Systems and methods of balancing network load for ultra high server availability
AssigneeCoupang Corp.
InventorsZhan CHEN, Seong Hyun JEONG, Hyeong Gun LEE
Life of this patent
Estimating the term…
Abstract
Systems and methods for monitoring utilization rates of a plurality of network-connected databases; receiving a first data read request from a first user device for a data element stored in the plurality of network-connected databases; selecting a first target database among the plurality of network-connected databases based on the utilization rates and a load sharing ratios; generating a first data query for a copy of the data element stored in the first target database; and forwarding the copy of the data element from the first target database to the first user device in response to the first data read request.
Claims21
1-20. (canceled)
A computer-implemented system for routing network traffic, the system comprising:
- a memory storing instructions;
- and
- at least one processor configured to execute the instructions for:
- monitoring a utilization rate of one or more databases;
- receiving a query;
- determining a load sharing ratio based on at least one of a status of the one or more databases, an amount of time the one or more databases have been available, one or more attributes of the one or more databases, an anticipated network load, a number of available databases of the one or more databases, or an input;
- selecting a target database from the one or more databases based on the utilization rate and the load sharing ratio;
- retrieving data from the target database associated with the query;
- and
- transmitting the retrieved data to a user device.
A computer-implemented method for routing network traffic, the method comprising:
- monitoring a utilization rate of one or more databases;
- receiving a query;
- determining a load sharing ratio based on at least one of a status of the one or more databases, an amount of time the one or more databases have been available, one or more attributes of the one or more databases, an anticipated network load, a number of available databases of the one or more databases, or an input;
- selecting a target database from the one or more databases based on the utilization rate and the load sharing ratio;
- retrieving data from the target database associated with the query;
- and
- transmitting the retrieved data to a user device.
Dependencies are inferred from the claim text.