Workload balancing for storlet infrastructure

A system, comprising:

• a memory;
• a processor device communicatively coupled to the memory;
• a parser unit configured to:
• parse a first computational algorithm into an abstract syntax tree;
• a proxy node communicatively coupled to the processor device and the memory wherein the proxy node includes a first storlet engine, and the proxy node is configured to:
• monitor the first storlet engine for the first computational algorithm, where the storlet engine includes:
• a lookup table including characteristics of one or more nodes,
• a parser unit configured to break down computational algorithms, and
• a resource availability monitor configured to monitor a workload of the one or more nodes;
• determine, by analyzing the abstract syntax tree, a first category of the first computational algorithm;
• identify, based on the first category of the computational algorithm, a first node of the lookup table with a first characteristic matching the first category for processing the first computational algorithm;
• and
• send the first computational algorithm to the first node.

A computer program product for selecting a first node for processing a computational algorithm within a storage environment, the storage environment comprising a computer readable storage medium having a computer readable application stored therein, wherein the computer readable application, when executed on a computing device, causes the computing device to:

• monitor a first storlet engine for a first computational algorithm, where the storlet engine includes:
• a lookup table including characteristics of one or more nodes,
• a parser unit configured to break down computational algorithms, and
• a resource availability monitor configured to monitor a workload of the one or more nodes;
• parse, using the parser unit, the first computational algorithm into an abstract syntax tree;
• determine, by analyzing the abstract syntax tree, a first category of the first computational algorithm;
• identify, based on the first category of the computational algorithm, a first node of the lookup table with a first characteristic matching the first category for processing the first computational algorithm;
• and
• send the first computational algorithm to the first node.