In the Virtual Extension

Contributed article — DOI: 10.1145/1965724.1965751
The Case for RAMCloud

John Ousterhout, Parag Agrawal, David Erickson, Christos Kozyrakis, Jacob Leverich, David Mazières, Subhasish Mitra, Aravind Narayanan, Diego Ongaro, Guru Parulkar, Mendel Rosenblum, Stephen M. Rumble, Eric Stratmann, and Ryan Stutsman

For the past four decades magnetic disks have been the primary storage location for online information in computer systems. Over that period, disk technology has undergone dramatic improvements while being harnessed by higher-level storage systems (such as file systems and relational databases). However, disk performance has not improved as quickly as disk capacity, and developers find it increasingly difficult to scale disk-based systems to meet the needs of large-scale Web applications. Many computer scientists have proposed new approaches to disk-based storage as a solution, and others have suggested replacing disks with flash memory devices. In contrast, we say the solution is to shift the primary locus of online data from disk to DRAM, with disk relegated to a backup/archival role.

A new class of storage called RAMCloud will provide the storage substrate for many future applications. RAMCloud stores all of its information in the main memories of commodity servers and uses hundreds or thousands of these servers to create a large-scale storage system. Because all data is in DRAM at all times, RAMCloud promises 100x–1,000x lower latency than disk-based systems and 100x–1,000x greater throughput. Though individual memories are volatile, RAMCloud can use replication and backup techniques to provide data durability and availability equivalent to disk-based systems.

The combination of latency and scale offered by RAMCloud will change the storage landscape in three ways: simplify development of large-scale Web applications by eliminating many of the scalability issues that sap developer productivity today; enable a new class of applications that manipulate data 100x–1,000x more intensively than is possible today; and provide the scalable storage substrate needed for cloud computing and other data-center applications.

Back to Top

Review article — DOI: 10.1145/1965724.1965752
Workload Management for Power Efficiency in Virtualized Data Centers

Gargi Dasgupta, Amit Sharma, Akshat Verma, Anindya Neogi, and Ravi Kothari

By most estimates, energy-related costs will become the single largest contributor to the overall cost of operating a data center. Ironically, several studies have shown that a typical server in a data center is seriously underutilized. For example, Bohrer et al. find the average server utilization to vary between 11% and 50% for workloads from sports, e-commerce, financial, and Internet proxy clusters. This underutilization is the consequence of provisioning a server for the infrequent though inevitable peaks in the workload. Power-aware dynamic application placement can simultaneously address underutilization of servers as well as the rising energy costs in a data center by migrating applications to better utilize servers and switching freed-up servers to a lower power state.

Though the concept of dynamic application placement is not new, the two recent trends of virtualization and energy management technologies in modern servers have made it possible for it to be widely used in a data center. While virtualization has been the key enabler, power minimization has been the key driver for energy-aware dynamic application placement.

Server virtualization technologies first appeared in the 1960s to enable timesharing of expensive hardware between multiple users. As hardware became less expensive, virtualization gradually lost its charm. However, since the late 1990s there has been renewed interest in server virtualization and is now regarded as a disruptive business model to drive significant cost reductions. Advances in system management allow the benefits of virtualization to be now realized without any appreciable increase in the system management costs.

The benefits of virtualization include more efficient utilization of hardware (especially when each virtual machine, or VM, on a physical server reaches peak utilization at different points in time or when the applications in the individual VMs have complementary resource usage), as well as reduced floor space and facilities management costs. Additionally, virtualization software tends to hide the heterogeneity in server hardware and make applications more portable or resilient to hardware changes. Virtualization Planning entails sizing and placing existing or fresh workloads as VMs on physical servers.

In this article, the authors simplify resource utilization of a workload to be captured only by CPU utilization. However in practice, multiple parameters, such as memory, disk, and network I/O bandwidth consumption, among others, must be considered.