公开(公告)号：US10560394B2

公开(公告)日：2020-02-11

申请号：US15713230

申请日：2017-09-22

Applicant: CISCO TECHNOLOGY, INC.

Inventor： Prasannakumar Murugesan ,  Ajeet Pal Singh Gill ,  David A. Johnson ,  Ian McDowell Campbell ,  Ravinandan Arakali

IPC: H04L12/863 ,  H04L12/935 ,  H04W28/02 ,  H04L12/26 ,  H04L12/24

Abstract: In one embodiment, a method includes assigning a number of threads for user plane functions to a corresponding number of transmit queues for transmission of packets on a network interface, assigning additional threads exceeding the number of transmit queues to software transmission queues associated with the threads assigned to the transmit queues, identifying a load at each of the threads, dynamically updating assignment of the additional threads to the software transmission queues based on the load at the threads, and transmitting packets from the transmit queues for transmission on a network from a physical interface at a network device. An apparatus and logic are also disclosed herein.

公开(公告)号：US20190114206A1

公开(公告)日：2019-04-18

申请号：US15786657

申请日：2017-10-18

Applicant: Cisco Technology, Inc.

Inventor： Prasannakumar Murugesan ,  Ajeet Pal Singh Gill ,  Aeneas Sean Dodd-Noble ,  David A. Johnson ,  Ian McDowell Campbell ,  Tejas Birajdar

IPC: G06F9/50 ,  H04L12/875 ,  H04L12/863

Abstract: Disclosed is a method that includes periodically observing packets in a user plane according to at least one key performance indicator in a configuration file to yield an observation, wherein the observation represents a closed-loop demand of resources within the user plane. The method includes adjusting, via a scheduler in the user plane and based on the observation, a binding of cores to work items. The binding between cores and work items is dynamic and changeable to improve performance. The at least one key performance indicator can include one or more of a CPU utilization, latency and packet drops. The workload allocations can include work items that are individually scheduleable functions that operate on a queue of packets within the user plane.

公开(公告)号：US10382346B2

公开(公告)日：2019-08-13

申请号：US15791616

申请日：2017-10-24

Applicant: Cisco Technology, Inc.

Inventor： Prasannakumar Murugesan ,  Ajeet Pal Singh Gill ,  Aeneas Sean Dodd-Noble ,  David A. Johnson ,  Ian McDowell Campbell

IPC: H04L12/721 ,  H04L12/851

Abstract: In accordance with various implementations, a method is performed at a data plane node with one or more processors, non-transitory memory, and a control interface between a network function module associated with the data plane node and a switch associated with the data plane node. The method includes determining whether an offload capability is available for a data flow received at an ingress network interface of the data plane node. The method also includes determining whether the data flow satisfies offload criteria in response to determining that the offload capability is available. The method includes bypassing the network function module associated with the data plane node and providing the data flow to at least one of the switch associated with the data plane node or an egress network interface associated with the data plane node in response to determining the offload capability is available and the offload criteria is satisfied.

公开(公告)号：US10938727B2

公开(公告)日：2021-03-02

申请号：US16458829

申请日：2019-07-01

Applicant: Cisco Technology, Inc.

Inventor： Prasannakumar Murugesan ,  Ajeet Pal Singh Gill ,  Aeneas Sean Dodd-Noble ,  David A. Johnson ,  Ian McDowell Campbell

IPC: H04L12/851 ,  H04L12/721 ,  G06F13/12 ,  G06F13/00

Abstract: In accordance with various implementations, a method is performed at a data plane node with one or more processors, non-transitory memory, and a control interface between a network function module associated with the data plane node and a switch associated with the data plane node. The method includes determining whether an offload capability is available for a data flow received at an ingress network interface of the data plane node. The method also includes determining whether the data flow satisfies offload criteria in response to determining that the offload capability is available. The method includes bypassing the network function module associated with the data plane node and providing the data flow to at least one of the switch associated with the data plane node or an egress network interface associated with the data plane node in response to determining the offload capability is available and the offload criteria is satisfied.

公开(公告)号：US20190327177A1

公开(公告)日：2019-10-24

申请号：US16458829

申请日：2019-07-01

Applicant: Cisco Technology, Inc.

Inventor： Prasannakumar Murugesan ,  Ajeet Pal Singh Gill ,  Aeneas Sean Dodd-Noble ,  David A. Johnson ,  Ian McDowell Campbell

IPC: H04L12/851 ,  H04L12/721 ,  G06F13/00 ,  G06F13/12

Abstract: In accordance with various implementations, a method is performed at a data plane node with one or more processors, non-transitory memory, and a control interface between a network function module associated with the data plane node and a switch associated with the data plane node. The method includes determining whether an offload capability is available for a data flow received at an ingress network interface of the data plane node. The method also includes determining whether the data flow satisfies offload criteria in response to determining that the offload capability is available. The method includes bypassing the network function module associated with the data plane node and providing the data flow to at least one of the switch associated with the data plane node or an egress network interface associated with the data plane node in response to determining the offload capability is available and the offload criteria is satisfied.

公开(公告)号：US20190097939A1

公开(公告)日：2019-03-28

申请号：US15713230

申请日：2017-09-22

Applicant: CISCO TECHNOLOGY, INC.

Inventor： Prasannakumar Murugesan ,  Ajeet Pal Singh Gill ,  David A. Johnson ,  Ian McDowell Campbell ,  Ravinandan Arakali

IPC: H04L12/863

CPC classification number: H04L47/6255 ,  H04L41/20 ,  H04L43/0888 ,  H04L49/3063 ,  H04W28/0231

Abstract: In one embodiment, a method includes assigning a number of threads for user plane functions to a corresponding number of transmit queues for transmission of packets on a network interface, assigning additional threads exceeding the number of transmit queues to software transmission queues associated with the threads assigned to the transmit queues, identifying a load at each of the threads, dynamically updating assignment of the additional threads to the software transmission queues based on the load at the threads, and transmitting packets from the transmit queues for transmission on a network from a physical interface at a network device. An apparatus and logic are also disclosed herein.