Первые наброски airflow-gp

This commit is contained in:
2025-09-16 23:03:35 +03:00
parent c23512920b
commit e7e40d18f7
7 changed files with 344 additions and 0 deletions
+140
View File
@@ -0,0 +1,140 @@
version: "3.9"
services:
# Postgres только для Airflow метаданных
pgmeta:
image: postgres:16
# container_name: gp_pgmeta
env_file: .env
environment:
POSTGRES_USER: ${PG_USER}
POSTGRES_PASSWORD: ${PG_PASSWORD}
POSTGRES_DB: ${PG_DB}
ports:
- "5433:5432"
volumes:
- pgmeta:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U ${PG_USER} -d ${PG_DB}"]
interval: 5s
timeout: 5s
retries: 20
greenplum:
image: datagrip/greenplum:6.8
# container_name: gp_single
hostname: gpdbsne
# Порты: внешний 5432
ports:
- "5432:5432"
volumes:
- ./sql:/sql:ro
# Простая проверка доступности: psql откликается
healthcheck:
test: ["CMD-SHELL", "pg_isready -h 127.0.0.1 -p 5432 || echo 1"]
interval: 10s
timeout: 5s
retries: 30
kafka:
image: apache/kafka:3.8.0
environment:
KAFKA_BROKER_ID: 1
KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT,CONTROLLER:PLAINTEXT
KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:29092,PLAINTEXT_HOST://localhost:9092
KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 0
KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
KAFKA_PROCESS_ROLES: broker,controller
KAFKA_NODE_ID: 1
KAFKA_CONTROLLER_QUORUM_VOTERS: 1@kafka:29093
KAFKA_LISTENERS: PLAINTEXT://kafka:29092,CONTROLLER://kafka:29093,PLAINTEXT_HOST://0.0.0.0:9092
KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
KAFKA_CONTROLLER_LISTENER_NAMES: CONTROLLER
KAFKA_LOG_DIRS: /tmp/kraft-combined-logs
# 22-символьный base64 идентификатор для KRaft-кластера
CLUSTER_ID: aGVsbG93b3JsZGtpdGNoZW4
ports:
- "9092:9092"
kafka-ui:
image: provectuslabs/kafka-ui:v0.7.2
ports:
- 8082:8080
environment:
- DYNAMIC_CONFIG_ENABLED=true
- KAFKA_CLUSTERS_0_NAME=KafkaCluster
- KAFKA_CLUSTERS_0_BOOTSTRAPSERVERS=kafka:29092
volumes:
- kafka-ui-data:/app/data
depends_on:
- kafka
airflow-webserver:
image: apache/airflow:2.9.2
container_name: gp_airflow_web
env_file: .env
environment:
AIRFLOW__CORE__LOAD_EXAMPLES: "False"
AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://${PG_USER}:${PG_PASSWORD}@pgmeta:5432/${PG_DB}
command: >
bash -lc "pip install --no-cache-dir -r /opt/airflow/requirements.txt &&
airflow webserver"
ports:
- "8080:8080"
volumes:
- ./airflow/dags:/opt/airflow/dags
- ./airflow/requirements.txt:/opt/airflow/requirements.txt
depends_on:
pgmeta:
condition: service_healthy
kafka:
condition: service_started
greenplum:
condition: service_healthy
airflow-scheduler:
image: apache/airflow:2.9.2
container_name: gp_airflow_sch
env_file: .env
environment:
AIRFLOW__CORE__LOAD_EXAMPLES: "False"
AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://${PG_USER}:${PG_PASSWORD}@pgmeta:5432/${PG_DB}
command: >
bash -lc "pip install --no-cache-dir -r /opt/airflow/requirements.txt &&
airflow scheduler"
volumes:
- ./airflow/dags:/opt/airflow/dags
- ./airflow/requirements.txt:/opt/airflow/requirements.txt
depends_on:
pgmeta:
condition: service_healthy
kafka:
condition: service_started
greenplum:
condition: service_healthy
airflow-init:
image: apache/airflow:2.9.2
container_name: gp_airflow_init
env_file: .env
environment:
AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://${PG_USER}:${PG_PASSWORD}@pgmeta:5432/${PG_DB}
volumes:
- ./airflow/dags:/opt/airflow/dags
- ./airflow/requirements.txt:/opt/airflow/requirements.txt
entrypoint: ["/bin/bash", "-lc"]
command: |
set -e
until pg_isready -h pgmeta -U ${PG_USER} -d ${PG_DB}; do echo 'waiting for pgmeta'; sleep 2; done
pip install --no-cache-dir -r /opt/airflow/requirements.txt
airflow db migrate
airflow users create --username ${AIRFLOW_USER} --password ${AIRFLOW_PASSWORD} --firstname Admin --lastname User --role Admin --email admin@example.org
depends_on:
pgmeta:
condition: service_healthy
volumes:
pgmeta:
kafka-ui-data: