发明名称 Scheduler, multi-core processor system, and scheduling method
摘要 In an embodiment, a scheduler coordinates timings at which cores execute processes, for any two sequential processes to consecutively be executable. The processes are executed in order scheduled by the scheduler by concentrating on a specific core processes obstructing the consecutive execution such as an external interrupt and an internal interrupt. The scheduler does not always cause processes of another application to be executed during all standby time periods while the scheduler determines whether a length of a standby time period is shorter than a predetermined value, and does not cause any process of the other application to be executed when the length is shorter than that.
申请公布号 US9262209(B2) 申请公布日期 2016.02.16
申请号 US201313761866 申请日期 2013.02.07
申请人 Fujitsu Limited 发明人 Suzuki Takahisa;Yamashita Koichiro;Yamauchi Hiromasa;Kurihara Koji
分类号 G06F9/46;G06F9/48;G06F9/50 主分类号 G06F9/46
代理机构 Arent Fox LLP 代理人 Arent Fox LLP
主权项 1. A scheduler causing a specific core in a multi-core processor to execute a process comprising: first detecting, by the specific core, from a group of processes constituting a program to be executed, a group of unset scheduling processes whose group of subsequent processes is common; second detecting, by the specific core, for each of the unset scheduling processes of the detected group of unset scheduling processes and from a group of preceding processes for the unset scheduling processes, a preceding process belonging to a group to which the unset scheduling processes of the detected group of unset scheduling processes belong, the group to which the unset scheduling process belongs being among groups formed by grouping processes that share same or related data to be accessed; allocating, by the specific core, each of the unset scheduling processes of the detected group of unset scheduling processes respectively to a core in the multi-core processor and to which the detected preceding process is allocated; calculating, by the specific core, for each of the unset scheduling processes of the detected group of unset scheduling processes, elapsed time of an execution time period of each of the unset scheduling processes of the detected group of unset scheduling processes from an execution ending time at which the group of preceding processes for the unset scheduling processes of the detected group of unset scheduling processes completely ends; and setting, by the specific core, for each of the allocated unset scheduling processes, an execution starting time of each of the allocated unset scheduling process at an allocation destination core such that an execution of a respective unset scheduling process is to be completed at a most recent calculated elapsed time; wherein the allocating includes allocating an interrupt process consequent to the program to be executed and a second program is allocated, to a core for which no preceding process belonging to the group to which a respective unset scheduling process of the detected group of unset scheduling processes belongs is detected at the second detecting.
地址 Kawasaki JP
您可能感兴趣的专利