Microsoft Technology Licensing, LLC

Google Inc.

Other

Sandeep Singhal

Todd R Manion

Noah Horton

Ravi Rao

Christian F Huitema

Brian R Lieuallen

Kevin C Ransom

Manuel Costa

John L Miller

Jeremy Lee Dewey

Gursharan Singh Sidhu

Rohit Gupta

Scott A Senkeresty

Eliot John Flannery

Ming Zhang

David G Thaler

Guobin Shen

Aaron Wesley Cunningham

Pankaj Garg

Peter Bernard Key

Ryan Yonghee Kim

Thomas Karagiannis

Tomer Weisberg

Gianluigi Nusca

Arash Baratloo

R Scott Briggs

Pritam De

Wangyuan Zhang

Sangho Yoon

Pramod Gaud

Ayalvadi Jagannathan Ganesh

Guangda Lai

Geogy A Samuel

Zhifan Zhang

Gael Hatchue Njouyep

Dan Teodosiu

Benjamin M Schultz

Alireza Dabagh

Khawar Zuberi

Guhan Suriyanarayanan

Khaja Ehteshamuddin Ahmed

Alain Franck Gefflaut

Arsalan Ahmad

Robert C Combs

Sambhrama Madhusudhan Mundkur

Alain Gefflaut

Madhan Sivakumar

Kushal Suresh Narkhede

Tyler M Barton

Radu Simionescu

Nilesh R Shah

Luis M Hernandez

See-Mong Tan

Seyedeh Pardis Miri

Ramakrishna P Pamulapati

Noah Norton

Arsalan Ahmad Aachen

A method includes receiving data objects, determining a predicted lifespan of each data object, and instantiating multiple shard files. Each shard file has an associated predicted lifespan range. The method also includes writing each data object into a corresponding shard file having the associated predicted lifespan range that includes the predicted lifespan of the respective data object and storing the shard files in a distributed system. The method also includes determining whether any stored shard files satisfy a compaction criteria based on a number of deleted data objects in each corresponding stored shard file. For each stored shard file satisfying the compaction criteria, the method also includes compacting the stored shard file by rewriting the remaining data objects of the stored shard file into a new shard file.

Packing objects by predicted lifespans in cloud storage

A method is provided for a host node in a computer network to determine its coordinates in a d-dimensional network space, comprising discovering an address of a peer node in the network, measuring network latency between the host node and the peer node, determining whether network latency has been measured for at least d+1 peer nodes, where, if network latency has not been measured for at least d+1 peer nodes, estimating the network coordinates of the host node, and where, if network latency has been measured for at least d+1 peer nodes, calculating the network coordinates of the host node using d+1 measured latencies.

System and method for implementing PNRP locality

The described method and system enables a client at a branch office to retrieve data from a local hosted cache instead of an application server over a WAN to improve latency and reduce overall WAN traffic. A server at the data center may be adapted to provide either a list of hashes or the requested data based on whether a hosted cache system is enabled. A hosted cache at the client side may provide the data to the client based on the hashes. The hashes may be generated to provide a fingerprint of the data which may be used to index the data in an efficient manner.

Method and system of using a local hosted cache and cryptographic hash functions to reduce network traffic

Using location-independent names to identify content, a service for mapping endpoint requests to requested content. Content requested by an endpoint of the network is mapped to a dynamic 'swarm' of server, peer, or other endpoints capable of supporting the content download. Content names are mapped to a dynamically generated content swarm, presenting a current set of hosts, which can provide the requested content. Optionally, varying degrees of explicit visibility into routing paths and the performance tradeoffs between those routing paths is supported. Based on a set of class of service parameters for a given request for content, a host can initiate route selection based on class of service parameters, predicated on routing metrics maintained by the network by cooperating endpoints and/or network routers.

Network routing of endpoints to content based on content swarms

A Distributed Routing Table (DRT) mesh can comprise two or more nodes, each of which maintains its own routing table that represents some or all of the overall routing knowledge of the DRT mesh. Each node can be comprised of modular components that can perform various defined functions such that the features and abilities of the node can be customized by an application based on which modular components are instantiated. A routing table management module can maintain individual routing tables at each node, and can ensure that only entries that are close to the node, in a network topology sense, are maintained in the routing table. In addition, a security module can verify received messages based on an agreed-upon root certificate.

Distributed routing table architecture and design

An extensible virtual switch allows virtual machines to communicate with one another and optionally with other physical devices via a network. The extensible virtual switch includes an extensibility protocol binding, allowing different extensions to be added to the extensible virtual switch. The extensible virtual switch also includes a miniport driver on which the extensions are loaded, tying the lifetimes of the extensions to the lifetime of the extensible virtual switch.

Virtual switch extensibility

In computing environments having multiple computers, where such computers may comprise virtual machines, events are logged in association with corresponding activity identifiers. When a data packet associated with an activity is transferred to a destination machine, the activity identifier corresponding to the activity is transferred along with the data packet and used by the destination machine when logging its events. This allows events from the two machines to be correlated according to the activities to which they pertain.

Cross-machine event log correlation

Content retrieval techniques are described. In an implementation, a determination is made as to whether a client is permitted to receive content requested by the client. When the client is permitted to receive the content, a communication is formed to be communicated via a wide area network that includes a hash list having a hash of each of a plurality of blocks of the content, each hash being configured to enable the client to locate a corresponding one of the blocks of the content via a local area network.

Content retrieval

Automatic file replication and scanning for malware in a sharing environment is based on detection of file system changes. Only one client of the multi-client environment needs to include malware protection software for all clients to benefit. A file replication service for each client monitors a shared directory, and synchronizes files across clients at the file system driver level. When a new file appears in the shared directory of a client system, through this driver, the new file automatically gets replicated. A malware protection component operates by monitoring the directory for new or modified files. File replication causes automatic malware scanning on the client that has protection. When the file has been cleaned and re-written to the directory, the replication service senses that the file has changed and replicates the cleaned file to the other clients. Thus, the replication behavior produces a multiparty file scanning and cleansing protection scheme.

Distributed malicious software protection in file sharing environments

Architecture for exposing a virtual private network of peer devices into the public domain via an overlay network. Computing devices, peripheral devices, as well as mobile devices can be physically distributed, but appear to belong to the same virtual private (or home) network, and be accessible from anywhere. Benefits include access to user media/documents from anywhere, searching of all connected devices from one location, multicast and broadcast connectivity, management of the private network and the associated policies, and device discovery on the private network from across public networks. P2P networks and ad-hoc networks can be exposed as a virtual interface, as well as the utilization of client operating systems to create the virtual network, grouping, graphing, the integration with relay services and other NAT/firewall traversal schemes, and the creation of a P2P overlay manager on a physical NIC (network interface card) address rather than a virtual address.

Private virtual LAN spanning a public network for connection of arbitrary hosts

A service for facilitating a determination of path quality between a first endpoint node and a second endpoint node in a network of nodes is provided. Path quality information is aggregated from across network internet service providers (ISPs), giving authorized endpoints access to path quality information for specified path segments of a path to another endpoint. Path quality information includes one or more metrics that measure available bandwidth, loss rate and/or latency.

Characterization of network path quality for network applications and services

A firewall functions normally to pass data on open ports to a respective service or endpoint associated with an open port. Invitations may sent to from an internal endpoint to an external peer-to-peer network endpoint inviting a connection back to the internal endpoint. Rather than leave ports open in a firewall for such connections, an invitation manager analyzes the invitation and in real time programs an exception in the firewall based on the invitation. The exceptions may be programmed for a limited duration, based on the nature of the internal endpoint. When an authenticated connection is required, a public key or handle to a public key for the external endpoint may be passed to the firewall for use in establishing the connection.

Integration of social network information and network firewalls

The claimed invention adapts an existing operating system native replication service component to interface with a general application running on a peer-to-peer network. The claimed invention provides the general application with replication services without the need for coding this functionality from scratch. The claimed invention also adapts the replication service functionality to create a topology of connections based on information received from a peer-to-peer network component, thereby making the replication service function more efficiently with a peer-to-peer network.

Methodology and system for file replication based on a peergroup

Growing community of inventors

Kirkland, WA, United States of America

Sandeep Singhal