Routable application partitioning

Abstract

An apparatus, system, and storage medium that in an embodiment determine the active partitions of an application and assign the active partitions among servers via a routing table. The routing table is sent to a client, who uses the routing table to send requests and/or messages to the active partitions. In an embodiment, the routing table includes identifiers of the active partitions and the associated partitions. If one of the servers fails or if the partitions have a loading imbalance, the partitions are reassigned via the routing table.

1 . An apparatus comprising:
 means for determining a plurality of active partitions of an application;   means for assigning the plurality of active partitions to a plurality of servers via a routing table, wherein the means for assigning further comprises means for setting identifiers of the active partitions and the associated plurality of servers in the routing table;   means for sending the routing table to a client, wherein the client desires to send requests to the active partitions via the routing table;   means for determining whether the routing table is stale;   means for instructing the client to wait if the routing table is stale; and   means for creating virtual queues for the active partitions, wherein the virtual queues are to receive messages from the client.   
   
   
       2 . The apparatus of  claim 1 , further comprising:
 means for reassigning one of the plurality of active partitions if one of the plurality of servers has failed.   
   
   
       3 . The apparatus of  claim 1 , further comprising:
 means for reassigning one of the plurality of active partitions if the plurality of active partitions have a loading imbalance.   
   
   
       4 . The apparatus of  claim 3 , wherein the means for reassigning further comprises:
 means for deactivating the one of the plurality of active partitions on a loaded server.   
   
   
       5 . The apparatus of  claim 4 , wherein the means for reassigning further comprises:
 means for removing the loaded server from an entry in the routing table that is associated with the one of the plurality of the active partitions.   
   
   
       6 . The apparatus of  claim 4 , wherein the means for reassigning further comprises:
 means for activating the one of the plurality of active partitions on a different server.   
   
   
       7 . A storage medium encoded with instructions, wherein the instructions when executed comprise:
 determining a plurality of active partitions of an application;   assigning the plurality of active partitions to a plurality of servers via a routing table, wherein the assigning further comprises setting identifiers of the active partitions and the associated plurality of servers in the routing table;   sending the routing table to a client, wherein the client desires to send requests to the active partitions via the routing table;   determining whether the routing table is stale;   instructing the client to wait if the routing table is stale; and   creating virtual queues for the active partitions, wherein the virtual queues are to receive messages from the client.   
   
   
       8 . The storage medium of  claim 7 , further comprising:
 reassigning one of the plurality of active partitions if one of the plurality of servers has failed.   
   
   
       9 . The storage medium of  claim 7 , further comprising:
 reassigning one of the plurality of active partitions if the plurality of active partitions have a loading imbalance.   
   
   
       10 . The storage medium of  claim 9 , wherein the reassigning further comprises:
 deactivating the one of the plurality of active partitions on a loaded server.   
   
   
       11 . The storage medium of  claim 10 , wherein the reassigning further comprises:
 removing the loaded server from an entry in the routing table that is associated with the one of the plurality of the active partitions.   
   
   
       12 . The storage medium of  claim 10 , wherein the reassigning further comprises:
 activating the one of the plurality of active partitions on a different server.   
   
   
       13 . A computer system comprising:
 a processor; and   memory encoded with instructions, wherein the instructions when executed on the processor comprise:
 determining a plurality of active partitions of an application, 
 assigning the plurality of active partitions to a plurality of servers via a routing table, wherein the assigning further comprises setting identifiers of the active partitions and the associated plurality of servers in the routing table, 
 sending the routing table to a client, wherein the client desires to send requests to the active partitions via the routing table, 
 determining whether the routing table is stale, 
 instructing the client to wait if the routing table is stale, and 
 creating virtual queues for the active partitions, wherein the virtual queues are to receive messages from the client. 
   
   
   
       14 . The computer system of  claim 13 , wherein the instructions further comprise:
 reassigning at least one of the plurality of active partitions if one of the plurality of servers has failed.   
   
   
       15 . The computer system of  claim 13 , wherein the instructions further comprise:
 reassigning one of the plurality of active partitions if the plurality of active partitions have a loading imbalance.   
   
   
       16 . The computer system of  claim 15 , wherein the reassigning further comprises:
 deactivating the one of the plurality of active partitions on a loaded server.   
   
   
       17 . The computer system of  claim 16 , wherein the reassigning further comprises:
 removing the loaded server from an entry in the routing table that is associated with the one of the plurality of the active partitions.   
   
   
       18 . The computer system of  claim 16 , wherein the reassigning further comprises:
 activating the one of the plurality of active partitions on a different server.   
   
   
       19 . The computer system of  claim 16 , wherein the determining whether the routing table is stale further comprises:
 determining whether the routing table is stale in response to the requests from the clients.   
   
   
       20 . The computer system of  claim 19 , wherein the client waits for the entries in the routing table that are associated with the active partitions to change if the routing table is stale.