Abstract: Various embodiments include a system for generating performance monitoring data in a computing system. The system includes a unit level counter with a set of counters, where each counter increments during each clock cycle in which a corresponding electronic signal is at a first state, such as a high or low logic level state. Periodically, the unit level counter transmits the counter values to a corresponding counter collection unit. The counter collection unit includes a set of counters that aggregates the values of the counters in multiple unit level counters. Based on certain trigger conditions, the counter collection unit transmits records to a reduction channel. The reduction channel includes a set of counters that aggregates the values of the counters in multiple counter collection units. Each virtual machine executing on the system can access a different corresponding reduction channel, providing secure performance metric data for each virtual machine.

Abstract: A direct current (DC)-DC conversion circuit for balancing direct current buses is provided, including: a first switching transistor, a second switching transistor, a third switching transistor, and a fourth switching transistor that are connected in series between direct current buses, and are respectively connected in antiparallel with a diode; a first inductor, one end of which is connected to a positive electrode of a battery, and a second end is connected to a first node; a second inductor, one end of which is connected to a negative electrode of the battery, and a second end of which is connected to a third node; a first switch, connected between the first inductor and the positive electrode of the battery or between the second inductor and the negative electrode of the battery; and a third switch and a third inductor that are connected in parallel, connected between a second node and a ground.

Abstract: Various embodiments include a system for generating performance monitoring data in a computing system. The system includes a unit level counter with a set of counters, where each counter increments during each clock cycle in which a corresponding electronic signal is at a first state, such as a high or low logic level state. Periodically, the unit level counter transmits the counter values to a corresponding counter collection unit. The counter collection unit includes a set of counters that aggregates the values of the counters in multiple unit level counters. Based on certain trigger conditions, the counter collection unit transmits records to a reduction channel. The reduction channel includes a set of counters that aggregates the values of the counters in multiple counter collection units. Each virtual machine executing on the system can access a different corresponding reduction channel, providing secure performance metric data for each virtual machine.

Abstract: Embodiments of the present disclosure can provide distributed system resource allocation methods and apparatuses. The method comprises: receiving a resource preemption request sent by a resource scheduling server, the resource preemption request comprising job execution information corresponding to a first job management server; determining, according to the job execution information corresponding to the first job management server and comprised in the resource preemption request, resources to be returned by a second job management server and a resource return deadline; and returning, according to and the resource return deadline and a current job execution progress of the second job management server, the resources to be returned to the resource scheduling server before expiration of the resource return deadline.

Abstract: A priority-based resource allocation method, includes accepting a resource application submitted by a job, the resource application including resource demand information and job priority information; determining, according to the resource demand information of the resource application, whether remaining resources of a system meet the resource application, and traversing, in an allocated resource application queue when the remaining resources do not meet the resource application, allocated resource applications having job priorities lower than that of the resource application; using the sum of system resources occupied by all traversed resource applications plus the remaining resources as available resources; and stopping traversing when the available resources meet the resource application, and allocating the available resources to the resource application.

Abstract: Embodiments of the present disclosure can provide distributed system resource allocation methods and apparatuses. The method comprises: receiving a resource preemption request sent by a resource scheduling server, the resource preemption request comprising job execution information corresponding to a first job management server; determining, according to the job execution information corresponding to the first job management server and comprised in the resource preemption request, resources to be returned by a second job management server and a resource return deadline; and returning, according to and the resource return deadline and a current job execution progress of the second job management server, the resources to be returned to the resource scheduling server before expiration of the resource return deadline.

Abstract: A computer system resource allocation method is disclosed. The method may be implemented by a process and may comprise acquiring a total system resource and resource allocation data of each resource user submitting a resource application request, the resource allocation data including a maximum resource quota and a requested amount of resource by the each resource user, determining a corresponding resource saturation rate as a ratio between the amount of requested resource and the maximum resource quota, sorting the resource users according to the calculated resource saturation rates of the respective resource users, determining a boundary resource user using a set condition, according to the sorted resource users, and identifying resource users with a resource saturation rate smaller than or equal to that of the boundary resource user to be B-class resource users, and identifying resource users with a resource saturation rate larger than that of the boundary resource user to be C-class resource users.

Abstract: A priority-based resource allocation method, includes accepting a resource application submitted by a job, the resource application including resource demand information and job priority information; determining, according to the resource demand information of the resource application, whether remaining resources of a system meet the resource application, and traversing, in an allocated resource application queue when the remaining resources do not meet the resource application, allocated resource applications having job priorities lower than that of the resource application; using the sum of system resources occupied by all traversed resource applications plus the remaining resources as available resources; and stopping traversing when the available resources meet the resource application, and allocating the available resources to the resource application.

Abstract: A computer system resource allocation method is disclosed. The method may be implemented by a process and may comprise acquiring a total system resource and resource allocation data of each resource user submitting a resource application request, the resource allocation data including a maximum resource quota and a requested amount of resource by the each resource user, determining a corresponding resource saturation rate as a ratio between the amount of requested resource and the maximum resource quota, sorting the resource users according to the calculated resource saturation rates of the respective resource users, determining a boundary resource user using a set condition, according to the sorted resource users, and identifying resource users with a resource saturation rate smaller than or equal to that of the boundary resource user to be B-class resource users, and identifying resource users with a resource saturation rate larger than that of the boundary resource user to be C-class resource users.