Smartly essential
Ever since computing technology started to be used by the public and private sectors, some 50 years ago, its use has been relentless and the pace ever increasing. Moreover, the scope and focus have been shifting: It all used to happen in the Data Processing department, remember? Now information technology (IT) is used by virtually everyone. It is, in many ways, an integral part of our daily lives. IT is used for the common cash withdrawal at an ATM to the mining of the vast amounts of data that is generated by social applications. These applications are pushed by the requirement for a better insight into clients’ needs that would help “see it coming”.
One consequence is that organizations, in their pursuit of “a better IT”, have accumulated a huge diversity of equipment, networks, architectures, software, operational procedures, standards, and practices. The result is a complex, heavy, and inflexible infrastructure, with many components and interconnections. This burden leads to a framework that lacks common operational tools that are able to provide global and unified views and management. The diversified environments demand a vast set of skills and are labor inefficient. The IT infrastructure of the enterprise is reaching the point of being unmanageable.
CEOs1 see harnessing the benefits of technologies as a key way to differentiate their organizations and outperform the competition. So they are placing increasingly complex demands (and hopes) upon IT.
No longer just about data processing, IT is being looked upon to support the strategic initiatives of the CEO, empowering employees, and providing the means for new collaborative modes and organizational ways. Management demands adaptability and flexibility because that is the best guarantee against an uncertain future. A future that no one can foresee but, all agree, will be very different from the present.
The IBM response is an optimized smarter infrastructure, one that is flexible, scalable, and provides diversified components which are tuned to the task. Examples include online analytics and features that are managed in a cloud.
This chapter introduces the IBM zEnterprise EC12 and explains how, with its innovations and traditional strengths, it can play an essential role in a smarter IT infrastructure.
1.1 Of technology, information, architectures, and success
Rarely is there a chance to have a fresh start. Therefore, evolution is a necessity. Today, multitier workloads, and their deployment on heterogeneous infrastructures are commonplace. What is harder to find is the infrastructure setup with the robustness, flexibility, and ability to provide the high quality of service that is required by mission-critical applications. It is also hard to find an infrastructure with the characteristics that are demanded by the users and lines of business, such as availability, simplicity, and consistent response.
Creating and maintaining these high-level qualities of service from a large collection of distributed components demands significant knowledge and effort. It implies acquiring and installing extra equipment and software to ensure availability and security, monitoring, and managing. Additional manpower and skills are required to configure, administer, troubleshoot, and tune such a complex set of separate and diverse environments. Still, the resulting infrastructures are not uniform, do not scale well, and are not fully integrated.
What might be a feasible setup with a few servers becomes difficult to handle with tens of servers, and a nightmare with hundreds of servers. When it is possible, it is expensive. Often, by the end of the lifecycle of the distributed equipment, its residual value is nil. Therefore, new acquisitions, new software licenses, and recertification becomes necessary.
To compound it, there is a daily pressure to run businesses cost-effectively, while still supporting growth and innovation. Clearly, adding more hardware is not going to solve the problem, it will make it only worse. The resource-constrained environments of today need a better way.
Aligning IT with the goals of the business and the speed of IT execution with the pace of business is an absolute top priority. This calls for a transformation of the IT delivery model. The IBM vision of the future is based on new levels of efficiency and service excellence for businesses, which are driven by and from the data center. This evolution prepares systems to perform the following functions:
•Handle massive scale and integration.
•Capture, store, manage, and deliver vast amounts of data.
•Analyze and unlock the insights of the data.
Business service workloads will continue to be inherently diverse and will require dissimilar system structures on which to deploy them. Freedom to select the best placement for the applications’ component is a requirement for overall efficiency and IT optimization. One size really does not fit all.
The required infrastructure must be dynamic, automated, and possess policy-based resource provisioning, deployment, reallocation, and optimization. This smarter infrastructure is composed of diverse systems that are flexible, highly virtualized, automated, and is managed as a whole, in accordance with specified workload service-level objectives. This description finds a good fit in cloud computing.
Where “the cloud” offers standardized elements and patterned services, organizations, which are bound to their history, have largely heterogeneous environments and many tailored or purposefully built applications and computing islands. These islands seem to be antagonistic positions, but consider that both are best met by environments where resources can be finely grained and easily shared, yet subject to tight security and governance controls.
The ability to provision a piece of infrastructure (a virtual server, for instance) on demand, or order a service (and implicitly the virtual server where it runs), demands the utmost flexibility and governance from the underlying infrastructure. It requires good insight into the interplay between the infrastructure and workloads to achieve flexibility and manageability.
An essential piece of a smarter infrastructure
Upon recognizing the problem, and commanding a large spectrum of technologies, IBM is uniquely positioned to provide a solution. Management of large, heterogeneous workloads, and providing finely grained and shared-all resources, is the defining principle of the IBM high-end mainframe systems. These high-end mainframes are sustained by their built-in extreme virtualization capabilities.
The IBM zEnterprise EC12 is heir to the IBM zEnterprise 196. The zEnterprise EC12 (zEC12) is a hybrid system which IBM introduced to help overcome fundamental problems of today's IT infrastructures and simultaneously provide a foundation for the future. This integrated hybrid infrastructure has three main components:
•The IBM zEnterprise central processor complex (CPC) implements the System z platform environments.
•The IBM zEnterprise BladeCenter Extension (zBX) implements IBM POWER® and IBM System x® environments, and specialized solutions and appliances.
•The IBM zEnterprise Unified Resource Manager provides the overall management capabilities for the other components.
Figure 1-1 shows an image of the IBM zEnterprise EC12.
 
Figure 1-1 IBM zEnterprise EC12 with its management capabilities
IBM brought together multiple platforms and created a scalable solution that simplifies hardware, firmware management, support, and the definition and management of a network of virtualized servers. Thus, clients can start to replace individual islands of computing with a more integrated and hybrid infrastructure. This configuration can reduce complexity, improve security, and bring applications closer to the data that they need.
 
Terminology: In the remainder of the book, we use the designation CPC to refer to the central processor complex. The reference zEnterprise CPC includes zEC12, z196, and z114.
1.2 zEC12 technical description
In this section, we briefly review the most significant characteristics of the zEC12. Chapter 2, “Hardware overview” on page 21, provides further technical details.
The zEC12 employs leading-edge silicon-on-insulator 32 nm (CMOS 13s-SOI) and other technologies, such as storage-class memory, InfiniBand, and Ethernet. The
IBM zEnterprise EC12, when compared to its predecessor, the IBM zEnterprise 196, offers improvements in several areas. Improvements include a faster and redesigned high-frequency chip, more granularity options, better availability, and enhanced on-demand options.
The IBM zEnterprise EC12 is the first system to offer a Transactional Execution Facility, which is known in the industry as hardware transactional memory. In addition, several features are introduced, namely in the connectivity and data encryption areas, and the
IBM Flash Express for Storage Class Memory, a solid-state disk-based offering. In addition,
IBM zAware, an analytical and statistical based offering, possesses sophisticated detection and diagnostic capabilities which contribute to system availability.
zEC12 is a symmetric multiprocessor (SMP) system with a scalable design. Five models are offered:
•H20
•H43
•H66
•H89
•HA1
The model name represents the maximum number of processors that can be configured in the model (“A1” stands for 101).
The zEC12 system architecture ensures continuity and upgradability from the z196 and
IBM z10™ EC systems. Figure 1-1 on page 3 shows the IBM zEnterprise EC12 with its management capabilities.
The IBM commitment to the zEC12 and its sustained investment in the system and its predecessors is portrayed in Figure 1-2 on page 5. The figure provides a comparison of the zEC12 with previous System z systems, regarding four major attributes:
•Single engine processing capacity (based on the Processor Capacity Index (PCI)2)
•Number of engines
•Memory
•I/O bandwidth (servers use a subset of their designed I/O capability)
Figure 1-2 High End System z systems design comparison
The zEC12 has a machine type (M/T) designation of 2827 and is a two-frame system. The frames are known as the A frame and the Z frame.
The A frame contains the following elements:
•The processor cage
•Modular cooling units (different for water and air cooling)
•PCIe I/O drawers, I/O drawers, I/O cages, and their I/O features, available in several combinations
•Power supplies
•An optional integrated battery feature (IBF)
The Z frame contains the following elements:
•Two redundant Support Elements (SEs)
•PCIe I/O drawers, I/O drawers, and their I/O features, available in several combinations
•Power supplies
•An optional IBF
The SE can be used to configure and manage the zEC12 system. When configured for an ensemble environment, the SE can also be used to manage the controlled zBX.
zEC12 offers both air-cooled and water-cooled versions. If you are looking to build a green data center, water cooling and high-voltage DC power provide better energy efficiency. These features potentially lower costs, without significantly changing the system physical footprint (the water cooling option adds a few inches of depth to the back of both system frames).
The zEC12 offers top exit cabling options for power and I/O, as an alternative to having all the cables exiting under the CPC to under the raised floor. A non-raised floor installation of the zEC12 air-cooled systems is also possible, although water-cooled systems must be installed on a raised floor. Top exit cabling can also help to increase the air flow. These options are offered on new build and MES orders. The increased flexibility allows you to choose the options that best meet the requirements of your data center.
1.2.1 Processor cage
zEC12 employs the same technologies of the z196 but also incorporates new ones. The
IBM z/Architecture® processor chip is redesigned and operates at increased frequency over its predecessor, retaining industry leadership. Although the zEC12 potentially includes several hundred processor chips, only the central processor, z/Architecture, and chips are described in the section that follows.
zEC12 processor cage
On a zEC12, the processor cage houses from one to four processor books that are fully interconnected. Each book contains a multiple chip module (MCM), memory, and connectors to the PCIe I/O drawers, I/O drawers, I/O cage, and coupling link connectors. Despite the multi-book design, the system is a symmetric multiprocessor, scalable up to 120 cores.
The zEC12 is the first mainframe to implement a high-speed six-core design. At 5.5 GHz, it is the fastest commercial processor chip in the industry, at the time of writing. Each core is known as a PU (processor unit).
zEC12 is built on the proven superscalar microprocessor architecture that is already deployed on the z196. However, the PU chip has several distinctive innovations, notably in the out-of-order instruction execution design and on-chip caches. Improvements have been made in error checking and correcting (namely in the memory design) and specialized circuitry (for instance, to support improved out-of-order execution and decimal floating point operations). zEC12 is the first system to implement hardware transactional memory, through its Transactional Execution Facility.
In each book, the MCM has eight chips: six PU chips and two storage control chips. Each PU chip has either four, five, or six enabled cores. zEC12 offers two options to cool the MCMs:
•Modular radiator units (MRUs) with air-cooling backup, which exchange heat with an internal, closed-loop, water system
•Water Cooling Units which are connected to building chilled water systems with back door heat-exchange units
One of the options must be selected at the time of ordering because they are factory installed. It is also a requirement because it is not possible to convert between the options in the field.
In any model of the system, two PUs are designated as spares, and each individual PU can be transparently spared, as with the z196.
Up to 3 TB of memory are available, with up to 1 TB configurable per logical partition, as with the z196. For enhanced availability, memory is implemented as a Redundant Array of Independent Memory (RAIM). In each book, up to 960 GB can be installed, but part of this number is redundant, so up to 768 GB of usable memory can be configured. In addition,
32 GB are part of the base and reserved for the hardware system area (HSA), making the maximum amount of purchasable memory 3040 GB, just short of 3 TB (with redundancy, a total of 3.75 GB are installed). Plan-ahead memory, a capability whereby memory can be installed but not enabled for use until needed, further enhances system availability for continuous operations.
Processor unit characterization
At system initialization time, each purchased processor unit (PU) is characterized as one of various types. It is also possible to characterize PUs dynamically. A PU that is not characterized cannot be used. A PU can be characterized in the following ways:
•Central processor (CP)
The standard processor. For use with any supported operating system and user applications.
•Internal Coupling Facility (ICF)
Used for z/OS clustering. ICFs are dedicated to this function and exclusively run the Coupling Facility Control Code (CFCC).
•Integrated Facility for Linux (IFL)
Used by Linux on System z and for z/VM processing in support of Linux. z/VM is often used to host multiple Linux virtual machines (called guests). It is not possible for the
initial program load (IPL) operating systems other than z/VM or Linux on an IFL.
•System assist processor (SAP)
Offloads and manages I/O operations. Several are standard with the zEC12. More can be configured if additional I/O processing capacity is needed.
•IBM System z Application Assist Processor (zAAP)3
Used under z/OS for designated workloads, which include the IBM Java virtual machine (JVM) and XML System Services functions.
 
Statement of Direction: zEC12 is planned to be the last high-end System z server to offer support for zAAP specialty engine processors. IBM intends to continue support for running zAAP workloads on zIIP processors (“zAAP on zIIP”).
• IBM System z Integrated Information Processor (zIIP)3
Used under z/OS for designated workloads, which include various XML System Services, IPSec offload, certain parts of IBM DB2 DRDA®, star schema, IBM HiperSockets™ for large messages, and the IBM GBS Scalable Architecture for Financial Reporting.
 
zAAP and zIIP:
•Work that is dispatched on zAAP and zIIP does not incur any IBM software charges. zAAPs and zIIPs contribute to a lower cost of computing by taking some of the z/OS load that would otherwise run on CPs.
•It is possible to run a zAAP-eligible workload on zIIPs if no zAAPs are installed on the system. This capability is offered to enable the optimization and maximization of investments on zIIPs.
CP Assist for Cryptographic Function
The zEC12 continues to use the cryptographic assist implementation, first deployed in 2003, known as CP Assist for Cryptographic Function (CPACF).
CPACF is physically implemented in the six-core chip by the compression and cryptography accelerators. Each core has one dedicated coprocessor (CoP) integrating the CPACF and the compression unit. This configuration eliminates any interferences that could occur with the implementation on the z196 and z10 where two cores share the coprocessor.
The CPACF offers the full complement of the Advanced Encryption Standard (AES) algorithm and Secure Hash Algorithm (SHA) along with the Data Encryption Standard (DES) algorithm. CPACF must be explicitly enabled, using a no-charge enablement feature, except for the SHAs, which are shipped enabled with each server.
The CP Assist for Cryptographic Function supports the following functions:
•DES, which includes:
 – Single-length key DES
 – Double-length key DES
 – Triple-length key DES (also known as Triple-DES)
•AES for 128-bit, 192-bit, and 256-bit keys
•SHA:
 – SHA-1: 160 bits
 – SHA-2: 224 bits, 256 bits, 384 bits, and 512 bits
•Message authentication code (MAC):
 – Single-length key MAC
 – Double-length key MAC
•Pseudo Random Number Generation (PRNG) for cryptographic key generation
PRNG is also a standard function that is supported on the Crypto Express4S and Crypto Express3 features.
•Protected key capabilities
 
 
 
Keys: The keys must be provided in clear form only.
1.2.2 I/O subsystem
The z/Architecture defines an I/O subsystem to which I/O processing is offloaded. This is a significant contributor to the performance and availability of the system, and it strongly contrasts with the architectures of other servers.
The z/Architecture also specifies that peripheral devices are managed by control units and are reached through channels from the CPC. A control unit provides controlling function for a device or set of devices, and may be physically implemented with the device or in an independent unit.
The current generation of the I/O platform, particularly through the usage of 
Peripheral Component Interconnect Express (PCIe), InfiniBand, enhanced cards, and protocols (High Performance FICON for System z (zHPF)), is intended to provide significant performance improvements over the I/O platforms that are used on previous systems. The offerings include: I/O infrastructure elements, the PCIe I/O drawer, the I/O drawer4, and the I/O cage4.
As with its predecessors, the zEC12 implements the z/Architecture I/O subsystem through a dedicated subsystem, which is known as the channel subsystem. It is composed of the following elements:
•System Assist Processor
System Assist Processor (SAP) is a specialized processor that uses the installed PUs. (Each zEC12 PU can be characterized as one of six configurations. For more information see “Processor unit characterization” on page 7.) Its role is to offload I/O operations and manage channels and the I/O operations’ queues. It relieves the other PUs of all I/O tasks, allowing them to be dedicated to application logic. Enough SAP processors are automatically defined, depending on the model of the machine. The processors are part of the base configuration of the system.
•Hardware System Area
Hardware system area (HSA) is a reserved part of the system memory and contains the I/O configuration. It is used by SAPs. On the zEC12, a fixed amount of 32 GB is reserved, which is not part of the client-purchased memory. This amount provides for greater configuration flexibility and higher availability by eliminating planned and pre-planned outages.
•Channels
Channels are dedicated processors that communicate with the I/O control units (CUs). They manage the data transfer between memory and the external devices. Channels are contained in the I/O card features.
•Channel path
Channel paths are the means by which the channel subsystem communicates with the I/O devices. Because of I/O virtualization, multiple independent channel paths can be established on a single channel, allowing sharing of the channel between multiple logical partitions, with each partition having a unique channel path. The function that allows sharing I/O paths across logical partitions is known as the multiple image facility (MIF).
On the zEC12, the Channel subsystem enhancement for I/O resilience was introduced, providing improved throughput and reduced I/O service times.
•Subchannels
Subchannels are displayed to a program as a logical device (programs do not directly communicate with the devices) and contain the information that is required to perform an I/O operation. One subchannel exists for each I/O device addressable by the channel subsystem. The zEC12 has three subchannel sets5.
In addition to the channel subsystem, zEC12 also implements a queued direct I/O (QDIO) infrastructure, present also on predecessor systems. QDIO is a highly efficient data transfer mechanism that is designed to dramatically reduce system overhead and improve throughput by using system memory queues and a signaling protocol to directly exchange data between the OSA microprocessor and network software.
QDIO is the interface between the operating system and the OSA hardware. The other users of QDIO are HiperSockets using the QDIO Accelerator function and FICON Channels in FCP mode.
The I/O subsystem direction of the zEC12 is evolutionary, expanding on developments from the z196, and includes both PCIe and InfiniBand infrastructures (replacing the self-timed interconnect features that are found in previous System z systems). This infrastructure is designed to reduce overhead and latency and provide increased data throughput.
The PCIe I/O bus connects the processor cage to the PCIe I/O drawers. The InfiniBand I/O bus connects the processor cage to I/O drawers or the I/O cage. PCIe I/O drawers house PCIe I/O cards. I/O cages and I/O drawers house I/O cards.
Peripheral Component Interconnect Express
Peripheral Component Interconnect Express (PCIe) is a standard for computer expansion cards. It includes a serial bus standard that is used by a large variety of computer platforms. The bus operates at 8 GBps.
The PCI Special Interest Group is responsible for developing and maintaining format specifications.
PCIe in the zEC12 provides an internal I/O infrastructure that positions the system for continued support of the industry’s direction for high-performance I/O.
InfiniBand
InfiniBand is an industry-standard specification that defines a first-order interconnection technology, which is used to interconnect servers, communications infrastructure equipment, storage, and embedded systems. InfiniBand is a fabric architecture that uses switched, point-to-point channels with data transfers of up to 120 Gbps, both in chassis backplane applications and through copper and optical fiber connections.
A single connection can carry several types of traffic, such as communications, management, clustering, and storage. Additional characteristics include low processing overhead, low latency, and high bandwidth. Thus, it can become pervasive.
InfiniBand is scalable, as experience proves, from two-node interconnects to clusters of thousands of nodes, including high-performance computing clusters. It is a mature and field-proven technology, which is used in thousands of data centers.
InfiniBand is being used by the zEC12. Within the system, the cables from the processor cage to the I/O cages and I/O drawers (not the PCIe I/O drawers) carry the InfiniBand protocol. For external usage, InfiniBand (IFB) links are available to interconnect zEnterprise and z10 systems in a Parallel Sysplex (z/OS cluster). IFB links can completely replace the InterSystem Channel-3 (ISC-3) and ICB-4 offerings available on previous systems.
I/O cage
The I/O cage accommodates up to 28 I/O features, in any combination. On the zEC12, a maximum of one I/O cage is supported, when carried-forward on an upgrade from a previous system. It is housed, along with the processor cage, in the A frame.
I/O drawer
An I/O drawer provides increased I/O granularity and capacity flexibility, as compared with the I/O cage. I/O drawers can be concurrently added and removed in the field, an advantage over I/O cages, which also eases pre-planning. The zEC12 system can have up to two I/O drawers, when carried-forward on an upgrade. The drawers can be installed both on the A frame and on the Z frame. I/O drawers were first offered with the z10 BC, and each can accommodate up to eight I/O features, in any combination.
PCIe I/O drawer
The PCIe I/O drawer was introduced with the z196. This drawer provides for a higher number of cards (four times as much as the I/O drawer and a 14% increase over the I/O cage) and finer port granularity. The PCIe I/O drawers can be concurrently installed and repaired in the field. Each drawer can accommodate up to 32 PCIe I/O features in any combination. Up to five PCIe I/O drawers can be installed on the zEC12.
PCIe I/O features and I/O features
The zEC12 supports the following PCIe features, which can be installed only in the PCIe I/O drawers:
•FICON Express8S
•OSA-Express4S
•Crypto Express4S
•Flash Express
When carried forward on an upgrade, the zEC12 also supports the following I/O features, which can be installed in up to two I/O drawers or in an I/O cage:
•FICON Express8
•FICON Express4 10 KM LX and SX
•OSA-Express3 10 GbE, GbE, and 1000BASE-T
•Crypto Express3
•ISC-3 coupling links
In addition, IFB coupling links, which attach directly to the processor books, are supported.
For a description of each I/O feature that is supported by the zEC12, refer to 2.9, “I/O features” on page 35.
IBM Enterprise Systems Connection (ESCON) channels
IBM ESCON® channels represent the first use of optical I/O technology on the mainframe. They are much slower than IBM Fibre Connection (FICON) channels and provide connectivity to ESCON disks, tapes, and printer devices.
ESCON channels are not supported on zEC12. IBM Facilities Cabling Services - ESCON to FICON migration services are available for managing the transition from ESCON to FICON. This transition includes the flexible migration of ESCON devices to match your expected lifecycle and investment priorities.
IBM Fibre Connection (FICON) channels
FICON channels follow the Fibre Channel (FC) standard, support data storage and access requirements, and the latest FC technology in storage and access devices. FICON channels support the following protocols:
•Native FICON. An enhanced protocol (over FC) providing for communication across channels, channel-to-channel (CTC) connectivity, and with FICON devices such as disks, tapes, and printers. Includes the zHigh Performance FICON protocol and is used in z/OS, z/VM, IBM z/VSE® (no zHPF), z/TPF, and Linux on System z environments.
•Fibre Channel Protocol (FCP). A Standard protocol for communicating with disk and tape devices through Fibre Channel switches and directors. The FCP channel can connect to FCP SAN fabrics and access FCP/SCSI devices. FCP is used by z/VM and Linux on System z environments.
There are some restrictions on combining the FICON Express8S, FICON Express8, and FICON Express4 features.
Depending on the feature, auto-negotiated link data rates of 1, 2, 4, or 8 Gbps are supported (1, 2, and 4 for FICON Express4; 2, 4, and 8 for FICON Express8 and FICON Express8S).
FICON Express8 is the most recent feature and provides significant improvements in start I/Os and data throughput over previous cards. FICON Express8S are PCIe cards and offer better port granularity and improved capabilities. FICON Express8S is the preferred technology.
Open Systems Adapter
The Open Systems Adapter (OSA) features provide local networking (LAN) connectivity and comply with IEEE standards. In addition, OSA features assume several functions of the TCP/IP stack that normally are performed by the processor. These functions can provide significant performance benefits.
There are some restrictions on combining the OSA-Express4S and OSA-Express3. The OSA-Express2 10 GbE LR features are not supported, fulfilling the IBM Statement of General Direction.
Cryptography
The Crypto Express4S and Crypto Express3 features provide tamper-sensing and tamper-responding, high-performance cryptographic operations. Each Crypto Express4S feature has one PCI Express adapter and each Crypto Express3 feature has two PCI Express adapters. Each of the adapters can be configured in one of the modes:
•Secure IBM CCA coprocessor. For secure key encrypted transactions using CCA callable services (default).
 – Designed to support security-rich cryptographic functions, use of secure encrypted key values, and user-defined extensions (UDX).
 – Designed for Federal Information Processing Standard (FIPS) 140-2 Level 4 certification.
•Accelerator. For public key and private key cryptographic operations that are used with Secure Sockets Layer/Transport Layer Security (SSL/TLS) acceleration.
 – Designed to support high-performance clear key RSA operations.
 – Offloads compute-intensive RSA public-key and private-key cryptographic operations that are employed in the SSL/TLS protocol.
•Secure IBM Enterprise PKCS #11 (EP11) coprocessor (Crypto Express4S only): Implements industry standardized set of services that adhere to the PKCS #11.
 – Designed for extended evaluations to meet public sector requirements.
 – Designed for Federal Information Processing Standard (FIPS) 140-2 Level 4 and Common Criteria certifications.
 – Introduces the PKCS #11 secure key function.
 – Requires: CPACF and TKE workstation for management of the feature.
The features have specialized hardware to perform DES, TDES, AES, RSA, SHA-1, and SHA-2 cryptographic operations. The tamper-resistant hardware security module (HSM), which is contained in the Crypto Express4S and Crypto Express3 features, is designed to meet the FIPS 140-2 Level 4 security requirements for hardware security models.
The configurable Crypto Express features are supported by z/OS, z/VM, z/VSE, z/TPF (accelerator mode only), and Linux on System z.
A paper, which is written by atsec information security corporation, on Payment Card Industry compliance, recognizes the inherent qualities of the mainframe and the simplification in the infrastructure that it can provide. For more information, see this website:
Coupling links
Coupling links are used when clustering zEC12 and System z systems running the z/OS operating system. A clustered configuration is known as a Parallel Sysplex and can have up to 32 member nodes. The links provide high-speed bidirectional communication between members of a sysplex. The zEC12 supports the following links:
•Internal coupling (IC) links for memory-to-memory transfers between LPARs
•12x InfiniBand links for distances up to 150 meters (492 feet)
•For unrepeated distances up to 10 Km (6.2 miles):
 – 1x InfiniBand links
 – InterSystem Channel-3 (ISC-3) links, when carried forward on an upgrade
InfiniBand (HCA3-O) coupling links were introduced with the z196 to provide a performance improvement that reduces overhead and latency. Refer to 2.10.3, “InfiniBand coupling links” on page 43, for a technical description.
 
Statement of Direction: The IBM zEnterprise EC12 is planned to be the last high-end System z server to offer support of the InterSystem Channel-3 (ISC-3) for Parallel Sysplex environments at extended distances. ISC-3 will not be supported on future high-end System z servers as carry forward on an upgrade. Enterprises should continue migrating from ISC-3 features to InfiniBand Coupling Links.
HiperSockets
The HiperSockets function is an integrated function of the CPCs that provides users with attachments to up to 32 high-speed virtual local area networks with minimal system and network overhead.
HiperSockets is a function of the virtualization Licensed Internal Code (LIC) and performs memory-to-memory data transfers in a secure way. The HiperSockets function eliminates having to use I/O subsystem operations and having to traverse an external network connection to communicate between logical partitions in the same CPC. Therefore, HiperSockets offers significant value in server consolidation by connecting virtual servers and simplifying the Enterprise network.
HiperSockets improved functions (also available on z196) include the ability to integrate in the intraensemble data network (IEDN), and support for bridging to z/VM virtual switches.
Flash Express
Flash Express is an optional feature introduced with the zEC12. It is based on PCIe
Flash Express memory cards that are implemented via internal Flash Solid State Disk (SSD). This feature is designed to help improve platform resilience and system performance, and offers a capacity of 1.4 TB of usable storage per pair of cards. A maximum of four pairs of cards can be installed on a zEC12, providing a maximum capacity of 5.6 TB of storage.
When used under z/OS V1R13, Flash Express might help improve availability and handling of paging workload spikes. Using Flash Express can help availability by eliminating slow downs that can occur at the start of the workday. It can also help to eliminate delays that might occur when collecting diagnostic data during failures. Flash Express might, therefore, be able to help organizations meet their most demanding service level agreements.
Flash Express is easy to configure, requires no special skills, and provides rapid time to value. Additional usage of Flash Express is expected to be supported later.
1.2.3 Hardware Management Console and Support Element
The Hardware Management Console (HMC) and Support Elements (SEs) are appliances that together provide hardware platform management for System z. Hardware platform management covers a complex set of setup, configuration, operation, monitoring, and service management tasks and services that are essential to the use of the System z hardware.
1.2.4 Capacity on demand and performance
In the same footprint, the zEC12 101-way system can deliver up to 50% more capacity than the largest 80-way z196. The zEC12 1-way system has approximately 25% more capacity than the z196 1-way. Numerous improvements in the processor chip design, including new instructions, refinements to out-of-order execution, and restructured caches contribute to the additional capacity. Some functionality will be used only by using the latest levels of compilers and JVMs.
The zEC12 continues to offer all the specialty engines available with z196. See “Processor unit characterization” on page 7.
The zEC12 enhances the availability and flexibility of just-in-time deployment of more system resources, which is known as capacity on demand (CoD).
On the zEC12 it is possible to perform just-in-time deployment of capacity resources. This function is designed to provide more flexibility to dynamically change capacity when business requirements change. CoD provides flexibility, granularity, and responsiveness by allowing the user to change capacity dynamically as business requirements change. With the proper contracts, up to eight temporary capacity offerings can be installed on the system. Additional capacity resources can be dynamically activated, either fully or in part, by using granular activation controls directly from the management console, without having to interact with IBM Support.
The following tasks can be performed:
•Define one or more flexible configurations that can be used to solve multiple temporary situations.
•Have multiple configurations active at the same time. The configurations themselves have flexible selective activation of only the needed resources.
•Purchase capacity either before or after execution for On/Off Capacity on Demand. This capacity is represented by tokens that are used up at execution time.
•Add permanent capacity to the system while temporary changes are active.
A similar capability is not available with the zBX. For more information, see 3.6, “zEC12 capacity on demand (CoD)” on page 84.
1.3 IBM zEnterprise BladeCenter Extension
The IBM zEnterprise BladeCenter Extension Model 003 (zBX) is available as an option with the zEC12 systems. This model provides several distributed environments (IBM AIX® on POWER7®, Linux on System x, and Microsoft Windows on System x) for a blade form factor, which is connected to the zEC12 through virtual LANs supported on a high-speed private network.
The zBX is managed through the Support Elements of its controlling zEC12 and by using the Unified Resource Manager functions. In bringing together multiple platforms, IBM has created a scalable solution that simplifies hardware and firmware management and support, and the definition and management of a network of virtualized servers.
The zBX Model 003 consists of the following components:
•Up to four IBM Enterprise racks
•Up to eight BladeCenter chassis (two per rack), with up to 14 blades each
•Select IBM blades, up to 112
•Two Top of Rack (TOR) 1000BASE-T switches for the intranode management network (INMN)
The INMN provides connectivity for management purposes between the SE and zBX of the CPC.
•Two TOR 10 GbE switches for the IEDN
The IEDN is used for data paths between the zEC12 CPC and the zBX, and the other ensemble members.
•Eight Gbps Fibre Channel switch modules for connectivity to an SAN
•Power distribution units (PDUs) and cooling fans
The zBX is configured with redundant components to provide qualities of service similar to that of zEC12, such as firmware management and the capability for concurrent upgrades and repairs.
The zBX components are configured, managed, and serviced the same way as the CPC components. Although the zBX processors are not z/Architecture processors and run specific software, including hypervisors, the software intrinsic to the zBX components does not require any additional administration effort or tuning by the user. In fact, it is handled as System z Licensed Internal Code. The zBX hardware features are part of the mainframe, not add-ons.
 
Statement of Direction:
•IBM intends to deliver automated multi-site recovery for zBX hardware components that are based upon IBM GDPS® technologies. These capabilities will help facilitate the management of planned and unplanned outages across IBM zEnterprise EC12.
•IBM intends to deliver new functionality with IBM Systems Director offerings to support the IBM zBX. Such planned new capabilities will be designed to provide virtual image management and enhanced energy management functions for IBM Power Systems™ and System x blades.
The zBX Model 003 can be controlled only from a zEC12, and the zBX Model 002 can be controlled from either a z196 or a z114. However, a zEC12 can connect to, and use, a zBX Model 002 controlled by a z196 or a z114. A zBX Model 002 controlled by a z196 must be upgraded to Model 003 at the time of upgrading the controlling z196 to zEC12. During the upgrade, the virtualization and configuration data is preserved; however, the process is disruptive, and requires a planned outage.
IBM blades
IBM offers a selected set of IBM blades that can be installed and operated on the zBX Model 003. These blades were tested to ensure compatibility and manageability in the zEnterprise environment. The following blades are available:
•Select IBM POWER7 PS701 Express blades
•Select IBM System x blades (HX5 7873 dual-socket 16-core)
•IBM DataPower® XI50z blades (double-width)
The POWER7 blades offer a virtualized environment through the IBM PowerVM® Enterprise Edition hypervisor. The virtual servers run the AIX operating system. The System x blades have an integrated hypervisor using Kernel-based virtual machines (KVM), which provides a virtualized environment for running Linux and Windows operating systems.
IBM WebSphere DataPower Integration Appliance X150 for zEnterprise
The IBM WebSphere® DataPower Integration Appliance XI50 for zEnterprise
(DataPower XI50z) is integrated into the zEnterprise infrastructure. DataPower XI50z is a multifunctional appliance that can help provide multiple levels of XML optimization. It can also streamline and secure valuable service-oriented architecture (SOA) applications, and provide drop-in integration for heterogeneous environments by enabling core Enterprise Service Bus (ESB) functionality, including routing, bridging, transformation, and event handling. This appliance can help to simplify, govern, and enhance the network security for XML and web services.
For a more detailed description of the IBM DataPower X150z integration appliance, see this website:
1.4 Unified Resource Manager
The zEC12 system perfectly fits in a smart infrastructure, continuing IBM high-end systems’ leadership and being both the next step in the evolution of mainframes and a premier solution for centrally managed enterprise cloud environments. It is a true hybrid computing system that is composed of virtualized heterogeneous resources that are integrated and managed as a single system by the IBM zEnterprise Unified Resource Manager.
The Unified Resource Manager is an integral part of the zEC12 system. It provides end-to-end management of CPCs and zBX resources, and of virtualized environments, with the ability to align those resources according to individual workload requirements.
Through virtualization, the physical resources can be shared among multiple workloads. Most likely, the workloads have varying policies with different objectives. The goal of the
Unified Resource Manager is to fulfill the objectives of the workload policies in the most optimal and efficient way.
The Unified Resource Manager provides energy monitoring and management, goal-oriented policy management, increased security, virtual networking, and data management, consolidated in a single interface that can be tied to business requirements.
The functions that pertain to an ensemble are provided by the Hardware Management Console (HMC) and Support Elements. For more information see 3.3, “Hardware Management Console functions” on page 77.
The Unified Resource Manager resource management functions are delivered in tiers, by two operational suites. Within the Unified Resource Manager several roles are defined. This configuration promotes security through task isolation and authorization.
Resource management suites
The functions that are delivered by the Unified Resource Manager are accessed through the Hardware Management Console (HMC) and provide the following capabilities:
•Integrated hardware management across all elements of the system, the CPC, the zBX, and the integrated networks.
•Fully automatic and coherent integrated resource discovery and inventory for all elements of the system without requiring user configuration, deployment of libraries or sensors, or user scheduling.
•Hypervisors shipped, serviced, and deployed as zEC12 LIC. They are booted automatically at power-on reset, and managed through the isolated intranode management network (INMN).
•Virtual server lifecycle management, enabling uniform directed and dynamic virtual server provisioning across all hypervisors from a single point of control.
•Representation of the physical and virtual resources that are used in the context of a deployed business function as a named workload.
•Monitoring and trend reporting of CPU energy efficiency, which can be helpful in managing the costs of deployed workloads.
•Delivery of system activity through a new user interface, the Monitors Dashboard (which augments the existing System Activity Display), enabling a broader and more granular view of system resource consumption.
The Unified Resource Manager offers the ability to optimize technology deployment according to individual workload requirements. To achieve this optimization, the Unified Resource Manager is delivered in two suites of tiered functionality:
•Manage
•Automate/Advanced Management
Refer to the following IBM Redbooks publications to read more about Unified Resource Manager functions and capabilities:
•Building an Ensemble Using IBM zEnterprise Unified Resource Manager, SG24-7921
•IBM zEnterprise EC12 Technical Guide, SG24-8049
1.5 Ensembles
This heterogeneous infrastructure also includes the concept of ensemble: a collection of highly virtualized diverse systems that can be managed as a single logical entity, and where diverse workloads can be deployed.
Each CPC, with its optional zBX, makes up a node of an ensemble. An ensemble is composed of up to eight members, with up to eight CPCs and up to 896 blades that are housed in up to eight zBXs. There are also dedicated integrated networks for management and data, and the Unified Resource Manager function. The Unified Resource Manager provides advanced end-to-end management capabilities for the diverse environments within the zBX.
The concept of an ensemble is similar to that of a cloud. An ensemble provides a perfect infrastructure to support a cloud because the real purpose of an ensemble is to provide infrastructure resources in a way that ensures that the workloads which run on it achieve their business requirement objectives. Those objectives are specified through policies, which the ensemble implements.
 
Statement of Direction: IBM intends to deliver workload-aware optimization for IBM System x Blades in the zBX. This structure allows virtual CPU capacity to be adjusted automatically across virtual servers within a hypervisor, helping to ensure that System x resources in the zBX are used per the defined SLAs.
Diverse workloads span several platform infrastructures, so the ensemble owns the physical resources in those infrastructures and manages them to fulfill the workload policies. Ensemble resources can be shared by multiple workloads and optimized for each workload. Virtualization provides the most flexible and cost effective way to meet policy requirements.
Many mission-critical workloads today have one or more components on System z, using System z environments for database and other capabilities. The ability to collocate all of the workload components under the same management platform, and thereby benefit from uniformly high qualities of service, is appealing and provides tangible benefits and a rapid ROI.
Role of the Hardware Management Console in an ensemble
The Unified Resource Manager is installed in the Hardware Management Console (HMC), and alongside other functionality, enables extending those tasks to an ensemble.
The HMC allows viewing and managing multinodal configurations with virtualization, I/O networks, support networks, power subsystems, cluster connectivity infrastructure, and storage subsystems. The HMC has a management responsibility for the entire ensemble, while the SE has management responsibility at the node level. When tasks are performed on the HMC, the commands are sent to one or more SEs, which then issue commands to their local CPCs and zBXs. This configuration represents a well-layered structure that supports the components of the ensemble.
The HMC is used to manage, monitor, and operate one or more nodes that are configured as members of an ensemble. An ensemble is managed by a primary/alternate HMC pair.
The HMC possesses a highly interactive and dynamic web-based user interface. The views, management, and monitoring tasks of the HMC user interface provide everything that is needed for complete management of the virtual machine lifecycle across the zEnterprise hypervisors:
•IBM PR/SM™
•z/VM
•PowerVM Enterprise Edition
•System x blades integrated hypervisor (using Kernel-based virtual machines)
Virtual machines can be managed from their inception all the way through monitoring, migration, and policy-based administration during their deployment.
The HMC is the authoritative owning (stateful) component for Unified Resource Manager configuration and policies the scope of which spans all of the managed nodes in the ensemble. In addition, the HMC has an active role in ongoing system monitoring and adjustment.
Typical functions that can be performed from an HMC go beyond the simple operational start/stop actions on virtual servers. Functions also include instantiating an ensemble, defining virtual servers and workloads, and assigning those virtual servers to one or more workloads. This structure requires both the Manage and Automate suites of the Unified Resource Manager to be available. The suites are orderable features of the zEC12 system.
1.6 Reliability, availability, and serviceability (RAS)
The zEC12 continues to offer the high quality of service and reliability, availability, and serviceability (RAS) that is traditional in IBM mainframes.
The RAS strategy employs a building-block approach developed to meet the client's stringent requirements for achieving continuous reliable operation. Those building blocks are
error prevention, error detection, recovery, problem determination, service structure,
change management, measurement, and analysis.
Most hardware upgrades can be installed concurrently. The zEC12 reaches new availability levels by eliminating various pre-planning needs and other disruptive operations.
The RAS strategy is focused on a recovery design that is necessary to mask errors and make them transparent to client operations. One example is the use of Redundant Array of Independent Memory (RAIM), a concept similar to RAID (disk). An extensive hardware recovery design is implemented to detect and correct array faults. In cases where total transparency cannot be achieved, the system can restart with the maximum possible capacity.
The IBM mainframe systems have gone through decades of intense engineering development. The introduction of zEC12 adds, once again, new, carefully engineered RAS features, providing the highest possible level of RAS.
For a more detailed description of the zEC12 RAS features, see the corresponding chapter in the IBM zEnterprise EC12 Technical Guide, SG24-8049.
1.7 Software
The IBM zEnterprise EC12 is supported by a large set of software, including independent software vendor (ISV) applications. The extensive software portfolio on the zEC12 spans from IBM WebSphere; full support for service-oriented architecture (SOA); web services;
Java Platform, Enterprise Edition; Linux; and open standards; to the more traditional batch and transactional environments. Examples of these types of environments include
IBM Customer Information Control System (CICS®) and IBM Information Management System (IMS™).
For instance, considering just the Linux on System z environment, more than 3,000 applications are offered by over 400 ISVs. In addition, any AIX products that run today on
IBM POWER servers continue to run on the zBX POWER7 blades’ virtualized AIX environment, and System x blades support Linux and Windows. There are also specialized solutions such as the DataPower XI50z appliance.
Use of some features might require the latest releases. The following operating systems are supported by the zEC12:
•z/OS Version 1 Release 12 or later releases
•z/OS Version 1 Release 11 with the IBM Lifecycle Extension with PTFs
•z/OS Version 1 Release 10 with the IBM Lifecycle Extension with PTFs
•z/VM Version 5 Release 4 or later
•z/VSE Version 4 Release 3 or later
•z/TPF Version 1 Release 1
•Linux on System z distributions:
 – SUSE: SLES 10 and SLES 116
 – Red Hat: RHEL 57 and RHEL 6
The following operating systems support IBM blades on the zBX:
•For the POWER7 blades: AIX Version 5 Release 3 or later, with the PowerVM Enterprise Edition
•For the System x blades:
 – Linux on System x (64-bit only):
 • Red Hat: RHEL 5.5 and up, RHEL 6.0 and up
 • SUSE: SLES 10 (SP4) and up, SLES 11 SP1 and up
 – Windows Server 2008 R2 and Windows Server 2008 SP2 (Datacenter Edition is recommended), 64-bit only
IBM compilers
Empower your business applications with IBM compilers on the IBM zEnterprise System.
With IBM Enterprise COBOL and Enterprise PL/I, you can use decades of IBM experience in application development to integrate COBOL and PL/I with web services, XML, and Java. Such interoperability enables you to capitalize on existing IT investments while smoothly incorporating new, web-based applications into your organizations infrastructure.
z/OS XL C/C++ helps you to create and maintain critical business applications that are written in C or C++ to maximize application performance and improve developer productivity. z/OS XL C/C++ can transform C or C++ source code to fully use System z hardware, including zEnterprise. This function is possible through hardware tailored optimizations, built-in functions, performance-tuned libraries, and language constructs that simplify system programming and boost application runtime performance.
Enterprise COBOL, Enterprise PL/I, and XL C/C++ are leading-edge, z/OS-based compilers that maximize middleware by providing access to IBM DB2, CICS, and IMS systems.
More information about software support can be found in Chapter 4, “Operating system support and considerations” on page 97.
1 See the IBM 2012 Global Chief Executive Officer Study at http://www.ibm.com/ceostudy
2 PCI values can be obtained from SC28-1187 Large Systems Performance Reference, at this website: https://www-304.ibm.com/servers/resourcelink/lib03060.nsf/pages/lsprindex
3 z/VM V5 R4 and later support zIIP and zAAP processors for z/OS guest workloads.
4 No new orders. Carry forward or system upgrade only.
5 Subchannel set 0 can have up to 63.75 K devices (256 devices are reserved). Subchannels 1 and 2 can have up to 64 K devices each.
6 SLES is the abbreviation for SUSE Linux Enterprise Server.
7 RHEL is the abbreviation for Red Hat Enterprise Linux.
..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset