Log3C is a general framework that identifies service system problems from system logs. It utilizes both system logs and system KPI metrics to promptly and precisely identify impactful system problems. Log3C consists of four steps: Log parsing, Sequence vectorization, Cascading Clustering and Correlation analysis. This is a joint work by CUHK and Microsoft Research.
The repository contains the source code of Log3C, including data loading, sequence vectorization, cascading clustering, data saving, etc. The core part is the cascading clustering algorithm, which groups a large number of sequence vectors into clusters by iteratively sampling, clustering, matching. For more details, please refer to our paper:
- Shilin He, Qingwei Lin, Jian-Guang Lou, Hongyu Zhang, Michael R. Lyu, Dongmei Zhang. Identifying Impactful Service System Problems via Log Analysis, in Proc. of the 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), 2018.
- Python version 3.5 or above
- All required packages are installed
- Windows, Linux or macOS platform
Note: Anaconda (Python 3.5 or above) is highly recommended, all required packages are already installed in Anaconda. You can also install the required packages with the "requirements.txt" by using command:
pip install -r requirements.txt
Download the project code files with:
git clone https://github.com/logpai/Log3C.git
Go to the project directory
To use the model, open a terminal, change directory to this project code, run the command:
- run.py: main entry function, which defines all the required hyper-parameters.
- cascading_clustering.py: implementation of the cascading clustering algorithm.
- dataloader.py: load the input data files into memory
- save_results.py: save the clustering result into files.
For details, please refer to the code comments.
- Multiple log sequence matrix files: each file consists of log sequence vectors within a time interval.
- The KPI data: each KPI value corresponds to the system status of a time interval.
- A log sequence matrix at time interval T0:
Assume that there are N time intervals in total, then we have N such matrixes as well as N KPI values. These K KPI values are stored in one file, which is shown as below.
- KPI data
Only one KPI file, which contains N KPI values.