Managing energy and server resources in hosting centers
SOSP '01 Proceedings of the eighteenth ACM symposium on Operating systems principles
MediSyn: a synthetic streaming media service workload generator
NOSSDAV '03 Proceedings of the 13th international workshop on Network and operating systems support for digital audio and video
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
ATC'07 2007 USENIX Annual Technical Conference on Proceedings of the USENIX Annual Technical Conference
PowerNap: eliminating server idle power
Proceedings of the 14th international conference on Architectural support for programming languages and operating systems
The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines
The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines
DFS: a file system for virtualized flash storage
FAST'10 Proceedings of the 8th USENIX conference on File and storage technologies
GreenHDFS: towards an energy-conserving, storage-efficient, hybrid Hadoop compute cluster
HotPower'10 Proceedings of the 2010 international conference on Power aware computing and systems
Analysis of disk power management for data-center storage systems
Proceedings of the 3rd International Conference on Future Energy Systems: Where Energy, Computing and Communication Meet
Power-reduction techniques for data-center storage systems
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
The objective of this research is to present an energy-conserving, self-adaptive Commodity Green Cloud Storage, called Lightning. Lightning's File System dynamically configures the servers in the Cloud Storage into logical Hot and Cold Zones. Lightning uses data-classification driven data placement to realize guaranteed, substantially long, periods (several days) of idleness in a significant subset of servers designated as the Cold Zone, in the commodity datacenter backing the Cloud Storage. These servers are then transitioned to inactive power modes and the resulting energy savings substantially reduce the operating costs of the datacenter. Furthermore, the energy savings allow Lightning to improve the data access performance by incorporation of high-performance, though high-cost Solid State Drives (SSD) without exceeding the total cost of ownership (TCO) of the datacenter. Analytical cost model analysis of Lightning suggests savings in the upwards of $24 million in the TCO of a 20,000 server datacenter. The simulation results show that Lightning can achieve 46% energy costs reduction even when the datacenter is at 80% capacity utilization.