Abstract: A system and method for logging for asynchronously replicating volume groups. A write request to write data to a location in a volume may be received. Metadata associated with the write request may be stored. It may be determined if the write request possibly overlaps with one or more earlier write requests to the volume that have not yet been replicated to a secondary storage. The data may be stored in a replication log only if the write request possibly overlaps with one or more earlier write requests to the volume. The data may not be stored in the replication log if the write request does not overlap with one or more earlier write requests to the volume. The data may be written to the location in the volume. Changes to the volume may periodically be replicated to the secondary storage using the replication log.

Abstract: A method for managing a memory of a computer system to store a data of a first size, comprising the steps of defining chunks of the memory, wherein each chunk is a continuous memory space of a predetermined size. Defining chunk pools for managing the chunks, wherein each chunk pool corresponds to chunks of a particular size and defining unit pools for managing units of the first size, wherein the chunk pool corresponding to the unit pool provides a chunk of the particular size to be separated into the units of the first size, and the data of the first size is stored in the units.

Abstract: Method and apparatus for migrating a volume and a virtual disk from a first storage controller to a second storage controller in a distributed storage system having volumes and virtual disks associated with storage controllers. In one embodiment, the virtual disk is migrated to the second storage controller, and requests for data reads/writes associated with the virtual disk are routed to the second controller. Further, in another embodiment, the volume is migrated to the second storage controller, and requests for data reads/writes associated with the volume are routed to the second controller. A contact address may be associated with a plurality of storage controllers and once a session between an application server and a volume is established, the application server may be redirected so as to communicate with the storage controller associated with the volume using the IP address of the storage controller.

Abstract: Embodiments of the present invention provide storage management system and method for managing a geographically distributed storage. In one embodiment, the system includes a plurality of sites organized in a tree form and a management module associated with each site. The plurality of sites include a plurality of management sites each having a network of nodes and storage devices, and at least one parent site having a plurality of virtual nodes corresponding to the plurality of sites. The management module for each site includes a site manager component, a storage resource manager component, and a node manager component.

Abstract: Apparatus and methods for synchronizing a distributed mirror. A computer system incorporating the invention may divide a mirror source into N chunks, assigning N storage processors responsibility for respective chunks of the mirror. The storage processors then may communicate among themselves to synchronize a distributed mirror. The storage processors may communicate mirror source blocks or their addresses and host-initiated (user) data requests. A storage processor may assist the synchronization of a mirror. The processor may accept responsibility for a chunk of a mirror source and communicate with a second storage processor responsible for another chunk of the mirror source to synchronize the mirror. The storage processor may track addresses of source blocks currently in use for synchronization, as well as addresses of source blocks to be synchronized after the blocks currently in use for synchronization.

Abstract: Apparatus and methods for distributing iSCSI and SCSI targets. The initiator may assist in the distribution and order the SCSI commands. A subset of target storage processors may act as proxies. Target storage processors forward requests to a selected target storage processor which decides whether any and which of the other target storage processors is to process a forwarded request. The target storage processors may act as peers. A target storage processor communicates each received request to all of the other storage processors. Each of the target storage processors determines whether a request it received is to execute. A target storage processors may arrange themselves into layers to divide the SCSI and iSCSI protocol work. A distributed system associates each of multiple egress target storage processors with a respective ingress target storage processor and associates a set of blocks of storage with each of the egress target storage processors.

Abstract: A method for managing a memory of a computer system to store a data of a first size, comprising the steps of defining chunks of the memory, wherein each chunk is a continuous memory space of a predetermined size. Defining chunk pools for managing the chunks, wherein each chunk pool corresponds to chunks of a particular size and defining unit pools for managing units of the first size, wherein the chunk pool corresponding to the unit pool provides a chunk of the particular size to be separated into the units of the first size, and the data of the first size is stored in the units.

Abstract: A method for managing a memory of a computer system to store a data of a first size, comprising the steps of defining chunks of the memory, wherein each chunk is a continuous memory space of a predetermined size. Defining chunk pools for managing the chunks, wherein each chunk pool corresponds to chunks of a particular size and defining unit pools for managing units of the first size, wherein the chunk pool corresponding to the unit pool provides a chunk of the particular size to be separated into the units of the first size, and the data of the first size is stored in the units.

Abstract: A method for managing a memory of a computer system to store a data of a first size, comprising the steps of defining chunks of the memory, wherein each chunk is a continuous memory space of a predetermined size. Defining chunk pools for managing the chunks, wherein each chunk pool corresponds to chunks of a particular size and defining unit pools for managing units of the first size, wherein the chunk pool corresponding to the unit pool provides a chunk of the particular size to be separated into the units of the first size, and the data of the first size is stored in the units.

Abstract: In a data communication system, a sending entity divides data into a plurality of groups, each of which is segmented into a plurality of packets, and then sequentially transmits the packets in each group to the receiving entity. The receiving entity receives each packet, and determines whether the packet is sequentially received in a group. When an out-of-sequence error arises, the receiving entity discards the received packet, and sends a negative acknowledgment to the sending entity if no negative acknowledgment has been sent for the group. Only a single negative acknowledgment is sent for the group until an expected packet is received. When all packets of the group are received, the receiving entity sends a positive acknowledgment to the sending entity.

Abstract: A novel system and apparatus for transmitting data between the two nodes of a network is provided. The transmission is effected by using an error recovery protocol featuring a positive group acknowledgement. A sender unit on one node receives the user data and groups the data into consecutive cells, the cells being clustered into groups, each cell in a group being assigned a unique sequence number. The groups of cells are transmitted over a physical channel to a receiver unit on a different node. The receiver unit examines the cell stream and issues an acknowledgment message to the sender unit only when all of the cells in a group have been received. Once the sender unit has completed the transmission of a group of cells, it starts observing the physical channel for an acknowledgement message from the receiver unit. If after a predetermined time period the acknowledgement message has not been received, the sender unit transmits the group of cells again.

Abstract: A new method of processing Asynchronous Transfer Mode (ATM) signaling messages is described wherein a plurality of computing units (CUs), each running signaling processing software, collectively provide signaling processing services for all the ports of a switch. As more ports, and more cards, are added to a switch, CUs can be incrementally added to support additional traffic. More significantly, in order to optimize the utilization rates of the plurality of CUs, the method provides for dynamic load-sharing of signaling traffic between CUs, such that a CU is allocated not on a per port basis, but on a per switched virtual circuit (SVC) session basis.