{"title":"在抢占式多任务操作系统中利用进程间调度降低能耗","authors":"S. Mostafa, S. Kusakabe","doi":"10.1109/PLATCON.2016.7456832","DOIUrl":null,"url":null,"abstract":"In this paper, we propose a new approach to efficiently reduce energy consumption when running multithreaded processes concurrently. Current proportional sharing schedulers of general purpose OSs don't take into account greedy behavior of multithreaded process (processes with more threads receive more aggregate CPU time from the scheduler relative to processes with fewer threads) when scheduling threads. In order to reduce energy consumption for simultaneous multithreaded (SMT) architectures, we investigate the effect of adjusting the weights of running sibling threads (threads forked from the same process) using novel proportional sharing scheduler, Thread Weight Readjustment Scheduler (TWRS), which aims to reduce the greedy behavior and the number of context switches. The context switches time is a pure overhead because the system does no useful work while switching. Reducing such overhead leads to minimizing energy consumption. TWRS provides a practical solution for multitasking OSs because it operates in concert with existing kernels. We have implemented TWRS in Linux 2.6.24-1, which represents the most prevalent scheduler design, e.g. Completely Fair Scheduler (CFS). The proposed scheduler based on a modification on the Linux kernel to schedule multithreaded processes in a multitasking OS environment. Our evaluation shows that our scheduler reduces energy consumption.","PeriodicalId":247342,"journal":{"name":"2016 International Conference on Platform Technology and Service (PlatCon)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Towards Reducing Energy Consumption Using Inter-Process Scheduling in Preemptive Multitasking OS\",\"authors\":\"S. Mostafa, S. Kusakabe\",\"doi\":\"10.1109/PLATCON.2016.7456832\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we propose a new approach to efficiently reduce energy consumption when running multithreaded processes concurrently. Current proportional sharing schedulers of general purpose OSs don't take into account greedy behavior of multithreaded process (processes with more threads receive more aggregate CPU time from the scheduler relative to processes with fewer threads) when scheduling threads. In order to reduce energy consumption for simultaneous multithreaded (SMT) architectures, we investigate the effect of adjusting the weights of running sibling threads (threads forked from the same process) using novel proportional sharing scheduler, Thread Weight Readjustment Scheduler (TWRS), which aims to reduce the greedy behavior and the number of context switches. The context switches time is a pure overhead because the system does no useful work while switching. Reducing such overhead leads to minimizing energy consumption. TWRS provides a practical solution for multitasking OSs because it operates in concert with existing kernels. We have implemented TWRS in Linux 2.6.24-1, which represents the most prevalent scheduler design, e.g. Completely Fair Scheduler (CFS). The proposed scheduler based on a modification on the Linux kernel to schedule multithreaded processes in a multitasking OS environment. Our evaluation shows that our scheduler reduces energy consumption.\",\"PeriodicalId\":247342,\"journal\":{\"name\":\"2016 International Conference on Platform Technology and Service (PlatCon)\",\"volume\":\"65 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 International Conference on Platform Technology and Service (PlatCon)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/PLATCON.2016.7456832\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 International Conference on Platform Technology and Service (PlatCon)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PLATCON.2016.7456832","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Towards Reducing Energy Consumption Using Inter-Process Scheduling in Preemptive Multitasking OS
In this paper, we propose a new approach to efficiently reduce energy consumption when running multithreaded processes concurrently. Current proportional sharing schedulers of general purpose OSs don't take into account greedy behavior of multithreaded process (processes with more threads receive more aggregate CPU time from the scheduler relative to processes with fewer threads) when scheduling threads. In order to reduce energy consumption for simultaneous multithreaded (SMT) architectures, we investigate the effect of adjusting the weights of running sibling threads (threads forked from the same process) using novel proportional sharing scheduler, Thread Weight Readjustment Scheduler (TWRS), which aims to reduce the greedy behavior and the number of context switches. The context switches time is a pure overhead because the system does no useful work while switching. Reducing such overhead leads to minimizing energy consumption. TWRS provides a practical solution for multitasking OSs because it operates in concert with existing kernels. We have implemented TWRS in Linux 2.6.24-1, which represents the most prevalent scheduler design, e.g. Completely Fair Scheduler (CFS). The proposed scheduler based on a modification on the Linux kernel to schedule multithreaded processes in a multitasking OS environment. Our evaluation shows that our scheduler reduces energy consumption.