Mellanox Technologies, Ltd.

Yamin Friedman

Idan Burstein

Roee Moyal

Yuval Shpigelman

Ariel Shahar

Gal Yefet

Idan Borshteen

Gil Levy

Diego Crupnicoff

Daniel Marcovitch

Hillel Chapman

Ron Yuval Efraim

Michael Kagan

Liran Liss

Dror Goldenberg

Matty Kadosh

Aviad Shaul Yehezkel

Omer Shabtai

Rabia Loulou

Tzah Oved

Alexander Eli Rosenbaum

Rotem Levinson

Mark B Rosenbluth

Noam Bloch

Ilan Pardo

Avi Urman

Eitan Hirshberg

Ran Avraham Koren

Michael Cotsford

Gil Kremer

Charlie Mbariky

Daniil Provotorov

Natan Oppenheimer

Technologies for payload direct memory storing (PDMS) for out-of-order delivery of packets in remote direct memory access (RDMA) are described. A responder device includes an RDMA transport layer that can receive packets out of order and allow direct data placement of packet data in order. The responder device receives a first packet with a first packet number and first location information. The responder device stores first packet data to a first location according to the first location information. The responder device also receives a second packet and stores second packet data to a second location according to the second location information. A second packet number indicates that the first packet is received out of order. The first and second packet data are stored in order. The responder device can provide an indication that a message has arrived in response to determining that all packets of the message have arrived.

Payload direct memory storing (PDMS) for remote direct memory access (RDMA)

Technologies for optimizing the spreading of traffic across multiple local output ports while considering both local load and end-to-end (E2E) load are described. One device has multiple outgoing ports and a network adapter that determines, for a first flow of packets, a first end-to-end (E2E) congestion rate of at least some of the outgoing ports. The network adapter determines a port state of at least some of the outgoing ports. The network adapter receives a first packet associated with the first flow of packets. The network adapter determines, using a first desired rate for the first flow, the first E2E congestion rates, and the port states, i) a first time at which the first packet is to be transmitted and ii) a first outgoing port on which the first packet is to be transmitted. The first packet is sent on the first outgoing port at the first time.

Combined congestion control and load balancing

Technologies for spreading packets of transport flows across multiple network paths are described. A network controller includes a transport layer and a network layer. The transport layer includes a flow scheduler to schedule a transport flow from one of a plurality of transport flows. The network layer includes multipath logic to receive packets from the transport flow and select which path of a plurality of paths to a destination to use for the packets based on path congestion weights corresponding to the plurality of paths.

Routing transport flows in a transport layer over multiple paths in a network layer

An apparatus for cache management includes an interface and a processor. The interface is for communicating with a cache memory configured to store data items. The cache controller is configured to obtain a classification of the data items into a plurality of groups, to obtain respective target capacities for at least some of the groups, each target capacity defining a respective required size of a portion of the cache memory that is permitted to be occupied by the data items belonging to the group, and to cache new data items in the cache memory, or evict cached data items from the cache memory, in accordance with a policy that complies with the target capacities specified for the groups.

Cache management using groups partitioning

Technologies for spreading a burst of data across multiple network paths in remote direct memory access (RDMA) over converged Ethernet (RoCE) and InfiniBand are described. A network interface controller sends a first burst of a transport flow directed to a second node over a first network path. The network interface controller determines that a second burst is to be sent over a different network path, and identifies a second network path using a multipath context. The multipath context stores a first weight value or a first state associated with the first network path and a second weight value or a second state associated with the second network path. The network interface controller sends the second burst of data to the second node via the second network path.

Remote direct memory access (RDMA) multipath

A method and system are provided for limiting unnecessary data traffic on the data busses connecting the various levels of system memory. Some embodiments may include processing an invalidation command associated with a system or network operation requiring temporary storage of data in a local memory area. The invalidation command may comprise a memory location indicator capable of identifying the physical addresses of the associated data in the local memory area. Some embodiments may preclude the data associated with the system or network operation from being written to a main memory by invalidating the memory locations holding the temporary data once the system or network operation has finished utilizing the local memory area.

Methods and systems for limiting data traffic while processing computer system operations

A system which facilitates efficient operation of plural agents, the system comprising a device which services the plural agents; and functionality which resides on the device and which provides a given quality of service, defined in terms of at least one resource, to at least one subset of agents from among the plural agents.

Providing network quality of service for multiple users

Apparatus for data communication includes a network interface for connection to a packet data network and a host interface for connection to a host computer, which includes a central processing unit (CPU) and a host memory. Packet processing circuitry receives, via the host interface, from a kernel running on the CPU, associations between multiple remote direct memory access (RDMA) sessions and multiple different User Datagram Protocol (UDP) 5-tuple, which are assigned respectively to the RDMA sessions, and receives from an application running on the CPU a request to send an RDMA message, using a selected group of one or more of the RDMA sessions, to a peer application over the packet data network, and in response to the request, transmits, via the network interface, one or more data packets using a UDP 5-tuple that is assigned to one of the RDMA sessions in the selected group.

Session-based remote direct memory access

In one embodiment, a communication apparatus, including a network interface configured to receive over a network a sequence of data packets of a network flow having a defined packet order, wherein the network interface is configured to receive an out-of-order data packet instead of multiple missing data packets according to the defined packet order, a timer, and packet processing circuitry configured to activate the timer responsively to receiving the out-of-order data packet, and set the time period over which the timer is activated responsively to a quantity of the multiple missing data packets.

Out-of-order packet processing

A method and system are provided for limiting unnecessary data traffic on the data communication connections connecting various system components, including the various levels of system memory. Some embodiments may include processing a buffer allotment request and/or a buffer release command in coordination with a system or network operation requiring temporary storage of data in a memory buffer. The buffer allotment request may be capable of indicating the amount of storage space required on the memory buffer to execute the system or network operation. The system may be capable of precluding the system or network operation from executing until there is sufficient space in the memory buffer to complete the operation without evicting operational data from the memory buffer. In some embodiments, the buffer release command may signal completion of the system or network operation and release of the utilized memory buffer space for other operations.

Methods and systems for managing memory buffer usage while processing computer system operations

A network adapter includes a port and one or more circuits. The port communicates packets over a network in which switches forward packets in accordance with tuples of the packets. The one or more circuits are to hold a user-programmable scheme specifying assignments of the packets of a given flow destined to a peer node to sub-flows having respective different tuples, assign first packets of the given flow to one or more of the sub-flows in accordance with the user-programmable scheme, by setting respective tuples of the first packets, transmit the first packets to the peer node via the port, monitor notifications received from the network, the notifications being indicative of respective states of the sub-flows, based on the notifications and on the user-programmable scheme determine an assignment of second packets of the given flow to the sub-flows, and transmit the second packets to the peer node via the port.

Flexible per-flow multipath managed by sender-side network adapter

An apparatus includes a memory and control circuitry. The control circuitry is configured to receive packets, which are en-route to undergo transport-layer processing in a network device in accordance with a transport protocol that requires arrival of the packets in a sequential order, to detect that one or more of the packets deviate from the sequential order, to buffer the one or more deviating packets in the memory, and, using the memory, to reorder the packets and provide the packets in the sequential order to the network device.

Handling of out-of-order transport-layer packets using reorder buffer

In one embodiment, a communication apparatus, including a network interface configured to receive over a network a sequence of data packets of a network flow having a defined packet order, wherein the network interface is configured to receive an out-of-order data packet instead of multiple missing data packets according to the defined packet order, a timer, and packet processing circuitry configured to activate the timer responsively to receiving the out-of-order data packet, and set the time period over which the tinier is activated responsively to a quantity of the multiple missing data packets.

Technologies for spreading a single transport flow across multiple network paths in remote direct memory access (RDMA) over converged Ethernet (RoCE) and InfiniBand are described. A network interface controller receives a first packet and a second packet of a transport flow directed to a second node. The network interface controller assigns a first network routing identifier to the first packet and a second network routing identifier to the second packet, the first network routing identifier corresponding to a first network path between the first and second nodes, the second network routing identifier corresponding to a second network path between the first node and the second node. The network interface controller schedules a first packet of the transport flow to be sent via the first network path and a second packet of the transport flow to be sent via the second network path.

Growing community of inventors

Nesher, Israel

Yamin Friedman