Ensuring predictable and quantifiable networking performance

• US 9,537,773 B2
• Filed: 12/29/2015
• Issued: 01/03/2017
• 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:
  US14/983,007
• Publication Number:
  US 20160134538A1
• Time in Patent Office: 371 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 computing system comprising:

one or more processors;

one or more hardware storage devices having stored computer-executable instructions which are executable by the one or more processors for implementing a method for addressing network congestion within a computing environment that includes a plurality of computing systems, the plurality of computing systems managing sending message processors that communicate packets comprising one or more data flows that are sent to and received by one or more receiving message processors managed by the computing system, wherein the method comprises the following;

the computer system identifying a predetermined bandwidth limitation associated with the plurality of computing systems;

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

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

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

the computer system determining an extent in which the particular bandwidth limitation is exceeded by the at least one violating message processor;

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 at least one violating message processor.

2. The computing system of claim 1, wherein the computer system manages a plurality of receiving message processors, corresponding to a plurality of virtual machines, each of the receiving message processors comprising a separate virtual machine.

3. The computing system of claim 2, wherein the plurality of virtual machines belong to a single tenant.

4. The computing system of claim 3, wherein the plurality of virtual machines belong to different tenants.

5. The computing system of claim 1, wherein the computer system comprises a hypervisor, and wherein said detecting the onset of congestion is performed by a virtual switch within the hypervisor and wherein the adaptive rate limiter is included within a virtual switch of the hypervisor.

6. The computing system 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.

7. The computing system as recited in claim 1, wherein the at least one feedback message is an instruction to reduce the bandwidth utilized by the at least one violating message processor in accordance with an additive increase/multiplicative decrease (AIMD) algorithm.

8. The computing system 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 a protocol different than Transmission Control Protocol (TCP).

9. A computing system comprising:

one or more processors;

a hypervisor that receive one or more data flows from a plurality of sending virtual machines that communicate packets to one or more receiving virtual machines managed by the hypervisor; and

a virtual machine switch that includes a congestion detector that performs the following;

identifies a predetermined bandwidth limitation associated with the plurality of sending virtual machines;

calculates a combined bandwidth of the one or more received data flows;

detect an onset of congestion by at least determining that the calculated combined bandwidth is within a specified threshold of the predetermined bandwidth limitation;

subsequent to detecting the onset of congestion, identify at least one violating virtual machine associated with the one or more data flows as a cause of the detected onset of congestion by at least determining that the at least one violating virtual machine is utilizing a bandwidth that exceeds a particular bandwidth limitation associated with the at least one violating virtual machine;

determine an extent in which the particular bandwidth limitation is exceeded by the at least one violating virtual machine;

formulate at least one feedback message that serves to rate limit the at least one violating virtual machine; and

send the feedback message for delivery to at least one adaptive rate limiter that is enabled to limit bandwidth utilization of the at least one violating virtual machine.

10. The computing system of claim 9, wherein the one or more receiving virtual machines comprises a plurality of virtual machines.

11. The computing system of claim 10, wherein the plurality of virtual machines belong to a single tenant.

12. The computing system of claim 10, wherein the plurality of virtual machines belong to a plurality of tenants.

13. The computing system of claim 9, wherein the virtual machine switch further includes the adaptive rate limiter.

14. A computer-implemented method for addressing network congestion within a computing environment having a plurality of computing systems, the plurality of computing systems managing sending message processors that communicate packets comprising one or more data flows that are sent to and received by one or more receiving message processors managed by at least one computing system for processing the received data flows, wherein the method comprises the following:

the at least one computer system identifying a predetermined bandwidth limitation associated with the plurality of computing systems;

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

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

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

the at least one computer system determining an extent in which the particular bandwidth limitation is exceeded by the at least one violating message processor;

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

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

15. The method of claim 14, wherein the computer system manages a plurality of receiving message processors, corresponding to a plurality of virtual machines, each of the receiving message processors comprising a separate virtual machine.

16. The method of claim 15, wherein the plurality of virtual machines belong to a single tenant.

17. The method of claim 14, wherein the computer system comprises a hypervisor, and wherein said detecting the onset of congestion is performed by a virtual switch within the hypervisor.

18. The method as recited in claim 17, wherein the adaptive rate limiter is included within a virtual switch of the hypervisor.

19. The method as recited in claim 14, wherein detecting the onset of congestion comprises an act of using Explicit Congestion Notification (ECN) to detect the onset of congestion.

20. The method as recited in claim 14, wherein the at least one feedback message is an instruction to reduce the bandwidth utilized by the at least one violating message processor in accordance with an additive increase/multiplicative decrease (AIMD) algorithm.