C/C++ IBM Open Class® Library: As previously announced

in Software Announcement 203-131, dated May 13, 2003,

the application development support (that is, the headers,

source, sidedecks, objects, and samples from the Applica-

tion Support Class and Collection Class libraries) is with-

drawn from the C/C++ IBM Open Class Library (IOC) in

z/OS V1.5. Applications that use these IOC libraries cannot

be compiled nor linked using z/OS V1.5. Run-time support

for the execution of existing applications which use IOC

libraries is provided with z/OS V1.5, but is planned to be

removed in a future release.

z/OS 64-bit C/C++ environment: z/OS V1.6 delivers the

capability to exploit 64-bit virtual in developing and

deploying new applications that require a signiﬁ cantly

larger addressability of data. This capability is provided

with enhanced UNIX System Services, 64-bit Language

Environment (LE) run-time developed with the C/C++ com-

piler 64-bit support, and the Program Management Binder

64-bit support. The availability of this support completes

the major steps of the z/OS 64-bit virtual roadmap.

Java

Unicode

SDK for z/OS, Java 2 Technology Edition, 1.4 provides a

full-function Software Development Kit (SDK) at the Java

2 technology level, compliant with the Sun SDK 1.4 APIs.

With SDK for z/OS, Java 2 Technology Edition, V1.4, cus-

tomers can:

• Test and deploy Java applications at the Java 2 SDK 1.4 API level

• Continue the “write once, run anywhere” Java paradigm at the Java 2 API level

• Take advantage of the new Java 2 function, including XML and Web services

• Continue to take advantage of:

– Common cross platform programming Security APIs

within Java framework

– Java Record Input/Output (JRIO) APIs to provide

record-oriented access to VSAM datasets, System catalogs, and PDS directory

– Persistent reusable JVM technology for CICS, IMS,

and DB2

• Leverage traditional zSeries software and server beneﬁ ts: scalability, reliability, availability, performance and serviceability

IBM 64-Bit SDK for z/OS, Java 2 Technology Edition, 1.4

(5655-I56) provides a full-function Software Development

Kit (SDK) at the Java 2 technology level, compliant with

the Sun SDK 1.4 APIs. With 64-bit SDK for z/OS, Java 2

Technology Edition, 1.4, you can run Java applications that

were previously storage constrained.

The Java SDK for z/OS is available via download from the

IBM ^ zSeries Java Web site and by tape from IBM

Software Delivery and Fulﬁ llment (SDF) in SMP/E format.

For additional information about zSeries Java products, go

to: ibm.com/servers/eserver/zseries/software/java/.

z/OS provides Unicode Callable System Services – code

page and case conversions from EBCDIC to Unicode:

• DB2 V7 is the ﬁ rst exploiter

• New hardware instruction on zSeries servers has been implemented to provide superior performance

• Unicode Normalization Services allows programmers to decompose or compose characters from another code page and can apply normalization forms to have the same meaning.

REXX Functions

• z/OS V1.4 extends the REXX language on z/OS when used in a UNIX System Services zSeries REXX environment. It includes functions for standard REXX I/O and to easily access some common ﬁ le services and environments variables.

Communication Services

z/OS Version 1 Release 6 base elements

z/OS Communications Server (Multiprotocol/HPR Services, TCP/IP Services, SNA/APPN Services)

OSA Support Facility

z/OS Version 1 Release 6 optional no-charge features

z/OS Communications Server Security Level 3

The z/OS base includes z/OS Communication Server,

which enables: world class TCP/IP and SNA networking

support, including enterprise class dependability; perfor-

mance and scalability; highly secure connectivity; sup-

port for multiple protocols; and efﬁ cient use of networking

assets.

z/OS can provide near continuous availability for TCP/IP

applications and their users with two key features in z/OS:

Sysplex Distributor and Dynamic VIPA.

Dynamic Virtual IP Address Takeover

VIPA represents an IP address that is not tied to a speciﬁ c

hardware adapter address. The beneﬁ t can be that if an

adapter fails, the IP protocol can ﬁ nd an alternate path to

the same software, be it the TCP/IP services on a zSeries

server or an application.

In case of a failure of the primary IP stack, VIPA Takeover

introduced in OS/390 V2.8 can support movement to a

backup IP stack on a different server in a Parallel Sysplex

cluster. Dynamic VIPA Takeover can enhance the initial

V2.8 functions, providing VIPA takeback support. This can

allow the movement of workload back from the alternate to

the primary IP stack.

With Sysplex-Wide Security Associations (SWSA) in z/OS

V1.4, IPSec protected workloads are expected to now

realize all the beneﬁ ts derived from workload balancing,

such as optimal routing of new work to the target system

and server application based on QoS and WLM advice,

increased availability by routing around failed components

and increased ﬂ exibility in adding additional workload in a

nondisruptive manner.

Sysplex Distributor

Introduced in OS/390 2.10, Sysplex Distributor is a soft-

ware-only means of distributing IP workload across a

Parallel Sysplex cluster. Client connections appear to be

connected to a single IP address, yet the connections are

routed to z/OS images on servers on different zSeries 800/

900 or S/390 servers. In addition to load balancing, Sys-

plex Distributor simpliﬁ es the task of moving applications

within a Parallel Sysplex environment.

In z/OS we have taken the functions provided by the

Cisco MNLB Workload Agent and Systems Manager, and

integrated them into Enhanced Sysplex Distributor. This

can eliminate the need for separate Cisco LocalDirector

machines in the network and the need for MNLB work-

load agents to be run on the zSeries servers. It can also

improve performance, while allowing the Sysplex Distribu-

tor to decide, based on priority supplied by WLM, the

Service Policy Agent and the TCP/IP stack status, on the

application instance the packet is sent to.

z/OS supports Enterprise Identity Mapping (EIM). EIM

deﬁ nes a user’s security context that is consistent through-

out an enterprise, regardless of the User ID used and

regardless of which platform the user is accessing. RACF

commands are enhanced to allow a security administrator

to deﬁ ne EIM information for EIM applications to use. The

EIM information consists of the LDAP host name where the

EIM domain resides, the EIM domain name, and the bind

distinguished name and password an application may use

to establish a connection with the domain.

Intrusion Detection Services (IDS)

Introduced in z/OS V1.2 and enhanced in V1.5, IDS

enables the detection of attacks on the TCP/IP stack and

the application of defensive mechanisms on the z/OS

server. The focus of IDS is self-protection. IDS can be used

alone or in combination with an external network-based

Intrusion Detection System. IDS is integrated into the z/OS

Communications Server stack.

IPv6

• IPv6 (Internet Protocol version 6) is supported in z/OS and can dramatically increase network addressability in support of larger internal and multi-enterprise networks. z/OS provides compatibility with existing network addressing and mixed-mode addressing with IPv4.

HiperSockets

• HiperSockets, introduced in z/OS 1.2, provides very high-speed, low latency TCP/IP data communications across LPARs resident within the same zSeries server.

HiperSockets acts like a TCP/IP network within the server.

• HiperSockets Accelerator provides an “accelerated routing path” which concentrates trafﬁ c between OSAExpress external network connections and HiperSockets connected LPARs. This function can improve performance, simplify conﬁ guration, and increase scalability while lowering cost by reducing the number of networking adapters and associated I/O cage slots required for large numbers of virtual servers.

Communications Services highlights:

• A single high-performance TCP/IP stack providing support for both IPv4 and IPv6 applications

• High Performance Native Sockets (HPNS) for TCP/IP applications

• Support for the latest security protocols - SSL & TLS

• Multinode Persistent Sessions for SNA applications running in a Parallel Sysplex environment

• Simple Network Time Protocol Support (SNTP) for client/ server synchronization

• New conﬁ guration support for Enterprise Extender (EE) XCA major nodes allows activation and inactivation at the GROUP level. In addition, the EE XCA major node now supports conﬁ guration updates when the major node is active. This provides ﬂ exibility and can help improve availability by allowing updates to occur without necessarily affecting existing sessions.

• Alternate route selection for SNA and Enterprise Extender (EE): VTAM allows alternate route selection for sessions using Enterprise Extender (EE) connection networks when connectivity fails due to temporary conditions in the underlying IP network. This can help improve availability for sessions using EE connection networks.

• Separate address space for TN3270 servers

• TCP/IP Sysplex health monitoring

Network Services beneﬁ ts can include:

•

Function for on demand Internet and intranet applications

• Multivendor, multiplatform connectivity

• Mainframe class of service over IP networks

• Dramatic improvements in TCP/IP performance include optimization of the TCP/IP stack, and inclusion of a number of performance related capabilities

z/OS

UNIX

z/OS Version 1 Release 6 base elements

z/OS UNIX

z/OS UNIX is an integral element of z/OS and is a key ele-

ment of the zSeries’ open and distributed computing strat-

egy. Many middleware and application products that run

on z/OS use z/OS UNIX.

z/OS contains the UNIX application services (shell, utilities

and debugger) and the UNIX System Services (kernel and

runtime environment). The shell and utilities provide the

standard command interface familiar to interactive UNIX

users. z/OS includes all of the commands and utilities

speciﬁ ed in the X/Open Company’s Single UNIX Speciﬁ ca-

tion, also known as UNIX 95 or XPG4.2. The z/OS UNIX

Services Debugger provides a set of commands that

allow a C language program to be debugged interactively.

The command set is familiar to many UNIX users. With

Language Environment, z/OS supports industry standards

for C programming, shell and utilities, client/server appli-

cations, and the majority of the standards for thread man-

agement and the X/Open Single UNIX Speciﬁ cation. The

combination of open computing and z/OS allows the trans-

parent exchange of data, easy portability of applications,

cross-network management of data and applications, and

the exploitation of traditional zSeries system strengths in

an open environment.

Highlights

• X/Open UNIX 95 Branded

• Permanent z/OS UNIX Kernel (restart capability provided in z/OS 1.3)

• Integrated/converged z/OS UNIX Sockets

• Web application and UNIX C program performance improvements

• Improved z/OS UNIX setup

• Multiprocess/Multiuser Kernel Support

• Performance enhancements include recompiled and optimized functions within the kernel, and shell and utilities; addition of Socket Functions; use of Communication Storage Management buffer transfer instead of data movement; and optimized NFS Logical File System.

• Multiprocess/Multiuser can allow faster process creation for customers and reduced storage usage for servers

• Semaphores without contention using the hardware Perform Locked Operation (PLO) instruction

• Shared memory (captured storage) can reduce real storage when sharing large amounts of virtual storage

• UNIX System Services and UNIX debugger add support for IEEE-ﬂ oating point

• UNIX System Services provides greater security granularity for HFS and zFS ﬁ le systems with support for Access Control Lists (ACLs)

• More ﬁ le descriptors per UNIX process are provided in z/OS 1.6, which supports up to 64K per process

• Additional support for 64-bit programming, conditional variables in shared memory, Euro symbol, and superkill support, along with enhancements to the automount daemon and Unicode

UNIX System Services beneﬁ ts can include:

• Development and execution of UNIX applications — z/OS is a UNIX platform

• Increased application portfolio on z/OS as Independent Software Vendors can use USS to port their applications to z/OS

• Portability of applications to and from other platforms

• Use of UNIX development skills in a z/OS environment

• Consolidate multiple UNIX systems

• Scalability for high growth UNIX applications

•

Parallel Sysplex support to share UNIX ﬁ le systems ben-

eﬁ ts with Web server applications and others who access

the hierarchical ﬁ le system. This support can make your data and information that reside in the HFS available to

your customers at any time, no matter where the applica-

tions are running in the Parallel Sysplex environment.

Distributed Computing Services

z/OS Version 1 Release 6 base elements

Network File System (NFS) DCE Base Services Distributed File Service (including zFS and SMB)

z/OS UNIX supports hierarchical ﬁ le systems that use

UNIX APIs. Applications can work with data in both UNIX

hierarchical ﬁ le systems and traditional zSeries data sets.

zSeries File System (zFS)

zFile System (zFS) is the strategic UNIX ﬁ le system for

z/OS and complements the z/OS Hierarchical File System

(HFS). zFS uses the same APIs as HFS.

zFS can provide the following beneﬁ ts over HFS:

• Improved performance

• Additional function

– Disk space can be shared between ﬁ le systems in the

same data set

– File system quota (maximum ﬁ le system size). With

zFS the ﬁ le system quota can be increased with a simple administrative command.

– Can improve failure recovery. zFS performs asynchro-

nous writes to disk and does not wait for a synch interval to begin writes.

zFS or zFS-related administration, system management,

performance, conﬁ guration support, and scalability have

been further enhanced in z/OS 1.4:

• Dynamic reconﬁ guration for ﬁ le system conﬁ guration options

• Dynamic use of secondary allocation for a zFS aggregate (data set) or ﬁ le system

• Improvements in the UNIX System Services automount support for zFS

• Addition of ISHELL support for zFS

• Ability to perform I/O operations in parallel for a zFS aggregate that spans multiple DASD volumes. This is designed to provide improved performance when using multi-DASD volume aggregates.

• Support for 64-bit user virtual buffer addresses

The Hierarchical File System (HFS) functionality has been

stabilized. HFS is expected to continue shipping as part of

the operating system and will be supported in accordance

with the terms of a customer’s applicable support agree-

ment. IBM intends to continue enhancing zFS functional-

ity, including RAS and performance capabilities, in future

z/OS releases. All requirements for UNIX ﬁ le services are

expected to be addressed in the context of zFS only.

z/OS to share HFS, zFS, Sequential ﬁ les and Record Files

Systems (RFS) such as PDS, PDS/E or VSAM data sets

with Windows workstations. SMB can automatically handle

the conversion between ASCII and EBCDIC making full

use of USS ﬁ le tagging Access Control Lists (ACLs) sup-

port. This enhances the ability to develop applications on

Windows and deploy on z/OS. z/OS also supports printing

of SMB ﬁ les without requiring that code be installed on the

clients and without requiring unique printer setup on the

workstations.

SMB Support has been further enhanced in z/OS 1.4 by:

• Simpliﬁ ed user administration with Windows Domain ID mapping

• Performance improvements with RFS and large PDS or PDS/E ﬁ le systems

• Exploitation of zFS performance

• Network File System (NFS) acts as a ﬁ le server to workstations, personal computers, or other authorized systems in a TCP/IP network. It also provides a z/OS client. The remote data sets or ﬁ les are mounted from the mainframe (z/OS) to appear as local directories and ﬁ les on the client system. NFS also provides access to the Hierarchical File System (HFS) and zSeries File System (zFS).

Internet Services

z/OS Version 1 Release 6 base elements

IBM HTTP Server

z/OS Version 1 Release 6 optional no-charge features

IBM HTTP Server North America Secure

Distributed File Services (DFS) Server Message Block

(SMB)

Microsoft Windows networking compatible ﬁ le and print

serving is available in z/OS with Native SMB File and Print

Serving for Windows Clients. SMB ﬁ le serving enables

The IBM HTTP Server offers HTTP 1.1 compliance, support

for Java technology, and the ability to manage Internet

processing through the Workload Manager (WLM). Ben-

eﬁ ts can include:

• Utilization of large storage capacity

• Single point of entry and control

• Consolidation of multiple Web sites

• Exploitation of z/OS WLM

Print Services

IP PrintWay extended mode: Infoprint Central is backed

by a new architecture in the component that delivers print

or e-mail output to printers, servers or users over TCP/IP

or Internet Printing Protocol (IPP). IP PrintWay extended

mode uses the SYSOUT Application Programming Inter-

face (SAPI) to access print jobs and job information from

the JES spool. The advantage of this change can be

higher availability and throughput, more ﬂ exibility for han-

dling print-related tasks, and scalability of Infoprint Server

for very large distributed print environments.

z/OS Version 1 Release 6 optional priced features

Infoprint Services:

- IP Printway

- NetSpool

- z/OS Print Interfaces

™

Infoprint Server provides a reliable, high availability, secu-

rity-rich and scalable foundation for customer’s enterprise

printing infrastructure. Infoprint Server and its compan-

ion product, Infoprint Server Transforms, include a print

interface, printer inventory, application output capture

program, and print drivers and management tools that let

you manage any print job to any printer deﬁ ned to Infoprint

Server, including electronic distribution for presentation

over the Web.

Infoprint Central

Infoprint Central is a Web-based, GUI for managing print

jobs and printers throughout the enterprise from anywhere

in the enterprise using a Web browser. Intended primar-

ily for help desk operators, it lets users query the status

of jobs and printers, see job and printer messages, stop

and start printers, move jobs from one printer to another,

cancel or hold jobs, and many other functions. Infoprint

Central can use integrated z/OS security services so that

users can be authorized to perform only certain tasks, or

to perform tasks only on designated devices.

Common message log: A new common message log helps

to improve productivity of help desk operators for print

problem diagnosis and resolution, thus helping to increase

system availability and user satisfaction. Messages can

easily be accessed from Infoprint Central for a particular

job or printer.

These capabilities give you the ﬂ exibility to deliver output

on demand, anywhere you need it:

• Legacy CICS and IMS applications that generate SNA Character String (SCS) or 3270 output formats can print to LAN-attached PCL printers, without changes to the application program

• Output can be sent as e-mail instead of, or in addition to print

• A consolidated printer inventory lets you deﬁ ne all printers used with Infoprint Server, and printers driven by Print Services Facility (PSF) in one place. Printers can be deﬁ ned and modiﬁ ed from a single easy-to-use interface.

• IP PrintWay provides support for printers attached to the

network using TCP/IP, VTAM

-controlled coax printers, and for printers and servers over the Internet using the industry-standard Internet Printing Protocol (IPP). Easy to use ISPF menus also enable management of distributed printers.

• The Print Interface supports print submission from applications running in UNIX System Services (USS), from Windows users via native Windows SMB, from applications on other servers, and over the Internet using IPP.

™

• Data stream transforms let you print AFP

applications on printers using PCL, PostScript or PDF. You can also print PCL, PostScript and PDF output on AFP printers.

A transform from SAP to AFP and a certiﬁ ed SAP Output

•

Management System lets you print SAP application output on your fast, reliable AFP printers, and receive print completion notiﬁ cation back at the SAP Application Server.

Beneﬁ ts of consolidating your enterprise printing onto z/OS

using Infoprint Server can include:

• Reduced total cost of ownership for distributed print operations

• Improved productivity with simpliﬁ ed print operations and management

• Investment protection and leverage for your AFP applications and printers

• Faster deployment of on demand initiatives with ﬂ exible output delivery options

Library Server converts BookManager documents to HTML

for display through a Web browser.

Library Center

IBM is providing an alternative way to navigate our z/OS

library on the Internet. Beginning with z/OS 1.5, the Library

Center for z/OS provides a Microsoft Windows Explorer-like

view of the contents of the entire z/OS and Software Prod-

ucts DVD Collection. The Library Center uses the new IBM

Library Server with new advanced search functions to help

users ﬁ nd information “on demand.”

The Library Center offers easier navigation and new

advanced search features.

• An IBM Redbook™ bookshelf lets the user perform a BookManager search and locate a corresponding Redbook in PDF format. The search scope pull-down lets the user launch searches in other repositories such as the WebSphere Application Server for z/OS or Google.

• The Library Center also provides a handheld mode to support both connected and disconnected handhelds

Softcopy Publications Support

z/OS Version 1 Release 6 base elements

BookManager® READ V31 Library Server

GDDM Library Center

z/OS Version 1 Release 6 optional no-charge features

BookManager Build

1. Disabled on z/OS.e

BookManager READ is used to display, search,

and manage online documents and bookshelves.

BookManager BUILD is an optional feature that allows

the creation of softcopy documents that can be used

by any of the BookManager products.

Integrated Testing

z/OS is system-integration tested using a production-like

environment. The z/OS environment includes subsystems,

such as CICS, IMS, DB2 and WebSphere. This additional

testing supplements existing functional tests, with a focus

on tasks performed by customers in the production envi-

ronment, thus helping establishments move more quickly

to new functions.

Publications

For a list of the publications available for z/OS, visit the

z/OS library Web site at: ibm.com/servers/eserver/zseries/

zos/bkserv.

Installation Considerations

CustomPac is a suite of services designed to help you

efﬁ ciently install, migrate and maintain a z/OS system. It

can also help with migrating and maintaining z/OS system-

related products and/or third parties’ software vendor

products. Options include:

• RefreshPac®, which includes preventative software services

• ProductPac

• SystemPac

for custom-built products

for installation or system replacement

z/OS 1.6 is supported on the following IBM servers:

• IBM

zSeries 800, 890, 900 and 990 servers (or

compatible servers in z/Architecture mode)

Migration/Coexistence

General coexistence, release migrations, and fallback:

z/OS continues to deliver compatibility and ﬂ exibility as

the user migrates systems in a multisystem conﬁ guration

by allowing several releases of z/OS, OS/390, and z/OS.e

to coexist. This includes Parallel Sysplex and non-Parallel

Sysplex multisystem conﬁ gurations.

Highlights

• Customized services and products to help meet customer speciﬁ c needs

• Efﬁ cient and effective exploitation of new z/OS functions

• A solution for businesses that lack skilled system programmers

• Installation of IBM and selected third-party software vendor products in one package

z/OS.e can be ordered by ServerPac and SystemPac only.

ServerPac is a software package, available free of charge

with a z/OS license, that creates or replaces a z/OS,

OS/390, or z/OS.e system.

CBPDO is a no-charge software package for adding or

upgrading products or services or both, on an existing

z/OS systems.

z/OS 1.4 and 1.5 are supported on the following IBM servers:

• S/390 Parallel Enterprise Server™ G5/G6 (or compatible server) (ESA/390 mode)

• Multiprise

3000 Enterprise Server (or compatible

server) (ESA/390 mode)

• IBM

zSeries 800, 890, 900 and 990 servers (or

compatible servers in z/Architecture mode)

Coexistence allows systems within a multisystem conﬁ gu-

ration to be upgraded to a new release level of the operat-

ing system one system at a time. This is contingent on the

fact that the release the user is migrating to can coexist

with the lowest release running in the user’s multisystem

conﬁ guration.

IBM has a consistent coexistence, migration, and fallback

policy. Migration forward as well as backward should be

made within the same releases supported by the coexis-

tence policy.

This consistent coexistence, migration and fallback policy

applies to release migrations for:

• Single system conﬁ gurations

• Individual systems within a multisystem conﬁ guration

• Cases where a simultaneous IPL is used to migrate all systems in a multisystem conﬁ guration at the same time

Customers are able to upgrade to z/OS 1.6 from z/OS 1.3,

1.4 or 1.5 in a single step.

For additional information on coexistence and release

migration information, refer to z/OS Planning for Installation

(GA22-7504) at: ibm.com/servers/eserver/zseries/zos/

bkserv/ﬁ nd_books.html.

The following table describes the migration/coexistence

supported releases. The release shown in column 1 is the

highest release running in a multisystem conﬁ guration.

Migration/Coexistence Supported Releases (OS/390 & z/OS)

Release Migration/Coexistence Release

z/OS R4 {z/OS.e R4, z/OS R4}, {z/OS.e R3, z/OS R3}, z/OS R2, {z/OS R1, OS/390 R10} z/OS.e R4 {z/OS.e R4, z/OS R4}, {z/OS.e R3, z/OS R3}, z/OS R2, {z/OS R1, OS/390 R10}

z/OS R5 {z/OS.e R5, z/OS R5}, {z/OS.e R4, z/OS R4}, {z/OS.e R3, z/OS R3}, z/OS R2

z/OS.e R5 {z/OS.e R5, z/OS R5}, {z/OS.e R4, z/OS R4}, {z/OS.e R3, z/OS R3}, z/OS R2

z/OS R6 {z/OS.e R6, z/OS R6}, {z/OS.e R5, z/OS R5}, {z/OS.e R4, z/OS R4}, {z/OS.e R3, z/OS R3}

z/OS.e R6 {z/OS.e R6, z/OS R6}, {z/OS.e R5, z/OS R5}, {z/OS.e R4, z/OS R4}, {z/OS.e R3, z/OS R3}

z/OS R7

z/OS.e R7 {z/OS.e R7, z/OS R7}, {z/OS.e R6, z/OS R6}, {z/OS.e R5, z/OS R5}, {z/OS.e R4, z/OS R4}

1. OS/390 R10 and z/OS R1 treated as one coexistence level

2. z/OS R7 is planned to be available September 2005

z/OS R7, z/OS R6, z/OS R5, z/OS R4

Migration, installation and customization enhancements

For information on migration to the latest z/OS releases,

see the z/OS Migration Web page ibm.com/zseries/zos/

migration. The publications, z/OS V1.6 Migration are avail-

able from this site for helping to plan the migration to z/OS

V1.6.

zSeries Bimodal Support for z/OS

IBM provides the z/OS Bimodal Migration Accommoda-

tion Offering to assist customers in migrating from OS/390

to z/OS. This addresses many customer requests to have

a “fallback” option to 31-bit mode when ﬁ rst migrating to

z/OS in 64-bit mode on a z/Architecture server. IBM has

reconsidered the investment in 31-bit support on a zSeries

server to encourage our customers to move forward. This

offering is available for 6 months for each z/OS license

(5694-A01) starting from the registration of a z/OS license

to a z/Architecture server. This offering only applies to

z/OS Version 1 Releases 2, 3, and 4, and will not be pro-

vided for z/OS 1.5 or for any z/OS.e releases.

This information is being provided to you to facilitate

release planning and to help ensure appropriate position-

ing for future software migrations.

Note: Speciﬁ c functions might only be available on the

up-level systems, or it might be necessary to up-level all

systems to enable some functions.

For additional information on z/OS planning, refer to z/OS

and z/OS.e Planning for Installation, available on the z/OS

Web site in the z/OS Library at: ibm.com/servers/eserver/

zseries/zos.

For the latest information regarding z/OS and OS/390

marketing and service withdrawal dates visit: ibm.com/

servers/eserver/zseries/zos/support/zos_eos_dates.html.

Wizards

z/OS wizards are available on the Internet to help to set

up some of the z/OS functions. These wizards are interac-

tive assistants that ask a series of questions about the

task to be performed (for example, setting up a Parallel

Sysplex environment). The wizards can simplify planning

and conﬁ guration by exploiting recommended values and

by building customized checklists. For conﬁ guration tasks,

these wizards also generate outputs like jobs, policies, or

parmlib members that can be uploaded to z/OS.

For more information about wizards visit the Web site at:

ibm.com/servers/eserver/zseries/zos/wizards/.

z/VM

Order z/OS through the Internet

ShopzSeries (formerly SHOPS390) provides an easy way

to plan and order your z/OS ServerPac or CBPDO. It will

analyze your current installation, determine the correct

product migration, and present your new conﬁ guration

based on z/OS. Additional products can also be added to

your order (including determination of whether all product

requisites are satisﬁ ed).

IBM Service is available through ShopzSeries as an Inter-

net-based, strategic software tool available to fulﬁ ll orders

24x7 (365 days a year). Through Service in ShopzSeries,

customers can quickly and easily order and receive cor-

rective or preventive service electronically over the Internet

or by standard physical media. For preventive service,

customers can order just critical service (HIPERs and PTFs

that resolve PE PTFs), the latest recommended service

(which includes all critical service), or all available service.

Service in ShopzSeries reduces customers’ research time

and effort by using their uploaded SMP/E Consolidated

Software Inventory (CSI) so that all applicable service,

including reach ahead service, for the installed FMIDs in

the target zones is selected. ShopzSeries also uses the

CSI information to limit the size of the service order, only

sending applicable service that has not already been

processed by SMP/E. IBM Technical Support is available

through RETAIN for problems and Q&A.

ShopzSeries is available in the U.S. and several countries

in Europe. In countries where ShopzSeries is not available

yet, please contact your IBM representative (or Business

Partner) to handle your order via the traditional IBM order-

ing process.

For more details and availability, visit the ShopzSeries Web

site at: ibm.com/software/shopzSeries.

The infrastructure for on demand environments can be

deployed with visionary technology on z/VM, including

advanced virtualization, support for open-source soft-

ware, and autonomic computing enhancements. With

virtualization technology as its foundation, z/VM continues

to provide new function and technology exploitation on

the mainframe that enables you to virtualize processor,

communication, memory, storage, I/O, and networking

resources, with the potential to help reduce the need to

plan for, purchase, and install hardware to support new

workloads.

z/VM supports Linux, one of the world’s leading Open

Source operating system, on the mainframe. Within the VM

environment, Linux images can share hardware resources

and use internal high-speed communications. While ben-

eﬁ ting from the reliability, availability and serviceability of

zSeries servers, z/VM V4 offers an ideal platform for con-

solidating select UNIX, Windows, and Linux workloads on

a single physical zSeries server, which allows you to run

tens to hundreds of Linux images. z/VM V4 is priced on a

per-engine basis and supports IBM Integrated Facility for

Linux (IFL) engines for Linux-based workloads, as well as

standard engines for all other zSeries and S/390 workloads.

z/VM V4 is the follow-on product for VM/ESA® and z/VM V3.

It provides additional support and exploitation opportuni-

ties for the thousands of users who have built enterprise-

wide automation and infrastructure enhancements on the

VM platform in support of their applications, database

systems, and on demand business solutions.

z/VM V5 offers new levels of price/performance, functional

capabilities, and hardware exploitation that increase the

attractiveness of deploying Linux solutions on the main-

frame. You can add capacity to existing zSeries systems

for hosting Linux on z/VM workloads by conﬁ guring their

server with IFL engines. z/VM V5 is the follow-on product

to z/VM V4.

z/VM Version 3 (V3)

z/VM offers a new technology base for customers look-

ing to use IBM Virtual Machine technology on one of the

industry’s best-of-breed server platform, zSeries. When

z/VM is running on a zSeries server, it’s possible to run 64-

bit capable OS/390 2.10, z/OS, and Linux on zSeries as

guest systems of z/VM, in addition to ESA/390 guest oper-

ating systems such as OS/390, VSE/ESA, TPF, and Linux

on S/390. To operate z/OS as a guest of z/VM on a zSeries

server, z/VM must be operating in 64-bit mode. z/VM will

allow customers to develop and test their 64-bit Parallel

Sysplex applications in a guest environment before putting

them into production. This may help reduce the need to

invest in separate standalone conﬁ gurations.

z/VM can also reduce storage constraints by eliminating

the 2 GB central storage limitation, providing plenty of

headroom for increasing on demand business require-

ments and growing back-ofﬁ ce applications within a single

machine image. Customers experiencing real memory

constraints can experience relief by running z/VM in 64-bit

mode on a zSeries server. This constraint relief is provided

for ESA/390 guest operating systems. Support for large

real memory with z/VM may beneﬁ t customers running a

large number of Linux on zSeries and S/390 guest systems.

• Capability and usability improvements to FTP server for Web browsers

• Reduced load on hosts with support for IP Multicasting

• Improved data transfer performance with QDIO supporting Gigabit Ethernet, Fast Ethernet, and 155 ATM (Ethernet LAN Emulation)

• Support for the DFSMS/MVS

Program Management binder and loader functionality to enhance application afﬁ nity between CMS and OS/390 or z/OS

Note: z/VM V3.1 has been withdrawn from marketing effec-

tive August 27, 2004.

z/VM Version 4 (V4)

With z/VM and the IBM Integrated Facility for Linux (IFL), a

low-cost, ﬂ exible environment is created to test and develop

on Linux while running Linux production applications on

IBM z990, z890, z900, z800, S/390 Parallel Enterprise

Server Generation 5 and 6, S/390 Multiprise 3000, or

equivalent servers. Support for IFL processor features by

z/VM V4 or later is designed to run Linux workloads with-

out increasing the IBM software charges for z/OS, z/OS.e,

OS/390, VM, VSE/ESA, or TPF operating systems and

applications running on standard engines of the z990, z890,

z900, z800, and S/390 servers in other logical partitions.

Additional enhancements in z/VM V3 include:

• Native FlashCopy for Enterprise Storage Server (ESS) for high-speed data copy

• Guest support enhancements for 3494 VTS and FICON attached 3590 A60 Tape Controller

Connectivity enhancements for TCP/IP Feature for z/VM:

• Improved security with the inclusion of a Secure Socket Layer (SSL) server

• Transparent data access to remote systems data with an NFS Client

Engine-based pricing for z/VM V4 and its optional features

allows customers the opportunity to exploit the zSeries

and S/390 servers more cost effectively than a discrete

server implementation. With engine-based pricing, cus-

tomers pay a one-time software license charge (OTC) for

each processor engine. This can be for standard proces-

sor engines or IFL engines. Traditional operating systems

such as z/OS, z/OS.e, OS/390, TPF, VSE/ESA, z/VM V3.1,

or VM/ESA are not supported nor can they operate on IFL

engines. Only Linux workloads in an LPAR or Linux guests

of z/VM V4 or later can operate on the IFL engine.

z/VM provides the capability to account for the use of

system resources by virtual machines, including those run-

ning Linux. Accounting records are produced that track a

virtual machine’s use of processor, paging, I/O, and virtual

network resources, including virtual channel-to-channel

adapters (CTCAs), inter-user communication vehicle (IUCV)

or advanced program-to-program (APPC) connections, and

virtual (guest LAN) network interface cards (NICs).

z/VM V4.4 extends its virtualization technology in support of

Linux and other guests while providing some enhancements

that enable z/VM to be self-optimized and self-managed:

• Reducing contention for the z/VM Control Program (CP) scheduler lock may help increase the number of Linux and other guest virtual machines that can be managed concurrently.

• Enhancing the Virtual Machine Resource Manager (VMRM) to provide the infrastructure necessary to support more extensive workload and systems resource management features by providing:

– monitor data showing actual workload achievement

– an interface to dynamically change users in work-

loads, workload characteristics, and goals

– more ﬂ exibility using the VMRM conﬁ guration ﬁ le when

managing multiple users

– improvements in the reliability and performance of the

VMRM service virtual machine’s monitor data handling

– serviceability enhancements including improved mes-

sages, logﬁ le entries, and new server options

• Simulating virtual FICON CTCA devices for guest operating systems enhances previous virtual-CTCA support by adding the FICON protocol as an option for guest operating systems. Guests use virtual CTCAs to communicate among themselves within a single z/VM system image, without the need for real FICON CTCAs.

• Supporting real and virtual integrated 3270 console devices. Real support enables this device, provided by the Hardware Management Console (HMC) to be used as the system operator console. Virtual support enables testing of guest operating systems and utilities such as Stand-Alone Program Loader (SAPL) and standalone DASD Dump-Restore (DDR), that support the integrated 3270 console device.

Delivering the Performance Toolkit for VM™ to process

•

performance data obtained from the Resource

Linux

Management Facility (RMF) Performance Monitoring (PM) client

application, rmfpms. Linux performance data obtained from RMF is presented on display screens and in printed reports

similar to the way VM data is viewed and

presented.

With corresponding function available in Linux on zSeries

and S/390, z/VM V4.4 provides:

• The attachment of Small Computer System Interface (SCSI) devices to guest Linux images using Fibre Channel Protocol (FCP) channels on zSeries processors

• IPL from FCP-attached disks for Linux and other guest operating systems with necessary SCSI support, when z/VM is running on a z990, z890, z900, or z800 server equipped with the SCSI IPL Feature Enabler

• Enhanced page-fault handling

• Clear-key RSA functions of the IBM PCI Cryptographic Coprocessor (PCICC) or the IBM PCI Cryptographic Accelerator (PCICA).

Exploiting New Technology

z/VM provides a highly-ﬂ exible test and production environ-

ment for enterprises deploying the latest on demand busi-

ness solutions. Enterprises that require multi-system server

solutions will ﬁ nd that z/VM helps them meet the demands

of their businesses and IT infrastructures with a broad

range of support for such operating system environments

as z/OS, z/OS.e, OS/390, TPF, VSE/ESA, CMS, and Linux

on zSeries and S/390. The ability to support multiple

machine images and architectures enables z/VM to run

multiple production and test versions of zSeries and S/390

operating systems, all on the same system. z/VM can help

simplify migration from one release to another, facilitate

the transition to newer applications, provide a test system

whenever one is needed, and consolidate several systems

onto one physical machine. z/VM can also be used to pro-

vide virtual access to the latest DASD and processor archi-

tecture for systems that lack such support.

New technological enhancements in z/VM V4.4 provide

• Exploitation of the zSeries 890 and 990 server

– extending Dynamic-I/O conﬁ guration support allows

channel paths, control units, and devices to be dynamically added, changed, and deleted in a Logical Channel SubSystem (LCSS) environment

– support for extended I/O-measurement facilities

provides improved capacity planning and I/O performance measurement

– handling I/O-conﬁ guration deﬁ nition and dynamic-I/O

conﬁ guration in an environment of up to 30 LPARs, an increase from the previous limit of 15

• Support for the zSeries capability to cascade two FICON directors within a Fibre-Channel fabric. z/VM and its guests can take advantage of this enhanced and simpliﬁ ed connectivity, which is particularly useful in disasterrecovery and business continuity situations.

• Support for the IBM TotalStorage Enterprise Storage Server (ESS) FlashCopy V2 providing increased ﬂ exibility for improved capacity management and utilization.

• Support for the IBM ESS Peer-to-Peer Remote Copy Extended Distance (PPRC-XD) function, extending the distance well beyond the 103 km supported with PPRC synchronous mode. PPRC-XD is suitable for data migration, backup, and disaster recovery procedures. PPRC Version 2 (V2) is also supported for guest operating

systems, offering an asynchronous cascading solution providing a complete, consistent, and coherent copy of data at a remote site.

• Support for IBM TotalStorage Enterprise Tape Controller 3592 Model J70 and Tape Drive 3592 Model J1A, this including support of Write Once Read Many (WORM) data cartridges.

Systems Management

Improvements in systems management some of which

help to provide self-conﬁ guring, self-managing, and self-

optimization facilities in z/VM V4.4 include:

• Functions that may be called by client applications to allocate and manage resources for guests running i

z/VM virtual machines (virtual images). Use of the appli-

tion programming interfaces (APIs) through an application provided by a customer or solution provider are designed so that such applications can allow administra-

tors who lack in-depth VM knowledge to manage a large

number of virtual images, running in a single z/VM system.

• Hardware Conﬁ guration Manager (HCM) and Hardware Conﬁ guration Deﬁ nition (HCD) components to create and manage your I/O conﬁ guration. This new support provides a comprehensive, easy-to-use I/O-conﬁ guration-management environment similar to that available with the z/OS operating system.

• Performance Toolkit for VM that provides enhanced capabilities for a z/VM systems programmer, operator, or performance analyst to monitor and report performance data. The toolkit is an optional, per-engine-priced feature derived from the FCON/ESA program (5788-LGA), providing:

– full-screen mode system console operation and man-

agement of multiple z/VM systems

– post-processing of Performance Toolkit for VM history

ﬁ les and of VM monitor data captured by the MONWRITE utility

– viewing of performance monitor data using either Web

browsers or PC-based 3270 emulator graphics

The toolkit also provides the capability to monitor TCP/IP

for z/VM, as well as to process Linux performance data.

Application Enablement

• C/C++ for z/VM Compiler (5654-A22)

CMS will host the new C/C++ for z/VM compiler (5654-

A22). This environment allows C/C++ programs to be compiled and executed on CMS and creates portability between z/VM and z/OS C/C++ programs. C/C++ source ﬁ les can be read from a CMS minidisk, the SFS, or the Byte File System (BFS) and output can be written to any of these ﬁ le systems. C/C++ will only execute on z/VM V4.4 and can only be licensed to operate on standard processor engines. In order to support the C/C++ for z/VM compiler, the C/C++, the Language Environment has been updated to the level shipped with z/OS V1.4 and is integrated into the base of z/VM V4.4.

• IBM Debug Tool for z/VM V4.1 (5654-A23)

IBM Debug Tool for z/VM V4.1 (5654-A23) is an IBM inter-

active source-level debugging tool for compiled applica-

tions. It helps you increase debugging efﬁ ciencies and aids

in reducing application-development cycle times. This pro-

gram testing and analysis aid helps you examine, monitor, and control the execution of application programs written

in C, C++, COBOL, or PL/I on a z/VM system. By using the

disassembly view, Debug Tool can also supports programs

compiled with the NOTEST compiler option and applications that include other languages such as Assembler.

Networking with z/VM

TCP/IP for z/VM delivers expanded Internet/intranet

access, improved on demand business performance

and extended function. Performance of the TCP/IP stack

was enhanced by redesigning algorithms to reduce path

lengths, recoding procedures to optimize high-use paths,

identifying and implementing performance improvement

items, and adding virtual multiprocessing capabilities.

TCP/IP is designed to support the z/Architecture

HiperSockets function for high-speed communication

among virtual machines and logical partitions within the

same zSeries server. The HiperSockets function allows vir-

tual machines and logical partitions to communicate inter-

nally over the memory bus using the internal-queued-direct

(IQD) channel type in the z990, z890, z900, and z800. TCP/

IP broadcast support is now available for the HiperSockets

environment when utilizing Internet Protocol version 4 (IPv4)

with z/VM V4.4. Applications that use the broadcast function

can now propagate frames to all TCP/IP applications.

The z890 and z990 servers include an important perfor-

mance enhancement that virtualizes adapter interruptions

and can be used with V=V guests (pageable guests) on

z/VM V4.4. With the enhancement of the TCP/IP stack in

z/VM V4.4 to use adapter interruptions for OSA-Express,

TCP/IP for VM can beneﬁ t from this performance assist for

both HiperSockets and OSA-Express adapters.

z/VM V4.4 exploits the Virtual Local Area Network (VLAN)

technology. VLANs ease the administration of logical

groups of users so that they can communicate as if they

were on the same physical LAN. VLANs help increase

trafﬁ c ﬂ ow and may help reduce overhead to allow the

organization of networks by trafﬁ c patterns rather than by

physical location. To support VLAN, z/VM V4.4 provides:

• Enhancements to TCP/IP for z/VM to enable membership in a VLAN for QDIO and HiperSockets adapters

• Enhancements to z/VM guest-LAN simulation to allow virtual QDIO and HiperSockets adapters to participate in a VLAN

• Management and control of VLAN topology by the z/VM virtual switch

The guest LAN support provided in z/VM V4.2 simulates

the HiperSockets function for communication among

virtual machines without the need for real IQD channels,

much as VM simulates channel-to-channel adapters for

communication among virtual machines without the need

for ESCON, FICON, or other real channel-to-channel con-

nections. With the guest LAN capability, customers with

S/390 servers can gain the beneﬁ ts of HiperSockets com-

munication among the virtual machines within a VM image,

since no real IQD channels are required.

z/VM V4.4 further enhances its virtualization technology by

providing the capability to deploy virtual IP switches in the

guest LAN environment. The z/VM virtual switch replaces

the need for virtual machines acting as routers to provide

IPv4 connectivity to a physical LAN through an OSA-

Express adapter. Routers consume valuable processor

cycles and require additional copying of data being trans-

ported. The virtual-switch function alleviates this problem

and also provides centralized network conﬁ guration and

control. These controls allow the LAN administrator to

more easily grant and revoke access to the network and to

manage the conﬁ guration of VLAN segments.

TCP/IP for z/VM provides numerous self-protection func-

tions. A Secure Sockets Layer (SSL) server is available to

facilitate secure and private conversations between z/VM

servers and external clients. The upgraded SSL server in

z/VM V4.4 provides appropriate RPM format packages for

the SUSE LINUX Enterprise Server 8 (SLES 8). Security

of the TCP/IP stack has been improved to help prevent

additional types of Denial of Service (DoS) attacks includ-

ing: Smurf, Fraggle, Ping-o-Death, Kiss of Death (KOD),

KOX, Blat, SynFlood, Stream, and R4P3D. The overall

security and auditability of the TCP/IP for z/VM stack and

the integrity of the z/VM system have been improved by

providing

better controls, monitoring, and defaults. An IMAP

user authentication exit has been added that removes prior

user ID and password length restrictions and eliminates the

need for every IMAP client to have a VM user ID and pass-

word.

TCP/IP for z/VM, formerly a priced, optional feature of

VM/ESA and z/VM V3, is packaged at no additional charge

and shipped enabled for use with z/VM V4 and V5. The

former priced, optional features of TCP/IP — the Network

File System (NFS) server and TCP/IP source — are also

packaged with TCP/IP for z/VM at no additional change.

In addition to the new function provided by the Performance

Toolkit for VM, RealTime Monitor (RTM), and Performance

Reporting Facility (PRF) are still available in z/VM V4.4 to

support new and changed monitor records in z/VM. RTM

simpliﬁ es performance analysis and the installation man-

agement of VM environments. PRF uses system monitor

data to analyze system performance and to detect and

diagnose performance problems. RACF for z/VM is avail-

able as an priced, optional feature of z/VM V4 and provides

improved data security for an installation. RTM, PRF, and

the Performance Toolkit are also priced, optional features of

z/VM V4 as is the Directory Maintenance Facility (DirMaint).

z/VM Version 5 (V5)

z/VM continues the evolution of its premier world-class

zSeries virtualization technology with a new version z/VM Ver-

sion 5 Release 1, offering traditional capabilities to manage

zSeries operating systems, including Linux, on a single main-

frame as guests of z/VM. z/VM V5.1 is designed to operate

only on zSeries servers that support the z/Architecture (64-

bit) including the z990, z890, z900, and z800 or equivalent.

Engine-based Value Unit Pricing

z/VM V5 introduced engine-based Value Unit Pricing which

replaces the per-engine pricing model that is available

with z/VM V4 as well as providing a lower entry price.

Engine-based Value Unit pricing is designed to provide a

decreasing price curve which may help provide improved

price/performance as hardware capacities and work-

load grow. Value Unit pricing for z/VM V5 can provide for

a lower price per processor engine as more processor

engines are licensed with z/VM V5.1 across the enterprise.

Value Unit Pricing helps you to:

• Add capacity and workload with an incremental and improved price

• Manage software costs better

• Aggregate licenses acquired across machines that are part of your enterprise

Engine-base Value Unit Pricing of z/VM V5 should not be

tied to, or associated with, MSU-based Value Unit Pricing.

Enhancements in z/VM V5.1 include:

Virtualization Technology and Linux Enablement

• Support for SCSI FCP disks enable the deployment of a Linux server farm on z/VM using only SCSI disks. SCSI disks can be used as such by guests through dedicated FCP subchannels, and are also supported as emulated 9336 Fixed-Block Architecture (FBA) devices for use by guests, CMS, and CP. With this support, you can install, IPL, and operate z/VM from SCSI disks. The z/VM SCSI support for system disks is based on emulation of the IBM FB-512 disk architecture and this emulation is also available for guest use. VM supports an individual emulated FBA disk up to 381 GB in size. However, directory, paging, and spooling allocations must reside within the ﬁ rst 64 GB of a CP-formatted volume. Other kinds of CP allocations may be deﬁ ned beyond the ﬁ rst 64 GB.

• z/VM V5.1 includes the capability to install z/VM both from a DVD to an ESS SCSI disk emulated as a FBA device and a 3390 DASD. Installing from a DVD can signiﬁ cantly reduce the required installation media and allows you to install to a zSeries server using only SCSI disks. This is expected to be most beneﬁ cial in a z/VM environment with Linux guests and without traditional installation devices such as IBM TotalStorage tape drives attached to the IBM zSeries server.

• Coordinated near-continuous availability and disaster

recovery for Linux guests by providing a new HyperSwap

function so that the virtual devices associated with one real disk can be swapped transparently to another. HyperSwap can be used to switch to secondary disk storage subsystems mirrored by Peer-to-Peer Remote Copy (PPRC). HyperSwap is exploited by GDPS 3.1 to provide a coordinated near-continuous

availability and disaster recovery solution for distributed applications, such as WebSphere, that span z/OS images running natively and Linux guests running under z/VM.

• PCIX Cryptographic Coprocessor (PCIXCC) support provides z/OS and Linux guest support for the PCIXCC Feature available with the z990 and z890 severs. Delivery of the z/VM PCIXCC support satisﬁ es the Statement

of Direction made on May 13, 2003. z/VM V5.1 supports the third-generation cryptographic feature, Crypto Express2, which replaces the PCICA and PCIXCC features. Crypto Express2 combines the functions of both

PCICA and PCIXCC in one feature providing improved secure-key operations. Coincident with the availability of this new cryptographic hardware feature, z/VM V5.1 pro-

vides support for Crypto Express2 clear-key cryptographic

functions for Linux for zSeries guests and clear-key and secure-key cryptographic functions for z/OS guests.

• The Systems Management APIs, introduced in z/VM V4.4, provided a basic set of functions that may be called by applications to allocate and manage resources for guests running in z/VM virtual machines

(virtual images). Although these APIs are primarily

intended for managing Linux virtual images, they can be used to manage many types of z/VM virtual machine. All enhancements to the APIs in z/VM V5.1 have been implemented using Version 2 (V2) of the RPC server. In addition to usability enhancements, new functions include:

– DASD volume management for virtual images

– VMRM conﬁ guration ﬁ le management

– Query status of active images

– Query VMRM measurement data

– Removal of user ID entries in an authorization ﬁ le

with a single request

– Query all shared storage segments instead of

one at a time

• A new programming service is provided by an emulated DIAGNOSE instruction that helps enable a guest virtual machine to specify an action to be taken by CP when the guest becomes unresponsive. A time interval and action are speciﬁ ed by the guest. If the guest fails to reissue the DIAGNOSE instruction within the speciﬁ ed time interval, CP performs the action.

• A new publication, Getting Started with Linux on zSeries, describes z/VM basics and how to conﬁ gure and use z/VM functions and facilities to create and manage Linux servers running on zSeries processors. The publication is designed to help systems personnel (system programmers, administrators, and operators) with limited knowledge of z/VM deploy Linux servers on z/VM more quickly and more easily.

Network Virtualization and Security

• The virtual IP switch, introduced in z/VM V4.4, was designed to improve connectivity to a physical LAN for hosts coupled to a guest LAN. The virtual switch has been enhanced to provide enhanced failover support for less disruptive recovery for some common network failures helping to provide business continuity as well as infrastructure reliability and availability. With the PTFs

for APARs VM63538 and PQ97436, z/VM V5.1 supports Layer 2 mode for OSA-Express and OSA-Express2. The enhanced virtual switch support provides a new transport option to allow the virtual switch to operate in Layer 2 mode. In this mode, each port on the virtual switch is referenced by its Media Access Control (MAC) address instead of by an Internet Protocol (IP) address. Data is transported and delivered in Ethernet frames, providing the ability to send and receive protocol-independent trafﬁ c for both IP (IPv4 or IPv6) and non-IP, such as IPX, NetBIOS, or SNA.

• Authorization capabilities have been enhanced for z/VM guest LANs and virtual switches by using Resource Access Control Facility (RACF) or any equivalent External Security Manager (ESM) that supports this function. It is designed to provide ESM centralized control of authorizations and Virtual LAN (VLAN) assignment.

• More Device Connections for TCP/IP for z/VM

TCP/IP stack utilization improvements for OSA-Express

–

For the z890 and z990 servers, the number of TCP/IP

stacks that can share an OSA-Express increases per logical partition (LPAR) from 84 to 160 on October 29,

2004. This increase provides additional connections to enable more virtual machines to be connected to an external network and is supported with the PTFs for APARs PQ91421 and VM63524 for z/VM 3.1, 4.3, 4.4, and 5.1.

– Improved virtualization supporting more TCP/IP stacks

with OSA-Express2

With the new OSA-Express2 feature on the z890 and

z990, available January 28, 2005, the number of connections (TCP/IP stacks) allowed can be increased up to 640. Support for 640 TCP/IP stacks is applicable to the OSA-Express2 features (Gigabit Ethernet SX, Gigabit Ethernet LX, 10 Gigabit Ethernet LR) running in QDIO mode only. z/VM V5.1 supports this new capability to allow additional connections to virtual machines, particularly Linux images, with the PTFs for APARs PQ91421 and VM63524.

Technology Exploitation

• z/VM 5.1 supports the z890 and the z990 including:

– Four Logical Channel SubSystems (LCSSs) on the

z990 and two on the z890

– Transparent sharing of internal and external channel

types across LCSSs

– Open Systems Adapter-Express Integrated Console

Controller (OSA-ICC) function

– Crypto Express2 for z/OS and Linux guests

– OSA-Express2 Gigabit Ethernet (GbE) and 10 GbE

– FICON Express2 requires PTF for HCM/HCD APAR

VM63610

– FCP LUN Access Control for added control of SCSI

devices and is supported by z/VM V5.1 on the z990 and z890 with the PTF for APAR VM63328.

– Up to 24 real processor engines in a single z/VM

image on a z990 satisﬁ es the Statement of Direction made on May 13, 2003.

• IPv6 support for guest LANs has been enhanced to allow the z/VM TCP/IP stack to be conﬁ gured for IPv6 networks connected through an OSA-Express and OSAExpress2 operating in QDIO mode. The stack can be conﬁ gured to provide static routing of IPv6 packets and to send IPv6 Router Advertisements. In addition, support is being provided to help application developers to develop socket applications for IPv6 communications.

(PRF and RealTime Monitor (RTM)) to help manage your

performance more efﬁ ciently. Other new function includes

• High-level Linux reports based on application monitor records created by SUSE LINUX Enterprise Server 8 (SLES 8)

• New reports for SCSI disks

• Support for application monitor records created by SLES 9 with the PTF for APAR VM63580

Note: Delivery of equivalent function to PRF in the

Performance Toolkit for VM satisﬁ es the Statement of

Direction made on May 13, 2003 to remove the RTM and

PRF features in a future release of z/VM. The RTM and

PRF features have been withdrawn from z/VM V5.1. These

features are still available with z/VM V4.4 but cannot be

licensed with z/VM V5.1.

For further information see the

GM13-0137.

z/VM Reference Guide

Systems Management Improvements

The Performance Toolkit for VM has been enhanced in

z/VM V5.1 to provide functional equivalence to the Perfor-

mance Reporting Facility (PRF) priced, optional feature,

thereby virtually eliminating the need for separate products

VSE/ESA

VSE clients with growing core VSE workloads, growing

Linux workloads, or both will ﬁ nd the z890 to be a robust,

cost-effective server solution and a unique opportunity to

reduce IT cost though infrastructure simpliﬁ cation.

VSE/ESA is designed to protect extensive customer invest-

ments in existing core VSE applications, data, IT skills,

equipment, business processes, and end user training.

Standards-based, no-charge connectors provide ﬂ exible

interoperability between VSE and Java technology-capable

platforms such as Linux on zSeries. Connectors enable

Linux-based applications to access core VSE applications

and data. In addition, optional priced IBM middleware such

as CICS Transaction Gateway, DB2 UDB or DB2 Connect,

and WebSphere MQ complement VSE connectors.

VSE, Linux (exploiting IFLs), z/VM, and z890 are a compelling

combination for VSE clients seeking a competitive IT advan-

tage. New, state-of-the-art Linux-based Web applications and

existing VSE applications and data can form comprehensive,

integrated solutions that combine the best of on demand

business with traditional transaction and batch processing.

z/OS remains an attractive migration target for some VSE

clients. Afﬁ nity between VSE and z/OS has been an endur-

ing part of IBM’s strategy for VSE. One objective of afﬁ nity

is to help ensure that clients can adapt their core VSE

assets and skills to z/OS.

combination of VSE and Linux even more effec

encryption assist, and OSA-Express adapter

VSE/ESA 2.6 and 2.7 operate in 31-bit mode in

a 31-bit guest under z/VM. Linux for zSeries is

new applications requiring 64-bit capability.

z/VSE

z/VSE will be the replacement product for VSE/ESA and

is anticipated to be the basis for future VSE development.

z/VSE will continue the VSE tradition of providing robust,

cost-effective mainframe solutions. z/VSE is designed to

bring the value of innovative zSeries technologies to VSE

clients. It will continue to emphasize investment protection,

network integration, and infrastructure simpliﬁ cation. z/VSE

will focus on exploiting synergies with Linux on zSeries.

When available, z/VSE 3.1 plans to add support for FCP-

attached SCSI disks to the z890 items already included

in VSE/ESA 2.7. z/VSE can execute in 31-bit mode only. It

does not implement z/Architecture, and speciﬁ cally does

not implement 64-bit mode capabilities. z/VSE is designed

to exploit selected features of IBM zSeries hardware. Linux

for zSeries is available for new on demand business appli-

cations requiring 64-bit capability.

Note: All statements regarding IBM’s plans, directions, and

intent are subject to change or withdrawal without notiﬁ ca-

tion. For more information on VSE, see the VSE Web site at

ibm.com/servers/eserver/zseries/os/vse.

tive), PCICA

interrupts.

LPARs, or as

available for

z890 is supported by VSE/ESA Version 2 Release 6 or later.

VSE/ESA 2.6 support includes zSeries features such as

FICON Express, FICON Express2, OSA-Express, OSA-

Express2, OSA-Integrated Console Controller, up to 30

LPARs, and up to two Logical Channel SubSystems (4

on z990). VSE/ESA 2.7 adds HiperSockets

(to make the

To learn more

Visit the zSeries World Wide Web site at ibm.com/eserver/

zseries or call IBM DIRECT at 1 800 IBM-CALL in the U.S.

and Canada.

Australia 132 426

Austria 0660.5109

Belgium 02-225.33.33

Brazil 0800-111426

China (20) 8755 3828

France 0800-03-03-03

Germany 01803-313233

Hong Kong (20) 2825 6222

Hungary 165-4422

India (80) 526 9050

Indonesia (21) 252 1222

Ireland 1-850-205-205

Israel 03-6978111

Italy 167-017001

Japan 0120 300 426

Korea (02) 781 7800

Malaysia (03) 717 7890

Mexico 91-800-00316

Netherlands 020-513.5151

New Zealand 0800-801-800

Philippines (02) 819 2426

Poland (022) 878-6777

Singapore 1800 320 1975

South Africa 0800-130130

Spain 900-100400

Sweden 020-220222

Switzerland 0800 55 12 25

Taiwan 0800 016 888

Thailand (02) 273 4444

Vietnam Hanoi (04) 843 6675

Vietnam HCM (08) 829 8342

United Kingdom 0990-390390

Endnotes:

1) The GbE features support two ports per feature and the 10 GbE feature supports one port per feature.

2) For SNA trafﬁ c in QDIO mode use Enterprise Extender or TN3270E.

3) IEEE 802.1q,

4) When the OSA-Express2 GbE features become available, the OSAExpress Gigabit Ethernet features will no longer be orderable.

5) The OSA-Express2 10 Gigabits per second (Gbps) link data rate does not represent the actual throughput of the OSA-Express2 10 GbE feature. Actual throughput is dependent upon many factors, including trafﬁ c direction, the pattern of acknowledgement trafﬁ c, packet size, the application, TCP/IP, the network, disk subsystem, and the number of clients being served.

6) and OSA-Express

7) VLAN id, IEEE 802.1q

8) As of December 3, 2004, z/VM VSWITCH support exploits the Layer 2 support within the z/VM Control Program

9) and OSA-Express (GbE, 1000BASE-T Ethernet and Fast Ethernet)

10) The PCICA and PCIXCC features are no longer orderable upon the availability of the Crypto Express2 feature.

11) Crypto Express2, PCIXCC and PCICA features occupy a card slot but they do not use CHPIDs.

Integrated Marketing Communications, Server Group Route 100 Somers, NY 10589 U.S.A.

References in this publication to IBM products or services do not imply that IBM intends to make them available in every country in which IBM operates. Consult your local IBM business contact for information on the products, features, and services available in your area.

IBM, IBM eServer, IBM ^,the IBM logo, the e-business logo, AFP, APPN, BookManager, CICS, DB2, DB2 Connect, DB2 Universal Database, DFSMSdfp, DFSMSdss, DFSMShsm, DFSMSrmm, DFSMS/MVS, DFSORT, DirMaint, EKCD, Encina, Enterprise Storage Server, ESCON, FICON, FlashCopy, FFST, GDDM, GDPS, HiperSockets, Hiperspace, HyperSwap, IMS, InfoPrint, Intelligent Miner, IP PrintWay, Language Environment, MQSeries, Multiprise, MVS, Net.Data, Netﬁ nity, NetSpool, NetView, Open Class, OS/2, OS/390, Parallel Sysplex, Performance Toolkit for VM, PR/SM, Processor Resource/Systems Manager, ProductPac, pSeries, RACF, RAMAC, RefreshPac, Resource Link, RMF, RS/6000, S/390, S/390 Parallel Enterprise Server, Sysplex Timer, SystemPac, Tivoli, Tivoli Storage Manager, TotalStorage, VisualAge, VM/ESA, VSE/ESA, VTAM, WebSphere, xSeries, z/Architecture, z/OS, z/VM, and zSeries are trademarks or registered trademarks of the International Business Machines Corporation in the United States and other countries or both.

Java and all Java-based trademarks are trademarks or of Sun Microsystems, Inc. in the United States or other countries.

Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both.

UNIX is a registered trademark of The Open Group in the Unites States and other countries.

Microsoft, Windows and Windows NT are registered trademarks of Microsoft Corporation In the United States, other countries, or both.

Intel is a trademark of Intel Corporation in the United States, other countries or both.

Other trademarks and registered trademarks are the properties of their respective companies.

IBM hardware products are manufactured from new parts, or new and used parts. Regardless, our warranty terms apply.

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 conﬁ guration, the storage conﬁ guration, 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.

Photographs shown are engineering prototypes. Changes may be incorporated in production models.

This equipment is subject to all applicable FCC rules and will comply with them upon delivery.

Information concerning non-IBM products was obtained from the suppliers of those products. Questions concerning those products should be directed to those suppliers.

All customer examples described are presented as illustrations of how these customers have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics may vary by customer.

All statements regarding IBM’s future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.

Prices subject to change without notice. Contact your IBM representative or Business Partner for the most current pricing in your geography.

ZSO00525-USEN-03

GM13-0522-03

IBM Z 890 User Manual

Specifications and Main Features

Frequently Asked Questions

User Manual