update site at 20240408-211317, machine LiaoSirui-MacMini.local

监控/PrometheusStack/采集客户端/node-exporter/常用告警.md

@@ -0,0 +1,118 @@
+```yaml
+[root@gtcq-gt-monitor-prometheus-01 rules]# more    gt-dwz-monitor.rules
+groups:
+- name: dwz-gt-monitor
+  rules:
+  - alert: "node-Agent告警"
+    expr: up{job="gt-dwz-node-exporter"} == 0
+    for: 120s
+    labels:
+      severity: "重要"
+      team: dwz-gt-monitor
+      alert_type: "Agent告警" 
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ $labels.instance }} 已停止采集监控数据 30s！"
+      description: "{{ $labels.instance }} job {{ $labels.job }} 暴露监控数据已停止."
+
+  - alert: "CPU使用率监控"
+    expr: ceil(100 - sum(increase(node_cpu_seconds_total{job="gt-dwz-node-exporter",mode="idle"}[5m]))  by(instance) / sum(increase(node_cpu_seconds_total{job="gt-dwz-node-exporter"}[5m])) 
+ by(instance)*100) > 80
+    for: 2m
+    labels:
+      severity: "重要"
+      team: bdfb
+      alert_type: "CPU告警"
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} CPU使用率过高"
+      description: "IP:{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}的CPU使用大于80% (当前值: {{ $value }})"
+
+  - alert: "磁盘使用率监控"
+    expr: round((1 - (node_filesystem_avail_bytes{fstype=~"ext3|ext4|xfs|nfs",job="gt-dwz-node-exporter"} / node_filesystem_size_bytes{fstype=~"ext3|ext4|xfs|nfs",job="gt-dwz-node-exporter"
+})) * 100)  > 80
+    for: 2m
+    labels:
+      severity: "重要"
+      team: dwz-gt-monitor
+      alert_type: "Disk告警"
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} : {{ $labels.mountpoint }} 分区使用率过高"
+      description: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}的{{ $labels.mountpoint }} 分区使用大于80% (当前值: {{ $value }}%)"
+
+  - alert: "内存使用率监控"
+    expr: ceil( (1 - (node_memory_MemAvailable_bytes{job="gt-dwz-node-exporter"} / (node_memory_MemTotal_bytes{job="gt-dwz-node-exporter"})))* 100 ) > 80
+    for: 2m
+    labels:
+      severity: "重要"
+      team: dwz-gt-monitor
+      alert_type: "MEM告警"
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}内存使用率过高"
+      description: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}内存使用大于80% (当前值: {{ $value }})"
+
+  - alert: "服务器大法宝CPULoad5"
+    expr: node_load5{job="gt-dwz-node-exporter"} > 100
+    for: 2m
+    labels:
+      severity: "重要"
+      team: dwz-gt-monitor
+      alert_type: "负载告警"
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}CPU负载过高"
+      description: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} CPU负载load大于100 (当前值: {{ $value }})"
+
+  - alert: "服务器文件句柄监控"
+    expr: node_filefd_allocated{job="gt-dwz-node-exporter"} > 50000
+    for: 2m
+    labels:
+      severity: "重要"
+      team: dwz-gt-monitor
+      alert_type: "文件句柄告警"
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} 文件句柄使用过高"
+      description: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} 文件句柄使用过高大于50000 (当前值: {{ $value }})"
+
+  - alert: "服务器TCP连接数监控"
+    expr: node_sockstat_TCP_tw{job="gt-dwz-node-exporter"} > 15000
+    for: 2m
+    labels:
+      severity: "重要"
+      team: dwz-gt-monitor
+      alert_type: "TCP连接数告警"
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} 等待关闭的TCP连接数过高"
+      description: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} 等待关闭的TCP连接数TIME_WAIT过高大于15000 (当前值: {{ $value }})"
+
+  - alert: "服务器入口流量监控"
+    expr: round((sum by (instance)  (irate(node_network_receive_bytes_total{job="gt-dwz-node-exporter",device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])))/1024/1024) > 50
+    for: 2m
+    labels:
+      severity: "重要"
+      team: dwz-gt-monitor
+      alert_type: "流量告警"
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}监控入口流量过高"
+      description: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} 监控入口流量过高过高大于50MB (告警值: {{ $value }}MB)"
+
+  - alert: "服务器出口流量监控"
+    expr: round((sum by (instance)  (irate(node_network_transmit_bytes_total{job="gt-dwz-node-exporter",device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])))/1024/1024) > 50
+    for: 2m
+    labels:
+      severity: "重要"
+      team: dwz-gt-monitor
+      alert_type: "流量告警"
+      alert_host: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }}"
+    annotations:
+      summary: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} 监控出口流量过高"
+      description: "{{ reReplaceAll \":(.*)\" \"\" $labels.instance }} 监控出口流量过高过高大于50MB (告警值: {{ $value }}MB)"
+[root@gtcq-gt-monitor-prometheus-01 rules]# 
+
+```
+

运维研发/项目管理与团队协作/Jira/Jira基础概念/自定义字段和界面.md

@@ -11,4 +11,5 @@
 
 ## 配置字段和状态
 
-## 添加自定义问题类型
+## 添加自定义问题类型
+

运维研发/项目管理与团队协作/Jira/Jira基础概念/配置工作流.md

@@ -10,4 +10,6 @@
 - 条件 – 检查用户是否应该执行转换
 - 验证程序 – 在执行转换之前，检查转换的任何输入（例如，用户的输入）是否有效
 - 后期功能 – 执行转换之后，执行其他处理操作
-- 属性 – 可用于进一步自定义转换的键值对
+- 属性 – 可用于进一步自定义转换的键值对
+
+需要针对不同的Issue类型制定不同的工作流，也就是绘制工作流状态转换图 。方框代表状态，箭头代表转换动作，其中黑色方框代表初始态，蓝色方框代表过程态，绿色方框代表终结态

运维研发/项目管理与团队协作/Jira/Jira实战/内部工单系统-IT资产.md

@@ -0,0 +1,43 @@
+## 上架机器流程
+
+提交工单的基础信息：
+
+- 需要开通的网络关系
+- 是否申请 sudo 权限
+- 机器连接方式：jumpserver 或者 ssh
+- 是否需要测试
+
+```mermaid
+sequenceDiagram
+actor OPSM as 运维负责人
+actor OPS as 上架负责人
+actor OPSMK as 监控工程师(k8s)
+actor OPSJ as JumpServer负责人
+actor OPSN as 网络工程师
+participant E as 流程结束
+OPSM->>OPSJ: 添加远程
+OPSJ->>OPSM: 返回远程信息并分配权限
+OPSM->>OPS: 提交申请并手动指派上架人员
+OPS->>OPS: 进行上架处理步骤，详见上架文档
+OPS->>OPSMK: 添加监控
+OPSMK->>OPS: 返回监控配置并等待确认
+OPS->>OPSN: 提交网络配置信息
+OPSN->>OPS: 返回上架网络信息并等待确认
+OPS->>OPSM: 返回上架信息并等待确认
+OPS->>E: 确认后结束流程
+```
+
+
+
+## 下架机器流程
+
+```mermaid
+sequenceDiagram
+actor REQ as 申请人
+actor OPSM as 运维负责人
+actor OPSN as 网络工程师
+actor OPSN as 网络工程师
+participant E as 流程结束
+
+```
+

运维研发/项目管理与团队协作/Jira/Jira简介.md

@@ -26,6 +26,8 @@ Jira 是 Atlassian 公司出品的项目与事务跟踪工具，被广泛应用
 - 界面（提交的部分）
 - 字段（记录问题信息）
 
+![image-20240408112825678](./.assets/Jira简介/image-20240408112825678.png)
+
 ![img](./.assets/Jira简介/fields_diagram.png)
 
 通过自定义字段、界面和方案，可以充分利用 JIRA 系统的全部功能，并确保 Jira 的用户高效地工作
@@ -40,4 +42,8 @@ Jira 是 Atlassian 公司出品的项目与事务跟踪工具，被广泛应用
 
 - Jira 使用：<https://www.yiibai.com/jira/jira-introduction.html>
 
-- <https://doc.devpod.cn/jira/jira-15237264.html>
+- <https://doc.devpod.cn/jira/jira-15237264.html>
+
+- <https://blog.csdn.net/Nicolege678/article/details/124605511>
+
+- <https://blog.csdn.net/qq_41386332/article/details/108658431>