AGILE: elastic distributed resource scaling for Infrastructure-as-a-Service

TLDR

Dynamic VM scaling in cloud applications requires future load knowledge, which providers lack, forcing over‑provisioning or SLO violations. AGILE aims to mitigate over‑provisioning and SLO violations by predicting medium‑term resource demand with wavelets and reducing startup times via dynamic VM cloning. It employs wavelet analysis for medium‑term demand forecasting and dynamic VM cloning to accelerate instance startup. Evaluations on RUBiS and Google cluster traces show AGILE improves true‑positive rates by up to 3.42×, cuts false positives to 0.34×, and lowers penalties and user dissatisfaction under target SLO violation rates.

Abstract

Dynamically adjusting the number of virtual machines (VMs) assigned to a cloud application to keep up with load changes and interference from other uses typically requires detailed application knowledge and an ability to know the future, neither of which are readily available to infrastructure service providers or application owners. The result is that systems need to be over-provisioned (costly), or risk missing their performance Service Level Objectives (SLOs) and have to pay penalties (also costly). AGILE deals with both issues: it uses wavelets to provide a medium-term resource demand prediction with enough lead time to start up new application server instances before performance falls short, and it uses dynamic VM cloning to reduce application startup times. Tests using RUBiS and Google cluster traces show that AGILE can predict varying resource demands over the medium-term with up to 3.42× better true positive rate and 0.34× the false positive rate than existing schemes. Given a target SLO violation rate, AGILE can efficiently handle dynamic application workloads, reducing both penalties and user dissatisfaction.