IBM United States
Hardware Announcement 102-209
August 13, 2002
New Functions for IBM zSeries Servers Enhance Connectivity
(Corrected on September 3, 2002)
In the Description section, the Availability of OSA-Express Enhancements
section was updated.
At a Glance
New connectivity and Geographically Dispersed Parallel Sysplex (GDPS) functions on zSeries servers (z800 and z900).
For ordering, contact:
Your IBM representative, an IBM Business Partner, or IBM Americas Call Centers at 800-IBM-CALL (Reference: YE001).
IBM is announcing new functions in a continuing quest to provide connectivity options for Fibre Connection (FICON) and Open Systems Adapter Express (OSA-Express) in the zSeries environment.
Two new offerings in support of FICON environments are being offered.
In response to customer requirements, the OSA-Express features, when configured for Queued Direct Input/Output (QDIO) mode (OSD CHPID type), now support the setting of multiple secondary routing partitions, in addition to the one primary routing partition.
IBM is announcing enhancements to Geographically Dispersed Parallel Sysplex (GDPS).
zSeries FICON support of cascaded directors is planned to be included in the January 31, 2003, maintenance level of driver 3G for the z800 and z900 servers. This function also requires, either of IBM's re-marketed INRANGE FC/9000 or McDATA Intrepid FICON directors with cascading support when available and z/OS V1.3 or V1.4 with service as defined in the PSP Buckets for device type 2032 or 2042, or processor 2064 or 2066.
Support of 2 Gbps link data rates and the setting of multiple secondary routing partitions for OSA are included in the latest maintenance levels of driver 3G for the z800 and z900 servers.
Prerequisites for GDPS may be found in the GDPS white paper at:
or by sending a note to firstname.lastname@example.org.
Planned Availability Dates
zSeries FICON Support of Cascaded Directors
Today, IBM is announcing an enhancement to Native FICON (FC Channel Path Identifier [CHPID] type) channels, adding zSeries FICON support of cascaded directors, planned to be available on January 31, 2003. This support is for a two-switch configuration only. With cascading, a Native FICON (FC CHPID type) channel or a FICON Channel to Channel (CTC) can connect a server to a device or other server with two native FICON directors in between. This cascaded director support is planned to be delivered in conjunction with IBM's re-marketed INRANGE FC/9000 and McDATA Intrepid FICON directors. Cascaded director support (sometimes referred to as cascaded switching) is for single-vendor fabrics only.
This announcement pertains to all Native FICON (FC CHPID type) channels implemented on either existing FICON features on z900, or new/existing FICON Express features on z900 and z800. This announcement is for Native FICON (FC CHPID type) channels only including FICON CTC.
IBM plans to support a limited number of early installations for qualified customers through IBM's Early Support Program. Contact your IBM representative if you are interested in participating in this program.
Cascaded support is important for disaster recovery and business continuity solutions. It can provide high-availability connectivity as well as the potential for fiber infrastructure cost savings for extended storage networks. FICON two director cascaded technology can allow for shared links and therefore improved utilization of intersite connected resources and infrastructure. Solutions such as Geographically Dispersed Parallel Sysplex (GDPS) can benefit from the reduced inter-site configuration complexity that Native FICON cascaded directors provide. While specific cost savings vary depending upon infrastructure, workloads and size of data transfers, generally customers who have data centers separated between two sites may reduce the number of cross site connections by using cascaded directors. Further savings may be realized in the reduction of the number of channels and switch ports.
Another important value of FICON cascaded directors is its ability to provide high integrity data paths. The high integrity function is an integral component of the FICON architecture when configuring FICON channel paths through a cascaded fabric. To support the introduction of FICON cascaded switching, IBM has worked with the FICON director vendors to help ensure that robustness in the channel to control unit path is maintained to the same high standard of error detection, recovery, and data integrity, that has existed for many years with both ESCON® and the initial implementation of FICON.
End-to-end data integrity is designed to be maintained through the cascaded director fabric. Data integrity helps ensure that any changes to the customer's data streams are always detected, and the data frames (data streams) are delivered to the correct end point (an end point being a FICON channel port or a FICON Control Unit [CU] port). For FICON channels, Cyclic Redundancy Checking (CRC), and Longitudinal Redundancy Checking (LRC) are bit patterns added to the customer data streams to allow for detection of any bit changes in the data stream. With FICON cascaded switching, new integrity features are introduced within the FICON channel and the FICON cascaded switch fabric to help ensure the detection and reporting of any miscabling actions occurring within the fabric during operational use that may cause a frame to be delivered to the wrong end point.
Compatibility: A FICON channel when configured to operate with a cascaded switch fabric, requires that the switch fabric supports high integrity. During initialization, the FICON channel will query the switch fabric to determine that it supports high integrity, and if it does, then the channel will complete the initialization process allowing the channel to operate with the fabric. Both McDATA and INRANGE may offer features to support high integrity cascading. For more information on availability, contact McDATA and INRANGE directly.
Once a FICON switch fabric has been customized to support FICON cascaded
switching and the required switches have been customized in the fabric
switch list, the fabric will check that its inter-switch-links (ISLs) are
installed to the correct switches before they are made operational. Once
the ISLs are operational, any changes to the ISL connections will be
checked by switches within the fabric before they can be used (the
connected switches must be in the switch fabric list). With this
checking, if an ISL is incorrectly installed, the fabric is designed to
stop using the links for customer data streams thereby preventing frames
from being delivered to the wrong end points.
FICON Express Features Support 2 Gbps Link Speeds
IBM announces the availability of 2 Gbps links for the zSeries FICON Express features configured as native FICON (FC CHPID type) or Fibre Channel Protocol (FCP CHPID type). This 2 Gbps support is available for the FICON Express features on zSeries 900 and zSeries 800.
This announcement is consistent with the industry's movement to support of 2 Gbps link data rates as defined by the industry standard, Fibre Channel architecture. The FICON Express features are capable of auto-negotiation with the attached device to operate at 1 or 2 Gbps.
Applications with highly sequential large data transfers of all reads or all writes (previously limited to 100 Megabytes per second [MB/s] with the 1 Gbps link) can now achieve up to 150 to 170 MB/s with the 2 Gbps link, which means up to a 50 to 70 % improvement in the effective data throughput.
To benefit from 2 Gbps link data rates, the infrastructure needs to be positioned to take advantage of this higher data rate capability. For 2 Gbps link capability, each FICON/Fibre Channel port and each FICON/Fibre Channel device must be capable of 2 Gbps, for a 2 Gbps end-to-end data path.
For FICON/Fibre Channel directors, 2 Gbps support is, or is planned to be, available for IBM remarketed McDATA and INRANGE directors. The McDATA Intrepid 6064 director introduced a 2 Gbps Fibre Channel capability earlier this year (IBM 2032-064). Refer to ibm.com/storage/mcdata for additional details. The INRANGE FC/9000 Fibre Channel director is expected to support a 2 Gbps link data rate, (64-port IBM 2042-001, 128-port IBM 2042-128). Refer to ibm.com/storage/inrange for additional details.
For IBM Disk Drives, 2 Gbps support is available with the IBM TotalStorage Enterprise Storage Server (ESS) Machine Type 2105, Model 800. As announced on July 15, 2002, the ESS General availability is planned to be August 16, 2002. Refer to Hardware Announcement 102-201 , dated July 15, 2002.
The major benefit for disk transfers will be increased data throughput. Theoretically, up to twice the data may be transferred over the same number of connections when the link speed is doubled.
Note: In most applications, the sustained throughput is 70 to 80% of the maximum theoretical speeds.
The following matrix contrasts the unrepeated distances capable when using single mode or multimode fiber at 1 Gbps and 2 Gbps.
1 Gbps link 2 Gbps link Fiber Type Light Unrepeated Link Unrepeated Link in Microns (u) Source Distance Budget Distance Budget 9 u single mode LX laser 10 km 7.8 dB 10 km 7.8 dB 6.2 miles 6.2 miles 50 u multimode SX laser 500 meters 3.9 dB 300 meters 2.8 dB 1640 feet 984 feet 62.5 u multimode SX laser 250 meters 2.8 dB 120 meters 2.2 dB 820 feet 394 feet
Note: These numbers reflect the Fibre Channel Physical Interface specification. The link budget above is derived from combining the channel insertion loss budget with the unallocated link margin budget. The light budget numbers have been rounded to the nearest 10th.
Refer also to Planning for Fiber Optic Links (ESCON, FICON, Coupling Links, and Open Systems Adapters), GA23-0367-07b or higher, which can be found on ResourceLink.
Care should be taken to ensure that the tactical as well as the strategic requirements for your data center, Storage Area Network (SAN), and Network Attached Storage (NAS) infrastructures are taken into consideration as you employ 2 Gbps and beyond link data rates.
Note: Mode Conditioning Patch (MCP) cables are not supported at the 2 Gbps link data rate.
Additionally, as distance solutions are planned, attention must be paid to the types of fiber optic cabling employed and the associated distance limitations. Dense Wave® Division Multiplexing (DWDM) and optical amplifier technologies may soon be or may be available in 2 Gbps link speeds from Cisco Systems and Nortel Networks. For more information on availability, contact these vendors directly.
Note that in the FICON/FCP environment, a single vendor fabric is
supported; there cannot be a mix of Nortel Networks and Cisco Systems
equipment in the same SAN. Neither can there be a mix of McDATA and
INRANGE directors in the same SAN.
Network Connectivity Update
Support for Multiple Secondary Router Settings: Presently an OSA-Express feature allows the setting of two routing stacks/interfaces (one primary and one secondary) that serve as receptors for all Internet Protocol (IP) packets with IP destination addresses not matching a registered IP address on the OSA-Express feature. For QDIO, these designations are presently set through a statement in the TCP/IP profile on z/OS and z/VM and in the chandev.conf file on Linux.
You will now be able to define multiple secondary routers (only one Primary) for QDIO Gigabit Ethernet and Fast Ethernet only. IP packets received from the Local Area Network (LAN) with an unknown destination address will be routed in the following manner:
There is no way to explicitly set the order of the secondary routers.
Availability of OSA-Express Enhancements
IBM announced OSA-Express enhancements for networking on April 30, 2002. The hardware support became available May 15, 2002. Now, IBM is announcing the availability of the following functions in the z/OS Version 1 Release 4 environment.
Refer to Software Announcement 202-190 , dated August 13, 2002.
Geographically Dispersed Parallel Sysplex (GDPS) Enhancements: GDPS, an industry leading e-business availability solution, available through IBM Global Services, is a multisite solution that is designed to provide the capability to manage the remote copy configuration and storage subsystems, automate Parallel Sysplex operational tasks, and perform failure recovery from a single point of control, thereby helping to improve application availability. GDPS supports both the synchronous Peer-to-Peer Remote Copy (PPRC), as well as the asynchronous Extended Remote Copy (XRC) forms of remote copy. Depending on the form of remote copy, the solution is referred to as GDPS/PPRC or GDPS/XRC. GDPS/PPRC and GDPS/XRC have been enhanced to include the following new functions:
For a more detailed description of GDPS and these functions, refer to the white paper available at:
Use Priority/Reference Code: YE001 Phone: 800-IBM-CALL Fax: 800-2IBM-FAX Internet: email@example.com Mail: IBM Atlanta Sales Center Dept. YE001 P.O. Box 2690 Atlanta, GA 30301-2690
You can also contact your local IBM Business Partner or IBM representative. To identify them, call 800-IBM-4YOU.
Note: Shipments will begin after the planned availability date.