Semi-hierarchical system and method for administration of clusters of computer resources

Abstract

A method for managing clustered computer resources, and particularly very large scale clusters of computer resources by a semi-hierarchical n level, n+1 tier approach. Controller resources and controlled resources exist at different hardware levels. The top level consists of controller nodes and a first tier is defined for at least part of the top level. At a last level, at which controlled nodes are found, a last tier is defined. Additional levels of controlled and controller resources may exist between the top and last levels. At least one logical intermediate tier is introduced between adjacent levels and comprises at least one proxy or set of proxy processes.

1 . A method for providing management of a system of scalable clusters of computer resources, wherein the computer resources comprises at least controlled and controller resources, comprising the steps of:
 providing at least one first level of controller resources;   providing at least one second level of controlled resources, wherein said at least one first said at least one second levels are different hardware levels; and   providing an intermediate tier comprising a logical grouping of nodes from more than one of said hardware levels and comprising at least one proxy set of processes representing the processes of clustered controller and controlled computer resources at the different hardware levels and acting as an interface between said controller and said controlled computer resources.   
   
   
       2 . The method of  claim 1  wherein said at least one proxy is provided in at least one of controller and controlled computer resources. 
   
   
       3 . The method of  claim 1  further comprising providing at least one proxy resource manager running on at least one controller resource. 
   
   
       4 . The method of  claim 4  wherein said at least one proxy manager is adapted to move from one controller resource to another controller resource. 
   
   
       5 . The method of  claim 3  further comprising at least one of said at least one proxy set of processes gathering event information from said controlled resources and providing event information to said at least one proxy manager. 
   
   
       6 . The method of  claim 3  further comprising at least one of said at least one proxy set of processes filtering said event information prior to providing filtered event information to said at least one proxy manager. 
   
   
       7 . A method for managing computer resources in a system comprising a first tier of computer resources comprising a plurality of controller resources, a last tier of computer resources comprising a plurality of controlled nodes, wherein said first tier and said last tier are different hardware levels from each other, and at least one intermediate tier comprising a logical grouping of nodes from said first and last tier and having at least one proxy set of processes representing the processes of clustered controller and controlled computer resources and acting as an interface between said controller and said controlled computer resources, said method comprising the steps of:
 at least one of said at least one proxy set of processes gathering event information from said plurality of controlled resources in said last tier;   at least one of said at least one proxy set of processes filtering said event information; and   at least one of said at least one proxy set of processes providing filtered event information to at least one of said plurality of controller resources in said first tier.   
   
   
       8 . The method of  claim 7  further comprising said at least one of said plurality of controller resources managing said plurality of controlled resources in response to said filtered event information. 
   
   
       9 . The method of  claim 8  wherein said managing comprises performing predictive analysis. 
   
   
       10 . A method for providing management of scalable clusters of computer resources, including controlled and controller resources, comprising the steps of:
 providing n different hardware levels of computer resources wherein a first level comprises controller resources and a last level comprises at least one cluster of controlled resources;   providing n+1 logical tiers wherein a first tier comprises said first level, a last tier comprises said last level, and an intermediate tier comprising resources from more than one hardware level of resources and comprises at least one proxy comprising at least one process for representing cluster resources; and   providing at least one proxy manager.   
   
   
       11 . The method of  claim 10  wherein said proxy runs on at least one of a controller resource and a controlled resource. 
   
   
       12 . The method of  claim 10  wherein at least one proxy resource manager runs on at least one controller resource. 
   
   
       13 . The method of  claim 12  wherein said at least one proxy manager can move from one controller resource to another controller resource. 
   
   
       14 . The method of  claim 12  further comprising said at least one proxy gathering event information from said controlled resources at said last level and providing event information to said at least one proxy manager. 
   
   
       15 . The method of  claim 14  further comprising said at least one proxy filtering event information.