Integrated configuration engine for interference mitigation in cloud computing

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.

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.

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.