Automatic failure diagnosis is crucial for large microservice systems. Currently, most failure diagnosis methods rely solely on single-modal data (ie using either metrics, logs, or traces). In this study, we conduct an empirical study using real-world failure cases to show that combining these sources of data (multimodal data) leads to a more accurate diagnosis. However, effectively representing these data and addressing imbalanced failures remain challenging. To tackle these issues, we propose DiagFusion , a robust failure diagnosis approach that uses multimodal data. It leverages embedding techniques and data augmentation to represent the multimodal data of service instances, combines deployment data and traces to build a dependency graph, and uses a graph neural network to localize the root cause instance and determine the failure type. Our evaluations using real-world datasets show that DiagFusion, outperforms existing methods in terms of root cause instance localization (improving by 20.9% to 368%) and failure type determination (improving by 11.0% to 169%).

Widely adopted for their scalability and flexibility, modern microservice systems present unique failure diagnosis challenges due to their independent deployment and dynamic interactions. This complexity can lead to cascading failures that negatively impact operational efficiency and user experience. Recognizing the critical role of fault diagnosis in improving the stability and reliability of microservice systems, researchers have conducted extensive studies and achieved a number of significant results. This survey provides an exhaustive review of 98 scientific papers from 2003 to the present, including a thorough examination and elucidation of the fundamental concepts, system architecture, and problem statement. It also includes a qualitative analysis of the dimensions, providing an in-depth discussion of current best practices and future directions, aiming to further its development and application. In addition, this survey compiles publicly available datasets, toolkits, and evaluation metrics to facilitate the selection and validation of techniques for practitioners.

Proactive failure detection of instances is vitally essential to microservice systems because an instance failure can propagate to the whole system and degrade the system's performance. Over the years, many single-modal (i.e., metrics, logs, or traces) databased anomaly detection methods have been proposed. However, they tend to miss a large number of failures and generate numerous false alarms because they ignore the correlation of multimodal data. In this work, we propose AnoFusion, an unsupervised failure detection approach, to proactively detect instance failures through multimodal data for microservice systems. It applies a Graph Transformer Network (GTN) to learn the correlation of the heterogeneous multimodal data and integrates a Graph Attention Network (GAT) with Gated Recurrent Unit (GRU) to address the challenges introduced by dynamically changing multimodal data. We evaluate the performance of AnoFusion through two datasets, demonstrating that it achieves the F₁-score of 0.857 and 0.922, respectively, outperforming the state-of-the-art failure detection approaches.

Cloud systems have become increasingly popular in recent years due to their flexibility and scalability. Each time cloud computing applications and services hosted on the cloud are affected by a cloud outage, users can experience slow response times, connection issues or total service disruption, resulting in a significant negative business impact. Outages are usually comprised of several concurring events/source causes, and therefore understanding the context of outages is a very challenging yet crucial first step toward mitigating and resolving outages. In current practice, on-call engineers with in-depth domain knowledge, have to manually assess and summarize outages when they happen, which is time-consuming and labor-intensive. In this paper, we first present a large-scale empirical study investigating the way on-call engineers currently deal with cloud outages at Microsoft, and then present and empirically validate a novel approach (dubbed Oasis) to help the engineers in this task. Oasis is able to automatically assess the impact scope of outages as well as to produce human-readable summarization. Specifically, Oasis first assesses the impact scope of an outage by aggregating relevant incidents via multiple techniques. Then, it generates a human-readable summary by leveraging fine-tuned large language models like GPT-3.x. The impact assessment component of Oasis was introduced in Microsoft over three years ago, and it is now widely adopted, while the outage summarization component has been recently introduced, and in this article we present the results of an empirical evaluation we carried out on 18 real-world cloud systems as well as a human-based evaluation with outage owners. The results obtained show that Oasis can effectively and efficiently summarize outages, and lead Microsoft to deploy its first prototype which is currently under experimental adoption by some of the incident teams.

Additive key performance indicators (KPIs, such as page view, revenue, error count) with multi-dimensional attributes (such as ISP, Province, DataCenter) are common and important monitoring metrics in Internet companies. When an anomaly happens to an overall KPI, it is critical but challenging to localize the root cause, which is one (or more) combination of attribute values in multiple dimensions. For example, is the total page view (PV) decrease caused by the PV decrease from “Beijing” or “China Mobile in Beijing”, or “Beijing and Shanghai”? However, this task is very challenging for two major reasons. First, the PVs of different combinations are interdependent, thus the PV anomalies at the root cause can cause the changes of many other PVs at different aggregation levels. Second, there could be tens of thousands of combinations to investigate in multi-dimensional attribute space. It is a difficulty to find the root cause from a huge search space. To address the first challenge, our approach HotSpot uses a novel potential score based on the ripple effect for anomaly propagation that we reveal. To address the second challenge, HotSpot adopts the Monte Carlo Tree Search (MCTS) algorithm and a hierarchical pruning strategy. Using the real-world data from a top global search engine, we show that HotSpot achieves a great improvement on effectiveness and robustness, i.e., 95% of all types of root cause cases using HotSpot (compared to only 15% using existing approaches) achieves a F-score over 90%. Operational experiences show that HotSpot can reduce the localization time from more than 1 hour in manual efforts to less than 20 seconds.

Syslogs on switches are a rich source of information for both post-mortem diagnosis and proactive prediction of switch failures in a datacenter network. However, such information can be effectively extracted only through proper processing of syslogs, e.g., using suitable machine learning techniques. A common approach to syslog processing is to extract (i.e., build) templates from historical syslog messages and then match syslog messages to these templates. However, existing template extraction techniques either have low accuracies in learning the “correct” set of templates, or does not support incremental learning in the sense the entire set of templates has to be rebuilt (from processing all historical syslog messages again) when a new template is to be added, which is prohibitively expensive computationally if used for a large datacenter network. To address these two problems, we propose a frequent template tree (FT-tree) model in which frequent combinations of (syslog) words are identified and then used as message templates. FTtree empirically extracts message templates more accurately than existing approaches, and naturally supports incremental learning. To compare the performance of FT-tree and three other template learning techniques, we experimented them on two-years' worth of failure tickets and syslogs collected from switches deployed across 10+ datacenters of a tier-1 cloud service provider. The experiments demonstrated that FT-tree improved the estimation/prediction accuracy (as measured by F1) by 155% to 188%, and the computational efficiency by 117 to 730 times.