Storage networking products
This chapter introduces storage networking options that can be employed to build an optimal storage environment. It describes both Ethernet and Fibre Channel options.
This chapter includes the following sections:
9.1 Overview
Data access requirements of the many applications in use across an organization are different, and therefore cannot be solved with a single storage networking approach. There are trade-offs in cost, ease-of-management, performance, distance, and maturity.
The two popular models for attaching the storage to the network are storage area network (SAN) and network-attached storage (NAS). These methods help to remove direct attachments between storage and server, providing more flexibility in storage provisioning and the maximization of valuable storage and host resource.
The SAN can be viewed as an extension of the storage bus concept that enables storage devices and servers to interconnect by using elements such as routers, switches, directors, and gateways. Storage I/O, command, and control communications are performed on this dedicated network, providing an any-to-any connection for processors and storage on that network.
The most common transport media is Fibre Channel (FC). Fibre Channel Protocol (FCP) is the I/O protocol for open systems. Fibre Connectivity (FICON) and FCP are available for mainframe environments to communicate. These protocols offer high data rates and low latency communication, which are a requirement for today’s data intensive applications.
Internet SCSI (iSCSI), Fibre Channel over IP (FCIP), Internet Fibre Channel Protocol (iFCP), Fibre Channel over Ethernet (FCoE), and Fibre Channel over Converged Enhanced Ethernet (FCoCEE) all provide the ability to implement storage connectivity by using Ethernet based solutions to extend the distance of an existing FC environment or maximize the Ethernet-based resources that are available.
9.2 SAN and related technologies
This section provides an overview of some key SAN technologies.
9.2.1 Storage area network
A SAN is a dedicated network for storage devices and the systems that access those devices. Figure 9-1 on page 233 represents the typical installation of a SAN. Storage networking today typically uses the FC technology, but the concept of a SAN is independent of the underlying type of network. I/O requests to disk storage on a SAN are called block I/Os because, similar to the direct-attached disk, the read and write I/O commands identify a specific device (disk drive or tape drive) and, for disks, specific block (sector) locations on the disk.
Figure 9-1 shows a typical SAN environment.
Figure 9-1 Typical SAN environment
SANs are used to connect shared storage arrays and tape libraries to multiple servers, and are used by clustered servers for failover. Through correct architecture and configuration, both availability and performance are increased.
A SAN facilitates direct, high-speed data transfers between servers and storage devices, potentially done in any of the following ways:
•Server to storage: This capability is the traditional model of interaction with storage devices. The advantage is that the same storage device can be accessed serially or concurrently by multiple servers.
•Server to server: With this capability, the SAN can be used for high-speed, high-volume communications between servers. In addition, the SAN is used as a communication path between cluster nodes in clustered systems, such as IBM PowerHA® SystemMirror® for AIX.
•Storage to storage: This outboard data movement capability enables data to be moved without server intervention, freeing up server processor cycles for other activities such as application processing. Examples include a disk device backing up its data to a tape device without server intervention, or remote device mirroring across the SAN.
SANs allow applications that move data to perform better, for example, by sending the data directly from the source to the target device with minimal server intervention. SANs also enable network architectures where multiple hosts access multiple storage devices that connect to the same network.
SAN usage can potentially offer the following benefits:
•Improvements to application availability: Storage is independent of applications and accessible through multiple data paths for better reliability, availability, and serviceability.
•Higher application performance: Storage processing is off-loaded from servers and moved onto a separate network.
•Centralized and consolidated storage: Management, scalability, flexibility, and availability are simpler.
•Data transfer and vaulting to remote sites: Remote copy of data is enabled for protection from disasters and malicious attacks.
•Simplified centralized management: Having a single image of storage media simplifies management.
•Storage cloud services: Storage virtualization and dynamic storage provisioning require the reliable SAN layer.
Fibre Channel
FC is well-established in the open systems environment as the underlying architecture of the SAN. FC is a technology standard that allows data to be transferred from one network node to another at a high speed. The interconnections between nodes are not necessarily based on fiber optics, but can also be based on copper cables. FC is ideal for moving large volumes of data across long distances quickly and reliably. In current implementations, the FC standard speed is generally available from 2 Gbps up to 32 Gbps. However, older 4 Gbps and 8 Gbps equipment is being replaced by faster connections.
FC is structured with independent layers, as are other networking protocols. Five layers exist, where 0 is the lowest layer. The physical layers are 0 - 2. These layers carry the physical attributes of the network and transport the data that is created by the higher-level protocols such as:
•Small Computer System Interface (SCSI)
•Transmission Control Protocol/Internet Protocol (TCP/IP)
•Fibre Channel connection (FICON)
Converged network
SAN and LAN are often implemented as separate network infrastructures by using Ethernet network interface cards (NICs), and Fibre Channel by using FC host bus adapters (HBAs). With today’s high-performance networks, many servers are only able to use a small fraction of the available capacity of either network infrastructure.
Each of these networks requires its own adapters, fabrics, cables, tools, switches, management, and skills. If all of these components are combined, or converged, the potential for reducing cables, adapters, switches, and the skills that are required is clear. Replacing multiple networks with one in sometimes is an available option.
At a minimum, a converged network requires an adapter at the server that can carry the storage and IP networking workload. The access layer of the network (network switches or routers) must support multi-protocol traffic that is a combination of FC-based and IP-based data transport.
In contrast to the traditional server model, Figure 9-2 shows how the Converged Network Adapter (CNA) in a server, which is connected to the Enhanced Ethernet, has the potential to reduce the components that are required.
Figure 9-2 Serve with CNA installed
By using an FC driver, the CNA functionally represents a traditional FC HBA to the server’s operating system. By using NIC or clustering drivers, the CNA functionally represents a traditional networking or clustering device to the server’s operating system. The FC traffic is encapsulated into FCoE frames and these FCoE frames are converged with networking or clustering traffic.
The fabric contains FCoE-capable switches that can pass FC traffic to the attached SANs and Ethernet traffic to the attached Ethernet network. These switches must be able to support Enhanced Ethernet.
9.2.2 IP storage networking technologies
In contrast with the converged network, where the access layer transports the storage and IP-based workloads on a single medium (single cable and adapter), IP storage networking uses the IP-based networks only for storage workloads. The LAN or WAN cable that connects to the server’s NIC transports only storage data and does not serve IP-based traffic.
With the continuous development of the IP-based networking technologies and increasing nominal capacities (10 Gbps and 40 Gbps), the potential for implementation of the IP storage networking solutions is growing. However, Internet Small Computer System Interface (iSCSI), Fibre Channel over IP (FCIP), and iFCP are SAN extension technologies that are ideal for connecting smaller departmental and less I/O-intensive systems into a SAN.
SAN deployment and its resulting benefits are primarily focused on mission-critical islands of application servers within individual data centers. The difficulty and cost that are associated with migrating the large number of data center midrange servers to FC made it impractical for IT managers to extend the benefits of SAN to midrange applications.
A basic diagram of these technologies is shown in Figure 9-3.
Figure 9-3 IP Storage Technology
Internet Small Computer System Interface
iSCSI allows storage to be accessed over a Internet Protocol network as though it was locally attached. The server pushes out the SCSI commands through the Ethernet NIC. As the SCSI commands exit out through the server, they are encapsulated within an IP packet and forwarded across the LAN to a LAN/SAN gateway interface. These iSCSI packets are then translated onto the FC SAN through the TCP/IP transport and conversion protocol.
The iSCSI is an ideal point-to-multipoint solution for connecting dispersed SAN islands. By using the iSCSI, midrange servers can gain access to consolidated storage while they retain their existing IP infrastructure. This configuration allows a cost-effective extension of SAN benefits to midrange applications on servers within the data center and on departmental servers throughout the enterprise.
The iSCSI uses TCP/IP for reliable data transmission over potentially unreliable networks. The iSCSI layer interfaces to the operating system’s standard SCSI set. It includes encapsulated SCSI commands, and data and status reporting capability. When, for example, the operating system or application requires a data write operation, the SCSI Command Descriptor Block (CDB) must be encapsulated for transport over a serial gigabit link and delivered to the target.
Fibre Channel over IP
FCIP uses a tunneling protocol to transport FC frames over an existing IP infrastructure. It is therefore better suited for point-to-point solutions (Figure 9-4). By using FCIP, clients can use their current WAN infrastructure for connecting remote SAN islands over long distances.
Figure 9-4 FCIP with IP Tunneling example
FCIP is an ideal combination of technologies to address the dual requirements of storage networking and networking over distance. FC is a mature technology that is optimized for storage data movement within the campus and data center.
FC represents a major investment in software compatibility, interoperability, and applications for campus-based storage networking. Likewise, IP is a mature technology that is optimized for data movement across WAN distances. It represents a major investment in software compatibility, equipment interoperability, and applications for WAN-based data networking.
FCIP solutions encapsulate FC and transport it over a TCP socket. As in all IP networks, performance can vary based on these factors:
•The types of switches and routers
•The number of hops that the packets must traverse
•The level of congestion in the network
Internet Fibre Channel Protocol
iFCP is TCP/IP-based method for interconnecting FC SANs, SAN devices, and IP networks. iFCP technology provides multipoint access to FC devices. iFCP capitalizes on Internet Protocol network services while using the performance and interoperability capabilities of the FC network. With iFCP, existing SCSI and FC networks can be interconnected into the existing Internet Protocol environment. iFCP can be used with FC switching and routing protocols, or it can completely replace them.
iFCP is designed for clients that might have a wide range of FC devices (that is, HBAs, subsystems, hubs, switches, and so on) and want the flexibility to interconnect these devices with an IP network. iFCP can interconnect FC SANs with IP and allow clients the freedom to use Internet Protocol (IP) networks in place of FC networks for the SAN itself. Through the implementation of iFCP as a gateway-to-gateway protocol, these clients can maintain the benefit of their FC devices while using a highly scalable, manageable, and flexible enterprise IP network as the transport medium.
iFCP enables FC device-to-device communication over an IP network, providing more flexibility compared to enabling only SAN-to-SAN communication.
A drawback of the FCIP protocol, which makes iFCP more attractive, is that FCIP is a protocol that uses tunneling to encapsulate FC data packets for forwarding over the IP network. Therefore, FCIP works only within an FC infrastructure. However, iFCP can handle both iSCSI and FCIP traffic. Applications that are developed for FC SAN environments are supported over iFCP.
The benefits of iFCP for storage networks are that scalability, distance, and connectivity issues are virtually eliminated. The existing Ethernet protocol structure allows the rapid deployment of applications and solutions that already use the TCP/IP protocol layers. With one less routing protocol to support, network complexity and management are also potentially reduced. More importantly, the lower cost of InfiniBand network switches as opposed to FC switches enables a lower total cost of ownership (TCO) of the enterprise SAN.
Fibre Channel over Ethernet
FCoE is an enhancement that expands FC into the Ethernet by combining two leading-edge technologies (FC and the Ethernet). It is the transport, or mapping, of encapsulated FC frames over the Ethernet. The Ethernet provides the physical interface and FC provides the transport protocol, the combination of which provides an FC frame that is delivered in an Ethernet frame.
Mixing FCoE and existing FC and Ethernet networks is easy and expected. The most probable implementation is “from the edge.” This process involves adding FCoE with new equipment while keeping existing Ethernet and FC hardware and cabling in place until it makes sense to replace it with FCoE.
FCoE has these highlights:
•FCoE uses CNA.
•CNAs transfer either Ethernet NIC traffic, FC traffic, or both.
•Enhanced Ethernet protocol supports FC traffic.
•Enhancements add lossless data transmission and more management functions.
•FCoE is also called FCoCEE.
•CNAs use 10 Gb physical Ethernet ports.
Each port can run all NIC, all FC, or mixed NIC and FC traffic.
For more information about FCoE and iSCSI, see Storage and Network Convergence Using FCoE and iSCSI, SG24-7986.
9.2.3 SAN topologies
FC-based networks support three types of topologies:
•Point-to-point (FC-P2P)
Point-to-point is the simplest topology for an FC SAN. It allows the host and storage to connect directly.
•Loop (arbitrated) (FC-AL)
Arbitrated loop, which is also known as FC-AL, is an FC topology in which devices are connected in a one-way loop fashion in a ring topology.
•Switched (FC-SW)
Switched fabric is a computer network topology where many storage devices connect to each other through switches.
These topologies can be implemented separately or interconnected to form a fabric. The fabric can also be extended to cover even greater distances.
More definitions of SAN topologies exist, but they are always variations or combinations of these three basic concepts, such as these topologies:
•Single switch topology
•Cascaded and ring topology
•Mesh topology
•Core-Edge topology
•Edge-Core-Edge topology
Point-to-point topology
The point-to-point topology is the easiest FC configuration to implement, and it is also the easiest to administer. This simple link can be used to provide a high-speed interconnection between two nodes, as shown in Figure 9-5. A node is any device with one or more FC ports. Because connectivity is limited to two nodes, the exploitation of point-to-point in tape environments is limited. However, the distance between nodes can be up to 10 km (6.2 miles), which enables a tape library to be at another site.
When greater connectivity and performance are required, each device can be connected to a fabric without incurring any additional expense beyond the cost of the fabric.
Figure 9-5 shows a point-to-point topology.
Figure 9-5 Point-to-point topology
Switched topology
FC switches provide increased bandwidth, scalable performance, an increased number of devices, and, in certain cases, increased redundancy. FC switches vary in the number of ports and media types that they support.
Multiple switches can be connected to form a switched fabric that can support many host servers and storage subsystems, as shown in Figure 9-6 on page 240. When switches are connected, all configurations are merged into one fabric configuration that is shared throughout the SAN.
The switches can be interconnected in a number of topology configurations to provide better performance, more available ports, and improved redundancy.
Traffic can be routed in many ways. For technical, security, or other reasons, various levels of zoning or other mechanisms can be used to restrict the any-to-any access. Performance monitoring and configuration changes or upgrades that are needed to keep the network performing adequately are more complex.
Figure 9-6 shows a switched topology.
Figure 9-6 Example of a switched fabric
Loop (arbitrated) topology
|
Note: Loop technology is now rare in production environments. It is included briefly here because some existing tape technology still in production today uses it.
|
FC-AL offers relatively high bandwidth and connectivity at a low cost. For a node to transfer data, it must first arbitrate to win control of the loop. When the node has control, it is now free to establish a virtual point-to-point connection with another node on the loop. After this point-to-point (virtual) connection is established, the two nodes use all of the loop’s bandwidth until the data transfer operation is complete. After the transfer is complete, any node on the loop can now arbitrate to win control of the loop.
Figure 9-7 shows a loop (arbitrated) topology.
Figure 9-7 Arbitrated loop topology
9.2.4 Physical components of SAN infrastructure
SAN infrastructure is composed of a number of physical components. HBAs, cables, transceivers, switching, routing, and storage subsystem host ports all combine to create the end to end communication path.
Cables and connectors
FC connectors are available mainly in two types as LC and LC connectors. LC connectors are now the standard. See Figure 9-8.
Figure 9-8 Standard LC connector
Transceivers
Transceivers are plugged on switches or directors on each port and used to convert the internal communication transport to gigabit transport. 2 Gbps, 4 Gbps, 8 Gbps, 10 Gbps, 16 Gbps, and 20 Gbps transceivers are called Small Form-Factor Pluggable (SFP) media. Figure 9-9 shows an SFP.
Figure 9-9 Fiber Optic SFP
Host bus adapters
The HBA connects to the bus of the host or storage system. It can connect to the cable that leads to the SAN. The function of the HBA is to convert the parallel electrical signals from the bus into a signal that can be transported to the storage or host.
HBAs are available for Fibre Channel, iSCSI, and FCoE, among others. Figure 9-10 shows FC, iSCSI, and FCoE HBAs.
HBAs with two or four FC ports are typically available.
Figure 9-10 Available HBAs
SAN switches, routers, and directors
SAN switches help servers, tape drives, libraries, and SAN storage to connect in a switched fabric. It provides connectivity and easy access to the data that is stored on your SAN storage devices, SAN switches provide high-speed reliable access.
Figure 9-11 shows a SAN384B-2 director class switch.
Figure 9-11 IBM Storage Networking SAN384B-2
Fibre Channel connection
FICON is a high-speed I/O interface for mainframe computer connections to storage devices. A FICON channel is a high-bandwidth connection between the processor and a storage device.
FICON channels increase I/O capacity through a combination of architecture and faster physical link rates. This combination makes them more efficient than IBM Enterprise Systems Connection (ESCON), the previous IBM fiber optic channel standard.
FICON is based on FC and runs on an FC infrastructure, but it requires separate FICON support from FC switches.
For more information about FICON, see the FICON Native Implementation and Reference Guide, SG24-6266.
9.2.5 Network-attached storage
NAS is a device on a network that can be shared with non-storage traffic. Currently, the network is usually an Ethernet LAN, but it can be any network that supports the IP-based protocols that NAS uses.
Figure 9-12 on page 244 shows a diagram of an NAS appliance. In contrast to the “block I/O” that is used by SANs, NAS I/O requests are called “file I/Os”. File I/O is a higher-level type of request that specifies the file to be accessed, an offset into the file (as though the file was a set of contiguous bytes), and a number of bytes to read or write beginning at that offset. File I/O requests are mainly Common Internet File System (CIFS), Network File System (NFS), or specialized I/O protocols for file access and file sharing. Unlike block I/O, no awareness exists of a disk volume or disk sectors in a file I/O request. Inside the NAS product, an operating system tracks where files are on disk and issues a block I/O request to the disks to fulfill file I/O read and write requests.
Figure 9-12 NAS network diagram
In contrast to SAN devices that can usually also be direct-attached (for example, by point-to-point FC) and network-attached by SAN hubs and switches, an NAS device is generally only an NAS device and attaches only to processors over a local area network (LAN) or wide area network (WAN).
NAS benefits
NAS products provide a wide range of network attachment capabilities to a broad range of host and client systems.
An NAS device offers the following benefits:
•Ease of installation
NAS is generally easier to install and manage than a SAN. An NAS appliance can usually be installed on an existing LAN/WAN network. NAS manufacturers often cite “up and running” times of 30 minutes or less. NAS can be accessed by any operating system.
Hosts can potentially start to access NAS storage quickly, without needing disk volume definitions or special device drivers. In contrast, SANs take more planning, including the design of an FC network and the selection and installation of SAN management software.
•Resource pooling
NAS allows capacity within the appliance to be pooled. That is, the NAS device is configured as one or more file systems, each on a specified set of disk volumes. All users that access the same file system are assigned space within it on demand. That approach is more efficient than buying each user their own disk volumes or DAS, which often results in certain users having too much capacity and others too little. Therefore, NAS pooling can minimize the need to manually reassign capacity among users.
However, NAS pooling resides within an NAS appliance, and little if any sharing of resources occurs across multiple appliances. It raises costs and management complexity as the number of NAS nodes increases. In contrast, an advantage of a SAN is that all devices (multiple disk and tape systems) on a SAN can be pooled. As total capacity grows, a SAN can become easier to manage and more cost-effective.
•File sharing
NAS provides file sharing by using the NFS and CIFS protocols.
NAS gateways
An NAS gateway provides the function of a conventional NAS appliance, but without integrated disk storage. The disk storage is attached externally to the gateway, possibly sold separately, and can also be a stand-alone offering for direct or SAN attachment. The gateway accepts a file I/O request (for example, by using the NFS or CIFS protocols). It then translates that request to a SCSI block I/O request to access the external attached disk storage. In the simplest terms, an NAS gateway is an NAS system in which the storage is externally attached rather than captively attached.
The gateway approach to file sharing offers the benefits of a conventional NAS appliance, with more potential advantages:
•Increased disk capacity scalability (compared to the capacity limits of an integrated NAS appliance).
•Ability to offer file sharing and block I/O on the same disk system. Disk capacity in the SAN can be shared (reassigned) among gateway and non-gateway use. Therefore, a gateway can be viewed as an NAS/SAN hybrid that increases flexibility, and potentially lowers costs.
9.3 Storage area networking products
SAN switches interconnect multiple host servers with storage servers and devices to create a SAN. The SAN switches can be used either as stand-alone devices to build a simple SAN fabric, or they can be interconnected with other switches to build a larger SAN fabric.
With the continuously increasing bandwidth of data centers’ Ethernet, clients want unified storage and IP-based networking. IBM offers the solution for converged networking where both types of traffic use the same network infrastructure.
This section describes the IBM SAN product portfolio, which includes FC switches and directors with FC and FICON ports. It describes the following entry, midrange, and enterprise-level switch products:
•IBM SAN b-type switches and directors
•Cisco switches and directors
For the latest SAN products and information, see this website:
IBM SAN switch offerings can be positioned into four broad product groups:
•Entry SAN switches
•Midrange SAN switches
•Enterprise SAN switches
•SAN specialty switches
9.3.1 Common characteristics
All IBM SAN products offer the following capabilities:
•Industry standard performance with 2, 4, 8, 10, and, in many cases, 16 Gigabits per second (Gbps) throughput
•Intelligent Fabric Services Architecture that provides switch interoperability
•Enterprise-level scalability with fault-tolerant core-to-edge SAN fabrics that contain thousands of devices
•Open fabric management that allows support for the widest range of solutions, from small workgroup SANs up to large enterprise SAN fabrics with thousands of devices
•Flexible management options, including Tivoli Ready certification for the centralized management of large enterprise SAN fabrics
•Manageable by IBM Tivoli Storage Productivity Center for Fabric
•Common enterprise SAN fabric that simplifies deployment, management, and network growth
•Flexible FC connectivity provides connectivity to a host of IBM and other vendors’ servers and storage products
•Pay-as-you-grow scalability provides scalable network growth in a modular, cost-effective, and non-disruptive manner
9.3.2 Features specific to the IBM b-type SAN switches and directors
The following features are specific to the IBM b-type SAN switches and directors:
•Common firmware
The common firmware enables the introduction of new switch technologies while protecting earlier switch investments, in addition to mixing and matching the SAN components, as required.
•IBM Network Advisor
IBM Network Advisor is an intuitive graphical user interface (GUI) that allows network managers to monitor and manage SAN fabrics that consist of switches with a Java capable web browser from standard desktop workstations.
•Advanced Security
Advanced Security significantly reduces the security holes that are left by traditional SAN implementations. It also greatly improves the ability to minimize SAN-specific vulnerabilities by providing a comprehensive, policy-based security system for IBM SAN switch fabrics.
•Advanced Zoning
Advanced Zoning provides data exchange between devices in the same zone and prohibits exchange to any device that is not in the same zone. The zoning is enforced in application-specific integrated circuit (ASIC) hardware, preventing unauthorized devices from accessing the fabric.
•Extended Fabric
The Extended Fabric feature provides extensions within the internal switch buffers. This feature maintains performance for distances greater than 10 km (6.2 miles).
•Fabric Manager
Fabric Manager provides a Java based application that can simplify the management of a multiple switch fabric. It administers, configures, and maintains fabric switches and SANs with host-based software.
•Inter-switch link (ISL) Trunking
The ISL Trunking feature allows ISLs between the same pair of switches to be grouped and to act as a single, high-speed “pipe” or trunk. Up to eight ISLs can be combined into a single logical ISL with a total bandwidth of 128 Gbps that can support any number of devices. ISL Trunking is designed to significantly reduce traffic congestion in storage networks.
•Virtual Fabrics
The IBM b-type switches support the American National Standards Institute implementation of Virtual Fabrics (VFs). VFs add the capability for physical switches to be partitioned into independently managed logical switches, each with its own data, control, and management paths.
9.3.3 Fabric Vision
Fabric Vision with IBM SAN b-type Gen 5 Fibre Channel technology offers enhanced capabilities for managing your storage network that include simplified monitoring, increased availability, and reduced costs.
Fabric Vision simplifies and improves network monitoring with comprehensive visibility into network health and performance:
•A customizable health and performance dashboard simplifies management with critical information provided together on one window.
•Predefined policies, rules, and actions simplify the deployment of monitoring, but allow customization to match the aggressiveness of alerts and actions that you want.
•The solution’s ClearLink diagnostics capability enables visibility to proactively discover issues with links, such as cabling or optics, to avoid problems that are caused by signal degradation.
•The ability to increase instrumentation and granularity helps identify latency, congestion, cyclic redundancy check (CRC) errors, timeouts, and other issues in the fabric. These help storage administrators visualize the network’s health and performance.
For more information about the IBM b-type SAN switches and directors, see IBM b-type Gen 5 16 Gbps Switches and Network Advisor, SG24-8186.
9.3.4 Features specific to the Cisco SAN switches and directors
The following features are specific to the Cisco SAN switches and directors:
•Common firmware
The common firmware enables the introduction of new switch technologies while protecting earlier switch investments, in addition to mixing and matching the SAN components, as required.
•Multiprotocol intelligence
The Cisco SAN switches and directors transparently support FC, IBM FICON, and TCP/IP-based storage protocols.
•Virtual SAN (VSAN)
The integrated hardware-based VSAN technology enables the physical switch infrastructure to be divided into several separate logical SAN fabrics, each with their own fabric services. This feature enhances the reliability of the SAN fabrics and helps in implementing interoperability between different SAN products.
•Inter-VSAN routing
The integrated hardware-based inter-VSAN routing enables the routing of traffic at a line rate between VSANs, without requiring external hardware.
•Fabric-wide quality of service (QoS)
Fabric-wide QoS helps manage bandwidth and control latency to prioritize critical traffic and enables migration from a SAN island to enterprise-wide storage networks.
•Virtual machine-aware SAN deployment
Provides end-to-end visibility all the way from the VM down to storage, with resource allocation, performance measurements, and predictions that are available on a per-VM basis to enable rapid troubleshooting in mission-critical virtualized environments.
•Advanced traffic management
Advanced traffic management capabilities are designed to simplify deployment and optimization of large-scale fabrics:
– Virtual output queuing: Helps ensure line-rate performance on each port, independent of traffic patterns, by eliminating head-of-line blocking.
– Up to 4,095 buffer-to-buffer credits: Can be assigned to an individual port for optimal bandwidth usage across distances.
– Fibre Channel shortest path first (FSPF)-based multipathing: Provides the intelligence to load balance across up to 16 equal cost paths and, during a switch failure, dynamically reroute traffic.
•Port Channels
The Port Channels feature allows the aggregation of up to 16 physical ISLs into a single logical bundle, providing optimized bandwidth usage across all links. The bundle can consist of any speed-matched ports from any module in the chassis, helping to ensure that the bundle can remain active even in a module failure.
•Cisco Data Center Network Manager (DCNM)
Cisco DCNM (formerly Cisco Fabric Manager) is an easy-to-use application that simplifies management across multiple switches and converged fabrics.
For more information about the Cisco SAN switches and directors, see IBM and Cisco: Together for a World Class Data Center, SG24-8105.
9.3.5 Entry-level SAN switches
The IBM SAN switch entry-level products are designed specifically to address the needs of small to medium-size SAN environments. They can be used to create a wide range of high-performance SAN solutions, from simple single-switch configurations to larger multi-switch configurations that support fabric connectivity and advanced business continuity capabilities.
Infrastructure simplification solutions for IBM Power Systems include storage consolidation and high-availability server clustering with IBM disk storage arrays. Business continuity solutions include data protection with IBM tape libraries and devices and IBM Tivoli Storage Manager data protection software. IBM entry fabric switches provide up to twenty-four 16 Gbps ports for fully non-blocking performance, and advanced intelligence features.
This section introduces the ideal IBM SAN switch solutions for entry-level applications.
The following entry-level products are included:
IBM System Storage SAN24B-4 Express
The SAN24B-4 Express (model 2498-24E) is a high-performance scalable switch that provides a 24-port fabric with a Ports on Demand feature, so you can scale your network as you grow. You can get the switch with an 8-port license and then can upgrade it conveniently up to 24 ports by enabling the license. With auto-sensing link speeds at 1, 2, 4, and 8 Gbps and a flexible design that allows you to configure this switch as a fabric switch or an Access Gateway, it is suitable for small to midsize businesses.
A single SAN24B-4 Express switch can serve as the cornerstone of a SAN when you want to obtain the benefits of storage consolidation and implement FC storage systems. An entry-level 8-port storage consolidation solution can support up to seven servers with a single path to either disk or tape. The Ports on Demand (POD) feature is designed to enable a base switch to grow to 16 - 24 ports to support more servers and more storage devices without taking the switch offline. Figure 9-13 shows the SAN24B-4 Express fabric switch.
Figure 9-13 IBM System Storage SAN24B-4 Express
The SAN24B-4 fabric switch requires Fabric OS V6.1.0 or later. The switch offers easy to use Web Tools, 8-Gb FC, Long-Distance Support, Advanced Zoning, Full-fabric Support, Fiber Watch, Advanced Performance Monitoring, Fabric Vision Technology, Enhanced Group Management, and ISL Trunking. The base switch also offers eight default ports. The POD licenses are available in 8-port increments. With flexible architecture that is based on GoldenEye2 ASIC, the switch supports F, FL, E, and M ports at 8 Gbps. The switch also has USB port support for firmware download, configuration upload and download, and supportsave. The SAN24B-4 has a 1U form factor and is a single field-replaceable unit (FRU) with no field-replaceable parts. The switch has one power supply and three integrated fans.
|
Support: The Access Gateway mode is supported only in 24-port configurations, and only 2 GB Brocade branded USB drives are supported on the USB port. The 4 Gbps and 8 Gbps link speeds are supported only with Brocade-branded SFPs.
|
For more information, see this website:
IBM System Networking SAN24B-5
The IBM System Networking SAN24B-5 switch is designed to provide outstanding price and performance value, combining flexibility, simplicity, 16 Gbps FC technology, and enterprise-class functions in an entry-level switch. The SAN24B-5 is configurable in 12 or 24 ports and supports 2, 4, 8 or 16 Gbps speeds in an efficiently designed 1U form factor. The base unit includes one (2498-24G/2498-X24) or two (2498-F24) integrated power supplies and fans. A second power supply provides more redundancy for increased resiliency.
The IBM System Networking SAN24B-5 switch is shown in Figure 9-14.
Figure 9-14 The IBM System Networking SAN24B-5 switch
The SAN24B-5 fabric switch requires Fabric OS V7.0.1 or later. The switch offers easy to use Web Tools, 16-Gb FC, Long-Distance Support, Advanced Zoning, Full-fabric Support, Fiber Watch, Advanced Performance Monitoring, Fabric Vision Technology, Enhanced Group Management, and ISL Trunking. The base switch also offers 12 default ports. The POD license is available for the remaining 12 ports. With flexible architecture that is based on Condor3 ASIC, the switch supports F, E, EX, D, and M ports at 16 Gbps. The FL port is not available. The switch also has USB port support for firmware download, configuration upload and download, and supportsave. The SAN24B-5 has a 1U form factor and is a single FRU with one hot-swappable power supply as a replaceable part. The secondary redundant power supply and fan assembly is an optional feature.
For more information, see IBM System Networking SAN24B-5 Switch, TIPS1128.
Also, see the product website:
9.3.6 Midrange SAN switches
The IBM midrange SAN solutions provide more capability, features, and benefits beyond the simple entry solutions. They provide 1, 2, 4, 8, and 16 Gbps port-to-port non-blocking throughput with auto-sensing capability for connecting to older 1 Gbps host servers, storage, and switches. They are available in 48 - 96 ports with the POD scalability models.
The IBM SAN switches can be used to create dedicated, reliable, and high-performance networks for storage products, such as disk subsystems, tape drives, and tape drive libraries. In addition, all of these models are fully interoperable with the previous IBM SAN switches. They can be added to existing fabrics, enabling transition from existing FC storage networks to the faster technology.
The IBM SAN switch solutions are ideal for midrange applications. The following midrange SAN switches are included:
•Cisco MDS 9396S 16G Multilayer Fabric Switch for IBM System Storage
IBM System Storage SAN48B-5
The IBM System Storage SAN48B-5 SAN switch (model 2498-F48) is designed to meet the demands of hyper-scale, private cloud storage environments by delivering 16 Gbps FC technology and capabilities that support highly virtualized environments. To enable greater flexibility and investment protection, the SAN48B-5 is configurable in 24, 36, or 48 ports and supports 2, 4, 8, 10, or 16 Gbps speeds in an efficiently designed 1U package. The switch is shown in Figure 9-15.
Figure 9-15 Front view of IBM System Storage SAN48B-5 switch
The SAN48B-5 fabric switch requires Fabric OS V7.0.1 or later. The base model of the switch has 24 ports that are enabled, and the POD licenses are available in 12-port increments. The switch can simplify server virtualization and virtual desktop infrastructure (VDI) management. The switch meets the high-throughput demand of enterprise data center switch capabilities, such as native 10 Gbps support for dense wavelength division multiplexing (DWDM) or in-flight data compression and encryption.
The SAN48B-5 can be deployed as a full-fabric switch or as an Access Gateway, which simplifies fabric topologies and heterogeneous fabric connectivity. The default mode setting is a switch. Access Gateway mode uses N_Port ID Virtualization (NPIV) switch standards to present physical and virtual servers directly to the core of SAN fabrics. This configuration makes it transparent to the SAN fabric, which greatly reduces the management of the network edge. The SAN48B-5 in Access Gateway mode can connect servers to NPIV-enabled b-type and m-type SAN directors, switches, and routers.
For more information, see IBM System Storage SAN48B-5, TIPS1125.
Also, see the product website:
IBM System Networking SAN96B-5
The IBM System Networking SAN96B-5 SAN switch (models 2498-F96 and 2498-N96) is designed to meet the demands of hyper-scale, private cloud storage environments by delivering 16 Gbps FC technology and capabilities that support highly virtualized environments. To enable greater flexibility and investment protection, the SAN96B-5 is configurable in 48, 72, or 96 ports, and supports 2, 4, 8, 10, or 16 Gbps speeds in an efficiently designed 2U package.
The IBM System Networking SAN96B-5 is shown in Figure 9-16.
Figure 9-16 IBM System Networking SAN96B-5
High availability features make the IBM System Networking SAN96B-5 suitable for use as a core switch in midrange environments or as an edge-switch in enterprise environments where a wide range of SAN infrastructure simplification and business continuity configurations are possible. IBM Power Systems, z Systems, and many other vendor servers, disk, and tape devices are supported in many common operating system (OS) environments.
Optional features provide specialized distance extension, dynamic routing between separate or heterogeneous fabrics, link trunking, FICON, performance monitoring, and advanced security capabilities.
A single physical chassis can be subdivided into two or more logical switches that create a logical fabric with other switches. Integrated Routing is a licensed feature that is supported on every port of the switch and requires the POD license for all 96 ports.
The ports on the switch are grouped in 8-port groups that match the trunk group, and with ISL Trunking, speeds of up to 128 Gbps can be achieved per trunk. Dynamic Path Selection can be used for optimizing the performance and load balancing, and the switch can be managed by using Web Tools.
The IBM System Networking SAN96B-5 switch is available in two models to accommodate different rack airflow requirements:
•2498-F96 with airflow from non-port side to port side
•2498-N96 with airflow from port side to non-port side
For more information, see IBM System Networking SAN96B-5, TIPS1103.
Also, see the product website:
Cisco MDS 9148S 16G Multilayer Fabric Switch for IBM System Storage
The Cisco MDS 9148S 16G Multilayer Fabric Switch for IBM System Storage is the latest generation of the highly reliable, flexible, and low-cost Cisco MDS 9100 Series switches. It combines high performance with exceptional flexibility and cost effectiveness. This powerful, compact one rack-unit (1RU) switch scales from 12 to 48 line-rate 16 Gbps FC ports.
The Cisco MDS 9148S is excellent for the following purposes:
•A stand-alone SAN in small departmental storage environments
•A top-of-the-rack switch in medium-sized redundant fabrics
•An edge switch in enterprise data center core-edge topologies
Figure 9-17 shows the Cisco MDS 9148S switch.
Figure 9-17 Cisco MDS 9148S switch
For more information, see Cisco MDS 9148S 16G Multilayer Fabric Switch for IBM System Storage, TIPS1255.
Also, see the product website:
Cisco MDS 9396S 16G Multilayer Fabric Switch for IBM System Storage
MDS 9396S provides up to 96 autosensing Fibre Channel ports, capable of speeds of 2, 4, 8 and 16 Gbps, which results in 16 Gbps of dedicated bandwidth for each port. The switch comes with 48 enabled ports, and it can be scaled up by adding one or more 12-port MDS 9396S On-Demand Port Activation licenses.
MDS 9396S scales from 48 to 96 high-performance Fibre Channel ports in a 2RU form factor. It offers more buffer-to-buffer credits than previous-generation fabric switches. In addition, it supports 32 virtual SANs (VSANs), making it an excellent choice for stand-alone small and mid sized business Fibre Channel networks
Figure 9-18 shows the Cisco MDS 9396S 16G Multilayer Fabric Switch for IBM System Storage
Figure 9-18 Cisco MDS 9396S 16G Multilayer Fabric Switch for IBM System Storage
For more information, see the product website:
9.3.7 Enterprise SAN switches
The IBM enterprise SAN switches and directors address enterprise SAN client requirements for infrastructure simplification and improved business continuity.
The SAN directors are designed to operate with other members of the IBM System Networking Switch family. You can configure a wide range of highly scalable solutions that address demands for integrated, heterogeneous mainframe and open server enterprise SANs.
The following enterprise products are included:
•Cisco MDS 9706 Multilayer Director for IBM System Storage
This section introduces IBM System Networking Switch solutions ideal for enterprise environments. Advanced security with comprehensive, policy-based security capabilities can improve availability and simplify operation.
IBM System Storage SAN384B-2 and SAN768B-2
The IBM System Storage SAN384B-2 (model 2499-416) and IBM System Storage SAN768B-2 are fabric backbone switches. They are the premier platform for the consolidation of your data center connectivity, providing high-performance and highly available data networking with industry-leading 16 Gbps FC technology. They are also among the members of the IBM b-type SAN family that are designed to use the new IBM and Brocade data center fabric architecture.
The SAN384B-2 and SAN768B-2 interoperate with other members of the IBM b-type SAN family, in addition to other fabrics:
•They can be configured with a wide range of connectivity options, including 16, 10, 8, 4, and 2 Gbps FC, up to 4 Gbps FICON, and FCIP over 1 gigabit per second Ethernet (GbE).
•They are designed to enable support for emerging high-performance and high-function network protocols, including FCoCEE.
•They are designed to serve as the basis for transforming existing networks into a unified, high-performance data center fabric, connecting applications with their data and virtual servers with virtual storage.
As members of the IBM family of b-type SAN products, the SAN384B-2 and SAN768B-2 are designed to participate in fabrics that contain other b-type SAN devices that are manufactured by Brocade. Their versatile hardware can serve as a new top tier (or backbone) in a complex fabric and provide connections to other b-type SAN directors, switches, and routers.
The IBM System Storage SAN384B-2 and SAN768B-2 are shown in Figure 9-19.
Figure 9-19 The IBM System Storage SAN384B-2 (left) and SAN768B-2 (right)
The IBM System Storage SAN384B-2 and SAN768B-2 offer the following hardware features:
•The SAN384B-2 chassis includes two control processor blades and two core module blades. It also has space for up to four port blades, dual power supplies, and two fan modules in an 8U rack height (plus 1U exhaust shelf).
•The SAN768B-2 chassis includes two control processor blades and two core module blades. It also has space for up to eight port blades and dual power supplies with an option for two more power supplies, and three fan modules in a 14U rack height.
•Up to ten SAN384B-2 or SAN768B-2 switches can be connected with high-speed UltraScale optical inter-chassis links.
•The following blades are available:
– 16 Gbps 32-port and 48-port FC blades, capable of speeds of 2, 4, 8, 10, and 16 Gbps
– 16 Gbps 64-port FC blade, with 16 Quad Small Form-factor Pluggable (QSFP) ports and Multiple-Fiber Push-On/Pull-off (MTP/MPO) connectivity
– 8 Gbps 64-port FC blade, with special mini optical transceiver (mSFP) optics included
– 8 Gbps Enhanced Extension blade that contains 22 ports that are capable of 8 and 4 Gbps FC connection or 1 Gbps copper Ethernet connection, and two 10 GbE ports
– 8 Gbps 16-port FC Encryption blade
– 10 Gbps 24-port FCoE blade (SAN768B-2 only)
•The following transceivers are available:
– 16 Gbps, 10 Gbps, and 8 Gbps shortwave SFPs
– 16 Gbps, 10 Gbps, and 8 Gbps 10 km (6.2 miles) longwave SFPs
– 16 Gbps and 8 Gbps 25 km (15.5 miles) extended distance longwave SFPs
•In addition, the following transceivers are available for the Enhanced Extension blade and the 24-port FCoE blade:
– 10 Gbps Ethernet SR and LR SFP+
•In addition, the following transceivers are available for the Enhanced Extension blade only:
– 4 Gbps shortwave and 10 km longwave SFP
– 1 Gbps copper SFP
•Full Fabric and Universal Port operation (E_Port, F_Port, and FL_Port)
For more information, see IBM System Storage SAN768B-2 and SAN384B-2 Fabric Backbones, TIPS1127.
Also, see the product website:
Cisco MDS 9500 Series Multilayer Directors
The Cisco MDS9500 Series Multilayer Directors include these models:
•Cisco MDS9506 - model 2054-E04 with up to 192 ports
•Cisco MDS9513 - model 2054-E11 with up to 528 ports
|
Note: As of 19 April 2014, Cisco MDS9509 - model 2054-E07 was withdrawn from marketing and replaced by the new Cisco MDS9710, which is model 9710-E08.
|
The Cisco MDS 9500 Series Multilayer Directors support 1, 2, 4, 8, and 10 Gbps FC switch connectivity and intelligent network services. These services help improve the security, performance, and manageability that are required to consolidate geographically dispersed storage devices into a large enterprise SAN.
Both models of Cisco MDS9500 Series Multilayer Directors use two Supervisor-2A Modules that are designed for high availability and performance. The Supervisor-2A Module combines an intelligent control module and a high-performance crossbar switch fabric in a single unit. It uses FSPF multipath routing, which provides intelligence to load balance across a maximum of 16 equal-cost paths and to dynamically reroute traffic if a switch fails.
Each Supervisor-2A Module provides the necessary crossbar bandwidth to deliver full system performance in the Cisco MDS 9500 directors with more Advanced Fibre Channel Switching modules or Fabric3 Switching modules. It is designed to eliminate the impact on system performance of the loss or removal of a single crossbar module.
The Cisco MDS9500 MDS 9500 Series Multilayer Directors support the deployment of FCoE by using 10 Gbps Ethernet-SR X2 transceivers.
The Cisco MDS9500 Series Multilayer Directors are shown in Figure 9-20.
Figure 9-20 Cisco MDS 9500 Series Multilayer Directors: MDS9513 (left) and MDS9506 (right)
For more information, see the product website:
Cisco MDS 9706 Multilayer Director for IBM System Storage
Cisco MDS 9706 Multilayer Director for IBM System Storage is a director-class SAN switch that is designed for deployment in small to mid sized storage networks that can support enterprise clouds and business transformation. It layers a comprehensive set of intelligent features onto a high-performance, protocol-independent switch fabric
Using Cisco MDS 9700 Family switching modules, MDS 9706 supports up to 192 ports in a 6-slot modular chassis, with up to 768 ports in a single rack. Ports can be configured in these ways:
•Fibre Channel (2/4/8 Gbps, 4/8/16 Gbps, or 10 Gbps)
•FCoE (10 Gbps)
•A mix of both Fibre Channel and FCoE
MDS 9706 supports the same Fibre Channel and FCoE switching modules as Cisco MDS 9710 Director for IBM System Networking for a high degree of system commonality.
In addition to meeting the basic requirements of non-disruptive software upgrades and redundancy of all critical hardware components, MDS 9706 software architecture offers outstanding availability. MDS 9706 provides redundancy on all major hardware components, including the supervisor and fabric modules and the power supplies. Cisco MDS 9700 Series Supervisor Module automatically restarts failed processes, making MDS 9706 exceptionally robust.
Figure 9-21 shows the Cisco MDS 9706 Multilayer Director for IBM System Storage.
Figure 9-21 Cisco MDS 9706 Multilayer Director for IBM System Storage
For more information about the Cisco MDS 9706 Multilayer Director for IBM System Storage, see the following website:
Cisco MDS 9710 Multilayer Director
The Cisco MDS 9710 Multilayer Director offers an enterprise-class solution for large virtualized data centers or cloud installations that require high-performance, scalable, and reliable low-latency SANs.
The Cisco MDS 9710 Multilayer Director supports 2, 4, 8, 10, and 16 Gbps FC switch connectivity and intelligent network services. These features help improve the security, performance, and manageability that are required to consolidate geographically dispersed storage devices into a large enterprise SAN. It also supports 10 Gbps FCoE connectivity in parallel with FC, offering a seamless transition to IP-based storage networking.
The Cisco MDS 9710 Multilayer Director uses two new hot-swappable, redundant Supervisor-1 Modules that are designed for high availability and performance. In addition, the director uses separate hot-swappable, redundant crossbar modules.
The Cisco MDS 9710 Multilayer Director is shown in Figure 9-22.
Figure 9-22 Cisco MDS 9710 Multilayer Director
For more information, see Cisco MDS 9710 Multilayer Director for IBM System Networking, TIPS1046, or the product website:
9.3.8 SAN specialty switches
The SAN switches offer special functions that relate to multi-protocol routing.
The following enterprise products are described:
IBM System Storage SAN06B-R Extension Switch
A wide range of IBM System Storage midrange and enterprise SAN infrastructure simplification and business continuity solutions can be created with the IBM System Networking SAN06B-R Extension Switch. Infrastructure simplification solutions for the IBM Power Systems and System x families include disaster tolerance over metropolitan and global IP networks with IBM disk arrays, tape libraries, and IBM Tivoli Storage Manager data protection software. Separate SAN islands can also be consolidated by using FC routing. Support for z Systems servers is provided by the optional High-Performance Extension and FICON Control Unit Port (CUP) Activation features.
Local site infrastructure simplification solutions can be extended to one or more remote sites for enhanced data protection and disaster tolerance. The IBM System Storage SAN06B-R Extension Switch provides FCIP and FCIP Tunneling Service for distance extension, which can enable cost-effective and manageable metropolitan and global business continuity solutions. This extended distance connectivity can help create consolidated remote tape vaulting data protection, plus Metro Mirror and Global Mirror disk-based, disaster-tolerant solutions.
Since the introduction of SANs, clients built multiple SAN networks (or islands) for various applications, often with fabric switch components from various manufacturers. Certain islands were built by various departments within a company, whereas other islands resulted from mergers, acquisitions, or reorganizations. These islands, which were often created to isolate important applications or to implement equipment with various capabilities, constrain opportunities for enhanced infrastructure simplification and vital business continuity solutions.
The IBM System Networking SAN06B-R Extension Switch (model 2498-R06) provides the FC-FC Routing Service. This service allows the interconnection of multiple SAN islands without requiring that the separate fabrics are merged into a single large SAN. This capability can help create a tiered or extended enterprise SAN infrastructure without needing to redesign or reconfigure the entire environment.
The IBM System Networking SAN06B-R Extension Switch is shown in Figure 9-23.
Figure 9-23 The IBM System Networking SAN06B-R Extension Switch
For more information, see IBM System Storage SAN06B-R Extension Switch, TIPS1126, or the product website:
IBM System Storage SAN42B-R Extension Switch
The IBM System Storage SAN42B-R switch is intended as a platform for FCIP. This configuration enables the transmission of FC data over long distances by way of IP networks by wrapping FC frames in IP packets. Each end of the FCIP communication path must be a compatible FCIP device. The switch can operate independently or in a fabric that contains multiple extension switches.
The SAN42B-R provides the following software features:
•Multiple logical FCIP tunnels with a maximum tunnel bandwidth up to 20 Gbps allow for scalable connectivity between sites.
•The FCIP Trunking feature allows multiple IP source and destination address pairs. These pairs are defined as FCIP circuits, through multiple 1/10 GbE or 40 GbE interfaces to provide a high-bandwidth FCIP tunnel and lossless failover resiliency. In addition, each FCIP circuit supports four QoS classes (Class-F, High, Medium, and Low Priority), each as a Transmission Control Protocol (TCP) connection.
•Hardware-based compression delivers the ability to maximize throughput over lower bandwidth links in the WAN, optimizing the cost efficiencies of FCIP. The SAN42B-R compresses FC frames before they are encapsulated into FCIP packets.
•Key protocol features are enabled in the FCIP implementation to optimize the performance of Extension over IP networks, including WAN Optimized TCP, 9 K jumbo frames, and end-to-end path maximum transmission unit (MTU) auto discovery.
•Hardware-based IPsec supports a mix of secure and non-secure tunnels on the same Ethernet port, jumbo frames, and VLAN-tagged connections. The IPsec function can support both IPv4 and IPv6.
•FastWrite, Open Systems Tape Pipelining, and Advanced Accelerator for FICON mitigate the latency effect of a long-distance FCIP distance connection over an IP WAN.
•Built-in WAN link tester generates traffic over an IP connection to test for maximum throughput, congestion, loss percentage, out of order deliver, latency, and other network conditions. It helps determine the health of a WAN link before you deploy it for use.
•Fabric Vision advanced monitoring provides the following functions:
– Policy-based monitoring monitors FCIP connectivity and WAN anomalies by using multi-layer metrics.
– Flow monitoring reports I/O operations per second (IOPS) and the data rate of individual I/O flows of inter-data center (DC) replication and tape backup operations.
– Flow generator generates FC frames for a defined flow with a default or custom size and pattern, and sends them across an FCIP tunnel to help validate end-to-end network setup and configuration.
•Fabric OS delivers distributed intelligence throughout the network and enables a wide range of applications.
The IBM System Storage SAN42B-R switch is available in three configurations, as shown in Table 9-1.
Table 9-1 IBM System Storage 42B-R configurations
|
Product configuration
|
FC ports
|
Ethernet ports
|
WAN rate limiting
|
Approximate application throughput
|
|
Base configuration
|
24 x 16 Gbps
|
16 x 1/10 Gbps
|
5 Gbps
|
15 Gbps
|
|
Medium configuration
(Base plus WAN Rate Upgrade 1)
|
24 x 16 Gbps
|
16 x 1/10 Gbps
|
10 Gbps
|
30 Gbps
|
|
Maximum configuration
(Base plus WAN Rate Upgrade 1 plus WAN Rate Upgrade 2)
|
24 x 16 Gbps
|
16 x 1/10 Gbps
2 x 40 Gbps
|
Unlimited
|
80 Gbps
|
|
Note: The approximate application throughput values in Table 9-1 assume that a degree of data compression is occurring. However, IBM makes no promises, guarantees, or any indication that a level of compression is possible for client-specific data. Certain data is highly compressible and other data cannot be compressed. The amount of application throughput varies depending on data compressibility and the selected compression mode.
|
The IBM System Storage SAN42B-R Extension Switch is shown in Figure 9-24.
Figure 9-24 IBM System Storage SAN42B-R Extension Switch
The IBM System Networking SAN06B-R Extension Switch offers the following highlights:
•Rack-mountable 2U chassis
•Base configuration includes a comprehensive set of advanced services, including Fabric Vision, Extension Trunking, Adaptive Rate Limiting, ISL Trunking, IPsec, Compression, and Extended Fabric
•Optional licenses are available for Integrated Routing, FICON CUP, and Advanced FICON Accelerator
•Built-in encryption and compression of storage data flows over long-distance links with no performance penalty
•Extension Trunking increases WAN use and protects against WAN link failures
For more information, see IBM System Storage SAN42B-R Extension Switch, TIPS1209, or the product website:
Cisco MDS 9250i Multiservice Fabric Switch for IBM System Storage
The Cisco MDS 9250i Multiservice Fabric Switch, the next generation of the Cisco MDS 9200 Series Multiservice Switches, is an optimized platform for deploying high-performance SAN extension solutions, distributed intelligent fabric services, and cost-effective multiprotocol connectivity for both open systems and mainframe environments.
With a compact form factor and advanced capabilities that are typically available only on director-class switches, the Cisco MDS 9250i Multiservice Fabric Switch is an ideal solution for departmental and remote branch-office SANs and in large-scale SANs with the Cisco MDS 9710 Multilayer Director.
The Cisco MDS 9250i Multiservice Fabric Switch offers up to 40 16-Gbps FC ports, two 1/10 Gigabit Ethernet IP storage services ports, and eight 10-Gigabit Ethernet FCoE ports in a fixed 2RU form factor.
The Cisco MDS 9250i Multiservice Fabric Switch is shown in Figure 9-25.
Figure 9-25 Cisco MDS 9250i Multiservice Fabric Switch
For more information, see Cisco MDS 9250i Multiservice Fabric Switch for IBM System Storage, TIPS1167, or the product website:
9.3.9 SAN solutions
IBM SAN solutions integrate IBM and other vendor server, storage, SAN switches, and software components into solution templates that are extensively tested to provide high availability, scalability, security, and simplicity of management. IBM SAN solutions are offered with worldwide IBM service and end-to-end solution support. These solutions templates might be customized by IBM Business Partners or IBM Global Services to address individual customer requirements.
For more information, see the following website:
9.4 Selecting the best alternative
Which storage networking alternative is the best for a specific organization might be obvious based on organizational objectives, current storage infrastructure, and what the alternatives provide. Or it might be an open question. Storage technology has clearly become more varied and sophisticated, and the decisions are more complex than ever. Choice means flexibility, and that is good, but which choice to make is not always clear:
•If a group of individual users with PCs needs to share disk storage capacity and also share files in that storage, an NAS might be easiest to install and manage.
•If application servers need to share disk storage and are each accessing independent (block I/O) databases, an FC-based SAN might be appropriate.
•For a few servers where no SAN exists, iSCSI might be less expensive and less complex.
•For many servers and greater distances, FCoE can be used over existing Ethernet infrastructures. However, it can add increased complexity.
•If required, FCIP or iFCP provides a cost-effective way to achieve business protection, enabling solutions, such as remote tape archiving.
9.5 More information
For more information about all of the SAN-related topics and the products that are described in this chapter, see the following publications:
•Introduction to Storage Area Networks, SG24-5470
•IBM b-type Gen 5 16 Gbps Switches and Network Advisor, SG24-8186
•IBM and Cisco: Together for a World Class Data Center, SG24-8105
•SAN Storage Performance Management Using Tivoli Storage Productivity Center, SG24-7364
•Implementing an IBM b-type SAN with 8 Gbps Directors and Switches, SG24-6116
•IBM/Cisco Multiprotocol Routing: An Introduction and Implementation, SG24-7543
•Implementing an IBM/Cisco SAN, SG24-7545
For more information, see the following website:
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.