Abstract: A network of computing devices includes a timing reference, a free-run node, and an aggregator. The reference calculates a first communication packet having a reference timestamp and reference data, and transmits the first packet to the free-run node. The free-run node receives the first packet from the timing reference, calculates a second packet having metadata that includes the reference timestamp, a sparse hash value calculated from the reference data, and a free-run node timestamp, and publishes the second packet to the aggregator. The aggregator receives the second packet and calculates a compensation value from the reference timestamp, the sparse hash value, and the free-run node timestamp. Computer-implemented methods include the free-run node receiving the compensation value and updating its local dock based on the compensation value. Other methods include the aggregator determining an optimal packet path through a network of computing devices based on the metadata.

Abstract: A network of computing devices includes a timing reference, a free-run node, and an aggregator. The reference calculates a first communication packet having a reference timestamp and reference data, and transmits the first packet to the free-run node. The free-run node receives the first packet from the timing reference, calculates a second packet having metadata that includes the reference timestamp, a sparse hash value calculated from the reference data, and a free-run node timestamp, and publishes the second packet to the aggregator. The aggregator receives the second packet and calculates a compensation value from the reference timestamp, the sparse hash value, and the free-run node timestamp. Computer-implemented methods include the free-run node receiving the compensation value and updating its local clock based on the compensation value. Other methods include the aggregator determining an optimal packet path through a network of computing devices based on the metadata.

Abstract: Methods, systems, and apparatus for network monitoring and analytics are disclosed. The methods, systems, and apparatus for network monitoring and analytics perform highly probable identification of related messages using one or more sparse hash function sets. Highly probable identification of related messages enables a network monitoring and analytics system to trace the trajectory of a message traversing the network and measure the delay for the message between observation points. The sparse hash function value, or identity, enables a network monitoring and analytics system to identify the transit path, transit time, entry point, exit point, and/or other information about individual packets and to identify bottlenecks, broken paths, lost data, and other network analytics by aggregating individual message data.

Abstract: Methods, systems, and apparatus for network monitoring and analytics are disclosed. The methods, systems, and apparatus for network monitoring and analytics perform highly probable identification of related messages using one or more sparse hash function sets. Highly probable identification of related messages enables a network monitoring and analytics system to trace the trajectory of a message traversing the network and measure the delay for the message between observation points. The sparse hash function value, or identity, enables a network monitoring and analytics system to identify the transit path, transit time, entry point, exit point, and/or other information about individual packets and to identify bottlenecks, broken paths, lost data, and other network analytics by aggregating individual message data.