摘要:
An apparatus for translating a message between a first transmission protocol to a second transmission protocol limits buffer sizes for storing incoming and outcoming message data. To that end, each message has a message size that is no larger than a maximum message size, and the first protocol transports message data with message envelopes having an envelope size that is no larger than a maximum envelope size. The apparatus further includes a first protocol interface for interfacing with first protocol devices that communicate via the first protocol, a second protocol interface for interfacing with second protocol devices that communicate via the second protocol, and control logic that couples the first protocol interface with the second protocol interface.
摘要:
A multicast network device, such as a router, may support a plurality of multicast routing protocols. Each multicast routing protocol maintains its own routing table that stores the multicast routes known to the multicast routing protocol. A unicast routing table may also be included in the network device. Some multicast protocols make us of unicast as well as multicast routes. A single multicast routing table is provided to store the multicast routes for each multicast routing protocol and a selected set of unicast routes form the unicast routing table. Multicast routing table management logic controls the content of the multicast routing table. The single multicast routing table allows for efficient access to the multicast and unicast routes as well as for the exchange of routing information between different multicast routing protocols.
摘要:
A multicast network device, such as a route may support a plurality of multicast routing protocols. A single multicast routing table may be provided to store the multicast routes for each multicast routing protocol and a selected set of unicast routes from a unicast routing table. In order to synchronize route changes in the multicast routing table with the plurality of multicast routing protocols, a route ID value is assigned to each route in the multicast routing table. Each multicast routing protocol is assigned a bookmark in a route change queue, where the bookmark is assigned the route ID value of the last route processed by the multicast routing protocol. When a route is changed, the route is assigned a new route ID value and stored in the route change queue. A multicast routing protocol may determine if a route change has occurred by comparing its bookmark to the highest route ID value in the route change queue.
摘要:
An apparatus and method of requesting retransmission of at least a portion of a message (having a plurality of message segments) from a sender utilizes message units in a memory device for storing data relating to retransmit messages. In particular, each message unit in the memory has data for one message segment. To that end, a retransmit message requesting retransmission of a set of message segments to a given receiver is received from the given receiver. The given retransmit message then is parsed to determine both the identity of the given receiver, and the identity of the set of message segments requested by the given receiver. A message unit then is produced in the memory for each of the set of message segments that does not have an existing message unit in memory. Data representing the identity of the given receiver then is added to all message units for the set of message segments.
摘要:
Safe and efficient passing of information from a forwarding-plane to a control-plane is provided. The information can be passed from a forwarding-plane process to a control-plane process without having to modify the control-plane process and without requiring the processes to pass information via shared memory. The information is encoded in the forwarding-plane process. The encoded information is passed to the operating system, wherein the operating system interprets the encoded information and reports the information to the control plane process. The present invention can be advantageously utilized in passing multicast events from a forwarding-plane process to a control-plane process. Multicast events can be passed from a forwarding-plane process to a control-plane process without having to modify the control-plane process and without requiring the processes to pass messages via shared memory.
摘要:
Described are a method and a device for efficiently switching multicast data flows from a shared distribution tree to a shortest path distribution tree. The method achieves an efficient and scalable tree switch that reduces the latency of multicast data transmitted from the source to receivers. A determination is made for each source group (S,G) entry in a portion of a forwarding plane database of a router as to whether a byte count for that entry exceeds a threshold value. A message sent from the forwarding plane to the router control plane indicates the (S,G) entries determined to have byte counts exceeding the respective threshold values. For each message entry, the respective shared distribution tree is switched to a shortest path distribution tree. The method achieves a substantial reduction in the number of inter-process messages exchanged between the control plane and the forwarding plane compared to conventional tree switchover techniques.
摘要:
Safe and efficient passing of information from a forwarding-plane to a control-plane is provided. The information can be passed from a forwarding-plane process to a control-plane process without having to modify the control-plane process and without requiring the processes to pass information via shared memory. The information is encoded in the forwarding-plane process. The encoded information is passed to the operating system, wherein the operating system interprets the encoded information and reports the information to the control plane process. The present invention can be advantageously utilized in passing multicast events from a forwarding-plane process to a control-plane process. Multicast events can be passed from a forwarding-plane process to a control-plane process without having to modify the control-plane process and without requiring the processes to pass messages via shared memory.
摘要:
Described are a method and a device for efficiently switching multicast data flows from a shared distribution tree to a shortest path distribution tree. The method achieves an efficient and scalable tree switch that reduces the latency of multicast data transmitted from the source to receivers. A determination is made for each source group (S,G) entry in a portion of a forwarding plane database of a router as to whether a byte count for that entry exceeds a threshold value. A message sent from the forwarding plane to the router control plane indicates the (S,G) entries determined to have byte counts exceeding the respective threshold values. For each message entry, the respective shared distribution tree is switched to a shortest path distribution tree. The method achieves a substantial reduction in the number of inter-process messages exchanged between the control plane and the forwarding plane compared to conventional tree switchover techniques.