z196 and z114 hw subsystems update zos 2012-03-14 - z196...z114, z196, & z10 bc •2 i/o domains...

© Copyright IBM Corporation 2012

IBM System z

GSE z/OS workgroup meeting 2012/03/14

z196 and z114 HW Subsystems Update

Jean-Paul GoemaereIBM Belgium / Luxemburg


IBM System z

I/O infrastructure� New PCIe-based I/O infrastructure� New PCIe I/O drawer

� Increased port granularity

� Designed for improved power and bandwidth compared to I/O cage and I/O drawer

Storage� New PCIe-based FICON Express8S features� ESCON Statement of Direction

Networking� New PCIe-based OSA-Express4S features

Coupling� New 12x InfiniBand and 1x InfiniBand features (HCA3-O fanouts)

� 12x InfiniBand – improved service times when using 12x IFB3 protocol� 1x InfiniBand – increased port count

zEnterprise 114 and zEnterprise 196 GA2


IBM System z

STIz990/z890

STIz9

InfiniBandz10/z196 GA1

STIz900/z800

PCIe: Peripheral Component Interface (PCI) ExpressSTI: Self-Timed Interconnect

6 GBps

2.7 GBps

2 GBps

1 GBps

I/O Subsystem Internal Bus Interconnect Speeds (GBps)

PCIez196 GA2

z1148 GBps


IBM System z

IBM System zBalanced System

Comparisonfor High End Servers

Balanced SystemCPU, nWay, Memory,

I/O Bandwidth*

Memory

3 TB**

System I/O Bandwidth384 GB/Sec*

PCI for1-way

12021.5 TB**

64-way

920

80-wayProcessors

288 GB/sec*

600512 GB

54-way

96 GB/sec

450256 GB

32-way

24 GB/sec

30064 GB

16-way

* Servers exploit a subset of its designed I/O capability** Up to 1 TB per LPARPCI – Processor Capacity Index

172.8 GB/sec*

z10 EC

z9 EC

zSeries 990

zSeries 900

z196 - 2011


IBM System z

z196 GA2 I/O Infrastructure (PCIe Based) with PCIe I/O drawerBook 3Book 1

Memory

x16 PCIeGen2 8 GBps

Memory Memory Memory

Book 0 Book 2

PCIeswitch

OSA-Express4S

PCIe (8x) PCIe (8x) HCA2 (8x)

PCIeswitch

PCIeswitch

FICON Express8S

PCIeswitch

4 GB/s PCIeGen2 x8

…

SC1, SC0 (FBC)

PU PU

PU PU PU

PU

SC1, SC0 (FBC)

PU PU

PU PU PU

PU

SC1, SC0 (FBC)

PU PU

PU PU PU

PU

SC1, SC0 (FBC)

PU PU

PU PU PU

PU

PCIe I/O drawerPCIe I/O drawer

FanoutsFanoutsFanoutsFanouts

6 GBps

HCA2 (8x)

IFB-MPRII

IFB-MP

FICON Express8

2 GBps mSTI

Channels

1 GBpsmSTI

2 GBps mSTI

Ports

2GBpsmSTI

FP

GA

FP

GA

FP

GA

FP

GA

RII IFB-MPIFB-MP

OSA-Express3

I/O Cage & I/O drawerI/O Cage & I/O drawer

RIIRII


IBM System z

z114 and z196 at GA2 support two different internal I/O infrastructures

� The current InfiniBand I/O infrastructure first made available on z10– InfiniBand fanouts supporting the current 6 GBps InfiniBand I/O interconnect– InfiniBand I/O card domain multiplexers with Redundant I/O interconnect in:

• The 14U, 28-slot, 7-domain I/O cage (z196 only)• The 5U, 8-slot, 2-domain IO drawer (z114 and z196)

– Selected legacy I/O feature cards• Carry forward and new build

� The New PCI Express I/O infrastructure– PCIe fanouts supporting a new 8 GBps PCIe I/O interconnect– PCIe switches with Redundant I/O interconnect in for I/O domains in a

new 7U, 32-slot, 4-domain I/O drawer (z114 and z196 GA2)– New FICON Express8S and OSA-Express4S I/O feature cards

• Designed to:

� Reduce purchase granularity (fewer ports per card)

� Improve performance

� Increase I/O port density

� Save energy


IBM System z

PCIe I/O Drawer


IBM System z

PCIe I/O drawer and PCIe I/O features

� Increased infrastructure bandwidth– PCI Express 2 x16 - 8 GBps interconnect

(Compared to 6 GBps 12x Infiniband DDR interconnect)– PCI Express 2 x8 - 4 GBps available to PCIe I/O feature cards

(Compared to 2 GBps or less available to older I/O feature cards)

� Compact– Two 32-slot PCIe I/O drawers occupy the same space as one 28-slot I/O cage– Increases I/O port density 14% (Equivalent to an increase from 28 to 32 slots)

� Improved I/O feature purchase granularity– “Half high” I/O feature cards compared to older I/O feature cards– Two FICON Express8S channels per feature (Four on FICON Express8)– One or two OSA-Express4S ports per feature (Two or four on OSA-Express3)

� Reduced power consumption

� Designed for Improved Reliability, Availability, an d Serviceability– Concurrent field MES install and repair– Symmetrical, redundant cooling across all cards and power supplies– Temperature monitoring of critical ASICs


IBM System z

7U

7U

Rear

Front� Supports only the new PCIe I/O cards

introduced with z114 and z196 GA2.

� Supports 32 PCIe I/O cards, 16 front and 16 rear, vertical orientation, in four 8-card domains (shown as 0 to 3).

� Requires four PCIe switch cards ( ��), each connected to an 8 MBps PCIe I/O interconnect to activate all four domains.

� To support Redundant I/O Interconnect(RII) between front to back domain pairs 0-1 and 2-3 the two interconnects to each pair must be from 2 different PCIe fanouts. (All four domains in one of these cages can be activated with two fanouts.)

� Concurrent field install and repair.

� Requires 7 EIA Units of space(12.25 inches ≈ 311 mm)

Domain 0 Domain 2

� �

� �

Domain 3 Domain 1

New 32 slot PCIe I/O drawer

z114TLLB9


IBM System z

z196TLLB10

z114 & z196•4 I/O domains•32 I/O slots (PCIe I/O cards only)• At least two PCIe fanouts (4 ports per drawer)•7 EIA Units

z114, z196, & z10 BC•2 I/O domains•8 I/O slots (legacy I/O cards only)• At least 2 HCA2-C fanouts (2 ports per drawer)•Up to two drawers on a pair of fanouts•5 EIA Units

z196 & earlier (except z10 BC and z800)•7 I/O domains•28 I/O slots (legacy I/O cards only)•Up to 4 fanouts (z9 and later Systems) for all 7 domains•14 EIA Units

z114

Not Supported

I/O drawer

FC 4000

PCIe I/O drawer

FC 4003

z114 & z196 GA2 I/O Drawers and Cages


IBM System z

z196 and z114 I/O Features


IBM System z

*All statements regarding IBM's plans, directions, and intent are subject to change or withdrawal with out notice. Any reliance on these statements of general direction is at the rel ying party's sole risk and will not create liabilit y or obligation for IBM.

ESCON Statement of Direction* - July 12, 2011

� The IBM zEnterprise 196 and the IBM zEnterprise 114 are the last System z servers to support ESCON channels. IBM plans to not offer ESCO N channels as an orderable feature on System z servers that follow the z196 (m achine type 2817) and z114 (machine type 2818). In addition, ESCON channels ca nnot be carried forward on an upgrade to such follow-on servers.

� This plan applies to channel path identifier (CHPID ) types CNC, CTC, CVC, and CBY and to features 2323 and 2324.

� IBM Global Technology Services offers an ESCON to F ICON Migration solution, Offering ID #6948-97D, to help facilitate migration from ESCON to FICON. This offering is designed to help customers to simplify and manage a single physical and operational environment - FICON channels on the main frame with continued connectivity to ESCON devices.

� This is a restatement of general direction already published. Refer to Hardware Announcement 111-012, dated February 15, 2011.


IBM System z

z196TLLB13

� PRIZM is a purpose built appliance designed exclusi vely for IBM System z

� PRIZM converts native FICON (FC) protocol to native ESCON (CNC) protocol allowing ESCON and B/T devices to connect t o FICON channels

Front View

Rear View

2U

ESCON Ports: MT-RJ

FICON Ports: LC Duplex

PRIZM Basics


IBM System z

z196TLLB14

Where Does PRIZM Fit in the Data Center?

Native FICON Tape & DASD

FICON Channel Extension

1. Point-to-Point FICON

2. Switched FICON

3. Cascaded and Channel Extended FICON

ISL

IP

*PRIZM supports all ESCON control units: Tape, Printers, Com Devices, FEPs etc.

ESCON Device Pool

FICON

FICON

ESCON

ESCON


IBM System z

z196 GA2 and z114 I/O Features supported

� Features – PCIe I/O drawer– FICON Express8S

• SX and LX– OSA-Express4S

• 10 GbE LR and SR• GbE SX and LX

� Features – I/O cage and I/O drawer– Crypto Express3– ESCON (240 or fewer)– FICON Express8 (Carry forward or RPQ 8P2534 to fill empty slots)– FICON Express4 (Carry forward only)– ISC-3– OSA-Express3 1000BASE-T– OSA-Express3 (Carry forward or RPQ 8P2534 to fill empty slots)

• 10 GbE, GbE– OSA-Express2 (Carry forward only)

• GbE, 1000BASE-T– PSC (Carry forward or new build, no MES add)

28 slot I/O cage(not on z114)

8 slot I/O drawer

PCIe I/O drawer

32 I/O slots

Supported features


IBM System z

� For FICON, zHPF, and FCP environments� CHPID types: FC and FCP

� 2 PCHIDs/CHPIDs

�Auto-negotiates to 2, 4, or 8 Gbps

�Increased performance compared to FICON Express8

� 10KM LX - 9 micron single mode fiberƒ Unrepeated distance - 10 kilometers (6.2 miles)

ƒ Receiving device must also be LX

� SX - 50 or 62.5 micron multimode fiber

ƒ Distance variable with link data rate and fiber type

ƒ Receiving device must also be SX

� 2 channels of LX or SX (no mix)

� Small form factor pluggable (SFP) optics� Concurrent repair/replace action for each SFP LX SX

FICON Express8S – PCIe I/O drawer

# 0409 – 10KM LX, # 0410 – SX

OR

2, 4, 8 Gbps

2, 4, 8 Gbps

FLASH

SFP+

SFP+ IBM ASIC

IBM ASIC

PCIeSwitch

HBAASIC

HBAASIC

FLASH


IBM System z

1200

14000

31000

20000

52000

20000

92000

0

10000

20000

30000

40000

50000

60000

70000

80000

90000

100000

I/O driver benchmark I/Os per second4k block sizeChannel 100% utilized

FICONExpress4

andFICON

Express2

zHPF

FICON Express8

zHPF

FICON Express8FICON

Express4and

FICONExpress2

ESCON

zHPF

FICON Express8S

FICON Express8S

z10 z10z196z10

z196z10

z196z114

z196z114

FICON performance on System z

350

520620

770

620

1600

0100200300400500600700800900

10001100120013001400150016001700

FICON Express44 Gbps

I/O driver benchmarkMegaBytes per secondFull-duplexLarge sequentialread/write mix

FICONExpress44 Gbps

FICON Express

88 Gbps

FICON Express88 Gbps FICON

Express8S8 Gbps

FICON Express8

S8 Gbps

z10z9 z10

z196z10

z196z10

z196z114

z196z114

zHPF

zHPF

zHPF

77% increase

108% increase


IBM System z

FCP performance on System z

15750

31500

60000

84000 8400092000

0

10000

20000

30000

40000

50000

60000

70000

80000

90000

100000

FE8 FE8 FE8S8 Gbps 8 Gbps 8 Gbps

I/Os per secondRead/writes/mix 4k block size, channel 100% utilized

z9 z9 z10 z10 z196z196z114

520

770

1500

0

200

400

600

800

1000

1200

1400

1600 MegaBytes per second (full-duplex)Large sequential Read/write mix

z10z196z10

z196z114

95% increase

10% increase

FE44 Gbps

FE44 Gbps

FE44 Gbps

FE8S8 Gbps

FE88 Gbps

FE44 Gbps


IBM System z

z196TLLB19

FCP channels to support T10-DIF for enhanced reliability

� System z Fibre Channel Protocol (FCP) has implement ed support of the American National Standards Institute's (ANSI) T10 Data Inte grity Field (DIF) standard.

– Data integrity protection fields are generated by the operating system and propagated through the storage area network (SAN).

– System z helps to provide added end-to-end data protection between the operating system and the storage device

� An extension to the standard, Data Integrity Extens ions (DIX), provides checksum protection from the application layer through the h ost bus adapter (HBA), where cyclical redundancy checking (CRC) protection is im plemented

� T10-DIF support by the FICON Express8S and FICON Ex press8 features, when defined as CHPID type FCP, is exclusive to z196 and z114.

� Exploitation of the T10-DIF standard requires suppo rt by the operating system and the storage device

– z/VM V5.4, V6.1 with PTFs and V6.2 for guest exploitation– Linux on System z distributions:

• IBM is working with its Linux distribution partners to include support in future Linux on System z distribution releases. .


IBM System z

� 10 Gigabit Ethernet (10 GbE)

� CHPID types: OSD, OSX

� Single mode (LR) or multimode (SR) fiber

� One port of LR or one port of SR

� 1 PCHID/CHPID

� Gigabit Ethernet (GbE)

� CHPID types: OSD (OSN not supported)

� Single mode (LX) or multimode (SX) fiber

� Two ports of LX or two ports of SX

� 1 PCHID/CHPID

� Small form factor optics – LC Duplex

OSA-Express4S fiber optic – PCIe I/O drawer

# 0406 – 10 GbE LR, # 0407 – 10 GbE SR

PCIeIBM ASIC

FPGA

PCIeIBM ASIC

FPGA

# 0404 – GbE LX, # 0405 – GbE SX


IBM System z

OSA-Express4S 10 GbE performance (laboratory)Mixed Streams – 1492 Byte MTUs

1240

2080

0

500

1000

1500

2000

2500

MB

ps

680

1180

0

200

400

600

800

1000

1200

1400

MB

ps

615

1120

0

200

400

600

800

1000

1200

1400M

Bps

11801680

0

500

1000

1500

2000

2500

MB

ps

Inbound Streams – 1492 Byte MTUs

OSA-E3 OSA-E4S

80% increase

70% increase 70% increase

40% increase

Mixed Streams – 8000 Byte MTUsInbound Streams – 8000 Byte MTUs

OSA-E3 OSA-E4S

OSA-E3 OSA-E4S OSA-E3 OSA-E4S

Notes:� 1 megabyte per second(MBps) is 1,048,576bytes per second

� MBps represents payloadthroughput (doesnot count packetand frame headers)

Maximum transmission units (MTUs)


IBM System z

z196TLLB22

z196/z114 HiperSockets – doubled the number

HiperSockets

L3 z/VM LP4

L2 z/VM LP5

z/VSELP3

Linux on System zLP2

z/OSLP1

� High-speed “intraserver” network

� Independent, integrated, virtual LANs

� Communication path – system memory

� Communication across LPARs– Single LPAR - connect up to 32 HiperSockets

� Support for multiple LCSS's & spanned channels

� Virtual LAN (IEEE 802.1q) support

� HiperSockets Network Concentrator

� Broadcast support for IPv4 packets

� IPv6

� HiperSockets Network Traffic Analyzer (HS NTA)

� No physical cabling or external connections require d


IBM System z

Support for HiperSockets Completion Queue

� HiperSockets Completion Queue: (Statement of Direction July 12, 2011)– IBM plans to support transferring HiperSockets messages asynchronously, in

addition to the current synchronous manner on z196 and z114. This could be especially helpful in burst situations. The Completion Queue function is designed to allow HiperSockets to transfer data synchronously if possible and asynchronously if necessary, thus combining ultra-low latency with more tolerance for traffic peaks. HiperSockets Completion Queue is planned to be supported in the z/VM and z/VSE environments in a future deliverable

� Operating System Support– z/OS V1.13 (Toleration, no exploitation) – Linux on System z distributions

• Red Hat Enterprise Linux (RHEL) 6.2• Novell SUSE Linux Enterprise Server (SLES) 11 SP2


IBM System z

Support for HiperSockets Integration with the IEDN

� HiperSockets integration with the IEDN: (Statement of Direction July 12, 2011)– Within a zEnterprise environment, it is planned for HiperSockets to be integrated

with the intraensemble data network (IEDN), extending the reach of the HiperSockets network outside of the central processor complex (CPC) to the entire ensemble, appearing as a single Layer 2 network. HiperSockets integration with the IEDN is planned to be supported in z/OS V1.13 and z/VM in a future deliverable*

� Operating System Support:– z/OS V1.13 with PTFs– z/VM V6.2 with PTFs planned to be available April 13, 2012

CEC X

z/OS LPAR

OSX NIC

Server A

(native)

HiperSockets (IQDX)

IQDX NIC

PR/SM

If 1

OSX NIC

Linux LPAR

Server B

(native)If A

z/VM LPAR B

VSwitch B

Primary BC

zLin

ux

QB

1zL

inu

x Q

B2

zLin

ux

QB

3zL

inu

x Q

B4

OS

X

Upl

ink

Por

t

HS

Brid

ge

Por

tzL

inu

x V

B1

z/O

S

VB

2

QEBSMz/VM LPAR A

VSwitch A

Secondary BC

zLin

ux

QA

1zL

inu

x Q

A2

zLin

ux

QA

3zL

inu

x Q

A4

OS

X

Upl

ink

Por

t

HS

Brid

ge

Por

tzL

inu

x V

A1

z/O

S

VA

2

QEBSM


IBM System z

z196TLLB25

CPU CPU CPU CPU

Other Bulk SD EE

Q1 Q2 Q3 Q4

z/OS Instance

(TCP/IP stack)

OSA-Express

Device

WAN

IWQ

EE traffic separation optimizes the host inbound EE processing

Inbound Workload Queuing for Enterprise Extender

� OSA separates inbound network traffic to multiple input queues (based on type of workload) on the same host (device) interface

� Each input queue can be serviced concurrently by separate processors

� Stack receives pre-sorted packets and host processing is optimized based on the unique requirements for each unique type of workload

� New – Enterprise Extender traffic is added as a new input queue (new IWQ)!


IBM System z

Coupling HW


IBM System z

Up to 16 CHPIDs – across 2 ports*

z114 and z196 GA2 InfiniBand HCA3 Fanouts


IFB IFB

HCA3-O for 12x IFB & 12x IFB3

IFB

HCA3-O LR for 1x IFB

IFB IFB IFB

* Performance considerations may reduce the number of CHPIDs per port.

� New 12x InfiniBand and 1x InfiniBand fanout cards� Exclusive to zEnterprise 196 and zEnterprise 114

– HCA3-O fanout for 12x InfiniBand coupling links• CHPID type – CIB

– Improved service times with 12x IFB3 protocol– Two ports per feature– Fiber optic cabling – 150 meters– Supports connectivity to HCA2-O

(No connectivity to System z9 HCA1-O)– Link data rate of 6 GBps

– HCA3-O LR fanout for 1x InfiniBand coupling links• CHPID type – CIB

– Four ports per feature– Fiber optic cabling

– 10 km unrepeated, 100 km repeated– Supports connectivity to HCA2-O LR– Link data rate server-to-server 5 Gbps– Link data rate with WDM; 2.5 or 5 Gbps

Note: The InfiniBand link data rates do not represent the performance of the link. The actual performance is dependent upon many factors including latency through the adapters, cable lengths, and the type of workload.


IBM System z

12x InfiniBand Coupling IFB3 Protocol (HCA3-O fanout)

� Two protocols1. 12x IFB – HCA3-O to HCA3-O or HCA2-O

2. 12x IFB3 - improved service times for HCA3-O to HCA3-O

– 12x IFB3 service times are designed to be 40% faster than 12x IFB

� 12x IFB3 protocol activation requirements– Four or fewer CHPIDs per HCA3-O port

• If more than four CHPIDs are defined per port, CHPIDs will use IFB protocol and run at 12x IFB service times


IFB IFB

HCA3-O for 12x IFB & 12x IFB3

* Performance considerations may reduce the number of CHPIDs per port.

Note: The InfiniBand link data rates do not represent the performance of the link. The actual performance is dependent upon many factors including latency through the adapters, cable lengths, and the type of workload.


IBM System z

z196TLLB29

STP Recovery Enhancements – Going away signal

� Going away signal is a reliable unambiguous signal to indicate that the CPC is about to enter a check stopped state

� In an STP-only Coordinated Timing Network, when a g oing away signal from the CTS is received by the BTS,

– BTS safely takes over as CTS– Going away signal has priority over OLS in a 2 server CTN– BTS can also use going away signal to take over as CTS for CTNs with 3 or more

servers without communicating with Arbiter

� Dependencies on OLS and CAR removed in a 2 server C TN

� Dependency on BTS>Arbiter communication removed in CTNs with 3 or more servers

� Prerequisites:– InfiniBand (IFB) links using

• HCA3-O to HCA3-O

– 12x IFB or 12x IFB3• HCA3-O LR to HCA3-O LR

– 1x IFB

� Current recovery design still used when going away signal not received by BTS and for other failure types

Driver 93 onlyHiper EC.MCL N48165.053 (alert/circumvention)

Hiper EC.MCL N48165.057 (alert/fix)


IBM System z

z196TLLB30

zBX Virtual Servers improved time

•SE's Battery Operated Clock (BOC)•server's Time-of-Day (TOD)•Network Time Protocol (NTP)•Universal Time Coordinated (UTC)


IBM System z

Latest news March 6th, 2012


IBM System z

LGR is the very best

z/VM software

enhancement since

64-bit support became

available.”

“

– Mark Shackelford, Vice President, Information Services, Baldor

� Increased flexibility with Live Guest Relocation (LGR) to move virtual servers without disruption.

� Increased management of resources with multi-system virtualization to allow up to four z/VM®

instances to be clustered as a single system image.

� Increased scalability with up to four systems horizontally, even on mixed hardware generations.

� Increased availability through non-disruptively moving work to available system resources and non-disruptively moving system resources to work.

Relief from the challenges associated with virtual machine sprawl on competitive systems

Superior virtualization for today and the future: z/VM 6.2


IBM System z

Increased flexibility for deployment and managementIncreased flexibility for deployment and management

Enhanced disaster recoveryEnhanced disaster recovery

Dynamic discovery of storage resourcesDynamic discovery of storage resources

APIs for Unified Resource Manager� Integration between Unified Resource Manager and the broader ecosystem of

management tools �Programmatic access to the same functions provided by the Hardware Management

Console

�Simplified configuration of storage resources and v irtual servers

Geographically Dispersed Parallel Sysplex ™ (GDPS®)�End-to-end application CA/DR now available for all zEnterprise resources

including zBX

New capabilities for IBM zEnterprise System and Unified Resource Manager


IBM System z

Network simplification and enhancementsNetwork simplification and enhancements

• HiperSocketsTCompletion Queue

• Improved network monitoring and metrics• HiperSockets integration with the intraensemble data network (IEDN)

• z/VM® V6.2 HiperSockets Virtual Switch Bridge support

• Server Application State Protocol (SASP) load balancing

New capabilities for IBM zEnterprise System and Unified Resource Manager

• Support for additional configurations• Support for additional configurations

• Additional Fibre Channel optics for BladeCenter chassis• Support for BladeCenter HX5 blade with 192 and 256 GB memory• Up to 56 System x blades• SAP support for System x Linux and Microsoft Windows


IBM System z

z196TLLB35

System z Statements of Direction

All statements regarding IBM's plans, directions, and intent are subject to change or withdrawal without notice. Any reliance on these Statements of General Direction is at the relying party's sole risk and will not create liability or obligation for IBM.


IBM System z

z196TLLB36


zEnterprise – Statements of Direction (SODs)

� The IBM zEnterprise 196 and the zEnterprise 114 are t he last System z servers to support the Power Sequence Controller (PSC) feature .

– IBM intends to not offer support for the PSC (feature #6501) on future System z servers after the z196 (2817) and z114 (2818). PSC features cannot be ordered and cannot be carried forward on upgrade to such a follow-on server.

� The IBM zEnterprise 196 and the zEnterprise 114 are t he last System z servers to offer ordering of ISC-3

– Enterprises should begin migrating from ISC-3 features (#0217, #0218, #0219) to 12x InfiniBand (#0163 - HCA2-O or #0171 - HCA3-O fanout) or 1x InfiniBand (#0168 - HCA2-O LR or #0170 - HCA3-O LR fanout) coupling links.

� The IBM zEnterprise 196 and the zEnterprise 114 are t he last System z servers to support ESCON channels

– IBM plans not to offer ESCON channels as an orderable feature on System z servers that follow the z196 (machine type 2817) and z114 (machine type 2818). In addition, ESCON channels cannot be carried forward on an upgrade to such follow-on servers. This plan applies to channel path identifier (CHPID) types CNC, CTC, CVC, and CBY and to features #2323 and #2324.

– System z customers should continue migrating from ESCON to FICON. Alternate solutions are available for connectivity to ESCON devices


IBM System z

z196TLLB37


zEnterprise – Statements of Direction (SODs) - continued

� The IBM zEnterprise 196 and the zEnterprise 114 are t he last System z servers to support OSA-Express2 features:

– Enterprises should begin migrating from OSA-Express2 features (#3364, #3365, #3366) to OSA-Express3/OSA Express4S features.

� The IBM zEnterprise 196 and the zEnterprise 114 are t he last System z servers to support dial-up modems for use with the Remote Supp ort Facility (RSF), and the External Time Source (ETS) option of Server Time Pr otocol (STP).

– The currently available Network Time Protocol (NTP) server option for ETS as well as Internet time services available using broadband connections can be used to provide the same degree of accuracy as dial-up time services.

– Enterprises should begin migrating from dial-up modems to Broadband for RSF connections.


IBM System z

z196TLLB38


zEnterprise – Statements of Direction (SODs) – October 12, 2011� Removal of modem support

– Beginning with the next System z server after the IBM zEnterprise 196 and 114, the new Hardware Management Console (HMC) is intended to no longer provide modem support. As a result, modems will not be allowed for use with the Remote Support Facility (RSF), and one of the External Time Source (ETS) options of Server Time Protocol (STP). Only broadband connections will be allowed. The new HMC driver is planned to provide enhanced security by providing Network Time Protocol (NTP) authentication support, when a NTP server is accessed to get accurate time for the STP Coordinated Timing Network (CTN).

– Note that the above changes will affect new orders of z196 and z114, as well as upgrades of HMC driver levels to this new version

– Enterprises using modems for RSF or STP should plan on migrating to broadband connections. The currently available NTP server option for ETS, as well as internet time services available using broadband connections, can be used to provide the same degree of accuracy as dial-up time services

– Reference: Integrating the Hardware Management Console's Broadband Remote Support Facility into your Enterprise, SC28-6880

� Note: When implemented, the above changes are intended to apply to new HMC orders for z196 and z114, as well as upgrades of older HMCs to this new version of HMC LIC.


IBM System z

z196TLLB39


zEnterprise – Statements of Direction (SODs) – October 12, 2011

� IBM intends that the zEnterprise196 and zEnterprise 114 will be the last servers to offer ordering of the external Ethernet switch.

� As a result, it will no longer be possible to order as server features on future System z servers the Ethernet switches required to by HMCs. Customers should plan to use existing supported switches or to acquire additional switches separately to implement the required HMC LAN connectivity.

� Note: Ethernet switches are offered today as FC #0070 on zEnterprise servers.

CEC BPH Connections


IBM System z

z196TLLB40


zEnterprise – Statements of Direction (SODs) – October 12, 2011� GDPS/Global Mirror clusters managed by SA AppMan:

– GDPS plans to enhance its Distributed Cluster Management (DCM) support for IBM Tivoli System Automation Application Manager (SA AppMan) by extending it to the GDPS/Global Mirror (GM) offering in addition to the GDPS/PPRC offering available today. This will allow for coordinated disaster recovery across System z and distributed servers at unlimited distances. With GDPS/GM managing replication of data for both System z and for the distributed servers under SA AppMan control, this solution can also provide cross-platform data consistency across the System z and distributed servers.

� GDPS DCM support for stand alone distributed server s: – GDPS plans to enhance its DCM support for SA AppMan by extending it to stand

alone distributed servers, building upon the support for clustered distributed servers available today. This capability can benefit distributed servers running on a zBX or on other distributed platforms, which are not members of a clustered network, and will allow continuous availability and disaster recovery across heterogeneous platforms. Support is planned for GDPS/PPRC and GDPS/GM.


IBM System z

z196TLLB41



� HMC z/VM Tower Systems Management Support – z/VM 6.2 is intended to be the last release supported by the HMC z/VM Tower

systems management support originally introduced with System z9. The alternative implementation for virtual server and virtual resource management for z/VM V6 continues to be supported by the zEnterprise Unified Resource Manager on zEnterprise or later.


IBM System z

z196TLLB42



� Global Resource Serialization (GRS) ring to support FICON channels– Many customers are migrating from ESCON channels to FICON channels, and in

Hardware Announcement dated July 12, 2011, IBM announced that the zEnterprise 196 (z196) and zEnterprise 114 (z114) generation of servers is intended to be the last to support ESCON channels. Although IBM recommends that you use GRS Star, and for GRS Ring environments recommends XCF communications for CTC management, IBM intends to extend z/OS Global Resource Serialization (GRS) Ring function to natively support FICON channel-to-channel (CTC) connections in the z/OS release following z/OS V1.13, and to make this support available on z/OS V1.11, V1.12, and V1.13

� Revision of FICON Express4 support on future System z servers: – In previous statements of direction IBM stated that the IBM zEnterprise 196 and

IBM zEnterprise 114 would be the last servers to support FICON Express4 channels. IBM now plans to support carry forward of the FICON Express4 features (#3321 and #3322 only) into the server after the zEnterprise System.


IBM System z


zEnterprise – Statements of Direction (SODs) – March 6, 2012

� Removal of support for Ethernet half-duplex operati on and 10 Mbps link data rate

– The next IBM mainframe product family announced after the IBM zEnterprise196 (z196) and the IBM zEnterprise 114 (z114) is planned to be the last System z product family to support half-duplex operation and 10 Mbps link data rate for copper Ethernet environments. The 1000BASE-T Ethernet feature will support full-duplex operation and auto-negotiation to 100 or 1000 Mbps exclusively.


IBM System z

Questions?


IBM System z

Thank you

z196 and z114 hw subsystems update zos 2012-03-14 - z196...z114, z196, & z10 bc •2 i/o domains...

Documents