Techniques for a deterministic distributed cache to accelerate SQL queries

A distributed computing system providing an analytical data processing service comprising:

• one or more processors;
• and
• one or more memories storing computer-executable instructions that, when executed with the one or more processors, cause the distributed computing system to:
• execute a cluster comprising a plurality of nodes;
• maintain a state of the cluster, the state comprising a plurality of token bounds uniformly associated with the plurality of nodes;
• receive, by a driver node of the plurality of nodes, a query for execution;
• identify, based at least in part on the query, a set of one or more data segments corresponding to the query;
• compute, by the driver node, a set of tokens corresponding to the set of one or more data segments;
• launch, on a first executor executing on a first worker node of the plurality of nodes, a first task to process a first data segment from the set of one or more data segments, the first worker node selected based at least in part on a first token of the set of tokens corresponding to a first pair of token bounds of the plurality of token bounds, the first pair of token bounds associated with the first worker node based at least on a uniform distribution of the plurality of token bounds to one or more executors of the plurality of nodes;
• and
• obtain, by the first worker node, the first data segment from a distributed cache within the cluster, the distributed cache characterized by the plurality of token bounds uniformly associated with the plurality of nodes of the cluster.

A non-transitory computer readable medium storing computer-executable instructions that, when executed by one or more processors, cause a distributed computer system to at least:

• execute a cluster comprising a plurality of nodes;
• maintain a state of the cluster, the state comprising a plurality of token bounds uniformly associated with the plurality of nodes;
• receive, by a driver node of the plurality of nodes, a query for execution;
• identify, based at least in part on the query, a set of one or more data segments corresponding to the query;
• compute, by the driver node, a set of tokens corresponding to the set of one or more data segments;
• launch, on a first executor executing on a first worker node of the plurality of nodes, a first task to process a first data segment from the set of one or more data segments, the first worker node selected based at least in part on a first token of the set of tokens corresponding to a first pair of token bounds of the plurality of token bounds, the first pair of token bounds associated with the first worker node based at least on a uniform distribution of the plurality of token bounds to one or more executors of the plurality of nodes;
• and
• obtain, by the first worker node, the first data segment from a distributed cache within the cluster, the distributed cache characterized by the plurality of token bounds uniformly associated with the plurality of nodes of the cluster.