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 101–200 of 1,004
DeepRan: Attention-based BiLSTM and CRF for Ransomware Early Detection and Classification
Roy, K. C., & Chen, Q. (2020) · Information Systems Frontiers · doi:10.1007/s10796-020-10017-4 · Cited by 99
“PCA divides system log count vectors into normal and abnormal space (Xu et al. 2009), and logistic regression generates a binary regression function based on the count vector of system logs to detect anomaly (Liang et al. 2007).”
MethodAligning Real Process Executions and Prescriptive Process Models through Automated Planning
de Leoni, M., & Marrella, A. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.03.047 · Cited by 98
“To our knowledge, the same limitation is also shared by techniques to debug the execution of distributed systems (e.g. ( Reynolds et al., 2006; Xu et al., 2009))”
BackgroundComplexity vs. performance: empirical analysis of machine learning as a service
Yao, Y., Xiao, Z., Wang, B., Viswanath, B., Zheng, H.-T., & Zhao, B. Y. (2017) · ACM Internet Measurement Conference (IMC) · doi:10.1145/3131365.3131372 · Cited by 121
“3131372 with examples ranging from network link prediction [43, 54], network localization [41, 77], user behavior analysis [71, 72], congestion control protocols [59, 74], performance characterization [8, 76], botnet detection [31], and network management [1].”
BackgroundPrecomputing possible configuration error diagnoses
Rabkin, A., & Katz, R. H. (2011) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase.2011.6100053 · Cited by 88
“Previous work has shown how to map log messages back to the origin line in the source code [6], [7].”
BackgroundSpatio-temporal factorization of log data for understanding network events
Kimura, T., Ishibashi, K., Mori, T., Sawada, H., Toyono, T., Nishimatsu, K., Watanabe, A., Shimoda, A., & Shiomoto, K. (2014) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2014.6847986 · Cited by 87
“Log parsing technique has been reported in other studies [19], [25].”
ResultLog-based Abnormal Task Detection and Root Cause Analysis for Spark
Lu, S., Rao, B., Wei, X., Tak, B., Wang, L., & Wang, L. (2017) · 2017 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws.2017.135 · Cited by 86
“[17] use an automatic log parser to parse source code and combine PCA to detect anomaly, it is based on abstract syntax tree (AST) to analyze source code and uses machine learning to train data.”
MethodChukwa: a system for reliable large-scale log collection
Rabkin, A., & Katz, R. H. (2010) · Cited by 86
Studying the relationship between logging characteristics and the code quality of platform software
Shang, W., Nagappan, M., & Hassan, A. E. (2013) · Empirical Software Engineering · doi:10.1007/s10664-013-9274-8 · Cited by 100
“To study the relation between logging characteristics and code quality, we conduct case studies on two large and widely used open-source platform software: – Hadoop (http://hadoop.apache.org) is a large distributed data processing platform that implements the MapReduce (Dean and Ghemawat 2008)…”
MethodDesh: deep learning for system health prediction of lead times to failure in HPC
Das, A., Mueller, F., Siegel, C., & Vishnu, A. (2018) · Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing · doi:10.1145/3208040.3208051 · Cited by 78
“One concern with these solutions making them incompatible with HPC systems are fault injections [14, 18, 38, 45] and source code referenced log statement parsing or augmentation [44].”
BackgroundNedelkoski, S., Bogatinovski, J., Acker, A., Cardoso, J., & Kao, O. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-67667-4_8 · Cited by 118
Accurate, Low Cost and Instrumentation-Free Security Audit Logging for Windows
Ma, S., Lee, K. H., Kim, C. H., Rhee, J., Zhang, X., & Xu, D. (2015) · Annual Computer Security Applications Conference · doi:10.1145/2818000.2818039 · Cited by 86
Chen, P., Qi, Y., & Hou, D. (2019) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2016.2607739 · Cited by 72
“These methods employ the log information reported by the system to investigate the causes of performance problems [37], [38], [39], [40], [41], [42].”
MethodTowards just-in-time suggestions for log changes
Li, H., Shang, W., Zou, Y., & Hassan, A. E. (2016) · Empirical Software Engineering · doi:10.1007/s10664-016-9467-z · Cited by 103
“Since console logs, generated in large-scale data centers, often consist of voluminous messages and it is difficult for operators to detect noteworthy logs, Xu et al. (2009) propose a method to mine logs to automatically detect system runtime problems within a short time.”
BackgroundMethodInfluentialRoot-Cause Metric Location for Microservice Systems via Log Anomaly Detection
Wang, L., Zhao, N., Chen, J., Li, P., Zhang, W., & Sui, K. (2020) · 2020 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws49710.2020.00026 · Cited by 84
“In the literature, much efforts have been dedicated in log anomaly detection, for example, PCA-based method [20], clustering-based method [29], Invariant Mining [21].”
MethodPerformance analysis of idle programs
Altman, E., Arnold, M., Fink, S. J., & Mitchell, N. (2010) · Conference on Object-Oriented Programming Systems, Languages, and Applications · doi:10.1145/1869459.1869519 · Cited by 84
“A few previous works have been developed to mine log information in large systems [22, 23].”
BackgroundMethodAn Improved KNN-Based Efficient Log Anomaly Detection Method with Automatically Labeled Samples
Ying, S., Wang, B., Wang, L., Li, Q., Zhao, Y., Shang, J., Huang, H., Cheng, G., Yang, Z., & Geng, J. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3441448 · Cited by 84
SwissLog: Robust Anomaly Detection and Localization for Interleaved Unstructured Logs
Li, X., Chen, P., Jing, L., He, Z., & Yu, G. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3162857 · Cited by 96
“Such changes make the log key-based anomaly detection [4], [5], [6], [7] approaches perform unsatisfactorily since they consider a changed logging statement as a new template.”
BackgroundMethodInfluentialPivot Tracing: Dynamic Causal Monitoring for Distributed Systems
Mace, J., Roelke, R., & Fonseca, R. (2017) · ACM Transactions on Computer Systems · doi:10.1145/3208104 · Cited by 51
“While there has been great progress in using machine learning techniques [60, 76, 78, 103] and static analysis [106, 107] to improve the quality of logs and their use in troubleshooting, they carry an inherent tradeoff between recall and overhead, as what gets logged must be defined a priori .”
Predictive maintenance based on event-log analysis: A case study
Wang, J., Li, C., Han, S., Sarkar, S., & Zhou, X. (2017) · IBM Journal of Research and Development · doi:10.1147/jrd.2017.2648298 · Cited by 99
ASAP: A Self-Adaptive Prediction System for Instant Cloud Resource Demand Provisioning
Jiang, Y., Perng, C.-S., Li, T., & Chang, R. (2011) · Proceedings · doi:10.1109/icdm.2011.25 · Cited by 80
“[10] proposed a large-scale console logs mining system to detect the abnormal behaviors of distributed system.”
Insider Threat Detection with Long Short-Term Memory
Lu, J., & Wong, R. K. (2019) · Proceedings of the Australasian Computer Science Week Multiconference · doi:10.1145/3290688.3290692 · Cited by 75
“Anomaly detection models are usually built based on unsupervised machine learning models such as PCA [38, 39], Invariant mining (IM)[20], or supervised machine learning models like SVM [14] or RNN [24].”
MethodCo-analysis of RAS Log and Job Log on Blue Gene/P
Zheng, Z., Yu, L., Tang, W., Lan, Z., Gupta, R., Desai, N., Coghlan, S., & Buettner, D. (2011) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps.2011.83 · Cited by 79
Zhao, X., Rodrigues, K., Luo, Y., Yuan, D., & Stumm, M. (2016) · Operating Systems Design and Implementation · doi:10.5555/3026877.3026924 · Cited by 71
An Approach for Anomaly Diagnosis Based on Hybrid Graph Model with Logs for Distributed Services
Jia, T., Chen, P., Yang, L., Li, Y., Meng, F., & Xu, J. (2017) · 2017 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws.2017.12 · Cited by 78
Dynamic log file analysis: An unsupervised cluster evolution approach for anomaly detection
Landauer, M., Wurzenberger, M., Skopik, F., Settanni, G., & Filzmoser, P. (2018) · Computers & Security · doi:10.1016/j.cose.2018.08.009 · Cited by 89
“Moreover, locating lines that contain significant words like “error” is also not enough for a thorough analysis of the system and neither is the presence or absence of certain lines sufficient to indicate problems, but rather the dynamic relationships and correlations between lines have to be considered when performin…”
Maintainable Log Datasets for Evaluation of Intrusion Detection Systems
Landauer, M., Skopik, F., Frank, M., Hotwagner, W., Wurzenberger, M., & Rauber, A. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3201582 · Cited by 105
“…system performance and not purposefully incorporated variations as accomplished by our model-driven KDD Cup 1999 [22] Military IT ✓ ✓ ✓ ✓ ✓ ✓ HDFS [23] Supercomputer ✓ ✓ VAST Challenge 2011 [24] Enterprise IT [11] Linux OS ✓ ✓ ✓ ✓ ADFA-WD [26] Windows OS ✓ ✓ ✓ ✓ Skopik et al. [27] Enterprise IT ✓…”
LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models
Zhong, A., Mo, D., Liu, G., Liu, J., Lu, Q., Zhou, Q., Wu, J., Li, Q., & Wen, Q. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671810 · Cited by 59
Statistical debugging for real-world performance problems
Song, L., & Lu, S. (2014) · Conference on Object-Oriented Programming Systems, Languages, and Applications · doi:10.1145/2660193.2660234 · Cited by 78
An empirical investigation of practical log anomaly detection for online service systems
Zhao, N., Wang, H., Li, Z., Peng, X., Wang, G., Pan, Z., Wu, Y., Feng, Z., Wen, X., Zhang, W., et al. (2021) · Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3468264.3473933 · Cited by 77
“have provided a detailed experience report [31] about these traditional statistical methods, including PCA [47], LogCluster [35], InvariantMining [37] and some other classification-based supervised methods [22, 34].”
BackgroundMethodInfluentialLandauer, M., Skopik, F., Stojanović, B., Flatscher, A., & Ullrich, T. (2024) · International Journal of Information Security · doi:10.1007/s10207-024-00921-0 · Cited by 89
Studying the characteristics of logging practices in mobile apps: a case study on F-Droid
Zeng, Y., Chen, J., Shang, W., & Chen, T.-H. P. (2019) · Empirical Software Engineering · doi:10.1007/s10664-019-09687-9 · Cited by 101
“The valuable information in logs is leveraged in various software development and operation activities including bug fixing (Xu et al. 2009), test results analyses (Malik et al. 2013), anomaly detection (Tan et al. 2008), and system monitoring (Yuan et al. 2012c; Boulon et al. 2008).”
MethodAdaptive system anomaly prediction for large-scale hosting infrastructures
Tan, Y., Gu, X., & Wang, H. (2010) · ACM Symposium on Principles of Distributed Computing (PODC) · doi:10.1145/1835698.1835741 · Cited by 76
Unsupervised Cross-system Log Anomaly Detection via Domain Adaptation
Han, X., & Yuan, S. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482209 · Cited by 75
LogGD: Detecting Anomalies from System Logs with Graph Neural Networks
Xie, Y., Zhang, H., & Babar, M. A. (2022) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs57517.2022.00039 · Cited by 96
“Traditional ML-based methods, such as LR [8], SVM [9], PCA (Principal Component Analysis) [54] and LogCluster [10], are often more efficient compared with deep learning based methods in terms of time costs.”
MethodAnomaly Detection in Operating System Logs with Deep Learning-Based Sentiment Analysis
Studiawan, H., Sohel, F. A., & Payne, C. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2020.3037903 · Cited by 73
Exploring the Effectiveness of LLMs in Automated Logging Statement Generation: An Empirical Study
Li, Y., Huo, Y., Jiang, Z., Zhong, R., He, P., Su, Y., Briand, L., & Lyu, M. R.-T. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3475375 · Cited by 91
Detecting the performance impact of upgrades in large operational networks
Mahimkar, A. A., Song, H. H., Ge, Z., Shaikh, A., Wang, J., Yates, J. M., Zhang⋆, Y., & Emmons, J. (2010) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/1851182.1851219 · Cited by 72
“[38] use PCA to extract features from the console logs and decision trees to learn rules from the PCA output.”
MethodAnomaly detection and diagnosis for cloud services: Practical experiments and lessons learned
Sauvanaud, C., Kaâniche, M., Kanoun, K., Lazri, K., & Silvestre, G. (2018) · Journal of Systems and Software · doi:10.1016/j.jss.2018.01.039 · Cited by 81
“Principal Component Analysis is applied on application logs in Xu et al. (2009) and in Lakhina et al. (2004) for the detection of anomalies in network traffic.”
MethodStudying and detecting log-related issues
Hassani, M., Shang, W., Shihab, E., & Tsantalis, N. (2018) · Empirical Software Engineering · doi:10.1007/s10664-018-9603-z · Cited by 79
“Logs are used during various software development activities such as bug fixing (Xu et al. 2009), anomaly detection (Tan et al. 2008), testing results analyses (Malik et al. 2013), and system monitoring (Yuan et al. 2012c; Boulon et al. 2008).”
MethodLiu, Z., Xia, X., Lo, D., Xing, Z., Hassan, A. E., & Li, S. (2019) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2019.2941943 · Cited by 81
“tasks, including execution anomaly detection [2], [3], problem diagnosis [4]–[7], deployment verification [8], etc.”
MethodLog 2 : a cost-aware logging mechanism for performance diagnosis
Ding, R. F., Zhou, H., Lou, J., Zhang, H., Lin, Q., Fu, Q., Zhang, D., & Xie, T. (2015) · Figshare · Cited by 117
What happened in my network: mining network events from router syslogs
Qiu, T., Ge, Z., Pei, D., Wang, J., & Xu, J. J. (2010) · ACM Internet Measurement Conference (IMC) · doi:10.1145/1879141.1879202 · Cited by 71
“propose a general methodology to mine the console logs and to automatically detect system running time problem [19].”
MethodDetecting anomalies in microservices with execution trace comparison
Meng, L., Ji, F., Sun, Y., & Wang, T. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.040 · Cited by 70
Jiang, H., Li, X., Yang, Z., & Xuan, J. (2017) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse.2017.71 · Cited by 70
“Fu et al. [15] and Xu et al. [16] conduct anomaly detection through log analysis.”
SemParser: A Semantic Parser for Log Analytics
Huo, Y., Su, Y., Lee, C., & Lyu, M. R. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00082 · Cited by 58
“(1) We first follow the previous studies to evaluate in the HDFS [35] dataset, which includes log messages by running map-reduce tasks on more than 200 nodes.”
MethodBigDebug: debugging primitives for interactive big data processing in spark
Gulzar, M. A., Interlandi, M., Yoo, S., Tetali, S. D., Condie, T., Millstein, T. D., & Kim, M. (2016) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/2884781.2884813 · Cited by 69
“[37] parse console logs and combine source code analysis to detect abnormal behavior.”
BackgroundExecution anomaly detection in large-scale systems through console log analysis
Bao, L., Li, Q., Lu, P., Lu, J., Ruan, T., & Zhang, K. (2018) · Journal of Systems and Software · doi:10.1016/j.jss.2018.05.016 · Cited by 67
A Survey on Log Anomaly Detection using Deep Learning
Yadav, R. B., Kumar, P. S., & Dhavale, S. V. (2020) · 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito48877.2020.9197818 · Cited by 54
Lent, R., Grochla, K., Gelenbe, E., & Czachórski, T. (2016) · Communications in computer and information science · doi:10.1007/978-3-319-47217-1 · Cited by 69
Proactive failure detection learning generation patterns of large-scale network logs
Kimura, T., Watanabe, A., Toyono, T., & Ishibashi, K. (2015) · International Conference on Network and Service Management (CNSM) · doi:10.1109/cnsm.2015.7367332 · Cited by 76
“Thus, we took a supervised machine learning method and associated failures described in trouble tickets and log messages occurred before them.”
MethodLogUAD: Log Unsupervised Anomaly Detection Based on Word2Vec
Wang, J., Zhao, C., He, S., Gu, Y., Alfarraj, O., & Abugabah, A. (2021) · Computer Systems Science and Engineering · doi:10.32604/csse.2022.022365 · Cited by 68
“[13] used principal component analysis (PCA) to detect abnormal events and found that PCA with term weighting technology in information retrieval got good anomaly detection results without too much parameter adjustment.”
MethodFD4C: Automatic Fault Diagnosis Framework for Web Applications in Cloud Computing
Wang, T., Zhang, W., Ye, C., Wei, J., Zhong, H., & Huang, T. (2016) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2015.2430834 · Cited by 68
“In our future work, we will integrate some fine-grained methods, such as tracing request (see [44]) and analyzing logs (see [45]) to locate suspicious sections of source code.”
MethodJuggling the Jigsaw: towards automated problem inference from network trouble tickets
Potharaju, R., Jain, N., & Nita-Rotaru, C. (2013) · Networked Systems Design and Implementation · Cited by 79
An empirical study of log analysis at Microsoft
He, S., Zhang, X., He, P., Xu, Y., Li, L., Kang, Y., Ma, M., Wei, Y., Dang, Y., Rajmohan, S., et al. (2022) · Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3540250.3558963 · Cited by 51
“Over the last decade, log analysis has attracted much attention from academia [7, 13, 25, 37, 39, 49].”
BackgroundMethodInfluentialLog-based software monitoring: a systematic mapping study
Cândido, J., Aniche, M. F., & van Deursen, A. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.489 · Cited by 87
Improving Log-based Field Failure Data Analysis of multi-node computing systems
Pecchia, A., Cotroneo, D., Kalbarczyk, Z., & Iyer, R. K. (2011) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn.2011.5958210 · Cited by 65
“, [8], [18], [4], [25], [26], use statistical”
DeepSyslog: Deep Anomaly Detection on Syslog Using Sentence Embedding and Metadata
Zhou, J., Qian, Y., Zou, Q., Liu, P., & Xiang, J. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3201379 · Cited by 69
“…the request traces [1], train a vector machine to classify event data set [2], conduct principal component analysis (PCA) over log message counters [3], [4], employ invariant mining to capture co-occurrence patterns between dis-coherent log keys [5], and identify execution anomalies from program…”
BackgroundMethodInfluentialLogging library migrations: a case study for the apache software foundation projects
Kabinna, S., Bezemer, C., Shang, W., & Hassan, A. E. (2016) · International Conference on Mining Software Repositories (MSR) · doi:10.1145/2901739.2901769 · Cited by 63
POD-Diagnosis: Error Diagnosis of Sporadic Operations on Cloud Applications
Xu, X., Zhu, L., Weber, I., Bass, L., & Sun, D. (2014) · 2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks · doi:10.1109/dsn.2014.94 · Cited by 60
“[17] parses console logs by combining source code analyses.”
MethodKahuna: Problem diagnosis for Mapreduce-based cloud computing environments
Tan, J., Pan, X., Marinelli, E., Kavulya, S. P., Gandhi, R., & Narasimhan, P. (2010) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms.2010.5488446 · Cited by 62
“[28] mined error messages in DataNode logs to identify those correlated with”
MethodSelf-adaptive cloud monitoring with online anomaly detection
Wang, T., Xu, J., Zhang, W., Gu, Z., & Zhong, H. (2017) · Future Generation Computer Systems · doi:10.1016/j.future.2017.09.067 · Cited by 62
“Xu et al. [38] analyze logs to extract feature vectors, and then use PCA to detect the change of correlations between vector dimensions.”
MethodCloudSeer: Workflow Monitoring of Cloud Infrastructures via Interleaved Logs
Yu, X., Joshi, P., Xu, J., Jin, G., Zhang, H., & Jiang, G. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/2980024.2872407 · Cited by 60
KubAnomaly: Anomaly detection for the Docker orchestration platform with neural network approaches
Tien, C., Huang, T., Tien, C., Huang, T., & Kuo, S. (2019) · Engineering Reports · doi:10.1002/eng2.12080 · Cited by 61
“Xu et al 8 parsed console logs via source code analysis and information retrieval to create composite features for automatically detecting a system runtime problem.”
MethodLandauer, M., Skopik, F., & Wurzenberger, M. (2024) · Proceedings of the ACM on Software Engineering · doi:10.1145/3660768 · Cited by 61
“The main idea of detecting anomalies in this data set is that some data blocks are not processed correctly by the system, which is reflected by the log events generated as the block goes through an abnormal execution flow, in which case the entire sequence should be detected as anomalous [37].”
BackgroundImproving Log-Based Anomaly Detection by Pre-Training Hierarchical Transformers
Huang, S.-H., Liu, Y., Fung, C. J., Wang, H., Yang, H.-L., & Luan, Z.-Z. (2023) · IEEE transactions on computers · doi:10.1109/tc.2023.3257518 · Cited by 54
Visual, Log-Based Causal Tracing for Performance Debugging of MapReduce Systems
Tan, J., Kavulya, S. P., Gandhi, R., & Narasimhan, P. (2010) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2010.63 · Cited by 61
“Other work has focused on handling errors: [31] mined DataNode logs to detect outlier error messages; [32] traces errors to originating components.”
BackgroundUiLog: Improving Log-Based Fault Diagnosis by Log Analysis
Zou, D., Qin, H., & Jin, H. (2016) · Journal of Computer Science and Technology · doi:10.1007/s11390-016-1678-7 · Cited by 61
“Keywords fault diagnosis, system event log, log classification, fault correlation analysis”
MethodXia, B., Bai, Y., Yin, J., Li, Y., & Xu, J. (2020) · Information Systems Frontiers · doi:10.1007/s10796-020-10026-3 · Cited by 61
“– PCA (Wei et al. 2009): is an unsupervised principal component analysis-based anomaly detection technique which improves the parser of unstructured systems and visualizes the promising diagnosis of abnormal instances.”
MethodInfluentialA Systematic Review on Anomaly Detection for Cloud Computing Environments
Hagemann, T., & Katsarou, K. (2020) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3442536.3442550 · Cited by 82
Machine learning to detect anomalies in web log analysis
Cao, Q., Qiao, Y., & Lyu, Z. (2017) · 2017 3rd IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/compcomm.2017.8322600 · Cited by 55
“Due to the development of machine learning, many machine learning algorithms are also applied in log-based anomaly detection [2].”
MethodMachine Learning With Variational AutoEncoder for Imbalanced Datasets in Intrusion Detection
Lin, Y., Liu, Z.-Q., Hwang, R., Nguyen, V.-L., Lin, P., & Lai, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3149295 · Cited by 68
“The HDFS dataset is a public dataset made by [38], and the complete raw dataset is available from Loghub [40].”
MethodLi, B., Ma, S., Deng, R., Choo, K. R., & Yang, J. Q. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3152620 · Cited by 69
“While the performance evaluation findings using both HDFS [1] and BGL [37] datasets suggested that FedLog out-performs two other competing log-based anomaly detection models [7], [8] under both centralized learning and federated learning paradigms, there are a number of potential extensions to this…”
MethodInfluentialJallad, K. A., Aljnidi, M., & Desouki, M. S. (2019) · Journal Of Big Data · doi:10.1186/s40537-019-0248-6 · Cited by 59
Understanding Log Lines Using Development Knowledge
Shang, W., Nagappan, M., Hassan, A. E., & Jiang, Z. M. (2014) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme.2014.24 · Cited by 67
An empirical study on crash recovery bugs in large-scale distributed systems
Gao, Y., Dou, W., Qin, F., Gao, C., Wang, D., Wei, J., Huang, R., Zhou, L., & Wu, Y. (2018) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3236024.3236030 · Cited by 70
“Xu et al. [39] automatically finds out problems at runtime by mining console logs.”
BackgroundCalifornia fault lines: understanding the causes and impact of network failures
Turner, D., Levchenko, K., Snoeren, A. C., & Savage, S. (2010) · ACM SIGCOMM Computer Communication Review · doi:10.1145/1851275.1851220 · Cited by 71
RAGLog: Log Anomaly Detection using Retrieval Augmented Generation
Pan, J. Z., Wong, S. L., & Yidi, Y. (2024) · IEEE World Forum on Public Safety Technology (WF-PST) · doi:10.1109/wfpst58552.2024.00034 · Cited by 83
Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection
Wang, Z., Chen, Z., Ni, J., Liu, H., Chen, H., & Tang, J. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467125 · Cited by 56
“For example, system logs that record the detailed messages of run time information of modern computer systems are extensively used for anomaly detection [14, 23, 27, 36].”
MethodInfluentialTemporal Logical Attention Network for Log-Based Anomaly Detection in Distributed Systems
Liu, Y., Ren, S., Wang, X., & Zhou, M. (2024) · Sensors · doi:10.3390/s24247949 · Cited by 110
“Xu et al. [12] proposed source code-based parsing to extract log templates.”
Online failure prediction in cloud datacenters by real-time message pattern learning
Watanabe, Y., Otsuka, H., Masataka, S., Kikuchi, S., & Matsumoto, Y. (2012) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom.2012.6427566 · Cited by 56
Device-Agnostic Log Anomaly Classification with Partial Labels
Meng, W., Liu, Y., Zhang, S., Pei, D., Dong, H., Song, L., & Luo, X. (2018) · 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS) · doi:10.1109/iwqos.2018.8624141 · Cited by 52
“For example, [18] utilizes source code of gengrating logs to extract log templates, but not all source codes can be acquired.”
BackgroundMethodLogClass: Anomalous Log Identification and Classification With Partial Labels
Meng, W., Liu, Y., Zhang, S., Zaiter, F., Zhang, Y., Huang, Y., Yu, Z., Zhang, Y., Song, L., Zhang, M., et al. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3055425 · Cited by 56
“Consequently, in this article we ignore these parameter words following popular log-based anomaly detection methods, e.g., Invariants Mining [23], PCA [32], LogRubust [11], and LogAnomaly [7].”
MethodJia, T., Wu, Y., Hou, C., & Li, Y. (2021) · 2021 IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE) · doi:10.1109/issre52982.2021.00021 · Cited by 55
A protocol-independent container network observability analysis system based on eBPF
Liu, C., Cai, Z., Wang, B., Tang, Z., & Liu, J. (2020) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads51040.2020.00099 · Cited by 55
Safety Risk Monitoring of Cyber-Physical Power Systems Based on Ensemble Learning Algorithm
Li, Q., Meng, S., Zhang, S., Wu, M., Zhang, J., Ahvanooey, M. T., & Aslam, M. S. (2019) · IEEE Access · doi:10.1109/access.2019.2896129 · Cited by 55
“In the absence of training data, unstructured log data conversion can also be done by analyzing the source code generated by its logs [10].”
MethodNo More Labelled Examples? An Unsupervised Log Parser with LLMs
Huang, J., Jiang, Z., Chen, Z., & Lyu, M. R.-T. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3729377 · Cited by 63
Limplock: understanding the impact of limpware on scale-out cloud systems
Do, T., Hao, M., Leesatapornwongsa, T., Patana-anake, T., & Gunawi, H. S. (2013) · Symposium on Cloud Computing · doi:10.1145/2523616.2523627 · Cited by 67
“To unearth design flaws, pinpoint implementation bugs, or diagnose misconfiguration, many approaches analyze systemspecific information such as request flows [38], systems logs [51], and configuration snapshots [48].”
BackgroundSelf-Adaptive Cloud Capacity Planning
Jiang, Y., Perng, C.-S., Li, T., & Chang, R. (2012) · IEEE International Conference on Services Computing · doi:10.1109/scc.2012.8 · Cited by 53
“Xu et al [18] introduced an anomaly detection algorithm to detect the system faults by utilizing the system source code and logs.”
MethodLOGAN: Problem Diagnosis in the Cloud Using Log-Based Reference Models
Tak, B. C., Tao, S., Yang, L., Zhu, C., & Ruan, Y. (2016) · 2016 IEEE International Conference on Cloud Engineering (IC2E) · doi:10.1109/ic2e.2016.12 · Cited by 54
“Xu et al. [16] developed an automated anomaly detection mechanism that applies PCA (Principal Component Analysis) to log feature vectors.”
MethodnLSALog: An Anomaly Detection Framework for Log Sequence in Security Management
Yang, R., Qu, D., Gao, Y., Qian, Y., & Tang, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2953981 · Cited by 52
“For HDFS log dataset [43], the block_id identifier is taken as the basic operating unit for the study of this dataset in literature [17], [25], and the log messages contains in the same block_id are treated as a session window.”
MethodSPINE: a scalable log parser with feedback guidance
Wang, X., Zhang, X., Li, L., He, S., Zhang, H., Liu, Y., Zheng, L., Kang, Y., Lin, Q., Dang, Y., et al. (2022) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3540250.3549176 · Cited by 63
“A straightforward idea for log parsing is to match log messages with the logging statements in the corresponding source code [34].”
BackgroundLayerLog: Log sequence anomaly detection based on hierarchical semantics
Zhang, C., Wang, X., Zhang, H., Zhang, J., Zhang, H., Liu, C., & Han, P. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109860 · Cited by 54
MetaLog: Generalizable Cross-System Anomaly Detection from Logs with Meta-Learning
Zhang, C., Jia, T., Shen, G., Zhu, P., & Li, Y. (2024) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3597503.3639205 · Cited by 64
LLMeLog: An Approach for Anomaly Detection based on LLM-enriched Log Events
He, M., Jia, T., Duan, C., Cai, H., Li, Y., & Huang, G. (2024) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre62328.2024.00023 · Cited by 79
“To deeply understand these problems, in this paper, we first make an empirical study on the representations of log events from three public datasets [15] including HDFS [16], BGL [17], and Thunderbird [17].”
Principled workflow-centric tracing of distributed systems
Sambasivan, R. R., Shafer, I., Mace, J., Sigelman, B. H., Fonseca, R., & Ganger, G. R. (2016) · Proceedings of the Seventh ACM Symposium on Cloud Computing · doi:10.1145/2987550.2987568 · Cited by 47
Using deep learning to solve computer security challenges: a survey
Choi, Y.-H., Liu, P., Shang, Z., Wang, H., Wang, Z., Zhang, L., Zhou, J., & Zou, Q. (2020) · Cybersecurity · doi:10.1186/s42400-020-00055-5 · Cited by 63
DeCaf: diagnosing and triaging performance issues in large-scale cloud services
Bansal, C., Renganathan, S., Asudani, A., Midy, O., & Janakiraman, M. (2020) · Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering: Software Engineering in Practice · doi:10.1145/3377813.3381353 · Cited by 44
“al [32] jointly analyze source code and console logs to extract features and perform anomaly detecting on these feature collections.”
Liu, P., Chen, Y., Nie, X., Zhu, J., Zhang, S., Sui, K., Zhang, M., & Pei, D. (2019) · 2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE) · doi:10.1109/issre.2019.00014 · Cited by 48
“Works [71, 72] train the normal pattern from history data and use these patterns to detect the anomalies.”
MethodJin, M., Lv, A., Zhu, Y., Wen, Z., Zhong, Y., Zhao, Z., Wu, J., Li, H., He, H., & Chen, F. (2020) · IEEE Access · doi:10.1109/access.2020.3044610 · Cited by 50
A Systematic Mapping Study in AIOps
Notaro, P., Cardoso, J., & Gerndt, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-76352-7_15 · Cited by 63
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.