download:深度解锁SpringCloud主流组件 一战解决微服务诸多难题
本课程是一门基于SpringCloud整合"猫眼"商城后台项目进行的微服务课程,从零起步到深度讲解包括Gateway,Hystrix,Ribbon,Feign等几大主流组件及其高级特性。同时还会引入微服务安全,自动化测试和Docker部署等工作中会遇到的微服务难题,并讲解产生原因和解决方案,从根本上帮助大家解决工作和面试的难题!
适合人群
想要了解微服务的同学;
对SpringCloud诸多开发高级特性感兴趣的同学;
工作、面试遇到奇葩问题无从着手的同学们
技术储备要求
熟悉Spring、SpringMVC框架基本应用
熟悉MySQL常用命令
了解基础Linux命令
ansible部署prometheus+node-exporter
简单部署prometheus监控系统
yum装置ansible
yum install ansible
ansible的hosts文件
[alertmanagers]
10.9.119.1
[prometheus]
10.9.119.1
[node-exporter]
10.9.119.1
10.9.119.2
10.9.119.3
文件层次格式如下:
prometheus
prometheus.yml
- hosts: prometheus
remote_user: root
tasks:- name: create dir
file:
path: /opt/prometheus
state: directory # 没有目录则创立 - name: copy file
unarchive:
old-src: prometheus-2.24.0.linux-amd64.tar.gz
dest: /opt/prometheus - name: create link
file:
old-src: /opt/prometheus/prometheus-2.24.0.linux-amd64
dest: /opt/prometheus/prometheus
state: link # 软链接 - name: copy service file
template:
old-src: prometheus.service.j2
dest: /usr/lib/systemd/system/prometheus.service - name: copy config yaml
template:
old-src: prometheus.yml.j2
dest: /opt/prometheus/prometheus/prometheus.yml
notify:- restart prometheus
- name: create rules dir
file:
path: /opt/prometheus/prometheus/rules
state: directory - name: copy rules yaml # node里面有特殊符号所以运用copy
copy:
old-src: node.yml
dest: /opt/prometheus/prometheus/rules/node.yml
notify: # 此动作将触发handlers- restart prometheus
- name: start prometheus
service:
name: prometheus
state: started
enabled: yes
handlers: - name: restart prometheus
service:
name: prometheus
state: restarted
prometheus.service.j2 能够运用copy模块,这里运用了template
- name: create dir
[Unit]
Description=Prometheus
Documentation=
After=network.target
[Service]
WorkingDirectory=/opt/prometheus/prometheus
ExecStart=/opt/prometheus/prometheus/prometheus
ExecReload=/bin/kill -HUP $MAINPID
ExecStop=/bin/kill -KILL $MAINPID
Type=simple
KillMode=control-group
Restart=on-failure
RestartSec=3s
[Install]
WantedBy=multi-user.target
prometheus.yml.j2
全局配置
global:
scrape_interval: 30s #抓取距离时间
evaluation_interval: 30s #规则引擎执行距离时间
query_log_file: ./promql.log
告警配置
alerting:
alertmanagers: # Alertmanagers配置
- static_configs: # Alertmanager静态配置
- targets: # alertmanager发送目的配置
{% for alertmanager in groups[‘alertmanagers’] %}- {{ alertmanager }}:9093
{% endfor %}
rule_files: # 规则文件配置
- {{ alertmanager }}:9093
- targets: # alertmanager发送目的配置
- “rules/*.yml”
scrape_configs: # 抓取配置 - job_name: ‘prometheus’ #任务 采集目的分类
static_configs: # 抓取目的静态配置- targets:
{% for prometheu in groups[‘prometheus’] %}- “{{ prometheu }}:9090” #抓取目的
{% endfor %}
- “{{ prometheu }}:9090” #抓取目的
- targets:
- job_name: “node”
static_configs:- targets:
{% for node in groups[‘node-exporter’] %}- “{{ node }}:9100”
{% endfor %}
node-rules规则文件node.yml
- “{{ node }}:9100”
- targets:
groups:
-
name: node.rules # 报警规则组称号
rules:- alert: node is Down
expr: up == 0
for: 30s #持续时间,表示持续30秒获取不到信息,则触发报警
labels:
severity: serious # 自定义标签 严重的
annotations:
summary: “Instance {{ $labels.instance }} down” # 自定义摘要
description: “{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes.” # 自定义详细描绘 - alert: node Filesystem
expr: 100 - (node_filesystem_free_bytes{fstype=~“ext4|xfs”} / node_filesystem_size_bytes{fstype=~“ext4|xfs”} * 100) > 80
for: 2m
labels:
severity: warning
annotations:
summary: “{{KaTeX parse error: Expected 'EOF', got '}' at position 16: labels.instance}̲}: {{labels.mountpoint }} 分区运用过高”
description: “{{KaTeX parse error: Expected 'EOF', got '}' at position 16: labels.instance}̲}: {{labels.mountpoint }} 分区运用大于 80% (当前值: {{ $value }})” - alert: node Memory
expr: 100 - (node_memory_MemFree_bytes+node_memory_Cached_bytes+node_memory_Buffers_bytes) / node_memory_MemTotal_bytes * 100 > 80
for: 2m
labels:
severity: warning
annotations:
summary: “{{KaTeX parse error: Expected 'EOF', got '}' at position 16: labels.instance}̲}: 内存运用过高" de…labels.instance}}: 内存运用大于 80% (当前值: {{ $value }})” - alert: node CPU
expr: 100 - (avg(irate(node_cpu_seconds_total{mode=“idle”}[5m])) by (instance) * 100) > 80
for: 2m
labels:
severity: warning
annotations:
summary: “{{KaTeX parse error: Expected 'EOF', got '}' at position 16: labels.instance}̲}: CPU运用过高" d…labels.instance}}: CPU运用大于 80% (当前值: {{ $value }})”
node-exporter
node-exporter.yml
- alert: node is Down
-
hosts: node-exporter
remote_user: root
tasks:- name: create dir
file:
path: /opt/prometheus
state: directory - name: copy file
unarchive:
old-src: node_exporter-1.0.1.linux-amd64.tar.gz
dest: /opt/prometheus - name: create link
file:
old-src: /opt/prometheus/node_exporter-1.0.1.linux-amd64
dest: /opt/prometheus/node_exporter
state: link - name: copy service file
template:
old-src: node_exporter.service.j2
dest: /usr/lib/systemd/system/node_exporter.service - name: start node_exporter
service:
name: node_exporter
state: restarted
enabled: yes
node_exporter.service.j2
- name: create dir
[Unit]
Description=Node Exporter
Documentation=
After=network.target
[Service]
WorkingDirectory=/opt/prometheus/node_exporter/
ExecStart=/opt/prometheus/node_exporter/node_exporter
ExecStop=/bin/kill -KILL $MAINPID
Type=simple
KillMode=control-group
Restart=on-failure
RestartSec=3s
[Install]
WantedBy=multi-user.target
alertmanager
alertmanager.yaml
- hosts: alertmanagers
remote_user: root
tasks:- name: create dir
file:
path: /opt/prometheus
state: directory - name: copy file
unarchive:
old-src: alertmanager-0.21.0.linux-amd64.tar.gz
dest: /opt/prometheus - name: create link
file:
old-src: /opt/prometheus/alertmanager-0.21.0.linux-amd64
dest: /opt/prometheus/alertmanager
state: link - name: copy service file
template:
old-src: alertmanager.service.j2
dest: /usr/lib/systemd/system/alertmanager.service - name: copy config yaml
template:
old-src: alertmanager.yml.j2
dest: /opt/prometheus/alertmanager/alertmanager.yml
notify:- restart alertmanager
- name: start server
service:
name: alertmanager
state: restarted
enabled: yes
handlers: - name: restart alertmanager
service:
name: alertmanager
state: restarted
alertmanager.service.j2
- name: create dir
[Unit]
Description=AlertManager
Documentation=
After=network.target
[Service]
WorkingDirectory=/opt/prometheus/alertmanager/
ExecStart=/opt/prometheus/alertmanager/alertmanager
ExecReload=/bin/kill -HUP $MAINPID
ExecStop=/bin/kill -KILL $MAINPID
Type=simple
KillMode=control-group
Restart=on-failure
RestartSec=3s
[Install]
WantedBy=multi-user.target
alertmanager.yml.j2 这里运用了邮箱告警
global:
resolve_timeout: 5m # 当告警的状态有firing变为resolve的以后还要呆多长时间,才宣公告警解除。
smtp_from: “123456789@qq.com”
smtp_smarthost: ‘smtp.qq.com:465’
smtp_auth_username: “123456789@qq.com” # 邮箱账号
smtp_auth_password: “bcvizcgqbgojjjeb” # 口令密码,非QQ密码
smtp_require_tls: false # 运用465端口,这里选false
route:
group_by: [‘alertname’] # 采用哪个标签作为分组的根据
group_wait: 10s # 分组等候的时间10s
group_interval: 10s # 上下两组发送告警的距离时间10s
repeat_interval: 24h # 反复发送告警时间。默许1h 不会反复发送相同告警 静默
receiver: ‘default-receiver’ # 默许接纳人
一切不匹配以下子路由的告警都将保存在根节点,并发送到’default-receiver’
routes: # 分组
- receiver: ‘db’
group_wait: 10s
match_re:运用正则匹配告警包含两个效劳,发送到db
service: mysql|redis #一切service=mysql或者service=redis的告警分配到db接纳端 - receiver: ‘web’
group_by: [product, environment] # 采用product和environment标签作为分组的根据
match:
team: frontend # 一切告警标签带有frontend发送到web
receivers: - name: ‘default-receiver’
email_configs:- to: ‘123456789@qq.com’ # 告警收件人
- name: ‘db’
# 经过邮箱发送报警
email_configs:
- to: ‘111111111@qq.com’ - name: ‘web’
email_configs:
- to: ‘222222222@qq.com’
inhibit_rules: # 抑止,但两个都报警了,级别严重的会抑止级别正告的,只发作严重级别的告警- source_match:
severity: ‘critical’ # critaical的报警会抑止warning级别的报警信息
target_match:
severity: ‘warning’
equal: [‘alertname’, ‘dev’, ‘instance’]
- source_match: