Constructing Large-Scale Real-World Benchmark Datasets for AIOps

doi:10.12142/ZTECOM.202603008

ZTE Communications ›› 2026, Vol. 24 ›› Issue (3): 59-69.DOI: 10.12142/ZTECOM.202603008

• Industry-Academia Co-Research • Previous Articles Next Articles

Constructing Large-Scale Real-World Benchmark Datasets for AIOps

Li Zeyan¹, Han Jing²(), Zhao Nengwen¹, Zhang Shenglin³, Sun Yongqian³, Chen Pengfei⁴, Wen Xidao¹, Ma Minghua⁵, Pei Dan¹

^1.Tsinghua University, Beijing 100084, China
^2.ZTE Corporation, Shenzhen 518057, China
^3.Nankai University, Tianjin 300071, China
^4.Sun Yat?sen University, Guangzhou 510275, China
^5.Microsoft Research, Redmond, WA 98052, USA

Received:2025-02-21 Online:2026-09-03 Published:2026-09-20
About author:Li Zeyan received his PhD degree in computer science and technology from Tsinghua University, China in 2023, where he was a member of the Tsinghua NetMan Lab under the supervision of Prof. Pei Dan. He received his bachelor's degree in computer science and technology from Tsinghua University in 2018. His research interests focus on Artificial Intelligence for IT Operations (AIOps), particularly intelligent fault localization, root cause analysis, and reliability management for large-scale online service systems.
Han Jing (han.jing28@zte.com.cn) is a researcher and engineer at ZTE Corporation, where she develops next-generation intelligent network architectures, 6G wireless intelligence, and automated software maintenance systems.
Zhao Nengwen received her PhD degree in computer science and technology from Tsinghua University, China in 2022 under the supervision of Prof. Pei Dan, and her bachelor's degree in computer science and technology from Wuhan University, China in 2017. Her research interests include Artificial Intelligence for IT Operations (AIOps), software maintenance, and reliability management, with particular emphasis on anomaly detection, alert management, log anomaly detection, and software change analysis in large-scale online service systems.
Zhang Shenglin is a Professor at the College of Software, Nankai University, China and an affiliated faculty member of the Tsinghua NetMan Lab. He received his PhD degree in computer science and technology from Tsinghua University, China under the supervision of Prof. Pei Dan and Prof. Liu Ying, and his bachelor's degree in network engineering from Xidian University, China in 2012. During his doctoral studies, he was a visiting scholar at the School of Computer Science, Georgia Institute of Technology, USA. His research focuses on Artificial Intelligence for IT Operations (AIOps), including failure detection, diagnosis and prediction, root cause analysis, log and multimodal observability analysis, and reliability management for large-scale service and cloud systems.
Sun Yongqian is an Associate Professor at Nankai University, China and an affiliated faculty member of the Tsinghua NetMan Lab. He received his PhD degree from the Department of Computer Science and Technology at Tsinghua University, China under the supervision of Prof. Pei Dan and Prof. Zhao Youjian, and his bachelor's degree in statistics from Northwestern Polytechnical University, China in 2012. His research interests center on Artificial Intelligence for IT Operations (AIOps), including anomaly detection, failure diagnosis, root cause analysis, failure prediction, and intelligent operations for microservice and large-scale software systems.
Chen Pengfei is a Professor and doctoral supervisor at the School of Computer Science and Engineering, Sun Yat-sen University, China. He received his PhD degree in computer science from Xi'an Jiaotong University, China in 2016. His research interests include Artificial Intelligence for IT Operations (AIOps), distributed systems, cloud computing, microservices, software reliability, and computer networks, with particular focus on automated performance diagnosis, root cause analysis, anomaly detection, and intelligent management of cloud-native and microservice systems.
Wen Xidao was a postdoctoral researcher at Tsinghua University, China and a member of the Tsinghua NetMan Lab, completing his postdoctoral work in 2022. His research interests include Artificial Intelligence for IT Operations (AIOps), data mining, machine learning, time-series analysis, anomaly detection, fault diagnosis, and intelligent operations for large-scale service systems. He has collaborated extensively on research in multivariate time-series anomaly detection, software change analysis, root cause diagnosis, AIOps benchmarks, and large language models for IT operations.
Ma Minghua is a Senior Researcher at Microsoft Research in Redmond, USA. He received his PhD degree in computer science and technology from Tsinghua University, China in 2021 under the supervision of Prof. Pei Dan. From 2019 to 2020, he was a visiting scholar at the School of Computer Science, Georgia Institute of Technology, USA. His research interests lie at the intersection of software engineering, systems, and artificial intelligence, with a particular focus on Cloud Intelligence and Artificial Intelligence for IT Operations (AIOps).
Pei Dan is a Professor in the Department of Computer Science and Technology, Tsinghua University, China and the leader of the Tsinghua NetMan Lab. His current research focuses on Artificial Intelligence for IT Operations (AIOps) for critical infrastructure and embodied systems, as well as time-series intelligence. Before joining Tsinghua University, he was a researcher at AT&T Labs–Research in the United States. He is a Senior Member of both ACM and IEEE and has extensive research experience in networked systems, large-scale service reliability, intelligent operations, root cause analysis, anomaly detection, and time-series intelligence.
Supported by:
ZTE Industry?University?Institute Cooperation Funds(IA20231009003)

Abstract

Abstract:

Artificial Intelligence for IT Operations (AIOps) has emerged as a critical approach for managing complex IT systems, yet its advancement has been hindered by the lack of comprehensive public datasets for evaluation. This study addresses this challenge by introducing three large-scale, real-world benchmark datasets specifically designed for AIOps research and development. We present datasets covering key AIOps scenarios: key performance indicator (KPI) anomaly detection with diverse patterns from multiple Internet companies, multi-dimensional root cause localization with 400 labeled cases, and failure discovery and diagnosis containing 169 injected failures across various system components. These datasets are distinguished by their scale, authenticity, and detailed ground-truth labels, enabling rigorous evaluation of AIOps algorithms. The practical value of our datasets has been validated through three annual AIOps algorithm competitions (2018–2020), which attracted over 400 participating teams and led to numerous research publications. By providing these comprehensive benchmarks, our work establishes a foundation for reproducible AIOps research and facilitates fair comparison of different approaches, serving a role for AIOps analogous to that of ImageNet in computer vision.

Key words: AIOps, benchmark datasets, KPI anomaly detection, root cause localization, failure discovery and diagnosis

Li Zeyan, Han Jing, Zhao Nengwen, Zhang Shenglin, Sun Yongqian, Chen Pengfei, Wen Xidao, Ma Minghua, Pei Dan. Constructing Large-Scale Real-World Benchmark Datasets for AIOps[J]. ZTE Communications, 2026, 24(3): 59-69.

Figures/Tables 13

References 58

[1]	Moore S. Gartner: how to get started with AIOps [EB/OL]. [2024-04-15].
[2]	Bu J, Liu Y, Zhang S, et al. Rapid deployment of anomaly detection models for large number of emerging KPI streams [C]//Proceedings of the 2018 IEEE International Performance, Computing and Communications Conference (IPCCC). IEEE, 2018: 1–8. DOI: 10.1109/PCCC.2018.8711315
[3]	Xu H, Chen W, Zhao N, et al. Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications [C]//Proceedings of the 2018 World Wide Web Conference (WWW). ACM, 2018: 187–196. DOI: 10.1145/3178876.3185996
[4]	Liu D P, Zhao Y J, Xu H W, et al. Opprentice: towards practical and automatic anomaly detection through machine learning [C]//Proceedings of the 2015 Internet Measurement Conference. ACM, 2015: 211–224. DOI: 10.1145/2815675.2815679
[5]	Ma M, Zhang S, Chen J, et al. Jump-starting multivariate time series anomaly detection for online service systems [C]//Proceedings of the 2021 USENIX Annual Technical Conference. USENIX Association, 2021: 413–426. DOI: 10.5555/3472716.3472752
[6]	Li Z Y, Luo C Y, Zhao Y W, et al. Generic and robust localization of multi-dimensional root causes [C]//Proceedings of IEEE 30th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 2019: 47–57. DOI: 10.1109/ISSRE.2019.00015
[7]	Gu J, Luo C, Qin S, et al. Efficient incident identification from multi-dimensional issue reports via metaheuristic search [C]//Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020). ACM, 2020: 1234–1245. DOI: 10.1145/3368089.3409742
[8]	Ahmed F, Erman J, Ge Z H, et al. Detecting and localizing end-to-end performance degradation for cellular data services based on TCP loss ratio and round trip time [J]. IEEE/ACM transactions on networking, 2017, 25(6): 3709–3722. DOI: 10.1109/TNET.2017.2761758
[9]	Bhagwan R, Kumar R, Ramjee R, et al. Adtributor: revenue debugging in advertising systems [C]//Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14). USENIX Association, 2014: 43–55
[10]	Jing P K, Han Y N, Sun J Y, et al. AutoRoot: a novel fault localization schema of multi-dimensional root causes [C]//Proceedings of IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 2021: 1–7. DOI: 10.1109/wcnc49053.2021.9417302
[11]	Lin Q, Lou J-G, Zhang H, et al. iDice: problem identification for emerging issues [C]//Proceedings of the 38th International Conference on Software Engineering (ICSE 2016). ACM, 2016: 214–224. DOI: 10.1145/2884781.2884824
[12]	Lin F, Muzumdar K, Laptev N P, et al. Fast dimensional analysis for root cause investigation in a large-scale service environment [J]. Proceedings of the ACM on measurement and analysis of computing systems, 2020, 4(2): 1–23. DOI: 10.1145/3392149
[13]	Qureshi M A, Qiu L L, Mahimkar A, et al. Multi-dimensional impact detection and diagnosis in cellular networks [C]//Proceedings of 16th International Conference on Mobility, Sensing and Networking (MSN). IEEE, 2020: 561–568. DOI: 10.1109/msn50589.2020.00093
[14]	Sun Y Q, Zhao Y J, Su Y, et al. HotSpot: anomaly localization for additive KPIs with multi-dimensional attributes [J]. IEEE access, 2018, 6: 10909–10923. DOI: 10.1109/ACCESS.2018.2804764
[15]	Wang H, Rong G P, Xu Y C, et al. ImpAPTr: a tool for identifying the clues to online service anomalies [C]//Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering. ACM, 2021: 1307–1311. DOI: 10.1145/3324884.3415301
[16]	Zhang X, Du C, Li Y F, et al. HALO: hierarchy-aware fault localization for cloud systems [C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. ACM, 2021: 3948–3958. DOI: 10.1145/3447548.3467190
[17]	Ma M H, Yin Z, Zhang S L, et al. Diagnosing root causes of intermittent slow queries in cloud databases [J]. Proceedings of the VLDB endowment, 2020, 13(8): 1176–1189. DOI: 10.14778/3389133.3389136
[18]	Zhao N, Chen J, Wang Z, et al. Real-time incident prediction for online service systems [C]//Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020). ACM, 2020: 315–326. DOI: 10.1145/3368089.3409745
[19]	Lin Q, Hsieh K, Dang Y, et al. Predicting node failure in cloud service systems [C]//Proceedings of the 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2018). ACM, 2018: 858–868. DOI: 10.1145/3236024.3275511
[20]	Xu Y, Sui K, Yao R, et al. Improving service availability of cloud systems by predicting disk error [C]//Proceedings of the 2018 USENIX Annual Technical Conference (USENIX ATC 18). USENIX Association, 2018: 481–494. DOI: 10.5555/3277355.3277400
[21]	Chen Y J, Yang X, Lin Q W, et al. Outage prediction and diagnosis for cloud service systems [C]//Proceedings of World Wide Web Conference. ACM, 2019: 2659–2665. DOI: 10.1145/3308558.3313501
[22]	Shatnawi M, Hefeeda M. Real-time failure prediction in online services [C]//Proceedings of IEEE Conference on Computer Communications (INFOCOM). IEEE, 2015: 1391–1399. DOI: 10.1109/infocom.2015.7218516
[23]	Zhang K, Xu J, Min M R, et al. Automated IT system failure prediction: a deep learning approach [C]//Proceedings of the 2016 IEEE International Conference on Big Data (Big Data 2016). IEEE, 2016: 1291–1300. DOI: 10.1109/BigData.2016.7840760
[24]	Chen Z B, Kang Y, Li L Q, et al. Towards intelligent incident management: why we need it and how we make it [C]//Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ACM, 2020: 1487–1497. DOI: 10.1145/3368089.3417055
[25]	Chen J, He X, Lin Q, et al. An empirical investigation of incident triage for online service systems [C]//Proceedings of the 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice. IEEE, 2019: 111–120. DOI: 10.1109/ICSE-SEIP.2019.00021
[26]	Chen J, He X, Lin Q, et al. Continuous incident triage for large-scale online service systems [C]//Proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering (ASE 2019). IEEE, 2019: 1126–1129. DOI: 10.1109/ASE.2019.00128
[27]	Lou J G, Lin Q W, Ding R, et al. Experience report on applying software analytics in incident management of online service [J]. Automated software engineering, 2017, 24(4): 905–941. DOI: 10.1007/s10515-017-0218-1
[28]	Delimitrou C, Kozyrakis C. Quasar: resource-efficient and QoS-aware cluster management [J]. ACM SIGPLAN notices, 2014, 49(4): 127–144. DOI: 10.1145/2644865.2541941
[29]	Cortez E, Bonde A, Muzio A, et al. Resource central: understanding and predicting workloads for improved resource management in large cloud platforms [C]//Proceedings of the 26th Symposium on Operating Systems Principles. ACM, 2017: 153–167. DOI: 10.1145/3132747.3132772
[30]	Laptev N, Amizadeh S, Flint I. Generic and scalable framework for automated time-series anomaly detection [C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2015: 1939–1947. DOI: 10.1145/2783258.2788611
[31]	Zhou X, Peng X, Xie T, et al. Latent error prediction and fault localization for microservice applications by learning from system trace logs [C]//Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ACM, 2019: 683–694. DOI: 10.1145/3338906.3338961
[32]	NetManAIOps. KPI-Anomaly-Detection: 2018 AIOps Challenge dataset [EB/OL]. [2024-04-15].
[33]	NetManAIOps. MultiDimension-Localization: 2019 AIOps Challenge dataset [EB/OL]. [2024-04-15].
[34]	NetManAIOps. AIOps-Challenge-2020-Data [EB/OL]. [2024-04-15].
[35]	Wang X R, Yin K L, Ouyang Q Y, et al. Identifying erroneous software changes through self-supervised contrastive learning on time series data [C]//Proceedings of IEEE 33rd International Symposium on Software Reliability Engineering (ISSRE). IEEE, 2022: 366–377. DOI: 10.1109/issre55969.2022.00043
[36]	Ren H S, Xu B X, Wang Y J, et al. Time-series anomaly detection service at microsoft [C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2019: 3009–3017. DOI: 10.1145/3292500.3330680
[37]	Zhao N W, Zhu J, Liu R, et al. Label-less: a semi-automatic labelling tool for KPI anomalies [C]//Proceedings of IEEE Conference on Computer Communications. IEEE, 2019: 1882–1890. DOI: 10.1109/infocom.2019.8737429
[38]	Cai Y, Han B, Li J, et al. ModelCoder: a fault model based automatic root cause localization framework for microservice systems [C]//Proceedings of IEEE/ACM 29th International Symposium on Quality of Service (IWQOS). IEEE, 2021: 1–6. DOI: 10.1109/iwqos52092.2021.9521318
[39]	Yu G B, Chen P F, Chen H Y, et al. MicroRank: end-to-end latency issue localization with extended spectrum analysis in microservice environments [C]//Proceedings of the Web Conference 2021. ACM, 2021: 3087–3098. DOI: 10.1145/3442381.3449905
[40]	Li Z Y, Chen J J, Jiao R, et al. Practical root cause localization for microservice systems via trace analysis [C]//Proceedings of IEEE/ACM 29th International Symposium on Quality of Service (IWQOS). IEEE, 2021: 1–10. DOI: 10.1109/iwqos52092.2021.9521340
[41]	Chen Z, Liu J, Su Y, et al. Adaptive performance anomaly detection for online service systems via pattern sketching [C]//Proceedings of the 44th International Conference on Software Engineering (ICSE 2022). ACM, 2022: 2009–2020. DOI: 10.1145/3510003.3510087
[42]	AIOps Workshop [EB/OL]. [2024-04-15].
[43]	Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database [C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009). IEEE, 2009: 248–255. DOI: 10.1109/CVPR.2009.5206848
[44]	Notaro P, Cardoso J, Gerndt M. A survey of AIOps methods for failure management [J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2021, 12(6): 1–45. DOI: 10.1145/3483423
[45]	Zhang X, Kim J, Lin Q, et al. Cross-dataset time series anomaly detection for cloud systems [C]//Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC 19). USENIX Association, 2019: 1063–1076. DOI: 10.5555/3358807.3358903
[46]	Lavin A, Ahmad S. Evaluating real-time anomaly detection algorithms: the numenta anomaly benchmark [C]//Proceedings of IEEE 14th International Conference on Machine Learning and Applications (ICMLA). IEEE, 2015: 38–44. DOI: 10.1109/ICMLA.2015.141
[47]	Li Z, Chen J, Chen Y, et al. Generic and robust root cause localization for multi-dimensional data in online service systems [J]. Journal of systems and software, 2023, 203: 111748. DOI: 10.1016/j.jss.2023.111748
[48]	Li Z, Zhao N, Li M, et al. Actionable and interpretable fault localization for recurring failures in online service systems [C]//Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2022). ACM, 2022: 996–1008. DOI: 10.1145/3540250.3549162
[49]	Kim M, Sumbaly R, Shah S. Root cause detection in a service-oriented architecture [J]. ACM SIGMETRICS performance evaluation review, 2013, 41(1): 93–104. DOI: 10.1145/2494232.2465753
[50]	Ma M, Xu J, Wang Y, et al. AutoMAP: diagnose your microservice-based web applications automatically [C]//Proceedings of the 2020 World Wide Web Conference (WWW 2020). ACM, 2020: 320–330. DOI: 10.1145/3366423.3380115
[51]	Lin J, Chen P, Zheng Z. Microscope: pinpoint performance issues with causal graphs in micro-service environments [C]//Proceedings of the 16th International Conference on Service-Oriented Computing (ICSOC 2018). Springer, 2018: 3–20. DOI: 10.1007/978-3-030-03596-9_1
[52]	Gan Y, Liang M, Dev S, et al. Sage: practical and scalable ML-driven performance debugging in microservices [C]//Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2021). ACM, 2021: 135–151. DOI: 10.1145/3445814.3446700
[53]	Yu Q, Pei C, Hao B, et al. CMDiagnostor: an ambiguity-aware root cause localization approach based on call metric data [C]//Proceedings of the ACM Web Conference 2023 (WWW 2023). ACM, 2023: 2937–2947. DOI: 10.1145/3543507.3583347
[54]	Liu P, Chen Y, Nie X, et al. FluxRank: a widely-deployable framework to automatically localize root cause machines for software service failure mitigation [C]//Proceedings of the 2019 IEEE 30th International Symposium on Software Reliability Engineering. IEEE, 2019: 35–46. DOI: 10.1109/ISSRE.2019.00014
[55]	Wu L, Tordsson J, Bogatinovski J, et al. MicroDiag: fine-grained performance diagnosis for microservice systems [C]//Proceedings of IEEE/ACM International Workshop on Cloud Intelligence (CloudIntelligence). IEEE, 2021: 31–36. DOI: 10.1109/cloudintelligence52565.2021.00015
[56]	Lu X, Xie Z, Li Z, et al. Generic and robust performance diagnosis via causal inference for OLTP database systems [C]//Proceedings of the 2022 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid 2022). IEEE, 2022: 655–664. DOI: 10.1109/CCGrid54584.2022.00076
[57]	Li M, Li Z, Yin K, et al. Causal inference-based root cause analysis for online service systems with intervention recognition [C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022). ACM, 2022: 3230–3240. DOI: 10.1145/3534678.3539041
[58]	Lee C, Yang T, Chen Z, et al. Eadro: an end-to-end troubleshooting framework for microservices on multi-source data [C]//Proceedings of the 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023). IEEE, 2023: 1750–1762. DOI: 10.1109/ICSE48619.2023.00150

Statistic	Value	Range	Mean
KPI series	26	-	-
Data points	4 821 526	16 495–295 379	185 443.31
Reported anomaly ratio	-	0.01%–4.37%	0.96%
Time span/d	-	60–207	148.31

Statistic	Value	Range	Mean
KPI series	26	-	-
Data points	4 821 526	16 495–295 379	185 443.31
Reported anomaly ratio	-	0.01%–4.37%	0.96%
Time span/d	-	60–207	148.31

Dataset	Origin	Average Length	Average Anomaly Ratio
A	Real	211 969.75	0.022 7
WSD	Real	36 471.00	0.016
UCR	Real	55 935.25	0.003
TODS	Real	10 000.00	0.058
Yahoo	Real	1 561.22	0.007
NAB	Real	15 863.10	0.098

Dataset	Origin	Average Length	Average Anomaly Ratio
A	Real	211 969.75	0.022 7
WSD	Real	36 471.00	0.016
UCR	Real	55 935.25	0.003
TODS	Real	10 000.00	0.058
Yahoo	Real	1 561.22	0.007
NAB	Real	15 863.10	0.098

Order ID	Timestamp	Amount (CNY)	Region	ISP
T001	2021.11.11 10:00:01	102	Beijing	China Mobile
T002	2021.11.11 10:00:05	134	Beijing	China Unicom

Constructing Large-Scale Real-World Benchmark Datasets for AIOps

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 58

Related Articles 0

Recommended Articles

Metrics

callType	startTime(Unix)/ms	elapsedTime/ms	success	traceId	id	pid	cmdbId	serviceName
OSB	1590249600016	274	True	568385015	919979385015	None	os_021	osb_001
CSF	1590249600025	257	True	568385015	4eba31485915	919979385015	os_021	csf_001
RemoteProcess	1590249600026	254	True	568385015	82dad5063a15	4eba31485915	docke_ 003	csf_001

Category	Metrics List
Docker	container_{thread_total, fgct, thread_idle, thread_used_pct, session_used, thread_running, fgc, cpu_used, mem_used, fail_percent}
Linux	Agent_ping, Buffers_used, CPU_{idle_pct, user_time, system_time, iowait_time, util_pct}, Cache_used, Disk_{rd_ios, io_util, await, avgqu_sz, svctm, wr_kbs, rd_kbs, wr_ios}, FS_{used_space, used_pct, total_space, max_util, max_avail}, ICMP_ping, Incoming_network_traffic, Memory_{used_pct, used, available, free, available_pct, total}, Num_{of_processes, of_running_processes}, Outgoing_network_traffic, Page_{po, pi}, Processor_{load_5_min, load_1_min, load_15_min}, Received_{packets, errors_packets, queue}, Recv_total, Send_total, Sent_{errors_packets, queue, packets}, Shared_memory, Swap_used_pct, System_{wait_queue_length, block_queue_length}, Zombie_Process, ss_total
Oracle	ACS, AIOS, AWS, Asm_Free_Tb, CPU_{free_pct, Used_Pct}, Call_Per_Sec, DFParaWrite_Per_Sec, DbFile_Used_Pct, DbTime, Exec_Per_Sec, Hang, LFParaWrite_Per_Sec, LFSync_Per_Sec, Logic_Read_Per_Sec, Login_Per_Sec, MEM_{real_util, Used, Total, Used_Pct}, New_{Tbs_Free_Gb, Tbs_Used_Pct}, On_Off_State, PGA_{Used_Pct, used_total}, Physical_Read_Per_Sec, Proc_{User_Used_Pct, Used_Pct}, Redo_Per_Sec, Row_Lock, SEQ_Used_Pct, SctRead_Per_Sec, SeqRead_Per_Sec, Sess_{Used_Undo, Used_Temp, Connect, Active}, Session_pct, TPS_Per_Sec, Tbs_{Used_Pct, Free_Gb}, TempTbs_Pct, Total_Tbs_Size, UndoTbs_Pct, Used_Tbs_Size, User_Commit, tnsping_result_time
Redis	Redis_key_count, blocked_clients, connected_clients, evicted_keys, expired_keys, instantaneous_{output_kbps, input_kbps, ops_per_sec}, keyspace_{hits, misses}, maxmemory, mem_fragmentation_ratio, redis_{ping, load}, rejected_connections, total_{connections_received, commands_processed}, used_{memory_peak, cpu_sys, memory_rss, cpu_user, memory}

Component	Injection type	Description
Database	Close	Close the listening port of the target instance
Database	Session limit	Decrease the session limit of the target instance
Container	CPU stress (*)	Stress the CPU of the target container
Container	Network delay ($)	Randomly delay packets on the target container
Container	Network loss ($)	Randomly drop packets on the target container
Physical node	Network delay ($)	Randomly delay packets on the target node
Physical node	Network loss ($)	Randomly drop packets on the target node

Dataset	Origin	Cases	Modality
Dataset C	Real	169	Trace/Metric
DejaVu	Testbed	601	Trace/Metric
Eadro	Testbed	117	Log/Metric/Trace
Nezha	Testbed	21	Log/Metric/Trace
SMAP, MSL	Real	105	Metric
TraceRCA	Testbed	33	Trace