Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (3)
✅ Files skipped from review due to trivial changes (2)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughDocker Compose에 로그 볼륨 마운트를 추가하고 Promtail/Loki용 설정과 Logback 파일 기반 로깅을 도입했으며, Prometheus scrape 설정에 Changes
Sequence DiagramsequenceDiagram
participant App as App<br/>(kareer-blue / kareer-green)
participant FS as FileSystem<br/>(./logs/blue or ./logs/green)
participant Promtail as Promtail
participant Loki as Loki
participant Prometheus as Prometheus
App->>FS: Logback writes info/warn/error logs
FS->>Promtail: Mounted volumes expose /app/logs/...
Promtail->>Promtail: Tail files per scrape configs
Promtail->>Loki: POST /loki/api/v1/push (labeled by job,deployment)
Loki->>Loki: Store indexed logs
Prometheus->>App: Scrape metrics (https, application=kareer_server)
Estimated Code Review Effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly Related PRs
Suggested Reviewers
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (3)
src/main/resources/logback-spring.xml (2)
47-62: ERROR 로그는 더 긴 보관 기간을 고려해 보세요.현재 모든 로그 레벨이 7일 보관으로 설정되어 있습니다. ERROR 로그는 장애 분석 및 디버깅에 중요하므로 14~30일 정도로 더 긴 보관 기간을 설정하는 것이 일반적입니다.
💡 ERROR 로그 보관 기간 연장 제안
<appender name="ERROR_FILE" class="ch.qos.logback.core.rolling.RollingFileAppender"> <file>${LOG_BASE}/error/${APP_NAME}.error.log</file> <rollingPolicy class="ch.qos.logback.core.rolling.TimeBasedRollingPolicy"> <fileNamePattern>${LOG_BASE}/error/${APP_NAME}.error.%d{yyyy-MM-dd}.log</fileNamePattern> - <maxHistory>7</maxHistory> + <maxHistory>30</maxHistory> </rollingPolicy>🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/main/resources/logback-spring.xml` around lines 47 - 62, The ERROR_FILE appender currently uses a TimeBasedRollingPolicy with <maxHistory>7</maxHistory>; increase this to a longer retention (e.g., set maxHistory to 14 or 30) to retain ERROR logs for a longer period for debugging; update the RollingFileAppender configuration for ERROR_FILE (the TimeBasedRollingPolicy tied to ERROR_FILE and its fileNamePattern) to the chosen maxHistory value and keep the rest of the appender configuration unchanged.
3-3:LOG_BASE가 설정되지 않은 경우 기본값을 제공하세요.환경 변수
LOG_BASE가 설정되지 않으면 로그 파일 경로가_IS_UNDEFINED/info/...로 설정되어 오류가 발생할 수 있습니다.♻️ 기본값 추가 제안
- <property name="LOG_BASE" value="${LOG_BASE}"/> + <property name="LOG_BASE" value="${LOG_BASE:-/app/logs}"/>🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/main/resources/logback-spring.xml` at line 3, The LOG_BASE property is currently used without a fallback which leads to paths like "_IS_UNDEFINED/info/..."; update the <property name="LOG_BASE" value="..."/> declaration so the value uses a Spring placeholder with a sensible default (e.g. ./logs) when LOG_BASE is not set; locate the property with name="LOG_BASE" in logback-spring.xml and change its value attribute to include the default fallback using the placeholder syntax so log file paths never resolve to an undefined token.deployment/promtail/promtail-config.yml (1)
2-3: positions 파일이 컨테이너 재시작 시 유실될 수 있습니다.
/tmp/positions.yaml은 컨테이너 재시작 시 초기화됩니다. 이로 인해 Promtail이 이미 전송한 로그를 다시 전송하거나, 로그 위치를 잃어버릴 수 있습니다.♻️ 영구 볼륨 사용 권장
docker-compose-promtail.yml에 볼륨을 추가하고 경로를 변경하세요:
positions: - filename: /tmp/positions.yaml + filename: /positions/positions.yamldocker-compose-promtail.yml:
volumes: - promtail_positions:/positions # ... 기존 볼륨들 volumes: promtail_positions:🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@deployment/promtail/promtail-config.yml` around lines 2 - 3, 현재 promtail-config.yml의 positions.filename이 /tmp/positions.yaml로 설정되어 컨테이너 재시작 시 유실될 가능성이 있습니다; 변경 방법은 promtail-config.yml에서 positions.filename을 영구 볼륨 경로(예: /positions/positions.yaml)로 수정하고, docker-compose-promtail.yml에 promtail_positions 같은 명시적 볼륨을 추가하여 컨테이너의 /positions 경로에 마운트하도록 설정하면 됩니다 — 참조할 심볼: positions.filename in promtail-config.yml and volume name promtail_positions in docker-compose-promtail.yml.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@deployment/docker-compose-promtail.yml`:
- Around line 12-24: The mounted container log paths in the docker-compose
service (volumes entries mapping ./logs/blue/* and ./logs/green/* →
/app/logs/...) do not match the paths referenced in promtail-config.yml (e.g.
/var/log/info/*.log); update either the volume mounts or promtail-config.yml so
the file_glob targets the actual container paths (reference: volumes entries,
promtail-config.yml, and command: -config.file=/etc/promtail/config.yml), and
also ensure the service is attached to a network that can reach Loki (add a
network section or use host network) so Promtail can connect to the external
Loki endpoint.
- Line 5: The docker-compose service is using an unpinned image tag
"grafana/promtail:latest" which causes non-deterministic deployments; update the
image reference used in the compose file (the "image: grafana/promtail:latest"
line) to a fixed, supported version such as "grafana/promtail:3.6.0" to lock the
Promtail version and avoid using :latest.
In `@deployment/docker-compose.yml`:
- Line 15: 환경 변수 LOG_BASE의 컨테이너 경로가 잘못되어 있어 로그가 컨테이너 내부 위치와 매칭되지 않습니다;
docker-compose.yml에서 환경 변수 LOG_BASE 값을 호스트 상대 경로(./logs/blue)가 아닌 컨테이너 내부 경로인
/app/logs로 변경하고, 동일한 변경을 다른 서비스의 LOG_BASE 설정(예: kareer-green 환경 변수)에도 적용해 컨테이너 내
Logback이 /app/logs를 사용하도록 수정하세요.
In `@deployment/promtail/promtail-config.yml`:
- Around line 8-60: Promtail is not matching the Docker Compose volume paths:
update each job's __path__ entries (e.g., for job_name: info_blue, info_green,
warn_blue, warn_green, error_blue, error_green) to point to the actual mounted
directories used in docker-compose (for example change /var/log/info/*.log to
/app/logs/blue/info/*.log for info_blue and to /app/logs/green/info/*.log for
info_green) and similarly update warn and error jobs to
/app/logs/<blue|green>/warn/*.log and /app/logs/<blue|green>/error/*.log so
blue/green are distinct and paths match the compose mounts.
---
Nitpick comments:
In `@deployment/promtail/promtail-config.yml`:
- Around line 2-3: 현재 promtail-config.yml의 positions.filename이
/tmp/positions.yaml로 설정되어 컨테이너 재시작 시 유실될 가능성이 있습니다; 변경 방법은 promtail-config.yml에서
positions.filename을 영구 볼륨 경로(예: /positions/positions.yaml)로 수정하고,
docker-compose-promtail.yml에 promtail_positions 같은 명시적 볼륨을 추가하여 컨테이너의 /positions
경로에 마운트하도록 설정하면 됩니다 — 참조할 심볼: positions.filename in promtail-config.yml and
volume name promtail_positions in docker-compose-promtail.yml.
In `@src/main/resources/logback-spring.xml`:
- Around line 47-62: The ERROR_FILE appender currently uses a
TimeBasedRollingPolicy with <maxHistory>7</maxHistory>; increase this to a
longer retention (e.g., set maxHistory to 14 or 30) to retain ERROR logs for a
longer period for debugging; update the RollingFileAppender configuration for
ERROR_FILE (the TimeBasedRollingPolicy tied to ERROR_FILE and its
fileNamePattern) to the chosen maxHistory value and keep the rest of the
appender configuration unchanged.
- Line 3: The LOG_BASE property is currently used without a fallback which leads
to paths like "_IS_UNDEFINED/info/..."; update the <property name="LOG_BASE"
value="..."/> declaration so the value uses a Spring placeholder with a sensible
default (e.g. ./logs) when LOG_BASE is not set; locate the property with
name="LOG_BASE" in logback-spring.xml and change its value attribute to include
the default fallback using the placeholder syntax so log file paths never
resolve to an undefined token.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 00000463-e817-46a4-812f-3d61d1e9ecc1
📒 Files selected for processing (6)
deployment/docker-compose-monitoring.ymldeployment/docker-compose-promtail.ymldeployment/docker-compose.ymldeployment/prometheus/prometheus.ymldeployment/promtail/promtail-config.ymlsrc/main/resources/logback-spring.xml
…into feat/#195-monitoring
jeong1112
reviewed
Mar 26, 2026
Collaborator
There was a problem hiding this comment.
저희가 현재 Blue, Green 컨테이너로 나눠놓은 것은 버전 관리가 아니고 무중단 배포를 하기 위함인데 로그를 분리해서 저장하는 이유가 있나요?
Collaborator
Author
There was a problem hiding this comment.
장애 영향 범위를 최소화 하여 원인이 발생한 컨테이너에 대해서만 로그를 확인할 수 있어 더 유용하고, 롤백을 하게 될 경우에도 어떤 환경의 문제/로그인지 빠르고 정확하게 확인할 수 있다는 점에서 분리했습니당.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Related issue 🛠
Work Description 📝
1. Prometheus, Grafana 연동 확인
2. 로그 수집 환경 설정 (Promtail + Loki)
ScreenShots 📷
To Reviewers 📢
Summary by CodeRabbit
새로운 기능
기타