Systems and methods for managing connections in scalable clusters
AssigneeCoupang Corp.
InventorRajorshi SEN
Life of this patent
Estimating the term…
Abstract
Systems and methods for managing cluster workloads. A system including one or more processors, and non-transitory memory including instructions. When executed by the one or more processors, the instructions perform method steps. The method steps may include receiving a query from a user device. The method steps may also include parsing a table property from the query, determining that the parsed table property is associated with a stored table, and identifying at least one cluster from the plurality of clusters that include the stored table. The method steps may further include identifying an optimal cluster from the at least one cluster and sending the query to the optimal cluster for execution.
Claims20
A method for managing cluster workloads, the method comprising:
- receiving, from a user device, a query;
- parsing, at the parsing module, a table property from the query;
- determining that the parsed table property is associated with a stored table;
- identifying at least one cluster from among a plurality of clusters including the stored table;
- identifying, using a polling module, an optimal cluster from among the at least one cluster;
- and
- sending the query to the optimal cluster for execution.
A system comprising:
- non-transitory memory comprising instructions;
- one or more processors configured to execute the instructions causing the one or more processors to:
- receive, from a user device, a query;
- parse, at the parsing module, a table property from the query;
- determine whether the parsed name table property is associated with a stored table;
- in response to determining an association, identify at least one cluster from among a plurality of clusters including the stored table;
- identify, using a polling module, an optimal cluster from among the at least one cluster;
- and
- send the query to the identified optimal cluster for execution.
A method for managing cluster workloads, the method comprising:
- receiving, from a user device, a structured query;
- parsing, at the parsing module, a table property from the structured query;
- determining whether the parsed table property is associated with a stored table;
- in response to determining an association, identifying at least one dataset including the stored table;
- in response to identifying at least one dataset including the stored table, identifying at least one cluster including the at least one dataset;
- identifying, using a polling module, an optimal cluster from among the at least one cluster;
- opening a connection, over a network, between the user device and the optimal cluster;
- sending the structured query to the optimal cluster for execution;
- and
- transmitting, over the network, a response from the optimal cluster to the user device.
Dependencies are inferred from the claim text.