Distributed fabric management protocol

FIELD OF THE INVENTION

The invention relates generally to data centers and data processing. More particularly, the invention relates to a set of protocols and software components for centralized management of a distributed fabric of independent network elements.

BACKGROUND

Data centers are generally centralized facilities that provide the Internet and intranet services needed to support businesses and organizations. A typical data center may house a variety of types of electronic equipment, such as computers, servers (eg, email servers, proxy servers, and DNS servers), switches, routers, data storage devices, and other associated components. A given data center may have hundreds or thousands of interconnected network elements, which presents a complex, tedious task to a network administrator responsible for individually configuring each network element and the structural system as a whole.

The <patcit><text>US 2008/0 275 975 A1</text></patcit> discloses a rack switch with a rack and multiple blade server chassis inside the rack. Each blade server chassis has a variety of server blades in communication with at least one switch. Each switch contains a variety of external ports. At least two of the external ports on each switch are inter-switch link (ISL) ports. The rack switch also includes a variety of inter-switch links. Each inter-switch link electrically connects an ISL port of one of the switches to an ISL port of another one of the switches. The plurality of inter-switch links connects the switches such that the switches are concatenated in a loop. The inter-switch links convey Ethernet packets that represent server-to-server communication between server blades of different blade server chassis.

The <patcit><text>US 2010/0 162 036 A1</text></patcit> discloses a method for connecting a computing device to a cluster by recognizing the device; determining if the device is authorized to join the cluster; the device is configured; and assign a cluster role to the device. A device can be assigned a role as a cluster master, backup master, active device, standby device, or other role. The cluster master can be configured to assign tasks such as network flow processing to cluster devices. The cluster master and the backup master can maintain global runtime synchronization data associated with each of the network flows, shared resources, cluster configurations, and the like. The devices within the cluster can monitor each other. The monitoring may include the transmission of status messages, include the indicators of the device health to the other devices in the cluster. If a device meets failover conditions, a failover operation can be performed to replace the device with another standby device.

SUMMARY

In one aspect, the invention features a distributed structure system having a plurality of independent network elements interconnected by switch-over interconnections and assigned to a same group. Each network element includes one or more switching chips, a processor and a memory in which a layered program code executed by the processor is stored. The layered program code of each network element includes a device configuration (DC) stacking module and a switch discovery protocol (SDP) module. The SDP module of each network element, when executed, detects any other network element in the group and selects one of the network elements as a master network element. The SDP module of the main network element, when executed, sends messages to the DC stack module of the main network element. Each message sent identifies one of the network elements in the group. The DC stack module of the main network element, when executed, maintains a record of all network elements that are currently members of the group.

In another aspect, the invention features a computer program product for managing a distributed fabric system in which a plurality of independent network elements are interconnected by cross-switch connections. The network elements are assigned to a same group. The computer program product comprises a computer readable storage medium having computer readable program code formed thereon. The computer readable program code includes a switch discovery protocol (SDP) module configured to recognize each network element in the group and to select one of the network elements as a main network element. The SDP module, when executed by the main network element, is further configured to issue a message for each network element in the group. A device configuration (DC) stack module is set up to exchange switch information with every other network element in the distributed fabric system. The DC stack module, when executed by the main network element, is configured to receive each message issued by the SDP module executing on the main network element and to maintain a record of all network elements that are currently members in the group.

In yet another aspect, the invention features a method of managing a distributed fabric system in which a plurality of independent network elements are interconnected by cross-switch connections. The network elements are assigned to a same group. The method comprises recognizing each network element in the group and selecting one of the network elements in the group as a main network element. The selected master network element outputs a message for each network element in the group in response to the messages issued by the main network element and maintains a record of all network elements that are currently members of the group.

list of figures

The foregoing and other advantages of this invention may be better understood by referring to the following description taken in conjunction with the accompanying drawings, in which like reference characters indicate the same structural elements and features throughout the several figures. The drawings are not necessarily to scale, instead more emphasis may be placed on illustrating the principles of the invention.<ul list-style="none" id="ul_0001"><li id="ul_0001_0001"><figref>1</figref> FIG. 10 shows an embodiment of a network environment including a data center with a plurality of network elements, a server, and a management station.</li><li id="ul_0001_0002"><figref>2</figref> FIG. 12 is a block diagram of one embodiment of the data center including a main controller (controller) network element, a back-up network element, and a plurality of sequence network elements. FIG.</li><li id="ul_0001_0003"><figref>3</figref> FIG. 12 is a functional block diagram of one embodiment of a network element that includes a processor in communication with a memory and a layered software stored in the memory. FIG.</li><li id="ul_0001_0004"><figref>4A</figref> Figure 12 shows a block diagram of the layered software in a main network element and various communication channels between layers of the software.</li><li id="ul_0001_0005"><figref>4B</figref> Figure 12 shows a block diagram of the layered software in a sequence network element and various communication channels between layers of the software.</li><li id="ul_0001_0006"><figref>5</figref> FIG. 12 is a flowchart of one embodiment of a process for adding a new network element to the group of network elements. FIG.</li><li id="ul_0001_0007"><figref>6</figref> FIG. 12 is a flow chart of another embodiment of a process for adding a new network element to the group of network elements. FIG.</li><li id="ul_0001_0008"><figref>7</figref> FIG. 12 is a diagram of an example of a control flow through the layered software of the main network element and the sequence network element for applying a configuration to the sequence network element.</li><li id="ul_0001_0009"><figref>8th</figref> Figure 12 is a diagram of an example of a control flow through the layered software of the main network element and the sequence network element for collecting information from a sequence network element using an RPC call.</li><li id="ul_0001_0010"><figref>9</figref> FIG. 12 is a diagram of an example of a control flow through the layered software of the main network element and the sequence network element for updating firmware in a sequence network element.</li></ul>

DETAILED DESCRIPTION

Distributed structure systems described herein contain a plurality of interconnected independent network elements. Each of these network elements includes one or more switching chips to route packets through the distributed structure. Hereinafter, such network elements may be interchangeably referred to as "switches". These network elements exchange data with each other according to certain protocols. These protocols act to group the switches together so that they can be managed centrally as a single virtual switch. One of the protocols is a switch discovery protocol (SDP) that allows the network elements to detect when a network element joins or leaves the distributed fabric system. The SDP also selects a main network element or a control unit. Another protocol is a device configuration (DC) stack protocol that the network elements use to exchange switch information. On the main network element, the DC stack protocol is also set up to maintain a record of the network elements currently in the group. The main network element allows a network administrator to communicate with remotely located network elements to obtain information gathered by their switching chips, set parameters of their switching chips, configure the network element, and install updated versions of their firmware. Accordingly, the main network element provides a central location

<figref>1</figref> shows an embodiment of a network environment <b>2</b>that is a data center <b>10</b> contains that with a management station <b>4</b> and a server <b>6</b> over a network <b>8th</b> is in data exchange. For embodiments of the network<b>8th</b> include, but are not limited to, local-area networks (LANs), metro-area networks (MANs), and wide-area networks (WANs) such as the Internet or World Wide Web. In one embodiment, the network is<b>8th</b> set up as a Layer 2 (Layer 2 (L2)) VLAN. At the data center<b>10</b> It is generally a facility that hosts various computers, routers, switches, and other associated equipment with the support of applications and data that are an integral part of the operation of a business, organization, or other entity.

The data center <b>10</b> contains a variety of network elements <b>14</b>using inter-switch links (ISLs) <b>16</b> in data exchange. At each of the network elements<b>14</b> These are independent (stand-alone) packet-switched switches that are jointly set up to form a single distributed structure system, each designated as a member of a particular group (or cluster). Each group has a main (or control unit) network element, one or more standby or backup network elements, and one or more sequence network elements, as described in more detail in connection with<figref>2</figref> is described. The data center<b>10</b> can have more than one group, although each network element can only be a member of a single group. Members of the same group share the same group ID (GID). Users can set the GID through the command-line interface (CLI); the default value is 0. For network element embodiments<b>14</b> include, but are not limited to, core switches, access switches, fabric cards, line cards, and management modules in a physical chassis switch. Although only five network elements<b>14</b> As shown, the number of network elements in the distributed fabric system may be in the hundreds or thousands.

The data center <b>10</b> can be designed in a single location or distributed over several locations. Although each one (or both) from the management station<b>4</b> and the server <b>6</b> outside the data center <b>10</b> they can be shown as part of the data center <b>10</b> to be viewed as. In the data center<b>10</b> The functionality occurs on three levels: a management level, a control level and a data level. The administration of the group, such as configuration management, runtime configuration management, presentation of information (show and show), graph generation, and SNMP request handling, takes place at the administrative level. The control plane is assigned to those functions that involve network signal transmission and control. The data level manages the data flow. In the data center<b>10</b> For example, the functionality of the management layer is implemented centrally at a main network element, as further described herein. The functionality of the control level can be mainly with the server<b>6</b> be realized or distributed among the network elements. In general, the functionality of the data layer is among the network elements<b>14</b> distributed.

The management station <b>4</b> provides a centralized administration point for managing and controlling the network switches <b>14</b> of the distributed structure system. Through the management station<b>4</b> Communicates a user or network administrator of the data center <b>10</b> with the main network element to manage the group of imaginable thousands of network elements from a single location. One on the management station<b>4</b> Running a graphical user interface (GUI) may be used to provide the network administrator with a view of the entire network topology of the distributed fabric system. An example of such a GUI application is the Blade Harmony Manager® provided by IBM Corporation of Armonk, NY.

In addition, the management station <b>4</b> directly (point-to-point) or indirectly with the main network element <b>14</b> of the data center <b>10</b> be connected via one of a variety of connections, such as standard telephone lines, Digital Subscriber Line (DSL), asynchronous DSL, LAN or WAN connections (eg T1, T3), broadband connections (Frame Relay, ATM) and wireless connections (eg 802.11 (a), 802.11 (b), 802.11 (g), 802.11 (n)). Using a network protocol such as Telnet or SNMP (Simple Network Management Protocol), the management station can<b>4</b> to a command line interface of the given network element <b>14</b> access.

In general, it is the server <b>6</b> to a computer (or a group of computers), the data center <b>10</b> provide one or more services, examples of which include, but are not limited to, email servers, proxy servers, DNS servers, and a control system implemented at the control level of the distributed fabric system. To support the control plane functionality of an entire network element cluster, the server is<b>6</b> configured with sufficient processing power (eg with multiple processor cores).

<figref>2</figref> shows an embodiment of the data center <b>10</b> with the multitude of network elements <b>14</b>which includes a main (control units) switch 14-1, a backup (standby) switch 14-2, and a variety of sequential switches <b>14</b>Count -3, 14-4, 14-N. In general, one of the network elements is considered the main switch<b>14</b>-<b>1</b> Another is selected as the backup switch <b>14</b>-<b>2</b> and all other switches are follow-on switches. At the main switch<b>14</b>-<b>1</b> It is the control center for the entire distributed fabric system, and the next switch places any network element under the control of the main switch <b>14</b>-<b>1</b> where the main switch <b>14</b>-<b>1</b> Control plane and data plane packets to the follower network elements <b>14</b>-<b>3</b>. <b>14</b>-<b>4</b>. <b>14-N</b> sends and receives from them. During normal operation of the distributed fabric system, the backup switch operates<b>14</b>-<b>2</b> like a follow-up switch, except that the backup switch <b>14</b>-<b>2</b> in the event of a failure of the current main switch takes over the ownership of the main element.

The main switch <b>14</b>-<b>1</b> and the backup switch <b>14</b>-<b>2</b> stand over the ISLs <b>16</b> in each case in data exchange with each of the subsequent switches <b>14</b>-<b>3</b>. <b>14</b>-<b>4</b>. <b>14-N</b>, Other connection configurations may be used, such as concatenation, full mesh, star and stacked, without departing from the principles described herein. In one embodiment, the ISLs are<b>16</b>over which the network elements <b>14</b> Exchange data to 10 Gb Ethernet connections (with the network elements <b>14</b> according to the standard IEEE 802.Qgb exchange data).

Applications in such a distributed structure system preferably have three modes: a main mode, a backup mode, and a member mode. Depending on the role of a given network element, applications running on the network element will run in the appropriate mode. For example, be on the main switch<b>14</b>-<b>1</b> running applications in main mode. Each application can use a different approach, taking on different responsibilities in different modes. Example implementations of these applications include a purely centralized approach, a fully distributed approach, or a combination of a centralized and distributed approach. Applications running on a network element have a global view of all data ports on all network elements in the distributed fabric system.

<figref>3</figref> shows a simplified embodiment of a network element <b>14</b>that is a processor <b>20</b> in data exchange with a memory <b>22</b> and one in the memory <b>22</b> stored stratified software <b>24</b> contains. The layered software<b>24</b> contains a set of software components that cover all network elements <b>14</b> are common. In short, the set of software components includes protocols for grouping the plurality of network elements<b>14</b>to build a single big switch. By implementing the protocols provided by this set of software components, herein referred to as M-DFP or "Management Distributed Fabric Protocol", the group of network elements can be connected to a stacked switch, a virtual switch or to form a distributed chassis switch. This set of software components can also be used to implement a physical chassis switch. In general, the M-DFP software components are in the software stack<b>24</b> between the applications on a network element and the SDK (software development kit) on a system. An SDK includes runtime tools such as the Linux kernel, development tools, software libraries, and frameworks.

The layered software stack <b>24</b> contains a path selection layer <b>26</b>, a switch discovery protocol (SDP) module 28, an Ethernet based L2 transport (EL2T) layer 30, a remote procedure call (RPC) module 32, a port assignment / macro module <b>34</b>, a DC stacking module <b>36</b>, Application Programming Interface (DC) APIs 38, a switch-connect / disconnect module <b>40</b>, a CP (check point) module 42, and a Trivial File Transfer Protocol (TFTP) module 44. To implement the M-DFP between the network elements <b>14</b> Required data exchange can be carried out on standard Ethernet connections, a structure connection or any proprietary bus.

In a brief overview, the path selection layer (PSL) facilitates <b>26</b> CPU-to-CPU data exchange with SDP and EL2T module support <b>28</b>. <b>30</b>, The SDP module<b>28</b> and the PSL <b>26</b> work together to determine the output port through which a packet is sent from the network element to a remote network element. The PSL<b>26</b> contains a driver interface to both socket and data pins.

The SDP module <b>28</b> Detects when switches join or leave the group, known as "switch-found" or "switch-gone" events. Detecting the abandonment of a switch can be accomplished using an overaging mechanism. Downlink events on the ISLs<b>16</b> can also trigger a "switch gone" detection under certain conditions. The SDP module<b>28</b> reports the DC stacking module <b>36</b> on the same network element "Switch found" (STACK_RESET) - and "Switch gone" (STACK_EXIT) events for further processing. Other functions of the SDP module<b>28</b> lie therein, the health of the ISLs <b>16</b> check for all possible paths between the local network element and other remote network elements and provide a priority-based main-element selection mechanism.

The EL2T layer <b>30</b> provides a simple L2 transport protocol to exchange data between the upper layer protocols over the EL2T layer <b>30</b> to facilitate. In one embodiment, these upper layer protocols include the RPC module<b>32</b>, the DC stacking module <b>36</b>, the CP module <b>42</b>, the TFTP module <b>44</b> and all applications on the network element <b>14</b>,

The RPC module <b>32</b> provides an RPC mechanism based on the EL2T layer and through the DC-API layer <b>38</b> on the main switch <b>14</b>-<b>1</b> is used to exchange data with a remote network element.

The port assignment / macro module <b>34</b> At the top of layered software, applications provide mapping from a global CLI port to a physical device and port. In cooperation with the DC stacking module<b>36</b> and the SDP module <b>28</b> Maintains the port assignment / macro module <b>34</b> the assignment.

The DC stacking module <b>36</b> uses data structures to form a stack of network elements in the same group, with the network elements being coordinated to work together as a single switch. The DC stack modules<b>36</b> all network elements in the same group swap with each other using the EL2T module <b>30</b> for information exchange and stacking data. In addition, the DC stack modules work<b>36</b> on different network elements together to make sure the main switch <b>14</b>-<b>1</b> (by HOST UPDATE events) has up-to-date information for existing network elements. A HOST_ACTIVATE event is sent to the DC Stacking Module<b>36</b> to provide information refresh whenever the switch information for a given network element has changed and the DC Stack Module <b>36</b> already received a STACK_RESET event for this given network element.

Through the DC API layer <b>38</b> can on the network element <b>14</b> Executed Applications Make program calls to the hardware switching chips of the network element to either retrieve information from the chips or set parameters on the chips. These chips can be located either on the local network element or on a remote network element.

The switch connection / disconnect module <b>40</b> notifies applications on the network element of changes on the network element, placing applications at the top of the layered software stack <b>24</b> provides a global view of all data ports on all network elements in the group.

The CP module <b>42</b> supported on the main switch <b>14</b>-<b>1</b> Running applications, in preparation for an emergency fail-over from backup to main switch, each relevant database and each relevant state with the backup switch <b>14</b>-<b>2</b> to synchronize.

The TFTP module <b>44</b> provides a transport layer over the EL2T layer <b>30</b> ready for the DC stacking module <b>36</b> and applications to support either a configuration or a firmware image from the main switch <b>14</b>-<b>1</b> to any subsequent switch <b>14</b>-<b>3</b>. <b>14</b>-<b>4</b>. <b>14-N</b> to send via push transmission.

<figref>4A</figref> and <figref>4B</figref> show software stack <b>24</b> in a main switch <b>14</b>-<b>1</b> or in a follow-up switch <b>14</b>-<b>3</b> (as a representative example). Here each contains software stack<b>24</b> an application layer <b>50</b> with diverse applications <b>54</b>which includes a configuration application, a CLI application and a system log application as examples. double arrows<b>52</b> represent control flows between components in the software stack <b>24</b>,

In the layered software stack <b>24</b> is the SDP module <b>28</b> between the overlying DC stacking module <b>36</b> and the underlying path selection layer <b>26</b> arranged. The SDP module<b>28</b> includes a switch discovery protocol (SDP), a member tracking layer (MTL), and a path health maintenance (PHM) component. The SDP is a broadcast protocol that runs on a standard L2 VLAN that is used to discover switches in the distributed fabric system. After a switch receives a packet for the SDP, associated switch information is routed to maintain membership in the MTL. Such packets are referred to as switch discovery protocol data units or SDPDUs.

The MTL is a database layer of the SDP module <b>28</b> to keep track of the current network element members in the same group and maintain switch information for all such members. The switch information for each network element includes: the switch number, the switch's MAC address, switch information (SI) and switch member (SM) sequence numbers, and a timestamp of the last SDPDU received from a remote network element. Any changes to the switch information will be reported to the MTL for tracking. If an ISL<b>16</b> fails, the switch information experienced through this connection is deleted in the MTL. To aid in detecting a "gone switch" event, the MTL implements an overaging mechanism to declare a remote network element "over-age" using timers if no SDPDU is received by that network element for a fixed amount of time. The MTL also selects the main network element of a group based on switch priorities (carried in the SDPDUs of the network elements). After selection, the selected main network element reports the switch member information to the DC stack module<b>36</b> of the main network element. In addition, the MTL of the main network element forwards a message to the DC stack module<b>36</b> to notify you of any change in switch membership in the group, whether it comes from a newly discovered switch or from being aware of a switch abandonment.

The PHM component of the SDP module <b>28</b> Maintains the functional states of all possible paths between the local network element and all other remote network elements. When an SDPDU is received from a network element, the functional states for that network element in the MTL are also updated. The EL2T<b>30</b> and the PSL <b>26</b> use this health information to determine the path or port used for data exchange between the local network element and a remote network element

<figref>5</figref> shows an embodiment of a process <b>70</b>through which a new switch <b>14</b>-<b>5</b> join a stack (or a group, a cluster). After a restart, the new switch transmits<b>14</b>-<b>5</b> periodically (step <b>72</b>SDPDUs over its ISL ports. In response to receiving an SDPDU from the new switch<b>14</b>-<b>5</b> reported (step <b>74</b>) the SDP module <b>28</b> on the main switch <b>14</b>-<b>1</b> a STACK_RESET event to the DC module <b>36</b> For processing. In response to this STACK_RESET message, the DC Stack Module exchanges<b>36</b> with the DC stacking module <b>36</b> on the new switch <b>14</b>-<b>5</b> Data, with the aim of carrying out an information exchange.

During this exchange of information, the main switch gives itself <b>14</b>-<b>1</b> to recognize itself by sending an ICH_BIN_HAUPTELEMENT message to the DC Stacking Module <b>36</b> the new switch <b>14</b>-<b>5</b> sends (step <b>76</b>). The ICH_BIN_HAUPTELEMENT message preferably contains a signature indicating the current configuration of the main switch<b>14</b>-<b>1</b> designated. The new switch<b>14</b>-<b>5</b> responds to the message by making a request for a configuration (KONF_ANFR) to the main switch <b>14</b>-<b>1</b> sends (step <b>78</b>). In response to this KONF_ANFR message sends (step<b>80</b>) the main switch <b>14</b>-<b>1</b> one through the switch <b>14</b>-<b>5</b> Configuration script to be executed to the new switch <b>14</b>-<b>5</b>to join the pile. The configuration script implements the user configuration specified by the CLI. An example configuration performed by executing the configuration script is to determine which VLANs are allowed on a given port. After completing the script, the new switch issues<b>14</b>-<b>5</b> a message from (step <b>82</b>) to join the pile. Subsequently, the main switch notifies<b>14</b>-<b>1</b> the new switch <b>14</b>-<b>5</b> about its inclusion in the stack by sending a MEMBER_SEIN message (step <b>84</b>). After the new switch<b>14</b>-<b>5</b> joined the stack, the main switch <b>14</b>-<b>1</b> the new switch <b>14</b>-<b>5</b> manage and control.

Before the new switch <b>14</b>-<b>5</b> can join the stack, the image (ie the firmware) on the new switch <b>14</b>-<b>5</b> with the on the main switch <b>14</b>-<b>1</b> be executed image compatible. A check may be made in response to the ICH_BIN_HAUPTELEMENT and KONF_ANFR messages. Based on information carried by the KONF_ANFR message, the main switch<b>14</b>-<b>1</b> the version number of the on the new switch <b>14</b>-<b>5</b> experienced image. When the main switch<b>14</b>-<b>1</b> if the images are not compatible, the main switch will push-send a compatible firmware version to the new switch <b>14</b>-<b>5</b>,

<figref>6</figref> shows a shortened version <b>70 '</b> of the process <b>70</b> from <figref>5</figref>through which a new switch <b>14</b>-<b>5</b> join a stack (or a group, a cluster). As with the process<b>70</b> from <figref>5</figref> is the main switch <b>14</b>-<b>1</b> recognize itself by responding to receiving an SDPDU from the new switch <b>14</b>-<b>5</b> an ICH_BIN_MANUAL message to the new switch <b>14</b>-<b>5</b> sends (step <b>90</b>). In the shortened version, a quick join can be done when the new switch<b>14</b>-<b>5</b> already the same configuration as the main switch <b>14</b>-<b>1</b> has. Each of the messages contains additional information to facilitate this determination. For example, the ICH_BIN_HAUPTELEMENT message contains a signature indicating the current configuration of the main switch<b>14</b>-<b>1</b> designated. Based on this signature, the new switch determines (step<b>92</b>) that he has the same configuration as the current configuration of the main switch <b>14</b>-<b>1</b> has. Instead of issuing a KONF_ANFR message (step<b>78</b>. <figref>5</figref>) drives the new switch <b>14</b>-<b>5</b> accordingly, continue to send a STACK_RESET message (step <b>94</b>) to indicate a willingness to join the stack. In response, the main switch picks up<b>14</b>-<b>1</b> the new switch <b>14</b>-<b>5</b> in the stack by sending the MEMBER_SEIN message to the new switch <b>14</b>-<b>5</b> sends (step <b>96</b>). This "quick join" process can speed up the process of adding a new switch to a stack, thereby helping to stabilize the distributed fabric system by reducing the time during which the ISL is unstable. For example, an accidentally disconnected ISL is temporarily unstable after reconnecting.

<figref>7</figref> shows an example of the control flow through the layered software <b>24</b> the main switch <b>14</b>-<b>1</b> and the follow-up switch <b>14</b>-<b>3</b>For example, if a network administrator sends a configuration to the next switch <b>14</b>-<b>3</b> would like to apply. From the management station<b>4</b> (<figref>1</figref>), the network administrator provides through a command line interface (CLI) application <b>54</b>-<b>1</b> a connection to the main switch <b>14</b>-<b>1</b> and communicate with him.

Typically, a CLI script maintains a user configuration and the main switch pushes the CLI script to the next switch <b>14</b>-3. To push the CLI script, the CLI application swaps<b>54</b>-<b>1</b> with the TFTP module <b>44</b> Data off (arrow <b>100</b>) to the CLI script file for transmission to the remote sequential switch <b>14</b>-<b>3</b> prepare. The TFTP module<b>44</b> calls the EL2T layer <b>30</b> on (arrow <b>102</b>). From the EL2T layer<b>30</b> the packet processing goes to the path selection layer <b>26</b> over (arrow <b>104</b>), which determines the output port, through the packets to the next switch <b>14</b>-<b>3</b> to be sent. The path selection layer<b>26</b> exchanges with the SDK package interface <b>110</b> Data off (arrow <b>106</b>) that connects to the appropriate data port <b>112</b> forms (arrow <b>108</b>) through which the packets are to be sent. Go through the packages with the CLI script (arrow<b>114</b>) an ISL connection <b>16</b> to the next switch <b>14</b>-<b>3</b>,

At the next switch <b>14</b>-<b>3</b> The packet processing moves up through the layers of the software stack in an order <b>24</b>leading to the from the main switch <b>14</b>-<b>1</b> is reversed when preparing the packets taken for transmission. More specifically, the packets are running from the data port<b>112</b> up to the SDP packet interface <b>110</b> (Arrow <b>116</b>), then to the path selection layer <b>26</b> (Arrow <b>118</b>), the EL2T layer <b>30</b> (Arrow <b>120</b>) and the TFTP module <b>44</b> (Arrow <b>122</b>), then the TFTP module <b>44</b> to the CLI application <b>54</b>-<b>1</b> (Arrow <b>124</b>), which receives and executes the CLI script to apply the user configuration.

Running the CLI script generates (arrow <b>126</b>) Calls the DC API <b>38</b>, The DC API<b>38</b> that calls the switching chips <b>132</b> on the sequential switch <b>14</b>-<b>3</b> associated SDK <b>130</b> on (arrow <b>128</b>). The SDK<b>130</b> is operated to the chips <b>132</b> according to the on the application layer <b>50</b> configured CLI script to configure (arrow <b>134</b>).

<figref>8th</figref> shows an example of the control flow through the layered software <b>24</b> the main switch <b>14</b>-<b>1</b> and the follow-up switch <b>14</b>-<b>3</b>For example, if a network administrator receives information from a switching chip <b>132</b> collect or connect to a data port on a follow-up switch <b>14</b>-<b>3</b> want to manage. The network administrator issues from the management station<b>4</b> out about the application of the CLI <b>54</b>-<b>1</b> a connection to the main switch <b>14</b>-<b>1</b> and communicate with him.

In a nutshell gives the main switch <b>14</b>-<b>1</b> one through the follower switch <b>14</b>-<b>3</b> received and processed RPC call to collect the requested information or to manage the data port. More specifically, the packet processing moves from the CLI application<b>54</b>-<b>1</b> through the software stack <b>24</b> the main switch <b>14</b>-<b>1</b> down to the DC API <b>38</b> (Arrow <b>150</b>) and the DC API <b>38</b> to the RPC module <b>32</b> (Arrow <b>152</b>). The RPC module<b>32</b> calls the EL2T layer <b>30</b> on (arrow <b>154</b>), the EL2T layer <b>30</b> calls the path selection layer <b>26</b> on (arrow <b>156</b>) and the path selection layer <b>26</b> exchanges with the SDK package interface <b>110</b> Data off (arrow <b>158</b>). The SDK package interface<b>110</b> forms a connection to the corresponding data port <b>112</b> (Arrow <b>160</b>) through which the packets are to be sent. Go through the packages containing the RPC call (arrow<b>162</b>) an ISL connection <b>16</b> to the next switch <b>14</b>-<b>3</b>,

As in connection with <figref>7</figref> described, the packet processing moves at the next switch <b>14</b>-<b>3</b> in an order up through the layers of the software stack <b>24</b>which is used when preparing the RPC call packets for transmission through the main switch <b>14</b>-<b>1</b> down through the software stack traversed path is reversed. The packets run from the data port<b>112</b> up to the SDP packet interface <b>110</b> (Arrow <b>164</b>), then to the path selection layer <b>26</b> (Arrow <b>166</b>), then to the EL2T layer <b>30</b> (Arrow <b>168</b>), then from the EL2T layer <b>30</b> to the RPC module <b>32</b> (Arrow <b>170</b>). The RPC module<b>32</b> calls an RPC CLI application <b>54</b>-<b>2</b> on (arrow <b>172</b>). The RPC CLI application<b>54</b>-<b>2</b> performs the operation specified by the RPC call by calling the DC API <b>38</b> is output (arrow <b>174</b>). In response to this call, the DC API calls<b>38</b> that's the switching chips <b>132</b> associated SDK <b>130</b> on (arrow <b>176</b>). The SDK<b>130</b> gives a command to the chips <b>132</b> off (arrow <b>178</b>), for example, a connection of the chips <b>132</b> to configure or information from the chips <b>132</b> to collect.

<figref>9</figref> shows an example of the control flow through the layered software stack <b>24</b> the main switch <b>14</b>-<b>1</b> and the follow-up switch <b>14</b>-<b>3</b>if, for example, a network administrator switched the firmware in the sequential switch <b>14</b>-<b>3</b> want to update. To realize a firmware update, the network administrator puts out of the management station<b>4</b> from a connection to the main switch <b>14</b>-<b>1</b> and sends the new firmware to the main switch <b>14</b>-<b>1</b>, Through the CLI<b>54</b>-<b>1</b> the main switch <b>14</b>-<b>1</b> The network administrator can perform the firmware update of any subsequent switch without connecting to any network element other than the main switch <b>14</b>-<b>1</b> to have to produce.

To send the firmware update to the remote follow-up switch, the CLI application sends <b>54</b>-<b>1</b> the data containing the firmware update along a path down through the software stack that was generated by the CLI script during the in-game <figref>7</figref> described remote control configuration path is similar. The firmware update is running to the TFTP module<b>44</b> continue (arrow <b>200</b>) to the firmware update file for transmission to the remote follow-up switch <b>14</b>-<b>3</b> prepare. The TFTP module<b>44</b> calls the EL2T layer <b>30</b> on (arrow <b>202</b>). From the EL2T layer<b>30</b> the packet processing goes to the path selection layer <b>26</b> over (arrow <b>204</b>). The path selection layer<b>26</b> exchanges with the SDK package interface <b>110</b> Data off (arrow <b>206</b>), which connects to the data port <b>112</b> forms (arrow <b>208</b>) through which the packets are to be sent. Go through the packages with the firmware update (arrow<b>210</b>) an ISL connection <b>16</b> to the next switch <b>14</b>-<b>3</b>,

At the next switch <b>14</b>-<b>3</b> The packet processing moves in an order up through the layers of the software stack that are to the main switch <b>14</b>-<b>1</b> order reversed when preparing the firmware update for the transfer order. The packets run from the data port<b>112</b> up to the SDP packet interface <b>110</b> (Arrow <b>212</b>), then to the path selection layer <b>26</b> (Arrow <b>214</b>), to the EL2T layer <b>30</b> (Arrow <b>216</b>) and the TFTP module <b>44</b> (Arrow <b>218</b>), then the TFTP module <b>44</b> to the CLI application <b>54</b>-<b>1</b> (Arrow <b>220</b>). The CLI application<b>54</b>-<b>1</b> programs the flash <b>54</b>-<b>3</b> (ie a non-volatile memory) so um (arrow <b>222</b>) that it contains the firmware update.

As will be apparent to those skilled in the art, aspects of the present invention may be embodied as a system, method, and computer program product. Thus, aspects of the present invention may be fully embodied in hardware, entirely in software (including, but not limited to, firmware, program code, resident software, microcode), or a combination of hardware and software. All such embodiments may be referred to herein generally as a "circuit," "module," or "system." Additionally, aspects of the present invention may be in the form of a computer program product included in one or more computer readable media having computer readable program code formed thereon.

Any combination of one or more computer-readable media may be used. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. For example, a computer-readable storage medium may be, but is not limited to, a system, apparatus, or unit of electronic, magnetic, optical, electromagnetic, infrared, or semiconductor-use type, and any suitable combination of the foregoing. More specific examples of the computer-readable storage medium may include (non-exhaustive list): an electrical connection to one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), an erasable programmable read-only memory (EPROM) or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM) ), an optical storage unit, a magnetic storage unit, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any subject medium that may include or store a program for use by or in connection with a system, apparatus, or unit for executing instructions. an erasable programmable read-only memory (EPROM) or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM) ), an optical storage unit, a magnetic storage unit, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any subject medium that may include or store a program for use by or in connection with a system, apparatus, or unit for executing instructions. a magnetic storage unit or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any subject medium that may include or store a program for use by or in connection with a system, apparatus, or unit for executing instructions. a magnetic storage unit or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any subject medium that may include or store a program for use by or in connection with a system, apparatus, or unit for executing instructions.

A computer readable signal medium may include a propagated data signal having computer readable program code formed therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may be formed in any of a variety of forms including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that may transmit, propagate, or transport a program for use by or in connection with a system, apparatus, or unit for executing instructions.

A program code embodied in a computer readable medium may be transmitted by any suitable means including, but not limited to, wireless, wired, fiber optic, radio frequency (RF), etc., or any suitable combination thereof.

Computer program code for performing operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object-oriented programming language such as JAVA, Smalltalk, C ++ and Visual C ++ or the like and conventional procedural programming languages ​​such as the C and Pascal programming languages ​​or the like programming languages. The program code may be executed entirely on the user's computer, partly on the user's computer, as a standalone software package, partly on the user's computer and partly on a remote computer, or entirely on a remote computer or server.

The program code may be executed entirely on a user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partly on a remote computer, or entirely on a remote computer or server. Each such remotely located computer may be connected to the user's computer via any type of network, such as a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (for example, by an internet service provider over the internet).

Aspects of the present invention will be described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It is understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or the block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a universal computer, dedicated computer, or other programmable data processing device processor to generate a machine such that the instructions,

These computer program instructions may also be stored in a computer readable medium that may direct a computer, other programmable computing device, or other device to function in a particular manner such that the instructions stored in the computer readable medium produce an article of manufacture, including instructions corresponding to those described in U.S. Pat Block or in the blocks of the flowchart and / or the block diagram specified function / action.

The computer program instructions may also be loaded onto a computer, other programmable computing device, or other device to cause a series of operations to be performed on the computer, the other programmable device, or the other devices to generate a process implemented on the computer the instructions executed on the computer or other programmable device provide processes for realizing the functions / actions specified in the block or blocks of the flowchart and / or block diagram.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or section of code having one or more executable instructions for implementing the specified logical function (s). It should also be noted that in some alternative implementations, the functions specified in the block may occur in a different order than that indicated in the figures. For example, two consecutive blocks may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order depending on the functionality involved. It is also noted that each block of the block diagrams and / or mapping of schedules and combinations of blocks in the block diagrams and / or the mapping of schedules may be realized by dedicated hardware based systems or combinations of dedicated hardware and computer instructions having the stated functions or functions Perform actions.

Aspects of the described invention may be implemented in one or more integrated circuit (IC) chips fabricated by semiconductor manufacturing processes. The manufacturer of the IC chips can distribute them in the form of raw wafers (on a single wafer with several unpacked chips), as a bare chip, or in a packaged form. In packaged form, the IC chip is mounted in a single chip package, for example a plastic carrier having terminals attached to a motherboard or other parent carrier, or in a multi-chip package, for example, a ceramic carrier having surface leads and / or hidden leads. The IC chip is then with other chips, discrete circuit elements and / or other signal processing units as part of either an intermediate product, such as a motherboard, or a final product. The end product can be any product that includes IC chips, ranging from electronic game systems and other simple applications to sophisticated computer products with a display, input unit and central processor.

Many changes and variations will be apparent to those skilled in the art without departing from the scope and spirit of the invention. The embodiments have been chosen to best describe the modes of operation of the invention and the practical application, and to enable others skilled in the art to appreciate the invention for a variety of embodiments with various modifications as appropriate to the particular use contemplated.

The terminology used herein is for the purpose of describing particular embodiments only and is not to be construed as limiting the invention. As used herein, the singular forms "a," "an," and "the" and their declinations are also intended to include plurals unless clearly stated otherwise in context. It is further understood that the terms "having" and / or "comprising" in this document indicate the presence of specified features, integers, steps, acts, elements, and / or components, but not the presence or addition of one or more others Exclude features, integers, steps, operations, elements, components and / or groups thereof.

The corresponding structures, materials, acts and equivalents of all means or steps and functional elements in the following claims are intended to include all structures, materials or acts for performing the function in combination with other claimed elements as specifically claimed. The description of the present invention has been presented for purposes of illustration and description, but is not to be construed as exhaustive or limited to the invention in the form disclosed.

Although the invention has been shown and described with reference to specific preferred embodiments, it should be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the following claims becomes.