Determination of a type of destage to perform based on preference between performance of operations and preservation of drive life using a machine learning module

A system, comprising:

• a memory;
• and
• a processor coupled to the memory, wherein the processor performs operations, the operations performed by the processor comprising:
• configuring the system to perform a full stride destage, a strip destage, and an individual track destage;
• receiving, by a machine learning module, a plurality of inputs corresponding to a plurality of factors that affect performance of data transfer operations and preservation of drive life in the system;
• in response to receiving the inputs, generating, by the machine learning module, a first output, a second output, and a third output that indicate a preference measure for the full stride destage, the strip destage, and the individual track destage respectively;
• and
• determining which type of destage to perform based on the first output, the second output, and the third output, and performing the determined type of destage, the operations further comprising determining a margin of error to adjust weights in the machine learning module, wherein determining of the margin of error includes comparing a maximum bandwidth to a current bandwidth, and in response to determining that the current bandwidth is greater than the maximum bandwidth, setting a first expected output corresponding to the first output and a second expected output corresponding to the second output to a first value, and setting a third expected output corresponding to the third output to a second value that is greater than the first value.

A computer program product, the computer program product comprising a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code configured to perform operations, the operations comprising:

• configuring a storage controller to perform a full stride destage, a strip destage, and an individual track destage;
• receiving, by a machine learning module, a plurality of inputs corresponding to a plurality of factors that affect performance of data transfer operations and preservation of drive life in the storage controller;
• in response to receiving the inputs, generating, by the machine learning module, a first output, a second output, and a third output that indicate a preference measure for the full stride destage, the strip destage, and the individual track destage respectively;
• and
• determining which type of destage to perform based on the first output, the second output, and the third output, and performing the determined type of destage, the operations further comprising determining a margin of error to adjust weights in the machine learning module, wherein determining of the margin of error includes comparing a maximum bandwidth to a current bandwidth, and in response to determining that the current bandwidth is greater than the maximum bandwidth, setting a first expected output corresponding to the first output and a second expected output corresponding to the second output to a first value, and setting a third expected output corresponding to the third output to a second value that is greater than the first value.