Detecting large-scale system problems by mining console logs
The DOI matches its Crossref record; 43 of the 44 references it cites were found in a registry or an index.
Abstract
Surprisingly, console logs rarely help operators detect problems in large-scale datacenter services, for they often consist of the voluminous intermixing of messages from many software components written by independent developers. We propose a general methodology to mine this rich source of information to automatically detect system runtime problems. We first parse console logs by combining source code analysis with information retrieval to create composite features. We then analyze these features using machine learning to detect operational problems. We show that our method enables analyses that are impossible with previous methods because of its superior ability to create sophisticated features. We also show how to distill the results of our analysis to an operator-friendly one-page decision tree showing the critical messages associated with the detected problems. We validate our approach using the Darkstar online game server and the Hadoop File System, where we detect numerous real problems with high accuracy and few false positives. In the Hadoop case, we are able to analyze 24 million lines of console logs in 3 minutes. Our methodology works on textual console logs of any size and requires no changes to the service software, no human input, and no knowledge of the software's internals.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Besides, Log2Vec also adopts MIMICK [49], an approach of inducing word embedding from character-level features to handle OOV words to improve anomaly detection performance.”
From Log-based Anomaly Detection Without Log Parsing (2021) · cites this paper as [49]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Jolliffe, I. (2005) · Encyclopedia of Statistics in Behavioral Science · doi:10.1002/0470013192.bsa501 · Cited by 14,310
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Term-weighting approaches in automatic text retrieval
Salton, G., & Buckley, C. (1988) · Information Processing & Management · doi:10.1016/0306-4573(88)90021-0 · Cited by 9,740 · cited 2×
“We have investigated a variety of such methods and have found that Principal Component Analysis (PCA) [5, 16] combined with term-weighting techniques from information retrieval [23, 26] yields excellent anomaly detection results on both feature matrices, while requiring little parameter tuning.”
MethodWitten, I. H. (2008) · Cited by 9,143
Data mining: practical machine learning tools and techniques with Java implementations
Witten, I. H., & Frank, E. (2002) · ACM SIGMOD Record · doi:10.1145/507338.507355 · Cited by 5,137
The text mining handbook: advanced approaches in analyzing unstructured data
(2007) · Choice Reviews Online · doi:10.5860/choice.44-5684 · Cited by 1,598
Control Procedures for Residuals Associated With Principal Component Analysis
Jackson, J. E., & Mudholkar, G. S. (1979) · Technometrics · doi:10.1080/00401706.1979.10489779 · Cited by 1,237
Diagnosing network-wide traffic anomalies
Lakhina, A., Crovella, M., & Diot, C. (2004) · Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications · doi:10.1145/1015467.1015492 · Cited by 1,039
YALE: rapid prototyping for complex data mining tasks
Mierswa, I., Wurst, M., Klinkenberg, R., Scholz, M., & Euler, T. (2006) · Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1150402.1150531 · Cited by 1,010
Pinpoint: problem determination in large, dynamic Internet services
Chen, M. Y., Kiciman, E., Fratkin, E., Fox, A., & Brewer, E. (2003) · Proceedings International Conference on Dependable Systems and Networks · doi:10.1109/dsn.2002.1029005 · Cited by 835 · cited 1×
“, 2002; Ma & Hellerstein, 2001) to more detailed tracing such as execution paths (Chen et al., 2002; Chen & Brewer, 2004).”
BackgroundSelf-citation
Research works printed but not linked: 4
- [2] D. Borthakur. The hadoop distributed file system: Architecture and design. Hadoop Project Website, 2007. -
- [5] R. Dunia and S. J. Qin. Multi-dimensional fault diagnosis using a subspace approach. In Proc. ACC , 1997. -
- [8] R. Fonseca and et al. Xtrace: A pervasive network tracing framework. In In Proc. NSDI , 2007. -
- [14] W. Jiang and et al. Understanding customer problem troubleshooting from storage system logs. In Proceedings of USENIX FAST'09 , 2009. -
Cited by
Items 201–300 of 1,004
EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records
Niu, H., Omitaomu, O. A., Langston, M. A., Olama, M., Özmen, Ö., Klasky, H. B., Laurio, A., Ward, M. C., & Nebeker, J. R. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104605 · Cited by 59
MoniLog: An Automated Log-Based Anomaly Detection System for Cloud Computing Infrastructures
Vervaet, A. (2021) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde51399.2021.00317 · Cited by 59
Zhang, C., Wang, X., Zhang, H., Zhang, H., & Han, P. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3125967 · Cited by 49
MLog: Mogrifier LSTM-Based Log Anomaly Detection Approach Using Semantic Representation
Fu, Y., Liang, K., & Xu, J. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3289488 · Cited by 49
“For unsupervised approaches including PCA, LogCluster and DeepLog, only normal log sequences in the training dataset are used to build the anomaly prediction model.”
BackgroundMethodInfluentialAn improved partitioning mechanism for optimizing massive data analysis using MapReduce
Slagter, K. D., Hsu, C., Chung, Y., & Zhang, D. (2013) · The Journal of Supercomputing · doi:10.1007/s11227-013-0924-9 · Cited by 54
“Therefore, there has been a variety of research on MapReduce in order to improve the performance of the framework or the performance of specific applications like datamining [14, 22], graph mining [5], text analysis [20], or genetic algorithms [6, 21] that run on the framework.”
BackgroundALchemist: Fusing Application and Audit Logs for Precise Attack Provenance without Instrumentation
Yu, L., Ma, S., Zhang, Z., Tao, G., Zhang, X., Xu, D., Urias, V. E., Han, L., Ciocarlie, G. F., Yegneswaran, V., et al. (2021) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2021.24445 · Cited by 71
“…is related to data provenance [65], [17], [62], [21], [15], [64], [37], [55], [30] [69], audit logging [57], [41], [40], [62], [18], [61], [36], [75], [74], log parsing [79], [70], [58], [34], [66], [26] and causality analysis [80], [42], [41], [40], [35], [45], [52], [53], [54], [43] [77], [78].”
Zeufack, V., Kim, D., Seo, D., & Lee, A. (2021) · High-Confidence Computing · doi:10.1016/j.hcc.2021.100030 · Cited by 49
“Here, we can mention PCA [6] which extracts state ratio vectors and message count vectors and uses Principal Component Analysis to detect anomalies.”
InfluentialOn Predictability of System Anomalies in Real World
Tan, Y., & Gu, X. (2010) · Proceedings - International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems · doi:10.1109/mascots.2010.22 · Cited by 49
On the effectiveness of log representation for log-based anomaly detection
Wu, X., Li, H., & Khomh, F. (2023) · Empirical Software Engineering · doi:10.1007/s10664-023-10364-1 · Cited by 53
“…Du et al. 2017; Fu et al. 2009; He et al. 2016b; Le and Zhang 2021; Lu et al. 2018; Meng et al. 2019; Nedelkoski et al. 2020; Wang et al. 2018; Xu et al. 2009; Zhang et al. 2019), failure diagnosis (Fu et al. 2013; Yuan et al. 2010), performance regression analysis (Chow et al. 2014; Liao et…”
BackgroundMethodInfluentialMPI: multiple perspective attack investigation with semantics aware execution partitioning
Zhang, X., Xu, D., Ma, S., Zhai, J., Wang, F., & Lee, K. H. (2017) · Rutgers University Community Repository (Rutgers University) · doi:10.7282/00000295 · Cited by 48
An exploratory study on assessing the energy impact of logging on Android applications
Chowdhury, S., Nardo, S. D., Hindle, A., & Jiang, Z. M. (2017) · Empirical Software Engineering · doi:10.1007/s10664-017-9545-x · Cited by 56
“Software developers, testers and operators leverage logs extensively to monitor the health of their applications (Xu et al. 2009a), to verify the correctness of their tests (Jiang et al. 2008) and to debug execution failures (Yuan et al. 2010; Yuan et al. 2011).”
BackgroundOliner, A. J., Ganapathi, A., & Xü, W. (2011) · Queue · doi:10.1145/2076796.2082137 · Cited by 48
From logs to Stories: Human-Centred Data Mining for Cyber Threat Intelligence
Afzaliseresht, N., Miao, Y., Michalska, S., Liu, Q., & Wang, H. (2020) · IEEE Access · doi:10.1109/access.2020.2966760 · Cited by 47
“For example, a decision tree (as a level of analysis display) in the work by Xu et al. [14] was used to demonstrate how the system decides to assign a normal or abnormal label to a log record.”
MethodLogStamp: Automatic Online Log Parsing Based on Sequence Labelling
Tao, S., Meng, W., Cheng, Y., Zhu, Y., Liu, Y., Du, C., Han, T., Zhao, Y., Wang, X., & Yang, H. (2022) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/3543146.3543168 · Cited by 54
ELT: Efficient Log-based Troubleshooting System for Cloud Computing Infrastructures
Kc, K., & Gu, X. (2011) · 2011 IEEE 30th International Symposium on Reliable Distributed Systems · doi:10.1109/srds.2011.11 · Cited by 47
“This assumption is similar to previous console log analysis system [20].”
BackgroundMethodResultInfluentialZhang, Y., Makarov, S., Ren, X., Lion, D., & Yuan, D. (2017) · ACM SIGOPS Symposium on Operating Systems Principles (SOSP) · doi:10.1145/3132747.3132768 · Cited by 47
“Before the event chaining analysis, Pensieve parses all the log messages from the log file by mapping them to LPSes and extracting variable values (log parsing has been extensively discussed in prior works [25, 27, 31]).”
MethodDoomsday: Predicting Which Node Will Fail When on Supercomputers
Das, A., Mueller, F., Hargrove, P., Roman, E., & Baden, S. B. (2018) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/sc.2018.00012 · Cited by 55
“TBP [9] [21] [22] [32] [33] No Source Code X X X X × X Lead Time X × X × × × Location X × X × × × Prediction X X X × × × Scalability X × × X × X Unsupervised X X × X X X”
BackgroundDemonstration-Free: Towards More Practical Log Parsing with Large Language Models
Xiao, Y., Le, V.-H., & Zhang, H. (2024) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3691620.3694994 · Cited by 61
“A straightforward method of log parsing involves matching raw log messages with logging statements within the source code [40, 56] or designing handcrafted regular expressions to extract log templates and parameters [62].”
FLAP: An End-to-End Event Log Analysis Platform for System Management
Li, T., Jiang, Y., Zeng, C., Xia, B., Liu, Z., Zhou, W., Zhu, X., Wang, W., Zhang, L., Wu, J., et al. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098022 · Cited by 45
“Many Linux services, such as openssh, Kerboros 5, and Samba 3 [27], also have similar number of event types.”
BackgroundLogAssist: Assisting Log Analysis Through Log Summarization
Locke, S., Li, H., Chen, T.-H., Shang, W., & Liu, W. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2021.3083715 · Cited by 45
An empirical study of the impact of log parsers on the performance of log-based anomaly detection
Fu, Y., Yan, M. L., Xu, Z., Xia, X., Zhang, X., & Yang, D. (2022) · Empirical Software Engineering · doi:10.1007/s10664-022-10214-6 · Cited by 53
“Xu et al. (2009) proposed to apply PCA for anomaly detection based on their four key insights.”
MethodInfluentialWurzenberger, M., Höld, G., Landauer, M., & Skopik, F. (2023) · Computers & Security · doi:10.1016/j.cose.2023.103631 · Cited by 50
SMARTLOG: Place error log statement by deep understanding of log intention
Jia, Z., Li, S., Liu, X., Liao, X., & Liu, Y. (2018) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner.2018.8330197 · Cited by 45
“High-quality error logs can greatly ease the failure diagnosis and reduce the system recovery time, and thus different log handling technologies are proposed such as log enhancement [2], log characterization [3], [4], [5] and postmortem analysis [6], [7], [8], [9].”
BackgroundPredictDeep: Security Analytics as a Service for Anomaly Detection and Prediction
Elsayed, M. A., & Zulkernine, M. (2020) · IEEE Access · doi:10.1109/access.2020.2977325 · Cited by 55
“The dataset represents a benchmark used in several related studies [13]–[16].”
BackgroundMethodInfluentialRobust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Models
Ott, H., Bogatinovski, J., Acker, A., Nedelkoski, S., & Kao, O. (2021) · 2021 IEEE/ACM International Workshop on Cloud Intelligence (CloudIntelligence) · doi:10.1109/cloudintelligence52565.2021.00013 · Cited by 36
Loader: A Log Anomaly Detector Based on Transformer
Xiao, T. Y., Quan, Z., Wang, Z.-J., Le, Y., Du, Y., Liao, X., Li, K., & Li, K. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3280575 · Cited by 47
“A. Experimental Settings 1) Datasets: We evaluate our approach Loader based on three public log datasets, i.e., the HDFS log dataset [7], the Blue Gene/L log dataset [41], and the Thunderbird log dataset [41] (denoted by HDFS , BGL , and Thunderbird respectively).”
BackgroundMethodInfluentialA Survey on the Applications of Semi-supervised Learning to Cyber-security
Mvula, P. K., Branco, P., Jourdan, G.-V., & Viktor, H. L. (2024) · ACM Computing Surveys · doi:10.1145/3657647 · Cited by 61
LogGT: Cross-system log anomaly detection via heterogeneous graph feature and transfer learning
Wang, P., Zhang, X., Cao, Z., Xu, W., & Li, W. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124082 · Cited by 47
Self-citationAnomaly detection techniques for a web defacement monitoring service
Davanzo, G., Medvet, E., & Bartoli, A. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.04.038 · Cited by 47
Log-Based Anomaly Detection of CPS Using a Statistical Method
Harada, Y., Yamagata, Y., Mizuno, O., & Choi, E.-H. (2017) · International Workshop on Empirical Software Engineering in Practice (IWESEP) · doi:10.1109/iwesep.2017.12 · Cited by 44
GLAD-PAW: Graph-Based Log Anomaly Detection by Position Aware Weighted Graph Attention Network
Wan, Y., Liu, Y., Wang, D., & Wen, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-75762-5_6 · Cited by 44
Graph Neural Networks based Log Anomaly Detection and Explanation
Li, Z., Shi, J., & van Leeuwen, M. (2024) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3639478.3643084 · Cited by 43
Large language model-based optical network log analysis using LLaMA2 with instruction tuning
Pang, Y., Zhang, M., Liu, Y., Li, X., Wang, Y., Huan, Y., Liu, Z., Li, J., & Wang, D. (2024) · Journal of Optical Communications and Networking · doi:10.1364/jocn.527874 · Cited by 49
“ONLA-LLM is compared with the following baselines and GPT-4 in anomaly detection and classification: Principal component analysis (PCA) [42]: PCA is an unsupervised machine learning algorithm.”
MethodArtificial Intelligence for Software Engineering: The Journey So Far and the Road Ahead
Ahmed, I., Aleti, A., Cai, H., Chatzigeorgiou, A., He, P., Hu, X., Pezzè, M., Poshyvanyk, D., & Xia, X. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3719006 · Cited by 54
“For example, the most widely used log-based anomaly detection datasets ( HDFS [136] and BGL [87]) were collected more than ten years ago.”
Improving Performances of Log Mining for Anomaly Prediction Through NLP-Based Log Parsing
Aussel, N., Petetin, Y., & Chabridon, S. (2018) · Proceedings - International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems · doi:10.1109/mascots.2018.00031 · Cited by 56
“Log mining has been the subject of many publications [1], [2], [3], log parsing as well [4], [5].”
BackgroundMethodAnomaly Detection in Log Files Using Selected Natural Language Processing Methods
Ryciak, P., Wasielewska, K., & Janicki, A. (2022) · Applied Sciences · doi:10.3390/app12105089 · Cited by 54
Towards an NLP-based log template generation algorithm for system log analysis
Kobayashi, S., Fukuda, K., & Esaki, H. (2014) · Proceedings of The Ninth International Conference on Future Internet Technologies · doi:10.1145/2619287.2619290 · Cited by 38
“Towards an NLP-based log template generation algorithm for system log analysis Satoru KobayashiKensuke Fukuda Hiroshi Esaki University of Tokyo NII University of Tokyo sat@hongo.wide.ad.jp kensuke@nii.ac.jp hiroshi@wide.ad.jp ABSTRACT System log from network equipment is one of the most…”
Sifter: Scalable Sampling for Distributed Traces, without Feature Engineering
Las-Casas, P., Papakerashvili, G., Anand, V., & Mace, J. (2019) · Proceedings of the ACM Symposium on Cloud Computing · doi:10.1145/3357223.3362736 · Cited by 42
Faster, deeper, easier: crowdsourcing diagnosis of microservice kernel failure from user space
Pan, Y., Ma, M., Jiang, X., & Wang, P. (2021) · Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis · doi:10.1145/3460319.3464805 · Cited by 42
“Most of them such as [11, 26, 28, 34] describe the system performance through various models and detect anomalies by detecting violations of these standards.”
BackgroundLLM-LADE: Large language model-based log anomaly detection with explanation
Zhang, Z., Li, S., Zhang, L., Ye, J., Hu, C., & Yan, L. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114064 · Cited by 42
Provenance from log files: a BigData problem
Ghoshal, D., & Plale, B. (2013) · EDBT/ICDT Workshops · doi:10.1145/2457317.2457366 · Cited by 42
Bhanage, D. A., Pawar, A., & Kotecha, K. V. (2021) · IEEE Access · doi:10.1109/access.2021.3128283 · Cited by 56
“Second, using an open-source platform (for example, GitHub) allows designing a system by many developers [4], multiple development styles resulted in complex logging.”
BackgroundMethodSmart-troubleshooting connected devices: Concept, challenges and opportunities
Caporuscio, M., Flammini, F., Khakpour, N., Singh, P., & Thornadtsson, J. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.09.004 · Cited by 43
Research on anomaly detection and real-time reliability evaluation with the log of cloud platform
Wang, B., Hua, Q., Zhang, H., Tan, X. L., Nan, Y., Chen, R., & Shu, X. (2022) · Alexandria Engineering Journal · doi:10.1016/j.aej.2021.12.061 · Cited by 46
Automated Dynamic Firmware Analysis at Scale: A Case Study on Embedded Web InterfacesPreprint
Costin, A., Zarras, A., & Francillon, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.03609 · Cited by 42
“ents: The failure analysis and determination in large-scale deployments [20] can be improved and automated in several ways. One way is to perform log pre-processing [86], log mining [65] and analysis [84]. This approach often uses clustering and machine learning techniques to classify an unknown execution of the syste…”
MethodA comprehensive study of machine learning techniques for log-based anomaly detection
Ali, S., Boufaied, C., Bianculli, D., Branco, P., & Briand, L. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10669-3 · Cited by 50
Workload-aware anomaly detection for Web applications
Wang, T., Wei, J., Zhang, W., Zhong, H., & Huang, T. (2013) · Journal of Systems and Software · doi:10.1016/j.jss.2013.03.060 · Cited by 40
“In the future work, we will integrate some fine-granularity ethods, such as tracing request (e.g. Reynolds et al., 2006) and nalyzing logs (e.g. Xu et al., 2009), in our approach for locatng suspicious sections of source code, when the anomalies are etected.”
MethodMultivariate Big Data Analysis for intrusion detection: 5 steps from the haystack to the needle
Camacho, J., García-Giménez, J. M., García, M. F., & Maciá‐Fernández, G. (2019) · Computers & Security · doi:10.1016/j.cose.2019.101603 · Cited by 46
Anomaly Detection via Mining Numerical Workflow Relations from Logs
Zhang, B., Zhang, H., Moscato, P., & Zhang, A. (2020) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds51746.2020.00027 · Cited by 46
“Deep Learning [20]) and unsupervised approaches (such as Log Clustering [9], Principle Component Analysis [10], Invariants Mining [11]).”
InfluentialExperience mining Google’s production console logs
Xu, W., & Huang, L. (n.d.) · Cited by 40
Self-citationAn Exploratory Study of Logging Configuration Practice in Java
Chen, Z., Yin, J., Deng, S., Ye, M., Fu, M., & Xie, T. (2019) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme.2019.00079 · Cited by 39
“The rich information in logs is crucial for many tasks, such as failure diagnosis [1], [2], performance analysis [3], and user behavior analysis [4].”
BackgroundSemi-automated protocol disambiguation and code generation
Yen, J., Lévai, T., Ye, Q., Ren, X., Govindan, R., & Raghavan, B. (2021) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/3452296.3472910 · Cited by 39
“Past studies have explored Principal Component Analysis [84], rule-based analysis [25], statistic analysis [56, 79], and ML-based methods [72] to solve log analysis problems.”
Gholamian, S., & Ward, P. A. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.12489 · Cited by 43
“C ACM Symposium on Operating Systems Principles (3) SOSP [2], [10], [33]”
BackgroundMethodInfluentialRobust and Transferable Log-based Anomaly Detection
Jia, P., Cai, S., Ooi, B. C., Wang, P., & Xiong, Y. (2023) · Proceedings of the ACM on Management of Data · doi:10.1145/3588918 · Cited by 47
“0 on the HDFS [63] dataset but decreases to 0 .”
BackgroundMethodInfluentialXie, Y., Zhang, H., & Babar, M. A. (2024) · Proceedings of the ACM on software engineering. · doi:10.1145/3660800 · Cited by 40
Examining the Stability of Logging Statements
Kabinna, S., Shang, W., Bezemer, C., & Hassan, A. E. (2016) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner.2016.29 · Cited by 47
CausalConvLSTM: Semi-Supervised Log Anomaly Detection Through Sequence Modeling
Yen, S., Moh, M., & Moh, T.-S. (2019) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2019.00217 · Cited by 38
“The explanation for this is that CausalConvLSTM can take ordering information into consideration, which is important for the detection of the execution path anomalies that exists in the HDFS dataset [2].”
BackgroundMethodInfluentialLandscape of Automated Log Analysis: A Systematic Literature Review and Mapping Study
Korzeniowski, Ł., & Goczyła, K. (2022) · IEEE Access · doi:10.1109/access.2022.3152549 · Cited by 48
Investigating and improving log parsing in practice
Fu, Y., Yan, M. L., Xu, J., Li, J., Liu, Z., Zhang, X., & Yang, D. (2022) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3540250.3558947 · Cited by 46
“[47] used static source analysis to extract all log printing statements from the source code and types of variables contained in the log messages.”
BackgroundMethodHuang, L., & Zhu, T. (2021) · Proceedings of the ACM Symposium on Cloud Computing · doi:10.1145/3472883.3486994 · Cited by 37
Self-citationImproving Log-Based Anomaly Detection with Component-Aware Analysis
Yin, K., Yan, M., Xu, L., Xu, Z., Li, Z., Yang, D., & Zhang, X. (2020) · 2020 IEEE International Conference on Software Maintenance and Evolution (ICSME) · doi:10.1109/icsme46990.2020.00069 · Cited by 37
“Logbased anomaly detection has become a research question, and many approaches [1]–[3] have been proposed.”
BackgroundMethodInfluentialPreLog: A Pre-trained Model for Log Analytics
Le, V.-H., & Zhang, H. (2024) · Proceedings of the ACM on Management of Data · doi:10.1145/3654966 · Cited by 46
Assessing and improving the effectiveness of logs for the analysis of software faults
Cinque, M., Cotroneo, D., Natella, R., & Pecchia, A. (2010) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn.2010.5544279 · Cited by 37
“Recent studies were also devoted to exploiting log contents for anomaly detection in complex systems [23].”
BackgroundLADRA: Log-based abnormal task detection and root-cause analysis in big data processing with Spark
Lu, S., Wei, X., Rao, B., Tak, B., Wang, L., & Wang, L. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2018.12.002 · Cited by 42
QLLog: A log anomaly detection method based on Q-learning algorithm
Duan, X., Ying, S., Yuan, W., Cheng, H., & Yin, X. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102540 · Cited by 39
Anomaly Detection using Distributed Log Data: A Lightweight Federated Learning Approach
Guo, Y., Wu, Y., Zhu, Y., Yang, B., & Han, C. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533294 · Cited by 46
“Typical unsupervised methods are Log3C [15], Invariants Mining [16], PCA [17] and Log Clustering [18].”
MethodLoGenText: Automatically Generating Logging Texts Using Neural Machine Translation
Ding, Z., Li, H., & Shang, W. (2022) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner53432.2022.00051 · Cited by 45
“Prior work has leveraged the rich information in logs to support different software engineering activities, including system comprehension [3], [4], anomaly detection [5], [6], [7], [8], [9], and failure diagnosis [10], [11].”
BackgroundAn Assessment of ChatGPT on Log Data
Mudgal, P., & Wouhaybi, R. H. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-7587-7_13 · Cited by 56
Failure Diagnosis of Complex Systems
Kavulya, S. P., Joshi, K., Giandomenico, F. D., & Narasimhan, P. (2012) · Springer eBooks · doi:10.1007/978-3-642-29032-9_12 · Cited by 37
“Log analysis [66, 67, 93] and rule-based techniques [8,31,32] are also widely used in data center applications.”
BackgroundMethodPerformance troubleshooting in data centers: an annotated bibliography?
Wang, C., Kavulya, S. P., Tan, J., Hu, L., Kutare, M., Kasick, M., Schwan, K., Narasimhan, P., & Gandhi, R. (2013) · ACM SIGOPS Operating Systems Review · doi:10.1145/2553070.2553079 · Cited by 36
Gurumdimma, N. Y., Jhumka, A., Liakata, M., Chuah, E., & Browne, J. C. (2016) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds.2016.017 · Cited by 36
“Detecting fault occurrences (i.e., errors) using event logs and other data has received good attention, with reasonably good results, e.g., [1]–[4].”
BackgroundPredicting Performance Anomalies in Software Systems at Run-time
Zhao, G., Hassan, S., Zou, Y., Truong, D., & Corbin, T. (2021) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3440757 · Cited by 42
“For example, a NameNode in Hadoop Distributed File System is not updated after deleting a data block [69].”
BackgroundLogging Practices in Software Engineering: A Systematic Mapping Study
Gu, S., Rong, G., Zhang, H., & Shen, H. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2022.3166924 · Cited by 54
A Directed Acyclic Graph Approach to Online Log ParsingPreprint
He, P., Zhu, J., Xu, P., Zheng, Z., & Lyu, M. R.-T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.04356 · Cited by 42
“Specifically, raw log messages in the HDFS dataset [8] record system operations on 575,061 HDFS blocks with a total of 29 log event types.”
BackgroundMethodInfluentialCAT: Beyond Efficient Transformer for Content-Aware Anomaly Detection in Event Sequences
Zhang, S., Liu, Y., Zhang, X., Cheng, W., Chen, H., & Xiong, H. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539155 · Cited by 35
“Hadoop Distributed File System (HDFS [40]): This dataset was generated by a Hadoop-based map-reduce cloud environment using benchmark workloads, and manually labeled through handcrafted rules to identify the anomalies.”
BackgroundMethodSelf-Healing REST Services Using Artificial Intelligence in Multi-Cloud Environments
Jaiswal, I. A. (2024) · Scientific Journal of Artificial Intelligence and Blockchain Technologies · doi:10.63345/sjaibt.v1.i3.201 · Cited by 39
Cowic: A Column-Wise Independent Compression for Log Stream Analysis
Lin, H., Zhou, J., Yao, B., Guo, M., & Li, J. (2015) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid.2015.45 · Cited by 42
“For log search, our approach achieves better query times than using traditional compression algorithms for both in-core and out-of-core cases.”
MethodCrashTuner: detecting crash-recovery bugs in cloud systems via meta-info analysis
Lu, J., Liu, C., Li, L., Feng, X., Tan, F., Yang, J., & You, L. (2019) · ACM SIGOPS Symposium on Operating Systems Principles (SOSP) · doi:10.1145/3341301.3359645 · Cited by 35
“[58] detect anomaly executions by applying machine learning techniques to console logs from a system.”
BackgroundMethodInfluentialLogNADS: Network anomaly detection scheme based on log semantics representation
Liu, X., Liu, W., Di, X., Li, J., Cai, B., Ren, W., & Yang, H. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.05.024 · Cited by 36
Mining unstructured log files for recurrent fault diagnosis
Reidemeister, T., Jiang, M., & Ward, P. A. S. (2011) · IFIP/IEEE International Symposium on Integrated Network Management (IM) · doi:10.1109/inm.2011.5990536 · Cited by 42
LPV: A Log Parser Based on Vectorization for Offline and Online Log Parsing
Xiao, T. Y., Quan, Z., Wang, Z.-J., Zhao, K., & Liao, X. (2020) · Proceedings · doi:10.1109/icdm50108.2020.00175 · Cited by 43
“For open-source softwares, there is also effort to parse logs by leveraging source code analysis [8], as a log’s schema is hidden in the log printing statement.”
BackgroundMethodInfluentialLLM Meets ML: Data-efficient Anomaly Detection on Unstable Logs
Hadadi, F., Xu, Q., Bianculli, D., & Briand, L. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3771283 · Cited by 37
“The majority of anomaly detection methods [20, 24, 50, 56, 61, 64, 90, 92] have been proposed for and evaluated on stable log datasets.”
Tracing Back Log Data to its Log Statement: From Research to Practice
Schipper, D., Aniche, M. F., & Arie Van Deursen, A. (2019) · International Conference on Mining Software Repositories (MSR) · doi:10.1109/msr.2019.00081 · Cited by 40
“of other systems, normally about 1%-5% [28], as developers try to be as efficient as possible in their logging.”
BackgroundMethodInfluentialLog-Based Anomaly Detection with the Improved K-Nearest Neighbor
Wang, B., Ying, S., Cheng, G., Wang, R., Yang, Z., & Dong, B. (2020) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194020500114 · Cited by 34
DeepMIT: A Novel Malicious Insider Threat Detection Framework based on Recurrent Neural Network
Sun, D., Liu, M., Li, M., Shi, Z., Liu, P., & Wang, X. (2021) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd49262.2021.9437887 · Cited by 34
“Existing anomaly detection-based methods could be classified into two categories as classification-based methods [1] which always use machine learning or deep learning to train anomaly classification models, and prediction-based methods [2] which always predict and define anomalous behaviors by the…”
MethodTowards structured log analysis
Jayathilake, D. (2012) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse.2012.6261962 · Cited by 34
“On the other hand, line logs too exhibit a structure and their analysis can benefit from a structureoriented methodology.”
BackgroundOnline detection of multi-component interactions in production systems
Oliner, A. J., & Aiken, A. (2011) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn.2011.5958206 · Cited by 34
“While we discuss this further in Section 3.1, the process of converting raw measurements into anomaly signals is well-studied for a wide variety of data types [11], [13], [15], [20], [25], [27], [39], [40] and this paper focuses instead on how to use anomaly signals to efficiently infer component…”
BackgroundMethodInfluentialProactive Failure Detection Learning Generation Patterns of Large-Scale Network Logs
Kimura, T., Watanabe, A., Toyono, T., & Ishibashi, K. (2018) · IEICE Transactions on Communications · doi:10.1587/transcom.2018ebp3103 · Cited by 34
Logan: A Distributed Online Log Parser
Agrawal, A., Karlupia, R., & Gupta, R. K. (2019) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2019.00211 · Cited by 37
“We perform evaluation on four public [15], [16], [17], [4] and two new datasets.”
MethodLiao, L., Chen, J., Li, H., Zeng, Y., Shang, W., Guo, J., Sporea, C., Toma, A., & Sajedi, S. (2020) · Empirical Software Engineering · doi:10.1007/s10664-020-09866-z · Cited by 33
“Xu et al. (2009) extract event features from the execution logs and leverage PCA to detect performance-related anomalies.”
BackgroundMethodLogging Practices with Mobile Analytics: An Empirical Study on Firebase
Harty, J., Zhang, H.-N., Wei, L.-L., Pascarella, L., Aniche, M., & Shang, W.-Y. (2021) · International Conference on Mobile Software Engineering and Systems · doi:10.1109/mobilesoft52590.2021.00013 · Cited by 28
LogLS: Research on System Log Anomaly Detection Method Based on Dual LSTM
Chen, Y., Luktarhan, N., & Lv, D. (2022) · Symmetry · doi:10.3390/sym14030454 · Cited by 39
Discrete log anomaly detection: A novel time-aware graph-based link prediction approach
Yan, L., Luo, C., & Shao, R. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119576 · Cited by 37
Zhang, Y., Rodrigues, K., Luo, Y., Stumm, M., & Yuan, D. (2019) · ACM SIGOPS Symposium on Operating Systems Principles (SOSP) · doi:10.1145/3341301.3359650 · Cited by 33
“Statistical fault localization: A large portion of fault localization research uses statistical debugging [7, 16, 24, 25, 27, 28, 33, 48].”
BackgroundMining temporal invariants from partially ordered logs
Beschastnikh, I., Brun, Y., Ernst, M. D., Krishnamurthy, A., & Anderson, T. E. (2012) · ACM SIGOPS Operating Systems Review · doi:10.1145/2094091.2094101 · Cited by 33
“Detecting anomalies in distributed systems is a popular research area [30, 17, 36].”
BackgroundLightweight and Adaptive Service API Performance Monitoring in Highly Dynamic Cloud Environment
Xu, J., Wang, Y., Chen, P., & Wang, P. (2017) · 2017 IEEE International Conference on Services Computing (SCC) · doi:10.1109/scc.2017.80 · Cited by 28
Automating Root Cause Analysis via Machine Learning in Agile Software Testing Environments
Kahles, J., Torronen, J., Huuhtanen, T., & Jung, A. (2019) · IEEE International Conference on Software Testing, Verification and Validation (ICST) · doi:10.1109/icst.2019.00047 · Cited by 32
“[24] apply principal component analysis (PCA) combined with term-weighting to parsed console logs.”
MethodPaddy: An Event Log Parsing Approach using Dynamic Dictionary
Huang, S., Liu, Y., Fung, C., He, R., Zhao, Y., Yang, H., & Luan, Z. (2020) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms47738.2020.9110435 · Cited by 38
“Traditionally, log parsing relies heavily on regular expressions [2, 3] designed by developers.”
BackgroundMethodAn Effective Approach for Parsing Large Log Files
Sedki, I., Hamou‐Lhadj, A., Mohamed, O. A., & Shehab, M. A. (2022) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme55016.2022.00009 · Cited by 46
“…of information on the execution of a software system that is used to help with different software engineering activities, such as anomaly detection [1] [2] [3] [4], debugging and comprehension of system failures [5] [6] [7] [8] [9], testing and performance analysis [10] [11] [12], operational…”
BackgroundMethodInferring and asserting distributed system invariants
Grant, S., Cech, H. L., & Beschastnikh, I. (2018) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3180155.3180199 · Cited by 38
“For example, some work uses mining to detect dependencies [37], anomalies [53, 55], and performance bugs [48].”
Background
Metadata
- Authors
- Xu, W., Huang, L., Fox, A., Patterson, D., & Jordan, M. I.
- Affiliations
- University of California, Berkeley (US)
- Intel (United States) (US)
- Venue
- Proceedings of the ACM SIGOPS 22nd symposium on Operating systems principles
- Publisher
- ACM
- Published
- 2009-10-11
- Pages
- 117-132
- OpenAlex
- W2039157918
- Cited by
- 1,332
- References
- 44
- Citations by year
- 2026: 100 · 2025: 126 · 2024: 134 · 2023: 138 · 2022: 97 · 2021: 126 · 2020: 96 · 2019: 89 · 2018: 72 · 2017: 49 · 2016: 62 · 2015: 48 · 2014: 41 · 2013: 37 · 2012: 42
- FWCI
- 31.53
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGOPS Symposium on Operating Systems Principles (SOSP) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- fault detection, log parsing, composite features, source code analysis, information retrieval, decision tree, Hadoop
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.