Ensuring predictable and quantifiable networking performance

• US 9,231,869 B2
• Filed: 08/05/2014
• Issued: 01/05/2016
• Est. Priority Date: 06/21/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Kim, Changhoon, Greenberg, Albert G., Dabagh, Alireza, Khalidi, Yousef A., Bansal, Deepak, Kandula, Srikanth
• Primary Examiner(s): LY, ANH VU H
• Application Number:
  US14/452,256
• Publication Number:
  US 20140347998A1
• Time in Patent Office: 518 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 2009/45595 Network integration; Enabling network access in virtual machine instances
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: H04L 47/11 Identifying congestion
• CPC Class Codes: H04L 47/12 Avoiding congestion; Recovering from congestion
• CPC Class Codes: H04L 47/263 Rate modification at the source after receiving feedback
• CPC Class Codes: H04L 47/762 triggered by the network
• CPC Class Codes: H04L 47/822 Collecting or measuring resource availability data
• CPC Class Codes: H04L 49/70 Virtual switches
• CPC Class Codes: H04L 69/16 Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
• CPC Class Codes: Y02D 30/50 in wire-line communication networks, e.g. low power modes or reduced link rate

Abstract

The ensuring of predictable and quantifiable networking performance. Embodiments of the invention combine a congestion free network core with a hypervisor based (i.e., edge-based) throttling design to help insure quantitative and invariable subscription bandwidth rates. A lightweight shim layer in a hypervisor can adaptively throttle the rate of VM-to-VM traffic flow. A receiving hypervisor can detect congestion and communicate back to sending hypervisors that rates are to be regulated. In response, sending hypervisors can reduce transmission rate to mitigate congestion at the receiving hypervisor. In some embodiments, the principles are extended to any message processors communicating over a congestion free network.

Claims

1. A method implemented in a computing environment that includes a plurality of computing nodes that provide services for one or more users, with the plurality of computing nodes each including a message processor that communicates packets comprising data flows that are received by at least one computer system that includes one or more processors and system memory, the computer system also including a message processor for processing the data flows to provide the services for the one or more users, wherein the implemented method is a method for addressing network congestion arising from one or more of the computing nodes, the method comprising the following acts:

the computer system accessing a predetermined bandwidth limitation for a message processor, the predetermined bandwidth limitation indicating a quantitative and invariant minimum bandwidth for the message processor;

the computer system accessing one or more data flows;

the computer system calculating a combined bandwidth of the one or more received data flows;

the computer system detecting an onset of congestion at the computer system by determining that the calculated combined bandwidth is within a specified threshold;

the computer system, subsequent to detecting the onset of congestion, identifying at least one violating message processor of one of the computing nodes associated with the one or more data flows as a cause of the onset of congestion by determining that the at least one violating message processor is utilizing a bandwidth that exceeds a bandwidth limitation associated with the at least one violating message processor;

the computer system determining an extent in which the at least one violating message processor is over utilizing the bandwidth;

the computer system formulating at least one feedback message that serves to rate limit the at least one violating message processor; and

the computer system sending the feedback message for delivery to at least one adaptive rate limiter that is enabled to limit bandwidth utilization of the violating message processor.

2. The method as recited in claim 1, wherein the at least one data flow comprises a first data flow having a protocol complying with Transmission Control Protocol (TCP) as well as least one other data flow having an other protocol different than Transmission Control Protocol (TCP).

3. The method as recited in claim 2, wherein the other protocol comprises User Datagram Protocol (UDP).

4. The method as recited in claim 1, wherein said computer system is a virtual machine associated with a hypervisor.

5. The method as recited in claim 1, wherein the at least one feedback message is an instruction to reduce the bandwidth utilized by the violating message processor.

6. The method as recited in claim 5, wherein the instruction is an instruction to reduce the bandwidth in accordance with an additive increase/multiplicative decrease (AIMD) algorithm.

7. The method as recited in claim 1, wherein detecting the onset of congestion comprises an act of a software meter detecting the onset of congestion at the computer system.

8. The method as recited in claim 1, wherein detecting the onset of congestion comprises an act of using Explicit Congestion Notification (ECN) to detect the onset of congestion.

9. The method as recited in claim 1, wherein said detecting the onset of congestion is performed by a virtual switch within a hypervisor.

10. The method as recited in claim 1, wherein the adaptive rate limiter is included within a virtual switch of a hypervisor.

11. One or more computer hardware storage devices having stored thereon computer executable instructions that, when executed by one or more processors, implement a computer-controlled method for addressing network congestion arising from one or more of computing nodes in a computing environment that includes a plurality of computing nodes that provide services for one or more users, with the plurality of computing nodes each including a message processor that communicates packets comprising data flows that are received by at least one computer system that includes one or more processors and system memory, the computer system also including a message processor for processing the data flows to provide the services for the one or more users, wherein the implemented method is a method for addressing network congestion arising from one or more of the computing nodes, wherein the method includes:

the computer system accessing a predetermined bandwidth limitation for a message processor, the predetermined bandwidth limitation indicating a quantitative and invariant minimum bandwidth for the message processor;

the computer system accessing one or more data flows;

the computer system calculating a combined bandwidth of the one or more received data flows;

the computer system detecting an onset of congestion at the computer system by determining that the calculated combined bandwidth is within a specified threshold;

the computer system, subsequent to detecting the onset of congestion, identifying at least one violating message processor of one of the computing nodes associated with the one or more data flows as a cause of the onset of congestion by determining that the at least one violating message processor is utilizing a bandwidth that exceeds a bandwidth limitation associated with the at least one violating message processor;

the computer system determining an extent in which the at least one violating message processor is over utilizing the bandwidth;

the computer system formulating at least one feedback message that serves to rate limit the at least one violating message processor; and

the computer system sending the feedback message for delivery to at least one adaptive rate limiter that is enabled to limit bandwidth utilization of the violating message processor.

12. The method as recited in claim 11, wherein the at least one data flow comprises a first data flow having a protocol complying with Transmission Control Protocol (TCP) as well as least one other data flow having an other protocol different than Transmission Control Protocol (TCP).

13. The method as recited in claim 12, wherein the other protocol comprises User Datagram Protocol (UDP).

14. The method as recited in claim 11, wherein the adaptive rate limiter is included within a virtual switch of a hypervisor of a virtual machine.

15. The method as recited in claim 11, wherein the at least one feedback message is an instruction to reduce the bandwidth utilized by the violating message processor.

16. The method as recited in claim 15, wherein the instruction is an instruction to reduce the bandwidth in accordance with an additive increase/multiplicative decrease (AIMD) algorithm.

17. The method as recited in claim 11, wherein detecting the onset of congestion comprises an act of a software meter detecting the onset of congestion at the computer system.

18. The method as recited in claim 11, wherein detecting the onset of congestion comprises an act of using Explicit Congestion Notification (ECN) to detect the onset of congestion.

19. The method as recited in claim 11, wherein detecting the onset of congestion is performed by a virtual switch within a hypervisor of a virtual machine.

20. A computing system comprising:

at least one processor; and

system memory having stored computer-executable instructions which executed by the at least one processor, implement a method in a computing environment that includes a plurality of computing nodes that provide services for one or more users, with the plurality of computing nodes each including a message processor that communicates packets comprising data flows that are received by at least one computer system that includes one or more processors and system memory, the computer system also including a message processor for processing the data flows to provide the services for the one or more users, wherein the implemented method is a method for addressing network congestion arising from one or more of the computing nodes, the method comprising the following acts;

the computer system accessing a predetermined bandwidth limitation for a message processor, the predetermined bandwidth limitation indicating a quantitative and invariant minimum bandwidth for the message processor;

the computer system accessing one or more data flows;

the computer system calculating a combined bandwidth of the one or more received data flows;

the computer system detecting an onset of congestion at the computer system by determining that the calculated combined bandwidth is within a specified threshold;

the computer system, subsequent to detecting the onset of congestion, identifying at least one violating message processor of one of the computing nodes associated with the one or more data flows as a cause of the onset of congestion by determining that the at least one violating message processor is utilizing a bandwidth that exceeds a bandwidth limitation associated with the at least one violating message processor;

the computer system determining an extent in which the at least one violating message processor is over utilizing the bandwidth;

the computer system formulating at least one feedback message that serves to rate limit the at least one violating message processor; and

the computer system sending the feedback message for delivery to at least one adaptive rate limiter that is enabled to limit bandwidth utilization of the violating message processor.