Integrated procedure for partitioning network data services among multiple subscribers

Abstract

A method and apparatus for partitioning network data services among multiple subscribers uses information stored in several tables to define a plurality of independent networks where each independent network comprises a set of access ports and a unique set of destination addresses and is logically separate from all other independent networks so that no information can pass from one independent network to another independent network. When a subscriber makes a request to use an independent network, a subscriber key that is based on the subscriber identity and the network access port is used to determine whether the subscriber has permission to use the independent network. If the subscriber has permission to use the independent network, information retrieved from the tables is used to determine whether the source subscriber or a destination subscriber has control over the resource. If a destination subscriber has control over the resource, using information in the request to identify a destination subscriber and a response port; and if the source subscriber has control over the resource, using the identity to determine whether the source subscriber can access the resource.

1 . A method for partitioning network data services among multiple subscribers, each of whom makes requests to selectively access a plurality of data services, the method comprising: 
 (a) defining at least one session for each of the multiple subscribers, during which session requests from the each subscriber can be generated;    (b) assigning to each session a throughput metric that measures quality of service;    (c) assigning at least one active session list and one inactive list to each of the multiple subscribers and placing sessions defined for each subscriber on the active session list assigned to that subscriber; and    (d) ordering the active session lists from a first list to a last list and servicing pending requests in sessions in the first active session list.    
   
   
       2 . The method of  claim 1  wherein step (a) comprises opening a session for one of the multiple subscribers when the one subscriber generates a request and closing the session when no further requests are generated.  
   
   
       3 . The method of  claim 1  wherein step (a) comprises assigning each session to a session group defined by a set of resources used by the each session.  
   
   
       4 . The method of  claim 3  wherein step (d) comprises checking the session group prior to servicing pending requests in the each session to determine whether the resources assigned to the each session group have reached capacity and bypassing the session when the set of resources has reached capacity.  
   
   
       5 . The method of  claim 1  wherein step (b) comprises assigning to each session a throughput metric that is related to a fraction of the currently available throughput capacity that is allocated to the each session.  
   
   
       6 . The method of  claim 5  wherein an application responds to a request for service by returning an estimate of the resource capacity that will be necessary to respond to the request and wherein step (b) comprises adjusting the throughput metric based on the estimate.  
   
   
       7 . The method of  claim 6  further comprising (e) selecting the next eligible subscriber for servicing requests when a throughput adjustment results in a subscriber exceeding an allocated capacity.  
   
   
       8 . The method of  claim 1  wherein step (d) comprises servicing pending requests in an active session on the first active session list until the throughput consumed by all requests serviced is estimated to exceed a predetermined amount of allocated capacity or all requests have been serviced.  
   
   
       9 . The method of  claim 8  wherein step (d) further comprises removing the active session from the first active session list and placing the active session on another session list when the throughput consumed by all requests serviced is estimated to exceed a predetermined amount of capacity allocated to the active session.  
   
   
       10 . The method of  claim 8  wherein step (d) further comprises removing the active session from the first active session list and placing the active session on the inactive list when all requests have been serviced.  
   
   
       11 . Apparatus for partitioning network data services among multiple subscribers, each of whom makes requests to selectively access a plurality of data services, the method comprising: 
 means for defining at least one session for each of the multiple subscribers, during which session requests from the each subscriber can be generated;    means for assigning to each session a throughput metric that measures quality of service;    means for assigning at least one active session list and one inactive list to each of the multiple subscribers and placing sessions defined for each subscriber on the active session list assigned to that subscriber; and    means for ordering the active session lists from a first list to a last list and servicing pending requests in sessions in the first active session list.    
   
   
       12 . The apparatus of  claim 11  wherein the means for defining at least one session comprises means for opening a session for one of the multiple subscribers when the one subscriber generates a request and means for closing the session when no further requests are generated.  
   
   
       13 . The apparatus of  claim 11  wherein the means for defining comprises means for assigning each session to a session group defined by a set of resources used by the each session.  
   
   
       14 . The apparatus of  claim 13  wherein the means for ordering the active session lists comprises means for checking the session group prior to servicing pending requests in the each session to determine whether the resources assigned to the each session group have reached capacity and means for bypassing the session when the set of resources has reached capacity.  
   
   
       15 . The apparatus of  claim 11  wherein the means for assigning to each session a throughput metric comprises means for assigning to each session a throughput metric that is related to a fraction of the currently available throughput capacity that is allocated to the each session.  
   
   
       16 . The apparatus of  claim 15  wherein an application responds to a request for service by returning an estimate of the resource capacity that will be necessary to respond to the request and wherein the means for assigning to each session a throughput metric comprises means for adjusting the throughput metric based on the estimate.  
   
   
       17 . The apparatus of  claim 16  further comprising means for selecting the next eligible subscriber for servicing requests when a throughput adjustment results in a subscriber exceeding an allocated capacity.  
   
   
       18 . The apparatus of  claim 11  wherein the means for ordering the active session lists comprises means for servicing pending requests in an active session on the first active session list until the throughput consumed by all requests serviced is estimated to exceed a predetermined amount of allocated capacity or all requests have been serviced.  
   
   
       19 . The apparatus of  claim 18  wherein the means for ordering the active session lists further comprises means for removing the active session from the first active session list and means for placing the active session on another session list when the throughput consumed by all requests serviced is estimated to exceed a predetermined amount of capacity allocated to the active session.  
   
   
       20 . The apparatus of  claim 18  wherein the means for ordering the active session lists further comprises means for removing the active session from the first active session list and means for placing the active session on the inactive list when all requests have been serviced.  
   
   
       21 . A computer program product for partitioning network data services among multiple subscribers, each of whom makes requests to selectively access a plurality of data services, the computer program product comprising a computer usable medium having computer readable program code thereon, including: 
 program code for defining at least one session for each of the multiple subscribers, during which session requests from the each subscriber can be generated;    program code for assigning to each session a throughput metric that measures quality of service;    program code for assigning at least one active session list and one inactive list to each of the multiple subscribers and placing sessions defined for each subscriber on the active session list assigned to that subscriber; and    program code for ordering the active session lists from a first list to a last list and servicing pending requests in sessions in the first active session list.