b2894lxlx/tms-erp-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

init

Browse Source
This commit is contained in:
kk
2026-07-08 17:57:11 +08:00
commit f1e6599892
743 changed files with 159169 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
script/docker/app/.env
+2
View File
@@ -0,0 +1,2 @@
REGISTER=192.168.0.188/blade
TAG=4.10.0.RELEASE
script/docker/app/deploy.sh
+166
View File
@@ -0,0 +1,166 @@
#!/bin/bash
#使用说明，用来提示输入参数
usage() {
echo "Usage: sh 执行脚本.sh [port|mount|base|monitor|modules|prometheus|alertmanager|stop|rm|rmiNoneTag]"
exit 1
}
#开启所需端口
port(){
#gateway
firewall-cmd --add-port=88/tcp --permanent
#web
firewall-cmd --add-port=8000/tcp --permanent
#nacos
firewall-cmd --add-port=8848/tcp --permanent
firewall-cmd --add-port=9848/tcp --permanent
firewall-cmd --add-port=9849/tcp --permanent
#sentinel
firewall-cmd --add-port=8858/tcp --permanent
#grafana
firewall-cmd --add-port=3000/tcp --permanent
#mysql
firewall-cmd --add-port=3306/tcp --permanent
#redis
firewall-cmd --add-port=3379/tcp --permanent
#admin
firewall-cmd --add-port=7002/tcp --permanent
#ureport
firewall-cmd --add-port=8108/tcp --permanent
#zipkin
firewall-cmd --add-port=9411/tcp --permanent
#prometheus
firewall-cmd --add-port=9090/tcp --permanent
#swagger
firewall-cmd --add-port=18000/tcp --permanent
#powerjob
firewall-cmd --add-port=7700/tcp --permanent
firewall-cmd --add-port=10086/tcp --permanent
firewall-cmd --add-port=10010/tcp --permanent
#firewalld
service firewalld restart
}
##放置挂载文件
mount(){
#挂载配置文件
if test ! -f "/docker/nginx/api/nginx.conf" ;then
mkdir -p /docker/nginx/api
cp nginx/api/nginx.conf /docker/nginx/api/nginx.conf
fi
if test ! -f "/docker/nginx/web/nginx.conf" ;then
mkdir -p /docker/nginx/web
cp nginx/web/nginx.conf /docker/nginx/web/nginx.conf
cp -r nginx/web/html /docker/nginx/web/html
fi
if test ! -f "/docker/nacos/conf/application.properties" ;then
mkdir -p /docker/nacos/conf
cp nacos/conf/application.properties /docker/nacos/conf/application.properties
fi
if test ! -f "/docker/prometheus/prometheus.yml" ;then
mkdir -p /docker/prometheus
cp prometheus/config/prometheus.yml /docker/prometheus/prometheus.yml
fi
if test ! -f "/docker/prometheus/rules/alert_rules.yml" ;then
mkdir -p /docker/prometheus/rules
cp prometheus/config/alert_rules.yml /docker/prometheus/rules/alert_rules.yml
fi
if test ! -f "/docker/grafana/grafana.ini" ;then
mkdir -p /docker/grafana
cp prometheus/config/grafana.ini /docker/grafana/grafana.ini
fi
if test ! -f "/docker/alertmanager/alertmanager.yml" ;then
mkdir -p /docker/alertmanager
cp prometheus/config/alertmanager.yml /docker/alertmanager/alertmanager.yml
fi
if test ! -f "/docker/alertmanager/templates/wechat.tmpl" ;then
mkdir -p /docker/alertmanager/templates
cp prometheus/config/wechat.tmpl /docker/alertmanager/templates/wechat.tmpl
fi
if test ! -f "/docker/webhook_dingtalk/dingtalk.yml" ;then
mkdir -p /docker/webhook_dingtalk
cp prometheus/config/dingtalk.yml /docker/webhook_dingtalk/dingtalk.yml
fi
#增加目录权限
chmod -R 777 /docker/prometheus
chmod -R 777 /docker/grafana
chmod -R 777 /docker/alertmanager
}
#启动基础模块
base(){
docker-compose up -d nacos sentinel seata-server web-nginx blade-nginx blade-redis powerjob-server
}
#启动监控模块
monitor(){
docker-compose up -d blade-admin
}
#启动程序模块
modules(){
docker-compose up -d blade-gateway1 blade-gateway2 blade-auth1 blade-auth2 blade-report blade-desk blade-system blade-log blade-flow blade-resource blade-job
}
#启动普罗米修斯模块
prometheus(){
docker-compose up -d prometheus node-exporter mysqld-exporter cadvisor grafana
}
#启动监听模块
alertmanager(){
docker-compose up -d alertmanager webhook-dingtalk
}
#关闭所有模块
stop(){
docker-compose stop
}
#删除所有模块
rm(){
docker-compose rm
}
#删除Tag为空的镜像
rmiNoneTag(){
docker images|grep none|awk '{print $3}'|xargs docker rmi -f
}
#根据输入参数，选择执行对应方法，不输入则执行使用说明
case "$1" in
"port")
port
;;
"mount")
mount
;;
"base")
base
;;
"monitor")
monitor
;;
"modules")
modules
;;
"prometheus")
prometheus
;;
"alertmanager")
alertmanager
;;
"stop")
stop
;;
"rm")
rm
;;
"rmiNoneTag")
rmiNoneTag
;;
*)
usage
;;
esac
script/docker/app/docker-compose.yml
+366
View File
@@ -0,0 +1,366 @@
version: '3'
services:
####################################################################################################
###=================================== 以下为中间件模块 =========================================###
####################################################################################################
nacos:
image: nacos/nacos-server:v3.1.2
hostname: "nacos-standalone"
environment:
- NACOS_AUTH_ENABLE=true
- NACOS_AUTH_CACHE_ENABLE=true
- NACOS_AUTH_IDENTITY_KEY=nacos
- NACOS_AUTH_IDENTITY_VALUE=nacos
- NACOS_AUTH_TOKEN= # 请阅读官方文档了解规则后替换为自己的token：https://nacos.io/zh-cn/docs/v2/guide/user/auth.html
- MODE=standalone
- TZ=Asia/Shanghai
volumes:
- /docker/nacos/standalone-logs/:/home/nacos/logs
- /docker/nacos/conf/application.properties:/home/nacos/conf/application.properties
ports:
- 8848:8848
- 9848:9848
- 8080:8080
networks:
blade_net:
ipv4_address: 172.30.0.48
sentinel:
image: bladex/sentinel-dashboard:1.8.6
hostname: "sentinel"
environment:
- TZ=Asia/Shanghai
ports:
- 8858:8858
restart: on-failure
networks:
blade_net:
ipv4_address: 172.30.0.58
seata-server:
image: seataio/seata-server:1.6.1
hostname: "seata-server"
ports:
- 8091:8091
environment:
- TZ=Asia/Shanghai
- SEATA_PORT=8091
- STORE_MODE=file
networks:
blade_net:
ipv4_address: 172.30.0.68
blade-nginx:
image: nginx:stable-alpine-perl
hostname: "blade-nginx"
environment:
- TZ=Asia/Shanghai
ports:
- 88:88
volumes:
- /docker/nginx/api/nginx.conf:/etc/nginx/nginx.conf
privileged: true
restart: always
networks:
- blade_net
web-nginx:
image: nginx:stable-alpine-perl
hostname: "web-nginx"
environment:
- TZ=Asia/Shanghai
ports:
- 8000:8000
volumes:
- /docker/nginx/web/html:/usr/share/nginx/html
- /docker/nginx/web/nginx.conf:/etc/nginx/nginx.conf
privileged: true
restart: always
networks:
- blade_net
blade-redis:
image: redis:7-alpine
hostname: "blade-redis"
environment:
- TZ=Asia/Shanghai
ports:
- 3379:6379
volumes:
- /docker/redis/data:/data
command: "redis-server --appendonly yes"
privileged: true
restart: always
networks:
- blade_net
##powerjob.network.external.address可配置为外部宿主机地址，更详细见：https://www.yuque.com/powerjob/guidence/deploy_server
powerjob-server:
container_name: powerjob-server
image: powerjob/powerjob-server:4.3.6
restart: always
environment:
JVMOPTIONS: "-Xmx512m -Dpowerjob.network.external.address=172.30.0.70 -Dpowerjob.network.external.port.http=10010 -Dpowerjob.network.external.port.akka=10086"
PARAMS: "--spring.datasource.core.jdbc-url=jdbc:mysql://mysql服务ip:端口/powerjob-product?useUnicode=true&characterEncoding=UTF-8&useSSL=false --spring.datasource.core.username=mysql账号名 --spring.datasource.core.password=mysql密码 --oms.mongodb.enable=false"
ports:
- 7700:7700
- 10086:10086
- 10010:10010
networks:
blade_net:
ipv4_address: 172.30.0.70
####################################################################################################
###================================= 以下为BladeX服务模块 =======================================###
####################################################################################################
blade-admin:
image: "${REGISTER}/blade-admin:${TAG}"
environment:
- TZ=Asia/Shanghai
ports:
- 7002:7002
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.72
blade-gateway1:
image: "${REGISTER}/blade-gateway:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.81
blade-gateway2:
image: "${REGISTER}/blade-gateway:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.82
blade-auth1:
image: "${REGISTER}/blade-auth:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.91
blade-auth2:
image: "${REGISTER}/blade-auth:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.92
blade-report:
image: "${REGISTER}/blade-report:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
ports:
- 8108:8108
networks:
blade_net:
ipv4_address: 172.30.0.98
blade-log:
image: "${REGISTER}/blade-log:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
- blade_net
blade-desk:
image: "${REGISTER}/blade-desk:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
- blade_net
blade-system:
image: "${REGISTER}/blade-system:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
- blade_net
blade-flow:
image: "${REGISTER}/blade-flow:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
- blade_net
blade-resource:
image: "${REGISTER}/blade-resource:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
- blade_net
blade-job:
image: "${REGISTER}/blade-job:${TAG}"
environment:
- TZ=Asia/Shanghai
privileged: true
restart: always
networks:
- blade_net
####################################################################################################
###=============================== 以下为Prometheus监控模块 =====================================###
####################################################################################################
prometheus:
image: prom/prometheus:v2.24.1
hostname: "prometheus"
environment:
- TZ=Asia/Shanghai
ports:
- 9090:9090
volumes:
- /docker/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
- /docker/prometheus/rules:/etc/prometheus/rules
command: "--config.file=/etc/prometheus/prometheus.yml --web.enable-lifecycle"
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.90
node-exporter:
image: prom/node-exporter:v1.0.1
hostname: "node-exporter"
environment:
- TZ=Asia/Shanghai
ports:
- 9190:9100
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.93
mysqld-exporter:
image: prom/mysqld-exporter:v0.12.1
hostname: "mysqld-exporter"
environment:
- TZ=Asia/Shanghai
# 需要先在mysql服务执行如下语句
# =====================================================================================
# === CREATE USER 'exporter'@'mysql服务ip' IDENTIFIED BY '密码'; ===
# === GRANT PROCESS, REPLICATION CLIENT, SELECT ON *.* TO 'exporter'@'mysql服务ip'; ===
# === flush privileges; ===
# =====================================================================================
- DATA_SOURCE_NAME=exporter:密码@(mysql服务ip:mysql服务端口)/
ports:
- 9104:9104
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.94
cadvisor:
image: google/cadvisor:v0.33.0
hostname: "cadvisor"
environment:
- TZ=Asia/Shanghai
ports:
- 18080:8080
volumes:
- /:/rootfs:ro
- /var/run:/var/run:rw
- /sys:/sys:ro
- /var/lib/docker/:/var/lib/docker:ro
- /dev/disk/:/dev/disk:ro
command: "detach=true"
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.180
grafana:
image: grafana/grafana:7.3.7
hostname: "grafana"
environment:
- TZ=Asia/Shanghai
- GF_SERVER_ROOT_URL=https://grafana.bladex.vip
- GF_SECURITY_ADMIN_PASSWORD=1qaz@WSX
ports:
- 3000:3000
volumes:
- /docker/grafana/grafana.ini:/etc/grafana/grafana.ini
- /docker/grafana:/var/lib/grafana
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.30
alertmanager:
image: prom/alertmanager:v0.21.0
hostname: "alertmanager"
environment:
- TZ=Asia/Shanghai
ports:
- 9093:9093
volumes:
- /docker/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml
- /docker/alertmanager/data:/etc/alertmanager/data
- /docker/alertmanager/templates:/etc/alertmanager/templates
command: "--config.file=/etc/alertmanager/alertmanager.yml --storage.path=/etc/alertmanager/data"
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.99
webhook-dingtalk:
image: timonwong/prometheus-webhook-dingtalk:v1.4.0
hostname: "webhook-dingtalk"
environment:
- TZ=Asia/Shanghai
ports:
- 8060:8060
command: "ding.profile=webhook_robot=https://oapi.dingtalk.com/robot/send?access_token=xxxxx"
privileged: true
restart: always
networks:
blade_net:
ipv4_address: 172.30.0.96
networks:
blade_net:
driver: bridge
ipam:
config:
- subnet: 172.30.0.0/16
script/docker/app/nacos/conf/application.properties
+55
View File
@@ -0,0 +1,55 @@
# spring
server.servlet.contextPath=${SERVER_SERVLET_CONTEXTPATH:/nacos}
server.contextPath=/nacos
server.port=${NACOS_APPLICATION_PORT:8848}
server.tomcat.accesslog.max-days=30
server.tomcat.accesslog.pattern=%h %l %u %t "%r" %s %b %D %{User-Agent}i %{Request-Source}i
server.tomcat.accesslog.enabled=${TOMCAT_ACCESSLOG_ENABLED:false}
server.error.include-message=ALWAYS
# default current work dir
server.tomcat.basedir=file:.
#*************** Config Module Related Configurations ***************#
### Deprecated configuration property, it is recommended to use `spring.sql.init.platform` replaced.
#spring.datasource.platform=${SPRING_DATASOURCE_PLATFORM:}
spring.sql.init.platform=${SPRING_DATASOURCE_PLATFORM:}
nacos.cmdb.dumpTaskInterval=3600
nacos.cmdb.eventTaskInterval=10
nacos.cmdb.labelTaskInterval=300
nacos.cmdb.loadDataAtStart=false
db.num=${MYSQL_DATABASE_NUM:1}
db.url.0=jdbc:mysql://${MYSQL_SERVICE_HOST}:${MYSQL_SERVICE_PORT:3306}/${MYSQL_SERVICE_DB_NAME}?${MYSQL_SERVICE_DB_PARAM:characterEncoding=utf8&connectTimeout=1000&socketTimeout=3000&autoReconnect=true&useSSL=false}
db.user.0=${MYSQL_SERVICE_USER}
db.password.0=${MYSQL_SERVICE_PASSWORD}
## DB connection pool settings
db.pool.config.connectionTimeout=${DB_POOL_CONNECTION_TIMEOUT:30000}
db.pool.config.validationTimeout=10000
db.pool.config.maximumPoolSize=20
db.pool.config.minimumIdle=2
### The auth system to use, currently only 'nacos' and 'ldap' is supported:
nacos.core.auth.system.type=${NACOS_AUTH_SYSTEM_TYPE:nacos}
### worked when nacos.core.auth.system.type=nacos
### The token expiration in seconds:
nacos.core.auth.plugin.nacos.token.expire.seconds=${NACOS_AUTH_TOKEN_EXPIRE_SECONDS:18000}
### The default token:
nacos.core.auth.plugin.nacos.token.secret.key=${NACOS_AUTH_TOKEN:}
### Turn on/off caching of auth information. By turning on this switch, the update of auth information would have a 15 seconds delay.
nacos.core.auth.caching.enabled=${NACOS_AUTH_CACHE_ENABLE:false}
nacos.core.auth.enable.userAgentAuthWhite=${NACOS_AUTH_USER_AGENT_AUTH_WHITE_ENABLE:false}
nacos.core.auth.server.identity.key=${NACOS_AUTH_IDENTITY_KEY:}
nacos.core.auth.server.identity.value=${NACOS_AUTH_IDENTITY_VALUE:}
## spring security config
### turn off security
nacos.security.ignore.urls=${NACOS_SECURITY_IGNORE_URLS:/,/error,/**/*.css,/**/*.js,/**/*.html,/**/*.map,/**/*.svg,/**/*.png,/**/*.ico,/console-fe/public/**,/v1/auth/**,/v1/console/health/**,/actuator/**,/v1/console/server/**}
# metrics for elastic search
management.metrics.export.elastic.enabled=false
management.metrics.export.influx.enabled=false
nacos.naming.distro.taskDispatchThreadCount=10
nacos.naming.distro.taskDispatchPeriod=200
nacos.naming.distro.batchSyncKeyCount=1000
nacos.naming.distro.initDataRatio=0.9
nacos.naming.distro.syncRetryDelay=5000
nacos.naming.data.warmup=true
nacos.console.ui.enabled=true
nacos.core.param.check.enabled=true
script/docker/app/nginx/api/nginx.conf
+77
View File
@@ -0,0 +1,77 @@
user root;
worker_processes 1;
error_log /var/log/nginx/error.log warn;
pid /var/run/nginx.pid;
events {
worker_connections 1024;
}
http {
include /etc/nginx/mime.types;
default_type application/octet-stream;
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent" "$http_x_forwarded_for"';
access_log /var/log/nginx/access.log main;
sendfile on;
#tcp_nopush on;
keepalive_timeout 65;
#gzip on;
#include /etc/nginx/conf.d/*.conf;
upstream gateway {
server 172.30.0.81;
server 172.30.0.82;
}
upstream auth {
server 172.30.0.91:8100;
server 172.30.0.92:8100;
}
server {
listen 88;
server_name gateway;
location / {
proxy_redirect off;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_buffering off;
proxy_pass http://gateway/;
}
location ~ ^/(api/)?actuator {
return 403;
}
}
server {
listen 9000;
server_name auth;
location / {
proxy_redirect off;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_buffering off;
proxy_pass http://auth/;
}
location ~ ^/(api/)?actuator {
return 403;
}
}
}
script/docker/app/nginx/web/html/index.html
+10
View File
@@ -0,0 +1,10 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Hello BladeX</title>
</head>
<body>
<div style="text-align: center">Hello BladeX !</div>
</body>
</html>
script/docker/app/nginx/web/nginx.conf
+77
View File
@@ -0,0 +1,77 @@
user root;
worker_processes 1;
error_log /var/log/nginx/error.log warn;
pid /var/run/nginx.pid;
events {
worker_connections 1024;
}
http {
include /etc/nginx/mime.types;
default_type application/octet-stream;
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent" "$http_x_forwarded_for"';
access_log /var/log/nginx/access.log main;
sendfile on;
#tcp_nopush on;
keepalive_timeout 65;
#include /etc/nginx/conf.d/*.conf;
gzip on;
gzip_min_length 1k;
gzip_buffers 4 16k;
gzip_http_version 1.1;
gzip_comp_level 2;
gzip_types text/plain application/javascript application/x-javascript text/javascript text/css application/xml;
gzip_vary on;
gzip_proxied expired no-cache no-store private auth;
gzip_disable "MSIE [1-6]\.";
upstream gateway {
server 172.30.0.81;
server 172.30.0.82;
}
server {
listen 8000;
server_name web;
root /usr/share/nginx/html;
location /{
index index.html;
error_page 404 /index.html;
}
location ~ ^/(api/)?actuator {
return 403;
}
location ^~ /oauth/redirect {
rewrite ^(.*)$ /index.html break;
}
location ^~ /api/ {
proxy_redirect off;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_buffering off;
rewrite ^/api/(.*)$ /$1 break;
proxy_pass http://gateway/;
}
}
}
script/docker/app/prometheus/config/alert_rules.yml
+118
View File
@@ -0,0 +1,118 @@
groups:
- name: alert_rules
rules:
- alert: CpuUsageAlertWarning
expr: sum(avg(irate(node_cpu_seconds_total{mode!='idle'}[5m])) without (cpu)) by (instance) > 0.60
for: 2m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} CPU usage high"
description: "{{ $labels.instance }} CPU usage above 60% (current value: {{ $value }})"
- alert: CpuUsageAlertSerious
#expr: sum(avg(irate(node_cpu_seconds_total{mode!='idle'}[5m])) without (cpu)) by (instance) > 0.85
expr: (100 - (avg by (instance) (irate(node_cpu_seconds_total{job=~".*",mode="idle"}[5m])) * 100)) > 85
for: 3m
labels:
level: serious
annotations:
summary: "Instance {{ $labels.instance }} CPU usage high"
description: "{{ $labels.instance }} CPU usage above 85% (current value: {{ $value }})"
- alert: MemUsageAlertWarning
expr: avg by(instance) ((1 - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) / node_memory_MemTotal_bytes) * 100) > 70
for: 2m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} MEM usage high"
description: "{{$labels.instance}}: MEM usage is above 70% (current value is: {{ $value }})"
- alert: MemUsageAlertSerious
expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)/node_memory_MemTotal_bytes > 0.90
for: 3m
labels:
level: serious
annotations:
summary: "Instance {{ $labels.instance }} MEM usage high"
description: "{{ $labels.instance }} MEM usage above 90% (current value: {{ $value }})"
- alert: DiskUsageAlertWarning
expr: (1 - node_filesystem_free_bytes{fstype!="rootfs",mountpoint!="",mountpoint!~"/(run|var|sys|dev).*"} / node_filesystem_size_bytes) * 100 > 80
for: 2m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} Disk usage high"
description: "{{$labels.instance}}: Disk usage is above 80% (current value is: {{ $value }})"
- alert: DiskUsageAlertSerious
expr: (1 - node_filesystem_free_bytes{fstype!="rootfs",mountpoint!="",mountpoint!~"/(run|var|sys|dev).*"} / node_filesystem_size_bytes) * 100 > 90
for: 3m
labels:
level: serious
annotations:
summary: "Instance {{ $labels.instance }} Disk usage high"
description: "{{$labels.instance}}: Disk usage is above 90% (current value is: {{ $value }})"
- alert: NodeFileDescriptorUsage
expr: avg by (instance) (node_filefd_allocated{} / node_filefd_maximum{}) * 100 > 60
for: 2m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} File Descriptor usage high"
description: "{{$labels.instance}}: File Descriptor usage is above 60% (current value is: {{ $value }})"
- alert: NodeLoad15
expr: avg by (instance) (node_load15{}) > 80
for: 2m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} Load15 usage high"
description: "{{$labels.instance}}: Load15 is above 80 (current value is: {{ $value }})"
- alert: NodeAgentStatus
expr: avg by (instance) (up{}) == 0
for: 2m
labels:
level: warning
annotations:
summary: "{{$labels.instance}}: has been down"
description: "{{$labels.instance}}: Node_Exporter Agent is down (current value is: {{ $value }})"
- alert: NodeProcsBlocked
expr: avg by (instance) (node_procs_blocked{}) > 10
for: 2m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} Process Blocked usage high"
description: "{{$labels.instance}}: Node Blocked Procs detected! above 10 (current value is: {{ $value }})"
- alert: NetworkTransmitRate
#expr: avg by (instance) (floor(irate(node_network_transmit_bytes_total{device="ens192"}[2m]) / 1024 / 1024)) > 50
expr: avg by (instance) (floor(irate(node_network_transmit_bytes_total{}[2m]) / 1024 / 1024 * 8 )) > 40
for: 1m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} Network Transmit Rate usage high"
description: "{{$labels.instance}}: Node Transmit Rate (Upload) is above 40Mbps/s (current value is: {{ $value }}Mbps/s)"
- alert: NetworkReceiveRate
#expr: avg by (instance) (floor(irate(node_network_receive_bytes_total{device="ens192"}[2m]) / 1024 / 1024)) > 50
expr: avg by (instance) (floor(irate(node_network_receive_bytes_total{}[2m]) / 1024 / 1024 * 8 )) > 40
for: 1m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} Network Receive Rate usage high"
description: "{{$labels.instance}}: Node Receive Rate (Download) is above 40Mbps/s (current value is: {{ $value }}Mbps/s)"
- alert: DiskReadRate
expr: avg by (instance) (floor(irate(node_disk_read_bytes_total{}[2m]) / 1024 )) > 200
for: 2m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} Disk Read Rate usage high"
description: "{{$labels.instance}}: Node Disk Read Rate is above 200KB/s (current value is: {{ $value }}KB/s)"
- alert: DiskWriteRate
expr: avg by (instance) (floor(irate(node_disk_written_bytes_total{}[2m]) / 1024 / 1024 )) > 20
for: 2m
labels:
level: warning
annotations:
summary: "Instance {{ $labels.instance }} Disk Write Rate usage high"
description: "{{$labels.instance}}: Node Disk Write Rate is above 20MB/s (current value is: {{ $value }}MB/s)"
script/docker/app/prometheus/config/alertmanager.yml
+56
View File
@@ -0,0 +1,56 @@
global:
# 在没有报警的情况下声明为已解决的时间
resolve_timeout: 5m
# 配置邮件发送信息
smtp_smarthost: 'smtp.163.com:25'
# 邮箱地址
smtp_from: 'bladejava@163.com'
# 邮箱地址
smtp_auth_username: 'bladejava@163.com'
# 邮箱授权码，需要自行开启设置，非邮箱密码
smtp_auth_password: 'xxxxxxxx'
# 邮箱地址
smtp_hello: 'bladejava@163.com'
smtp_require_tls: false
templates:
# 告警模板文件
- "/etc/alertmanager/templates/wechat.tmpl"
route:
# 接收到告警后到自定义分组
group_by: ["alertname"]
# 分组创建后初始化等待时长
group_wait: 10s
# 告警信息发送之前的等待时长
group_interval: 30s
# 重复报警的间隔时长
repeat_interval: 5m
# 默认消息接收
receiver: "wechat"
receivers:
# 微信
- name: "wechat"
wechat_configs:
# 是否发送恢复信息
- send_resolved: true
# 填写应用 AgentId
agent_id: "1000002"
# 填写应用 Secret
api_secret: "jxxxxxxxxxxxxxxxxxxxc"
# 填写企业 ID
corp_id: "wwxxxxxxxxxxx01d"
# 填写接收消息的群体
to_user: "@all"
# 钉钉
- name: 'dingtalk'
webhook_configs:
# prometheus-webhook-dingtalk服务的地址
- url: http://172.30.0.96:8060/dingtalk/webhook_robot/send
send_resolved: true
# 邮件
- name: 'email'
email_configs:
- to: 'your email'
send_resolved: true
script/docker/app/prometheus/config/dingtalk.yml
+12
View File
@@ -0,0 +1,12 @@
timeout: 5s
targets:
webhook_robot:
# 钉钉机器人创建后的webhook地址
url: https://oapi.dingtalk.com/robot/send?access_token=xxxxxxxxxxxx
webhook_mention_all:
# 钉钉机器人创建后的webhook地址
url: https://oapi.dingtalk.com/robot/send?access_token=xxxxxxxxxxxx
# 提醒全员
mention:
all: true
script/docker/app/prometheus/config/grafana.ini
+849
View File
@@ -0,0 +1,849 @@
##################### Grafana Configuration Example #####################
#
# Everything has defaults so you only need to uncomment things you want to
# change
# possible values : production, development
;app_mode = production
# instance name, defaults to HOSTNAME environment variable value or hostname if HOSTNAME var is empty
;instance_name = ${HOSTNAME}
#################################### Paths ####################################
[paths]
# Path to where grafana can store temp files, sessions, and the sqlite3 db (if that is used)
;data = /var/lib/grafana
# Temporary files in `data` directory older than given duration will be removed
;temp_data_lifetime = 24h
# Directory where grafana can store logs
;logs = /var/log/grafana
# Directory where grafana will automatically scan and look for plugins
;plugins = /var/lib/grafana/plugins
# folder that contains provisioning config files that grafana will apply on startup and while running.
;provisioning = conf/provisioning
#################################### Server ####################################
[server]
# Protocol (http, https, h2, socket)
;protocol = http
# The ip address to bind to, empty will bind to all interfaces
;http_addr =
# The http port to use
;http_port = 3000
# The public facing domain name used to access grafana from a browser
;domain = localhost
# Redirect to correct domain if host header does not match domain
# Prevents DNS rebinding attacks
;enforce_domain = false
# The full public facing url you use in browser, used for redirects and emails
# If you use reverse proxy and sub path specify full url (with sub path)
;root_url = %(protocol)s://%(domain)s:%(http_port)s/
# Serve Grafana from subpath specified in `root_url` setting. By default it is set to `false` for compatibility reasons.
;serve_from_sub_path = false
# Log web requests
;router_logging = false
# the path relative working path
;static_root_path = public
# enable gzip
;enable_gzip = false
# https certs & key file
;cert_file =
;cert_key =
# Unix socket path
;socket =
#################################### Database ####################################
[database]
# You can configure the database connection by specifying type, host, name, user and password
# as separate properties or as on string using the url properties.
# Either "mysql", "postgres" or "sqlite3", it's your choice
;type = sqlite3
;host = 127.0.0.1:3306
;name = grafana
;user = root
# If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;"""
;password =
# Use either URL or the previous fields to configure the database
# Example: mysql://user:secret@host:port/database
;url =
# For "postgres" only, either "disable", "require" or "verify-full"
;ssl_mode = disable
;ca_cert_path =
;client_key_path =
;client_cert_path =
;server_cert_name =
# For "sqlite3" only, path relative to data_path setting
;path = grafana.db
# Max idle conn setting default is 2
;max_idle_conn = 2
# Max conn setting default is 0 (mean not set)
;max_open_conn =
# Connection Max Lifetime default is 14400 (means 14400 seconds or 4 hours)
;conn_max_lifetime = 14400
# Set to true to log the sql calls and execution times.
;log_queries =
# For "sqlite3" only. cache mode setting used for connecting to the database. (private, shared)
;cache_mode = private
#################################### Cache server #############################
[remote_cache]
# Either "redis", "memcached" or "database" default is "database"
;type = database
# cache connectionstring options
# database: will use Grafana primary database.
# redis: config like redis server e.g. `addr=127.0.0.1:6379,pool_size=100,db=0,ssl=false`. Only addr is required. ssl may be 'true', 'false', or 'insecure'.
# memcache: 127.0.0.1:11211
;connstr =
#################################### Data proxy ###########################
[dataproxy]
# This enables data proxy logging, default is false
;logging = false
# How long the data proxy waits before timing out, default is 30 seconds.
# This setting also applies to core backend HTTP data sources where query requests use an HTTP client with timeout set.
;timeout = 30
# How many seconds the data proxy waits before sending a keepalive probe request.
;keep_alive_seconds = 30
# How many seconds the data proxy waits for a successful TLS Handshake before timing out.
;tls_handshake_timeout_seconds = 10
# How many seconds the data proxy will wait for a server's first response headers after
# fully writing the request headers if the request has an "Expect: 100-continue"
# header. A value of 0 will result in the body being sent immediately, without
# waiting for the server to approve.
;expect_continue_timeout_seconds = 1
# The maximum number of idle connections that Grafana will keep alive.
;max_idle_connections = 100
# How many seconds the data proxy keeps an idle connection open before timing out.
;idle_conn_timeout_seconds = 90
# If enabled and user is not anonymous, data proxy will add X-Grafana-User header with username into the request, default is false.
;send_user_header = false
#################################### Analytics ####################################
[analytics]
# Server reporting, sends usage counters to stats.grafana.org every 24 hours.
# No ip addresses are being tracked, only simple counters to track
# running instances, dashboard and error counts. It is very helpful to us.
# Change this option to false to disable reporting.
;reporting_enabled = true
# Set to false to disable all checks to https://grafana.net
# for new versions (grafana itself and plugins), check is used
# in some UI views to notify that grafana or plugin update exists
# This option does not cause any auto updates, nor send any information
# only a GET request to http://grafana.com to get latest versions
;check_for_updates = true
# Google Analytics universal tracking code, only enabled if you specify an id here
;google_analytics_ua_id =
# Google Tag Manager ID, only enabled if you specify an id here
;google_tag_manager_id =
#################################### Security ####################################
[security]
# disable creation of admin user on first start of grafana
;disable_initial_admin_creation = false
# default admin user, created on startup
;admin_user = admin
# default admin password, can be changed before first start of grafana, or in profile settings
;admin_password = admin
# used for signing
;secret_key = SW2YcwTIb9zpOOhoPsMm
# disable gravatar profile images
;disable_gravatar = false
# data source proxy whitelist (ip_or_domain:port separated by spaces)
;data_source_proxy_whitelist =
# disable protection against brute force login attempts
;disable_brute_force_login_protection = false
# set to true if you host Grafana behind HTTPS. default is false.
;cookie_secure = false
# set cookie SameSite attribute. defaults to `lax`. can be set to "lax", "strict", "none" and "disabled"
;cookie_samesite = lax
# set to true if you want to allow browsers to render Grafana in a <frame>, <iframe>, <embed> or <object>. default is false.
;allow_embedding = false
# Set to true if you want to enable http strict transport security (HSTS) response header.
# This is only sent when HTTPS is enabled in this configuration.
# HSTS tells browsers that the site should only be accessed using HTTPS.
;strict_transport_security = false
# Sets how long a browser should cache HSTS. Only applied if strict_transport_security is enabled.
;strict_transport_security_max_age_seconds = 86400
# Set to true if to enable HSTS preloading option. Only applied if strict_transport_security is enabled.
;strict_transport_security_preload = false
# Set to true if to enable the HSTS includeSubDomains option. Only applied if strict_transport_security is enabled.
;strict_transport_security_subdomains = false
# Set to true to enable the X-Content-Type-Options response header.
# The X-Content-Type-Options response HTTP header is a marker used by the server to indicate that the MIME types advertised
# in the Content-Type headers should not be changed and be followed.
;x_content_type_options = true
# Set to true to enable the X-XSS-Protection header, which tells browsers to stop pages from loading
# when they detect reflected cross-site scripting (XSS) attacks.
;x_xss_protection = true
#################################### Snapshots ###########################
[snapshots]
# snapshot sharing options
;external_enabled = true
;external_snapshot_url = https://snapshots-origin.raintank.io
;external_snapshot_name = Publish to snapshot.raintank.io
# Set to true to enable this Grafana instance act as an external snapshot server and allow unauthenticated requests for
# creating and deleting snapshots.
;public_mode = false
# remove expired snapshot
;snapshot_remove_expired = true
#################################### Dashboards History ##################
[dashboards]
# Number dashboard versions to keep (per dashboard). Default: 20, Minimum: 1
;versions_to_keep = 20
# Minimum dashboard refresh interval. When set, this will restrict users to set the refresh interval of a dashboard lower than given interval. Per default this is 5 seconds.
# The interval string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
;min_refresh_interval = 5s
# Path to the default home dashboard. If this value is empty, then Grafana uses StaticRootPath + "dashboards/home.json"
;default_home_dashboard_path =
#################################### Users ###############################
[users]
# disable user signup / registration
;allow_sign_up = true
# Allow non admin users to create organizations
;allow_org_create = true
# Set to true to automatically assign new users to the default organization (id 1)
;auto_assign_org = true
# Set this value to automatically add new users to the provided organization (if auto_assign_org above is set to true)
;auto_assign_org_id = 1
# Default role new users will be automatically assigned (if disabled above is set to true)
;auto_assign_org_role = Viewer
# Require email validation before sign up completes
;verify_email_enabled = false
# Background text for the user field on the login page
;login_hint = email or username
;password_hint = password
# Default UI theme ("dark" or "light")
;default_theme = dark
# External user management, these options affect the organization users view
;external_manage_link_url =
;external_manage_link_name =
;external_manage_info =
# Viewers can edit/inspect dashboard settings in the browser. But not save the dashboard.
;viewers_can_edit = false
# Editors can administrate dashboard, folders and teams they create
;editors_can_admin = false
# The duration in time a user invitation remains valid before expiring. This setting should be expressed as a duration. Examples: 6h (hours), 2d (days), 1w (week). Default is 24h (24 hours). The minimum supported duration is 15m (15 minutes).
;user_invite_max_lifetime_duration = 24h
[auth]
# Login cookie name
;login_cookie_name = grafana_session
# The maximum lifetime (duration) an authenticated user can be inactive before being required to login at next visit. Default is 7 days (7d). This setting should be expressed as a duration, e.g. 5m (minutes), 6h (hours), 10d (days), 2w (weeks), 1M (month). The lifetime resets at each successful token rotation.
;login_maximum_inactive_lifetime_duration =
# The maximum lifetime (duration) an authenticated user can be logged in since login time before being required to login. Default is 30 days (30d). This setting should be expressed as a duration, e.g. 5m (minutes), 6h (hours), 10d (days), 2w (weeks), 1M (month).
;login_maximum_lifetime_duration =
# How often should auth tokens be rotated for authenticated users when being active. The default is each 10 minutes.
;token_rotation_interval_minutes = 10
# Set to true to disable (hide) the login form, useful if you use OAuth, defaults to false
;disable_login_form = false
# Set to true to disable the signout link in the side menu. useful if you use auth.proxy, defaults to false
;disable_signout_menu = false
# URL to redirect the user to after sign out
;signout_redirect_url =
# Set to true to attempt login with OAuth automatically, skipping the login screen.
# This setting is ignored if multiple OAuth providers are configured.
;oauth_auto_login = false
# OAuth state max age cookie duration in seconds. Defaults to 600 seconds.
;oauth_state_cookie_max_age = 600
# limit of api_key seconds to live before expiration
;api_key_max_seconds_to_live = -1
# Set to true to enable SigV4 authentication option for HTTP-based datasources.
;sigv4_auth_enabled = false
#################################### Anonymous Auth ######################
[auth.anonymous]
# enable anonymous access
;enabled = false
# specify organization name that should be used for unauthenticated users
;org_name = Main Org.
# specify role for unauthenticated users
;org_role = Viewer
# mask the Grafana version number for unauthenticated users
;hide_version = false
#################################### GitHub Auth ##########################
[auth.github]
;enabled = false
;allow_sign_up = true
;client_id = some_id
;client_secret = some_secret
;scopes = user:email,read:org
;auth_url = https://github.com/login/oauth/authorize
;token_url = https://github.com/login/oauth/access_token
;api_url = https://api.github.com/user
;allowed_domains =
;team_ids =
;allowed_organizations =
#################################### GitLab Auth #########################
[auth.gitlab]
;enabled = false
;allow_sign_up = true
;client_id = some_id
;client_secret = some_secret
;scopes = api
;auth_url = https://gitlab.com/oauth/authorize
;token_url = https://gitlab.com/oauth/token
;api_url = https://gitlab.com/api/v4
;allowed_domains =
;allowed_groups =
#################################### Google Auth ##########################
[auth.google]
;enabled = false
;allow_sign_up = true
;client_id = some_client_id
;client_secret = some_client_secret
;scopes = https://www.googleapis.com/auth/userinfo.profile https://www.googleapis.com/auth/userinfo.email
;auth_url = https://accounts.google.com/o/oauth2/auth
;token_url = https://accounts.google.com/o/oauth2/token
;api_url = https://www.googleapis.com/oauth2/v1/userinfo
;allowed_domains =
;hosted_domain =
#################################### Grafana.com Auth ####################
[auth.grafana_com]
;enabled = false
;allow_sign_up = true
;client_id = some_id
;client_secret = some_secret
;scopes = user:email
;allowed_organizations =
#################################### Azure AD OAuth #######################
[auth.azuread]
;name = Azure AD
;enabled = false
;allow_sign_up = true
;client_id = some_client_id
;client_secret = some_client_secret
;scopes = openid email profile
;auth_url = https://login.microsoftonline.com/<tenant-id>/oauth2/v2.0/authorize
;token_url = https://login.microsoftonline.com/<tenant-id>/oauth2/v2.0/token
;allowed_domains =
;allowed_groups =
#################################### Okta OAuth #######################
[auth.okta]
;name = Okta
;enabled = false
;allow_sign_up = true
;client_id = some_id
;client_secret = some_secret
;scopes = openid profile email groups
;auth_url = https://<tenant-id>.okta.com/oauth2/v1/authorize
;token_url = https://<tenant-id>.okta.com/oauth2/v1/token
;api_url = https://<tenant-id>.okta.com/oauth2/v1/userinfo
;allowed_domains =
;allowed_groups =
;role_attribute_path =
#################################### Generic OAuth ##########################
[auth.generic_oauth]
;enabled = false
;name = OAuth
;allow_sign_up = true
;client_id = some_id
;client_secret = some_secret
;scopes = user:email,read:org
;email_attribute_name = email:primary
;email_attribute_path =
;login_attribute_path =
;id_token_attribute_name =
;auth_url = https://foo.bar/login/oauth/authorize
;token_url = https://foo.bar/login/oauth/access_token
;api_url = https://foo.bar/user
;allowed_domains =
;team_ids =
;allowed_organizations =
;role_attribute_path =
;tls_skip_verify_insecure = false
;tls_client_cert =
;tls_client_key =
;tls_client_ca =
#################################### Basic Auth ##########################
[auth.basic]
;enabled = true
#################################### Auth Proxy ##########################
[auth.proxy]
;enabled = false
;header_name = X-WEBAUTH-USER
;header_property = username
;auto_sign_up = true
;sync_ttl = 60
;whitelist = 192.168.1.1, 192.168.2.1
;headers = Email:X-User-Email, Name:X-User-Name
# Read the auth proxy docs for details on what the setting below enables
;enable_login_token = false
#################################### Auth LDAP ##########################
[auth.ldap]
;enabled = false
;config_file = /etc/grafana/ldap.toml
;allow_sign_up = true
# LDAP backround sync (Enterprise only)
# At 1 am every day
;sync_cron = "0 0 1 * * *"
;active_sync_enabled = true
#################################### SMTP / Emailing ##########################
[smtp]
;enabled = false
;host = localhost:25
;user =
# If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;"""
;password =
;cert_file =
;key_file =
;skip_verify = false
;from_address = admin@grafana.localhost
;from_name = Grafana
# EHLO identity in SMTP dialog (defaults to instance_name)
;ehlo_identity = dashboard.example.com
# SMTP startTLS policy (defaults to 'OpportunisticStartTLS')
;startTLS_policy = NoStartTLS
[emails]
;welcome_email_on_sign_up = false
;templates_pattern = emails/*.html
#################################### Logging ##########################
[log]
# Either "console", "file", "syslog". Default is console and file
# Use space to separate multiple modes, e.g. "console file"
;mode = console file
# Either "debug", "info", "warn", "error", "critical", default is "info"
;level = info
# optional settings to set different levels for specific loggers. Ex filters = sqlstore:debug
;filters =
# For "console" mode only
[log.console]
;level =
# log line format, valid options are text, console and json
;format = console
# For "file" mode only
[log.file]
;level =
# log line format, valid options are text, console and json
;format = text
# This enables automated log rotate(switch of following options), default is true
;log_rotate = true
# Max line number of single file, default is 1000000
;max_lines = 1000000
# Max size shift of single file, default is 28 means 1 << 28, 256MB
;max_size_shift = 28
# Segment log daily, default is true
;daily_rotate = true
# Expired days of log file(delete after max days), default is 7
;max_days = 7
[log.syslog]
;level =
# log line format, valid options are text, console and json
;format = text
# Syslog network type and address. This can be udp, tcp, or unix. If left blank, the default unix endpoints will be used.
;network =
;address =
# Syslog facility. user, daemon and local0 through local7 are valid.
;facility =
# Syslog tag. By default, the process' argv[0] is used.
;tag =
#################################### Usage Quotas ########################
[quota]
; enabled = false
#### set quotas to -1 to make unlimited. ####
# limit number of users per Org.
; org_user = 10
# limit number of dashboards per Org.
; org_dashboard = 100
# limit number of data_sources per Org.
; org_data_source = 10
# limit number of api_keys per Org.
; org_api_key = 10
# limit number of orgs a user can create.
; user_org = 10
# Global limit of users.
; global_user = -1
# global limit of orgs.
; global_org = -1
# global limit of dashboards
; global_dashboard = -1
# global limit of api_keys
; global_api_key = -1
# global limit on number of logged in users.
; global_session = -1
#################################### Alerting ############################
[alerting]
# Disable alerting engine & UI features
;enabled = true
# Makes it possible to turn off alert rule execution but alerting UI is visible
;execute_alerts = true
# Default setting for new alert rules. Defaults to categorize error and timeouts as alerting. (alerting, keep_state)
;error_or_timeout = alerting
# Default setting for how Grafana handles nodata or null values in alerting. (alerting, no_data, keep_state, ok)
;nodata_or_nullvalues = no_data
# Alert notifications can include images, but rendering many images at the same time can overload the server
# This limit will protect the server from render overloading and make sure notifications are sent out quickly
;concurrent_render_limit = 5
# Default setting for alert calculation timeout. Default value is 30
;evaluation_timeout_seconds = 30
# Default setting for alert notification timeout. Default value is 30
;notification_timeout_seconds = 30
# Default setting for max attempts to sending alert notifications. Default value is 3
;max_attempts = 3
# Makes it possible to enforce a minimal interval between evaluations, to reduce load on the backend
;min_interval_seconds = 1
# Configures for how long alert annotations are stored. Default is 0, which keeps them forever.
# This setting should be expressed as a duration. Examples: 6h (hours), 10d (days), 2w (weeks), 1M (month).
;max_annotation_age =
# Configures max number of alert annotations that Grafana stores. Default value is 0, which keeps all alert annotations.
;max_annotations_to_keep =
#################################### Annotations #########################
[annotations.dashboard]
# Dashboard annotations means that annotations are associated with the dashboard they are created on.
# Configures how long dashboard annotations are stored. Default is 0, which keeps them forever.
# This setting should be expressed as a duration. Examples: 6h (hours), 10d (days), 2w (weeks), 1M (month).
;max_age =
# Configures max number of dashboard annotations that Grafana stores. Default value is 0, which keeps all dashboard annotations.
;max_annotations_to_keep =
[annotations.api]
# API annotations means that the annotations have been created using the API without any
# association with a dashboard.
# Configures how long Grafana stores API annotations. Default is 0, which keeps them forever.
# This setting should be expressed as a duration. Examples: 6h (hours), 10d (days), 2w (weeks), 1M (month).
;max_age =
# Configures max number of API annotations that Grafana keeps. Default value is 0, which keeps all API annotations.
;max_annotations_to_keep =
#################################### Explore #############################
[explore]
# Enable the Explore section
;enabled = true
#################################### Internal Grafana Metrics ##########################
# Metrics available at HTTP API Url /metrics
[metrics]
# Disable / Enable internal metrics
;enabled = true
# Graphite Publish interval
;interval_seconds = 10
# Disable total stats (stat_totals_*) metrics to be generated
;disable_total_stats = false
#If both are set, basic auth will be required for the metrics endpoint.
; basic_auth_username =
; basic_auth_password =
# Metrics environment info adds dimensions to the `grafana_environment_info` metric, which
# can expose more information about the Grafana instance.
[metrics.environment_info]
#exampleLabel1 = exampleValue1
#exampleLabel2 = exampleValue2
# Send internal metrics to Graphite
[metrics.graphite]
# Enable by setting the address setting (ex localhost:2003)
;address =
;prefix = prod.grafana.%(instance_name)s.
#################################### Grafana.com integration ##########################
# Url used to import dashboards directly from Grafana.com
[grafana_com]
;url = https://grafana.com
#################################### Distributed tracing ############
[tracing.jaeger]
# Enable by setting the address sending traces to jaeger (ex localhost:6831)
;address = localhost:6831
# Tag that will always be included in when creating new spans. ex (tag1:value1,tag2:value2)
;always_included_tag = tag1:value1
# Type specifies the type of the sampler: const, probabilistic, rateLimiting, or remote
;sampler_type = const
# jaeger samplerconfig param
# for "const" sampler, 0 or 1 for always false/true respectively
# for "probabilistic" sampler, a probability between 0 and 1
# for "rateLimiting" sampler, the number of spans per second
# for "remote" sampler, param is the same as for "probabilistic"
# and indicates the initial sampling rate before the actual one
# is received from the mothership
;sampler_param = 1
# sampling_server_url is the URL of a sampling manager providing a sampling strategy.
;sampling_server_url =
# Whether or not to use Zipkin propagation (x-b3- HTTP headers).
;zipkin_propagation = false
# Setting this to true disables shared RPC spans.
# Not disabling is the most common setting when using Zipkin elsewhere in your infrastructure.
;disable_shared_zipkin_spans = false
#################################### External image storage ##########################
[external_image_storage]
# Used for uploading images to public servers so they can be included in slack/email messages.
# you can choose between (s3, webdav, gcs, azure_blob, local)
;provider =
[external_image_storage.s3]
;endpoint =
;path_style_access =
;bucket =
;region =
;path =
;access_key =
;secret_key =
[external_image_storage.webdav]
;url =
;public_url =
;username =
;password =
[external_image_storage.gcs]
;key_file =
;bucket =
;path =
[external_image_storage.azure_blob]
;account_name =
;account_key =
;container_name =
[external_image_storage.local]
# does not require any configuration
[rendering]
# Options to configure a remote HTTP image rendering service, e.g. using https://github.com/grafana/grafana-image-renderer.
# URL to a remote HTTP image renderer service, e.g. http://localhost:8081/render, will enable Grafana to render panels and dashboards to PNG-images using HTTP requests to an external service.
;server_url =
# If the remote HTTP image renderer service runs on a different server than the Grafana server you may have to configure this to a URL where Grafana is reachable, e.g. http://grafana.domain/.
;callback_url =
# Concurrent render request limit affects when the /render HTTP endpoint is used. Rendering many images at the same time can overload the server,
# which this setting can help protect against by only allowing a certain amount of concurrent requests.
;concurrent_render_request_limit = 30
[panels]
# If set to true Grafana will allow script tags in text panels. Not recommended as it enable XSS vulnerabilities.
;disable_sanitize_html = false
[plugins]
;enable_alpha = false
;app_tls_skip_verify_insecure = false
# Enter a comma-separated list of plugin identifiers to identify plugins that are allowed to be loaded even if they lack a valid signature.
;allow_loading_unsigned_plugins =
;marketplace_url = https://grafana.com/grafana/plugins/
#################################### Grafana Image Renderer Plugin ##########################
[plugin.grafana-image-renderer]
# Instruct headless browser instance to use a default timezone when not provided by Grafana, e.g. when rendering panel image of alert.
# See ICU’s metaZones.txt (https://cs.chromium.org/chromium/src/third_party/icu/source/data/misc/metaZones.txt) for a list of supported
# timezone IDs. Fallbacks to TZ environment variable if not set.
;rendering_timezone =
# Instruct headless browser instance to use a default language when not provided by Grafana, e.g. when rendering panel image of alert.
# Please refer to the HTTP header Accept-Language to understand how to format this value, e.g. 'fr-CH, fr;q=0.9, en;q=0.8, de;q=0.7, *;q=0.5'.
;rendering_language =
# Instruct headless browser instance to use a default device scale factor when not provided by Grafana, e.g. when rendering panel image of alert.
# Default is 1. Using a higher value will produce more detailed images (higher DPI), but will require more disk space to store an image.
;rendering_viewport_device_scale_factor =
# Instruct headless browser instance whether to ignore HTTPS errors during navigation. Per default HTTPS errors are not ignored. Due to
# the security risk it's not recommended to ignore HTTPS errors.
;rendering_ignore_https_errors =
# Instruct headless browser instance whether to capture and log verbose information when rendering an image. Default is false and will
# only capture and log error messages. When enabled, debug messages are captured and logged as well.
# For the verbose information to be included in the Grafana server log you have to adjust the rendering log level to debug, configure
# [log].filter = rendering:debug.
;rendering_verbose_logging =
# Instruct headless browser instance whether to output its debug and error messages into running process of remote rendering service.
# Default is false. This can be useful to enable (true) when troubleshooting.
;rendering_dumpio =
# Additional arguments to pass to the headless browser instance. Default is --no-sandbox. The list of Chromium flags can be found
# here (https://peter.sh/experiments/chromium-command-line-switches/). Multiple arguments is separated with comma-character.
;rendering_args =
# You can configure the plugin to use a different browser binary instead of the pre-packaged version of Chromium.
# Please note that this is not recommended, since you may encounter problems if the installed version of Chrome/Chromium is not
# compatible with the plugin.
;rendering_chrome_bin =
# Instruct how headless browser instances are created. Default is 'default' and will create a new browser instance on each request.
# Mode 'clustered' will make sure that only a maximum of browsers/incognito pages can execute concurrently.
# Mode 'reusable' will have one browser instance and will create a new incognito page on each request.
;rendering_mode =
# When rendering_mode = clustered you can instruct how many browsers or incognito pages can execute concurrently. Default is 'browser'
# and will cluster using browser instances.
# Mode 'context' will cluster using incognito pages.
;rendering_clustering_mode =
# When rendering_mode = clustered you can define maximum number of browser instances/incognito pages that can execute concurrently..
;rendering_clustering_max_concurrency =
# Limit the maximum viewport width, height and device scale factor that can be requested.
;rendering_viewport_max_width =
;rendering_viewport_max_height =
;rendering_viewport_max_device_scale_factor =
# Change the listening host and port of the gRPC server. Default host is 127.0.0.1 and default port is 0 and will automatically assign
# a port not in use.
;grpc_host =
;grpc_port =
[enterprise]
# Path to a valid Grafana Enterprise license.jwt file
;license_path =
[feature_toggles]
# enable features, separated by spaces
;enable =
[date_formats]
# For information on what formatting patterns that are supported https://momentjs.com/docs/#/displaying/
# Default system date format used in time range picker and other places where full time is displayed
;full_date = YYYY-MM-DD HH:mm:ss
# Used by graph and other places where we only show small intervals
;interval_second = HH:mm:ss
;interval_minute = HH:mm
;interval_hour = MM/DD HH:mm
;interval_day = MM/DD
;interval_month = YYYY-MM
;interval_year = YYYY
# Experimental feature
;use_browser_locale = false
# Default timezone for user preferences. Options are 'browser' for the browser local timezone or a timezone name from IANA Time Zone database, e.g. 'UTC' or 'Europe/Amsterdam' etc.
;default_timezone = browser
script/docker/app/prometheus/config/prometheus.yml
+68
View File
@@ -0,0 +1,68 @@
# my global config
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets: ['172.30.0.99:9093']
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
- "rules/alert_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# 监控 prometheus
- job_name: 'prometheus'
static_configs:
- targets: ['172.30.0.90:9090'] #填写prometheus服务ip:端口
# 监控 linux
- job_name: linux
static_configs:
- targets: ['172.30.0.93:9100'] #填写node-exporter的docker服务ip:端口或者宿主机ip:映射的端口
labels:
instance: localhost:linux #实例名称或ip
# 监控 mysql
- job_name: 'mysql'
static_configs:
- targets: ['172.30.0.94:9104'] #填写mysqld-exporter的docker服务ip:端口或者宿主机ip:映射的端口
labels:
instance: localhost:mysql #实例名称或ip
# 监控 cadvisor
- job_name: "docker"
static_configs:
- targets: ['172.30.0.180:8080'] #填写cadvisor服务ip:端口
# 监控 nacos
- job_name: "nacos"
metrics_path: '/nacos/actuator/prometheus'
static_configs:
- targets: ['172.30.0.48:8848'] #填写nacos服务ip:端口
# 监控 bladex
- job_name: "bladex"
metrics_path: "/actuator/prometheus"
scrape_interval: 5s
consul_sd_configs:
#必须保证prometheus能调用否则不会显示
#若是docker部署必须保证网络与各服务调通
- server: '172.30.0.72:7002' #填写实现consul-api的blade-admin服务ip:端口
#匹配所有service
services: []
relabel_configs:
#service 源标签
- source_labels: [__meta_consul_service]
#匹配 "blade" 开头的service
regex: "blade*"
#执行的动作
action: drop
#将service的label重写为application
- source_labels: [__meta_consul_service]
target_label: application
- source_labels: [__meta_consul_service_address]
target_label: instance
- source_labels: [__meta_consul_tags]
target_label: job
script/docker/app/prometheus/config/wechat.tmpl
+34
View File
@@ -0,0 +1,34 @@
{{ define "wechat.default.message" }}
{{- if gt (len .Alerts.Firing) 0 -}}
{{- range $index, $alert := .Alerts -}}
{{- if eq $index 0 -}}
==========告警通知==========
告警类型: {{ $alert.Labels.alertname }}
告警状态: {{ $alert.Status }}
告警级别: {{ $alert.Labels.level }}
{{- end }}
==========告警详情==========
告警主题: {{ $alert.Annotations.summary }}
告警详情: {{ $alert.Annotations.description }}
故障时间: {{ $alert.StartsAt.Local }}
{{ if gt (len $alert.Labels.instance) 0 -}}故障实例: {{ $alert.Labels.instance }}{{- end -}}
{{- end }}
{{- end }}
{{- if gt (len .Alerts.Resolved) 0 -}}
{{- range $index, $alert := .Alerts -}}
{{- if eq $index 0 -}}
==========恢复通知==========
告警类型: {{ $alert.Labels.alertname }}
告警状态: {{ $alert.Status }}
告警级别: {{ $alert.Labels.level }}
{{- end }}
==========恢复详情==========
告警主题: {{ $alert.Annotations.summary }}
告警详情: {{ $alert.Annotations.description }}
故障时间: {{ $alert.StartsAt.Local }}
恢复时间: {{ $alert.EndsAt.Local }}
{{ if gt (len $alert.Labels.instance) 0 -}}故障实例: {{ $alert.Labels.instance }}{{- end -}}
{{- end }}
{{- end }}
{{- end }}
script/docker/app/prometheus/dashboard/bladex-docker.json
+1705
View File
File diff suppressed because it is too large Load Diff
script/docker/app/prometheus/dashboard/bladex-jvm.json
+3825
View File
File diff suppressed because it is too large Load Diff
script/docker/app/prometheus/dashboard/bladex-linux.json
+3841
View File
File diff suppressed because it is too large Load Diff
script/docker/app/prometheus/dashboard/bladex-mysql.json
+5055
View File
File diff suppressed because it is too large Load Diff
script/docker/app/prometheus/dashboard/bladex-nacos.json
+4539
View File
File diff suppressed because it is too large Load Diff
script/docker/elk/README.md
+27
View File
@@ -0,0 +1,27 @@
## 一、调整内存：max virtual memory areas vm.max_map_count [65530] is too low, increase to at least [262144]（elasticsearch用户拥有的内存权限太小，至少需要262144）
#### 1.修改配置sysctl.conf
[root@localhost ~]# vi /etc/sysctl.conf
#### 2.添加下面配置：
vm.max_map_count=262144
#### 3.重新加载：
[root@localhost ~]# sysctl -p
#### 4.最后重新启动elasticsearch，即可启动成功。
## 二、Docker 命令自动补全
#### 1.安装依赖工具bash-complete
[root@localhost ~]# yum install -y bash-completion
[root@localhost ~]# source /usr/share/bash-completion/completions/docker
[root@localhost ~]# source /usr/share/bash-completion/bash_completion
## 三、将本文件夹内的文件拷贝至服务器
#### 1.对sh脚本赋予执行权限
#### 2.执行 ./deploy.sh
#### 3.等待服务启动完毕即可
#### 4.卸载执行 ./undeploy.sh
script/docker/elk/deploy.sh
+88
View File
@@ -0,0 +1,88 @@
#./bin/bash
# 定义颜色
BLUE_COLOR="\033[36m"
RED_COLOR="\033[31m"
GREEN_COLOR="\033[32m"
VIOLET_COLOR="\033[35m"
RES="\033[0m"
echo -e "${BLUE_COLOR}# ######################################################################${RES}"
echo -e "${BLUE_COLOR}# Docker ELK Deploy Script #${RES}"
echo -e "${BLUE_COLOR}# ######################################################################${RES}"
# 创建目录
echo -e "${BLUE_COLOR}---> create [elasticsearch]directory start.${RES}"
if [ ! -d "./elasticsearch/" ]; then
mkdir -p ./elasticsearch/master/conf ./elasticsearch/master/data ./elasticsearch/master/logs \
./elasticsearch/slave1/conf ./elasticsearch/slave1/data ./elasticsearch/slave1/logs \
./elasticsearch/slave2/conf ./elasticsearch/slave2/data ./elasticsearch/slave2/logs
fi
echo -e "${RED_COLOR}---> create [kibana]directory start.${RES}"
if [ ! -d "./kibana/" ]; then
mkdir -p ./kibana/conf ./kibana/logs
fi
echo -e "${GREEN_COLOR}---> create [logstash]directory start.${RES}"
if [ ! -d "./logstash/" ]; then
mkdir -p ./logstash/conf ./logstash/logs
fi
echo -e "${GREEN_COLOR}---> create [filebeat]directory start.${RES}"
if [ ! -d "./filebeat/" ]; then
mkdir -p ./filebeat/conf ./filebeat/logs ./filebeat/data
fi
echo -e "${VIOLET_COLOR}---> create [nginx]directory start.${RES}"
if [ ! -d "./nginx/" ]; then
mkdir -p ./nginx/conf ./nginx/logs ./nginx/www
fi
echo -e "${BLUE_COLOR}===> create directory success.${RES}"
# 目录授权(data/logs 都要授读/写权限)
echo -e "${BLUE_COLOR}---> directory authorize start.${RES}"
if [ -d "./elasticsearch/" ]; then
chmod 777 ./elasticsearch/master/data/ ./elasticsearch/master/logs/ \
./elasticsearch/slave1/data/ ./elasticsearch/slave1/logs/ \
./elasticsearch/slave2/data/ ./elasticsearch/slave2/logs
fi
if [ -d "./filebeat/" ]; then
chmod 777 ./filebeat/data/ ./filebeat/logs/
fi
echo -e "${BLUE_COLOR}===> directory authorize success.${RES}"
# 移动配置文件
echo -e "${BLUE_COLOR}---> move [elasticsearch]config file start.${RES}"
if [ -f "./es-master.yml" ] && [ -f "./es-slave1.yml" ] && [ -f "./es-slave2.yml" ]; then
mv ./es-master.yml ./elasticsearch/master/conf
mv ./es-slave1.yml ./elasticsearch/slave1/conf
mv ./es-slave2.yml ./elasticsearch/slave2/conf
fi
echo -e "${RED_COLOR}---> move [kibana]config file start.${RES}"
if [ -f "./kibana.yml" ]; then
mv ./kibana.yml ./kibana/conf
fi
echo -e "${GREEN_COLOR}---> move [logstash]config file start.${RES}"
if [ -f "./logstash.yml" ] && [ -f "./logstash-filebeat.conf" ]; then
mv ./logstash-filebeat.conf ./logstash/conf
mv ./logstash.yml ./logstash/conf
fi
echo -e "${GREEN_COLOR}---> move [filebeat]config file start.${RES}"
if [ -f "./filebeat.yml" ]; then
mv ./filebeat.yml ./filebeat/conf
fi
echo -e "${VIOLET_COLOR}---> move [nginx]config file start.${RES}"
if [ -f "./nginx.conf" ]; then
mv ./nginx.conf ./nginx/conf
fi
echo -e "${BLUE_COLOR}===> move config files success.${RES}"
echo -e "${GREEN_COLOR}>>>>>>>>>>>>>>>>>> The End <<<<<<<<<<<<<<<<<<${RES}"
# 部署项目
echo -e "${BLUE_COLOR}==================> Docker deploy Start <==================${RES}"
docker-compose up --build -d
script/docker/elk/docker-compose.yml
+115
View File
@@ -0,0 +1,115 @@
version: "3"
services:
es-master:
container_name: es-master
hostname: es-master
image: elasticsearch:7.1.1
restart: always
ports:
- 9200:9200
- 9300:9300
volumes:
- ./elasticsearch/master/conf/es-master.yml:/usr/share/elasticsearch/config/elasticsearch.yml
- ./elasticsearch/master/data:/usr/share/elasticsearch/data
- ./elasticsearch/master/logs:/usr/share/elasticsearch/logs
environment:
- "ES_JAVA_OPTS=-Xms512m -Xmx512m"
es-slave1:
container_name: es-slave1
image: elasticsearch:7.1.1
restart: always
ports:
- 9201:9200
- 9301:9300
volumes:
- ./elasticsearch/slave1/conf/es-slave1.yml:/usr/share/elasticsearch/config/elasticsearch.yml
- ./elasticsearch/slave1/data:/usr/share/elasticsearch/data
- ./elasticsearch/slave1/logs:/usr/share/elasticsearch/logs
environment:
- "ES_JAVA_OPTS=-Xms512m -Xmx512m"
es-slave2:
container_name: es-slave2
image: elasticsearch:7.1.1
restart: always
ports:
- 9202:9200
- 9302:9300
volumes:
- ./elasticsearch/slave2/conf/es-slave2.yml:/usr/share/elasticsearch/config/elasticsearch.yml
- ./elasticsearch/slave2/data:/usr/share/elasticsearch/data
- ./elasticsearch/slave2/logs:/usr/share/elasticsearch/logs
environment:
- "ES_JAVA_OPTS=-Xms512m -Xmx512m"
es-head:
container_name: es-head
image: mobz/elasticsearch-head:5
restart: always
ports:
- 9100:9100
depends_on:
- es-master
- es-slave1
- es-slave2
kibana:
container_name: kibana
hostname: kibana
image: kibana:7.1.1
restart: always
ports:
- 5601:5601
volumes:
- ./kibana/conf/kibana.yml:/usr/share/kibana/config/kibana.yml
environment:
- elasticsearch.hosts=http://es-master:9200
depends_on:
- es-master
- es-slave1
- es-slave2
filebeat:
# 容器名称
container_name: filebeat
# 主机名称
hostname: filebeat
# 镜像
image: docker.elastic.co/beats/filebeat:7.1.1
# 重启机制
restart: always
# 持久化挂载
volumes:
- ./filebeat/conf/filebeat.yml:/usr/share/filebeat/filebeat.yml
# 映射到容器中[作为数据源]
- ./logs:/home/project/elk/logs
- ./filebeat/logs:/usr/share/filebeat/logs
- ./filebeat/data:/usr/share/filebeat/data
# 将指定容器连接到当前连接，可以设置别名，避免ip方式导致的容器重启动态改变的无法连接情况
links:
- logstash
ports:
- 9000:9000
# 依赖服务[可无]
depends_on:
- es-master
- es-slave1
- es-slave2
logstash:
container_name: logstash
hostname: logstash
image: logstash:7.1.1
command: logstash -f ./conf/logstash-filebeat.conf
restart: always
volumes:
# 映射到容器中
- ./logstash/conf/logstash-filebeat.conf:/usr/share/logstash/conf/logstash-filebeat.conf
- ./logstash/conf/logstash.yml:/usr/share/logstash/config/logstash.yml
ports:
- 5044:5044
depends_on:
- es-master
- es-slave1
- es-slave2
script/docker/elk/es-master.yml
+28
View File
@@ -0,0 +1,28 @@
# 集群名称
cluster.name: es-cluster
# 节点名称
node.name: es-master
# 是否可以成为master节点
node.master: true
# 是否允许该节点存储数据,默认开启
node.data: false
# 网络绑定
network.host: 0.0.0.0
# 设置对外服务的http端口
http.port: 9200
# 设置节点间交互的tcp端口
transport.port: 9300
# 集群发现
discovery.seed_hosts:
- es-master
- es-slave1
- es-slave2
# 手动指定可以成为 mater 的所有节点的 name 或者 ip，这些配置将会在第一次选举中进行计算
cluster.initial_master_nodes:
- es-master
# 支持跨域访问
http.cors.enabled: true
http.cors.allow-origin: "*"
# 安全认证
xpack.security.enabled: false
#http.cors.allow-headers: "Authorization"
script/docker/elk/es-slave1.yml
+28
View File
@@ -0,0 +1,28 @@
# 集群名称
cluster.name: es-cluster
# 节点名称
node.name: es-slave1
# 是否可以成为master节点
node.master: true
# 是否允许该节点存储数据,默认开启
node.data: true
# 网络绑定
network.host: 0.0.0.0
# 设置对外服务的http端口
http.port: 9201
# 设置节点间交互的tcp端口
#transport.port: 9301
# 集群发现
discovery.seed_hosts:
- es-master
- es-slave1
- es-slave2
# 手动指定可以成为 mater 的所有节点的 name 或者 ip，这些配置将会在第一次选举中进行计算
cluster.initial_master_nodes:
- es-master
# 支持跨域访问
http.cors.enabled: true
http.cors.allow-origin: "*"
# 安全认证
xpack.security.enabled: false
#http.cors.allow-headers: "Authorization"
script/docker/elk/es-slave2.yml
+28
View File
@@ -0,0 +1,28 @@
# 集群名称
cluster.name: es-cluster
# 节点名称
node.name: es-slave2
# 是否可以成为master节点
node.master: true
# 是否允许该节点存储数据,默认开启
node.data: true
# 网络绑定
network.host: 0.0.0.0
# 设置对外服务的http端口
http.port: 9202
# 设置节点间交互的tcp端口
#transport.port: 9302
# 集群发现
discovery.seed_hosts:
- es-master
- es-slave1
- es-slave2
# 手动指定可以成为 mater 的所有节点的 name 或者 ip，这些配置将会在第一次选举中进行计算
cluster.initial_master_nodes:
- es-master
# 支持跨域访问
http.cors.enabled: true
http.cors.allow-origin: "*"
# 安全认证
xpack.security.enabled: false
#http.cors.allow-headers: "Authorization"
script/docker/elk/filebeat.yml
+37
View File
@@ -0,0 +1,37 @@
filebeat.inputs:
- type: log
enabled: true
paths:
# 当前目录下的所有.log文件
- /home/project/elk/logs/*.log
multiline.pattern: ^\[
multiline.negate: true
multiline.match: after
- type: tcp
enabled: true
max_message_size: 10MiB
host: "0.0.0.0:9000"
filebeat.config.modules:
path: ${path.config}/modules.d/*.yml
reload.enabled: false
setup.template.settings:
index.number_of_shards: 1
setup.dashboards.enabled: false
setup.kibana:
host: "http://kibana:5601"
# 不直接传输至ES
#output.elasticsearch:
# hosts: ["http://es-master:9200"]
# index: "filebeat-%{[beat.version]}-%{+yyyy.MM.dd}"
output.logstash:
hosts: ["logstash:5044"]
processors:
- add_host_metadata: ~
- add_cloud_metadata: ~
script/docker/elk/kibana.yml
+8
View File
@@ -0,0 +1,8 @@
# 服务端口
server.port: 5601
# 服务IP
server.host: "0.0.0.0"
# ES
elasticsearch.hosts: ["http://es-master:9200"]
# 汉化
i18n.locale: "zh-CN"
script/docker/elk/logstash-filebeat.conf
+23
View File
@@ -0,0 +1,23 @@
input {
# 来源beats
beats {
# 端口
port => "5044"
}
}
# 分析、过滤插件，可以多个
filter {
grok {
match => { "message" => "%{COMBINEDAPACHELOG}"}
}
geoip {
source => "clientip"
}
}
output {
# 选择elasticsearch
elasticsearch {
hosts => ["http://es-master:9200"]
index => "%{[@metadata][beat]}-%{[@metadata][version]}-%{+YYYY.MM.dd}"
}
}
script/docker/elk/logstash.yml
+8
View File
@@ -0,0 +1,8 @@
# 服务IP
http.host: "0.0.0.0"
# ES
xpack.monitoring.elasticsearch.hosts: [ "http://es-master:9200" ]
xpack.monitoring.enabled: true
xpack.management.enabled: false
script/docker/elk/undeploy.sh
+16
View File
@@ -0,0 +1,16 @@
#./bin/bash
# 定义颜色
BLUE_COLOR="\033[36m"
RED_COLOR="\033[31m"
GREEN_COLOR="\033[32m"
VIOLET_COLOR="\033[35m"
RES="\033[0m"
echo -e "${BLUE_COLOR}# ######################################################################${RES}"
echo -e "${BLUE_COLOR}# Docker ELK UnDeploy Script #${RES}"
echo -e "${BLUE_COLOR}# ######################################################################${RES}"
# 部署项目
echo -e "${BLUE_COLOR}==================> Docker UnDeploy Start <==================${RES}"
docker-compose stop
docker-compose rm
script/docker/skywalking/docker-compose.yml
+48
View File
@@ -0,0 +1,48 @@
version: '3.3'
services:
elasticsearch:
image: docker.elastic.co/elasticsearch/elasticsearch:7.17.11
container_name: elasticsearch
restart: always
ports:
- 9200:9200
- 9300:9300
environment:
- discovery.type=single-node
- TZ=Asia/Shanghai
- bootstrap.memory_lock=true
- "ES_JAVA_OPTS=-Xms1024m -Xmx1024m"
ulimits:
memlock:
soft: -1
hard: -1
skywalking-oap:
image: docker.io/apache/skywalking-oap-server:9.5.0
container_name: skywalking-oap
depends_on:
- elasticsearch
restart: always
ports:
- 11800:11800
- 12800:12800
environment:
SW_CORE_RECORD_DATA_TTL: 15
SW_CORE_METRICS_DATA_TTL: 15
SW_STORAGE: elasticsearch
SW_STORAGE_ES_CLUSTER_NODES: elasticsearch:9200
SW_ENABLE_UPDATE_UI_TEMPLATE: "true"
TZ: Asia/Shanghai
JAVA_OPTS: "-Xms2048m -Xmx2048m"
skywalking-ui:
image: docker.io/apache/skywalking-ui:9.5.0
container_name: skywalking-ui
depends_on:
- skywalking-oap
links:
- skywalking-oap
restart: always
ports:
- 8880:8080
environment:
SW_OAP_ADDRESS: http://skywalking-oap:12800
script/fatjar/service.cmd
+1
View File
@@ -0,0 +1 @@
java -Xms1024m -Xmx1024m -jar app.jar
script/fatjar/service.sh
+76
View File
@@ -0,0 +1,76 @@
#!/bin/bash
#设置jar文件名
APP_NAME=app.jar
#使用说明，用来提示输入参数
usage() {
echo "Usage: sh 执行脚本.sh [start|stop|restart|status]"
exit 1
}
#检查程序是否在运行
is_exist(){
pid=`ps -ef|grep $APP_NAME|grep -v grep|awk '{print $2}' `
#如果不存在返回1，存在返回0
if [ -z "${pid}" ]; then
return 1
else
return 0
fi
}
#启动方法
start(){
is_exist
if [ $? -eq "0" ]; then
echo "${APP_NAME} is already running. pid=${pid} ."
else
nohup java -Xms1024m -Xmx1024m -jar $APP_NAME > /dev/null 2>&1 &
fi
}
#停止方法
stop(){
is_exist
if [ $? -eq "0" ]; then
kill -9 $pid
else
echo "${APP_NAME} is not running"
fi
}
#输出运行状态
status(){
is_exist
if [ $? -eq "0" ]; then
echo "${APP_NAME} is running. Pid is ${pid}"
else
echo "${APP_NAME} is NOT running."
fi
}
#重启
restart(){
stop
start
}
#根据输入参数，选择执行对应方法，不输入则执行使用说明
case "$1" in
"start")
start
;;
"stop")
stop
;;
"status")
status
;;
"restart")
restart
;;
*)
usage
;;
esac