A Data-Driven Approach for Adaptive Real-Time Log Parsing in Cloud Environments
Bibliographic record
Abstract
In the era of rapidly expanding cloud computing centers and large-scale services, analyzing system logs has become crucial for monitoring the quality of service. With systems generating vast amounts of logs, manual analysis is no longer feasible, necessitating automatic and precise log analysis techniques. The process begins with log parsing, a critical first step towards automating the analysis by transforming unstructured logs into structured records. However, current log parsing techniques lack adaptability. First, they struggle with software or firmware updates, as previously learned templates fail to recognize new log types. Second, they perform poorly across different services, unable to accurately parse logs from newly introduced services, further hindering effective log parsing. To address these challenges, we propose an adaptive log parsing method for largescale cloud environments called AdapLog. AdapLog leverages an online data-driven approach that efficiently processes grouped log messages without manual parameter tuning. Evaluation results indicate that our log parsing method outperforms state-of-the-art techniques across most experiments with respect to parsing accuracy (up to 4.2 x higher) and time (up to 13.4 x less per log).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".