IBM System z10:
What’s new?
© 2008 IBM Corporation
IBM System z10 Business Class
Hardware Innovation
© 2008 IBM Corporation
Trademarks
The following are trademarks of the International Business Machines Corporation in the United States and/or other countries.
Certified Used Equipment
DB2*
DS8000
ESCON*
FICON*
GDPS*
HiperSockets
HyperSwap
IBM*
IBM eServer
IBM logo*
Multiprise*
Parallel Sysplex*
PR/SM
Resource Link
S/390*
Scalable Architecture for Financial Reporting
Systems Director Active Energy Manager
System Storage
System z*
System z9*
System z10
Tivoli*
z9
z10
z10 BC
z10 EC
zArchitecture*
z/OS*
z/VM*
z/VSE
zSeries*
* Registered trademarks of IBM Corporation
The following are trademarks or registered trademarks of other companies.
Adobe, the Adobe logo, PostScript, and the PostScript logo are either registered trademarks or trademarks of Adobe Systems Incorporated in the United States, and/or other countries.
Cell Broadband Engine is a trademark of Sony Computer Entertainment, Inc. in the United States, other countries, or both and is used under license there from.
Java and all Java-based trademarks are trademarks of Sun Microsystems, Inc. in the United States, other countries, or both.
Microsoft, Windows, Windows NT, and the Windows logo are trademarks of Microsoft Corporation in the United States, other countries, or both.
InfiniBand is a trademark and service mark of the InfiniBand Trade Association.
Intel, Intel logo, Intel Inside, Intel Inside logo, Intel Centrino, Intel Centrino logo, Celeron, Intel Xeon, Intel SpeedStep, Itanium, and Pentium are trademarks or registered trademarks of Intel
Corporation or its subsidiaries in the United States and other countries.
UNIX is a registered trademark of The Open Group in the United States and other countries.
Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both.
ITIL is a registered trademark, and a registered community trademark of the Office of Government Commerce, and is registered in the U.S. Patent and Trademark Office.
IT Infrastructure Library is a registered trademark of the Central Computer and Telecommunications Agency, which is now part of the Office of Government Commerce.
* All other products may be trademarks or registered trademarks of their respective companies.
Notes:
Performance is in Internal Throughput Rate (ITR) ratio based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput that
any user will experience will vary depending upon considerations such as the amount of multiprogramming in the user's job stream, the I/O configuration, the storage configuration, and the
workload processed. Therefore, no assurance can be given that an individual user will achieve throughput improvements equivalent to the performance ratios stated here.
IBM hardware products are manufactured from new parts, or new and serviceable used parts. Regardless, our warranty terms apply.
All customer examples cited or described in this presentation are presented as illustrations of the manner in which some customers have used IBM products and the results they may have
achieved. Actual environmental costs and performance characteristics will vary depending on individual customer configurations and conditions.
This publication was produced in the United States. IBM may not offer the products, services or features discussed in this document in other countries, and the information may be subject
to change without notice. Consult your local IBM business contact for information on the product or services available in your area.
All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
Information about non-IBM products is obtained from the manufacturers of those products or their published announcements. IBM has not tested those products and cannot confirm the
performance, compatibility, or any other claims related to non-IBM products. Questions on the capabilities of non-IBM products should be addressed to the suppliers of those products.
Prices subject to change without notice. Contact your IBM representative or Business Partner for the most current pricing in your geography.
3
IBM System z
© 2008 IBM Corporation
The modern mainframe for small and medium enterprises
The mainframe made over – Smart, Cool, Affordable
IBM System z10™ Business Class (z10 BC™)
Machine Type: 2098
1 Model: E10
Single Frame
Non-raised floor option
Processor Cores:
Memory:
  Enterprise Quad Core technology – 3.5 GHz
  Lower 4 GB entry point
  Enhanced capacity 5-way model with up to 5
zAAPs/zIIPs
  8 GB HSA separately
managed and not included in
customer purchased
memory
  Up to a 10-way IFL or Coupling Facility
  Core sparing technology
  2 SAPs standard per system
  Configurable PUs allow you to design the
system to meet your needs (e.g. CPs, IFLs,
ICFs, zAAPs, zIIPs, SAPs)
4
IBM System z
  Customer maximum 248 GB
–  120 GB- Oct. 08
–  248 GB – June 09
I/O:
  New I/O drawer (RAS)
  6 GBps InfiniBand® host
buses for I/O
  High Performance FICON®
for System z
  FICON/FCP Serviceability
Enhancements
  OSA-Express3 GbE,
10 GbE, 1000BASE-T
  InfiniBand Coupling Links
  Continued lower capacity /
priced I/O cards
© 2008 IBM Corporation
New levels of application performance
Designed for an expanded set of workloads
  The z10™ BC can deliver up to 50% more performance for general purpose workloads
than an IBM System z9® Business Class (z9™ BC)*
  The uniprocessor can deliver up to 40% more performance than z9 BC uniprocessor**
  Up to 1.9x performance improvements for CPU intensive jobs or tasks
  Up to 10X improvement in decimal floating point instructions
Customer Engines
  Up to 10 IFLs for large scale consolidation
z10 BC
3.5 GHz processor chip
Hardware Decimal Floating Point
z9 BC
IFL
Crypto
zIIP
z890
zAAP
z800
Capacity
More capacity and engines for traditional growth and consolidation
All performance information was determined in a controlled environment.
* LSPR mixed workload average running z/OS® 1.9 - z10 BC z05 versus z9 BC z04 ** LSPR mixed workload average running z/OS 1.9 - z10 BC z01 versus z9 BC z01
5
IBM System z
© 2008 IBM Corporation
Slower
Faster
The right size for existing and future applications
Smart, affordable and flexible
6
Z01
Z02
Z03
Z04
Z05
Y01
Y02
Y03
Y04
Y05
X01
X02
X03
X04
X05
W01
W02
W03
W04
W05
V01
V02
V03
V04
V05
U01
U02
U03
U04
U05
T01
T02
T03
T04
T05
S01
S02
S03
S04
S05
R01
R02
R03
R04
R05
Q01
Q02
Q03
Q04
Q05
P01
P02
P03
P04
P05
O01
O02
O03
O04
O05
N01
N02
N03
N04
N05
M01
M02
M03
M04
M05
L01
L02
L03
L04
L05
K01
K02
K03
K04
K05
J01
J02
J03
J04
J05
I01
I02
I03
I04
I05
H01
H02
H03
H04
H05
G01
G02
G03
G04
G05
F01
F02
F03
F04
F05
z10 BC Model E10 with 130 capacity settings
►
Granularity designed for flexibility and growth
►
Any to any capacity upgradeability within the Model
►
All IBM System z10 Enterprise Class (z10 EC™)
temporary capacity offerings are available on z10 BC
►
CBU capability from smallest to largest capacities
►
Increased number of specialty engines than z9 BC
►
All specialty engines run at full capacity
►
Linux only IFL and ICF only servers (A00)
CP
IFL
zAAP
zIIP
ICF
Additional
SAPs
Spares
0-5
0-10
0-5
0-5
0-10
0-2
0
when fully
configured
E01
E02
E03
E04
E05
D01
D02
D03
D04
D05
C01
C02
C03
C04
C05
B01
B02
B03
B04
B05
Remember the IBM Processor Capacity Reference (zPCR) is a free tool
available for download that can be used to size your System z processors.
http://www-03.ibm.com/support/techdocs/atsmastr.nsf/WebIndex/PRS1381
A01
A02
A03
A04
A05
1-way
2-way
3-way
4-way
5-way
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
IBM System z
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
Specialty
Engine
© 2008 IBM Corporation
IBM z10 BC continues the CMOS Mainframe heritage
3.5
GHz
3500
3000
1.4
GHz
MHz
2500
2000
625
MHz
1500
139
MHz
1000
1.0
GHz
413
MHz
500
0
1997
1999
2002
2004
2006
2008
Multiprise
2000
Multiprise
3000
z800
z890
z9 BC
z10 BC
  Multiprise® 2000 – 1st full-custom
CMOS S/390®
  Multiprise 3000 – Internal disk, IFL
introduced on midrange
7
IBM System z
  IBM eServer™ zSeries® 800 (z800) – Full 64-bit z/Architecture®
  IBM eServer zSeries 890 (z890) – Superscalar CISC pipeline
  z9 BC – System level scaling
  z10 BC – Architectural
extensions
  Higher frequency CPU
© 2008 IBM Corporation
Making high performance a reality
Designed for the next evolution of Enterprise applications
  New Enterprise Quad Core z10 processor chip
–  3.5 GHz – additional throughput means improved price/performance
–  Cache rich environment optimized for data serving
–  50+ instructions added to improve compiled
code efficiency
–  Support for 1 MB page frames
  Hardware accelerators on the chip
–  Hardware data compression
–  Cryptographic functions
–  Hardware Decimal Floating point
Enterprise Quad Core
z10 processor chip
  CPU intensive workloads get performance
improvements from new core pipeline design
8
IBM System z
© 2008 IBM Corporation
Focused performance boost
Hardware Decimal Floating Point
Up to 10X improvement
in decimal floating point
instructions*
  Decimal arithmetic widely used in commercial and financial applications
  Computations often handled in software
  First delivered in millicode on the System z9 – brought improved precision and
function
–  Avoids rounding and other problems with binary/decimal conversions
  Integrated on every z10 core to deliver a performance boost to execution of decimal
arithmetic
  Growing industry support for hardware decimal floating point standardization
–  Java BigDecimal, C#, XML, C/C++, GCC, DB2® V9, Enterprise PL/1, Assembler
–  Open standard definition led by IBM
Delivering the benefits of System z
to a new set of workloads
* All performance information was determined in a controlled environment.
9
IBM System z
© 2008 IBM Corporation
Connecting to the world —
z can do IT all
  Improved performance and flexibility for connectivity
  Broad set of options to meet your needs
To the Network with OSA
Within the server
  QDIO Data Connection Isolation
  OSA-Express3
–  10 Gigabit Ethernet LR and SR
–  1 Gigabit Ethernet SX and LX
–  1000BASE-T Ethernet – including
  HiperSockets
–  Multi Write Facility
–  Layer 2 and layer 3 support
support for ICC and OSA for NCP
For Clustering
  InfiniBand Coupling Links
  ICB-4 (12 connections)
  ISC-3 (peer mode only)
  IC (define only)
  STP
–  NTP Server and NTP Client support to
provide common time synchronization
across heterogeneous platforms
–  Enhanced time accuracy (NTP server
* Note: Red items carry
with Pulse per second)
forward on a Machine MES
  Support for n-2 and above servers
only, not available for new
  OSA-Express2
–  1000BASE-T Ethernet
–  Gigabit Ethernet LX and SX
–  10 Gigabit Ethernet LR
To the Data
  FICON/FCP – zHPF
–  FICON Express41
–  FICON Express2
–  FICON Express
(Required for FCV)
  ESCON®
system orders
1zHPF
10
IBM System z
only applies to FICON Express4 and FICON Express2
© 2008 IBM Corporation
Protecting with IBM’s world-class Business
Resiliency solutions
  New I/O drawer with concurrent add/replace for drawers 2-4
  Preplanning capabilities to avoid future planned outages, e.g.
dynamic LPAR allocation without a system outage and plan
ahead memory
  Integrated enterprise level resiliency for heterogeneous
data center disaster recovery management
  Policy driven flexibility to add capacity and backup processors
  Basic HyperSwap improves storage availability *
  Integrated cryptographic accelerator
  Tamper-resistant Crypto Express2 feature with enhanced secure
key AES support and capability for increased Personal Account
Numbers
  Audit logging on new Trusted Key Entry (TKE) 5.3 with optional
Smart Card reader
  System z – the only platform that is EAL5 certified
* All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represents goals and objectives only.
11
IBM System z
© 2008 IBM Corporation
z10 BC – The mainframe made over —
Smart, Cool, Affordable
One Hardware Model
Hot Pluggable I/O Drawer
New CPC and I/O Drawers
InfiniBand (IFB)
MBA to I/O interconnect
Faster Uni Processor – 3.5 Ghz
InfiniBand Coupling Links
Up to 5 CPs and 5 zAAP/zIIP
or up to 10 IFLs or CFs
STP over InfiniBand
130 CP Capacity Settings
Replaceable PU and SC SCMs
Up to 248 GB* Customer Memory
(120 GB-Oct. 08, 248-June 09)
FICON Express4 Performance
Improvement
New Family of OSA-Express3
HiperSockets Layer 2 Support
Separate 8 GB of fixed HSA
Enhanced CPACF with SHA 512,
AES 192 and 256-bit keys
HiperDispatch
CBU & On/Off CoD Increased
Functionality and Flexibility
Capacity Provisioning Support
Large Page Support (1 MB)
Hardware Decimal Floating Point
Scheduled Outage Reduction
Improved RAS
Power Monitoring Support
If it’s “mainframe-like” it’s not a “Mainframe”
12
IBM System z
© 2008 IBM Corporation
IBM System z10 Enterprise Class
October 2008 Announcement
© 2008 IBM Corporation
z10 EC – Functions and Features (October 21, 2008)
Plan Ahead memory
Capacity Provisioning
Enhancements – Capacity
Tokens
Run production workload with
CBU test. T & Cs apply
LPAR Dynamic PU reassignment
CPU Measurement Facility
Change weights of LPARs
HMC Console Messenger
HMC and z/VM System
Management
NTP Server on HMC
14
IBM System z
CFCC Level 16
STP Enhancements
PSIFB replacement for ISC-3
High Performance FICON for
System z
OSA-Express3 GbE and
1000BASE-T
Crypto TKE 5.3 Enhancements
z/VM Image Mode
QDIO Connection Isolation
© 2008 IBM Corporation
z10 EC Plan Ahead Memory
  Provides the ability to plan for non-disruptive memory upgrades without exploitation of
Enhanced Book Availability
–  Memory cards are pre-installed based on planned target capacity
–  Supports all System z10 models
–  Can be ordered with standard or “Flexible” memory on multiple book z10s
(Different benefits than “Flexible Memory” in most cases)
  Pre-installed memory is activated by installing a new LICCC
–  Orderable via Resource Link by the customer (CIU upgrade)
–  Orderable as an ordinary MES by IBM
–  Memory upgrade orders use the pre-installed memory first
  Pre-planned memory install
–  FC 1996 - Charged when physical memory is installed used to track the quantity of
physical increments of plan ahead memory capacity
Cost part pre-paid
–  Increment size of 16 GB (based on minimum memory purchase increment)
  Pre-planned memory activation
–  FC 1997 - Charged when Plan Ahead Memory is enabled based on the amount of
Plan Ahead memory that is being activated
Remaining cost paid at time of activation
–  Subsequent memory upgrade orders will use up the Plan Ahead memory first
  Plan Ahead Memory is NOT temporary CoD or CBU memory
(Removing memory is disruptive)
15
IBM System z
© 2008 IBM Corporation
Capacity Tokens Overview
  Pre-paid Offering
–  Non-expiring
  Post-paid Offering
–  To set spending limits on the offering record expires after 180 days
Types of Tokens:
  Specialty engines: IFL/ICF/zIIP/zAAP/SAP Day tokens
–  The specialty engine tokens to be billed per day equal the highest activation
level for this resource during the current 24 hour billing window period
–  Example: if five zAAPs were the max activation level during this window, at the
end of the window five zAAP tokens will be subtracted
  CP MSU Tokens
CP 1 MSU Token is used per MSU day per 24 hour period
Example: 86 additional MSUs for 300 days (86x300=25,800 MSU tokens)
  CBU Tokens
Length of the CBU contact one to five years
Number of CBU tests remaining within the CBU record (MAX 15)
16
IBM System z
© 2008 IBM Corporation
z10 – Running Production workload with CBU
Test
  Customers may now execute production workload during a CBU test
provided:
–  An amount of System z production workload Capacity equivalent to the CBU
Upgrade is shut down or otherwise made unusable by the Customer for the
duration test
–  The appropriate contracts are in place. All new CBU contract documents
contain these new CBU Test terms
–  Existing CBU customers will need to execute IBM Customer Agreement
Amendment for IBM System z Capacity Backup Upgrade Tests
–  Applies to any System z capable of CBU
17
IBM System z
© 2008 IBM Corporation
z10 EC LPAR Dynamic PU Reassignment
  PR/SM dynamic relocation of running processors to different processor cores
  Designed to optimize physical processor location for the current LPAR logical processor configuration
  Swap an active PU with a different active PU in a different book
–  Designed Benefit: Better L2 cache reuse
–  CP, zAAP, zIIP, IFL and ICF supported
–  Triggers: Partition activation/deactivation, machine upgrades/downgrades, logical processors on/off
  Designed to provide the most benefit for:
–  Multiple book machines
–  Dedicated partitions and wide partitions with HiperDispatch active
IBM System z
Processor Book 1
Processor Book 0
Processor Book 2
HCA2-Cs
Memory
18
HCA2-Cs
Memory
HCA2-Cs
Memory
Memory
Processor Book 3
Swap
HCA2-Cs
© 2008 IBM Corporation
System z10 CPU Measurement Facility
  CPU Measurement Facility
– Ability to surface specific performance information
– Will not have tools available at announce/GA to
manipulate/interpret the data
– Will be helpful for analysis of customer data
– Data would be sent to IBM for analysis
19
IBM System z
© 2008 IBM Corporation
z10 Scheduled Operations for Change LPAR
Weights
  Requirement to change the weights of LPARs on a scheduled basis (as
opposed to manually doing this through Change LPAR Controls
  New Scheduled operation (for 2.10.1 or higher):
  Once scheduled, details for the operation can only be shown on the SE
(use Single Object Operations if on the HMC)
20
IBM System z
© 2008 IBM Corporation
HMC/SE Console Messenger
  Provide basic messaging capabilities that allow system operators or administrators to
coordinate their activities
  Provide this capability to HMC and SE users
  Allow messaging between local users and remote users using existing HMC and SE
interconnection protocols
–  Use same TCP/IP-based protocols, network ports as is used for existing HMC to
HMC and HMC to SE communication
  Console Messenger provides basic features, but does not aim to be a full fledged
collaboration application ala Lotus® Sametime, Microsoft Messenger, etc.
  Interactive chats between two partners
–  Send/receive messages with chat history displayed in the task panel
  Broadcast message to all sessions on a selected console
–  Send one-shot message to all sessions on selected console
  Plain text messages in chats and broadcast messages
  Not Supported:
–  Multi-party chat sessions
–  Rich text messages
–  File transfer as part of chat sessions
–  Buddy lists
–  Active user online / offline tracking
21
IBM System z
© 2008 IBM Corporation
NTP Client support on HMC (and TKE)
  Added to the HMC and TKE
  HMC and TKE can both obtain their time via NTP
  NTP client support on SE, used for STP-only CTNs, can use
the HMC as an NTP time server.
22
IBM System z
© 2008 IBM Corporation
z/VM-Mode LPAR Support for IBM System z10
  New LPAR type for IBM System z10: z/VM-mode
–  Allows z/VM V5.4 users to configure all CPU types in a z10 LPAR
  Offers added flexibility for hosting mainframe workloads
–  Add IFLs to an existing standard-engine z/VM LPAR to host Linux workloads
–  Add CPs to an existing IFL z/VM LPAR to host z/OS, z/VSE, or traditional CMS workloads
–  Add zAAPs and zIIPs to host eligible z/OS specialty-engine processing
–  Test integrated Linux and z/OS solutions in the same LPAR
  No change to IBM software licensing
–  Software continues to be licensed according to CPU type
Linux Production
Dev/Test and Optional Failover
z/VM-mode LPAR
z/OS
z/OS
CFCC
CMS
Linux Linux
Linux Linux Linux
z/OS Production
z/OS
z/OS
z/OS
CFCC
z/VM
z/VM
LPAR
LPAR
LPAR
LPAR
LPAR
LPAR
CP
CP
CP
CP
CP
zAAP
zAAP
zAAP
zIIP
zIIP
ICF
ICF
IFL
IFL
IFL
IFL
IFL
IBM System z10
23
IBM System z
© 2008 IBM Corporation
z10 HMC Support for z/VM
  New HMC support that exploits z/VM Systems Management APIs:
–  Define and change shared user definitions via:
Profile Create | Delete | Replace | Query *
–  Define and change virtual hardware resources via:
Virtual Network LAN Access | Create | Delete | Query *
CPU Allocate | Deallocate | Query
I/O Allocate | Deallocate | Query
Virtual Memory Allocate | Deallocate | Query
Volume Create | Delete | Query
  These tasks target a single CPC Image
  Require SMAPI v5.3 or later
–  The Profiles task and Edit VMRM File task requires SMAPI
v5.4 or later. Most require a Directory Manager
  Expectation is that the end user for these tasks is already
knowledgeable in the areas of user directories, profiles, prototypes,
volume space and resource management
  Improved performance for HMC-to-z/VM
communications in z/VM V5.4
–  Integration of SCLP interface into the Systems
Management APIs reduces time required to
process HMC tasks
* New APIs introduced in z/VM V5.4
24
IBM System z
© 2008 IBM Corporation
z10 CFCC Level 16
  Designed to improve CF Duplexing performance
–  System z10 exclusive
–  Requires two CFCC level 16 CFs
–  Ready to Commit (RTC) signal is now asynchronous to the transaction
CF to CF exchange without z/OS waiting for acknowledgement
Designed to enhance performance, especially in the GDPS environment
  New command for list notifications
–  WebSphere MW Shared Queue environment
–  CF notification improvements to avoid false schedules in IMS
–  Parallelize cleaning up the lock table.
  Structure and CF Storage Sizing with CFCC level 16
–  May increase storage requirements when moving from:
CF Level 15 (or below) to CF Level 16
  CF Sizer Tool recommended
–  http://www.ibm.com/systems/z/cfsizer/
  OS requirements for z10 Servers with CFLEVEL 16
–  z/OS 1.8 or higher plus PTF
(z/OS 1.7 with Lifecycle Extension, 5637-A01, plus PTF)
–  z/VM 5.2 or higher for guest virtual coupling
  Migrating to new level of CFCC requires one to recycle the CF LPAR
25
IBM System z
© 2008 IBM Corporation
z10 CFCC Level 16
  New command for list notifications (shared queues)
–  With shared queues (IMS, MQ), the CF will notify only one of the connectors
instead of all. This avoids the overhead of false scheduling CF requests.
–  Prior to CFCC 16, non-empty state change is broadcast to all connectors
First one to respond reads entry
All others try, find nothing to read, but pay cost for effort
–  CFCC 16
Notify only one connector - First connector determined by round robin
If List went to “Empty” after period of time, then Success!
If not, then notify all other connectors (as done previously)
Hey, I got a
message for
one of you!
What is
What
is
it?
What
is
it?
What
is
it?
What
it? is
it?
MQ
IMS
26
IBM System z
© 2008 IBM Corporation
OSA-Express Queued Direct Input/Output
(QDIO), data connection isolation for z/VM
  OSA-Express QDIO data connection isolation for the z/VM environment on System z10 and
System z9
–  Multi-tier security zones are fast becoming the network configuration standard for new
workloads. Therefore, it is essential for workloads (servers and clients) hosted in a virtualized
environment (shared resources) to be protected from intrusion or exposure of data and
processes from other workloads
–  With QDIO, data connection isolation, internal "routing" can be disabled on a per QDIO
connection basis. Establish security zone boundaries that have been defined by network
administrators and have a mechanism to isolate a QDIO data connection (on an OSA port),
forcing traffic to flow to the external network, ensuring that all communication flows only
between an operating system and the external network
–  QDIO data connection isolation is designed to give the ability to adhere to security and
HIPPA-security guidelines and regulations for network isolation between the instances sharing
physical network connectivity. This support does not affect the ability to share an OSAExpress port. Sharing occurs as it does today, but the ability to communicate between sharing
QDIO data connections may be restricted through the use of this support. Ability to decide
whether an operating system's or VSWITCH's OSA-Express QDIO connection is to be
nonisolated (default) or isolated
  Supported by z/VM 5.3 plus PTFs and all of the OSA-Express3 and OSA-Express2 features
(CHPID type OSD) on System z10 and to the OSA-Express2 features on System z9
27
IBM System z
© 2008 IBM Corporation
z10 High Performance FICON for System z (zHPF)
  FICON architecture for protocol simplification and efficiency, reducing the number of Information
Units (IUs) processed. When exploited by the FICON channel, the z/OS operating system, and
the control unit, FICON channel overhead is reduced and performance improved
–  Packages a series of commands in a single packet that looks like an SCSI CDB
–  Allows streaming of data for multiple commands in a single data transfer
  The maximum number of I/Os per second is designed to be improved up to 100%* for small block
sizes data transfers that can exploit the zHPF protocol
  Requires control unit feature code for exploitation
–  Feature is ‘High Performance FICON’
–  Requires a priced license feature (one time charge) and a monthly maintenance charge
–  IBM System Storage DS8000 family – Release 4.1(LMC level 5.4.1.xx (bundle version
64.1.x.x), or later.)
  Applicable to all FICON Express4 and Express2 features CHPID type FC
–  Implemented in System z10 Licensed Internal Code
–  An FC channel can support multiple CUs using both older FICON protocol and zHPF
protocol at the same time. Control unit capability is determined automatically
–  zHPF protocols will not be used unless all the CHPIDs and control unit ports for the device
support the new protocols
  Exclusive to System z10
  Supported by z/OS 1.8 and higher releases with PTF
*Note: Some complex channel programs can not be converted to zHPF protocol
28
IBM System z
© 2008 IBM Corporation
z10 High Performance FICON for System z (zHPF)
  Optimization of storage area network (SAN) traffic using zHPF to improve performance
–  Maximum number of I/Os per second can be increased by up to 100%*
–  For OLTP workloads (DB2, VSAM, PDSE, and zFS ) that transfer small blocks of fixed size data (4K blocks)
  Exclusive to System z10 – FICON Express4 and FICON Express2
  Requires
–  Control unit exploitation – IBM DS8000 Release 4.1
–  z/OS V1.7 with the IBM Lifecycle Extension for z/OS V1.7 (5637-A01), V1.8, V1.9, or V1.10 with PTFs
z
z
H
H
P
P
F
F
MegaBytes per second (full-duplex)
Large sequential read/write mix
FICON Express4
4 Gbps
I/Os per second
4k block size, channel 100% utilized
FICON
Express4
4 Gbps
FICON
FICON Express4
and
Express4
FICON
and
FICON Express2
Express2
FICON
Express2
2 Gbps
FICON
Express
1 Gbps
FICON
G5/G6
z900
FICON Express4
FICON Express2
FICON
Express
2 Gbps
FICON
Express
FICON
Express
FICON
z990
z890
z900
z800
z9
z990
z890
FICON
z10
z9
z10
zHPF
G5/G6
z900
z900
z800
z990
z890
z9
z990
z890
z10
z10
zHPF
* Some complex channel programs can not be converted to zHPF protocol
29
IBM System z
© 2008 IBM Corporation
z10 FICON – Name Server Registration
  The FICON channel now provides the same information to the fabric as
is commonly provided by open systems, registering with the name
server in the attached FICON directors
–  Enables quick and efficient management of storage area network
(SAN) and perform problem determination and analysis.
  Platform registration is a standard service defined in the Fibre Channel Generic Services 3 (FC-GS-3) standard (INCITS (ANSI) T11.3 group)
–  It allows a platform (storage subsystem, host, etc.) to register
information about itself with the fabric (directors).
  Applicable to all FICON Express4, FICON Express2, and FICON
Express features - CHPID type FC
  Exclusive to System z10
  Transparent to operating systems
30
IBM System z
© 2008 IBM Corporation
z10 OSA-Express3
  Double density of ports compared to OSA-Express2
–  Reduced CHPIDs to manage
–  Reduced I/O slots
–  Reduced I/O cages or I/O drawers
–  Up to 96 LAN ports versus 48
  Designed to reduce the minimum round-trip networking time between z10 BC & z10 EC
systems (reduced latency)
–  Designed to improve round trip at the TCP/IP application layer
OSA-Express3 10 GbE
45% improvement compared to the OSA-Express2 10 GbE
OSA-Express3 GbE
45% improvement compared to the OSA-Express2 GbE
–  Designed to improve throughput (mixed inbound/outbound)
OSA-Express3 10 GbE
1.0 GBytes/ps @ 1492 MTU
1.1 GBytes/ps @ 8992 MTU
3-4 times the throughput of OSA-Express2 10 GbE
0.90 of Ethernet line speed sending outbound 1506-byte frames
1.25 of Ethernet line speed sending outbound 4048-byte frames
The above statements are based on OSA-Express3 performance measurements performed in a test environment on a System z10 EC
and do not represent actual field measurements. Results may vary.
31
IBM System z
© 2008 IBM Corporation
z10 OSA-Express3 – 10 GbE
  10 Gigabit Ethernet LR (Long Reach) and
SR (Short Reach)
–  One port per PCI-E adaptor
–  Two ports per feature
–  Small form factor connector (LC Duplex)
LR = Single Mode 9 micron fiber
SR = Multimode 50 or 62.5 micron fiber
–  Two CHPIDs, one port each
Type OSD (QDIO TCPIP and Layer 2)
  New Microprocessor and hardware data
router
–  Large send packet construction, inspection
and routing preformed in hardware instead
of firmware
–  Large send for IPv4 traffic
–  Checksum offload
–  Concurrent LIC update
–  Designed to improve performance for
standard (1492 byte) and jumbo frames
(8992 byte)
  Up to 45% reduction in latency compared
to OSA-Express2 10 GbE
32
IBM System z
PCI-E
LC Duplex SM
PCI-E
LC Duplex SM
10 GbE – LR, 2 ports
PCI-E
PCI-E
LC Duplex MM
LC Duplex MM
10 GbE – SR, 2 ports
© 2008 IBM Corporation
z10 EC OSA-Express3 GbE – 4 ports feature
  Gigabit Ethernet LX and SX
–  Four ports per feature options
–  Two ports* per PCI-E adaptor/CHPID
OS PTF required to use 2nd port
–  CHPIDs support
OSD (QDIO TCPIP and Layer 2)
OSN (OSA-Express for NCP)
–  Small form factor connector (LC Duplex)
LC Duplex SM
PCI-E
  New microprocessor and hardware data
router
–  Large send packet construction, inspection
and routing preformed in hardware instead
of firmware
–  Large send for IPv4 traffic
4 LX ports
or
4 SX ports
PCI-E
LC Duplex MM
GbE - 4 ports
–  Checksum offload
–  Concurrent LIC update
  Up to 45% reduction in latency compared to
OSA-Express2 GbE
* NOTE: To use 2-Ports per PCI-E adaptor, the following is required – z/OS V1.9+, z/VM V5.2+, z/VSE V4.1+, zTPF 1.1 PUT 4 with APARs.
If this support isn’t installed, only port zero on a PCI-E adaptor is ‘visible’ to the Operating System
33
IBM System z
© 2008 IBM Corporation
z10 EC OSA-Express3 – 1000BASE-T, 4 port
feature
  1000BASE-T Ethernet
  Two and Four ports per feature options
–  RJ45, Cat 5 UTP
–  Two ports* per PCI-E adaptor/CHPID
–  CHPIDs Supported
OSC (OSA-Integrated Console)
OSD (TCPIP and Layer 2)
PCI-E
PCI-E
OS PTF required to use 2nd port
OSE (Non-QDIO TCPIP and SNA/APPN®)
OSN (OSA-Express for NCP)
  New microprocessor and hardware data
router
–
–
–
–
–
Large send for IPv4 traffic
Checksum offload
Concurrent LIC update
Auto-negotiation 10/100/1000
Large send packet construction, inspection and
routing performed in hardware
1000BASE-T, 4 ports
Notes:
  For CHPID type OSC, Port 0 is only used. Port
1 not ‘visible’ to OS
  For CHPID type OSD, OSE, both ports on
each PCI-E adaptor are used
  Each PCI-E adaptor can be defined as the
same or different CHPID type
* NOTE: To use 2-Ports per PCI-E adaptor, the following is required – z/OS V1.9+, z/VM V5.2+, z/VSE V4.1+, zTPF 1.1 PUT 4 with APARs.
If this support isn’t installed, only port zero on a PCI-E adaptor is ‘visible’ to the Operating System.
34
IBM System z
© 2008 IBM Corporation
z10 Coupling Link Options
  PSIFB – 12x IB-DDR for high speed communication at medium distance
–  New CHPID – CIB (Coupling using InfiniBand)
–  New 50 micron OM3 (2000 MHz-km) multimode fiber with MPO connectors
–  Up to 150m
  PSIFB – 1x IB-SDR or 1x IB-DDR
–  Unrepeated distanced up to 10 km
–  Repeated distances at up to 100 km when attached to a Dense Wavelength Division
Multiplexer (DWDM) qualified by System z10
–  Speed may be auto-negotiated if the attached DWDM is capable of operating at SDR or DDR
Supports SDR at 2.5 Gbps when connected to a DWDM capable of SDR speed
Supports DDR at 5 Gbps when connected to a DWDM capable of DDR speed
–  9 micron single mode fiber optic cables with LC Duplex connectors.
  ICB-4 for short distances over copper cabling
–  New ICB-4 cables are required
z10 to z10 and z10 to System z9/z990/z890
–  10 meter distance remains
–  ICB-4 for non-raised floor z10 BC not supported (non-raised z9 BC with ICB-4 will not
connect to z10 BC)
–  ICB-4 not supported on z10 EC Model E64
  ISC-3 for extended distance over fiber optic cabling
–  No change to current cabling
  Internal Coupling channels (IC)
Note: The InfiniBand link data rates of 6 GBps, 3 GBps, 2.5 Gbps, or 5 Gbps 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. With InfiniBand coupling links, while the link data rate may be higher than that of ICB
(12x IB-SDR or 12x IB-DDR) or ISC-3 (1x IB-SDR or 1x IB-DDR), the service times of coupling operations are greater, and the actual throughput may be less than with ICB
links or ISC-3 links.
35
IBM System z
© 2008 IBM Corporation
Server Time Protocol (STP) Enhancements
  Enhanced Accuracy to an External Time Source (ETS)
–  Designed for 10 microseconds accuracy vs 100 milliseconds accuracy with dial out from HMC or NTP
Client support
–  Utilizes highly stable, accurate Pulse Per Second (PPS) output from NTP servers available from some
vendors
–  Available on z10, and z9
–  Fulfills Statement of Direction made in October 2006
  Continuous Availability of External Time Source (ETS)
–  ETS configured for Backup Time Server (BTS) can be used for time adjustments to maintain ETS
accuracy, if ETS configured for Preferred Time Server (PTS) not accessible
–  Applies to NTP server support with or without PPS
  Enhanced STP recovery when Internal Battery Feature is in use
–  Designed to enable PTS/CTS to reconfigure the BTS as the CTS if
Power outage of PTS/CTS
Power outage of site where PTS/CTS and Arbiter are located
  STP configuration and time information saved across Power on Resets or power outages
–  Does not require Initializing the time or reassigning PTS/CTS roles
–  “One server” configuration enhancement
–  Available on z10, z9, z990 and z890
  NTP Server on Hardware Management Console
–  NTP Client on Support Element (SE) can access NTP server using a secure LAN connection
  API to automate STP CTN Reconfiguration
–  Allows automation to reconfigure special roles of servers (PTS, BTS, Arbiter) after a recovery action
–  Maintains recovery capability in the event of a second failure
36
IBM System z
© 2008 IBM Corporation
IBM System z10 EC Key Dates
  IBM System z10 Enterprise Class (z10 EC) Announce – October 21, 2008
–
–
–
–
First Day Orders for GA2 Systems
Resource Link™ support available
Capacity Planning Tools (zPCR, zTPM, zCP3000) - updated
SAPR Guide and SA Confirmation Checklist available
SAPR Guide, SA06-016 - updated
  Planned Availability Dates:
  October 28, 2008
–
–
–
–
–
–
z10 EC features and functions
OSA-Express QDIO data connection isolation for the z/VM® environment on z10 EC, z9 EC, z9 BC
TKE 5.3 LIC (#0854) on z10 EC, z9 EC, z9 BC
TKE additional smart cards (#0884) on z10 EC, z9 EC, z9 BC
TKE smart card reader (#0885) on z10 EC, z9 EC, z9 BC
STP enhancements on z10 EC
  January 28, 2009
–
–
–
–
–
–
–
–
–
–
Functions:
OSA-Express QDIO data connection isolation for the z/VM environment on System z10 and z9
STP enhancements on z9 EC, z9 BC, z990, z890
MES features:
HCA2-O LR fanout card for 1x long reach InfiniBand® (#0168) on z10 EC
OSA-Express3 1000BASE-T (#3367) and 10 GbE SR (#3371) on z10 EC
Capacity on Demand features (#9917 - #9929) on z10 EC
TKE 5.3 LIC (#0854) on z10 EC, z9 EC, z9 BC
TKE additional smart cards (#0884) on z10 EC, z9 EC, z9 BC
TKE smart card reader (#0885) on z10 EC, z9 EC, z9 BC
  1H09
–  HMC feature #0090 on z10 EC, z9™ EC, z9 BC
–  Statement of Direction* - PSIFB on z10 EC any z9 General Purpose Server
  ITSO Redbooks® (Draft versions) – All updated – October
z10 EC Technical Introduction, SG24-7515 – October 21, 2008
z10 EC Technical Guide, SG24-7516 – October 21, 2008
z10 EC Capacity on Demand, SG24-7504 – October 21,, 2008
System z I/O Connectivity Handbook, SG24-5444 – October 21, 2008
* All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represents goals and objectives only.
37
IBM System z
© 2008 IBM Corporation