WO2020165910A1

WO2020165910A1 - Technique for providing priority-aware caching in the fast-path of a virtual switch

Info

Publication number: WO2020165910A1
Application number: PCT/IN2019/050123
Authority: WO
Inventors: Ashvin Lakshmikantha
Original assignee: Telefonaktiebolaget Lm Ericsson (Publ)
Priority date: 2019-02-16
Filing date: 2019-02-16
Publication date: 2020-08-20

Abstract

A method by a virtual switch to provide priority-aware caching in a fast-path of the virtual switch. The method includes receiving a packet belonging to a flow, processing the packet through a packet processing pipeline responsive to a determination that the packet does not match any entries in an exact match cache, where the exact match cache includes a plurality of regions each associated with a different priority level, determining, as a result of the processing of the packet through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the flow and a priority level of the flow, and inserting an entry for the flow into a region of the exact match cache associated with the determined priority level of the flow, where the entry for the flow specifies the set of actions to perform for subsequent packets belonging to the flow.

Description

TECHNIQUE FOR PROVIDING PRIORITY- AWARE CACHING IN THE FAST-PATH

OF A VIRTUAL SWITCH

TECHNICAL FIELD

[0001] Embodiments of the invention relate to the field of computer networks, and more specifically to providing priority-aware caching in the fast-path of virtual switches.

BACKGROUND ART

[0002] A virtual switch is a software application that facilitates communication between virtual machines (VMs) and between VMs and other network elements. When a virtual switch (e.g., Open vSwitch) receives the first packet belonging to a new flow, it processes the packet through its packet processing pipeline (e.g., an OpenFlow pipeline) to determine the set of actions to perform for the packet, which typically involves performing several flow table lookups. The set of actions may include, for example, modifying one or more packet header fields, encapsulating/decapsulating the packet, and forwarding the packet out of a particular port. Processing the packet through the packet processing pipeline can take a relatively long time (e.g., due to having to perform several flow table lookups) and is hence referred to as the“slow-path.”

[0003] Virtual switches may use flow caching techniques to improve packet processing performance. For example, once the virtual switch determines the set of actions to apply for the first packet belonging to the flow (e.g., based on processing the packet through the packet processing pipeline), the virtual switch may insert an entry for the flow into an exact match cache, where the entry specifies the set of actions to perform for subsequent packets belonging to the same flow. The virtual switch may then process each subsequent packet belonging to the flow based on a single lookup in the exact match cache without having to process that packet through the packet processing pipeline.

[0004] The exact match cache may be implemented as a hash table that uses the five-tuple or ten-tuple of packets as the key (that uniquely identifies the different flows) and the set of actions to perform as the corresponding value. Lookups in the exact match cache can be performed in constant time (0(1) in Big-0 notation) and thus the use of the exact match cache significantly improves packet processing performance.

[0005] The exact match cache is typically designed to fit within the Ll-cache of the Central Processing Unit (CPU) to ensure high performance. Deviating from this guideline may cause Ll-cache misses and cause throughput to be significantly reduced. The default configuration for Open vSwitch allows for a maximum of 8,192 entries in the exact match cache, which can be implemented as a hash table with the 8,192 entries arranged in 4,096 rows with two buckets per row (to minimize collisions).

[0006] When the number of active flows being received by the virtual switch gets large, the exact match cache may not be able to store entries for all of the active flows. Thus, the virtual switch may also include a secondary cache to accommodate additional flows. The secondary cache is not an exact match cache but supports wild card matching. The data in this secondary cache may be organized in a tree structure to allow lookups with wildcarded packet fields. Thus, unlike entries in the exact match cache which match specific flows (sometimes referred to as“microflows”), an entry in the secondary cache may match multiple flows. The secondary cache may be referred to as a megaflow cache or an aggregated cache. The aggregated cache is typically stored in main memory (e.g., Random Access Memory) and generally takes longer to access compared to the exact match cache (e.g., aggregated cache accesses typically take 80-100 CPU clock cycles per access). As such, frequent consultation of the aggregated cache may reduce throughput.

[0007] In general, when the virtual switch receives a packet belonging to a flow, it first performs a lookup in the exact match cache. If a matching entry is found in the exact match cache, then the virtual switch performs the set of actions specified by that entry. However, if the virtual switch does not find a matching entry in the exact match cache, then the virtual switch performs a lookup in the aggregated cache. If a matching entry is found in the aggregated cache, then the virtual switch performs the set of actions specified by that entry. However, if the virtual switch does not find a matching entry in the aggregated cache, then the virtual switch resorts to processing the packet through the packet processing pipeline (the slow-path). In general, processing the packet using the exact match cache or the aggregated cache is significantly faster than processing the packet through the packet processing pipeline and is hence referred to as the“fast-path.”

[0008] To improve packet processing performance, when the virtual switch receives a packet belonging to a flow, it may insert an entry for the flow into the exact match cache. If there is a collision in the exact match cache (e.g., both buckets are full at the corresponding row in the exact match cache), then the new entry replaces one of the existing entries (thereby causing an existing entry to be evicted). Entries in the exact match cache may be replaced using a least recently used replacement policy. The eviction of the existing entry would cause a future cache miss for the flow corresponding to that entry, thereby negatively impacting the packet processing performance for that flow. The fast-path of the virtual switch, and more specifically the exact match cache, is agnostic to traffic priority or Quality of Service (QoS) considerations. There is no preferential treatment awarded to higher priority flows when there are collisions in the exact match cache. As a result, it is possible for an entry for a lower priority flow to replace an entry for a higher priority flow in the exact match cache, which negatively impacts the packet processing performance for the higher priority flow.

SUMMARY

[0009] A method by a virtual switch implemented by one or more network devices to provide priority-aware caching in a fast-path of the virtual switch. The method includes receiving a packet belonging to a first flow, processing the packet belonging to the first flow through a packet processing pipeline of the virtual switch in response to a determination that the packet belonging to the first flow does not match any entries in an exact match cache, where the exact match cache includes a plurality of regions, and where each of the plurality of regions is associated with a different one of a plurality of priority levels, determining, as a result of the processing of the packet belonging to the first flow through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the first flow and a priority level of the first flow, and inserting an entry for the first flow into a region of the exact match cache associated with the determined priority level of the first flow, where the entry for the first flow specifies the set of actions to perform for subsequent packets belonging to the first flow.

[0010] A network device configured to implement a virtual switch that provides priority- aware caching in a fast-path of the virtual switch. The network device includes a set of one or more processors and a non-transitory computer-readable storage medium storing instructions, which when executed by the set of one or more processors, causes the network device to receive a packet belonging to a first flow, process the packet belonging to the first flow through a packet processing pipeline of the virtual switch in response to a determination that the packet belonging to the first flow does not match any entries in an exact match cache, where the exact match cache includes a plurality of regions, and where each of the plurality of regions is associated with a different one of a plurality of priority levels, determine, as a result of the processing of the packet belonging to the first flow through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the first flow and a priority level of the first flow, and insert an entry for the first flow into a region of the exact match cache associated with the determined priority level of the first flow, where the entry for the first flow specifies the set of actions to perform for subsequent packets belonging to the first flow.

[0011] A non-transitory computer-readable storage medium storing instructions, which when executed by a set of one or more processors of a network device implementing a virtual switch, causes the network device to perform operations for providing priority-aware caching in a fast-path of the virtual switch. The operations include receiving a packet belonging to a first flow, processing the packet belonging to the first flow through a packet processing pipeline of the virtual switch in response to a determination that the packet belonging to the first flow does not match any entries in an exact match cache, where the exact match cache includes a plurality of regions, and where each of the plurality of regions is associated with a different one of a plurality of priority levels, determining, as a result of the processing of the packet belonging to the first flow through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the first flow and a priority level of the first flow, and inserting an entry for the first flow into a region of the exact match cache associated with the determined priority level of the first flow, where the entry for the first flow specifies the set of actions to perform for subsequent packets belonging to the first flow.

BRIEF DESCRIPTION OF THE DRAWINGS

[0012] 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:

[0013] Figure 1 is a block diagram of a network device implementing a virtual switch that provides priority- aw are caching in the fast-path, according to some embodiments.

[0014] Figure 2 is a diagram illustrating a scenario that may occur in existing virtual switches where an entry for a lower priority flow replaces an entry for a higher priority flow in the exact match cache.

[0015] Figure 3A is a diagram illustrating an entry for a low priority flow being inserted into the exact match cache, according to some embodiments.

[0016] Figure 3B is a diagram illustrating an entry for an evicted flow being re-inserted into the exact match cache, according to some embodiments.

[0017] Figure 4 is a flow diagram of a process for providing priority-aware caching in the fast-path of a virtual switch, according to some embodiments. [0018] Figure 5A 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.

[0019] Figure 5B illustrates an exemplary way to implement a special-purpose network device according to some embodiments of the invention.

[0020] Figure 5C illustrates various exemplary ways in which virtual network elements (VNEs) may be coupled according to some embodiments of the invention.

[0021] Figure 5D 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.

[0022] Figure 5E 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.

[0023] Figure 5F 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.

[0024] Figure 6 illustrates a general purpose control plane device with centralized control plane (CCP) software 650), according to some embodiments of the invention.

DETAILED DESCRIPTION

[0025] The following description describes methods and apparatus for providing priority- aware caching in the fast-path of a virtual switch. 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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/medium), 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.

[0030] 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).

[0031] As used herein, a“flow” generally refers to a sequence of packets that share a common set of attributes (e.g., packet header values) and that are to be treated the same or similarly for packet processing/forwarding purposes. In some embodiments, a flow may be uniquely identified by a five-tuple (e.g., source Internet Protocol (IP) address, source port, destination IP address, destination port, and protocol) or ten-tuple (e.g., two layers of five- tuples).

[0032] As mentioned above, a virtual switch may insert entries for flows into the exact match cache to improve packet processing performance. With existing virtual switches, if there is a collision in the exact match cache, then the virtual switch evicts one of the existing entries from the exact match cache (e.g., using a least recently used replacement policy) to make room for the new entry. The eviction of the existing entry would cause a future cache miss (in the exact match cache) for the flow corresponding to that entry, thereby negatively impacting the packet processing performance for that flow. The fast-path of the virtual switch, and more specifically the exact match cache, is agnostic to traffic priority or Quality of Service (QoS) considerations. There is no preferential treatment awarded to higher priority flows when there are collisions in the exact match cache. As a result, it is possible for an entry for a lower priority flow to replace an entry for a higher priority flow in the exact match cache, which negatively impacts the performance of the higher priority flows.

[0033] Embodiments described herein overcome some of the disadvantages of existing virtual switches by providing priority-aware caching in the fast-path. According to some embodiments, a virtual switch includes an exact match cache that is partitioned into multiple regions, where each region is associated with a different priority level. When the virtual switch receives the first packet belonging to a flow, it processes the packet through a packet processing pipeline of the virtual switch. The virtual switch determines, as a result of processing of the packet through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the flow and the priority level of the flow. The virtual switch then inserts an entry for the flow into the region of the exact match cache associated with the determined priority level of the flow, where the entry for the first flow specifies the set of actions to perform for subsequent packets belonging to the flow. Partitioning the exact match cache into different regions and inserting entries into the regions according to flow priority levels ensures that entries for lower priority flows do not replace/evict entries for higher priority flows in the exact match cache. When the virtual switch receives a subsequent packet belonging to the flow, it iteratively matches the subsequent packet against entries in the exact match cache region by region in order of priority level until finding the entry for the flow. Upon finding the entry for the flow in the exact match cache, the virtual switch performs the set of actions specified by that entry without processing the subsequent packet through the packet processing pipeline. Various embodiments are described and claimed herein below.

[0034] Figure 1 is a block diagram of a network device implementing a virtual switch that provides priority-aware caching in the fast-path, according to some embodiments. As shown in the diagram, the network device 100 executes a virtual switch daemon 110 in user space and executes a kernel module 120 in kernel space. Also, the network device 100 executes virtual machines 160A-Z. The virtual switch daemon 110 and the kernel module 120 may communicate with each other (e.g., using an inter-process communication interface such as Netlink) to collectively implement a virtual switch 190 that facilitates communication between the virtual machines 160 and between the virtual machines 160 and other network elements (e.g., the virtual switch 190 may facilitate communication between virtual machines 160 and network elements that are external to the network device 100 via the network interface card(s) 170).

[0035] The virtual switch daemon 110 includes a packet processing pipeline 115 that is used for determining how to process incoming packets. In one embodiment, the packet processing pipeline 115 includes multiple flow tables, where each flow table includes one or more flow entries. Each flow entry may include a match criteria and a corresponding set of actions to perform. The virtual switch daemon 110 may process a packet through the packet processing pipeline 115 by matching the packet against the flow entries of the flow tables. When a matching entry is found, the set of actions specified by that entry is performed. The set of actions may include, for example, directing the packet to another flow table in the packet processing pipeline 115, modifying one or more packet header fields, encapsulating/decapsulating the packet, and/or forwarding the packet out of a particular port. In one embodiment, the packet processing pipeline is an OpenFlow pipeline. As mentioned above, processing packets through the packet processing pipeline 115 can take a relatively long time and is hence referred to as the“slow-path.”

[0036] In one embodiment, the network device 100 is communicatively coupled to a Software Defined Networking (SDN) controller 180 (sometimes simply referred to as “controller”). The controller 180 may communicate with the virtual switch daemon 110 to program the packet processing pipeline 115 to implement the desired packet processing behavior. In one embodiment, the controller 180 communicates with the virtual switch daemon 110 using OpenFlow or a similar southbound communications protocol.

[0037] The kernel module 120 (which may be implemented as a module of an operating system (e.g., Linux operating system) executing on the network device 100) includes an aggregated cache 125 and an exact match cache 130. As mentioned above, the aggregated cache 125 and the exact match cache 130 may be used to provide a“fast-path” that improves packet processing performance compared to processing packets through the packet processing pipeline 115 (the“slow-path”). While a certain arrangement of components is shown in the diagram, it should be understood that this is purely exemplary and that other embodiments may arrange the components differently to achieve the same/similar functionality. For example, in some embodiments, the aggregated cache 125 and the exact match cache 130 may be implemented/maintained in user space instead of kernel space.

[0038] As mentioned above, with existing virtual switches, the fast-path of the virtual switch, and more specifically the exact match cache, is agnostic to traffic priority or Quality of Service (QoS) considerations. There is no preferential treatment awarded to higher priority flows when there are collisions in the exact match cache. As a result, it is possible for an entry for a lower priority flow to replace an entry for a higher priority flow in the exact match cache, which negatively impacts the performance of the higher priority flows. Such a scenario is illustrated in Figure 2.

[0039] Figure 2 is a diagram illustrating a scenario that may occur in existing virtual switches where an entry for a lower priority flow replaces an entry for a higher priority flow in the exact match cache. Referring to Figure 2, the example assumes that the exact match cache 130 is implemented as a hash table with 4,096 rows (each row corresponding to a hash value), where each row has two buckets (so the exact match cache 130 can store a total of 8,192 entries). Also, the example assumes that the virtual switch 190 is receiving at least three active flows (flows having flow identifiers (IDs) Oxfeal, 0x6578, and 0x3879, respectively). The flow having flow ID Oxfeal is considered a high priority flow (e.g., carrying high performance computing (HPC) traffic), the flow having flow ID 0x6578 is considered a medium priority flow (e.g., carrying storage area network (SAN) traffic), and the flow having flow ID 0x3879 is considered a low priority flow (e.g., carrying wide area network (WAN) traffic). It is possible that multiple flows map to the same hash value in the exact match cache 130. In this example, the high priority flow, the medium priority flow, and the low priority flow may all map to a hash value of 1. Also, in this example, the exact match cache 130 currently includes an entry for the high priority flow (flow ID Oxfeal) in bucket B1 of the row corresponding to the hash value of 1 and an entry for the medium priority flow (flow ID 0x6578) in bucket B2 of the row corresponding to the hash value of 1. Thus, the row corresponding to the hash value of 1 is currently fully occupied (both buckets in that row are occupied). [0040] When the virtual switch 190 receives a packet belonging to the low priority flow (flow ID 0x3879), it inserts an entry for that flow into the exact match cache 130 (into the row corresponding to the hash value of the flow - which in this example is the row corresponding to the hash value of 1 since the low priority flow maps to the hash value of 1). In this example, since the row corresponding to the hash value of 1 is currently fully occupied, the virtual switch 190 needs to evict one of the existing entries in that row to make room for the new entry. The virtual switch 190 may choose which entry to evict based on a predefined replacement policy such as a least recently used replacement policy. In this example, regardless of which entry the virtual switch 190 chooses to evict, the end result is that an entry for a higher priority flow (either flow ID 0x4781 or flow ID 0x6578) is evicted to make room for the entry for the low priority flow (flow ID 0x3879), which will cause a future cache miss for the higher priority flow. As such, the packet processing performance for a higher priority flow is negatively impacted by a lower priority flow, and this can happen even when there is no congestion at the virtual switch 190.

[0041] As will be described in further detail herein, embodiments address some of the drawbacks of existing virtual switches (e.g., the drawback mentioned above where an entry for a lower priority flow can replace/evict an entry for a higher priority flow) by providing priority-aware caching in the fast-path. Returning to Figure 1, in one embodiment, the exact match cache 130 is partitioned into multiple regions, where each region is associated with a different priority level. In the example shown in Figure 1, the exact match cache 130 is partitioned into a high priority region 140, a medium priority region 145, and a low priority region 150. The partitioning of the exact match cache 130 shown in the diagram is by way of example and not intended to be limiting. It should be understood that different embodiments may partition the exact match cache 130 into more or less regions depending on the number of priority levels being used. While, the Ethernet standard supports 8 different priorities and the Internet Engineering Task Force (IETF) standard supports 64 different Differentiated Services Code Points (DSCPs), it may not be necessary to partition the exact match cache 130 into 8 or 64 different regions. In one embodiment, multiple Ethernet priorities or DSCPs can be mapped to the same priority level/region in the exact match cache 130 without significantly impacting the end-user experience. Different implementations may partition the exact match cache 130 differently depending on traffic characteristics. For most implementations, partitioning the exact match cache 130 into two to four partitions may be sufficient to provide acceptable QoS. While some embodiments may use a static partitioning of the exact match cache 130 (where the number of regions and/or size of each region is fixed), other embodiments may dynamically partition the exact match cache 130 (e.g., such that the number of regions and/or the size of each region may change during operation of the virtual switch 190 based on the observed/historical traffic characteristics). In one embodiment, the exact match cache 130 is sized to fit within the Ll- cache of the CPU to ensure high performance.

[0042] When the virtual switch 190 receives the first packet belonging to a new flow, it processes the packet through the packet processing pipeline 115 to determine the set of actions to perform for the packet and to determine the priority level of the flow. The set of actions may include, for example, modifying one or more packet header fields, encapsulating/decapsulating the packet, and forwarding the packet out of a particular port. The priority level of the flow may be determined based on one or more factors such as the input port from which the packet belonging to the flow was received, the Virtual Local Area Network (VLAN) over which the packet belonging to the flow was received, the 802. Ip bits of the packet belonging to the flow, the DSCP bits of the packet belonging to the flow, and/or the destination IP address of the packet belonging to the flow. These factors are provided by way of example and not intended to be limiting. It should be understood that embodiments may use other factors/attributes to determine the priority level of the flow.

[0043] Upon processing the packet belonging to the flow through the packet processing pipeline 115, the virtual switch 190 may insert an entry for the flow into the region of the exact match cache 130 associated with the determined priority level of the flow. For example, if the virtual switch 190 determines, as a result of processing the packet belonging to the flow through the packet processing pipeline 115, that the flow is a high priority flow, then the virtual switch 190 inserts an entry for the flow into the high priority region 140 of the exact match cache 130. Otherwise, if the virtual switch 190 determines that the flow is a medium priority flow, then the virtual switch 190 inserts an entry for the flow into the medium priority region 145 of the exact match cache 130. Otherwise, if the virtual switch 190 determines that the flow is a low priority flow, then the virtual switch 190 inserts an entry for the flow into the low priority region 150 of the exact match cache 130. This ensures that the high priority region 140 only includes entries for high priority flows, the medium priority region 145 only includes entries for medium priority flows, and the low priority region 150 only includes entries for low priority flows. This helps avoid collisions in the exact match cache 130 between flows having different priority levels, which improves overall QoS. An entry for a flow in the exact match cache 130 matches packets belonging to that flow. In one embodiment, an entry for a flow in the exact match cache 130 specifies a five-tuple or ten-tuple that uniquely identifies that flow and a set of actions to perform for matching packets (packets that have the specified five-tuple/ten-tuple). The set of actions may be the same or similar to the set of actions determined as a result of processing the first packet belonging to the flow through the packet processing pipeline 115. It should be noted that entries are inserted into the region of the exact match cache 130 associated with the priority level of the flow as determined from processing the packet through the packet processing pipeline 115. Thus, the priority level of a flow may be determined based on more than just a single packet field (e.g., more than just the 802. Ip bits or DSCP bits carried by the packet). As mentioned above, the priority level of a flow may be determined based on a variety of factors. In one embodiment, these factors can be programmed into the packet processing pipeline 115 by the controller 180.

[0044] If there is a collision in the exact match cache 130 (e.g., because all of the buckets in the row corresponding to the hash value of the flow are occupied), then the virtual switch 190 may evict an existing entry to accommodate the new entry. The virtual switch 190 may use any suitable replacement policy to choose which entry to evict. It should be noted that since the entry for the flow is inserted into the region of the exact match cache 130 corresponding to the priority level of that flow, it cannot replace/evict an existing entry for a flow having a different priority level. Thus, by design, an entry for a low priority flow cannot replace/evict an entry for a higher priority flow.

[0045] In one embodiment, in response to a determination that an entry for a flow is to be evicted from the exact match cache 130, the virtual switch 190 inserts an entry for that flow into the aggregated cache 125. An entry for a flow in the aggregated cache 125 matches packets belonging to that flow and possibly one or more other flows (e.g., since it can use wildcard matching). In one embodiment, the entry that is inserted in the aggregated cache 125 specifies the priority level of that flow. As will be described in further detail below, this will allow the virtual switch 190 to determine the priority level of the flow without having to process the packet through the packet processing pipeline 115. The aggregated cache 125 is typically stored in main memory (e.g., Random Access Memory) and thus does not have the same storage constraints that the exact match cache 130 typically has (as mentioned above, the exact match cache 130 is typically stored in Ll-cache). As such, it may not be necessary to partition the aggregated cache 125 into regions as done for the exact match cache 130.

[0046] In one embodiment, when the virtual switch 190 receives a packet belonging to a flow, it iteratively matches the packet against entries in the exact match cache 130 region by region in order of priority level. For example, if the exact match cache 130 is partitioned into a high priority region 140, medium priority region 145, and low priority region 150 (as shown in Figure 1), the virtual switch 190 may first match the packet against entries in the high priority region 140 of the exact match cache 130. If the virtual switch 190 finds a matching entry in the high priority region 140, then the virtual switch 190 performs the set of actions specified by the matching entry. However, if the virtual switch 190 does not find a matching entry in the high priority region 140, then the virtual switch 190 matches the packet against entries in the medium priority region 145 of the exact match cache 130. If the virtual switch 190 finds a matching entry in the medium priority region 145, then the virtual switch 190 performs the set of actions specified by the matching entry. However, if the virtual switch 190 does not find a matching entry in the medium priority region 145, then the virtual switch 190 matches the packet against entries in the low priority region 150 of the exact match cache 130. If the virtual switch 190 finds a matching entry in the low priority region 150, then the virtual switch 190 performs the set of actions specified by the matching entry. If the virtual switch 190 does not find a matching entry in the low priority region 150, then this means that an entry for the flow does not exist in the exact match cache 130.

[0047] In one embodiment, if the packet does not match any of the entries in the exact match cache 130, then the virtual switch 190 matches the packet against entries in the aggregated cache 125. If the virtual switch 190 finds a matching entry in the aggregated cache 125, then the virtual switch 190 performs the set of actions specified the matching entry. As mentioned above, the entry in the aggregated cache 125 may specify the priority level of the flow corresponding to that entry. In such an embodiment, if the packet matches the entry in the aggregated cache 125, the virtual switch 190 may insert an entry for that flow into the region of the exact match cache 130 associated with the priority level specified by the matching entry in the aggregated cache 125. This allows the virtual switch 190 to insert the entry for the flow into the correct region of the exact match cache 130 without having to incur the expense of processing the packet through the packet processing pipeline 115 to determine the priority level of the flow. In one embodiment, if the packet does not match any of the entries in the exact match cache 130 and also does not match any of the entries in the aggregated cache 125, then the virtual switch 190 resorts to processing the packet through the packet processing pipeline 115.

[0048] Thus, embodiments provide priority-aware caching in the fast-path of a virtual switch 190 that avoids collisions between flows having different priority levels, which allows for better overall QoS. For example, with priority- aw are caching, even if the virtual switch 190 receives a large number of lower priority flows, the packet processing performance of the higher priority flows will not suffer.

[0049] Figure 3A is a diagram illustrating an entry for a low priority flow being inserted into the exact match cache, according to some embodiments. As shown in the diagram, the exact match cache 130 is partitioned into a high priority region (rows 0-255), a medium priority region (rows 256-511), and a low priority region (rows 512-4095). In this example, each region may be implemented as a separate hash table. For example, the high priority region may be implemented as a hash table with 256 rows (with each row corresponding to a hash value) with each row having two buckets, the medium priority region may be implemented as a hash table with 256 rows with each row having two buckets, and the low priority region may be implemented as a hash table with 3,584 rows with each row having two buckets. As with the example shown in Figure 2, the virtual switch 190 is receiving a high priority flow (flow ID Oxfel), a medium priority flow (flow ID 0x6578), and a low priority flow (flow ID 0x3879), where all of the flows map to a hash value of 1.

[0050] When the virtual switch 190 receives a packet belonging to the low priority flow (flow ID 0x3879), it inserts an entry for that flow into the low priority region of the exact match 130 (into the row corresponding to the hash value of the flow - which in this example is the row corresponding to the hash value of 1 (i.e., row number 513)). In this example, since this row is currently fully occupied, the virtual switch 190 evicts one of the existing entries in that row (e.g., using a least recently used replacement policy) to make room for the new entry. In this example, it is assumed that the new entry (i.e., the entry for flow ID 0x3879) replaces/evicts the entry for flow ID 0xl24f (in bucket B2). It should be noted that by design the entry for flow ID 0x3879 (which is a low priority flow) can only replace/evict an existing entry for another low priority flow and cannot replace/evict an entry for a higher priority flow even if the higher priority flow maps to the same hash value as the low priority flow. Also, it should be noted that while the entries shown in the diagrams specify flow ID as the match criteria to identify flows, this is used as a shorthand in the example to identify the flows. It should be understood that entries may use other means as the match criteria to identify flows (e.g., five-tuple/ten-tuple for entries in the exact match cache 130 and wildcard matching for entries in the aggregated cache 125).

[0051] Figure 3B is a diagram illustrating an entry for an evicted flow being re-inserted into the exact match cache, according to some embodiments. In one embodiment, the virtual switch 190 inserts an entry for a flow evicted from the exact match cache 130 into the aggregated cache 125. For instance, continuing with the example discussed above, as shown in Figure 3B, the virtual switch 190 may insert an entry for the evicted flow (flow ID 0xl24f) into the aggregated cache 125. This entry may specify the priority level of the flow. In this example, the entry in the aggregated cache 125 specifies that the flow is a low priority flow (e.g., since the entry was evicted from the low priority region of the exact match cache 130). If the virtual switch 190 subsequently receives a packet belonging to that flow (flow ID 0xl24f), it will not find an entry for the flow in the exact match cache 130 but will find the entry for that flow in the aggregated cache 125. In response, the virtual switch 190 may perform the set of actions specified by the entry in the aggregated cache 125 and also re-insert an entry for that flow (flow ID 0xl24f) into the region of the exact match cache 130 associated with the priority level specified by the entry in the aggregated cache 125. In this example, since the entry in the aggregated cache 125 specifies that the flow is a low priority flow, the virtual switch 190 inserts an entry for the flow into the low priority region of the exact match cache 130. In this manner, the virtual switch 190 may re-insert the entry for the flow into the correct region of the exact match cache 130 without having to incur the expense of processing the packet through the packet processing pipeline 115 to re determine the priority level of the flow.

[0052] Figure 4 (which is represented as Figure 4 A and Figure 4B) is a flow diagram of a process for providing priority-aware caching in the fast-path of a virtual switch, according to some embodiments. In one embodiment, the process is implemented by a virtual switch (e.g., virtual switch 190) implemented by one or more network devices (e.g., network device 100). The operations in the flow diagram will be described with reference to the exemplary embodiments of the other figures. However, it should be understood that the operations of the flow diagram 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 diagram.

[0053] In one embodiment, at block 405, the process is initiated when the virtual switch receives a packet belonging to a first flow. At block 410, the virtual switch processes the packet through a packet processing pipeline (e.g., because the packet does not match any of the entries in an exact match cache and an aggregated cache) and at block 415, determines, as a result of processing of the packet belonging to the first flow through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the first flow and a priority level of the first flow. In one embodiment, the priority level of the first flow is determined based on one or more of: an input port from which the packet belonging to the first flow was received, a VLAN over which the packet belonging to the first flow was received, 802. Ip bits of the packet belonging to the first flow, DSCP bits of the packet belonging to the first flow, and a destination IP address of the packet belonging to the first flow.

[0054] At block 420, the virtual switch inserts an entry for the first flow into a region of the exact match cache associated with the determined priority level of the first flow, where the entry for the first flow specifies the set of actions to perform for subsequent packets belonging to the first flow. In one embodiment, the exact match cache is implemented using separate hash tables for each of the plurality of regions. In one embodiment, each of the separate hash tables may include two buckets per hash value (e.g., to minimize collisions). In one embodiment, the virtual switch 190 evicts an entry for a second flow (that is different from the first flow) from the region of the exact match cache associated with the determined priority level of the first flow in response to a determination that there is a collision in the exact match cache for the entry for the first flow (e.g., if the first flow and the second flow have the same priority level, they both map to the same hash value, and the row in the exact match cache 130 corresponding to that hash value is fully occupied). In one embodiment, the virtual switch inserts an entry for the (evicted) second flow into the aggregated cache, where the entry for the second flow in the aggregated cache specifies the priority level of the second flow. If the virtual switch subsequently receives a packet belonging to the second flow, it may insert an entry for the second flow into a region of the exact match cache associated with the priority level specified by the entry for the second flow in the aggregated cache in response to a determination that the packet belonging to the second flow does not match any entries in the exact match cache but matches the entry for the second flow in the aggregated cache. In one embodiment, the packet belonging to the second flow is matched against entries in the aggregated cache using wildcard matching (e.g., wildcarded packet fields).

[0055] In one embodiment, at block 425, if the virtual switch receives a subsequent packet belonging to the first flow, at block 430, it iteratively matches the subsequent packet against entries in the exact match cache region by region in order of priority level until finding the entry for the first flow. In one embodiment the packet belonging to the first flow is matched against entries in the exact match cache using a five-tuple or ten-tuple as a key. In one embodiment, block 430 involves, at block 435, selecting the region associated with the highest priority level, at block 440, matching the subsequent packet against entries in the selected region, and at decision block 445, determining whether the entry for the first flow was found in the selected region. If the entry is not found in the selected region, then at block 450, the virtual switch may select the region associated with the next highest priority level and at block 440, match the subsequent packet against entries in the selected region. The virtual switch may repeat operations 440-450 for each region in the exact match cache until the entry for the first flow is found. Returning to decision block 445, if the virtual switch finds the entry for the first flow in the selected region, then at block 455, the virtual switch performs the set of actions specified by the entry for the first flow without processing the subsequent packet through the packet processing pipeline.

[0056] Figure 5A 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 5A shows NDs 500A-H, and their connectivity by way of lines between 500A-500B, 500B-500C, 500C-500D, 500D-500E, 500E-500F, 500F-500G, and 500A-500G, as well as between 500H and each of 500A, 500C, 500D, and 500G. 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 500A, 500E, and 500F 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).

[0057] Two of the exemplary ND implementations in Figure 5 A are: 1) a special-purpose network device 502 that uses custom application-specific integrated-circuits (ASICs) and a special-purpose operating system (OS); and 2) a general purpose network device 504 that uses common off-the-shelf (COTS) processors and a standard OS.

[0058] The special-purpose network device 502 includes networking hardware 510 comprising a set of one or more processor(s) 512, forwarding resource(s) 514 (which typically include one or more ASICs and/or network processors), and physical network interfaces (NIs) 516 (through which network connections are made, such as those shown by the connectivity between NDs 500A-H), as well as non-transitory machine readable storage media 518 having stored therein networking software 520. During operation, the networking software 520 may be executed by the networking hardware 510 to instantiate a set of one or more networking software instance(s) 522. Each of the networking software instance(s) 522, and that part of the networking hardware 510 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) 522), form a separate virtual network element 530A-R. Each of the virtual network element(s) (VNEs) 530A-R includes a control communication and configuration module 532A-R (sometimes referred to as a local control module or control communication module) and forwarding table(s) 534A-R, such that a given virtual network element (e.g., 530A) includes the control communication and configuration module (e.g., 532A), a set of one or more forwarding table(s) (e.g., 534A), and that portion of the networking hardware 510 that executes the virtual network element (e.g., 530A).

[0059] Software 520 can include code such as priority-aware caching component 525, which when executed by networking hardware 510, causes the special-purpose network device 502 to perform operations of one or more embodiments described herein above as part networking software instances 522 (e.g., to provide priority-aware caching in the fast- path of a virtual switch).

[0060] The special-purpose network device 502 is often physically and/or logically considered to include: 1) a ND control plane 524 (sometimes referred to as a control plane) comprising the processor(s) 512 that execute the control communication and configuration module(s) 532A-R; and 2) a ND forwarding plane 526 (sometimes referred to as a forwarding plane, a data plane, or a media plane) comprising the forwarding resource(s) 514 that utilize the forwarding table(s) 534A-R and the physical NIs 516. By way of example, where the ND is a router (or is implementing routing functionality), the ND control plane 524 (the processor(s) 512 executing the control communication and configuration module(s) 532A-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) 534A-R, and the ND forwarding plane 526 is responsible for receiving that data on the physical NIs 516 and forwarding that data out the appropriate ones of the physical NIs 516 based on the forwarding table(s) 534A- R.

[0061] Figure 5B illustrates an exemplary way to implement the special-purpose network device 502 according to some embodiments of the invention. Figure 5B shows a special- purpose network device including cards 538 (typically hot pluggable). While in some embodiments the cards 538 are of two types (one or more that operate as the ND forwarding plane 526 (sometimes called line cards), and one or more that operate to implement the ND control plane 524 (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 536 (e.g., a first full mesh coupling the line cards and a second full mesh coupling all of the cards).

[0062] Returning to Figure 5A, the general purpose network device 504 includes hardware 540 comprising a set of one or more processor(s) 542 (which are often COTS processors) and physical NIs 546, as well as non-transitory machine readable storage media 548 having stored therein software 550. During operation, the processor(s) 542 execute the software 550 to instantiate one or more sets of one or more applications 564A-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 554 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 562A-R called software containers that may each be used to execute one (or more) of the sets of applications 564A-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 run; and where the set of applications running in a given user space, unless explicitly allowed, cannot access the memory of the other processes. In another such alternative embodiment the virtualization layer 554 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 564A-R is run on top of a guest operating system within an instance 562A-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 unikernel(s), 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 sendees needed by the application. As a unikernel can be implemented to run directly on hardware 540, 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 unikernels running directly on a hypervisor represented by virtualization layer 554, unikernels running within software containers represented by instances 562A-R, or as a combination of unikemels and the above-described techniques (e.g., unikemels and virtual machines both run directly on a hypervisor, unikemels and sets of applications that are run in different software containers).

[0063] The instantiation of the one or more sets of one or more applications 564A-R, as well as virtualization if implemented, are collectively referred to as software instance(s) 552. Each set of applications 564A-R, corresponding virtualization construct (e.g., instance 562A-R) if implemented, and that part of the hardware 540 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) 560A-R.

[0064] The virtual network element(s) 560A-R perform similar functionality to the virtual network element(s) 530A-R - e.g., similar to the control communication and configuration module(s) 532A and forwarding table(s) 534A (this virtualization of the hardware 540 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 562A-R corresponding to one VNE 560A-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 562A-R to VNEs also apply to embodiments where such a finer level of granularity and/or unikemels are used.

[0065] In certain embodiments, the virtualization layer 554 includes a virtual switch that provides similar forwarding services as a physical Ethernet switch. Specifically, this virtual switch forwards traffic between instances 562A-R and the physical NI(s) 546, as well as optionally between the instances 562A-R; in addition, this virtual switch may enforce network isolation between the VNEs 560A-R that by policy are not permitted to communicate with each other (e.g., by honoring virtual local area networks (VLANs)). [0066] Software 550 can include code such as priority-aware caching component 563, which when executed by processor(s) 542, cause the general purpose network device 504 to perform operations of one or more embodiments described herein above as part software instances 562A-R (e.g., to provide priority-aware caching in the fast-path of a virtual switch).

[0067] The third exemplary ND implementation in Figure 5A is a hybrid network device 506, 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 502) could provide for para- virtualization to the networking hardware present in the hybrid network device 506.

[0068] 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) 530A- R, VNEs 560A-R, and those in the hybrid network device 506) receives data on the physical NIs (e.g., 516, 546) and forwards that data out the appropriate ones of the physical NIs (e.g., 516, 546). 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.

[0069] Figure 5C illustrates various exemplary ways in which VNEs may be coupled according to some embodiments of the invention. Figure 5C shows VNEs 570A.1-570A.P (and optionally VNEs 570A.Q-570A.R) implemented in ND 500A and VNE 570H.1 in ND 500H. In Figure 5C, VNEs 570A.1-P are separate from each other in the sense that they can receive packets from outside ND 500A and forward packets outside of ND 500A; VNE 570A.1 is coupled with VNE 570H.1, and thus they communicate packets between their respective NDs; VNE 570A.2-570A.3 may optionally forward packets between themselves without forwarding them outside of the ND 500A; and VNE 570A.P may optionally be the first in a chain of VNEs that includes VNE 570A.Q followed by VNE 570A.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 5C 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).

[0070] The NDs of Figure 5A, 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., username/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 5 A may also host one or more such servers (e.g., in the case of the general purpose network device 504, one or more of the software instances 562A-R may operate as servers; the same would be true for the hybrid network device 506; in the case of the special-purpose network device 502, one or more such servers could also be run on a virtualization layer executed by the processor(s) 512); in which case the servers are said to be co-located with the VNEs of that ND.

[0071] A virtual network is a logical abstraction of a physical network (such as that in Figure 5 A) 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).

[0072] 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).

[0073] 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 IP VPN) 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).

[0074] Figure 5D illustrates a network with a single network element on each of the NDs of Figure 5A, 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 5D illustrates network elements (NEs) 570A-H with the same connectivity as the NDs 500A-H of Figure 5A.

[0075] Figure 5D illustrates that the distributed approach 572 distributes responsibility for generating the reachability and forwarding information across the NEs 570A-H; in other words, the process of neighbor discovery and topology discovery is distributed.

[0076] For example, where the special-purpose network device 502 is used, the control communication and configuration module(s) 532A-R of the ND control plane 524 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 570A-H (e.g., the processor(s) 512 executing the control communication and configuration module(s) 532A-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 524. The ND control plane 524 programs the ND forwarding plane 526 with information (e.g., adjacency and route information) based on the routing structure(s). For example, the ND control plane 524 programs the adjacency and route information into one or more forwarding table(s) 534A-R (e.g., Forwarding Information Base (FIB), Label Forwarding Information Base (LFIB), and one or more adjacency structures) on the ND forwarding plane 526. 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 502, the same distributed approach 572 can be implemented on the general purpose network device 504 and the hybrid network device 506.

[0077] Figure 5D illustrates that a centralized approach 574 (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 574 has the responsibility for the generation of reachability and forwarding information in a centralized control plane 576 (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 576 has a south bound interface 582 with a data plane 580 (sometime referred to the infrastructure layer, network forwarding plane, or forwarding plane (which should not be confused with a ND forwarding plane)) that includes the NEs 570A-H (sometimes referred to as switches, forwarding elements, data plane elements, or nodes). The centralized control plane 576 includes a network controller 578, which includes a centralized reachability and forwarding information module 579 that determines the reachability within the network and distributes the forwarding information to the NEs 570A- H of the data plane 580 over the south bound interface 582 (which may use the OpenFlow protocol). Thus, the network intelligence is centralized in the centralized control plane 576 executing on electronic devices that are typically separate from the NDs. In one embodiment, the network controller 578 may include a priority-aware component 581 that when executed by the network controller 578, causes the network controller 578 to perform operations of one or more embodiments described herein above (e.g., to program the packet processing pipeline of a virtual switch to support priority-aware caching in the fast-path).

[0078] For example, where the special-purpose network device 502 is used in the data plane 580, each of the control communication and configuration module(s) 532A-R of the ND control plane 524 typically include a control agent that provides the VNE side of the south bound interface 582. In this case, the ND control plane 524 (the processor(s) 512 executing the control communication and configuration module(s) 532A-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 576 to receive the forwarding information (and in some cases, the reachability information) from the centralized reachability and forwarding information module 579 (it should be understood that in some embodiments of the invention, the control communication and configuration module(s) 532A-R, in addition to communicating with the centralized control plane 576, 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 574, but may also be considered a hybrid approach). [0079] While the above example uses the special-purpose network device 502, the same centralized approach 574 can be implemented with the general purpose network device 504 (e.g., each of the VNE 560A-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 576 to receive the forwarding information (and in some cases, the reachability information) from the centralized reachability and forwarding information module 579; it should be understood that in some embodiments of the invention, the VNEs 560A-R, in addition to communicating with the centralized control plane 576, 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 506. In fact, the use of SDN techniques can enhance the NFV techniques typically used in the general purpose network device 504 or hybrid network device 506 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.

[0080] Figure 5D also shows that the centralized control plane 576 has a north bound interface 584 to an application layer 586, in which resides application(s) 588. The centralized control plane 576 has the ability to form virtual networks 592 (sometimes referred to as a logical forwarding plane, network services, or overlay networks (with the NEs 570A-H of the data plane 580 being the underlay network)) for the application(s) 588. Thus, the centralized control plane 576 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).

[0081] While Figure 5D shows the distributed approach 572 separate from the centralized approach 574, 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) 574, 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 574, but may also be considered a hybrid approach.

[0082] While Figure 5D illustrates the simple case where each of the NDs 500A-H implements a single NE 570A-H, it should be understood that the network control approaches described with reference to Figure 5D also work for networks where one or more of the NDs 500A-H implement multiple VNEs (e.g., VNEs 530A-R, VNEs 560A-R, those in the hybrid network device 506). Alternatively or in addition, the network controller 578 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 578 may present the implementation of a VNE/NE in a single ND as multiple VNEs in the virtual networks 592 (all in the same one of the virtual network(s) 592, each in different ones of the virtual network(s) 592, or some combination). For example, the network controller 578 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 576 to present different VNEs in the virtual network(s) 592 (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).

[0083] On the other hand, Figures 5E and 5F respectively illustrate exemplary abstractions of NEs and VNEs that the network controller 578 may present as part of different ones of the virtual networks 592. Figure 5E illustrates the simple case of where each of the NDs 500A-H implements a single NE 570A-H (see Figure 5D), but the centralized control plane 576 has abstracted multiple of the NEs in different NDs (the NEs 570A-C and G-H) into (to represent) a single NE 5701 in one of the virtual network(s) 592 of Figure 5D, according to some embodiments of the invention. Figure 5E shows that in this virtual network, the NE 5701 is coupled to NE 570D and 570F, which are both still coupled to NE 570E.

[0084] Figure 5F illustrates a case where multiple VNEs (VNE 570A.1 and VNE 570H.1) are implemented on different NDs (ND 500 A and ND 500H) and are coupled to each other, and where the centralized control plane 576 has abstracted these multiple VNEs such that they appear as a single VNE 570T within one of the virtual networks 592 of Figure 5D, according to some embodiments of the invention. Thus, the abstraction of a NE or VNE can span multiple NDs.

[0085] While some embodiments of the invention implement the centralized control plane 576 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).

[0086] Similar to the network device implementations, the electronic device(s) running the centralized control plane 576, and thus the network controller 578 including the centralized reachability and forwarding information module 579, 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 6 illustrates, a general purpose control plane device 604 including hardware 640 comprising a set of one or more processor(s) 642 (which are often COTS processors) and physical NIs 646, as well as non- transitory machine readable storage media 648 having stored therein centralized control plane (CCP) software 650 and a priority-aware caching component 651.

[0087] In embodiments that use compute virtualization, the processor(s) 642 typically execute software to instantiate a virtualization layer 654 (e.g., in one embodiment the virtualization layer 654 represents the kernel of an operating system (or a shim executing on a base operating system) that allows for the creation of multiple instances 662A-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 654 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 662A-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 08 services) that provide the particular 08 services needed by the application, and the unikernel can run directly on hardware 640, directly on a hypervisor represented by virtualization layer 654 (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 662 A-R). Again, in embodiments where compute virtualization is used, during operation an instance of the CCP software 650 (illustrated as CCP instance 676A) is executed (e.g., within the instance 662 A) on the virtualization layer 654. In embodiments where compute virtualization is not used, the CCP instance 676A is executed, as a unikemel or on top of a host operating system, on the“bare metal” general purpose control plane device 604. The instantiation of the CCP instance 676A, as well as the virtualization layer 654 and instances 662A-R if implemented, are collectively referred to as software instance(s) 652.

[0088] In some embodiments, the CCP instance 676A includes a network controller instance 678. The network controller instance 678 includes a centralized reachability and forwarding information module instance 679 (which is a middleware layer providing the context of the network controller 578 to the operating system and communicating with the various NEs), and an CCP application layer 680 (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 680 within the centralized control plane 576 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.

[0089] The priority- aw are caching component 651 can be executed by hardware 640 to perform operations of one or more embodiments described herein above as part of software instances 652 (e.g., to program the packet processing pipeline of a virtual switch to support priority-aware caching in the fast-path).

[0090] The centralized control plane 576 transmits relevant messages to the data plane 580 based on CCP application layer 680 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 580 may receive different messages, and thus different forwarding information. The data plane 580 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.

[0091] 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).

[0092] 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.

[0093] 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.

[0094] However, when an unknown packet (for example, a“missed packet” or a“match- miss” as used in OpenFlow parlance) arrives at the data plane 580, the packet (or a subset of the packet header and content) is typically forwarded to the centralized control plane 576. The centralized control plane 576 will then program forwarding table entries into the data plane 580 to accommodate packets belonging to the flow of the unknown packet. Once a specific forwarding table entry has been programmed into the data plane 580 by the centralized control plane 576, the next packet with matching credentials will match that forwarding table entry and take the set of actions associated with that matched entry.

[0095] 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.

[0096] Some portions of the preceding detailed descriptions have been presented in terms of algorithms and symbolic representations of transactions on data bits within a computer memory. These algorithmic descriptions and representations are the ways used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self- consistent sequence of transactions leading to a desired result. The transactions are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like.

[0097] It should be borne in mind, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise as apparent from the above discussion, it is appreciated that throughout the description, discussions utilizing terms such as "processing" or "computing" or "calculating" or "determining" or "displaying" or the like, refer to the action and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.

[0098] The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform the required method transactions. The required structure for a variety of these systems will appear from the description above. In addition, embodiments of the present invention are not described with reference to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of embodiments as described herein.

[0099] An embodiment may be an article of manufacture in which a non-transitory machine-readable medium (such as microelectronic memory) has stored thereon instructions (e.g., computer code) which program one or more data processing components (generically referred to here as a“processor”) to perform the operations described above. In other embodiments, some of these operations might be performed by specific hardware components that contain hardwired logic (e.g., dedicated digital filter blocks and state machines). Those operations might alternatively be performed by any combination of programmed data processing components and fixed hardwired circuit components.

[00100] Throughout the description, embodiments of the present invention have been presented through flow diagrams. It will be appreciated that the order of transactions and transactions described in these flow diagrams are only intended for illustrative purposes and not intended as a limitation of the present invention. One having ordinary skill in the art would recognize that variations can be made to the flow diagrams without departing from the broader spirit and scope of the invention as set forth in the following claims.

[00101] In the foregoing specification, embodiments have been described with reference to specific exemplary embodiments thereof. It will be evident that various modifications may be made thereto without departing from the broader spirit and scope of the invention as set forth in the following claims. The specification and drawings are, accordingly, to be regarded in an illustrative sense rather than a restrictive sense.

Claims

CLAIMS:

1. A method by a virtual switch implemented by one or more network devices to provide priority-aware caching in a fast-path of the virtual switch, the method comprising: receiving (405) a packet belonging to a first flow;

processing (410) the packet belonging to the first flow through a packet processing pipeline of the virtual switch in response to a determination that the packet belonging to the first flow does not match any entries in an exact match cache of the virtual switch, wherein the exact match cache includes a plurality of regions, and wherein each of the plurality of regions is associated with a different one of a plurality of priority levels;

determining (415), as a result of the processing of the packet belonging to the first flow through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the first flow and a priority level of the first flow; and

inserting (420) an entry for the first flow into a region of the exact match cache associated with the determined priority level of the first flow, wherein the entry for the first flow specifies the set of actions to perform for subsequent packets belonging to the first flow.

2. The method of claim 1, further comprising:

receiving (425) a subsequent packet belonging to the first flow;

iteratively matching (430) the subsequent packet against entries in the exact match cache region by region in order of priority level until finding the entry for the first flow; and

performing (455) the set of actions specified by the entry for the first flow without processing the subsequent packet through the packet processing pipeline in response to finding the entry for the first flow.

3. The method of claim 2, wherein the packet belonging to the first flow is matched against entries in the exact match cache using a five-tuple or ten-tuple as a key.

4. The method of claim 1, further comprising: evicting an entry for a second flow from the region of the exact match cache associated with the determined priority level of the first flow in response to a determination that there is a collision in the exact match cache for the entry for the first flow.

5. The method of claim 4, further comprising:

inserting an entry for the second flow into an aggregated cache of the virtual switch, wherein the entry for the second flow in the aggregated cache specifies the priority level of the second flow.

6. The method of claim 5, further comprising:

receiving a packet belonging to the second flow; and

inserting an entry for the second flow into a region of the exact match cache associated with the priority level specified by the entry for the second flow in the aggregated cache in response to a determination that the packet belonging to the second flow does not match any entries in the exact match cache but matches the entry for the second flow in the aggregated cache.

7. The method of claim 6, wherein the packet belonging to the second flow is matched against entries in the aggregated cache using wildcard matching.

8. The method of claim 1, wherein the priority level of the first flow is determined based on one or more of: an input port from which the packet belonging to the first flow was received, a Virtual Local Area Network (VLAN) over which the packet belonging to the first flow was received, 802. Ip bits of the packet belonging to the first flow, Differentiated Services Code Point (DSCP) bits of the packet belonging to the first flow, and a destination IP address of the packet belonging to the first flow.

9. The method of claim 1, wherein the exact match cache is implemented using separate hash tables for each of the plurality of regions.

10. The method of claim 9, wherein each hash table includes two buckets per hash value.

11. A network device (504) configured to implement a virtual switch that provides priority-aware caching in a fast-path of the virtual switch, the network device comprising: a set of one or more processors (542); and

a non-transitory computer-readable storage medium (548) storing instructions (563), which when executed by the set of one or more processors, causes the network device to:

receive a packet belonging to a first flow,

process the packet belonging to the first flow through a packet processing pipeline of the virtual switch in response to a determination that the packet belonging to the first flow does not match any entries in an exact match cache of the virtual switch, wherein the exact match cache includes a plurality of regions, and wherein each of the plurality of regions is associated with a different one of a plurality of priority levels,

determine, as a result of the processing of the packet belonging to the first flow through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the first flow and a priority level of the first flow, and

insert an entry for the first flow into a region of the exact match cache associated with the determined priority level of the first flow, wherein the entry for the first flow specifies the set of actions to perform for subsequent packets belonging to the first flow.

12. The network device of claim 11, wherein the non-transitory computer-readable storage medium stores further instructions, which when executed by the set of one or more processors, causes the network device to:

receive a subsequent packet belonging to the first flow,

iteratively match the subsequent packet against entries in the exact match cache region by region in order of priority level until finding the entry for the first flow, and

perform the set of actions specified by the entry for the first flow without processing the subsequent packet through the packet processing pipeline in response to finding the entry for the first flow.

13. The network device of claim 12, wherein the packet belonging to the first flow is matched against entries in the exact match cache using a five-tuple or ten-tuple as a key.

14. The network device of claim 11, wherein the non-transitory computer-readable storage medium stores further instructions, which when executed by the set of one or more processors, causes the network device to:

evict an entry for a second flow from the region of the exact match cache associated with the determined priority level of the first flow in response to a determination that there is a collision in the exact match cache for the entry for the first flow.

15. The network device of claim 14, wherein the non-transitory computer-readable storage medium stores further instructions, which when executed by the set of one or more processors, causes the network device to:

16. A non-transitory computer-readable storage medium storing instructions, which when executed by a set of one or more processors of a network device implementing a virtual switch, causes the network device to perform operations for providing priority-aware caching in a fast-path of the virtual switch, the operations comprising:

receiving (405) a packet belonging to a first flow;

determining (415), as a result of the processing of the packet belonging to the first flow through the packet processing pipeline, a set of actions to perform for subsequent packets belonging to the first flow and a priority level of the first flow; and inserting (420) an entry for the first flow into a region of the exact match cache associated with the determined priority level of the first flow, wherein the entry for the first flow specifies the set of actions to perform for subsequent packets belonging to the first flow.

17. The non-transitory computer-readable medium of claim 16, wherein the instructions, when executed by the set of one or more processors of the network device, causes the network device to perform further operations comprising:

receiving (425) a subsequent packet belonging to the first flow;

18. The non-transitory computer-readable storage medium of claim 16, wherein the instructions, when executed by the set of one or more processors of the network device, causes the network device to perform further operations comprising:

evicting an entry for a second flow from the region of the exact match cache associated with the determined priority level of the first flow in response to a determination that there is a collision in the exact match cache for the entry for the first flow.

19. The non-transitory computer-readable storage medium of claim 18, wherein the instructions, when executed by the set of one or more processors of the network device, causes the network device to perform further operations comprising:

20. The non-transitory computer-readable storage medium of claim 16, wherein the priority level of the first flow is determined based on one or more of: an input port from which the packet belonging to the first flow was received, a Virtual Local Area Network (VLAN) over which the packet belonging to the first flow was received, 802. Ip bits of the packet belonging to the first flow, Differentiated Services Code Point (DSCP) bits of the packet belonging to the first flow, and a destination IP address of the packet belonging to the first flow.