arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.16166cs.DC
收藏

简单策略的价值:用并行性和系统架构购买性能

The Merit of Simple Policies: Buying Performance With Parallelism and System Architecture

University of Rome Sapienza(罗马大学)

Mert Yildiz, Alexey Rolich, Andrea Baiocchi

AI总结:

研究发现,在计算集群服务器数量变化时,平均作业响应时间达到最小值,且简单策略如Join Idle Queue在高并行度下性能与复杂策略相当,多阶段服务器集群进一步提升了性能。

摘要:

尽管调度和任务分配已广泛研究,但谷歌近期公开了大规模高分辨率云工作负载数据集。我们重新审视了基于这些测量数据的交通工作负载的调度和分配算法。主要发现是,在计算集群服务器数量变化时,平均作业响应时间在总计算预算保持不变的约束下达到最小值。此外,简单策略如Join Idle Queue在适当高并行度下性能与复杂基于大小的策略相当。进一步,使用多阶段服务器集群,即使使用非常简单的Round Robin策略,也能获得优于基于大小的调度策略的性能。结论是,计算系统的并行性和架构可能比策略更强大,可用于控制性能,特别是在现实工作负载流量下。

英文摘要:

While scheduling and dispatching of computational workloads is a well-investigated subject, only recently has Google provided publicly a vast high-resolution measurement dataset of its cloud workloads. We revisit dispatching and scheduling algorithms fed by traffic workloads derived from those measurements. The main finding is that mean job response time attains a minimum as the number of servers of the computing cluster is varied, under the constraint that the overall computational budget is kept constant. Moreover, simple policies, such as Join Idle Queue, appear to attain the same performance as more complex, size-based policies for suitably high degrees of parallelism. Further, better performance, definitely outperforming size-based dispatching policies, is obtained by using multi-stage server clusters, even using very simple policies such as Round Robin. The takeaway is that parallelism and architecture of computing systems might be powerful knobs to control performance, even more than policies, under realistic workload traffic.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑