The convergence of microservice architectures and serverless computing promises an elastic and cost-efficient model for modern cloud applications that often span multiple geo-distributed regions. However, prevailing serverless orchestrators that prioritize resource utilization or simple cold-start mitigation often prove suboptimal concerning SLO compliance and cost-efficiency in this emerging use case. In this paper, we present Krysha, an adaptive orchestration framework that jointly optimizes function scheduling and resource allocation for geo-distributed serverless microservices. Krysha employs a novel bi-level scheduling strategy: global-level early-binding to regions for fast function dispersion, coupled with regional-level late-binding to compute nodes for optimized resource use and cost. Moreover, Krysha achieves fine-grained resource allocation by decoupling CPU and memory provisioning and applying in-place vertical scaling on individual function instances. These capabilities are guided by a comprehensive cost model and practical online optimization techniques. Our extensive evaluation shows that Krysha can achieve up to 74.7% cost savings in scaled deployments compared to state-of-the-art alternatives while maintaining SLO requirements.

Resource orchestration and configuration parameter search are key concerns for container-based infrastructure in cloud data centers. Large configuration search space and cloud uncertainties are often mitigated using contextual bandit techniques for resource orchestration including the state-of-the-art Drone orchestrator. Complexity in the cloud provider environment due to varying numbers of virtual machines introduces variability in workloads and resource metrics, making orchestration decisions less accurate due to increased nonlinearity and noise. Ksurf, a state-of-the-art variance-minimizing estimator method ideal for highly variable cloud data, enables optimal resource estimation under conditions of high cloud variability. This work evaluates the performance of Ksurf on estimation-based resource orchestration tasks involving highly variable workloads when employed as a contextual multi-armed bandit objective function model for cloud scenarios using Drone. Ksurf enables significantly lower latency variance of over$40\%$at p95 and p99, demonstrates significant reduction in CPU and master node memory usage on Kubernetes, resulting in a$7\%$cost savings in average worker pod count on$VarBench$Kubernetes benchmark.

Serverless computing promises on-demand elasticity and simplified deployment, yet today's production-grade serverless platforms remain tied to a single-provider, centrally scheduled control plane. This centralized scheduling model faces mounting challenges in handling heterogeneous policies, data governance constraints, and dynamic workloads for the modern web, where applications increasingly span multiple geo-distributed autonomous administrative domains. In this paper, we present Mocha, a decentralized, policy-aware framework for scheduling serverless functions across a federated ecosystem. At its core, Mocha proposes a hierarchically structured distributed hash table that embeds geographical and organizational context to facilitate locality-aware scheduling without any central authority. By implementing a formally specified compliance engine at each domain, Mocha guarantees that all regulatory, locality, and resource constraints are honored for function placement decisions. Experiments show that Mocha reduces scheduling tail latency by 4–9× compared to alternatives while maintaining full policy adherence.

Conventional consensus algorithms, such as Paxos and Raft, encounter inefficiencies when applied to large-scale distributed systems due to the requirement of waiting for replies from a majority of nodes. To address these challenges, we propose Cabinet, a novel consensus algorithm that introduces dynamically weighted consensus, allocating distinct weights to nodes based on any given failure thresholds. Cabinet dynamically adjusts nodes' weights according to their responsiveness, assigning higher weights to faster nodes. The dynamic weight assignment maintains an optimal system performance, especially in large-scale and heterogeneous systems where node responsiveness varies. We evaluate Cabinet against Raft with distributed MongoDB and PostgreSQL databases using YCSB and TPC-C workloads. The evaluation results show that Cabinet outperforms Raft in throughput and latency under increasing system scales, complex networks, and failures in both homogeneous and heterogeneous clusters, offering a promising high-performance consensus solution.

The advances in virtualization technologies have sparked a growing transition from virtual machine (VM)-based to container-based infrastructure for cloud computing. From the resource orchestration perspective, containers' lightweight and highly configurable nature not only enables opportunities for more optimized strategies, but also poses greater challenges due to additional uncertainties and a larger configuration parameter search space. Towards this end, we propose Drone, a resource orchestration framework that adaptively configures resource parameters to improve application performance and reduce operational cost in the presence of cloud uncertainties. Built on Contextual Bandit techniques, Drone is able to achieve a balance between performance and resource cost on public clouds, and optimize performance on private clouds where a hard resource constraint is present. We show that our algorithms can achieve sub-linear growth in cumulative regret, a theoretically sound convergence guarantee, and our extensive experiments show that Drone achieves an up to 45% performance improvement and a 20% resource footprint reduction across batch processing jobs and microservice workloads.

As error/failure rates in supercomputers are projected to grow, computationally intensive scientific applications that lever-age large-scale parallelization will suffer from the increased error rate. In this work, we apply "coded computing" to protein folding simulations in an error-prone environment. We implemented the fast Fourier Poisson method for solving electrostatic equations at each time step of the simulation, and we utilize coded FFT algorithm to protect the compute-intensive FFT algorithm from soft errors. Through experiments on Amazon AWS, we showed that coded protein folding can be implemented with less than 10% overhead in total simulation time, and also showed that coded computing approach is faster than classical checkpointing method when the error rate is high.