Аннотация:Modern supercomputer schedulers on average may leave ~10% and sometimes as much as 30% of the
computational resources idle. One possible approach to increase the load is to use an additional queue of low-priority jobs small enough to fit into the schedule gaps. We propose to use this approach for non-parallel jobs with arbitrary runtime wrapped in containers to allow them to be saved and migrated to other nodes or back to the queue. As a result, all the idle nodes can be used for computations. We also estimate the increase in average load and utilization efficiency that can be achieved using this approach.