HK1166570A - Method and system for integrating virtual and physical network switching equipment to heterogeneous exchange domain - Google Patents

Description

Method and system for integrating virtual and physical network switching devices into heterogeneous switching domains

Technical Field

The present invention relates to distributed switching technology, and more particularly, to a switching domain capable of integrating virtual and physical switches.

Background

With the popularity of modern networks, different types of network devices are being used to process and route packets in a complex network switching architecture. Traditionally, many benefits have been realized by connecting physical switch devices to logical entities, such as ports, bridges, and network switches, which are connected in a direct, physical manner between network components. While connections between network components involve an integration between homogeneous sets of physical devices.

Increasingly, Virtual Machines (VMs) connected to virtual switches are integrated into network topologies. Virtualized environments managed by a Virtual Machine Manager (VMM) are deployed in different ways across different physical topologies. Problems can arise when a virtual switch component interacts with a physical switch component. Connecting between physical and virtual switching devices in a network is challenging compared to connecting between physical network components.

Challenges faced in implementing connections between heterogeneous network components include the dynamic nature of the virtual switches and the different types of topologies upon which the virtual switches are deployed, e.g., virtual switches that connect multiple virtual machines simultaneously, complex and dynamically changing network topologies, and performance maintenance, energy savings, and efficiency standards.

For the management of large numbers of heterogeneous devices, one of ordinary skill in the art will recognize that challenges and benefits are significant. Accordingly, there is a need for improved methods and systems to overcome the above-mentioned deficiencies.

Disclosure of Invention

According to one aspect of the invention, there is provided a method of integrating virtual and physical network switching devices into heterogeneous switching domains, the method comprising:

appending, by a first switching device, a header to a packet received from a virtual machine, wherein the header includes domain information describing a component of the heterogeneous switching domain;

processing the data packet by the first switching device, wherein the processing is controlled by the header;

forwarding the processed data packet, wherein the forwarding is controlled by the header.

Preferably:

the processed data packet is forwarded to a second switching device, which is a switch or a router.

Preferably:

any of the switching devices is physical or virtual, and the heterogeneous switching domain includes at least one virtual switching device.

Preferably, the domain information includes:

an input port of a switching device in the heterogeneous switching domain; and

an output port of the switching device.

Preferably:

the domain information includes processing applied to the data packet by the switching device.

Preferably:

the domain information includes filtering options applied to the data packet by the switching device.

Preferably:

the domain information includes a communication path applied to the processed data packet by the switching device, the communication path routing the processed data packet through both a physical switching device and a virtual switching device.

Preferably:

the domain information includes energy control and efficiency policies to be applied to the operation of the first switching device.

According to one aspect of the invention, there is provided a system for integrating virtual and physical network components into a heterogeneous switching domain, comprising:

a communications controller having a Switch Acceleration Engine (SAE), wherein the switch acceleration engine is to:

decoding a header of a packet received from a virtual machine, wherein the header includes domain information about the heterogeneous switching domain;

processing the data packet, wherein the processing is controlled by the header; and

forwarding the processed data packet to a network component, wherein the forwarding is controlled by the header.

Preferably:

the network component to which the header is forwarded is a physical switching device.

Preferably:

the network component to which the header is forwarded is the virtual machine.

Preferably:

the domain information includes

An input port of a switching device in the heterogeneous switching domain; and

an output port of the switching device.

Preferably:

the domain information includes processing applied to the data packet by the switching device.

Preferably:

the domain information includes filtering options applied to the data packet by the switching device.

Preferably:

the domain information includes a communication path applied to the processed data packet by the switching device, the communication path routing the processed data packet through both a physical switching device and a virtual switching device.

Preferably: the domain information includes energy control and efficiency policies to be applied to the operation of a network component.

According to one aspect of the invention, there is provided a system for integrating virtual and physical network components into a heterogeneous switching domain, comprising:

a server;

a first virtual machine running on the server;

a virtual switch running on the server, the virtual switch receiving and processing a data packet from a first virtual machine, wherein upon receipt of the data packet from the first virtual machine, the virtual switch appends a header to the data packet, the header containing domain information relating to the heterogeneous switching domain; and

a physical switch connected to the server, wherein upon receipt of the data packet, the physical switch decodes the appended header and processes the data packet according to the header.

Preferably:

the system further comprises:

a communication controller installed in the server; and

a Switching Acceleration Engine (SAE) in the communication controller, the switching acceleration engine receiving and processing data packets.

Preferably:

the switch acceleration engine processes the data packet according to the header appended to the data packet.

Preferably:

based on certain considerations, the virtual switch offloads a portion of packet processing to the switch acceleration engine.

Preferably:

the consideration is to improve system performance.

Preferably:

the consideration is to improve the system performance.

Preferably:

the system further comprises

A second virtual machine, wherein the virtual switch is further to switch packets from the first virtual machine to the second virtual machine.

Preferably:

the system further comprises

A second virtual machine, wherein the virtual switch is further to switch packets from the first virtual machine to the second virtual machine bypassing the physical switch.

Drawings

The principles of the present invention are further explained in the following description and the accompanying drawings so that those skilled in the art can best practice and utilize the invention.

FIG. 1 is a block diagram of one embodiment of a network topology;

FIG. 2 is a more detailed block diagram of a server connected to a switch, the server including virtual components, according to one embodiment of the invention;

FIG. 3 is a block diagram of a system having a connection between a physical switching component and a server having a virtual component in accordance with one embodiment of the present invention;

FIG. 4 is a block diagram of a system having heterogeneous switching domains in accordance with one embodiment of the present invention;

FIG. 5 is a block diagram of a communication controller having a switch acceleration engine according to one embodiment of the present invention;

FIG. 6 is a schematic diagram of different arrangements of heterogeneous switching domain controllers according to one embodiment of the present invention;

FIG. 7 is a flow diagram of a method for integrating virtual and physical network switching components into a switching domain according to one embodiment of the invention;

the invention is illustrated in the figures in which elements are first shown and described, with reference to the drawing figures in which like reference numerals are used to indicate the leftmost digit(s) in the corresponding reference number.

Detailed Description

The accompanying drawings, to which reference is made in the following detailed description of the invention, illustrate exemplary embodiments that constitute the invention. Other embodiments are possible and modifications may be made to the embodiments without departing from the spirit and scope of the invention. The following detailed description is, therefore, not to be taken in a limiting sense. Rather, the scope of the invention is defined by the claims of the present application.

The features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The benefits of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. The following detailed description is exemplary and explanatory and is intended to provide further explanation of the invention as claimed.

Reference throughout this specification to "one embodiment," "an example embodiment," or the like, means that the embodiment described may include a particular feature, structure, or characteristic. However, not every embodiment necessarily includes the particular feature, structure, or characteristic. Moreover, such phrases are not intended to refer to the same embodiment. When a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the purview of one skilled in the art to effect such feature, structure, or characteristic in connection with other ones of the embodiments whether or not explicitly described.

Overview

In general, certain embodiments described herein relate to implementing a distributed switching domain that includes heterogeneous network switching/routing components. Conventional approaches to improving network switching performance have focused on logically connected physical switching devices.

In conventional implementations, however, a switch domain is not created that includes both virtual and physical switching resources. Certain embodiments provided herein describe methods and systems for creating a switch domain that includes a virtual switch and a physical switch. Other types of heterogeneous resources may also be operatively connected using the method, as described below.

The conventional method and the switch domain without creating an integrated network card resource and virtual switch. The embodiments provided herein describe a method for integrating network card resources with switch acceleration engines in a distributed switching domain using a virtual switch. Other types of network card resources and virtual components may also be operatively connected using the described method, as described below.

Fig. 1 is a block diagram of an example network topology 100. Network topology 100 includes servers 120A-B, access switches 130A-B, network 160, and core switch 110. The physical connections between the servers 120A-B and the access switches 130A-B, and between the core switch 110, the network 160, and the two switches 130A-B, respectively, are shown. In one embodiment, the relationship of core switches 110 to access switches 130A-B may be referred to as a hierarchical relationship, where core switches 110 are superior.

In one non-limiting example, network topology 100 is a subset of a data center network and servers 120A-B are configured to host applications and data for clients connected to network 160 (not shown). Those skilled in the art will appreciate that the teachings herein may be applied to a variety of different network configurations and purposes.

Server devices 120A-B are typical computer systems comprising multiple processors and multiple shared or separate memory components, such as, but not limited to, one or more computing devices incorporated in a clustered computing environment or server farm. The computing processes performed by a clustered computing environment or server farm may be implemented by multiple processors located at the same or different locations. In another embodiment, server devices 120A-B may be implemented in a single computing device. Examples of computing devices include, but are not limited to, devices with a central processing unit, application specific integrated circuits, or other types of computing devices with at least one processor and memory.

Network 160 may be any single or combination type of network such as, but not limited to, a local area network, a wide area network, a wired connection network (e.g., ethernet) or a wireless connection network (e.g., WiFi, 3G) that communicatively connects the network components shown in fig. 1 (core switch 110, access switches 130A-B and servers 120A-B) with other network components.

The access switches 130A-B are typically bridge devices with data ports and may additionally have routing/switching capabilities, such as L2/L3 switches/routers. The switch has at least two, and even up to 400 and more data ports, and can directly perform full-duplex communication from any data port to other data ports, effectively using any data port as an input and any port as an output. Herein, for ease of discussion, data ports and their corresponding connections may be interchangeably referred to as data lanes, communication links, data links, and so forth.

As used herein, access switches 130A-B and hosts 120A-B should comprise a single physical device (not shown) that is a combination of host 120A and access switch 130A, as the specific depiction in the figures should not be construed as limiting. Access switches 130A-B also broadly encompass the use of switch logic in modern hierarchical switching architectures. The core switches 110 are typically high-speed switches arranged in a network topology to connect multiple access switches 130. The term "physical", as used herein to describe network components, generally refers to "non-virtual" in "non-virtualized devices".

Further, as the teachings herein for path selection and processing are generally applicable to all components that handle these functions, the terms "route," "switch," and "route/switch," as used herein, are generally used interchangeably.

Fig. 2 illustrates an example of a server 120A and an access switch 130A. Server 120A includes virtual machines 240A-B, virtual switch 250, Communication Controller (CC)270, Virtual Machine Manager (VMM)245, and processor 260. A physical link is shown between server 120A and access switch 130A.

Virtual Machines (VMs) 240A-B are typically dynamically configured software entities that appear to be separate network entities in a network, each having a Media Access Control (MAC) address. Virtual machines 240A-B are also typically an instance of a virtual machine that is part of a virtualization platform. Those of ordinary skill in the art are aware of modern virtualization platforms and their implementations. Systems with virtual machines typically provide a complete system platform, supporting the execution of a complete Operating System (OS). Virtual machines are typically managed by a virtual machine manager (also referred to as a hypervisor), such as VMM 245.

Virtual Switch (VS)250 is generally used to provide communication between virtual machines 240A-B and other network components. In an example operation, virtual switch 250 receives a data packet from virtual machine 240A, reads the source MAC address and the destination MAC address, and forwards the data packet into the memory subsystem of the server. Through this forwarding operation, virtual switch 250 allows virtual machine 240A to communicate with external devices and other virtual machines in server 120A.

Those skilled in the art will appreciate that in some embodiments, the virtual control platform of a virtualization system (e.g., VMM 245) may be unaware of various aspects of the physical portion of the network topology. The lack of information in this regard by VMM 245 is particularly important for the connection between the physical and virtual switching components. As discussed below, some embodiments can provide additional information for virtual components, thereby improving connectivity between heterogeneous components in a network.

Processor 260 is typically a single processor, a plurality of processors, or a combination thereof. A processor device may have one or more processor cores. For example, at least one processor device and memory may be used to implement the embodiments described above.

After reading this description, it will become apparent to a person skilled in the art how to implement the invention in other computer systems and/or computer architectures. Although operations may be described as a sequential process, some of the operations may in fact be performed in parallel, concurrently, and/or in a distributed environment, with program code stored locally or remotely for access by a single or multiple processors. In addition, the order of the operations in some embodiments may be rearranged without departing from the spirit and scope of the invention.

Fig. 3 depicts a network topology 300 similar to network topology 100 of fig. 1, with a dashed box representing a conventional switched connection 310. The switch connection 310 contains a core switch 110 and an access switch 130A. It should be noted that the switch connection 310 does not include the communication controller 270 and the virtual switch 250.

As noted above, various ways of connecting physical components to switched connection 310 are traditionally being explored. For example, network traffic has been "tagged" with a basic information header. These labels are designed to logically connect or "stack" the physical switches by providing reference information (e.g., packet source and destination information that enables packets to be routed through switch connection 310). As described above, conventional labels that enable these physical connections between physical devices do not have the details required to connect heterogeneous network devices, such as virtual and physical switches. Alternative methods used in embodiments will be discussed below.

Heterogeneous switching domain

Fig. 4 depicts a network topology in one embodiment having a Heterogeneous Switching Domain (HSD)410 that includes Virtual Switch (VS)250, access switch 130A, and core switch 110.

As used in some embodiments, HSD410 may link/integrate/combine virtual switch devices and physical switch devices into a single switch domain. For example, in one embodiment, HSD410 enables access switches 130A and VS250 to have similar attribute filters, QoS, and traffic management features. The benefits provided by integrating virtual switch and physical switch characteristics/attributes may be appreciated by those of ordinary skill in the art in light of the following examples.

From a network perspective, when a packet enters an "edge" switch port of HSD410, the packet is treated as if it passed through the components of HSD410 by a single switching engine. Alternatively, in one embodiment, HSD410 preferably serves as an extension of the switch fabric between all of the included components.

It will also be appreciated by those skilled in the art having the benefit of this teaching that this connection of heterogeneous connection devices into a single domain contrasts with the conventional "stacking" discussed in FIG. 3.

Enhanced header

One way to connect HSD410 to virtual and physical network components is to use pre-defined enhanced headers for processed packets as they interact with the switches within HSD 410. Unlike the limited legacy tags described above, the enhanced header contains additional information related to enabling the functionality of HSD410 as described in this embodiment. In one embodiment, the enhanced header may contain and distribute up-to-date status information about the components of network topology 400. In one embodiment, the information about the operation of HSD410 stored and relayed through the enhanced header may be referred to as "domain information".

While conventional labels for packets in homogeneous networks may include references to different points in the network, such as source and destination, some embodiments of the enhanced headers described herein include commands that affect different building network considerations, such as performance, power savings, and efficiency.

The following lists H1-H8 are non-limiting example lists of related items that may be included in an enhanced header according to one embodiment of the present invention:

h1: a command specifying an input port of a packet into a network switch component.

H2: a command specifying that a packet flows out of an output port of a network switch component.

H3: commands specifying additional operations to be performed before a packet is forwarded by a network switch component.

H4: commands that specify conditions that must be met before a packet is forwarded by a network switch component. For example, conditions may be set such that permission must be granted to egress from a particular designated egress port of a particular network switch component before a packet is forwarded out of HSD 410.

H5: commands specifying packet filtering options. For example, packets may be filtered according to their origin or destination sub-domains.

H6: commands that specify the options and conditions for packet processing. In one embodiment, because VS250 is implemented with processor 260, its benefits are realized by implementing packet processing options/conditions that are tailored to the performance and workload of processor 260. In one embodiment, processing functions may be dynamically reallocated between virtual and physical resources due to heterogeneous integration of HSD410 (virtual to physical connections).

H7: a command specifying a forwarding option, the option specifying a communication path within the network. In one embodiment, each communication path may have a different weight, performance, congestion level, and these characteristics may be used to provide source-based packet direction. For a given embodiment scenario, one of ordinary skill in the art will appreciate that such capabilities in the embodiment are particularly useful for routing packets into and out of a virtual switch. A virtual switch, like all components within a virtual platform, typically does not have comprehensive information about physical characteristics outside the platform. In one embodiment, connecting virtual and physical switches into HSD410 may improve the routing performance of VS250 by providing information about the components within HSD 410. Such improvements in routing may generally improve, for example, load balancing across the network.

H8: commands specifying energy control and efficiency policies to be applied to different integrated components within HSD 410. As with the physical characteristics discussed in connection with H7, the full power saving option has been difficult to implement in conventional network implementations with virtual components. In one embodiment, by integrating physical and virtual switches in HSD410, a unified approach may be taken to perform energy control and efficiency approaches. Such an approach may include, for example, regulatory policies implemented in accordance with the IEEE p802.3az standard, also known as Energy Efficient Ethernet (Energy Efficient Ethernet).

Those skilled in the art will appreciate that the above items H1-H8 are to be understood as non-limiting examples of information that may be conveyed in an enhanced header. HSD410 and its functions/benefits may take a variety of embodiments without departing from the spirit and scope of the present invention.

An example of an enhanced header is the HIGIG header from blond corporation of deluxe, california, usa (HIGIG HEADER). One type of HiGig header interface is a 10Gbps full-duplex chip-to-chip interface, which can improve the expandability and performance of the system. Some implementations and customizations of the HiGig header (also including the HiGig + and HiGig2 protocols) may be used by embodiments to provide a standard mechanism for interconnecting physical and virtual switches to a heterogeneous switching domain such as HSD 410. Embodiments of the protocol may define forwarding frames for unicast, broadcast, multicast (Layer 2 and IP) and control traffic. The HiGig/HiGig + protocol implements a HiGig frame, which is formed by prepending a 12-byte to 16-byte HiGig header to a standard ethernet frame. It should be understood that this particular header is merely an example, and that only one protocol type capable of implementing certain embodiments is described herein.

In some implementations, the HiGig header contains information about the packet and its source, destination ports and port images. In embodiments, this information may speed up table lookups within and among the switching domains, thereby improving the overall performance of the system.

Exchange acceleration engine (SAE)

Fig. 5 depicts an embodiment of server 120A and access switch 130A, where server 120A contains virtual switch 250 and Communication Controller (CC) 270. The communication controller 270 is shown with an SEA 570. As described above, in addition to connecting VS250 and physical switches (130A, 110), some embodiments of HSD410 may incorporate a Communication Controller (CC) 270. Specifically, in one embodiment using HSD410, a Switch Acceleration Engine (SAE)570 can be coupled to VS250 and switches 130A, 110.

In one embodiment, Communications Controller (CC)270 has a Switching Acceleration Engine (SAE)570 (also referred to as a NIC switching engine) therein. In addition to Switching Acceleration Engine (SAE)570 on communication controller 270 of server 120A, additional processing resources may be made available to HSD410 for use. SAE570 may be implemented as a specially designed processor that performs the switching functions of the physical and virtual components of HSD 410.

In one embodiment, VS250 may selectively offload processing functions to SAE570 as circumstances require. Inclusion of SAE570, as a different type of hardware component integrated into HSD410, enhances the heterogeneous nature of the HSD410 structure.

In one embodiment, VS250 may accelerate the switching/processing/forwarding performance of VS250 by using the switching functionality of SAE 570. In this embodiment, communication controller 270 becomes an additional hardware acceleration engine for VS250 through the use of SAE 570. The virtual switching functionality improved by SAE570 includes efficient handling of the enhanced header as described.

Advantageous effects

The integration provided by HSD410, as described above, has a number of benefits. The following items B1-B10 are a non-limiting list of example benefits that may be derived in various embodiments and other implementation details.

B1, embodiments that reduce the number of virtual and physical devices in a network must be managed separately by integrating a physical switch and a virtual switch into a single switching entity. In one embodiment, a smaller number of devices are also required to participate in the topology protocol used in packet processing.

B2, improved monitoring of switch traffic by communicating within HSD410 in a unified manner. E.g., VS250, may coordinate packet monitoring with access switch 130A. In one embodiment, VS250 can replicate the packet and send it to a different switch entity, such as a monitor port on switch 130A. This provides a more efficient traffic monitoring method since the enhanced header described above may contain information about the characteristics and traffic of all integrated components in HSD 410.

The integration of B4, VS250 with access switch 130A allows developers to improve the efficiency and operation of the virtual switching process. As will be appreciated by one of ordinary skill in the art in light of the present description, a virtual switch may benefit from having additional processing capabilities applied to switching tasks. Due to the integration of VS250 and access switch 130A, in particular embodiments, selected processing tasks may be dynamically offloaded from VS250 to access switch 130A. As described above, SAE570 can also perform this offload procedure. In particular embodiments, the resources in the integrated network components may be self-balancing, e.g., automatically performing functions where they are most appropriate based on the operation of the system.

B6, in particular embodiments, may increase security issues for system 400 by interfacing with network components within HSD 410. In one embodiment, the "edge" of HSD410 may be configured with an application security program. For example, additional conditions may be set for the ports of an external component (e.g., VS 250) before the packet is allowed to access the designated input port. In one embodiment, one of the ways to enhance the edge security policy of HSD410 is to use the enhanced header described above.

B7, the same assignment of security policies discussed in B6 above, may be used in embodiments to assign and apply power saving and control policies to different components. For example, those skilled in the art will appreciate that if VS250 is using two redundant traffic paths at 50% utilization, detecting this and moving one of the connections to 0% utilization and the other to 100% utilization may save power in some situations. In one embodiment, connecting VS250 with other resources in HSD410 both helps detect this situation and corrects it by enforcing a policy.

Implementation means of different hardware vendors

Since some embodiments of HSD410 described herein are designed for switching logic that integrates both virtual and physical switching entities, in one embodiment, a Software Development Kit (SDK) is provided that allows virtual switches without integration capability to be integrated into the HSD410 entity.

For example, if a particular "trivial/general" virtual switch implementation does not have the features/functionality to be able to integrate it into HSD410, the SDK allows this functionality to be added. One feature that may be added is the ability to work with the enhanced headers described above, which in one embodiment provide a coordinated connection between the virtual switch and the physical switch. Such an SDK, or similar switch driver, may transform a trivial virtual switch into a specialized virtual switch capable of producing the benefits of the embodiments described herein.

As described above, in one embodiment, virtual switch 250 is integrated into HSD410 such that this switch has different policies, features, and attributes on its switching functions. As will be appreciated by those of ordinary skill in the art in light of the teachings herein, different network switching components (e.g., communications controllers, switches) from different vendors may have different features, which may be advantageous in that such features may be readily and consistently applied by embodiments to virtual switches within HSD 410.

For example, applying access switch 130A's vendor-specific characteristics to VS250 may enable VS250 to achieve improvements in aspects related to integration between these components.

Fig. 6 depicts a network topology 600 illustrating an embodiment of Heterogeneous Switched Domain Controllers (HSDC) 610A-D. In various embodiments, HSDC610A-D provides centralized logical operations that employ the above-described functionality of HSD 410. For example, HSDC610A-D may coordinate enforcement of security policies for heterogeneous components throughout the domain. As will be appreciated by one of ordinary skill in the art in light of the teachings herein, HSDC610A-D may perform its controller functions by managing the creation, modification, and application of the enhanced headers described above that are used by the components of HSD 410.

The logic and controller functions described in the embodiments of HSDC610A-D above may be located in one or more components of network topology 600. The illustrated arrangement embodiment includes: HSDC610A is part of communications controller 270, HSDC 610B is part of access switch 130A, HSDC 610C is part of server 120A, and HSDC 610D is part of core switch 110. The above-described arrangement of HSDC610A-D as a hardware or software implementation should not be limited by the illustrated embodiments.

Method 700

This section and fig. 7 are a summary of the above-described aspects, and a flowchart of an example method 700 for integrating a virtual network switch device and a physical network switch device into heterogeneous switch domains is provided herein. The method 700, as an embodiment of the present invention, should not be limited to the above description and may be applied to other applications.

As shown in fig. 7, one embodiment of a method 700 begins at step 710, where a header is appended to a data packet received from a virtual machine by a first switching device, the header including domain information regarding a heterogeneous switching domain. In one embodiment, VS250 may append a header to a data packet received from VM 240A. Once step 710 is complete, method 700 proceeds to step 720.

In step 720, the data packet is processed by the first switching device, the processing being controlled by the header. In one embodiment, the packet is processed by VS250, this process being controlled by the header. Once step 720 is complete, method 700 proceeds to step 730.

In step 730, the packet is forwarded, which is controlled by the header. In one embodiment, VS250 forwards the packet to access switch 130A or SAE 570. Once step 730 is complete, method 700 ends.

Summary of the invention

While various embodiments of the present invention have been described above, it should be understood that they have been presented by way of example only, and not limitation. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should not be unduly limited to any of the embodiments set forth herein and should be determined with reference to the claims and their equivalents.

Claims (10)

1. A method of integrating virtual and physical network switching devices into heterogeneous switching domains, the method comprising:

appending, by a first switching device, a header to a packet received from a virtual machine, wherein the header includes domain information describing a component of the heterogeneous switching domain;

processing the data packet by the first switching device, wherein the processing is controlled by the header;

forwarding the processed data packet, wherein the forwarding is controlled by the header.

2. The method of claim 1, wherein the processed packet is forwarded to a second switching device, the second switching device being a switch or a router.

3. The method of claim 2, wherein any of the switch devices is physical or virtual, and wherein the heterogeneous switch domain comprises at least one virtual switch device.

4. The method of claim 1, wherein the domain information comprises:

an input port of a switching device in the heterogeneous switching domain; and

an output port of the switching device.

5. The method of claim 1, wherein the domain information comprises processing applied to the packet by the switching device.

6. The method of claim 1, wherein the domain information comprises filtering options applied to the packet by the switching device.

7. The method of claim 1, wherein the domain information comprises a communication path applied to the processed packet by the switching device, the communication path routing the processed packet through both a physical switching device and a virtual switching device.

8. The method of claim 1, wherein the domain information includes energy control and efficiency policies to be applied to the operation of the first switching device.

9. A system for integrating virtual and physical network components into a heterogeneous switching domain, the system comprising:

a communication controller having a switch acceleration engine, wherein the switch acceleration engine is to:

decoding a header of a packet received from a virtual machine, wherein the header includes domain information about the heterogeneous switching domain;

processing the data packet, wherein the processing is controlled by the header; and

forwarding the processed data packet to a network component, wherein the forwarding is controlled by the header.

10. A system for integrating virtual and physical network components into a heterogeneous switching domain, the system comprising:

a server;

a first virtual machine running on the server;

a virtual switch running on the server, the virtual switch receiving and processing a data packet from a first virtual machine, wherein upon receipt of the data packet from the first virtual machine, the virtual switch appends a header to the data packet, the header containing domain information relating to the heterogeneous switching domain; and

a physical switch connected to the server, wherein upon receipt of the data packet, the physical switch decodes the appended header and processes the data packet according to the header.