Dilina Dehigama

Dilina Dehigama, Shyam Jesalpura, David Schall et al.

Online services strive to maintain application responsiveness even when the traffic is unpredictable and fluctuating. Today's online services are commonly deployed as chains of microservices, each microservice packaged as one or more containers inside virtual machines (VMs). While performant and affordable when the load is steady, VM-based deployments are known to be slow to scale when the load spikes, resulting in degraded performance for end-users of the service. To avoid such performance degradations, service providers can over-provision their deployments; however, such a strategy is costly and inefficient, leaving resources under-utilized for extended periods. To address the challenge of unpredictable load spikes, we propose Flare, a hybrid microservice architecture that combines VMs with serverless computing. Flare utilizes VMs to cost-effectively handle steady workloads and leverages serverless elasticity to absorb traffic spikes. When a spike occurs, Flare detects which specific service(s) are overloaded and shifts the excess load of only those services to serverless, thus minimizing the cost overhead. Flare seamlessly integrates into existing auto-scaling and serverless infrastructure, requiring minimal changes to the control plane and no modifications to the application.

Dilina Dehigama, Shyam Jesalpura, Zeyu Xu et al.

Cloud-based online services face significant sub-second load fluctuations while needing to meet strict Service Level Objectives (SLOs). Cluster operators often over-provision resources to protect SLOs, sacrificing utilization and cost efficiency. Existing reactive and proactive autoscalers, serverless (FaaS) deployments, and VM/FaaS hybrid systems fail to reconcile strict SLO compliance with low cost and high utilization under fine-grained load fluctuation. We introduce Spandana, an architecture that addresses this trade off by decoupling SLO enforcement from cost optimization. A lightweight controller colocated with each application VM enforces SLOs by steering each arriving request between the VM and FaaS. Requests that can meet the SLO stay on the VM; the remaining requests are forwarded to a stock FaaS layer such as AWS Lambda. For cost optimization, Spandana's resource allocator determines the most-efficient VM provisioning by accounting for VM cost, FaaS cost, and traffic volatility, allowing the VM pool to run at high utilization. Our evaluation shows that Spandana maintains strict SLO adherence, achieves 76-86% CPU utilization, and reduces cost by 5-44% over three SOTA baselines.