In enterprise data centers power usage is a problem impacting server density and the total cost of ownership. Storage uses a significant fraction of the power budget and there are no widely deployed power-saving solutions for enterprise storage systems. The traditional view is that enterprise workloads make spinning disks down ineffective because idle periods are too short. We analyzed block-level traces from 36 volumes in an enterprise data center for one week and concluded that significant idle periods exist, and that they can be further increased by modifying the read/write patterns using write off-loading. Write off-loading allows write requests on spun-down disks to be temporarily redirected to persistent storage elsewhere in the data center. The key challenge is doing this transparently and efficiently at the block level, without sacrificing consistency or failure resilience. We describe our write offloading design and implementation that achieves these goals. We evaluate it by replaying portions of our traces on a rack-based testbed. Results show that just spinning disks down when idle saves 28–36 % of energy, and write off-loading further increases the savings to 45–60%. 1

This paper makes two main contributions. First, it introduces Diverted Accesses, a technique that leverages the redundancy in storage systems to conserve disk energy. Second, it evaluates the previous (redundancy-oblivious) energy conservation techniques, along with Diverted Accesses, as a function of the amount and type of redundancy in the system. The evaluation is based on novel analytic models of the energy consumed by the techniques. Using these energy models and previous models of reliability, availability, and performance, we can determine the best redundancy configuration for new energy-aware storage systems. To study Diverted Accesses for realistic systems and workloads, we simulate a wide-area storage system under two file-access traces. Our modeling results show that Diverted Accesses is more effective and robust than the redundancy-oblivious techniques. Our simulation results show that our technique can conserve 20-61 % of the disk energy consumed by the wide-area storage system.

Abstract — Energy-efficiency is becoming increasingly important for storage systems to reduce the total cost of ownership (TCO). In this paper, we propose an energy saving policy named eRAID for conventional disk based RAID-1 systems using redundancy. In particular, we develop a dynamic performance control scheme with the help of a performance predictor based on queueing network theory. Moreover, we discuss alternative data layout schemes that are more energy-efficient than traditional disk mirroring. Experimental results show that eRAID can save up to 30 % energy without violating predefined performance constraints. I.

Over-provisioning is a standard capacity planning practice that leads to disk drives that operate mostly under very low utilization (as low as single digit utilization) but that are consuming disproportional amounts of power. Methodologies that place the disk drive into a low power mode during idle times can assist in conserving power. This is a challenging problem because the performance of future jobs cannot be compromised, yet there is no knowledge of future disk arrivals. In this paper we explore the above problem by exploring ranges and trade offs of possible power savings and performance within a set of enterprise storage traces. We demonstrate the difficulty of obtaining significant power savings even in traces where overall utilization is less than 5 % and explore the feasibility of popular schemes such as workload shaping for power savings. We also propose an autonomic algorithm that suggests when and for how long a power savings mode should be activated given an acceptable performance degradation target that is user provided. The robustness of the algorithm is illustrated via extensive experimentation.

Abstract — Power consumption is an important issue for cluster supercomputers as it directly affects their running cost and cooling requirements. This paper investigates the memory energy efficiency of high-end data servers used for supercomputers. Emerging memory technologies allow memory devices to dynamically adjust their power states. To achieve maximum energy saving, the memory management on data servers needs to judiciously utilize these energy-aware devices. As we explore different management schemes under four real-world parallel I/O workloads, we find that the memory energy consumption is determined by a complex interaction among four important factors: (1) cache hit rates that may directly translate performance gain into energy saving, (2) cache populating schemes that perform buffer allocation and affect access locality at the chip level, (3) request clustering that aims to temporally align memory transfers from different buses into the same memory chips, and (4) access patterns in workloads that affect the first three factors. I.

Ever-increasing complexity of large-scale applications and continuous increases in sizes of the data they process make the problem of maximizing performance of such applications a very challenging task. In particular, many challenging applications from the domains of astrophysics, medicine, biology, computational chemistry, and materials science are extremely data intensive. Such applications typically use a disk system to store and later retrieve their large data sets, and consequently, their disk performance is a critical concern. Unfortunately, while disk density has significantly improved over the last couple of decades, disk access latencies have not. As a result, I/O is increasingly becoming a bottleneck for dataintensive applications, and has to be addressed at the software level if we want to extract the maximum performance from modern computer architectures. This paper presents a compiler-directed code restructuring scheme for improving the I/O performance of data-intensive scientific applications. The proposed approach improves I/O performance by reducing the number of disk accesses through a new concept called disk reuse maximization. In this context, disk reuse refers to reusing the data in a given set of disks as much as possible before moving to other disks. Our compiler-based approach restructures application code, with the help of a polyhedral tool, such that disk reuse is maximized to the extent allowed by intrinsic data dependencies in the application code. The proposed optimization can be applied to each loop nest individually or to the entire application code. The experiments show that the average I/O improvements brought by the loop nest based version of our approach are 9.0 % and 2.7%, over the original application codes and the codes optimized using conventional schemes, respectively. Further, the average improvements obtained when our approach is applied to the entire application code are 15.0 % and 13.5%, over the original application codes and the codes optimized using

Reducing the energy footprint of data centers continues to receive significant attention due to both its financial and environmental impact. There are numerous methods that limit the impact of both factors, such as expanding the use of renewable energy or participating in automated demand-response programs. To take advantage of these methods, servers and applications must gracefully handle intermittent constraints in their power supply. In this paper, we propose blinking—metered transitions between a highpower active state and a low-power inactive state—as the primary abstraction for conforming to intermittent power constraints. We design Blink, an application-independent hardware-software platform for developing and evaluating blinking applications, and define multiple types of blinking policies. We then use Blink to design BlinkCache, a blinking version of memcached, to demonstrate the effect of blinking on an example application. Our results show that a load-proportional blinking policy combines the advantages of both activation and synchronous blinking for realistic Zipf-like popularity distributions and wind/solar power signals by achieving near optimal hit rates (within 15 % of an activation policy), while also providing fairer access to the cache (within 2 % of a synchronous policy) for equally popular objects.

Large-scale high-speed mass-storage systems account for a large part of the energy consumed at data centers. To conserve energy consumed by these storage systems, we propose a high-speed tiered-storage system with a poweraware proactive method of storage-tiering management that minimizes loss of performance, which we have called the energy-efficient High-speed Tiered-Storage system (eHiTS). eHiTS consists of a tiered-storage system with high-speed online storage as the first tier and low-power nearline storage with high capacity as the second tier. All files are always stored in nearline storage when it is created, in which the hard disk drives are usually left powered off. Based on hints from a high-performance computing (HPC) application, only the volume that includes the accessed files (datasets) is copied from nearline to online storage before access. The results obtained from our testbed with 64-TB capacity revealed that eHiTS was able to conserve up to 16 % of the energy consumed by an ordinary tiered-storage system with the same capacity. This corresponded to a 55%-energy saving in 1-PB capacity. 1.