Amazon Spot Instances provide inexpensive service for high-performance computing. With spot instances, it is possible to get at most 90% off as discount in costs by bidding spare Amazon Elastic Computer Cloud (Amazon EC2) instances. In exchange for low cost, spot instances bring the reduced reliability onto the computing environment, because this kind of instance could be revoked abruptly by the providers due to supply and demand, and higher-priority customers are first served. To achieve high performance on instances with compromised reliability, Spark is applied to run jobs. In this thesis, a wide set of spark experiments are conducted to study its performance on spot instances. Without stateful replicating, Spark suffers from cascad- ing rollback and is forced to regenerate these states for ad hoc practices repeatedly. Such downside leads to discussion on trade-off between compatible slow checkpointing and regenerating on rollback and inspires us to apply multiple fault tolerance schemes. And Spark is proven to finish a job only with proper revocation rate. To validate and evaluate our work, prototype and simulator are designed and implemented. And based on real history price records, we studied how various checkpoint write frequencies and bid level affect performance. In case study, experiments show that our presented techniques can lead to ~20% shorter completion time and ~25% lower costs than those cases without such techniques. And compared with running jobs on full-price instance, the absolute saving in costs can be ~70%.

As information systems leaders tap into the global market of cloud computing-based services, they struggle to maintain consistent application performance due to lack of a process framework for managing quality of service (QoS) in the cloud. Guided by the disruptive innovation theory, the purpose of this case study was to identify a process framework for meeting the QoS requirements of private cloud service users. Private cloud implementation was explored by selecting an organization in California through purposeful sampling. Information was gathered by interviewing 23 information technology (IT) professionals, a mix of frontline engineers, managers, and leaders involved in the implementation of private cloud. Another source of data was documents such as standard operating procedures, policies, and guidelines related to private cloud implementation. Interview transcripts and documents were coded and sequentially analyzed. Three prominent themes emerged from the analysis of data: (a) end user expectations, (b) application architecture, and (c) trending analysis. The findings of this study may help IT leaders in effectively managing QoS in cloud infrastructure and deliver reliable application performance that may help in increasing customer population and profitability of organizations. This study may contribute to positive social change as information systems managers and workers can learn and apply the process framework for delivering stable and reliable cloud-hosted computer applications.