| Presentation | 2023-01-19 Failure Analysis of Microservices using Continuous DAG Learning Nobukazu Fukuda, Chao Wu, Shingo Horiuchi, Kenichi Tayama, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Microservice has become a popular software architecture of ICT services for various benefits. Accordingly, troubleshooting microservices is a challenging issue because of complex service dependencies and large scale. Therefore, we propose a deep learning model to predict the location and propagation of a failure to help understand the system and the root cause. When a failure occurs, the proposed method encodes metrics, non-invasive telemetry, and generates a failure propagation graph which represents the propagation of failure impact. We conducted experiments on a dataset built from microservices and demonstrated that the proposed method can predict the impact of a failure. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Microservice / Root Cause Analysis / DAG |
| Paper # | ICM2022-32,LOIS2022-32 |
| Date of Issue | 2023-01-12 (ICM, LOIS) |
| Conference Information | |
| Committee | LOIS / ICM |
|---|---|
| Conference Date | 2023/1/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Kitakyushu International Conference Center |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Practical Use of Lifelog, Office Information System, Business Management, etc. |
| Chair | Hiroyuki Toda(NTT) / Yuji Nomura(Fujitsu) |
| Vice Chair | Manabu Motegi(Takushoku Univ.) / Yu Miyoshi(NTT) / Eiji Takahashi(NEC) |
| Secretary | Manabu Motegi(Nagasaki Univ.) / Yu Miyoshi(NTT) / Eiji Takahashi(NTT) |
| Assistant | Mana Sasagawa(NTT) / Ryo Yamamoto(Univ. of Electro-Comm) |
| Paper Information | |
| Registration To | Technical Committee on Life Intelligence and Office Information Systems / Technical Committee on Information and Communication Management |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Failure Analysis of Microservices using Continuous DAG Learning |
| Sub Title (in English) | |
| Keyword(1) | Microservice |
| Keyword(2) | Root Cause Analysis |
| Keyword(3) | DAG |
| 1st Author's Name | Nobukazu Fukuda |
| 1st Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 2nd Author's Name | Chao Wu |
| 2nd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 3rd Author's Name | Shingo Horiuchi |
| 3rd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 4th Author's Name | Kenichi Tayama |
| 4th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| Date | 2023-01-19 |
| Paper # | ICM2022-32,LOIS2022-32 |
| Volume (vol) | vol.122 |
| Number (no) | ICM-337,LOIS-338 |
| Page | pp.pp.7-12(ICM), pp.7-12(LOIS), |
| #Pages | 6 |
| Date of Issue | 2023-01-12 (ICM, LOIS) |