The evolution of cloud computing and microservices is gradually supplanting traditional network deployment schemes within data centers. As applications deploy substantial computing resources in data centers, a fierce competition for network services ensues, marked by stringent quality requirements. Simultaneously, safeguarding the time sensitivity of the main flow becomes imperative. However, prevailing container network solutions primarily ensure service quality through scheduling and orchestration, neglecting the influence of computing resources on network service quality under intense resource competition. Consequently, our focus revolves around exploring the preservation of time-sensitive attributes of primary service network links, aiming to enhance the service quality of container networks in highly competitive computing resource environments. This paper introduces a novel container network solution designed to meet the quality of service requirements for time-sensitive data in container networks. Implemented on the Kubernetes platform, this solution establishes an underlay network structure based on Cilium for transmitting network packets requiring performance guarantees and exhibiting time sensitivity. Utilizing eBPF programs with adjusted CPU affinity for packet forwarding, the solution records packets necessitating quality of service guarantees. Network service quality is ensured through algorithms such as Multiqueue Priority, Earliest TxTime First, Enhancements for Scheduled Traffic, etc. The network packets requiring performance guarantees and time sensitivity refer to the TSN (Time-Sensitive Networking) standard. To assess the solution’s effectiveness, we deployed Kubernetes on two directly connected physical servers. Measurements were conducted in scenarios of both idle and highly competitive computing resources, evaluating bandwidth, latency, and jitter of container access packets across different hosts. The results confirm a noteworthy enhancement in container network service quality under highly competitive computing resource environments.

After trading the hardware cost and deployment complexity of inter-microservice communication architecture, the data plane of service mesh has gradually changed from sidecar mode to sidecarless mode. In sidecarless mode, the traffic of microservices need to be processed by zero-trust tunnel, so that the confidentiality, integrity and authentication of application data can be achieved. Thus, the efficiency of zero trust tunnel has a great impact on the performance of inter-microservices communication. However, current zero trust tunnel schemes require additional data transmission and processing, resulting in serious performance degradation. Thus, in this paper, we propose an efficient zero-trust tunnel which is called EZTunnel. Based on a programmable kernel, EZTunnel can execute L4 traffic management and security policies during system calls, thereby improving the communication performance between microservices. Through experiments under different traffic characteristic, we show that EZTunnel can achieve better inter-microservice request response delay, flow completion time and communication bandwidth than current zero-trust tunnel.

In recent years, the integration of Large Language Models (LLMs) with graph neural networks (GNNs) has opened new avenues in handling Text-Attributed Graphs (TAGs). This paper presents a novel approach leveraging LLMs for tackling TAG node classification problems, focusing on text augmentation and structural information enhancement through neighbor information integration. Our method employs a supervised fine-tuning process for LLMs with generated structure-ware rationales that involve structural information from TAGs. Through a combination of structure-aware rationale generation and alignment training, we enhance the learning and integration of graph structural information. We demonstrate the effectiveness of our approach across multiple datasets, showcasing improvements in node classification accuracy. Our contributions include the development of a self-guided approach to generate high-quality rationale text and the fine-tuning of a text embedding model for enhanced graph information understanding, ultimately feeding enriched features into a GNN for final node classification.

Cloud computing and microservices are increasingly supplanting traditional network deployment strategies within data centers due to their inherent flexibility in infrastructure management and rapid scalability. Nevertheless, current approaches often fall short in addressing quality of service (QoS) for virtual networks, especially under conditions of intense resource competition. This shortfall prevents the fulfillment of critical services’ requirements for low latency and predictability. To mitigate this challenge, we propose a cloud-native network service architecture designed to deliver consistently low latency and predictable packet arrival times. This architecture dynamically coordinates and reserves computational resources even during high contention periods, thereby maintaining container network QoS and ensuring the stable availability of microservice applications under extreme conditions. We validated the effectiveness of our proposed solution by deploying multiple container nodes across two directly connected servers and establishing a Kubernetes cluster. By launching a large volume of tasks within a constrained time frame, we assessed the container network’s load, latency, and jitter during peak usage periods. Our results indicate that, although our solution exhibits marginally reduced performance compared to the open-source Kubernetes network plugin under low-load conditions, it significantly outperforms the plugin under high-load scenarios. Specifically, when host CPU usage surpasses 90% and memory usage exceeds 80%, the open-source plugin experiences notable packet loss and long-tail latency distributions. In contrast, our solution demonstrates an 84% reduction in jitter compared to the open-source CNI.

Graph anomaly detection aims to identify graph components, e.g., nodes and edges, that deviate significantly from normal distribution. However, we observe that there exist two challenges that degrade the detection performance, i.e., over-smoothing and over-fitting. First, as anomalies are only a small percentage of the entire dataset, the neighboring nodes of anomalous nodes are mostly normal. As a result, after aggregating multi-hops of neighboring nodes, the representations of anomalies are more similar to normal nodes, making them less distinguishable and causing the over-smoothing problem. Second, over-fitting arises from the lack of labels, caused by the high cost of labeling real-world data. In consequence, the supervision information could be insufficient, leading to model over-fitting. To deal with these two challenges, we propose a framework, named CL-GAD, that leverages cross-layer representations for graph anomaly detection. By utilizing information from different hops of neighboring nodes, we could capture the cross-layer information of anomalies, which is distinct from normal nodes, to solve the over-smoothing aggregation problem. To deal with the over-fitting problem, we introduce an alignment training design that enables the utilization of the vast amount of unlabeled data during training. We conduct extensive experiments on real-world datasets to evaluate our framework, and the results demonstrate its superiority over state-of-the-art baselines.