Mellanox Technologies, Ltd.

Dror Bohrer

Noam Bloch

Lior Narkis

Hillel Chapman

Michael Kagan

Ariel Shahar

Idan Burstein

Eitan Zahavi

Roee Moyal

Peter Paneah

Diego Crupnicoff

Dror Goldenberg

Richard Leigh Graham

Ariel Shachar

Adi Menachem

Alex Shpiner

Igor Voks

David Mozes

Achiad Shochat

Dotan Finkelstein

Jacob Ruthstein

Tamir Azarzar

Gilad Hammer

Shahar Sarfaty

A network adapter includes a host interface and circuitry. The host interface is configured to connect locally between the network adapter and a host via a bus. The circuitry is configured to receive from one or more source nodes, over a communication network to which the network adapter is coupled, multiple packets destined to the host, and temporarily store the received packets in a queue of the network adapter, to send the stored packets from the queue to the host over the bus, to monitor a performance attribute of the bus, and in response to detecting, based at least on the monitored performance attribute, an imminent overfilling state of the queue, send a congestion notification to at least one of the source nodes from which the received packets originated.

Managing congestion in a network adapter based on host bus performance

A network interface device is connected to a host computer by having a memory controller, and a scatter-gather offload engine linked to the memory controller. The network interface device prepares a descriptor including a plurality of specified memory locations in the host computer, incorporates the descriptor in exactly one upload packet, transmits the upload packet to the scatter-gather offload engine via the uplink, invokes the scatter-gather offload engine to perform memory access operations cooperatively with the memory controller at the specified memory locations of the descriptor, and accepts results of the memory access operations.

Efficient scatter-gather over an uplink

A method includes, in a Network Interface Controller (NIC) that communicates over a network, generating indications pertaining to a performance of the NIC. The indications are classified with respect to severity. At least some of the indications, for which the severity exceeds a predefined severity threshold, are assembled in performance notification packets. The performance notification packets are sent over the network.

High definition, scalable network monitoring and debugging in real-time

A computer peripheral device includes a host interface, which is configured to communicate over a bus with a host processor and with a system memory of the host processor. Processing circuitry in the peripheral device is configured to receive and execute work items submitted to the peripheral device by client processes running on the host processor, and responsively to completing execution of the work items, to write completion reports to the system memory, including first completion reports of a first data size and second completion reports of a second data size, which is smaller than the first data size.

Size reduction of completion notifications

A packet processing device CPU, including multiple processing cores. A NIC, which is coupled to the CPU, includes at least one network port, receives a flow of incoming data packets in a sequential order from a packet communication network, and receive logic, which delivers the incoming data packets in the flow to a designated group of the cores for processing by the cores in the group, while distributing the incoming data packets to the cores in alternation among the cores in the group. In response to the incoming data packets, the cores in the group generate corresponding outgoing data packets and queue the outgoing data packets for transmission by the NIC in the sequential order of the incoming data packets. Transmit logic in the NIC transmits the outgoing data packets to the network in the sequential order via the at least one network port.

Shared processing of a packet flow by multiple cores

Packet flows received in a data network are assigned to respective entries of a database. During an accumulation interval byte counts of the assigned packet flows are accumulated in the respective database entries. The packet flows are classified as elephant flows when differences between the byte counts and a reference byte count exceed a threshold and are reported after expiration of the accumulation interval.

Ability to detect unlimited elephant flows

Network interface apparatus includes a host interface and a network interface, which receives packets in multiple packet flows destined for one or more virtual machines running on a host processor. Packet processing circuitry receives a first instruction from the host processor to offload preprocessing of the data packets in a specified flow in accordance with a specified rule, and initiates preprocessing of the data packets while writing one or more initial data packets from the specified flow to a temporary buffer. Upon subsequently receiving a second instruction to enable the specified rule, the initial data packets are delivered from the temporary buffer, after preprocessing by the packet processing circuitry, directly to a virtual machine to which the specified flow is destined, followed by preprocessing and delivery of subsequent data packets in the specified flow to the virtual machine.

Maintaining packet order in offload of packet processing functions

A method for communication includes receiving at a receiving node over a network from a sending node a succession of data packets belonging to a sequence of transactions, including at least one or more first packets belonging to a first transaction and one or more second packets belonging to a second transaction executed by the sending node after the first transaction, wherein at least one of the second packets is received at the receiving node before at least one of the first packets. At the receiving node, upon receipt of the data packets, data are written from the data packets in the succession to respective locations in a buffer. Execution of the second transaction at the receiving node is delayed until all of the first packets have been received and the first transaction has been executed at the receiving node.

Handling transport layer operations received out of order

A network communication device includes a host interface, which is coupled to communicate with a host processor, having a memory, so as to receive a work request to convey one or more data blocks over a network. The work request specifies a memory region of a given data size, and at least one data integrity field (DIF), having a given field size, is associated with the data blocks. Network interface circuitry is configured to execute an input/output (I/O) data transfer operation responsively to the work request so as to transfer to or from the memory a quantity of data that differs from the data size of the memory region by a multiple of the field size, while adding the at least one DIF to the transferred data or removing the at least one DIF from the transferred data.

Growing community of inventors

Nesher, Israel

Dror Bohrer