Cisco Technology, Inc.

Devi Prasad Ivaturi

Ali Golshan

Madhuri Kolli

Pags Krishnamoorthy

Venkatesh Janakiraman

Neelima Mehta

Kushal A Patel

Golshan Ali

Pags Krishnamoor-Thy

Methods and devices are provided for efficient transmission of data between storage area networks. According to some aspects of the invention, novel methods are provided for processing data packets sent by, or received from, a storage area network. Some such aspects of the invention involve storing a packet (or a portion of a packet) in a single memory location during an encapsulation or de-encapsulation process. Instead of repeatedly copying the packet during processing, pointer information is passed along that indicates the single memory location. In some aspects of the invention, the segment boundaries of a packet are retained after data transmission. If data in the packet need to be re-transmitted, the packet is re-transmitted with the same segment boundaries.

Methods and devices for transmitting data between storage area networks

Methods and devices are provided for efficient transmission of data between storage area networks. According to some aspects of the invention, a 'slim' TCP stack is provided which eliminates the socket layer found in a conventional TCP stack, thereby eliminating socket buffers and the associated buffer-to-buffer copying. Moreover, by eliminating the socket layer, one eliminates the listen state. This condition allows TCP processing in an interrupt context instead of client/server operation with a listen state. Accordingly, some aspects of the invention provide for transmitting data between SANs in an interrupt context.

A new search protocol uses a message which a router periodically transmits onto the local LANs connected to its ports, and in response to the new protocol, all end stations receiving the message transmit their addresses to the router. The addresses transmitted to the router comprise the addresses and any other information needed by the router to reach the end station. For example, for an Ethernet LAN the layeror MAC layer address of the end station is transmitted to the router. In the event that the protocol of the LAN uses source routing, the information transmitted to the router includes both the MAC address and the Route Information Field of the end station. In any event, the router uses the information received from the end stations to build its routing table. Then, upon receipt of the next CANUREACH message from a peer router, the desired destination end station will appear in the router's routing table, and there will be no need to waste bandwidth by transmitting search messages looking for the end station. The new protocol messages are transmitted periodically in order to keep the routing tables current is as the network changes dynamically.

MAC address population protocol

The invention is a new field in an ARP packet which designates the canonical format of the addresses written into fields such as ar$sha (the source station hardware address) and ar$spa (the source station protocol address) ar$tha (the target station hardware address), ar$tpa (the target station protocol address) so that a receiving station can determine the canonical format used to create these fields. The station receiving the ARP request or ARP response packet can then write its ARP table entry in the correct canonical format for its computer network.

ARP packet to preserve canonical form of addresses

Computerized system and method are provided which have particular utility in the field of automated testing. In one embodiment of the method of the present invention, an array is stored in computer-readable memory. The array has a plurality of tuples, each of which includes a respective action field, a respective expected result field, a respective success field, and a respective failure field. The respective action field is for specifying at least one respective action whose performance by the system-under-test is to be commanded. The respective reaction field is for specifying at least one respective expected result to be achieved by performance of the respective action. The respective success and failures fields are for specifying further appropriate actions to be executed if the respective expected result is achieved (i.e., if a success condition occurs), or if the respective expected result is not achieved (i.e., if a failure condition occurs). A processor generates a command to the system-under-test to perform the action specified by the action field of a beginning tuple. The processor then receives an indication of an actual result of execution of the command by system-under-test, and compares this actual result to the expected result specified in the reaction field of the beginning tuple in order to determine whether a success or failure condition has occurred. Based upon whether a success or failure condition is determined by the processor to have occurred, the further action specified in the success or failure fields is executed.

Growing community of inventors

San Jose, CA, United States of America

Devi Prasad Ivaturi