/Patent Tracker
AmazonGranted patentAI & softwareInterest 3/10

Amazon patents system to route data queries to the right server cluster

This patent describes a method for distributing data processing tasks across multiple groups of computers. The system estimates how much power a specific data request needs and tentatively assigns it to a cluster that likely has enough capacity. A leader node in that cluster then checks current conditions to confirm the task can be handled, or rejects it so another cluster can take over.

Why it mattersThis improves the efficiency of large-scale data centers by ensuring queries are sent to servers that are actually capable of handling them, reducing wasted processing power.

In the filing’s own words

A distributed computing system comprises a plurality of clusters of computing devices, including at least a first cluster with a first number of computing devices and a second cluster with a second number of computing devices. In response to receiving a request to process a query, the distributed computing system analyzes the query to generate an estimate of computing resources to be used when processing the query. The distributed computing system selects between the first and second cluster, based at least in part on the estimate, and tentatively assigns the query to the selected cluster for processing. The cluster to which the request is assigned determines if it has sufficient capacity to process the request.

What exactly they claim (claim 1)

1. A system, comprising: a plurality of clusters of computing devices, the plurality of clusters of computing devices comprising a first cluster and a second cluster, wherein the first cluster comprises a different number of computing devices than the second cluster; at least one processor; and at least one memory, the at least one memory comprising instructions that, in response to execution by the at least one processor, cause the system to at least: receive a request to process a query; obtain a first estimate of at least one computing resource that would be utilized by processing the query, based at least in part on first performance data received from the first cluster; determine to tentatively assign the query to the first cluster for processing, based at least on the first estimate and a number of computing devices in the first cluster compared to a number of computing devices in the second cluster; and send the request to process the query to the first cluster, wherein a leader node of the first cluster: determines, in response to the first cluster being tentatively assigned the query, whether at least one computing device of the first cluster is able to process the query based on a second estimate, generated by the leader node, based on second performance data obtained subsequently to the first performance data, of resources available to the first cluster; and causes the request to be either accepted and processed by the first cluster, or else rejected and not processed by the first cluster based, at least in part, on the determination of whether the at least one computing device of the first cluster is able to process the query, wherein the second cluster is caused to process the query based, at least in part, on the rejection.

Facts

Company
Amazon (Amazon Technologies, Inc.)
Official title
Resource allocation based on query analysis
Patent number
US12737357B1
Application number
17219507
Filed
Mar 31, 2021
Granted
Sep 15, 2026
Inventors
4
Claims
20

Classified under

G06F 16/24542 Physics & computingG06F 9/5027 Physics & computingG06F 9/5061 Physics & computingG06F 16/24568 Physics & computingG06F 16/248 Physics & computingG06F 16/285 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Amazon in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.