Burstiness-aware service level planning for enterprise application clouds

Abstract

Enterprise applications are being increasingly deployed on cloud infrastructures. Often, a cloud service provider (SP) enters into a Service Level Agreement (SLA) with a cloud subscriber, which specifies performance requirements for the subscriber's applications. An SP needs systematic Service Level Planning (SLP) tools that can help estimate the resources needed and hence the cost incurred to satisfy their customers' SLAs. Enterprise applications typically experience bursty workloads and the impact of such bursts needs to be considered during SLP exercises. Unfortunately, most existing approaches do not consider workload burstiness. We propose a Resource Allocation Planning (RAP) technique, which allows an SP to identify a time varying allocation plan of resources to applications that satisfies bursts. Extensive simulation results show that the proposed RAP variants can identify resource allocation plans that satisfy SLAs without exhaustively generating all possible plans. Furthermore, the results show that RAP can permit SPs to more accurately determine the capacity required for meeting specified SLAs compared to other competing techniques especially for bursty workloads.

BDMaaS+: Business-Driven and Simulation-Based Optimization of IT Services in the Hybrid Cloud

“…Therefore, the IC+SLO approach aims at finding a minimal cost allocation that respects the defined SLAs. Let us also specify that some work [17] define SLAs to specify the requirements a VM allocation should provide/guarantee. However, such solutions do not associate a monetary cost to SLO violations but only invalidate the allocations that do not satisfy the defined SLAs [17]- [21].…”

Building efficient and practical machine learning systems

“…As case studies, we design two novel services: Quasi-Shortest-Service-First Scheduling to minimize the cluster-wide average JCT ( §2.4.2), and Cluster Energy Saving to improve the cluster energy efficiency ( §2.4.3). Other services based on machine learning prediction can also be integrated into our framework, e.g., burstiness-aware resource manager [67,68], network-aware job scheduler [69,70], etc. (2) High usability: our framework can be deployed into arbitrary GPU clusters.…”