Transparent Throughput Elasticity for IaaS Cloud Storage Using Guest-Side Block-Level Caching

Abstract

International audienceStorage elasticity on IaaS clouds is a crucial feature in the age of data-intensive computing. However, the traditional provisioning model of leveraging virtual disks of fixed capacity and performance characteristics has limited ability to match the increasingly dynamic nature of I/O application requirements. This mismatch is particularly problematic in the context of scientific applications that interleave periods of I/O inactivity with I/O intensive bursts. In this context, overprovisioning for best performance during peaks leads to significant extra costs because of unnecessarily tied-up resources, while any other trade-off leads to performance loss. This paper provides a transparent solution that automatically boosts I/O bandwidth during peaks for underlying virtual disks, effectively avoiding overprovisioning without performance loss. Our proposal relies on the idea of leveraging short-lived virtual disks of better performance characteristics (and thus more expensive) to act during peaks as a caching layer for the persistent virtual disks where the application data is stored. We show how this idea can be achieved efficiently at the block-device level, using a caching mechanism that leverages iterative behavior and learns from past experience. We demonstrate the benefits of our proposal both for microbenchmarks and for two real-life applications using large-scale experiments

Towards Transparent Throughput Elasticity for IaaS Cloud Storage

“…This paper extends our previous work [26] where we introduced an elastic disk throughput solution that can deliver high performance during I/O peaks while minimizing costs related to storage. Our initial proposal focused on the idea of using small, short-lived, and fast virtual disks to temporarily boost the maximum achievable throughput during I/O peaks by acting as a caching layer for larger but slower virtual disks that are used as primary storage.…”

To Overlap or Not to Overlap: Optimizing Incremental MapReduce Computations for On-Demand Data Upload

“…Thus, an interesting avenue is to explore the cost also when taking storage into consideration. In this context, we plan to study the viability of several storage elasticity features introduced by our previous work [11,12,13].…”

Performance Model of MapReduce Iterative Applications for Hybrid Cloud Bursting

“…Performance and cost prediction in a single data center have been studied from multiple angles. A storage performance and cost model for iterative applications was introduced in [14]. Given the data-intensive nature of MapReduce applications and the need to persist data between jobs, such a direction is an important complement to our own work.…”