Cross-platform workload processing

Abstract

A system and technique for workload processing includes a scheduler operable to receive a request to process a workload where the workload includes data and an associated process, and determine a type of the workload. Historical execution statistics are accessed associated with previous processing requests for the determined type of the workload. A determination is made whether the data of the workload and the process of the workload are available, and if so, a determination is made as to resource availability on a computing platform for processing the workload. If sufficient resources are available to process the workload based on the historical execution statistics for the type of the workload, processing of the workload is initiated on the computing platform.

What is claimed is: 
     
         1 . A system, comprising:
 a host having a processor unit and a memory; and   a scheduler executable by the processor unit to:
 receive a request to process a workload, the workload including data and an associated process; 
 determine a type of the workload; 
 access historical processing data to determine historical execution statistics associated with previous processing requests for the determined type of the workload; 
 determine whether the data of the workload is available for processing; 
 in response to determining that the data is available for processing, determine whether the process of the workload is available; 
 in response to determining that the process is available, determine resource availability on a computing platform for processing the workload; 
 determine whether the resources available on the computing platform are sufficient to process the workload based on the historical execution statistics for the type of the workload; and 
 in response to determining that the resources available on the computing platform are sufficient to process the workload based on the historical execution statistics, initiate processing of the workload on the computing platform. 
   
     
     
         2 . The system of  claim 1 , wherein the scheduler is operable to:
 determine workload processing statistics of the workload processing; and   update the execution statistics with the workload processing statistics.   
     
     
         3 . The system of  claim 1 , wherein the scheduler is operable to:
 access a set of rules indicating resource utilization for a plurality of different types of workloads; and   determine the resource utilization from the rules for processing the workload.   
     
     
         4 . The system of  claim 1 , wherein the scheduler is operable to determine execution statistics for a same data type as the data of the workload. 
     
     
         5 . The system of  claim 1 , wherein the scheduler is operable to determine data throughput statistics for a same type of data as the data of the workload. 
     
     
         6 . The system of  claim 1 , wherein the scheduler is operable to:
 determine a first workload process for the workload, the first workload process processing the data from a first state to a second state;   automatically initiate the first workload process on a first computing platform in response to the data in the first state being available to the first computing platform;   determine a second workload process for the workload, the second workload process processing the data from the second state to a third state; and   automatically initiate the second workload process on a second computing platform in response to the data in the second state being available to the second computing platform.   
     
     
         7 . The system of  claim 1 , wherein the scheduler is operable to access a set of rules to determine a priority of the workload relative to other workloads for processing on the computing platform. 
     
     
         8 . The system of  claim 1 , further comprising, in response to determining that the data and the process of the workload are available, placing the data and the process each in a respective input queue. 
     
     
         9 . The system of  claim 1 , wherein the historical execution statistics include a throughput time value for the type of the workload. 
     
     
         10 . A computer program product for cross-platform workload processing, the computer program product comprising:
 a non-transitory computer readable medium having computer readable program code embodied therewith, the computer readable program code comprising computer readable program code configured to:
 receive a request to process a workload, the workload including data and an associated process; 
 determine a type of the workload; 
 access historical processing data to determine historical execution statistics associated with previous processing requests for the determined type of the workload; 
 determine whether the data of the workload is available for processing; 
 in response to determining that the data is available for processing, determine whether the process of the workload is available; 
 in response to determining that the process is available, determine resource availability on a computing platform for processing the workload; 
 determine whether the resources available on the computing platform are sufficient to process the workload based on the historical execution statistics; and 
 in response to determining that the resources available on the computing platform are sufficient to process the workload based on the historical execution statistics, initiate processing of the workload on the computing platform. 
   
     
     
         11 . The computer program product of  claim 10 , wherein the computer readable program code is configured to:
 determine workload processing statistics of the workload processing; and   update the execution statistics with the workload processing statistics.   
     
     
         12 . The computer program product of  claim 10 , wherein the computer readable program code is configured to:
 access a set of rules indicating resource utilization for a plurality of different types of workloads; and   determine the resource utilization from the rules for processing the workload.   
     
     
         13 . The computer program product of  claim 10 , wherein the computer readable program code is configured to determine execution statistics for a same data type as the data of the workload. 
     
     
         14 . The computer program product of  claim 10 , wherein the computer readable program code is configured to determine data throughput statistics for a same type of data as the data of the workload. 
     
     
         15 . The computer program product of  claim 10 , wherein the computer readable program code is configured to:
 determine a first workload process for the workload, the first workload process processing the data from a first state to a second state;   automatically initiate the first workload process on a first computing platform in response to the data in the first state being available to the first computing platform;   determine a second workload process for the workload, the second workload process processing the data from the second state to a third state; and   automatically initiate the second workload process on a second computing platform in response to the data in the second state being available to the second computing platform.   
     
     
         16 . The computer program product of  claim 10 , wherein the computer readable program code is configured to, in response to determining that the data and the process of the workload are available, place the data and the process each in a respective input queue. 
     
     
         17 . The computer program product of  claim 10 , wherein the computer readable program code is configured to access the historical execution statistics to determine a throughput time value for the type of the workload. 
     
     
         18 . A system, comprising:
 a computing platform having a processor unit and a memory; and   a scheduler executable to:
 receive a request to process a workload; 
 access historical execution statistics associated with previous processing requests for a same type of workload processing; 
 determine, from the statistics, that processing the workload includes a plurality of sequentially related processing events; 
 determine, from a first input location, whether a first data and a first process associated with a first processing event of the plurality of processing events is available; 
 in response to determining that the first data and the first process are available, determine resource availability on the computing platform for executing the first processing event; 
 in response to determining sufficient resource availability on the computing platform to execute the first processing event, initiate execution of the first processing event; 
 determine, from a second input location, whether a second data resulting from the first processing event and a second process associated with a second processing event of the plurality of processing events is available; 
 in response to determining that the second data and the second process are available, determine resource availability on the computing platform for executing the second processing event; and 
 in response to determining sufficient resource availability on the computing platform to execute the second processing event, initiate execution of the second processing event. 
   
     
     
         19 . The system of  claim 18 , wherein the scheduler is executable to determine resource availability on the computing platform based on an observation of current workload processing levels of the computing platform. 
     
     
         20 . The system of  claim 18 , wherein the scheduler is executable to:
 determine that a third data is needed for the second processing event;   determine, from a third input location, whether the third data is available;   in response to determining that the second data, the third data, and the second process are available, determine resource availability on the computing platform for executing the second processing event; and   in response to determining sufficient resource availability on the computing platform to execute the second processing event, initiate execution of the second processing event.