Classifications

• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L12/00—Data switching networks
  • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
  • H04L12/46—Interconnection of networks
  • H04L12/4633—Interconnection of networks using encapsulation techniques, e.g. tunneling
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L67/00—Network arrangements or protocols for supporting network services or applications
  • H04L67/01—Protocols
  • H04L67/10—Protocols in which an application is distributed across nodes in the network
  • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F11/00—Error detection; Error correction; Monitoring
  • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
  • G06F11/16—Error detection or correction of the data by redundancy in hardware
  • G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
  • G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
  • H04L69/30—Definitions, standards or architectural aspects of layered protocol stacks
  • H04L69/32—Architecture of open systems interconnection [OSI] 7-layer type protocol stacks, e.g. the interfaces between the data link level and the physical level
  • H04L69/322—Intralayer communication protocols among peer entities or protocol data unit [PDU] definitions
  • H04L69/329—Intralayer communication protocols among peer entities or protocol data unit [PDU] definitions in the application layer [OSI layer 7]

Definitions

• This invention relates generally to data and information communications systems and their operation, and, more particularly, to the field of storage area networking Even more particularly, the present invention relates to Fibre Channel Storage Area Networks (SANs) and an encapsulation protocol for linking Storage Area Networks over a packet-based network
• SANs Fibre Channel Storage Area Networks
• encapsulation protocol for linking Storage Area Networks over a packet-based network
• storage routers In order for devices of a storage area network that use Fibre Channel to function with storage devices that use SCSI, storage routers must be installed between these devices.
• storage routers are essential to shifting data back-up processes from a primary computer network to the storage area network, since most data back-up storage devices use the SCSI interface and can only connect to the storage area network through a storage router.
• SCSI interface SCSI interface
• storage routers will be increasingly essential to enable rapid, seamless communication among servers, storage devices and storage area network devices that use diverse protocols.
• SANs are local Fibre Channel networks that serve one particular organization or one particular site. These SANs can be quite large, but cannot span great distances as they have distance limitations imposed upon them by the infrastructure necessary to carry Fibre Channel.
• Fibre Channel standard defines a means to communicate over spans up to 10 km and, in some cases, up to 30 km in length.
• the organization implementing the Fibre Channel network must typically own the fiber or lease dark fiber from some other party, which can be very expensive and, in most cases, is cost prohibitive.
• Fibre Channel traffic can only carry Fibre Channel protocol traffic. They cannot be shared with other protocols. It is therefore more cost effective to transmit data over long distances using a protocol that can be carried over already existing networks, such as those owned by phone companies that can carry ATM traffic, SONET traffic and IP traffic. Therefore, SANs are usually limited as to the geographic area that they can serve (i.e., they are limited to local operation). Furthermore, two or more geographically diverse SANs cannot interconnect in a seamless fashion such that they operate and behave as if they were local to one another because the infrastructure to connect them does not exist or is cost prohibitive.
• an encapsulation protocol with the ability to use existing telecommunications networks t connect multiple storage area networks over a packet-based network protocol such as IP, ATM, SONET, or other such currently existing telecommunications protocol.
• the present invention provides an encapsulation protocol method and system for linking of multiple SANs over a packet-based network that substantially eliminates or reduces the disadvantages and problems associated with use of a Fibre Channel protocol over large distances.
• the present invention provides a means for seamlessly interconnecting geographically distinct SANs such that they operate as if they were local to one another.
• the present invention provides a method and system for encapsulating SCSI protocol for data transmission between two or more nodes across a packet-based network.
• the method of the present invention includes the steps of, at each node in the network, identifying all other available nodes on the network, and the remote devices attached to those nodes; representing one or more of the attached remote devices such that they are made available to the node's local hosts; encapsulating the I/O phases between one or more local hosts and one or more of the remote devices; and repeating the encapsulating step for subsequent I/Os between one or more hosts and one or more devices.
• the step of encapsulating I/O phases between a local host and a remote device can further comprise encapsulating task management functions, error recovery functions and normal I/O processing functions.
• Each node can be a Fibre Channel-to-SCSI router.
• Fibre Channel Protocol such as would be necessary to support a corporate or global storage area network solution.
• the present invention provides an important technical advantage of an encapsulation protocol with the ability to use existing telecommunications networks to connect multiple storage area networks over a packet-based network protocol, such as IP, ATM, SONET, or other such currently existing telecommunications protocol.
• a packet-based network protocol such as IP, ATM, SONET, or other such currently existing telecommunications protocol.
• the present invention provides yet another important technical advantage of an encapsulation protocol that can link multiple storage area networks over a packet-based network in a seamless fashion, such that the multiple SANs operate as a single unified SAN.
• FIGURE 1 is a simplified block diagram illustrating one implementation of the method and system of this invention within a typical SAN environment.
• the present invention provides a method and system for encapsulating SCSI protocol for transmission between one or more nodes across a packet-based network that takes advantage of existing telecommunication networks to efficiently and cost-effectively connect multiple, and perhaps and geographically diverse SANs, such that they can operate as a single storage area network.
• the method and system of this invention can thus effectively overcome distance limitations of existing Fibre Channel networks so that the SAN model can be extended to many SANs, over many miles.
• the present invention could, for example, link a corporate SAN in Los Angeles to another corporate SAN in New York or Tokyo.
• this invention will allow a back-up library to reside off-site at a remote location, thus ensuring data integrity should the local location be damaged by disaster, like fire or flood.
• SANs implementing the present invention need not be limited to local use only.
• FIGURE 1 is a simplified block diagram illustrating one implementation of the method and system of this invention within a typical SAN environment.
• Network 100 of FIGURE 1 includes remote hosts 110, which can be local Fibre Channel SANs that access another local Fibre Channel SAN 115 for tape back-up and disk mirroring, for example.
• Fibre Channel hosts 110 and Fibre Channel host 115 are attached to nodes 120, 130 and 150, respectively, which can be Fibre Channel-to-SCSI routers, such as those manufactured and sold by Crossroads
• Nodes 120, 130 and 150 can be interfaces to the rest of the network 100 for SANs 110 and 115.
• the Fibre Channel-to-SCSI routers that comprise nodes 120, 130 and 150 all can implement the EP layer such that the Fibre Channel protocol flows seamlessly over the packet-based WAN (wide area network) 140.
• WAN 140 represents a physical packet-based transport such as ATM or Ethernet.
• WAN 140 can be a dedicated link or switched network.
• Hosts 110 and 115 are connected to their respective nodes via Fibre Channel links 190.
• Nodes 120, 130 and 150 are each connected to WAN 140 via network links 192.
• Fibre Channel links 190 can be copper or fiber-optic links, as required for a given application.
• Network links 192 can similarly be copper or fiber-optic, as needed.
• Remote host 110 and local host 115 can be comprised of multiple targets and multiple initiators.
• SAN 115 includes Fibre Channel hub (switch) 160, tape library 170 and disk 180. Although only tape library 170 and disk 180 are shown, multiple initiators and target devices can be attached to Fibre Channel hub 160 and through it to Fibre Channel-to-SCSI router 150. Fibre Channel SAN 115 can thus comprise multiple hosts and multiple initiators.
• Connecting two or more SANs together using an extender protocol requires mapping the local address of each SCSI device on one SAN to an intermediate address to get across the extender, and then mapping each intermediate address into a remote address on a remote SAN
• This mapping is required to allow initiators on one SAN to address SCSI devices on a remote SAN as if they were SCSI devices on the local SAN to which the initiator is attached
• devices on a remote SAN can be represented in such a way that they are made available to initiators on other SANs
• the method and system of this invention provide a means to define the communications across the extension protocol, I e , a means to map Fibre Channel data into an extension protocol such that it can be decoded back to a Fibre Channel protocol for communication with a target at a remote SAN
• the present invention thus defines a protocol that can be used to encapsulate Fibre Channel in a packet-based network This is accomplished by converting data to be transmitted from the protocol to be extended (Fibre Channel) to the extension protocol (the packet-based protocol for the particular application) and back to the extended protocol (Fibre Channel) at the remote SAN
• the encapsulation protocol of the present invention can be configured to convert specific commands for a given protocol and can be extended to include new commands as the Fibre Channel protocol expands to provide new functionality Any Fibre Channel commands or messages referenced in the present invention are illustrative but not exclusive
• the EP layer of the method and system of the present invention is composed of two parts Aspen Node Management (ANM) and Fibre Channel Protocol-Encapsulation Protocol (FCP-EP) These names have been arbitrarily chosen for desc ⁇ ptive purposes only ANM can be thought of as the control mechanism It defines a client server environment so that multiple SANs with multiple initiators and multiple targets can be managed concurrently as individual nodes on, for example, WAN 140 of FIGURE 1
• ANM is designated as a server node and all nodes (including the server node) are clients
• the following messages are used to define and manage the ANM control mechanism • Client Node Register Used by a client node to register with the server node This registers the client's EP address to allow the server to open future connections to the client (if necessary) • Client Node Target Register Used by a client node to register FC targets with the server node This registers all FC targets found on the local FC network • Target Table Update Sent by the server node to update a client's global target table
• FCP-EP can be thought of as a data mechanism It defines the disassembly and reassembly of
• the FCP-EP layer can itself be a packet-based protocol with payload definitions that are very similar to the payload definitions of SCSI-FCP sequences
• the FCP sequences from the local SAN can be divided into smaller packets that are compatible with the lower-level transport protocol being used (e g , ATM or Ethernet)
• the lower-level transport protocol e g , ATM or Ethernet
• Message identifiers are used to retain sequence information du ⁇ ng disassembly
• the disassembled sequences are then combined into frames for transport across the physical link Once across the link, another node receives these frames and uses the message identifiers to reassemble the FCP sequences
• the packets can then be ready for transmission to the local SAN in the same format in which they were originally produced
• the following messages are used to define and manage the FCP-EP data mechanism
• SCSI Data Request Contains information regarding data transfer size for a write request This message requests an amount of data specified by a Data Size field, starting at a relative offset specified by a Relative Offset field
• SCSI Data Contains a block of data and is used for reads and writes
• SCSI Data Response Contains a block of data as well as FCP response information
• the method and system of this invention can be implemented within a Fibre Channel-to-SCSI router such as routers 120, 130 and 150 of FIGURE 1 (nodes 120, 130 and 150)
• the present invention can be implemented purely as software instructions stored withm memory within the Fibre Channel-to-SCSI routers and can be easily upgraded as new versions with new functionality are created. No change in the hardware of existing Fibre Channel-to-SCSI routers, is required to incorporate this invention.
• the memory in which the software instructions of this invention are stored can be RAM (random access memory) or ROM (read-only memory), or other memory storage device.
• An implementation of the present invention can include a dynamic discovery mechanism by which each node (router) in a multi-node implementation can communicate with every other node in order to, for example, initially discover the presence of other such nodes within the system.
• This dynamic discovery mechanism can be used to allow each node to communicate with every other node through a common server.
• Each node in the network can thus discover the presence of other nodes and communicate to the other nodes what attached targets it has available.
• Each node can receive this information from every other node and can represent to their own attached hosts, or to technicians configuring each router (node), all of the available targets on all the available nodes.
• At least one router must be designated as the server through which this discovery functionality can be implemented.
• Other routers can also be designated as servers for, for example, fail over and error recovery cases or as a back-up.
• a Fibre Channel-to-SCSI router can, however, contain and provide the server function. If the server function is provided by a separate device, the separate server can be integrated into the standard network equipment not within the SAN, and the routers of the SAN can communicate with this server to receive the required information. The server would thus be a true "server,” instead of an additional function within a Fibre Channel-to-SCSI router.
• the server function of this invention can be analogized to a DNS server within an IP network.
• the DNS server exists in the network infrastructure and knows how to communicate with the main servers. There is a defined protocol by which the main servers in an IP network can discover each other.
• the dynamic discovery mechanism of the present invention provides essentially the same function, and can thus be integrated into the network, leaving the Fibre Channel-to-SCSI routers to be simple client nodes that can communicate with one another and with the server to discover information about any other nodes on the network.
• the encapsulation protocol method and system of the present invention can be used over existing internet infrastmcmres and other existing network protocols.
• the extension protocol can be a typical IP network protocol, an ATM network, gigabit Ethernet, or any protocol that allows data packets to flow between nodes.
• the method and system of this invention by encapsulating Fibre Channel SCSI, provide a means by which data can be routed between any SCSI protocol SANs on either end of an extension network.
• the method and system of this invention define a dynamic way to discover all the nodes available within a network implementation, so that a 1-to-n or an n-to-n relationship can be established between multiple nodes (routers) having multiple targets and initiators Each node (router) is an access point to its respective SAN
• the method and system of this invention extend standardized messages across the intervening WAN 140 in such a way that they can be de-coded at a remote SAN and acted on within the remote SAN without loss or corruption
• Standardized messages can thus be extended across WAN 140 from a local SAN to a remote SAN without the need for a proprietary protocol format
• a Fibre Channel-to-SCSI router implementing this invention first comes online within a storage area network 110 or 115, it registers with the designated server to identify itself to the network and to receive in exchange information about every other node present on the network, and of the SCSI targets available on each node Similarly, the designated server can detect when a Fibre Channel-to-SCSI router drops from the network due to maintenance or malfunction
• This functionality can be provided with, for example, a heartbeat message within the Fibre Channel SCSI protocol
• the present invention is not limited to use in applications having storage area networks that each use the same Fibre Channel protocol
• host 115 and hosts 110 of FIGURE 1 can each use a different protocol and still function properly using the encapsulation protocol of the present invention
• the present invention provides sufficient information for translation to occur between, for example, a Fibre Channel network on one side of the extender and a parallel SCSI network on the other side of the extender
• the present invention can perform this translation between any two types of SCSI networks
• one embodiment of the method of the present invention comprises the following steps A Fibre Channel-to-SCSI router is brought online, the router communicates with a designated server to identify itself to the network and also to receive information of the other available nodes on the network The Fibre Channel-to-SCSI router will also receive information on the available devices attached to each of the other network nodes This process occurs at each node as it comes online on the storage area network The method and system of the present invention thus determines at each node what other nodes are available and what devices are attached to each of those nodes
• the method of this invention represents each available device at each node as either a single target having one or more LUNs, or as a group of targets with one or more LUNs, and makes designed devices available to all other hosts on the local storage area network This means that each node coming online represents the reported devices on other nodes in such a way that they are made available to its own hosts
• Communications from hosts attached to a Fibre Channel-to-SCSI router coming online can then be encapsulated and sent across to available devices over the extender through WAN 140 and, similarly, encapsulated messages can be received at the local node and passed on to its local hosts
• This invention can thus encapsulate the I/O phases between a local host and remote devices that are made available to the host
• the I/O phases encapsulated between a local host and a remote device can include, for example, a command phase, a data phase and a response phase
• a host can thus send a command which is encapsulated by its associated Fibre Channel-to- SCSI router (node) and forwarded over the extender (WAN 140) to a remote node associated with the device for which the command is intended.
• the remote node will de-encapsulate the command and forward it to the intended device
• the device may then send back data or a response, or data and a response, which are then encapsulated by the remote node and sent to the node associated with the initiator (host) sending the command
• the node associated with the initiating host receives and de- encapsulates the response or data, or combination of the two, and forwards them to the host
• This sequence of command, data and/or response can comprise an I/O phase to be encapsulated
• the present invention provides the encapsulation protocol but does not alter the data transmitted between host and device in any other way
• the step of encapsulating the I/O phases between a local host and a remote device is repeated as necessary for subsequent I/Os Encapsulation can be performed between multiple hosts attached to multiple nodes communicating with multiple devices, all associated with multiple local or remote SANs
• the method and system of this invention establish an initial network configuration and maintain communication between local routers in a local SAN and remote routers at one or more remote SANs, or between other local routers within the same SAN
• the step of encapsulating the I/O phases can further comprise encapsulating individual commands and messages for a given Fibre Channel, SCSI or other protocol
• task management functions, error recovery functions, and other I/O processing functions can be encapsulated
• the method and system of this invention can be easily expanded to provide the same encapsulation function for additional commands and messages that may be added to existing protocols
• the present invention provides the capability for extending an SAN model to many SANs over distances much greater than those currently allowed by the Fibre Channel protocol
• This invention provides the capability to interconnect SANs in geographically diverse locations, such as different cities, in such a way that they can function in a seamless manner as if they comp ⁇ se a single local SAN
• the present invention allows a back-up library to reside off-site at a remote location, thus ensuring data integrity should the local location be damaged by some failure or disaster.

Applications Claiming Priority (3)

Publications (1)

Family

ID=22597864

Family Applications (1)

Country Status (6)

Families Citing this family (15)

Family Cites Families (6)

• 2000
  • 2000-11-13 JP JP2001545919A patent/JP2003517765A/ja not_active Withdrawn
  • 2000-11-13 CN CN00817156.4A patent/CN1409903A/zh active Pending
  • 2000-11-13 AU AU47070/01A patent/AU4707001A/en not_active Abandoned
  • 2000-11-13 WO PCT/US2000/042087 patent/WO2001044891A2/en not_active Application Discontinuation
  • 2000-11-13 EP EP00992795A patent/EP1240575A2/en not_active Withdrawn
  • 2000-11-13 CA CA002391353A patent/CA2391353A1/en not_active Abandoned

Non-Patent Citations (1)

Also Published As

Similar Documents

Legal Events