Analytic modeling of multitier Internet applications

Abstract

Since many Internet applications employ a multitier architecture, in this article, we focus on the problem of analytically modeling the behavior of such applications. We present a model based on a network of queues where the queues represent different tiers of the application. Our model is sufficiently general to capture (i) the behavior of tiers with significantly different performance characteristics and (ii) application idiosyncrasies such as session-based workloads, tier replication, load imbalances across replicas, and caching at intermediate tiers. We validate our model using real multitier applications running on a Linux server cluster. Our experiments indicate that our model faithfully captures the performance of these applications for a number of workloads and configurations. Furthermore, our model successfully handles a comprehensive range of resource utilization-from 0 to near saturation for the CPU-for two separate tiers. For a variety of scenarios, including those with caching at one of the application tiers, the average response times predicted by our model were within the 95% confidence intervals of the observed average response times. Our experiments also demonstrate the utility of the model for dynamic capacity provisioning, performance prediction, bottleneck identification, and session policing. In one scenario, where the request arrival rate increased from less than 1500 to nearly 4200 requests/minute, a dynamic provisioning technique employing our model was able to maintain response time targets by increasing the capacity of two of the tiers by factors of 2 and 3.5, respectively.A preliminary version of this paper appeared in

Dynamic power management for QoS-aware applications

“…Load balancing aims to partition incoming requests among multiple instances of the same application in order to lead to a better utilization of system resources or to provide performance guarantees (e.g., [28,29]). Integrated frameworks such as IBMs WebSphere Application Server and the Tivoli suite combine admission control and load balancing in cluster or data-centre environments [30]. Other DPM solutions are based on system reconfiguration steps that include powering off components while idle, and switching them to low-power operating modes when underutilised (see for example, [31,32,33] and [34] for a recent survey).…”

Improving the performances of JMS-based applications

“…Besides the above-mentioned heuristics-based approaches, another category of work on resource management of Internet services has studied mathematical characterization and analytical modeling of the systems [7,8,9,10,11].…”

“…For instance, in [8,12], authors propose a model for multitier Internet applications. This model captures the structure and the behavior of Internet applications built as cooperative entities (i.e.…”

Scalability and Performance Management of Internet Applications in the Cloud

“…The dormant VMs are prepared with the required software and scaled rapidly when the workload increase, which eliminates the overhead of resource provisioning. A multi-tier system is modeled in [103] and [104] as a closed network of queues. However, because the authors consider a single queue per a tier, their system is able to capture a single resource bottleneck at a time (e.g., CPU utilization or 3.…”

“…This enabled their technique to predict different resources bottlenecks. Nevertheless, modeling the multi-tier system as an open network, as in [98] [23] [32], neglects the impact of the user thinking time, which is an unrealistic assumption for Internet applications [71] [103] [104]. In general, implementing the scalability to Internet applications using queuing theory is complex.…”