IP Library › Granted Patent US 12,513,089
Granted Patent B2
US 12,513,089 · App. 17/545,962 · Granted Dec 30, 2025

Congestion control

Inventors: Roberto Penaranda Cebrian (Santa Clara, CA); Robert Southworth (Chatsworth, CA); Pedro Yebenes Segura (San Jose, CA); Rong Pan (Saratoga, CA); Allister Alemania (North Plains, OR); Nayan Amrutlal Suthar (Pune, IN); Malek Musleh (Portland, OR)
Assignee: Intel Corporation
H04L47/25H04L47/27H04L47/283
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,513,089
App. No.
17/545,962
Granted
Dec 30, 2025
Kind
B2
Abstract

Examples described herein relate to a network interface device that is to adjust a transmission rate of packets based on a number of flows contributing to congestion and/or based on whether latency is increasing or decreasing. In some examples, adjusting the transmission rate of packets based on a number of flows contributing to congestion comprises adjust an additive increase (AI) parameter based on the number of flows contributing to congestion. In some examples, latency is based on a measured roundtrip time and a baseline roundtrip time.

Claims (33)

1 . An apparatus comprising:

a network interface device comprising:

circuitry to adjust a transmission rate of packets based on a number of multiple flows contributing to congestion;

a direct memory access (DMA) circuitry;

a host interface; and

a network interface, wherein the adjust the transmission rate based on the number of flows contributing to congestion comprises adjust an additive increase parameter based on the number of multiple flows contributing to congestion and wherein the adjust the transmission rate based on the number of multiple flows contributing to congestion comprises adjust a congestion window size based on the additive increase parameter and the number of multiple flows contributing to congestion.

2 . The apparatus of claim 1 , wherein the number of multiple flows contributing to congestion is received in a packet header field from a network interface device that detected the congestion.

3 . The apparatus of claim 1 , wherein the circuitry is to adjust a congestion window size based on a difference between round trip time (RTT) and a baseline RTT.

4 . The apparatus of claim 3 , wherein the RTT is based on a difference between packet transmit time and time of received acknowledgement (ACK).

5 . The apparatus of claim 3 , wherein the adjust the congestion window size comprises increase the congestion window size based on a first threshold.

6 . The apparatus of claim 3 , wherein the adjust the congestion window size comprises set the congestion window to a congestion window value based on the difference being more than a first threshold and less than a second threshold.

7 . The apparatus of claim 3 , wherein the adjust the congestion window size comprises decrease the congestion window size based on a second threshold.

8 . The apparatus of claim 1 , wherein the circuitry comprises a programmable packet processing pipeline that comprises one or more match-action units (MAUs).

9 . The apparatus of claim 1 , comprising a server comprising at least one processor to execute a driver to configure the circuitry to adjust a packet transmission rate based on the number of multiple flows contributing to congestion.

10 . The apparatus of claim 9 , comprising a datacenter comprising the server and a second server, wherein the second server is to received transmitted packets from the network interface device.

11 . An apparatus comprising:

a network interface device comprising:

a direct memory access (DMA) circuitry;

a host interface;

a network interface; and

circuitry to adjust a transmit rate of packets of a flow based on whether latency is increasing or decreasing, a number of multiple flows contributing to congestion, wherein the adjust the transmit rate of packets of the flow comprises adjust a congestion window size based on an additive increase (AI) parameter and the number of multiple flows contributing to congestion.

12 . The apparatus of claim 11 , wherein the latency is based on a measured roundtrip time and a baseline roundtrip time.

13 . At least one non-transitory computer-readable medium comprising instructions stored thereon, which when executed by one or more processors, cause the one or more processors to:

configure a network interface device to adjust a transmission rate of packets based on a number of multiple flows contributing to congestion and/or based on whether latency is increasing or decreasing, wherein:

the network interface device comprises a direct memory access (DMA) circuitry; a host interface; and a network interface, and

the adjust the transmission rate of packets based on the number of multiple flows contributing to congestion comprises adjust a congestion window size based on an additive increase (AI) parameter and based on the number of multiple flows contributing to congestion.

14 . The computer-readable medium of claim 13 , comprising instructions stored thereon, which when executed by one or more processors, cause the one or more processors to:

configure the network interface device to adjust a congestion window size based on a determined difference of round trip time (RTT) relative to a baseline RTT.

15 . The computer-readable medium of claim 13 , wherein the latency is based on a measured roundtrip time and a baseline roundtrip time.

16 . The apparatus of claim 1 , wherein the additive increase parameter is consistent with High Precision Congestion Control (HPCC).

17 . The apparatus of claim 12 , wherein:

the baseline roundtrip time comprises a roundtrip time of an uncongested network and

the circuitry to adjust the transmit rate of packets of the flow based on whether latency is increasing or decreasing by adjusting the congestion window size towards a target congestion window value.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 28, 2022
From: PENARANDA CEBRIAN, ROBERTO; SOUTHWORTH, ROBERT; YEBENES SEGURA, PEDRO; PAN, RONG; ALEMANIA, ALLISTER; SUTHAR, NAYAN AMRUTLAL; MUSLEH, MALEK
To: INTEL CORPORATION
Reel/Frame 058807/0497 →
Continuity (1)
Related Publication 20220103484A1 · Mar 31, 2022
References Cited (37)
US 7693052B2 · Jin · 2010 [cited by examiner]
US 8837279B2 · Nemeth · 2014 [cited by examiner]
US 8923115B2 · Pelletier · 2014 [cited by examiner]
US 8923123B2 · Kulkarni · 2014 [cited by examiner]
US 9432297B2 · Wu · 2016 [cited by examiner]
US 9485184B2 · Mehrotra · 2016 [cited by examiner]
US 10033653B2 · Persson · 2018 [cited by examiner]
US 10361963B2 · Li · 2019 [cited by examiner]
US 10492097B2 · Lee · 2019 [cited by examiner]
US 11115308B2 · Zheng · 2021 [cited by examiner]
US 11134018B2 · Kameyama · 2021 [cited by examiner]
US 11509593B2 · Kumar · 2022 [cited by examiner]
US 11516139B2 · Ismailsheriff · 2022 [cited by examiner]
US 12074794B2 · Pan · 2024 [cited by examiner]
US 12212502B2 · Debbage · 2025 [cited by examiner]
US 20060050640A1 · Jin et al. · 2006 [cited by applicant]
US 20090073975A1 · Shimonishi · 2009 [cited by applicant]
US 20210112002A1 · Pan et al. · 2021 [cited by applicant]
US 20220311711A1 · Jepsen · 2022 [cited by examiner]
KR 20160144257A · 2016 [cited by applicant]
Gaoxiong Zeng et al., ‘Combining ECN and RTT for Datacenter Transport’ In Proceedings of APNet' 17, Hong Kong, China, Aug. 4, 2017, pp. 1-7. [cited by applicant]
International Search Report and Written Opinion for PCT Patent Application No. PCT/US22/48237, Mailed Feb. 1, 2023, 12 pages. [cited by applicant]
Samba Siva Reddy Maripalli et al., ‘Congestion Control for TCP in Data-Center Networks’, International Journal of Computer Science and Information Technologies, vol. 5(2), 2014, pp. 1903-1907. [cited by applicant]
Alizadeh, Mohammad et al., “Data Center TCP (DCTCP)”, SIGCOMM, New Delhi, India, 2010, 12 pages. [cited by applicant]
Bosshart, Pat et al., “P4: Programming Protocol-Independent Packet Processors”, ACM SIGCOMM Computer Communication Review, vol. 44, No. 3, Jul. 2014, pp. 88-95. [cited by applicant]
Brakmo, Lawrence S. et al., “TCP Vegas: New Techniques for Congestion Detection and Avoidance,” SIGCOMM, vol. 24, No. 4, 1994, 12 pages. [cited by applicant]
Gao, Yixiao et al., “DCQCN+: Taming Large-Scale Incast Congestion in RDMA over Ethernet Networks”, in 2018 EEE 26th International Conference on Network Protocols (ICNP), Cambridge, United Kingdom, 2018, 11 pages. [cited by applicant]
InfiniBand Trade Association, “Supplement to InfiniBand™ Architecture Specification vol. 1, Release 1.2.1, Annex A17: RoCEv2”, Sep. 2, 2014, 23 pages. [cited by applicant]
Kumar, Gautam et al., “Swift: Delay is Simple and Effective for Congestion Control in the Datacenter,” SIGCOMM 20, New York, NY, USA, 2020, 15 pages. [cited by applicant]
Li, Yuliang et al., “HPCC: High Precision Congestion Control”, SIGCOMM, Beijing, China, 2019, 15 pages. [cited by applicant]
Mittal, Radhika et al., “TIMELY: RTT-based Congestion Control for the”, SIGCOMM, London, UK, 2015, 14 pages. [cited by applicant]
Montazeri, Behnam et al., “Homa: A Receiver-Driven Low-Latency Transport Protocol Using Network Priorities”, SIGCOMM, Budapest, Hungary, 2018, 15 pages. [cited by applicant]
Musleh, Malek et al., “Fabsim-X: A Simulation Framework for the Analysis of Large-Scale Topologies and Congestion Control Protocols in Data Center Networks”, in 28th International Symposium on Modeling, Analysis, and Si… [cited by applicant]
The P4.org Applications Working Group, “In-band Network Telemetry (INT) Dataplane Specification, Version 2.1”, Nov. 2020, 56 pages. [cited by applicant]
Zhu, Yibo, “Congestion Control for Large-Scale RDMA Deployments”, SIGCOMM, London, UK, 2015, 14 pages. [cited by applicant]
Extended European Search Report for Patent Application No. 22904876.4, Mailed Oct. 9, 2025, 12 pages. [cited by applicant]
Zhang Jiao et al.: “Receiver-Driven RDMA Congestion Control by Differentiating Congestion Types in Datacenter Networks”, 2021 IEEE 29TH International Conference On Network Protocols (ICNP), IEEE, Nov. 1, 2021 (Nov. 1, 2… [cited by applicant]