Methods, systems, and computer readable media for monitoring latency and/or time-based data locations of multicast communications are disclosed. One exemplary method includes monitoring sequence numbers of multicast messages at a plurality of physical network locations, reporting when a sequence number value for the multicast messages reaches a predetermined value, and receiving the reports and using the reports to generate an indication of relative latencies and/or time-based data locations across the physical network locations.
Drawings
Claims17
A method for monitoring latency associated with multicast communications, the method comprising:
monitoring sequence numbers of multicast messages at a plurality of physical network locations, wherein the physical network locations are hops along at least one path in a network for the multicast messages;
at each physical network location, sending a report when a sequence number value for the multicast messages reaches a predetermined value, wherein the reports each include a sequence number associated with a monitored message and a time stamp of an arrival time at which the monitored message arrived at the respective physical network location, wherein the sequence number being reported is the same across each physical network location;
and
at a latency determination server (LDS), receiving the reports and using the reports to generate an indication of relative latencies and/or time-based data locations across the physical network locations, wherein using the reports to generate an indication of relative latencies and/or time-based data locations across the physical network locations includes generating a latency metric based upon the time stamps in the reports indicating the arrival times at which the monitored message with the same sequence number was received at the physical network locations.
1 more element
A system for monitoring latency associated with multicast communications, the system comprising:
a plurality of physical network locations for monitoring sequence numbers of multicast messages, wherein the physical network locations are hops along at least one path in a network for the multicast messages, wherein each physical network location is configured to send a report when a sequence number value for the multicast messages reaches a predetermined value, wherein the reports each include a sequence number associated with a monitored message and a time stamp of an arrival time at which the monitored message arrived at the respective physical network location, wherein the sequence number being reported is the same across each physical network location;
and
a latency determination server (LDS) for receiving reports from the plurality of physical network locations and using the reports to generate an indication of a relative latencies and/or time-based data locations across the physical network locations, wherein using the reports to generate an indication of relative latencies and/or time-based data locations across the physical network locations includes generating a latency metric based upon the time stamps in the reports indicating the arrival times at which the monitored message with the same sequence number was received at the physical network locations.
A non-transitory computer readable medium comprising computer executable instructions embodied in the computer readable medium that when executed by a processor of a computer perform steps comprising:
monitoring sequence numbers of multicast messages at a plurality of physical network locations, wherein the physical network locations are hops along at least one path in a network for the multicast messages;
at each physical network location, sending a report when a sequence number value for the multicast messages reaches a predetermined value, wherein the reports each include a sequence number associated with a monitored message and a time stamp of an arrival time at which the monitored message arrived at the respective physical network location, wherein the sequence number being reported is the same across each physical network location;
and
at a latency determination server (LDS), receiving the reports and using the reports to generate an indication of relative latencies and/or time-based data locations across the physical network locations, wherein using the reports to generate an indication of relative latencies and/or time-based data locations across the physical network locations includes generating a latency metric based upon the time stamps in the reports indicating the arrival times at which the monitored message with the same sequence number was received at the physical network locations.
#The subject matter described herein relates to monitoring latency associated with communicating data in a network. More specifically, the subject matter relates to methods, systems, and computer readable media for monitoring latency and/or time-based data locations of multicast communications.
#Multicast communications are those in which one or more senders transmit a data stream or data feed to multiple different receivers using multiple different channels. That is, multicast communications include packet data feeds that are addressed to a group of destinations simultaneously. Individual packets of a multicast data feed are embedded with monotonically increasing sequence numbers, so that dropped or lost packets may be more easily detected. Currently, the embedded or encoded sequence numbers associated with multicast data packets are only analyzed to determine whether there are gaps in the data, for example, by determining which packet sequence numbers were not received by a receiver or receiving endpoint.
#In multicast communications, it is desirable to measure packet latency, where latency is defined as the relative delay in delivery of the same multicast packet to different network locations. This is especially true in the field of financial market and stock exchange communications. In some aspects, receivers may even pay a premium price to guarantee receipt of exchange communications over a low latency channel. Thus, it is useful to monitor and calculate respective channel latency in real-time, for example, to diagnose and hopefully resolve communication issues. Currently, there is not a simple, inexpensive, and real-time or near real-time method of monitoring and calculating latency within a multicast network.
Brief description of the drawings5 figures
#The subject matter described herein will now be explained with reference to the accompanying drawings of which:
#FIG. 1 is an exemplary network diagram for sending and receiving multicast communications according to an embodiment of the subject matter described herein;
#FIG. 2 is a schematic block diagram illustrating exemplary routing of a multicast communication according to an embodiment of the subject matter described herein;
Detailed description4,117 words
#The subject matter described herein includes methods, systems, and computer readable media for monitoring latency of multicast communications. Multicast communications (packets, multiple messages within packets, or messages spread across multiple packets) include embedded sequence numbers, referred to herein as sequence number identifier values. Notably, methods, systems, and computer readable media set forth herein are configured to utilize these pre-existing sequence numbers identifier values associated with packets to passively monitor latency associated with multicast communications, for example, by tracking the arrival time of each packet sequence identifier value at and/or between various physical locations (e.g., hops) in real-time, or near real-time. This information can be used to detect trouble spots within a multicast network so that network operators can identify, de-bug, and improve multicast communication efficiency.
#The term “multicast data feeds”, “multicast communications”, and/or “multicast packets” refer to data feeds sent by at least one sender to multiple receivers, simultaneously. Multicast communications are those having a transport layer protocol including a User Datagram Protocol (UDP), a Pragmatic General Multicast (PGM), or any other suitable protocol.
#Reference will now be made in detail to exemplary embodiments of the subject matter described herein, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.
Application
14/626,863Filed 19 Feb 2015
Published
US 2016/0248650 A125 Aug 2016
Granted
9 Oct 2018
Term ends
21 Feb 2035Estimated · howhide20 years from earliest known nonprovisional domestic filing plus recorded patent term adjustment, including 2 days of adjustment. Maintenance-fee lapses, terminal disclaimers and statutory extensions have not been checked. The continuity chain may be incomplete; this is not an enforceability determination.