摘要:
A method and apparatus for hierarchical redundancy for a distributed control plane. In one embodiment of the invention, control plane processes are distributed among a plurality of processing entities including an active primary control processing entity and multiple secondary processing entities. Each of the secondary processing entities performs a dual role; an active role and a standby role. An application redundancy manager (ARM) instantiated on the active primary control processing entity manages the redundancy services for the secondary processing entities. For each secondary processing entity, the ARM selects one of the secondary processing entities to act as a backup for another one of the secondary processing entities. Upon a failure of one of the secondary processing entities, the ARM causes the secondary processing entity backing up the failed secondary processing entity to transition its standby role to an active role regarding the services provided by the failed secondary processing entity.
摘要:
A method and apparatus for a distributed control plane. In one embodiment of the invention, a primary control card distributes control plane process instances among one or more secondary cards, including a secondary control card and/or one or more Advanced Service Engine (ASE) cards. The primary control card associates particular control messages with particular control plane process instances. Upon a line card receiving a control message that is associated with a particular control plane instance, the line card forwards the control message directly to that particular control plane instance.
摘要:
A method and apparatus for a distributed control plane. In one embodiment of the invention, a primary control card distributes control plane process instances among one or more secondary cards, including a secondary control card and/or one or more Advanced Service Engine (ASE) cards. The primary control card associates particular control messages with particular control plane process instances. Upon a line card receiving a control message that is associated with a particular control plane instance, the line card forwards the control message directly to that particular control plane instance.
摘要:
A method and apparatus for hierarchical redundancy for a distributed control plane. In one embodiment of the invention, control plane processes are distributed among a plurality of processing entities including an active primary control processing entity and multiple secondary processing entities. Each of the secondary processing entities performs a dual role; an active role and a standby role. An application redundancy manager (ARM) instantiated on the active primary control processing entity manages the redundancy services for the secondary processing entities. For each secondary processing entity, the ARM selects one of the secondary processing entities to act as a backup for another one of the secondary processing entities. Upon a failure of one of the secondary processing entities, the ARM causes the secondary processing entity backing up the failed secondary processing entity to transition its standby role to an active role regarding the services provided by the failed secondary processing entity.
摘要:
Methods and systems are provided for steering network packets. According to one embodiment, a dynamically configurable steering table is stored within a memory of each network interface of a networking routing/switching device. The steering table represents a mapping that logically assigns each of the network interfaces to one of multiple packet processing resources of the network routing/switching device. The steering table has contained therein information indicative of a unique identifier/address of the assigned packet processing resource. Responsive to receiving a packet on a network interface, the network interface performs Layer 1 or Layer 2 steering of the received packet to the assigned packet processing resource by retrieving the information indicative of the unique identifier/address of the assigned packet processing resource from the steering table based on a channel identifier associated with the received packet and the received packet is processed by the assigned packet processing resource.
摘要:
Methods and systems are provided for steering network packets. According to one embodiment, a mapping associates a processing resource with a network interface module (netmod) and/or a number of line interface ports included within the netmod. In one embodiment, the mapping is configurable within the processing resource and pushed to the netmod. The netmod uses the mapping to steer network packets to the processing resource when the packets conform to the mapping. The mapping may be additionally used to identify a specific process that is to be performed against the packets once the processing resource receives the steered packets from the netmod.
摘要:
Methods and systems are provided for bridging heterogeneous media packets using a single processor resource having a virtual bridge. Network interfaces associated with heterogeneous media channels relay network packets to the virtual bridge. The virtual bridge accesses metadata associated with the relayed network packets and translates the network packets between media formats. The translated network packets are then relayed to an appropriate network interface. In one embodiment, the virtual bridge is dynamically configurable within the processing resource.
摘要:
Methods and systems are provided for steering network packets. According to one embodiment a method is provided for steering incoming network packets. Each network packet processing resource of a network routing/switching device is dynamically assigned to one or more network interfaces of the network routing/switching device. Each of the network packet processing resources includes one or more processing elements and a memory. Incoming network packets received by the network interfaces are steered to an appropriate network packet processing resource based on the dynamic assignment.
摘要:
A system and method for dynamically selecting a level of compression to be applied to data to be served to a client. The level of compression may be selected on the basis of one or more factors, such as: the bandwidth of a communication link between the client and a server, the amount of data requested by the client, the workload of the server, whether the data are cacheable, etc. The server can readily obtain information such as the amount of requested data and the available CPU time on the server. To determine the bandwidth, the server may conduct a test transfer of a known amount of data to or from the client, or consult a database identifying known or expected bandwidths for specific client connections (or addresses). Based on the selected factor(s), the server dynamically selects a level of compression for the data.
摘要:
Techniques for automatically modifying behavior of a compiled application include receiving a first set of compiled instructions for the application. The first set of compiled instructions is modified to generate a modified set of compiled instructions. Modifying the first set of compiled instructions includes inserting a new set of one or more instructions for invoking a first routine that provides new behavior. The first routine is not part of the first set of compiled instructions. These techniques allow an administrator to automatically instrument compiled code of an application to provide new behavior for the application without taking the application offline for substantial periods of time. In particular, the techniques allow a service provider to automatically instrument existing applications, components, and sub-components to measure and respond to server-side performance without taking the applications offline.