Traditional server failure prediction methods predominantly rely on single-modality data such as system logs or system status curves. This reliance may lead to an incomplete understanding of system health and impending issues, proving inadequate for the complex and dynamic landscape of contemporary cloud computing environments. The potential of multimodal data to provide comprehensive insights is widely acknowledged, yet the lack of a holistic dataset and the challenges inherent in integrating features from both structured and unstructured data have impeded the exploration of multimodal-based server failure prediction. Addressing these challenges, this paper presents an industrial-scale, comprehensive dataset for server failure prediction, comprising nearly 80 types of structured and unstructured data sourced from real-world industrial cloud systems 1. Building on this resource, we introduce MISP, a model that leverages multimodal fusion techniques for server failure prediction. MISP transforms multimodal data into multi-dimensional sequences, extracts and encodes features both within and across the modalities, and ultimately computes the failure probability from the synthesized features. Experiments demonstrate that MISP significantly outperforms existing methods, enhancing prediction accuracy by approximately 25% over previous state-of-the-art approaches.
Log-based failure prediction helps identify and mitigate system failures ahead of time, increasing the reliability of cloud elastic computing systems. However, most existing log-based failure prediction approaches only focus on semantic information, and do not make full use of the information contained in the timestamps of log messages. This paper proposes time-aware attention-based transformer (TAAT), a failure prediction approach that extracts semantic and temporal information simultaneously from log messages and their timestamps. TAAT first tokenizes raw log messages into specific exceptions, and then performs: 1) exception sequence embedding that reorganizes the exceptions of each node as an ordered sequence and converts them to vectors; 2) time relation estimation that computes time relation matrices from the timestamps; and, 3) time-aware attention that computes semantic correlation matrices from the exception sequences and then combines them with time relation matrices. Experiments on Alibaba Cloud demonstrated that TAAT achieves an approximately 10% performance improvement compared with the state-of-the-art approaches. TAAT is now used in the daily operation of Alibaba Cloud. Moreover, this paper also releases the real-world cloud computing failure prediction dataset used in our study, which consists of about 2.7 billion syslogs from about 300,000 node controllers during a 4-month period. To our knowledge, this is the largest dataset of its kind, and is expected to be very useful to the community.
Seasonal-trend decomposition (STD) is a crucial task in time series data analysis. Due to the challenges of scalability, there is a pressing need for an ultra-fast online algorithm. However, existing algorithms either fail to handle long-period time series (such as OnlineSTL), or need time-consuming iterative processes (such as OneShotSTL). Therefore, we propose BacktrackSTL, the first non-iterative online STD algorithm with period-independent O(1) update complexity. It is also robust to outlier, seasonality shift and trend jump because of the combination of outlier-resilient smoothing, non-local seasonal filtering and backtrack technique. Experimentally, BacktrackSTL decomposes a value within 1.6 μs, which is 15X faster than the state-of-the-art online algorithm OneShotSTL, while maintaining comparable accuracy to the best offline algorithm RobustSTL. We have also deployed BacktrackSTL on the top of Apache Flink to decompose monitoring metrics in Alibaba Cloud for over a year. Besides, we have open-sourced the artifact of this proposal on GitHub.