Achieving Power-Efficiency in Clusters without Distributed File System Complexity

Abstract

Power-efficient operation is a desirable property, particularly for large clusters housed in datacenters. Recent work has advocated turning off entire nodes to achieve power-proportionality, but this leads to problems with availability and fault tolerance because of the resulting limits imposed on the replication strategies used by the distributed file systems (DFS) employed in these environments, with counter-measures adding substantial complexity to DFS designs. To achieve power-efficiency for a cluster without impacting data availability and recovery from failures and maintain simplicity in DFS design, our solution exploits cluster nodes that have the ability to operate in at least two extreme system-level power states, characterized by minimum vs. maximum power consumption and performance. The paper describes a cluster built with power-efficient node prototypes and presents experimental evaluations to demonstrate power-efficiency.

Energy wasting at internet data centers due to fear

“…-The worsening write rate due to write-offloading associated with writing on machines that are not running at the time that writing occurs [3]. -The number of replicas of each file is constant and static.…”

“…Moreover, another justification of this new function is that it lends less weight to the value of C(y) given in (2) in the function (3). Hence the importance of switching off machines is relaxed.…”

Deadline-Aware Energy Management in Data Centers

“…Small Size Examples: In Table 1 and Table 2, the speed of servers, service demands of jobs, arrival slots of jobs, deadlines of jobs follows a uniform distribution taking integer values from [1,4], [1,5], [2,6], [1,4] × τ, respectively. We assume that all servers are ON, initially.…”

“…The methods aiming to reduce data center power consumption could be classified into four approaches [1]: powerproportionality, which attempt to guarantee that servers consuming power in proportion to their utilization [2]- [4]; energyefficient server design, which attempt to determine the proper server architecture for a given workload [5]- [7]; dynamic server provisioning, which attempts to determine the times when the servers should be kept on or off [8], [9]; consolidation and virtualization, which attempts to reduce the power consumption by resource sharing [10]- [12]. We refer the reader to [13]- [17] for further literature related to our work.…”

KnightShift: Scaling the Energy Proportionality Wall through Server-Level Heterogeneity

“…Researchers then focused on increasing the length of idle periods by queueing requests [26] or by shifting I/O burden directly to disk and memory [2,3]. However, as multicore servers becomes dominant, idle periods are virtually nonexistent [26,34].…”