Application startup page fault management in a hardware multithreading environment

摘要

A method, system and computer-usable medium are disclosed for startup page fault management improves application startup performance by assigning startup tasks to a hardware thread 0 across plural processing cores in a simultaneous multithreading environment to provide more rapid processing of processor bound page faults. I/O bound page faults are flagged to associated with predetermined cache locations to improve data and text first reference page-in I/O response.

主权项

1. A system comprising:
a processor; a data bus coupled to the processor; and a computer-usable medium embodying computer program code, the computer-usable medium being coupled to the data bus, the computer program code used for application startup page fault management and comprising instructions executable by the processor and configured for: detecting of an application startup for an application designated to receive the application startup page fault management; determining plural tasks associated with the startup of the application; scheduling the plural tasks to a hardware thread 0 of each of plural processor cores; executing application startup to a predetermined steady state, wherein the predetermined steady state comprises at least a predetermined number of dispatches of each of the plural tasks on their respective thread 0; and responsive to the predetermined steady state, scheduling tasks associated with the application to hardware threads in addition to thread 0.