Modern cloud services rely on a high volume of changes for rapid innovation, yet these changes are a primary cause of production incidents. To manage this risk, industry practice employs tiered change management pipelines that concentrate static rules and human reviews. However, our analysis of ByteDance's cloud platform (Volcano Engine) reveals a critical long tail problem: while high-risk changes undergo extensive scrutiny, 78.1% of change-induced incidents originate from the sheer volume of low-risk changes that receive minimal review. At this scale, exhaustive manual review is fundamentally infeasible. To address this, we present Aegis, a novel knowledge-driven system that provides interpretable change risk assessment. Aegis automatically constructs a knowledge base from historical operational data, distilling it into generalized risk heuristics and identifying relevant precedent cases. When a new change is proposed, Aegis generates human-readable warnings grounded in this historical evidence, explaining why a change is risky. We have deployed Aegis in Volcano Engine's production environment for five months, where it processed tens of thousands of change requests. Its risk escalations achieved a 75% acceptance rate from production engineers and successfully prevented multiple potential incidents.

Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure is lost when stored as flat sequences. As a result, state-of-the-art methods often miss true dependencies within executions while learning spurious correlations across unrelated events. We propose KRONE, the first hierarchical anomaly detection framework that automatically derives execution hierarchies from flat logs to enable modular, multi-level anomaly detection. At its core, the KRONE Log Abstraction Model extracts application-specific semantic hierarchies, which are used to recursively decompose log sequences into coherent execution units, referred to as KRONE Seqs. This transforms sequence-level detection into a set of modular KRONE Seq-level detection tasks. For each test KRONE Seq, KRONE adopts a hybrid modular detection strategy that routes between an efficient level-independent Local-Context detector for rapid filtering and a Nested-Aware detector that captures cross-level semantic dependencies, augmented with LLM-based anomaly detection and explanation. KRONE further optimizes detection through cached result reuse and early-exit strategies along the hierarchy. Experiments on three public benchmarks and one industrial dataset from ByteDance Cloud demonstrate that KRONE achieves substantial improvements in accuracy (42.49% to 87.98%), F1 score, data efficiency (117.3x reduction), resource efficiency (43.7x reduction), and interpretability. KRONE improves F1-score by 10.07% (82.76% to 92.83%) over prior methods while reducing LLM usage to only 1.1% to 3.3% of the test data. Code: https://github.com/LeiMa0324/KRONE Demo: https://leima0324.github.io/KRONE_Demo_official/

Runtime failures are commonplace in modern distributed systems. When such issues arise, users often turn to platforms such as Github or JIRA to report them and request assistance. Automatically identifying the root cause of these failures is critical for ensuring high reliability and availability. However, prevailing automatic root cause analysis (RCA) approaches rely significantly on comprehensive runtime monitoring data, which is often not fully available in issue platforms. Recent methods leverage large language models (LLMs) to analyze issue reports, but their effectiveness is limited by incomplete or ambiguous user-provided information. To obtain more accurate and comprehensive RCA results, the core idea of this work is to extract additional diagnostic clues from code to supplement data-limited issue reports. Specifically, we propose COCA, a code knowledge enhanced root cause analysis approach for issue reports. Based on the data within issue reports, COCA intelligently extracts relevant code snippets and reconstructs execution paths, providing a comprehensive execution context for further RCA. Subsequently, COCA constructs a prompt combining historical issue reports along with profiled code knowledge, enabling the LLMs to generate detailed root cause summaries and localize responsible components. Our evaluation on datasets from five real-world distributed systems demonstrates that COCA significantly outperforms existing methods, achieving a$\mathbf{2 8. 3 \%}$improvement in root cause localization and a 22.0 % improvement in root cause summarization. Furthermore, COCA's performance consistency across various LLMs underscores its robust generalizability.

A common practice in the reliability engineering of cloud services involves the collection of monitoring metrics, followed by comprehensive analysis to identify performance issues. However, existing methods often fall short of detecting diverse and evolving anomalies across different services. More-over, there exists a significant gap between the technical and business interpretation of anomalies, i.e., a detected anomaly may not have an actual impact on system performance or user experience. To address these challenges, we propose ADAMAS, an adaptive AutoML-based anomaly detection framework aiming to achieve practical anomaly detection in production cloud systems. To improve the ability to detect cross-service anomalies, we design a novel unsupervised evaluation function to facilitate the automatic searching of the optimal model structure and parameters. ADAMAS also contains a lightweight human-in-the-loop design, which can efficiently incorporate expert knowledge to adapt to the evolving anomaly patterns and bridge the gap between predicted anomalies and actual business exceptions. Fur-thermore, through monitoring the rate of mispredicted anomalies, ADAMAS proactively re-configures the optimal model, forming a continuous loop of system improvement. Extensive evaluation on one public and two industrial datasets shows that ADAMAS outperforms all baseline models with a 0.891 F1-score. The ablation study also proves the effectiveness of the evaluation function design and the incorporation of expert knowledge.

Effective alert diagnosis is essential for ensuring the reliability of large-scale online service systems. However, on-call engineers are often burdened with manually inspecting massive volumes of logs to identify root causes. While various automated tools have been proposed, they struggle in practice due to alert-agnostic log scoping and the inability to organize complex data effectively for reasoning. To overcome these limitations, we introduce LogPilot, an intent-aware and scalable framework powered by Large Language Models (LLMs) for automated log-based alert diagnosis. LogPilot introduces an intent-aware approach, interpreting the logic in alert definitions (e.g., PromQL) to precisely identify causally related logs and requests. To achieve scalability, it reconstructs each request’s execution into a spatiotemporal log chain, clusters similar chains to identify recurring execution patterns, and provides representative samples to the LLMs for diagnosis. This clustering-based approach ensures the input is both rich in diagnostic detail and compact enough to fit within the LLM’s context window. Evaluated on real-world alerts from Volcano Engine Cloud, LogPilot improves the usefulness of root cause summarization by 50.34% and exact localization accuracy by 54.79% over state-of-the-art methods. With a diagnosis time under one minute and a cost of only $0.074 per alert, LogPilot has been successfully deployed in production, offering an automated and practical solution for service alert diagnosis.

High-quality logging is critical for the reliability of cloud services, yet the industrial process for improving it is typically manual, reactive, and unscalable. Existing automated tools inherit this reactive nature, failing to answer the crucial whether-to-log question and are constrained to simple logging statement insertion, thus addressing only a fraction of the real-world logging improvement.To address these gaps and cope with logging debt in large-scale codebases, we propose LogImprover, a framework powered by Large Language Models (LLMs) that automates proactive logging quality improvement. LogImprover introduces two paradigm shifts: from reactive generation to proactive discovery, and from simple insertion to holistic logging patch generation. First, it identifies potential logging gaps based on principles distilled from industrial best practices. Then, it grounds each candidate through a cascading, structure-aware RAG module. Next, it prunes false positives by analyzing call-stack logging responsibilities and implicit logger inheritance. Finally, it generates holistic and explainable logging patches that reflect real-world development practices.Our evaluation provides dual confirmation of its effectiveness: LogImprover significantly outperforms state-of-the-art base-lines in closed-world experiments and achieves 68.12% developer acceptance rate in its real-world deployment. This success demonstrates the practical value of automating the entire logging quality improvement lifecycle, from discovery to recommendation.

Reliability management in cloud service systems is challenging due to the cascading effect of failures. Error wrapping, a practice prevalent in modern microservice development, enriches errors with context at each layer of the function call stack, constructing an error chain that describes a failure from its technical origin to its business impact. However, this also presents a significant traceability problem when recovering the complete error propagation path from the final log message back to its source. Existing approaches are ineffective at addressing this problem. To fill this gap, we present ErrorPrism in this work for automated reconstruction of error propagation paths in production microservice systems. ErrorPrism first performs static analysis on service code repositories to build a function call graph and map log strings to relevant candidate functions. This significantly reduces the path search space for subsequent analysis. Then, ErrorPrism employs an LLM agent to perform an iterative backward search to accurately reconstruct the complete, multi-hop error path. Evaluated on 67 production microservices at ByteDance, ErrorPrism achieves 97.0% accuracy in reconstructing paths for 102 real-world errors, outperforming existing static analysis and LLM-based approaches. ErrorPrism provides an effective and practical tool for root cause analysis in industrial microservice systems.

Cloud systems, typically comprised of various components (e.g., microservices), are susceptible to performance issues, which may cause service-level agreement violations and financial losses. Identifying performance issues is thus of paramount importance for cloud vendors. In current practice, crucial metrics, i.e., Key Performance Indicators (KPIs), are monitored periodically to provide insight into the operational status of components. Identifying performance issues is often formulated as an anomaly detection problem, which is tackled by analyzing each metric independently. However, this approach overlooks the complex dependencies existing among cloud components. Some graph neural network-based methods take both temporal and relational information into account; however, the correlation violations in the metrics that serve as indicators of underlying performance issues are difficult for them to identify. Furthermore, a large volume of components in a cloud system results in a vast array of noisy metrics. This complexity renders it impractical for engineers to fully comprehend the correlations, making it challenging to identify performance issues accurately. To address these limitations, we propose Identifying Performance Issues based on Relational-Temporal Features (ISOLATE), a learning-based approach that leverages both the relational and temporal features of metrics to identify performance issues. In particular, it adopts a graph neural network with attention to characterizing the relations among metrics and extracts long-term and multi-scale temporal patterns using a GRU and a convolution network, respectively. The learned graph attention weights can be further used to localize the correlation-violated metrics. Moreover, to relieve the impact of noisy data, ISOLATE utilizes a Positive Unlabeled (PU) Learning strategy that tags pseudo-labels based on a small portion of confirmed negative examples. Extensive evaluation on both public and industrial datasets shows that ISOLATE outperforms all baseline models with 0.945 F1 score and 0.920 Hit rate@3. The ablation study also proves the effectiveness of the relational-temporal features and the PU-Learning strategy. Furthermore, we share the success stories of leveraging ISOLATE to identify performance issues in Huawei Cloud, which demonstrates its superiority in practice.

Logs are imperative in the maintenance of online service systems, which often encompass important information for effective failure mitigation. While existing anomaly detection methodologies facilitate the identification of anomalous logs within extensive runtime data, manual investigation of log messages by engineers remains essential to comprehend faults, which is labor-intensive and error-prone. Upon examining the log-based troubleshooting practices at CloudA1, we find that engineers typically prioritize two categories of log information for diagnosis. These include fault-indicating descriptions, which record abnormal system events, and fault-indicating parameters, which specify the associated entities. Motivated by this finding, we propose an approach to automatically extract such fault-indicating information from logs for fault diagnosis, named LoFI. LoFI comprises two key stages. In the first stage, LoFI performs coarse-grained filtering to collect logs related to the faults based on semantic similarity. In the second stage, LoFI leverages a pre-trained language model with a novel prompt-based tuning method to extract fine-grained information of interest from the collected logs. We evaluate LoFI on logs collected from Apache Spark and an industrial dataset from CloudA. The experimental results demonstrate that LoFI outperforms all baseline methods by a significant margin, achieving an absolute improvement of 25.8˜37.9 in F1 over the best baseline method, ChatGPT. This highlights the effectiveness of LoFI in recognizing fault-indicating information. Furthermore, the successful deployment of LoFI at CloudA and user studies validate the utility of our method2.

To ensure the reliability of cloud systems, their run-time status reflecting the service quality is periodically monitored with monitoring metrics, i.e., KPIs (key performance indicators). When performance issues happen, root cause localization pinpoints the specific KPIs that are responsible for the degradation of overall service quality, facilitating prompt problem diagnosis and resolution. To this end, existing methods generally locate root-cause KPIs by identifying the KPIs that exhibit a similar anomalous trend to the overall service performance. While straightforward, solely relying on the similarity calculation may be ineffective when dealing with cloud systems with complicated interdependent services. Recent deep learning-based methods offer improved performance by modeling these intricate dependencies. However, their high computational demand often hinders their ability to meet the efficiency requirements of industrial applications. Furthermore, their lack of interpretability further restricts their practicality. To overcome these limitations, we propose KPIRoot, an effective and efficient method for root cause localization integrating both advantages of similarity analysis and causality analysis, where similarity measures the trend alignment of KPI and causality measures the sequential order of variation of KPI. Furthermore, we leverage symbolic aggregate approximation to produce a more compact representation for each KPI, enhancing the overall analysis efficiency of the approach. The experimental results show that KPIRoot outperforms seven state-of-the-art baselines by 7.9%~28.3%, while time cost is reduced by 56.9%. Moreover, we share our experience of deploying KPIRoot in the production environment of a large-scale cloud provider Cloud ${\mathcal{H}^{\ast}}$.

Log data have facilitated various tasks of software development and maintenance, such as testing, debugging and diagnosing. Due to the unstructured nature of logs, log parsing is typically required to transform log messages into structured data for automated log analysis. Given the abundance of log parsers that employ various techniques, evaluating these tools to comprehend their characteristics and performance becomes imperative. Loghub serves as a commonly used dataset for benchmarking log parsers, but it suffers from limited scale and representativeness, posing significant challenges for studies to comprehensively evaluate existing log parsers or develop new methods. This limitation is particularly pronounced when assessing these log parsers for production use. To address these limitations, we provide a new collection of annotated log datasets, denoted Loghub-2.0, which can better reflect the characteristics of log data in real-world software systems. Loghub-2.0 comprises 14 datasets with an average of 3.6 million log lines in each dataset. Based on Loghub-2.0, we conduct a thorough re-evaluation of 15 state-of-the-art log parsers in a more rigorous and practical setting. Particularly, we introduce a new evaluation metric to mitigate the sensitivity of existing metrics to imbalanced data distributions. We are also the first to investigate the granular performance of log parsers on logs that represent rare system events, offering in-depth details for software diagnosis. Accurately parsing such logs is essential, yet it remains a challenge. We believe this work could shed light on the evaluation and design of log parsers in practical settings, thereby facilitating their deployment in production systems.

In cloud systems, incidents are potential threats to customer satisfaction and business revenue. When customers are affected by incidents, they often request customer support service (CSS) from the cloud provider by submitting a support ticket. Many tickets could be duplicate as they are reported in a distributed and uncoordinated manner. Thus, aggregating such duplicate tickets is essential for efficient ticket management. Previous studies mainly rely on tickets' textual similarity to detect duplication; however, duplicate tickets in a cloud system could carry semantically different descriptions due to the complex service dependency of the cloud system. To tackle this problem, we propose iPACK, an incident-aware method for aggregating duplicate tickets by fusing the failure information between the customer side (i.e., tickets) and the cloud side (i.e., incidents). We extensively evaluate iPACK on three datasets collected from the production environment of a large-scale cloud platform, Azure. The experimental results show that iPACK can precisely and comprehensively aggregate duplicate tickets, achieving an F1 score of 0.871~0.935 and outperforming state-of-the-art methods by 12.4%~31.2%.

Software logs record system activities, aiding maintainers in identifying the underlying causes for failures and enabling prompt mitigation actions. However, maintainers need to inspect a large volume of daily logs to identify the anomalous logs that reveal failure details for further diagnosis. Thus, how to automatically distinguish these anomalous logs from normal logs becomes a critical problem. Existing approaches alleviate the burden on software maintainers, but they are built upon an improper yet critical assumption: logging statements in the software remain unchanged. While software keeps evolving, our empirical study finds that evolving software brings three challenges: log parsing errors, evolving log events, and unstable log sequences. In this paper, we propose a novel unsupervised approach named Evolving Log analyzer (EvLog) to mitigate these challenges. We first build a multi-level representation extractor to process logs without parsing to prevent errors from the parser. The multi-level representations preserve the essential semantics of logs while leaving out insignificant changes in evolving events. EvLog then implements an anomaly discriminator with an attention mechanism to identify the anomalous logs and avoid the issue brought by the unstable sequence. EvLog has shown effectiveness in two real-world system evolution log datasets with an average F1 score of 0.955 and 0.847 in the intra-version setting and inter-version setting, respectively, which outperforms other state-of-the-art approaches by a wide margin. To our best knowledge, this is the first study on localizing anomalous logs over software evolution. We believe our work sheds new light on the impact of software evolution with the corresponding solutions for the log analysis community.

As modern software systems continue to grow in terms of complexity and volume, anomaly detection on multivariate monitoring metrics, which profile systems’ health status, becomes more and more critical and challenging. In particular, the dependency between different metrics and their historical patterns plays a critical role in pursuing prompt and accurate anomaly detection. Existing approaches fall short of industrial needs for being unable to capture such information efficiently. To fill this significant gap, in this paper, we propose CMAnomaly, an anomaly detection framework on multivariate monitoring metrics based on collaborative machine. The proposed collaborative machine is a mechanism to capture the pairwise interactions along with feature and temporal dimensions with linear time complexity. Cost-effective models can then be employed to leverage both the dependency between monitoring metrics and their historical patterns for anomaly detection. The proposed framework is extensively evaluated with both public data and industrial data collected from a large-scale online service system of Huawei Cloud. The experimental results demonstrate that compared with state-of-the-art baseline models, CMAnomaly achieves an average F1 score of 0.9494, outperforming baselines by 6.77% ~ 10.68%, and runs 10× ~ 20× faster. Furthermore, we also share our experience of deploying CMAnomaly in Huawei Cloud.

Logs have been widely adopted in software system development and maintenance because of the rich runtime information they record. In recent years, the increase of software size and complexity leads to the rapid growth of the volume of logs. To handle these large volumes of logs efficiently and effectively, a line of research focuses on developing intelligent and automated log analysis techniques. However, only a few of these techniques have reached successful deployments in industry due to the lack of public log datasets and open benchmarking upon them. To fill this significant gap and facilitate more research on AI-driven log analytics, we have collected and released loghub, a large collection of system log datasets. In particular, loghub provides 19 real-world log datasets collected from a wide range of software systems, including distributed systems, supercomputers, operating systems, mobile systems, server applications, and standalone software. In this paper, we summarize the statistics of these datasets, introduce some practical usage scenarios of the loghub datasets, and present our benchmarking results on loghub to benefit the researchers and practitioners in this field. Up to the time of this paper writing, the loghub datasets have been downloaded for roughly 90,000 times in total by hundreds of organizations from both industry and academia. The loghub datasets are available at https://github.com/logpai/loghub.

Ensuring the reliability of cloud systems is critical for both cloud vendors and customers. Cloud systems often rely on virtualization techniques to create instances of hardware resources, such as virtual machines. However, virtualization hinders the observability of cloud systems, making it challenging to diagnose platform-level issues. To improve system observability, we propose to infer functional clusters of instances, i.e., groups of instances having similar functionalities. We first conduct a pilot study on a large-scale cloud system, i.e., Huawei Cloud, demonstrating that instances having similar functionalities share similar communication and resource usage patterns. Motivated by these findings, we formulate the identification of functional clusters as a clustering problem and propose a non-intrusive solution called Prism. Prism adopts a coarse-to-fine clustering strategy. It first partitions instances into coarse-grained chunks based on communication patterns. Within each chunk, Prism further groups instances with similar resource usage patterns to produce fine-grained functional clusters. Such a design reduces noises in the data and allows Prism to process massive instances efficiently. We evaluate Prism on two datasets collected from the real-world production environment of Huawei Cloud. Our experiments show that Prism achieves a v-measure of ∼0.95, surpassing existing state-of-the-art solutions. Additionally, we illustrate the integration of Prism within monitoring systems for enhanced cloud reliability through two real-world use cases.

To ensure the performance of online service systems, their status is closely monitored with various software and system metrics. Performance anomalies represent the performance degradation issues (e.g., slow response) of the service systems. When performing anomaly detection over the metrics, existing methods often lack the merit of interpretability, which is vital for engineers and analysts to take remediation actions. Moreover, they are unable to effectively accommodate the ever-changing services in an online fashion. To address these limitations, in this paper, we propose ADSketch, an interpretable and adaptive performance anomaly detection approach based on pattern sketching. ADSketch achieves interpretability by identifying groups of anomalous metric patterns, which represent particular types of performance issues. The underlying issues can then be immediately recognized if similar patterns emerge again. In addition, an adaptive learning algorithm is designed to embrace unprecedented patterns induced by service updates or user behavior changes. The proposed approach is evaluated with public data as well as industrial data collected from a representative online service system in Huawei Cloud. The experimental results show that ADSketch outperforms state-of-the-art approaches by a significant margin, and demonstrate the effectiveness of the online algorithm in new pattern discovery. Furthermore, our approach has been successfully deployed in industrial practice.

The past two decades have witnessed the rapid development of personalized recommendation techniques. Despite the significant progress made in both research and practice of recommender systems, to date, there is a lack of a widely-recognized benchmarking standard in this field. Many of the existing studies perform model evaluations and comparisons in an ad-hoc manner, for example, by employing their own private data splits or using a different experimental setting. However, such conventions not only increase the difficulty in reproducing existing studies, but also lead to inconsistent experimental results among them. This largely limits the credibility and practical value of research results in this field. To tackle these issues, we present an initiative project aimed for open benchmarking for recommender systems. In contrast to some earlier attempts towards this goal, we take one further step by setting up a standardized benchmarking pipeline for reproducible research, which integrates all the details about datasets, source code, hyper-parameter settings, running logs, and evaluation results. The benchmark is designed with comprehensiveness and sustainability in mind. It spans both matching and ranking tasks, and also allows anyone to easily follow and contribute. We believe that our benchmark could not only reduce the redundant efforts of researchers to re-implement or re-run existing baselines, but also drive more solid and reproducible research on recommender systems.

Click-through rate (CTR) prediction is a critical task for many applications, as its accuracy has a direct impact on user experience and platform revenue. In recent years, CTR prediction has been widely studied in both academia and industry, resulting in a wide variety of CTR prediction models. Unfortunately, there is still a lack of standardized benchmarks and uniform evaluation protocols for CTR prediction research. This leads to non-reproducible or even inconsistent experimental results among existing studies, which largely limit the practical value and potential impact of their research. In this work, we aim to perform open benchmarking for CTR prediction and present a rigorous comparison of different models in a reproducible manner. To this end, we ran over 7,000 experiments for more than 12,000 GPU hours in total to re-evaluate 24 existing models on multiple dataset settings. Surprisingly, our experiments show that with sufficient hyper-parameter search and model tuning, many deep models have smaller differences than expected. The results also reveal that making real progress on the modeling of CTR prediction is indeed a very challenging research task. We believe that our benchmarking work could not only allow researchers to gauge the effectiveness of new models conveniently but also make them fairly compare with the state of the arts. We have publicly released the benchmarking tools, evaluation protocols, and experimental settings of our work to promote reproducible research in this field.

As online service systems continue to grow in terms of complexity and volume, how service incidents are managed will significantly impact company revenue and user trust. Due to the cascading effect, cloud failures often come with an overwhelming number of incidents from dependent services and devices. To pursue efficient incident management, related incidents should be quickly aggregated to narrow down the problem scope. To this end, in this paper, we propose GRLIA, an incident aggregation framework based on graph representation learning over the cascading graph of cloud failures. A representation vector is learned for each unique type of incident in an unsupervised and unified manner, which is able to simultaneously encode the topological and temporal correlations among incidents. Thus, it can be easily employed for online incident aggregation. In particular, to learn the correlations more accurately, we try to recover the complete scope of failures’ cascading impact by leveraging fine-grained system monitoring data, i.e., Key Performance Indicators (KPIs). The proposed framework is evaluated with real-world incident data collected from a large-scale online service system of Huawei Cloud. The experimental results demonstrate that GRLIA is effective and outperforms existing methods. Furthermore, our framework has been successfully deployed in industrial practice.

Recently, deep learning-based models have been widely studied for click-through rate (CTR) prediction and lead to improved prediction accuracy in many industrial applications. However, current research focuses primarily on building complex network architectures to better capture sophisticated feature interactions and dynamic user behaviors. The increased model complexity may slow down online inference and hinder its adoption in real-time applications. Instead, our work targets at a new model training strategy based on knowledge distillation (KD). KD is a teacher-student learning framework to transfer knowledge learned from a teacher model to a student model. The KD strategy not only allows us to simplify the student model as a vanilla DNN model but also achieves significant accuracy improvements over the state-of-the-art teacher models. The benefits thus motivate us to further explore the use of a powerful ensemble of teachers for more accurate student model training. We also propose some novel techniques to facilitate ensembled CTR prediction, including teacher gating and early stopping by distillation loss. We conduct comprehensive experiments against 12 existing models and across three industrial datasets. Both offline and online A/B testing results show the effectiveness of our KD-based training strategy.

System logs record detailed runtime information of software systems and are used as the main data source for many tasks around software engineering. As modern software systems are evolving into large scale and complex structures, logs have become one type of fast-growing big data in industry. In particular, such logs often need to be stored for a long time in practice (e.g., a year), in order to analyze recurrent problems or track security issues. However, archiving logs consumes a large amount of storage space and computing resources, which in turn incurs high operational cost. Data compression is essential to reduce the cost of log storage. Traditional compression tools (e.g., gzip) work well for general texts, but are not tailed for system logs. In this paper, we propose a novel and effective log compression method, namely logzip. Logzip is capable of extracting hidden structures from raw logs via fast iterative clustering and further generating coherent intermediate representations that allow for more effective compression. We evaluate logzip on five large log datasets of different system types, with a total of 63.6 GB in size. The results show that logzip can save about half of the storage space on average over traditional compression tools. Meanwhile, the design of logzip is highly parallel and only incurs negligible overhead. In addition, we share our industrial experience of applying logzip to Huawei's real products.