Back to results
US 11,641,245 B2Granted
Timestamp confidence level
AssigneeMellanox Technologies, Ltd.
InventorsDotan David Levi, Wojciech Wasko, Natan Manevich, Roee Moyal, Eliel Peretz, Eran Ben Elisha, Ariel Almog, Teferet Geula, Amit Mandelbaum
Life of this patent
Estimating the term…
Abstract
In one embodiment, an event processing system includes a clock configured to provide time values, and event processing circuitry, which is configured to generate a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred.
Claims42
An event processing system, comprising:
- a clock configured to provide time values;
- and
- event processing circuitry to:
- generate a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred;
- and
- add the timestamp and the confidence level to a data packet.
3 more elements
An event processing system, comprising:
- a clock configured to provide time values;
- event processing circuitry to generate a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred;
- and
- a data analyzer configured to receive a dataset including event data items having respective timestamps and respective confidence levels.
1 more element
An event processing system, comprising:
- a clock configured to provide time values;
- event processing circuitry to generate a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred;
- a first network node;
- and
- a second network node, the first and second network nodes being connected directly by a cable, wherein:
- the first network node comprises first event processing circuitry configured to:
- identify occurrence of the event;
- and generate the timestamp for the identified event responsively to the time value indicative of when a hardware operation associated with the event occurred;
- and
- the second network node comprises second event processing circuitry configured to generate the confidence level indicative of the degree of confidence of the accuracy of the timestamp generated by the first network node responsively to a common traffic pattern between the first network node and the second network node.
7 more elements
An event processing system, comprising:
- a clock configured to provide time values;
- event processing circuitry to generate a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred;
- and
- clock synchronization circuitry configured to:
- receive a plurality of clock synchronization messages including respective timestamps, the respective timestamps having associated confidence levels indicative of respective degrees of confidence of respective accuracy of the respective timestamps;
- select at least one of the respective timestamps responsively to respective ones of the associated confidence levels;
- and
- perform a clock synchronization responsively to the selected at least one of the respective timestamps.
5 more elements
An event processing method, comprising:
- providing time values;
- generating a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred;
- adding the timestamp and the confidence level to a data packet.
An event processing method, comprising:
- providing time values;
- generating a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred;
- identifying, in a first network node, occurrence of the event;
- generating, in the first network node, the timestamp for the identified event responsively to the time value indicative of when a hardware operation associated with the event occurred;
- and
- generating in a second network node connected directly by a cable to the first network node, the confidence level indicative of the degree of confidence of the accuracy of the timestamp generated by the first network node responsively to a common traffic pattern between the first network node and the second network node.
3 more elements
An event processing method, comprising:
- providing time values;
- generating a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred;
- receiving a plurality of clock synchronization messages including respective timestamps, the respective timestamps having associated confidence levels indicative of respective degrees of confidence of respective accuracy of the respective timestamps;
- selecting at least one of the respective timestamps responsively to respective ones of the associated confidence levels;
- and
- performing a clock synchronization responsively to the selected at least one of the respective timestamps.
3 more elements
An event processing method, comprising:
- providing time values;
- generating a confidence level indicative of a degree of confidence of an accuracy of a timestamp, the timestamp being generated for an event responsively to a time value indicative of when an operation associated with the event occurred;
- and
- receiving a dataset including event data items having respective timestamps and respective confidence levels.
1 more element
Dependencies are inferred from the claim text.