Low-latency high-throughput scalable data caching

A method comprising:

• receiving, by a load balancer service, a first request from a client device based on the client device being located in a first geolocation in close proximity to a second geolocation of a first data source, wherein the first data source is connected to a first data cache located in a same geographical region as the first data source over a network and the first data source stores a plurality of data entries selected based on the second geolocation;
• requesting, by the load balancer service, a first data entry associated with the first request from a data cache service, wherein the first data entry is available from a master data source connected to the first data source over the network;
• determining, by the data cache service, that the first data entry is unavailable in both the first data cache and the first data source;
• and
• responsive to determining that the first data entry is unavailable, rejecting, by the load balancer service, the first request, wherein the first data source retrieves the first data entry from the master data source after the first request is rejected.

A computer-readable non-transitory storage medium storing executable instructions, which when executed by a computer system, cause the computer system to:

• receive, by a load balancer service, a first request from a client device based on the client device being located in a first geolocation in close proximity to a second geolocation of a first data source, wherein the first data source is connected to a first data cache located in a same geographical region as the first data source over a network and the first data source stores a plurality of data entries selected based on the second geolocation;
• request, by the load balancer service, a first data entry associated with the first request from a data cache service, wherein the first data entry is available from a master data source connected to the first data source over the network;
• determine, by the data cache service, that the first data entry is unavailable in both the first data cache and the first data source;
• and
• responsive to determining that the first data entry is unavailable, reject, by the load balancer service, the first request, wherein the first data source retrieves the first data entry from the master data source after the first request is rejected.