Skip to content

fix(stand): bounded logs + restart policies + Flink failure-rate restart budget (P2.1-P2.3) #214

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
brownjuly2003-code merged 3 commits into from
Jul 20, 2026
Merged

fix(stand): bounded logs + restart policies + Flink failure-rate restart budget (P2.1-P2.3) #214

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e2c2017
fix(stand): bound container logs, restart policies, and Flink restart…
JuliaEdom Jul 20, 2026
0b7a1c7
fix(flink): route restart strategy through Configuration/env.configur…
JuliaEdom Jul 20, 2026
136e38d
Merge branch 'main' into fix/p2-stand-hardening
brownjuly2003-code Jul 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
280 changes: 147 additions & 133 deletions docker-compose.cdc.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,133 +1,147 @@
services:
kafka:
environment:
KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:9092

cdc-kafka-init:
image: confluentinc/cp-kafka:7.7.0
depends_on:
kafka:
condition: service_healthy
entrypoint: ["/bin/bash", "-c"]
command:
- |
set -euo pipefail
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic connect-agentflow-configs --partitions 1 --replication-factor 1 --config cleanup.policy=compact
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic connect-agentflow-offsets --partitions 25 --replication-factor 1 --config cleanup.policy=compact
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic connect-agentflow-status --partitions 5 --replication-factor 1 --config cleanup.policy=compact
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.postgres.public.orders_v2 --partitions 3 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.postgres.public.users_enriched --partitions 3 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic __debezium-heartbeat.cdc.postgres --partitions 1 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.mysql --partitions 1 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic __debezium-heartbeat.cdc.mysql --partitions 1 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.mysql.agentflow_demo.products_current --partitions 3 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.mysql.agentflow_demo.sessions_aggregated --partitions 3 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic schemahistory.cdc.mysql.agentflow_demo --partitions 1 --replication-factor 1 --config cleanup.policy=delete --config retention.ms=-1
kafka-configs --bootstrap-server kafka:9092 --alter --entity-type topics --entity-name schemahistory.cdc.mysql.agentflow_demo --add-config cleanup.policy=delete,retention.ms=-1

postgres-source:
image: postgres:16
command:
- "postgres"
- "-c"
- "wal_level=logical"
- "-c"
- "max_replication_slots=4"
- "-c"
- "max_wal_senders=4"
environment:
POSTGRES_DB: agentflow_demo
POSTGRES_USER: cdc_reader
POSTGRES_PASSWORD: agentflow
ports:
- "5433:5432"
volumes:
- ./docker/postgres-source/init.sql:/docker-entrypoint-initdb.d/001-agentflow-cdc.sql:ro
- postgres-cdc-data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U cdc_reader -d agentflow_demo"]
interval: 10s
timeout: 5s
retries: 5

mysql-source:
image: mysql:8.4
command:
- "--server-id=223344"
- "--log-bin=mysql-bin"
- "--binlog-format=ROW"
- "--binlog-row-image=FULL"
- "--binlog-expire-logs-seconds=864000"
environment:
MYSQL_DATABASE: agentflow_demo
MYSQL_USER: cdc_reader
MYSQL_PASSWORD: agentflow
MYSQL_ROOT_PASSWORD: agentflow-root
ports:
- "3307:3306"
volumes:
- ./docker/mysql-source/init.sql:/docker-entrypoint-initdb.d/001-agentflow-cdc.sql:ro
- mysql-cdc-data:/var/lib/mysql
healthcheck:
test: ["CMD-SHELL", "mysqladmin ping -h localhost -ucdc_reader -pagentflow --silent"]
interval: 10s
timeout: 5s
retries: 10

kafka-connect:
image: agentflow-kafka-connect:local
build:
context: .
dockerfile: docker/kafka-connect/Dockerfile
depends_on:
cdc-kafka-init:
condition: service_completed_successfully
postgres-source:
condition: service_healthy
mysql-source:
condition: service_healthy
ports:
- "8083:8083"
environment:
CONNECT_BOOTSTRAP_SERVERS: kafka:9092
CONNECT_REST_ADVERTISED_HOST_NAME: kafka-connect
CONNECT_REST_PORT: 8083
CONNECT_GROUP_ID: agentflow-connect
CONNECT_CONFIG_STORAGE_TOPIC: connect-agentflow-configs
CONNECT_OFFSET_STORAGE_TOPIC: connect-agentflow-offsets
CONNECT_STATUS_STORAGE_TOPIC: connect-agentflow-status
CONNECT_CONFIG_STORAGE_REPLICATION_FACTOR: 1
CONNECT_OFFSET_STORAGE_REPLICATION_FACTOR: 1
CONNECT_STATUS_STORAGE_REPLICATION_FACTOR: 1
CONNECT_KEY_CONVERTER: org.apache.kafka.connect.json.JsonConverter
CONNECT_VALUE_CONVERTER: org.apache.kafka.connect.json.JsonConverter
CONNECT_KEY_CONVERTER_SCHEMAS_ENABLE: "false"
CONNECT_VALUE_CONVERTER_SCHEMAS_ENABLE: "false"
CONNECT_PLUGIN_PATH: /usr/share/java,/usr/share/confluent-hub-components,/usr/share/java/debezium
CONNECT_CONFIG_PROVIDERS: file
CONNECT_CONFIG_PROVIDERS_FILE_CLASS: org.apache.kafka.common.config.provider.FileConfigProvider
CONNECT_OFFSET_FLUSH_INTERVAL_MS: 10000
KAFKA_BOOTSTRAP_SERVERS: kafka:9092
volumes:
- ./docker/kafka-connect/secrets:/opt/connect/secrets:ro
healthcheck:
test: ["CMD-SHELL", "curl -fsS http://localhost:8083/connectors >/dev/null"]
interval: 10s
timeout: 5s
retries: 12

cdc-register-connectors:
image: agentflow-kafka-connect:local
depends_on:
kafka-connect:
condition: service_healthy
environment:
CONNECT_URL: http://kafka-connect:8083
KAFKA_BOOTSTRAP_SERVERS: kafka:9092
volumes:
- ./scripts/register_cdc_connectors.sh:/usr/local/bin/register_cdc_connectors.sh:ro
entrypoint: ["/bin/bash", "/usr/local/bin/register_cdc_connectors.sh"]

volumes:
postgres-cdc-data:
mysql-cdc-data:
# Bounded container logs: the 2026-07-18 soak filled the stand's disk with
# unrotated json-file logs (TM alone grew to 3.8G) and took the pipeline down.
x-logging: &default-logging
driver: json-file
options:
max-size: "50m"
max-file: "3"

services:
kafka:
logging: *default-logging
environment:
KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:9092

cdc-kafka-init:
logging: *default-logging
image: confluentinc/cp-kafka:7.7.0
depends_on:
kafka:
condition: service_healthy
entrypoint: ["/bin/bash", "-c"]
command:
- |
set -euo pipefail
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic connect-agentflow-configs --partitions 1 --replication-factor 1 --config cleanup.policy=compact
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic connect-agentflow-offsets --partitions 25 --replication-factor 1 --config cleanup.policy=compact
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic connect-agentflow-status --partitions 5 --replication-factor 1 --config cleanup.policy=compact
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.postgres.public.orders_v2 --partitions 3 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.postgres.public.users_enriched --partitions 3 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic __debezium-heartbeat.cdc.postgres --partitions 1 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.mysql --partitions 1 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic __debezium-heartbeat.cdc.mysql --partitions 1 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.mysql.agentflow_demo.products_current --partitions 3 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic cdc.mysql.agentflow_demo.sessions_aggregated --partitions 3 --replication-factor 1
kafka-topics --bootstrap-server kafka:9092 --create --if-not-exists --topic schemahistory.cdc.mysql.agentflow_demo --partitions 1 --replication-factor 1 --config cleanup.policy=delete --config retention.ms=-1
kafka-configs --bootstrap-server kafka:9092 --alter --entity-type topics --entity-name schemahistory.cdc.mysql.agentflow_demo --add-config cleanup.policy=delete,retention.ms=-1

postgres-source:
logging: *default-logging
image: postgres:16
command:
- "postgres"
- "-c"
- "wal_level=logical"
- "-c"
- "max_replication_slots=4"
- "-c"
- "max_wal_senders=4"
environment:
POSTGRES_DB: agentflow_demo
POSTGRES_USER: cdc_reader
POSTGRES_PASSWORD: agentflow
ports:
- "5433:5432"
volumes:
- ./docker/postgres-source/init.sql:/docker-entrypoint-initdb.d/001-agentflow-cdc.sql:ro
- postgres-cdc-data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U cdc_reader -d agentflow_demo"]
interval: 10s
timeout: 5s
retries: 5

mysql-source:
logging: *default-logging
image: mysql:8.4
command:
- "--server-id=223344"
- "--log-bin=mysql-bin"
- "--binlog-format=ROW"
- "--binlog-row-image=FULL"
- "--binlog-expire-logs-seconds=864000"
environment:
MYSQL_DATABASE: agentflow_demo
MYSQL_USER: cdc_reader
MYSQL_PASSWORD: agentflow
MYSQL_ROOT_PASSWORD: agentflow-root
ports:
- "3307:3306"
volumes:
- ./docker/mysql-source/init.sql:/docker-entrypoint-initdb.d/001-agentflow-cdc.sql:ro
- mysql-cdc-data:/var/lib/mysql
healthcheck:
test: ["CMD-SHELL", "mysqladmin ping -h localhost -ucdc_reader -pagentflow --silent"]
interval: 10s
timeout: 5s
retries: 10

kafka-connect:
logging: *default-logging
image: agentflow-kafka-connect:local
build:
context: .
dockerfile: docker/kafka-connect/Dockerfile
depends_on:
cdc-kafka-init:
condition: service_completed_successfully
postgres-source:
condition: service_healthy
mysql-source:
condition: service_healthy
ports:
- "8083:8083"
environment:
CONNECT_BOOTSTRAP_SERVERS: kafka:9092
CONNECT_REST_ADVERTISED_HOST_NAME: kafka-connect
CONNECT_REST_PORT: 8083
CONNECT_GROUP_ID: agentflow-connect
CONNECT_CONFIG_STORAGE_TOPIC: connect-agentflow-configs
CONNECT_OFFSET_STORAGE_TOPIC: connect-agentflow-offsets
CONNECT_STATUS_STORAGE_TOPIC: connect-agentflow-status
CONNECT_CONFIG_STORAGE_REPLICATION_FACTOR: 1
CONNECT_OFFSET_STORAGE_REPLICATION_FACTOR: 1
CONNECT_STATUS_STORAGE_REPLICATION_FACTOR: 1
CONNECT_KEY_CONVERTER: org.apache.kafka.connect.json.JsonConverter
CONNECT_VALUE_CONVERTER: org.apache.kafka.connect.json.JsonConverter
CONNECT_KEY_CONVERTER_SCHEMAS_ENABLE: "false"
CONNECT_VALUE_CONVERTER_SCHEMAS_ENABLE: "false"
CONNECT_PLUGIN_PATH: /usr/share/java,/usr/share/confluent-hub-components,/usr/share/java/debezium
CONNECT_CONFIG_PROVIDERS: file
CONNECT_CONFIG_PROVIDERS_FILE_CLASS: org.apache.kafka.common.config.provider.FileConfigProvider
CONNECT_OFFSET_FLUSH_INTERVAL_MS: 10000
KAFKA_BOOTSTRAP_SERVERS: kafka:9092
volumes:
- ./docker/kafka-connect/secrets:/opt/connect/secrets:ro
healthcheck:
test: ["CMD-SHELL", "curl -fsS http://localhost:8083/connectors >/dev/null"]
interval: 10s
timeout: 5s
retries: 12

cdc-register-connectors:
logging: *default-logging
image: agentflow-kafka-connect:local
depends_on:
kafka-connect:
condition: service_healthy
environment:
CONNECT_URL: http://kafka-connect:8083
KAFKA_BOOTSTRAP_SERVERS: kafka:9092
volumes:
- ./scripts/register_cdc_connectors.sh:/usr/local/bin/register_cdc_connectors.sh:ro
entrypoint: ["/bin/bash", "/usr/local/bin/register_cdc_connectors.sh"]

volumes:
postgres-cdc-data:
mysql-cdc-data:
Loading