A processor may identify, using historical data, an amount of computing resources consumed to remedy the failure with an automatic remedy step. The processor may determine that the amount of consumed computing resources to remedy the failure is less than an amount of computing resources consumed by restarting the process. The processor may perform the automatic remedy step. The processor may identify that the automatic remedy step has failed. The processor may determine a waiting period based on an estimated time to receive a user response to the failure and an estimated load on the computing cluster. The processor may display a generated alert to a user during the waiting period. The processor may identify that no user input has been received during the waiting period. The processor may release computing resources corresponding to the process.