Reducing Power Consumption in a Server Cluster

Abstract

A method of reducing power consumption of a server cluster of host systems with virtual machines executing on the host systems is provided. The method includes recommending host system power-on when there is a host system whose utilization is above a target utilization, and recommending host system power-off when there is a host system whose utilization is below the target utilization. Recommending host system power-on includes calculating impact of powering on a standby host system with respect to reducing the number of highly-utilized host systems in the server cluster. Recommending host system power-off includes calculating impact of powering off a host system with respect to decreasing the number of less-utilized host systems in the server cluster.

1 . (canceled) 
     
     
         2 . A method comprising:
 recommending host system power-on of a standby host system when there is a host system in a server cluster of host systems in which utilization is above a target utilization, wherein:
 recommending the host system power-on includes calculating an impact of powering on the standby host system with respect to reducing the number of highly-utilized host systems in the server cluster, the impact of powering on being calculated by simulating moving at least one virtual machine from at least one highly utilized host system to the standby host system being recommended to be powered-on; and 
 calculating the impact of powering on the standby host system comprises calculating an amount by which the utilization of a plurality of host systems in the server cluster exceeds the target utilization. 
   
     
     
         3 . The method of  claim 2 , further comprising:
 determining the utilization of each host system in the server cluster as a ratio of demand to capacity for that host system.   
     
     
         4 . The method of  claim 2 , wherein recommending the host system power-on comprises including iterating through standby host systems, and for each respective standby host system, invoking a software module supporting virtual machine resource constraints and quantifying the impact of powering on the respective standby host system. 
     
     
         5 . The method of  claim 2 , wherein calculating the impact of powering on is repeated for each standby host system in the server cluster to determine whether that standby host system should be recommended to be powered-on. 
     
     
         6 . The method of  claim 2 , further comprising:
 calculating an impact of powering off a host system within the server cluster by calculating an amount by which the utilization of a plurality of host systems in the server cluster is below the target utilization.   
     
     
         7 . The method of  claim 6 , wherein calculating the impact of powering off is repeated for each powered-on host system in the server cluster to determine whether that powered-on host system should be recommended to be powered-off. 
     
     
         8 . The method of  claim 2 , wherein recommending host system power-off includes calculating host power-off cost, wherein the host power-off cost is based upon assessing at least one of: a loss of the host system's resources during power-down, power consumed during a power-down period, a loss of the host system's resources during a subsequent power-on operation, power consumed during a power-up period, or costs of migrating virtual machines back onto the host system. 
     
     
         9 . A non-transitory computer-readable medium embodying computer instructions executable by a computing device, the computer instructions being configured to cause the computing device to at least:
 recommend host system power-on of a standby host system when there is a host system in a server cluster of host systems in which utilization is above a target utilization, wherein:
 recommending the host system power-on includes calculating an impact of powering on the standby host system with respect to reducing the number of highly-utilized host systems in the server cluster, the impact of powering on being calculated by simulating moving at least one virtual machine from at least one highly utilized host system to the standby host system being recommended to be powered-on; and 
 calculating the impact of powering on the standby host system comprises calculating an amount by which the utilization of a plurality of host systems in the server cluster exceeds the target utilization. 
   
     
     
         10 . The non-transitory computer-readable medium of  claim 9 , wherein the computer instructions are further configured to cause the computing device to at least:
 determine the utilization of each host system in the server cluster as a ratio of demand to capacity for that host system.   
     
     
         11 . The non-transitory computer-readable medium of  claim 9 , wherein recommending the host system power-on comprises including iterating through standby host systems, and for each respective standby host system, invoking a software module supporting virtual machine resource constraints and quantifying the impact of powering on the respective standby host system. 
     
     
         12 . The non-transitory computer-readable storage medium of  claim 9 , wherein calculating the impact is repeated for each standby host system in the server cluster to determine whether that standby host system should be recommended to be powered-on. 
     
     
         13 . The non-transitory computer-readable storage medium of  claim 9 , wherein the computer instructions are further configured to cause the computing device to at least:
 calculate the impact of powering off a host system within the server cluster by calculating an amount by which the utilization of a plurality of host systems in the server cluster is below the target utilization.   
     
     
         14 . The non-transitory computer-readable storage medium of  claim 13 , wherein calculating the impact of powering off is repeated for each powered-on host system in the server cluster to determine whether that powered-on host system should be recommended to be powered-off. 
     
     
         15 . The non-transitory computer-readable storage medium of  claim 9 , wherein recommending host system power-off includes calculating host power-off cost, wherein factors involved in calculating the host system power-off cost include one or more of a loss of the host system's resources during power-down, power consumed during a power-down period, a loss of the host system's resources during a subsequent power-on operation, power consumed during a power-up period, and costs of migrating virtual machines back onto the host system. 
     
     
         16 . A system comprising:
 a computing device; and   an application executable by the computing device, wherein the application, when executed by the computing device, is configured to cause the computing device to at least:
 recommend host system power-on of a standby host system when there is a host system in a server cluster of host systems in which utilization is above a target utilization, wherein:
 recommending the host system power-on includes calculating an impact of powering on the standby host system with respect to reducing the number of highly-utilized host systems in the server cluster, the impact of powering on being calculated by simulating moving at least one virtual machine from at least one highly utilized host system to the standby host system being recommended to be powered-on; and 
 calculating the impact of powering on the standby host system comprises calculating an amount by which the utilization of a plurality of host systems in the server cluster exceeds the target utilization. 
 
   
     
     
         17 . The system of  claim 16 , wherein the application causes the computing device to at least:
 determine the utilization of each host system in the server cluster as a ratio of demand to capacity for that host system.   
     
     
         18 . The system of  claim 16 , wherein recommending the host system power-on comprises including iterating through standby host systems, and for each respective standby host system, invoking a software module supporting virtual machine resource constraints and quantifying an impact of powering on the respective standby host system. 
     
     
         19 . The system of  claim 16 , wherein calculating the impact is repeated for each standby host system in the server cluster to determine whether the standby host system should be recommended to be powered-on. 
     
     
         20 . The system of  claim 16 , wherein the application causes the computing device to at least:
 calculate an impact of powering off a host system within the server cluster by calculating an amount by which the utilization of a plurality of host systems in the server cluster is below the target utilization.   
     
     
         21 . The system of  claim 16 , wherein calculating the impact of powering off is repeated for each powered-on host system in the server cluster to determine whether the powered-on host system should be recommended to be powered-off.