Integrated configuration engine for interference mitigation in cloud computing

• US 10,310,883 B2
• Filed: 07/06/2016
• Issued: 06/04/2019
• Est. Priority Date: 07/06/2015
• Status: Active Grant

• Current Assignee: Purdue Research Foundation (The Trustees of Purdue University (d/b/a Purdue University))
• Original Assignee: Purdue Research Foundation (The Trustees of Purdue University (d/b/a Purdue University))
• Inventors: Maji, Amiya Kumar, Mitra, Subrata, Bagchi, Saurabh
• Primary Examiner(s): Cao, Diem K
• Application Number:
  US15/203,733
• Publication Number:
  US 20170010911A1
• Time in Patent Office: 1,063 Days
• Field of Search: None
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2009/45591 Monitoring or debugging support
• 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: G06F 9/5083 Techniques for rebalancing the load in a distributed system

Abstract

A cloud computing system which is configured to monitor operating status of a plurality of virtual computing machines running on a physical computing machine, wherein said monitoring includes monitoring a cycles per instruction (CPI) parameter and a cache miss rate (CMR) parameter of at least one of the plurality of virtual computing machines. The system detects interference in the operation of the at least one virtual machine, with the detection including determining when at least one of the CPI and CMR values exceed a predetermined threshold. When interference is detected, the system reconfigures a load balancing module associated with the virtual machine in question to send fewer requests to the virtual machine.

Claims

1. A cloud computing system, comprising:

a) a computing engine configured to;

i) monitor operating status of a plurality of virtual computing machines running on a physical computing machine, wherein said monitoring includes monitoring a cycles per instruction (CPI) parameter and a cache miss rate (CMR) parameter of at least one of the plurality of virtual computing machines;

ii) detect interference in the operation of the at least one virtual machine, said detection including determining when at least one of said CPI and CMR values exceed a predetermined threshold;

iii) reconfigure a load balancing module associated with the at least one virtual machine to send fewer requests to said one of said virtual machines when said interference is detected;

iv) collect training data relating to the at least one virtual machine; and

v) utilize said training data to determine said estimated processor utilization;

wherein said reconfiguring the load balancing module comprises determining an estimated processor utilization of a web server running on said virtual computing machine, determining a request rate for the virtual machine that will reduce the processor utilization below a utilization threshold, and reducing said request scheduling weight to achieve said request rate.

2. The system of claim 1, wherein said reconfiguring the load balancing module comprises reducing a request scheduling weight associated with said virtual machine in said load balancing module.

3. The system of claim 1, wherein the computing engine is further configured to:

i) reconfigure a web server associated with the at least one virtual machine to improve performance of the at least one virtual machine if the interference exceeds a predetermined interference duration.

4. The system of claim 3, wherein said reconfiguration of the web server comprises reducing a maximum clients parameter of said web server, said maximum clients parameter representing a maximum number of worker threads that the web server can initiate.

5. A cloud computing system, comprising:

a) a computing engine configured to;

i) monitor operating status of a plurality of virtual computing machines running on a physical computing machine, wherein said monitoring includes monitoring a cycles per instruction (CPI) parameter and a cache miss rate (CMR) parameter of at least one of the plurality of virtual computing machines;

ii) detect interference in the operation of the at least one virtual machine, said detection including determining when at least one of said CPI and CMR values exceed a predetermined threshold;

iii) reconfigure a load balancing module associated with the at least one virtual machine to send fewer requests to said one of said virtual machines when said interference is detected, and

iv) reconfigure a web server associated with the at least one virtual machine to improve performance of the at least one virtual machine if the interference exceeds a predetermined interference duration,

wherein said reconfiguration of the web server comprises reducing a maximum clients parameter of said web server, said maximum clients parameter representing a maximum number of worker threads that the web server can initiate;

wherein said reconfiguration further comprises increasing a keep alive timeout parameter of said web server, said keep alive timeout parameter representing a duration a client connection to the web server is persisted in an idle state before being terminated.

6. A cloud computing system, comprising:

a plurality of physical computing machines having a processor and a memory, each of the physical computing machines comprising a plurality of virtual computing machines, each of the virtual computing machines running a web server module;

a computing engine, the computing engine configured to;

monitor operating status of a plurality of virtual computing machines running on a physical computing machine, wherein said monitoring includes monitoring a cycles per instruction (CPI) parameter and a cache miss rate (CMR) parameter of at least one of the plurality of virtual computing machines;

detect interference in the operation of the at least one virtual machine, said detection including determining when at least one of said CPI and CMR values exceed a predetermined threshold; and

reconfigure a load balancing module associated with the at least one virtual machine to send fewer requests to said one of said virtual machines when said interference is detected

collect training data relating to the at least one virtual machine; and

utilize said training data to determine said estimated processor utilization;

wherein said reconfiguring the load balancing module comprises determining an estimated processor utilization of a web server running on said virtual computing machine, determining a request rate for the virtual machine that will reduce the processor utilization below a utilization threshold, and reducing said request scheduling weight to achieve said request rate.

7. The system of claim 6, wherein said reconfiguring the load balancing module comprises reducing a request scheduling weight associated with said virtual machine in said load balancing module.

8. The system of claim 6, wherein the computing engine is further configured to:

i) reconfigure a web server associated with the at least one virtual machine to improve performance of the at least one virtual machine if the interference exceeds a predetermined interference duration.

9. The system of claim 8, wherein said reconfiguration of the web server comprises reducing a maximum clients parameter of said web server, said maximum clients parameter representing a maximum number of worker threads that the web server can initiate.

10. A cloud computing system, comprising:

a plurality of physical computing machines having a processor and a memory, each of the physical computing machines comprising a plurality of virtual computing machines, each of the virtual computing machines running a web server module;

a computing engine, the computing engine configured to;

monitor operating status of a plurality of virtual computing machines running on a physical computing machine, wherein said monitoring includes monitoring a cycles per instruction (CPI) parameter and a cache miss rate (CMR) parameter of at least one of the plurality of virtual computing machines;

detect interference in the operation of the at least one virtual machine, said detection including determining when at least one of said CPI and CMR values exceed a predetermined threshold; and

reconfigure a load balancing module associated with the at least one virtual machine to send fewer requests to said one of said virtual machines when said interference is detected;

reconfigure a web server associated with the at least one virtual machine to improve performance of the at least one virtual machine if the interference exceeds a predetermined interference duration;

collect training data relating to the at least one virtual machine; and

utilize said training data to determine said estimated processor utilization;

wherein said reconfiguring the load balancing module comprises determining an estimated processor utilization of a web server running on said virtual computing machine, determining a request rate for the virtual machine that will reduce the processor utilization below a utilization threshold, and reducing said request scheduling weight to achieve said request rate,

wherein said reconfiguration comprises reducing a maximum clients parameter of said web server, said maximum clients parameter representing a maximum number of worker threads that the web server can initiate;

wherein said reconfiguration further comprises increasing a keep alive timeout parameter of said web server, said keep alive timeout parameter representing a duration a client connection to the web server is persisted in an idle state before being terminated.