More Like this

1. No Reservations: A First Look at Amazon's Reserved Instance Marketplace

   Pradeep Ambati, David Irwin (July 2020, USENIX Workshop on Hot Topics in Cloud Computing (HotCloud))

   Cloud users can significantly reduce their cost (by up to 60%) by reserving virtual machines (VMs) for long periods (1 or 3 years) rather than acquiring them on demand. Unfortunately, reserving VMs exposes users to demand risk that can increase cost if their expected future demand does not materialize. Since accurately forecasting demand over long periods is challenging, users often limit their use of reserved VMs. To mitigate demand risk, Amazon operates a Reserved Instance Marketplace (RIM) where users may publicly list the remaining time on their VM reservations for sale at a price they set. The RIM enables users to limit demand risk by either selling VM reservations if their demand changes, or purchasing variable- and shorter-term VM reservations that better match their demand forecast horizon. Clearly, the RIM's potential to mitigate demand risk is a function of its price characteristics. However, to the best of our knowledge, historical RIM prices have neither been made publicly available nor analyzed. To address the problem, we have been monitoring and archiving RIM prices for 1.75 years across all 69 availability zones and 22 regions in Amazon's Elastic Compute Cloud (EC2). This paper provides a first look at this data and its implications for cost-effectively provisioning cloud infrastructure. 

   more » « less
2. Hedge Your Bets: Optimizing Long-term Cloud Costs by Mixing VM Purchasing Options

   https://doi.org/10.1109/IC2E48712.2020.00018  

   Ambati, Pradeep; Bashir, Noman; Irwin, David; Hajiesmaili, Mohammad; Shenoy, Prashant (April 2020, 2020 IEEE International Conference on Cloud Engineering (IC2E))

   Cloud platforms offer the same VMs under many purchasing options that specify different costs and time commitments, such as on-demand, reserved, sustained-use, scheduled reserve, transient, and spot block. In general, the stronger the commitment, i.e., longer and less flexible, the lower the price. However, longer and less flexible time commitments can increase cloud costs for users if future workloads cannot utilize the VMs they committed to buying. Large cloud customers often find it challenging to choose the right mix of purchasing options to reduce their long-term costs, while retaining the ability to adjust capacity up and down in response to workload variations.To address the problem, we design policies to optimize long-term cloud costs by selecting a mix of VM purchasing options based on short- and long-term expectations of workload utilization. We consider a batch trace spanning 4 years from a large shared cluster for a major state University system that includes 14k cores and 60 million job submissions, and evaluate how these jobs could be judiciously executed using cloud servers using our approach. Our results show that our policies incur a cost within 41% of an optimistic optimal offline approach, and 50% less than solely using on-demand VMs. 

   more » « less
3. E-VM: An Elastic Virtual Machine Scheduling Algorithm to Minimize the Total Cost of Ownership in a Hybrid Cloud

   Milan Shetti, Bingzhe Li (October 2021, 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking)

   IEEE (Ed.)

   A hybrid cloud that combines both public and private clouds is becoming more and more popular due to the advantages of improved security, scalability, and guaranteed SLA (Service-Level Agreement) at a lower cost than a separate private or public cloud. The existing studies rarely consider VM migrations in a hybrid cloud environment with dynamically changed VM workloads. From an enterprise’s perspective, these migrations are necessary to minimize the cost of utilizing public clouds and guarantee SLAs of VMs in a hybrid cloud environment. In this paper, we propose an elastic VM allocation and migration algorithm for a hybrid cloud, called E-VM, to fully utilize the resources in a private cloud and to minimize the cost of using a public cloud while guaranteeing the SLAs of all VMs. The E-VM considers the bi-direction migration between private and public clouds. Two components, VM-predictor and VM-selector, are designed and implemented in E-VM to determine if a migration has to be triggered between private and public clouds and which VMs will be migrated to the opposite cloud, respectively. Moreover, E-VM is designed based on the existing public cloud pricing models and can be easily adapted to any cloud service provider. According to simulator results based on a set of captured industrial VM traces/workloads and additional experiments directly on a real-world hybrid cloud, the proposed E-VM can significantly reduce the total cost of using the public cloud compared to the existing VM migration schemes. 

   more » « less
4. The Price Is (Not) Right: Reflections on Pricing for Transient Cloud Servers

   https://doi.org/10.1109/ICCCN.2019.8846933  

   Irwin, David; Shenoy, Prashant; Ambati, Pradeep; Sharma, Prateek; Shastri, Supreeth; Ali-Eldin, Ahmed (July 2019, 2019 28th International Conference on Computer Communication and Networks (ICCCN))

   Amazon introduced spot instances in December 2009, enabling “customers to bid on unused Amazon EC2 capacity and run those instances for as long as their bid exceeds the current Spot Price.” Amazon’s real-time computational spot market was novel in multiple respects. For example, it was the first (and to date only) large-scale public implementation of market-based resource allocation based on dynamic pricing after decades of research, and it provided users with useful information, control knobs, and options for optimizing the cost of running cloud applications. Spot instances also introduced the concept of transient cloud servers derived from variable idle capacity that cloud platforms could revoke at any time. Transient servers have since become central to efficient resource management of modern clusters and clouds. As a result, Amazon’s spot market was the motivation for substantial research over the past decade. Yet, in November 2017, Amazon effectively ended its real-time spot market by announcing that users no longer needed to place bids and that spot prices will “...adjust more gradually, based on longer-term trends in supply and demand.” The changes made spot instances more similar to the fixed-price transient servers offered by other cloud platforms. Unfortunately, while these changes made spot instances less complex, they eliminated many benefits to sophisticated users in optimizing their applications. This paper provides a retrospective on Amazon’s real-time spot market, including its advantages and disadvantages for allocating transient servers compared to current fixed-price approaches. We also discuss some fundamental problems with Amazon’s spot market, which we identified in prior work (from 2016), that predicted its eventual end. We then discuss potential options for allocating transient servers that combine the advantages of Amazon’s real-time spot market, while also addressing the problems that likely led to its elimination. 

   more » « less
5. Kerveros: Efficient and Scalable Cloud Admission Control

   Sajal, Sultan Mahmud; Marshall, Luke; Li, Beibin; Zhou, Shandan; Pan, Abhisek; Mellou, Konstantina; Narayanan, Deepak; Zhu, Timothy; Dion, David; Moscibroda, Thomas; et al (July 2023, 17th USENIX Symposium on Operating Systems Design and Implementation)

   The infinite capacity of cloud computing is an illusion: in reality, cloud providers cannot always have enough capacity of the right type, in the right place, at the right time to meet all demand. Consequently, cloud providers need to implement admission-control policies to ensure accepted capacity requests experience high availability. However, admission control in the public cloud is hard due to dynamic changes in both supply and demand: hardware might become unavailable, and actual VM consumption could vary for a variety of reasons including tenant scale-outs and fulfillment of VM reservations made by customers ahead of time. In this paper, we design and implement Kerveros, a flexible admission-control system that has three desired properties: i) high computational scalability to handle a large inventory, ii) accurate capacity provisioning for high VM availability, and iii) good packing efficiency to optimize resource usage. To achieve this, Kerveros uses novel bookkeeping techniques to quickly estimate the capacity available for incoming VM requests. Our system has been deployed in Microsoft Azure. Results from both simulations and production confirm that Kerveros achieves more than four nines of availability while sustaining request processing latencies of a few milliseconds. 

   more » « less