Core to resource mapping and resource to core mapping

Abstract

Core to resource and resource to core mapping is disclosed. In an embodiment, a method includes obtaining an input pattern including a plurality of resource identifiers corresponding to resources. The method further includes applying the input pattern to a guaranteed regular and uniform distribution process to obtain a distribution pattern that indicates a distribution of resources across cores or a distribution of the cores across the resources. The method further includes distributing the resources across the cores or distributing the cores across the resources according to the distribution pattern.

What is claimed is: 
     
         1 - 20 . (canceled) 
     
     
         21 . A method of distributing load across different processor cores of a computer that performs load balancing to distribute flows from clients to servers, the comprising:
 obtaining an input pattern including a plurality of identifiers corresponding to a plurality of servers;   generating, from the input pattern, a distribution pattern that identifies a distribution of flows from each core to a subset of servers that does not include all the plurality of servers; and   distributing, from the cores, the flows across the servers based on the identified distribution pattern.   
     
     
         22 . The method of  claim 21 , wherein the input pattern is a first pattern, and wherein generating the distribution pattern comprises:
 obtaining a second pattern by applying a stretch factor to the input pattern to replicate each server identifier a plurality of times;   obtaining a third pattern by applying a repeat factor to the second pattern, said third pattern including a plurality of instances of the second pattern;   partitioning the third pattern into a plurality of distribution sub-patterns each of which corresponds to a particular core and specifies a distribution of flows across the subset of servers associated with the particular core.   
     
     
         23 . The method of  claim 22  further comprising compressing a fourth pattern resulting from the partitioning of the third pattern to obtain the distribution pattern. 
     
     
         24 . The method of  claim 21 , wherein the input pattern includes only one identifier for each server in the plurality of servers. 
     
     
         25 . The method of  claim 21 , wherein the input pattern includes a plurality of instances of an identifier for at least one server in the plurality of servers, and includes different number instances of two identifiers for at least two servers in the plurality of servers. 
     
     
         26 . The method of  claim 21 , wherein the distribution pattern indicates a distribution of servers across cores. 
     
     
         27 . The method of  claim 21 , wherein the distribution pattern indicates a distribution of the cores across the server. 
     
     
         28 . The method of  claim 21 , wherein the distribution pattern includes a weight value for each server. 
     
     
         29 . The method of  claim 21 , wherein the distribution pattern assigns to each core only a subset of servers in order to decrease amount of resources consumed on the computer to maintain count of flows distributed to each server. 
     
     
         30 . The method of  claim 21 , wherein the input and distribution patterns account for at least one placeholder server for possible future addition of at least one server. 
     
     
         31 . A non-transitory machine readable medium storing a program for distributing load across different processor cores of a computer that performs load balancing to distribute flows from clients to servers, the program comprising sets of instructions for:
 obtaining an input pattern including a plurality of identifiers corresponding to a plurality of servers;   generating, from the input pattern, a distribution pattern that identifies a distribution of flows from each core to a subset of servers that does not include all the plurality of servers; and   distributing, from the cores, the flows across the servers based on the identified distribution pattern.   
     
     
         32 . The non-transitory machine readable medium of  claim 31 , wherein the input pattern is a first pattern, and wherein the set of instructions for generating the distribution pattern comprises the sets of instructions for:
 obtaining a second pattern by applying a stretch factor to the input pattern to replicate each server identifier a plurality of times;   obtaining a third pattern by applying a repeat factor to the second pattern, said third pattern including a plurality of instances of the second pattern;   partitioning the third pattern into a plurality of distribution sub-patterns each of which corresponds to a particular core and specifies a distribution of flows across the subset of servers associated with the particular core.   
     
     
         33 . The non-transitory machine readable medium of  claim 32 , wherein the program further comprises a set of instructions for compressing a fourth pattern resulting from the partitioning of the third pattern to obtain the distribution pattern. 
     
     
         34 . The non-transitory machine readable medium of  claim 31 , wherein the input pattern includes only one identifier for each server in the plurality of servers. 
     
     
         35 . The met non-transitory machine readable medium hod of  claim 31 , wherein the input pattern includes a plurality of instances of an identifier for at least one server in the plurality of servers, and includes different number instances of two identifiers for at least two servers in the plurality of servers. 
     
     
         36 . The non-transitory machine readable medium of  claim 31 , wherein the distribution pattern indicates a distribution of servers across cores. 
     
     
         37 . The non-transitory machine readable medium of  claim 31 , wherein the distribution pattern indicates a distribution of the cores across the server. 
     
     
         38 . The non-transitory machine readable medium of  claim 31 , wherein the distribution pattern includes a weight value for each server. 
     
     
         39 . The non-transitory machine readable medium of  claim 31 , wherein the distribution pattern assigns to each core only a subset of servers in order to decrease amount of resources consumed on the computer to maintain count of flows distributed to each server. 
     
     
         40 . The non-transitory machine readable medium of  claim 31 , wherein the input and distribution patterns account for at least one placeholder server for possible future addition of at least one server.