Error detection/correction and fault detection/recovery – Data processing system error or fault handling – Reliability and availability
Reexamination Certificate
2001-02-23
2004-08-31
Baderman, Scott (Department: 2184)
Error detection/correction and fault detection/recovery
Data processing system error or fault handling
Reliability and availability
C004S590000
Reexamination Certificate
active
06785843
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to intermediate nodes of a communications network and, in particular, to the infrastructure of an intermediate node, such as an aggregation router, used in a communications network, such as a computer network.
BACKGROUND OF THE INVENTION
A computer network is a geographically distributed collection of interconnected communication links and segments for transporting data between nodes, such as computers. Many types of network segments are available, with the types ranging from local area networks (LAN) to wide area networks (WAN). For example, the LAN may typically connect personal computers and workstations over dedicated, private communications links, whereas the WAN may connect large numbers of nodes over long-distance communications links, such as common carrier telephone lines. The Internet is an example of a WAN that connects disparate networks throughout the world, providing global communication between nodes on various networks. The nodes typically communicate over the network by exchanging discrete frames, cells or packets of data according to predefined protocols. In this context, a protocol consists of a set of rules defining how the nodes interact with each other.
Computer networks may be further interconnected by an intermediate network node, such as a switch or router, having a plurality of ports that may be coupled to the networks. To interconnect dispersed computer networks and/or provide Internet connectivity, many organizations rely on the infrastructure and facilities of Internet Service Providers (ISPs). ISPs typically own one or more backbone networks that are configured to provide high-speed connection to the Internet. To interconnect private networks that are geographically diverse, an organization may subscribe to one or more ISPs and couple each of its private networks to the ISP's equipment. Here, the router may be utilized to interconnect a plurality of private networks or subscribers to an IP “backbone” network. Routers typically operate at the network layer of a communications protocol stack, such as the internetwork layer of the Transmission Control Protocol/Internet Protocol (TCP/IP) communications architecture.
Simple networks may be constructed using general-purpose routers interconnected by links owned or leased by ISPs. As networks become more complex with greater numbers of elements, additional structure may be required. In a complex network, structure can be imposed on routers by assigning specific jobs to particular routers. A common approach for ISP networks is to divide assignments among access routers and backbone routers. An access router provides individual subscribers access to the network by way of large numbers of relatively low-speed ports connected to the subscribers. Backbone routers, on the other hand, provide transports to Internet backbones and are configured to provide high forwarding rates on fast interfaces. ISPs may impose further physical structure on their networks by organizing them into points of presence (POP). An ISP network usually consists of a number of POPs, each of which comprises a physical location wherein a set of access and backbone routers is located.
As Internet traffic increases, the demand for access routers to handle increased density and backbone routers to handle greater throughput becomes more important. In this context, increased density denotes a greater number of subscriber ports that can be terminated on a single router. Such requirements can be met most efficiently with platforms designed for specific applications. An example of such a specifically designed platform is an aggregation router. The aggregation router is an access router configured to provide high quality of service and guaranteed bandwidth for both data and voice traffic destined for the Internet. The aggregation router also provides a high degree of security for such traffic. These functions are considered “high-touch” features that necessitate substantial processing of the traffic by the router. More notably, the aggregation router is configured to accommodate increased density by aggregating a large number of leased lines from ISP subscribers onto a few trunk lines coupled to an Internet backbone.
The infrastructure of a typical router comprises functional components organized as a control plane and a data plane. The control plane includes the functional components needed to manage the traffic forwarding features of the router. These features include routing protocols, configuration information and other similar functions that determine the destinations of data packets based on information other than that contained within the packets. The data plane, on the other hand, includes functional components needed to perform forwarding operations for the packets.
For a single processor router, the control and data planes are typically implemented within the single processor. However, for some high performance routers, these planes are implemented within separate devices of the intermediate node. For example, the control plane may be implemented in a supervisor processor, such as a route processor, whereas the data plane may be implemented within a hardware-assist device, such as a co-processor or forwarding processor. In other words, the data plane is typically implemented in a specialized piece of hardware that is separate from the hardware that implements the control plane.
For implementations that require high availability, the data plane tends to be generally simple in terms of its organization and functions of the hardware and software. That is, the forwarding processor may be configured to operate reliably by reducing the complexity of its functional components. In contrast, the control plane tends to be more complex in terms of the quality and quantity of software operating on the supervisor processor. Failures are thus more likely to occur in the supervisor processor when executing such complicated code. In order to ensure high availability in an intermediate network node, it is desirable to configure the node such that if a failure arises with the control plane that requires restarting and reloading of software executing on the supervisor processor, the data plane continues to operate correctly. An example of such a high availability intermediate node is an asynchronous transfer mode (ATM) switch having a relatively simple switch fabric used to forward ATM cells from its input interfaces to output interfaces.
However, high-performance routers have evolved to where their data planes have become more complex in terms of software executing on their forwarding processors. This has increased the possibility of fatal errors arising in the forwarding processors that, in turn, halt forwarding of data traffic in the data planes. In a situation where a fatal error is detected in the data plane hardware or software, thereby requiring a reset and restart of the forwarding processor, the conventional approach is to restart the entire router including a restart of the control plane. Yet restarting of the entire router takes a relatively long period of time, e.g., on the order of minutes.
Specifically, restarting of the control plane requires reloading of an operating system executing on the supervisor processor, as well as reinitializing that operating system to a point where it acquires its necessary state. For example, re-initialization of the operating system includes acquiring lost dynamic state, such as routing protocol state information. A control plane restart is thus “visible” to neighboring routers as a topology change in the network that requires those neighbors having “knowledge” of the network to re-compute their routing databases when the restarted router is back online. In addition, the router must re-establish connections with its neighbors and exchange routing databases with those neighbors so as to “converge” its routing database. As noted, such activity consumes an excessive amount of time and the present invention is directed to a technique that addresses this prob
Hoerler Johannes Markus
McRae Andrew
Baderman Scott
Damiano Anne L.
LandOfFree
Data plane restart without state change in a control plane... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Data plane restart without state change in a control plane..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Data plane restart without state change in a control plane... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3344522