470 results about "Wire speed" patented technology

A network data classifier statistically classifies received data at wire-speed by examining, in part, the payloads of packets in which such data are disposed and without having a priori knowledge of the classification of the data. The network data classifier includes a feature extractor that extract features from the packets it receives. Such features include, for example, textual or binary patterns within the data or profiling of the network traffic. The network data classifier further includes a statistical classifier that classifies the received data into one or more pre-defined categories using the numerical values representing the features extracted by the feature extractor. The statistical classifier may generate a probability distribution function for each of a multitude of classes for the received data. The data so classified are subsequently be processed by a policy engine. Depending on the policies, different categories may be treated differently.

A Fibre Channel switch is presented that tracks the congestion status of destination ports in an XOFF mask at each input. A mapping is maintained between virtual channels on an ISL and the destination ports to allow changes in the XOFF mask to trigger a primitive to an upstream port that provides virtual channel flow control. The XOFF mask is also used to avoid sending frames to a congested port. Instead, these frames are stored on a single deferred queue and later processed in a manner designed to maintain frame ordering. A routing system is provided that applies multiple routing rules in parallel to perform line speed routing. The preferred switch fabric is cell based, with techniques used to manage path maintenance for variable length frames and to adapt to varying transmission rates in the system. Finally, the switch allows data and microprocessor communication to share the same crossbar network.

An architecture for an integrated circuit apparatus and method that allows significant performance improvements for signature based network applications. In various embodiments the architecture allows high throughput classification of packets into network streams, packet reassembly of such streams, filtering and pre-processing of such streams, pattern matching on header and payload content of such streams, and action execution based upon rule-based policy for multiple network applications, simultaneously at wire speed. The present invention is improved over the prior art designs, in performance, flexibility and pattern database size.

Method, apparatus, and systems for reliably transferring Ethernet packet data over a link layer and facilitating fabric-to-Ethernet and Ethernet-to-fabric gateway operations at matching wire speed and packet data rate. Ethernet header and payload data is extracted from Ethernet frames received at the gateway and encapsulated in fabric packets to be forwarded to a fabric endpoint hosting an entity to which the Ethernet packet is addressed. The fabric packets are divided into flits, which are bundled in groups to form link packets that are transferred over the fabric at the Link layer using a reliable transmission scheme employing implicit ACKnowledgements. At the endpoint, the fabric packet is regenerated, and the Ethernet packet data is de-encapsulated. The Ethernet frames received from and transmitted to an Ethernet network are encoded using 64b / 66b encoding, having an overhead-to-data bit ratio of 1:32. Meanwhile, the link packets have the same ratio, including one overhead bit per flit and a 14-bit CRC plus a 2-bit credit return field or sideband used for credit-based flow control.

A data packet classifier to classify a plurality of N-bit input tuples, said classifier comprising a hash address, a memory and a comparison unit. The hash address generator generate a plurality of M-bit hash addresses from said plurality of N-bit input tuples, wherein M is significantly smaller than N. The memory has a plurality of memory entries and is addressable by said plurality of M-bit hash addresses, each such address corresponding to a plurality of memory entries, each of said plurality of memory entries capable of storing one of said plurality of N-bit tuples and an associated process flow information. The comparison unit determines if an incoming N-bit tuple can be matched with a stored N-bit tuple. The associated process flow information is output if a match is found and wherein a new entry is created in the memory for the incoming N-bit tuple if a match is not found.

A packet forwarding method and apparatus performs multiprotocol routing (for IP and IPX protocols) and switching. Incoming data packets are examined and the flow (i.e., source and destination addresses and source and destination socket numbers) with which they are associated is determined. A flow table contains forwarding information that can be applied to the flow. If an entry is not present in the table for the particular flow, the packet is forwarded to the CPU to be processed. The CPU can then update the table with new forwarding information to be applied to all future packets belonging to the same flow. When the forwarding information is already present in the table, packets can thus be forwarded at wire speed. A dedicated ASIC is preferably employed to contain the table, as well as the engine for examining the packets and forwarding them according to the stored information. Decision-making tasks are thus more efficiently partitioned between the switch and the CPU so as to minimize processing overhead.

A method for processing data packets in a computer system may include receiving a data packet at a configurable logic device (e.g., an FPGA), each packet including header information regarding the data packet, the configurable logic device automatically identifying particular information elements in the header information of the data packet, the configurable logic device automatically executing a hash function programmed on the configurable logic device to calculate a hash value for the data packet based on the particular information elements, and processing the data packet based on the calculated hash value for the data packet. The calculate hash value may be used for various purposes, e.g., routing and / or load balancing of traffic across multiple interfaces. The configurable logic device may be able to execute the hash function at line rate, thus freeing up processor cycles in one or more related processors.

There is provided a hardware device for monitoring and intercepting data packetized data traffic at full line rate. In preferred high bandwidth embodiments, full line rate corresponds to rates that exceed 100 Mbytes / s and in some cases 1000 Mbytes / s. Monitoring and intercepting software, alone, is not able to operate on such volumes of data in real-time. A preferred embodiment comprises: a data delay buffer (208) with multiple delay outputs (216); a search engine logic (210) for implementing a set of basic search tools that operate in real-time on the data traffic; a programmable gate array (206); an interface (212) for passing data quickly to software sub-systems; and control means for implementing software control of the operation of the search tools. The programmable gate array (206) inserts the data packets into the delay buffer (208), extracts them for searching at the delay outputs and formats and schedules the operation of the search engine logic (210). One preferred embodiment uses an IP co-processor as the search engine logic.

Symmetric Connection Detection (SCD) is a method of detecting when a connection has been fully established in a resource-constrained environment, and works in high-speed routers, at line speed. Many network monitoring applications are only interested in connections that become fully established, so other connection attempts, such as port scanning attempts, simply waste resources if not filtered. SCD filters out unsuccessful connection attempts using a simple combination of Bloom filters to track the state of connection establishment for every flow in the network. Unsuccessful flows can be filtered out to a very high degree of accuracy, depending on the size of the bloom filter and traffic rate. The SCD methodology can also easily be adapted to accomplish port scan detection, and to detect or filter other types of invalid TCP traffic.

A Virtual Storage Server is provided for transferring data between a source storage device and one or more destination storage devices. A write command is issued to the one or more destinations for an amount of data. In response, one or more Transfer Ready Responses are returned indicating the amount of data the destinations are prepared to receive. The Virtual Storage Server then sends a read command to the source for an amount of data based on the amounts of data in the Transfer Ready Responses. The data is then transferred from the source storage device through the Virtual Storage Server to the one or more destination storage devices. Because data is transferred only in amounts that the destination is ready to receive, the Virtual Storage Server does not need a large buffer, and can basically send data received at wire speed. This process continues until the amount of data in the write command is transferred to the one or more destination storage devices.

A lookup engine for a network device is provided to lookup an address table. The lookup engine includes a parser for getting address information of an incoming packet. A predetermined number of shift control logic is provided for generating an I.I.D hash index for the incoming packet in response to the address information of the incoming packet. The output of each shift control logic is selected by a selector for looking up an address table, thereby to generate a forwarding information. With the implementation of the shift control logic, the lookup engine can construct each flow entry and classify the incoming packets belonging to this flow in wire-speed.

An advanced processor comprises a plurality of multithreaded processor cores each having a data cache and instruction cache. A data switch interconnect is coupled to each of the processor cores and configured to pass information among the processor cores. A messaging network is coupled to each of the processor cores and a plurality of communication ports. In one aspect of an embodiment of the invention, the data switch interconnect is coupled to each of the processor cores by its respective data cache, and the messaging network is coupled to each of the processor cores by its respective message station. Advantages of the invention include the ability to provide high bandwidth communications between computer systems and memory in an efficient and cost-effective manner.

A system including a storage processing device with an input / output module. The input / output module has port processors to receive and transmit network traffic. The input / output module also has a switch connecting the port processors. Each port processor categorizes the network traffic as fast path network traffic or control path network traffic. The switch routes fast path network traffic from an ingress port processor to a specified egress port processor. The storage processing device also includes a control module to process the control path network traffic received from the ingress port processor. The control module routes processed control path network traffic to the switch for routing to a defined egress port processor. The control module is connected to the input / output module. The input / output module and the control module are configured to interactively support data virtualization, data migration, data journaling, and snapshotting. The distributed control and fast path processors achieve scaling of storage network software. The storage processors provide line-speed processing of storage data using a rich set of storage-optimized hardware acceleration engines. The multi-protocol switching fabric provides a low-latency, protocol-neutral interconnect that integrally links all components with any-to-any non-blocking throughput.

A network transport layer accelerator accelerates processing of packets so that packets can be forwarded at wire-speed. To accelerate processing of packets, the accelerator performs pre-processing on a network transport layer header encapsulated in a packet for a connection and performs in-line network transport layer checksum insertion prior to transmitting a packet. A timer unit in the accelerator schedules processing of the received packets. The accelerator also includes a free pool allocator which manages buffers for storing the received packets and a packet order unit which synchronizes processing of received packets for a same connection.

A sampling based technique for eliminating duplicate data (de-duplication) stored on storage resources, is provided. According to the invention, when a new data set, e.g., a backup data stream, is received by a server, e.g., a storage system or virtual tape library (VTL) system implementing the invention, one or more anchors are identified within the new data set. The anchors are identified using a novel anchor detection circuitry in accordance with an illustrative embodiment of the present invention. Upon receipt of the new data set by, for example, a network adapter of a VTL system, the data set is transferred using direct memory access (DMA) operations to a memory associated with an anchor detection hardware card that is operatively interconnected with the storage system. The anchor detection hardware card may be implemented as, for example, a FPGA is to quickly identify anchors within the data set. As the anchor detection process is performed using a hardware assist, the load on a main processor of the system is reduced, thereby enabling line speed de-duplication.

A network transport layer accelerator accelerates processing of packets so that packets can be forwarded at wire-speed. To accelerate processing of packets, the accelerator performs pre-processing on a network transport layer header encapsulated in a packet for a connection and performs in-line network transport layer checksum insertion prior to transmitting a packet. A timer unit in the accelerator schedules processing of the received packets. The accelerator also includes a free pool allocator which manages buffers for storing the received packets and a packet order unit which synchronizes processing of received packets for a same connection.

A method and apparatus for classifying packets, e.g., at wire speed are disclosed. The method receives a packet and processes the packet through a hardware-based packet classifier having at least one evolving rule. The method then processes the packet through a software-based packet classifier if the hardware-based packet classifier is unable to classify the packet. In one embodiment, the at least one evolving rule is continuously modified in accordance with learned traffic characteristics of the received packets

An interface switch which presents itself as switch to an enterprise fabric formed of the devices from the same manufacturer as the interface switch and that of a host or node to an enterprise fabric from a different manufacturer. This allows each enterprise fabric to remain in a higher performance operating mode. The multiplexing of multiple streams of traffic between the N_ports on the first enterprise fabric and the second enterprise fabric is accomplished by N_port Virtualization. The interface switch can be connected to multiple enterprise fabrics. All control traffic address mappings between virtual and physical addresses may be mediated and translated by the CPU of the interface switch and address mappings for data traffic performed at wire speed. Since the interface switch may preferably be a single conduit between the enterprise fabrics, it is also a good point to enforce perimeter defenses against attacks.

A synchronous network traffic processor that synchronously processes, analyzes and generates data for high-speed network protocols, on a wire-speed, word-by-word basis. The synchronous network processor is protocol independent and may be programmed to convert protocols on the fly. An embodiment of the synchronous network processor described has a low gate count and can be easily implemented using programmable logic. An appropriately programmed synchronous network traffic processor may replace modules traditionally implemented with hard-wired logic or ASIC.

A system and method for reducing the overhead associated with direct data placement is provided. Processing time overhead is reduced by implementing packet-processing logic in hardware. Storage space overhead is reduced by combining results of hardware-based packet-processing logic with ULP software support; parameters relevant to direct data placement are extracted during packet-processing and provided to a control structure instantiation. Subsequently, payload data received at a network adapter is directly placed in memory in accordance with parameters previously stored in a control structure. Additionally, packet-processing in hardware reduces interrupt overhead by issuing system interrupts in conjunction with packet boundaries. In this manner, wire-speed direct data placement is approached, zero copy is achieved, and per byte overhead is reduced with respect to the amount of data transferred over an individual network connection. Movement of ULP data between application-layer program memories is thereby accelerated without a fully offloaded TCP protocol stack implementation.

An in-line hardware message filter device inspects incoming securities transactions. The invention is implemented as an integrated circuit (IC) device which contains computer code in the form of on-chip hardware instructions. Data messages comprising orders enter the device in exchange-specific formats. Messages that satisfy pre-determined risk assessment filters are allowed to pass through the device to the appropriate securities exchange for execution. The system functions as a passive device for all legitimate network traffic passing directly or indirectly between a customer's computer and a securities exchange's order-acceptance computer. Advantageously, the invention allows the broker-dealer to check and pass messages or orders as they come through the system without having to store the full message before making a risk assessment decision. The hardware-only nature of the invention serves to maximize the speed of order validation and to perform pre-trade checks in a cut-through or store-and-forward mode.

A technique and system for manipulating, converting or adapting datagram headers as required during traverse from one interface of a networking device to another, by novel clocked micro-sequencing and selection amongst input and output FIFO data streams, through dividing input serial data streams into small groups of FIFO input data streams and feeding the groups parallely into a matrix of a multilane highway of header unit input data, constant data pattern and computational unit busses controlled by such micro-sequencing so as to enable such processing of packet datagram headers and the like at very high wire speed, but using low clock speeds, and in a scalable manner.

A system including a storage processing device with an input / output module. The input / output module has port processors to receive and transmit network traffic. The input / output module also has a switch connecting the port processors. Each port processor categorizes the network traffic as fast path network traffic or control path network traffic. The switch routes fast path network traffic from an ingress port processor to a specified egress port processor. The storage processing device also includes a control module to process the control path network traffic received from the ingress port processor. The control module routes processed control path network traffic to the switch for routing to a defined egress port processor. The control module is connected to the input / output module. The input / output module and the control module are configured to interactively support data virtualization, data migration, data journaling, and snapshotting. The distributed control and fast path processors achieve scaling of storage network software. The storage processors provide line-speed processing of storage data using a rich set of storage-optimized hardware acceleration engines. The multi-protocol switching fabric provides a low-latency, protocol-neutral interconnect that integrally links all components with any-to-any non-blocking throughput.

A MIG welder and method of controlling a MIG welder which includes a wire speed selector that is used to generate a control signal which controls both the wire feed speed of a consumable electrode and the output current level of the power supply.

We formulate the network-wide traffic measurement / analysis problem as a series of set-cardinality-determination (SCD) problems. By leveraging recent advances in probabilistic distinct sample counting techniques, the set-cardinalities, and thus, the network-wide traffic measurements of interest can be computed in a distributed manner via the exchange of extremely light-weight traffic digests (TD's) amongst the network nodes, i.e. the routers. A TD for N packets only requires O(loglog N) bits of memory storage. The computation of such O(loglog N)-sized TD is also amenable for efficient hardware implementation at wire-speed of 10 Gbps and beyond. Given the small size of the TD's, it is possible to distribute nodal TD's to all routers within a domain by piggybacking them as opaque data objects inside existing control messages, such as OSPF link-state packets (LSPs) or I-BGP control messages. Once the required TD's are received, a router can estimate the traffic measurements of interest for each of its local link by solving a series of set-cardinality-determination problems. The traffic measurements of interest are typically in form of per-link, per-traffic-aggregate packet counts (or flow counts) where an aggregate is defined by the group of packets sharing the same originating and / or destination nodes (or links) and / or some intermediate nodes (or links). The local measurement results are then distributed within the domain so that each router can construct a network-wide view of routes / flow patterns of different traffic commodities where a commodity is defined as a group of packets sharing the same origination and / or termination nodes or links. After the initial network-wide traffic measurements are received, each router can further reduce the associated measurement / estimation errors by locally conducting a minimum square error (MSE) optimization based on network-wide commodity-flow conservation constraints.

An automatic wire feed adjuster, including a feeding mechanism including a pair of rollers that feeds a wire therebetween, a tension controller that adjusts a tension between the pair of rollers, a wire speed sensor that measures a fed speed of the wire after exiting the feeding mechanism, and a control circuit that compares a driven speed of the wire with the fed speed of the wire, and that decides whether to instruct the tension controller to adjust the tension between the pair of rollers.

A data packet classifier to classify a plurality of N-bit input tuples, said classifier comprising a hash address, a memory and a comparison unit. The hash address generator generate a plurality of M-bit hash addresses from said plurality of N-bit input tuples, wherein M is significantly smaller than N. The memory has a plurality of memory entries and is addressable by said plurality of M-bit hash addresses, each such address corresponding to a plurality of memory entries, each of said plurality of memory entries capable of storing one of said plurality of N-bit tuples and an associated process flow information. The comparison unit determines if an incoming N-bit tuple can be matched with a stored N-bit tuple. The associated process flow information is output if a match is found and wherein a new entry is created in the memory for the incoming N-bit tuple if a match is not found.

The invention is a system and method to uniquely associate remote wireless Access Points using a switch engine. This is necessary in a multi-point wireless network where a central wireless Access Point must be able to receive packets from remote Access Points and then retransmit them, with a modified identifier, back to the wireless port from which they were received. By using available switch engine hardware this invention takes advantage of lower cost, higher performance and increased features in commodity parts. The invention resolves differences in common Ethernet switch engines that make them unsuitable for direct interface to wireless networks such as that defined by IEEE Standard 802.11 by using an aggregated set of physical ports on the switch engine. The method allows the switch engine to operate in its normal manner while satisfying the requirements for switching data packets between the Access Points in a multi-point configuration.