Symantec Operating Corporation

Symantec Corporation

Slava Kritov

Hans Van Rietschote

Michael Spertus

William E Sobel

Alfred C Hartmann

Brian T Witten

Darrell Kienzle

Anthony T Orling

Stephen Duffy

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.

Dynamic tagging of network data based on service level objectives

A peer-to-peer storage manager measures availability (liveness) of the various nodes in a peer-to-peer storage pool, and adjusts the storage of data within the pool to meet performance expectations based on this liveness information. Based on node liveness statistics, the peer-to-peer storage manager fine tunes storage up or down to efficiently allocate storage while maintaining service level objectives for retrieval time probabilities. Responsive to node liveness information, the peer-to-peer storage manager can dynamically adjust redundancy and/or determine which nodes on which to store data. The peer-to-peer storage manager can execute these storage modifications using rateless erasure codes that allow highly robust storage with only weakly synchronized directory update protocols.

Adaptive liveness management for robust and efficient peer-to-peer storage

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. Logged information may be used to distinguish application problems from network performance problems.

Detection of network problems in a computing system

A system for a redundancy management service for peer-to-peer (P2P) networks includes one or more processors and memory coupled to the processors. The memory stores program instructions executable by the processors to receive a request at a device to upload a data object from the device into a P2P network. In response to receiving the request, the instructions are executable to identify a redundancy manager associated with the device and to transmit the data object to the redundancy manager. In addition, the instructions are executable to upload, from the redundancy manager to one or more target devices of the P2P network, a plurality of data blocks derived from the data object, such that the data object may be recovered from a subset of the plurality of data blocks.

Redundancy management service for peer-to-peer networks

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.

Bulk network transmissions using multiple connections primed to optimize transfer parameters

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.

Dynamic directories

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.

Preventing network micro-congestion using send pacing based on end-to-end bandwidth

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.

Growing community of inventors

Palo Alto, CA, United States of America

Slava Kritov