WO2002033915A1 - Method and apparatus for coordinating routing parameters via a back-channel communication medium - Google Patents

Method and apparatus for coordinating routing parameters via a back-channel communication medium Download PDF

Info

Publication number
WO2002033915A1
WO2002033915A1 PCT/US2001/031259 US0131259W WO0233915A1 WO 2002033915 A1 WO2002033915 A1 WO 2002033915A1 US 0131259 W US0131259 W US 0131259W WO 0233915 A1 WO0233915 A1 WO 0233915A1
Authority
WO
WIPO (PCT)
Prior art keywords
prefix
bgp
routing
channel
routing intelligence
Prior art date
Application number
PCT/US2001/031259
Other languages
French (fr)
Inventor
Omar C Baldonado
Sean P Finn
Mansour J. Karam
Michael A Lloyd
Herbert S. Madan
James G Mcguire
Jose-Miguel Pulido Villaverde
Original Assignee
Routescience Technologies Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US09/903,441 external-priority patent/US7080161B2/en
Priority claimed from US09/903,423 external-priority patent/US7363367B2/en
Priority claimed from US09/923,924 external-priority patent/US7406539B2/en
Application filed by Routescience Technologies Inc filed Critical Routescience Technologies Inc
Priority to AU2001294993A priority Critical patent/AU2001294993A1/en
Priority to US10/070,338 priority patent/US7720959B2/en
Priority to US10/070,515 priority patent/US7336613B2/en
Publication of WO2002033915A1 publication Critical patent/WO2002033915A1/en
Priority to US10/358,681 priority patent/US7487237B2/en
Priority to US12/286,019 priority patent/US20090031025A1/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/22Alternate routing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/02Topology update or discovery
    • H04L45/04Interdomain routing, e.g. hierarchical routing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/12Shortest path evaluation
    • H04L45/123Evaluation of link metrics
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/12Shortest path evaluation
    • H04L45/124Shortest path evaluation using a combination of metrics
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/50Routing or path finding of packets in data switching networks using label swapping, e.g. multi-protocol label switch [MPLS]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/11Identifying congestion
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/20Traffic policing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/28Flow control; Congestion control in relation to timing considerations
    • H04L47/283Flow control; Congestion control in relation to timing considerations in response to processing delays, e.g. caused by jitter or round trip time [RTT]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/508Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/508Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement
    • H04L41/5096Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement wherein the managed service relates to distributed or central networked applications
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/02Capturing of monitoring data
    • H04L43/026Capturing of monitoring data using flow identification
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0805Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
    • H04L43/0811Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking connectivity
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0805Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
    • H04L43/0817Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0823Errors, e.g. transmission errors
    • H04L43/0829Packet loss
    • H04L43/0835One way packet loss
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0823Errors, e.g. transmission errors
    • H04L43/0829Packet loss
    • H04L43/0841Round trip packet loss
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0852Delays
    • H04L43/0858One way delays
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0852Delays
    • H04L43/0864Round trip delays
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0852Delays
    • H04L43/087Jitter
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876Network utilisation, e.g. volume of load or congestion level
    • H04L43/0882Utilisation of link capacity
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/16Threshold monitoring

Definitions

  • This invention relates to the field of networking.
  • the invention relates to systems and methods for coordinating routing information amongst routers.
  • Description of the Related Art Internetworks such as the Internet are currently comprised of
  • BGP Border Gateway Protocol
  • BGPv4 constructs a directed graph of the Autonomous Systems, based on the information exchanged between BGP routers. Each Autonomous System is identified by a unique 16 bit AS number, and BGP ensures loop-free routing amongst the Autonomous Systems; BGP also enables the exchange of additional routing information between Autonomous Systems.
  • BGP is further described in several RFCs, which are compiled in The Big Book of Border Gateway Protocol RFCs. by Pete Loshin, which is hereby incorporated by reference.
  • the Border Gateway Protocol provides network administrators some measure of control over outbound traffic control from their respective organizations. For instance, the protocol includes a LOCAL_PREF attribute, which allows BGP speakers to inform other BGP speakers within the Autonomous System of the speaker's preference for an advertised route.
  • the local preference attribute includes a degree of preference for the advertised route, which enables comparison against other routes for the same destination.
  • the LOCAL_PREF attribute is shared with other routers within an Autonomous System via IBGP, it determines outbound routes used by routers within the Autonomous System.
  • a WEIGHT parameter may also be used to indicate route preferences; higher preferences are assigned to routes with higher values of WEIGHT.
  • the WEIGHT parameter is a proprietary addition to the BGPv4 supported by Cisco Systems, Inc. of San Jose, CA. In typical implementations, the WEIGHT parameter is given higher precedence than other BGP attributes.
  • the performance knobs described above are, however, rather simple, as they do not offer system administrators with sufficiently sophisticated means for enabling routers to discriminate amongst routes. There is a need for technology that enables greater control over outbound routing policy. In particular, there is a need to allow performance data about routes to be exchanged between routers. Additionally, system administrators should be able to fine tune routing policy based upon sophisticated, up-to-date measurements of route performance and pricing analysis of various routes.
  • the invention includes systems and methods for enabling networking devices to coordinate via a back-channel communication medium.
  • the information exchanged over the back-channel is used to increase the number of paths considered for the routers during route optimization.
  • a set of Routing Intelligence Units may be used to control a set of routers, such that each Routing Intelligence Unit controls a distinct subset of the routers.
  • the Routing Intelligence Units may assert routes to the routers under their control. In some embodiments, this is done via a Border Gateway Protocol (BGP) feed.
  • BGP Border Gateway Protocol
  • the Decision Makers communicate separately with one another, in order to coordinate routing policy amongst themselves. This coordination may be performed over a back-channel, which may take the form of physical or logical connections between the Routing Intelligence Units. In some embodiments, communications over the back-channel are conducted via separate BGP sessions.
  • the Routing Intelligence Unit may be configured as a route-reflector client to both other decision makers and the routers it controls. This ensures that the Routing Intelligence Unit does not simply transmit information in either direction without consideration.
  • a Routing Intelligence Unit send updates to other Routing Intelligence Units whenever the Routing Intelligence Unit is also asserting to the routers under its control. In alternative embodiments, the Routing Intelligence Unit may send updates when it decides that the current routes are correct.
  • performance scores for prefixes are communicated between Routing Intelligence Units. In some of the embodiments utilizing BGP for such coordination, these performance scores are translated to units of Local Preference. This ensures that the Routing Intelligence Units will automatically select and propagate the best score.
  • Routing Intelligence Units to evaluate prefixes that arrive via coordination.
  • the local route is chosen by default.
  • a static penalty is applied to all remote announcements.
  • dynamic penalties are applied.
  • Fig. 1 - Fig.4 illustrate different configurations of routing intelligence units and edge routers, according to some embodiments of the invention.
  • Figure 5a schematically illustrates an internal architecture of a routing intelligence unit according to some embodiments of the invention.
  • Figure 5b illustrates coordination between routing intelligence units via a back-channel according to embodiments of the invention.
  • Figure 6 illustrates a queuing and threading structure used in the routing intelligence unit in some embodiments of the invention.
  • one or more routing intelligence units are stationed at the premises of a multi-homed organization, each of which controls one or more edge routers. These devices inject BGP updates to the Edge Routers they control, based on performance data from measurements obtained locally, or from a Routing Intelligence Exchange— Routing Intelligence Exchanges are further described in U.S. Provisional Applications No. 60/241,450, filed October 17, 2000 and U.S. Provisional Application No. 60/275,206, filed March 12, 2001, and U.S. Applications No. 09/903,441, filed
  • ISPs 104 and 106 is controlled by a single device 100.
  • Figure 2 illustrates embodiments in which the routing intelligence unit 200 controls multiple edge routers 202 and 204, each of which in turn links to multiple ISPs 206, 208, 210, and 212;
  • Figure 2 also illustrates embodiments in which routers 203 205 controlled by the routing intelligence unit 200 are not coupled to SPALs.
  • routers 203 205 controlled by the routing intelligence unit 200 are not coupled to SPALs.
  • a single routing intelligence unit 300 controls multiple edge routers 302 and 304, each of which is linked to exactly one ISP 306 and 308.
  • different routing intelligence units 400 and 402 each connected to a set of local edge routers 404, 406, 408, and 410, may coordinate their decisions.
  • the routing intelligence units comprise processes running within one or more processors housed in the edge routers. Other configurations of routing intelligence units and edge routers will be apparent to those skilled in the art.
  • the routing intelligence units include a Decision Maker resource.
  • the objective of the Decision Maker is to improve the end-user, application level performance of prefixes whenever the differential in performance between the best route and the default BGP route is significant.
  • This general objective has two aspects: • One goal is to reach a steady state whereby prefixes are, most of the time, routed through the best available Service Provider Access Link (i.e., SPAL), that is, through the SPAL that is the best in terms of end- to-end user performance for users belonging to the address space corresponding to that prefix.
  • SPAL Service Provider Access Link
  • the Decision Maker will send a significant amount of updates to the router (over a tunable period of time) until steady state is reached.
  • the network conditions can vary along the path used by the packets that correspond to that prefix on their way to their destination.
  • the access link through which the prefix is routed can go down.
  • the Service Provider to which the prefix is routed can lose coverage for that prefix.
  • the routing intelligence unit should detect the deterioration/failure, and quickly take action to alleviate its effect on the end- user.
  • the routing intelligence unit converts measurements on the performance of routes traversing the edge- routers into scores that rate the quality of the end-to-end user experience. This score depends on the application of interest, namely voice, video and HTTP web traffic.
  • the routing intelligence unit attempts to optimize the performance of web applications, so its decisions are based on a score model for HTTP.
  • the customer has the choice between all of voice, video, and HTTP.
  • the maximum rate of update permitted by the routing intelligence unit is offered as, for example, a control, such as a knob that is set by the customer.
  • a control such as a knob that is set by the customer.
  • the rate of updates should be low enough not to overwhelm the router.
  • the selected rate will depend on the customer's setting (e.g., the traffic pattern, link bandwidth, etc.); for example, faster rates are reserved to large enterprises where the number of covered prefixes is large.
  • the most urgent updates are still scheduled first: this is performed by sorting the prefix update requests in a priority queue as a function of their urgency. The priority queue is then maintained in priority order.
  • the most urgent events (such as loss of coverage, or link failure) bypass this queue and are dealt with immediately.
  • the Decision Maker may directly use the corresponding information to function in an optimized way. For example, in some embodiments of the invention, the Decision Maker can use bandwidth information to make sure that a link of lower bandwidth is not swamped by too much traffic; in a similar manner, link utilization can be used to affect the rate of BGP updates sent to the router.
  • the decision maker may use per-link cost information, as provided by the user to tailor its operation. For example, assume that the router is connected to the Internet through two links: Link 1 is a full T3, while Link 2 is a burstable T3, limited to 3 Mbit/sec. That is, whenever load exceeds the 3 Mbit/sec mark on Link 2, the user incurs a penalty cost. Combining information pertaining to per-link cost and utilization, the Decision Maker can attempt to minimize the instances in which load exceeds 3 Mbit/sec on Link 2, thus resulting in reduced costs to the user.
  • the Decision Maker may also use configurable preference weights to adjust link selection.
  • the cost of carrying traffic may vary between links, or a user may for other reasons prefer the use of certain links.
  • the Decision Maker can attempt to direct traffic away from some links and towards others by penalizing the measurements obtained on the less preferred links; conversely, if different links have comparable measured performance, traffic is directed away from the less preferred links.
  • Some embodiments of this invention can take into account more parameters, such as more information about SPALs and prefixes. However, despite the utility of such enhancements, the Decision Maker is designed to work well even when it relies on information provided by solely by the edge stats measurements.
  • the design is such that the edge router falls back to the routing that is specified in the BGP feed.
  • the same Behavior takes place in case performance routes sent by the prefix scheduler Are filtered by the edge routers it controls..
  • a flapping control algorithm is included in the design, avoiding the occurrence of undesirable excessive flapping of a prefix among the different access links.
  • FIG. 5a A diagram showing the high-level architecture of Routing Intelligence Unit, and focused on its BGP settings is shown in Figure 5a.
  • three BGP peering types may exist between a given Routing Intelligence Unit 500 and the external world: one to control the local edge router or routers 502 that this particular Routing Intelligence Unit 500 is optimizing, one to a Routing Infrastructure Exchange (RIX) 504, and one to every other Routing Intelligence Unit device with which it coordinates 506, as further described in U.S. Provisional Applications No.
  • RIX Routing Infrastructure Exchange
  • the Edge Routers 502 are both route reflectors, and the peer BGP stacks are clients, as indicated by the labels "r" and "c".
  • the BGP Process 506 is a route reflector, and the BGP Stack is a client. Note that the separation between the BGP Process 506 and BGP Stack is not required in all embodiments. However, when they are separate, the use of route reflection allows the BGP Process 506 to behave as a normal BGP implementation (as described in The Big Book of Border Gateway Protocol RFCs referenced in the Background Of The Invention). Other configurations of the devices that may be used for propagation of BGP updates will be apparent to those skilled in the art.
  • FIG. 5B schematically illustrates a configuration in which multiple routing intelligence units may coordinate via a back-channel to exchange routing information and set routing policy.
  • Each Routing Intelligence Unit includes a Decision Maker 508 510 512, which in turn controls one or more routers 514 516 518 520 522.
  • the routers 514 516 518 520 522 may in turn be coupled to one or more ISPs 524 526 528.
  • Figure 5B also illustrates the back- channel 530, comprised of peerings between processes on Remote Coordination Processors (RCPs) 532 534 536; in some embodiments, these may be iBGP or eBGP peerings.
  • RCPs Remote Coordination Processors
  • the back-channel 530 may be used to communicate information on local path performance characteristics between Routing Intelligence Units, to increase the number of paths considered during optimization.
  • Such embodiments of the invention may employ BGP environments to support coordination between routers 514 516 518 520 522; alternatively, in some embodiments, this may be accomplished without BGP, by coupling the routers together, either physically or virtually.
  • the peerings on the back-channel 530 may be iBGP peerings.
  • each of the Routing Intelligence Units sends its best local score to the others via the back-channel 530.
  • local links are preferred over equivalent remote links.
  • a Routing Intelligence Unit does not send updates directly to remote routers. Rather, remote information is assessed by the local Routing Intelligence Unit prior to being forwarded to the associated router.
  • techniques such as route reflection and confederation may be used to scale the mesh.
  • the coordination BGP processes may be arranged to match the original router BGP mesh as closely as possible, controlling each BGP router with a separate Routing Intelligence Unit. Other arrangements for the back-channel will be apparent to those skilled in the art.
  • the routers under the control of the Decision Makers 508 510 512 are able to route between themselves by use of a single IP next-hop. For instance, in the example illustrated in Figure 5B, if a first router 514 forwards packets towards an established next-hop associated with a second router 518, then the packets will arrive at the second router 518.
  • the Routing Intelligence Units coordinate by exchanging their best scores with one another.
  • a Decision Maker 508 inside a Routing Intelligence Unit can elect to send an update on the back channel 530. In some such embodiments, this may occur whenever the Decision Maker 508 is also asserting to its routers 514 516. It may also occur when the Decision Maker 508 decides the current routes are correct.
  • Decision Makers 508 510 512 may inform one another about local conditions. Additionally, if local scores change by a sufficient amount, this may be announced via the back- channel 530, even if the change in score doesn't affect local routing.
  • the BGP processes used for coordination do not peer directly to the routers 514. Rather, they connect to the Decision Maker 508, and the Decision Maker 508 decides whether to pass on the update to the routers 514 516, as well as whether to modify it.
  • the BGP process for coordination is configured so that the Decision Maker 508 is a route reflector client of the other Decision Makers 510 512.
  • the Decision Maker 508 is also a route reflector client of the edge routers it controls 514 516.
  • the Decision Makers 508 510 512 do not simply transmit information in either direction without consideration; rather, these BGP processes are separate data channels.
  • a scalar performance score exchanged between Routing Intelligence Units may be translated to units of Local Preference, where some implementations of Local Preference use 8 bits and others use 16 bits. Using Local Preference ensures that the new BGP mesh 530, or back-channel, will automatically select and propagate the best score.
  • Other embodiments of the invention implemented with BGP may transfer scalar performance scores encoded within the community attribute, the extended communities attribute, the multi-exit discriminator attribute, or some combination of all of the above.
  • Embodiments of the invention also include procedures for a Decision Maker 508 to decide whether to use a prefix which arrives via coordination with the other decision makers 510 512. Some implementations avoid use of such remote routes unless they are distinctly attractive. Thus, in such embodiments, given a choice between comparable local and remote routes (wherein 'comparable' may mean within a winner-set width), the local route is always used. Other implementations may include: • a static penalty applied to all remote announcements
  • FIG. 6 A diagram showing the high level mechanics of the decision maker prefix scheduler is shown in Figure 6.
  • two threads essentially drive the operation of the scheduler.
  • the first thread polls the database for changes in terms of per-SPAL performance, load, or coverage, and decides on which prefix updates to insert in a Priority Queue that holds prefix update requests.
  • the second thread takes items out of the queue in a rate- controlled fashion, and converts the corresponding update requests into an appropriate set of UPDATES that it sends to the local routers, and an appropriate set of UPDATES that it sends to the back channel for communication to other Routing Intelligence Units.
  • This first thread 600 polls the database for changes in terms of per- SPAL performance, load, or coverage, and decides on which prefix updates to insert in a Priority Queue that holds prefix update requests. In some embodiments of the invention, such changes are checked for in
  • the first pass looks for group level changes, wherein a group comprises an arbitrary collection of prefixes. Groups are also described in U.S. Provisional Applications No. 60/241,450, filed October 17, 2000 and U.S. Provisional Application No. 60/275,206, filed March 12, 2001, and U.S. Applications No. 09/903,441, filed July 10, 2001, U.S. Application No.
  • An update request for a prefix can be made in a number of different circumstances.
  • Non-limiting examples of such circumstances include any one or more of the following: 1) i case a significant change in its performance score is witnessed on at least one of its local SPALs. 2) In case a significant change in its performance score is witnessed on a foreign SPAL (that is, a SPAL that is controlled by a different Routing Intelligence Unit box in a coordinated system).
  • a peering with either a local or a remote router goes down, for instance, during the router's maintenance windows.
  • an asynchronous thread goes through all groups in the GROUP SPAL table, checking whether the NEWJDATA bit is set. This bit is set by the measurement listener in case a new measurement from a /32 resulted in an update of delay, jitter, and loss in the database.
  • Delay, jitter, and loss also denoted as d, v, and p, are used to compute an application-specific score, denoted by m.
  • the scalar m. is used to rate application-specific performance; MOS stands for "Mean Opinion Score", and represents the synthetic application-specific performance.
  • MOS may be multiplied by a degradation factor that is function of link utilization, resulting in m. (That is, the larger the utilization of a given SPAL, the larger the degradation factor, and the lower the resulting m)
  • users of the device may also configure penalty factors per SPAL.
  • penalty factors include handicapping some links relative to others, to achieving cost
  • Provider X may charge substantially more per unit of bandwidth than Provider Y.
  • the penalty feature allows the user to apply an m penalty to SPAL X. This will cause Provider Y to receive more traffic, except for those prefixes in which the performance of Provider X is substantially better.
  • One implementation of this embodiment is to subtract the penalty for the appropriate SPAL after m is computed. Other implementations of the penalty feature will be apparent to those skilled in the art.
  • Algorithms for calculating MOS for HTTP (1.0 and 1.1) and for voice and video are also presented in U.S. Provisional Applications No. 60/241,450, filed October 17, 2000 and U.S. Provisional Application No. 60/275,206, filed March 12, 2001 , and U.S. Applications No. 09/903,441, filed July 10, 2001, U.S. Application No. 09/923,924, filed August 6, 2001, and U.S.
  • an asynchronous thread goes through all prefixes in the PREFIX table.
  • Checks 2, 3, and 4 are made: NEW_TNCOMING_BID in the PREFIX table indicates that a new bid was received from the coordination back channel;
  • NEW_INVALID in the PREFIX_SPAL table indicates, for a particular (Prefix P, SPAL x) pair a loss of coverage for Prefix P over SPAL x.
  • NEW_NATURAL_DATA indicates the receipt by Routing Intelligence Unit of an update message from a router, notifying it of a change in its natural BGP winner.
  • the Decision Maker only asserts a performance route in case it is not the same as the natural BGP route; hence, it can potentially receive updates concerning the natural BGP winners of given prefixes from routers to which it has asserted no performance route for those prefixes.
  • the advantage of such an implementation is that when no performance route is sent to a router, the routing intelligence unit will get routing updates from that router.
  • the Routing Intelligence Unit would never receive an update from the router pertaining to changes in the natural BGP winner for the different prefixes.
  • Routing Intelligence Unit were to assert performance routes regarding a given prefix P to all routers irrespectively of the current BGP winner for that prefix, it will never receive an update from the router pertaining to changes in the natural BGP winner for Prefix P. Indeed, the performance route would always be the winner, so the router would assume there is nothing to talk about.
  • the Peer Manager sees the change in natural BGP route and sets the NEW_NATURAL_DATA flag to 1 ; consequently, the prefix is considered for re-scheduling during this pass, in Thread 1 , as described above. Note that in case of changes in the natural BGP route for a given prefix, the Decision Maker will need two passes through the Priority Queue before the prefix is routed through its appropriate performance route.
  • ACCEPTING_DATA is set to 0 by the peer manager to notify the decision maker not to assert performance routes for this prefix. This would primarily occur in case the prefix is withdrawn from the BGP tables in all local routers. In this case, in the ROUTER_PREFIX_SPAL table, the peer manager would have set the ANNOUNCED bits for that prefix on all SPALs to zero. Clearly, a prefix is only considered for insertion in the queue in case ACCEPTING_DATA is set to 1.
  • the mechanism can cope r/ this in a number of ways:
  • scheduie_pref ix includes the related functionality, described below:
  • the decision maker determines whether the current route for P is included in W.
  • the back channel is sent updates pertaining to Prefix P even if the local prefix update request is dropped. For example, the performance on local links could have changed dramatically since the last time a bid was sent to the back channel for this prefix; in the event of such an occurrence, an updated bid is sent to the back channel (through the BGP peering set up for this purpose).
  • the Routing Intelligence Unit Before going ahead and inserting an update request for Prefix P in the queue, the Routing Intelligence Unit performs a check of the flapping history for Prefix P. In case this check shows that Prefix P has an excessive tendency to flap, no prefix update request is inserted in the queue. • In some embodiments of the invention, before the prefix is inserted in the queue, a SPAL is chosen at random from the winner set. In case the winner set includes a remote SPAL controlled by a coordinated Routing
  • the local SPAL is always preferred.
  • the randomness may be tweaked according to factors pertaining to any one or more of the following: link bandwidth, link cost, and traffic load for a given prefix.
  • Bids from remote SPALs under the control of coordinated Routing Intelligence Units may, in embodiments, be included in the winner set computation. Since the bids corresponding to such remote routes are filtered through BGP, they are in units which are compatible with iBGP's LocalPref, which in some implementations is limited to 0-255. Therefore one possible implementation is to multiply m by 255. The converted quantity is referred to as MSLP. For consistency, the m values computed for local SPALs are also converted to local_pref units.
  • the new winner is then determined to be the set of all SPALs for which MSLP is larger than MSLPmax - winner-set-threshold, where MSLP max represents the maximum MSLP for that prefix across all available SPALs, and winner-set-threshold represents a customer-tunable threshold specified in LocalPref units.
  • MSLP max represents the maximum MSLP for that prefix across all available SPALs
  • winner-set-threshold represents a customer-tunable threshold specified in LocalPref units.
  • the decision maker determines whether the current route for P is included in W. Indeed, in such a case, the performance of that prefix can't be improved much further, so no prefix update request needs to be inserted in the queue.
  • the Decision Maker may still send an update to the back channel in certain embodiments. For example, even though the current route for Prefix P is still part of the winner set, performance degradation could have affected all SPALs at once, in which case the bid that was previously sent to the back channel for Prefix P is probably inaccurate.
  • one may solve this problem by implementing the following: the last bid for a given prefix is saved as MYJBID in the PREFIX table; a low and high threshold are then computed using two user-configurable parameters, bid-threshold-low and bid- threshold- high.
  • prefix router
  • ROUTER_PREFIX_SPAL table send urgent withdrawal of this route to edge router continue 15 ⁇ get current_winner (prefix) and pending_winner (prefix) from prefix_spal table
  • the Routing Intelligence Unit before proceeding with sending the update request to the edge router, the Routing Intelligence Unit performs a check of the flapping history for Prefix P.
  • An algorithm whose operation is very close to the flapping detection algorithm in BGP monitors the flapping history of a prefix.
  • the algorithm can be controlled by, in one embodiment, three user-controlled parameters f iap_weight, f ap_iow, and f iap_high and works as follows: the tendency of a prefix to flap is monitored by a variable denoted
  • FORGIVING_MODE that resides in the PREFLX table.
  • FORGTVING_MODE and other flapping parameters are updated in Thread 2 right before a performance route pertaining to Prefix P is asserted to the local routers.
  • FORGIVINGJMODE is set to 1 , the tendency for Prefix P to flap is considered excessive, and the prefix update request is ignored. Conversely, in case
  • FORGIVINGJvlODE is set to 0
  • Prefix P has no abnormal tendency to flap, so it is safe to consider its update request.
  • a SPAL is chosen at random from the winner set. This way, traffic is spread across more than one SPAL, hence achieving some level of load balancing.
  • randomness can be tweaked in order to favor some SPALs and disregard others.
  • the winner set includes a remote SPAL controlled by a coordinated Routing Intelligence Unit as well as a local SPAL
  • the local SPAL is always preferred. In other words, a remote SPAL is only the winner in case it is the only available SPAL in the winner set.
  • the rank of the prefix update in the priority queue is determined by computing the percent improvement; that is, the percent improvement obtained from moving the prefix from its current route to the pending winner route.
  • percent-improvement [score(pending_winner) - Score(cu ⁇ ent_iOute)]/Score(current_route).
  • the special-spal-flag is part of the data structure for the update, as it will be used in the determination of which messages to send to the local routers.
  • elements are taken out of the queue in a rate- controlled manner.
  • this rate is specified by the customer.
  • the update rate is often referred to as the token rate.
  • Tokens are given at regular intervals, according to the update rate. Each time a token appears, the head of the queue is taken out of the queue, and considered for potential update. In case the database shows that more recent passes in Thread 1 have canceled the update request, it is dropped without losing the corresponding loken; the next update request is then taken out from the head of the queue; this procedure is performed until either the queue empties, or a valid request is obtained.
  • an update request that corresponds to Prefix P is determined to be current (thus, valid)
  • one or more of the following tasks are performed: The flapping state is updated for Prefix P.
  • the database is updated to reflect the new actual winner; more specifically, the pending winner, chosen before inserting the prefix update request at the end of the first thread now becomes the current winner.
  • the database is checked to determine the current state of each of the individual routers. Accordingly, individual UPDATES are formed and sent to each of the routers. For example, no performance route is sent to an edge router
  • elements are just taken out from the queue in a rate- controlled manner, according to an update rate that may be set by the customer.
  • the update rate is often referred to as the token rate: indeed, tokens are given at regular intervals, according to the update rate. Each time a token appears, the head of the queue is taken out, and considered for potential update.
  • the Decision Maker should assert the winning route for Prefix P.
  • a prefix update request is considered still valid, it is implemented.
  • a series of tasks are performed.
  • the flapping state is updated for Prefix P.
  • the tendency of a prefix to flap is monitored by a variable denoted INTERCHANGE_RATE that resides in the PREFIX table.
  • the f ia P _wei g ht parameter dictates the dynamics of 1NTERCHANGE_RATE; more specifically, at this point in the algorithm thread, INTERCHANGE_RATE is updated using the last value of INTERCHANGEJ ATE, as stored in the table,
  • Routing Intelligence Unit considers the tendency for that prefix to flap to be low.
  • TNTERCHANGEJRATE exceeds f ia P _high, the Routing Intelligence Unit considers the tendency for that prefix to flap to be high. That is, the algorithm functions in the following fashion:
  • FORGlVING_MODE (also in the PREFIX table) is set to 0, and INTERCHANGEJIATE exceeds f iap_hi g h, FORGIVING_MODE is set to 1.
  • FORGIVING_MODE is set to 1 , but TNTERCHANGEJRATE drops below f lap_low, FORGIVINGJVIODE is set to 0 again, and the prefix update request survives this Gheck. .
  • FORGIVING_MODE is set to 1 and TNTERCHANGEJRATE is larger than f iap_iow, or FORGIVING_MODE is set to 0, and INTERCHANGEJIATE is below f ia P _high, FORGIVING_MODE does not change. Note that the method presented above is only one technique for controlling flapping; others will be apparent to those skilled in the art.
  • the two parameters f iap_iow, and f iap_high are separated by an amount to avoid hysteresis between the two values.
  • the Decision Maker updates the PKLFIXJSPAL table to reflect this change; more specifically, CURRENT_WINNER is moved to PENDING_WINNER in the table.
  • the ROUTER_PREFIX_SPAL table is queried to capture the current state of each router in regards to Prefix P. Accordingly, different UPDATES are formed and sent to each of the routers.
  • the Decision Maker only asserts a performance route in case it is not the same as the natural BGP route; indeed, if Routing Intelligence Unit were to assert performance routes regarding a given prefix P to all routers irrespectively of the current BGP winner for that prefix, it will never receive an update from the router pertaining to changes in the natural BGP winner for Prefix P. (Indeed, the performance route would always be the winner, so the router would assume there is nothing to talk about.) Also, an UPDATE is sent to the back channel, describing to other
  • Routing Intelligence Units in a coordinated system the new local winner.
  • the database is updated to keep track of the messages that were sent to each of the routers, as well as the expected resulting state of these routers.
  • the database Prior to forming the UPDATES, the database is updated as to include the new flap parameters and prefix-SPAL information (i.e., the new current SPAL for that prefix).
  • the BGP update sent to an edge router may be filtered out by policy on the router. However, assuming the update is permissible, it may be made to win in the router's BGP comparison process.
  • One implementation is to have the edge router to apply a high Weight value to the incoming update.
  • a maximum queue size is to be chosen by the customer.
  • a small queue size may be chosen, so the maximum delay involved between the time instant a prefix update request is queued and the time instant it is considered by the second thread as a potential BGP update is small. For example, in case the token rate corresponding to a given link is 10 tokens per second, and we choose not to exceed a 2 second queuing delay, the queue should be able to accommodate 20 prefix update requests. Note that this method is simple, and only requires the knowledge of the token rate and the maximum acceptable delay.
  • Routing Intelligence Unit It is desirable for the Routing Intelligence Unit to remain conservative in the rate of updates it communicates to the edge-router. This is the function of the token rate, which acts as a brake to the whole system. In some embodiments of the invention, the responsibility for setting the token rate is transferred to the customer, who selects a token rate that best fits her bandwidth and traffic pattern.
  • a separate routing intelligence unit thread modifies the content of the database according to the state it gets from the router(s).
  • the Routing Intelligence Unit can operate more subtly in case it is a. perfect listener, we consider the Routing Intelligence Unit to be a perfect listener if it has knowledge of the individual BGP feeds from each individual SPAL. That is, in case the Routing Intelligence Unit is connected to three access links, each connecting to a separate provider, the Routing Intelligence Unit is a perfect listener if it has access to each of the three feeds handed by each of these providers.
  • Routing Intelligence Unit as a Perfect Listener is desirable, as it allows the support of private peerings. For example, unless Routing Intelligence Unit is configured as a Perfect listener, when Routing Intelligence Unit hears about a prefix, it can't assume that coverage exists for that prefix across all SPALs. Considering the scenario described above, a prefix that the Routing Intelligence Unit learns about could be covered by any of the three
  • Routing Intelligence Unit asserts a performance route for that prefix across SPAL 2, there is no guarantee that the traffic pertaining to that prefix will be transited by the Service Provider to which SPAL 2 is connected (which we denote Provider 2).
  • Provider 2 actually has a private peering with Provider X that obeys to some pre-specified contract, Provider X could well monitor the traffic from Provider 2, and filter all packets that do not conform to that contract. In case this contract namely specifies that Provider X will only provide transit to customers residing on Provider X's network, then the traffic pertaining to Prefix P will be dropped. If Routing Intelligence Unit were a Perfect Listener, it would only assert performance routes for prefixes across SPALs that are determined to have coverage for these prefixes. This behavior may be referred to as "extremely polite".
  • the Routing Intelligence Unit is capable of avoiding the "Rocking the boat” problem, which stems from unwanted propagation of prefixes which did not already exist in BGP.
  • An Intelligence Unit can operate in "impolite” mode, where any prefixes may be used, or in "polite” mode, where only those prefixes which were previously present in BGP can be used.
  • An ANNOUNCED bit resides in the ROUTER JPREFD JSPAL table, and is set by the Peer Manager in case the Routing Intelligence Unit hears about a prefix from any of the Routers. This bit allows use of "polite” mode by the following procedure: in case the ANNOUNCED bit is set to 0 for all (router, SPAL) combinations in the ROUTER_ PREFL _SPAL table, then ACCEPTING_DATA is set to 0 in the PREFLX table.
  • some embodiments of the invention send urgent BGP updates to the router. These urgent updates have priority over the entire algorithm described above. For example, in case a SPAL has lost coverage for a prefix, an urgent BGP message should be sent to the router, requesting to move the prefix to other SPALs. A list of urgent events upon which such actions may be taken, and a description of the algorithms pertaining to these actions, are described below.
  • a specific (Prefix P, SPAL x) pair is invalidated in case there are reasons to believe that SPAL x no longer provides coverage to Prefix P.
  • One possible implementation is described as follows. Measurements corresponding to a (Prefix, SPAL) pair are assumed to arrive to the Decision Maker at something close to a predictable rate. A background thread that is independent from Threads 1 and 2 computes this update rate, and stores a time of last update, the LAST_UPDATE_TIME.
  • LAST_ICR_TIME is reasonable given UPDATE_RATE. For example, assuming that measurements come in following a Poisson distribution, it is easy to verify whether LAST_ICR_TIME exceeds a fixed percentile of the inter-arrival interval. As LASTJ PDATEJTIME increases, the Decision Maker becomes more and more concerned about the validity of the path. In the current design, there are two thresholds: at the first threshold, the NEW NVALID and INVALID flags are set in the PREFIXJSPAL table. As described in Thread 1 above, setting the NEW_TNNALID flag for a (Prefix P, SPAL x) pair will prevent any new update requests for Prefix P to be routed through SPAL x.
  • the Decision Maker becomes "very concerned" about routing Prefix P through SPAL x; hence, an urgent check is made to see whether Prefix P is currently routed through SPAL x, in which case an urgent UPDATE is created (that is, an UPDATE that bypasses the entire queue system) in order to route Prefix through a different SPAL.
  • Some embodiments of the invention support a Saturation Avoidance Factor, which measures the effect of a prefix on other prefixes.
  • the "Saturation Avoidance Factor" (SAF) pertaining to a given prefix may be taken into account when prefixes are sorted in the Priority Queue.
  • This SAF measures the effect of a prefix on other prefixes. That is, if, upon scheduling a prefix on a given link, its effect on the other prefixes already scheduled on that link is high (i.e., this effectively means that the aggregate load for this prefix is large), its SAF should be low. The lower the SAF of a prefix, the lower its place in the Priority Queue. This way, the algorithm will always favor low load prefixes rather than high load prefixes.
  • the SAF is not directly proportional to load. For example, a prefix that has a load equal to 0.75C has a different SAF whether it is considered to be scheduled on an empty link or on a link which utilization has already reached 75%. In the later case, the SAF should be as low as possible, since scheduling the prefix on the link would result in a link overflow.
  • the token rate may be slower than the responded feedback.
  • the token rate may be slower than the rate at which utilization information comes in.
  • the token rate may be slower than the rate at which edge-stats measurements come in.
  • each prefix is considered at a time. That is, PQServiceRate is small enough so that no more than one token is handed at a time. For example, denoting by T the token rate obtained from the above considerations, PQServiceRate is equal to ⁇ IT. If more than one token were handed at one time, two large prefixes could be scheduled on the same link, just as in the example above, potentially leading to bad performance.
  • the SAF is a per-prefix, per- SPAL quantity.
  • a prefix carries with it a load of 75% the capacity of all SPALs. If we have a choice between two SPALs, SPAL 1 and SPAL 2, SPAL 1 already carrying a load of 50 %, the other having a load of 0%. In this case, moving Prefix p to SPAL 1 will result in bad performance not only for itself, but also for all other prefixes already routed through SPAL 1. In this case, the SAF is close to 0, even if performance data across SPAL 1 seems to indicate otherwise.
  • the SAF of moving Prefix p to SPAL 2 is, by contrast, very good, since the total load on the link will remain around 75% of total capacity, so delays will remain low. If, instead of carrying a load of 75%o capacity, Prefix p carried a load of 10% capacity, the results would have been different, and the SAF of Prefix p across SPALs 1 and 2 would have been close.
  • the schema may be include a load field in the SPAL table, and an SAF field in the PREFIX_SPAL table.
  • the SAF field is a per-prefix, per-SPAL information.
  • Edge-stats measurements may include measurements of delay, jitter, and loss; using these measurements, an application-specific performance score may be obtained based on which a decision is made on whether to send an update request for this prefix. Available bandwidth is a valuable quantity that is measured and included in the computation of the performance score in some embodiments of the invention.
  • token rates may differ on a per- link basis (which dictates the use of different queues for each link).
  • the token rate may be tailored to total utilization. Lowly utilized links can afford relatively higher token rates without fear of overflow, whereas links close to saturation should be handled more carefully.
  • Some embodiments of the invention provide one or more of the following modes of operation: 1.
  • the default mode the user specifies one token rate (and, optionally, a bucket size), shared equally among the prefixes updates destined to the different links.
  • the enhanced performance mode the user specifies a minimum token rate (and, optionally, a bucket size). Depending on factors such as the total bandwidth utilization and the bandwidth of individual links, the prefix scheduler takes the initiative to function at a higher speed when possible, allowing better performance when it is not dangerous to do so.
  • the custom mode in this case, the user can specify minimum and maximum token rates (and, optionally, bucket sizes), as well as conditions on when to move from a token rate to another. Using this custom mode, customers can tailor the prefix scheduler to their exact need.
  • the priority queue is sized in such a way that the delay spent in the queue is minimized, there is still an order of magnitude between the time scale of the BGP world, at which level decisions are taken, and the physical world, in which edge stats and interface stats are measured. That is, even though the queuing delay is comparable to other delays involved in the process of changing a route, prefix performance across a given link or the utilization of a given link can change much more quickly. For example, a 2 second queuing delay could be appropriate in the BGP world, while 2 seconds can be enough for congestion to occur across a given link, or for the link utilization to go from 25% to 75%... For this reason, in some embodiments of the invention, the winner set is re-evaluated at the output of the priority queue.

Abstract

Systems and methods are described for enabling routers to coordinate via a back-channel communication medium. The information exchanged over the back-channel is used to increase the number of paths considered for the routers during route optimization. The Decision Makers may assert routes and prefixes to the routers under their control. This may be done via a Border Gateway Protocol (BGP) feed. The Decision Makers, in turn, communicate separately with one another, in order to coordinate routing policy amongst themselves. This coordination may be performed over a back-channel, which may take the form of physical or logical connections between the Decision Makers.

Description

METHOD AND APPARATUS FOR COORDINATING ROUTING PARAMETERS VIA A BACK-CHANNEL COMMUNICATION
MEDIUM
BACKGROUND OF THE INVENTION
Field of the Invention
This invention relates to the field of networking. In particular, the invention relates to systems and methods for coordinating routing information amongst routers. Description of the Related Art Internetworks such as the Internet are currently comprised of
Autonomous Systems, which exchange routing information via exterior gateway protocols. Amongst the most important of these protocols is the Border Gateway Protocol, or BGP. BGPv4 constructs a directed graph of the Autonomous Systems, based on the information exchanged between BGP routers. Each Autonomous System is identified by a unique 16 bit AS number, and BGP ensures loop-free routing amongst the Autonomous Systems; BGP also enables the exchange of additional routing information between Autonomous Systems. BGP is further described in several RFCs, which are compiled in The Big Book of Border Gateway Protocol RFCs. by Pete Loshin, which is hereby incorporated by reference.
The Border Gateway Protocol provides network administrators some measure of control over outbound traffic control from their respective organizations. For instance, the protocol includes a LOCAL_PREF attribute, which allows BGP speakers to inform other BGP speakers within the Autonomous System of the speaker's preference for an advertised route. The local preference attribute includes a degree of preference for the advertised route, which enables comparison against other routes for the same destination. As the LOCAL_PREF attribute is shared with other routers within an Autonomous System via IBGP, it determines outbound routes used by routers within the Autonomous System.
A WEIGHT parameter may also be used to indicate route preferences; higher preferences are assigned to routes with higher values of WEIGHT. The WEIGHT parameter is a proprietary addition to the BGPv4 supported by Cisco Systems, Inc. of San Jose, CA. In typical implementations, the WEIGHT parameter is given higher precedence than other BGP attributes.
The performance knobs described above are, however, rather simple, as they do not offer system administrators with sufficiently sophisticated means for enabling routers to discriminate amongst routes. There is a need for technology that enables greater control over outbound routing policy. In particular, there is a need to allow performance data about routes to be exchanged between routers. Additionally, system administrators should be able to fine tune routing policy based upon sophisticated, up-to-date measurements of route performance and pricing analysis of various routes.
SUMMARY OF THE INVENTION
The invention includes systems and methods for enabling networking devices to coordinate via a back-channel communication medium. The information exchanged over the back-channel is used to increase the number of paths considered for the routers during route optimization.
In embodiments of the invention, a set of Routing Intelligence Units may be used to control a set of routers, such that each Routing Intelligence Unit controls a distinct subset of the routers. The Routing Intelligence Units may assert routes to the routers under their control. In some embodiments, this is done via a Border Gateway Protocol (BGP) feed. The Decision Makers, in turn, communicate separately with one another, in order to coordinate routing policy amongst themselves. This coordination may be performed over a back-channel, which may take the form of physical or logical connections between the Routing Intelligence Units. In some embodiments, communications over the back-channel are conducted via separate BGP sessions. In embodiments utilizing BGP for communication to the routers and the back-channel, the Routing Intelligence Unit may be configured as a route-reflector client to both other decision makers and the routers it controls. This ensures that the Routing Intelligence Unit does not simply transmit information in either direction without consideration.
In some embodiments of the invention, a Routing Intelligence Unit send updates to other Routing Intelligence Units whenever the Routing Intelligence Unit is also asserting to the routers under its control. In alternative embodiments, the Routing Intelligence Unit may send updates when it decides that the current routes are correct. In some embodiments of the invention, performance scores for prefixes are communicated between Routing Intelligence Units. In some of the embodiments utilizing BGP for such coordination, these performance scores are translated to units of Local Preference. This ensures that the Routing Intelligence Units will automatically select and propagate the best score. Some embodiments of the invention include techniques enabling
Routing Intelligence Units to evaluate prefixes that arrive via coordination. In some embodiments, when local and remote routes have comparable scores, the local route is chosen by default. In other embodiments, a static penalty is applied to all remote announcements. In some embodiments, dynamic penalties are applied. These and other embodiments are described in greater detail infra.
BRIEF DESCRIPTION OF THE FIGURES
Fig. 1 - Fig.4 illustrate different configurations of routing intelligence units and edge routers, according to some embodiments of the invention.
Figure 5a schematically illustrates an internal architecture of a routing intelligence unit according to some embodiments of the invention.
Figure 5b illustrates coordination between routing intelligence units via a back-channel according to embodiments of the invention.
Figure 6 illustrates a queuing and threading structure used in the routing intelligence unit in some embodiments of the invention.
DETAILED DESCRIPTION
A. System Overview
In some embodiments of the invention, one or more routing intelligence units are stationed at the premises of a multi-homed organization, each of which controls one or more edge routers. These devices inject BGP updates to the Edge Routers they control, based on performance data from measurements obtained locally, or from a Routing Intelligence Exchange— Routing Intelligence Exchanges are further described in U.S. Provisional Applications No. 60/241,450, filed October 17, 2000 and U.S. Provisional Application No. 60/275,206, filed March 12, 2001, and U.S. Applications No. 09/903,441, filed
July 10, 2001 , U.S. Application No. 09/923,924, filed August 6, 2001, and U.S. Application No. 09/903,423, filed July 10, 2001, which are hereby incorporated by reference in their entirety. Different configurations of these routing intelligence units and edge routers are illustrated in Figures 1 through 4. In some embodiments illustrated in Figure 1, one edge router 102 with multiple
ISPs 104 and 106 is controlled by a single device 100. Figure 2 illustrates embodiments in which the routing intelligence unit 200 controls multiple edge routers 202 and 204, each of which in turn links to multiple ISPs 206, 208, 210, and 212; Figure 2 also illustrates embodiments in which routers 203 205 controlled by the routing intelligence unit 200 are not coupled to SPALs. In
Figure 3, a single routing intelligence unit 300 controls multiple edge routers 302 and 304, each of which is linked to exactly one ISP 306 and 308. In additional embodiments illustrated in Figure 4, different routing intelligence units 400 and 402, each connected to a set of local edge routers 404, 406, 408, and 410, may coordinate their decisions. In some embodiments of the invention, the routing intelligence units comprise processes running within one or more processors housed in the edge routers. Other configurations of routing intelligence units and edge routers will be apparent to those skilled in the art.
B. Architecture of Routing Intelligence Units
The routing intelligence units include a Decision Maker resource. At a high level, the objective of the Decision Maker is to improve the end-user, application level performance of prefixes whenever the differential in performance between the best route and the default BGP route is significant. This general objective has two aspects: • One goal is to reach a steady state whereby prefixes are, most of the time, routed through the best available Service Provider Access Link (i.e., SPAL), that is, through the SPAL that is the best in terms of end- to-end user performance for users belonging to the address space corresponding to that prefix. To achieve this goal, the Decision Maker will send a significant amount of updates to the router (over a tunable period of time) until steady state is reached. This desirable steady state results from a mix of customer-tunable criteria, which may include but are not limited to end-to-end user measurements, load on the links, and/or cost of the links. • Current measurements of end-to-end user performance on the Internet show that fluctuations in performance are frequent. Indeed, the reasons for deterioration of performance of a prefix may include, but are not limited to the following:
The network conditions can vary along the path used by the packets that correspond to that prefix on their way to their destination. Alternatively, the access link through which the prefix is routed can go down.
The Service Provider to which the prefix is routed can lose coverage for that prefix. In such occurrences, the routing intelligence unit should detect the deterioration/failure, and quickly take action to alleviate its effect on the end- user.
In order to optimize application performance, the routing intelligence unit converts measurements on the performance of routes traversing the edge- routers into scores that rate the quality of the end-to-end user experience. This score depends on the application of interest, namely voice, video and HTTP web traffic. In some embodiments of the invention, by default, the routing intelligence unit attempts to optimize the performance of web applications, so its decisions are based on a score model for HTTP. However, in such embodiments, the customer has the choice between all of voice, video, and HTTP.
In order to avoid swamping routers with BGP updates, in some embodiments of the invention, the maximum rate of update permitted by the routing intelligence unit is offered as, for example, a control, such as a knob that is set by the customer. The faster the rate of updates, the faster the system can react in the event of specific performance deteriorations or link failures.
However, the rate of updates should be low enough not to overwhelm the router. In some embodiments, the selected rate will depend on the customer's setting (e.g., the traffic pattern, link bandwidth, etc.); for example, faster rates are reserved to large enterprises where the number of covered prefixes is large. Even when the rate of updates is slow, in some embodiments of the invention, the most urgent updates are still scheduled first: this is performed by sorting the prefix update requests in a priority queue as a function of their urgency. The priority queue is then maintained in priority order. In some embodiments of the invention, the most urgent events (such as loss of coverage, or link failure) bypass this queue and are dealt with immediately.
In case interface statistics are available, the Decision Maker may directly use the corresponding information to function in an optimized way. For example, in some embodiments of the invention, the Decision Maker can use bandwidth information to make sure that a link of lower bandwidth is not swamped by too much traffic; in a similar manner, link utilization can be used to affect the rate of BGP updates sent to the router. Finally, the decision maker may use per-link cost information, as provided by the user to tailor its operation. For example, assume that the router is connected to the Internet through two links: Link 1 is a full T3, while Link 2 is a burstable T3, limited to 3 Mbit/sec. That is, whenever load exceeds the 3 Mbit/sec mark on Link 2, the user incurs a penalty cost. Combining information pertaining to per-link cost and utilization, the Decision Maker can attempt to minimize the instances in which load exceeds 3 Mbit/sec on Link 2, thus resulting in reduced costs to the user.
In some implementations, the Decision Maker may also use configurable preference weights to adjust link selection. The cost of carrying traffic may vary between links, or a user may for other reasons prefer the use of certain links. The Decision Maker can attempt to direct traffic away from some links and towards others by penalizing the measurements obtained on the less preferred links; conversely, if different links have comparable measured performance, traffic is directed away from the less preferred links. Some embodiments of this invention can take into account more parameters, such as more information about SPALs and prefixes. However, despite the utility of such enhancements, the Decision Maker is designed to work well even when it relies on information provided by solely by the edge stats measurements.
In case the routing intelligence unit fails, the design is such that the edge router falls back to the routing that is specified in the BGP feed. The same Behavior takes place in case performance routes sent by the prefix scheduler Are filtered by the edge routers it controls.. Finally, in some embodiments of the invention, a flapping control algorithm is included in the design, avoiding the occurrence of undesirable excessive flapping of a prefix among the different access links.
A diagram showing the high-level architecture of Routing Intelligence Unit, and focused on its BGP settings is shown in Figure 5a. In the embodiments illustrated in Figure 5a, three BGP peering types may exist between a given Routing Intelligence Unit 500 and the external world: one to control the local edge router or routers 502 that this particular Routing Intelligence Unit 500 is optimizing, one to a Routing Infrastructure Exchange (RIX) 504, and one to every other Routing Intelligence Unit device with which it coordinates 506, as further described in U.S. Provisional Applications No.
60/241,450, filed October 17, 2000 and U.S. Provisional Application No. 60/275,206, filed March 12, 2001, U.S. Applications No. 09/903,441 , filed July 10, 2001, U.S. Application No. 09/923,924, filed August 6, 2001, and U.S. Application No. 09/903,423, filed July 10, 2001, which are hereby incorporated by reference in their entirety. In the diagram shown in Figure 5a, the three external peering types are shown as the arrows at far left (to the Edge Routers 502 and to RIX 504) and far right 506. In order for BGP updates to be propagated to the appropriate devices, some devices are configured to be route reflectors, and others as route reflector clients. In embodiments illustrated in Figure 5a, the Edge Routers 502 are both route reflectors, and the peer BGP stacks are clients, as indicated by the labels "r" and "c". Similarly, in the peering between the BGP Process 506 and the BGP Stack, the BGP Process 506 is a route reflector, and the BGP Stack is a client. Note that the separation between the BGP Process 506 and BGP Stack is not required in all embodiments. However, when they are separate, the use of route reflection allows the BGP Process 506 to behave as a normal BGP implementation (as described in The Big Book of Border Gateway Protocol RFCs referenced in the Background Of The Invention). Other configurations of the devices that may be used for propagation of BGP updates will be apparent to those skilled in the art.
C. Coordination Between Routing Intelligence Units
Figure 5B schematically illustrates a configuration in which multiple routing intelligence units may coordinate via a back-channel to exchange routing information and set routing policy. Each Routing Intelligence Unit includes a Decision Maker 508 510 512, which in turn controls one or more routers 514 516 518 520 522. The routers 514 516 518 520 522 may in turn be coupled to one or more ISPs 524 526 528. Figure 5B also illustrates the back- channel 530, comprised of peerings between processes on Remote Coordination Processors (RCPs) 532 534 536; in some embodiments, these may be iBGP or eBGP peerings. Other implementations will be apparent to those skilled in the art. The back-channel 530, or mesh, may be used to communicate information on local path performance characteristics between Routing Intelligence Units, to increase the number of paths considered during optimization. Such embodiments of the invention may employ BGP environments to support coordination between routers 514 516 518 520 522; alternatively, in some embodiments, this may be accomplished without BGP, by coupling the routers together, either physically or virtually. In embodiments of the invention utilizing BGP environments for coordination, the peerings on the back-channel 530 may be iBGP peerings.
In some embodiments of the invention, each of the Routing Intelligence Units sends its best local score to the others via the back-channel 530. In some such embodiments, local links are preferred over equivalent remote links. Additionally, in some such embodiments, a Routing Intelligence Unit does not send updates directly to remote routers. Rather, remote information is assessed by the local Routing Intelligence Unit prior to being forwarded to the associated router.In embodiments of the back-channel 530 utilizing BGP, techniques such as route reflection and confederation may be used to scale the mesh. In one such embodiment, the coordination BGP processes may be arranged to match the original router BGP mesh as closely as possible, controlling each BGP router with a separate Routing Intelligence Unit. Other arrangements for the back-channel will be apparent to those skilled in the art.
In some embodiments of the invention, the routers under the control of the Decision Makers 508 510 512 are able to route between themselves by use of a single IP next-hop. For instance, in the example illustrated in Figure 5B, if a first router 514 forwards packets towards an established next-hop associated with a second router 518, then the packets will arrive at the second router 518.
In some embodiments, the Routing Intelligence Units coordinate by exchanging their best scores with one another. In some implementations, a Decision Maker 508 inside a Routing Intelligence Unit can elect to send an update on the back channel 530. In some such embodiments, this may occur whenever the Decision Maker 508 is also asserting to its routers 514 516. It may also occur when the Decision Maker 508 decides the current routes are correct. By exchanging information via the back channel 530, Decision Makers 508 510 512 may inform one another about local conditions. Additionally, if local scores change by a sufficient amount, this may be announced via the back- channel 530, even if the change in score doesn't affect local routing. In embodiments of the invention, the BGP processes used for coordination do not peer directly to the routers 514. Rather, they connect to the Decision Maker 508, and the Decision Maker 508 decides whether to pass on the update to the routers 514 516, as well as whether to modify it. In some embodiments of the invention, the BGP process for coordination is configured so that the Decision Maker 508 is a route reflector client of the other Decision Makers 510 512. The Decision Maker 508 is also a route reflector client of the edge routers it controls 514 516. Thus, in such embodiments, the Decision Makers 508 510 512 do not simply transmit information in either direction without consideration; rather, these BGP processes are separate data channels.
In embodiments of coordination implemented with BGP, a scalar performance score exchanged between Routing Intelligence Units may be translated to units of Local Preference, where some implementations of Local Preference use 8 bits and others use 16 bits. Using Local Preference ensures that the new BGP mesh 530, or back-channel, will automatically select and propagate the best score. Other embodiments of the invention implemented with BGP may transfer scalar performance scores encoded within the community attribute, the extended communities attribute, the multi-exit discriminator attribute, or some combination of all of the above.
Embodiments of the invention also include procedures for a Decision Maker 508 to decide whether to use a prefix which arrives via coordination with the other decision makers 510 512. Some implementations avoid use of such remote routes unless they are distinctly attractive. Thus, in such embodiments, given a choice between comparable local and remote routes (wherein 'comparable' may mean within a winner-set width), the local route is always used. Other implementations may include: • a static penalty applied to all remote announcements
• a static penalty per remote Decision Maker
• a static penalty per remote SPAL
• dynamic penalties per remote Decision Maker
In the case of dynamic penalties per Decision Maker, it is possible to have one Decision Maker 508 probe all others 510 512 actively, and use the measure of distance between Routing Intelligence Units as a dynamic penalty. Other methodologies for implementing dynamic penalties will be apparent to those skilled in the art.
D. Queuing Architecture
A diagram showing the high level mechanics of the decision maker prefix scheduler is shown in Figure 6. As illustrated in Figure 6, two threads essentially drive the operation of the scheduler. The first thread polls the database for changes in terms of per-SPAL performance, load, or coverage, and decides on which prefix updates to insert in a Priority Queue that holds prefix update requests. The second thread takes items out of the queue in a rate- controlled fashion, and converts the corresponding update requests into an appropriate set of UPDATES that it sends to the local routers, and an appropriate set of UPDATES that it sends to the back channel for communication to other Routing Intelligence Units.
In the following, we describe each thread separately. In the description, we will refer to tables in the database, and to fields within these tables. The contents of this database are also explicated in U.S. Provisional Applications
No. 60/241,450, filed October 17, 2000 and U.S. Provisional Application No. 60/275,206, filed March 12, 2001, and U.S. Applications No. 09/903,441 , filed July 10, 2001, U.S. Application No. 09/923,924, filed August 6, 2001, and U.S. Application No. 09/903,423, filed July 10, 2001, which are hereby incorporated by reference in their entirety.
Thread 1
This first thread 600 polls the database for changes in terms of per- SPAL performance, load, or coverage, and decides on which prefix updates to insert in a Priority Queue that holds prefix update requests. In some embodiments of the invention, such changes are checked for in
2 passes. The first pass looks for group level changes, wherein a group comprises an arbitrary collection of prefixes. Groups are also described in U.S. Provisional Applications No. 60/241,450, filed October 17, 2000 and U.S. Provisional Application No. 60/275,206, filed March 12, 2001, and U.S. Applications No. 09/903,441, filed July 10, 2001, U.S. Application No.
09/923,924, filed August 6, 2001, and U.S. Application No. 09/903,423, filed July 10, 2001, which are hereby incorporated by reference in their entirety. In case a significant change in performance for a group is noticed, the group is unpacked into its individual prefixes; the corresponding prefixes are checked and considered for insertion in the priority queue. The second pass captures prefixes for which there are no group-level performance changes.
An update request for a prefix can be made in a number of different circumstances. Non-limiting examples of such circumstances include any one or more of the following: 1) i case a significant change in its performance score is witnessed on at least one of its local SPALs. 2) In case a significant change in its performance score is witnessed on a foreign SPAL (that is, a SPAL that is controlled by a different Routing Intelligence Unit box in a coordinated system).
3) In case any of the local SPALs becomes invalid. 4) In case an update pertaining to this prefix was received from the router.
5) A peering with either a local or a remote router goes down, for instance, during the router's maintenance windows.
6) At the user's request.
Note that measurements reside at the group level; hence, Check 1 can be done in the first pass. On the other hand, all of Checks 2, 3, and 4 are prefix-specific and may be performed in Pass 2: indeed, foreign performance updates are transferred through the back channel in BGP messages, and hence correspond to particular prefixes. Also, SPALs may become invalid for some, and not necessary all prefixes in a group. Finally, updates from the router relate to the change of winner SPALs for some prefixes, or to the withdrawal of other prefixes. (In fact, any information that is transferred by BGP relates to prefixes.)
Pass 1 :
In some embodiments of the invention, in the first pass, an asynchronous thread goes through all groups in the GROUP SPAL table, checking whether the NEWJDATA bit is set. This bit is set by the measurement listener in case a new measurement from a /32 resulted in an update of delay, jitter, and loss in the database. Delay, jitter, and loss, also denoted as d, v, and p, are used to compute an application-specific score, denoted by m. The scalar m. is used to rate application-specific performance; MOS stands for "Mean Opinion Score", and represents the synthetic application-specific performance. In embodiments of the invention, MOS may be multiplied by a degradation factor that is function of link utilization, resulting in m. (That is, the larger the utilization of a given SPAL, the larger the degradation factor, and the lower the resulting m) In embodiments of the invention, users of the device may also configure penalty factors per SPAL. Non-limiting examples of the uses of such penalty features include handicapping some links relative to others, to achieving cost
1 ? control, or accomplishing other policy objectives. As a non-limiting example, Provider X may charge substantially more per unit of bandwidth than Provider Y. In such a situation, the penalty feature allows the user to apply an m penalty to SPAL X. This will cause Provider Y to receive more traffic, except for those prefixes in which the performance of Provider X is substantially better. One implementation of this embodiment is to subtract the penalty for the appropriate SPAL after m is computed. Other implementations of the penalty feature will be apparent to those skilled in the art.
Even when NEWJDATA is set, the variation in d, v, and p can be small enough so that the change in the resulting scalar m is insignificant. Hence, in some embodiments of the invention, the prefix is only considered for insertion in the queue in case the change in m is significant enough. The corresponding pseudo-code is shown below.
for each group {
// First pass: only consider groups for which there is a change in the group pref data compute_winner_set = 0 ;
for each spal (<> other)
{
// check whether there is new data for this group if (new_da a (group, spal)==l) { compute m (spal, d, v, p, spal- penalty) , store in local memory new_data (group, spal) = 0 ,- if (significant change in m) { store m (spal, d, v, p) in group_spal compute_winner__set = 1; break; }
if (compute_winner_set) for each prefix schedule_prefi (prefix) // see below
} In some embodiments of the invention, rolling averages are used to update measurements of delay, jitter, and loss, i.e., d = alpha* d + (1 - alpha) *dnew v = beta*v + (1 - beta)*vnew p — gamma* p + (1 — gamma) *pnew, where dnew, vnew, pnew represent the new delay, jitter, and loss measurements. Algorithms for calculating MOS for HTTP (1.0 and 1.1) and for voice and video are also presented in U.S. Provisional Applications No. 60/241,450, filed October 17, 2000 and U.S. Provisional Application No. 60/275,206, filed March 12, 2001 , and U.S. Applications No. 09/903,441, filed July 10, 2001, U.S. Application No. 09/923,924, filed August 6, 2001, and U.S.
Application No. 09/903,423, filed July 10, 2001. Values used for the models employed by these algorithms in embodiments of the invention are presented in an XML format below. Note that since MOS is computed per group, a selection from the sets of the following parameters may be made to allow different optimization goals for each group.
<module> <engine slot- T'> application modeW'httpl .O" [alpha="0.9" beta="0.9" gamma="0.9" theta="1.18" phi="0.13" omega="0.15" psi="0.25"] /> </engine> </module>
<module> <engine slot="l ',> application model— 'http 1.1 " [alpha- '0.9" beta="0.9" gamma="0.9" theta="l .3" phi="0.31" omega-"0.41 " psi="l .0"] /> </engine> </module> <module> <engine slot="l"> <application model- 'voice" [alpha="0.9" beta="0.9" gamma="0.9" theta ="1.5" phi="6.0" omega="23.0" psi="0.0"] /> </engine> </module>
<module> <engine slot- '1"> <application model="video" [alpha- '0.9" beta="0.9" gamma="0.9" theta="1.0" phi="4.0" omega="69.0" psi="0.0"] /> </engine> </module>
The values presented above are given as examples only. Many different models for deriving MOS scores for different applications will be apparent to those skilled in the art.
Pass 2
In some embodiments of the invention, in the second pass, an asynchronous thread goes through all prefixes in the PREFIX table. In some such embodiments, for each prefix, Checks 2, 3, and 4 are made: NEW_TNCOMING_BID in the PREFIX table indicates that a new bid was received from the coordination back channel; NEW_INVALID in the PREFIX_SPAL table indicates, for a particular (Prefix P, SPAL x) pair a loss of coverage for Prefix P over SPAL x. NEW_NATURAL_DATA indicates the receipt by Routing Intelligence Unit of an update message from a router, notifying it of a change in its natural BGP winner. In fact, the Decision Maker only asserts a performance route in case it is not the same as the natural BGP route; hence, it can potentially receive updates concerning the natural BGP winners of given prefixes from routers to which it has asserted no performance route for those prefixes. (The advantage of such an implementation is that when no performance route is sent to a router, the routing intelligence unit will get routing updates from that router. In contrast, if performances route were asserted regardless of whether they agree with the natural BGP choice, the Routing Intelligence Unit would never receive an update from the router pertaining to changes in the natural BGP winner for the different prefixes. If Routing Intelligence Unit were to assert performance routes regarding a given prefix P to all routers irrespectively of the current BGP winner for that prefix, it will never receive an update from the router pertaining to changes in the natural BGP winner for Prefix P. Indeed, the performance route would always be the winner, so the router would assume there is nothing to talk about.)
The following example illustrates the usefulness of the NEWJMATURALjDATA flag: Assume that the Decision Maker controls 3 routers, each of which controls its individual SPAL. Assume that the Decision Maker has just determined that Prefix P will move to SPAL 1. Assume that Prefix P believes that the natural BGP route for Prefix P as saved by Router 1 is
SPAL 1, the same as its current performance assertion. The Decision Maker's logical operation is to withdraw Prefix P's last performance route (say SPAL 3). However, it turned out that this BGP natural route has, in fact changed to SPAL 2; indeed, this could have happened during the previous assertion of a performance route for Prefix P (since, in this case, as mentioned above, the
Decision Maker receives no updates for Prefix P from the router, despite potential changes in Prefix P's natural BGP winner). As a result of this discrepancy, all traffic pertaining to Prefix P will be routed through SPAL 2, the current natural BGP winner for Prefix P, which is not the desired behavior. This is the primary reason for NEW_NATURAL_DATA: as such an event occurs, the router sends an update back to the Decision Maker, communicating to it the change in natural route. The incoming BGP messages from the local routers are processed by a process referred to as the Peer Manager. The Peer Manager sees the change in natural BGP route and sets the NEW_NATURAL_DATA flag to 1 ; consequently, the prefix is considered for re-scheduling during this pass, in Thread 1 , as described above. Note that in case of changes in the natural BGP route for a given prefix, the Decision Maker will need two passes through the Priority Queue before the prefix is routed through its appropriate performance route.
Finally, the ACCEPTING_DATA bit in the prefix table is checked. ACCEPTING_DATA is set to 0 by the peer manager to notify the decision maker not to assert performance routes for this prefix. This would primarily occur in case the prefix is withdrawn from the BGP tables in all local routers. In this case, in the ROUTER_PREFIX_SPAL table, the peer manager would have set the ANNOUNCED bits for that prefix on all SPALs to zero. Clearly, a prefix is only considered for insertion in the queue in case ACCEPTING_DATA is set to 1.
for each pref ix
{
//Checks 2 and 4: scan the prefix_group table get new_bid, new_natural , and accepting_data from prefix_group if (new_bid) | | (new_natural)
{ if (accepting_data)
schedule_ ?refix (prefix) // see below
} //Check 3: scan the prefix_spal table get new_invalid, from pre ix_spal if (new_invalid)
{ schedule_j?refix (prefix) ) }
Note that asserting a performance route about a prefix that does not exist in any of the routers' BGP tables could be problematic, depending on the surrounding network environment. If the set of controlled routers do not emit routes to any other BGP routers, then it is acceptable to generate new prefixes. But if any propagation is possible, there is a danger of generating an attractor for some traffic.
Specifically, if the new route is the most specific route known for some addresses, then any traffic to those addresses will tend to forward from uncontrolled routers towards the controlled routers. This can be very disruptive, since such routing decisions could be very far from optimal. The mechanism can cope r/ this in a number of ways:
• Prevent any use of a prefix unknown to BGP. This is achieved using the ACCEPTING D ATA check included in some embodiments of the invention. • Permit all such use, in a context where new routes cannot propagate
• Permit such use, but mark any new prefix with the well-known community value no-advertise to prevent propagation
• Permit such use, but configure the routers to prevent any further propagation (in some embodiments, by filtering such prefixes)
Deciding to Insert a Prefix Update Request in the Priority Queue: The schedule prefiτ Function
Once a prefix P makes it through the checks imposed in either Pass 1 or Pass 2, it is considered for insertion into the prefix update priority queue. scheduie_pref ix includes the related functionality, described below:
• First of all, a winner set of SPALs is re-computed for P; this set includes SPALs for which the performance is close to maximal.
• After the winner set W is computed for P, the decision maker determines whether the current route for P is included in W. • In case of a coordinated Routing Intelligence Unit system, in some embodiments of the invention, the back channel is sent updates pertaining to Prefix P even if the local prefix update request is dropped. For example, the performance on local links could have changed dramatically since the last time a bid was sent to the back channel for this prefix; in the event of such an occurrence, an updated bid is sent to the back channel (through the BGP peering set up for this purpose).
• In case the current route is not part of the newly computed winner set, it is clear that Prefix P is not routed optimally. Before going ahead and inserting an update request for Prefix P in the queue, the Routing Intelligence Unit performs a check of the flapping history for Prefix P. In case this check shows that Prefix P has an excessive tendency to flap, no prefix update request is inserted in the queue. • In some embodiments of the invention, before the prefix is inserted in the queue, a SPAL is chosen at random from the winner set. In case the winner set includes a remote SPAL controlled by a coordinated Routing
Intelligence Unit as well as a local SPAL, the local SPAL is always preferred. Also, in some embodiments of the invention, the randomness may be tweaked according to factors pertaining to any one or more of the following: link bandwidth, link cost, and traffic load for a given prefix. Finally, the state in the database is updated, and the element is inserted in the Priority Queue. The rank of the prefix update in the priority queue is determined by computing the potential percent improvement obtained from moving the prefix from its current route to the pending winner route. At the outset, a winner set of SPALs is re-computed for P; this set includes SPALs for which the performance is close to maximal. In some embodiments of the invention, invalid SPALs are excluded from the winner set computation. Bids from remote SPALs under the control of coordinated Routing Intelligence Units may, in embodiments, be included in the winner set computation. Since the bids corresponding to such remote routes are filtered through BGP, they are in units which are compatible with iBGP's LocalPref, which in some implementations is limited to 0-255. Therefore one possible implementation is to multiply m by 255. The converted quantity is referred to as MSLP. For consistency, the m values computed for local SPALs are also converted to local_pref units. The new winner is then determined to be the set of all SPALs for which MSLP is larger than MSLPmax - winner-set-threshold, where MSLPmax represents the maximum MSLP for that prefix across all available SPALs, and winner-set-threshold represents a customer-tunable threshold specified in LocalPref units. The related pseudo-code is shown below.
for each spal (<> other) { get invalid bit from prefix_spal if (invalid)
{ mark spal as invalid, not to be used in winner_set computation continue } convert m (spal) to MSLP Store MSLP in prefix_spal table } for spal=other
{ get MSLP_other = other^bid in prefix_group table
} compute winner_set (prefix) // considers winners among all valid spals and other_bid
After the winner set W is computed for P, the decision maker determines whether the current route for P is included in W. Indeed, in such a case, the performance of that prefix can't be improved much further, so no prefix update request needs to be inserted in the queue.
Even though an update request for a given prefix is ignored, the Decision Maker may still send an update to the back channel in certain embodiments. For example, even though the current route for Prefix P is still part of the winner set, performance degradation could have affected all SPALs at once, in which case the bid that was previously sent to the back channel for Prefix P is probably inaccurate. In some embodiments, one may solve this problem by implementing the following: the last bid for a given prefix is saved as MYJBID in the PREFIX table; a low and high threshold are then computed using two user-configurable parameters, bid-threshold-low and bid- threshold- high. In case of a significant difference between the MSLP score on the current route and the last score sent to the back channel for that prefix (i.e., MYJBID) is witnessed (that is, if the new score falls below (1 -bid- threshold-low)* 100% or jumps to a value that is larger than (1+bid- threshold-high)* 100% of MY_BID), a BGP message is sent to the back channel, carrying the new bid for Prefix P to remote coordinated Routing Intelligence Units. Pseudo-code illustrating the functionality described here is shown below.
5
//First, detect non-communicated withdrawal of a prefix if winner_set only comprises remote link
{ for all local routers 0 if performance route exists for that
(prefix, router) pair in the ROUTER_PREFIX_SPAL table send urgent withdrawal of this route to edge router continue 15 } get current_winner (prefix) and pending_winner (prefix) from prefix_spal table
if (pending_winner ! =current_winner) 0 { if (current_winner in winner_set)
{ update pending_winner = current_winner in database 5 continue
} if (current_winner not in winner_set) && (pending_winner in winner_set)
{ 30 continue
}
if (current_winner==pending_winner) { if (new_natural )
{ for all routers { current_route_per_router = SPAL (prefix, router, type = natural, state = latest_ON) if (current_route_per_router exists) S &. (current_route_per_router != current_winner) { special_route = current_route_per_router set local special_route_flag = 1 ; break;
}
else { current_route = current_winner
} if (current_route in winner_set) | | (special_route==current_winner) { get bid_low_threshold and bid_high_threshold from prefix_group table if ( (MSLP (prefix, current_spal) < bid_low_threshold) | |, (MSLP (prefix, current_spal) bid_Jb.igh_thresh.old) )
{ compute bid_low_threshold and bid_high_threshold from MSLP (prefix ) store bid__low_threshold and bid_high_threshold in prefix_group
^? form UPDATE to send to backchannel SBGP
} continue }
}
At this point, it is clear that Prefix P is not routed optimally. In some embodiments of the invention, before proceeding with sending the update request to the edge router, the Routing Intelligence Unit performs a check of the flapping history for Prefix P. An algorithm whose operation is very close to the flapping detection algorithm in BGP monitors the flapping history of a prefix. The algorithm can be controlled by, in one embodiment, three user-controlled parameters f iap_weight, f ap_iow, and f iap_high and works as follows: the tendency of a prefix to flap is monitored by a variable denoted
FORGIVING_MODE that resides in the PREFLX table. FORGTVING_MODE and other flapping parameters are updated in Thread 2 right before a performance route pertaining to Prefix P is asserted to the local routers. In case FORGIVINGJMODE is set to 1 , the tendency for Prefix P to flap is considered excessive, and the prefix update request is ignored. Conversely, in case
FORGIVINGJvlODE is set to 0, Prefix P has no abnormal tendency to flap, so it is safe to consider its update request.
get flapping state for prefix from prefix_group table if (excessive flapping)
{ continue
If a prefix survives to this point in Thread 1 , it will deterministically be inserted in the queue. Hence, all bits that were checked should be reset at this point so that some other pass on the prefixes does not reconsider and reschedule the prefix update request. For example, in case the prefix belongs to a group for
Li which there was a significant change in m, the prefix will be considered for insertion in the queue in Pass 1, and should not be reconsidered in Pass2.
//reset prefix level bits, if necessary for each spal (<> other)
{ get new_invalid bit from prefix_spal if (new_invalid) reset new_invalid to 0 in prefix_spal } get new_bid and new_natural bits from prefix_group if (new_bid) reset new_bid to 0 in prefix_group if (new_natural) reset new_natural to 0 in prefix_group
In some embodiments of the invention, before the prefix is inserted in the queue, a SPAL is chosen at random from the winner set. This way, traffic is spread across more than one SPAL, hence achieving some level of load balancing. In order to achieve some set of desirable policies, randomness can be tweaked in order to favor some SPALs and disregard others. For example, in some embodiments, in case the winner set includes a remote SPAL controlled by a coordinated Routing Intelligence Unit as well as a local SPAL, the local SPAL is always preferred. In other words, a remote SPAL is only the winner in case it is the only available SPAL in the winner set. Also, depending on the weight of a prefix and the observed load on different links, one can tweak the probabilities in such a way that the prefix is routed through a SPAL that fits it best. (This feature corresponds to the "Saturation Avoidance Factor" ~ SAF, described later in this document) After a winner is selected, PENDINGJ INNER in PREFIX_SPAL is updated to reflect the new potential winner. Finally, the element is inserted in the Priority Queue. In some embodiments, the rank of the prefix update in the priority queue is determined by computing the percent improvement; that is, the percent improvement obtained from moving the prefix from its current route to the pending winner route. That is, percent-improvement = [score(pending_winner) - Score(cuιτent_iOute)]/Score(current_route). The special-spal-flag is part of the data structure for the update, as it will be used in the determination of which messages to send to the local routers.
if ( (winner_set_size>l) and (other in winner_set) ) remove other from winner_set select spal from winner_set at random update PENDINGJfilNNER in PREFIX_SPAL table compute percent_improvement for prefix insert prefix in prefix update queue
Thread 2
In this thread 702, elements are taken out of the queue in a rate- controlled manner. In some embodiments of the invention, this rate is specified by the customer. The update rate is often referred to as the token rate. Tokens are given at regular intervals, according to the update rate. Each time a token appears, the head of the queue is taken out of the queue, and considered for potential update. In case the database shows that more recent passes in Thread 1 have canceled the update request, it is dropped without losing the corresponding loken; the next update request is then taken out from the head of the queue; this procedure is performed until either the queue empties, or a valid request is obtained. In some embodiments of the invention, when an update request that corresponds to Prefix P is determined to be current (thus, valid), one or more of the following tasks are performed: The flapping state is updated for Prefix P.
The database is updated to reflect the new actual winner; more specifically, the pending winner, chosen before inserting the prefix update request at the end of the first thread now becomes the current winner.
The database is checked to determine the current state of each of the individual routers. Accordingly, individual UPDATES are formed and sent to each of the routers. For example, no performance route is sent to an edge router
2^ in case the BGP winner for Prefix P, according to that router is found to be the same.
An UPDATE is sent to the back channel, describing the new local winner. Finally, the database is updated to keep track of the messages that were sent to each of the routers, as well as the expected resulting state of these routers.
In this thread 702, elements are just taken out from the queue in a rate- controlled manner, according to an update rate that may be set by the customer. The update rate is often referred to as the token rate: indeed, tokens are given at regular intervals, according to the update rate. Each time a token appears, the head of the queue is taken out, and considered for potential update.
Assume that the update request concerns Prefix P. The PREFLX_SPAL table is checked to obtain the P ENDING JWINNER and CURRENT JWINNER for Prefix P. In case PENDING, WINNER and CURRENT, WINNER correspond to the same SPAL, this is an indication that a more recent pass in Thread 1 has canceled the update request; in this case, the update request is dropped, without losing the corresponding token; the next token request is then polled from the head of the queue; this procedure is performed until either the queue empties, or a valid request, for which PENDINGJ TNNER and CURRENT_WINNER are different, is obtained.
Having different pending and current winners reflects a valid update request. In this case, the Decision Maker should assert the winning route for Prefix P. When a prefix update request is considered still valid, it is implemented. In the process, a series of tasks are performed. First, the flapping state is updated for Prefix P. In some embodiments of the invention, the tendency of a prefix to flap is monitored by a variable denoted INTERCHANGE_RATE that resides in the PREFIX table. The f iaP_weight parameter dictates the dynamics of 1NTERCHANGE_RATE; more specifically, at this point in the algorithm thread, INTERCHANGE_RATE is updated using the last value of INTERCHANGEJ ATE, as stored in the table,
LASTJCR TIME, also stored in the PREFIX table, and f iap_weight. In case the new computed INTERCHANGE_RATE is below f iap_iow, Routing Intelligence Unit considers the tendency for that prefix to flap to be low. On the other hand, when TNTERCHANGEJRATE exceeds f iaP_high, the Routing Intelligence Unit considers the tendency for that prefix to flap to be high. That is, the algorithm functions in the following fashion:
• In case FORGlVING_MODE (also in the PREFIX table) is set to 0, and INTERCHANGEJIATE exceeds f iap_high, FORGIVING_MODE is set to 1.
• In case FORGIVING_MODE is set to 1 , but TNTERCHANGEJRATE drops below f lap_low, FORGIVINGJVIODE is set to 0 again, and the prefix update request survives this Gheck. . In case FORGIVING_MODE is set to 1 and TNTERCHANGEJRATE is larger than f iap_iow, or FORGIVING_MODE is set to 0, and INTERCHANGEJIATE is below f iaP_high, FORGIVING_MODE does not change. Note that the method presented above is only one technique for controlling flapping; others will be apparent to those skilled in the art.
In some embodiments of the invention, the two parameters f iap_iow, and f iap_high are separated by an amount to avoid hysteresis between the two values. Then, the Decision Maker updates the PKLFIXJSPAL table to reflect this change; more specifically, CURRENT_WINNER is moved to PENDING_WINNER in the table. At this time, the ROUTER_PREFIX_SPAL table is queried to capture the current state of each router in regards to Prefix P. Accordingly, different UPDATES are formed and sent to each of the routers.
In some embodiments of the invention, the Decision Maker only asserts a performance route in case it is not the same as the natural BGP route; indeed, if Routing Intelligence Unit were to assert performance routes regarding a given prefix P to all routers irrespectively of the current BGP winner for that prefix, it will never receive an update from the router pertaining to changes in the natural BGP winner for Prefix P. (Indeed, the performance route would always be the winner, so the router would assume there is nothing to talk about.) Also, an UPDATE is sent to the back channel, describing to other
Routing Intelligence Units in a coordinated system the new local winner. Finally, the database is updated to keep track of the messages that were sent to each of the routers, as well as the expected resulting state of these routers. Prior to forming the UPDATES, the database is updated as to include the new flap parameters and prefix-SPAL information (i.e., the new current SPAL for that prefix). The BGP update sent to an edge router may be filtered out by policy on the router. However, assuming the update is permissible, it may be made to win in the router's BGP comparison process. One implementation is to have the edge router to apply a high Weight value to the incoming update.
(Weight is a common BGP knob, supported in most major implementations of the protocol, but it is not in the original protocol specification) This technique constrains the update so that it gains an advantage only on the router or routers to which the update is directly sent; this is desirable if some other routers are not controlled by a device such as the one described here. It is also possible to send the update with normal BGP attributes which make the route attractive, such as a high LocalPref value.
if (local_token available)
{ get prefix at the head of the local update queue updatePrefixSpal (prefix, spal) updateFlapStats (prefix) compute bid_low_threshold and bid_high_threshold from MSLP (prefix) store bid_low_threshold and bid_high_threshold in prefix_group form UPDATE to send to local SBGP form UPDATE to send to backchannel SBGP
}
E. Technical Considerations
Queue Size In some embodiments of the invention, a maximum queue size is to be chosen by the customer. In some embodiments, a small queue size may be chosen, so the maximum delay involved between the time instant a prefix update request is queued and the time instant it is considered by the second thread as a potential BGP update is small. For example, in case the token rate corresponding to a given link is 10 tokens per second, and we choose not to exceed a 2 second queuing delay, the queue should be able to accommodate 20 prefix update requests. Note that this method is simple, and only requires the knowledge of the token rate and the maximum acceptable delay.
Maximum Rate of Prefix Updates
It is desirable for the Routing Intelligence Unit to remain conservative in the rate of updates it communicates to the edge-router. This is the function of the token rate, which acts as a brake to the whole system. In some embodiments of the invention, the responsibility for setting the token rate is transferred to the customer, who selects a token rate that best fits her bandwidth and traffic pattern.
F. Feedback from the Listener BGP
The feedback from the listener BGP is valuable as it describes the actual current state of the local edge routers. Accordingly, in some embodiments of the invention, a separate routing intelligence unit thread modifies the content of the database according to the state it gets from the router(s). The Routing Intelligence Unit can operate more subtly in case it is a. perfect listener, we consider the Routing Intelligence Unit to be a perfect listener if it has knowledge of the individual BGP feeds from each individual SPAL. That is, in case the Routing Intelligence Unit is connected to three access links, each connecting to a separate provider, the Routing Intelligence Unit is a perfect listener if it has access to each of the three feeds handed by each of these providers. Configuring Routing Intelligence Unit as a Perfect Listener is desirable, as it allows the support of private peerings. For example, unless Routing Intelligence Unit is configured as a Perfect listener, when Routing Intelligence Unit hears about a prefix, it can't assume that coverage exists for that prefix across all SPALs. Considering the scenario described above, a prefix that the Routing Intelligence Unit learns about could be covered by any of the three
SPALs the router is connected to. For example, assume that only SPAL 1 has coverage for a given prefix P; in case the Routing Intelligence Unit asserts a performance route for that prefix across SPAL 2, there is no guarantee that the traffic pertaining to that prefix will be transited by the Service Provider to which SPAL 2 is connected (which we denote Provider 2). In case Provider 2 actually has a private peering with Provider X that obeys to some pre-specified contract, Provider X could well monitor the traffic from Provider 2, and filter all packets that do not conform to that contract. In case this contract namely specifies that Provider X will only provide transit to customers residing on Provider X's network, then the traffic pertaining to Prefix P will be dropped. If Routing Intelligence Unit were a Perfect Listener, it would only assert performance routes for prefixes across SPALs that are determined to have coverage for these prefixes. This behavior may be referred to as "extremely polite".
In some embodiments, the Routing Intelligence Unit is capable of avoiding the "Rocking the boat" problem, which stems from unwanted propagation of prefixes which did not already exist in BGP. The Routing
Intelligence Unit can operate in "impolite" mode, where any prefixes may be used, or in "polite" mode, where only those prefixes which were previously present in BGP can be used. An ANNOUNCED bit resides in the ROUTER JPREFD JSPAL table, and is set by the Peer Manager in case the Routing Intelligence Unit hears about a prefix from any of the Routers. This bit allows use of "polite" mode by the following procedure: in case the ANNOUNCED bit is set to 0 for all (router, SPAL) combinations in the ROUTER_ PREFL _SPAL table, then ACCEPTING_DATA is set to 0 in the PREFLX table.
G. Urgent Events
In case a catastrophic event occurs, such as a link going down, some embodiments of the invention send urgent BGP updates to the router. These urgent updates have priority over the entire algorithm described above. For example, in case a SPAL has lost coverage for a prefix, an urgent BGP message should be sent to the router, requesting to move the prefix to other SPALs. A list of urgent events upon which such actions may be taken, and a description of the algorithms pertaining to these actions, are described below.
Algorithm for the Detection of an Invalid SPAL
In some embodiments of the invention, a specific (Prefix P, SPAL x) pair is invalidated in case there are reasons to believe that SPAL x no longer provides coverage to Prefix P. One possible implementation is described as follows. Measurements corresponding to a (Prefix, SPAL) pair are assumed to arrive to the Decision Maker at something close to a predictable rate. A background thread that is independent from Threads 1 and 2 computes this update rate, and stores a time of last update, the LAST_UPDATE_TIME.
Another background thread verifies that LAST_ICR_TIME is reasonable given UPDATE_RATE. For example, assuming that measurements come in following a Poisson distribution, it is easy to verify whether LAST_ICR_TIME exceeds a fixed percentile of the inter-arrival interval. As LASTJ PDATEJTIME increases, the Decision Maker becomes more and more worried about the validity of the path. In the current design, there are two thresholds: at the first threshold, the NEW NVALID and INVALID flags are set in the PREFIXJSPAL table. As described in Thread 1 above, setting the NEW_TNNALID flag for a (Prefix P, SPAL x) pair will prevent any new update requests for Prefix P to be routed through SPAL x. At this stage, no other action is taken. At the second threshold, the Decision Maker becomes "very concerned" about routing Prefix P through SPAL x; hence, an urgent check is made to see whether Prefix P is currently routed through SPAL x, in which case an urgent UPDATE is created (that is, an UPDATE that bypasses the entire queue system) in order to route Prefix through a different SPAL.
H. Saturation Avoidance Factor
Some embodiments of the invention support a Saturation Avoidance Factor, which measures the effect of a prefix on other prefixes. In some embodiments of the invention, the "Saturation Avoidance Factor" (SAF) pertaining to a given prefix may be taken into account when prefixes are sorted in the Priority Queue. This SAF measures the effect of a prefix on other prefixes. That is, if, upon scheduling a prefix on a given link, its effect on the other prefixes already scheduled on that link is high (i.e., this effectively means that the aggregate load for this prefix is large), its SAF should be low. The lower the SAF of a prefix, the lower its place in the Priority Queue. This way, the algorithm will always favor low load prefixes rather than high load prefixes.
Note that in some embodiments, the SAF is not directly proportional to load. For example, a prefix that has a load equal to 0.75C has a different SAF whether it is considered to be scheduled on an empty link or on a link which utilization has already reached 75%. In the later case, the SAF should be as low as possible, since scheduling the prefix on the link would result in a link overflow.
At times, the token rate may be slower than the responded feedback. In case link utilization information is obtained through interface-stats, the token rate may be slower than the rate at which utilization information comes in. Also, the token rate may be slower than the rate at which edge-stats measurements come in.
Additionally, in some embodiments, each prefix is considered at a time. That is, PQServiceRate is small enough so that no more than one token is handed at a time. For example, denoting by T the token rate obtained from the above considerations, PQServiceRate is equal to \IT. If more than one token were handed at one time, two large prefixes could be scheduled on the same link, just as in the example above, potentially leading to bad performance.
In some embodiments of the invention, the SAF is a per-prefix, per- SPAL quantity. For example, assume that a prefix carries with it a load of 75% the capacity of all SPALs. If we have a choice between two SPALs, SPAL 1 and SPAL 2, SPAL 1 already carrying a load of 50 %, the other having a load of 0%. In this case, moving Prefix p to SPAL 1 will result in bad performance not only for itself, but also for all other prefixes already routed through SPAL 1. In this case, the SAF is close to 0, even if performance data across SPAL 1 seems to indicate otherwise. On the other hand, the SAF of moving Prefix p to SPAL 2 is, by contrast, very good, since the total load on the link will remain around 75% of total capacity, so delays will remain low. If, instead of carrying a load of 75%o capacity, Prefix p carried a load of 10% capacity, the results would have been different, and the SAF of Prefix p across SPALs 1 and 2 would have been close. In some embodiments of the invention, without knowing the load of a link, we can still measure the effect of moving a given prefix to a given SPAL through RTT measurements. That is, instead of measuring the load directly, we measure the end result, that is the amount by which performance of prefixes across a link worsens as a result of moving a prefix to it.
Modifying the Schema for the Support of SAF
In order to support SAF, the schema may be include a load field in the SPAL table, and an SAF field in the PREFIX_SPAL table. In some embodiments, the SAF field is a per-prefix, per-SPAL information.
I. Available Bandwidth
Edge-stats measurements may include measurements of delay, jitter, and loss; using these measurements, an application-specific performance score may be obtained based on which a decision is made on whether to send an update request for this prefix. Available bandwidth is a valuable quantity that is measured and included in the computation of the performance score in some embodiments of the invention.
J. Differentiated Queues and Token Rates per Link
In some embodiments of the invention, token rates may differ on a per- link basis (which dictates the use of different queues for each link).
In some embodiments, the token rate may be tailored to total utilization. Lowly utilized links can afford relatively higher token rates without fear of overflow, whereas links close to saturation should be handled more carefully.
Some embodiments of the invention provide one or more of the following modes of operation: 1. The default mode: the user specifies one token rate (and, optionally, a bucket size), shared equally among the prefixes updates destined to the different links.
2. The enhanced performance mode: the user specifies a minimum token rate (and, optionally, a bucket size). Depending on factors such as the total bandwidth utilization and the bandwidth of individual links, the prefix scheduler takes the initiative to function at a higher speed when possible, allowing better performance when it is not dangerous to do so.
3. The custom mode: in this case, the user can specify minimum and maximum token rates (and, optionally, bucket sizes), as well as conditions on when to move from a token rate to another. Using this custom mode, customers can tailor the prefix scheduler to their exact need.
K. Prefix Winner set Re-compulation
Even though the priority queue is sized in such a way that the delay spent in the queue is minimized, there is still an order of magnitude between the time scale of the BGP world, at which level decisions are taken, and the physical world, in which edge stats and interface stats are measured. That is, even though the queuing delay is comparable to other delays involved in the process of changing a route, prefix performance across a given link or the utilization of a given link can change much more quickly. For example, a 2 second queuing delay could be appropriate in the BGP world, while 2 seconds can be enough for congestion to occur across a given link, or for the link utilization to go from 25% to 75%... For this reason, in some embodiments of the invention, the winner set is re-evaluated at the output of the priority queue.
L. Conclusion
The foregoing description of various embodiments of the invention has been presented for purposes of illustration and description. It is not intended to limit the invention to the precise forms disclosed. Many modifications and equivalent arrangements will be apparent.

Claims

CLAIMSWhat is claimed is:
1. A communications back-channel, for coordinating routing decisions, the communications back channel comprising:
a plurality of networking devices;
a plurality of routing intelligence units, wherein each of the plurality of the plurality of routing intelligence units includes software for controlling a distinct subset of the plurality of networking devices, each of the plurality of routing intelligence units further including:
one or more processes for controlling the distinct subset of networking devices; and
one or more coordination processes for exchanging routing parameters with the plurality of routing intelligence units.
2. The communications back-channel of claim 1, wherein the one or more processes for controlling the distinct subset of networking devices are Border
Gateway Protocol (BGP) sessions.
3. The communications back-channel of claim 2, wherein each of the routing intelligence units is a route-reflector client.
4. The communications back-channel of claim 3, wherein each of the distinct subset of networking devices is a route reflector to the route reflector client.
5. The communications back-channel of claim 1, wherein the one or more coordination process in each of the routing intelligence units includes BGP sessions.
6. The communications back-channel of claim 5, wherein the BGP sessions in the one or more coordination processes of each of the routing intelligence units includes: at least one BGP process; and
at least one BGP stack, such that the at least one BGP stack exchanges routing parameters between the routing intelligence unit and the at least one BGP process, and the at least one BGP process exchanges routing parameters with the plurality of routing intelligence units.
7. The communications back-channel of claim 6, wherein the at least one BGP stack is a route reflector client, and the at least one BGP process is a route reflector.
8. The communications back-channel of claim 6, wherein the routing parameters include local path performance characteristics.
9. The communications back-channel of claim 6, wherein the routing parameters include performance scores for routes.
10. The communications back-channel of claim 9, wherein the performance scores are exchanged via a Local Preference field.
11. The communications back-channel of claim 1 , further comprising:
a plurality of communication links directly coupling the plurality of routing intelligence units, wherein the plurality of communication links are dedicated exclusively for exchanging routing parameters between the plurality of routing intelligence units.
12. The communications back-channel of claim 11, wherein the plurality of communication links are at least partially comprised of physical links between the plurality of routing intelligence units.
13. The communications back-channel of claim 1 1 , wherein the plurality of communication links are at least partially comprised of logical links between the plurality of routing intelligence units.
14. A method of exchanging routing parameters amongst a plurality of decision makers, each decision maker controlling a distinct subset of a plurality of routers, wherein the plurality of decision makers are in communication via a dedicated mesh, the method comprising:
asserting a first plurality of preferred routes for a first plurality of prefixes to the subset of routers; and
concurrent with the asserting the first plurality of preferred routes, sending a plurality of local performance scores for the first plurality of routes to the plurality of decision makers via the dedicated mesh.
15. The method of claim 14, further comprising:
receiving a second plurality of routes for a second plurality of prefixes via the dedicated mesh.
16. The method of claim 15, further comprising:
receiving a plurality of performance scores for the second plurality of routes.
17. The method of claim 16, wherein the plurality of performance scores are included in one or more Local Preferences fields in a BGP feed.
18. The method of claim 16, further comprising:
applying penalties to each of the plurality of performance scores.
19. The method of claim 14, wherein the asserting the first plurality of preferred routes is performed via a BGP feed to the subset of routers.
20. The method of claim 14, wherein the plurality of local performance scores are sent via a BGP feed to the dedicated mesh.
21. The method of claim 14, wherein the dedicated mesh is at least partially comprised of physical links between the plurality of decision makers.
22. The method of claim 14, wherein the dedicated mesh is at least partially comprised of logical links between the plurality of decision makers.
PCT/US2001/031259 2000-10-17 2001-10-05 Method and apparatus for coordinating routing parameters via a back-channel communication medium WO2002033915A1 (en)

Priority Applications (5)

Application Number Priority Date Filing Date Title
AU2001294993A AU2001294993A1 (en) 2000-10-17 2001-10-05 Method and apparatus for coordinating routing parameters via a back-channel communication medium
US10/070,338 US7720959B2 (en) 2000-10-17 2001-10-17 Method and apparatus for characterizing the quality of a network path
US10/070,515 US7336613B2 (en) 2000-10-17 2001-10-17 Method and apparatus for the assessment and optimization of network traffic
US10/358,681 US7487237B2 (en) 2000-10-17 2003-02-04 Load optimization
US12/286,019 US20090031025A1 (en) 2000-10-17 2008-09-26 Load optimization

Applications Claiming Priority (12)

Application Number Priority Date Filing Date Title
US24145000P 2000-10-17 2000-10-17
US60/241,450 2000-10-17
US27520601P 2001-03-12 2001-03-12
US60/275,206 2001-03-12
US09/903,441 US7080161B2 (en) 2000-10-17 2001-07-10 Routing information exchange
US09/903,423 2001-07-10
US09/903,423 US7363367B2 (en) 2000-10-17 2001-07-10 Systems and methods for robust, real-time measurement of network performance
US09/903,441 2001-07-10
US09/923,924 US7406539B2 (en) 2000-10-17 2001-08-06 Method and apparatus for performance and cost optimization in an internetwork
US09/923,924 2001-08-06
US09/960,623 US7349994B2 (en) 2000-10-17 2001-09-20 Method and apparatus for coordinating routing parameters via a back-channel communication medium
US09/960,623 2001-09-20

Related Parent Applications (2)

Application Number Title Priority Date Filing Date
US09/960,623 Continuation-In-Part US7349994B2 (en) 2000-10-17 2001-09-20 Method and apparatus for coordinating routing parameters via a back-channel communication medium
PCT/US2001/031420 Continuation-In-Part WO2002033892A2 (en) 2000-10-17 2001-10-04 Systems and methods for robust, real-time measurement of network performance

Related Child Applications (2)

Application Number Title Priority Date Filing Date
PCT/US2001/032312 Continuation-In-Part WO2002033894A2 (en) 2000-10-17 2001-10-17 Method and apparatus for performance and cost optimization in an internetwork
US10/358,681 Continuation-In-Part US7487237B2 (en) 2000-10-17 2003-02-04 Load optimization

Publications (1)

Publication Number Publication Date
WO2002033915A1 true WO2002033915A1 (en) 2002-04-25

Family

ID=27559305

Family Applications (3)

Application Number Title Priority Date Filing Date
PCT/US2001/031259 WO2002033915A1 (en) 2000-10-17 2001-10-05 Method and apparatus for coordinating routing parameters via a back-channel communication medium
PCT/US2001/032476 WO2002033896A2 (en) 2000-10-17 2001-10-17 Method and apparatus for characterizing the quality of a network path
PCT/US2001/032319 WO2002033895A2 (en) 2000-10-17 2001-10-17 Method and apparatus for the assesssment and optimization of network traffic

Family Applications After (2)

Application Number Title Priority Date Filing Date
PCT/US2001/032476 WO2002033896A2 (en) 2000-10-17 2001-10-17 Method and apparatus for characterizing the quality of a network path
PCT/US2001/032319 WO2002033895A2 (en) 2000-10-17 2001-10-17 Method and apparatus for the assesssment and optimization of network traffic

Country Status (7)

Country Link
US (2) US7349994B2 (en)
EP (1) EP1350363B1 (en)
AT (1) ATE522041T1 (en)
AU (4) AU2001294993A1 (en)
CA (2) CA2424680C (en)
IL (3) IL155356A0 (en)
WO (3) WO2002033915A1 (en)

Families Citing this family (57)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2002213287A1 (en) 2000-10-17 2002-04-29 Routescience Technologies Inc Method and apparatus for performance and cost optimization in an internetwork
US7487237B2 (en) * 2000-10-17 2009-02-03 Avaya Technology Corp. Load optimization
US7720959B2 (en) 2000-10-17 2010-05-18 Avaya Inc. Method and apparatus for characterizing the quality of a network path
US7756032B2 (en) 2000-10-17 2010-07-13 Avaya Inc. Method and apparatus for communicating data within measurement traffic
US8023421B2 (en) * 2002-07-25 2011-09-20 Avaya Inc. Method and apparatus for the assessment and optimization of network traffic
US7269157B2 (en) 2001-04-10 2007-09-11 Internap Network Services Corporation System and method to assure network service levels with intelligent routing
US7668966B2 (en) * 2001-11-02 2010-02-23 Internap Network Services Corporation Data network controller
US7133365B2 (en) * 2001-11-02 2006-11-07 Internap Network Services Corporation System and method to provide routing control of information over networks
US7222190B2 (en) * 2001-11-02 2007-05-22 Internap Network Services Corporation System and method to provide routing control of information over data networks
US7561517B2 (en) 2001-11-02 2009-07-14 Internap Network Services Corporation Passive route control of data networks
JP4080765B2 (en) * 2002-03-01 2008-04-23 株式会社日立製作所 Network system
JP4061308B2 (en) * 2002-10-15 2008-03-19 テレフオンアクチーボラゲット エル エム エリクソン(パブル) A system that provides flexible billing in the network
US7359930B2 (en) 2002-11-21 2008-04-15 Arbor Networks System and method for managing computer networks
WO2004056047A1 (en) * 2002-12-13 2004-07-01 Internap Network Services Corporation Topology aware route control
US7983239B1 (en) 2003-01-07 2011-07-19 Raytheon Bbn Technologies Corp. Systems and methods for constructing a virtual model of a multi-hop, multi-access network
US9137033B2 (en) * 2003-03-18 2015-09-15 Dynamic Network Services, Inc. Methods and systems for monitoring network routing
AU2004220872A1 (en) * 2003-03-18 2004-09-30 Renesys Corporation Methods and systems for monitoring network routing
US7881229B2 (en) * 2003-08-08 2011-02-01 Raytheon Bbn Technologies Corp. Systems and methods for forming an adjacency graph for exchanging network routing data
US7606927B2 (en) * 2003-08-27 2009-10-20 Bbn Technologies Corp Systems and methods for forwarding data units in a communications network
US8166204B2 (en) * 2003-08-29 2012-04-24 Raytheon Bbn Technologies Corp. Systems and methods for automatically placing nodes in an ad hoc network
US20050071469A1 (en) * 2003-09-26 2005-03-31 Mccollom William G. Method and system for controlling egress traffic load balancing between multiple service providers
US8295175B2 (en) * 2003-09-30 2012-10-23 Ciena Corporation Service metrics for managing services transported over circuit-oriented and connectionless networks
US8139475B2 (en) * 2004-07-29 2012-03-20 Telecom Italia S.P.A. Method and system for fault and performance recovery in communication networks, related network and computer program product therefor
WO2006029399A2 (en) 2004-09-09 2006-03-16 Avaya Technology Corp. Methods of and systems for network traffic security
US7630392B2 (en) * 2005-05-31 2009-12-08 Cisco Technology, Inc. Multi-homing using controlled route leakage at a backup service provider
WO2006133622A1 (en) * 2005-06-13 2006-12-21 Huawei Technologies Co., Ltd. An edge/packet gateway control system and a method for achieving the control by the edge/packet gateway
US7675912B1 (en) * 2005-07-05 2010-03-09 Cisco Technology, Inc. Method and apparatus for border gateway protocol (BGP) auto discovery
EP1910938A2 (en) * 2005-07-08 2008-04-16 At&T Corp. Method and system for gateway selection in inter-region communication on ip networks
US7961625B2 (en) 2005-08-01 2011-06-14 Limelight Networks, Inc. Routing under heavy loading
US7706280B2 (en) * 2005-08-01 2010-04-27 Limelight Networks, Inc. Heavy load packet-switched routing
US7647426B2 (en) * 2006-01-12 2010-01-12 Cisco Technology, Inc. Method and apparatus for achieving Border Gateway Protocol convergence using alternate route information
US7688819B2 (en) * 2006-03-06 2010-03-30 Cisco Technology, Inc. Faster routing protocol convergence using efficient message markup
KR101194140B1 (en) * 2006-12-27 2012-10-23 인텔 코오퍼레이션 Method and apparatus for determining a route metric
US8289845B1 (en) 2007-05-15 2012-10-16 Avaya Inc. Assured path optimization
US8233905B2 (en) * 2007-06-15 2012-07-31 Silver Spring Networks, Inc. Load management in wireless mesh communications networks
US8645568B2 (en) * 2007-11-16 2014-02-04 Equinix, Inc. Various methods and apparatuses for a route server
US8169921B2 (en) 2008-09-30 2012-05-01 At&T Intellectual Property I, Lp Methods and apparatus to monitor border gateway protocol sessions
US7894461B2 (en) * 2008-11-20 2011-02-22 At&T Intellectual Property I, L.P. Methods and apparatus to infer the status of border gateway protocol sessions
US8488490B2 (en) * 2009-10-14 2013-07-16 At&T Intellectual Property I, L.P. Methods and apparatus to determine a capacity for a network layer topology
US9503375B1 (en) * 2010-06-30 2016-11-22 F5 Networks, Inc. Methods for managing traffic in a multi-service environment and devices thereof
US8719926B2 (en) * 2011-02-11 2014-05-06 Verizon Patent And Licensing Inc. Denial of service detection and prevention using dialog level filtering
US11178244B2 (en) * 2011-08-09 2021-11-16 Comcast Cable Communications, Llc Content delivery network routing using border gateway protocol
US8976710B2 (en) * 2011-12-27 2015-03-10 Infosys Limited Methods for discovering and analyzing network topologies and devices thereof
US9137142B2 (en) * 2012-03-31 2015-09-15 Juniper Networks, Inc. Reduced traffic loss for border gateway protocol sessions in multi-homed network connections
US8831019B2 (en) 2012-05-18 2014-09-09 Renesys Path reconstruction and interconnection modeling (PRIM)
US8989046B1 (en) 2012-11-12 2015-03-24 The Aerospace Corporation Inter-domain routing message distribution through wide area broadcast channel
US10003536B2 (en) 2013-07-25 2018-06-19 Grigore Raileanu System and method for managing bandwidth usage rates in a packet-switched network
US9525638B2 (en) 2013-10-15 2016-12-20 Internap Corporation Routing system for internet traffic
US10924408B2 (en) 2014-11-07 2021-02-16 Noction, Inc. System and method for optimizing traffic in packet-switched networks with internet exchanges
US9769070B2 (en) 2015-01-28 2017-09-19 Maxim Basunov System and method of providing a platform for optimizing traffic through a computer network with distributed routing domains interconnected through data center interconnect links
US10505818B1 (en) 2015-05-05 2019-12-10 F5 Networks. Inc. Methods for analyzing and load balancing based on server health and devices thereof
US10091330B2 (en) * 2016-03-23 2018-10-02 Cisco Technology, Inc. Interest scheduling by an information and data framework in a content centric network
US11252088B2 (en) 2017-08-31 2022-02-15 Pensando Systems Inc. Methods and systems for network congestion management
US11212227B2 (en) 2019-05-17 2021-12-28 Pensando Systems, Inc. Rate-optimized congestion management
US11595308B2 (en) * 2019-06-13 2023-02-28 At&T Intellectual Property I, L.P. Closed loop prefix management and controller for whiteboxes
US11394700B2 (en) 2020-01-31 2022-07-19 Pensando Systems Inc. Proxy service through hardware acceleration using an IO device
US11431681B2 (en) 2020-04-07 2022-08-30 Pensando Systems Inc. Application aware TCP performance tuning on hardware accelerated TCP proxy services

Family Cites Families (261)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA1118084A (en) 1979-06-22 1982-02-09 Edmund Szybicki Alternate routing for a telephone system
US4345116A (en) 1980-12-31 1982-08-17 Bell Telephone Laboratories, Incorporated Dynamic, non-hierarchical arrangement for routing traffic
US4495570A (en) 1981-01-14 1985-01-22 Hitachi, Ltd. Processing request allocator for assignment of loads in a distributed processing system
FR2555388B1 (en) 1983-11-23 1986-02-21 Cit Alcatel BACKUP DEVICE OF A SUBSCRIBER TERMINAL IN A DIGITAL CONCENTRATOR
JPS61114363A (en) 1984-11-07 1986-06-02 Hitachi Ltd Job transfer system between computer systems
US4901244A (en) * 1985-01-25 1990-02-13 Szeto Lai Wan M Apparatus for, and method of, analyzing signals
US4669113A (en) 1985-04-26 1987-05-26 At&T Company Integrated network controller for a dynamic nonhierarchical routing switching network
US4726017A (en) 1985-05-21 1988-02-16 Fla. Multidrop data concentrator communication network
US5287537A (en) 1985-11-15 1994-02-15 Data General Corporation Distributed processing system having plural computers each using identical retaining information to identify another computer for executing a received command
US4704724A (en) 1985-12-05 1987-11-03 Bell Communications Research, Inc. Routing of network traffic
US4748658A (en) 1986-07-16 1988-05-31 Bell Communications Research, Inc. Architecture for allocating resources in a telecommunications network
US4788721A (en) 1987-12-09 1988-11-29 Bell Communications Research, Inc. Routing of network traffic
US4920432A (en) 1988-01-12 1990-04-24 Eggers Derek C System for random access to an audio video data library with independent selection and display at each of a plurality of remote locations
US4949248A (en) 1988-07-15 1990-08-14 Caro Marshall A System for shared remote access of multiple application programs executing in one or more computers
US4931941A (en) 1988-07-25 1990-06-05 Bell Communications Research, Inc. Adaptive routing of network traffic
US4949187A (en) 1988-12-16 1990-08-14 Cohen Jason M Video communications system having a remotely controlled central source of video and audio data
US5341477A (en) 1989-02-24 1994-08-23 Digital Equipment Corporation Broker for computer network server selection
US5072371A (en) * 1989-03-01 1991-12-10 The United States Of America As Represented By The United States Department Of Energy Method for simultaneous overlapped communications between neighboring processors in a multiple
US4939726A (en) 1989-07-18 1990-07-03 Metricom, Inc. Method for routing packets in a packet communication network
US5471622A (en) 1989-10-04 1995-11-28 Paralogic, Inc. Run-time system having nodes for identifying parallel tasks in a logic program and searching for available nodes to execute the parallel tasks
US5652841A (en) * 1990-02-06 1997-07-29 Nemirovsky; Paul Method and apparatus for aggregating terminals into clusters to assist in the construction of a distributed data communication network
AU7499291A (en) 1990-03-05 1991-10-10 Massachusetts Institute Of Technology Switching networks with expansive and/or dispersive logical clusters for message routing
US5142570A (en) 1990-06-15 1992-08-25 Bell Communications Research, Inc. Routing of network traffic using discrete traffic measurement data
US5172413A (en) 1990-12-20 1992-12-15 Sasktel Secure hierarchial video delivery system and method
US5471623A (en) * 1991-02-26 1995-11-28 Napolitano, Jr.; Leonard M. Lambda network having 2m-1 nodes in each of m stages with each node coupled to four other nodes for bidirectional routing of data packets between nodes
US5253341A (en) 1991-03-04 1993-10-12 Rozmanith Anthony I Remote query communication system
EP0504537A1 (en) 1991-03-22 1992-09-23 International Business Machines Corporation Method and apparatus for the testing and evaluation of geographically distributed telecommunication networks
EP0528075A1 (en) 1991-08-19 1993-02-24 ALCATEL BELL Naamloze Vennootschap Performance measurement device for a telecommunication path and method used therein
DE69232164T2 (en) 1991-08-22 2002-07-18 Sun Microsystems Inc Network video provider device and method
US5247347A (en) 1991-09-27 1993-09-21 Bell Atlantic Network Services, Inc. Pstn architecture for video-on-demand services
US5528281A (en) 1991-09-27 1996-06-18 Bell Atlantic Network Services Method and system for accessing multimedia data over public switched telephone network
US5481738A (en) * 1992-02-20 1996-01-02 International Business Machines Corporation Apparatus and method for communicating a quiesce and unquiesce state between elements of a data processing complex
US5371532A (en) 1992-05-15 1994-12-06 Bell Communications Research, Inc. Communications architecture and method for distributing information services
US5291554A (en) 1992-05-28 1994-03-01 Tv Answer, Inc. Shared-price custom video rentals via interactive TV
ES2129038T3 (en) * 1992-11-27 1999-06-01 Ibm ROAD TO MULTIPLE DESTINATIONS BETWEEN DOMAINS.
US5442389A (en) 1992-12-28 1995-08-15 At&T Corp. Program server for interactive television system
EP0608653A1 (en) 1993-01-26 1994-08-03 International Business Machines Corporation Method and system for routing information between nodes in a communication network
US5375070A (en) 1993-03-01 1994-12-20 International Business Machines Corporation Information collection architecture and method for a data communications network
US5508732A (en) 1993-03-22 1996-04-16 International Business Machines Corporation Data server, control server and gateway architecture system and method for broadcasting digital video on demand
US5406502A (en) 1993-06-29 1995-04-11 Elbit Ltd. System and method for measuring the operation of a device
US5442390A (en) 1993-07-07 1995-08-15 Digital Equipment Corporation Video on demand with memory accessing and or like functions
US5414455A (en) 1993-07-07 1995-05-09 Digital Equipment Corporation Segmented video on demand system
US5631897A (en) 1993-10-01 1997-05-20 Nec America, Inc. Apparatus and method for incorporating a large number of destinations over circuit-switched wide area network connections
BE1007682A3 (en) 1993-10-29 1995-09-12 Philips Electronics Nv SWITCHING DEVICE.
US6197065B1 (en) * 1993-11-01 2001-03-06 Biomet, Inc. Method and apparatus for segmental bone replacement
JP3420621B2 (en) 1993-11-04 2003-06-30 富士通株式会社 Distributed route selection controller for communication networks
JP3361865B2 (en) 1993-12-13 2003-01-07 富士通株式会社 Automatic setting method of static routing information and computer for automatically setting routing information
US5974457A (en) 1993-12-23 1999-10-26 International Business Machines Corporation Intelligent realtime monitoring of data traffic
US5475615A (en) 1993-12-23 1995-12-12 U S West Advanced Technologies, Inc. Method and system for sizing interactive video delivery systems
US5636216A (en) 1994-04-08 1997-06-03 Metricom, Inc. Method for translating internet protocol addresses to other distributed network addressing schemes
US5668800A (en) 1994-05-02 1997-09-16 International Business Machines Corporation Path testing in communications networks
US5535195A (en) 1994-05-06 1996-07-09 Motorola, Inc. Method for efficient aggregation of link metrics
US5467345A (en) 1994-05-31 1995-11-14 Motorola, Inc. Packet routing system and method therefor
US5694546A (en) * 1994-05-31 1997-12-02 Reisman; Richard R. System for automatic unattended electronic information transport between a server and a client by a vendor provided transport software with a manifest list
US5515511A (en) 1994-06-06 1996-05-07 International Business Machines Corporation Hybrid digital/analog multimedia hub with dynamically allocated/released channels for video processing and distribution
US5452294A (en) 1994-07-05 1995-09-19 Motorola, Inc. Method and apparatus for adaptive route selection in communication networks
JP3224963B2 (en) 1994-08-31 2001-11-05 株式会社東芝 Network connection device and packet transfer method
US5519435A (en) 1994-09-01 1996-05-21 Micropolis Corporation Multi-user, on-demand video storage and retrieval system including video signature computation for preventing excessive instantaneous server data rate
EP0701349A1 (en) 1994-09-07 1996-03-13 T.R.T. Telecommunications Radioelectriques Et Telephoniques Data transmission system and node with congestion monitoring
US5675741A (en) 1994-10-25 1997-10-07 Cabletron Systems, Inc. Method and apparatus for determining a communications path between two nodes in an Internet Protocol (IP) network
US6751562B1 (en) * 2000-11-28 2004-06-15 Power Measurement Ltd. Communications architecture for intelligent electronic devices
NL9500512A (en) * 1995-03-15 1996-10-01 Nederland Ptt Apparatus for determining the quality of an output signal to be generated by a signal processing circuit, and a method for determining the quality of an output signal to be generated by a signal processing circuit.
US5659796A (en) * 1995-04-13 1997-08-19 Cray Research, Inc. System for randomly modifying virtual channel allocation and accepting the random modification based on the cost function
JP2666769B2 (en) 1995-05-16 1997-10-22 日本電気株式会社 Internet protocol routing method and apparatus
US5654958A (en) 1995-06-05 1997-08-05 Motorola, Inc. System and method for learning and dynamic routing of data in a mobile communication network
US6393486B1 (en) * 1995-06-23 2002-05-21 Cisco Technology, Inc. System and method using level three protocol information for network centric problem analysis and topology construction of actual or planned routed network
US5563875A (en) 1995-07-10 1996-10-08 International Business Machines Corporation Wrap-around route testing in packet communications networks
US5826253A (en) 1995-07-26 1998-10-20 Borland International, Inc. Database system with methodology for notifying clients of any additions, deletions, or modifications occurring at the database server which affect validity of a range of data records cached in local memory buffers of clients
US5590126A (en) 1995-09-27 1996-12-31 Lucent Technologies Inc. Method for call establishment and rerouting in mobile computing networks
US5629930A (en) 1995-10-31 1997-05-13 Northern Telecom Limited Call routing in an ATM switching network
US5754639A (en) 1995-11-03 1998-05-19 Lucent Technologies Method and apparatus for queuing a call to the best split
JPH09135032A (en) 1995-11-08 1997-05-20 Mitsubishi Electric Corp Hybrid integrated circuit device for acceleration detecting
US5812528A (en) 1995-11-17 1998-09-22 Telecommunications Techniques Corporation Measuring round trip time in ATM network virtual connections
US5822520A (en) 1995-12-26 1998-10-13 Sun Microsystems, Inc. Method and apparatus for building network test packets
US5845091A (en) 1996-02-15 1998-12-01 Bay Networks, Inc. Forwarding of internetwork packets to a destination network via a selected one of a plurality of paths
US5793976A (en) 1996-04-01 1998-08-11 Gte Laboratories Incorporated Method and apparatus for performance monitoring in electronic communications networks
US6085238A (en) * 1996-04-23 2000-07-04 Matsushita Electric Works, Ltd. Virtual LAN system
US5787253A (en) 1996-05-28 1998-07-28 The Ag Group Apparatus and method of analyzing internet activity
US5940478A (en) 1996-05-31 1999-08-17 Octel Communications Corporation Method and system for extended addressing plans
US5892754A (en) * 1996-06-07 1999-04-06 International Business Machines Corporation User controlled adaptive flow control for packet networks
US5944779A (en) * 1996-07-02 1999-08-31 Compbionics, Inc. Cluster of workstations for solving compute-intensive applications by exchanging interim computation results using a two phase communication protocol
US5841775A (en) 1996-07-16 1998-11-24 Huang; Alan Scalable switching network
US6185601B1 (en) 1996-08-02 2001-02-06 Hewlett-Packard Company Dynamic load balancing of a network of client and server computers
US5805594A (en) 1996-08-23 1998-09-08 International Business Machines Corporation Activation sequence for a network router
US6055561A (en) 1996-10-02 2000-04-25 International Business Machines Corporation Mapping of routing traffic to switching networks
DE19645339B4 (en) 1996-11-04 2010-05-06 Valeo Schalter Und Sensoren Gmbh Method for measuring the distance dependent on the vehicle data from a vehicle
US5802106A (en) 1996-12-06 1998-09-01 Packeteer, Inc. Method for rapid data rate detection in a packet communication environment without data rate supervision
US6012088A (en) 1996-12-10 2000-01-04 International Business Machines Corporation Automatic configuration for internet access device
PT945045E (en) * 1996-12-13 2000-10-31 Koninkl Kpn Nv DEVICE AND A METHOD FOR DETERMINING THE QUALITY OF A SIGNAL
US6226266B1 (en) 1996-12-13 2001-05-01 Cisco Technology, Inc. End-to-end delay estimation in high speed communication networks
US6052718A (en) * 1997-01-07 2000-04-18 Sightpath, Inc Replica routing
US6549954B1 (en) * 1997-01-16 2003-04-15 Advanced Micro Devices, Inc. Object oriented on-chip messaging
US6034946A (en) 1997-04-15 2000-03-07 International Business Machines Corporation Selection of routing paths in data communications networks to satisfy multiple requirements
US6286045B1 (en) 1997-05-19 2001-09-04 Matchlogic, Inc. Information storage and delivery over a computer network using centralized intelligence to monitor and control the information being delivered
US6341309B1 (en) 1997-05-27 2002-01-22 Novell, Inc. Firewall system for quality of service management
US6119235A (en) 1997-05-27 2000-09-12 Ukiah Software, Inc. Method and apparatus for quality of service management
US6134589A (en) 1997-06-16 2000-10-17 Telefonaktiebolaget Lm Ericsson Dynamic quality control network routing
US6178448B1 (en) 1997-06-18 2001-01-23 International Business Machines Corporation Optimal link scheduling for multiple links by obtaining and utilizing link quality information
US6904110B2 (en) 1997-07-31 2005-06-07 Francois Trans Channel equalization system and method
US6006264A (en) 1997-08-01 1999-12-21 Arrowpoint Communications, Inc. Method and system for directing a flow between a client and a server
US6912222B1 (en) * 1997-09-03 2005-06-28 Internap Network Services Corporation Private network access point router for interconnecting among internet route providers
US6009081A (en) * 1997-09-03 1999-12-28 Internap Network Services Private network access point router for interconnecting among internet route providers
DE69819756D1 (en) 1997-09-16 2003-12-18 Transnexus Inc GUIDANCE ARRANGEMENT FOR INTERNET TELEPHONY
US6434606B1 (en) 1997-10-01 2002-08-13 3Com Corporation System for real time communication buffer management
US6026411A (en) 1997-11-06 2000-02-15 International Business Machines Corporation Method, apparatus, and computer program product for generating an image index and for internet searching and querying by image colors
JP3937533B2 (en) 1997-11-07 2007-06-27 セイコーエプソン株式会社 Remote coordinate input device and remote coordinate input method
US6026441A (en) 1997-12-16 2000-02-15 At&T Corporation Method for establishing communication on the internet with a client having a dynamically assigned IP address
US6339595B1 (en) 1997-12-23 2002-01-15 Cisco Technology, Inc. Peer-model support for virtual private networks with potentially overlapping addresses
US6111881A (en) 1997-12-29 2000-08-29 Nortel Networks Corporation Signaling protocol for rerouting ATM connections in PNNI environments
US6078953A (en) 1997-12-29 2000-06-20 Ukiah Software, Inc. System and method for monitoring quality of service over network
US6078963A (en) * 1998-01-16 2000-06-20 At&T Corp. Router with de-centralized processing using intelligent ports
US6185598B1 (en) * 1998-02-10 2001-02-06 Digital Island, Inc. Optimized network resource location
US6438592B1 (en) 1998-02-25 2002-08-20 Michael G. Killian Systems for monitoring and improving performance on the world wide web
US6370163B1 (en) 1998-03-11 2002-04-09 Siemens Information And Communications Network, Inc. Apparatus and method for speech transport with adaptive packet size
EP1062758A1 (en) * 1998-03-12 2000-12-27 BRITISH TELECOMMUNICATIONS public limited company Method and apparatus for signal degradation measurement
US6665271B1 (en) 1998-03-17 2003-12-16 Transnexus, Llc System for real-time prediction of quality for internet-based multimedia communications
US6453356B1 (en) * 1998-04-15 2002-09-17 Adc Telecommunications, Inc. Data exchange system and method
US6167052A (en) 1998-04-27 2000-12-26 Vpnx.Com, Inc. Establishing connectivity in networks
US7046653B2 (en) * 1998-05-01 2006-05-16 Jan Nigrin Diversity communication system and method of operation thereof
US6493353B2 (en) * 1998-05-07 2002-12-10 Mci Communications Corporation Communications signaling gateway and system for an advanced service node
US6560204B1 (en) * 1998-05-13 2003-05-06 Telcordia Technologies, Inc. Method of estimating call level traffic intensity based on channel link measurements
US6311144B1 (en) 1998-05-13 2001-10-30 Nabil A. Abu El Ata Method and apparatus for designing and analyzing information systems using multi-layer mathematical models
US6707824B1 (en) * 1998-05-20 2004-03-16 Nortel Networks Limited Method and apparatus for flexible egress traffic queuing
US6260070B1 (en) 1998-06-30 2001-07-10 Dhaval N. Shah System and method for determining a preferred mirrored service in a network by evaluating a border gateway protocol
US6385198B1 (en) * 1998-06-11 2002-05-07 Synchrodyne Networks, Inc. Signaling for timely forwarding in packet switching network with a common time reference
US6711152B1 (en) * 1998-07-06 2004-03-23 At&T Corp. Routing over large clouds
US6108703A (en) 1998-07-14 2000-08-22 Massachusetts Institute Of Technology Global hosting system
US6173324B1 (en) 1998-07-15 2001-01-09 At&T Corp Method and apparatus for fault detection and isolation in data
JP2000049825A (en) 1998-07-27 2000-02-18 Nec Corp Multiplex system and its control method
JP3602972B2 (en) * 1998-07-28 2004-12-15 富士通株式会社 Communication performance measuring device and its measuring method
US6487172B1 (en) 1998-08-21 2002-11-26 Nortel Networks Limited Packet network route selection method and apparatus using a bidding algorithm
US6584093B1 (en) * 1998-08-25 2003-06-24 Cisco Technology, Inc. Method and apparatus for automatic inter-domain routing of calls
US6963914B1 (en) 1998-09-01 2005-11-08 Lucent Technologies Inc. Method and apparatus for retrieving a network file using a logical reference
US6130890A (en) 1998-09-11 2000-10-10 Digital Island, Inc. Method and system for optimizing routing of data packets
US6529499B1 (en) 1998-09-22 2003-03-04 Lucent Technologies Inc. Method for providing quality of service for delay sensitive traffic over IP networks
US6189044B1 (en) * 1998-10-14 2001-02-13 Hughes Electronics Corporation Dynamic routing method for packet switched satellite communications
US20010010059A1 (en) * 1998-10-28 2001-07-26 Steven Wesley Burman Method and apparatus for determining travel time for data sent between devices connected to a computer network
US6385643B1 (en) * 1998-11-05 2002-05-07 Bea Systems, Inc. Clustered enterprise Java™ having a message passing kernel in a distributed processing system
US6687229B1 (en) * 1998-11-06 2004-02-03 Lucent Technologies Inc Quality of service based path selection for connection-oriented networks
US6522627B1 (en) 1998-11-12 2003-02-18 Nortel Networks Limited Managing internet protocol connection oriented services
JP2000151708A (en) * 1998-11-18 2000-05-30 Nec Corp Broadcast communication method and its device
US6317778B1 (en) * 1998-11-23 2001-11-13 International Business Machines Corporation System and method for replacement and duplication of objects in a cache
US6909700B1 (en) 1998-11-24 2005-06-21 Lucent Technologies Inc. Network topology optimization methods and apparatus for designing IP networks with performance guarantees
US6795399B1 (en) 1998-11-24 2004-09-21 Lucent Technologies Inc. Link capacity computation methods and apparatus for designing IP networks with performance guarantees
US6446028B1 (en) 1998-11-25 2002-09-03 Keynote Systems, Inc. Method and apparatus for measuring the performance of a network based application program
US6317792B1 (en) 1998-12-11 2001-11-13 Webtv Networks, Inc. Generation and execution of scripts for enabling cost-effective access to network resources
US6363332B1 (en) * 1998-12-22 2002-03-26 Caterpillar Inc. Method and apparatus for predicting a fault condition using non-linear curve fitting techniques
US6714549B1 (en) * 1998-12-23 2004-03-30 Worldcom, Inc. High resiliency network infrastructure
US7085230B2 (en) 1998-12-24 2006-08-01 Mci, Llc Method and system for evaluating the quality of packet-switched voice signals
US7099282B1 (en) 1998-12-24 2006-08-29 Mci, Inc. Determining the effects of new types of impairments on perceived quality of a voice service
US6611872B1 (en) * 1999-01-11 2003-08-26 Fastforward Networks, Inc. Performing multicast communication in computer networks by using overlay routing
US6452950B1 (en) 1999-01-14 2002-09-17 Telefonaktiebolaget Lm Ericsson (Publ) Adaptive jitter buffering
US6282562B1 (en) 1999-01-14 2001-08-28 Net Reality Method for economically sub-optimizing interactions in data-communications network environments, and a device according to the method
US6856627B2 (en) 1999-01-15 2005-02-15 Cisco Technology, Inc. Method for routing information over a network
US6631134B1 (en) * 1999-01-15 2003-10-07 Cisco Technology, Inc. Method for allocating bandwidth in an optical network
US6598145B1 (en) * 1999-02-12 2003-07-22 Avici Systems Irregular network
JP2000312226A (en) 1999-02-25 2000-11-07 Hitachi Ltd Method for warranting communication quality
US6760775B1 (en) * 1999-03-05 2004-07-06 At&T Corp. System, method and apparatus for network service load and reliability management
US6538416B1 (en) 1999-03-09 2003-03-25 Lucent Technologies Inc. Border gateway reservation protocol for tree-based aggregation of inter-domain reservations
US6594268B1 (en) 1999-03-11 2003-07-15 Lucent Technologies Inc. Adaptive routing system and method for QOS packet networks
US6711137B1 (en) 1999-03-12 2004-03-23 International Business Machines Corporation System and method for analyzing and tuning a communications network
US6795860B1 (en) 1999-04-05 2004-09-21 Cisco Technology, Inc. System and method for selecting a service with dynamically changing information
US6505254B1 (en) * 1999-04-19 2003-01-07 Cisco Technology, Inc. Methods and apparatus for routing requests in a network
US6819662B1 (en) * 1999-04-29 2004-11-16 Telecommunications Research Laboratories Method for protecting a telecommunications network
US6801502B1 (en) 1999-05-07 2004-10-05 At&T Corp. Method and apparatus for load-sensitive routing of long-lived packet flows
US20020124100A1 (en) 1999-05-20 2002-09-05 Jeffrey B Adams Method and apparatus for access to, and delivery of, multimedia information
US6553423B1 (en) * 1999-05-27 2003-04-22 Cisco Technology, Inc. Method and apparatus for dynamic exchange of capabilities between adjacent/neighboring networks nodes
US6728777B1 (en) * 1999-06-02 2004-04-27 Nortel Networks Limited Method for engineering paths for multicast traffic
US6601098B1 (en) 1999-06-07 2003-07-29 International Business Machines Corporation Technique for measuring round-trip latency to computing devices requiring no client-side proxy presence
US6463454B1 (en) 1999-06-17 2002-10-08 International Business Machines Corporation System and method for integrated load distribution and resource management on internet environment
US6275470B1 (en) 1999-06-18 2001-08-14 Digital Island, Inc. On-demand overlay routing for computer-based communication networks
US6973490B1 (en) 1999-06-23 2005-12-06 Savvis Communications Corp. Method and system for object-level web performance and analysis
AU775495B2 (en) 1999-06-30 2004-08-05 Apptitude Acquisition Corporation Method and apparatus for monitoring traffic in a network
US6771646B1 (en) 1999-06-30 2004-08-03 Hi/Fn, Inc. Associative cache structure for lookups and updates of flow records in a network monitor
US6839751B1 (en) * 1999-06-30 2005-01-04 Hi/Fn, Inc. Re-using information from data transactions for maintaining statistics in network monitoring
US6539425B1 (en) * 1999-07-07 2003-03-25 Avaya Technology Corp. Policy-enabled communications networks
US6633878B1 (en) 1999-07-30 2003-10-14 Accenture Llp Initializing an ecommerce database framework
US6766381B1 (en) 1999-08-27 2004-07-20 International Business Machines Corporation VLSI network processor and methods
US6785704B1 (en) * 1999-12-20 2004-08-31 Fastforward Networks Content distribution system for operation over an internetwork including content peering arrangements
US6415323B1 (en) 1999-09-03 2002-07-02 Fastforward Networks Proximity-based redirection system for robust and scalable service-node location in an internetwork
US6728484B1 (en) * 1999-09-07 2004-04-27 Nokia Corporation Method and apparatus for providing channel provisioning in optical WDM networks
US6631419B1 (en) 1999-09-22 2003-10-07 Juniper Networks, Inc. Method and apparatus for high-speed longest prefix and masked prefix table search
US6704795B1 (en) * 1999-10-12 2004-03-09 Cisco Technology, Inc. Technique for reducing consumption of router resources after BGP restart
US6836463B2 (en) 1999-10-15 2004-12-28 Nokia Corporation System for communicating labeled routing trees to establish preferred paths and source routes with local identifiers in wireless computer networks
US6728779B1 (en) * 1999-12-01 2004-04-27 Lucent Technologies Inc. Method and apparatus for exchanging routing information in a packet-based data network
EP1111532A1 (en) * 1999-12-20 2001-06-27 TELEFONAKTIEBOLAGET LM ERICSSON (publ) Method for transporting physical objects, transportation system and transportation means
US6829221B1 (en) * 1999-12-27 2004-12-07 Nortel Networks Limited Border gateway protocol manager and method of managing the selection of communication links
US6614789B1 (en) 1999-12-29 2003-09-02 Nasser Yazdani Method of and apparatus for matching strings of different lengths
US6608841B1 (en) 1999-12-30 2003-08-19 Nokia Networks Oy System and method for achieving robust IP/UDP/RTP header compression in the presence of unreliable networks
US6625648B1 (en) 2000-01-07 2003-09-23 Netiq Corporation Methods, systems and computer program products for network performance testing through active endpoint pair based testing and passive application monitoring
US7003571B1 (en) * 2000-01-31 2006-02-21 Telecommunication Systems Corporation Of Maryland System and method for re-directing requests from browsers for communication over non-IP based networks
US6633640B1 (en) 2000-02-01 2003-10-14 Avaya Technology Corp. Methods and apparatus for analysis of load-balanced multi-site call processing systems
US6873600B1 (en) * 2000-02-04 2005-03-29 At&T Corp. Consistent sampling for network traffic measurement
US6820133B1 (en) 2000-02-07 2004-11-16 Netli, Inc. System and method for high-performance delivery of web content using high-performance communications protocol between the first and second specialized intermediate nodes to optimize a measure of communications performance between the source and the destination
US20010037311A1 (en) 2000-02-18 2001-11-01 Mccoy James Efficient internet service cost recovery system and method
US20010026537A1 (en) * 2000-02-24 2001-10-04 Michael Massey Satellite internet backbone network system using virtual onboard switching
US6661797B1 (en) 2000-02-28 2003-12-09 Lucent Technologies Inc. Quality of service based path selection for connection-oriented networks
US6430160B1 (en) 2000-02-29 2002-08-06 Verizon Laboratories Inc. Estimating data delays from poisson probe delays
US6826613B1 (en) * 2000-03-15 2004-11-30 3Com Corporation Virtually addressing storage devices through a switch
US6601101B1 (en) * 2000-03-15 2003-07-29 3Com Corporation Transparent access to network attached devices
US7162539B2 (en) * 2000-03-16 2007-01-09 Adara Networks, Inc. System and method for discovering information objects and information object repositories in computer networks
FR2806862B1 (en) 2000-03-24 2002-09-27 Phonatis METHOD AND SYSTEM FOR REDUCING TELEPHONE INVOICES FROM COMPANIES
US6768969B1 (en) 2000-04-03 2004-07-27 Flint Hills Scientific, L.L.C. Method, computer program, and system for automated real-time signal analysis for detection, quantification, and prediction of signal changes
US6741569B1 (en) 2000-04-18 2004-05-25 Telchemy, Incorporated Quality of service monitor for multimedia communications system
US20020103631A1 (en) * 2000-04-21 2002-08-01 Anja Feldmann Traffic engineering system and method
US7024475B1 (en) * 2000-04-24 2006-04-04 Nortel Networks Limited Performance modeling of a communications system
US7123620B1 (en) 2000-04-25 2006-10-17 Cisco Technology, Inc. Apparatus and method for scalable and dynamic traffic engineering in a data communication network
US7343422B2 (en) * 2000-04-28 2008-03-11 Adara Networks, Inc. System and method for using uniform resource locators to map application layer content names to network layer anycast addresses
US7065584B1 (en) 2000-04-28 2006-06-20 Lucent Technologies Inc. Method and apparatus for network mapping using end-to-end delay measurements
GB0028113D0 (en) * 2000-05-15 2001-01-03 Band X Ltd Communication system and method
US6556582B1 (en) 2000-05-15 2003-04-29 Bbnt Solutions Llc Systems and methods for collision avoidance in mobile multi-hop packet radio networks
US7111073B1 (en) 2000-05-30 2006-09-19 Cisco Technology, Inc. Apparatus for estimating delay and jitter between network routers
US6658000B1 (en) * 2000-06-01 2003-12-02 Aerocast.Com, Inc. Selective routing
US6963575B1 (en) 2000-06-07 2005-11-08 Yipes Enterprise Services, Inc. Enhanced data switching/routing for multi-regional IP over fiber network
AU2001268411A1 (en) 2000-06-14 2002-01-02 Core Express, Inc. Route selection within a network with peering connections
US6748426B1 (en) * 2000-06-15 2004-06-08 Murex Securities, Ltd. System and method for linking information in a global computer network
US6751661B1 (en) 2000-06-22 2004-06-15 Applied Systems Intelligence, Inc. Method and system for providing intelligent network management
US6829654B1 (en) * 2000-06-23 2004-12-07 Cloudshield Technologies, Inc. Apparatus and method for virtual edge placement of web sites
US6956858B2 (en) 2000-06-30 2005-10-18 Mayan Networks Corporation Network routing table and packet routing method
US7020086B2 (en) * 2000-07-03 2006-03-28 Telefonaktiebolaget Lm Ericsson (Publ) Lagrange quality of service routing
US6751664B1 (en) 2000-07-05 2004-06-15 At&T Corp. Method for monitoring and meeting customer bandwidth demand in operational IP data networks
US6999432B2 (en) * 2000-07-13 2006-02-14 Microsoft Corporation Channel and quality of service adaptation for multimedia over wireless networks
US6839745B1 (en) * 2000-07-19 2005-01-04 Verizon Corporate Services Group Inc. System and method for generating reports in a telecommunication system
US20020010765A1 (en) * 2000-07-21 2002-01-24 John Border Method and system for prioritizing traffic in a network
US6973038B1 (en) 2000-07-28 2005-12-06 Tactical Networks A.S. System and method for real-time buying and selling of internet protocol (IP) transit
US6912203B1 (en) 2000-07-31 2005-06-28 Cisco Technology, Inc. Method and apparatus for estimating delay and jitter between many network routers using measurements between a preferred set of routers
US6981055B1 (en) * 2000-08-22 2005-12-27 Internap Network Services Corporation Method and system for optimizing routing through multiple available internet route providers
US7698463B2 (en) 2000-09-12 2010-04-13 Sri International System and method for disseminating topology and link-state information to routing nodes in a mobile ad hoc network
WO2002023337A2 (en) 2000-09-12 2002-03-21 Falcon Asset Acquisition Group Method and apparatus for flash load balancing
US6760777B1 (en) * 2000-09-15 2004-07-06 Pluris, Inc. Method and apparatus for distributing and providing fault tolerance to path-vector routing protocols within a multi-processor router
US7222268B2 (en) * 2000-09-18 2007-05-22 Enterasys Networks, Inc. System resource availability manager
US7043541B1 (en) * 2000-09-21 2006-05-09 Cisco Technology, Inc. Method and system for providing operations, administration, and maintenance capabilities in packet over optics networks
US7107326B1 (en) 2000-10-13 2006-09-12 3Com Corporation Method and system for integrating IP address reservations with policy provisioning
US7363367B2 (en) * 2000-10-17 2008-04-22 Avaya Technology Corp. Systems and methods for robust, real-time measurement of network performance
US7487237B2 (en) 2000-10-17 2009-02-03 Avaya Technology Corp. Load optimization
AU2002213287A1 (en) 2000-10-17 2002-04-29 Routescience Technologies Inc Method and apparatus for performance and cost optimization in an internetwork
US7336613B2 (en) * 2000-10-17 2008-02-26 Avaya Technology Corp. Method and apparatus for the assessment and optimization of network traffic
US8023421B2 (en) 2002-07-25 2011-09-20 Avaya Inc. Method and apparatus for the assessment and optimization of network traffic
US7720959B2 (en) 2000-10-17 2010-05-18 Avaya Inc. Method and apparatus for characterizing the quality of a network path
US7406539B2 (en) 2000-10-17 2008-07-29 Avaya Technology Corp. Method and apparatus for performance and cost optimization in an internetwork
US7756032B2 (en) 2000-10-17 2010-07-13 Avaya Inc. Method and apparatus for communicating data within measurement traffic
US7080161B2 (en) * 2000-10-17 2006-07-18 Avaya Technology Corp. Routing information exchange
US6894991B2 (en) 2000-11-30 2005-05-17 Verizon Laboratories Inc. Integrated method for performing scheduling, routing and access control in a computer network
US7155436B2 (en) * 2001-01-12 2006-12-26 Vendaria, Inc Method and system for generating and providing rich media presentations optimized for a device over a network
TWI223942B (en) 2001-02-20 2004-11-11 Li Jian Min Contents transmission network system and creating method thereof
US20030023709A1 (en) 2001-02-28 2003-01-30 Alvarez Mario F. Embedded controller and node management architecture for a modular optical network, and methods and apparatus therefor
US7110393B1 (en) 2001-02-28 2006-09-19 3Com Corporation System and method for providing user mobility handling in a network telephony system
JP2004533738A (en) * 2001-03-02 2004-11-04 カセンナ インコーポレイテッド A metadata-enabled push-pull model for efficiently distributing video content over networks with low latency
US7139242B2 (en) 2001-03-28 2006-11-21 Proficient Networks, Inc. Methods, apparatuses and systems facilitating deployment, support and configuration of network routing policies
US7269157B2 (en) * 2001-04-10 2007-09-11 Internap Network Services Corporation System and method to assure network service levels with intelligent routing
US7730528B2 (en) * 2001-06-01 2010-06-01 Symantec Corporation Intelligent secure data manipulation apparatus and method
US7085264B2 (en) * 2001-12-18 2006-08-01 Nortel Networks Limited System and method for controlling media gateways that interconnect disparate networks
US7535913B2 (en) * 2002-03-06 2009-05-19 Nvidia Corporation Gigabit ethernet adapter supporting the iSCSI and IPSEC protocols
JP3667700B2 (en) 2002-03-06 2005-07-06 エルピーダメモリ株式会社 Input buffer circuit and semiconductor memory device
US6983323B2 (en) 2002-08-12 2006-01-03 Tippingpoint Technologies, Inc. Multi-level packet screening with dynamically selected filtering criteria
EP1554658A2 (en) * 2002-10-24 2005-07-20 Optical Solutions, Inc. Passive optical network address association recovery
US7830861B2 (en) * 2003-10-16 2010-11-09 At&T Intellectual Property Ii, L.P. Method and apparatus for functional architecture of voice-over-IP SIP network border element
US20050132060A1 (en) 2003-12-15 2005-06-16 Richard Mo Systems and methods for preventing spam and denial of service attacks in messaging, packet multimedia, and other networks
US6984991B2 (en) * 2004-05-11 2006-01-10 International Business Machines Corporation Initialization of a bidirectional, self-timed parallel interface with automatic testing of AC differential wire pairs
JP2008508805A (en) * 2004-07-29 2008-03-21 インテリ7・インコーポレーテッド System and method for characterizing and managing electronic traffic
US20060291446A1 (en) * 2005-06-24 2006-12-28 Donald Caldwell Systems, methods, and devices for managing routing

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
J. YU: "Scalable Routing Design Principles", RFC 2791 NETWORK WORKING GROUP, 31 July 2000 (2000-07-31), pages 1 - 24, XP002191098 *

Also Published As

Publication number Publication date
IL190568A0 (en) 2008-11-03
EP1350363A2 (en) 2003-10-08
WO2002033895A3 (en) 2003-08-07
US7675868B2 (en) 2010-03-09
US20080186877A1 (en) 2008-08-07
AU2001294993A1 (en) 2002-04-29
US20020075813A1 (en) 2002-06-20
AU2002211777A1 (en) 2002-04-29
CA2637743C (en) 2012-08-21
US7349994B2 (en) 2008-03-25
IL155356A (en) 2008-07-08
IL155356A0 (en) 2003-11-23
AU2002213353A1 (en) 2002-04-29
WO2002033896A3 (en) 2002-11-21
AU2002211775A1 (en) 2002-04-29
ATE522041T1 (en) 2011-09-15
EP1350363B1 (en) 2011-08-24
CA2424680A1 (en) 2002-04-25
WO2002033896A2 (en) 2002-04-25
CA2424680C (en) 2010-01-05
WO2002033895A2 (en) 2002-04-25
CA2637743A1 (en) 2002-04-25

Similar Documents

Publication Publication Date Title
US7349994B2 (en) Method and apparatus for coordinating routing parameters via a back-channel communication medium
US7406539B2 (en) Method and apparatus for performance and cost optimization in an internetwork
US7840704B2 (en) Method and apparatus for performance and cost optimization in an internetwork
JP4212566B2 (en) Route selection method and apparatus for distribution in IP network
US8203954B1 (en) Link policy routing based on link utilization
Quoitin et al. Interdomain traffic engineering with BGP
US8175006B2 (en) Multi-path load balancing using route controller
US9015299B1 (en) Link grouping for route optimization
US6914886B2 (en) Controlling traffic on links between autonomous systems
US8094555B2 (en) Dynamic weighted-fair load-balancing
US8611251B2 (en) Method and apparatus for the distribution of network traffic
US8630297B2 (en) Method and apparatus for the distribution of network traffic
US9154402B2 (en) Method and system for gateway selection in inter-region communication on IP networks
CN111771359B (en) Method and system for connecting communication networks
CN108400936A (en) Information Network method for routing based on MPLS
JP2005057487A (en) Path controller for selecting a plurality of paths, path selecting method, program thereof, and recording medium
EP1185041B1 (en) OSPF autonomous system with a backbone divided into two sub-areas
Yu et al. Latency equalization as a new network service primitive
Ludwig Traffic engineering with BGP
Arnold A Traffic Engineering Attribute for BGP
Elsayed et al. LMPS: Localized multi-path Selection for QoS routing in VoIP networks
Headquarters Transport Diversity: Performance Routing (PfR) Design Guide
Lorensen Traffic Aware Policy-based Internet Routing

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ PH PL PT RO RU SD SE SG SI SK SL TJ TM TR TT TZ UA UG US US US US US US UZ VN YU ZA ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
REG Reference to national code

Ref country code: DE

Ref legal event code: 8642

122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase

Ref country code: JP