System and method for load balancing based on expected latency for use in media content or other environments
First Claim
1. A system for selection of servers based on expected latency, comprising:
- a computer including a processor and memory;
an access point that operates on the computer as a load balancer to provide access to a plurality of servers, for use in processing requests at the plurality of servers;
an expected latency selection component, that is used by the access point to determine a distribution of the requests to the plurality of servers, based on a determination of expected latency at the plurality of servers, wherein the expected latency is determined based on measurement, for each server of the plurality of servers able to receive requests from the access point, data indicative of success latency, success rate, amount of outstanding requests, and failure latency for that server;
wherein each server of the plurality of servers is associated with an endpoint at which that server receives requests from the access point; and
whereupon the access point receiving a particular request for data, the determination of expected latency at the plurality of servers is used to determine a particular endpoint associated with a particular server to direct the particular request.
1 Assignment
0 Petitions
Accused Products
Abstract
In accordance with an embodiment, described herein is a system and method for load balancing of requests to servers based on expected latency, for use in the providing of media content or other types of data. The system comprises an access point, or other process or component, which operates as a load balancer in providing access to one or more servers, for use in processing requests at those servers. Each of the servers can be associated with an endpoint. An expected latency selection component can be used by the access point to determine how requests are distributed or load balanced to servers, based on a determination of expected latency at those servers. Upon the access point receiving a particular request, the determination of expected latency can be used to determine which endpoint or server to direct that particular request.
33 Citations
17 Claims
-
1. A system for selection of servers based on expected latency, comprising:
-
a computer including a processor and memory; an access point that operates on the computer as a load balancer to provide access to a plurality of servers, for use in processing requests at the plurality of servers; an expected latency selection component, that is used by the access point to determine a distribution of the requests to the plurality of servers, based on a determination of expected latency at the plurality of servers, wherein the expected latency is determined based on measurement, for each server of the plurality of servers able to receive requests from the access point, data indicative of success latency, success rate, amount of outstanding requests, and failure latency for that server; wherein each server of the plurality of servers is associated with an endpoint at which that server receives requests from the access point; and whereupon the access point receiving a particular request for data, the determination of expected latency at the plurality of servers is used to determine a particular endpoint associated with a particular server to direct the particular request. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method for selection of servers based on expected latency, comprising:
-
providing, at a computer including a processor and memory, an access point that operates on the computer as a load balancer in providing access to a plurality of servers, for use in processing requests at the plurality of servers, and an expected latency selection component, that is used by the access point to determine a distribution of the requests to the plurality of servers, based on a determination of expected latency at the plurality of servers, wherein the expected latency is determined based on measuring, for each server of the plurality of servers able to receive requests from the access point, data indicative of success latency, success rate, amount of outstanding requests, and failure latency for that server; associating each server of the plurality of servers with an endpoint at which that server receives requests from the access point; and upon receiving, at the access point, a particular request for data, determining according to the determination of expected latency at the plurality of servers, a particular endpoint associated with a particular server to direct the particular request. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A non-transitory computer readable storage medium, including instructions stored thereon which when read and executed by one or more computers cause the one or more computers to perform the steps comprising:
performing, at a computer including a processor and memory, a process which operates as a load balancer in providing access to a plurality of servers, for use in processing requests at the plurality of servers, and determines a distribution of the requests to the plurality of servers, based on a determination of expected latency at the plurality of servers, wherein the expected latency is determined based on measuring, for each server of the plurality of servers able to receive requests, data indicative of success latency, success rate, amount of outstanding requests, and failure latency for that server; associating each server of the plurality of servers with an endpoint at which that server receives requests; and upon receiving a particular request for data, determining according to the determination of expected latency at the plurality of servers, a particular endpoint associated with a particular server to direct the particular request. - View Dependent Claims (14, 15, 16, 17)
Specification