Data set and node cache-based scheduling method and device

A data set and node cache-based scheduling device, comprising:

• a storage resource information obtaining module configured to obtain storage resource information of each host node;
• a host node screening module configured to obtain operation information of a training task in response to receiving the training task, and screen host nodes that satisfy a space required by the training task according to the operation information and the storage resource information;
• a host node scoring module configured to score each host node according to the storage resource information in response to no host node satisfying the space required by the training task;
• a host node selection module configured to select, from among all the host nodes, a host node to be executed that is used to execute the training task according to scoring results;
• and
• a training task execution module configured to obtain and delete an obsolete data set cache in the host node to be executed, and execute the training task in the host node to be executed.