Database operation classification

A network device comprising a processing resource in communication with a memory resource including instructions executable to:

• continuously track a plurality of database operations performed and a plurality of expected database operations for an event that executes for a time period;
• separate the plurality of database operations performed and the plurality of expected database operations into a plurality of database operation types;
• generate a plurality of clusters for each of the plurality of database operation types based on a ratio of the database operations performed compared to the plurality of expected database operations and the time period for the event for each of the plurality of database operation types;
• classify the clusters for each of the plurality of operation types based on performance;
• and
• evaluate a system performance metric for each of the plurality of database operation types based on a classification of real time data into the clusters for each of the plurality of database operation types.

A non-transitory computer-readable medium storing instructions executable by the processing resource to:

• determine a plurality of attributes and a plurality of statistical properties associated with each one of a plurality of database operations received at a switching device;
• generate a data set based of the plurality of attributes and the plurality of statistical properties;
• cluster, into a plurality of dusters, the generated data set using an unsupervised machine learning mechanism;
• create a classifier for each of the plurality of clusters using a supervised machine learning mechanism and based on labels received by the switching device for each one of the plurality of database operations;
• and
• dynamically classify new database operations continuously received at the switching device using the created classifiers.