Uptime-Optimized Cloud Architecture as a Brokered Service

TL;DR

This paper introduces a framework that models and optimizes cloud architectures to meet uptime SLAs cost-effectively, addressing the gap in existing solutions that lack mathematical SLA mapping.

Contribution

It presents a novel model-based framework for automatically selecting the most cost-effective high-availability cloud architecture to meet specific uptime SLAs.

Findings

Framework effectively determines minimal TCO solutions for given SLAs

Model-based approach reduces over-engineering and SLA violations

Supports automated, SLA-driven cloud architecture design

Abstract

Enterprise workloads usually call for an uptime service level agreement (SLA) at the pain of contractual penalty in the event of slippage. Often, the strategy is to introduce ad-hoc HA (High Availability) mechanisms in response. Implemented solutions that we surveyed do not mathematically map their availability model to the required uptime SLA and to any expected penalty payout. In most client cases that we observed, this either resulted in an over-engineered solution that had more redundancies than was required, or in an inadequate solution that could potentially slip on the system uptime SLA stipulated in the contract. In this paper, we propose a framework backed by a model, to automatically determine the HA-enabled solution with the least TCO (total cost of ownership) for a given uptime SLA and slippage penalty. We attempt to establish that our work is best implemented as a brokered service that recommends an uptime-optimized cloud architecture.