公开(公告)号：US09146783B2

公开(公告)日：2015-09-29

申请号：US14044583

申请日：2013-10-02

Applicant: NetApp, Inc.

Inventor： Naveen Bali ,  Naresh M. Patel ,  Manpreet Singh

IPC: G06F9/455 ,  G06F9/46 ,  G06F9/50 ,  G06F1/32 ,  G06F9/48

CPC classification number: G06F9/5027 ,  G06F1/3287 ,  G06F1/329 ,  G06F9/4893 ,  G06F2209/5017 ,  Y02D10/24

Abstract: Aspects of the present invention concern a method and system for scheduling a request for execution on multiple processors. This scheduler divides processes from the request into a set of domains. Instructions in the same domain are capable of executing the instructions associated with the request in a serial manner on a processor without conflicts. A relative processor utilization for each domain in the set of the domains is based upon a workload corresponding to an execution of the request. If there are processors available then the present invention provisions a subset of available processors to fulfill an aggregate processor utilization. The aggregate processor utilization is created from a combination of the relative processor utilization associated with each domain in the set of domains. If processors are not needed then some processors may be shut down. Shutting down processors in accordance with the schedule saves energy without sacrificing performing.

Abstract translation: 本发明的方面涉及一种用于在多个处理器上调度执行请求的方法和系统。 该调度程序将请求中的进程分为一组域。 相同域中的指令能够在处理器上以串行方式执行与请求相关联的指令，而不会发生冲突。 域集合中每个域的相对处理器利用率基于与请求的执行相对应的工作负载。 如果存在可用的处理器，则本发明提供可用处理器的子集以实现聚合处理器利用。 聚合处理器利用率是通过与该组域中的每个域相关联的相对处理器利用率的组合来创建的。 如果不需要处理器，那么一些处理器可能会被关闭。 按照时间表关闭处理器可以节省能源，而不会牺牲性能。

公开(公告)号：US20140033221A1

公开(公告)日：2014-01-30

申请号：US14044583

申请日：2013-10-02

Applicant: NetApp, Inc.

Inventor： Naveen Bali ,  Naresh M. Patel ,  Manpreet Singh

IPC: G06F9/50 ,  G06F1/32

CPC classification number: G06F9/5027 ,  G06F1/3287 ,  G06F1/329 ,  G06F9/4893 ,  G06F2209/5017 ,  Y02D10/24

Abstract: Aspects of the present invention concern a method and system for scheduling a request for execution on multiple processors. This scheduler divides processes from the request into a set of domains. Instructions in the same domain are capable of executing the instructions associated with the request in a serial manner on a processor without conflicts. A relative processor utilization for each domain in the set of the domains is based upon a workload corresponding to an execution of the request. If there are processors available then the present invention provisions a subset of available processors to fulfill an aggregate processor utilization. The aggregate processor utilization is created from a combination of the relative processor utilization associated with each domain in the set of domains. If processors are not needed then some processors may be shut down. Shutting down processors in accordance with the schedule saves energy without sacrificing performing.

Abstract translation: 本发明的方面涉及一种用于在多个处理器上调度执行请求的方法和系统。 该调度程序将请求中的进程分为一组域。 相同域中的指令能够在处理器上以串行方式执行与请求相关联的指令，而不会发生冲突。 域集合中每个域的相对处理器利用率基于与请求的执行相对应的工作负载。 如果存在可用的处理器，则本发明提供可用处理器的子集以实现聚合处理器利用。 聚合处理器利用率是通过与该组域中的每个域相关联的相对处理器利用率的组合来创建的。 如果不需要处理器，那么一些处理器可能会被关闭。 按照时间表关闭处理器可以节省能源，而不会牺牲性能。