Method and system for identifying matching packets

US9438517B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9438517-B2
Application numberUS-201314067656-A
CountryUS
Kind codeB2
Filing dateOct 30, 2013
Priority dateOct 30, 2012
Publication dateSep 6, 2016
Grant dateSep 6, 2016

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

In a method of identifying matching packets at different locations in a network, a first plurality of packets is received at a first location in the network, and a first subset thereof is selected in accordance with a filter. A second plurality of packets is received at a second location in the network, and a second subset thereof is selected in accordance with the same filter. Each packet in the first and second subsets is parsed to extract invariant header fields from an outermost IP header inwards, until a minimal set of invariant header fields is obtained for that packet, or until it is determined that a minimal set is not obtainable for that packet. A packet signature is computed from the minimal set for each packet having a minimal set, and the packet signatures are compared to identify matching packets in the first and second subsets.

First claim

Opening claim text (preview).

We claim: 1. A method, comprising: receiving, by a device, a first subset of a first plurality of packets, the first plurality of packets being associated with a first location in a network, and the first subset of the first plurality of packets being selected based on a filter; receiving, by the device, a second subset of a second plurality of packets, the second plurality of packets being associated with a second location in the network, the second location being different than the first location, and the second subset of the second plurality of packets being selected based on the filter; parsing, by the device, each packet in the first subset and the second subset to extract invariant header fields from an outermost internet protocol (IP) header until a minimal set of invariant header fields is obtained, for each packet, that uniquely identifies each packet throughout the network, or until the minimal set of invariant header fields cannot be obtained for each packet, the minimal set of invariant header fields including a minimum set of invariant header fields, of each packet, that uniquely identifies each packet throughout the network within a particular time period, the particular time period being long enough in duration to allow each packet to traverse the network, but short enough in duration to prevent a same packet signature from being computed for different packets, the minimal set of invariant header fields not being obtainable for a particular packet with a particular protocol combination, the particular protocol combination including no known identifier or sequence number that uniquely identifies the particular packet at the first location and the second location; computing, by the device, a packet signature from the minimal set of invariant header fields for each packet in the first subset and the second subset for which a minimal set of invariant header fields is obtained; and comparing, by the device, packet signatures associated with the first subset and packet signatures associated with the second subset to identify matching packets with a same packet signature in the first subset and the second subset. 2. The method of claim 1 , where each packet in the first subset and the second subset is parsed header by header from the outermost IP header inwards. 3. The method of claim 1 , where: at least some of the packets in the first subset have different protocol combinations, at least some of the packets in the second subset have different protocol combinations, and the minimal set of invariant header fields for each packet in the first subset and the second subset, for which a minimal set of invariant header fields is obtained, depends on the protocol combination of each packet. 4. The method of claim 1 , wherein the minimal set of invariant header fields includes an IP source address, an IP destination address, and at least one additional invariant header field selected from an identifier and a sequence number. 5. The method of claim 1 , where the packet signature for each packet in the first subset and the second subset, for which a minimal set of invariant header fields is obtained, is computed by applying a hash function to the minimal set of invariant header fields for each packet. 6. The method of claim 5 , further comprising: storing each packet in the first subset and the second subset in memory and in a hash table indexed by packet signature. 7. The method of claim 1 , further comprising: assigning a first timestamp to each packet in the first subset; assigning a second timestamp to each packet in the second subset; and comparing first timestamps and second timestamps of the matching packets in the first subset and the second subset to determine a latency between the first location and the second location in the network. 8. The method of claim 1 , where: the filter includes a first filter condition based on a first invariant header field selected from an identifier and a sequence number, and the first filter condition defines at least one of an entire identifier, an entire sequence number, a subset of the identifier, or a subset of the sequence number. 9. The method of claim 8 , further comprising: counting each packet in the first subset and the second subset to obtain a total number of packets; comparing the total number of packets to a predetermined threshold; and when the total number of packets is less than the predetermined threshold, adding a second filter condition to the filter, the second filter condition being based on a second invariant header field selected from another identifier and another sequence number, and the second filter condition defining at least one of an entire identifier, an entire sequence number, a subset of the identifier, or a subset of the sequence number. 10. A system, comprising: a first probe to: receive a first plurality of packets at a first location in a network; and select a first subset of the first plurality of packets in accordance with a filter; a second probe to: receive a second plurality of packets at a second location in the network, the second location being different than the first location; and select a second subset of the second plurality of packets in accordance with the filter; and a packet-matching unit to: parse each packet in the first subset and the second subset to extract invariant header fields from an outermost interne protocol (IP) header until a set of invariant header fields is obtained, for each packet, that uniquely identifies each packet throughout the network, or until the set of invariant header fields cannot be obtained for each packet, the set of invariant header fields including a minimum set of invariant header fields, of each packet, that uniquely identifies each packet throughout the network within a particular time period, the particular time period being long enough in duration to allow each packet to traverse the network, but short enough in duration to prevent a same packet signature from being computed for different packets, the set of invariant header fields not being obtainable for a particular packet with a particular protocol combination, the particular protocol combination including no known identifier or sequence number that uniquely identifies the particular packet at the first location and the second location; compute a packet signature from the set of invariant header fields for each packet in the first subset and the second subset for which a set of invariant header fields is obtained; and compare packet signatures associated with the first subset and packet signatures associated with the second subset to identify matching packets with a same packet signature in the first subset and the second subset. 11. The system of claim 10 , where: the first probe is incorporated into a first network node physically located at the first location, and the second probe is incorporated into a second network node physically located at the second location. 12. The system of claim 10 , where each packet in the first subset and the second subset is parsed header by header from the outermost IP header inwards. 13. The system of claim 10 , where: at least some of the packets in the first subset have different protocol combinations, at least some of the packets in the second subset have different protocol combinations, and the set of invariant header fields for each packet in the first subset and the second subset, for which a set of invariant header fields is obtained, depends on the protocol combination of each packet. 14. The system of claim 10 , where the s

Assignees

Inventors

Classifications

  • H04L47/115Primary

    using a dedicated packet · CPC title

  • Traffic characterised by specific attributes, e.g. priority or QoS · CPC title

  • by adaptive sampling · CPC title

  • using flow identification · CPC title

  • by filtering · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9438517B2 cover?
In a method of identifying matching packets at different locations in a network, a first plurality of packets is received at a first location in the network, and a first subset thereof is selected in accordance with a filter. A second plurality of packets is received at a second location in the network, and a second subset thereof is selected in accordance with the same filter. Each packet in t…
Who is the assignee on this patent?
Jds Uniphase Corp, Viavi Solutions Inc
What technology area does this patent fall under?
Primary CPC classification H04L47/115. Mapped technology areas include Electricity.
When was this patent published?
Publication date Tue Sep 06 2016 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).