Self-adaptive management of the sleep depths of idle nodes in large scale systems to balance between energy consumption and response times
Self-adaptive management of the sleep depths of idle nodes in large scale systems to balance between energy consumption and response times
复制标题
DOI：
10.1109/cloudcom.2012.6427509
复制
发表时间：
2012-12
期刊：
影响因子：
--
通讯作者：
Yongpeng Liu;Hong Zhu;Kai Lu;Xiaoping Wang
中科院分区：
文献类型：
--
作者：
Yongpeng Liu;Hong Zhu;Kai Lu;Xiaoping Wang
由于真实的工作负载的时变特性，大规模计算机系统在大多数运行时间内具有相当数量的空闲节点。他们消耗能量，但没有做任何有用的事情。为了节省这种活动空闲节点所造成的巨大能量浪费，大多数现代计算节点提供多级动态睡眠机制以降低功耗。然而，唤醒睡眠节点需要时间，从而影响系统的响应时间和性能。节点处于更深的睡眠状态，它消耗更少的能量，但具有更长的唤醒延迟。本文提出了一种睡眠状态管理模型，以平衡系统的能量消耗和响应时间。在该模型中，空闲节点被分为不同的组，根据他们的睡眠状态。每个组包含相同睡眠深度级别的节点，并形成一定准备程度的储备池。在资源分配过程中，优先向应用提供池中准备程度最高的节点。当最高准备级别的池中的节点不足时，分配下一准备级别的池中的节点。在每次分配和回收节点之后，通过上下改变节点的睡眠深度来调整每一级池中的节点数量。因此，可以随时维护备用池。显然，影响空闲节点管理有效性的一个关键因素是备用池的大小。本文提出并研究了一种自适应的方法来解决这个问题，使储备池的大小动态调整，根据应用程序。实验结果表明，通过自适应管理，空闲节点的功耗降低了84.12%，而降低速率的代价仅为8.85%。
Due to the time-varying nature of real workload, a large scale computer system has quite a number of idle nodes in most time of operation. They consume energy, but do nothing useful. To save the huge energy waste caused by such active idle nodes, most modern compute nodes provide multiple level dynamic sleep mechanisms to reduce power consumption. However, awaking sleeping nodes takes time, thus affects the response times and performance of the system. A node is deeper in sleep, it consumes less energy, but has longer wakeup latency. This paper proposes a sleep state management model to balance the system's energy consumption and response times. In this model, idle nodes are classified into different groups according to their sleep states. Each group contains nodes of same level of sleep depth and forms a reserve pool of a certain readiness level. In a resource allocation process, nodes in the pool of highest level of readiness are preferentially provided to the application. When the nodes in the pool of the highest readiness level are not sufficient, the nodes in the pool(s) of next level(s) of readiness are allocated. After each allocation and reclaim of nodes, the numbers of nodes in each level of pools are adjusted by changing the sleep depth of the nodes up and down. Thus, the reserve pools can be maintained at all times. Obviously, a key factor that affects the effectiveness of the idle node management is the sizes of the reserve pools. This paper proposes and investigates a self-adaptive approach to this problem so that the sizes of reserve pools are dynamically adjusted according to the applications. Our experiments demonstrated that, by applying our self-adaptive management, the power consumption of idle nodes can be reduced by 84.12% with the cost of slowdown rate being only 8.85%.