US 12,333,334 B2
Method for monitoring job scheduler, apparatus and system for executing the method
Young Hoon Jung, Seoul (KR); Se Jun Kim, Seoul (KR); and Da Seul Bae, Seoul (KR)
Assigned to SAMSUNG SDS CO., LTD., Seoul (KR)
Filed by SAMSUNG SDS CO., LTD, Seoul (KR)
Filed on Oct. 25, 2022, as Appl. No. 17/972,738.
Claims priority of application No. 10-2021-0143756 (KR), filed on Oct. 26, 2021.
Prior Publication US 2023/0129998 A1, Apr. 27, 2023
Int. Cl. G06F 9/48 (2006.01)
CPC G06F 9/4881 (2013.01) [G06F 9/485 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method for monitoring a job scheduler, the method performed on a computing device including one or more processors and a memory storing one or more programs executed by the one or more processors, the method comprising:
checking whether it is necessary to determine whether to expand a resource of a computing environment to be scheduled when a job is performed by scheduling by a job scheduler;
calculating a value of a score function for a scheduling policy currently executing and a maximum value of a predetermined score function, when it is necessary to determine whether to expand the resource of the computing environment to be scheduled;
determining to expand the resource of the computing environment to be scheduled, based on the value of the score function and the maximum value of the predetermined score function; and
learning the scheduling policy of the job scheduler using a predetermined artificial neural network model,
wherein the learning of the scheduling policy comprises:
generating learning data based on job-related log information provided in the computing environment to be scheduled;
learning the scheduling policy by inputting the learning data into the artificial neural network model;
checking whether performance of the job scheduler according to the learned scheduling policy is equal to or greater than performance of the job scheduler according to a previous scheduling policy; and
updating the learned scheduling policy to the scheduling policy of the job scheduler when the performance of the job scheduler according to the learned scheduling policy is equal to or greater than the performance of the job scheduler according to the previous scheduling policy.