NVM provides large memory capacity,long-term data durability,and high memory bandwidth for multi-thread applications on cloud servers.Nowadays,cloud servers often employ NUMA architecture,where the thread scheduling m...NVM provides large memory capacity,long-term data durability,and high memory bandwidth for multi-thread applications on cloud servers.Nowadays,cloud servers often employ NUMA architecture,where the thread scheduling mechanism plays a vital role in overall system performance because of the NUMA property.However,with the increase in server resources’diversity,i.e.,hybrid memory systems using DRAM and NVM on NUMA nodes,the exploration space for thread scheduling is expanding rapidly.Unfortunately,the existing thread schedulers,including rule-based algorithms and scheduling domain methods,cannot provide ideal scheduling solutions in such complicated cases.And,those thread schedulers neglect customized heterogeneous memory structures,thus degrading overall system performance.Fortunately,reinforcement learning can choose actions with maximum rewards values in a specific environment,leading the scheduler towards an optimal solution.In this paper,we propose a thread scheduling approach,i.e.,Smart Scheduler,by leveraging a reinforcement learning method.Smart Scheduler takes OS event information as input,extends LinUCB to explore the scheduling space,and guides threadlevel scheduling.We evaluate Smart Scheduler on the off-the-shelf server equipped with NVM.The experimental results show that the proposed Smart Scheduler can converge faster(usually within 20 actions)than rule-based algorithms and scheduling domain methods and reduce program execution time by up to 59.9%.It also outperforms rule-based algorithms and scheduling domain methods by 4.1%and 19.1%in quality of service latency.展开更多
Publisher Correction:CCF Transactions on High Performance Computing https://doi.org/10.1007/s42514-022-00110-2 Inadvertently,during the production process of the article(Chen et al.2022),reference citations were mista...Publisher Correction:CCF Transactions on High Performance Computing https://doi.org/10.1007/s42514-022-00110-2 Inadvertently,during the production process of the article(Chen et al.2022),reference citations were mistakenly typeset in both numbered and author/year formats.For this journal,cite references in the text should be by name and year in parentheses.The original article has been corrected.We apologize for any inconvenience caused to the readers.展开更多
基金supported by the Key Research and Development Program of Guang Dong(No.2021B0101310002)NSFC under grant No.62072432.
文摘NVM provides large memory capacity,long-term data durability,and high memory bandwidth for multi-thread applications on cloud servers.Nowadays,cloud servers often employ NUMA architecture,where the thread scheduling mechanism plays a vital role in overall system performance because of the NUMA property.However,with the increase in server resources’diversity,i.e.,hybrid memory systems using DRAM and NVM on NUMA nodes,the exploration space for thread scheduling is expanding rapidly.Unfortunately,the existing thread schedulers,including rule-based algorithms and scheduling domain methods,cannot provide ideal scheduling solutions in such complicated cases.And,those thread schedulers neglect customized heterogeneous memory structures,thus degrading overall system performance.Fortunately,reinforcement learning can choose actions with maximum rewards values in a specific environment,leading the scheduler towards an optimal solution.In this paper,we propose a thread scheduling approach,i.e.,Smart Scheduler,by leveraging a reinforcement learning method.Smart Scheduler takes OS event information as input,extends LinUCB to explore the scheduling space,and guides threadlevel scheduling.We evaluate Smart Scheduler on the off-the-shelf server equipped with NVM.The experimental results show that the proposed Smart Scheduler can converge faster(usually within 20 actions)than rule-based algorithms and scheduling domain methods and reduce program execution time by up to 59.9%.It also outperforms rule-based algorithms and scheduling domain methods by 4.1%and 19.1%in quality of service latency.
文摘Publisher Correction:CCF Transactions on High Performance Computing https://doi.org/10.1007/s42514-022-00110-2 Inadvertently,during the production process of the article(Chen et al.2022),reference citations were mistakenly typeset in both numbered and author/year formats.For this journal,cite references in the text should be by name and year in parentheses.The original article has been corrected.We apologize for any inconvenience caused to the readers.
