Transient Guarantees: Maximizing the Value of Idle Cloud Capacity

Shastri, Supreeth; Rizk, Amr; Irwin, David

doi:10.1109/sc.2016.84

Cited by 19 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While this change reduced some of the complexity of using spot VMs and much of their demand-induced volatility, it also eliminated many of their benefits. By not setting the price based on supply and demand, users have less visibility into when their VMs may be revoked, i.e., they could be revoked when the price is above or below their maximum price, which makes it difficult to optimally configure applications to minimize the performance impact of revocations [27]. In addition, users cannot necessarily obtain spot VMs at any time under periods of resource constraint if they are willing to pay a high enough price, i.e., by forcing EC2 to revoke VMs from a lower-paying user.…”

Section: Discussionmentioning

confidence: 99%

“…For example, to enable accessibility for a high enough price, EC2 must be willing to revoke spot VMs from their current users and provision them to users willing to pay more. Such revocations, which are akin to failures, incur an overhead that reduces the performance capacity (and thus value) of spot VMs [27,32]. Many applications also either fail or perform poorly under unexpected and frequent revocations, and require significant modifications to gracefully handle them.…”

Section: Background and Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Cloud Index Tracking

Shastri¹,

Irwin²

2018

Proceedings of the ACM Symposium on Cloud Computing

Self Cite

View full text Add to dashboard Cite

Cloud spot markets rent VMs for a variable price that is typically much lower than the price of on-demand VMs, which makes them attractive for a wide range of large-scale applications. However, applications that run on spot VMs suffer from cost uncertainty, since spot prices fluctuate, in part, based on supply, demand, or both. The difficulty in predicting spot prices affects users and applications: the former cannot effectively plan their IT expenditures, while the latter cannot infer the availability and performance of spot VMs, which are a function of their variable price. Prior work attempts to address this uncertainty by modeling and predicting individual spot prices based on historical data. However, a single model likely does not apply to different spot VMs, since they may have different levels of supply and demand. In addition, cloud providers may unilaterally change spot pricing algorithms, as EC2 has done multiple times, which can invalidate existing price models and prediction methods.To address the problem, we use properties of cloud infrastructure and workloads to show that prices become more stable and predictable as they are aggregated together. We leverage this observation to define an aggregate index price for spot VMs that serves as a reference for what users should expect to pay. We show that, even when the spot prices for individual VMs are volatile, the index price remains stable and predictable. We then introduce cloud index tracking: a migration policy that tracks the index price to ensure applications running on spot VMs incur a predictable cost by migrating to a new spot VM if the current VM's price significantly deviates from the index price. We implement cloud index tracking on EC2, and show that it yields a predictable cost near that of the index price, but with much higher availability compared to prior work, which aggressively migrates to the lowest cost VM.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Background and Motivationmentioning

confidence: 99%

Cloud Index Tracking

Shastri¹,

Irwin²

2018

Proceedings of the ACM Symposium on Cloud Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…AWS allows customers to bid on spot instances while Azure and Google Cloud [29,34] sell them at globally fixed prices. Prior research has explored the economic incentives for spot instances [41,42,50,64,67,100,102,108,110,112,113]. However, prior work used full spot instances to produce memory; Memtrade is more generic, enabling finegrained consumption of excess memory from any instance type.…”

Section: Related Workmentioning

confidence: 99%

Memtrade: A Disaggregated-Memory Marketplace for Public Clouds

Maruf,

Zhong,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

We present Memtrade, the first memory disaggregation system for public clouds. Public clouds introduce a set of unique challenges for resource disaggregation across different tenants, including security, isolation and pricing. Memtrade allows producer virtual machines (VMs) to lease both their unallocated memory and allocated-but-idle application memory to remote consumer VMs for a limited period of time. Memtrade does not require any modifications to host-level system software or support from the cloud provider. It harvests producer memory using an application-aware control loop to form a distributed transient remote memory pool with minimal performance impact; it employs a broker to match producers with consumers while satisfying performance constraints; and it exposes the matched memory to consumers as a secure KV cache. Our evaluation using realworld cluster traces shows that Memtrade provides significant performance benefit for consumers (improving average read latency up to 2.8×) while preserving confidentiality and integrity, with little impact on producer applications (degrading performance by less than 2.1%).

show abstract

“…Dynamic pricing is an efective mechanism to stabilize demands for networking, computing, and utility resources [28,52,53]. Auction-based pricing [55,76] has been introduced in IaaS cloud markets to encourage SPs' consuming spare resources, where they bid against dynamically-set cheaper spot prices with no or little availability guarantees, e.g., Amazon EC2's spot instances [4,42].…”

Section: Related Workmentioning

confidence: 99%

Incentivizing self-capping to increase cloud utilization

Shahrad

Klein

Zheng

et al. 2017

Proceedings of the 2017 Symposium on Cloud Computing

View full text Add to dashboard Cite

Cloud Infrastructure as a Service (IaaS) providers continually seek higher resource utilization to better amortize capital costs. Higher utilization not only can enable higher proit for IaaS providers but also provides a mechanism to raise energy eiciency; therefore creating greener cloud services. Unfortunately, achieving high utilization is diicult mainly due to infrastructure providers needing to maintain spare capacity to service demand luctuations.Graceful degradation is a self-adaptation technique originally designed for constructing robust services that survive resource shortages. Previous work has shown that graceful degradation can also be used to improve resource utilization in the cloud by absorbing demand luctuations and reducing spare capacity. In this work, we build a system and pricing model that enables infrastructure providers to incentivize their tenants to use graceful degradation. By using graceful degradation with an appropriate pricing model, the infrastructure provider can realize higher resource utilization while simultaneously, its tenants can increase their proit. Our proposed solution is based on a hybrid model which guarantees both reserved and peak on-demand capacities over lexible periods. It also includes a global dynamic price pair for capacity which remains uniform during each tenant's Service Level Agreement (SLA) term.We evaluate our scheme using simulations based on real-world traces and also implement a prototype using RUBiS on the Xen hypervisor as an end-to-end demonstration. Our analysis shows that the proposed scheme never hurts a tenant's net proit, but can improve it by as much as 93%. Simultaneously, it can also improve the efective utilization of contracts from 42% to as high as 99%.

show abstract

Transient Guarantees: Maximizing the Value of Idle Cloud Capacity

Cited by 19 publications

References 14 publications

Cloud Index Tracking

Cloud Index Tracking

Memtrade: A Disaggregated-Memory Marketplace for Public Clouds

Incentivizing self-capping to increase cloud utilization

Contact Info

Product

Resources

About