IP Library Granted Patent US 11,258,719
Granted Patent B1
US 11,258,719 · App. 17/001,614 · Granted Feb 22, 2022

Methods, systems and computer readable media for network congestion control tuning

Inventor: Christian Paul Sommers (Bangor, CA)
Assignee: KEYSIGHT TECHNOLOGIES, INC.
H04L47/2466H04L43/04H04L43/10H04L67/1097
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 11,258,719
App. No.
17/001,614
Granted
Feb 22, 2022
Kind
B1
Abstract

The subject matter described herein includes methods, systems, and computer readable media for network congestion control tuning. A method for network congestion control tuning occurs at a network congestion control tuning analyzer. The method includes receiving in-band telemetry (INT) metadata from a system under test (SUT); analyzing network information associated with one or more remote direct memory access (RDMA) transactions for determining a tuning action for adjusting a data center quantized congestion notification (DCQCN) mechanism associated with the SUT, wherein the network information includes the INT metadata and DCQCN information; and performing the tuning action for adjusting the DCQCN mechanism associated with the SUT.

Claims (39)

1. A method for network congestion control tuning, the method comprising:

at a network congestion control tuning analyzer:

receiving in-band telemetry (INT) metadata from a system under test (SUT);

analyzing network information associated with one or more remote direct memory access (RDMA) transactions for determining a tuning action for adjusting a data center quantized congestion notification (DCQCN) mechanism associated with the SUT, wherein the network information includes the INT metadata and DCQCN information, wherein determining the tuning action includes determining one or more tuning recommendations for adjusting or tuning at least one network congestion control parameter; and

performing the tuning action for adjusting the DCQCN mechanism associated with the SUT, wherein performing the tuning action includes adjusting or facilitating an adjustment of the at least one network congestion control parameter in accordance with the one or more tuning recommendations, wherein the at least one network congestion control parameter includes a headroom buffer parameter, a priority-based flow control (PFC) threshold parameter, or an explicit congestion notification (ECN) threshold parameter.

2. The method of claim 1 wherein analyzing the network information includes:

correlating the INT metadata and network congestion control information associated with the one or more RDMA transactions; and

detecting a network congestion pattern using the INT metadata and the network congestion control information associated with the SUT, wherein the network congestion pattern indicates network conditions that cause or contribute to network congestion.

3. The method of claim 2 wherein performing the tuning action includes using previously-stored captured traffic data and the network congestion pattern to simulate a traffic workload including RDMA payloads usable for subsequent testing.

4. The method of claim 1 wherein the INT metadata from the SUT is triggered by:

inserting INT instruction headers in RDMA packets; or

generating test RDMA packets containing INT instruction headers.

5. The method of claim 4 wherein the INT instruction headers are removed by an in-line device prior to the RDMA packets reaching a destination.

6. The method of claim 2 wherein the network congestion control information associated with the SUT includes ECN information or PFC information.

7. The method of claim 1 wherein the tuning action includes generating a performance metric associated with network congestion, reporting device or protocol issues associated with network congestion, generating a network congestion report, or triggering additional testing and/or analysis using one or the more tuning recommendations.

8. The method of claim 1 wherein the SUT includes a local area network, a wide area network, a data center related network, a converged Ethernet network, a network switch, a data server, a web server, an RDMA over converged Ethernet (RoCE) related node, or a data center related node and wherein the network congestion control tuning analyzer includes a network equipment test system, a network tap, a network monitoring device, a network interface card (NIC), a traffic generator, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or a processor.

9. A system for network congestion control tuning, the system comprising:

at least one processor; and

a network congestion control tuning analyzer implemented using the at least one processor, the network congestion control tuning analyzer configured for:

receiving in-band telemetry (INT) metadata from a system under test (SUT);

analyzing network information associated with one or more remote direct memory access (RDMA) transactions for determining a tuning action for adjusting a data center quantized congestion notification (DCQCN) mechanism associated with the SUT, wherein the network information includes the INT metadata and DCQCN information, wherein determining the tuning action includes determining one or more tuning recommendations for adjusting or tuning at least one network congestion control parameter; and

performing the tuning action for adjusting the DCQCN mechanism associated with the SUT, wherein performing the tuning action includes adjusting or facilitating an adjustment of the at least one network congestion control parameter in accordance with the one or more tuning recommendations, wherein the at least one network congestion control parameter includes a headroom buffer parameter, a priority-based flow control (PFC) threshold parameter, or an explicit congestion notification (ECN) threshold parameter.

10. The system of claim 9 wherein the network congestion control tuning analyzer is configured for:

correlating the INT metadata and network congestion control information associated with the one or more RDMA transactions; and

detecting a network congestion pattern using the INT metadata and the network congestion control information associated with the SUT, wherein the network congestion pattern indicates network conditions that cause or contribute to network congestion.

11. The system of claim 10 wherein the network congestion control tuning analyzer is configured for using previously-stored captured traffic data and the network congestion pattern to simulate a traffic workload including RDMA payloads usable for subsequent testing.

12. The system of claim 9 wherein the INT metadata from the SUT is triggered by the network congestion control tuning analyzer or a related node inserting INT instruction headers in RDMA packets or generating test RDMA packets containing INT instruction headers.

13. The system of claim 12 wherein an in-line device removes the INT instruction headers prior to the RDMA packets reaching a destination.

14. The system of claim 10 wherein the network congestion control information associated with the SUT includes ECN information or PFC information.

15. The system of claim 9 wherein the tuning action includes generating a performance metric associated with network congestion, reporting device or protocol issues associated with network congestion, generating a network congestion report, or triggering additional testing and/or analysis using the one or more tuning recommendations.

16. The system of claim 9 wherein the SUT includes a local area network, a wide area network, a data center related network, a converged Ethernet network, a network switch, a data server, a web server, an RDMA over converged Ethernet (RoCE) related node, or a data center related node and wherein the network congestion control tuning analyzer includes a network equipment test system, a network tap, a network monitoring device, a network interface card (NIC), a traffic generator, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or a processor.

17. A non-transitory computer readable medium having stored thereon executable instructions that when executed by at least one processor of at least one computer cause the at least one computer to perform steps comprising:

at a network congestion control tuning analyzer:

receiving in-band telemetry (INT) metadata from a system under test (SUT);

analyzing network information associated with one or more remote direct memory access (RDMA) transactions for determining a tuning action for adjusting a data center quantized congestion notification (DCQCN) mechanism associated with the SUT, wherein the network information includes the INT metadata and DCQCN information, wherein determining the tuning action includes determining one or more tuning recommendations for adjusting or tuning at least one network congestion control parameter; and

performing the tuning action for adjusting the DCQCN mechanism associated with the SUT, wherein performing the tuning action includes adjusting or facilitating an adjustment of the at least one network congestion control parameter in accordance with the one or more tuning recommendations, wherein the at least one network congestion control parameter includes a headroom buffer parameter, a priority-based flow control (PFC) threshold parameter, or an explicit congestion notification (ECN) threshold parameter.

18. The non-transitory computer readable medium of claim 17 wherein analyzing the network information includes:

correlating the INT metadata and network congestion control information associated with the one or more RDMA transactions; and

detecting a network congestion pattern using the INT metadata and the network congestion control information associated with the SUT, wherein the network congestion pattern indicates network conditions that cause or contribute to network congestion.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 19, 2021
From: SOMMERS, CHRISTIAN PAUL
To: KEYSIGHT TECHNOLOGIES, INC.
Reel/Frame 055339/0164 →
Cited By (7)
US 12,242,413 US 12,301,480 US 12,368,673 US 12,368,675 US 12,375,561 US 12,375,562 US 12,683,899