Abstract: A method for controlling command message flow in a network including a server and a client. A command window, comprising a maximum number of command messages that may be outstanding at the server, is included in messages sent from the server to the client. The value of the command window at the server is modified in accordance with available server resources for receiving command messages. When there are insufficient resources at the server to process one of the command messages delivered to the server, then a pause message is sent to the client indicating which said command message cannot be received; indicia is stored that indicates the command message initially discarded; and subsequent said command messages delivered to the server are discarded until an initially discarded said command message is again delivered to the server.

Abstract: A system and method for determining route quality in a network in which multiple routes exist between a transmitting end-point and a receiving end-point. Initially, a routing sequence number is associated with each transmission sent on a route in the network, such that consecutive transmissions sent on one of the routes have consecutive routing sequence numbers. The routing sequence number for a first one of the routes is included in transmissions sent on a second one of the routes. The routing sequence number of the first route, received on the second route, is used as an indicator of the route quality of the first route, and this indicator is compared to an expected routing sequence number for the first route to determine a likelihood of whether the transmissions sent via the first route are either lost or delayed. The expected routing sequence number is normally incremented each time a transmission is received on the second route.

Abstract: A system and method for message routing in a computer network. The present system establishes a routing layer between the network and transport layers in a network, for communicating routing information between end-points in the network. A route management connection for communicating route management information between two ports in the network is established between pseudo end-points in the network. A route and route set are established between end-points in the network, where the route set provides a relationship between two end-point incarnations that indicates the existence of at least one route between the end-points. A route set management connection is established between the end-points for managing connections that are established on the route set. A route between the end points is selected using a route in the route set, and an application connection is established between two applications running on respective end-points in the network, using the route set and the route set management connection.

Abstract: A system and method for selecting a route, from within the set of network routes between the source and destination end-points, for retransmission of information initially sent via a suspected failed route such that the selected route has a minimum number of network components in common with the suspected failed route. In one aspect, the routes between source and destination end-points are grouped into a route set and placed in order in a circular list by the destination end-point. When the source end-point deems it necessary to retransmit information sent via a suspected failed route, it selects the next acceptable route following the suspected failed route from the circular list. The circular list order is determined such that adjacent routes have few common network components.

Abstract: A system for addressing end-points in a network wherein a transmission is sent between a source end-point and a destination end-point via a respective source port and a destination port connected by a fabric. A payload offset and buffer pool handle are included in a network header sent with the transmission. The buffer pool handle is used to determine a specific queue of pool buffers within the destination port. A pool buffer descriptor, describing a header buffer and a payload buffer each within the destination end-point, is dequeued from a queue indicated by the buffer pool handle. The payload offset in the network header is then decoded to locate a first number of bytes of data in the transmission to be transferred into the header buffer a second number of bytes of data to be transferred into the payload buffer.

Abstract: The present invention provides a method for copying data through a virtualized storage system using distributed table driven (I/O) mapping. In a system having a virtual disk (the “original disk”), a persistent mapping table for this virtual disk exists on a controller, and volatile copies of some or all entries in this mapping table are distributed to one or more more mapping agents. The method of the present invention creates a new virtual disk mapping table that has the exact same entries as the mapping table as the original virtual disk. The new snapshot disk then shares the same storage as the original disk, so it is space efficient. Furthermore, creating new snapshot disk involves only copying the contents of the mapping table, not moving data, so the creation is fast. In order to allow multiple virtual disks to share storage segments, writes to either the original virtual disk or the snapshot copy cannot be seen by the other.

Abstract: A computer network has two or more switches and a plurality of links. A first machine and a second machine are interconnected by the network in such a way that there exist multiple paths through the network from an N_Port of the first machine to an N_Port of the second machine. Network traffic from the N_Port of the first machine to the N_Port of the second machine is distributed between the multiple paths such that frames related to any single exchange traverse the same path yet frames of a first exchange need not traverse the same path as frames of a second exchange. Frames of each exchange therefore tend to be received by their destination in order with respect to other frames of that exchange, while they are not necessarily received in-order with respect to frames of other exchanges.

Abstract: Briefly, the present invention provides a system and method for distributing SCSI semantics throughout a network. Specifically, the present invention distributes the SCSI semantics through multiple parallel agents and a separate controller. This configuration allows performance-sensitive distribution of SCSI semantics to be parallelized and optimized for performance in the agents, while the control and management of the SCSI semantics is centralized in the controller chosen for optimal cost, management, and other implementation practicalities. In this design, the SCSI semantics are stored in the controller, and portions of the SCSI semantics are distributed to the mapping agents as cached, read-only information. The controller is responsible for persistent storage of the SCSI semantics, thereby consolidating the costs and management for the SCSI semantics in a single component.