Intel Corporation

Other

Dinesh Kumar

Patrick L Connor

Andrew J Herdrich

Alexander W Min

Kapil Sood

Daniel J Dahle

Jeffrey B Shaw

Ren Wang

Christian Maciocco

Scott P Dubal

Sanjeev Jain

Edwin Verplanke

Iosif Gasparakis

Nrupal R Jani

James Robert Hearn

Mohan J Kumar

David J Harriman

Tsung-Yuan Charles Tai

Ravishankar Iyer

Linden Cornett

Mrittika Ganguli

Yadong Li

Nimrod Diamant

Brian J Skerry

John R Fastabend

Kiran A Patil

Neerav Parikh

Ira Weiny

Sravanthi Tangeda

Hieu Trung Tran

Ranganath Sunku

Irene Liew

Kavindya Deegala

Robert Valiquette

Technologies for adaptive platform resource management include a compute node to manage a processor core mapping scheme between virtual machines (VMs) and a virtual switch of the compute node via a set of virtual ports. The virtual switch is also coupled to a network interface controller (NIC) of the compute node via another set of virtual ports. Each of the VMs is configured to either provide ingress or egress to the NIC or provide ingress/egress across the VMs, via the virtual ports. The virtual ports for providing ingress or egress to the NIC are pinned to a same processor core of a processor of the compute node, and each of the virtual ports for providing ingress and/or egress across the VMs are pinned to a respective processor core of the processor such that data is transferred across VMs by coupled virtual ports that are pinned to the same processor core.

Technologies for adaptive platform resource assignment

Technologies for enhanced network discovery and configuration include a network with a fabric manager and multiple network devices. A network device requests platform information from a management controller and receives the platform information via a sideband interface. The network device broadcasts a discovery message indicative of the platform information on a link layer network. The fabric manager discovers the network topology with an enhanced link layer discovery protocol and creates a vPOD in the network. The vPOD includes an application network with multiple racks. The fabric manager creates a tagged network domain for the vPOD. The fabric manager sends an out-of-band configuration command to the network device with a tag associated with the vPOD. After receiving the out-of-band configuration command, the network device receives a packet, compares domain metadata of the packet to the tag received from the fabric manager, and routes the packet. Other embodiments are described and claimed.

Technologies for network discovery

Devices and techniques for out-of-band platform tuning and configuration are described herein. A device can include a telemetry interface to a telemetry collection system and a network interface to network adapter hardware. The device can receive platform telemetry metrics from the telemetry collection system, and network adapter silicon hardware statistics over the network interface, to gather collected statistics. The device can apply a heuristic algorithm using the collected statistics to determine processing core workloads generated by operation of a plurality of software systems communicatively coupled to the device. The device can provide a reconfiguration message to instruct at least one software system to switch operations to a different processing core, responsive to detecting an overload state on at least one processing core, based on the processing core workloads. Other embodiments are also described.

Out-of-band platform tuning and configuration

Technologies for offloading data object replication and service function chain management include a switch communicatively coupled to one or more computing nodes capable of executing virtual machines and storing data objects. The switch is configured to determine metadata of a service function chain, transmit a network packet to a service function of the service function chain being executed by one or more of the computing nodes for processing the network packet. The switch is further configured to receive feedback from service function, update the metadata based on the feedback, and transmit the network packet to a next service function of the service function chain. Additionally or alternatively, the switch is configured to identify a plurality of computing nodes (i.e., storage nodes) at which to store a received data object, replicate the data object based on the number of storage nodes, and transmit each of the received data object and replicated data object(s) to different corresponding storage nodes. Other embodiments are described and claimed.

Technologies for offloading data object replication and service function chain management

Devices and techniques for hardware accelerated packet processing are described herein. A device can communicate with one or more hardware switches. The device can detect characteristics of a plurality of packet streams. The device may distribute the plurality of packet streams between the one or more hardware switches and software data plane components based on the detected characteristics of the plurality of packet streams, such that at least one packet stream is designated to be processed by the one or more hardware switches. Other embodiments are also described.

Apparatus and method for hardware-accelerated packet processing

In embodiments, apparatuses, methods and storage media (transitory and non-transitory) are described that are associated with end-to-end datacenter performance control. In various embodiments, an apparatus for computing may receive a datacenter performance target, determine an end-to-end datacenter performance level based at least in part on quality of service data collected from a plurality of nodes, and send a mitigation command based at least in part on a result of a comparison of the end-to-end datacenter performance level determined to the datacenter performance target. In various embodiments, the apparatus for computing may include one or more processors, a memory, a datacenter performance monitor to receive a datacenter performance target corresponding to a service level agreement, and a mitigation module to send a mitigation command based at least in part on a result of a comparison of an end-to-end datacenter performance level to a datacenter performance target.

End-to-end datacenter performance control

Technologies for identifying service functions that may be performed in parallel in a service function chain include a computing device for running one or more virtual machines for each of a plurality of service functions based on a preferred service function chain being selected. To identify which service functions may be performed in parallel, the computing device may determine which service functions are not required to be performed on a critical path of the service function chain and/or which service functions are not required to be performed in real-time. Additionally, selecting the preferred service function chain may be based on selection criteria.

Parallel processing of service functions in service function chains

A plurality of packets associated with a plurality of protocols are received, wherein the plurality of packets are to be processed by a plurality of processors. Packets associated with a first protocol are sent to be processed by at least one of the plurality of processors before sending packets associated with a second protocol to be processed, in response to determining that the packets associated with the first protocol have a higher priority for processing than the packets associated with the first protocol.

Prioritization of network traffic

A network controller with a bootable Host Bus Adapter, particularly suitable for iSCSI applications is described. In one example, this includes, a host bus interface, a register to the host bus indicating a mass storage device, a network interface, and a boot memory extension including a driver for the mass storage device that binds to a BIOS.

LAN controller with bootable host bus adapter

Growing community of inventors

Beaverton, OR, United States of America

Dinesh Kumar