Jun 2026· IEEE Conference on Network Softwarization· pp. 225-230· 0 citations· 19 references
Computer Science
Abstract
Efficient resource management remains a main challenge in Kubernetes, where scaling plays a key role in ensuring that resource provisioning adapts to workload variability. Vertical Pod Autoscaler (VPA) is the default mechanism in Kubernetes for vertical scaling, but its reliance on evicting pods to apply new resource values often disrupts applications. To address this, Kubernetes introduced In-Place Resource Resizing (IRR), which allows CPU and memory requests to be updated directly on running pods without eviction. In this paper, we experimentally evaluate VPA combined with IRR under dynamic and longrunning workloads. We designed and implemented a trafficdriven ns-3 workload to generate realistic CPU and memory variations over time, and developed a controller that bridges VPA recommendations with IRR to enable automated, eviction-free vertical scaling while considering QoS-related constraints defined by Kubernetes. Our evaluation analyzes the stability and responsiveness of IRR under different workload intensities, and extends the analysis to power consumption. The results show that eviction-free vertical scaling with IRR provides more stable resource and power behavior compared to the traditional VPA.
Modern cloud-native applications increasingly rely on Kubernetes to orchestrate large-scale, heterogeneous workloads. However, experimenting with its cluster-level mechanisms in a scalable way, such as its diverse scheduling policies, remains difficult in production environments due to operational costs and limited observability. This demonstration showcases KubeTwin, a practical framework that creates and maintains a live Digital Twin of a Kubernetes cluster. KubeTwin enables the modeling of multi-cluster infrastructures, including edge and cloud nodes, heterogeneous resource capacities, and network latencies, allowing for safe experimentation, debugging, and what-if analysis without disrupting production workloads. Through an interactive demonstration, we show how researchers and developers can leverage KubeTwin to (i) assess the performance of workloads under diverse traffic patterns and (ii) evaluate diverse scheduling strategies under different infrastructure scenarios. The demo highlights how Kubernetes Digital Twins can bridge the gap between simulation and real-world experimentation, providing a powerful tool for both operational decision-making and research prototyping.
José Santos, D. Borsatti, Walter Cerroni et al.· IEEE Conference on Network S...· 0 citations
The widespread adoption of microservices architectures on Kubernetes has introduced significant challenges in resource management, particularly the inadequacy of default load balancing under dynamic workloads and issues with pod resource sharing under contention. This paper proposes an integrated auto-scaling platform that combines the Horizontal Pod Autoscaler (HPA), Metrics Server, and Prometheus to dynamically optimize resource utilization in a Kubernetes-in-Docker (KIND) cluster. The experimental platform was deployed on an Ubuntu 22.04 host with a three-node KIND cluster (one master, two workers), using Kubernetes v1.27.3 and Docker v24.0.7, with performance evaluated through CPU utilization and requests per second (RPS) metrics collected via Prometheus and visualized in Grafana. Results demonstrate that HPA effectively responds to workload increases by provisioning additional pods, maintaining system stability and throughput during high-demand periods, with CPU usage and RPS exhibiting predictable scaling behavior aligned with the 15-second Metrics Server scraping interval. The novelty of this work lies in the systematic integration of HPA with Prometheus custom metrics within a KIND environment, extending evaluation across multiple lightweight Kubernetes distributions including microk8s and minikube. This approach enhances scalability, computational efficiency, and cost-effectiveness for microservice-based systems.
Shamsuddeen Rabiu, Sani Muhammad Tanko, Eli Adama Jiya· Journal of Basics and Applie...· 0 citations
A comprehensive review of Kubernetes scheduling strategies published between January 2023 and January 2026 is presented and a multi-dimensional taxonomy is established that categorizes scheduling approaches based on common objectives, modification methods, optimization methodologies, targeted workloads, evaluation methods, scheduling scopes, and performance metrics.
Mohammed Alhakimi, R. Latip· Computers· 0 citations
Efficient workload scheduling is central to the performance, scalability, and cost-effectiveness of modern clouds. In the most popular cloud platform today, Kubernetes (K8s), the scheduler can be extended with multiple scheduling plugins, enabling fine-grained control over scheduling decisions. However, cloud providers often lack clear insights into the trade-offs of individual placement strategies and resort to combining multiple plugins without a clear rationale. This uncertainty creates a gap in understanding which scheduling configuration yields optimal results for a given application or traffic pattern under specific infrastructure conditions. Thus, this paper investigates the implications of different scheduling strategies in K8s by leveraging KubeTwin (KT), a high-fidelity simulator for the K8s platform designed for reproducible experimentation. This work extended KT with advanced scheduling capabilities to evaluate the impact of single and combined scheduling plugins across diverse workloads and infrastructure conditions, focusing on key aspects such as performance, fairness, and resource utilization. The results highlight that Node-affinity and Diktyo single-purpose plugins consistently outperform multi-objective scheduling combinations, achieving the lowest deployment costs (below 50 price/day), shortest queue times (under 50 ms), and fastest response times (below 200 ms). In contrast, combined strategies, such as Balanced, result in significantly higher costs and higher latency. This study shows that combining multiple optimization criteria within a single scheduling strategy often degrades performance, whereas targeted, single-objective plugins deliver robust and predictable behavior across heterogeneous infrastructures and workload patterns.
José Santos, D. Borsatti, Walter Cerroni et al.· IEEE Conference on Network S...· 1 citation
Serverless computing has emerged as an efficient paradigm for scalable and cost-effective cloud application deployment through dynamic resource allocation. However, widely used autoscaling mechanisms, particularly CPU-threshold-based approaches such as the Knative Pod Autoscaler (KPA), often exhibit limited adaptability under highly dynamic and bursty workloads, leading to increased latency, SLA violations, scaling instability, and inefficient resource utilization. To address these limitations, this paper proposes a hybrid congestion-aware autoscaling framework for serverless platforms inspired by TCP slow-start and congestion control principles. The proposed method integrates multiple runtime metrics, including workload intensity, CPU utilization, memory usage, request latency, queue congestion, and TCP-inspired congestion window dynamics, into a unified weighted decision model to achieve both responsiveness and stability. The framework is implemented in a Knative-based Kubernetes environment and evaluated using 100,000 requests under 100 concurrent users, with comparisons against Knative KPA and an LSTM-based predictive autoscaling baseline. Experimental results demonstrate that the proposed approach consistently outperforms both baselines across key performance metrics. Specifically, it reduces P50, P90, and P99 response times to 0.29 s, 0.56 s, and 1.12 s, respectively, compared to 0.41 s, 0.88 s, and 2.31 s in KPA. Average response time is reduced to 0.32 s, while throughput increases to 246.80 req/s. In addition, the proposed method improves resource efficiency to 0.87 and decreases total execution time to 405.19 s. Stability is also significantly enhanced, with scaling oscillation rate reduced to 1.5, SLA violation rate reduced to 1.9%, and cold start delay reduced to 0.49 s. Overall, the results confirm that the proposed TCP-inspired hybrid autoscaling approach significantly improves latency performance, scalability, and resource efficiency in serverless environments.
Mohammad Tari, Mostafa Ghobayee-Arani, Jafar Pouramini· International Journal of Clo...· 0 citations
Cloud‑native progressive delivery orchestrators reduce deployment risk by automating canary deployment rollback procedures, dramatically reducing mean time to recover from deployment failures. However, existing research predominantly evaluates these tools in hyperscale environments, masking the transient computational overhead they introduce in resource‑constrained edge deployments. This study empirically evaluates and compares the automated incident mitigation latency and computational resource volatility of Flagger and Argo Rollouts within a strictly resource‑constrained Kubernetes environment. A low virtual central processing unit Kubernetes testbed was provisioned using Talos Linux with strict hypervisor‑level central processing unit pinning, simulating edge computing conditions. Deterministic fault injection spanning four fault classes, two workload runtimes, and two network topology configurations was executed across thirty trials. A Shapiro-Wilk normality assessment, Welch t-test, Mann-Whitney U test, Cohen's d, and 95% confidence intervals were applied to compare temporal and computational metrics. Memory utilization remained statically bounded, averaging 24.01 megabytes for Flagger and 35.47 megabytes for Argo Rollouts. Under standard fault conditions, neither orchestrator demonstrated a consistent temporal advantage. However, under memory exhaustion progressing to CrashLoopBackOff, Argo Rollouts recovered in a mean of 29.67 seconds against Flagger's 166.79 seconds, a statistically significant 5.6-fold degradation with a large effect size. Argo Rollouts sustained transient central processing unit surges of 159 to 168 millicpu against Flagger's bounded ceiling of 17 to 18 millicpu. Progressive delivery automation introduces non‑negligible and fault-type-dependent computational overhead in resource‑constrained environments. Flagger is recommended for strict resource predictability in threshold-breach environments, while Argo Rollouts is recommended where broader fault-type resilience is operationally critical.
Gagah Syuja Saka Abdullah, Rama Aria Megantara· SinkrOn· 0 citations