An Efficient Checkpointing Scheme Using Price History of Spot Instances in Cloud Computing Environment

Abstract

The cloud computing is a computing paradigm that users can rent computing resources from service providers as much as they require. A spot instance in cloud computing helps a user to utilize resources with less expensive cost, even if it is unreliable. When a user performs tasks with unreliable spot instances, failures inevitably lead to the delay of task completion time and cause a seriously deterioration in the QoS of users. Therefore, we propose a price history based checkpointing scheme to avoid the delay of task completion time. The proposed checkpointing scheme reduces the number of checkpoint trials and improves the performance of task execution. The simulation results show that our scheme outperforms the existing checkpointing schemes in terms of the reduction of both the number of checkpoint trials and total costs per spot instance for user's bid.

A fair multi-attribute combinatorial double auction model for resource allocation in cloud computing

“…are used in different situations for resource allocation and pricing. Spot pricing [9], an auction mechanism proposed by Amazon, is successfully accepted in the current Cloud market and literature [15][16][17]. This section lists some recent research works related to Cloud auction.…”

Self-managed cost-efficient virtual elastic clusters on hybrid Cloud infrastructures

“…The literature already includes several checkpointing strategies in order to save the work just before an out-of-bid situation occurs, like [41] or [42]. However, none of them are actually tested in a real environment and, thus, the authors do not describe the technologies they are using to perform the checkpoints.…”

“…It can be considered as an evolution of the algorithm proposed in [42], for two main reasons. Firstly, the hourly checkpoints can save job process facing an unexpected peak where the variation of prices is very high.…”

High Performance Scientific Computing over Hybrid Cloud Platforms

“…Several checkpointing strategies have been developed in previous studies for saving work immediately before an out-of-bid situation occurs, such as [199] and [103]. However, none of them were actually tested in a real environment so the the technologies used to produce the checkpoints were never described.…”

“…This can be considered as an improvement on the algorithm proposed in [103], for two main reasons. First, the hourly checkpoints can save the job under processing when there is an unexpected peak if the variation in the price is very high.…”