Classifications

• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04Q—SELECTING
  • H04Q11/00—Selecting arrangements for multiplex systems
  • H04Q11/04—Selecting arrangements for multiplex systems for time-division multiplexing
  • H04Q11/0428—Integrated services digital network, i.e. systems for transmission of different types of digitised signals, e.g. speech, data, telecentral, television signals
  • H04Q11/0478—Provisions for broadband connections

Definitions

• the field of the invention is that of communication over a broadband network of data processing systems, for example, a network using a SONET backbone and Hybrid Fiber-Coax(ial cable) ("HFC") access network to connect users to the backbone-
• HFC Hybrid Fiber-Coax(ial cable)
• a packet communications standard for the HFC environment is DOCSIS (Data Over Cable Service Interface Specification, Document No. SP-RFI-I05-991105) of CableLabs.
• Fig. 1 shows a typical configuration of wide-area delivery of data to HFC systems (each connected to 200-2000 households passed (HHP) ) .
• the head-end termination system 2 is connected to a SONET ring 4 via a multiplexer drop on the ring 6.
• the head-end 2 is connected to a fiber node 9 by a fiber downstream connection 7 and a fiber upstream connection 8.
• the fiber node 9 has coax connectors 10 out to cable modem subscribers (i.e. homes 11).
• These multiplexers currently cost some $50,000 in addition to the head-end termination system, and scaling up of service to a community may require new multiplexers and servers .
• the failure of a component on the head-end termination system can take an entire "downstream" (from the head-end to the end-user) sub-network ( Figure 7) out of communication with the attached networks .
• FIG. 2 shows a system 20 having a reverse path monitoring system 22, an IP switch 24, a router 26, modulators and up-converters 28, a provisioning system 30, telephony parts 32, and a plurality of CMTS's 34 (cable modem termination systems) .
• This type of system typically is constructed with multiple systems from multiple vendors, has different management systems, a large footprint, high power requirements and high operating costs .
• FIG. 3 A typical current network broadband cable network for delivery of voice and data is shown in Fig. 3.
• Two OC-12 packet over SONET (POS) links 40, 42 are each connected to one of two backbone routers 44, 46 which are in turn networked to two switches 48, 50.
• the switches 48, 50 are networked to CMTS head-end routers 52, 54.
• the CMTS head-end routers 52, 54 are connected to a plurality of optical nodes 56 through a CMTS 61.
• the switches 48, 50 are also connected to a plurality of telephone trunk gateways 58 which are in turn connected to the public switched telephone network (PSTN) 60.
• PSTN public switched telephone network
• this type of network also typically has multiple vendors for its multiple systems, has different management systems, a large footprint, high power requirements and high operating costs . It remains desirable to have a truly integrated solution to reduce the size of the system, its power needs, and its costs, as well as to ensure greater consistency and increased reliability in data delivery .
• the problems of providing an integrated network solution for data processing in a broadband network environment are solved by the present invention of a highly integrated carrier-class broadband access system for delivering high quality voice, data and video services.
• a process and system are provided in which switching to the HFC conduits is performed in the IP (Internet Protocol) or Network Layer (OSI Layer 3) using combinations of Wide Area Network (WAN) interface cards, HFC interface (Cable Modem Termination) cards, and inter- chassis link (ICL) cards in a fully meshed common chassis, controlled by a cluster manager.
• the ICLs may stretch over several miles, but the cluster of chassises, controlled by the cluster manager, acts as a single IP switch.
• the chassis can interface with other broadband access media as well, for example Digital Subscriber Line (DSL) , fixed wireless Local Multi-point Distribution Service (LMDS) and Multi-channel Multi-point Distribution Service (MMDS), as well as "fiber to the curb” (FTTC) .
• DSL Digital Subscriber Line
• LMDS fixed wireless Local Multi-point Distribution Service
• MMDS Multi-channel Multi-point Distribution Service
• FTTC fiber to the curb
• the invention offers the flexibility of deploying a variety of local and wide-area configurations, making it suitable for smaller operators requiring a ready path for scaling up.
• Different media cards may be used for different modes of broadband communication, such as one-way cable with telephone modem return.
• the invention also allows several levels of redundancy for different network elements, allowing an operator to provide higher availability by having redundancy of particularly stressed elements.
• the invention supports tiered voice and data systems .
• the invention provides a reliable, scalable system with a small footprint and low power requirement .
• Fig. 1 shows a prior art network having an HFC head-end server connected to a SONET ring through a multiplexer drop
• Fig. 2 shows a prior art HFC data over cable delivery system
• Fig. 3 shows a prior art data delivery network
• Fig. 4 is a block diagram of a chassis according to principles of the invention.
• Fig. 5 shows an integrated cable infrastructure having the chassis of Fig. 4;
• Fig. 6 shows a network using a plurality of chassises, such as the one of Fig. 4, in a ring topology
• Fig. 7 shows a first hierarchical network having a primary chassis and a secondary chassis operating according to principles of the present invention
• Fig. 8 shows a star network having a plurality of chassises such as the one of Fig. 4;
• Fig. 9 shows a second hierarchical network having a plurality of chassises such as the one of Fig. 4;
• Fig. 10 shows a meshed network having a plurality of chassises such as the one Fig. 4;
• Fig. 11 is a block diagram of the application cards and backplane portions of the chassis of Fig. 4;
• Fig. 12 is a schematic diagram of the backplane interconnections, including the switching mesh
• Fig. 13 is a block diagram of a BAS header according to principles of the present invention
• Fig. 14 is a block diagram of a Gigabit Ethernet inter- chassis link or egress application module
• Fig. 15 is a block diagram of an ARP table
• Fig. 16 is a block diagram of a two egress modules in a chassis
• Fig. 17 is a block diagram of a route server
• Fig. 18 is a block diagram of a chassis controller module
• Fig. 19 is a block diagram of the network management architecture
• Fig. 20 is a block diagram of the CMTS application module
• Figure 21 is a block diagram of the backplane mesh interface
• Figure 22 is a block diagram of the MCC tag.
• Fig. 4 shows a chassis 200 operating according to principles of the present invention.
• the chassis 200 integrates a plurality of network interfaces and applications into a single switch system.
• the chassis of the invention is a fully-meshed IP-switch with. igh performance packet forwarding, filtering and QoS/CoS (Quality of Service/Class of Service) capabilities using low-level embedded software controlled by a cluster manager in a chassis controller.
• the packet forwarding, filtering and QoS/CoS is distributed across application modules (also called "cards") inside the chassis.
• the operations are performed in each of the modules by a fast IP processor.
• the chassis controller and cluster manager control the operation and configure each of the modules .
• Higher-level software resides in the cluster manager, including router server functions (RIPvl, RIPv2 , OSPF, etc.), network management (SNMP V1/V2) , security, DHCP, LDAP, and remote access software (VPNs, PPTP, L2TP, and PPP) , and can be readily modified or upgraded.
• the chassis 200 has fourteen (14) slots for modules. Twelve of those fourteen slots hold application modules 205, and two slots hold chassis controller modules 210.
• Each application module has an on-board DC-DC converter 202 and is "hot-pluggable" into the chassis.
• the chassis controller modules 210 are for redundant system clock/bus arbitration.
• the chassis also has redundant power supply modules .
• the power supply modules and the DC-DC converters comprise a fully distributed power supply in the chassis . Examples of applications that may be integrated in the chassis are a CMTS module 215, an Ethernet module 220, a SONET module 225, and a telephony application 230.
• Another application may be an inter-chassis link (ICL) port 235 through which the chassis may be linked to another chassis.
• the ICL port is the only egress port.
• the ICL port may be implemented using any egress module, e.g., 10/100 Ethernet, IG Ethernet, and Packet-over-SONET (PoS) .
• Fig. 5 shows an integrated cable infrastructure 260 having the chassis 200 of Fig. 4.
• the chassis 200 is part of a regional hub 262 for voice and data delivery.
• the hub 262 includes a video controller application 264, a video server 266, Web/cache servers 268, and an operation support system (OSS) 270, all networked to the chassis 200 acting as an IP access switch.
• the chassis 200 is connected to a SONET ring 272, outside the hub 262, having an Internet connection 274 and a Public Switched Telephone Network (PSTN) connection 276.
• PSTN Public Switched Telephone Network
• the chassis 200 is also connected by an HFC link 278 to cable customers and provides IP-based services including voice, data, video and fax services.
• Each HFC application module can handle up to 2000 cable modem service subscribers. The logical limit to the number of subscribers is 8192.
• the chassis can support a plurality of HFC links and also a plurality of chassises may be networked together (as described below) to support over one
• the local HFC cable system or loop is a coaxial cable distribution network with a drop to a cable modem.
• Fig. 6 shows a ring network 300 using a plurality of chassises of Figure 4.
• the plurality of chassises 302, 304, 306, 308 are connected as a ring over full-duplex inter- chassis links 310, 312, 314, 316.
• the ring configuration allows chassis 302 and its associated cable networks to communicate with chassis 306 and its associated cable networks through chassis 308 should chassis 304 or the ICLs 310, 312 between them fail.
• Fig. 7 shows a first hierarchical network 328 having a primary chassis 330 and a secondary chassis 332 operating according to principles of the present invention.
• the primary chassis is connected to fiber optic communication lines (OC-n) 334, 336. OC-12 lines are shown in the drawing, however OC-3 and OC-48 are also supported.
• OC-n fiber optic communication lines
• the primary chassis 330 may also be connected to the PSTN 338.
• the primary 330 and secondary 332 chassises are linked by a full-duplex link 340 that may be a Fast Ethernet (FE) , Gigabit Ethernet, or a Packet-over-SONET (PoS) type connection.
• the secondary chassis 332 is connected to a plurality of optical nodes 342.
• the primary chassis manages the cluster with its cluster manager.
• Other configurations are possible, including a "star" configuration 350, as shown in Fig. 8 with a primary chassis 352 and secondary chassises 354, 356, 358, 360, 362, or a tiered arrangement 380, as shown in Fig.
• a mesh configuration 400 is shown in Figure 10 with chassises 402, 404, 406, 408, 410 where each chassis has in inter-chassis link to every other chassis.
• Primary and secondary chassises are determined by system configuration. Each chassis is substantially the same as every other chassis.
• Fig. 11 shows application modules connected to a backplane 420 of the chassis 200 of Fig. 4.
• Each application module 422 interfaces with the backplane 420 through a Mesh Communication Chip (MCC) 424 that will be described more fully below.
• MCC 424 has twelve (12) serial link interfaces 426, eleven that run to the backplane 420.
• the eleven serial links that run to the backplane on each application module are for connecting the application module to every other application module in the chassis.
• One link is for connecting the module with itself, i.e., a loop-back.
• the application modules 422 are connected to chassis controllers 428, 430 over a chassis management bus 432.
• the second chassis controller 430 is optionally used for redundancy in order to make the system more reliable.
• a second chassis management bus (not shown) is provided in a preferred embodiment also for redundancy/reliability purposes .
• the backplane is fully meshed meaning that every application module has a direct point-to-point link to every other application module in the chassis through the serial links.
• the mesh threads in the mesh backplane each provide a continuous direct channel for communication of data at a rate of 1.5 gigabits per second or greater. Only a portion of the connections 200 are shown in Fig. 11 as an example.
• the backplane mesh is shown in Fig. 12.
• the 12 channels with serial links of the MCC are numbered 0 to 11. The number is referred to as the channel ID or CID. Channels will be described more fully below.
• the slots on the backplane are also numbered from 0 to 11 (slot ID, or SID) .
• SID slot ID
• the chassis system does not require, however, that a channel 0 be wired to a slot 0 on the backplane.
• a serial link may be connected to any slot.
• the slot IDs are dynamically configured depending on system topology. This allows for freedom in backplane wiring which reduces routing complexity.
• each application module is also connected to a chassis management bus 432 that provides the modules a connection to the chassis controllers.
• the chassis For switching packets between chassises over the inter- chassis links (ICLs) and for switching packets inside the chassises over the MCC links, the chassis has a inter-chassis switching layer.
• the inter-chassis switching layer lies below the IP layer 3 (L3, the network layer) . Packet processing in the chassis is broken down into two types of traffic: unicast and broadcast/multicast. Switching through the inter-chassis switching layer is accomplished using the inter-chassis header 500 (also called the inter-chassis tag) shown in Fig. 13.
• the Bas_Type field 502 has x bits and indicates the inter-chassis header type. This field may be used to indicate that the fabric interface address (FIA) has logical ports, to indicate whether the packet is a broadcast or unicast packet and to indicate relevant fields in the BAS header.
• the Bas_Type field 502 is for decoding the BAS header and to assist in packet forwarding.
• the Keep field 504 has x bits and determines whether the packet may be dropped due to congestion.
• the priority field has x bits (not shown in Figure 13) and determines the packet priority and where to queue the packet due to congestion.
• the fragment field 506 has x bits and indicates the packet fragmentation and whether the packet consists of two frames .
• a next_Hop field 508 has a plurality of bits and is used for next hop information for intra-chassis packet transfer. This field is inactive unless the Bas_Type field indicates otherwise.
• the Encap_Type field 510 is a one-bit field that indicates whether the packet needs further Layer 2 (data layer, below the inter-chassis switching layer) processing or whether the packet can be forwarded without further processing.
• the Mcast_Type field 512 is a one-bit field that indicates whether the packet is broadcast or multicast .
• the Dest_FIA_Type field 514 is a one-bit field that indicates whether the destination FIA is provided in short form ( ⁇ chassis/slot/port>) or long form ( ⁇ chassis/slot/port/logical port>) .
• the Src_FIA_Type field 516 is a one-bit field that indicates whether the source FIA field is provided in short form or long form.
• the Data_Type field 518 has a plurality of bits and is used to indicate the type of traffic being carried in the payload.
• the TTL field (not shown) has a plurality of bits and is a fail-safe mechanism to prevent packets from staying in the system indeterminately.
• the TTL is decremented each time it is received at an ICL port. If this field is zero after decrementing, the packet is discarded.
• the Forwarding Info field 520 has a plurality of bits and contains the forwarding table revision, the forward_table_entry key/id, and the next hop information.
• the Destination FIA field 522 has a plurality of bits and indicates the final destination of the packet.
• This field contains the chassis/slot/port and logical port information.
• a chassis value of zero has a special meaning, denoting the chassis with a Master Agent (to be described below) .
• a port value of zero also has a special meaning, denoting that the receiver of the packet is an application module.
• the logical port may be used to indicate which stack/entity in the module is to receive the packet. All edge ports and ICL ports are therefore 1-based, i.e. the port numbers are greater than zero .
• the Src FIA field 524 has a plurality of bits and indicates the source of the packet. This field is used by a route server to identify the source of the incoming packets.
• the application cards are also called data processors, data processing application module, and data communication module.
• Fig. 14 is a block diagram of an Ethernet application module 550 in the chassis. The application module is connected to both the mesh backplane 552 and to the management busses A 554 and B 556. In the Ethernet application module 550, a fast IP processor (FIPP) 558 is connected to both a PCI bus 560 and an F-bus 562.
• FIPP fast IP processor
• the FIPP 558 has an Advanced RISC Machines (ARM) processor core 564 and six micro-engines 566.
• the FIPP 558 is connected to a DRAM 568 for storing packets and an SRAM 570 for storing a routing table.
• An Ethernet device 572 having 8 ports is connected to the F-bus 562.
• An MCC 574 is also connected to the F-bus.
• the MCC 574 provides the connections to the mesh backplane 552.
• the Ethernet device 572 provides connections to the outside of the chassis.
• Two MAC devices are connected between the PCI bus 560 and the management buses.
• MAC A 576 is connected between the PCI bus 560 and management bus A 554.
• MAC B 578 is connected between the PCI bus 560 and management bus B 556.
• a data packet comes into the Ethernet device 572, it goes through the FIPP 558 "and is stored in the DRAM 568.
• the micro-engines 566 examine the data packets in parallel. The micro-engines 566 look at the IP address in the packet and then look up the destination address in the forwarding table stored in the SRAM 570. The forwarding table provides the chassis, slot and port that the packet will go out on.
• the packet comes in over the Ethernet device, the packet has an Ethernet header. If the packet goes out the same slot through which it came, a inter-chassis header is not applied. The FIPP determines the sending port and sends the packet out that port. If the packet is to exit by a different slot, the Ethernet header is removed .
• the minimum information in the BAS header is destination data, chassis, slot, and port information.
• the packet further includes an IP header and a payload.
• the FIPP has transmit queues where the packets are queued before transmission. The packets are sent over the F-bus 562 to the MCC 574 which sends data out in 64-byte chunks.
• the application module 550 puts the packet, or pointers to the packet, into a queue in DRAM 570. If the packet is to go out one of the serial ports, the FIPP 558 looks up the destination in an ARP table in the SRAM 570. The ARP table is shown in Fig. 15. The FIPP finds the chassis, slot and port. The chassis address does not change unless the destination is an ICL. In the case of the same chassis, the application module finds the MCC address for the IP packet and sends it out. If the packet is to go to some other chassis, the application module asks if any port is an ICL. If it is, then the application module sends the packet out that port . Fig.
• CMTS application card also referred to as a HFC DOCSIS Interface card.
• HFC-on-PCI technology is currently used because of currently available Broadcom technology, however, in the future other types of interface technology may be used.
• Fig. 16 shows two application modules 600, 602 in a chassis.
• the application modules 600, 602 are connected over management busses 604, 606 and the mesh backplane 608.
• the second application module 602 has a route server 610 attached to the PCI bus 612.
• the route server for a chassis can reside on any application module.
• the route server is a Pentium® processor.
• Each chassis in a network of chassises has a route server. Only one route server in the network, however, may be active at any one time.
• the route server broadcasts over the management bus and also over the ICLs that it is a route server.
• one route server is designated to be the primary route server. All other route servers are secondary.
• the router servers in the network send out routing information every 30 seconds.
• the primary route server broadcasts its chassis, slot and port to all other route servers .
• Fig. 17 shows conceptually the updating of the route servers by the "control" or primary route server.
• the primary route server has logical ports equivalent to Ethernet ports .
• the primary router When a packet is sent to a route server in one of the chassises networked together, the primary router receives the packet information as though the primary router was receiving the packet itself.
• the primary router builds a routing table and a forwarding table and broadcasts them out to all application modules and all other chassises on the network.
• the forwarding table is built from information in the routing table.
• the forwarding table contains such information as chassis, slot and port of a packet, QoS data, CMTS information, multicast domain information and next-hop ICL information.
• Fig. 18 shows a chassis controller connected to the management busses in a chassis.
• each chassis has two chassis controllers.
• the chassis controller is not connected to the mesh backplane.
• the chassis controller has network management tasks and provisioning tasks.
• the chassis controller enables an entire chassis cluster to appear to be one managed element.
• the chassis controller has a processor and a memory and a craft interface .
• the processor is a Pentium® processor.
• the craft interface is a network management interface using 10/100 based Ethernet .
• the clusters shown in Figs. 8-10. collectively function as a single router, that is, an IP-Layer-3 switch, with a number of external ports. Physically these external ports would be distributed across multiple chassises, which may be distributed across remote locations.
• the ICLs "virtualize" the physical distribution of the external points.
• the cluster manager 100 runs a general purpose operating system such as Windows NT. It is a set of more specific entities, including: (1) a Master Agent (MA) or network manager; (2) an application module; (3) a Resource Manager (RM) for providing a census of card resources; (4) a User
• UM maintaining a dynamic view of IP end users served by the cluster
• FT Forwarding Table Manager
• FM Filter Manager
• LS Load Sharing Manager
• the System Management Server on the cluster manager also represents the clustered chassis as a single virtual entity.
• the cluster manager can also function as an RAS Server for dial-in modems.
• a RADIUS client on the cluster manager communicates with a RADIUS server provided by the network administrator .
• General purpose functions like Web Server and Mail Server can be run on the cluster manager.
• FTP and Telnet allows the administrator to access the cluster manager remotely.
• the invention allows resource sharing. For example, IP traffic coming into an HFC interface on a secondary chassis potentially has voice as its payload. This IP packet would be switched to a VOIP/PSTN card, which may be on a different chassis in a different location. The IP packet with the voice payload is routed to the appropriate VOIP/PSTN card by the distributed IP switch fabric. The originating chassis tags the packet with the highest "class of service" priority, allowing the route/switch decision to be performed with minimal latency. The cluster manager keeps a centralized resource map of all the resources (including the location of DSOs available) in the clustered system.
• the chassis controller communicates with the application modules in the chassis over the management busses.
• the chassis controller and the application modules each have an agent for communication purposes .
• the chassis controller has a master agent and the application modules have subagents ( Figure 19) .
• the subagents communicate their chassis, application module, and slot information to the master agent in that chassis.
• Fig. 19 shows a plurality of chassises in a network.
• the first chassis brought up is designated to be the primary chassis.
• the primary chassis has an additional master agent, referred to as the "master- master” .
• All the chassises in the network communicate with the master-master agent.
• Each application module in every chassis communicates its IP address ( "10.chassis . slot .port” ) to both the master agent for its chassis and the master-master as shown in Fig. 19.
• the number "10" in the IP address signifies a private network address.
• the master-master agent distributes its chassis ID over the management bus.
• the chassis ID of the primary chassis shifts to one after the primary chassis is designated as the primary chassis.
• link detection protocol LDP
• An LDP message is sent out every link of the current chassis. If the send chassis receives a return signal, the chassis controller identifies that as an ICL.
• the LDP enables each chassis to identify its ICL links .
• the primary chassis broadcasts over its ICL links that it has the master master agent.
• Fig. 21 is a block diagram of the Mesh Communication Chip (MCC) .
• the MCC ASIC provides connectivity to all other cards in the chassis via high speed differential pairs shown as fully duplexed serial links 215.
• Each differential pair operates at greater than one gigabit per second data throughput.
• An F-bus interface 805 connects the MCC 300 to the FIFO bus (F-bus) .
• Twelve transmit FIFOs 810 and 12 receive FIFOs 815 are connected to the F-bus interface 805.
• Each transmit FIFO has a parallel to serial data compressor (12 data compressors in all, 820), and each receive FIFO has a data expander (12 data expanders in all, 825) .
• Twelve serializers 830 serve the data compressors 820 and data expanders 825, one compressor and one expander for each serializer.
• a channel in the MCC is defined as a serial link together with its encoding/decoding logic, transmit queue and receive queue. The serial lines running from the channels connect to the backplane mesh. All the channels can transmit data at the same time .
• a current implementation of the invention uses a Mesh Communication Chip to interconnect up to thirteen F-buses in a full mesh using serial link technology.
• Each MCC has two F-bus interfaces and twelve serial link interfaces .
• the MCC transmits and receives packets on the F-buses in programmable size increments from 64 bytes to entire packets. It contains twelve virtual transmit processors (VTPs) which take packets from the F-bus and send them out the serial links, allowing twelve outgoing packets simultaneously.
• VTPs virtual transmit processors
• the VTPs read the MCC tag on the front of the packet and dynamically bind themselves to the destination slot(s) indicated in the header.
• the packet transmit path is from the PHY/MAC to the processor, then from the processor to the MCC and out the mesh.
• the processor does Layer 3 and Layer 4 look-ups in the FIPP to determine the packet's destination and Quality of Service (QoS) , modifies the header as necessary, and prepends the MCC tag to the packet before sending it to the MCC.
• QoS Quality of Service
• the packet receive path is from the mesh to the MCC and on to the processor, then from the processor to the MAC/Phy and out the channel.
• the processor strips off the MCC tag before sending the packet on to the MAC.
• Fig. 22 shows a packet tag, also called the MCC tag.
• the MCC tag is a 32-bit tag used to route a packet through the backplane mesh. The tag is added to the front of the packet by the slot processor before sending it to the MCC.
• the tag has four fields: a destination mask field, a priority field, a keep field, and a reserved field.
• the destination . mask field is the field holding the mask of slots in the current chassis to which the packet is destined, which may or may not be the final destination in the system.
• the MCC uses the destination mask to determine which transmit queue (s) the packet is destined for.
• For a receive packet the MCC uses the priority and keep fields to determine which packets to discard in an over-committed slot.
• the reserved field is unused in the current embodiment of the invention.
• the MCC has two independent transmit mode selectors, slot-to-channel mapping and virtual transmit mode.
• slot- to-channel mapping the MCC transparently maps SIDs to CIDs and software does not have to keep track of the mapping.
• virtual transmit mode the MCC handles multicast packets semi- transparently.
• the MCC takes a single F-bus stream and directs it to multiple channels.
• the transmit ports in the MCC address virtual transmit processors (VTPs) rather than slots.
• the F-bus interface directs the packet to the selected virtual transmit processor.
• the VTP saves the Destination Mask field from the MCC tag and forwards the packet data (including the MCC tag) to the set of transmit queues indicated in the Destination Mask.
• All subsequent 64-byte "chunks" of the packet are sent by the slot processor using the same port ID, and so are directed to the same VTP.
• the VTP forwards chunks of the packet to the set of transmit queues indicated in the Destination Mask field saved from the MCC tag.
• the VTP clears its destination mask. If the next chunk addressed to that port is not the start of a new packet (i.e., with the SOP bit set) , the VTP does not forward the chunk to any queue.
• the MCC maintains a set of "channel busy" bits which it uses to prevent multiple VTPs from sending packets to the same CID simultaneously.
• This conflict prevention mechanism is not intended to assist the slot processor in management of busy channels, but rather to prevent complete corruption of packets in the event that the slot processor accidentally sends two packets to the same slot simultaneously.
• the VTPs get a new packet, they compare the destination CID mask with the channel busy bits. If any channel is busy, it is removed from the destination mask and an error is recorded for that CID. The VTP then sets all the busy bits for all remaining destination channels and transmits the packet . When the VTP sees EOP on the F-bus for the packet, it clears the channel busy bits for its destination CIDs .
• the F-bus interface performs the I/O functions between the MCC and the remaining portion of the application module.
• the application module adds a 32-bit packet tag (MCC tag) , shown in Figure 22, to each data packet to be routed through the mesh.
• MCC tag 32-bit packet tag
• the data received or transmitted on the F-bus is up to 64 bits wide.
• the F-bus interface adds 4 status bits to the transmit data to make, a 68-bit data segment.
• the F-bus interface drops the 68-bit data segment into the appropriate transmit FIFO as determined from the packet tag.
• the data from a transmit FIFO is transferred to the associated data compressor where the 68-bit data segment is reduced to 10-bit segments.
• the data is then passed to the associated serializer where the data is further reduced to a serial stream..
• the serial stream is sent out the serial link to the backplane .
• Serializer for that channel expands the data to a 10-bit data segment and the associated data expander expands the data to a 68-bit data segment which is passed on to the related FIFO and then from the FIFO to the F-bus interface.
• a Fast IP Processor is provided with 32/64 Mbytes of high-speed synchronous SDRAM, 8 Mbytes of high-speed synchronous SRAM, and boot flash.
• the FIPP has a 32-bit PCI bus and a 64-bit FIFO bus (F-bus) .
• the FIPP transfers packet data to and from all F-bus-connected devices. It provides IP forwarding in both unicast and multicast mode. Routing tables are received over the management bus from the chassis route server.
• the FIPP also provides higher layer functions such as filtering, and CoS/QoS.
• Each line card has a clock subsystem that produces all the clocks necessary for each card. This will lock to the reference clock provided by the System Clock and Management Bus Arbitration Card.
• Each card has hot-plug, power-on reset circuitry, and Sanity Timer functions . All cards have on-board DC-to-DC converters to go from the -48V rail in the backplane to whatever voltages, are required for the application. Some cards (such as the CMTS card) likely will have two separate and isolated supplies to maximize the performance of the analog portions of the card.

Landscapes

• Engineering & Computer Science (AREA)
• Computer Networks & Wireless Communication (AREA)
• Data Exchanges In Wide-Area Networks (AREA)

Priority Applications (5)

Applications Claiming Priority (2)

Publications (2)

Family

ID=23881956

Family Applications (1)

Country Status (8)

Cited By (4)

Families Citing this family (37)

Citations (3)

Family Cites Families (29)

• 1999
  • 1999-12-28 US US09/474,039 patent/US6826195B1/en not_active Expired - Lifetime
• 2000
  • 2000-12-28 JP JP2001548974A patent/JP2004504734A/ja active Pending
  • 2000-12-28 EP EP00989555A patent/EP1243106A2/en not_active Withdrawn
  • 2000-12-28 CN CN00819186A patent/CN1437815A/zh active Pending
  • 2000-12-28 AU AU26051/01A patent/AU2605101A/en not_active Abandoned
  • 2000-12-28 CN CNA2004100422866A patent/CN1538694A/zh active Pending
  • 2000-12-28 BR BR0016863-7A patent/BR0016863A/pt not_active IP Right Cessation
  • 2000-12-28 WO PCT/US2000/035490 patent/WO2001048983A2/en not_active Application Discontinuation
  • 2000-12-28 CA CA002396046A patent/CA2396046A1/en not_active Abandoned

Patent Citations (3)

Also Published As

Similar Documents

Legal Events