# 获取所有信息
redis-cli INFO

# 按模块获取
redis-cli INFO server      # 服务器信息
redis-cli INFO clients      # 客户端信息
redis-cli INFO memory       # 内存信息
redis-cli INFO persistence  # 持久化信息
redis-cli INFO stats        # 统计信息
redis-cli INFO replication  # 复制信息
redis-cli INFO cpu          # CPU 信息
redis-cli INFO keyspace     # 数据库键空间信息
redis-cli INFO modules      # 模块信息
redis-cli INFO commandstats # 命令统计

redis-cli INFO server | grep -E "redis_version|uptime_in_seconds|hz|config_file"

redis-cli INFO clients | grep -E "connected_clients|blocked_clients|tracking_clients"

redis-cli INFO memory | grep -E "used_memory_human|used_memory_peak_human|mem_fragmentation_ratio|mem_allocator"

redis-cli INFO persistence | grep -E "rdb_last_save_time|rdb_last_bgsave_status|aof_enabled|aof_last_rewrite_status"

redis-cli INFO stats | grep -E "total_commands_processed|instantaneous_ops_per_sec|keyspace_hits|keyspace_misses|rejected_connections|expired_keys"

# 键空间命中率
HITS=$(redis-cli INFO stats | grep keyspace_hits | cut -d: -f2 | tr -d '\r')
MISSES=$(redis-cli INFO stats | grep keyspace_misses | cut -d: -f2 | tr -d '\r')
TOTAL=$((HITS + MISSES))
if [ $TOTAL -gt 0 ]; then
    HIT_RATE=$(echo "scale=2; $HITS * 100 / $TOTAL" | bc)
    echo "Hit rate: ${HIT_RATE}%"
fi

redis-cli INFO replication | grep -E "role|connected_slaves|master_link_status|master_last_io_seconds_ago|slave_repl_offset"

redis-cli INFO commandstats | head -20

# 实时打印所有命令（生产慎用！会影响性能约 50%）
redis-cli monitor

# 只监控特定命令
redis-cli monitor | grep -E "SET|GET"

# 只监控特定 Key
redis-cli monitor | grep "user:1001"

# 统计命令频率（采样分析）
redis-cli monitor | head -10000 | awk '{print $4}' | sort | uniq -c | sort -nr | head -10

# 实时统计信息
redis-cli --stat
# ------- data ------ -  ----- load ----  -  -  -  -
#   db   keys    mem     clients  blocked   requests     connections
#    0    1000  2.50M        5        0       1000/s          10
#    0    1001  2.51M        5        0       1200/s          10

# 延迟测试
redis-cli --latency
# min: 0, max: 1, avg: 0.19 (264 samples)

# 延迟历史
redis-cli --latency-history
# min: 0, max: 1, avg: 0.19 (132 samples) -- 15.00 seconds range

# 延迟分布图
redis-cli --latency-dist

# 采样特定命令的延迟
redis-cli --intrinsic-latency 5
# 5 seconds of testing...
# 128 microseconds per call (best of 1000 calls)

# Docker 方式
docker run -d --name redis-exporter \
  -p 9121:9121 \
  oliver006/redis_exporter \
  --redis.addr redis://192.168.1.100:6379 \
  --redis.password YourPassword

version: '3.8'

services:
  redis:
    image: redis:7.2
    container_name: redis
    ports:
      - "6379:6379"
    command: redis-server --requirepass mypassword --appendonly yes
    networks:
      - monitoring

  redis-exporter:
    image: oliver006/redis_exporter:latest
    container_name: redis-exporter
    ports:
      - "9121:9121"
    environment:
      REDIS_ADDR: redis://redis:6379
      REDIS_PASSWORD: mypassword
    depends_on:
      - redis
    networks:
      - monitoring

  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
    networks:
      - monitoring

  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    ports:
      - "3000:3000"
    environment:
      GF_SECURITY_ADMIN_PASSWORD: admin123
    volumes:
      - grafana-data:/var/lib/grafana
    depends_on:
      - prometheus
    networks:
      - monitoring

volumes:
  grafana-data:

networks:
  monitoring:
    driver: bridge

# prometheus.yml
global:
  scrape_interval: 15s
  evaluation_interval: 15s

scrape_configs:
  - job_name: 'redis'
    static_configs:
      - targets: ['redis-exporter:9121']
    metrics_path: /metrics

# QPS
rate(redis_commands_processed_total[5m])

# 内存使用
redis_memory_used_bytes

# 连接数
redis_connected_clients

# 命中率
rate(redis_keyspace_hits_total[5m]) / (rate(redis_keyspace_hits_total[5m]) + rate(redis_keyspace_misses_total[5m]))

# 延迟（通过 exporter）
redis_commands_duration_seconds_total

# 淘汰数
rate(redis_evicted_keys_total[5m])

# 慢查询
redis_slowlog_length

# 主从复制延迟
redis_connected_slave_lag_seconds

# alert-rules.yml
groups:
  - name: redis_alerts
    rules:
      - alert: RedisDown
        expr: redis_up == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Redis 实例宕机"
          description: "Redis {{ $labels.instance }} 已停止响应"

      - alert: RedisHighMemory
        expr: redis_memory_used_bytes / redis_memory_max_bytes > 0.8
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Redis 内存使用率超过 80%"

      - alert: RedisHighFragmentation
        expr: redis_mem_fragmentation_ratio > 1.5
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Redis 内存碎片率过高"

      - alert: RedisLowHitRate
        expr: rate(redis_keyspace_hits_total[5m]) / (rate(redis_keyspace_hits_total[5m]) + rate(redis_keyspace_misses_total[5m])) < 0.8
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Redis 命中率低于 80%"

      - alert: RedisTooManyConnections
        expr: redis_connected_clients > 8000
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Redis 连接数过多"

      - alert: RedisReplicationBroken
        expr: redis_connected_slaves < 1
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Redis 主从复制断开"

# 日志轮转（logrotate）
# /etc/logrotate.d/redis
/var/log/redis/redis-server.log {
    daily
    rotate 7
    compress
    delaycompress
    missingok
    notifempty
    create 640 redis redis
    postrotate
        /bin/kill -USR1 $(cat /var/run/redis/redis-server.pid 2>/dev/null) 2>/dev/null || true
    endscript
}

# 定期监控内存增长趋势
redis-cli INFO memory | grep used_memory_human
# 预测何时达到 maxmemory

# 通过命令统计找出耗时命令
redis-cli INFO commandstats | sort -t= -k3 -nr | head -10

# Prometheus + Alertmanager + 钉钉/企业微信
# 配置告警规则，发送到通知渠道