使用 Grafana Loki 构建网站访问统计分析系统

yum install -y libmaxminddb-devel libmaxminddb

mkdir -p /tmp/compile/openresty-$(nginx -v 2>&1|cut -d "/" -f2)/modules
cd /tmp/compile/openresty-$(nginx -v 2>&1|cut -d "/" -f2)/modules
git clone https://ghproxy.com/https://github.com/leev/ngx_http_geoip2_module.git

# 进入 OpenResty 源码目录
cd /data/scripts/oneinstack/src/openresty-1.19.3.1/bundle/nginx-1.19.3

# 配置编译时所需的环境变量（否则将失败）
export LUAJIT_LIB="/usr/local/openresty/luajit/lib/"
export LUAJIT_INC="../LuaJIT-*/src/"

# 获取已安装的 OpenResty 编译选项，以避免"二进制不兼容"错误
COMPILEOPTIONS=$(nginx -V 2>&1|grep -i "arguments"|cut -d ":" -f2-)

# 使用这些选项配置编译，将 GeoIP2 添加为动态模块
eval ./configure $COMPILEOPTIONS --add-dynamic-module=/tmp/compile/openresty-1.19.3.1/modules/ngx_http_geoip2_module/

# 仅编译模块
make modules

ls -lh objs/*.so
-rwxr-xr-x 1 root root 86K Jul 27 11:22 objs/ngx_http_geoip2_module.so
-rwxr-xr-x 1 root root 62K Jul 27 11:22 objs/ngx_stream_geoip2_module.so  # 这个动态库文件为 L4 使用，我们使用上面那个即可

# 创建模块目录
mkdir -p /usr/local/openresty/nginx/modules

# 复制动态库文件，方便后续引用
cp -a objs/*.so /usr/local/openresty/nginx/modules/

# 编辑 Nginx 主配置文件，加入模块加载指令
vim /etc/nginx/nginx.conf

# 在配置文件开头添加以下行
load_module modules/ngx_http_geoip2_module.so;

# 在 Nginx 主配置文件的 http 段中加入以下内容
vim /etc/nginx/nginx.conf

# GeoIP 配置
geoip2 /etc/nginx/geoip2/GeoLite2-Country.mmdb {
     auto_reload 5m;
     $geoip2_metadata_country_build metadata build_epoch;
     $geoip2_data_country_code default=US country iso_code;
     $geoip2_data_country_name country names en;
}

vim /etc/nginx/nginx.conf

# 添加 Dashboard 所需的日志格式
log_format json_analytics escape=json '{'
                            '"msec": "$msec", ' # request unixtime in seconds with a milliseconds resolution
                            '"connection": "$connection", ' # connection serial number
                            '"connection_requests": "$connection_requests", ' # number of requests made in connection
                    '"pid": "$pid", ' # process pid
                    '"request_id": "$request_id", ' # the unique request id
                    '"request_length": "$request_length", ' # request length (including headers and body)
                    '"remote_addr": "$remote_addr", ' # client IP
                    '"remote_user": "$remote_user", ' # client HTTP username
                    '"remote_port": "$remote_port", ' # client port
                    '"time_local": "$time_local", '
                    '"time_iso8601": "$time_iso8601", ' # local time in the ISO 8601 standard format
                    '"request": "$request", ' # full path no arguments if the request
                    '"request_uri": "$request_uri", ' # full path and arguments if the request
                    '"args": "$args", ' # args
                    '"status": "$status", ' # response status code
                    '"body_bytes_sent": "$body_bytes_sent", ' # the number of body bytes exclude headers sent to a client
                    '"bytes_sent": "$bytes_sent", ' # the number of bytes sent to a client
                    '"http_referer": "$http_referer", ' # HTTP referer
                    '"http_user_agent": "$http_user_agent", ' # user agent
                    '"http_x_forwarded_for": "$http_x_forwarded_for", ' # http_x_forwarded_for
                    '"http_host": "$http_host", ' # the request Host: header
                    '"server_name": "$server_name", ' # the name of the vhost serving the request
                    '"request_time": "$request_time", ' # request processing time in seconds with msec resolution
                    '"upstream": "$upstream_addr", ' # upstream backend server for proxied requests
                    '"upstream_connect_time": "$upstream_connect_time", ' # upstream handshake time incl. TLS
                    '"upstream_header_time": "$upstream_header_time", ' # time spent receiving upstream headers
                    '"upstream_response_time": "$upstream_response_time", ' # time spend receiving upstream body
                    '"upstream_response_length": "$upstream_response_length", ' # upstream response length
                    '"upstream_cache_status": "$upstream_cache_status", ' # cache HIT/MISS where applicable
                    '"ssl_protocol": "$ssl_protocol", ' # TLS protocol
                    '"ssl_cipher": "$ssl_cipher", ' # TLS cipher
                    '"scheme": "$scheme", ' # http or https
                    '"request_method": "$request_method", ' # request method
                    '"server_protocol": "$server_protocol", ' # request protocol, like HTTP/1.1 or HTTP/2.0
                    '"pipe": "$pipe", ' # "p" if request was pipelined, "." otherwise
                    '"gzip_ratio": "$gzip_ratio", '
                    '"http_cf_ray": "$http_cf_ray",'
                    '"geoip_country_code": "$geoip2_data_country_code"'
                    '}';

# 更改对应虚拟主机中的日志格式为上面定义的 json_analytics
vim vhost/www.conf

server {
  listen 443 http2;
  server_name www.treesir.pub;
  access_log /data/wwwlogs/nps_www_access_nginx.log json_analytics;
  ...
}

vim /etc/nginx/nginx.conf # 更改主配置文件，在 http 段加入以下内容

# 获取 CDN 后真实 IP
set_real_ip_from 0.0.0.0/0;
real_ip_header X-Forwarded-For;

curl -L "https://github.com/docker/compose/releases/download/1.29.2/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose \
&& chmod +x /usr/local/bin/docker-compose \
&& ln -s /usr/local/bin/docker-compose /usr/bin/docker-compose \
&& docker-compose --version

mkdir -p /data/docker-compose/loki-promtail/
cd /data/docker-compose/loki-promtail/

# 创建 docker-compose.yaml 文件
cat > docker-compose.yaml << EOF
version: "3"

networks:
  loki:

services:
  promtail:
    image: grafana/promtail:2.7.4
    volumes:
      - /data/wwwlogs:/data/wwwlogs:ro
      - ./config/config.yml:/etc/promtail/config.yml:ro
      - /etc/localtime:/etc/localtime
    command: -config.file=/etc/promtail/config.yml
EOF

mkdir -p config

cat > config/config.yml << EOF
server:
  http_listen_port: 0
  grpc_listen_port: 0

positions:
  filename: /tmp/positions.yaml

clients:
  - url: https://\${USER_ID}:\${TOKEN}@logs-prod-021.grafana.net/loki/api/v1/push

scrape_configs:
    - job_name: system
      pipeline_stages:
      - replace:
          expression: '(?:[0-9]{1,3}\.){3}([0-9]{1,3})'
          replace: '***'
      static_configs:
      - targets:
         - www.treesir.pub
        labels:
         job: nginx_access_log
         host: ali-vps
         agent: promtail
         __path__: /data/wwwlogs/nps_www_access_nginx.log
EOF

docker-compose up -d

sum(sum by (remote_addr) (
  sum by (remote_addr, geoip_country_code) (
    count_over_time(
      {job="$job"}
      | json
      | __error__="" and remote_addr != "" and http_user_agent !~ "^Blackbox.*"
      [24h]
    )
  ) ^ 0
))