Intel Corporation

Noam Elati

Eliel Louzoun

Anjali Singhai Jain

Linden Cornett

Manasi Deval

Ben-Zion Friedman

Patrick Fleming

Stephen Doyle

Gregory J Bowers

Sarig Livne

Parthasarathy Sarangam

Daniel Daly

Ronen Aharon Hyatt

Piotr Uminski

Hemanth Krishnan

Boris Kleiman

Adam Conyers

Venkidesh Krishna Iyer

Nadav Turbovich

Danny Volkind

Michael G Lefevre

Examples described herein relate to a network interface device comprising a packet transmission scheduler. In some examples, the packet transmission scheduler is to: perform packet transmit arbitration among nodes, wherein based on a first node of the nodes having transmission paused by flow control, the perform packet transmit arbitration among nodes comprises retain relative priority of a packet departure time for the first node with respect to a second packet departure time associated with a second node of the nodes during a duration of flow control. In some examples, retaining relative priority of a packet departure time for the first node with respect to a second packet departure time associated with a second node of the nodes during a duration of flow control comprises adjust the packet departure time and the second packet departure time to stay within a time window but not rollover.

Packet transmission scheduling fairness

Examples described herein relate to a network interface device comprising circuitry to: allocate a first number of buffers to store received packets associated with a first descriptor ring; allocate a second number of buffers to store received packets associated with a second descriptor ring; and based on receipt of a packet, copy the received packet into a number of buffers based on whether the received packet is associated with the first descriptor ring or the second descriptor ring. In some examples, the circuitry is to copy the received packet starting at an offset from a start of a starting buffer in a number of buffers, wherein the offset is based on whether the received packet is associated with the first descriptor ring or the second descriptor ring and wherein the number of buffers is based on whether the received packet is associated with the first descriptor ring or the second descriptor ring.

Configurable receive buffer size

Examples described herein relate to a network interface device comprising: a device interface; at least one processor; a direct memory access (DMA) device; and a packet processing circuitry. In some examples, the at least one processor, when operational, is configured to: in connection with a first operation: perform a format translation of a first descriptor from a first format associated with an emulated device to a second format associated with the packet processing circuitry and provide, to the packet processing circuitry, the translated first descriptor. In some examples, the at least one processor, when operational, is configured to: in connection with a second operation: perform a descriptor format translation of a second descriptor from the second format associated with the packet processing circuitry to the first format associated with the emulated software device and provide, to the emulated device, the translated second descriptor.

Virtual device portability

Techniques to use descriptors for packet transmit scheduling include grouping a plurality of data descriptors associated with blocks of data with a single descriptor. The single descriptor to include information related to the plurality of data descriptors. The single descriptor to be used to schedule transmission of the blocks of data from a computing platform.

Techniques to use descriptors for packet transmit scheduling

Examples described herein relate to a device indicating a number of available interrupt messages that is more than physical resources available to store the available interrupt messages and allocating one or more physical resources to provide one or more interrupt messages based on allocation of the one or more interrupt messages to a destination entity. The destination entity can request a maximum permitted allocation of interrupt messages regardless of interrupt message use level. The destination entity can request a maximum permitted allocation of interrupt messages regardless of interrupt message use level and allocate the requested maximum permitted allocation of interrupt messages for use in a configuration region of a device. However, based on unavailability of a physical resource to store a first interrupt message, allocation of the first interrupt message to a destination entity may not be permitted.

Dynamic interrupt provisioning

An apparatus, a method, and a computer program for generating data packets according to a transport protocol from an application buffer comprising a plurality of data streams is provided. The apparatus comprises an input circuit configured to receive metadata comprising at least one of information about data packet types supported by the transport protocol, information about an offset and a length of the supported data packet types, and information about possible stream header start positions, possible payload start positions and possible offsets in the data streams. Further, the apparatus comprises a parsing circuit configured to identify offsets in an application buffer as possible segmentation points based on the metadata, to segment the application buffer at the possible segmentation points into segments for data packets, and to generate data packets according to the transport protocol based on the segments. Furthermore, an apparatus, a method and a computer program for processing the application buffer is provided.

Concept for segmenting an application buffer into data packets

Methods, apparatus, and systems for implementing a semi-flexible Receive Segment Coalescing (RSC) control path. Logic for evaluating packet coalescing open flow criteria and close flow criteria are implemented in hardware on a network device that receives packets from one or more networks. packet coalescing open profiles and packet coalescing close profiles are also stored on the network device, wherein each packet coalescing open profile defines a set of packet coalescing open flow criteria to be applied for that packet coalescing open profile and each packet coalescing close profile defines a set of packet coalescing close flow criteria to be applied for that packet coalescing open profile. packet coalescing open flow and close flow profiles are then assigned to packet coalescing-enabled receive queues on the network device and corresponding open and flow criteria are used to perform packet coalescing-related processing of packets in the receive queues. The scheme supports hardware-based packet coalescing packet processing while providing flexibility in meeting the requirements of different operating systems and future usage models on a single network device.

Semi-flexible packet coalescing control path

Packets received non-contiguously from a network are processed by a network interface controller by coalescing received packet payload into receive buffers on a receive buffer queue and writing descriptors associated with the receive buffers for a same flow consecutively in a receive completion queue. System performance is optimized by reusing a small working set of provisioned receive buffers to minimize the memory footprint of memory allocated to store packet data. The remainder of the provisioned buffers are in an overflow queue and can be assigned to the network interface controller if the small working set of receive buffers is not sufficient to keep up with the received packet rate. The receive buffer queue can be refilled based on either timers or when the number of buffers in the receive buffer queue is below a configurable low watermark.

Apparatus and method for buffer management for receive segment coalescing

An apparatus, a method and a computer program for generating data packets according to a transport protocol from an application buffer comprising a plurality of data streams is provided. The apparatus comprises an input circuit configured to receive metadata comprising at least one of information about data packet types supported by the transport protocol, information about an offset and a length of the supported data packet types, and information about possible stream header start positions, possible payload start positions and possible offsets in the data streams. Further, the apparatus comprises a parsing circuit configured to identify offsets in an application buffer as possible segmentation points based on the metadata, to segment the application buffer at the possible segmentation points into segments for data packets, and to generate data packets according to the transport protocol based on the segments. Furthermore, an apparatus, a method and a computer program for processing the application buffer is provided.

Technologies for performing dynamic configurations to a transmit scheduler of a network device with minimal downtime are disclosed. The transmit scheduler includes a topology of scheduling nodes. The transmit scheduler identifies, from a number of configuration operations to be executed on one or more of the scheduling nodes, one or more first configuration operations to be executed while the scheduling nodes are active, one or more second configuration operations to be executed while the scheduling nodes are inactive, and one or more third configuration operations to be executed via a cache. The first operations are executed as part of a background process. The second operations are executed while the scheduling nodes are inactive. The third operations are executed via the cache.

Growing community of inventors

Zichron Yaakov, Israel

Noam Elati