Abstract: A system comprises a plurality of nodes coupled via a network. The plurality of nodes are configured to communicate by transmitting and receiving messages between the plurality of nodes. Each message comprises a first version identifier indicative of a first version of an object in a first node of the plurality of nodes, wherein the first node is the transmitter of the message. A second node of the plurality of nodes receives the message, and is configured to upgrade to the first version of the object responsive to the first version identifier indicating that the first version is newer than a second version in the second node (as indicated by a second version identifier in the second node). The second node is configured to include the first version identifier in subsequent messages transmitted by the second node.

Abstract: Various systems and methods for exchanging communications between devices coupled by an address translation device are disclosed. These techniques can be used to facilitate automatic relationship discovery. One method involves extracting a sequence number from a TCP acknowledgment message being conveyed from a network interface to a TCP stack, and then sending a new TCP message, which includes the sequence number.

Abstract: A system for dynamic tagging of network data based on service level objectives comprises one or more processors and memory coupled to the processors. The memory comprises program instructions executable by the processors to identify a service level objective associated with a particular task that comprises a transmission of data packets over a network on behalf of an application, where the network includes one or more devices (such as routers, switches, etc.) configured to provide different levels of service to data packets based at least in part on service level indicators included within the packets. The instructions are executable to dynamically generate service level indicators corresponding to the identified service level objectives for inclusion in the data packets of the task, and to transmit the packets including the service level indicators into the network.

Abstract: A method and mechanism for monitoring performance in a network computing system. A user application on a source system is configured to communication with a destination system. The application is configured to load a dynamic linked library upon execution. The dynamic linked library is configured to store packet identifiers and time stamp information for communication packets received from the application prior to the packets being conveyed to the destination system. Upon receipt of an acknowledgement packet from the destination system, the library code is configured to retrieve the previously stored time stamp information, determine transit latency information corresponding to the communication packet, and log the determined transit latency information. Acknowledgement packets may further include time stamp information which may be utilized to determine additional latency information corresponding to the communication packet and/or acknowledgement packet.

Abstract: A system and method for writing and reading blocks of a data volume are disclosed. The method provides continuous data protection (CDP) for a data volume by backing up blocks of the data volume in real time to a local CDP log and transmitting the blocks over the Internet for storage in a remote CDP log on a server computer system in response to write requests that change the blocks of the data volume. In response to a read request for a particular block the method attempts to read the block from the data volume. If the block is not present in the data volume the method attempts to read the block from the local CDP log. If the block is not present in the local CDP log the method request the server computer system to read the block from the remote CDP log and return the block.

Abstract: In some embodiments, a system comprises at least one computer system, wherein the computer system is configured to execute a virtual machine corresponding to a user. The system further comprises a storage subsystem configured to store data representing the virtual machine and at least one file server. The file server is coupled to a network to which the computer system is configured to be coupled, and is also coupled to the storage subsystem. The file server is configured to provide the computer system with access to the data representing the virtual machine from the storage subsystem over the network. In some embodiments, the computer system is configured for essentially continuous connection to the network during use. In other embodiments, the computer system is configured for intermittent connection to the network during use.

Abstract: A system for bulk network transmissions using multiple connections primed to optimize transfer parameters includes one or more processors and memory coupled to the processors. The memory stores program instructions executable by the processors to establish a plurality of network connections designated to be used for a single bulk data transfer. The instructions are further executable to adjust the values of one or more configuration parameters of each of the connections. The adjusting includes sending one or more priming packets over each of the connections. The instructions are also executable to perform the bulk transfer as a sequence of sub-transfers. Each sub-transfer includes a transmission of a predetermined amount of application data over each connection of a selected subset of the plurality of network connections.

Abstract: A system and method for creating and utilizing dynamic directories in a computing system. A computing system includes a file system and a dynamic directory mechanism. The dynamic directory mechanism is configured to enable a user to create dynamic directories which are identifiable as having special behaviors associated with them. The user may create executable instructions for performing the special behaviors in a user space of an operating system and associate the special behaviors with selected native file system operations which may be performed on the directory. In response to detecting an operation on a directory is initiated, the mechanism determines whether the directory is a dynamic directory. If the directory is a dynamic directory, the mechanism determines whether any predetermined special behaviors have been defined for the initiated operation and if so performs the special behaviors.

Abstract: A cluster comprises a plurality of computer systems, wherein each of the plurality of computer systems is configured to execute one or more virtual machines. Each of the plurality of computer systems comprises hardware and a plurality of instructions. The plurality of instructions, when executed on the hardware, migrates at least a first virtual machine executing on a first computer system of the plurality of computer systems to a second computer system of the plurality of computer systems. The plurality of instructions migrates the first virtual machine responsive to a first load of the first computer system prior to the migration exceeding a second load of the second computer system prior to the migration.

Abstract: A system and method for writing and reading blocks of a data volume are disclosed. The method provides continuous data protection (CDP) for a data volume by backing up blocks of the data volume in real time to a local CDP log and transmitting the blocks over the Internet for storage in a remote CDP log on a server computer system in response to write requests that change the blocks of the data volume. In response to a read request for a particular block the method attempts to read the block from the data volume. If the block is not present in the data volume the method attempts to read the block from the local CDP log. If the block is not present in the local CDP log the method request the server computer system to read the block from the remote CDP log and return the block.

Abstract: A system for preventing network micro-congestion using send pacing based on end-to-end bandwidth. The system includes one or more processors and memory coupled to the processors, wherein the memory contains program instructions executable by the processors to obtain an estimate of end-to-end network bandwidth available to a particular application-level data transfer operation in progress over a network between a first endpoint and a second endpoint. Based at least in part on the estimate of end-to-end bandwidth, the instructions are further executable to introduce a delay between transmissions of two or more successive messages or packets of the particular application-level data transfer operation from the first endpoint.

Abstract: One or more computer systems, a carrier medium, and a method are provided for transferring a virtual machine between computer systems. In one embodiment, a first computer system and a second computer system are coupled to communicate at least intermittently. In response to a request, a first virtual machine executing on the first computer system is transferred to the second computer system. For example, in one embodiment, the first computer system suspends the first virtual machine to an image, which is transmitted to the second computer system. The first virtual machine is resumed on the second computer system from the image. In one particular implementation, the first computer system may suspend the image to a first storage device accessible to the first computer system, and the image may be copied over a network to a second storage device accessible to the second computer system.

Abstract: An apparatus comprises a plurality of nodes interconnected as peers in a peer-to-peer network. At least some nodes are configured to update an object, thereby generating a plurality of versions of the object. Any of the plurality of nodes is configured to detect a conflict between a first version and a second version of the plurality of versions, and any of the plurality of nodes is configured to provide an indication of a resolution of the conflict to other ones of the plurality of nodes. Each version may be identified by a version descriptor that includes a version identifier (ID) and a parent version ID. If the version is the result of a conflict resolution, the version descriptor may also include a resolved version ID identifying the losing version. The resolved version ID may be used to prevent the raising of the same conflict after it has been resolved.

Abstract: In one embodiment, a method includes detecting that an application in a first node is to failover; provisioning a second node to execute the application responsive to the detecting; and failing the application over from the first node to the second node. Additionally, embodiments comprising computer accessible media encoded with instructions which, when executed, implement the method are contemplated. In another embodiment, a system comprising a plurality of nodes. A first node of the plurality of nodes is configured to monitor performance of an application executing on a second node of the plurality of nodes during use. In response to a detection that the application is to failover from the first node, a third node is configured to be provisioned to execute the application. The application is failed over to the third node during use.

Abstract: One or more computer systems, a carrier medium, and a method are provided for backing up virtual machines. The backup may occur, e.g., to a backup medium or to a disaster recovery site, in various embodiments. In one embodiment, an apparatus includes a computer system configured to execute at least a first virtual machine, wherein the computer system is configured to: (i) capture a state of the first virtual machine, the state corresponding to a point in time in the execution of the first virtual machine; and (ii) copy at least a portion of the state to a destination separate from a storage device to which the first virtual machine is suspendable. A carrier medium may include instructions which, when executed, cause the above operation on the computer system. The method may comprise the above highlighted operations.

Abstract: A system for efficient backups using dynamically shared storage pools in peer-to-peer networks comprises one or more processors and memory coupled to the processors. The memory stores instructions executable by the processors to implement a backup manager configured to dynamically subdivide a storage pool into one or more portions of storage currently designated for local backup data and one or more portions of storage currently designated for peer-to-peer (P2P) backup data. In response to local backup data received from a backup client, the backup manager may store the local backup data in a portion of the storage pool that is currently designated for local backup data. The backup manager may then generate a P2P version of the local backup data, e.g., by encrypting and/or redundancy encoding the local backup data, and transmit parts of the P2P version to each of one or more peer devices in the P2P network.

Abstract: In one embodiment, a method is contemplated. The method includes creating a copy of a volume, wherein the copy corresponds to a first point in time. Write operations to the volume are logged separate from the volume. The method also includes recovering a state of the volume to a second point in time subsequent to the first point in time using the copy of the volume from the first point in time and at least a subset of the write operations from the log. The subset of write operations occurs subsequent to the first point in time and prior to the second point in time. In some embodiments, an end marker may be included in the log, and recovery to a write operation that is indicated as the end of a transaction (by the end marker) may be performed.

Abstract: A storage management system may provide virtual storage devices for use by an operating system. The storage management system may map files representing the virtual storage devices to a plurality of volumes to be stored on physical storage devices. In various embodiments, the storage management system may include storage management components which manage the files representing the virtual storage devices. In one implementation, the storage management system may support a set of storage commands for the virtual storage devices, including standard commands used by the operating system to communicate with storage devices, and additional commands for communicating with the storage management components.

Abstract: In one embodiment, a computer accessible medium comprises instructions which, when executed, check a first storage from which a computer system is configured to boot for a block identified in a read request. The block is included within an image of a set of software resources to be provisioned on the computer system. If the block is stored in the first storage, the instructions supply the block from the first storage in response to the read request. Otherwise, the instructions: fetch the block from an image repository system that stores the image; store the block in the first storage; and supply the block in response to the read request. In another embodiment, the instructions store a block identified in a write request to the first storage. The instructions record that the block is modified in the first storage with respect to the image stored in an image repository system.

Abstract: A first computer system may be configured to execute a first application in a first virtual machine. A second computer system may be coupled to the first computer system. In response to a failure, the first computer system is configured to failover the first virtual machine to the second computer system. A carrier medium comprises first instructions which, when executed, initiate a failover of a first virtual machine. An application executes on the first virtual machine. The failover occurs from a first computer system on which a failure occurs to a second computer system.