WO2021240215A1

WO2021240215A1 - Reordering and reframing packets

Info

Publication number: WO2021240215A1
Application number: PCT/IB2020/054991
Authority: WO
Inventors: Amir ROOZBEH; Alireza FARSHIN; Tom Francois G. BARBETTE; Hamid GHASEMIRAHNI; Dejan Kostic; JR. Gerald Q. MAGUIRE
Original assignee: Telefonaktiebolaget Lm Ericsson (Publ)
Priority date: 2020-05-26
Filing date: 2020-05-26
Publication date: 2021-12-02

Abstract

A method for processing packets in a network is described. The method includes receiving a plurality of packets from a set of operator networks; determining a class from a plurality of classes for each packet based on attributes associated with each packet; adding each packet to a delay queue from a plurality of delay queues, wherein each delay queue is associated with a different class and each packet is added to a delay queue according to a class determined for the packet; updating a flow table based on the plurality of packets being added to corresponding delay queues, wherein the flow table tracks the plurality of delay queues; and flushing a first delay queue associated with a first class based on the flow table in response to determining occurrence of a first event such that each packet in the queue is transmitted towards a first destination.

Description

SPECIFICATION

REORDERING AND REFRAMING PACKETS

TECHNICAL FIELD

[0001] Embodiments of the invention relate to the field of packet processing; and more specifically, reordering packets by a reframer operating in a network system according to class/type of the packets.

BACKGROUND ART

[0002] Recent advances in networking hardware have made multi- 100-Gbps interfaces and packet switching possible, facilitating faster Internet access. This faster access, growing traffic demands, emerging applications, and their various quality of service requirements means that network and datacenter operators must process packets at higher speeds with low latency and predictable performance. Thus, datacenter operators have incentives to partner with telecommunication operators to directly send user packets from a Packet Data Network Gateway (PDN GW) or Packet Gateway (PGW) to their datacenters or Points of Presence (PoP). This allows datacenter operators to monitor and manage each datacenter’s ingress traffic, enabling joint optimization of resource allocation and traffic engineering policies. Additionally, this promotes a flat Internet architecture, brings services closer to the users, and reduces service latency. However, improvements in packet analysis can still be achieved to optimize packet processing.

SUMMARY

[0003] A method for processing packets in a network system is described. The method includes receiving a plurality of packets from a set of operator networks; determining a class from a plurality of classes for each packet in the plurality of packets based on attributes associated with each packet; adding each packet to a delay queue from a plurality of delay queues, wherein each delay queue is associated with a different class from the plurality of classes and each packet from the plurality of packets is added to a delay queue according to a class determined for the packet; updating a flow table based on the plurality of packets being added to corresponding delay queues in the plurality of delay queues, wherein the flow table tracks the plurality of delay queues; and flushing a first delay queue from the plurality of delay queues and associated with a first class from the plurality of classes based on the flow table in response to determining occurrence of a first event such that each packet in the first delay queue, which are associated with the first class, is transmitted towards a first destination. [0004] A non-transitory machine-readable storage medium that provides instructions that, when executed by a processor, will cause said processor to perform operations is described. The operations include receiving a plurality of packets from a set of operator networks; determining a class from a plurality of classes for each packet in the plurality of packets based on attributes associated with each packet; adding each packet to a delay queue from a plurality of delay queues, wherein each delay queue is associated with a different class from the plurality of classes and each packet from the plurality of packets is added to a delay queue according to a class determined for the packet; updating a flow table based on the plurality of packets being added to corresponding delay queues in the plurality of delay queues, wherein the flow table tracks the plurality of delay queues; and flushing a first delay queue from the plurality of delay queues and associated with a first class from the plurality of classes based on the flow table in response to determining occurrence of a first event such that each packet in the first delay queue, which are associated with the first class, is transmitted towards a first destination.

[0005] The reframer and packet reordering procedures described herein may result in performance improvements at both the hardware level (physical network functions and modem network interface cards (NICs)) and the software level. For example, the reframer results in efficient utilization of memory/rule tables, which improves the time to perfbrm/match rule lookup for a packet. This happens because by reordering packets by class/type, a small, fast rule table of a NIC may stay hot for a longer period of time, as subsequent packets of the same flow are classified/matched faster.

BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The invention may best be understood by referring to the following description and accompanying drawings that are used to illustrate embodiments of the invention. In the drawings:

[0007] Figure 1 shows a network system with a reframer, according to one example embodiment.

[0008] Figure 2 shows the reframer deployed at various locations within the network system, including within a Packet Data Network Gateway (PDN GW), according to some example embodiments.

[0009] Figure 3 shows different modules/units within a reframer and their interaction to enable the actions of the reframer, according to one example embodiment.

[0010] Figure 4 shows an example rule table with a set of rules that may operate in a networking device, including a network interface card (NIC), router, or switch, according to one example embodiment. [0011] Figure 5 shows an example of a rule/flow table architecture that may be used within a NIC, a router, a switch, or a similar device, according to one example embodiment.

[0012] Figure 6 shows a set of rules deployed in a hierarchical table/memory system, according to one example embodiment.

[0013] Figure 7 shows the set of rules deployed in a hierarchical table/memory system following a miss in a first table and a hit in a second table, according to one example embodiment.

[0014] Figure 8 shows a set of rules deployed in a hierarchical table/memory system of a NIC and use with a reframer, according to one example embodiment.

[0015] Figure 9 shows a flow diagram of a method for reordering packets using a reframer, according to one example embodiment.

[0016] Figure 10A illustrates connectivity between network devices (NDs) within an exemplary network, as well as three exemplary implementations of the NDs, according to some embodiments of the invention.

[0017] Figure 10B illustrates an exemplary way to implement a special-purpose network device according to some embodiments of the invention.

[0018] Figure IOC illustrates various exemplary ways in which virtual network elements (VNEs) may be coupled according to some embodiments of the invention.

[0019] Figure 10D illustrates a network with a single network element (NE) on each of the NDs, and within this straight forward approach contrasts a traditional distributed approach (commonly used by traditional routers) with a centralized approach for maintaining reachability and forwarding information (also called network control), according to some embodiments of the invention.

[0020] Figure 10E illustrates the simple case of where each of the NDs implements a single NE, but a centralized control plane has abstracted multiple of the NEs in different NDs into (to represent) a single NE in one of the virtual network(s), according to some embodiments of the invention.

[0021] Figure 10F illustrates a case where multiple VNEs are implemented on different NDs and are coupled to each other, and where a centralized control plane has abstracted these multiple VNEs such that they appear as a single VNE within one of the virtual networks, according to some embodiments of the invention.

[0022] Figure 11 illustrates a general-purpose control plane device with centralized control plane (CCP), according to some embodiments of the invention. DETAILED DESCRIPTION

[0023] The following description describes methods and apparatuses for reordering and reframing packets by a reframer operating in a network system. In the following description, numerous specific details such as logic implementations, opcodes, means to specify operands, resource partitioning/sharing/duplication implementations, types and interrelationships of system components, and logic partitioning/integration choices are set forth in order to provide a more thorough understanding of the present invention. It will be appreciated, however, by one skilled in the art that the invention may be practiced without such specific details. In other instances, control structures, gate level circuits and full software instruction sequences have not been shown in detail in order not to obscure the invention. Those of ordinary skill in the art, with the included descriptions, will be able to implement appropriate functionality without undue experimentation.

[0024] References in the specification to “one embodiment,” “an embodiment,” “an example embodiment,” etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0025] Bracketed text and blocks with dashed borders (e.g., large dashes, small dashes, dot- dash, and dots) may be used herein to illustrate optional operations that add additional features to embodiments of the invention. However, such notation should not be taken to mean that these are the only options or optional operations, and/or that blocks with solid borders are not optional in certain embodiments of the invention.

[0026] In the following description and claims, the terms “coupled” and “connected,” along with their derivatives, may be used. It should be understood that these terms are not intended as synonyms for each other. “Coupled” is used to indicate that two or more elements, which may or may not be in direct physical or electrical contact with each other, co-operate or interact with each other. “Connected” is used to indicate the establishment of communication between two or more elements that are coupled with each other.

[0027] A reframer that reshapes network traffic distribution is described herein. The reframer can be installed in the data plane of a network system (e.g., after or within a Packet Data Network Gateway (PDN GW) or Packet Gateway (PGW) and before datacenters or Points of Presence (PoP)). Figure 1 shows a network system 100 with a reframer 102, according to one example embodiment. As shown in Figure 1, a series of packets 104 from an operator network 108 (e.g., a cellular network) are received by a PDN GW 106 of the operator network 108 and are each classified into a set of classes/types (represented by the letters A-C). The PDN GW 106 passes the packets 104 to the reframer 102 such that the reframer 102 can reorder the packets 104 based on the classes for use by a datacenter/outside network 110 (e.g., for distribution to services in other areas of the Internet). In particular, in the example of Figure 1, the reframer 102 groups packets 104 based on class such that the packets 104, which were originally received in terms of class as CACBCABCBA, are arranged as CCCCBBBAAA (i.e., the packets 104 are placed in order of class). In this fashion, other nodes in the network system 100, such as any physical node function 112 (e.g., a router, gateway, or firewall), virtual network function (VNF) 116 running on a server 114 (e.g., a router or firewall VNF 116 running on a server 114), or application 120 or other endpoint service running on a server 118 receiving those packets 104 will benefit from the action of the reframer 102 (i.e., re-ordering of the packets 104). Namely, the reordering of the packets 104 will allow more efficient processing of the packets 104, as will be described in further detail below.

[0028] Although the reframer 102 shown in Figure 1 is within a standalone box, the reframer 102 may be deployed in various locations within the network system 100 as shown in Figure 2. For example, as noted above, the reframer 102 can be a standalone box as also shown in Figure 1 and Figure 2 (Case A), the reframer 102 can be integrated into a physical node function 112 (e.g., a gateway, router, or firewall) (Case B), the reframer 102 can be implemented in software running on commodity servers 116 (e.g. similar to a VNF) (Case C), or the reframer 102 can be integrated into a programable network interface card (NIC) of a server 118 (Case D). The earlier the reframer 102 is installed in the network system 100 (i.e., the closer the reframer 102 is to the device/operator network 108 that generates or is otherwise the source of the packets 104), the potentially more nodes (e.g., physical and virtual network functions) will benefit from reframing/reordering of packets 104. For instance, the reframer 102 can be located or otherwise implemented within the PDN GW 106.

[0029] Figure 3 shows a set of modules/units within a reframer 102 and their interaction to enable the actions of the reframer 102, according to one example embodiment. Each module of the reframer 102 will be described by way of example below. Further, each of the modules of the reframer 102 may be implemented with some combination of software and/or hardware, including circuits, memories, and other physical components.

[0030] As shown in Figure 3, the reframer 102 may include a receiver (RX) medium access controller 302. The RX medium access controller 302 enables the reframer 102 to receive packets 104 (e.g., Ethernet packets) from external devices (e.g., the PDN GW 106 or devices within the operator network 108). In one embodiment, the RX medium access controller 302 is implemented by a network inference card (NIC).

[0031] As shown in Figure 3, the reframer 102 may also include a classifier 304 for classifying packets 104. In particular, when a packet 104 is received by the RX medium access controller 302, the packet 104 will be delivered to the classifier 304. The classifier 304 classifies the packet 104 into a set of traffic classes/types (i.e., traffic class A, B, or C), updates corresponding classification/rule/flow tables 322 with the appropriate information, and directs the packet 104 to a specific queue 320I-320₃ or memory address in the reframer’s memory. In one embodiment, the classifier 304 performs classification based on the information available in the received packet 104 and the information given to the classifier 304 for distinguishing packets/flows/traffic classes from each other. This information will be used to identify specific packets 104 among all received packets 104, which may be use-case specific. For instance, the information used by the classifier 304 to classify packets 104 could include: (1) an application identifier and/or destination port number; (2) a combination of a user identifier, user selector, and a barrier selector (e.g., traffic related to mobile gateway); (3) source address (e.g., source Internet Protocol (IP) address), source port number, destination address (e.g., destination IP address), and/or destination port number; and (4) a virtual local area network (VFAN) and/or the Internet Protocol (IP) 5-tuple (i.e., a collection of five features, including the layer-4 protocol along with source and destination IP addresses and ports).

[0032] In one embodiment, the reframer 102 can receive the information for classifying packets 104 as a series of classification rules that can be installed in a programmable classifier 304 and that use one or more pieces of information described above to classify packets 104 into one of a plurality of classes (e.g., the classes A-C). Additionally, based on the location of the reframer 102 in the network system 100, this classification information can be provided by (a) a network controller (e.g., a software defined network (SDN) controller) when it identifies a new flow of packets 104 sharing a same class; (b) a network administrator during the initialization phase of the reframer 102, (c) a receiving application (e.g., when the reframer 102 is implemented logically within or before a NIC of the receiving server 118).

[0033] In an example embodiment, which is shown in Figures 1, 2, and 3, the classifier 304 is configured to distinguish the traffic classes A, B, and C. As noted above, this classification can be performed by examining contents of the packets 104 in relation to classification rules. Additionally, the classifier 304 sets one or more flow/classification tables 322 with corresponding information and directs all packets 104 in class A to queue 320i, all packets 104 in class B to queue 3202, and all packets 104 in class C to queue 320₃. These queues 320 may be referred to as delay queues, as they hold corresponding packets 104 prior to their transmission toward a destination. In this configuration, each queue 320 may have a set capacity. Although shown with three queues 320, the number of queues 320 can be expanded to match the number of traffic classes/types. In particular, although the reframer 102 is described in relation to the classes A-C, in other embodiments, the reframer 102 may operate in relation to more or fewer classes and the use of the three classes A-C is for illustration purposes.

[0034] As described above, the reframer 102 may use a flow table 322. The flow table 322 can include one or more columns, including (1) a flow identifier column 324A that includes identifiers (IDs) of packet flows of a class, which could be a hash of relevant fields of packets 104; (2) a first packet time column 324B that indicates the time that a first packet 104 is directed to a specific queue 320 when the queue 320 had been empty (e.g., the time can be obtained from the wall-clock time of the reframer 102 or any other counter available to the reframer 102 (e.g., a hardware timestamp counter) and this time value will be reset when a scheduler/flushing priority engine flushes the queue 320); (3) a last packet time column 324C that indicates the time that a last packet 104 of a queue 320 has arrived and/or was stored in the queue 320 (e.g., the time value of this column 324C will be updated every time a new packet 104 is directed/added to the queue 320); and (4) a pointer to queue column 324D that indicates the location of the enqueued packets 104 and corresponding queue 320 for a specific packet flow associated with the entry in the table 322.

[0035] In one embodiment, the flow table 322 may not include the last packet time column 324C and instead the time value from this column 324C is embedded in the corresponding packet(s) 104 of the queue 320 (e.g., each packet 104 of the queue 320 or only the last packet 104 of the queue 320). In this case, a queue 320 can be implemented as a linked list where each packet 104 is added to a corresponding linked list at arrival with a corresponding timestamp showing the arrival time of the packet 104.

[0036] In the example shown in Figure 3, the first packet 104 received by the reframer 102 is of class/type A and arrives at time 02. Further, all packets 104 classified as class A will be stored in queue 320i with the address of pi and the last packet 104 of class A arrived at time 30. The first packet 104 of class B arrives at time 05, all packets 104 classified as class B will be stored in the queue 3202 with the address of p2, and the last packet 104 of class B arrived at time 20. The first packet 104 of class C arrives at time 09, all packets 104 classified as class C will be stored in queue 3203 with the address of p3, and the last packet 104 of class C arrived at time 35.

[0037] As shown in Figure 3, the reframer 102 may include a scheduler 306. The scheduler 306 determines when to flush a queue 320 and send/transmit a corresponding set of packets 104 from a single flow/traffic class to a destination. In one embodiment, the scheduler 306 determines to flush a queue 320 when at least one of the following three conditions is met: (1) a time period from when a last packet 104 of a flow/class was received by the reframer 102 is equal to or larger than a predefined time period T1 ; (2) a first packet 104 has been enqueued in the queue 320 for more than or equal to a predefined time period T2, and (3) a number of enqueued packets 104 in the queue 320 reaches a predefined threshold N_MAX. In one embodiment, when the decision is made to flush a queue 320, the scheduler 306 sets a ready to flush flag 326I-3263 of the queue 320.

[0038] In one embodiment, the predefined time periods T1 and T2 and the predefined threshold N_MAX can be configured to fixed values for all flows/classes based on pre-analyzed traffic behavior and sizes of batching at end nodes. However, in some embodiments, a feedback-based approach may also or alternatively be employed by the reframer 102 in which the scheduler 306 starts with initial values for the predefined time periods T1 and T2 and the predefined threshold N_MAX and adapts these values based on received feedback from application/receiver nodes. In some embodiments, the predefined time periods T1 and T2 and the predefined threshold N_MAX can be set for each flow/class/queue separately and may be adjusted/adapted for each flow/class/queue independently based on received feedback from application/receiver nodes (e.g., for each flow/identifier the reframer 102 will maintain independent and potentially different predefined time periods T1 and T2 and predefined thresholds N_MAX). Moreover, the scheduler 306 (or a different module in the reframer 102) could adapt these values based on a length/size/capacity of the queues 320 (i.e., how many packets 104 occupy the queue 320) and without feedback from outside the reframer 102 (i.e., a self-adaptive approach). In the example shown in Figure 3, all queues 320 (e.g., queue 320i, queue 3202, and queue 3203) can be set to flush at the same time.

[0039] As shown in Figure 3, the reframer 102 may include a flushing priority engine 308.

The flushing priority engine 308 can emit batches of flows of packets 104 to the next module in the processing pipeline according to a priority model/scheduling policy when multiple queues 320 are ready to be flushed (i.e., events associated with flushing two or more queues 320 are detected within a designated time period). The flushing priority engine 308 may be configured based on service level objectives (SLOs) of a corresponding network operator. Some possible scheduling/priority policies for the flushing priority engine 308 include: (1) prioritize mice over elephant flows (i.e., flush the queue 320 with the shortest flow of packets 104 first); (2) prioritize older over newer flows (i.e., flush the queue 320 with the oldest flow of packets 104 first) with respect to the timestamp of the first packet 104 (e.g., the first packet time value in a flow table 322); and (3) prioritize older over newer flows with respect to packet 104 waiting time in the set of queues 320 (i.e., flush the queue 320 with the oldest enqueued flow of packets 104 first).

[0040] After a queue 320 has been successfully flushed, the corresponding ready to flush flag 326 of the queue 320 may be changed to unset and the relevant parts of the flow table 322 may be reset. In the example of Figure 3, class/flow C in queue 3203 has a higher priority than class/flow A in queue 320i. Further, class/flow A in queue 320i has a higher priority than class/flow B in queue 3202. This results in the flushing priority engine 308 flushing the queues 320 in the following order when corresponding events are detected during a designated time period: queue 3203 is flushed first, queue 320i is flushed second, and finally queue 3202 is flushed third.

[0041] As shown in Figure 3, the reframer 102 may include an optimizer 310. The optimizer 310 may perform further optimization operations on flows of packets 104 flushed from a queue 320 or emitted from flushing priority engine 308. The optimization operations may be performed prior to the flush, during the flush, or following the flush. These operations may include one or more of Transmission Control Protocol (TCP) Acknowledgement (ACK) coalescing and building a super frame (i.e., a frame composed of multiple packets 104 from a single class/queue 320).

[0042] As shown in Figure 3, the reframer 102 may include a transmitter (TX) medium access controller 312. The TX medium access controller 312 transmits packets 104 to devices/nodes outside the reframer 102 or outside the device implementing the reframer 102. As shown in Figure 3, the output packets 104 are re-ordered toward the next node in the network system 100. [0043] As shown in Figure 3, the reframer 102 may include a statistics engine 314. The statistics engine 314 may gather statistics regarding different queues 320, including the size of each queue 320 before flushing. This statistical information may be used by the scheduler 306 for self-adaptive parameter adjustment during scheduling flushing of queues 320.

[0044] As shown in Figure 3, the reframer 102 may include a north bound module 316. The north bound module 316 can provide information (e.g., hints) to other nodes in the network system 100, based on information gathered from the statistics engine 314. For instance, the north bound module 316 can inform a NIC of a receiving node about the average size of the queues 320 and/or the possible temporal order of different traffic classes/flows. This statistical information can be used to optimize the receiving NIC resources (e.g., LRO, sizes of queues 320, etc.) and/or application/server resources.

[0045] The reframer 102 described herein, may result in performance improvements at both the hardware level (e.g., physical network functions and modem network interface cards (NICs)) and the software level. In particular, with respect to hardware performance improvements, modem NICs and many physical network functions (e.g., routers and firewalls) examine/classify input packets based on pre-defmed rules to perform different actions. These physical network functions steer packets to different ports or core/application processors that are responsible for those packets via matching the packets to one of the available rules in their classification/rule/flow tables. Figure 4 shows an example rule table 400 with a set of rules that may operate in a network device, including a NIC, router, switch, or another similar device, according to one example embodiment. Accordingly, although a NIC may be used for illustrative purposes, other network devices may also be used. As used herein, processing rules may be comprised of a set of parameters that are used for matching with a packet and a set of actions that are performed in relation to a matching packet.

[0046] The rule table of nodes may be built on a high-speed memory (e.g., cache or ternary content addressable memory (TCAM)) to support fast parallel lookup. However, suitable memories, such as TCAMs, are expensive and limited in size, which cannot accommodate many rules. Therefore, a small TCAM lookup table can be followed/supplemented by tables that are bigger but slower (e.g., a bigger table can be stored in dynamic random-access memory (DRAM) or static random -access memory (DRAM) in a router, switch, or NIC). When the processing rules cannot fit in the TCAM, then the rule table is divided into multiple tables, and some of the rules are stored in these slower memories.

[0047] Figure 5 shows an example of a rule/flow table architecture 500 that may be used within a network device, including a NIC, a router, a switch, or another similar device. Accordingly, although a NIC may be used for illustrative purposes, other network devices may also be used. As shown in Figure 5, the rule/flow table architecture 500 is implemented as a pipeline. In some embodiments, the rule/flow table pipeline starts with a very fast TCAM, which can perform fast parallel lookups in a hardware table 502i. Although it is desirable to keep all the rules in the TCAM based on the lookup speed of this medium, as noted above, the TCAM is a limited and expensive resource and it cannot accommodate many rules. Therefore, the pipeline will continue with hardware tables 502 built on slower memories (e.g., SRAM or DRAM onboard the NIC). The rule/flow table architecture 500 can potentially be extended with additional hardware tables 502 in other memories (e.g., the hardware table 502N) and a set of software tables (e.g., software tables 504 in the processor’s/host’s main memory or storage where the NIC is installed). In particular, a search of rules in the hardware table 502i, which is stored in fast TCAM, can first be used to determine a match with a packet 104 such that classification and an action can be performed. When no match is found in the hardware table 502i, a subsequent hardware table 502 is used, which may be stored in a slower memory than the TCAM (e.g., SRAM) until all the hardware tables 502I-502N have been searched without locating a match for the packet 104. Thereafter, software tables 504I-504M stored in another type of memory (e.g., DRAM) may be searched until a match is located. After a match is located in a table 502/504, an action is performed (e.g., forwarding the packet 104 on a particular port, processing the packets 104 using a prescribed set of operations, etc.). Accessing a rule stored on a software table 504 may be very expensive in terms of access time, as every access will pay the cost of a peripheral component interconnect express (PCIe) transaction (e.g., a direct memory access (DMA)) to/from main memory. Accordingly, it is desirable to avoid these types of lookups. Namely, in a hierarchical memory system of a destination system, it is desirable to find a matching rule in a higher hierarchical memory than a lower hierarchical memory, as the higher hierarchical memory offers improved speed of lookup.

[0048] Each of these tables 502/504 in the pipeline includes a set of rules. Tables 502/504 that are not within the TCAM will evaluate rules sequentially. In particular, as shown in Figure 6, each table 600A and 600B is built on a set of rules 602I-6025O. If the rules 602 in one table 600 fail to result in a match with a packet 104, then the rules 602 in the next rule table 600 will be evaluated. For example, if the rules 602I-6026 in table 600A fail to match with the packet 104, the rules 6027-60250 in the table 600B are sequentially reviewed until a match is determined. [0049] As navigation is performed lower in a table 600 or deeper in a pipeline of tables 600, the cost to access and evaluate rules against a packet 104 will be higher as a result of the non parallel lookup and the speed of the memory that stores the rules 602 becomes slower as the pipeline is traversed. Therefore, it is desirable that for a given packet 104, the matching rule 602 is available in the fastest and earliest table 600 in a pipeline and within a table 600 as high as possible.

[0050] To address this desire, recently matched rules 602 (e.g., “hot” rules) can be loaded in a table 600 stored in a fastest memory (e.g., TCAM). Additionally, rules 602 that are not matched with any packet 104 for a long period of time (e.g., “cold” rules) will be pushed to a lower level in a table 600 or a deeper table 600 in the pipeline (when there is not enough space in high-level tables 600). In the example shown in Figure 6, if the packet 104 is matched with rule 602s, then this rule 602s will be loaded to the first line of table 600A. Consequently, the last rule 602 of table 600A (i.e., rule 602r,)_ will be pushed to the first line of table 600B as there is not enough space in table 600A. Finally, the position of other rules 602 in both tables 600A and 600B will be updated accordingly as shown in Figure 7.

[0051] The rule lookup operations described herein benefits from input packets 104 being arranged in order based on class/type, as ordering packets 104 improves the locality of rules 602. This means that re-ordering performed by the reframer 102 can result in a higher probability to perform a faster rule lookup for a packet 104 since the matching rule 602 is most probably located in the fastest rule table 600 (e.g., a table 600 stored in TCAM). In some embodiments, the statistics gathered by the reframer 102 can be used for this rule positioning optimization and/or the reframer 102 can be integrated into a NIC to reshuffle/reposition the rules 602 in the pipeline to avoid unnecessary access to slow memory.

[0052] To illustrate the benefit of the reframer 102, the example reframer 102 shown in Figure 3 can be used with a receiving NIC’s rule/flow table that is implemented with a pipeline of two tables: (1) one table within a small TCAM that can accommodate only one rule and (2) a second, larger software table that includes 49 more rules as shown in Figure 8. In this example, a TCAM 802 in the NIC 804 includes the table 600A with the rule 602i and the table 600B is stored in a slower memory with rules 6022-60250. In this example, a packet 104 in class A is matched with rule 602 io, a packet 104 in class B is matched with rule 60220, and a packet 104 in class C is matched with rule 60230.

[0053] In cases where the reframer 102 orders packets 104 in a network system 100, the first packet 104 (i.e., the packet 104 with the class A) reaches the TCAM 802. Since rule 602io is not available in the table 600A within the TCAM 802 (i.e., a TCAM miss), table 600B will be evaluated until rule 602 io is reached and a match occurs. Consequently, the table 600A within the TCAM 802 is updated with rule 602io. The next two packets 104, all of which are associated with class A, are matched by the rule 602io available in the TCAM 802 (i.e., a TCAM hit).

When the train/flow of packets 104 associated with class A finishes, the next packet 104, which is associated with class B arrives. However, packet B does not match with the available rule 602io in table 600A of the TCAM 802. In this case, a TCAM miss occurs and table 600B is evaluated until the packet 104 is matched with rule 60220. Consequently, the table 600A within the TCAM 802 is updated with rule 60220. The next two packets 104, all of which are associated with class B, are matched by the rule 60220 available in the TCAM 802 (i.e., a TCAM hit).

When the train/flow of packets 104 associated with class B finishes, the next packet 104, which is associated with class C, arrives. However, packet C does not match with the available rule 60220 in table 600A of the TCAM 802. In this case, a TCAM miss occurs and table 600B is evaluated until the packet 104 is matched with rule 60230. Consequently, the table 600A within the TCAM 802 is updated with rule 60230. The next three packets 104, all of which are associated with class C, are matched by the rule 60230 available in the TCAM 802 (i.e., a TCAM hit). Accordingly, when a reframer 102 is used in the network system 100, only three misses and corresponding fetches from slower memory (i.e., the memory storing table 600B) is required. [0054] In cases where a reframer 102 does not order packets 104 in a network system 100, for every packet a TCAM miss is likely to occur that results in (1) a corresponding search of a table 600 in a slower memory and (2) an eventual fetch of a matching rule 602 to the table 600A of the TCAM 802. Therefore, based on the example of Figure 8, when a reframer 102 is not used, the slower table 600B will be accessed ten times to match the series of packets 104.

[0055] Accordingly, as described herein, the reframer 102 provides significant efficiency improvements/optimizations to hardware. Namely, as shown in the example, the reframer 102 results in efficient utilization of memory/rule tables, which improves the time to perform/match rule lookup for a packet 104 in a destination node. This happens because the small fast table (i.e., the table stored in TCAM) stays hot for a longer period of time and subsequent packets 104 of the same flow are classified/matched faster.

[0056] As noted above, the reframer 102 may also provide improvements at the software level, including improvements associated with network stack effects and network function effects. For example, the software stack may gain significantly from the reframer 102. These improvements can include (1) improved CPU cache locality, (2) fewer context switches, and (3) improved caching. With respect to improved CPU cache locality, ordering of packets 104 brings a higher degree of locality for a CPU. This means that when the reframer 102 is used in a network system 100, the loaded data and instruction for processing a packet 104 (i.e., a corresponding action) can be (re)used for many other packets 104 within a train/set/flow of packets 104 as all of the packets 104 in a flow requires the same processing. However, when the reframer 104 is not used in a network system 100, data and instructions must be loaded form main memory of a server for every packet 104, which results in consumption of resources. As noted above, ordering packets 104 improves/reduces CPU cycles spent on the network stack and it results in fewer cache misses.

[0057] With respect to context switches, when running multiple processes on a single CPU, the CPU must switch between contexts when different types/classes of data are available for processing. A context-switch can take up to 3 Ops to complete, which can see the arrival of millions of packets 104 at a high rate. Therefore, receiving packets 104 in trains/flows of multiple similar processes/packet classes/types will reduce the number of context switches. [0058] With respect to caching, NFV applications may implement a software-based caching. For instance, IP routers remember the last destination IP seen and the last output. By receiving packets 104 with the same destination group in a train/flow of packets 104, the number of lookups can be highly diminished. For instance, a virtual network function can have two tables for lookup: a small “hot” table and a larger “general” table. Re-ordering packets 104 increases the probability of reusing information saved in the “hot” table.

[0059] Figure 9 shows a flow diagram for a method 900 for reordering packets 104 using a reframer 102, according to one example embodiment. The operations in the flow diagrams will be described with reference to the exemplary embodiments of the other figures. However, it should be understood that the operations of the flow diagrams can be performed by embodiments of the invention other than those discussed with reference to the other figures, and the embodiments of the invention discussed with reference to these other figures can perform operations different than those discussed with reference to the flow diagrams.

[0060] As shown in Figure 9, the method 900 may commence at operation 902 with a reframer 102 receiving a plurality of packets 104 from a set of operator networks 108. The packets 104 may have been received from a set of user devices and may be associated with different classes or flows of traffic (e.g., different types of data, different flow identifiers, etc.).

[0061] At operation 904, the reframer 102 determines a class from a plurality of classes for each packet 104 in the plurality of packets 104 based on attributes associated with each packet 104. For example, the plurality of classes may be the classes A-C and the reframer 102 may attempt to classify the packets 104 amongst the classes A-C at operation 904. In one embodiment, the attributes associated with each packet 104 includes one or more of (1) an application identifier, (2) a destination port number, (3) a user identifier, (4) a user selector, (5) a barrier selector, (6) a source address, (7) a source port number, (8) a destination address, and (9) information associated with a virtual local area network (VLAN) and/or an Internet Protocol (IP).

[0062] At operation 906, the reframer 102 adds each packet 104 from the plurality of received packets 104 to a delay queue 320 from a plurality of delay queues 320. In this arrangement, each delay queue 320 is associated with a different class from the plurality of classes and each packet 104 from the plurality of packets 104 is added to a delay queue according to a class determined for the packet 104. For example, the plurality of delay queues 320 can include the delay queues 320I-320₃, which are respectively associated with the classes A-C.

[0063] At operation 908, the reframer 102 updates a flow table 322 based on the plurality of packets 104 being added to corresponding delay queues 320 in the plurality of delay queues 320 such that the flow table 322 tracks the plurality of delay queues 320. In one embodiment, the flow table 322 includes one or more of (1) a flow identifier column 324A that identifies a flow of packets 104 from a corresponding class, (2) a first packet time column 324B that indicates the time a first packet 104 is added to an associated empty delay queue 320, (3) a last packet time column 324C that indicates the time that the last packet 104 of the associated delay queue 320 is stored in the delay queue 320, and (4) a pointer to a delay queue column 324D that indicates a location of the associated delay queue 320 in memory (e.g., the location/address of the first node in a linked list).

[0064] At operation 910, the reframer 102 prioritizes flushing of a first delay queue 320i, which is associated with a first class from the plurality of classes, or flushing of a second delay queue 3202, which is associated with a second class from the plurality of classes, when first and second events, which are respectively associated with each of the first and second delay queues

3201 and 3202, are detected within a designated time period (e.g., within 0-5ms), such that either the first delay queue 320i is flushed prior to the second delay queue 3202 or the second delay queue 3202 is flushed prior to the first delay queue 320i. In one embodiment, prioritizing prioritizes the flushing of the first delay queue 320i prior to flushing of the second delay queue

3202 when (1) the first delay queue 320i has more packets 104 than the second delay queue 3202 or (2) a first packet 104 in the first delay queue 320i is older than a first packet 104 in the second delay queue 3202.

[0065] At operation 912, the reframer 102 optimizes the packets in the first delay queue 320i prior to transmission to a first destination. In some embodiments, optimizing includes one or more of Transmission Control Protocol (TCP) Acknowledgement (ACK) coalescing and combining each of the packets 104 in the first delay queue 320i into a single frame.

[0066] At operation 914, the reframer 102 flushes the first delay queue 3201 from the plurality of delay queues 320I-3202 based on the flow table 322 in response to determining occurrence of the first event such that each packet 104 in the first delay queue 320i, which are associated with the first class, is transmitted towards the first destination. In particular, the first delay queue 320i is emptied and all packets 104 are transmitted towards the first destination. As noted above, this flush/transmission may be prioritized of the flush/transmission of the second delay queue 3202 when the first and second events are detected within a designated time period. In one embodiment, the first event includes one or more of (1) a time period from when a last packet 104 of the first class was received is equal to or larger than a first predefined time period (Tl), (2) a packet 104 has been enqueued in the first delay queue 320i for more than or equal to a second predefined time period (T2), and (3) a number of enqueued packets 104 in the first delay queue 320i reaches a predefined threshold (N_MAX). In one embodiment, the first predefined time period, the second predefined time period, and the predefined threshold are independently set for each delay queue 320 in the plurality of delay queues 320I-3203. Further, the first predefined time period, the second predefined time period, and the predefined threshold are independently set for each delay queue 320 based on statistics associated with each delay queue 320.

[0067] In one embodiment, each packet 104 from the first delay queue 3201 is passed to the first destination such that the packets 104 are processed by a network interface card of the first destination, including matching each packet 104 to processing rules stored in a hierarchical memory system of the first destination, including a first memory that stores a first set of rules 602 and a second memory that stores a second set of rules 602. Further, the first memory is logically higher in the hierarchical memory system than the second memory and the first set of rules 602 includes less rules 602 than the second set of rules 602. Additionally, each packet 104 from the first delay queue 320i matches to a single rule 602 from the first and second set of rules 602.

[0068] In one embodiment a rule 602 associated with a first packet 104 received by the first destination is maintained in a first cache memory located closer hierarchically to a processor of the first destination that a second cache memory such that the first packet 104 and at least one additional packet 104 received by the first destination immediately after the first packet 104 and which has a same class as the first packet 104, is processed according to the rule 602 and or data or an instruction associated with the rule 602 and without the need for one or more of retrieval of the rule 602 or the data and instruction form the second cache memory or a context switch by the processor.

[0069] At operation 916, the reframer 102 flushes the second delay queue 3202 from the plurality of delay queues based on the flow table 322 in response to determining occurrence of the second event such that each packet 104 in the second delay queue 3202, which are associated with the second class, is transmitted towards a second destination.

[0070] An electronic device stores and transmits (internally and/or with other electronic devices over a network) code (which is composed of software instructions and which is sometimes referred to as computer program code or a computer program) and/or data using machine-readable media (also called computer-readable media), such as machine-readable storage media (e.g., magnetic disks, optical disks, solid state drives, read only memory (ROM), flash memory devices, phase change memory) and machine-readable transmission media (also called a carrier) (e.g., electrical, optical, radio, acoustical or other form of propagated signals - such as carrier waves, infrared signals). Thus, an electronic device (e.g., a computer) includes hardware and software, such as a set of one or more processors (e.g., wherein a processor is a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application specific integrated circuit, field programmable gate array, other electronic circuitry, a combination of one or more of the preceding) coupled to one or more machine-readable storage media to store code for execution on the set of processors and/or to store data. For instance, an electronic device may include non-volatile memory containing the code since the non-volatile memory can persist code/data even when the electronic device is turned off (when power is removed), and while the electronic device is turned on that part of the code that is to be executed by the processor(s) of that electronic device is typically copied from the slower non volatile memory into volatile memory (e.g., dynamic random access memory (DRAM), static random access memory (SRAM)) of that electronic device. Typical electronic devices also include a set or one or more physical network interface(s) (NI(s)) to establish network connections (to transmit and/or receive code and/or data using propagating signals) with other electronic devices. For example, the set of physical NIs (or the set of physical NI(s) in combination with the set of processors executing code) may perform any formatting, coding, or translating to allow the electronic device to send and receive data whether over a wired and/or a wireless connection. In some embodiments, a physical NI may comprise radio circuitry capable of receiving data from other electronic devices over a wireless connection and/or sending data out to other devices via a wireless connection. This radio circuitry may include transmitter(s), receiver(s), and/or transceiver(s) suitable for radiofrequency communication. The radio circuitry may convert digital data into a radio signal having the appropriate parameters (e.g., frequency, timing, channel, bandwidth, etc.). The radio signal may then be transmitted via antennas to the appropriate recipient(s). In some embodiments, the set of physical NI(s) may comprise network interface controller(s) (NICs), also known as a network interface card, network adapter, or local area network (LAN) adapter. The NIC(s) may facilitate in connecting the electronic device to other electronic devices allowing them to communicate via wire through plugging in a cable to a physical port connected to a NIC. One or more parts of an embodiment of the invention may be implemented using different combinations of software, firmware, and/or hardware.

[0071] A network device (ND) is an electronic device that communicatively interconnects other electronic devices on the network (e.g., other network devices, end-user devices). Some network devices are “multiple services network devices” that provide support for multiple networking functions (e.g., routing, bridging, switching, Layer 2 aggregation, session border control, Quality of Service, and/or subscriber management), and/or provide support for multiple application services (e.g., data, voice, and video).

[0072] Figure 10A illustrates connectivity between network devices (NDs) within an exemplary network, as well as three exemplary implementations of the NDs, according to some embodiments of the invention. Figure 10A shows NDs 1000A-H, and their connectivity by way of lines between 1000A-1000B, lOOOB-lOOOC, lOOOC-lOOOD, 1000D-1000E, 1000E-1000F, 1000F-1000G, and 1000A-1000G, as well as between 1000H and each of 1000A, lOOOC,

1000D, and 1000G. These NDs are physical devices, and the connectivity between these NDs can be wireless or wired (often referred to as a link). An additional line extending from NDs 1000A, 1000E, and 1000F illustrates that these NDs act as ingress and egress points for the network (and thus, these NDs are sometimes referred to as edge NDs; while the other NDs may be called core NDs).

[0073] Two of the exemplary ND implementations in Figure 10A are: 1) a special-purpose network device 1002 that uses custom application-specific integrated-circuits (ASICs) and a special-purpose operating system (OS); and 2) a general purpose network device 1004 that uses common off-the-shelf (COTS) processors and a standard OS.

[0074] The special-purpose network device 1002 includes networking hardware 1010 comprising a set of one or more processor(s) 1012, forwarding resource(s) 1014 (which typically include one or more ASICs and/or network processors), and physical network interfaces (NIs) 1016 (through which network connections are made, such as those shown by the connectivity between NDs 1000A-H), as well as non-transitory machine readable storage media 1018 having stored therein networking software 1020. During operation, the networking software 1020 may be executed by the networking hardware 1010 to instantiate a set of one or more networking software instance(s) 1022. Each of the networking software instance(s) 1022, and that part of the networking hardware 1010 that executes that network software instance (be it hardware dedicated to that networking software instance and/or time slices of hardware temporally shared by that networking software instance with others of the networking software instance(s) 1022), form a separate virtual network element 1030A-R. Each of the virtual network element(s) (VNEs) 1030A-R includes a control communication and configuration module 1032A-R (sometimes referred to as a local control module or control communication module) and forwarding table(s) 1034A-R, such that a given virtual network element (e.g., 1030A) includes the control communication and configuration module (e.g., 1032A), a set of one or more forwarding table(s) (e.g., 1034A), and that portion of the networking hardware 1010 that executes the virtual network element (e.g., 1030A).

[0075] The special-purpose network device 1002 is often physically and/or logically considered to include: 1) a ND control plane 1024 (sometimes referred to as a control plane) comprising the processor(s) 1012 that execute the control communication and configuration module(s) 1032A-R; and 2) a ND forwarding plane 1026 (sometimes referred to as a forwarding plane, a data plane, or a media plane) comprising the forwarding resource(s) 1014 that utilize the forwarding table(s) 1034A-R and the physical NIs 1016. By way of example, where the ND is a router (or is implementing routing functionality), the ND control plane 1024 (the processor(s) 1012 executing the control communication and configuration module(s) 1032A-R) is typically responsible for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) and storing that routing information in the forwarding table(s) 1034A-R, and the ND forwarding plane 1026 is responsible for receiving that data on the physical NIs 1016 and forwarding that data out the appropriate ones of the physical NIs 1016 based on the forwarding table(s) 1034A-R.

[0076] Figure 10B illustrates an exemplary way to implement the special-purpose network device 1002 according to some embodiments of the invention. Figure 10B shows a special- purpose network device including cards 1038 (typically hot pluggable). While in some embodiments the cards 1038 are of two types (one or more that operate as the ND forwarding plane 1026 (sometimes called line cards), and one or more that operate to implement the ND control plane 1024 (sometimes called control cards)), alternative embodiments may combine functionality onto a single card and/or include additional card types (e.g., one additional type of card is called a service card, resource card, or multi -application card). A service card can provide specialized processing (e.g., Layer 4 to Layer 7 services (e.g., firewall, Internet Protocol Security (IPsec), Secure Sockets Layer (SSL) / Transport Layer Security (TLS), Intrusion Detection System (IDS), peer-to-peer (P2P), Voice over IP (VoIP) Session Border Controller, Mobile Wireless Gateways (Gateway General Packet Radio Service (GPRS) Support Node (GGSN), Evolved Packet Core (EPC) Gateway)). By way of example, a service card may be used to terminate IPsec tunnels and execute the attendant authentication and encryption algorithms. These cards are coupled together through one or more interconnect mechanisms illustrated as backplane 1036 (e.g., a first full mesh coupling the line cards and a second full mesh coupling all of the cards).

[0077] Returning to Figure 10A, the general purpose network device 1004 includes hardware 1040 comprising a set of one or more processor(s) 1042 (which are often COTS processors) and physical NIs 1046, as well as non-transitory machine readable storage media 1048 having stored therein software 1050. During operation, the processor(s) 1042 execute the software 1050 to instantiate one or more sets of one or more applications 1064A-R. While one embodiment does not implement virtualization, alternative embodiments may use different forms of virtualization. For example, in one such alternative embodiment the virtualization layer 1054 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 1062A-R called software containers that may each be used to execute one (or more) of the sets of applications 1064A-R; where the multiple software containers (also called virtualization engines, virtual private servers, or jails) are user spaces (typically a virtual memory space) that are separate from each other and separate from the kernel space in which the operating system is ran; and where tire set of applications running m a given user space, unless explicitly allowed, cannot access the memory of the other processes. In another such alternative embodiment the virtualization layer 1054 represents a hypervisor (sometimes referred to as a virtual machine monitor (VMM)) or a hypervisor executing on top of a host operating system, and each of the sets of applications 1064A-R is run on top of a guest operating system within an instance 1062A-R called a virtual machine (which may in some cases be considered a tightly isolated form of software container) that is run on top of the hypervisor - the guest operating system and application may not know they are running on a virtual machine as opposed to running on a “bare metal” host electronic device, or through para- virtualization the operating system and/or application may be aware of the presence of virtualization for optimization purposes. In yet other alternative embodiments, one, some or all of the applications are implemented as unikemel(s), which can be generated by compiling directly with an application only a limited set of libraries (e.g., from a library operating system (LifaQS) including drivers/libraries of OS services) that provide the particular OS services needed by the application. As a unikemel can be implemented to run directly on hardware 1040, directly on a hypervisor (in which case the unikemel is sometimes described as running within a LibOS virtual machine), or in a software container, embodiments can be implemented fully with unikemels running directly on a hypervisor represented by virtualization layer 1054, unikemels running within software containers represented by instances 1062A-R, or as a combination of unikemels and the above-described techniques (e.g., unikemels and virtual machines both ran directly on a hypervisor, unikemels and sets of applications that are run in different software containers).

[0078] The instantiation of the one or more sets of one or more applications 1064A-R, as well as virtualization if implemented, are collectively referred to as software instance(s) 1052. Each set of applications 1064A-R, corresponding virtualization constmct (e.g., instance 1062A-R) if implemented, and that part of the hardware 1040 that executes them (be it hardware dedicated to that execution and/or time slices of hardware temporally shared), forms a separate virtual network element(s) 1060A-R.

[0079] The virtual network element(s) 1060A-R perform similar functionality to the virtual network element(s) 1030A-R - e.g., similar to the control communication and configuration module(s) 1032A and forwarding table(s) 1034A (this virtualization of the hardware 1040 is sometimes referred to as network function virtualization (NFV)). Thus, NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which could be located in Data centers, NDs, and customer premise equipment (CPE). While embodiments of the invention are illustrated with each instance 1062A-R corresponding to one VNE 1060A-R, alternative embodiments may implement this correspondence at a finer level granularity (e.g., line card virtual machines virtualize line cards, control card virtual machine virtualize control cards, etc.); it should be understood that the techniques described herein with reference to a correspondence of instances 1062A-Rto VNEs also apply to embodiments where such a finer level of granularity and/or unikemels are used.

[0080] In certain embodiments, the virtualization layer 1054 includes a virtual switch that provides similar forwarding services as a physical Ethernet switch. Specifically, this virtual switch forwards traffic between instances 1062A-R and the physical NI(s) 1046, as well as optionally between the instances 1062A-R; in addition, this virtual switch may enforce network isolation between the VNEs 1060A-Rthat by policy are not permitted to communicate with each other (e.g., by honoring virtual local area networks (VLANs)).

[0081] The third exemplary ND implementation in Figure 10A is a hybrid network device 1006, which includes both custom ASICs/special-purpose OS and COTS processors/standard OS in a single ND or a single card within an ND. In certain embodiments of such a hybrid network device, a platform VM (i.e., a VM that that implements the functionality of the special- purpose network device 1002) could provide for para-virtualization to the networking hardware present in the hybrid network device 1006.

[0082] Regardless of the above exemplary implementations of an ND, when a single one of multiple VNEs implemented by an ND is being considered (e.g., only one of the VNEs is part of a given virtual network) or where only a single VNE is currently being implemented by an ND, the shortened term network element (NE) is sometimes used to refer to that VNE. Also in all of the above exemplary implementations, each of the VNEs (e.g., VNE(s) 1030A-R, VNEs 1060A- R, and those in the hybrid network device 1006) receives data on the physical NIs (e.g., 1016, 1046) and forwards that data out the appropriate ones of the physical NIs (e.g., 1016, 1046). For example, a VNE implementing IP router functionality forwards IP packets on the basis of some of the IP header information in the IP packet; where IP header information includes source IP address, destination IP address, source port, destination port (where “source port” and “destination port” refer herein to protocol ports, as opposed to physical ports of a ND), transport protocol (e.g., user datagram protocol (UDP), Transmission Control Protocol (TCP), and differentiated services code point (DSCP) values.

[0083] Figure IOC illustrates various exemplary ways in which VNEs may be coupled according to some embodiments of the invention. Figure IOC shows VNEs 1070A.1-1070A.P (and optionally VNEs 1070A.Q-1070A.R) implemented in ND 1000A and VNE 1070H.1 in ND 1000H. In Figure IOC, VNEs 1070A.1-P are separate from each other in the sense that they can receive packets from outside ND 1000A and forward packets outside of ND 1000A; VNE 1070A.1 is coupled with VNE 1070H.1, and thus they communicate packets between their respective NDs; VNE 1070A.2-1070A.3 may optionally forward packets between themselves without forwarding them outside of the ND 1000A; and VNE 1070A.P may optionally be the first in a chain of VNEs that includes VNE 1070A.Q followed by VNE 1070A.R (this is sometimes referred to as dynamic service chaining, where each of the VNEs in the series of VNEs provides a different service - e.g., one or more layer 4-7 network services). While Figure IOC illustrates various exemplary relationships between the VNEs, alternative embodiments may support other relationships (e.g., more/fewer VNEs, more/fewer dynamic service chains, multiple different dynamic service chains with some common VNEs and some different VNEs). [0084] The NDs of Figure 10A, for example, may form part of the Internet or a private network; and other electronic devices (not shown; such as end user devices including workstations, laptops, netbooks, tablets, palm tops, mobile phones, smartphones, phablets, multimedia phones, Voice Over Internet Protocol (VOIP) phones, terminals, portable media players, GPS units, wearable devices, gaming systems, set-top boxes, Internet enabled household appliances) may be coupled to the network (directly or through other networks such as access networks) to communicate over the network (e.g., the Internet or virtual private networks (VPNs) overlaid on (e.g., tunneled through) the Internet) with each other (directly or through servers) and/or access content and/or services. Such content and/or services are typically provided by one or more servers (not shown) belonging to a service/content provider or one or more end user devices (not shown) participating in a peer-to-peer (P2P) service, and may include, for example, public webpages (e.g., free content, store fronts, search services), private webpages (e.g., usemame/password accessed webpages providing email services), and/or corporate networks over VPNs. For instance, end user devices may be coupled (e.g., through customer premise equipment coupled to an access network (wired or wirelessly)) to edge NDs, which are coupled (e.g., through one or more core NDs) to other edge NDs, which are coupled to electronic devices acting as servers. However, through compute and storage virtualization, one or more of the electronic devices operating as the NDs in Figure 10A may also host one or more such servers (e.g., in the case of the general purpose network device 1004, one or more of the software instances 1062A-Rmay operate as servers; the same would be true for the hybrid network device 1006; in the case of the special-purpose network device 1002, one or more such servers could also be run on a virtualization layer executed by the processor(s) 1012); in which case the servers are said to be co-located with the VNEs of that ND.

[0085] A virtual network is a logical abstraction of a physical network (such as that in Figure 10A) that provides network services (e.g., L2 and/or L3 services). A virtual network can be implemented as an overlay network (sometimes referred to as a network virtualization overlay) that provides network services (e.g., layer 2 (L2, data link layer) and/or layer 3 (L3, network layer) services) over an underlay network (e.g., an L3 network, such as an Internet Protocol (IP) network that uses tunnels (e.g., generic routing encapsulation (GRE), layer 2 tunneling protocol (L2TP), IPSec) to create the overlay network).

[0086] A network virtualization edge (NVE) sits at the edge of the underlay network and participates in implementing the network virtualization; the network-facing side of the NVE uses the underlay network to tunnel frames to and from other NVEs; the outward-facing side of the NVE sends and receives data to and from systems outside the network. A virtual network instance (VNI) is a specific instance of a virtual network on a NVE (e.g., a NE/VNE on an ND, a part of a NE/VNE on a ND where that NE VNE is divided into multiple VNEs through emulation); one or more VNIs can be instantiated on an NVE (e.g., as different VNEs on an ND). A virtual access point (VAP) is a logical connection point on the NVE for connecting external systems to a virtual network; a VAP can be physical or virtual ports identified through logical interface identifiers (e.g., a VLAN ID).

[0087] Examples of network services include: 1) an Ethernet LAN emulation service (an Ethernet-based multipoint service similar to an Internet Engineering Task Force (IETF) Multiprotocol Label Switching (MPLS) or Ethernet VPN (EVPN) service) in which external systems are interconnected across the network by a LAN environment over the underlay network (e.g., an NVE provides separate L2 VNIs (virtual switching instances) for different such virtual networks, and L3 (e.g., IP/MPLS) tunneling encapsulation across the underlay network); and 2) a virtualized IP forwarding service (similar to IETF IP VPN (e.g., Border Gateway Protocol (BGP)/MPLS IPVPN) from a service definition perspective) in which external systems are interconnected across the network by an L3 environment over the underlay network (e.g., an NVE provides separate L3 VNIs (forwarding and routing instances) for different such virtual networks, and L3 (e.g., IP/MPLS) tunneling encapsulation across the underlay network)). Network services may also include quality of service capabilities (e.g., traffic classification marking, traffic conditioning and scheduling), security capabilities (e.g., filters to protect customer premises from network - originated attacks, to avoid malformed route announcements), and management capabilities (e.g., full detection and processing).

[0088] Fig. 10D illustrates a network with a single network element on each of the NDs of Figure 10A, and within this straight forward approach contrasts a traditional distributed approach (commonly used by traditional routers) with a centralized approach for maintaining reachability and forwarding information (also called network control), according to some embodiments of the invention. Specifically, Figure 10D illustrates network elements (NEs) 1070A-H with the same connectivity as the NDs 1000A-H of Figure 10A.

[0089] Figure 10D illustrates that the distributed approach 1072 distributes responsibility for generating the reachability and forwarding information across the NEs 1070A-H; in other words, the process of neighbor discovery and topology discovery is distributed.

[0090] For example, where the special-purpose network device 1002 is used, the control communication and configuration module(s) 1032A-R of the ND control plane 1024 typically include a reachability and forwarding information module to implement one or more routing protocols (e.g., an exterior gateway protocol such as Border Gateway Protocol (BGP), Interior Gateway Protocol(s) (IGP) (e.g., Open Shortest Path First (OSPF), Intermediate System to Intermediate System (IS-IS), Routing Information Protocol (RIP), Label Distribution Protocol (LDP), Resource Reservation Protocol (RSVP) (including RSVP-Traffic Engineering (TE): Extensions to RSVP for LSP Tunnels and Generalized Multi-Protocol Label Switching (GMPLS) Signaling RSVP-TE)) that communicate with other NEs to exchange routes, and then selects those routes based on one or more routing metrics. Thus, the NEs 1070A-H (e.g., the processor(s) 1012 executing the control communication and configuration module(s) 1032A-R) perform their responsibility for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) by distributively determining the reachability within the network and calculating their respective forwarding information. Routes and adjacencies are stored in one or more routing structures (e.g., Routing Information Base (RIB), Label Information Base (LIB), one or more adjacency structures) on the ND control plane 1024. The ND control plane 1024 programs the ND forwarding plane 1026 with information (e.g., adjacency and route information) based on the routing structure(s). For example, the ND control plane 1024 programs the adjacency and route information into one or more forwarding table(s) 1034A-R (e.g., Forwarding Information Base (FIB), Label Forwarding Information Base (LFIB), and one or more adjacency structures) on the ND forwarding plane 1026. For layer 2 forwarding, the ND can store one or more bridging tables that are used to forward data based on the layer 2 information in that data. While the above example uses the special-purpose network device 1002, the same distributed approach 1072 can be implemented on the general purpose network device 1004 and the hybrid network device 1006.

[0091] Figure 10D illustrates that a centralized approach 1074 (also known as software defined networking (SDN)) that decouples the system that makes decisions about where traffic is sent from the underlying systems that forwards traffic to the selected destination. The illustrated centralized approach 1074 has the responsibility for the generation of reachability and forwarding information in a centralized control plane 1076 (sometimes referred to as a SDN control module, controller, network controller, OpenFlow controller, SDN controller, control plane node, network virtualization authority, or management control entity), and thus the process of neighbor discovery and topology discovery is centralized. The centralized control plane 1076 has a south bound interface 1082 with a data plane 1080 (sometime referred to the infrastructure layer, network forwarding plane, or forwarding plane (which should not be confused with aND forwarding plane)) that includes the NEs 1070A-H (sometimes referred to as switches, forwarding elements, data plane elements, or nodes). The centralized control plane 1076 includes a network controller 1078, which includes a centralized reachability and forwarding information module 1079 that determines the reachability within the network and distributes the forwarding information to the NEs 1070A-H of the data plane 1080 over the south bound interface 1082 (which may use the OpenFlow protocol). Thus, the network intelligence is centralized in the centralized control plane 1076 executing on electronic devices that are typically separate from the NDs.

[0092] For example, where the special-purpose network device 1002 is used in the data plane 1080, each of the control communication and configuration module(s) 1032A-R of the ND control plane 1024 typically include a control agent that provides the VNE side of the south bound interface 1082. In this case, the ND control plane 1024 (the processor(s) 1012 executing the control communication and configuration module(s) 1032A-R) performs its responsibility for participating in controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) through the control agent communicating with the centralized control plane 1076 to receive the forwarding information (and in some cases, the reachability information) from the centralized reachability and forwarding information module 1079 (it should be understood that in some embodiments of the invention, the control communication and configuration module(s) 1032A-R, in addition to communicating with the centralized control plane 1076, may also play some role in determining reachability and/or calculating forwarding information - albeit less so than in the case of a distributed approach; such embodiments are generally considered to fall under the centralized approach 1074, but may also be considered a hybrid approach).

[0093] While the above example uses the special-purpose network device 1002, the same centralized approach 1074 can be implemented with the general purpose network device 1004 (e.g., each of the VNE 1060A-R performs its responsibility for controlling how data (e.g., packets) is to be routed (e.g., the next hop for the data and the outgoing physical NI for that data) by communicating with the centralized control plane 1076 to receive the forwarding information (and in some cases, the reachability information) from the centralized reachability and forwarding information module 1079; it should be understood that in some embodiments of the invention, the VNEs 1060A-R, in addition to communicating with the centralized control plane 1076, may also play some role in determining reachability and/or calculating forwarding information - albeit less so than in the case of a distributed approach) and the hybrid network device 1006. In fact, the use of SDN techniques can enhance the NFV techniques typically used in the general purpose network device 1004 or hybrid network device 1006 implementations as NFV is able to support SDN by providing an infrastructure upon which the SDN software can be run, and NFV and SDN both aim to make use of commodity server hardware and physical switches. [0094] Figure 10D also shows that the centralized control plane 1076 has a north bound interface 1084 to an application layer 1086, in which resides application(s) 1088. The centralized control plane 1076 has the ability to form virtual networks 1092 (sometimes referred to as a logical forwarding plane, network services, or overlay networks (with the NEs 1070A-H of the data plane 1080 being the underlay network)) for the application(s) 1088. Thus, the centralized control plane 1076 maintains a global view of all NDs and configured NEs/VNEs, and it maps the virtual networks to the underlying NDs efficiently (including maintaining these mappings as the physical network changes either through hardware (ND, link, or ND component) failure, addition, or removal).

[0095] While Figure 10D shows the distributed approach 1072 separate from the centralized approach 1074, the effort of network control may be distributed differently or the two combined in certain embodiments of the invention. For example: 1) embodiments may generally use the centralized approach (SDN) 1074, but have certain functions delegated to the NEs (e.g., the distributed approach may be used to implement one or more of fault monitoring, performance monitoring, protection switching, and primitives for neighbor and/or topology discovery); or 2) embodiments of the invention may perform neighbor discovery and topology discovery via both the centralized control plane and the distributed protocols, and the results compared to raise exceptions where they do not agree. Such embodiments are generally considered to fall under the centralized approach 1074, but may also be considered a hybrid approach.

[0096] While Figure 10D illustrates the simple case where each of the NDs 1000A-H implements a single NE 1070A-H, it should be understood that the network control approaches described with reference to Figure 10D also work for networks where one or more of the NDs 1000A-H implement multiple VNEs (e.g., VNEs 1030A-R, VNEs 1060A-R, those in the hybrid network device 1006). Alternatively or in addition, the network controller 1078 may also emulate the implementation of multiple VNEs in a single ND. Specifically, instead of (or in addition to) implementing multiple VNEs in a single ND, the network controller 1078 may present the implementation of a VNE/NE in a single ND as multiple VNEs in the virtual networks 1092 (all in the same one of the virtual network(s) 1092, each in different ones of the virtual network(s) 1092, or some combination). For example, the network controller 1078 may cause an ND to implement a single VNE (a NE) in the underlay network, and then logically divide up the resources of that NE within the centralized control plane 1076 to present different VNEs in the virtual network(s) 1092 (where these different VNEs in the overlay networks are sharing the resources of the single VNE/NE implementation on the ND in the underlay network). [0097] On the other hand, Figures 10E and 10F respectively illustrate exemplary abstractions of NEs and VNEs that the network controller 1078 may present as part of different ones of the virtual networks 1092. Figure 10E illustrates the simple case of where each of the NDs 1000A-H implements a single NE 1070A-H (see Figure 10D), but the centralized control plane 1076 has abstracted multiple of the NEs in different NDs (the NEs 1070A-C and G-H) into (to represent) a single NE 10701 in one of the virtual network(s) 1092 of Figure 10D, according to some embodiments of the invention. Figure 10E shows that in this virtual network, the NE 10701 is coupled to NE 1070D and 1070F, which are both still coupled to NE 1070E.

[0098] Figure 10F illustrates a case where multiple VNEs (VNE 1070A.1 and VNE 1070H.1) are implemented on different NDs (ND 1000A and ND 1000H) and are coupled to each other, and where the centralized control plane 1076 has abstracted these multiple VNEs such that they appear as a single VNE 1070T within one of the virtual networks 1092 of Figure 10D, according to some embodiments of the invention. Thus, the abstraction of a NE or VNE can span multiple NDs.

[0099] While some embodiments of the invention implement the centralized control plane 1076 as a single entity (e.g., a single instance of software running on a single electronic device), alternative embodiments may spread the functionality across multiple entities for redundancy and/or scalability purposes (e.g., multiple instances of software running on different electronic devices).

[00100] Similar to the network device implementations, the electronic device(s) running the centralized control plane 1076, and thus the network controller 1078 including the centralized reachability and forwarding information module 1079, may be implemented a variety of ways (e.g., a special purpose device, a general-purpose (e.g., COTS) device, or hybrid device). These electronic device(s) would similarly include processor(s), a set or one or more physical NIs, and a non-transitory machine-readable storage medium having stored thereon the centralized control plane software. For instance, Figure 11 illustrates, a general purpose control plane device 1104 including hardware 1140 comprising a set of one or more processor(s) 1142 (which are often COTS processors) and physical NIs 1146, as well as non-transitory machine readable storage media 1148 having stored therein centralized control plane (CCP) software 1150.

[00101] In embodiments that use compute virtualization, the processor(s) 1142 typically execute software to instantiate a virtualization layer 1154 (e.g., in one embodiment the virtualization layer 1154 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 1162A-R called software containers (representing separate user spaces and also called virtualization engines, virtual private servers, or jails) that may each be used to execute a set of one or more applications; in another embodiment the virtualization layer 1154 represents a hypervisor (sometimes referred to as a virtual machine monitor (VMM)) or a hypervisor executing on top of a host operating system, and an application is run on top of a guest operating system within an instance 1162A-R called a virtual machine (which in some cases may be considered a tightly isolated form of software container) that is run by the hypervisor ; in another embodiment, an application is implemented as a unikemel, which can be generated by compiling directly with an application only a limited set of libraries (e.g., from a library operating system (LibOS) including drivers/libraries of OS services) that provide the particular OS services needed by the application, and the unikernel can run directly on hardware 1140, directly on a hypervisor represented by virtualization layer 1154 (in which case the unikemel is sometimes described as running within a LibOS virtual machine), or in a software container represented by one of instances 1162A-R). Again, in embodiments where compute virtualization is used, during operation an instance of the CCP software 1150 (illustrated as CCP instance 1176A) is executed (e.g., within the instance 1162A) on the virtualization layer 1154. In embodiments where compute virtualization is not used, the CCP instance 1176A is executed, as a unikemel or on top of a host operating system, on the “bare metal” general purpose control plane device 1104. The instantiation of the CCP instance 1176A, as well as the virtualization layer 1154 and instances 1162A-R if implemented, are collectively referred to as software instance(s) 1152.

[00102] In some embodiments, the CCP instance 1176A includes a network controller instance 1178. The network controller instance 1178 includes a centralized reachability and forwarding information module instance 1179 (which is a middleware layer providing the context of the network controller 1078 to the operating system and communicating with the various NEs), and an CCP application layer 1180 (sometimes referred to as an application layer) over the middleware layer (providing the intelligence required for various network operations such as protocols, network situational awareness, and user - interfaces). At a more abstract level, this CCP application layer 1180 within the centralized control plane 1076 works with virtual network view(s) (logical view(s) of the network) and the middleware layer provides the conversion from the virtual networks to the physical view.

[00103] The centralized control plane 1076 transmits relevant messages to the data plane 1080 based on CCP application layer 1180 calculations and middleware layer mapping for each flow. A flow may be defined as a set of packets whose headers match a given pattern of bits; in this sense, traditional IP forwarding is also flow-based forwarding where the flows are defined by the destination IP address for example; however, in other implementations, the given pattern of bits used for a flow definition may include more fields (e.g., 10 or more) in the packet headers. Different NDs/NEs/VNEs of the data plane 1080 may receive different messages, and thus different forwarding information. The data plane 1080 processes these messages and programs the appropriate flow information and corresponding actions in the forwarding tables (sometime referred to as flow tables) of the appropriate NE/VNEs, and then the NEs/VNEs map incoming packets to flows represented in the forwarding tables and forward packets based on the matches in the forwarding tables.

[00104] Standards such as OpenFlow define the protocols used for the messages, as well as a model for processing the packets. The model for processing packets includes header parsing, packet classification, and making forwarding decisions. Header parsing describes how to interpret a packet based upon a well-known set of protocols. Some protocol fields are used to build a match structure (or key) that will be used in packet classification (e.g., a first key field could be a source media access control (MAC) address, and a second key field could be a destination MAC address).

[00105] Packet classification involves executing a lookup in memory to classify the packet by determining which entry (also referred to as a forwarding table entry or flow entry) in the forwarding tables best matches the packet based upon the match structure, or key, of the forwarding table entries. It is possible that many flows represented in the forwarding table entries can correspond/match to a packet; in this case the system is typically configured to determine one forwarding table entry from the many according to a defined scheme (e.g., selecting a first forwarding table entry that is matched). Forwarding table entries include both a specific set of match criteria (a set of values or wildcards, or an indication of what portions of a packet should be compared to a particular value/values/wildcards, as defined by the matching capabilities - for specific fields in the packet header, or for some other packet content), and a set of one or more actions for the data plane to take on receiving a matching packet. For example, an action may be to push a header onto the packet, for the packet using a particular port, flood the packet, or simply drop the packet. Thus, a forwarding table entry for IPv4/IPv6 packets with a particular transmission control protocol (TCP) destination port could contain an action specifying that these packets should be dropped.

[00106] Making forwarding decisions and performing actions occurs, based upon the forwarding table entry identified during packet classification, by executing the set of actions identified in the matched forwarding table entry on the packet.

[00107] However, when an unknown packet (for example, a “missed packet” or a “match- miss” as used in OpenFlow parlance) arrives at the data plane 1080, the packet (or a subset of the packet header and content) is typically forwarded to the centralized control plane 1076. The centralized control plane 1076 will then program forwarding table entries into the data plane 1080 to accommodate packets belonging to the flow of the unknown packet. Once a specific forwarding table entry has been programmed into the data plane 1080 by the centralized control plane 1076, the next packet with matching credentials will match that forwarding table entry and take the set of actions associated with that matched entry.

[00108] A network interface (NI) may be physical or virtual; and in the context of IP, an interface address is an IP address assigned to a NI, be it a physical NI or virtual NI. A virtual NI may be associated with a physical NI, with another virtual interface, or stand on its own (e.g., a loopback interface, a point-to-point protocol interface). A NI (physical or virtual) may be numbered (a NI with an IP address) or unnumbered (a NI without an IP address). A loopback interface (and its loopback address) is a specific type of virtual NI (and IP address) of a NE/VNE (physical or virtual) often used for management purposes; where such an IP address is referred to as the nodal loopback address. The IP address(es) assigned to the NI(s) of a ND are referred to as IP addresses of that ND; at a more granular level, the IP address(es) assigned to NI(s) assigned to a NE/VNE implemented on a ND can be referred to as IP addresses of that NE VNE.

[00109] Next hop selection by the routing system for a given destination may resolve to one path (that is, a routing protocol may generate one next hop on a shortest path); but if the routing system determines there are multiple viable next hops (that is, the routing protocol generated forwarding solution offers more than one next hop on a shortest path - multiple equal cost next hops), some additional criteria is used - for instance, in a connectionless network, Equal Cost Multi Path (ECMP) (also known as Equal Cost Multi Pathing, multipath forwarding and IP multipath) may be used (e.g., typical implementations use as the criteria particular header fields to ensure that the packets of a particular packet flow are always forwarded on the same next hop to preserve packet flow ordering). For purposes of multipath forwarding, a packet flow is defined as a set of packets that share an ordering constraint. As an example, the set of packets in a particular TCP transfer sequence need to arrive in order, else the TCP logic will interpret the out of order delivery as congestion and slow the TCP transfer rate down.

[00110] A Layer 3 (L3) Link Aggregation (LAG) link is a link directly connecting two NDs with multiple IP-addressed link paths (each link path is assigned a different IP address), and a load distribution decision across these different link paths is performed at the ND forwarding plane; in which case, a load distribution decision is made between the link paths.

[00111] Some NDs include functionality for authentication, authorization, and accounting (AAA) protocols (e.g., RADIUS (Remote Authentication Dial-In User Service), Diameter, and/or TACACS+ (Terminal Access Controller Access Control System Plus). AAA can be provided through a client/server model, where the AAA client is implemented on a ND and the AAA server can be implemented either locally on the ND or on a remote electronic device coupled with the ND. Authentication is the process of identifying and verifying a subscriber. For instance, a subscriber might be identified by a combination of a username and a password or through a unique key. Authorization determines what a subscriber can do after being authenticated, such as gaining access to certain electronic device information resources (e.g., through the use of access control policies). Accounting is recording user activity. By way of a summary example, end user devices may be coupled (e.g., through an access network) through an edge ND (supporting AAA processing) coupled to core NDs coupled to electronic devices implementing servers of service/content providers. AAA processing is performed to identify for a subscriber the subscriber record stored in the AAA server for that subscriber. A subscriber record includes a set of attributes (e.g., subscriber name, password, authentication information, access control information, rate-limiting information, policing information) used during processing of that subscriber’s traffic.

[00112] Certain NDs (e.g., certain edge NDs) internally represent end user devices (or sometimes customer premise equipment (CPE) such as a residential gateway (e.g., a router, modem)) using subscriber circuits. A subscriber circuit uniquely identifies within the ND a subscriber session and typically exists for the lifetime of the session. Thus, a ND typically allocates a subscriber circuit when the subscriber connects to that ND, and correspondingly de allocates that subscriber circuit when that subscriber disconnects. Each subscriber session represents a distinguishable flow of packets communicated between the ND and an end user device (or sometimes CPE such as a residential gateway or modem) using a protocol, such as the point-to-point protocol over another protocol (PPPoX) (e.g., where X is Ethernet or Asynchronous Transfer Mode (ATM)), Ethernet, 802. IQ Virtual LAN (VLAN), Internet Protocol, or ATM). A subscriber session can be initiated using a variety of mechanisms (e.g., manual provisioning a dynamic host configuration protocol (DHCP), DHCP/client-less internet protocol service (CLIPS) or Media Access Control (MAC) address tracking). For example, the point-to-point protocol (PPP) is commonly used for digital subscriber line (DSL) services and requires installation of a PPP client that enables the subscriber to enter a username and a password, which in turn may be used to select a subscriber record. When DHCP is used (e.g., for cable modem services), a username typically is not provided; but in such situations other information (e.g., information that includes the MAC address of the hardware in the end user device (or CPE)) is provided. The use of DHCP and CLIPS on the ND captures the MAC addresses and uses these addresses to distinguish subscribers and access their subscriber records. [00113] A virtual circuit (VC), synonymous with virtual connection and virtual channel, is a connection oriented communication service that is delivered by means of packet mode communication. Virtual circuit communication resembles circuit switching, since both are connection oriented, meaning that in both cases data is delivered in correct order, and signaling overhead is required during a connection establishment phase. Virtual circuits may exist at different layers. For example, at layer 4, a connection oriented transport layer datalink protocol such as Transmission Control Protocol (TCP) may rely on a connectionless packet switching network layer protocol such as IP, where different packets may be routed over different paths, and thus be delivered out of order. Where a reliable virtual circuit is established with TCP on top of the underlying unreliable and connectionless IP protocol, the virtual circuit is identified by the source and destination network socket address pair, i.e. the sender and receiver IP address and port number. However, a virtual circuit is possible since TCP includes segment numbering and reordering on the receiver side to prevent out-of-order delivery. Virtual circuits are also possible at Layer 3 (network layer) and Layer 2 (datalink layer); such virtual circuit protocols are based on connection oriented packet switching, meaning that data is always delivered along the same network path, i.e. through the same NEs/VNEs. In such protocols, the packets are not routed individually and complete addressing information is not provided in the header of each data packet; only a small virtual channel identifier (VCI) is required in each packet; and routing information is transferred to the NEs/VNEs during the connection establishment phase; switching only involves looking up the virtual channel identifier in a table rather than analyzing a complete address. Examples of network layer and datalink layer virtual circuit protocols, where data always is delivered over the same path: X.25, where the VC is identified by a virtual channel identifier (VCI); Frame relay, where the VC is identified by a VCI; Asynchronous Transfer Mode (ATM), where the circuit is identified by a virtual path identifier (VPI) and virtual channel identifier (VCI) pair; General Packet Radio Service (GPRS); and Multiprotocol label switching (MPLS), which can be used for IP over virtual circuits (Each circuit is identified by a label).

[00114] Certain NDs (e.g., certain edge NDs) use a hierarchy of circuits. The leaf nodes of the hierarchy of circuits are subscriber circuits. The subscriber circuits have parent circuits in the hierarchy that typically represent aggregations of multiple subscriber circuits, and thus the network segments and elements used to provide access network connectivity of those end user devices to the ND. These parent circuits may represent physical or logical aggregations of subscriber circuits (e.g., a virtual local area network (VLAN), a permanent virtual circuit (PVC) (e.g., for Asynchronous Transfer Mode (ATM)), a circuit-group, a channel, a pseudo-wire, a physical NI of the ND, and a link aggregation group). A circuit-group is a virtual construct that allows various sets of circuits to be grouped together for configuration purposes, for example aggregate rate control. A pseudo-wire is an emulation of a layer 2 point-to-point connection- oriented service. A link aggregation group is a virtual construct that merges multiple physical NIs for purposes of bandwidth aggregation and redundancy. Thus, the parent circuits physically or logically encapsulate the subscriber circuits.

[00115] Each VNE (e.g., a virtual router, a virtual bridge (which may act as a virtual switch instance in a Virtual Private LAN Service (VPLS) is typically independently administrable. For example, in the case of multiple virtual routers, each of the virtual routers may share system resources but is separate from the other virtual routers regarding its management domain, AAA (authentication, authorization, and accounting) name space, IP address, and routing database(s). Multiple VNEs may be employed in an edge ND to provide direct network access and/or different classes of services for subscribers of service and/or content providers.

[00116] Within certain NDs, “interfaces” that are independent of physical NIs may be configured as part of the VNEs to provide higher-layer protocol and service information (e.g., Layer 3 addressing). The subscriber records in the AAA server identify, in addition to the other subscriber configuration requirements, to which context (e.g., which of the VNEs/NEs) the corresponding subscribers should be bound within the ND. As used herein, a binding forms an association between a physical entity (e.g., physical NI, channel) or a logical entity (e.g., circuit such as a subscriber circuit or logical circuit (a set of one or more subscriber circuits)) and a context’s interface over which network protocols (e.g., routing protocols, bridging protocols) are configured for that context. Subscriber data flows on the physical entity when some higher-layer protocol interface is configured and associated with that physical entity.

[00117] Some NDs provide support for implementing VPNs (Virtual Private Networks) (e.g., Layer 2 VPNs and/or Layer 3 VPNs). For example, the ND where a provider’s network and a customer’s network are coupled are respectively referred to as PEs (Provider Edge) and CEs (Customer Edge). In a Layer 2 VPN, forwarding typically is performed on the CE(s) on either end of the VPN and traffic is sent across the network (e.g., through one or more PEs coupled by other NDs). Layer 2 circuits are configured between the CEs and PEs (e.g., an Ethernet port, an ATM permanent virtual circuit (PVC), a Frame Relay PVC). In a Layer 3 VPN, routing typically is performed by the PEs. By way of example, an edge ND that supports multiple VNEs may be deployed as a PE; and a VNE may be configured with a VPN protocol, and thus that VNE is referred as a VPN VNE.

[00118] Some NDs provide support for VPLS (Virtual Private LAN Service). For example, in a VPLS network, end user devices access content/services provided through the VPLS network by coupling to CEs, which are coupled through PEs coupled by other NDs. VPLS networks can be used for implementing triple play network applications (e.g., data applications (e.g., high speed Internet access), video applications (e.g., television service such as IPTV (Internet Protocol Television), VoD (Video-on-Demand) service), and voice applications (e.g., VoIP (Voice over Internet Protocol) service)), VPN services, etc. VPLS is a type of layer 2 VPN that can be used for multi-point connectivity. VPLS networks also allow end use devices that are coupled with CEs at separate geographical locations to communicate with each other across a Wide Area Network (WAN) as if they were directly attached to each other in a Local Area Network (LAN) (referred to as an emulated LAN).

[00119] In VPLS networks, each CE typically attaches, possibly through an access network (wired and/or wireless), to a bridge module of a PE via an attachment circuit (e.g., a virtual link or connection between the CE and the PE). The bridge module of the PE attaches to an emulated LAN through an emulated LAN interface. Each bridge module acts as a “Virtual Switch Instance” (VSI) by maintaining a forwarding table that maps MAC addresses to pseudowires and attachment circuits. PEs forward frames (received from CEs) to destinations (e.g., other CEs, other PEs) based on the MAC destination address field included in those frames.

[00120] While the invention has been described in terms of several embodiments, those skilled in the art will recognize that the invention is not limited to the embodiments described, can be practiced with modification and alteration within the spirit and scope of the appended claims.

The description is thus to be regarded as illustrative instead of limiting.

Claims

CLAIMS What is claimed is:

1. A method (900) for processing packets (104) in a network system (100), the method comprising: receiving (902) a plurality of packets (104) from a set of operator networks (108); determining (904) a class (A, B, or C) from a plurality of classes (A-C) for each packet in the plurality of packets based on attributes associated with each packet; adding (906) each packet to a delay queue (320) from a plurality of delay queues (320i- 320₃), wherein each delay queue is associated with a different class from the plurality of classes and each packet from the plurality of packets is added to a delay queue according to a class determined for the packet; updating (908) a flow table (322) based on the plurality of packets being added to corresponding delay queues in the plurality of delay queues, wherein the flow table tracks the plurality of delay queues; and flushing (914) a first delay queue from the plurality of delay queues and associated with a first class (A) from the plurality of classes based on the flow table in response to determining occurrence of a first event such that each packet in the first delay queue, which are associated with the first class, is transmitted towards a first destination.

2. The method of claim 1, wherein the attributes associated with each packet includes one or more of (1) an application identifier, (2) a destination port number, (3) a user identifier, (4) a user selector, (5) a barrier selector, (6) a source address, (7) a source port number, (8) a destination address, and (9) information associated with a virtual local area network (VLAN) or an Internet Protocol (IP).

3. The method of claim 1, wherein the flow table includes one or more of (1) a flow identifier column (324A) that identifies a flow of packets from a corresponding class, (2) a first packet time column (324B) that indicates the time a first packet is added to an associated empty delay queue, (3) a last packet time column (324C) that indicates the time that the last packet of the associated delay queue is stored in the delay queue, and (4) a pointer to a delay queue column (324D) that indicates a location of the associated delay queue.

4. The method of claim 1, wherein the first event includes one or more of (1) a time period from when a last packet of the first class was received is equal to or larger than a first predefined time period (Tl), (2) a packet has been enqueued in the first delay queue for more than or equal to a second predefined time period (T2), and (3) a number of enqueued packets in the first delay queue reaches a predefined threshold (N_MAX).

5. The method of claim 4, wherein the first predefined time period, the second predefined time period, and the predefined threshold are independently set for each delay queue in the plurality of delay queues; and wherein the first predefined time period, the second predefined time period, and the predefined threshold are independently set for each delay queue based on statistics associated with each delay queue.

6. The method of claim 1, further comprising: flushing (916) a second delay queue (3202) from the plurality of delay queues and associated with a second class (B) from the plurality of classes based on the flow table in response to determining occurrence of a second event such that each packet in the second delay queue, which are associated with the second class, is transmitted towards a second destination.

7. The method of claim 6, further comprising: prioritizing (910) flushing of the first delay queue or flushing of the second delay queue when the first and second events are detected within a designated time period, such that either the first delay queue is flushed prior to the second delay queue or the second delay queue is flushed prior to the first delay queue.

8. The method of claim 7, wherein the prioritizing prioritizes the flushing of the first delay queue prior to flushing of the second delay queue when (1) the first delay queue has more packets than the second delay queue or (2) a first packet in the first delay queue is older than a first packet in the second delay queue.

9. The method of claim 1, further comprising: optimizing (912) the packets in the first delay queue prior to transmission to the first destination, wherein the optimizing includes one or more of Transmission Control Protocol (TCP) Acknowledgement (ACK) coalescing and combining each of the packets in the first delay queue into a single frame.

10. The method of claim 1, wherein each packet from the first delay queue is passed to the first destination such that the packets are processed by a network interface card of the first destination, including matching each packet to rules (602) stored in a hierarchical memory system of the first destination, including a first memory that stores a first set of rules and a second memory that stores a second set of rules, wherein the first memory is logically higher in the hierarchical memory system than the second memory and the first set of rules includes less rules than the second set of rules; and wherein each packet from the first delay queue matches to a single rule from the first and second set of rules.

11. The method of claim 1, wherein a rule (602) associated with a first packet received by the first destination is maintained in a first cache memory located closer hierarchically to a processor of the first destination that a second cache memory such that the first packet and at least one additional packet received by the first destination immediately after the first packet and which has a same class as the first packet, is processed according to the rule and data or an instruction associated with the rule and without the need for retrieval of the rule or the data and instruction form the second cache memory or a context switch by the processor.

12. A non-transitory machine -readable storage medium that provides instructions that, when executed by a processor, will cause said processor to perform operations comprising: receiving (902) a plurality of packets (104) from a set of operator networks (108); determining (904) a class (A, B, or C) from a plurality of classes (A-C) for each packet in the plurality of packets based on attributes associated with each packet; adding (906) each packet to a delay queue (320) from a plurality of delay queues (320i- 32O3), wherein each delay queue is associated with a different class from the plurality of classes and each packet from the plurality of packets is added to a delay queue according to a class determined for the packet; updating (908) a flow table (322) based on the plurality of packets being added to corresponding delay queues in the plurality of delay queues, wherein the flow table tracks the plurality of delay queues; and flushing (914) a first delay queue (320i) from the plurality of delay queues and associated with a first class (A) from the plurality of classes based on the flow table in response to determining occurrence of a first event such that each packet in the first delay queue, which are associated with the first class, is transmitted towards a first destination.

13. The non-transitory machine-readable storage medium of claim 12, wherein the attributes associated with each packet includes one or more of (1) an application identifier, (2) a destination port number, (3) a user identifier, (4) a user selector, (5) a barrier selector, (6) a source address, (7) a source port number, (8) a destination address, and (9) information associated with a virtual local area network (VLAN) and/or an Internet Protocol (IP).

14. The non-transitory machine-readable storage medium of claim 12, wherein the flow table includes one or more of (1) a flow identifier column (324A) that identifies a flow of packets from a corresponding class, (2) a first packet time column (324B) that indicates the time a first packet is added to an associated empty delay queue, (3) a last packet time column (324C) that indicates the time that the last packet of the associated delay queue is stored in the delay queue, and (4) a pointer to a delay queue column (324D) that indicates a location of the associated delay queue.

15. The non-transitory machine-readable storage medium of claim 12, wherein the first event includes one or more of (1) a time period from when a last packet of the first class was received is equal to or larger than a first predefined time period (Tl), (2) a packet has been enqueued in the first delay queue for more than or equal to a second predefined time period (T2), and (3) a number of enqueued packets in the first delay queue reaches a predefined threshold (N_MAX).

16. The non-transitory machine-readable storage medium of claim 15, wherein the first predefined time period, the second predefined time period, and the predefined threshold are independently set for each delay queue in the plurality of delay queues; and wherein the first predefined time period, the second predefined time period, and the predefined threshold are independently set for each delay queue based on statistics associated with each delay queue.

17. The non-transitory machine-readable storage medium of claim 14, wherein the instructions, when executed by the processor, will cause said processor to further perform operations comprising: flushing (914) a second delay queue from the plurality of delay queues and associated with a second class (B) from the plurality of classes based on the flow table in response to determining occurrence of a second event such that each packet in the second delay queue, which are associated with the second class, is transmitted towards a second destination.

18. The non-transitory machine-readable storage medium of claim 17, wherein the instructions, when executed by the processor, will cause said processor to further perform operations comprising: prioritizing (910) flushing of the first delay queue or flushing of the second delay queue when the first and second events are detected within a designated time period, such that either the first delay queue is flushed prior to the second delay queue or the second delay queue is flushed prior to the first delay queue.

19. The non-transitory machine-readable storage medium of claim 18, wherein the prioritizing prioritizes the flushing of the first delay queue prior to flushing of the second delay queue when (1) the first delay queue has more packets than the second delay queue or (2) a first packet in the first delay queue is older than a first packet in the second delay queue.

20. The non-transitory machine-readable storage medium of claim 17, wherein the instructions, when executed by the processor, will cause said processor to further perform operations comprising: optimizing (912) the packets in the first delay queue prior to transmission to the first destination, wherein the optimizing includes one or more of Transmission Control Protocol (TCP) Acknowledgement (ACK) coalescing and combining each of the packets in the first delay queue into a single frame.

21. The non-transitory machine-readable storage medium of claim 12, wherein each packet from the first delay queue is passed to the first destination such that the packets are processed by a network interface card of the first destination, including matching each packet to rules (602) stored in a hierarchical memory system of the first destination, including a first memory that stores a first set of rules and a second memory that stores a second set of rules, wherein the first memory is logically higher in the hierarchical memory system than the second memory and the first set of rules includes less rules than the second set of rules; and wherein each packet from the first delay queue matches to a single rule from the first and second set of rules.