248 lines
9.0 KiB
YAML
248 lines
9.0 KiB
YAML
# ============================================================
|
||
# go-sms(Go-sms)本地开发环境中间件(Day 1)
|
||
# 使用:make up(启动并等待 healthy)/ make down(完全清理)/ make logs
|
||
# 端口规划(避免本机与中间件默认端口冲突):
|
||
# MySQL 13306 | Redis 16379 | Kafka 19092(compose 内 go-sms-kafka 提供,见下) | ETCD 12379
|
||
# ClickHouse HTTP 18123 / Native 19000 | MinIO API 19010 / Console 19011
|
||
#
|
||
# ℹ️ Kafka 说明(2026-11-13 S1-B 恢复 compose 管理):
|
||
# POC 老机该服务曾因容器脱离 compose 网络→QUORUM_VOTERS 解析失败而停用(2026-09-11
|
||
# Day47 运维处置,事故史见归档仓 docs/runbook/incident-response.md),期间以手动
|
||
# docker run 的 go-sms-kafka 承载。新机( debian13-smsDev )为干净网络,自 S1-B 起
|
||
# 恢复由本 compose 管理:服务名 kafka 即网络别名,QUORUM_VOTERS=1@kafka:29093 可解析。
|
||
# advertised=127.0.0.1:19092 为宿主观(configs/config.dev.yaml brokers 同址),
|
||
# 容器内 CLI 连不通属预期,验证须走 host 网络容器(scripts/init_kafka_topics.sh 同法)。
|
||
# ============================================================
|
||
name: go-sms-dev
|
||
|
||
services:
|
||
mysql:
|
||
image: mysql:8.0
|
||
container_name: go-sms-mysql
|
||
restart: unless-stopped
|
||
environment:
|
||
TZ: Asia/Shanghai
|
||
MYSQL_ROOT_PASSWORD: root123
|
||
MYSQL_DATABASE: gosms
|
||
MYSQL_USER: gosms
|
||
MYSQL_PASSWORD: gosms123
|
||
command:
|
||
- --character-set-server=utf8mb4
|
||
- --collation-server=utf8mb4_unicode_ci
|
||
- --default-time-zone=+08:00
|
||
# Day62d 吞吐修复:双 1 刷盘高并发小事务 fsync 排队(压测 SLOW 1394 条/审核
|
||
# UPDATE 1s),dev 回归 2/0(掉电丢 ≤1s 事务可接受);生产另评估。
|
||
- --innodb-flush-log-at-trx-commit=2
|
||
- --sync-binlog=0
|
||
# Day64 明细查询修复:message_detail 190 万行/2GB,默认 buffer_pool=128M
|
||
# 缓存零命中+HDD 全扫(实测 downlink-details 46-82s);调 4G 全热驻留
|
||
# (宿主 31G/可用 15G 余量充足;已先 SET GLOBAL 在线生效,此处持久化)。
|
||
# Day66 单表化后再调 6G:百万级/天写入冲刷 4G 池导致二级索引页换出,
|
||
# 冷查询 HDD 随机回表 29.5s;6G 给 detail 索引+数据页更多常驻余量
|
||
# (表+索引已 4.5G+;宿主 31G,在线 SET GLOBAL 生效,此处持久化)。
|
||
# 2026-11-13 S1-B SSD 基线(重建设计规范 §五):新机 /data 为 SSD(fio 4K
|
||
# 随机读 76.3k IOPS,老机 HDD 500 倍级),6G→10G(31G 内存容器组预算:
|
||
# MySQL 10G+CH 2G+Kafka 1G+Redis 0.5G+监控四件 1G≈14.5G,宿主留 16G 给
|
||
# Go 服务/编译/vscode-server);io_capacity 2000/10000 与 redo 1G 同步到位。
|
||
# 老机 HDD 三轮调参史(4G→6G)自此翻页,压测后(S5)再校。
|
||
- --innodb-buffer-pool-size=10G
|
||
- --innodb-io-capacity=2000
|
||
- --innodb-io-capacity-max=10000
|
||
- --innodb-redo-log-capacity=1G
|
||
ports:
|
||
- "13306:3306"
|
||
volumes:
|
||
- mysql-data:/var/lib/mysql
|
||
healthcheck:
|
||
test: ["CMD", "mysqladmin", "ping", "-h", "127.0.0.1", "-uroot", "-proot123"]
|
||
interval: 5s
|
||
timeout: 5s
|
||
retries: 30
|
||
start_period: 60s
|
||
|
||
redis:
|
||
image: redis:7.0
|
||
container_name: go-sms-redis
|
||
restart: unless-stopped
|
||
command:
|
||
- redis-server
|
||
- --appendonly
|
||
- "yes"
|
||
- --appendfsync
|
||
- everysec # Day54 R1 评审议题2前置①:显式 AOF everysec(丢 1s 容忍三前置之一;默认即 everysec,显式防漂移)
|
||
ports:
|
||
- "16379:6379"
|
||
volumes:
|
||
- redis-data:/data
|
||
healthcheck:
|
||
test: ["CMD", "redis-cli", "ping"]
|
||
interval: 5s
|
||
timeout: 3s
|
||
retries: 30
|
||
start_period: 10s
|
||
|
||
kafka:
|
||
image: apache/kafka:3.7.0
|
||
container_name: go-sms-kafka
|
||
restart: unless-stopped
|
||
environment:
|
||
# ---- KRaft 单节点模式(无 ZooKeeper);S1-B 恢复 compose 管理,事故史见文件头 ----
|
||
CLUSTER_ID: "5L6g3nShT-eMCtK--X86sw"
|
||
KAFKA_NODE_ID: 1
|
||
KAFKA_PROCESS_ROLES: broker,controller
|
||
KAFKA_CONTROLLER_QUORUM_VOTERS: 1@kafka:29093
|
||
# ---- 监听器:单一 listener,advertise 宿主机地址 ----
|
||
# 消费者组需经 metadata 返回的 endpoint 连接 Coordinator,
|
||
# 故统一广播 127.0.0.1:19092(宿主机端口映射 19092 -> 29092)
|
||
KAFKA_LISTENERS: PLAINTEXT://0.0.0.0:29092,CONTROLLER://0.0.0.0:29093
|
||
KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://127.0.0.1:19092
|
||
KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,CONTROLLER:PLAINTEXT
|
||
KAFKA_CONTROLLER_LISTENER_NAMES: CONTROLLER
|
||
KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
|
||
# ---- 单节点副本数必须为 1 ----
|
||
KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
|
||
KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
|
||
KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
|
||
KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 0
|
||
KAFKA_AUTO_CREATE_TOPICS_ENABLE: "true"
|
||
KAFKA_LOG_DIRS: /var/lib/kafka/data
|
||
# ---- 2026-11-13 S1-B SSD 基线(设计规范 §五):flush 放宽,掉电容忍靠
|
||
# page cache + 副本兜底(dev 单节点与 MySQL 2/0 同口径) ----
|
||
KAFKA_LOG_FLUSH_INTERVAL_MESSAGES: "100000"
|
||
KAFKA_LOG_FLUSH_INTERVAL_MS: "10000"
|
||
ports:
|
||
- "19092:29092"
|
||
volumes:
|
||
- kafka-data:/var/lib/kafka/data
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "bash -c '</dev/tcp/127.0.0.1/29092' || exit 1"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 30
|
||
start_period: 60s
|
||
|
||
# ---- 监控告警栈(Day 53 · runbook §6.2 P0) ----
|
||
# Prometheus 抓宿主网关 /metrics(host.docker.internal:host-gateway 映射);
|
||
# Alertmanager webhook 回推网关 /api/v1/alerts/sink(日志留痕验收抓手)。
|
||
# 宿主端口 19090/19093(避开常用 9090/9093 冲突)。
|
||
prometheus:
|
||
image: prom/prometheus:v2.53.0
|
||
container_name: go-sms-prometheus
|
||
restart: unless-stopped
|
||
command:
|
||
- --config.file=/etc/prometheus/prometheus.yml
|
||
- --storage.tsdb.retention.time=7d
|
||
volumes:
|
||
- ./deploy/monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
||
- ./deploy/monitoring/alert_rules.yml:/etc/prometheus/alert_rules.yml:ro
|
||
ports:
|
||
- "19090:9090"
|
||
extra_hosts:
|
||
- "host.docker.internal:host-gateway"
|
||
|
||
alertmanager:
|
||
image: prom/alertmanager:v0.27.0
|
||
container_name: go-sms-alertmanager
|
||
restart: unless-stopped
|
||
volumes:
|
||
- ./deploy/monitoring/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
|
||
ports:
|
||
- "19093:9093"
|
||
extra_hosts:
|
||
- "host.docker.internal:host-gateway"
|
||
|
||
etcd:
|
||
image: quay.io/coreos/etcd:v3.5.15
|
||
container_name: go-sms-etcd
|
||
restart: unless-stopped
|
||
environment:
|
||
ETCD_NAME: etcd0
|
||
ETCD_ADVERTISE_CLIENT_URLS: http://127.0.0.1:2379
|
||
ETCD_LISTEN_CLIENT_URLS: http://0.0.0.0:2379
|
||
ETCD_LISTEN_PEER_URLS: http://0.0.0.0:2380
|
||
ETCD_INITIAL_ADVERTISE_PEER_URLS: http://127.0.0.1:2380
|
||
ETCD_INITIAL_CLUSTER: etcd0=http://127.0.0.1:2380
|
||
ETCD_INITIAL_CLUSTER_STATE: new
|
||
ETCD_INITIAL_CLUSTER_TOKEN: go-sms-etcd
|
||
ETCD_AUTO_COMPACTION_RETENTION: "1"
|
||
command: ["etcd", "--data-dir=/etcd-data"]
|
||
ports:
|
||
- "12379:2379"
|
||
volumes:
|
||
- etcd-data:/etcd-data
|
||
healthcheck:
|
||
test: ["CMD", "etcdctl", "endpoint", "health", "--endpoints=127.0.0.1:2379"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 30
|
||
start_period: 15s
|
||
|
||
minio:
|
||
image: minio/minio:RELEASE.2024-06-13T22-53-53Z
|
||
container_name: go-sms-minio
|
||
restart: unless-stopped
|
||
environment:
|
||
MINIO_ROOT_USER: go-sms
|
||
MINIO_ROOT_PASSWORD: go-sms123456
|
||
command: ["server", "/data", "--console-address", ":9001"]
|
||
ports:
|
||
- "19010:9000" # S3 API
|
||
- "19011:9001" # Web Console
|
||
volumes:
|
||
- minio-data:/data
|
||
healthcheck:
|
||
test: ["CMD", "curl", "-f", "http://127.0.0.1:9000/minio/health/live"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 30
|
||
start_period: 15s
|
||
|
||
clickhouse:
|
||
image: clickhouse/clickhouse-server:24.3
|
||
container_name: go-sms-clickhouse
|
||
restart: unless-stopped
|
||
environment:
|
||
TZ: Asia/Shanghai
|
||
CLICKHOUSE_DB: gosms
|
||
CLICKHOUSE_USER: gosms
|
||
CLICKHOUSE_PASSWORD: gosms123
|
||
ports:
|
||
- "18123:8123" # HTTP
|
||
- "19000:9000" # Native
|
||
volumes:
|
||
- clickhouse-data:/var/lib/clickhouse
|
||
ulimits:
|
||
nofile:
|
||
soft: 262144
|
||
hard: 262144
|
||
healthcheck:
|
||
test: ["CMD", "clickhouse-client", "--user", "gosms", "--password", "gosms123", "--query", "SELECT 1"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 30
|
||
start_period: 30s
|
||
|
||
jaeger:
|
||
image: jaegertracing/all-in-one:1.57
|
||
container_name: go-sms-jaeger
|
||
restart: unless-stopped
|
||
environment:
|
||
COLLECTOR_OTLP_ENABLED: "true" # 启用 OTLP 接收(4318)
|
||
ports:
|
||
- "16686:16686" # Jaeger UI
|
||
- "14318:4318" # OTLP HTTP(应用上报)
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "wget -q --spider http://127.0.0.1:16686 || exit 1"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 30
|
||
start_period: 15s
|
||
|
||
volumes:
|
||
mysql-data:
|
||
redis-data:
|
||
kafka-data:
|
||
etcd-data:
|
||
minio-data:
|
||
clickhouse-data:
|