Abstract: Certain aspects of a method and system for transparent transmission control protocol (TCP) offload are disclosed. Aspects of a method may include collecting TCP segments in a network interface card (NIC) processor without transferring state information to a host system. The collected TCP segments may be buffered in a coalescer. The coalescer may verify that the network flow associated with the collected TCP segments has an entry in a flow lookup table (FLT). When the FLT is full, the coalescer may close a current entry and assign the network flow to the available entry. The coalescer may also update information in the FLT. When an event occurs that terminates the collection of TCP segments, the coalescer may generate a single aggregated TCP segment based on the collected TCP segments. The aggregated TCP segment and state information may be communicated to the host system for processing.

Abstract: A system and method for bandwidth management by controlling the bit rate of a signal stream in real time according to available link bandwidth. Applications include multiple-channel video data streams over a limited-bandwidth link such as a Digital Subscriber Line. A video signal is transrated at the head end to multiple streams having different bit rates, by a multirating device which sends the multiple streams over a network, along with metadata containing information about the data structure and parameters of the streams. At the network access edge, a demultirating device uses the metadata to select the stream with the highest video quality whose bit rate does not exceed the available bandwidth of the end-user's access link. This scheme provides multiple unicast signals to different end-users in place of a single multicast signal, supports multiple high-definition channels over a limited bandwidth link, and is compatible with standard encryption methods.

Abstract: Certain aspects of a method and system for transparent transmission control protocol (TCP) offload with best effort direct placement of incoming traffic are disclosed. Aspects of a method may include collecting TCP segments in a network interface card (NIC) processor without transferring state information to a host processor every time a TCP segment is received. When an event occurs that terminates the collection of TCP segments, the NIC processor may generate a new aggregated TCP segment based on the collected TCP segments. If a placement sequence number corresponding to the generated new TCP segment for the particular network flow is received before the TCP segment is received, the generated new TCP segment may be transferred directly from the memory to the user buffer instead of transferring the data to a kernel buffer, which would require further copy by the host stack from kernel buffer to user buffer.

Abstract: A method for communication includes inputting from a host processor to a network interface device a sequence of work requests indicative of operations to be carried out by the network interface device with respect to a plurality of the connections. The device looks ahead through the sequence in order to identify at least first and second operations that are to be carried out with respect to one of the connections in response to first and second work requests, respectively, wherein the second work request does not immediately follow the first work request in the sequence. The device loads the context data for the one of the connections from a host memory into a context cache, and performs at least the first and second operations sequentially while the context data are held in the cache.

Abstract: Certain aspects of a method and system for transparent transmission control protocol (TCP) offload are disclosed. Aspects of a method may include collecting TCP segments in a network interface card (NIC) processor without transferring state information to a host system. The collected TCP segments may be buffered in a coalescer. The coalescer may verify that the network flow associated with the collected TCP segments has an entry in a flow lookup table (FLT). When the FLT is full, the coalescer may close a current entry and assign the network flow to the available entry. The coalescer may also update information in the FLT. When an event occurs that terminates the collection of TCP segments, the coalescer may generate a single aggregated TCP segment based on the collected TCP segments. The aggregated TCP segment and state information may be communicated to the host system for processing.

Abstract: Certain aspects of a method and system for transparent TCP offload with a user space library are disclosed. Aspects of a method may include collecting TCP segments in a network interface card (NIC) without transferring state information to a host system. When an event occurs that terminates the collection of TCP segments, a single aggregated TCP segment based on the collected TCP segments may be generated. The aggregated TCP segment may be posted directly to a user space library, bypassing kernel processing of the aggregated TCP segment.

Abstract: Methods and systems for latency optimized ATS usage are disclosed. Aspects of one method may include communicating a memory access request using an untranslated address and also an address translation request using the same untranslated address, where the translation request may be sent without waiting for a result of the memory access request. The memory access request and the address translation request may be made in either order. A translation agent may be used to translate the untranslated address, and the translated address may be communicated to the device that made the memory access request. The translated address may also be used to make the memory access. Accordingly, by communicating the translated address without having to wait for completion of the memory access, or vice versa, the requesting device may reduce latency for memory accesses when using untranslated addresses.

Abstract: Certain aspects of a method and system for transparent TCP offload with a user space library are disclosed. Aspects of a method may include collecting TCP segments in a network interface card (NIC) without transferring state information to a host system. When an event occurs that terminates the collection of TCP segments, a single aggregated TCP segment based on the collected TCP segments may be generated. The aggregated TCP segment may be posted directly to a user space library, bypassing kernel processing of the aggregated TCP segment.

Abstract: Methods and systems for a fast drop recovery for a TCP connection are disclosed. Aspects of one method may include a receiving device on a network receiving an out-of-order data. The receiving device may then signal to a transmitting device on the network, which sent the out-of-order packet, to enter a congestion alleviation mode without waiting for a delay period. The network packet transfer may be via TCP protocol, for example. The delay period may comprise a retransmission time-out period if the receiving device does not save isles. If the receiving device does save one or more isles, the delay period may be a period associated with delayed ACK. The signal may comprise a TCP option and/or an available TCP flag. The signal may also comprise, for example, three duplicate ACKs. Other similar signals may be used for networks that use other protocols than TCP.

Abstract: Certain aspects of a method and system for transparent transmission control protocol (TCP) offload with transmit and receive coupling are disclosed. Aspects of a method may include collecting at least one received TCP segment for a determined network flow via a network interface card (NIC) processor. The state information for the received TCP segment and state information for transmitted TCP segments for the determined network flow may be stored at the NIC without transferring state information for the received TCP segment and the state information for the transmitted TCP segments to a host system communicatively coupled to the NIC. A new TCP segment comprising the collected TCP segments may be generated after a termination event occurs. The generated new TCP segment, new state information for the generated new TCP segment, and the state information for the transmitted TCP segments may be communicated to the host system for TCP offload.

Abstract: Certain aspects of a method and system for host memory alignment may include splitting a received read and/or write I/O request at a first of a plurality of memory cache line boundaries to generate a first portion of the received I/O request. A second portion of the received read and/or write I/O request may be split into a plurality of segments so that each of the plurality of segments is aligned with one or more of the plurality of memory cache line boundaries. A cost of memory bandwidth for accessing host memory may be minimized based on the splitting of the second portion of the received read and/or write I/O request.

Abstract: Certain aspects of a method and system for processing status blocks based on interrupt mapping may be disclosed. Exemplary aspects of the method may include determining whether a particular status block has been processed by at least one CPU based on comparing a value of a first register with a value of a second register, wherein the first register may comprise a running index value of at least one client segment within the particular status block and the second register may comprise a current running index value of at least one client segment. An interrupt may be generated, if the value of the first register is not equal to the value of the second register. The particular status block may be processed by at least one CPU based on the generated interrupt.

Abstract: Certain aspects of a method and system for host software concurrent processing of a network connection using multiple central processing units (CPUs) may be disclosed. Exemplary aspects of the method may include a network system comprising a plurality of processors and a NIC. After completion of one or more received I/O requests, a plurality of completions may be distributed among two or more of the plurality of CPUs. The plurality of CPUs may be enabled to handle processing for one or more network connections and each network connection may be associated with a plurality of completion queues. Each CPU may be associated with at least one global event queue.

Abstract: Certain aspects of a method and system for coalescing task completions may include coalescing a plurality of completions per connection associated with an I/O request. An event may be communicated to a global event queue, and an entry may be posted to the global event queue for a particular connection based on the coalesced plurality of completions. At least one central processing unit (CPU) may be interrupted based on the coalesced plurality of completions.

Abstract: Methods and systems for direct device access are disclosed. Aspects of one method may include a plurality of GOSs directly accessing a first network interface device, where the first network interface device may provide access to a network. One or more of the GOSs may be migrated to directly access a second network interface device, based on state information for each of the GOSs, where the state information may be maintained by the host. The GOSs may communicate data to a device coupled to the network by direct accessing the first and/or second network interface device. Similarly, the first and/or second network interface device may communicate data received from a device coupled to the network to one or more of the plurality of GOSs via direct access of the first and/or second network interface device.

Abstract: Certain aspects of a method and system for protocol offload in paravirtualized systems may be disclosed. Exemplary aspects of the method may include preposting of application buffers to a front-end driver rather than to a NIC in a paravirtualized system. The NIC may be enabled to place the received offloaded data packets into a received data buffer corresponding to a particular GOS. A back-end driver may be enabled to acknowledge the placed offloaded data packets. The back-end driver may be enabled to forward the received data buffer corresponding to the particular GOS to the front-end driver. The front-end driver may be enabled to copy offloaded data packets from a received data buffer corresponding to a particular guest operating system (GOS) to the preposted application buffers.

Abstract: Certain aspects of a method and system for delayed completion coalescing may be disclosed. Exemplary aspects of the method may include accumulating a plurality of bytes of incoming TCP segments in a host memory until a number of the plurality of bytes of incoming TCP segments reaches a threshold value. A completion queue entry (CQE) may be generated to a driver when the plurality of bytes of incoming TCP segments reaches the threshold value and the plurality of bytes of incoming TCP segments may be copied to a user application. The method may also include delaying in a driver, an update of a TCP receive window size until one of the incoming TCP segments corresponding to a particular sequence number is copied to the user application. The CQE may also be generated to the driver when at least one of the incoming TCP segments is received with a TCP PUSH bit SET and the TCP receive window size is greater than a particular window size value.

Abstract: Certain aspects of a method and system for user space TCP offload are disclosed. Aspects of a method may include offloading transmission control protocol (TCP) processing of received data to an on-chip processor. The received data may be posted directly to hardware, bypassing kernel processing of the received data, utilizing a user space library. If the received data is not cached in memory, an application buffer comprising the received data may be registered by the user space library. The application buffer may be pinned and posted to the hardware.

Abstract: Certain aspects of a method and system for transparent TCP offload with a user space library are disclosed. Aspects of a method may include collecting TCP segments in a network interface card (NIC) without transferring state information to a host system. When an event occurs that terminates the collection of TCP segments, a single aggregated TCP segment based on the collected TCP segments may be generated. The aggregated TCP segment may be posted directly to a user space library, bypassing kernel processing of the aggregated TCP segment.

Abstract: Methods and systems for a plurality of physical layers for network connection may include coupling a MAC to one of a plurality of PHYs. The coupling to a specific PHY may be based on auto-detection of network activity, or network devices, via the PHYs. Also, one of the PHYs may be coupled to the MAC as a power-up default. The PHYs may be coupled to a same network, by, for example, cables. A first cable to a first PHY may couple it to a first network switch and a second cable to a second PHY may couple it to a second network switch. The first network switch may be rated to handle, for example, a greater data rate than the second network switch. The first cable may not be able to be used as a cable for the second PHY, and vice versa.