Autonomic mix-aware provisioning for non-stationary data center workloads

Abstract

Online Internet applications see dynamic workloads that fluctuate over multiple time scales. This paper argues that the non-stationarity in Internet application workloads, which causes the request mix to change over time, can have a significant impact on the overall processing demands imposed on data center servers. We propose a novel mix-aware dynamic provisioning technique that handles both the non-stationarity in the workload as well as changes in request volumes when allocating server capacity in Internet data centers. Our technique employs the k-means clustering algorithm to automatically determine the workload mix and a queuing model to predict the server capacity for a given workload mix. We implement a prototype provisioning system that incorporates our technique and experimentally evaluate its efficacy on a laboratory Linux data center running the TPC-W web benchmark. Our results show that our k-means clustering technique accurately captures workload mix changes in Internet applications. We also demonstrate that mix-aware dynamic provisioning eliminates SLA violations due to under-provisioning with non-stationary web workloads, and that it offers a better resource usage by reducing over-provisioning when compared to a baseline provisioning approach that only reacts to workload volume changes. We also present a case study of our provisioning approach on Amazon's EC2 cloud platform.

Quality-of-service in cloud computing: modeling techniques and their applications

“…A queueing network approach is taken in [66] to provision resources for data-center applications. As the workload mix is observed to fluctuate over time, the queueing model is enhanced with a clustering algorithm that determines the workload mix.…”

Self-Tuning Transactional Data Grids: The Cloud-TM Approach

“…However, they all come with the limitations that are proper of the employed techniques: [35], [36] exploit queuing theory, but avoiding to explicitly modeling data contention; [37], [38], [39] rely only on machine learning, thus being prone to poor effectiveness when facing previously unseen workloads.…”

Robust Performance Control for Web Applications in the Cloud

“…Weighted metrics: As pointed out in (Singh et al, 2010), provisioning decisions solely made on the basis of request rate or percentage of CPU usage can incur errors by under-or over-provisioning an application. We propose instead to use a collection of metrics (e.g.…”