Automatic reassignment of tasks to different virtual machines

Abstract

The disclosed embodiments relate to a system for monitoring a virtual-machine environment. During operation, the system assigns a task, corresponding with a task request, to a first virtual machine. The performance of the task at the first virtual machine is monitored. Based on the monitoring, it is determined whether the performance of the task at the first virtual machine is unsatisfactory. If so, the task is automatically reassigned to a second virtual machine.

What is claimed is: 
     
         1 . A computer-implemented method for dynamically monitoring performance of a computing environment, comprising:
 assigning a task to a first virtual machine, the task corresponding with a task request;   monitoring performance of the task at the first virtual machine;   based on the monitoring, determining that the performance of the task at the first virtual machine is unsatisfactory; and   automatically reassigning the task to a second virtual machine.   
     
     
         2 . The computer-implemented method of  claim 1  further comprising authenticating a user. 
     
     
         3 . The computer-implemented method of  claim 1  further comprising detecting the task request as a new task request from a user. 
     
     
         4 . The computer-implemented method of  claim 1  further comprising prioritizing the task request. 
     
     
         5 . The computer-implemented method of  claim 1  further comprising prioritizing the task request based on a characteristic of a user, a characteristic of the task, a system load, or when the task request was received. 
     
     
         6 . The computer-implemented method of  claim 1  further comprising prioritizing the task request, wherein prioritizing the task includes generating a score and assigning a priority class or ranking based on the score. 
     
     
         7 . The computer-implemented method of  claim 1  further comprising obtaining the task request and placing a queue item identifying the task in a queue. 
     
     
         8 . The computer-implemented method of  claim 1  further comprising obtaining the task request and placing a queue item identifying the task in a queue, wherein a priority of the task is reflected within the queue, reflected based on the queue item's placement within a ranking, or is reflected by a priority indicator associated with the queue item. 
     
     
         9 . The computer-implemented method of  claim 1  further comprising monitoring loads of a plurality of virtual machines, including detecting characteristics of tasks being processed. 
     
     
         10 . The computer-implemented method of  claim 1  further comprising monitoring loads of a plurality of virtual machines, including detecting characteristics of tasks being processed, wherein the characteristics include resource requirements, current total processing times, and/or users submitting tasks. 
     
     
         11 . The computer-implemented method of  claim 1  further comprising selecting the task from a queue, wherein the selection is based on the task having a sufficiently high priority as compared to other tasks in the queue. 
     
     
         12 . The computer-implemented method of  claim 1  further comprising selecting the task from a queue, wherein the selection is based on the identifying available resources to process the task. 
     
     
         13 . The computer-implemented method of  claim 1 , wherein the first virtual machine to which the task is assigned is based on the first virtual machine having sufficient available resources to process the task. 
     
     
         14 . The computer-implemented method of  claim 1 , wherein the task is assigned to a host or a host cluster associated with the first virtual machine. 
     
     
         15 . The computer-implemented method of  claim 1 , wherein monitoring performance of the task at the first virtual machine comprises detecting whether the first virtual machine has not completed the task within a threshold duration of time, detecting how much of the first virtual machine's processing power and/or memory is being consumed by the performance of the task, determining whether any errors occur in association with the performance of the task, or a combination thereof. 
     
     
         16 . The computer-implemented method of  claim 1 , wherein determining that the performance is unsatisfactory is based on exceeding a threshold of the first virtual machine resources, exceeding a threshold of processing time of the task, and/or exceeding a threshold of errors. 
     
     
         17 . The computer-implemented method of  claim 1 , wherein automatically reassigning the task to the second virtual machine comprises selecting the second virtual machine based on the second virtual machine having more resources than the first virtual machine, the second virtual machine being in a large host-clustering network than the first virtual machine, and/or the second virtual machine currently processing a fewer number of tasks compared to a number of tasks being processed by the first virtual machine. 
     
     
         18 . A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method, the method comprising:
 assigning a task to a first virtual machine, the task corresponding with a task request;   monitoring performance of the task at the first virtual machine;   based on the monitoring, determining that the performance of the task at the first virtual machine is unsatisfactory; and   automatically reassigning the task to a second virtual machine.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 19 , wherein automatically reassigning the task to the second virtual machine comprises selecting the second virtual machine based on the second virtual machine having more resources than the first virtual machine, the second virtual machine being in a large host-clustering network than the first virtual machine, and/or the second virtual machine currently processing a fewer number of tasks compared to a number of tasks being processed by the first virtual machine. 
     
     
         20 . A system comprising:
 one or more data processors; and   a non-transitory computer readable storage medium containing instructions which when executed on the one or more processors, cause the one or more processors to perform actions including:   assigning a task to a first virtual machine, the task corresponding with a task request;   monitoring performance of the task at the first virtual machine;   based on the monitoring, determining that the performance of the task at the first virtual machine is unsatisfactory; and   automatically reassigning the task to a second virtual machine.