Method and a scheduler for controlling when a server provides service with rate control to an entity
AssigneeFORE Systems, Inc.
InventorJon C. R. Bennett
Life of this patent
Estimating the term…
Abstract
A method for scheduling when a server provides service to entities. The method includes the steps of identifying when a first entity requests service from the server. Next there is the step of providing service to an entity, such as a first entity or a second entity, as a function of virtual time. A scheduler for controlling when a server provides service to entities. The scheduler comprises a memory having times which are a function of when entities request service from the server. The scheduler is also comprised of a virtual clock that keeps track of time. The scheduler is also comprised of a controller which causes an entity to receive service from the server as a function of virtual time. Rate can also be utilized.
Claims19
A scheduler for controlling when N entities, where N is an integer .gtoreq.2, are operated upon by a server, each entity having a rate at which it is to receive service from the server, at least two entities having different rates, all rates of the entities total<1, comprising:
- a starting time memory having arrival times s.sub.i of the N entities, where 2.ltoreq.i<N and is an integer, and s.sub.i corresponds to the time the i'th entity first requests service from the server;
- a finishing time memory having finishing times f.sub.i of the N entities, where f.sub.i corresponds to the time the i'th entity is to be operated upon by the server;
- a virtual clock that keeps track of virtual time so the arrival times s.sub.i and finishing times f.sub.i can be identified, said virtual clock increments virtual time as a function of time regardless of any other considerations;
- and
- a controller which chooses entities to be operated upon by the server so the server provides service at an established rate with rate control, and no faster, in the order of the entities with an earliest finishing time f.sub.i and an arrival time s.sub.i being operated upon first, and then the entities with the earliest or latest starting time s.sub.i or having the highest or lowest id or rate if their finishing times are the same being operated upon next at each given time, with entities able to be operated upon by the server before their finishing time f.sub.i, else if there is no entity with an arrival time less than or equal to virtual time, the server does not provide service to any entity.
A method of scheduling when a server provides service to entities comprising the steps of:
- requesting service from the server by N entities, where N.gtoreq.1 and is an integer;
- storing when each of the N entities first requests service from the server and when each of the N entities is to have received service from the server;
- and
- providing an entity of the N entities service which has the earliest receiving time and a request time, unless there is more than one entity with the earliest receiving time in which case the entity with the earliest request time is provided service by the server and possibly before its finishing time;
- unless there is no entity with a request time less than or equal to virtual time, in which case the server does not provide service to an entity.
A scheduler for controlling when N entities, where N is an integer .gtoreq.2, are operated upon by a server, each entity having a rate at which it is to receive service from the server, at least two entities having different rates, all rates of the entities total .ltoreq.1, comprising:
- a starting time memory having starting times s.sub.i of the N entities, where 2.ltoreq.i<N and is an integer, and s.sub.i corresponds to the time the i'th entity first requests to be operated upon by the server;
- a finishing time memory having finishing times f.sub.i of the N entities, where f.sub.i corresponds to the time the i'th entity is to have been operated upon by the server;
- a virtual clock that keeps track of virtual time so present virtual time, arrival times s.sub.i and finishing times f.sub.i can be identified;
- and
- a controller which chooses entities to be operated upon by the server so the server provides service at an established rate with rate control, and no faster, in the order of the entity with an earliest finishing time f.sub.i and a starting time s.sub.i being operated upon first, and then the entities based on a predetermined criteria, said controller causing the virtual clock to increment present virtual time by a unit of virtual time after a predetermined period of time regardless of any other considerations.
A scheduler for scheduling when N entities, where N is an integer .gtoreq.1 are served by a server comprising:
- a starting time memory having starting times s.sub.i when the N entities request service, where 1.ltoreq.i.ltoreq.N and is an integer, and s.sub.i is the time at which the i'th entity may next get service from the server;
- a finishing time memory having finishing times f.sub.i when the N entities should be serviced, where f.sub.i is the time by which the i'th entity should be serviced by the server;
- a virtual clock that keeps track of time V.sub.k where k.gtoreq.0 and is an integer and
- V.sub.k =V.sub.k-1 +1
- where V.sub.k-1 is the virtual time when the server last served an entity;
- and
- a controller which chooses which entity is to be operated upon by the server in the order of the entity with an earliest finishing time f.sub.i and a start time s.sub.i receiving service first, and then the entities based on a predetermined criteria unless there is no entity with a starting time s.sub.i less than or equal to virtual time, in which case the server is idle.
A scheduler for controlling when a server provides service to entities, each entity having a rate at which it is to receive service from the server, at least two entities having different rates, all rates of the entities total .ltoreq.1, comprising:
- a memory having times which are a function of when entities request service from the server;
- a virtual clock that keeps track of virtual time as a function of a predetermined period of time if there is no service provided to an entity;
- and
- a controller which causes an entity to receive service from the server as a function of virtual time regardless of any other considerations so the server provides service at an established rate with rate control, and no faster.
A method for scheduling when a server provides service to entities comprising the steps of:
- identifying when entities request service from the server, where each entity has a rate at which it is to receive service from the server, at least two entities having different rates, all rates total .ltoreq.1;
- providing service to all the entities as a function of virtual time;
- and
- incrementing virtual time by one unit of virtual time or after a predetermined period of time if there is no service provided to an entity regardless of any other considerations so the server provides service at an established rate with rate control, and no faster.
A scheduler for controlling when N entities, where N is an integer .gtoreq.2, are operated upon by a server, each entity having a rate at which it is to receive service from the server, at least two entities having different rates, all rates of the entities total .ltoreq.1 comprising:
- a memory mechanism having arrival times s.sub.i of the N entities, where 2.ltoreq.i<N and is an integer, and s.sub.i corresponds to the time the i'th entity first requests service from the server and finishing times f.sub.i of the N entities, where f.sub.i corresponds to the time the i'th entity is to be operated upon by the server;
- a virtual clock that keeps track of virtual time so the arrival times s.sub.i and finishing times f.sub.i can be identified, said virtual clock increments virtual time as a function of time regardless of any other considerations;
- and
- a controller which chooses entities to be operated upon by the server so the server provides service at an established rate with rate control, and no faster, in the order of the entities with an earliest finishing time f.sub.i and an arrival time s.sub.i being operated upon first, and then the entities with the earliest or latest starting time s.sub.i or having the highest or lowest id or rate if their finishing times are the same being operated upon next at each given time, with entities able to be operated upon by the server before their finishing time f.sub.i, else if there is no entity with an arrival time less than or equal to virtual time, the server does not provide service to any entity.
A scheduler for controlling when N entities, where N is an integer .gtoreq.2, are operated upon by a server, each entity having a rate at which it is to receive service from the server, at least two entities having different rates, all rates of the entities total .ltoreq.1, comprising:
- a memory mechanism having arrival times s.sub.i of the N entities, where 2.ltoreq.i<N and is an integer, and s.sub.i corresponds to the time the i'th entity first requests service from the server and finishing times f.sub.i of the N entities, where f.sub.i corresponds to the time the i'th entity is to be operated upon by the server;
- a virtual clock that keeps track of virtual time so the arrival times s.sub.i and finishing times f.sub.i can be identified, said virtual clock increments virtual time as a function of time;
- and
- a controller which chooses entities to be operated upon by the server so the server provides service at an established rate with rate control, and no faster, in the order of the entities with an earliest finishing time f.sub.i and an arrival time s.sub.i being operated upon first, and then the entities with the earliest or latest starting time s.sub.i or having the highest or lowest id or rate if their finishing times are the same being operated upon next at each given time, with entities able to be operated upon by the server before their finishing time f.sub.i, else if there is no entity with an arrival time less than or equal to virtual time, the server does not provide service to any entity.
A scheduler for controlling when N entities, where N is an integer .gtoreq.2, are operated upon by a server, each entity having a rate at which it is to receive service from the server, at least two entities having different rates, all rates of the entities total .ltoreq.1, comprising:
- a starting time memory having arrival times s.sub.i of the N entities, where 2.ltoreq.i<N and is an integer, and s.sub.i corresponds to the time the i'th entity first requests service from the server;
- a finishing time memory having finishing times f.sub.i of the N entities, where f.sub.i corresponds to the time the i'th entity is to be operated upon by the server;
- a virtual clock that keeps track of virtual time so the arrival times s.sub.i and finishing times f.sub.i can be identified;
- and
- a controller which chooses entities to be operated upon by the server so the server provides service at an established rate with rate control, and no faster, in the order of the entities with an earliest finishing time f.sub.i and an arrival time s.sub.i being operated upon first, and then the entities with the earliest or latest starting time s.sub.i or having the highest or lowest id or rate if their finishing times are the same being operated upon next at each given time, with entities able to be operated upon by the server before their finishing time f.sub.i, else if there is no entity with an arrival time less than or equal to virtual time, the server does not provide service to any entity.
Dependencies are inferred from the claim text.