fix: postgres bool int

* add mute preview and an option to delete these active alerts(del_alert_cur:true)


---------

Co-authored-by: shardingHe <wangzihe@flashcat.cloud>
Co-authored-by: Yening Qin <710leo@gmail.com>

.gitignore

@@ -31,6 +31,9 @@ _test
 /etc/*.local.yml
 /etc/*.local.conf
 /etc/plugins/*.local.yml
+/etc/script/rules.yaml
+/etc/script/alert-rules.json
+/etc/script/record-rules.json
 /data*
 /tarball
 /run
@@ -43,6 +46,7 @@ _test
 /docker/mysqldata
 /docker/experience_pg_vm/pgdata
 /etc.local*
+/front/statik/statik.go
 
 .alerts
 .idea

.goreleaser.yaml

@@ -15,7 +15,8 @@ builds:
   - id: build
     hooks:
       pre:
-       - ./fe.sh
+      - cmd: sh -x ./fe.sh
+        output: true
     main: ./cmd/center/
     binary: n9e
     env:
@@ -41,22 +42,9 @@ builds:
     ldflags:
       - -s -w
       - -X github.com/ccfos/nightingale/v6/pkg/version.Version={{ .Tag }}-{{.Commit}}
-  - id: build-alert
-    main: ./cmd/alert/
-    binary: n9e-alert
-    env:
-      - CGO_ENABLED=0
-    goos:
-      - linux
-    goarch:
-      - amd64
-      - arm64
-    ldflags:
-      - -s -w
-      - -X github.com/ccfos/nightingale/v6/pkg/version.Version={{ .Tag }}-{{.Commit}}
-  - id: build-pushgw
-    main: ./cmd/pushgw/
-    binary: n9e-pushgw
+  - id: build-edge
+    main: ./cmd/edge/
+    binary: n9e-edge
     env:
       - CGO_ENABLED=0
     goos:
@@ -73,8 +61,7 @@ archives:
     builds:
       - build
       - build-cli
-      - build-alert
-      - build-pushgw
+      - build-edge
     format: tar.gz
     format_overrides:
       - goos: windows
@@ -84,7 +71,6 @@ archives:
     files:
       - docker/*
       - etc/*
-      - pub/*
       - integrations/*
       - cli/*
       - n9e.sql
@@ -104,7 +90,6 @@ dockers:
       - build
     dockerfile: docker/Dockerfile.goreleaser
     extra_files:
-      - pub
       - etc
       - integrations
     use: buildx
@@ -118,7 +103,6 @@ dockers:
       - build
     dockerfile: docker/Dockerfile.goreleaser.arm64
     extra_files:
-      - pub
       - etc
       - integrations
     use: buildx

Makefile

@@ -1,4 +1,4 @@
-.PHONY: prebuild start build
+.PHONY: prebuild build
 
 ROOT:=$(shell pwd -P)
 GIT_COMMIT:=$(shell git --work-tree ${ROOT}  rev-parse 'HEAD^{commit}')
@@ -6,16 +6,19 @@ _GIT_VERSION:=$(shell git --work-tree ${ROOT} describe --tags --abbrev=14 "${GIT
 TAG=$(shell echo "${_GIT_VERSION}" |  awk -F"-" '{print $$1}')
 RELEASE_VERSION:="$(TAG)-$(GIT_COMMIT)"
 
+all: prebuild build
+
 prebuild:
 	echo "begin download and embed the front-end file..."
 	sh fe.sh
 	echo "front-end file download and embedding completed."
 
-all: build
-
 build:
 	go build -ldflags "-w -s -X github.com/ccfos/nightingale/v6/pkg/version.Version=$(RELEASE_VERSION)" -o n9e ./cmd/center/main.go
 
+build-edge:
+	go build -ldflags "-w -s -X github.com/ccfos/nightingale/v6/pkg/version.Version=$(RELEASE_VERSION)" -o n9e-edge ./cmd/edge/
+
 build-alert:
 	go build -ldflags "-w -s -X github.com/ccfos/nightingale/v6/pkg/version.Version=$(RELEASE_VERSION)" -o n9e-alert ./cmd/alert/main.go
 
@@ -28,10 +31,10 @@ build-cli:
 run:
 	nohup ./n9e > n9e.log 2>&1 &
 
-run_alert:
+run-alert:
 	nohup ./n9e-alert > n9e-alert.log 2>&1 &
 
-run_pushgw:
+run-pushgw:
 	nohup ./n9e-pushgw > n9e-pushgw.log 2>&1 &
 
 release:

README.md

@@ -20,36 +20,77 @@
 <img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"/>
 </p>
 <p align="center">
-  告警管理专家，一体化开源观测平台！
+  An open-source cloud-native monitoring system that is <b>all-in-one</b> <br/>
+  <b>Out-of-the-box</b>, it integrates data collection, visualization, and monitoring alert <br/>
+  We recommend upgrading your <b>Prometheus + AlertManager + Grafana</b> combination to Nightingale!
 </p>
 
-[English](./README_en.md) | [中文](./README.md)
+[English](./README.md) | [中文](./README_zh.md)
 
-## 资料
 
-- 文档：[https://flashcat.cloud/docs/](https://flashcat.cloud/docs/)
-- 论坛提问：[https://answer.flashcat.cloud/](https://answer.flashcat.cloud/)
-- 报Bug：[https://github.com/ccfos/nightingale/issues](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&projects=&template=bug_report.yml)
-- 商业版本：[企业版](https://mp.weixin.qq.com/s/FOwnnGPkRao2ZDV574EHrw) | [专业版](https://mp.weixin.qq.com/s/uM2a8QUDJEYwdBpjkbQDxA) 感兴趣请 [联系我们交流试用](https://flashcat.cloud/contact/)
+## Highlighted Features
 
-## 功能和特点
+- **Out-of-the-box**
+  - Supports multiple deployment methods such as **Docker, Helm Chart, and cloud services**, integrates data collection, monitoring, and alerting into one system, and comes with various monitoring dashboards, quick views, and alert rule templates. **It greatly reduces the construction cost, learning cost, and usage cost of cloud-native monitoring systems**.
+- **Professional Alerting**
+  - Provides visual alert configuration and management, supports various alert rules, offers the ability to configure silence and subscription rules, supports multiple alert delivery channels, and has features such as alert self-healing and event management.
+- **Cloud-Native**
+  - Quickly builds an enterprise-level cloud-native monitoring system through a turnkey approach, supports multiple collectors such as [Categraf](https://github.com/flashcatcloud/categraf), Telegraf, and Grafana-agent, supports multiple data sources such as Prometheus, VictoriaMetrics, M3DB, ElasticSearch, and Jaeger, and is compatible with importing Grafana dashboards. **It seamlessly integrates with the cloud-native ecosystem**.
+- **High Performance and High Availability**
+  - Due to the multi-data-source management engine of Nightingale and its excellent architecture design, and utilizing a high-performance time-series database, it can handle data collection, storage, and alert analysis scenarios with billions of time-series data, saving a lot of costs.
+  - Nightingale components can be horizontally scaled with no single point of failure. It has been deployed in thousands of enterprises and tested in harsh production practices. Many leading Internet companies have used Nightingale for cluster machines with hundreds of nodes, processing billions of time-series data.
+- **Flexible Extension and Centralized Management**
+  - Nightingale can be deployed on a 1-core 1G cloud host, deployed in a cluster of hundreds of machines, or run in Kubernetes. Time-series databases, alert engines, and other components can also be decentralized to various data centers and regions, balancing edge deployment with centralized management. **It solves the problem of data fragmentation and lack of unified views**.
 
-- **统一接入各种时序库**：支持对接 Prometheus、VictoriaMetrics、Thanos、Mimir、M3DB 等多种时序库，实现统一告警管理
-- **专业告警能力**：内置支持多种告警规则，可以扩展支持所有通知媒介，支持告警屏蔽、告警抑制、告警自愈、告警事件管理
-- **无缝搭配 [FlashDuty](https://flashcat.cloud/product/flashcat-duty/)**：实现告警聚合收敛、认领、升级、排班、IM集成，确保告警处理不遗漏，减少打扰，更好协同
-- **支持所有常见采集器**：支持 categraf、telegraf、grafana-agent、datadog-agent、给类 exporter 作为采集器，没有什么数据是不能监控的
-- **统一的观测平台**：从 v6 版本开始，支持接入 ElasticSearch、Jaeger 数据源，逐步实现日志、链路、指标的一体化观测
 
-## 产品示意图
+#### If you are using Prometheus and have one or more of the following requirement scenarios, it is recommended that you upgrade to Nightingale:
+
+- Multiple systems such as Prometheus, Alertmanager, Grafana, etc. are fragmented and lack a unified view and cannot be used out of the box;
+- The way to manage Prometheus and Alertmanager by modifying configuration files has a big learning curve and is difficult to collaborate;
+- Too much data to scale-up your Prometheus cluster;
+- Multiple Prometheus clusters running in production environments, which faced high management and usage costs;
+
+#### If you are using Zabbix and have the following scenarios, it is recommended that you upgrade to Nightingale:
+
+- Monitoring too much data and wanting a better scalable solution;
+- A high learning curve and a desire for better efficiency of collaborative use in a multi-person, multi-team model;
+- Microservice and cloud-native architectures with variable monitoring data lifecycles and high monitoring data dimension bases, which are not easily adaptable to the Zabbix data model;
+
+
+#### If you are using [open-falcon](https://github.com/open-falcon/falcon-plus), we recommend you to upgrade to Nightingale：
+- For more information about open-falcon and Nightingale, please refer to read [Ten features and trends of cloud-native monitoring](https://mp.weixin.qq.com/s?__biz=MzkzNjI5OTM5Nw==&mid=2247483738&idx=1&sn=e8bdbb974a2cd003c1abcc2b5405dd18&chksm=c2a19fb0f5d616a63185cd79277a79a6b80118ef2185890d0683d2bb20451bd9303c78d083c5#rd)。
+
+## Getting Started
+
+[https://n9e.github.io/](https://n9e.github.io/)
+
+## Screenshots
 
 https://user-images.githubusercontent.com/792850/216888712-2565fcea-9df5-47bd-a49e-d60af9bd76e8.mp4
 
+## Architecture
 
-## 加入交流群
+<img src="doc/img/arch-product.png" width="600">
 
-欢迎加入 QQ 交流群，群号：479290895，也可以扫下方二维码加入微信交流群：
+Nightingale monitoring can receive monitoring data reported by various collectors (such as [Categraf](https://github.com/flashcatcloud/categraf) , telegraf, grafana-agent, Prometheus, etc.) and write them to various popular time-series databases (such as Prometheus, M3DB, VictoriaMetrics, Thanos, TDEngine, etc.). It provides configuration capabilities for alert rules, silence rules, and subscription rules, as well as the ability to view monitoring data. It also provides automatic alarm self-healing mechanisms (such as automatically calling back to a webhook address or executing a script after an alarm is triggered), and the ability to store and manage historical alarm events and view them in groups.
 
-<img src="doc/img/wecom.png" width="240">
+If the performance of a standalone time-series database (such as Prometheus) has bottlenecks or poor disaster recovery, we recommend using [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics). The VictoriaMetrics architecture is relatively simple, has excellent performance, and is easy to deploy and maintain. The architecture diagram is as shown above. For more detailed documentation on VictoriaMetrics, please refer to its [official website](https://victoriametrics.com/).
+
+**We welcome you to participate in the Nightingale open-source project and community in various ways, including but not limited to**：
+- Adding and improving documentation => [n9e.github.io](https://n9e.github.io/)
+- Sharing your best practices and experience in using Nightingale monitoring => [Article sharing]((https://n9e.github.io/docs/prologue/share/))
+- Submitting product suggestions => [github issue](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Ffeature&template=enhancement.md)
+- Submitting code to make Nightingale monitoring faster, more stable, and easier to use => [github pull request](https://github.com/didi/nightingale/pulls)
+
+
+**Respecting, recognizing, and recording the work of every contributor** is the first guiding principle of the Nightingale open-source community. We advocate effective questioning, which not only respects the developer's time but also contributes to the accumulation of knowledge in the entire community
+- Before asking a question, please first refer to the [FAQ](https://www.gitlink.org.cn/ccfos/nightingale/wiki/faq) 
+- We use [GitHub Discussions](https://github.com/ccfos/nightingale/discussions) as the communication forum. You can search and ask questions here.
+- We also recommend that you join ours [Slack channel](https://n9e-talk.slack.com/) to exchange experiences with other Nightingale users.
+
+
+## Who is using Nightingale
+You can register your usage and share your experience by posting on **[Who is Using Nightingale](https://github.com/ccfos/nightingale/issues/897)**.
 
 ## Stargazers over time
 [![Stargazers over time](https://starchart.cc/ccfos/nightingale.svg)](https://starchart.cc/ccfos/nightingale)
@@ -60,9 +101,4 @@ https://user-images.githubusercontent.com/792850/216888712-2565fcea-9df5-47bd-a4
 </a>
 
 ## License
-[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)
-
-## 社区管理
-
-[夜莺开源项目和社区治理架构（草案）](./doc/community-governance.md)
-
+[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)

README_en.md

@@ -1,104 +0,0 @@
-<p align="center">
-  <a href="https://github.com/ccfos/nightingale">
-    <img src="doc/img/nightingale_logo_h.png" alt="nightingale - cloud native monitoring" width="240" /></a>
-</p>
-
-<p align="center">
-<img alt="GitHub latest release" src="https://img.shields.io/github/v/release/ccfos/nightingale"/>
-<a href="https://n9e.github.io">
-  <img alt="Docs" src="https://img.shields.io/badge/docs-get%20started-brightgreen"/></a>
-<a href="https://hub.docker.com/u/flashcatcloud">
-  <img alt="Docker pulls" src="https://img.shields.io/docker/pulls/flashcatcloud/nightingale"/></a>
-<img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/ccfos/nightingale">
-<img alt="GitHub Repo issues" src="https://img.shields.io/github/issues/ccfos/nightingale">
-<img alt="GitHub Repo issues closed" src="https://img.shields.io/github/issues-closed/ccfos/nightingale">
-<img alt="GitHub forks" src="https://img.shields.io/github/forks/ccfos/nightingale">
-<a href="https://github.com/ccfos/nightingale/graphs/contributors">
-  <img alt="GitHub contributors" src="https://img.shields.io/github/contributors-anon/ccfos/nightingale"/></a>
-<a href="https://n9e-talk.slack.com/">
-  <img alt="GitHub contributors" src="https://img.shields.io/badge/join%20slack-%23n9e-brightgreen.svg"/></a>
-<img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"/>
-</p>
-<p align="center">
-  An open-source cloud-native monitoring system that is <b>all-in-one</b> <br/>
-  <b>Out-of-the-box</b>, it integrates data collection, visualization, and monitoring alert <br/>
-  We recommend upgrading your <b>Prometheus + AlertManager + Grafana</b> combination to Nightingale!
-</p>
-
-[English](./README.md) | [中文](./README_ZH.md)
-
-
-## Highlighted Features
-
-- **Out-of-the-box**
-  - Supports multiple deployment methods such as **Docker, Helm Chart, and cloud services**, integrates data collection, monitoring, and alerting into one system, and comes with various monitoring dashboards, quick views, and alert rule templates. **It greatly reduces the construction cost, learning cost, and usage cost of cloud-native monitoring systems**.
-- **Professional Alerting**
-  - Provides visual alert configuration and management, supports various alert rules, offers the ability to configure silence and subscription rules, supports multiple alert delivery channels, and has features such as alert self-healing and event management.
-- **Cloud-Native**
-  - Quickly builds an enterprise-level cloud-native monitoring system through a turnkey approach, supports multiple collectors such as [Categraf](https://github.com/flashcatcloud/categraf), Telegraf, and Grafana-agent, supports multiple data sources such as Prometheus, VictoriaMetrics, M3DB, ElasticSearch, and Jaeger, and is compatible with importing Grafana dashboards. **It seamlessly integrates with the cloud-native ecosystem**.
-- **High Performance and High Availability**
-  - Due to the multi-data-source management engine of Nightingale and its excellent architecture design, and utilizing a high-performance time-series database, it can handle data collection, storage, and alert analysis scenarios with billions of time-series data, saving a lot of costs.
-  - Nightingale components can be horizontally scaled with no single point of failure. It has been deployed in thousands of enterprises and tested in harsh production practices. Many leading Internet companies have used Nightingale for cluster machines with hundreds of nodes, processing billions of time-series data.
-- **Flexible Extension and Centralized Management**
-  - Nightingale can be deployed on a 1-core 1G cloud host, deployed in a cluster of hundreds of machines, or run in Kubernetes. Time-series databases, alert engines, and other components can also be decentralized to various data centers and regions, balancing edge deployment with centralized management. **It solves the problem of data fragmentation and lack of unified views**.
-
-
-#### If you are using Prometheus and have one or more of the following requirement scenarios, it is recommended that you upgrade to Nightingale:
-
-- Multiple systems such as Prometheus, Alertmanager, Grafana, etc. are fragmented and lack a unified view and cannot be used out of the box;
-- The way to manage Prometheus and Alertmanager by modifying configuration files has a big learning curve and is difficult to collaborate;
-- Too much data to scale-up your Prometheus cluster;
-- Multiple Prometheus clusters running in production environments, which faced high management and usage costs;
-
-#### If you are using Zabbix and have the following scenarios, it is recommended that you upgrade to Nightingale:
-
-- Monitoring too much data and wanting a better scalable solution;
-- A high learning curve and a desire for better efficiency of collaborative use in a multi-person, multi-team model;
-- Microservice and cloud-native architectures with variable monitoring data lifecycles and high monitoring data dimension bases, which are not easily adaptable to the Zabbix data model;
-
-
-#### If you are using [open-falcon](https://github.com/open-falcon/falcon-plus), we recommend you to upgrade to Nightingale：
-- For more information about open-falcon and Nightingale, please refer to read [Ten features and trends of cloud-native monitoring](https://mp.weixin.qq.com/s?__biz=MzkzNjI5OTM5Nw==&mid=2247483738&idx=1&sn=e8bdbb974a2cd003c1abcc2b5405dd18&chksm=c2a19fb0f5d616a63185cd79277a79a6b80118ef2185890d0683d2bb20451bd9303c78d083c5#rd)。
-
-## Getting Started
-
-[English Doc](https://n9e.github.io/) |  [中文文档](http://n9e.flashcat.cloud/)
-
-## Screenshots
-
-https://user-images.githubusercontent.com/792850/216888712-2565fcea-9df5-47bd-a49e-d60af9bd76e8.mp4
-
-## Architecture
-
-<img src="doc/img/arch-product.png" width="600">
-
-Nightingale monitoring can receive monitoring data reported by various collectors (such as [Categraf](https://github.com/flashcatcloud/categraf) , telegraf, grafana-agent, Prometheus, etc.) and write them to various popular time-series databases (such as Prometheus, M3DB, VictoriaMetrics, Thanos, TDEngine, etc.). It provides configuration capabilities for alert rules, silence rules, and subscription rules, as well as the ability to view monitoring data. It also provides automatic alarm self-healing mechanisms (such as automatically calling back to a webhook address or executing a script after an alarm is triggered), and the ability to store and manage historical alarm events and view them in groups.
-
-If the performance of a standalone time-series database (such as Prometheus) has bottlenecks or poor disaster recovery, we recommend using [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics). The VictoriaMetrics architecture is relatively simple, has excellent performance, and is easy to deploy and maintain. The architecture diagram is as shown above. For more detailed documentation on VictoriaMetrics, please refer to its [official website](https://victoriametrics.com/).
-
-**We welcome you to participate in the Nightingale open-source project and community in various ways, including but not limited to**：
-- Adding and improving documentation => [n9e.github.io](https://n9e.github.io/)
-- Sharing your best practices and experience in using Nightingale monitoring => [Article sharing]((https://n9e.github.io/docs/prologue/share/))
-- Submitting product suggestions => [github issue](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Ffeature&template=enhancement.md)
-- Submitting code to make Nightingale monitoring faster, more stable, and easier to use => [github pull request](https://github.com/didi/nightingale/pulls)
-
-
-**Respecting, recognizing, and recording the work of every contributor** is the first guiding principle of the Nightingale open-source community. We advocate effective questioning, which not only respects the developer's time but also contributes to the accumulation of knowledge in the entire community
-- Before asking a question, please first refer to the [FAQ](https://www.gitlink.org.cn/ccfos/nightingale/wiki/faq) 
-- We use [GitHub Discussions](https://github.com/ccfos/nightingale/discussions) as the communication forum. You can search and ask questions here.
-- We also recommend that you join ours [Slack channel](https://n9e-talk.slack.com/) to exchange experiences with other Nightingale users.
-
-
-## Who is using Nightingale
-You can register your usage and share your experience by posting on **[Who is Using Nightingale](https://github.com/ccfos/nightingale/issues/897)**.
-
-## Stargazers over time
-[![Stargazers over time](https://starchart.cc/ccfos/nightingale.svg)](https://starchart.cc/ccfos/nightingale)
-
-## Contributors
-<a href="https://github.com/ccfos/nightingale/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=ccfos/nightingale" />
-</a>
-
-## License
-[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)

README_zh.md

@@ -0,0 +1,74 @@
+<p align="center">
+  <a href="https://github.com/ccfos/nightingale">
+    <img src="doc/img/nightingale_logo_h.png" alt="nightingale - cloud native monitoring" width="240" /></a>
+</p>
+
+<p align="center">
+<a href="https://flashcat.cloud/docs/">
+  <img alt="Docs" src="https://img.shields.io/badge/docs-get%20started-brightgreen"/></a>
+<a href="https://hub.docker.com/u/flashcatcloud">
+  <img alt="Docker pulls" src="https://img.shields.io/docker/pulls/flashcatcloud/nightingale"/></a>
+<a href="https://github.com/ccfos/nightingale/graphs/contributors">
+  <img alt="GitHub contributors" src="https://img.shields.io/github/contributors-anon/ccfos/nightingale"/></a>
+<img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/ccfos/nightingale">
+<br/><img alt="GitHub Repo issues" src="https://img.shields.io/github/issues/ccfos/nightingale">
+<img alt="GitHub Repo issues closed" src="https://img.shields.io/github/issues-closed/ccfos/nightingale">
+<img alt="GitHub forks" src="https://img.shields.io/github/forks/ccfos/nightingale">
+<img alt="GitHub latest release" src="https://img.shields.io/github/v/release/ccfos/nightingale"/>
+<img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"/>
+<a href="https://n9e-talk.slack.com/">
+  <img alt="GitHub contributors" src="https://img.shields.io/badge/join%20slack-%23n9e-brightgreen.svg"/></a>
+</p>
+
+<p align="center">
+  告警管理专家，一体化的开源可观测平台
+</p>
+
+[English](./README.md) | [中文](./README_zh.md)
+
+夜莺Nightingale是中国计算机学会托管的开源云原生可观测工具，最早由滴滴于 2020 年孵化并开源，并于 2022 年正式捐赠予中国计算机学会。夜莺采用 All-in-One 的设计理念，集数据采集、可视化、监控告警、数据分析于一体，与云原生生态紧密集成，融入了顶级互联网公司可观测性最佳实践，沉淀了众多社区专家经验，开箱即用。
+
+## 资料
+
+- 文档：[flashcat.cloud/docs](https://flashcat.cloud/docs/)
+- 提问：[answer.flashcat.cloud](https://answer.flashcat.cloud/)
+- 报Bug：[github.com/ccfos/nightingale/issues](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&projects=&template=bug_report.yml)
+
+
+## 功能和特点
+
+- 统一接入各种时序库：支持对接 Prometheus、VictoriaMetrics、Thanos、Mimir、M3DB 等多种时序库，实现统一告警管理
+- 专业告警能力：内置支持多种告警规则，可以扩展支持所有通知媒介，支持告警屏蔽、告警抑制、告警自愈、告警事件管理
+- 高性能可视化引擎：支持多种图表样式，内置众多Dashboard模版，也可导入Grafana模版，开箱即用，开源协议商业友好
+- 无缝搭配 [Flashduty](https://flashcat.cloud/product/flashcat-duty/)：实现告警聚合收敛、认领、升级、排班、IM集成，确保告警处理不遗漏，减少打扰，更好协同
+- 支持所有常见采集器：支持 [Categraf](https://flashcat.cloud/product/categraf)、telegraf、grafana-agent、datadog-agent、各种 exporter 作为采集器，没有什么数据是不能监控的
+- 一体化观测平台：从 v6 版本开始，支持接入 ElasticSearch、Jaeger 数据源，实现日志、链路、指标多维度的统一可观测
+
+
+## 产品演示
+
+![演示](doc/img/n9e-screenshot-gif-v6.gif)
+
+## 部署架构
+
+![架构](doc/img/n9e-arch-latest.png)
+
+## 加入交流群
+
+欢迎加入 QQ 交流群，群号：479290895，QQ 群适合群友互助，夜莺研发人员通常不在群里。如果要报 bug 请到[这里](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&projects=&template=bug_report.yml)，提问到[这里](https://answer.flashcat.cloud/)。
+
+## Stargazers over time
+
+[![Stargazers over time](https://api.star-history.com/svg?repos=ccfos/nightingale&type=Date)](https://star-history.com/#ccfos/nightingale&Date)
+
+
+## Contributors
+<a href="https://github.com/ccfos/nightingale/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=ccfos/nightingale" />
+</a>
+
+## 社区治理
+[夜莺开源项目和社区治理架构（草案）](./doc/community-governance.md)
+
+## License
+[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)

alert/aconf/conf.go

@@ -2,11 +2,10 @@ package aconf
 
 import (
 	"path"
-
-	"github.com/toolkits/pkg/runner"
 )
 
 type Alert struct {
+	Disable     bool
 	EngineDelay int64
 	Heartbeat   HeartbeatConfig
 	Alerting    Alerting
@@ -54,9 +53,9 @@ type Ibex struct {
 	Timeout       int64
 }
 
-func (a *Alert) PreCheck() {
+func (a *Alert) PreCheck(configDir string) {
 	if a.Alerting.TemplatesDir == "" {
-		a.Alerting.TemplatesDir = path.Join(runner.Cwd, "etc", "template")
+		a.Alerting.TemplatesDir = path.Join(configDir, "template")
 	}
 
 	if a.Alerting.NotifyConcurrency == 0 {
@@ -70,4 +69,8 @@ func (a *Alert) PreCheck() {
 	if a.Heartbeat.EngineName == "" {
 		a.Heartbeat.EngineName = "default"
 	}
+
+	if a.EngineDelay == 0 {
+		a.EngineDelay = 30
+	}
 }

alert/alert.go

@@ -15,6 +15,7 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/router"
 	"github.com/ccfos/nightingale/v6/alert/sender"
 	"github.com/ccfos/nightingale/v6/conf"
+	"github.com/ccfos/nightingale/v6/dumper"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
@@ -47,16 +48,19 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
 	notifyConfigCache := memsto.NewNotifyConfigCache(ctx)
 	dsCache := memsto.NewDatasourceCache(ctx, syncStats)
+	userCache := memsto.NewUserCache(ctx, syncStats)
+	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
 
 	promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
 
 	externalProcessors := process.NewExternalProcessors()
 
-	Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache, alertRuleCache, notifyConfigCache, dsCache, ctx, promClients)
+	Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache, alertRuleCache, notifyConfigCache, dsCache, ctx, promClients, userCache, userGroupCache)
 
 	r := httpx.GinEngine(config.Global.RunMode, config.HTTP)
 	rt := router.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
 	rt.Config(r)
+	dumper.ConfigRouter(r)
 
 	httpClean := httpx.Init(config.HTTP, r)
 
@@ -67,9 +71,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 }
 
 func Start(alertc aconf.Alert, pushgwc pconf.Pushgw, syncStats *memsto.Stats, alertStats *astats.Stats, externalProcessors *process.ExternalProcessorsType, targetCache *memsto.TargetCacheType, busiGroupCache *memsto.BusiGroupCacheType,
-	alertMuteCache *memsto.AlertMuteCacheType, alertRuleCache *memsto.AlertRuleCacheType, notifyConfigCache *memsto.NotifyConfigCacheType, datasourceCache *memsto.DatasourceCacheType, ctx *ctx.Context, promClients *prom.PromClientMap) {
-	userCache := memsto.NewUserCache(ctx, syncStats)
-	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
+	alertMuteCache *memsto.AlertMuteCacheType, alertRuleCache *memsto.AlertRuleCacheType, notifyConfigCache *memsto.NotifyConfigCacheType, datasourceCache *memsto.DatasourceCacheType, ctx *ctx.Context, promClients *prom.PromClientMap, userCache *memsto.UserCacheType, userGroupCache *memsto.UserGroupCacheType) {
 	alertSubscribeCache := memsto.NewAlertSubscribeCache(ctx, syncStats)
 	recordingRuleCache := memsto.NewRecordingRuleCache(ctx, syncStats)
 
@@ -89,5 +91,5 @@ func Start(alertc aconf.Alert, pushgwc pconf.Pushgw, syncStats *memsto.Stats, al
 	go consumer.LoopConsume()
 
 	go queue.ReportQueueSize(alertStats)
-	go sender.StartEmailSender(notifyConfigCache.GetSMTP()) // todo
+	go sender.InitEmailSender(notifyConfigCache.GetSMTP())
 }

alert/common/conv.go

@@ -15,6 +15,7 @@ type AnomalyPoint struct {
 	Value     float64      `json:"value"`
 	Severity  int          `json:"severity"`
 	Triggered bool         `json:"triggered"`
+	Query     string       `json:"query"`
 }
 
 func NewAnomalyPoint(key string, labels map[string]string, ts int64, value float64, severity int) AnomalyPoint {

alert/common/key.go

@@ -22,6 +22,14 @@ func MatchTags(eventTagsMap map[string]string, itags []models.TagFilter) bool {
 	}
 	return true
 }
+func MatchGroupsName(groupName string, groupFilter []models.TagFilter) bool {
+	for _, filter := range groupFilter {
+		if !matchTag(groupName, filter) {
+			return false
+		}
+	}
+	return true
+}
 
 func matchTag(value string, filter models.TagFilter) bool {
 	switch filter.Func {

alert/dispatch/consume.go

@@ -83,6 +83,10 @@ func (e *Consumer) consumeOne(event *models.AlertCurEvent) {
 }
 
 func (e *Consumer) persist(event *models.AlertCurEvent) {
+	if event.Status != 0 {
+		return
+	}
+
 	if !e.ctx.IsCenter {
 		event.DB2FE()
 		err := poster.PostByUrls(e.ctx, "/v1/n9e/event-persist", event)

alert/dispatch/dispatch.go

@@ -28,9 +28,10 @@ type Dispatch struct {
 
 	alerting aconf.Alerting
 
-	senders      map[string]sender.Sender
-	tpls         map[string]*template.Template
-	ExtraSenders map[string]sender.Sender
+	Senders          map[string]sender.Sender
+	tpls             map[string]*template.Template
+	ExtraSenders     map[string]sender.Sender
+	BeforeSenderHook func(*models.AlertCurEvent) bool
 
 	ctx *ctx.Context
 
@@ -51,9 +52,10 @@ func NewDispatch(alertRuleCache *memsto.AlertRuleCacheType, userCache *memsto.Us
 
 		alerting: alerting,
 
-		senders:      make(map[string]sender.Sender),
-		tpls:         make(map[string]*template.Template),
-		ExtraSenders: make(map[string]sender.Sender),
+		Senders:          make(map[string]sender.Sender),
+		tpls:             make(map[string]*template.Template),
+		ExtraSenders:     make(map[string]sender.Sender),
+		BeforeSenderHook: func(*models.AlertCurEvent) bool { return true },
 
 		ctx: ctx,
 	}
@@ -63,7 +65,7 @@ func NewDispatch(alertRuleCache *memsto.AlertRuleCacheType, userCache *memsto.Us
 func (e *Dispatch) ReloadTpls() error {
 	err := e.relaodTpls()
 	if err != nil {
-		logger.Error("failed to reload tpls: %v", err)
+		logger.Errorf("failed to reload tpls: %v", err)
 	}
 
 	duration := time.Duration(9000) * time.Millisecond
@@ -83,23 +85,24 @@ func (e *Dispatch) relaodTpls() error {
 	smtp := e.notifyConfigCache.GetSMTP()
 
 	senders := map[string]sender.Sender{
-		models.Email:    sender.NewSender(models.Email, tmpTpls, smtp),
-		models.Dingtalk: sender.NewSender(models.Dingtalk, tmpTpls, smtp),
-		models.Wecom:    sender.NewSender(models.Wecom, tmpTpls, smtp),
-		models.Feishu:   sender.NewSender(models.Feishu, tmpTpls, smtp),
-		models.Mm:       sender.NewSender(models.Mm, tmpTpls, smtp),
-		models.Telegram: sender.NewSender(models.Telegram, tmpTpls, smtp),
+		models.Email:      sender.NewSender(models.Email, tmpTpls, smtp),
+		models.Dingtalk:   sender.NewSender(models.Dingtalk, tmpTpls),
+		models.Wecom:      sender.NewSender(models.Wecom, tmpTpls),
+		models.Feishu:     sender.NewSender(models.Feishu, tmpTpls),
+		models.Mm:         sender.NewSender(models.Mm, tmpTpls),
+		models.Telegram:   sender.NewSender(models.Telegram, tmpTpls),
+		models.FeishuCard: sender.NewSender(models.FeishuCard, tmpTpls),
 	}
 
 	e.RwLock.RLock()
-	for channel, sender := range e.ExtraSenders {
-		senders[channel] = sender
+	for channelName, extraSender := range e.ExtraSenders {
+		senders[channelName] = extraSender
 	}
 	e.RwLock.RUnlock()
 
 	e.RwLock.Lock()
 	e.tpls = tmpTpls
-	e.senders = senders
+	e.Senders = senders
 	e.RwLock.Unlock()
 	return nil
 }
@@ -140,7 +143,7 @@ func (e *Dispatch) HandleEventNotify(event *models.AlertCurEvent, isSubscribe bo
 	}
 
 	// 处理事件发送,这里用一个goroutine处理一个event的所有发送事件
-	go e.Send(rule, event, notifyTarget, isSubscribe)
+	go e.Send(rule, event, notifyTarget)
 
 	// 如果是不是订阅规则出现的event, 则需要处理订阅规则的event
 	if !isSubscribe {
@@ -167,35 +170,63 @@ func (e *Dispatch) handleSubs(event *models.AlertCurEvent) {
 
 // handleSub 处理订阅规则的event,注意这里event要使用值传递,因为后面会修改event的状态
 func (e *Dispatch) handleSub(sub *models.AlertSubscribe, event models.AlertCurEvent) {
-	if sub.IsDisabled() || !sub.MatchCluster(event.DatasourceId) {
+	if sub.IsDisabled() {
 		return
 	}
+
+	if !sub.MatchCluster(event.DatasourceId) {
+		return
+	}
+
+	if !sub.MatchProd(event.RuleProd) {
+		return
+	}
+
 	if !common.MatchTags(event.TagsMap, sub.ITags) {
 		return
 	}
+	// event BusiGroups filter
+	if !common.MatchGroupsName(event.GroupName, sub.IBusiGroups) {
+		return
+	}
 	if sub.ForDuration > (event.TriggerTime - event.FirstTriggerTime) {
 		return
 	}
+
+	if len(sub.SeveritiesJson) != 0 {
+		match := false
+		for _, s := range sub.SeveritiesJson {
+			if s == event.Severity || s == 0 {
+				match = true
+				break
+			}
+		}
+		if !match {
+			return
+		}
+	}
+
 	sub.ModifyEvent(&event)
 	LogEvent(&event, "subscribe")
+
+	event.SubRuleId = sub.Id
 	e.HandleEventNotify(&event, true)
 }
 
-func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, notifyTarget *NotifyTarget, isSubscribe bool) {
-	for channel, uids := range notifyTarget.ToChannelUserMap() {
-		ctx := sender.BuildMessageContext(rule, event, uids, e.userCache)
-		e.RwLock.RLock()
-		s := e.senders[channel]
-		e.RwLock.RUnlock()
-		if s == nil {
-			logger.Debugf("no sender for channel: %s", channel)
-			continue
+func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, notifyTarget *NotifyTarget) {
+	needSend := e.BeforeSenderHook(event)
+	if needSend {
+		for channel, uids := range notifyTarget.ToChannelUserMap() {
+			msgCtx := sender.BuildMessageContext(rule, []*models.AlertCurEvent{event}, uids, e.userCache)
+			e.RwLock.RLock()
+			s := e.Senders[channel]
+			e.RwLock.RUnlock()
+			if s == nil {
+				logger.Debugf("no sender for channel: %s", channel)
+				continue
+			}
+			s.Send(msgCtx)
 		}
-		logger.Debugf("send event: %s, channel: %s", event.Hash, channel)
-		for i := 0; i < len(ctx.Users); i++ {
-			logger.Debug("send event to user: ", ctx.Users[i])
-		}
-		s.Send(ctx)
 	}
 
 	// handle event callbacks

alert/eval/alert_rule.go

@@ -85,6 +85,7 @@ func (s *Scheduler) syncAlertRules() {
 		if rule == nil {
 			continue
 		}
+
 		if rule.IsPrometheusRule() {
 			datasourceIds := s.promClients.Hit(rule.DatasourceIdsJson)
 			for _, dsId := range datasourceIds {

alert/eval/eval.go

@@ -69,14 +69,16 @@ func (arw *AlertRuleWorker) Start() {
 	if interval <= 0 {
 		interval = 10
 	}
+
+	ticker := time.NewTicker(time.Duration(interval) * time.Second)
 	go func() {
+		defer ticker.Stop()
 		for {
 			select {
 			case <-arw.quit:
 				return
-			default:
+			case <-ticker.C:
 				arw.Eval()
-				time.Sleep(time.Duration(interval) * time.Second)
 			}
 		}
 	}()
@@ -163,6 +165,7 @@ func (arw *AlertRuleWorker) GetPromAnomalyPoint(ruleConfig string) []common.Anom
 		points := common.ConvertAnomalyPoints(value)
 		for i := 0; i < len(points); i++ {
 			points[i].Severity = query.Severity
+			points[i].Query = promql
 		}
 		lst = append(lst, points...)
 	}

alert/mute/mute.go

@@ -13,7 +13,11 @@ import (
 )
 
 func IsMuted(rule *models.AlertRule, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, alertMuteCache *memsto.AlertMuteCacheType) bool {
-	if TimeNonEffectiveMuteStrategy(rule, event) {
+	if rule.Disabled == 1 {
+		return true
+	}
+
+	if TimeSpanMuteStrategy(rule, event) {
 		return true
 	}
 
@@ -32,12 +36,9 @@ func IsMuted(rule *models.AlertRule, event *models.AlertCurEvent, targetCache *m
 	return false
 }
 
-// TimeNonEffectiveMuteStrategy 根据规则配置的告警时间过滤,如果产生的告警不在规则配置的告警时间内,则不告警
-func TimeNonEffectiveMuteStrategy(rule *models.AlertRule, event *models.AlertCurEvent) bool {
-	if rule.Disabled == 1 {
-		return true
-	}
-
+// TimeSpanMuteStrategy 根据规则配置的告警生效时间段过滤,如果产生的告警不在规则配置的告警生效时间段内,则不告警,即被mute
+// 时间范围，左闭右开，默认范围：00:00-24:00
+func TimeSpanMuteStrategy(rule *models.AlertRule, event *models.AlertCurEvent) bool {
 	tm := time.Unix(event.TriggerTime, 0)
 	triggerTime := tm.Format("15:04")
 	triggerWeek := strconv.Itoa(int(tm.Weekday()))
@@ -52,18 +53,33 @@ func TimeNonEffectiveMuteStrategy(rule *models.AlertRule, event *models.AlertCur
 		if !strings.Contains(enableDaysOfWeek[i], triggerWeek) {
 			continue
 		}
-		if enableStime[i] <= enableEtime[i] {
-			if triggerTime < enableStime[i] || triggerTime > enableEtime[i] {
-				continue
+
+		if enableStime[i] < enableEtime[i] {
+			if enableEtime[i] == "23:59" {
+				// 02:00-23:59，这种情况做个特殊处理，相当于左闭右闭区间了
+				if triggerTime < enableStime[i] {
+					// mute, 即没生效
+					continue
+				}
+			} else {
+				// 02:00-04:00 或者 02:00-24:00
+				if triggerTime < enableStime[i] || triggerTime >= enableEtime[i] {
+					// mute, 即没生效
+					continue
+				}
 			}
-		} else {
-			if triggerTime < enableStime[i] && triggerTime > enableEtime[i] {
+		} else if enableStime[i] > enableEtime[i] {
+			// 21:00-09:00
+			if triggerTime < enableStime[i] && triggerTime >= enableEtime[i] {
+				// mute, 即没生效
 				continue
 			}
 		}
-		// 到这里说明当前时刻在告警规则的某组生效时间范围内，直接返回 false
+
+		// 到这里说明当前时刻在告警规则的某组生效时间范围内，即没有 mute，直接返回 false
 		return false
 	}
+
 	return true
 }
 
@@ -156,13 +172,16 @@ func matchMute(event *models.AlertCurEvent, mute *models.AlertMute, clock ...int
 
 		for i := 0; i < len(mute.PeriodicMutesJson); i++ {
 			if strings.Contains(mute.PeriodicMutesJson[i].EnableDaysOfWeek, triggerWeek) {
-				if mute.PeriodicMutesJson[i].EnableStime <= mute.PeriodicMutesJson[i].EnableEtime {
+				if mute.PeriodicMutesJson[i].EnableStime == mute.PeriodicMutesJson[i].EnableEtime {
+					matchTime = true
+					break
+				} else if mute.PeriodicMutesJson[i].EnableStime < mute.PeriodicMutesJson[i].EnableEtime {
 					if triggerTime >= mute.PeriodicMutesJson[i].EnableStime && triggerTime < mute.PeriodicMutesJson[i].EnableEtime {
 						matchTime = true
 						break
 					}
 				} else {
-					if triggerTime < mute.PeriodicMutesJson[i].EnableStime || triggerTime >= mute.PeriodicMutesJson[i].EnableEtime {
+					if triggerTime >= mute.PeriodicMutesJson[i].EnableStime || triggerTime < mute.PeriodicMutesJson[i].EnableEtime {
 						matchTime = true
 						break
 					}
@@ -174,5 +193,21 @@ func matchMute(event *models.AlertCurEvent, mute *models.AlertMute, clock ...int
 		return false
 	}
 
+	var matchSeverity bool
+	if len(mute.SeveritiesJson) > 0 {
+		for _, s := range mute.SeveritiesJson {
+			if event.Severity == s || s == 0 {
+				matchSeverity = true
+				break
+			}
+		}
+	} else {
+		matchSeverity = true
+	}
+
+	if !matchSeverity {
+		return false
+	}
+
 	return common.MatchTags(event.TagsMap, mute.ITags)
 }

alert/naming/hashring.go

@@ -16,7 +16,7 @@ type DatasourceHashRingType struct {
 }
 
 // for alert_rule sharding
-var HostDatasource int64 = 100000
+var HostDatasource int64 = 99999999
 var DatasourceHashRing = DatasourceHashRingType{Rings: make(map[int64]*consistent.Consistent)}
 
 func NewConsistentHashRing(replicas int32, nodes []string) *consistent.Consistent {
@@ -53,9 +53,7 @@ func (chr *DatasourceHashRingType) GetNode(datasourceId int64, pk string) (strin
 func (chr *DatasourceHashRingType) IsHit(datasourceId int64, pk string, currentNode string) bool {
 	node, err := chr.GetNode(datasourceId, pk)
 	if err != nil {
-		if errors.Is(err, consistent.ErrEmptyCircle) {
-			logger.Debugf("rule id:%s is not work, datasource id:%d is not assigned to active alert engine", pk, datasourceId)
-		} else {
+		if !errors.Is(err, consistent.ErrEmptyCircle) {
 			logger.Debugf("rule id:%s is not work, datasource id:%d failed to get node from hashring:%v", pk, datasourceId, err)
 		}
 		return false
@@ -68,3 +66,14 @@ func (chr *DatasourceHashRingType) Set(datasourceId int64, r *consistent.Consist
 	defer chr.Unlock()
 	chr.Rings[datasourceId] = r
 }
+
+func (chr *DatasourceHashRingType) Clear() {
+	chr.Lock()
+	defer chr.Unlock()
+	for id := range chr.Rings {
+		if id == HostDatasource {
+			continue
+		}
+		delete(chr.Rings, id)
+	}
+}

alert/naming/heartbeat.go

@@ -96,6 +96,16 @@ func (n *Naming) heartbeat() error {
 		}
 	}
 
+	if len(datasourceIds) == 0 {
+		DatasourceHashRing.Clear()
+		for dsId := range localss {
+			if dsId == HostDatasource {
+				continue
+			}
+			delete(localss, dsId)
+		}
+	}
+
 	for i := 0; i < len(datasourceIds); i++ {
 		servers, err := n.ActiveServers(datasourceIds[i])
 		if err != nil {
@@ -157,3 +167,13 @@ func (n *Naming) ActiveServers(datasourceId int64) ([]string, error) {
 	// 30秒内有心跳，就认为是活的
 	return models.AlertingEngineGetsInstances(n.ctx, "datasource_id = ? and clock > ?", datasourceId, time.Now().Unix()-30)
 }
+
+func (n *Naming) ActiveServersByEngineName() ([]string, error) {
+	if !n.ctx.IsCenter {
+		lst, err := poster.GetByUrls[[]string](n.ctx, "/v1/n9e/servers-active?engine_name="+n.heartbeatConfig.EngineName)
+		return lst, err
+	}
+
+	// 30秒内有心跳，就认为是活的
+	return models.AlertingEngineGetsInstances(n.ctx, "engine_cluster = ? and clock > ?", n.heartbeatConfig.EngineName, time.Now().Unix()-30)
+}

alert/process/process.go

@@ -23,6 +23,8 @@ import (
 	"github.com/toolkits/pkg/str"
 )
 
+type EventMuteHookFunc func(event *models.AlertCurEvent) bool
+
 type ExternalProcessorsType struct {
 	ExternalLock sync.RWMutex
 	Processors   map[string]*Processor
@@ -43,6 +45,8 @@ func (e *ExternalProcessorsType) GetExternalAlertRule(datasourceId, id int64) (*
 	return processor, has
 }
 
+type HandleEventFunc func(event *models.AlertCurEvent)
+
 type Processor struct {
 	datasourceId int64
 
@@ -66,6 +70,10 @@ type Processor struct {
 	promClients *prom.PromClientMap
 	ctx         *ctx.Context
 	stats       *astats.Stats
+
+	HandleFireEventHook    HandleEventFunc
+	HandleRecoverEventHook HandleEventFunc
+	EventMuteHook          EventMuteHookFunc
 }
 
 func (p *Processor) Key() string {
@@ -102,6 +110,10 @@ func NewProcessor(rule *models.AlertRule, datasourceId int64, atertRuleCache *me
 		promClients: promClients,
 		ctx:         ctx,
 		stats:       stats,
+
+		HandleFireEventHook:    func(event *models.AlertCurEvent) {},
+		HandleRecoverEventHook: func(event *models.AlertCurEvent) {},
+		EventMuteHook:          func(event *models.AlertCurEvent) bool { return false },
 	}
 
 	p.mayHandleGroup()
@@ -133,6 +145,11 @@ func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inh
 			logger.Debugf("rule_eval:%s event:%v is muted", p.Key(), event)
 			continue
 		}
+
+		if p.EventMuteHook(event) {
+			continue
+		}
+
 		tagHash := TagHash(anomalyPoint)
 		eventsMap[tagHash] = append(eventsMap[tagHash], event)
 	}
@@ -174,6 +191,8 @@ func (p *Processor) BuildEvent(anomalyPoint common.AnomalyPoint, from string, no
 	event.RuleConfig = p.rule.RuleConfig
 	event.RuleConfigJson = p.rule.RuleConfigJson
 	event.Severity = anomalyPoint.Severity
+	event.ExtraConfig = p.rule.ExtraConfigJSON
+	event.PromQl = anomalyPoint.Query
 
 	if from == "inner" {
 		event.LastEvalTime = now
@@ -227,6 +246,8 @@ func (p *Processor) RecoverSingle(hash string, now int64, value *string) {
 	cachedRule.UpdateEvent(event)
 	event.IsRecovered = true
 	event.LastEvalTime = now
+
+	p.HandleRecoverEventHook(event)
 	p.pushEventToQueue(event)
 }
 
@@ -284,9 +305,12 @@ func (p *Processor) fireEvent(event *models.AlertCurEvent) {
 	if cachedRule == nil {
 		return
 	}
+
 	logger.Debugf("rule_eval:%s event:%+v fire", p.Key(), event)
 	if fired, has := p.fires.Get(event.Hash); has {
 		p.fires.UpdateLastEvalTime(event.Hash, event.LastEvalTime)
+		event.FirstTriggerTime = fired.FirstTriggerTime
+		p.HandleFireEventHook(event)
 
 		if cachedRule.NotifyRepeatStep == 0 {
 			logger.Debugf("rule_eval:%s event:%+v repeat is zero nothing to do", p.Key(), event)
@@ -296,11 +320,10 @@ func (p *Processor) fireEvent(event *models.AlertCurEvent) {
 		}
 
 		// 之前发送过告警了，这次是否要继续发送，要看是否过了通道静默时间
-		if event.LastEvalTime > fired.LastSentTime+int64(cachedRule.NotifyRepeatStep)*60 {
+		if event.LastEvalTime >= fired.LastSentTime+int64(cachedRule.NotifyRepeatStep)*60 {
 			if cachedRule.NotifyMaxNumber == 0 {
 				// 最大可以发送次数如果是0，表示不想限制最大发送次数，一直发即可
 				event.NotifyCurNumber = fired.NotifyCurNumber + 1
-				event.FirstTriggerTime = fired.FirstTriggerTime
 				p.pushEventToQueue(event)
 			} else {
 				// 有最大发送次数的限制，就要看已经发了几次了，是否达到了最大发送次数
@@ -309,7 +332,6 @@ func (p *Processor) fireEvent(event *models.AlertCurEvent) {
 					return
 				} else {
 					event.NotifyCurNumber = fired.NotifyCurNumber + 1
-					event.FirstTriggerTime = fired.FirstTriggerTime
 					p.pushEventToQueue(event)
 				}
 			}
@@ -317,6 +339,7 @@ func (p *Processor) fireEvent(event *models.AlertCurEvent) {
 	} else {
 		event.NotifyCurNumber = 1
 		event.FirstTriggerTime = event.TriggerTime
+		p.HandleFireEventHook(event)
 		p.pushEventToQueue(event)
 	}
 }
@@ -432,7 +455,7 @@ func labelMapToArr(m map[string]string) []string {
 }
 
 func Hash(ruleId, datasourceId int64, vector common.AnomalyPoint) string {
-	return str.MD5(fmt.Sprintf("%d_%s_%d_%d", ruleId, vector.Labels.String(), datasourceId, vector.Severity))
+	return str.MD5(fmt.Sprintf("%d_%s_%d_%d_%s", ruleId, vector.Labels.String(), datasourceId, vector.Severity, vector.Query))
 }
 
 func TagHash(vector common.AnomalyPoint) string {

alert/record/prom_rule.go

@@ -54,14 +54,16 @@ func (rrc *RecordRuleContext) Start() {
 	if interval <= 0 {
 		interval = 10
 	}
+
+	ticker := time.NewTicker(time.Duration(interval) * time.Second)
 	go func() {
+		defer ticker.Stop()
 		for {
 			select {
 			case <-rrc.quit:
 				return
-			default:
+			case <-ticker.C:
 				rrc.Eval()
-				time.Sleep(time.Duration(interval) * time.Second)
 			}
 		}
 	}()

alert/router/router.go

@@ -39,13 +39,13 @@ func New(httpConfig httpx.Config, alert aconf.Alert, amc *memsto.AlertMuteCacheT
 }
 
 func (rt *Router) Config(r *gin.Engine) {
-	if !rt.HTTP.Alert.Enable {
+	if !rt.HTTP.APIForService.Enable {
 		return
 	}
 
 	service := r.Group("/v1/n9e")
-	if len(rt.HTTP.Alert.BasicAuth) > 0 {
-		service.Use(gin.BasicAuth(rt.HTTP.Alert.BasicAuth))
+	if len(rt.HTTP.APIForService.BasicAuth) > 0 {
+		service.Use(gin.BasicAuth(rt.HTTP.APIForService.BasicAuth))
 	}
 	service.POST("/event", rt.pushEventToQueue)
 	service.POST("/event-persist", rt.eventPersist)

alert/sender/callback.go

@@ -1,6 +1,7 @@
 package sender
 
 import (
+	"encoding/json"
 	"strconv"
 	"strings"
 	"time"
@@ -50,6 +51,7 @@ type TaskForm struct {
 	Pause     string   `json:"pause"`
 	Script    string   `json:"script"`
 	Args      string   `json:"args"`
+	Stdin     string   `json:"stdin"`
 	Action    string   `json:"action"`
 	Creator   string   `json:"creator"`
 	Hosts     []string `json:"hosts"`
@@ -90,7 +92,7 @@ func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targe
 		return
 	}
 
-	tpl, err := models.TaskTplGet(ctx, "id = ?", id)
+	tpl, err := models.TaskTplGetById(ctx, id)
 	if err != nil {
 		logger.Errorf("event_callback_ibex: failed to get tpl: %v", err)
 		return
@@ -114,6 +116,30 @@ func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targe
 		return
 	}
 
+	tagsMap := make(map[string]string)
+	for i := 0; i < len(event.TagsJSON); i++ {
+		pair := strings.TrimSpace(event.TagsJSON[i])
+		if pair == "" {
+			continue
+		}
+
+		arr := strings.Split(pair, "=")
+		if len(arr) != 2 {
+			continue
+		}
+
+		tagsMap[arr[0]] = arr[1]
+	}
+	// 附加告警级别  告警触发值标签
+	tagsMap["alert_severity"] = strconv.Itoa(event.Severity)
+	tagsMap["alert_trigger_value"] = event.TriggerValue
+
+	tags, err := json.Marshal(tagsMap)
+	if err != nil {
+		logger.Errorf("event_callback_ibex: failed to marshal tags to json: %v", tagsMap)
+		return
+	}
+
 	// call ibex
 	in := TaskForm{
 		Title:     tpl.Title + " FH: " + host,
@@ -124,6 +150,7 @@ func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targe
 		Pause:     tpl.Pause,
 		Script:    tpl.Script,
 		Args:      tpl.Args,
+		Stdin:     string(tags),
 		Action:    "start",
 		Creator:   tpl.UpdateBy,
 		Hosts:     []string{host},

alert/sender/dingtalk.go

@@ -32,7 +32,7 @@ type DingtalkSender struct {
 }
 
 func (ds *DingtalkSender) Send(ctx MessageContext) {
-	if len(ctx.Users) == 0 || ctx.Rule == nil || ctx.Event == nil {
+	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
 		return
 	}
 
@@ -40,7 +40,7 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
 	if len(urls) == 0 {
 		return
 	}
-	message := BuildTplMessage(ds.tpl, ctx.Event)
+	message := BuildTplMessage(ds.tpl, ctx.Events)
 
 	for _, url := range urls {
 		var body dingtalk
@@ -49,7 +49,7 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
 			body = dingtalk{
 				Msgtype: "markdown",
 				Markdown: dingtalkMarkdown{
-					Title: ctx.Event.RuleName,
+					Title: ctx.Events[0].RuleName,
 					Text:  message,
 				},
 			}
@@ -57,7 +57,7 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
 			body = dingtalk{
 				Msgtype: "markdown",
 				Markdown: dingtalkMarkdown{
-					Title: ctx.Event.RuleName,
+					Title: ctx.Events[0].RuleName,
 					Text:  message + "\n" + strings.Join(ats, " "),
 				},
 				At: dingtalkAt{
@@ -81,7 +81,7 @@ func (ds *DingtalkSender) extract(users []*models.User) ([]string, []string) {
 		}
 		if token, has := user.ExtractToken(models.Dingtalk); has {
 			url := token
-			if !strings.HasPrefix(token, "https://") {
+			if !strings.HasPrefix(token, "https://") && !strings.HasPrefix(token, "http://") {
 				url = "https://oapi.dingtalk.com/robot/send?access_token=" + token
 			}
 			urls = append(urls, url)

alert/sender/email.go

@@ -2,6 +2,7 @@ package sender
 
 import (
 	"crypto/tls"
+	"errors"
 	"html/template"
 	"time"
 
@@ -22,18 +23,18 @@ type EmailSender struct {
 }
 
 func (es *EmailSender) Send(ctx MessageContext) {
-	if len(ctx.Users) == 0 || ctx.Rule == nil || ctx.Event == nil {
+	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
 		return
 	}
 	tos := extract(ctx.Users)
 	var subject string
 
 	if es.subjectTpl != nil {
-		subject = BuildTplMessage(es.subjectTpl, ctx.Event)
+		subject = BuildTplMessage(es.subjectTpl, []*models.AlertCurEvent{ctx.Events[0]})
 	} else {
-		subject = ctx.Event.RuleName
+		subject = ctx.Events[0].RuleName
 	}
-	content := BuildTplMessage(es.contentTpl, ctx.Event)
+	content := BuildTplMessage(es.contentTpl, ctx.Events)
 	es.WriteEmail(subject, content, tos)
 }
 
@@ -47,7 +48,7 @@ func extract(users []*models.User) []string {
 	return tos
 }
 
-func (es *EmailSender) SendEmail(subject, content string, tos []string, stmp aconf.SMTPConfig) {
+func SendEmail(subject, content string, tos []string, stmp aconf.SMTPConfig) error {
 	conf := stmp
 
 	d := gomail.NewDialer(conf.Host, conf.Port, conf.User, conf.Pass)
@@ -64,8 +65,9 @@ func (es *EmailSender) SendEmail(subject, content string, tos []string, stmp aco
 
 	err := d.DialAndSend(m)
 	if err != nil {
-		logger.Errorf("email_sender: failed to send: %v", err)
+		return errors.New("email_sender: failed to send: " + err.Error())
 	}
+	return nil
 }
 
 func (es *EmailSender) WriteEmail(subject, content string, tos []string) {
@@ -96,14 +98,16 @@ var mailQuit = make(chan struct{})
 func RestartEmailSender(smtp aconf.SMTPConfig) {
 	close(mailQuit)
 	mailQuit = make(chan struct{})
-	StartEmailSender(smtp)
+	startEmailSender(smtp)
 }
 
-func StartEmailSender(smtp aconf.SMTPConfig) {
+func InitEmailSender(smtp aconf.SMTPConfig) {
 	mailch = make(chan *gomail.Message, 100000)
+	startEmailSender(smtp)
+}
 
+func startEmailSender(smtp aconf.SMTPConfig) {
 	conf := smtp
-
 	if conf.Host == "" || conf.Port == 0 {
 		logger.Warning("SMTP configurations invalid")
 		return

alert/sender/feishu.go

@@ -31,11 +31,11 @@ type FeishuSender struct {
 }
 
 func (fs *FeishuSender) Send(ctx MessageContext) {
-	if len(ctx.Users) == 0 || ctx.Rule == nil || ctx.Event == nil {
+	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
 		return
 	}
 	urls, ats := fs.extract(ctx.Users)
-	message := BuildTplMessage(fs.tpl, ctx.Event)
+	message := BuildTplMessage(fs.tpl, ctx.Events)
 	for _, url := range urls {
 		body := feishu{
 			Msgtype: "text",
@@ -63,7 +63,7 @@ func (fs *FeishuSender) extract(users []*models.User) ([]string, []string) {
 		}
 		if token, has := user.ExtractToken(models.Feishu); has {
 			url := token
-			if !strings.HasPrefix(token, "https://") {
+			if !strings.HasPrefix(token, "https://") && !strings.HasPrefix(token, "http://") {
 				url = "https://open.feishu.cn/open-apis/bot/v2/hook/" + token
 			}
 			urls = append(urls, url)

alert/sender/feishucard.go

@@ -0,0 +1,144 @@
+package sender
+
+import (
+	"fmt"
+	"html/template"
+	"strings"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/poster"
+
+	"github.com/toolkits/pkg/logger"
+)
+
+type Conf struct {
+	WideScreenMode bool `json:"wide_screen_mode"`
+	EnableForward  bool `json:"enable_forward"`
+}
+
+type Te struct {
+	Content string `json:"content"`
+	Tag     string `json:"tag"`
+}
+
+type Element struct {
+	Tag      string    `json:"tag"`
+	Text     Te        `json:"text"`
+	Content  string    `json:"content"`
+	Elements []Element `json:"elements"`
+}
+
+type Titles struct {
+	Content string `json:"content"`
+	Tag     string `json:"tag"`
+}
+
+type Headers struct {
+	Title    Titles `json:"title"`
+	Template string `json:"template"`
+}
+
+type Cards struct {
+	Config   Conf      `json:"config"`
+	Elements []Element `json:"elements"`
+	Header   Headers   `json:"header"`
+}
+
+type feishuCard struct {
+	feishu
+	Card Cards `json:"card"`
+}
+
+type FeishuCardSender struct {
+	tpl *template.Template
+}
+
+const (
+	Recovered = "recovered"
+	Triggered = "triggered"
+)
+
+var (
+	body = feishuCard{
+		feishu: feishu{Msgtype: "interactive"},
+		Card: Cards{
+			Config: Conf{
+				WideScreenMode: true,
+				EnableForward:  true,
+			},
+			Header: Headers{
+				Title: Titles{
+					Tag: "plain_text",
+				},
+			},
+			Elements: []Element{
+				{
+					Tag: "div",
+					Text: Te{
+						Tag: "lark_md",
+					},
+				},
+				{
+					Tag: "hr",
+				},
+				{
+					Tag: "note",
+					Elements: []Element{
+						{
+							Tag: "lark_md",
+						},
+					},
+				},
+			},
+		},
+	}
+)
+
+func (fs *FeishuCardSender) Send(ctx MessageContext) {
+	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
+		return
+	}
+	urls, _ := fs.extract(ctx.Users)
+	message := BuildTplMessage(fs.tpl, ctx.Events)
+	color := "red"
+	lowerUnicode := strings.ToLower(message)
+	if strings.Count(lowerUnicode, Recovered) > 0 && strings.Count(lowerUnicode, Triggered) > 0 {
+		color = "orange"
+	} else if strings.Count(lowerUnicode, Recovered) > 0 {
+		color = "green"
+	}
+
+	SendTitle := fmt.Sprintf("🔔 %s", ctx.Events[0].RuleName)
+	body.Card.Header.Title.Content = SendTitle
+	body.Card.Header.Template = color
+	body.Card.Elements[0].Text.Content = message
+	body.Card.Elements[2].Elements[0].Content = SendTitle
+	for _, url := range urls {
+		fs.doSend(url, body)
+	}
+}
+
+func (fs *FeishuCardSender) extract(users []*models.User) ([]string, []string) {
+	urls := make([]string, 0, len(users))
+	ats := make([]string, 0)
+	for i := range users {
+		if token, has := users[i].ExtractToken(models.FeishuCard); has {
+			url := token
+			if !strings.HasPrefix(token, "https://") && !strings.HasPrefix(token, "http://") {
+				url = "https://open.feishu.cn/open-apis/bot/v2/hook/" + strings.TrimSpace(token)
+			}
+			urls = append(urls, url)
+		}
+	}
+	return urls, ats
+}
+
+func (fs *FeishuCardSender) doSend(url string, body feishuCard) {
+	res, code, err := poster.PostJSON(url, time.Second*5, body, 3)
+	if err != nil {
+		logger.Errorf("feishucard_sender: result=fail url=%s code=%d error=%v response=%s", url, code, err, string(res))
+	} else {
+		logger.Debugf("feishucard_sender: result=succ url=%s code=%d response=%s", url, code, string(res))
+	}
+}

alert/sender/mm.go

@@ -28,7 +28,7 @@ type MmSender struct {
 }
 
 func (ms *MmSender) Send(ctx MessageContext) {
-	if len(ctx.Users) == 0 || ctx.Rule == nil || ctx.Event == nil {
+	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
 		return
 	}
 
@@ -36,7 +36,7 @@ func (ms *MmSender) Send(ctx MessageContext) {
 	if len(urls) == 0 {
 		return
 	}
-	message := BuildTplMessage(ms.tpl, ctx.Event)
+	message := BuildTplMessage(ms.tpl, ctx.Events)
 
 	SendMM(MatterMostMessage{
 		Text:   message,

alert/sender/sender.go

@@ -17,13 +17,13 @@ type (
 
 	// MessageContext 一个event所生成的告警通知的上下文
 	MessageContext struct {
-		Users []*models.User
-		Rule  *models.AlertRule
-		Event *models.AlertCurEvent
+		Users  []*models.User
+		Rule   *models.AlertRule
+		Events []*models.AlertCurEvent
 	}
 )
 
-func NewSender(key string, tpls map[string]*template.Template, smtp aconf.SMTPConfig) Sender {
+func NewSender(key string, tpls map[string]*template.Template, smtp ...aconf.SMTPConfig) Sender {
 	switch key {
 	case models.Dingtalk:
 		return &DingtalkSender{tpl: tpls[models.Dingtalk]}
@@ -31,8 +31,10 @@ func NewSender(key string, tpls map[string]*template.Template, smtp aconf.SMTPCo
 		return &WecomSender{tpl: tpls[models.Wecom]}
 	case models.Feishu:
 		return &FeishuSender{tpl: tpls[models.Feishu]}
+	case models.FeishuCard:
+		return &FeishuCardSender{tpl: tpls[models.FeishuCard]}
 	case models.Email:
-		return &EmailSender{subjectTpl: tpls["mailsubject"], contentTpl: tpls[models.Email], smtp: smtp}
+		return &EmailSender{subjectTpl: tpls[models.EmailSubject], contentTpl: tpls[models.Email], smtp: smtp[0]}
 	case models.Mm:
 		return &MmSender{tpl: tpls[models.Mm]}
 	case models.Telegram:
@@ -41,23 +43,32 @@ func NewSender(key string, tpls map[string]*template.Template, smtp aconf.SMTPCo
 	return nil
 }
 
-func BuildMessageContext(rule *models.AlertRule, event *models.AlertCurEvent, uids []int64, userCache *memsto.UserCacheType) MessageContext {
+func BuildMessageContext(rule *models.AlertRule, events []*models.AlertCurEvent, uids []int64, userCache *memsto.UserCacheType) MessageContext {
 	users := userCache.GetByUserIds(uids)
 	return MessageContext{
-		Rule:  rule,
-		Event: event,
-		Users: users,
+		Rule:   rule,
+		Events: events,
+		Users:  users,
 	}
 }
 
-func BuildTplMessage(tpl *template.Template, event *models.AlertCurEvent) string {
+type BuildTplMessageFunc func(tpl *template.Template, events []*models.AlertCurEvent) string
+
+var BuildTplMessage BuildTplMessageFunc = buildTplMessage
+
+func buildTplMessage(tpl *template.Template, events []*models.AlertCurEvent) string {
 	if tpl == nil {
 		return "tpl for current sender not found, please check configuration"
 	}
 
-	var body bytes.Buffer
-	if err := tpl.Execute(&body, event); err != nil {
-		return err.Error()
+	var content string
+	for _, event := range events {
+		var body bytes.Buffer
+		if err := tpl.Execute(&body, event); err != nil {
+			return err.Error()
+		}
+		content += body.String() + "\n\n"
 	}
-	return body.String()
+
+	return content
 }

alert/sender/telegram.go

@@ -26,11 +26,11 @@ type TelegramSender struct {
 }
 
 func (ts *TelegramSender) Send(ctx MessageContext) {
-	if len(ctx.Users) == 0 || ctx.Rule == nil || ctx.Event == nil {
+	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
 		return
 	}
 	tokens := ts.extract(ctx.Users)
-	message := BuildTplMessage(ts.tpl, ctx.Event)
+	message := BuildTplMessage(ts.tpl, ctx.Events)
 
 	SendTelegram(TelegramMessage{
 		Text:   message,
@@ -55,7 +55,7 @@ func SendTelegram(message TelegramMessage) {
 			continue
 		}
 		var url string
-		if strings.HasPrefix(message.Tokens[i], "https://") {
+		if strings.HasPrefix(message.Tokens[i], "https://") || strings.HasPrefix(message.Tokens[i], "http://") {
 			url = message.Tokens[i]
 		} else {
 			array := strings.Split(message.Tokens[i], "/")

alert/sender/wecom.go

@@ -25,11 +25,11 @@ type WecomSender struct {
 }
 
 func (ws *WecomSender) Send(ctx MessageContext) {
-	if len(ctx.Users) == 0 || ctx.Rule == nil || ctx.Event == nil {
+	if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
 		return
 	}
 	urls := ws.extract(ctx.Users)
-	message := BuildTplMessage(ws.tpl, ctx.Event)
+	message := BuildTplMessage(ws.tpl, ctx.Events)
 	for _, url := range urls {
 		body := wecom{
 			Msgtype: "markdown",
@@ -46,7 +46,7 @@ func (ws *WecomSender) extract(users []*models.User) []string {
 	for _, user := range users {
 		if token, has := user.ExtractToken(models.Wecom); has {
 			url := token
-			if !strings.HasPrefix(token, "https://") {
+			if !strings.HasPrefix(token, "https://") && !strings.HasPrefix(token, "http://") {
 				url = "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=" + token
 			}
 			urls = append(urls, url)

center/cconf/conf.go

@@ -8,6 +8,7 @@ type Center struct {
 	I18NHeaderKey          string
 	MetricDesc             MetricDescType
 	AnonymousAccess        AnonymousAccess
+	UseFileAssets          bool
 }
 
 type Plugin struct {

center/cconf/plugin.go

@@ -13,10 +13,4 @@ var Plugins = []Plugin{
 		Type:     "elasticsearch",
 		TypeName: "Elasticsearch",
 	},
-	{
-		Id:       3,
-		Category: "logging",
-		Type:     "jaeger",
-		TypeName: "Jaeger",
-	},
 }

center/center.go

@@ -8,15 +8,19 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/alert/process"
 	"github.com/ccfos/nightingale/v6/center/cconf"
+	"github.com/ccfos/nightingale/v6/center/cstats"
 	"github.com/ccfos/nightingale/v6/center/metas"
 	"github.com/ccfos/nightingale/v6/center/sso"
 	"github.com/ccfos/nightingale/v6/conf"
+	"github.com/ccfos/nightingale/v6/dumper"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/models/migrate"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/httpx"
 	"github.com/ccfos/nightingale/v6/pkg/i18nx"
 	"github.com/ccfos/nightingale/v6/pkg/logx"
+	"github.com/ccfos/nightingale/v6/pkg/version"
 	"github.com/ccfos/nightingale/v6/prom"
 	"github.com/ccfos/nightingale/v6/pushgw/idents"
 	"github.com/ccfos/nightingale/v6/pushgw/writer"
@@ -41,7 +45,8 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 		return nil, err
 	}
 
-	i18nx.Init()
+	i18nx.Init(configDir)
+	cstats.Init()
 
 	db, err := storage.New(config.DB)
 	if err != nil {
@@ -49,6 +54,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	}
 	ctx := ctx.NewContext(context.Background(), db, true)
 	models.InitRoot(ctx)
+	migrate.Migrate(db)
 
 	redis, err := storage.NewRedis(config.Redis)
 	if err != nil {
@@ -69,16 +75,21 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	alertMuteCache := memsto.NewAlertMuteCache(ctx, syncStats)
 	alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
 	notifyConfigCache := memsto.NewNotifyConfigCache(ctx)
+	userCache := memsto.NewUserCache(ctx, syncStats)
+	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
 
 	promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
 
 	externalProcessors := process.NewExternalProcessors()
-	alert.Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache, alertRuleCache, notifyConfigCache, dsCache, ctx, promClients)
+	alert.Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache, alertRuleCache, notifyConfigCache, dsCache, ctx, promClients, userCache, userGroupCache)
 
 	writers := writer.NewWriters(config.Pushgw)
 
+	httpx.InitRSAConfig(&config.HTTP.RSA)
+	go version.GetGithubVersion()
+
 	alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
-	centerRouter := centerrt.New(config.HTTP, config.Center, cconf.Operations, dsCache, notifyConfigCache, promClients, redis, sso, ctx, metas, targetCache)
+	centerRouter := centerrt.New(config.HTTP, config.Center, cconf.Operations, dsCache, notifyConfigCache, promClients, redis, sso, ctx, metas, idents, targetCache, userCache, userGroupCache)
 	pushgwRouter := pushgwrt.New(config.HTTP, config.Pushgw, targetCache, busiGroupCache, idents, writers, ctx)
 
 	r := httpx.GinEngine(config.Global.RunMode, config.HTTP)
@@ -86,6 +97,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	centerRouter.Config(r)
 	alertrtRouter.Config(r)
 	pushgwRouter.Config(r)
+	dumper.ConfigRouter(r)
 
 	httpClean := httpx.Init(config.HTTP, r)
 

center/router/router.go

@@ -3,6 +3,8 @@ package router
 import (
 	"fmt"
 	"net/http"
+	"path"
+	"runtime"
 	"strings"
 	"time"
 
@@ -15,12 +17,16 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/aop"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/httpx"
+	"github.com/ccfos/nightingale/v6/pkg/version"
 	"github.com/ccfos/nightingale/v6/prom"
+	"github.com/ccfos/nightingale/v6/pushgw/idents"
 	"github.com/ccfos/nightingale/v6/storage"
 
 	"github.com/gin-gonic/gin"
 	"github.com/rakyll/statik/fs"
+	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
+	"github.com/toolkits/pkg/runner"
 )
 
 type Router struct {
@@ -32,13 +38,19 @@ type Router struct {
 	PromClients       *prom.PromClientMap
 	Redis             storage.Redis
 	MetaSet           *metas.Set
+	IdentSet          *idents.Set
 	TargetCache       *memsto.TargetCacheType
 	Sso               *sso.SsoClient
+	UserCache         *memsto.UserCacheType
+	UserGroupCache    *memsto.UserGroupCacheType
 	Ctx               *ctx.Context
+
+	DatasourceCheckHook func(*gin.Context) bool
 }
 
 func New(httpConfig httpx.Config, center cconf.Center, operations cconf.Operation, ds *memsto.DatasourceCacheType, ncc *memsto.NotifyConfigCacheType,
-	pc *prom.PromClientMap, redis storage.Redis, sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, tc *memsto.TargetCacheType) *Router {
+	pc *prom.PromClientMap, redis storage.Redis, sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, idents *idents.Set, tc *memsto.TargetCacheType,
+	uc *memsto.UserCacheType, ugc *memsto.UserGroupCacheType) *Router {
 	return &Router{
 		HTTP:              httpConfig,
 		Center:            center,
@@ -48,9 +60,14 @@ func New(httpConfig httpx.Config, center cconf.Center, operations cconf.Operatio
 		PromClients:       pc,
 		Redis:             redis,
 		MetaSet:           metaSet,
+		IdentSet:          idents,
 		TargetCache:       tc,
 		Sso:               sso,
+		UserCache:         uc,
+		UserGroupCache:    ugc,
 		Ctx:               ctx,
+
+		DatasourceCheckHook: func(ctx *gin.Context) bool { return false },
 	}
 }
 
@@ -95,10 +112,32 @@ func (rt *Router) configNoRoute(r *gin.Engine, fs *http.FileSystem) {
 		suffix := arr[len(arr)-1]
 
 		switch suffix {
-		case "png", "jpeg", "jpg", "svg", "ico", "gif", "css", "js", "html", "htm", "gz", "zip", "map":
-			c.FileFromFS(c.Request.URL.Path, *fs)
+		case "png", "jpeg", "jpg", "svg", "ico", "gif", "css", "js", "html", "htm", "gz", "zip", "map", "ttf":
+			if !rt.Center.UseFileAssets {
+				c.FileFromFS(c.Request.URL.Path, *fs)
+			} else {
+				cwdarr := []string{"/"}
+				if runtime.GOOS == "windows" {
+					cwdarr[0] = ""
+				}
+				cwdarr = append(cwdarr, strings.Split(runner.Cwd, "/")...)
+				cwdarr = append(cwdarr, "pub")
+				cwdarr = append(cwdarr, strings.Split(c.Request.URL.Path, "/")...)
+				c.File(path.Join(cwdarr...))
+			}
 		default:
-			c.FileFromFS("/", *fs)
+			if !rt.Center.UseFileAssets {
+				c.FileFromFS("/", *fs)
+			} else {
+				cwdarr := []string{"/"}
+				if runtime.GOOS == "windows" {
+					cwdarr[0] = ""
+				}
+				cwdarr = append(cwdarr, strings.Split(runner.Cwd, "/")...)
+				cwdarr = append(cwdarr, "pub")
+				cwdarr = append(cwdarr, "index.html")
+				c.File(path.Join(cwdarr...))
+			}
 		}
 	})
 }
@@ -113,7 +152,10 @@ func (rt *Router) Config(r *gin.Engine) {
 	if err != nil {
 		logger.Errorf("cannot create statik fs: %v", err)
 	}
-	r.StaticFS("/pub", statikFS)
+
+	if !rt.Center.UseFileAssets {
+		r.StaticFS("/pub", statikFS)
+	}
 
 	pagesPrefix := "/api/n9e"
 	pages := r.Group(pagesPrefix)
@@ -132,10 +174,14 @@ func (rt *Router) Config(r *gin.Engine) {
 		}
 
 		pages.POST("/auth/login", rt.jwtMock(), rt.loginPost)
-		pages.POST("/auth/logout", rt.jwtMock(), rt.logoutPost)
+		pages.POST("/auth/logout", rt.jwtMock(), rt.auth(), rt.logoutPost)
 		pages.POST("/auth/refresh", rt.jwtMock(), rt.refreshPost)
+		pages.POST("/auth/captcha", rt.jwtMock(), rt.generateCaptcha)
+		pages.POST("/auth/captcha-verify", rt.jwtMock(), rt.captchaVerify)
+		pages.GET("/auth/ifshowcaptcha", rt.ifShowCaptcha)
 
 		pages.GET("/auth/sso-config", rt.ssoConfigNameGet)
+		pages.GET("/auth/rsa-config", rt.rsaConfigGet)
 		pages.GET("/auth/redirect", rt.loginRedirect)
 		pages.GET("/auth/redirect/cas", rt.loginRedirectCas)
 		pages.GET("/auth/redirect/oauth", rt.loginRedirectOAuth)
@@ -203,6 +249,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/builtin-boards-cates", rt.auth(), rt.user(), rt.builtinBoardCateGets)
 		pages.POST("/builtin-boards-detail", rt.auth(), rt.user(), rt.builtinBoardDetailGets)
 		pages.GET("/integrations/icon/:cate/:name", rt.builtinIcon)
+		pages.GET("/integrations/makedown/:cate", rt.builtinMarkdown)
 
 		pages.GET("/busi-group/:id/boards", rt.auth(), rt.user(), rt.perm("/dashboards"), rt.bgro(), rt.boardGets)
 		pages.POST("/busi-group/:id/boards", rt.auth(), rt.user(), rt.perm("/dashboards/add"), rt.bgrw(), rt.boardAdd)
@@ -228,6 +275,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.PUT("/busi-group/:id/alert-rules/fields", rt.auth(), rt.user(), rt.perm("/alert-rules/put"), rt.bgrw(), rt.alertRulePutFields)
 		pages.PUT("/busi-group/:id/alert-rule/:arid", rt.auth(), rt.user(), rt.perm("/alert-rules/put"), rt.alertRulePutByFE)
 		pages.GET("/alert-rule/:arid", rt.auth(), rt.user(), rt.perm("/alert-rules"), rt.alertRuleGet)
+		pages.PUT("/busi-group/alert-rule/validate", rt.auth(), rt.user(), rt.perm("/alert-rules/put"), rt.alertRuleValidation)
 
 		pages.GET("/busi-group/:id/recording-rules", rt.auth(), rt.user(), rt.perm("/recording-rules"), rt.recordingRuleGets)
 		pages.POST("/busi-group/:id/recording-rules", rt.auth(), rt.user(), rt.perm("/recording-rules/add"), rt.bgrw(), rt.recordingRuleAddByFE)
@@ -237,6 +285,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.PUT("/busi-group/:id/recording-rules/fields", rt.auth(), rt.user(), rt.perm("/recording-rules/put"), rt.recordingRulePutFields)
 
 		pages.GET("/busi-group/:id/alert-mutes", rt.auth(), rt.user(), rt.perm("/alert-mutes"), rt.bgro(), rt.alertMuteGetsByBG)
+		pages.POST("/busi-group/:id/alert-mutes/preview", rt.auth(), rt.user(), rt.perm("/alert-mutes/add"), rt.bgrw(), rt.alertMutePreview)
 		pages.POST("/busi-group/:id/alert-mutes", rt.auth(), rt.user(), rt.perm("/alert-mutes/add"), rt.bgrw(), rt.alertMuteAdd)
 		pages.DELETE("/busi-group/:id/alert-mutes", rt.auth(), rt.user(), rt.perm("/alert-mutes/del"), rt.bgrw(), rt.alertMuteDel)
 		pages.PUT("/busi-group/:id/alert-mute/:amid", rt.auth(), rt.user(), rt.perm("/alert-mutes/put"), rt.alertMutePutByFE)
@@ -303,6 +352,8 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/notify-tpls", rt.auth(), rt.admin(), rt.notifyTplGets)
 		pages.PUT("/notify-tpl/content", rt.auth(), rt.admin(), rt.notifyTplUpdateContent)
 		pages.PUT("/notify-tpl", rt.auth(), rt.admin(), rt.notifyTplUpdate)
+		pages.POST("/notify-tpl", rt.auth(), rt.admin(), rt.notifyTplAdd)
+		pages.DELETE("/notify-tpl/:id", rt.auth(), rt.admin(), rt.notifyTplDel)
 		pages.POST("/notify-tpl/preview", rt.auth(), rt.admin(), rt.notifyTplPreview)
 
 		pages.GET("/sso-configs", rt.auth(), rt.admin(), rt.ssoConfigGets)
@@ -322,12 +373,29 @@ func (rt *Router) Config(r *gin.Engine) {
 
 		pages.GET("/notify-config", rt.auth(), rt.admin(), rt.notifyConfigGet)
 		pages.PUT("/notify-config", rt.auth(), rt.admin(), rt.notifyConfigPut)
+		pages.PUT("/smtp-config-test", rt.auth(), rt.admin(), rt.attemptSendEmail)
+
+		pages.GET("/es-index-pattern", rt.auth(), rt.esIndexPatternGet)
+		pages.GET("/es-index-pattern-list", rt.auth(), rt.esIndexPatternGetList)
+		pages.POST("/es-index-pattern", rt.auth(), rt.admin(), rt.esIndexPatternAdd)
+		pages.PUT("/es-index-pattern", rt.auth(), rt.admin(), rt.esIndexPatternPut)
+		pages.DELETE("/es-index-pattern", rt.auth(), rt.admin(), rt.esIndexPatternDel)
 	}
 
-	if rt.HTTP.Service.Enable {
+	r.GET("/api/n9e/versions", func(c *gin.Context) {
+		v := version.Version
+		lastIndex := strings.LastIndex(version.Version, "-")
+		if lastIndex != -1 {
+			v = version.Version[:lastIndex]
+		}
+
+		ginx.NewRender(c).Data(gin.H{"version": v, "github_verison": version.GithubVersion.Load().(string)}, nil)
+	})
+
+	if rt.HTTP.APIForService.Enable {
 		service := r.Group("/v1/n9e")
-		if len(rt.HTTP.Service.BasicAuth) > 0 {
-			service.Use(gin.BasicAuth(rt.HTTP.Service.BasicAuth))
+		if len(rt.HTTP.APIForService.BasicAuth) > 0 {
+			service.Use(gin.BasicAuth(rt.HTTP.APIForService.BasicAuth))
 		}
 		{
 			service.Any("/prometheus/*url", rt.dsProxy)
@@ -369,6 +437,8 @@ func (rt *Router) Config(r *gin.Engine) {
 			service.GET("/alert-his-events", rt.alertHisEventsList)
 			service.GET("/alert-his-event/:eid", rt.alertHisEventGet)
 
+			service.GET("/task-tpl/:tid", rt.taskTplGetByService)
+
 			service.GET("/config/:id", rt.configGet)
 			service.GET("/configs", rt.configsGet)
 			service.GET("/config", rt.configGetByKey)
@@ -387,11 +457,11 @@ func (rt *Router) Config(r *gin.Engine) {
 		}
 	}
 
-	if rt.HTTP.Heartbeat.Enable {
+	if rt.HTTP.APIForAgent.Enable {
 		heartbeat := r.Group("/v1/n9e")
 		{
-			if len(rt.HTTP.Heartbeat.BasicAuth) > 0 {
-				heartbeat.Use(gin.BasicAuth(rt.HTTP.Heartbeat.BasicAuth))
+			if len(rt.HTTP.APIForAgent.BasicAuth) > 0 {
+				heartbeat.Use(gin.BasicAuth(rt.HTTP.APIForAgent.BasicAuth))
 			}
 			heartbeat.POST("/heartbeat", rt.heartbeat)
 		}

center/router/router_alert_aggr_view.go

@@ -69,6 +69,11 @@ func (rt *Router) alertAggrViewPut(c *gin.Context) {
 			return
 		}
 	}
-
-	ginx.NewRender(c).Message(view.Update(rt.Ctx, f.Name, f.Rule, f.Cate, me.Id))
+	view.Name = f.Name
+	view.Rule = f.Rule
+	view.Cate = f.Cate
+	if view.CreateBy == 0 {
+		view.CreateBy = me.Id
+	}
+	ginx.NewRender(c).Message(view.Update(rt.Ctx))
 }

center/router/router_alert_cur_event.go

@@ -182,10 +182,19 @@ func (rt *Router) alertCurEventDel(c *gin.Context) {
 	ginx.BindJSON(c, &f)
 	f.Verify()
 
+	rt.checkCurEventBusiGroupRWPermission(c, f.Ids)
+
+	ginx.NewRender(c).Message(models.AlertCurEventDel(rt.Ctx, f.Ids))
+}
+
+func (rt *Router) checkCurEventBusiGroupRWPermission(c *gin.Context, ids []int64) {
 	set := make(map[int64]struct{})
 
-	for i := 0; i < len(f.Ids); i++ {
-		event, err := models.AlertCurEventGetById(rt.Ctx, f.Ids[i])
+	// event group id is 0, ignore perm check
+	set[0] = struct{}{}
+
+	for i := 0; i < len(ids); i++ {
+		event, err := models.AlertCurEventGetById(rt.Ctx, ids[i])
 		ginx.Dangerous(err)
 
 		if _, has := set[event.GroupId]; !has {
@@ -193,8 +202,6 @@ func (rt *Router) alertCurEventDel(c *gin.Context) {
 			set[event.GroupId] = struct{}{}
 		}
 	}
-
-	ginx.NewRender(c).Message(models.AlertCurEventDel(rt.Ctx, f.Ids))
 }
 
 func (rt *Router) alertCurEventGet(c *gin.Context) {

center/router/router_alert_rule.go

@@ -2,6 +2,7 @@ package router
 
 import (
 	"net/http"
+	"strconv"
 	"strings"
 	"time"
 
@@ -271,3 +272,54 @@ func (rt *Router) alertRuleGet(c *gin.Context) {
 
 	ginx.NewRender(c).Data(ar, err)
 }
+
+// pre validation before save rule
+func (rt *Router) alertRuleValidation(c *gin.Context) {
+	var f models.AlertRule //new
+	ginx.BindJSON(c, &f)
+
+	if len(f.NotifyChannelsJSON) > 0 && len(f.NotifyGroupsJSON) > 0 { //Validation NotifyChannels
+		ngids := make([]int64, 0, len(f.NotifyChannelsJSON))
+		for i := range f.NotifyGroupsJSON {
+			id, _ := strconv.ParseInt(f.NotifyGroupsJSON[i], 10, 64)
+			ngids = append(ngids, id)
+		}
+		userGroups := rt.UserGroupCache.GetByUserGroupIds(ngids)
+		uids := make([]int64, 0)
+		for i := range userGroups {
+			uids = append(uids, userGroups[i].UserIds...)
+		}
+		users := rt.UserCache.GetByUserIds(uids)
+		//If any users have a certain notify channel's token, it will be okay. Otherwise, this notify channel is absent of tokens.
+		ancs := make([]string, 0, len(f.NotifyChannelsJSON)) //absent Notify Channels
+		for i := range f.NotifyChannelsJSON {
+			flag := true
+			//ignore non-default channels
+			switch f.NotifyChannelsJSON[i] {
+			case models.Dingtalk, models.Wecom, models.Feishu, models.Mm,
+				models.Telegram, models.Email, models.FeishuCard:
+				// do nothing
+			default:
+				continue
+			}
+			//default channels
+			for ui := range users {
+				if _, b := users[ui].ExtractToken(f.NotifyChannelsJSON[i]); b {
+					flag = false
+					break
+				}
+			}
+			if flag {
+				ancs = append(ancs, f.NotifyChannelsJSON[i])
+			}
+		}
+
+		if len(ancs) > 0 {
+			ginx.NewRender(c).Message("All users are missing notify channel configurations. Please check for missing tokens (each channel should be configured with at least one user). %s", ancs)
+			return
+		}
+
+	}
+
+	ginx.NewRender(c).Message("")
+}

center/router/router_alert_subscribe.go

@@ -14,21 +14,18 @@ import (
 func (rt *Router) alertSubscribeGets(c *gin.Context) {
 	bgid := ginx.UrlParamInt64(c, "id")
 	lst, err := models.AlertSubscribeGets(rt.Ctx, bgid)
-	if err == nil {
-		ugcache := make(map[int64]*models.UserGroup)
-		for i := 0; i < len(lst); i++ {
-			ginx.Dangerous(lst[i].FillUserGroups(rt.Ctx, ugcache))
-		}
+	ginx.Dangerous(err)
 
-		rulecache := make(map[int64]string)
-		for i := 0; i < len(lst); i++ {
-			ginx.Dangerous(lst[i].FillRuleName(rt.Ctx, rulecache))
-		}
+	ugcache := make(map[int64]*models.UserGroup)
+	rulecache := make(map[int64]string)
 
-		for i := 0; i < len(lst); i++ {
-			ginx.Dangerous(lst[i].FillDatasourceIds(rt.Ctx))
-		}
+	for i := 0; i < len(lst); i++ {
+		ginx.Dangerous(lst[i].FillUserGroups(rt.Ctx, ugcache))
+		ginx.Dangerous(lst[i].FillRuleName(rt.Ctx, rulecache))
+		ginx.Dangerous(lst[i].FillDatasourceIds(rt.Ctx))
+		ginx.Dangerous(lst[i].DB2FE())
 	}
+
 	ginx.NewRender(c).Data(lst, err)
 }
 
@@ -83,6 +80,9 @@ func (rt *Router) alertSubscribePut(c *gin.Context) {
 			rt.Ctx,
 			"name",
 			"disabled",
+			"prod",
+			"cate",
+			"datasource_ids",
 			"cluster",
 			"rule_id",
 			"tags",
@@ -96,7 +96,9 @@ func (rt *Router) alertSubscribePut(c *gin.Context) {
 			"webhooks",
 			"for_duration",
 			"redefine_webhooks",
-			"datasource_ids",
+			"severities",
+			"extra_config",
+			"busi_groups",
 		))
 	}
 

center/router/router_builtin.go

@@ -91,6 +91,9 @@ func (rt *Router) builtinBoardCateGets(c *gin.Context) {
 		boardCate.Name = dir
 		files, err := file.FilesUnder(fp + "/" + dir + "/dashboards")
 		ginx.Dangerous(err)
+		if len(files) == 0 {
+			continue
+		}
 
 		var boards []Payload
 		for _, f := range files {
@@ -243,6 +246,9 @@ func (rt *Router) builtinAlertRules(c *gin.Context) {
 		alertCate.Name = dir
 		files, err := file.FilesUnder(fp + "/" + dir + "/alerts")
 		ginx.Dangerous(err)
+		if len(files) == 0 {
+			continue
+		}
 
 		alertRules := make(map[string][]models.AlertRule)
 		for _, f := range files {
@@ -309,3 +315,26 @@ func (rt *Router) builtinIcon(c *gin.Context) {
 	iconPath := fp + "/" + cate + "/icon/" + ginx.UrlParamStr(c, "name")
 	c.File(path.Join(iconPath))
 }
+
+func (rt *Router) builtinMarkdown(c *gin.Context) {
+	fp := rt.Center.BuiltinIntegrationsDir
+	if fp == "" {
+		fp = path.Join(runner.Cwd, "integrations")
+	}
+	cate := ginx.UrlParamStr(c, "cate")
+
+	var markdown []byte
+	markdownDir := fp + "/" + cate + "/markdown"
+	markdownFiles, err := file.FilesUnder(markdownDir)
+	if err != nil {
+		logger.Warningf("get markdown fail: %v", err)
+	} else if len(markdownFiles) > 0 {
+		f := markdownFiles[0]
+		fn := markdownDir + "/" + f
+		markdown, err = file.ReadBytes(fn)
+		if err != nil {
+			logger.Warningf("get collect fail: %v", err)
+		}
+	}
+	ginx.NewRender(c).Data(string(markdown), nil)
+}

center/router/router_captcha.go

@@ -0,0 +1,114 @@
+package router
+
+import (
+	"context"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/storage"
+	"github.com/gin-gonic/gin"
+	captcha "github.com/mojocn/base64Captcha"
+	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/logger"
+)
+
+type CaptchaRedisStore struct {
+	redis storage.Redis
+}
+
+func (s *CaptchaRedisStore) Set(id string, value string) error {
+	ctx := context.Background()
+	err := s.redis.Set(ctx, id, value, time.Duration(300*time.Second)).Err()
+	if err != nil {
+		logger.Errorf("captcha id set to redis error : %s", err.Error())
+		return err
+	}
+	return nil
+}
+
+func (s *CaptchaRedisStore) Get(id string, clear bool) string {
+	ctx := context.Background()
+	val, err := s.redis.Get(ctx, id).Result()
+	if err != nil {
+		logger.Errorf("captcha id get from redis error : %s", err.Error())
+		return ""
+	}
+
+	if clear {
+		s.redis.Del(ctx, id)
+	}
+
+	return val
+}
+
+func (s *CaptchaRedisStore) Verify(id, answer string, clear bool) bool {
+
+	old := s.Get(id, clear)
+	return old == answer
+}
+
+func (rt *Router) newCaptchaRedisStore() *CaptchaRedisStore {
+	if captchaStore == nil {
+		captchaStore = &CaptchaRedisStore{redis: rt.Redis}
+	}
+	return captchaStore
+}
+
+var captchaStore *CaptchaRedisStore
+
+type CaptchaReqBody struct {
+	Id          string
+	VerifyValue string
+}
+
+// 生成图形验证码
+func (rt *Router) generateCaptcha(c *gin.Context) {
+	var driver = captcha.NewDriverMath(60, 200, 0, captcha.OptionShowHollowLine, nil, nil, []string{"wqy-microhei.ttc"})
+	cc := captcha.NewCaptcha(driver, rt.newCaptchaRedisStore())
+	//data:image/png;base64
+	id, b64s, err := cc.Generate()
+
+	if err != nil {
+		ginx.NewRender(c).Message(err)
+		return
+	}
+
+	ginx.NewRender(c).Data(gin.H{
+		"imgdata":   b64s,
+		"captchaid": id,
+	}, nil)
+}
+
+// 验证
+func (rt *Router) captchaVerify(c *gin.Context) {
+
+	var param CaptchaReqBody
+	ginx.BindJSON(c, &param)
+
+	//verify the captcha
+	if captchaStore.Verify(param.Id, param.VerifyValue, true) {
+		ginx.NewRender(c).Message("")
+		return
+	}
+	ginx.NewRender(c).Message("incorrect verification code")
+}
+
+// 验证码开关
+func (rt *Router) ifShowCaptcha(c *gin.Context) {
+
+	if rt.HTTP.ShowCaptcha.Enable {
+		ginx.NewRender(c).Data(gin.H{
+			"show": true,
+		}, nil)
+		return
+	}
+
+	ginx.NewRender(c).Data(gin.H{
+		"show": false,
+	}, nil)
+}
+
+// 验证
+func CaptchaVerify(id string, value string) bool {
+	//verify the captcha
+	return captchaStore.Verify(id, value, true)
+}

center/router/router_datasource.go

@@ -25,6 +25,11 @@ type listReq struct {
 }
 
 func (rt *Router) datasourceList(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req listReq
 	ginx.BindJSON(c, &req)
 
@@ -65,6 +70,11 @@ func (rt *Router) datasourceBriefs(c *gin.Context) {
 }
 
 func (rt *Router) datasourceUpsert(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	username := Username(c)
@@ -105,6 +115,10 @@ func DatasourceCheck(ds models.Datasource) error {
 		return fmt.Errorf("url is empty")
 	}
 
+	if !strings.HasPrefix(ds.HTTPJson.Url, "http") {
+		return fmt.Errorf("url must start with http or https")
+	}
+
 	client := &http.Client{
 		Transport: &http.Transport{
 			TLSClientConfig: &tls.Config{
@@ -123,16 +137,14 @@ func DatasourceCheck(ds models.Datasource) error {
 	if ds.PluginType == models.PROMETHEUS {
 		subPath := "/api/v1/query"
 		query := url.Values{}
-		if strings.Contains(fullURL, "loki") {
+		if ds.HTTPJson.IsLoki() {
 			subPath = "/api/v1/labels"
-			query.Add("start", "1")
-			query.Add("end", "2")
 		} else {
 			query.Add("query", "1+1")
 		}
 		fullURL = fmt.Sprintf("%s%s?%s", ds.HTTPJson.Url, subPath, query.Encode())
 
-		req, err = http.NewRequest("POST", fullURL, nil)
+		req, err = http.NewRequest("GET", fullURL, nil)
 		if err != nil {
 			logger.Errorf("Error creating request: %v", err)
 			return fmt.Errorf("request url:%s failed", fullURL)
@@ -163,6 +175,11 @@ func DatasourceCheck(ds models.Datasource) error {
 }
 
 func (rt *Router) datasourceGet(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	err := req.Get(rt.Ctx)
@@ -170,6 +187,11 @@ func (rt *Router) datasourceGet(c *gin.Context) {
 }
 
 func (rt *Router) datasourceUpdataStatus(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	username := Username(c)
@@ -179,6 +201,11 @@ func (rt *Router) datasourceUpdataStatus(c *gin.Context) {
 }
 
 func (rt *Router) datasourceDel(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var ids []int64
 	ginx.BindJSON(c, &ids)
 	err := models.DatasourceDel(rt.Ctx, ids)

center/router/router_es_index_pattern.go

@@ -0,0 +1,81 @@
+package router
+
+import (
+	"net/http"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/gin-gonic/gin"
+	"github.com/toolkits/pkg/ginx"
+)
+
+// 创建 ES Index Pattern
+func (rt *Router) esIndexPatternAdd(c *gin.Context) {
+	var f models.EsIndexPatternFe
+	ginx.BindJSON(c, &f)
+
+	username := c.MustGet("username").(string)
+	now := time.Now().Unix()
+	f.CreateAt = now
+	f.CreateBy = username
+	f.UpdateAt = now
+	f.UpdateBy = username
+
+	err := f.Add(rt.Ctx)
+	ginx.NewRender(c).Message(err)
+}
+
+// 更新 ES Index Pattern
+func (rt *Router) esIndexPatternPut(c *gin.Context) {
+	var f models.EsIndexPatternFe
+	ginx.BindJSON(c, &f)
+
+	id := ginx.QueryInt64(c, "id")
+
+	esIndexPattern, err := models.EsIndexPatternGetById(rt.Ctx, id)
+	ginx.Dangerous(err)
+
+	if esIndexPattern == nil {
+		ginx.NewRender(c, http.StatusNotFound).Message("No such EsIndexPattern")
+		return
+	}
+
+	// f.UpdateBy = c.MustGet("username").(string)
+
+	ginx.NewRender(c).Message(esIndexPattern.Update(rt.Ctx, f))
+}
+
+// 删除 ES Index Pattern
+func (rt *Router) esIndexPatternDel(c *gin.Context) {
+	var f idsForm
+	ginx.BindJSON(c, &f)
+
+	if len(f.Ids) == 0 {
+		ginx.Bomb(http.StatusBadRequest, "ids empty")
+	}
+
+	ginx.NewRender(c).Message(models.EsIndexPatternDel(rt.Ctx, f.Ids))
+}
+
+// ES Index Pattern列表
+func (rt *Router) esIndexPatternGetList(c *gin.Context) {
+	datasourceId := ginx.QueryInt64(c, "datasource_id", 0)
+
+	var lst []*models.EsIndexPatternFe
+	var err error
+	if datasourceId != 0 {
+		lst, err = models.EsIndexPatternGets(rt.Ctx, "datasource_id = ?", datasourceId)
+	} else {
+		lst, err = models.EsIndexPatternGets(rt.Ctx, "")
+	}
+
+	ginx.NewRender(c).Data(lst, err)
+}
+
+// ES Index Pattern 单个数据
+func (rt *Router) esIndexPatternGet(c *gin.Context) {
+	id := ginx.QueryInt64(c, "id")
+
+	item, err := models.EsIndexPatternGet(rt.Ctx, "id=?", id)
+	ginx.NewRender(c).Data(item, err)
+}

center/router/router_heartbeat.go

@@ -35,9 +35,19 @@ func (rt *Router) heartbeat(c *gin.Context) {
 	err = json.Unmarshal(bs, &req)
 	ginx.Dangerous(err)
 
-	req.Offset = (time.Now().UnixMilli() - req.UnixTime)
-	req.RemoteAddr = c.ClientIP()
+	// maybe from pushgw
+	if req.Offset == 0 {
+		req.Offset = (time.Now().UnixMilli() - req.UnixTime)
+	}
+
+	if req.RemoteAddr == "" {
+		req.RemoteAddr = c.ClientIP()
+	}
+
 	rt.MetaSet.Set(req.Hostname, req)
+	var items = make(map[string]struct{})
+	items[req.Hostname] = struct{}{}
+	rt.IdentSet.MSet(items)
 
 	gid := ginx.QueryInt64(c, "gid", 0)
 

center/router/router_login.go

@@ -1,6 +1,7 @@
 package router
 
 import (
+	"encoding/base64"
 	"fmt"
 	"net/http"
 	"strconv"
@@ -12,6 +13,7 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/ldapx"
 	"github.com/ccfos/nightingale/v6/pkg/oauth2x"
 	"github.com/ccfos/nightingale/v6/pkg/oidcx"
+	"github.com/ccfos/nightingale/v6/pkg/secu"
 	"github.com/pelletier/go-toml/v2"
 
 	"github.com/dgrijalva/jwt-go"
@@ -21,20 +23,40 @@ import (
 )
 
 type loginForm struct {
-	Username string `json:"username" binding:"required"`
-	Password string `json:"password" binding:"required"`
+	Username    string `json:"username" binding:"required"`
+	Password    string `json:"password" binding:"required"`
+	Captchaid   string `json:"captchaid"`
+	Verifyvalue string `json:"verifyvalue"`
 }
 
 func (rt *Router) loginPost(c *gin.Context) {
 	var f loginForm
 	ginx.BindJSON(c, &f)
+	logger.Infof("username:%s login from:%s", f.Username, c.ClientIP())
 
-	user, err := models.PassLogin(rt.Ctx, f.Username, f.Password)
+	if rt.HTTP.ShowCaptcha.Enable {
+		if !CaptchaVerify(f.Captchaid, f.Verifyvalue) {
+			ginx.NewRender(c).Message("incorrect verification code")
+			return
+		}
+	}
+	authPassWord := f.Password
+	// need decode
+	if rt.HTTP.RSA.OpenRSA {
+		decPassWord, err := secu.Decrypt(f.Password, rt.HTTP.RSA.RSAPrivateKey, rt.HTTP.RSA.RSAPassWord)
+		if err != nil {
+			logger.Errorf("RSA Decrypt failed: %v username: %s", err, f.Username)
+			ginx.NewRender(c).Message(err)
+			return
+		}
+		authPassWord = decPassWord
+	}
+	user, err := models.PassLogin(rt.Ctx, f.Username, authPassWord)
 	if err != nil {
 		// pass validate fail, try ldap
 		if rt.Sso.LDAP.Enable {
 			roles := strings.Join(rt.Sso.LDAP.DefaultRoles, " ")
-			user, err = models.LdapLogin(rt.Ctx, f.Username, f.Password, roles, rt.Sso.LDAP)
+			user, err = models.LdapLogin(rt.Ctx, f.Username, authPassWord, roles, rt.Sso.LDAP)
 			if err != nil {
 				logger.Debugf("ldap login failed: %v username: %s", err, f.Username)
 				ginx.NewRender(c).Message(err)
@@ -67,6 +89,7 @@ func (rt *Router) loginPost(c *gin.Context) {
 }
 
 func (rt *Router) logoutPost(c *gin.Context) {
+	logger.Infof("username:%s login from:%s", c.GetString("username"), c.ClientIP())
 	metadata, err := rt.extractTokenMetadata(c.Request)
 	if err != nil {
 		ginx.NewRender(c, http.StatusBadRequest).Message("failed to parse jwt token")
@@ -492,10 +515,23 @@ type SsoConfigOutput struct {
 }
 
 func (rt *Router) ssoConfigNameGet(c *gin.Context) {
+	var oidcDisplayName, casDisplayName, oauthDisplayName string
+	if rt.Sso.OIDC != nil {
+		oidcDisplayName = rt.Sso.OIDC.GetDisplayName()
+	}
+
+	if rt.Sso.CAS != nil {
+		casDisplayName = rt.Sso.CAS.GetDisplayName()
+	}
+
+	if rt.Sso.OAuth2 != nil {
+		oauthDisplayName = rt.Sso.OAuth2.GetDisplayName()
+	}
+
 	ginx.NewRender(c).Data(SsoConfigOutput{
-		OidcDisplayName:  rt.Sso.OIDC.GetDisplayName(),
-		CasDisplayName:   rt.Sso.CAS.GetDisplayName(),
-		OauthDisplayName: rt.Sso.OAuth2.GetDisplayName(),
+		OidcDisplayName:  oidcDisplayName,
+		CasDisplayName:   casDisplayName,
+		OauthDisplayName: oauthDisplayName,
 	}, nil)
 }
 
@@ -520,8 +556,7 @@ func (rt *Router) ssoConfigUpdate(c *gin.Context) {
 		var config oidcx.Config
 		err := toml.Unmarshal([]byte(f.Content), &config)
 		ginx.Dangerous(err)
-
-		err = rt.Sso.OIDC.Reload(config)
+		rt.Sso.OIDC, err = oidcx.New(config)
 		ginx.Dangerous(err)
 	case "CAS":
 		var config cas.Config
@@ -537,3 +572,19 @@ func (rt *Router) ssoConfigUpdate(c *gin.Context) {
 
 	ginx.NewRender(c).Message(nil)
 }
+
+type RSAConfigOutput struct {
+	OpenRSA      bool
+	RSAPublicKey string
+}
+
+func (rt *Router) rsaConfigGet(c *gin.Context) {
+	publicKey := ""
+	if rt.HTTP.RSA.OpenRSA {
+		publicKey = base64.StdEncoding.EncodeToString(rt.HTTP.RSA.RSAPublicKey)
+	}
+	ginx.NewRender(c).Data(RSAConfigOutput{
+		OpenRSA:      rt.HTTP.RSA.OpenRSA,
+		RSAPublicKey: publicKey,
+	}, nil)
+}

center/router/router_mute.go

@@ -5,6 +5,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/common"
 	"github.com/ccfos/nightingale/v6/models"
 
 	"github.com/gin-gonic/gin"
@@ -29,16 +30,41 @@ func (rt *Router) alertMuteGets(c *gin.Context) {
 }
 
 func (rt *Router) alertMuteAdd(c *gin.Context) {
+
 	var f models.AlertMute
 	ginx.BindJSON(c, &f)
 
 	username := c.MustGet("username").(string)
 	f.CreateBy = username
 	f.GroupId = ginx.UrlParamInt64(c, "id")
-
 	ginx.NewRender(c).Message(f.Add(rt.Ctx))
 }
 
+//Preview events (alert_cur_event) that match the mute strategy based on the following criteria:
+//business group ID (group_id, group_id), product (prod, rule_prod),
+//alert event severity (severities, severity), and event tags (tags, tags).
+//For products of type not 'host', also consider the category (cate, cate) and datasource ID (datasource_ids, datasource_id).
+func (rt *Router) alertMutePreview(c *gin.Context) {
+	//Generally the match of events would be less.
+
+	var f models.AlertMute
+	ginx.BindJSON(c, &f)
+	f.GroupId = ginx.UrlParamInt64(c, "id")
+	ginx.Dangerous(f.Verify()) //verify and parse tags json to ITags
+	events, err := models.AlertCurEventGetsFromAlertMute(rt.Ctx, &f)
+	ginx.Dangerous(err)
+
+	matchEvents := make([]*models.AlertCurEvent, 0, len(events))
+	for i := 0; i < len(events); i++ {
+		events[i].DB2Mem()
+		if common.MatchTags(events[i].TagsMap, f.ITags) {
+			matchEvents = append(matchEvents, events[i])
+		}
+	}
+	ginx.NewRender(c).Data(matchEvents, err)
+
+}
+
 func (rt *Router) alertMuteAddByService(c *gin.Context) {
 	var f models.AlertMute
 	ginx.BindJSON(c, &f)

center/router/router_notify_config.go

@@ -2,15 +2,17 @@ package router
 
 import (
 	"encoding/json"
+	"strings"
 
 	"github.com/ccfos/nightingale/v6/alert/aconf"
 	"github.com/ccfos/nightingale/v6/alert/sender"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
-	"github.com/pelletier/go-toml/v2"
 
 	"github.com/gin-gonic/gin"
+	"github.com/pelletier/go-toml/v2"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/str"
 )
 
 func (rt *Router) webhookGets(c *gin.Context) {
@@ -178,16 +180,42 @@ func (rt *Router) notifyConfigPut(c *gin.Context) {
 
 	if f.Ckey == models.SMTP {
 		// 重置邮件发送器
-		var smtp aconf.SMTPConfig
-		err := toml.Unmarshal([]byte(f.Cval), &smtp)
-		ginx.Dangerous(err)
-
-		if smtp.Host == "" || smtp.Port == 0 {
-			ginx.Bomb(200, "smtp host or port can not be empty")
-		}
+		smtp := smtpValidate(f.Cval)
 
 		go sender.RestartEmailSender(smtp)
 	}
 
 	ginx.NewRender(c).Message(nil)
 }
+
+func smtpValidate(smtpStr string) aconf.SMTPConfig {
+	var smtp aconf.SMTPConfig
+	ginx.Dangerous(toml.Unmarshal([]byte(smtpStr), &smtp))
+
+	if smtp.Host == "" || smtp.Port == 0 {
+		ginx.Bomb(200, "smtp host or port can not be empty")
+	}
+	return smtp
+}
+
+type form struct {
+	models.Configs
+	Email string `json:"email"`
+}
+
+//After configuring the aconf.SMTPConfig, users can choose to perform a test. In this test, the function attempts to send an email
+func (rt *Router) attemptSendEmail(c *gin.Context) {
+	var f form
+	ginx.BindJSON(c, &f)
+
+	if f.Email = strings.TrimSpace(f.Email); f.Email == "" || !str.IsMail(f.Email) {
+		ginx.Bomb(200, "email(%s) invalid", f.Email)
+	}
+
+	if f.Ckey != models.SMTP {
+		ginx.Bomb(200, "config(%v) invalid", f)
+	}
+	smtp := smtpValidate(f.Cval)
+	ginx.NewRender(c).Message(sender.SendEmail("Email test", "email content", []string{f.Email}, smtp))
+
+}

center/router/router_notify_tpl.go

@@ -10,12 +10,25 @@ import (
 	"github.com/ccfos/nightingale/v6/center/cconf"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/tplx"
+
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/str"
 )
 
 func (rt *Router) notifyTplGets(c *gin.Context) {
+	m := make(map[string]struct{})
+	for _, channel := range models.DefaultChannels {
+		m[channel] = struct{}{}
+	}
+	m[models.EmailSubject] = struct{}{}
+
 	lst, err := models.NotifyTplGets(rt.Ctx)
+	for i := 0; i < len(lst); i++ {
+		if _, exists := m[lst[i].Channel]; exists {
+			lst[i].BuiltIn = true
+		}
+	}
 
 	ginx.NewRender(c).Data(lst, err)
 }
@@ -23,11 +36,7 @@ func (rt *Router) notifyTplGets(c *gin.Context) {
 func (rt *Router) notifyTplUpdateContent(c *gin.Context) {
 	var f models.NotifyTpl
 	ginx.BindJSON(c, &f)
-
-	if err := templateValidate(f); err != nil {
-		ginx.NewRender(c).Message(err.Error())
-		return
-	}
+	ginx.Dangerous(templateValidate(f))
 
 	ginx.NewRender(c).Message(f.UpdateContent(rt.Ctx))
 }
@@ -35,16 +44,28 @@ func (rt *Router) notifyTplUpdateContent(c *gin.Context) {
 func (rt *Router) notifyTplUpdate(c *gin.Context) {
 	var f models.NotifyTpl
 	ginx.BindJSON(c, &f)
-
-	if err := templateValidate(f); err != nil {
-		ginx.NewRender(c).Message(err.Error())
-		return
-	}
+	ginx.Dangerous(templateValidate(f))
 
 	ginx.NewRender(c).Message(f.Update(rt.Ctx))
 }
 
 func templateValidate(f models.NotifyTpl) error {
+	if len(f.Channel) > 32 {
+		return fmt.Errorf("channel length should not exceed 32")
+	}
+
+	if str.Dangerous(f.Channel) {
+		return fmt.Errorf("channel should not contain dangerous characters")
+	}
+
+	if len(f.Name) > 255 {
+		return fmt.Errorf("name length should not exceed 255")
+	}
+
+	if str.Dangerous(f.Name) {
+		return fmt.Errorf("name should not contain dangerous characters")
+	}
+
 	if f.Content == "" {
 		return nil
 	}
@@ -65,10 +86,7 @@ func templateValidate(f models.NotifyTpl) error {
 func (rt *Router) notifyTplPreview(c *gin.Context) {
 	var event models.AlertCurEvent
 	err := json.Unmarshal([]byte(cconf.EVENT_EXAMPLE), &event)
-	if err != nil {
-		ginx.NewRender(c).Message(err.Error())
-		return
-	}
+	ginx.Dangerous(err)
 
 	var f models.NotifyTpl
 	ginx.BindJSON(c, &f)
@@ -106,3 +124,25 @@ func (rt *Router) notifyTplPreview(c *gin.Context) {
 
 	ginx.NewRender(c).Data(ret, nil)
 }
+
+// add new notify template
+func (rt *Router) notifyTplAdd(c *gin.Context) {
+	var f models.NotifyTpl
+	ginx.BindJSON(c, &f)
+	f.Channel = strings.TrimSpace(f.Channel)
+	ginx.Dangerous(templateValidate(f))
+
+	count, err := models.NotifyTplCountByChannel(rt.Ctx, f.Channel)
+	ginx.Dangerous(err)
+	if count != 0 {
+		ginx.Bomb(200, "Refuse to create duplicate channel(unique)")
+	}
+	ginx.NewRender(c).Message(f.Create(rt.Ctx))
+}
+
+// delete notify template, not allowed to delete the system defaults(models.DefaultChannels)
+func (rt *Router) notifyTplDel(c *gin.Context) {
+	f := new(models.NotifyTpl)
+	id := ginx.UrlParamInt64(c, "id")
+	ginx.NewRender(c).Message(f.NotifyTplDelete(rt.Ctx, id))
+}

center/router/router_proxy.go

@@ -3,17 +3,20 @@ package router
 import (
 	"context"
 	"crypto/tls"
+	"fmt"
 	"net"
 	"net/http"
 	"net/http/httputil"
 	"net/url"
 	"strings"
+	"sync"
 	"time"
 
 	pkgprom "github.com/ccfos/nightingale/v6/pkg/prom"
 	"github.com/gin-gonic/gin"
 	"github.com/prometheus/common/model"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/logger"
 )
 
 type queryFormItem struct {
@@ -31,10 +34,14 @@ type batchQueryForm struct {
 func (rt *Router) promBatchQueryRange(c *gin.Context) {
 	var f batchQueryForm
 	ginx.Dangerous(c.BindJSON(&f))
+	var lst []model.Value
 
 	cli := rt.PromClients.GetCli(f.DatasourceId)
-
-	var lst []model.Value
+	if cli == nil {
+		logger.Warningf("no such datasource id: %d", f.DatasourceId)
+		ginx.NewRender(c).Data(lst, nil)
+		return
+	}
 
 	for _, item := range f.Queries {
 		r := pkgprom.Range{
@@ -66,10 +73,15 @@ func (rt *Router) promBatchQueryInstant(c *gin.Context) {
 	var f batchInstantForm
 	ginx.Dangerous(c.BindJSON(&f))
 
-	cli := rt.PromClients.GetCli(f.DatasourceId)
-
 	var lst []model.Value
 
+	cli := rt.PromClients.GetCli(f.DatasourceId)
+	if cli == nil {
+		logger.Warningf("no such datasource id: %d", f.DatasourceId)
+		ginx.NewRender(c).Data(lst, nil)
+		return
+	}
+
 	for _, item := range f.Queries {
 		resp, _, err := cli.Query(context.Background(), item.Query, time.Unix(item.Time, 0))
 		ginx.Dangerous(err)
@@ -139,21 +151,74 @@ func (rt *Router) dsProxy(c *gin.Context) {
 		http.Error(w, err.Error(), http.StatusBadGateway)
 	}
 
-	transport := &http.Transport{
-		TLSClientConfig: &tls.Config{InsecureSkipVerify: ds.HTTPJson.TLS.SkipTlsVerify},
-		Proxy:           http.ProxyFromEnvironment,
-		DialContext: (&net.Dialer{
-			Timeout: time.Duration(ds.HTTPJson.DialTimeout) * time.Millisecond,
-		}).DialContext,
-		ResponseHeaderTimeout: time.Duration(ds.HTTPJson.Timeout) * time.Millisecond,
-		MaxIdleConnsPerHost:   ds.HTTPJson.MaxIdleConnsPerHost,
+	transport, has := transportGet(dsId, ds.UpdatedAt)
+	if !has {
+		transport = &http.Transport{
+			TLSClientConfig: &tls.Config{InsecureSkipVerify: ds.HTTPJson.TLS.SkipTlsVerify},
+			Proxy:           http.ProxyFromEnvironment,
+			DialContext: (&net.Dialer{
+				Timeout: time.Duration(ds.HTTPJson.DialTimeout) * time.Millisecond,
+			}).DialContext,
+			ResponseHeaderTimeout: time.Duration(ds.HTTPJson.Timeout) * time.Millisecond,
+			MaxIdleConnsPerHost:   ds.HTTPJson.MaxIdleConnsPerHost,
+		}
+		transportPut(dsId, ds.UpdatedAt, transport)
+	}
+
+	modifyResponse := func(r *http.Response) error {
+		if r.StatusCode == http.StatusUnauthorized {
+			return fmt.Errorf("unauthorized access")
+		}
+		return nil
 	}
 
 	proxy := &httputil.ReverseProxy{
-		Director:     director,
-		Transport:    transport,
-		ErrorHandler: errFunc,
+		Director:       director,
+		Transport:      transport,
+		ErrorHandler:   errFunc,
+		ModifyResponse: modifyResponse,
 	}
 
 	proxy.ServeHTTP(c.Writer, c.Request)
 }
+
+var (
+	transports     = map[int64]http.RoundTripper{}
+	updatedAts     = map[int64]int64{}
+	transportsLock = &sync.Mutex{}
+)
+
+func transportGet(dsid, newUpdatedAt int64) (http.RoundTripper, bool) {
+	transportsLock.Lock()
+	defer transportsLock.Unlock()
+
+	tran, has := transports[dsid]
+	if !has {
+		return nil, false
+	}
+
+	oldUpdateAt, has := updatedAts[dsid]
+	if !has {
+		oldtran := tran.(*http.Transport)
+		oldtran.CloseIdleConnections()
+		delete(transports, dsid)
+		return nil, false
+	}
+
+	if oldUpdateAt != newUpdatedAt {
+		oldtran := tran.(*http.Transport)
+		oldtran.CloseIdleConnections()
+		delete(transports, dsid)
+		delete(updatedAts, dsid)
+		return nil, false
+	}
+
+	return tran, has
+}
+
+func transportPut(dsid, updatedat int64, tran http.RoundTripper) {
+	transportsLock.Lock()
+	transports[dsid] = tran
+	updatedAts[dsid] = updatedat
+	transportsLock.Unlock()
+}

center/router/router_server.go

@@ -28,6 +28,12 @@ func (rt *Router) serverHeartbeat(c *gin.Context) {
 
 func (rt *Router) serversActive(c *gin.Context) {
 	datasourceId := ginx.QueryInt64(c, "dsid")
+	engineName := ginx.QueryStr(c, "engine_name", "")
+	if engineName != "" {
+		servers, err := models.AlertingEngineGetsInstances(rt.Ctx, "engine_cluster = ? and clock > ?", engineName, time.Now().Unix()-30)
+		ginx.NewRender(c).Data(servers, err)
+		return
+	}
 
 	servers, err := models.AlertingEngineGetsInstances(rt.Ctx, "datasource_id = ? and clock > ?", datasourceId, time.Now().Unix()-30)
 	ginx.NewRender(c).Data(servers, err)

center/router/router_target.go

@@ -45,12 +45,32 @@ func (rt *Router) targetGets(c *gin.Context) {
 	bgid := ginx.QueryInt64(c, "bgid", -1)
 	query := ginx.QueryStr(c, "query", "")
 	limit := ginx.QueryInt(c, "limit", 30)
+	downtime := ginx.QueryInt64(c, "downtime", 0)
 	dsIds := queryDatasourceIds(c)
 
-	total, err := models.TargetTotal(rt.Ctx, bgid, dsIds, query)
+	var bgids []int64
+	var err error
+	if bgid == -1 {
+		user := c.MustGet("user").(*models.User)
+		if !user.IsAdmin() {
+			// 如果是非 admin 用户，全部对象的情况，找到用户有权限的业务组
+			userGroupIds, err := models.MyGroupIds(rt.Ctx, user.Id)
+			ginx.Dangerous(err)
+
+			bgids, err = models.BusiGroupIds(rt.Ctx, userGroupIds)
+			ginx.Dangerous(err)
+
+			// 将未分配业务组的对象也加入到列表中
+			bgids = append(bgids, 0)
+		}
+	} else {
+		bgids = append(bgids, bgid)
+	}
+
+	total, err := models.TargetTotal(rt.Ctx, bgids, dsIds, query, downtime)
 	ginx.Dangerous(err)
 
-	list, err := models.TargetGets(rt.Ctx, bgid, dsIds, query, limit, ginx.Offset(c, limit))
+	list, err := models.TargetGets(rt.Ctx, bgids, dsIds, query, downtime, limit, ginx.Offset(c, limit))
 	ginx.Dangerous(err)
 
 	if err == nil {
@@ -61,6 +81,12 @@ func (rt *Router) targetGets(c *gin.Context) {
 		for i := 0; i < len(list); i++ {
 			ginx.Dangerous(list[i].FillGroup(rt.Ctx, cache))
 			keys = append(keys, models.WrapIdent(list[i].Ident))
+
+			if now.Unix()-list[i].UpdateAt < 60 {
+				list[i].TargetUp = 2
+			} else if now.Unix()-list[i].UpdateAt < 180 {
+				list[i].TargetUp = 1
+			}
 		}
 
 		if len(keys) > 0 {
@@ -80,10 +106,6 @@ func (rt *Router) targetGets(c *gin.Context) {
 			}
 
 			for i := 0; i < len(list); i++ {
-				if now.Unix()-list[i].UpdateAt < 120 {
-					list[i].TargetUp = 1
-				}
-
 				if meta, ok := metaMap[list[i].Ident]; ok {
 					list[i].FillMeta(meta)
 				} else {

center/router/router_task_tpl.go

@@ -48,6 +48,19 @@ func (rt *Router) taskTplGet(c *gin.Context) {
 	}, err)
 }
 
+func (rt *Router) taskTplGetByService(c *gin.Context) {
+	tid := ginx.UrlParamInt64(c, "tid")
+
+	tpl, err := models.TaskTplGetById(rt.Ctx, tid)
+	ginx.Dangerous(err)
+
+	if tpl == nil {
+		ginx.Bomb(404, "no such task template")
+	}
+
+	ginx.NewRender(c).Data(tpl, err)
+}
+
 type taskTplForm struct {
 	Title     string   `json:"title" binding:"required"`
 	Batch     int      `json:"batch"`

center/sso/init.go

@@ -29,6 +29,8 @@ Port = 389
 BaseDn = 'dc=example,dc=org'
 BindUser = 'cn=manager,dc=example,dc=org'
 BindPass = '*******'
+# openldap format e.g. (&(uid=%s))
+# AD format e.g. (&(sAMAccountName=%s))
 AuthFilter = '(&(uid=%s))'
 CoverAttributes = true
 TLS = false

cli/upgrade/upgrade.go

@@ -18,9 +18,9 @@ func Upgrade(configFile string) error {
 		return err
 	}
 
-	ctx := ctx.NewContext(context.Background(), db, false)
+	ctx := ctx.NewContext(context.Background(), db, true)
 	for _, cluster := range config.Clusters {
-		count, err := models.GetDatasourcesCountBy(ctx, "", "", cluster.Name)
+		count, err := models.GetDatasourcesCountByName(ctx, cluster.Name)
 		if err != nil {
 			logger.Errorf("get datasource %s count error: %v", cluster.Name, err)
 			continue

cli/upgrade/upgrade.sql

@@ -8,6 +8,13 @@ insert into `role_operation`(role_name, operation) values('Standard', '/trace/ex
 insert into `role_operation`(role_name, operation) values('Standard', '/alert-rules-built-in');
 insert into `role_operation`(role_name, operation) values('Standard', '/dashboards-built-in');
 insert into `role_operation`(role_name, operation) values('Standard', '/trace/dependencies');
+insert into `role_operation`(role_name, operation) values('Standard', '/help/servers');
+insert into `role_operation`(role_name, operation) values('Standard', '/help/migrate');
+
+insert into `role_operation`(role_name, operation) values('Admin', '/help/source');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/sso');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/notification-tpls');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/notification-settings');
 
 alter table `board` add built_in tinyint(1) not null default 0 comment '0:false 1:true';
 alter table `board` add hide tinyint(1) not null default 0 comment '0:false 1:true';

cmd/alert/main.go

@@ -17,7 +17,7 @@ import (
 
 var (
 	showVersion = flag.Bool("version", false, "Show version.")
-	configDir   = flag.String("configs", osx.GetEnv("N9E_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_CONFIGS)")
+	configDir   = flag.String("configs", osx.GetEnv("N9E_ALERT_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_ALERT_CONFIGS)")
 	cryptoKey   = flag.String("crypto-key", "", "Specify the secret key for configuration file field encryption.")
 )
 

cmd/edge/edge.go

@@ -0,0 +1,77 @@
+package main
+
+import (
+	"context"
+	"errors"
+	"fmt"
+
+	"github.com/ccfos/nightingale/v6/alert"
+	"github.com/ccfos/nightingale/v6/alert/astats"
+	"github.com/ccfos/nightingale/v6/alert/process"
+	"github.com/ccfos/nightingale/v6/conf"
+	"github.com/ccfos/nightingale/v6/dumper"
+	"github.com/ccfos/nightingale/v6/memsto"
+	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/httpx"
+	"github.com/ccfos/nightingale/v6/pkg/logx"
+	"github.com/ccfos/nightingale/v6/prom"
+	"github.com/ccfos/nightingale/v6/pushgw/idents"
+	"github.com/ccfos/nightingale/v6/pushgw/writer"
+
+	alertrt "github.com/ccfos/nightingale/v6/alert/router"
+	pushgwrt "github.com/ccfos/nightingale/v6/pushgw/router"
+)
+
+func Initialize(configDir string, cryptoKey string) (func(), error) {
+	config, err := conf.InitConfig(configDir, cryptoKey)
+	if err != nil {
+		return nil, fmt.Errorf("failed to init config: %v", err)
+	}
+
+	logxClean, err := logx.Init(config.Log)
+	if err != nil {
+		return nil, err
+	}
+	//check CenterApi is default value
+	if len(config.CenterApi.Addrs) < 1 {
+		return nil, errors.New("failed to init config: the CenterApi configuration is missing")
+	}
+	ctx := ctx.NewContext(context.Background(), nil, false, config.CenterApi)
+
+	syncStats := memsto.NewSyncStats()
+
+	targetCache := memsto.NewTargetCache(ctx, syncStats, nil)
+	busiGroupCache := memsto.NewBusiGroupCache(ctx, syncStats)
+	idents := idents.New(ctx)
+	writers := writer.NewWriters(config.Pushgw)
+	pushgwRouter := pushgwrt.New(config.HTTP, config.Pushgw, targetCache, busiGroupCache, idents, writers, ctx)
+	r := httpx.GinEngine(config.Global.RunMode, config.HTTP)
+	pushgwRouter.Config(r)
+
+	if !config.Alert.Disable {
+		alertStats := astats.NewSyncStats()
+		dsCache := memsto.NewDatasourceCache(ctx, syncStats)
+		alertMuteCache := memsto.NewAlertMuteCache(ctx, syncStats)
+		alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
+		notifyConfigCache := memsto.NewNotifyConfigCache(ctx)
+		userCache := memsto.NewUserCache(ctx, syncStats)
+		userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
+
+		promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
+		externalProcessors := process.NewExternalProcessors()
+
+		alert.Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache, alertRuleCache, notifyConfigCache, dsCache, ctx, promClients, userCache, userGroupCache)
+
+		alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
+
+		alertrtRouter.Config(r)
+	}
+
+	dumper.ConfigRouter(r)
+	httpClean := httpx.Init(config.HTTP, r)
+
+	return func() {
+		logxClean()
+		httpClean()
+	}, nil
+}

cmd/edge/main.go

@@ -0,0 +1,68 @@
+package main
+
+import (
+	"flag"
+	"fmt"
+	"log"
+	"os"
+	"os/signal"
+	"syscall"
+
+	"github.com/ccfos/nightingale/v6/pkg/osx"
+	"github.com/ccfos/nightingale/v6/pkg/version"
+
+	"github.com/toolkits/pkg/runner"
+)
+
+var (
+	showVersion = flag.Bool("version", false, "Show version.")
+	configDir   = flag.String("configs", osx.GetEnv("N9E_EDGE_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_EDGE_CONFIGS)")
+	cryptoKey   = flag.String("crypto-key", "", "Specify the secret key for configuration file field encryption.")
+)
+
+func main() {
+	flag.Parse()
+
+	if *showVersion {
+		fmt.Println(version.Version)
+		os.Exit(0)
+	}
+
+	printEnv()
+
+	cleanFunc, err := Initialize(*configDir, *cryptoKey)
+	if err != nil {
+		log.Fatalln("failed to initialize:", err)
+	}
+
+	code := 1
+	sc := make(chan os.Signal, 1)
+	signal.Notify(sc, syscall.SIGHUP, syscall.SIGINT, syscall.SIGTERM, syscall.SIGQUIT)
+
+EXIT:
+	for {
+		sig := <-sc
+		fmt.Println("received signal:", sig.String())
+		switch sig {
+		case syscall.SIGQUIT, syscall.SIGTERM, syscall.SIGINT:
+			code = 0
+			break EXIT
+		case syscall.SIGHUP:
+			// reload configuration?
+		default:
+			break EXIT
+		}
+	}
+
+	cleanFunc()
+	fmt.Println("process exited")
+	os.Exit(code)
+}
+
+func printEnv() {
+	runner.Init()
+	fmt.Println("runner.cwd:", runner.Cwd)
+	fmt.Println("runner.hostname:", runner.Hostname)
+	fmt.Println("runner.fd_limits:", runner.FdLimits())
+	fmt.Println("runner.vm_limits:", runner.VMLimits())
+}

cmd/pushgw/main.go

@@ -17,7 +17,7 @@ import (
 
 var (
 	showVersion = flag.Bool("version", false, "Show version.")
-	configDir   = flag.String("configs", osx.GetEnv("N9E_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_CONFIGS)")
+	configDir   = flag.String("configs", osx.GetEnv("N9E_PUSHGW_CONFIGS", "etc"), "Specify configuration directory.(env:N9E_PUSHGW_CONFIGS)")
 	cryptoKey   = flag.String("crypto-key", "", "Specify the secret key for configuration file field encryption.")
 )
 

conf/conf.go

@@ -14,8 +14,6 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/ormx"
 	"github.com/ccfos/nightingale/v6/pushgw/pconf"
 	"github.com/ccfos/nightingale/v6/storage"
-
-	"github.com/gin-gonic/gin"
 )
 
 type ConfigType struct {
@@ -32,8 +30,10 @@ type ConfigType struct {
 }
 
 type CenterApi struct {
-	Addrs     []string
-	BasicAuth gin.Accounts
+	Addrs         []string
+	BasicAuthUser string
+	BasicAuthPass string
+	Timeout       int64
 }
 
 type GlobalConfig struct {
@@ -48,7 +48,7 @@ func InitConfig(configDir, cryptoKey string) (*ConfigType, error) {
 	}
 
 	config.Pushgw.PreCheck()
-	config.Alert.PreCheck()
+	config.Alert.PreCheck(configDir)
 	config.Center.PreCheck()
 
 	err := decryptConfig(config, cryptoKey)

conf/crypto.go

@@ -14,39 +14,22 @@ func decryptConfig(config *ConfigType, cryptoKey string) error {
 
 	config.DB.DSN = decryptDsn
 
-	for k := range config.HTTP.Alert.BasicAuth {
-		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.Alert.BasicAuth[k], cryptoKey)
+	for k := range config.HTTP.APIForService.BasicAuth {
+		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.APIForService.BasicAuth[k], cryptoKey)
 		if err != nil {
 			return fmt.Errorf("failed to decrypt http basic auth password: %s", err)
 		}
 
-		config.HTTP.Alert.BasicAuth[k] = decryptPwd
+		config.HTTP.APIForService.BasicAuth[k] = decryptPwd
 	}
 
-	for k := range config.HTTP.Pushgw.BasicAuth {
-		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.Pushgw.BasicAuth[k], cryptoKey)
+	for k := range config.HTTP.APIForAgent.BasicAuth {
+		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.APIForAgent.BasicAuth[k], cryptoKey)
 		if err != nil {
 			return fmt.Errorf("failed to decrypt http basic auth password: %s", err)
 		}
 
-		config.HTTP.Pushgw.BasicAuth[k] = decryptPwd
-	}
-
-	for k := range config.HTTP.Heartbeat.BasicAuth {
-		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.Heartbeat.BasicAuth[k], cryptoKey)
-		if err != nil {
-			return fmt.Errorf("failed to decrypt http basic auth password: %s", err)
-		}
-
-		config.HTTP.Heartbeat.BasicAuth[k] = decryptPwd
-	}
-
-	for k := range config.HTTP.Service.BasicAuth {
-		decryptPwd, err := secu.DealWithDecrypt(config.HTTP.Service.BasicAuth[k], cryptoKey)
-		if err != nil {
-			return fmt.Errorf("failed to decrypt http basic auth password: %s", err)
-		}
-		config.HTTP.Service.BasicAuth[k] = decryptPwd
+		config.HTTP.APIForAgent.BasicAuth[k] = decryptPwd
 	}
 
 	for i, v := range config.Pushgw.Writers {

doc/community-governance.md

@@ -77,4 +77,3 @@ Committer 记录并公示于 **[COMMITTERS](https://github.com/ccfos/nightingale
 2. 提问之前请先搜索 [Github Issues](https://github.com/ccfos/nightingale/issues "Github Issue")；
 3. 我们优先推荐通过提交 [Github Issue](https://github.com/ccfos/nightingale/issues "Github Issue") 来提问，如果[有问题点击这里](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&template=bug_report.yml "有问题点击这里") | [有需求建议点击这里](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Ffeature&template=enhancement.md "有需求建议点击这里")；
 
-最后，我们推荐你加入微信群，针对相关开放式问题，相互交流咨询 (请先加好友：[UlricGO](https://www.gitlink.org.cn/UlricQin/gist/tree/master/self.jpeg "UlricGO") 备注：夜莺加群+姓名+公司，交流群里会有开发者团队和专业、热心的群友回答问题)。

docker/Dockerfile.goreleaser

@@ -6,7 +6,7 @@ ADD n9e /app/
 ADD etc /app/
 ADD integrations /app/integrations/
 ADD --chmod=755 https://github.com/ufoscout/docker-compose-wait/releases/download/2.11.0/wait_x86_64 /wait
-RUN chmod +x /wait
+RUN chmod +x /wait && pip install requests
 
 EXPOSE 17000
 

docker/docker-compose.yaml

@@ -3,7 +3,7 @@ version: "3.7"
 services:
   mysql:
     # platform: linux/x86_64
-    image: "mysql:5.7"
+    image: "mysql:8"
     container_name: mysql
     hostname: mysql
     restart: always
@@ -43,22 +43,22 @@ services:
       - "--enable-feature=remote-write-receiver"
       - "--query.lookback-delta=2m"
 
-  ibex:
-    image: ulric2019/ibex:0.3
-    container_name: ibex
-    hostname: ibex
-    restart: always
-    environment:
-      GIN_MODE: release
-      TZ: Asia/Shanghai
-      WAIT_HOSTS: 127.0.0.1:3306
-    volumes:
-      - ./ibexetc:/app/etc
-    network_mode: host
-    depends_on:
-      - mysql
-    command: >
-      sh -c "/wait && /app/ibex server"
+  # ibex:
+  #   image: ulric2019/ibex:0.3
+  #   container_name: ibex
+  #   hostname: ibex
+  #   restart: always
+  #   environment:
+  #     GIN_MODE: release
+  #     TZ: Asia/Shanghai
+  #     WAIT_HOSTS: 127.0.0.1:3306
+  #   volumes:
+  #     - ./ibexetc:/app/etc
+  #   network_mode: host
+  #   depends_on:
+  #     - mysql
+  #   command: >
+  #     sh -c "/wait && /app/ibex server"
 
   n9e:
     image: flashcatcloud/nightingale:latest
@@ -76,7 +76,7 @@ services:
       - mysql
       - redis
       - prometheus
-      - ibex
+      # - ibex
     command: >
       sh -c "/wait && /app/n9e"
 
@@ -97,4 +97,4 @@ services:
     network_mode: host
     depends_on:
       - n9e
-      - ibex
+      # - ibex

docker/experience_pg_vm/initsql_for_postgres/a-n9e-for-Postgres.sql

@@ -53,7 +53,7 @@ insert into user_group_member(group_id, user_id) values(1, 1);
 CREATE TABLE configs (
     id bigserial,
     ckey varchar(191) not null,
-    cval varchar(4096) not null default '',
+    cval text not null default '',
     PRIMARY KEY (id),
     UNIQUE (ckey)
 ) ;
@@ -94,10 +94,18 @@ insert into role_operation(role_name, operation) values('Standard', '/log/explor
 insert into role_operation(role_name, operation) values('Standard', '/trace/explorer');
 insert into role_operation(role_name, operation) values('Standard', '/help/version');
 insert into role_operation(role_name, operation) values('Standard', '/help/contact');
+insert into role_operation(role_name, operation) values('Standard', '/help/servers');
+insert into role_operation(role_name, operation) values('Standard', '/help/migrate');
+
 insert into role_operation(role_name, operation) values('Standard', '/alert-rules-built-in');
 insert into role_operation(role_name, operation) values('Standard', '/dashboards-built-in');
 insert into role_operation(role_name, operation) values('Standard', '/trace/dependencies');
 
+insert into role_operation(role_name, operation) values('Admin', '/help/source');
+insert into role_operation(role_name, operation) values('Admin', '/help/sso');
+insert into role_operation(role_name, operation) values('Admin', '/help/notification-tpls');
+insert into role_operation(role_name, operation) values('Admin', '/help/notification-settings');
+
 insert into role_operation(role_name, operation) values('Standard', '/users');
 insert into role_operation(role_name, operation) values('Standard', '/user-groups');
 insert into role_operation(role_name, operation) values('Standard', '/user-groups/add');
@@ -292,6 +300,7 @@ CREATE TABLE alert_rule (
     runbook_url varchar(255),
     append_tags varchar(255) not null default '' ,
     annotations text not null ,
+    extra_config text not null ,
     create_at bigint not null default 0,
     create_by varchar(64) not null default '',
     update_at bigint not null default 0,
@@ -320,7 +329,7 @@ COMMENT ON COLUMN alert_rule.recover_duration IS 'unit: s';
 COMMENT ON COLUMN alert_rule.callbacks IS 'split by space: http://a.com/api/x http://a.com/api/y';
 COMMENT ON COLUMN alert_rule.append_tags IS 'split by space: service=n9e mod=api';
 COMMENT ON COLUMN alert_rule.annotations IS 'annotations';
-
+COMMENT ON COLUMN alert_rule.extra_config IS 'extra_config';
 
 CREATE TABLE alert_mute (
     id bigserial,
@@ -337,6 +346,7 @@ CREATE TABLE alert_mute (
     disabled smallint not null default 0 ,
     mute_time_type smallint not null default 0,
     periodic_mutes varchar(4096) not null default '',
+    severities varchar(32) not null default '',
     create_at bigint not null default 0,
     create_by varchar(64) not null default '',
     update_at bigint not null default 0,
@@ -363,13 +373,15 @@ CREATE TABLE alert_subscribe (
     datasource_ids varchar(255) not null default '' ,
     cluster varchar(128) not null,
     rule_id bigint not null default 0,
-    tags varchar(4096) not null default '' ,
+    severities varchar(32) not null default '',
+    tags varchar(4096) not null default '[]',
     redefine_severity smallint default 0 ,
     new_severity smallint not null ,
     redefine_channels smallint default 0 ,
     new_channels varchar(255) not null default '' ,
     user_group_ids varchar(250) not null ,
     webhooks text not null,
+    extra_config text not null,
     redefine_webhooks smallint default 0,
     for_duration bigint not null default 0,
     create_at bigint not null default 0,
@@ -389,8 +401,9 @@ COMMENT ON COLUMN alert_subscribe.new_severity IS '0:Emergency 1:Warning 2:Notic
 COMMENT ON COLUMN alert_subscribe.redefine_channels IS 'is redefine channels?';
 COMMENT ON COLUMN alert_subscribe.new_channels IS 'split by space: sms voice email dingtalk wecom';
 COMMENT ON COLUMN alert_subscribe.user_group_ids IS 'split by space 1 34 5, notify cc to user_group_ids';
+COMMENT ON COLUMN alert_subscribe.extra_config IS 'extra_config';
+
 
-  
 CREATE TABLE target (
     id bigserial,
     group_id bigint not null default 0 ,
@@ -456,6 +469,7 @@ CREATE TABLE recording_rule (
     prom_ql varchar(8192) not null ,
     prom_eval_interval int not null ,
     append_tags varchar(255) default '' ,
+    query_configs text not null ,
     create_at bigint default '0',
     create_by varchar(64) default '',
     update_at bigint default '0',
@@ -472,6 +486,7 @@ COMMENT ON COLUMN recording_rule.disabled IS '0:enabled 1:disabled';
 COMMENT ON COLUMN recording_rule.prom_ql IS 'promql';
 COMMENT ON COLUMN recording_rule.prom_eval_interval IS 'evaluate interval';
 COMMENT ON COLUMN recording_rule.append_tags IS 'split by space: service=n9e mod=api';
+COMMENT ON COLUMN recording_rule.query_configs IS 'query configs';
 
 
 CREATE TABLE alert_aggr_view (
@@ -732,4 +747,21 @@ CREATE TABLE sso_config (
     content text not null,
     PRIMARY KEY (id),
     UNIQUE (name)
-) ;
+) ;
+
+
+CREATE TABLE es_index_pattern (
+    id bigserial,
+    datasource_id bigint not null default 0,
+    name varchar(191) not null,
+    time_field varchar(128) not null default '@timestamp',
+    allow_hide_system_indices smallint not null default 0,
+    fields_format varchar(4096) not null default '',
+    create_at bigint default '0',
+    create_by varchar(64) default '',
+    update_at bigint default '0',
+    update_by varchar(64) default '',
+    PRIMARY KEY (id),
+    UNIQUE (datasource_id, name)
+) ;
+COMMENT ON COLUMN es_index_pattern.datasource_id IS 'datasource id';

docker/experience_pg_vm/initsql_for_postgres/b-ibex-for-Postgres.sql

@@ -1,16 +1,17 @@
 CREATE TABLE task_meta
 (
-    id        bigserial,
-    title     varchar(255)    not null default '',
-    account   varchar(64)     not null,
-    batch     int     not null default 0,
-    tolerance int     not null default 0,
-    timeout   int     not null default 0,
-    pause     varchar(255)    not null default '',
-    script    text            not null,
-    args      varchar(512)    not null default '',
-    creator   varchar(64)     not null default '',
-    created   timestamp       not null default CURRENT_TIMESTAMP,
+    id          bigserial,
+    title       varchar(255)    not null default '',
+    account     varchar(64)     not null,
+    batch       int     not null default 0,
+    tolerance   int     not null default 0,
+    timeout     int     not null default 0,
+    pause       varchar(255)    not null default '',
+    script      text            not null,
+    args        varchar(512)    not null default '',
+    stdin       varchar(1024)   not null default '' ,
+    creator     varchar(64)     not null default '',
+    created     timestamp       not null default CURRENT_TIMESTAMP,
     PRIMARY KEY (id)
 ) ;
 CREATE INDEX task_meta_creator_idx ON task_meta (creator);

docker/experience_pg_vm/n9eetc_pg/config.toml

@@ -9,7 +9,7 @@ Level = "DEBUG"
 # stdout, stderr, file
 Output = "stdout"
 # # rotate by time
-# KeepHours: 4
+# KeepHours = 4
 # # rotate by size
 # RotateNum = 3
 # # unit: MB
@@ -41,24 +41,17 @@ WriteTimeout = 40
 # http server idle timeout, unit: s
 IdleTimeout = 120
 
-[HTTP.Pushgw]
+[HTTP.ShowCaptcha]
+Enable = false 
+
+[HTTP.APIForAgent]
 Enable = true 
-# [HTTP.Pushgw.BasicAuth]
+# [HTTP.APIForAgent.BasicAuth]
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
-[HTTP.Alert]
+[HTTP.APIForService]
 Enable = true 
-[HTTP.Alert.BasicAuth]
-user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
-
-[HTTP.Heartbeat]
-Enable = true 
-# [HTTP.Heartbeat.BasicAuth]
-# user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
-
-[HTTP.Service]
-Enable = true 
-[HTTP.Service.BasicAuth]
+[HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.JWTAuth]
@@ -77,6 +70,16 @@ Enable = false
 HeaderUserNameKey = "X-User-Name"
 DefaultRoles = ["Standard"]
 
+[HTTP.RSA]
+# open RSA
+OpenRSA = false
+# RSA public key
+RSAPublicKeyPath = "/etc/n9e/public.pem"
+# RSA private key
+RSAPrivateKeyPath = "/etc/n9e/private.pem"
+# RSA private key password
+RSAPassWord = ""
+
 [DB]
 DSN="host=postgres port=5432 user=root dbname=n9e_v6 password=1234 sslmode=disable"
 # enable debug mode or not
@@ -115,7 +118,7 @@ RedisType = "standalone"
 IP = ""
 # unit ms
 Interval = 1000
-ClusterName = "default"
+EngineName = "default"
 
 # [Alert.Alerting]
 # NotifyConcurrency = 10
@@ -128,16 +131,49 @@ I18NHeaderKey = "X-Language"
 PromQuerier = true
 AlertDetail = true
 
-[Center.Ibex]
-Address = "http://ibex:10090"
-# basic auth
-BasicAuthUser = "ibex"
-BasicAuthPass = "ibex"
-# unit: ms
-Timeout = 3000
-
 [Pushgw]
+# use target labels in database instead of in series
 LabelRewrite = true
+# # default busigroup key name
+# BusiGroupLabelKey = "busigroup"
+# ForceUseServerTS = false
 
-[[Pushgw.Writers]]
-Url = "http://victoriametrics:8428/api/v1/write"
+# [Pushgw.DebugSample]
+# ident = "xx"
+# __name__ = "xx"
+
+# [Pushgw.WriterOpt]
+# QueueMaxSize = 1000000
+# QueuePopSize = 1000
+
+[[Pushgw.Writers]] 
+# Url = "http://127.0.0.1:8480/insert/0/prometheus/api/v1/write"
+Url = "http://victoriametrics:8428/api/v1/write"
+# Basic auth username
+BasicAuthUser = ""
+# Basic auth password
+BasicAuthPass = ""
+# timeout settings, unit: ms
+Headers = ["X-From", "n9e"]
+Timeout = 10000
+DialTimeout = 3000
+TLSHandshakeTimeout = 30000
+ExpectContinueTimeout = 1000
+IdleConnTimeout = 90000
+# time duration, unit: ms
+KeepAlive = 30000
+MaxConnsPerHost = 0
+MaxIdleConns = 100
+MaxIdleConnsPerHost = 100
+## Optional TLS Config
+# UseTLS = false
+# TLSCA = "/etc/n9e/ca.pem"
+# TLSCert = "/etc/n9e/cert.pem"
+# TLSKey = "/etc/n9e/key.pem"
+# InsecureSkipVerify = false
+# [[Writers.WriteRelabels]]
+# Action = "replace"
+# SourceLabels = ["__address__"]
+# Regex = "([^:]+)(?::\\d+)?"
+# Replacement = "$1:80"
+# TargetLabel = "__address__"

docker/experience_pg_vm/n9eetc_pg/template/email.tpl

@@ -214,7 +214,7 @@
 
             <footer>
                 <div class="copyright" style="font-style: italic">
-                    我们希望与您一起，将监控这个事情，做到极致！
+                    报警太多？使用 <a href="https://flashcat.cloud/product/flashduty/" target="_blank">FlashDuty</a> 做告警聚合降噪、排班OnCall！
                 </div>
             </footer>
         </div>

docker/initsql/a-n9e.sql

@@ -54,7 +54,7 @@ insert into user_group_member(group_id, user_id) values(1, 1);
 CREATE TABLE `configs` (
     `id` bigint unsigned not null auto_increment,
     `ckey` varchar(191) not null,
-    `cval` varchar(4096) not null default '',
+    `cval` text not null,
     PRIMARY KEY (`id`),
     UNIQUE KEY (`ckey`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
@@ -94,10 +94,17 @@ insert into `role_operation`(role_name, operation) values('Standard', '/log/expl
 insert into `role_operation`(role_name, operation) values('Standard', '/trace/explorer');
 insert into `role_operation`(role_name, operation) values('Standard', '/help/version');
 insert into `role_operation`(role_name, operation) values('Standard', '/help/contact');
+insert into `role_operation`(role_name, operation) values('Standard', '/help/servers');
+insert into `role_operation`(role_name, operation) values('Standard', '/help/migrate');
 insert into `role_operation`(role_name, operation) values('Standard', '/alert-rules-built-in');
 insert into `role_operation`(role_name, operation) values('Standard', '/dashboards-built-in');
 insert into `role_operation`(role_name, operation) values('Standard', '/trace/dependencies');
 
+insert into `role_operation`(role_name, operation) values('Admin', '/help/source');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/sso');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/notification-tpls');
+insert into `role_operation`(role_name, operation) values('Admin', '/help/notification-settings');
+
 insert into `role_operation`(role_name, operation) values('Standard', '/users');
 insert into `role_operation`(role_name, operation) values('Standard', '/user-groups');
 insert into `role_operation`(role_name, operation) values('Standard', '/user-groups/add');
@@ -274,6 +281,7 @@ CREATE TABLE `alert_rule` (
     `runbook_url` varchar(255),
     `append_tags` varchar(255) not null default '' comment 'split by space: service=n9e mod=api',
     `annotations` text not null comment 'annotations',
+    `extra_config` text not null comment 'extra_config',
     `create_at` bigint not null default 0,
     `create_by` varchar(64) not null default '',
     `update_at` bigint not null default 0,
@@ -298,6 +306,7 @@ CREATE TABLE `alert_mute` (
     `disabled` tinyint(1) not null default 0 comment '0:enabled 1:disabled',
     `mute_time_type` tinyint(1) not null default 0,
     `periodic_mutes` varchar(4096) not null default '',
+    `severities` varchar(32) not null default '',
     `create_at` bigint not null default 0,
     `create_by` varchar(64) not null default '',
     `update_at` bigint not null default 0,
@@ -317,6 +326,7 @@ CREATE TABLE `alert_subscribe` (
     `datasource_ids` varchar(255) not null default '' comment 'datasource ids',
     `cluster` varchar(128) not null,
     `rule_id` bigint not null default 0,
+    `severities` varchar(32) not null default '',
     `tags` varchar(4096) not null default '' comment 'json,map,tagkey->regexp|value',
     `redefine_severity` tinyint(1) default 0 comment 'is redefine severity?',
     `new_severity` tinyint(1) not null comment '0:Emergency 1:Warning 2:Notice',
@@ -324,6 +334,7 @@ CREATE TABLE `alert_subscribe` (
     `new_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
     `user_group_ids` varchar(250) not null comment 'split by space 1 34 5, notify cc to user_group_ids',
     `webhooks` text not null,
+    `extra_config` text not null comment 'extra_config',
     `redefine_webhooks` tinyint(1) default 0,
     `for_duration` bigint not null default 0,
     `create_at` bigint not null default 0,
@@ -395,6 +406,7 @@ CREATE TABLE `recording_rule` (
     `prom_ql` varchar(8192) not null comment 'promql',
     `prom_eval_interval` int not null comment 'evaluate interval',
     `append_tags` varchar(255) default '' comment 'split by space: service=n9e mod=api',
+    `query_configs` text not null comment 'query configs',
     `create_at` bigint default '0',
     `create_by` varchar(64) default '',
     `update_at` bigint default '0',
@@ -606,4 +618,19 @@ CREATE TABLE `sso_config` (
     `content` text not null,
     PRIMARY KEY (`id`),
     UNIQUE KEY (`name`)
+) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
+
+CREATE TABLE `es_index_pattern` (
+    `id` bigint unsigned not null auto_increment,
+    `datasource_id` bigint not null default 0 comment 'datasource id',
+    `name` varchar(191) not null,
+    `time_field` varchar(128) not null default '@timestamp',
+    `allow_hide_system_indices` tinyint(1) not null default 0,
+    `fields_format` varchar(4096) not null default '',
+    `create_at` bigint default '0',
+    `create_by` varchar(64) default '',
+    `update_at` bigint default '0',
+    `update_by` varchar(64) default '',
+    PRIMARY KEY (`id`),
+    UNIQUE KEY (`datasource_id`, `name`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;

docker/initsql/b-ibex.sql

@@ -6,17 +6,18 @@ use ibex;
 
 CREATE TABLE `task_meta`
 (
-    `id`        bigint unsigned NOT NULL AUTO_INCREMENT,
-    `title`     varchar(255)    not null default '',
-    `account`   varchar(64)     not null,
-    `batch`     int unsigned    not null default 0,
-    `tolerance` int unsigned    not null default 0,
-    `timeout`   int unsigned    not null default 0,
-    `pause`     varchar(255)    not null default '',
-    `script`    text            not null,
-    `args`      varchar(512)    not null default '',
-    `creator`   varchar(64)     not null default '',
-    `created`   timestamp       not null default CURRENT_TIMESTAMP,
+    `id`          bigint unsigned NOT NULL AUTO_INCREMENT,
+    `title`       varchar(255)    not null default '',
+    `account`     varchar(64)     not null,
+    `batch`       int unsigned    not null default 0,
+    `tolerance`   int unsigned    not null default 0,
+    `timeout`     int unsigned    not null default 0,
+    `pause`       varchar(255)    not null default '',
+    `script`      text            not null,
+    `args`        varchar(512)    not null default '',
+    `stdin`       varchar(1024)   not null default '',
+    `creator`     varchar(64)     not null default '',
+    `created`     timestamp       not null default CURRENT_TIMESTAMP,
     PRIMARY KEY (`id`),
     KEY (`creator`),
     KEY (`created`)

dumper/dumper.go

@@ -0,0 +1,8 @@
+package dumper
+
+import "github.com/gin-gonic/gin"
+
+// package level functions
+func ConfigRouter(r *gin.Engine) {
+	syncDumper.ConfigRouter(r)
+}

dumper/sync.go

@@ -0,0 +1,110 @@
+package dumper
+
+import (
+	"fmt"
+	"strings"
+	"sync"
+
+	"github.com/gin-gonic/gin"
+	"github.com/toolkits/pkg/time"
+)
+
+type SyncRecord struct {
+	Timestamp int64
+	Mills     int64
+	Count     int
+	Message   string
+}
+
+func (sr *SyncRecord) String() string {
+	var sb strings.Builder
+	sb.WriteString("timestamp: ")
+	sb.WriteString(time.Format(sr.Timestamp))
+	sb.WriteString(", mills: ")
+	sb.WriteString(fmt.Sprint(sr.Mills, "ms"))
+	sb.WriteString(", count: ")
+	sb.WriteString(fmt.Sprint(sr.Count))
+	sb.WriteString(", message: ")
+	sb.WriteString(sr.Message)
+
+	return sb.String()
+}
+
+type SyncRecords struct {
+	Current *SyncRecord
+	Last    *SyncRecord
+}
+
+type SyncDumper struct {
+	sync.RWMutex
+	records map[string]*SyncRecords
+}
+
+func NewSyncDumper() *SyncDumper {
+	return &SyncDumper{
+		records: make(map[string]*SyncRecords),
+	}
+}
+
+var syncDumper = NewSyncDumper()
+
+func (sd *SyncDumper) Put(key string, timestamp, mills int64, count int, message string) {
+	sr := &SyncRecord{
+		Timestamp: timestamp,
+		Mills:     mills,
+		Count:     count,
+		Message:   message,
+	}
+
+	sd.Lock()
+	defer sd.Unlock()
+
+	if _, ok := sd.records[key]; !ok {
+		sd.records[key] = &SyncRecords{Current: sr}
+		return
+	}
+
+	sd.records[key].Last = sd.records[key].Current
+	sd.records[key].Current = sr
+}
+
+// busi_groups:
+// last: timestamp, mills, count
+// curr: timestamp, mills, count
+func (sd *SyncDumper) Sprint() string {
+	sd.RLock()
+	defer sd.RUnlock()
+
+	var sb strings.Builder
+	sb.WriteString("\n")
+
+	for k, v := range sd.records {
+		sb.WriteString(k)
+		sb.WriteString(":\n")
+		if v.Last != nil {
+			sb.WriteString("last: ")
+			sb.WriteString(v.Last.String())
+			sb.WriteString("\n")
+		}
+		sb.WriteString("curr: ")
+		sb.WriteString(v.Current.String())
+		sb.WriteString("\n\n")
+	}
+
+	return sb.String()
+}
+
+func (sd *SyncDumper) ConfigRouter(r *gin.Engine) {
+	r.GET("/dumper/sync", func(c *gin.Context) {
+		clientIP := c.ClientIP()
+		if clientIP != "127.0.0.1" && clientIP != "::1" {
+			c.String(403, "forbidden")
+			return
+		}
+		c.String(200, sd.Sprint())
+	})
+}
+
+func PutSyncRecord(key string, timestamp, mills int64, count int, message string) {
+	syncDumper.Put(key, timestamp, mills, count, message)
+}

etc/alert.toml.example

@@ -1,60 +0,0 @@
-[Global]
-RunMode = "release"
-
-[CenterApi]
-Addrs = ["http://127.0.0.1:17000"]
-[CenterApi.BasicAuth]
-user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
-
-[Alert]
-[Alert.Heartbeat]
-# auto detect if blank
-IP = ""
-# unit ms
-Interval = 1000
-EngineName = "default02"
-
-[Log]
-# log write dir
-Dir = "logs"
-# log level: DEBUG INFO WARNING ERROR
-Level = "DEBUG"
-# stdout, stderr, file
-Output = "stdout"
-# # rotate by time
-# KeepHours = 4
-# # rotate by size
-# RotateNum = 3
-# # unit: MB
-# RotateSize = 256
-
-[HTTP]
-# http listening address
-Host = "0.0.0.0"
-# http listening port
-Port = 17001
-# https cert file path
-CertFile = ""
-# https key file path
-KeyFile = ""
-# whether print access log
-PrintAccessLog = false
-# whether enable pprof
-PProf = false
-# expose prometheus /metrics?
-ExposeMetrics = true
-# http graceful shutdown timeout, unit: s
-ShutdownTimeout = 30
-# max content length: 64M
-MaxContentLength = 67108864
-# http server read timeout, unit: s
-ReadTimeout = 20
-# http server write timeout, unit: s
-WriteTimeout = 40
-# http server idle timeout, unit: s
-IdleTimeout = 120
-
-[HTTP.Alert]
-Enable = true 
-[HTTP.Alert.BasicAuth]
-user001 = "ccc26da7b9aba533cbb263a36c07dcc5"

etc/config.toml

@@ -41,24 +41,17 @@ WriteTimeout = 40
 # http server idle timeout, unit: s
 IdleTimeout = 120
 
-[HTTP.Pushgw]
+[HTTP.ShowCaptcha]
+Enable = false 
+
+[HTTP.APIForAgent]
 Enable = true 
-# [HTTP.Pushgw.BasicAuth]
+# [HTTP.APIForAgent.BasicAuth]
 # user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
-[HTTP.Alert]
+[HTTP.APIForService]
 Enable = true 
-[HTTP.Alert.BasicAuth]
-user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
-
-[HTTP.Heartbeat]
-Enable = true 
-# [HTTP.Heartbeat.BasicAuth]
-# user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
-
-[HTTP.Service]
-Enable = true 
-[HTTP.Service.BasicAuth]
+[HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
 [HTTP.JWTAuth]
@@ -77,8 +70,19 @@ Enable = false
 HeaderUserNameKey = "X-User-Name"
 DefaultRoles = ["Standard"]
 
+[HTTP.RSA]
+# open RSA
+OpenRSA = false
+# RSA public key
+RSAPublicKeyPath = "/etc/n9e/public.pem"
+# RSA private key
+RSAPrivateKeyPath = "/etc/n9e/private.pem"
+# RSA private key password
+RSAPassWord = ""
+
 [DB]
 # postgres: host=%s port=%s user=%s dbname=%s password=%s sslmode=%s
+# postgres: DSN="host=127.0.0.1 port=5432 user=root dbname=n9e_v6 password=1234 sslmode=disable"
 DSN="root:1234@tcp(127.0.0.1:3306)/n9e_v6?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
 # enable debug mode or not
 Debug = false
@@ -141,12 +145,8 @@ LabelRewrite = true
 # __name__ = "xx"
 
 # [Pushgw.WriterOpt]
-# # Writer Options
-# QueueCount = 1000
 # QueueMaxSize = 1000000
 # QueuePopSize = 1000
-# # ident or metric
-# ShardingKey = "ident"
 
 [[Pushgw.Writers]] 
 # Url = "http://127.0.0.1:8480/insert/0/prometheus/api/v1/write"

etc/edge/edge.toml

@@ -3,9 +3,72 @@ RunMode = "release"
 
 [CenterApi]
 Addrs = ["http://127.0.0.1:17000"]
-[CenterApi.BasicAuth]
+BasicAuthUser = "user001"
+BasicAuthPass = "ccc26da7b9aba533cbb263a36c07dcc5"
+# unit: ms
+Timeout = 9000
+
+[Log]
+# log write dir
+Dir = "logs"
+# log level: DEBUG INFO WARNING ERROR
+Level = "DEBUG"
+# stdout, stderr, file
+Output = "stdout"
+# # rotate by time
+# KeepHours = 4
+# # rotate by size
+# RotateNum = 3
+# # unit: MB
+# RotateSize = 256
+
+[HTTP]
+# http listening address
+Host = "0.0.0.0"
+# http listening port
+Port = 19000
+# https cert file path
+CertFile = ""
+# https key file path
+KeyFile = ""
+# whether print access log
+PrintAccessLog = false
+# whether enable pprof
+PProf = false
+# expose prometheus /metrics?
+ExposeMetrics = true
+# http graceful shutdown timeout, unit: s
+ShutdownTimeout = 30
+# max content length: 64M
+MaxContentLength = 67108864
+# http server read timeout, unit: s
+ReadTimeout = 20
+# http server write timeout, unit: s
+WriteTimeout = 40
+# http server idle timeout, unit: s
+IdleTimeout = 120
+
+[HTTP.APIForAgent]
+Enable = true 
+# [HTTP.APIForAgent.BasicAuth]
+# user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
+
+[HTTP.APIForService]
+Enable = true 
+[HTTP.APIForService.BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
+[Alert]
+[Alert.Heartbeat]
+# auto detect if blank
+IP = ""
+# unit ms
+Interval = 1000
+EngineName = "edge"
+
+# [Alert.Alerting]
+# NotifyConcurrency = 10
+
 [Pushgw]
 # use target labels in database instead of in series
 LabelRewrite = true
@@ -18,12 +81,8 @@ LabelRewrite = true
 # __name__ = "xx"
 
 # [Pushgw.WriterOpt]
-# # Writer Options
-# QueueCount = 1000
 # QueueMaxSize = 1000000
 # QueuePopSize = 1000
-# # ident or metric
-# ShardingKey = "ident"
 
 [[Pushgw.Writers]] 
 # Url = "http://127.0.0.1:8480/insert/0/prometheus/api/v1/write"
@@ -56,48 +115,3 @@ MaxIdleConnsPerHost = 100
 # Regex = "([^:]+)(?::\\d+)?"
 # Replacement = "$1:80"
 # TargetLabel = "__address__"
-
-[Log]
-# log write dir
-Dir = "logs"
-# log level: DEBUG INFO WARNING ERROR
-Level = "DEBUG"
-# stdout, stderr, file
-Output = "stdout"
-# # rotate by time
-# KeepHours = 4
-# # rotate by size
-# RotateNum = 3
-# # unit: MB
-# RotateSize = 256
-
-[HTTP]
-# http listening address
-Host = "0.0.0.0"
-# http listening port
-Port = 17000
-# https cert file path
-CertFile = ""
-# https key file path
-KeyFile = ""
-# whether print access log
-PrintAccessLog = false
-# whether enable pprof
-PProf = false
-# expose prometheus /metrics?
-ExposeMetrics = true
-# http graceful shutdown timeout, unit: s
-ShutdownTimeout = 30
-# max content length: 64M
-MaxContentLength = 67108864
-# http server read timeout, unit: s
-ReadTimeout = 20
-# http server write timeout, unit: s
-WriteTimeout = 40
-# http server idle timeout, unit: s
-IdleTimeout = 120
-
-[HTTP.Pushgw]
-Enable = true 
-# [HTTP.Pushgw.BasicAuth]
-# user001 = "ccc26da7b9aba533cbb263a36c07dcc5"

etc/metrics.yaml

@@ -40,14 +40,14 @@ zh:
   kernel_processes_forked: fork的进程数
 
   mem_active: 活跃使用的内存总数(包括cache和buffer内存)
-  mem_available: 应用程序可用内存数
+  mem_available: 可用内存大小(bytes)
   mem_available_percent: 内存剩余百分比(0~100)
   mem_buffered: 用来给文件做缓冲大小
   mem_cached: 被高速缓冲存储器（cache memory）用的内存的大小（等于 diskcache minus SwapCache ）
   mem_commit_limit: 根据超额分配比率（'vm.overcommit_ratio'），这是当前在系统上分配可用的内存总量，这个限制只是在模式2('vm.overcommit_memory')时启用
   mem_committed_as: 目前在系统上分配的内存量。是所有进程申请的内存的总和
   mem_dirty: 等待被写回到磁盘的内存大小
-  mem_free: 空闲内存数
+  mem_free: 空闲内存大小(bytes)
   mem_high_free: 未被使用的高位内存大小
   mem_high_total: 高位内存总大小（Highmem是指所有内存高于860MB的物理内存,Highmem区域供用户程序使用，或用于页面缓存。该区域不是直接映射到内核空间。内核必须使用不同的手法使用该段内存）
   mem_huge_page_size: 每个大页的大小
@@ -74,14 +74,16 @@ zh:
   mem_write_back: 正在被写回到磁盘的内存大小
   mem_write_back_tmp: FUSE用于临时写回缓冲区的内存
 
-  net_bytes_recv: 网卡收包总数(bytes)
-  net_bytes_sent: 网卡发包总数(bytes)
+  net_bytes_recv: 网卡收包总数(bytes)，计算每秒速率时需要用到rate/irate函数
+  net_bytes_sent: 网卡发包总数(bytes)，计算每秒速率时需要用到rate/irate函数
   net_drop_in: 网卡收丢包数量
   net_drop_out: 网卡发丢包数量
   net_err_in: 网卡收包错误数量
   net_err_out: 网卡发包错误数量
   net_packets_recv: 网卡收包数量
   net_packets_sent: 网卡发包数量
+  net_bits_recv: 网卡收包总数(bits)，计算每秒速率时需要用到rate/irate函数
+  net_bits_sent: 网卡发包总数(bits)，计算每秒速率时需要用到rate/irate函数
 
   netstat_tcp_established: ESTABLISHED状态的网络链接数
   netstat_tcp_fin_wait1: FIN_WAIT1状态的网络链接数
@@ -93,10 +95,26 @@ zh:
   netstat_tcp_time_wait: TIME_WAIT状态的网络链接数
   netstat_udp_socket: UDP状态的网络链接数
 
+  netstat_sockets_used: 已使用的所有协议套接字总量
+  netstat_tcp_inuse: 正在使用（正在侦听）的TCP套接字数量
+  netstat_tcp_orphan: 无主（不属于任何进程）的TCP连接数（无用、待销毁的TCP socket数）
+  netstat_tcp_tw: TIME_WAIT状态的TCP连接数
+  netstat_tcp_alloc: 已分配（已建立、已申请到sk_buff）的TCP套接字数量
+  netstat_tcp_mem: TCP套接字内存Page使用量
+  netstat_udp_inuse: 在使用的UDP套接字数量
+  netstat_udp_mem: UDP套接字内存Page使用量
+  netstat_udplite_inuse: 正在使用的 udp lite 数量
+  netstat_raw_inuse: 正在使用的 raw socket 数量
+  netstat_frag_inuse: ip fragement 数量
+  netstat_frag_memory: ip fragement 已经分配的内存(byte）
+
   #[ping]
   ping_percent_packet_loss: ping数据包丢失百分比(%)
   ping_result_code: ping返回码('0','1')
 
+  net_response_result_code: 网络探测结果，0表示正常，非0表示异常
+  net_response_response_time: 网络探测时延，单位：秒
+
   processes_blocked: 不可中断的睡眠状态下的进程数('U','D','L')
   processes_dead: 回收中的进程数('X')
   processes_idle: 挂起的空闲进程数('I')
@@ -114,6 +132,9 @@ zh:
   system_load1: 1分钟平均load值
   system_load5: 5分钟平均load值
   system_load15: 15分钟平均load值
+  system_load_norm_1: 1分钟平均load值/逻辑CPU个数
+  system_load_norm_5: 5分钟平均load值/逻辑CPU个数
+  system_load_norm_15: 15分钟平均load值/逻辑CPU个数
   system_n_users: 用户数
   system_n_cpus: CPU核数
   system_uptime: 系统启动时间
@@ -327,8 +348,10 @@ en:
   mem_write_back: "The memory size of the disk is being written back to the disk"
   mem_write_back_tmp: "Fuse is used to temporarily write back the memory of the buffer area"
 
-  net_bytes_recv: "The total number of packaging of the network card (bytes)"
-  net_bytes_sent: "Total number of network cards (bytes)"
+  net_bytes_recv: "Total inbound traffic(bytes) of network card"
+  net_bytes_sent: "Total outbound traffic(bytes) of network card"
+  net_bits_recv: "Total inbound traffic(bits) of network card"
+  net_bits_sent: "Total outbound traffic(bits) of network card"
   net_drop_in: "The number of packets for network cards"
   net_drop_out: "The number of packets issued by the network card"
   net_err_in: "The number of incorrect packets of the network card"
@@ -363,6 +386,9 @@ en:
   system_load1: "1 minute average load value"
   system_load5: "5 minutes average load value"
   system_load15: "15 minutes average load value"
+  system_load_norm_1: "1 minute average load value/logical CPU number"
+  system_load_norm_5: "5 minutes average load value/logical CPU number"
+  system_load_norm_15: "15 minutes average load value/logical CPU number"
   system_n_users: "User number"
   system_n_cpus: "CPU nuclear number"
   system_uptime: "System startup time"
@@ -383,366 +409,366 @@ en:
   http_response_response_time: "When http ring application"
   http_response_result_code: "URL detection result 0 is normal, otherwise the URL cannot be accessed"
 
-# [mysqld_exporter]
-mysql_global_status_uptime: The number of seconds that the server has been up.(Gauge)
-mysql_global_status_uptime_since_flush_status: The number of seconds since the most recent FLUSH STATUS statement.(Gauge)
-mysql_global_status_queries: The number of statements executed by the server. This variable includes statements executed within stored programs, unlike the Questions variable. It does not count COM_PING or COM_STATISTICS commands.(Counter)
-mysql_global_status_threads_connected: The number of currently open connections.(Counter)
-mysql_global_status_connections: The number of connection attempts (successful or not) to the MySQL server.(Gauge)
-mysql_global_status_max_used_connections: The maximum number of connections that have been in use simultaneously since the server started.(Gauge)
-mysql_global_status_threads_running: The number of threads that are not sleeping.(Gauge)
-mysql_global_status_questions: The number of statements executed by the server. This includes only statements sent to the server by clients and not statements executed within stored programs, unlike the Queries variable. This variable does not count COM_PING, COM_STATISTICS, COM_STMT_PREPARE, COM_STMT_CLOSE, or COM_STMT_RESET commands.(Counter)
-mysql_global_status_threads_cached: The number of threads in the thread cache.(Counter)
-mysql_global_status_threads_created: The number of threads created to handle connections. If Threads_created is big, you may want to increase the thread_cache_size value. The cache miss rate can be calculated as Threads_created/Connections.(Counter)
-mysql_global_status_created_tmp_tables: The number of internal temporary tables created by the server while executing statements.(Counter)
-mysql_global_status_created_tmp_disk_tables: The number of internal on-disk temporary tables created by the server while executing statements. You can compare the number of internal on-disk temporary tables created to the total number of internal temporary tables created by comparing Created_tmp_disk_tables and Created_tmp_tables values.(Counter)
-mysql_global_status_created_tmp_files: How many temporary files mysqld has created.(Counter)
-mysql_global_status_select_full_join: The number of joins that perform table scans because they do not use indexes. If this value is not 0, you should carefully check the indexes of your tables.(Counter)
-mysql_global_status_select_full_range_join: The number of joins that used a range search on a reference table.(Counter)
-mysql_global_status_select_range: The number of joins that used ranges on the first table. This is normally not a critical issue even if the value is quite large.(Counter)
-mysql_global_status_select_range_check: The number of joins without keys that check for key usage after each row. If this is not 0, you should carefully check the indexes of your tables.(Counter)
-mysql_global_status_select_scan: The number of joins that did a full scan of the first table.(Counter)
-mysql_global_status_sort_rows: The number of sorted rows.(Counter)
-mysql_global_status_sort_range: The number of sorts that were done using ranges.(Counter)
-mysql_global_status_sort_merge_passes: The number of merge passes that the sort algorithm has had to do. If this value is large, you should consider increasing the value of the sort_buffer_size system variable.(Counter)
-mysql_global_status_sort_scan: The number of sorts that were done by scanning the table.(Counter)
-mysql_global_status_slow_queries: The number of queries that have taken more than long_query_time seconds. This counter increments regardless of whether the slow query log is enabled.(Counter)
-mysql_global_status_aborted_connects: The number of failed attempts to connect to the MySQL server.(Counter)
-mysql_global_status_aborted_clients: The number of connections that were aborted because the client died without closing the connection properly.(Counter)
-mysql_global_status_table_locks_immediate: The number of times that a request for a table lock could be granted immediately. Locks Immediate rising and falling is normal activity.(Counter)
-mysql_global_status_table_locks_waited: The number of times that a request for a table lock could not be granted immediately and a wait was needed. If this is high and you have performance problems, you should first optimize your queries, and then either split your table or tables or use replication.(Counter)
-mysql_global_status_bytes_received: The number of bytes received from all clients.(Counter)
-mysql_global_status_bytes_sent: The number of bytes sent to all clients.(Counter)
-mysql_global_status_innodb_page_size: InnoDB page size (default 16KB). Many values are counted in pages; the page size enables them to be easily converted to bytes.(Gauge)
-mysql_global_status_buffer_pool_pages: The number of pages in the InnoDB buffer pool.(Gauge)
-mysql_global_status_commands_total: The number of times each xxx statement has been executed.(Counter)
-mysql_global_status_handlers_total: Handler statistics are internal statistics on how MySQL is selecting, updating, inserting, and modifying rows, tables, and indexes. This is in fact the layer between the Storage Engine and MySQL.(Counter)
-mysql_global_status_opened_files: The number of files that have been opened with my_open() (a mysys library function). Parts of the server that open files without using this function do not increment the count.(Counter)
-mysql_global_status_open_tables: The number of tables that are open.(Gauge)
-mysql_global_status_opened_tables: The number of tables that have been opened. If Opened_tables is big, your table_open_cache value is probably too small.(Counter)
-mysql_global_status_table_open_cache_hits: The number of hits for open tables cache lookups.(Counter)
-mysql_global_status_table_open_cache_misses: The number of misses for open tables cache lookups.(Counter)
-mysql_global_status_table_open_cache_overflows: The number of overflows for the open tables cache.(Counter)
-mysql_global_status_innodb_num_open_files: The number of files InnoDB currently holds open.(Gauge)
-mysql_global_status_connection_errors_total: These variables provide information about errors that occur during the client connection process.(Counter)
-mysql_global_status_innodb_buffer_pool_read_requests: The number of logical read requests.(Counter)
-mysql_global_status_innodb_buffer_pool_reads: The number of logical reads that InnoDB could not satisfy from the buffer pool, and had to read directly from disk.(Counter)
+  # [mysqld_exporter]
+  mysql_global_status_uptime: The number of seconds that the server has been up.(Gauge)
+  mysql_global_status_uptime_since_flush_status: The number of seconds since the most recent FLUSH STATUS statement.(Gauge)
+  mysql_global_status_queries: The number of statements executed by the server. This variable includes statements executed within stored programs, unlike the Questions variable. It does not count COM_PING or COM_STATISTICS commands.(Counter)
+  mysql_global_status_threads_connected: The number of currently open connections.(Counter)
+  mysql_global_status_connections: The number of connection attempts (successful or not) to the MySQL server.(Gauge)
+  mysql_global_status_max_used_connections: The maximum number of connections that have been in use simultaneously since the server started.(Gauge)
+  mysql_global_status_threads_running: The number of threads that are not sleeping.(Gauge)
+  mysql_global_status_questions: The number of statements executed by the server. This includes only statements sent to the server by clients and not statements executed within stored programs, unlike the Queries variable. This variable does not count COM_PING, COM_STATISTICS, COM_STMT_PREPARE, COM_STMT_CLOSE, or COM_STMT_RESET commands.(Counter)
+  mysql_global_status_threads_cached: The number of threads in the thread cache.(Counter)
+  mysql_global_status_threads_created: The number of threads created to handle connections. If Threads_created is big, you may want to increase the thread_cache_size value. The cache miss rate can be calculated as Threads_created/Connections.(Counter)
+  mysql_global_status_created_tmp_tables: The number of internal temporary tables created by the server while executing statements.(Counter)
+  mysql_global_status_created_tmp_disk_tables: The number of internal on-disk temporary tables created by the server while executing statements. You can compare the number of internal on-disk temporary tables created to the total number of internal temporary tables created by comparing Created_tmp_disk_tables and Created_tmp_tables values.(Counter)
+  mysql_global_status_created_tmp_files: How many temporary files mysqld has created.(Counter)
+  mysql_global_status_select_full_join: The number of joins that perform table scans because they do not use indexes. If this value is not 0, you should carefully check the indexes of your tables.(Counter)
+  mysql_global_status_select_full_range_join: The number of joins that used a range search on a reference table.(Counter)
+  mysql_global_status_select_range: The number of joins that used ranges on the first table. This is normally not a critical issue even if the value is quite large.(Counter)
+  mysql_global_status_select_range_check: The number of joins without keys that check for key usage after each row. If this is not 0, you should carefully check the indexes of your tables.(Counter)
+  mysql_global_status_select_scan: The number of joins that did a full scan of the first table.(Counter)
+  mysql_global_status_sort_rows: The number of sorted rows.(Counter)
+  mysql_global_status_sort_range: The number of sorts that were done using ranges.(Counter)
+  mysql_global_status_sort_merge_passes: The number of merge passes that the sort algorithm has had to do. If this value is large, you should consider increasing the value of the sort_buffer_size system variable.(Counter)
+  mysql_global_status_sort_scan: The number of sorts that were done by scanning the table.(Counter)
+  mysql_global_status_slow_queries: The number of queries that have taken more than long_query_time seconds. This counter increments regardless of whether the slow query log is enabled.(Counter)
+  mysql_global_status_aborted_connects: The number of failed attempts to connect to the MySQL server.(Counter)
+  mysql_global_status_aborted_clients: The number of connections that were aborted because the client died without closing the connection properly.(Counter)
+  mysql_global_status_table_locks_immediate: The number of times that a request for a table lock could be granted immediately. Locks Immediate rising and falling is normal activity.(Counter)
+  mysql_global_status_table_locks_waited: The number of times that a request for a table lock could not be granted immediately and a wait was needed. If this is high and you have performance problems, you should first optimize your queries, and then either split your table or tables or use replication.(Counter)
+  mysql_global_status_bytes_received: The number of bytes received from all clients.(Counter)
+  mysql_global_status_bytes_sent: The number of bytes sent to all clients.(Counter)
+  mysql_global_status_innodb_page_size: InnoDB page size (default 16KB). Many values are counted in pages; the page size enables them to be easily converted to bytes.(Gauge)
+  mysql_global_status_buffer_pool_pages: The number of pages in the InnoDB buffer pool.(Gauge)
+  mysql_global_status_commands_total: The number of times each xxx statement has been executed.(Counter)
+  mysql_global_status_handlers_total: Handler statistics are internal statistics on how MySQL is selecting, updating, inserting, and modifying rows, tables, and indexes. This is in fact the layer between the Storage Engine and MySQL.(Counter)
+  mysql_global_status_opened_files: The number of files that have been opened with my_open() (a mysys library function). Parts of the server that open files without using this function do not increment the count.(Counter)
+  mysql_global_status_open_tables: The number of tables that are open.(Gauge)
+  mysql_global_status_opened_tables: The number of tables that have been opened. If Opened_tables is big, your table_open_cache value is probably too small.(Counter)
+  mysql_global_status_table_open_cache_hits: The number of hits for open tables cache lookups.(Counter)
+  mysql_global_status_table_open_cache_misses: The number of misses for open tables cache lookups.(Counter)
+  mysql_global_status_table_open_cache_overflows: The number of overflows for the open tables cache.(Counter)
+  mysql_global_status_innodb_num_open_files: The number of files InnoDB currently holds open.(Gauge)
+  mysql_global_status_connection_errors_total: These variables provide information about errors that occur during the client connection process.(Counter)
+  mysql_global_status_innodb_buffer_pool_read_requests: The number of logical read requests.(Counter)
+  mysql_global_status_innodb_buffer_pool_reads: The number of logical reads that InnoDB could not satisfy from the buffer pool, and had to read directly from disk.(Counter)
 
-mysql_global_variables_thread_cache_size: How many threads the server should cache for reuse.(Gauge)
-mysql_global_variables_max_connections: The maximum permitted number of simultaneous client connections.(Gauge)
-mysql_global_variables_innodb_buffer_pool_size: The size in bytes of the buffer pool, the memory area where InnoDB caches table and index data. The default value is 134217728 bytes (128MB).(Gauge)
-mysql_global_variables_innodb_log_buffer_size: The size in bytes of the buffer that InnoDB uses to write to the log files on disk.(Gauge)
-mysql_global_variables_key_buffer_size: Index blocks for MyISAM tables are buffered and are shared by all threads.(Gauge)
-mysql_global_variables_query_cache_size: The amount of memory allocated for caching query results.(Gauge)
-mysql_global_variables_table_open_cache: The number of open tables for all threads.(Gauge)
-mysql_global_variables_open_files_limit: The number of file descriptors available to mysqld from the operating system.(Gauge)
+  mysql_global_variables_thread_cache_size: How many threads the server should cache for reuse.(Gauge)
+  mysql_global_variables_max_connections: The maximum permitted number of simultaneous client connections.(Gauge)
+  mysql_global_variables_innodb_buffer_pool_size: The size in bytes of the buffer pool, the memory area where InnoDB caches table and index data. The default value is 134217728 bytes (128MB).(Gauge)
+  mysql_global_variables_innodb_log_buffer_size: The size in bytes of the buffer that InnoDB uses to write to the log files on disk.(Gauge)
+  mysql_global_variables_key_buffer_size: Index blocks for MyISAM tables are buffered and are shared by all threads.(Gauge)
+  mysql_global_variables_query_cache_size: The amount of memory allocated for caching query results.(Gauge)
+  mysql_global_variables_table_open_cache: The number of open tables for all threads.(Gauge)
+  mysql_global_variables_open_files_limit: The number of file descriptors available to mysqld from the operating system.(Gauge)
 
-# [redis_exporter]
-redis_active_defrag_running: When activedefrag is enabled, this indicates whether defragmentation is currently active, and the CPU percentage it intends to utilize.
-redis_allocator_active_bytes: Total bytes in the allocator active pages, this includes external-fragmentation.
-redis_allocator_allocated_bytes: Total bytes allocated form the allocator, including internal-fragmentation. Normally the same as used_memory.
-redis_allocator_frag_bytes: Delta between allocator_active and allocator_allocated. See note about mem_fragmentation_bytes.
-redis_allocator_frag_ratio: Ratio between allocator_active and allocator_allocated. This is the true (external) fragmentation metric (not mem_fragmentation_ratio).
-redis_allocator_resident_bytes: Total bytes resident (RSS) in the allocator, this includes pages that can be released to the OS (by MEMORY PURGE, or just waiting).
-redis_allocator_rss_bytes: Delta between allocator_resident and allocator_active.
-redis_allocator_rss_ratio: Ratio between allocator_resident and allocator_active. This usually indicates pages that the allocator can and probably will soon release back to the OS.
-redis_aof_current_rewrite_duration_sec: Duration of the on-going AOF rewrite operation if any.
-redis_aof_enabled: Flag indicating AOF logging is activated.
-redis_aof_last_bgrewrite_status: Status of the last AOF rewrite operation.
-redis_aof_last_cow_size_bytes: The size in bytes of copy-on-write memory during the last AOF rewrite operation.
-redis_aof_last_rewrite_duration_sec: Duration of the last AOF rewrite operation in seconds.
-redis_aof_last_write_status: Status of the last write operation to the AOF.
-redis_aof_rewrite_in_progress: Flag indicating a AOF rewrite operation is on-going.
-redis_aof_rewrite_scheduled: Flag indicating an AOF rewrite operation will be scheduled once the on-going RDB save is complete.
-redis_blocked_clients: Number of clients pending on a blocking call (BLPOP, BRPOP, BRPOPLPUSH, BLMOVE, BZPOPMIN, BZPOPMAX).
-redis_client_recent_max_input_buffer_bytes: Biggest input buffer among current client connections.
-redis_client_recent_max_output_buffer_bytes: Biggest output buffer among current client connections.
-redis_cluster_enabled: Indicate Redis cluster is enabled.
-redis_commands_duration_seconds_total: The total CPU time consumed by these commands.(Counter)
-redis_commands_processed_total: Total number of commands processed by the server.(Counter)
-redis_commands_total: The number of calls that reached command execution (not rejected).(Counter)
-redis_config_maxclients: The value of the maxclients configuration directive. This is the upper limit for the sum of connected_clients, connected_slaves and cluster_connections.
-redis_config_maxmemory: The value of the maxmemory configuration directive.
-redis_connected_clients: Number of client connections (excluding connections from replicas).
-redis_connected_slaves: Number of connected replicas.
-redis_connections_received_total: Total number of connections accepted by the server.(Counter)
-redis_cpu_sys_children_seconds_total: System CPU consumed by the background processes.(Counter)
-redis_cpu_sys_seconds_total: System CPU consumed by the Redis server, which is the sum of system CPU consumed by all threads of the server process (main thread and background threads).(Counter)
-redis_cpu_user_children_seconds_total: User CPU consumed by the background processes.(Counter)
-redis_cpu_user_seconds_total: User CPU consumed by the Redis server, which is the sum of user CPU consumed by all threads of the server process (main thread and background threads).(Counter)
-redis_db_keys: Total number of keys by DB.
-redis_db_keys_expiring: Total number of expiring keys by DB
-redis_defrag_hits: Number of value reallocations performed by active the defragmentation process.
-redis_defrag_misses: Number of aborted value reallocations started by the active defragmentation process.
-redis_defrag_key_hits: Number of keys that were actively defragmented.
-redis_defrag_key_misses: Number of keys that were skipped by the active defragmentation process.
-redis_evicted_keys_total: Number of evicted keys due to maxmemory limit.(Counter)
-redis_expired_keys_total: Total number of key expiration events.(Counter)
-redis_expired_stale_percentage: The percentage of keys probably expired.
-redis_expired_time_cap_reached_total: The count of times that active expiry cycles have stopped early.
-redis_exporter_last_scrape_connect_time_seconds: The duration(in seconds) to connect when scrape.
-redis_exporter_last_scrape_duration_seconds: The last scrape duration.
-redis_exporter_last_scrape_error: The last scrape error status.
-redis_exporter_scrape_duration_seconds_count: Durations of scrapes by the exporter
-redis_exporter_scrape_duration_seconds_sum: Durations of scrapes by the exporter
-redis_exporter_scrapes_total: Current total redis scrapes.(Counter)
-redis_instance_info: Information about the Redis instance.
-redis_keyspace_hits_total: Hits total.(Counter)
-redis_keyspace_misses_total: Misses total.(Counter)
-redis_last_key_groups_scrape_duration_milliseconds: Duration of the last key group metrics scrape in milliseconds.
-redis_last_slow_execution_duration_seconds: The amount of time needed for last slow execution, in seconds.
-redis_latest_fork_seconds: The amount of time needed for last fork, in seconds.
-redis_lazyfree_pending_objects: The number of objects waiting to be freed (as a result of calling UNLINK, or FLUSHDB and FLUSHALL with the ASYNC option).
-redis_master_repl_offset: The server's current replication offset.
-redis_mem_clients_normal: Memory used by normal clients.(Gauge)
-redis_mem_clients_slaves: Memory used by replica clients - Starting Redis 7.0, replica buffers share memory with the replication backlog, so this field can show 0 when replicas don't trigger an increase of memory usage.
-redis_mem_fragmentation_bytes: Delta between used_memory_rss and used_memory. Note that when the total fragmentation bytes is low (few megabytes), a high ratio (e.g. 1.5 and above) is not an indication of an issue.
-redis_mem_fragmentation_ratio: Ratio between used_memory_rss and used_memory. Note that this doesn't only includes fragmentation, but also other process overheads (see the allocator_* metrics), and also overheads like code, shared libraries, stack, etc.
-redis_mem_not_counted_for_eviction_bytes: (Gauge)
-redis_memory_max_bytes: Max memory limit in bytes.
-redis_memory_used_bytes: Total number of bytes allocated by Redis using its allocator (either standard libc, jemalloc, or an alternative allocator such as tcmalloc)
-redis_memory_used_dataset_bytes: The size in bytes of the dataset (used_memory_overhead subtracted from used_memory)
-redis_memory_used_lua_bytes: Number of bytes used by the Lua engine.
-redis_memory_used_overhead_bytes: The sum in bytes of all overheads that the server allocated for managing its internal data structures.
-redis_memory_used_peak_bytes: Peak memory consumed by Redis (in bytes)
-redis_memory_used_rss_bytes: Number of bytes that Redis allocated as seen by the operating system (a.k.a resident set size). This is the number reported by tools such as top(1) and ps(1)
-redis_memory_used_scripts_bytes: Number of bytes used by cached Lua scripts
-redis_memory_used_startup_bytes: Initial amount of memory consumed by Redis at startup in bytes
-redis_migrate_cached_sockets_total: The number of sockets open for MIGRATE purposes
-redis_net_input_bytes_total: Total input bytes(Counter)
-redis_net_output_bytes_total: Total output bytes(Counter)
-redis_process_id: Process ID
-redis_pubsub_channels: Global number of pub/sub channels with client subscriptions
-redis_pubsub_patterns: Global number of pub/sub pattern with client subscriptions
-redis_rdb_bgsave_in_progress: Flag indicating a RDB save is on-going
-redis_rdb_changes_since_last_save: Number of changes since the last dump
-redis_rdb_current_bgsave_duration_sec: Duration of the on-going RDB save operation if any
-redis_rdb_last_bgsave_duration_sec: Duration of the last RDB save operation in seconds
-redis_rdb_last_bgsave_status: Status of the last RDB save operation
-redis_rdb_last_cow_size_bytes: The size in bytes of copy-on-write memory during the last RDB save operation
-redis_rdb_last_save_timestamp_seconds: Epoch-based timestamp of last successful RDB save
-redis_rejected_connections_total: Number of connections rejected because of maxclients limit(Counter)
-redis_repl_backlog_first_byte_offset: The master offset of the replication backlog buffer
-redis_repl_backlog_history_bytes: Size in bytes of the data in the replication backlog buffer
-redis_repl_backlog_is_active: Flag indicating replication backlog is active
-redis_replica_partial_resync_accepted: The number of accepted partial resync requests(Gauge)
-redis_replica_partial_resync_denied: The number of denied partial resync requests(Gauge)
-redis_replica_resyncs_full: The number of full resyncs with replicas
-redis_replication_backlog_bytes: Memory used by replication backlog
-redis_second_repl_offset: The offset up to which replication IDs are accepted.
-redis_slave_expires_tracked_keys: The number of keys tracked for expiry purposes (applicable only to writable replicas)(Gauge)
-redis_slowlog_last_id: Last id of slowlog
-redis_slowlog_length: Total slowlog
-redis_start_time_seconds: Start time of the Redis instance since unix epoch in seconds.
-redis_target_scrape_request_errors_total: Errors in requests to the exporter
-redis_up: Flag indicating redis instance is up
-redis_uptime_in_seconds: Number of seconds since Redis server start
+  # [redis_exporter]
+  redis_active_defrag_running: When activedefrag is enabled, this indicates whether defragmentation is currently active, and the CPU percentage it intends to utilize.
+  redis_allocator_active_bytes: Total bytes in the allocator active pages, this includes external-fragmentation.
+  redis_allocator_allocated_bytes: Total bytes allocated form the allocator, including internal-fragmentation. Normally the same as used_memory.
+  redis_allocator_frag_bytes: Delta between allocator_active and allocator_allocated. See note about mem_fragmentation_bytes.
+  redis_allocator_frag_ratio: Ratio between allocator_active and allocator_allocated. This is the true (external) fragmentation metric (not mem_fragmentation_ratio).
+  redis_allocator_resident_bytes: Total bytes resident (RSS) in the allocator, this includes pages that can be released to the OS (by MEMORY PURGE, or just waiting).
+  redis_allocator_rss_bytes: Delta between allocator_resident and allocator_active.
+  redis_allocator_rss_ratio: Ratio between allocator_resident and allocator_active. This usually indicates pages that the allocator can and probably will soon release back to the OS.
+  redis_aof_current_rewrite_duration_sec: Duration of the on-going AOF rewrite operation if any.
+  redis_aof_enabled: Flag indicating AOF logging is activated.
+  redis_aof_last_bgrewrite_status: Status of the last AOF rewrite operation.
+  redis_aof_last_cow_size_bytes: The size in bytes of copy-on-write memory during the last AOF rewrite operation.
+  redis_aof_last_rewrite_duration_sec: Duration of the last AOF rewrite operation in seconds.
+  redis_aof_last_write_status: Status of the last write operation to the AOF.
+  redis_aof_rewrite_in_progress: Flag indicating a AOF rewrite operation is on-going.
+  redis_aof_rewrite_scheduled: Flag indicating an AOF rewrite operation will be scheduled once the on-going RDB save is complete.
+  redis_blocked_clients: Number of clients pending on a blocking call (BLPOP, BRPOP, BRPOPLPUSH, BLMOVE, BZPOPMIN, BZPOPMAX).
+  redis_client_recent_max_input_buffer_bytes: Biggest input buffer among current client connections.
+  redis_client_recent_max_output_buffer_bytes: Biggest output buffer among current client connections.
+  redis_cluster_enabled: Indicate Redis cluster is enabled.
+  redis_commands_duration_seconds_total: The total CPU time consumed by these commands.(Counter)
+  redis_commands_processed_total: Total number of commands processed by the server.(Counter)
+  redis_commands_total: The number of calls that reached command execution (not rejected).(Counter)
+  redis_config_maxclients: The value of the maxclients configuration directive. This is the upper limit for the sum of connected_clients, connected_slaves and cluster_connections.
+  redis_config_maxmemory: The value of the maxmemory configuration directive.
+  redis_connected_clients: Number of client connections (excluding connections from replicas).
+  redis_connected_slaves: Number of connected replicas.
+  redis_connections_received_total: Total number of connections accepted by the server.(Counter)
+  redis_cpu_sys_children_seconds_total: System CPU consumed by the background processes.(Counter)
+  redis_cpu_sys_seconds_total: System CPU consumed by the Redis server, which is the sum of system CPU consumed by all threads of the server process (main thread and background threads).(Counter)
+  redis_cpu_user_children_seconds_total: User CPU consumed by the background processes.(Counter)
+  redis_cpu_user_seconds_total: User CPU consumed by the Redis server, which is the sum of user CPU consumed by all threads of the server process (main thread and background threads).(Counter)
+  redis_db_keys: Total number of keys by DB.
+  redis_db_keys_expiring: Total number of expiring keys by DB
+  redis_defrag_hits: Number of value reallocations performed by active the defragmentation process.
+  redis_defrag_misses: Number of aborted value reallocations started by the active defragmentation process.
+  redis_defrag_key_hits: Number of keys that were actively defragmented.
+  redis_defrag_key_misses: Number of keys that were skipped by the active defragmentation process.
+  redis_evicted_keys_total: Number of evicted keys due to maxmemory limit.(Counter)
+  redis_expired_keys_total: Total number of key expiration events.(Counter)
+  redis_expired_stale_percentage: The percentage of keys probably expired.
+  redis_expired_time_cap_reached_total: The count of times that active expiry cycles have stopped early.
+  redis_exporter_last_scrape_connect_time_seconds: The duration(in seconds) to connect when scrape.
+  redis_exporter_last_scrape_duration_seconds: The last scrape duration.
+  redis_exporter_last_scrape_error: The last scrape error status.
+  redis_exporter_scrape_duration_seconds_count: Durations of scrapes by the exporter
+  redis_exporter_scrape_duration_seconds_sum: Durations of scrapes by the exporter
+  redis_exporter_scrapes_total: Current total redis scrapes.(Counter)
+  redis_instance_info: Information about the Redis instance.
+  redis_keyspace_hits_total: Hits total.(Counter)
+  redis_keyspace_misses_total: Misses total.(Counter)
+  redis_last_key_groups_scrape_duration_milliseconds: Duration of the last key group metrics scrape in milliseconds.
+  redis_last_slow_execution_duration_seconds: The amount of time needed for last slow execution, in seconds.
+  redis_latest_fork_seconds: The amount of time needed for last fork, in seconds.
+  redis_lazyfree_pending_objects: The number of objects waiting to be freed (as a result of calling UNLINK, or FLUSHDB and FLUSHALL with the ASYNC option).
+  redis_master_repl_offset: The server's current replication offset.
+  redis_mem_clients_normal: Memory used by normal clients.(Gauge)
+  redis_mem_clients_slaves: Memory used by replica clients - Starting Redis 7.0, replica buffers share memory with the replication backlog, so this field can show 0 when replicas don't trigger an increase of memory usage.
+  redis_mem_fragmentation_bytes: Delta between used_memory_rss and used_memory. Note that when the total fragmentation bytes is low (few megabytes), a high ratio (e.g. 1.5 and above) is not an indication of an issue.
+  redis_mem_fragmentation_ratio: Ratio between used_memory_rss and used_memory. Note that this doesn't only includes fragmentation, but also other process overheads (see the allocator_* metrics), and also overheads like code, shared libraries, stack, etc.
+  redis_mem_not_counted_for_eviction_bytes: (Gauge)
+  redis_memory_max_bytes: Max memory limit in bytes.
+  redis_memory_used_bytes: Total number of bytes allocated by Redis using its allocator (either standard libc, jemalloc, or an alternative allocator such as tcmalloc)
+  redis_memory_used_dataset_bytes: The size in bytes of the dataset (used_memory_overhead subtracted from used_memory)
+  redis_memory_used_lua_bytes: Number of bytes used by the Lua engine.
+  redis_memory_used_overhead_bytes: The sum in bytes of all overheads that the server allocated for managing its internal data structures.
+  redis_memory_used_peak_bytes: Peak memory consumed by Redis (in bytes)
+  redis_memory_used_rss_bytes: Number of bytes that Redis allocated as seen by the operating system (a.k.a resident set size). This is the number reported by tools such as top(1) and ps(1)
+  redis_memory_used_scripts_bytes: Number of bytes used by cached Lua scripts
+  redis_memory_used_startup_bytes: Initial amount of memory consumed by Redis at startup in bytes
+  redis_migrate_cached_sockets_total: The number of sockets open for MIGRATE purposes
+  redis_net_input_bytes_total: Total input bytes(Counter)
+  redis_net_output_bytes_total: Total output bytes(Counter)
+  redis_process_id: Process ID
+  redis_pubsub_channels: Global number of pub/sub channels with client subscriptions
+  redis_pubsub_patterns: Global number of pub/sub pattern with client subscriptions
+  redis_rdb_bgsave_in_progress: Flag indicating a RDB save is on-going
+  redis_rdb_changes_since_last_save: Number of changes since the last dump
+  redis_rdb_current_bgsave_duration_sec: Duration of the on-going RDB save operation if any
+  redis_rdb_last_bgsave_duration_sec: Duration of the last RDB save operation in seconds
+  redis_rdb_last_bgsave_status: Status of the last RDB save operation
+  redis_rdb_last_cow_size_bytes: The size in bytes of copy-on-write memory during the last RDB save operation
+  redis_rdb_last_save_timestamp_seconds: Epoch-based timestamp of last successful RDB save
+  redis_rejected_connections_total: Number of connections rejected because of maxclients limit(Counter)
+  redis_repl_backlog_first_byte_offset: The master offset of the replication backlog buffer
+  redis_repl_backlog_history_bytes: Size in bytes of the data in the replication backlog buffer
+  redis_repl_backlog_is_active: Flag indicating replication backlog is active
+  redis_replica_partial_resync_accepted: The number of accepted partial resync requests(Gauge)
+  redis_replica_partial_resync_denied: The number of denied partial resync requests(Gauge)
+  redis_replica_resyncs_full: The number of full resyncs with replicas
+  redis_replication_backlog_bytes: Memory used by replication backlog
+  redis_second_repl_offset: The offset up to which replication IDs are accepted.
+  redis_slave_expires_tracked_keys: The number of keys tracked for expiry purposes (applicable only to writable replicas)(Gauge)
+  redis_slowlog_last_id: Last id of slowlog
+  redis_slowlog_length: Total slowlog
+  redis_start_time_seconds: Start time of the Redis instance since unix epoch in seconds.
+  redis_target_scrape_request_errors_total: Errors in requests to the exporter
+  redis_up: Flag indicating redis instance is up
+  redis_uptime_in_seconds: Number of seconds since Redis server start
 
-# [windows_exporter]
-windows_cpu_clock_interrupts_total: Total number of received and serviced clock tick interrupts(counter)
-windows_cpu_core_frequency_mhz: Core frequency in megahertz(gauge)
-windows_cpu_cstate_seconds_total: Time spent in low-power idle state(counter)
-windows_cpu_dpcs_total: Total number of received and serviced deferred procedure calls (DPCs)(counter)
-windows_cpu_idle_break_events_total: Total number of time processor was woken from idle(counter)
-windows_cpu_interrupts_total: Total number of received and serviced hardware interrupts(counter)
-windows_cpu_parking_status: Parking Status represents whether a processor is parked or not(gauge)
-windows_cpu_processor_performance: Processor Performance is the average performance of the processor while it is executing instructions, as a percentage of the nominal performance of the processor. On some processors, Processor Performance may exceed 100%(gauge)
-windows_cpu_time_total: Time that processor spent in different modes (idle, user, system, ...)(counter)
-windows_cs_hostname: Labeled system hostname information as provided by ComputerSystem.DNSHostName and ComputerSystem.Domain(gauge)
-windows_cs_logical_processors: ComputerSystem.NumberOfLogicalProcessors(gauge)
-windows_cs_physical_memory_bytes: ComputerSystem.TotalPhysicalMemory(gauge)
-windows_exporter_build_info: A metric with a constant '1' value labeled by version, revision, branch, and goversion from which windows_exporter was built.(gauge)
-windows_exporter_collector_duration_seconds: Duration of a collection.(gauge)
-windows_exporter_collector_success: Whether the collector was successful.(gauge)
-windows_exporter_collector_timeout: Whether the collector timed out.(gauge)
-windows_exporter_perflib_snapshot_duration_seconds: Duration of perflib snapshot capture(gauge)
-windows_logical_disk_free_bytes: Free space in bytes (LogicalDisk.PercentFreeSpace)(gauge)
-windows_logical_disk_idle_seconds_total: Seconds that the disk was idle (LogicalDisk.PercentIdleTime)(counter)
-windows_logical_disk_read_bytes_total: The number of bytes transferred from the disk during read operations (LogicalDisk.DiskReadBytesPerSec)(counter)
-windows_logical_disk_read_latency_seconds_total: Shows the average time, in seconds, of a read operation from the disk (LogicalDisk.AvgDiskSecPerRead)(counter)
-windows_logical_disk_read_seconds_total: Seconds that the disk was busy servicing read requests (LogicalDisk.PercentDiskReadTime)(counter)
-windows_logical_disk_read_write_latency_seconds_total: Shows the time, in seconds, of the average disk transfer (LogicalDisk.AvgDiskSecPerTransfer)(counter)
-windows_logical_disk_reads_total: The number of read operations on the disk (LogicalDisk.DiskReadsPerSec)(counter)
-windows_logical_disk_requests_queued: The number of requests queued to the disk (LogicalDisk.CurrentDiskQueueLength)(gauge)
-windows_logical_disk_size_bytes: Total space in bytes (LogicalDisk.PercentFreeSpace_Base)(gauge)
-windows_logical_disk_split_ios_total: The number of I/Os to the disk were split into multiple I/Os (LogicalDisk.SplitIOPerSec)(counter)
-windows_logical_disk_write_bytes_total: The number of bytes transferred to the disk during write operations (LogicalDisk.DiskWriteBytesPerSec)(counter)
-windows_logical_disk_write_latency_seconds_total: Shows the average time, in seconds, of a write operation to the disk (LogicalDisk.AvgDiskSecPerWrite)(counter)
-windows_logical_disk_write_seconds_total: Seconds that the disk was busy servicing write requests (LogicalDisk.PercentDiskWriteTime)(counter)
-windows_logical_disk_writes_total: The number of write operations on the disk (LogicalDisk.DiskWritesPerSec)(counter)
-windows_net_bytes_received_total: (Network.BytesReceivedPerSec)(counter)
-windows_net_bytes_sent_total: (Network.BytesSentPerSec)(counter)
-windows_net_bytes_total: (Network.BytesTotalPerSec)(counter)
-windows_net_current_bandwidth: (Network.CurrentBandwidth)(gauge)
-windows_net_packets_outbound_discarded_total: (Network.PacketsOutboundDiscarded)(counter)
-windows_net_packets_outbound_errors_total: (Network.PacketsOutboundErrors)(counter)
-windows_net_packets_received_discarded_total: (Network.PacketsReceivedDiscarded)(counter)
-windows_net_packets_received_errors_total: (Network.PacketsReceivedErrors)(counter)
-windows_net_packets_received_total: (Network.PacketsReceivedPerSec)(counter)
-windows_net_packets_received_unknown_total: (Network.PacketsReceivedUnknown)(counter)
-windows_net_packets_sent_total: (Network.PacketsSentPerSec)(counter)
-windows_net_packets_total: (Network.PacketsPerSec)(counter)
-windows_os_info: OperatingSystem.Caption, OperatingSystem.Version(gauge)
-windows_os_paging_free_bytes: OperatingSystem.FreeSpaceInPagingFiles(gauge)
-windows_os_paging_limit_bytes: OperatingSystem.SizeStoredInPagingFiles(gauge)
-windows_os_physical_memory_free_bytes: OperatingSystem.FreePhysicalMemory(gauge)
-windows_os_process_memory_limix_bytes: OperatingSystem.MaxProcessMemorySize(gauge)
-windows_os_processes: OperatingSystem.NumberOfProcesses(gauge)
-windows_os_processes_limit: OperatingSystem.MaxNumberOfProcesses(gauge)
-windows_os_time: OperatingSystem.LocalDateTime(gauge)
-windows_os_timezone: OperatingSystem.LocalDateTime(gauge)
-windows_os_users: OperatingSystem.NumberOfUsers(gauge)
-windows_os_virtual_memory_bytes: OperatingSystem.TotalVirtualMemorySize(gauge)
-windows_os_virtual_memory_free_bytes: OperatingSystem.FreeVirtualMemory(gauge)
-windows_os_visible_memory_bytes: OperatingSystem.TotalVisibleMemorySize(gauge)
-windows_service_info: A metric with a constant '1' value labeled with service information(gauge)
-windows_service_start_mode: The start mode of the service (StartMode)(gauge)
-windows_service_state: The state of the service (State)(gauge)
-windows_service_status: The status of the service (Status)(gauge)
-windows_system_context_switches_total: Total number of context switches (WMI source is PerfOS_System.ContextSwitchesPersec)(counter)
-windows_system_exception_dispatches_total: Total number of exceptions dispatched (WMI source is PerfOS_System.ExceptionDispatchesPersec)(counter)
-windows_system_processor_queue_length: Length of processor queue (WMI source is PerfOS_System.ProcessorQueueLength)(gauge)
-windows_system_system_calls_total: Total number of system calls (WMI source is PerfOS_System.SystemCallsPersec)(counter)
-windows_system_system_up_time: System boot time (WMI source is PerfOS_System.SystemUpTime)(gauge)
-windows_system_threads: Current number of threads (WMI source is PerfOS_System.Threads)(gauge)
+  # [windows_exporter]
+  windows_cpu_clock_interrupts_total: Total number of received and serviced clock tick interrupts(counter)
+  windows_cpu_core_frequency_mhz: Core frequency in megahertz(gauge)
+  windows_cpu_cstate_seconds_total: Time spent in low-power idle state(counter)
+  windows_cpu_dpcs_total: Total number of received and serviced deferred procedure calls (DPCs)(counter)
+  windows_cpu_idle_break_events_total: Total number of time processor was woken from idle(counter)
+  windows_cpu_interrupts_total: Total number of received and serviced hardware interrupts(counter)
+  windows_cpu_parking_status: Parking Status represents whether a processor is parked or not(gauge)
+  windows_cpu_processor_performance: Processor Performance is the average performance of the processor while it is executing instructions, as a percentage of the nominal performance of the processor. On some processors, Processor Performance may exceed 100%(gauge)
+  windows_cpu_time_total: Time that processor spent in different modes (idle, user, system, ...)(counter)
+  windows_cs_hostname: Labeled system hostname information as provided by ComputerSystem.DNSHostName and ComputerSystem.Domain(gauge)
+  windows_cs_logical_processors: ComputerSystem.NumberOfLogicalProcessors(gauge)
+  windows_cs_physical_memory_bytes: ComputerSystem.TotalPhysicalMemory(gauge)
+  windows_exporter_build_info: A metric with a constant '1' value labeled by version, revision, branch, and goversion from which windows_exporter was built.(gauge)
+  windows_exporter_collector_duration_seconds: Duration of a collection.(gauge)
+  windows_exporter_collector_success: Whether the collector was successful.(gauge)
+  windows_exporter_collector_timeout: Whether the collector timed out.(gauge)
+  windows_exporter_perflib_snapshot_duration_seconds: Duration of perflib snapshot capture(gauge)
+  windows_logical_disk_free_bytes: Free space in bytes (LogicalDisk.PercentFreeSpace)(gauge)
+  windows_logical_disk_idle_seconds_total: Seconds that the disk was idle (LogicalDisk.PercentIdleTime)(counter)
+  windows_logical_disk_read_bytes_total: The number of bytes transferred from the disk during read operations (LogicalDisk.DiskReadBytesPerSec)(counter)
+  windows_logical_disk_read_latency_seconds_total: Shows the average time, in seconds, of a read operation from the disk (LogicalDisk.AvgDiskSecPerRead)(counter)
+  windows_logical_disk_read_seconds_total: Seconds that the disk was busy servicing read requests (LogicalDisk.PercentDiskReadTime)(counter)
+  windows_logical_disk_read_write_latency_seconds_total: Shows the time, in seconds, of the average disk transfer (LogicalDisk.AvgDiskSecPerTransfer)(counter)
+  windows_logical_disk_reads_total: The number of read operations on the disk (LogicalDisk.DiskReadsPerSec)(counter)
+  windows_logical_disk_requests_queued: The number of requests queued to the disk (LogicalDisk.CurrentDiskQueueLength)(gauge)
+  windows_logical_disk_size_bytes: Total space in bytes (LogicalDisk.PercentFreeSpace_Base)(gauge)
+  windows_logical_disk_split_ios_total: The number of I/Os to the disk were split into multiple I/Os (LogicalDisk.SplitIOPerSec)(counter)
+  windows_logical_disk_write_bytes_total: The number of bytes transferred to the disk during write operations (LogicalDisk.DiskWriteBytesPerSec)(counter)
+  windows_logical_disk_write_latency_seconds_total: Shows the average time, in seconds, of a write operation to the disk (LogicalDisk.AvgDiskSecPerWrite)(counter)
+  windows_logical_disk_write_seconds_total: Seconds that the disk was busy servicing write requests (LogicalDisk.PercentDiskWriteTime)(counter)
+  windows_logical_disk_writes_total: The number of write operations on the disk (LogicalDisk.DiskWritesPerSec)(counter)
+  windows_net_bytes_received_total: (Network.BytesReceivedPerSec)(counter)
+  windows_net_bytes_sent_total: (Network.BytesSentPerSec)(counter)
+  windows_net_bytes_total: (Network.BytesTotalPerSec)(counter)
+  windows_net_current_bandwidth: (Network.CurrentBandwidth)(gauge)
+  windows_net_packets_outbound_discarded_total: (Network.PacketsOutboundDiscarded)(counter)
+  windows_net_packets_outbound_errors_total: (Network.PacketsOutboundErrors)(counter)
+  windows_net_packets_received_discarded_total: (Network.PacketsReceivedDiscarded)(counter)
+  windows_net_packets_received_errors_total: (Network.PacketsReceivedErrors)(counter)
+  windows_net_packets_received_total: (Network.PacketsReceivedPerSec)(counter)
+  windows_net_packets_received_unknown_total: (Network.PacketsReceivedUnknown)(counter)
+  windows_net_packets_sent_total: (Network.PacketsSentPerSec)(counter)
+  windows_net_packets_total: (Network.PacketsPerSec)(counter)
+  windows_os_info: OperatingSystem.Caption, OperatingSystem.Version(gauge)
+  windows_os_paging_free_bytes: OperatingSystem.FreeSpaceInPagingFiles(gauge)
+  windows_os_paging_limit_bytes: OperatingSystem.SizeStoredInPagingFiles(gauge)
+  windows_os_physical_memory_free_bytes: OperatingSystem.FreePhysicalMemory(gauge)
+  windows_os_process_memory_limix_bytes: OperatingSystem.MaxProcessMemorySize(gauge)
+  windows_os_processes: OperatingSystem.NumberOfProcesses(gauge)
+  windows_os_processes_limit: OperatingSystem.MaxNumberOfProcesses(gauge)
+  windows_os_time: OperatingSystem.LocalDateTime(gauge)
+  windows_os_timezone: OperatingSystem.LocalDateTime(gauge)
+  windows_os_users: OperatingSystem.NumberOfUsers(gauge)
+  windows_os_virtual_memory_bytes: OperatingSystem.TotalVirtualMemorySize(gauge)
+  windows_os_virtual_memory_free_bytes: OperatingSystem.FreeVirtualMemory(gauge)
+  windows_os_visible_memory_bytes: OperatingSystem.TotalVisibleMemorySize(gauge)
+  windows_service_info: A metric with a constant '1' value labeled with service information(gauge)
+  windows_service_start_mode: The start mode of the service (StartMode)(gauge)
+  windows_service_state: The state of the service (State)(gauge)
+  windows_service_status: The status of the service (Status)(gauge)
+  windows_system_context_switches_total: Total number of context switches (WMI source is PerfOS_System.ContextSwitchesPersec)(counter)
+  windows_system_exception_dispatches_total: Total number of exceptions dispatched (WMI source is PerfOS_System.ExceptionDispatchesPersec)(counter)
+  windows_system_processor_queue_length: Length of processor queue (WMI source is PerfOS_System.ProcessorQueueLength)(gauge)
+  windows_system_system_calls_total: Total number of system calls (WMI source is PerfOS_System.SystemCallsPersec)(counter)
+  windows_system_system_up_time: System boot time (WMI source is PerfOS_System.SystemUpTime)(gauge)
+  windows_system_threads: Current number of threads (WMI source is PerfOS_System.Threads)(gauge)
 
-# [node_exporter]
-# SYSTEM
-# CPU context switch 次数
-node_context_switches_total: context_switches
-# Interrupts 次数
-node_intr_total: Interrupts
-# 运行的进程数
-node_procs_running: Processes in runnable state
-# 熵池大小
-node_entropy_available_bits: Entropy available to random number generators
-node_time_seconds: System time in seconds since epoch (1970)
-node_boot_time_seconds: Node boot time, in unixtime
-# CPU
-node_cpu_seconds_total: Seconds the CPUs spent in each mode
-node_load1: cpu load 1m
-node_load5: cpu load 5m
-node_load15: cpu load 15m
+  # [node_exporter]
+  # SYSTEM
+  # CPU context switch 次数
+  node_context_switches_total: context_switches
+  # Interrupts 次数
+  node_intr_total: Interrupts
+  # 运行的进程数
+  node_procs_running: Processes in runnable state
+  # 熵池大小
+  node_entropy_available_bits: Entropy available to random number generators
+  node_time_seconds: System time in seconds since epoch (1970)
+  node_boot_time_seconds: Node boot time, in unixtime
+  # CPU
+  node_cpu_seconds_total: Seconds the CPUs spent in each mode
+  node_load1: cpu load 1m
+  node_load5: cpu load 5m
+  node_load15: cpu load 15m
 
-# MEM
-# 内核态
-# 内核用于缓存数据结构供自己使用的内存
-node_memory_Slab_bytes: Memory used by the kernel to cache data structures for its own use
-# slab中可回收的部分
-node_memory_SReclaimable_bytes: SReclaimable - Part of Slab, that might be reclaimed, such as caches
-# slab中不可回收的部分
-node_memory_SUnreclaim_bytes: Part of Slab, that cannot be reclaimed on memory pressure
-# Vmalloc内存区的大小
-node_memory_VmallocTotal_bytes: Total size of vmalloc memory area
-# vmalloc已分配的内存，虚拟地址空间上的连续的内存
-node_memory_VmallocUsed_bytes: Amount of vmalloc area which is used
-# vmalloc区可用的连续最大快的大小，通过此指标可以知道vmalloc可分配连续内存的最大值
-node_memory_VmallocChunk_bytes: Largest contigious block of vmalloc area which is free
-# 内存的硬件故障删除掉的内存页的总大小
-node_memory_HardwareCorrupted_bytes: Amount of RAM that the kernel identified as corrupted / not working
-# 用于在虚拟和物理内存地址之间映射的内存
-node_memory_PageTables_bytes: Memory used to map between virtual and physical memory addresses (gauge)
-# 内核栈内存，常驻内存，不可回收
-node_memory_KernelStack_bytes: Kernel memory stack. This is not reclaimable
-# 用来访问高端内存，复制高端内存的临时buffer，称为“bounce buffering”，会降低I/O 性能
-node_memory_Bounce_bytes: Memory used for block device bounce buffers
-#用户态
-# 单个巨页大小
-node_memory_Hugepagesize_bytes: Huge Page size
-# 系统分配的常驻巨页数
-node_memory_HugePages_Total: Total size of the pool of huge pages
-# 系统空闲的巨页数
-node_memory_HugePages_Free: Huge pages in the pool that are not yet allocated
-# 进程已申请但未使用的巨页数
-node_memory_HugePages_Rsvd: Huge pages for which a commitment to allocate from the pool has been made, but no allocation
-# 超过系统设定的常驻HugePages数量的个数
-node_memory_HugePages_Surp: Huge pages in the pool above the value in /proc/sys/vm/nr_hugepages
-# 透明巨页 Transparent HugePages (THP)
-node_memory_AnonHugePages_bytes: Memory in anonymous huge pages
-# inactivelist中的File-backed内存
-node_memory_Inactive_file_bytes: File-backed memory on inactive LRU list
-# inactivelist中的Anonymous内存
-node_memory_Inactive_anon_bytes: Anonymous and swap cache on inactive LRU list, including tmpfs (shmem)
-# activelist中的File-backed内存
-node_memory_Active_file_bytes: File-backed memory on active LRU list
-# activelist中的Anonymous内存
-node_memory_Active_anon_bytes: Anonymous and swap cache on active least-recently-used (LRU) list, including tmpfs
-# 禁止换出的页，对应 Unevictable 链表
-node_memory_Unevictable_bytes: Amount of unevictable memory that can't be swapped out for a variety of reasons
-# 共享内存
-node_memory_Shmem_bytes: Used shared memory (shared between several processes, thus including RAM disks)
-# 匿名页内存大小
-node_memory_AnonPages_bytes: Memory in user pages not backed by files
-# 被关联的内存页大小
-node_memory_Mapped_bytes: Used memory in mapped pages files which have been mmaped, such as libraries
-# file-backed内存页缓存大小
-node_memory_Cached_bytes: Parked file data (file content) cache
-# 系统中有多少匿名页曾经被swap-out、现在又被swap-in并且swap-in之后页面中的内容一直没发生变化
-node_memory_SwapCached_bytes: Memory that keeps track of pages that have been fetched from swap but not yet been modified
-# 被mlock()系统调用锁定的内存大小
-node_memory_Mlocked_bytes: Size of pages locked to memory using the mlock() system call
-# 块设备(block device)所占用的缓存页
-node_memory_Buffers_bytes: Block device (e.g. harddisk) cache
-node_memory_SwapTotal_bytes: Memory information field SwapTotal_bytes
-node_memory_SwapFree_bytes: Memory information field SwapFree_bytes
+  # MEM
+  # 内核态
+  # 内核用于缓存数据结构供自己使用的内存
+  node_memory_Slab_bytes: Memory used by the kernel to cache data structures for its own use
+  # slab中可回收的部分
+  node_memory_SReclaimable_bytes: SReclaimable - Part of Slab, that might be reclaimed, such as caches
+  # slab中不可回收的部分
+  node_memory_SUnreclaim_bytes: Part of Slab, that cannot be reclaimed on memory pressure
+  # Vmalloc内存区的大小
+  node_memory_VmallocTotal_bytes: Total size of vmalloc memory area
+  # vmalloc已分配的内存，虚拟地址空间上的连续的内存
+  node_memory_VmallocUsed_bytes: Amount of vmalloc area which is used
+  # vmalloc区可用的连续最大快的大小，通过此指标可以知道vmalloc可分配连续内存的最大值
+  node_memory_VmallocChunk_bytes: Largest contigious block of vmalloc area which is free
+  # 内存的硬件故障删除掉的内存页的总大小
+  node_memory_HardwareCorrupted_bytes: Amount of RAM that the kernel identified as corrupted / not working
+  # 用于在虚拟和物理内存地址之间映射的内存
+  node_memory_PageTables_bytes: Memory used to map between virtual and physical memory addresses (gauge)
+  # 内核栈内存，常驻内存，不可回收
+  node_memory_KernelStack_bytes: Kernel memory stack. This is not reclaimable
+  # 用来访问高端内存，复制高端内存的临时buffer，称为“bounce buffering”，会降低I/O 性能
+  node_memory_Bounce_bytes: Memory used for block device bounce buffers
+  #用户态
+  # 单个巨页大小
+  node_memory_Hugepagesize_bytes: Huge Page size
+  # 系统分配的常驻巨页数
+  node_memory_HugePages_Total: Total size of the pool of huge pages
+  # 系统空闲的巨页数
+  node_memory_HugePages_Free: Huge pages in the pool that are not yet allocated
+  # 进程已申请但未使用的巨页数
+  node_memory_HugePages_Rsvd: Huge pages for which a commitment to allocate from the pool has been made, but no allocation
+  # 超过系统设定的常驻HugePages数量的个数
+  node_memory_HugePages_Surp: Huge pages in the pool above the value in /proc/sys/vm/nr_hugepages
+  # 透明巨页 Transparent HugePages (THP)
+  node_memory_AnonHugePages_bytes: Memory in anonymous huge pages
+  # inactivelist中的File-backed内存
+  node_memory_Inactive_file_bytes: File-backed memory on inactive LRU list
+  # inactivelist中的Anonymous内存
+  node_memory_Inactive_anon_bytes: Anonymous and swap cache on inactive LRU list, including tmpfs (shmem)
+  # activelist中的File-backed内存
+  node_memory_Active_file_bytes: File-backed memory on active LRU list
+  # activelist中的Anonymous内存
+  node_memory_Active_anon_bytes: Anonymous and swap cache on active least-recently-used (LRU) list, including tmpfs
+  # 禁止换出的页，对应 Unevictable 链表
+  node_memory_Unevictable_bytes: Amount of unevictable memory that can't be swapped out for a variety of reasons
+  # 共享内存
+  node_memory_Shmem_bytes: Used shared memory (shared between several processes, thus including RAM disks)
+  # 匿名页内存大小
+  node_memory_AnonPages_bytes: Memory in user pages not backed by files
+  # 被关联的内存页大小
+  node_memory_Mapped_bytes: Used memory in mapped pages files which have been mmaped, such as libraries
+  # file-backed内存页缓存大小
+  node_memory_Cached_bytes: Parked file data (file content) cache
+  # 系统中有多少匿名页曾经被swap-out、现在又被swap-in并且swap-in之后页面中的内容一直没发生变化
+  node_memory_SwapCached_bytes: Memory that keeps track of pages that have been fetched from swap but not yet been modified
+  # 被mlock()系统调用锁定的内存大小
+  node_memory_Mlocked_bytes: Size of pages locked to memory using the mlock() system call
+  # 块设备(block device)所占用的缓存页
+  node_memory_Buffers_bytes: Block device (e.g. harddisk) cache
+  node_memory_SwapTotal_bytes: Memory information field SwapTotal_bytes
+  node_memory_SwapFree_bytes: Memory information field SwapFree_bytes
 
-# DISK
-node_filesystem_avail_bytes: Filesystem space available to non-root users in byte
-node_filesystem_free_bytes: Filesystem free space in bytes
-node_filesystem_size_bytes: Filesystem size in bytes
-node_filesystem_files_free: Filesystem total free file nodes
-node_filesystem_files: Filesystem total free file nodes
-node_filefd_maximum: Max open files
-node_filefd_allocated: Open files
-node_filesystem_readonly: Filesystem read-only status
-node_filesystem_device_error: Whether an error occurred while getting statistics for the given device
-node_disk_reads_completed_total: The total number of reads completed successfully
-node_disk_writes_completed_total: The total number of writes completed successfully
-node_disk_reads_merged_total: The number of reads merged
-node_disk_writes_merged_total: The number of writes merged
-node_disk_read_bytes_total: The total number of bytes read successfully
-node_disk_written_bytes_total: The total number of bytes written successfully
-node_disk_io_time_seconds_total: Total seconds spent doing I/Os
-node_disk_read_time_seconds_total: The total number of seconds spent by all reads
-node_disk_write_time_seconds_total: The total number of seconds spent by all writes
-node_disk_io_time_weighted_seconds_total: The weighted of seconds spent doing I/Os
+  # DISK
+  node_filesystem_avail_bytes: Filesystem space available to non-root users in byte
+  node_filesystem_free_bytes: Filesystem free space in bytes
+  node_filesystem_size_bytes: Filesystem size in bytes
+  node_filesystem_files_free: Filesystem total free file nodes
+  node_filesystem_files: Filesystem total free file nodes
+  node_filefd_maximum: Max open files
+  node_filefd_allocated: Open files
+  node_filesystem_readonly: Filesystem read-only status
+  node_filesystem_device_error: Whether an error occurred while getting statistics for the given device
+  node_disk_reads_completed_total: The total number of reads completed successfully
+  node_disk_writes_completed_total: The total number of writes completed successfully
+  node_disk_reads_merged_total: The number of reads merged
+  node_disk_writes_merged_total: The number of writes merged
+  node_disk_read_bytes_total: The total number of bytes read successfully
+  node_disk_written_bytes_total: The total number of bytes written successfully
+  node_disk_io_time_seconds_total: Total seconds spent doing I/Os
+  node_disk_read_time_seconds_total: The total number of seconds spent by all reads
+  node_disk_write_time_seconds_total: The total number of seconds spent by all writes
+  node_disk_io_time_weighted_seconds_total: The weighted of seconds spent doing I/Os
 
-# NET
-node_network_receive_bytes_total: Network device statistic receive_bytes (counter)
-node_network_transmit_bytes_total: Network device statistic transmit_bytes (counter)
-node_network_receive_packets_total: Network device statistic receive_bytes
-node_network_transmit_packets_total: Network device statistic transmit_bytes
-node_network_receive_errs_total: Network device statistic receive_errs
-node_network_transmit_errs_total: Network device statistic transmit_errs
-node_network_receive_drop_total: Network device statistic receive_drop
-node_network_transmit_drop_total: Network device statistic transmit_drop
-node_nf_conntrack_entries: Number of currently allocated flow entries for connection tracking
-node_sockstat_TCP_alloc: Number of TCP sockets in state alloc
-node_sockstat_TCP_inuse: Number of TCP sockets in state inuse
-node_sockstat_TCP_orphan: Number of TCP sockets in state orphan
-node_sockstat_TCP_tw: Number of TCP sockets in state tw
-node_netstat_Tcp_CurrEstab: Statistic TcpCurrEstab
-node_sockstat_sockets_used: Number of IPv4 sockets in use
+  # NET
+  node_network_receive_bytes_total: Network device statistic receive_bytes (counter)
+  node_network_transmit_bytes_total: Network device statistic transmit_bytes (counter)
+  node_network_receive_packets_total: Network device statistic receive_bytes
+  node_network_transmit_packets_total: Network device statistic transmit_bytes
+  node_network_receive_errs_total: Network device statistic receive_errs
+  node_network_transmit_errs_total: Network device statistic transmit_errs
+  node_network_receive_drop_total: Network device statistic receive_drop
+  node_network_transmit_drop_total: Network device statistic transmit_drop
+  node_nf_conntrack_entries: Number of currently allocated flow entries for connection tracking
+  node_sockstat_TCP_alloc: Number of TCP sockets in state alloc
+  node_sockstat_TCP_inuse: Number of TCP sockets in state inuse
+  node_sockstat_TCP_orphan: Number of TCP sockets in state orphan
+  node_sockstat_TCP_tw: Number of TCP sockets in state tw
+  node_netstat_Tcp_CurrEstab: Statistic TcpCurrEstab
+  node_sockstat_sockets_used: Number of IPv4 sockets in use
 
-# [kafka_exporter]
-kafka_brokers: count of kafka_brokers (gauge)
-kafka_topic_partitions: Number of partitions for this Topic (gauge)
-kafka_topic_partition_current_offset: Current Offset of a Broker at Topic/Partition (gauge)
-kafka_consumergroup_current_offset: Current Offset of a ConsumerGroup at Topic/Partition (gauge)
-kafka_consumer_lag_millis: Current approximation of consumer lag for a ConsumerGroup at Topic/Partition (gauge)
-kafka_topic_partition_under_replicated_partition: 1 if Topic/Partition is under Replicated
+  # [kafka_exporter]
+  kafka_brokers: count of kafka_brokers (gauge)
+  kafka_topic_partitions: Number of partitions for this Topic (gauge)
+  kafka_topic_partition_current_offset: Current Offset of a Broker at Topic/Partition (gauge)
+  kafka_consumergroup_current_offset: Current Offset of a ConsumerGroup at Topic/Partition (gauge)
+  kafka_consumer_lag_millis: Current approximation of consumer lag for a ConsumerGroup at Topic/Partition (gauge)
+  kafka_topic_partition_under_replicated_partition: 1 if Topic/Partition is under Replicated
 
-# [zookeeper_exporter]
-zk_znode_count: The total count of znodes stored
-zk_ephemerals_count: The number of Ephemerals nodes
-zk_watch_count: The number of watchers setup over Zookeeper nodes.
-zk_approximate_data_size: Size of data in bytes that a zookeeper server has in its data tree
-zk_outstanding_requests: Number of currently executing requests
-zk_packets_sent: Count of the number of zookeeper packets sent from a server
-zk_packets_received: Count of the number of zookeeper packets received by a server
-zk_num_alive_connections: Number of active clients connected to a zookeeper server
-zk_open_file_descriptor_count: Number of file descriptors that a zookeeper server has open
-zk_max_file_descriptor_count: Maximum number of file descriptors that a zookeeper server can open
-zk_avg_latency: Average time in milliseconds for requests to be processed
-zk_min_latency: Maximum time in milliseconds for a request to be processed
-zk_max_latency: Minimum time in milliseconds for a request to be processed
+  # [zookeeper_exporter]
+  zk_znode_count: The total count of znodes stored
+  zk_ephemerals_count: The number of Ephemerals nodes
+  zk_watch_count: The number of watchers setup over Zookeeper nodes.
+  zk_approximate_data_size: Size of data in bytes that a zookeeper server has in its data tree
+  zk_outstanding_requests: Number of currently executing requests
+  zk_packets_sent: Count of the number of zookeeper packets sent from a server
+  zk_packets_received: Count of the number of zookeeper packets received by a server
+  zk_num_alive_connections: Number of active clients connected to a zookeeper server
+  zk_open_file_descriptor_count: Number of file descriptors that a zookeeper server has open
+  zk_max_file_descriptor_count: Maximum number of file descriptors that a zookeeper server can open
+  zk_avg_latency: Average time in milliseconds for requests to be processed
+  zk_min_latency: Maximum time in milliseconds for a request to be processed
+  zk_max_latency: Minimum time in milliseconds for a request to be processed

etc/ops.yaml

@@ -107,4 +107,5 @@ ops:
   - "/help/source"
   - "/help/sso"
   - "/help/notification-tpls"
-  - "/help/notification-settings"
+  - "/help/notification-settings"
+  - "/help/migrate"

etc/template/README.md

@@ -1,26 +0,0 @@
-# 告警消息模版文件
-
-模版中可以使用的变量参考`AlertCurEvent`对象
-模版语法如何使用可以参考[html/template](https://pkg.go.dev/html/template)
-
-## 如何在告警模版中添加监控详情url
-
-假设web的地址是http://127.0.0.1:18000/, 实际使用时用web地址替换该地址
-
-在监控模版中添加以下行:
-
-* dingtalk / wecom / feishu
-```markdown
-[监控详情](http://127.0.0.1:18000/metric/explorer?promql={{ .PromQl | escape }})
-```
-
-* mailbody
-
-```html
-<tr>
-  <th>监控详情：</th>
-  <td>
-    <a href="http://127.0.0.1:18000/metric/explorer?promql={{ .PromQl | escape }}" target="_blank">点击查看</a>
-  </td>
-</tr>
-```

etc/template/dingtalk.tpl

@@ -1,11 +0,0 @@
-#### {{if .IsRecovered}}<font color="#008800">S{{.Severity}} - Recovered - {{.RuleName}}</font>{{else}}<font color="#FF0000">S{{.Severity}} - Triggered - {{.RuleName}}</font>{{end}}
-
----
-
-- **规则标题**: {{.RuleName}}{{if .RuleNote}}
-- **规则备注**: {{.RuleNote}}{{end}}
-{{if not .IsRecovered}}- **触发时值**: {{.TriggerValue}}{{end}}
-{{if .TargetIdent}}- **监控对象**: {{.TargetIdent}}{{end}}
-- **监控指标**: {{.TagsJSON}}
-- {{if .IsRecovered}}**恢复时间**: {{timeformat .LastEvalTime}}{{else}}**触发时间**: {{timeformat .TriggerTime}}{{end}}
-- **发送时间**: {{timestamp}}

etc/template/email.tpl

@@ -1,217 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-    <meta charset="UTF-8">
-    <meta http-equiv="X-UA-Compatible" content="ie=edge">
-    <title>夜莺告警通知</title>
-    <style type="text/css">
-        .wrapper {
-            background-color: #f8f8f8;
-            padding: 15px;
-            height: 100%;
-        }
-        .main {
-            width: 600px;
-            padding: 30px;
-            margin: 0 auto;
-            background-color: #fff;
-            font-size: 12px;
-            font-family: verdana,'Microsoft YaHei',Consolas,'Deja Vu Sans Mono','Bitstream Vera Sans Mono';
-        }
-        header {
-            border-radius: 2px 2px 0 0;
-        }
-        header .title {
-            font-size: 14px;
-            color: #333333;
-            margin: 0;
-        }
-        header .sub-desc {
-            color: #333;
-            font-size: 14px;
-            margin-top: 6px;
-            margin-bottom: 0;
-        }
-        hr {
-            margin: 20px 0;
-            height: 0;
-            border: none;
-            border-top: 1px solid #e5e5e5;
-        }
-        em {
-            font-weight: 600;
-        }
-        table {
-            margin: 20px 0;
-            width: 100%;
-        }
-
-        table tbody tr{
-            font-weight: 200;
-            font-size: 12px;
-            color: #666;
-            height: 32px;
-        }
-
-        .succ {
-            background-color: green;
-            color: #fff;
-        }
-
-        .fail {
-            background-color: red;
-            color: #fff;
-        }
-
-        .succ th, .succ td, .fail th, .fail td {
-            color: #fff;
-        }
-
-        table tbody tr th {
-            width: 80px;
-            text-align: right;
-        }
-        .text-right {
-            text-align: right;
-        }
-        .body {
-            margin-top: 24px;
-        }
-        .body-text {
-            color: #666666;
-            -webkit-font-smoothing: antialiased;
-        }
-        .body-extra {
-            -webkit-font-smoothing: antialiased;
-        }
-        .body-extra.text-right a {
-            text-decoration: none;
-            color: #333;
-        }
-        .body-extra.text-right a:hover {
-            color: #666;
-        }
-        .button {
-            width: 200px;
-            height: 50px;
-            margin-top: 20px;
-            text-align: center;
-            border-radius: 2px;
-            background: #2D77EE;
-            line-height: 50px;
-            font-size: 20px;
-            color: #FFFFFF;
-            cursor: pointer;
-        }
-        .button:hover {
-            background: rgb(25, 115, 255);
-            border-color: rgb(25, 115, 255);
-            color: #fff;
-        }
-        footer {
-            margin-top: 10px;
-            text-align: right;
-        }
-        .footer-logo {
-            text-align: right;
-        }
-        .footer-logo-image {
-            width: 108px;
-            height: 27px;
-            margin-right: 10px;
-        }
-        .copyright {
-            margin-top: 10px;
-            font-size: 12px;
-            text-align: right;
-            color: #999;
-            -webkit-font-smoothing: antialiased;
-        }
-    </style>
-</head>
-<body>
-<div class="wrapper">
-    <div class="main">
-        <header>
-            <h3 class="title">{{.RuleName}}</h3>
-            <p class="sub-desc"></p>
-        </header>
-
-        <hr>
-
-        <div class="body">
-            <table cellspacing="0" cellpadding="0" border="0">
-                <tbody>
-                {{if .IsRecovered}}
-                <tr class="succ">
-                    <th>级别状态：</th>
-                    <td>S{{.Severity}} Recovered</td>
-                </tr>
-                {{else}}
-                <tr class="fail">
-                    <th>级别状态：</th>
-                    <td>S{{.Severity}} Triggered</td>
-                </tr>
-                {{end}}
-
-                <tr>
-                    <th>策略备注：</th>
-                    <td>{{.RuleNote}}</td>
-                </tr>
-                <tr>
-                    <th>设备备注：</th>
-                    <td>{{.TargetNote}}</td>
-                </tr>
-                {{if not .IsRecovered}}
-                <tr>
-                    <th>触发时值：</th>
-                    <td>{{.TriggerValue}}</td>
-                </tr>
-                {{end}}
-
-                {{if .TargetIdent}}
-                <tr>
-                    <th>监控对象：</th>
-                    <td>{{.TargetIdent}}</td>
-                </tr>
-                {{end}}
-                <tr>
-                    <th>监控指标：</th>
-                    <td>{{.TagsJSON}}</td>
-                </tr>
-
-                {{if .IsRecovered}}
-                <tr>
-                    <th>恢复时间：</th>
-                    <td>{{timeformat .LastEvalTime}}</td>
-                </tr>
-                {{else}}
-                <tr>
-                    <th>触发时间：</th>
-                    <td>
-                        {{timeformat .TriggerTime}}
-                    </td>
-                </tr>
-                {{end}}
-
-                <tr>
-                    <th>发送时间：</th>
-                    <td>
-                        {{timestamp}}
-                    </td>
-                </tr>
-                </tbody>
-            </table>
-
-            <hr>
-
-            <footer>
-                <div class="copyright" style="font-style: italic">
-                    我们希望与您一起，将监控这个事情，做到极致！
-                </div>
-            </footer>
-        </div>
-    </div>
-</div>
-</body>
-</html>

etc/template/feishu.tpl

@@ -1,7 +0,0 @@
-级别状态: S{{.Severity}} {{if .IsRecovered}}Recovered{{else}}Triggered{{end}}
-规则名称: {{.RuleName}}{{if .RuleNote}}
-规则备注: {{.RuleNote}}{{end}}
-监控指标: {{.TagsJSON}}
-{{if .IsRecovered}}恢复时间：{{timeformat .LastEvalTime}}{{else}}触发时间: {{timeformat .TriggerTime}}
-触发时值: {{.TriggerValue}}{{end}}
-发送时间: {{timestamp}}

etc/template/mailsubject.tpl

@@ -1 +0,0 @@
-{{if .IsRecovered}}Recovered{{else}}Triggered{{end}}: {{.RuleName}} {{.TagsJSON}}

etc/template/mm.tpl

@@ -1,7 +0,0 @@
-级别状态: S{{.Severity}} {{if .IsRecovered}}Recovered{{else}}Triggered{{end}}
-规则名称: {{.RuleName}}{{if .RuleNote}}
-规则备注: {{.RuleNote}}{{end}}
-监控指标: {{.TagsJSON}}
-{{if .IsRecovered}}恢复时间：{{timeformat .LastEvalTime}}{{else}}触发时间: {{timeformat .TriggerTime}}
-触发时值: {{.TriggerValue}}{{end}}
-发送时间: {{timestamp}}

etc/template/telegram.tpl

@@ -1,9 +0,0 @@
-**级别状态**: {{if .IsRecovered}}<font color="info">S{{.Severity}} Recovered</font>{{else}}<font color="warning">S{{.Severity}} Triggered</font>{{end}}
-**规则标题**: {{.RuleName}}{{if .RuleNote}}
-**规则备注**: {{.RuleNote}}{{end}}{{if .TargetIdent}}
-**监控对象**: {{.TargetIdent}}{{end}}
-**监控指标**: {{.TagsJSON}}{{if not .IsRecovered}}
-**触发时值**: {{.TriggerValue}}{{end}}
-{{if .IsRecovered}}**恢复时间**: {{timeformat .LastEvalTime}}{{else}}**首次触发时间**: {{timeformat .FirstTriggerTime}}{{end}}
-{{$time_duration := sub now.Unix .FirstTriggerTime }}{{if .IsRecovered}}{{$time_duration = sub .LastEvalTime .FirstTriggerTime }}{{end}}**持续时长**: {{humanizeDurationInterface $time_duration}}
-**发送时间**: {{timestamp}}

etc/template/wecom.tpl

@@ -1,9 +0,0 @@
-**级别状态**: {{if .IsRecovered}}<font color="info">S{{.Severity}} Recovered</font>{{else}}<font color="warning">S{{.Severity}} Triggered</font>{{end}}
-**规则标题**: {{.RuleName}}{{if .RuleNote}}
-**规则备注**: {{.RuleNote}}{{end}}{{if .TargetIdent}}
-**监控对象**: {{.TargetIdent}}{{end}}
-**监控指标**: {{.TagsJSON}}{{if not .IsRecovered}}
-**触发时值**: {{.TriggerValue}}{{end}}
-{{if .IsRecovered}}**恢复时间**: {{timeformat .LastEvalTime}}{{else}}**首次触发时间**: {{timeformat .FirstTriggerTime}}{{end}}
-{{$time_duration := sub now.Unix .FirstTriggerTime }}{{if .IsRecovered}}{{$time_duration = sub .LastEvalTime .FirstTriggerTime }}{{end}}**持续时长**: {{humanizeDurationInterface $time_duration}}
-**发送时间**: {{timestamp}}

fe.sh

@@ -1,17 +1,26 @@
 #!/bin/bash
 
-TAG=$(curl -sX GET https://api.github.com/repos/n9e/fe/releases/latest   | awk '/tag_name/{print $4;exit}' FS='[""]')
-VERSION=$(echo $TAG)
+cp -f ./docker/initsql/a-n9e.sql n9e.sql
 
-curl -o n9e-fe-${VERSION}.tar.gz -L https://github.com/n9e/fe/releases/download/${TAG}/n9e-fe-${VERSION}.tar.gz  
+if [ ! -d "./pub" ]; then
+    TAG=$(curl -sX GET https://api.github.com/repos/n9e/fe/releases/latest   | awk '/tag_name/{print $4;exit}' FS='[""]')
 
-tar zxvf n9e-fe-${VERSION}.tar.gz
+    if ! curl -o n9e-fe-${TAG}.tar.gz -L https://github.com/n9e/fe/releases/download/${TAG}/n9e-fe-${TAG}.tar.gz; then
+        echo "failed to download n9e-fe-${TAG}.tar.gz!"
+        exit 1
+    fi
 
-cp ./docker/initsql/a-n9e.sql n9e.sql
+    if ! tar zxf n9e-fe-${TAG}.tar.gz; then
+        echo "failed to untar n9e-fe-${TAG}.tar.gz!"
+        exit 2
+    fi
+fi
 
-# Embed files into a Go executable
-statik -src=./pub -dest=./front
+GOPATH=$(go env GOPATH)
+GOPATH=${GOPATH:-/home/runner/go}
 
-# rm the fe file
-rm n9e-fe-${VERSION}.tar.gz
-rm -r ./pub
+# Embed files into a go binary
+if ! $GOPATH/bin/statik -src=./pub -dest=./front; then
+    echo "failed to embed files into a go binary!"
+    exit 4
+fi

go.mod

@@ -7,18 +7,20 @@ require (
 	github.com/coreos/go-oidc v2.2.1+incompatible
 	github.com/dgrijalva/jwt-go v3.2.0+incompatible
 	github.com/gin-contrib/pprof v1.4.0
-	github.com/gin-gonic/gin v1.9.0
+	github.com/gin-gonic/gin v1.9.1
 	github.com/go-ldap/ldap/v3 v3.4.4
 	github.com/gogo/protobuf v1.3.2
 	github.com/golang-jwt/jwt v3.2.2+incompatible
 	github.com/golang/protobuf v1.5.2
 	github.com/golang/snappy v0.0.4
 	github.com/google/uuid v1.3.0
+	github.com/hashicorp/go-version v1.6.0
 	github.com/json-iterator/go v1.1.12
 	github.com/koding/multiconfig v0.0.0-20171124222453-69c27309b2d7
 	github.com/mailru/easyjson v0.7.7
-	github.com/mattn/go-isatty v0.0.17
-	github.com/pelletier/go-toml/v2 v2.0.6
+	github.com/mattn/go-isatty v0.0.19
+	github.com/mojocn/base64Captcha v1.3.5
+	github.com/pelletier/go-toml/v2 v2.0.8
 	github.com/pkg/errors v0.9.1
 	github.com/prometheus/client_golang v1.14.0
 	github.com/prometheus/common v0.39.0
@@ -27,7 +29,7 @@ require (
 	github.com/redis/go-redis/v9 v9.0.2
 	github.com/tidwall/gjson v1.14.0
 	github.com/toolkits/pkg v1.3.3
-	golang.org/x/oauth2 v0.3.0
+	golang.org/x/oauth2 v0.4.0
 	gopkg.in/gomail.v2 v2.0.0-20160411212932-81ebce5c23df
 	gorm.io/driver/mysql v1.4.4
 	gorm.io/driver/postgres v1.4.5
@@ -37,19 +39,21 @@ require (
 require (
 	github.com/Azure/go-ntlmssp v0.0.0-20220621081337-cb9428e4ac1e // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
-	github.com/bytedance/sonic v1.8.0 // indirect
+	github.com/bytedance/sonic v1.9.1 // indirect
 	github.com/cespare/xxhash/v2 v2.2.0 // indirect
 	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/fatih/camelcase v1.0.0 // indirect
 	github.com/fatih/structs v1.1.0 // indirect
+	github.com/gabriel-vasile/mimetype v1.4.2 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
 	github.com/go-asn1-ber/asn1-ber v1.5.4 // indirect
 	github.com/go-playground/locales v0.14.1 // indirect
 	github.com/go-playground/universal-translator v0.18.1 // indirect
-	github.com/go-playground/validator/v10 v10.11.2 // indirect
+	github.com/go-playground/validator/v10 v10.14.0 // indirect
 	github.com/go-sql-driver/mysql v1.6.0 // indirect
-	github.com/goccy/go-json v0.10.0 // indirect
+	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 // indirect
 	github.com/grpc-ecosystem/grpc-gateway v1.16.0 // indirect
 	github.com/jackc/chunkreader/v2 v2.0.1 // indirect
 	github.com/jackc/pgconn v1.13.0 // indirect
@@ -62,8 +66,8 @@ require (
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
 	github.com/josharian/intern v1.0.0 // indirect
-	github.com/klauspost/cpuid/v2 v2.0.9 // indirect
-	github.com/leodido/go-urn v1.2.1 // indirect
+	github.com/klauspost/cpuid/v2 v2.2.4 // indirect
+	github.com/leodido/go-urn v1.2.4 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
@@ -74,17 +78,18 @@ require (
 	github.com/tidwall/match v1.1.1 // indirect
 	github.com/tidwall/pretty v1.2.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
-	github.com/ugorji/go/codec v1.2.9 // indirect
+	github.com/ugorji/go/codec v1.2.11 // indirect
 	go.uber.org/automaxprocs v1.4.0 // indirect
-	golang.org/x/arch v0.0.0-20210923205945-b76863e36670 // indirect
-	golang.org/x/crypto v0.5.0 // indirect
-	golang.org/x/net v0.7.0 // indirect
-	golang.org/x/sys v0.5.0 // indirect
-	golang.org/x/text v0.7.0 // indirect
+	golang.org/x/arch v0.3.0 // indirect
+	golang.org/x/crypto v0.9.0 // indirect
+	golang.org/x/image v0.5.0 // indirect
+	golang.org/x/net v0.10.0 // indirect
+	golang.org/x/sys v0.8.0 // indirect
+	golang.org/x/text v0.9.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
-	google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef // indirect
-	google.golang.org/grpc v1.51.0 // indirect
-	google.golang.org/protobuf v1.28.1 // indirect
+	google.golang.org/genproto v0.0.0-20230110181048-76db0878b65f // indirect
+	google.golang.org/grpc v1.53.0 // indirect
+	google.golang.org/protobuf v1.30.0 // indirect
 	gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc // indirect
 	gopkg.in/square/go-jose.v2 v2.6.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect

go.sum

@@ -12,8 +12,8 @@ github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6r
 github.com/bsm/ginkgo/v2 v2.5.0 h1:aOAnND1T40wEdAtkGSkvSICWeQ8L3UASX7YVCqQx+eQ=
 github.com/bsm/gomega v1.20.0 h1:JhAwLmtRzXFTx2AkALSLa8ijZafntmhSoU63Ok18Uq8=
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
-github.com/bytedance/sonic v1.8.0 h1:ea0Xadu+sHlu7x5O3gKhRpQ1IKiMrSiHttPF0ybECuA=
-github.com/bytedance/sonic v1.8.0/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
+github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
+github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
 github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -45,6 +45,8 @@ github.com/fatih/camelcase v1.0.0 h1:hxNvNX/xYBp0ovncs8WyWZrOrpBNub/JfaMvbURyft8
 github.com/fatih/camelcase v1.0.0/go.mod h1:yN2Sb0lFhZJUdVvtELVWefmrXpuZESvPmqwoZc+/fpc=
 github.com/fatih/structs v1.1.0 h1:Q7juDM0QtcnhCpeyLGQKyg4TOIghuNXrkL32pHAUMxo=
 github.com/fatih/structs v1.1.0/go.mod h1:9NiDSp5zOcgEDl+j00MP/WkGVPOlPRLejGD8Ga6PJ7M=
+github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
+github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
 github.com/garyburd/redigo v1.6.2/go.mod h1:NR3MbYisc3/PwhQ00EMzDiPmrwpPxAn5GI05/YaO1SY=
 github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
 github.com/gin-contrib/pprof v1.4.0 h1:XxiBSf5jWZ5i16lNOPbMTVdgHBdhfGRD5PZ1LWazzvg=
@@ -53,8 +55,8 @@ github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE
 github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
 github.com/gin-gonic/gin v1.7.7/go.mod h1:axIBovoeJpVj8S3BwE0uPMTeReE4+AfFtqpqaZ1qq1U=
 github.com/gin-gonic/gin v1.8.1/go.mod h1:ji8BvRH1azfM+SYow9zQ6SZMvR8qOMZHmsCuWR9tTTk=
-github.com/gin-gonic/gin v1.9.0 h1:OjyFBKICoexlu99ctXNR2gg+c5pKrKMuyjgARg9qeY8=
-github.com/gin-gonic/gin v1.9.0/go.mod h1:W1Me9+hsUSyj3CePGrd1/QrKJMSJ1Tu/0hFEH89961k=
+github.com/gin-gonic/gin v1.9.1 h1:4idEAncQnU5cB7BeOkPtxjfCSye0AAm1R0RVIqJ+Jmg=
+github.com/gin-gonic/gin v1.9.1/go.mod h1:hPrL7YrpYKXt5YId3A/Tnip5kqbEAP+KLuI3SUcPTeU=
 github.com/go-asn1-ber/asn1-ber v1.5.4 h1:vXT6d/FNDiELJnLb6hGNa309LMsrCoYFvpwHDF0+Y1A=
 github.com/go-asn1-ber/asn1-ber v1.5.4/go.mod h1:hEBeB/ic+5LoWskz+yKT7vGhhPYkProFKoKdwZRWMe0=
 github.com/go-kit/log v0.1.0/go.mod h1:zbhenjAZHb184qTLMA9ZjW7ThYL0H2mk7Q6pNt4vbaY=
@@ -73,20 +75,22 @@ github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJn
 github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
 github.com/go-playground/validator/v10 v10.4.1/go.mod h1:nlOn6nFhuKACm19sB/8EGNn9GlaMV7XkbRSipzJ0Ii4=
 github.com/go-playground/validator/v10 v10.10.0/go.mod h1:74x4gJWsvQexRdW8Pn3dXSGrTK4nAUsbPlLADvpJkos=
-github.com/go-playground/validator/v10 v10.11.2 h1:q3SHpufmypg+erIExEKUmsgmhDTyhcJ38oeKGACXohU=
-github.com/go-playground/validator/v10 v10.11.2/go.mod h1:NieE624vt4SCTJtD87arVLvdmjPAeV8BQlHtMnw9D7s=
+github.com/go-playground/validator/v10 v10.14.0 h1:vgvQWe3XCz3gIeFDm/HnTIbj6UGmg/+t63MyGU2n5js=
+github.com/go-playground/validator/v10 v10.14.0/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
 github.com/go-sql-driver/mysql v1.6.0 h1:BCTh4TKNUYmOmMUcQ3IipzF5prigylS7XXjEkfCHuOE=
 github.com/go-sql-driver/mysql v1.6.0/go.mod h1:DCzpHaOWr8IXmIStZouvnhqoel9Qv2LBy8hT2VhHyBg=
 github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
 github.com/goccy/go-json v0.9.7/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
-github.com/goccy/go-json v0.10.0 h1:mXKd9Qw4NuzShiRlOXKews24ufknHO7gx30lsDyokKA=
-github.com/goccy/go-json v0.10.0/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
+github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/gofrs/uuid v4.0.0+incompatible h1:1SD/1F5pU8p29ybwgQSwpQk+mwdRrXCYuPhW6m+TnJw=
 github.com/gofrs/uuid v4.0.0+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang-jwt/jwt v3.2.2+incompatible h1:IfV12K8xAKAnZqdXVzCZ+TOjboZ2keLg81eXfW3O+oY=
 github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
+github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 h1:DACJavvAHhabrF08vX0COfcOBJRhZ8lUbR+ZWIs0Y5g=
+github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0/go.mod h1:E/TSTwGwJL78qG/PmXZO1EjYhfJinVAhrmmHX6Z8B9k=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
 github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
 github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
@@ -102,7 +106,7 @@ github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEW
 github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
+github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@@ -110,6 +114,8 @@ github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
 github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0 h1:gmcG1KaJ57LophUzW0Hy8NmPhnMZb4M0+kPpLofRdBo=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0/go.mod h1:BDjrQk3hbvj6Nolgz8mAMFbcEtjT1g+wF4CSlocrBnw=
+github.com/hashicorp/go-version v1.6.0 h1:feTTfFNnjP967rlCxM/I9g701jU+RN74YKx2mOkIeek=
+github.com/hashicorp/go-version v1.6.0/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09ZGVZPK5anwXA=
 github.com/jackc/chunkreader v1.0.0/go.mod h1:RT6O25fNZIuasFJRyZ4R/Y2BbhasbmZXF9QQ7T3kePo=
 github.com/jackc/chunkreader/v2 v2.0.0/go.mod h1:odVSm741yZoC3dpHEUXIqA9tQRhFrgOHwnPIn9lDKlk=
 github.com/jackc/chunkreader/v2 v2.0.1 h1:i+RDz65UE+mmpjTfyz0MoVTnzeYxroil2G82ki7MGG8=
@@ -169,8 +175,9 @@ github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnr
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
-github.com/klauspost/cpuid/v2 v2.0.9 h1:lgaqFMSdTdQYdZ04uHyN2d/eKdOMyi2YLSvlQIBFYa4=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
+github.com/klauspost/cpuid/v2 v2.2.4 h1:acbojRNwl3o09bUq+yDCtZFc1aiwaAAxtcn8YkZXnvk=
+github.com/klauspost/cpuid/v2 v2.2.4/go.mod h1:RVVoqg1df56z8g3pUjL/3lE5UfnlrJX8tyFgg4nqhuY=
 github.com/koding/multiconfig v0.0.0-20171124222453-69c27309b2d7 h1:SWlt7BoQNASbhTUD0Oy5yysI2seJ7vWuGUp///OM4TM=
 github.com/koding/multiconfig v0.0.0-20171124222453-69c27309b2d7/go.mod h1:Y2SaZf2Rzd0pXkLVhLlCiAXFCLSXAIbTKDivVgff/AM=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
@@ -185,8 +192,9 @@ github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/leodido/go-urn v1.2.0/go.mod h1:+8+nEpDfqqsY+g338gtMEUOtuK+4dEMhiQEgxpxOKII=
-github.com/leodido/go-urn v1.2.1 h1:BqpAaACuzVSgi/VLzGZIobT2z4v53pjosyNd9Yv6n/w=
 github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
+github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
+github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
 github.com/lib/pq v1.0.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
 github.com/lib/pq v1.1.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
 github.com/lib/pq v1.2.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
@@ -200,8 +208,8 @@ github.com/mattn/go-isatty v0.0.5/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hd
 github.com/mattn/go-isatty v0.0.7/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
 github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
 github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
-github.com/mattn/go-isatty v0.0.17 h1:BTarxUcIeDqL27Mc+vyvdWYSL28zpIhv3RoTdsLMPng=
-github.com/mattn/go-isatty v0.0.17/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
+github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
+github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/matttproud/golang_protobuf_extensions v1.0.4 h1:mmDVorXM7PCGKw94cs5zkfA9PSy5pEvNWRP0ET0TIVo=
 github.com/matttproud/golang_protobuf_extensions v1.0.4/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
@@ -210,9 +218,11 @@ github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJ
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
+github.com/mojocn/base64Captcha v1.3.5 h1:Qeilr7Ta6eDtG4S+tQuZ5+hO+QHbiGAJdi4PfoagaA0=
+github.com/mojocn/base64Captcha v1.3.5/go.mod h1:/tTTXn4WTpX9CfrmipqRytCpJ27Uw3G6I7NcP2WwcmY=
 github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
-github.com/pelletier/go-toml/v2 v2.0.6 h1:nrzqCb7j9cDFj2coyLNLaZuJTLjWjlaz6nvTvIwycIU=
-github.com/pelletier/go-toml/v2 v2.0.6/go.mod h1:eumQOmlWiOPt5WriQQqoM5y18pDHwha2N+QD+EUNTek=
+github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
+github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
@@ -267,8 +277,10 @@ github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.2/go.mod h1:R6va5+xMeoiuVRoj+gSkQ7d3FALtqAAGI1FQKckRals=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
-github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.8.3 h1:RP3t2pwF7cMEbC1dqtB6poj3niw/9gnV4Cjg5oW5gtY=
+github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/tidwall/gjson v1.14.0 h1:6aeJ0bzojgWLa82gDQHcx3S0Lr/O51I9bJ5nv6JFx5w=
 github.com/tidwall/gjson v1.14.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
 github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
@@ -283,8 +295,8 @@ github.com/ugorji/go v1.1.7/go.mod h1:kZn38zHttfInRq0xu/PH0az30d+z6vm202qpg1oXVM
 github.com/ugorji/go v1.2.7/go.mod h1:nF9osbDWLy6bDVv/Rtoh6QgnvNDpmCalQV5urGCCS6M=
 github.com/ugorji/go/codec v1.1.7/go.mod h1:Ax+UKWsSmolVDwsd+7N3ZtXu+yMGCf907BLYF3GoBXY=
 github.com/ugorji/go/codec v1.2.7/go.mod h1:WGN1fab3R1fzQlVQTkfxVtIBhWDRqOviHU95kRgeqEY=
-github.com/ugorji/go/codec v1.2.9 h1:rmenucSohSTiyL09Y+l2OCk+FrMxGMzho2+tjr5ticU=
-github.com/ugorji/go/codec v1.2.9/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
+github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
@@ -302,8 +314,9 @@ go.uber.org/tools v0.0.0-20190618225709-2cfd321de3ee/go.mod h1:vJERXedbb3MVM5f9E
 go.uber.org/zap v1.9.1/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
 go.uber.org/zap v1.10.0/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
 go.uber.org/zap v1.13.0/go.mod h1:zwrFLgMcdUuIBviXEYEH1YKNaOBnKXsx2IPda5bBwHM=
-golang.org/x/arch v0.0.0-20210923205945-b76863e36670 h1:18EFjUmQOcUvxNYSkA6jO9VAiXCnxFY6NyDX0bHDmkU=
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
+golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
+golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20190411191339-88737f569e3a/go.mod h1:WFFai1msRO1wXaEeE5yQxYXgSfI8pQAWXbQop6sCtWE=
 golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
@@ -316,9 +329,12 @@ golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5y
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20220722155217-630584e8d5aa/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
-golang.org/x/crypto v0.5.0 h1:U/0M97KRkSFvyD/3FSmdP5W5swImpNgle/EHFhOsQPE=
-golang.org/x/crypto v0.5.0/go.mod h1:NK/OQwhpMQP3MwtdjgLlYHnH9ebylxKWv3e0fK+mkQU=
+golang.org/x/crypto v0.9.0 h1:LF6fAI+IutBocDJ2OT0Q1g8plpYljMZ4+lty+dsqw3g=
+golang.org/x/crypto v0.9.0/go.mod h1:yrmDGqONDYtNj3tH8X9dzUun2m2lzPa9ngI6/RUPGR0=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
+golang.org/x/image v0.0.0-20190501045829-6d32002ffd75/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
+golang.org/x/image v0.5.0 h1:5JMiNunQeQw++mMOz48/ISeNu3Iweh/JaZU8ZLqHRrI=
+golang.org/x/image v0.5.0/go.mod h1:FVC7BI/5Ym8R25iw5OLsgshdUBbT1h5jZTpA+mvAdZ4=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
 golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
 golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
@@ -343,12 +359,12 @@ golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwY
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
-golang.org/x/net v0.7.0 h1:rJrUqqhjsgNp7KqAIc25s9pZnjU7TUcSY7HcVZjdn1g=
-golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/net v0.10.0 h1:X2//UzNDwYmtCLn7To6G58Wr6f5ahEAQgKNzv9Y951M=
+golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20200107190931-bf48bf16ab8d/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
-golang.org/x/oauth2 v0.3.0 h1:6l90koy8/LaBLmLu8jpHeHexzMwEita0zFfYlggy2F8=
-golang.org/x/oauth2 v0.3.0/go.mod h1:rQrIauxkUhJ6CuwEXwymO2/eh4xz2ZWF1nBkcxS+tGk=
+golang.org/x/oauth2 v0.4.0 h1:NF0gk8LVPg1Ml7SSbGyySuoxdsXitj7TvgvuRxIMc/M=
+golang.org/x/oauth2 v0.4.0/go.mod h1:RznEsdpjGAINPTOF0UH/t+xJ75L18YO3Ho6Pyn+uRec=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -375,10 +391,11 @@ golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.5.0 h1:MUK/U/4lj1t1oPg0HfuXDN/Z1wv31ZJ/YcPiGccS4DU=
-golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.8.0 h1:EBmGv8NaZBZTWvrbjNoL6HVt+IVy3QDQpJs7VRIw3tU=
+golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
@@ -389,8 +406,9 @@ golang.org/x/text v0.3.4/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
-golang.org/x/text v0.7.0 h1:4BRB4x83lYWy72KwLD/qYDuTu7q9PjSagHvijDw7cLo=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
+golang.org/x/text v0.9.0 h1:2sjJmO8cDvYveuX97RDLsxlyUxLl+GHoLxBiRdHllBE=
+golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -419,20 +437,20 @@ google.golang.org/appengine v1.6.7/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCID
 google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
 google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
 google.golang.org/genproto v0.0.0-20200513103714-09dca8ec2884/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
-google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef h1:uQ2vjV/sHTsWSqdKeLqmwitzgvjMl7o4IdtHwUDXSJY=
-google.golang.org/genproto v0.0.0-20221227171554-f9683d7f8bef/go.mod h1:RGgjbofJ8xD9Sq1VVhDM1Vok1vRONV+rg+CjzG4SZKM=
+google.golang.org/genproto v0.0.0-20230110181048-76db0878b65f h1:BWUVssLB0HVOSY78gIdvk1dTVYtT1y8SBWtPYuTJ/6w=
+google.golang.org/genproto v0.0.0-20230110181048-76db0878b65f/go.mod h1:RGgjbofJ8xD9Sq1VVhDM1Vok1vRONV+rg+CjzG4SZKM=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
 google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
 google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY=
 google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
 google.golang.org/grpc v1.33.1/go.mod h1:fr5YgcSWrqhRRxogOsw7RzIpsmvOZ6IcH4kBYTpR3n0=
-google.golang.org/grpc v1.51.0 h1:E1eGv1FTqoLIdnBCZufiSHgKjlqG6fKFf6pPWtMTh8U=
-google.golang.org/grpc v1.51.0/go.mod h1:wgNDFcnuBGmxLKI/qn4T+m5BtEBYXJPvibbUPsAIPww=
+google.golang.org/grpc v1.53.0 h1:LAv2ds7cmFV/XTS3XG1NneeENYrXGmorPxsBbptIjNc=
+google.golang.org/grpc v1.53.0/go.mod h1:OnIrk0ipVdj4N5d9IUoFUx72/VlD7+jUsHwZgwSMQpw=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
-google.golang.org/protobuf v1.28.1 h1:d0NfwRgPtno5B1Wa6L2DAG+KivqkdutMf1UhdNx175w=
-google.golang.org/protobuf v1.28.1/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
+google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc h1:2gGKlE2+asNV9m7xrywl36YYNnBG5ZQ0r/BOOxqPpmk=
 gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc/go.mod h1:m7x9LTH6d71AHyAX77c9yqWCCa3UKHcVEj9y7hAtKDk=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

integrations/AliYun/collect/cloud.toml

@@ -0,0 +1,21 @@
+# # collect interval
+# interval = 60
+[[instances]]
+# # endpoint region 参考 https://help.aliyun.com/document_detail/28616.html#section-72p-xhs-6qt
+# region="cn-beijing"
+# endpoint="metrics.cn-hangzhou.aliyuncs.com"
+# access_key_id="your-access-key-id"
+# access_key_secret="your-access-key-secret"
+# interval_times=4
+# delay="10m"
+# period="60s"
+# # namespace 参考 https://help.aliyun.com/document_detail/163515.htm?spm=a2c4g.11186623.0.0.44d65c58mhgNw3
+# namespaces=["acs_ecs_dashboard"]
+# [[instances.metric_filters]]
+# # metric name 参考 https://help.aliyun.com/document_detail/163515.htm?spm=a2c4g.11186623.0.0.401d15c73Z0dZh
+# # 参考页面中的Metric Id 填入下面的metricName ,页面中包含中文的Metric Name对应接口中的Description
+# metric_names=["cpu_cores","vm.TcpCount"]
+# namespace=""
+# ratelimit=25
+# catch_ttl="1h"
+# timeout="5s"

integrations/AliYun/dashboards/ecs.json

@@ -0,0 +1,313 @@
+{
+  "name": "阿里云ECS",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "ident",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_acs_ecs_dashboard_cpu_utilization_average,ident)",
+        "multi": true,
+        "allOption": true
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "8606d5ad-c3c7-4b1d-86bf-474d3302ee17",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "8606d5ad-c3c7-4b1d-86bf-474d3302ee17",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_ecs_dashboard_cpu_utilization_average{ident=~\"$ident\"}) by (ident,instance_id)"
+          }
+        ],
+        "name": "CPU平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c7034fe3-5521-4867-a8bd-429767cc03a2",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "55404296-0bd9-409d-aeaf-e9c7cceea0dd",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_ecs_dashboard_memory_usedutilization_average{ident=~\"$ident\"}) by (ident,instance_id)"
+          }
+        ],
+        "name": "内存平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "e4c11925-b359-4edb-9269-4bdd4d230224",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "0c7b3a5a-ef12-4349-be9b-7a245bf01418",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "expr": "sum(aliyun_acs_ecs_dashboard_load_5m_average{ident=~\"$ident\"}) by (ident,instance_id)",
+            "refId": "B",
+            "legend": "{{ident}} {{instance_id}} 5分钟负载"
+          }
+        ],
+        "name": "系统负载[5m]",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "percent"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "388d4da6-eb1f-48f1-955d-37579809dfec",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 5,
+          "i": "5abea3d2-ea82-4bdb-a4f0-4dd1316c0377",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_ecs_dashboard_diskusage_utilization_average{ident=~\"$ident\"}) by (ident,instance_id)"
+          }
+        ],
+        "name": "磁盘平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "percent"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "f8d19cc9-0168-4c13-b9a9-c7980eced974",
+        "layout": {
+          "x": 0,
+          "y": 9,
+          "w": 12,
+          "h": 4,
+          "i": "f8d19cc9-0168-4c13-b9a9-c7980eced974"
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_ecs_dashboard_intranet_in_average{ident=~\"$ident\"}) by (ident,instance_id)",
+            "legend": "主机：{{ident}} 实例ID: {{instance_id}} 入流量",
+            "step": 300,
+            "time": {
+              "start": "now-5m",
+              "end": "now"
+            }
+          },
+          {
+            "expr": "sum(aliyun_acs_ecs_dashboard_intranet_out_average{ident=~\"$ident\"}) by (ident,instance_id)",
+            "refId": "B",
+            "legend": "主机：{{ident}} 实例ID: {{instance_id}} 出流量",
+            "step": 300,
+            "time": {
+              "start": "now-5m",
+              "end": "now"
+            }
+          }
+        ],
+        "name": "网络流量",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "bitsSI"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/dashboards/rds.json

@@ -0,0 +1,313 @@
+{
+  "name": "阿里云RDS",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "instance_id",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_acs_rds_dashboard_cpu_usage_average,instance_id)",
+        "multi": false
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_cpu_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "CPU平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "09903231-6557-42be-9cf3-2873878e9bf2",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_memory_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "内存平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "37447883-ad79-46bc-888a-1be2835c1c64",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_disk_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "磁盘平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c9735607-3f24-44a7-bbf1-3ad39441c5c9",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "93a4c8a6-ac23-4e26-8a38-781ec1668820",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_iops_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "IOPS平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "b516e7dc-8022-409d-b907-18c4143df891",
+        "layout": {
+          "h": 5,
+          "w": 24,
+          "x": 0,
+          "y": 8,
+          "i": "b516e7dc-8022-409d-b907-18c4143df891",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_delete_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": "delete"
+          },
+          {
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_insert_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "insert"
+          },
+          {
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_insert_select_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "C",
+            "legend": "insert_select"
+          },
+          {
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_update_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "D",
+            "legend": "update"
+          },
+          {
+            "expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_select_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "E",
+            "legend": "select"
+          }
+        ],
+        "name": "SQL执行量",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "percent"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/dashboards/redis.json

@@ -0,0 +1,298 @@
+{
+  "name": "阿里云REDIS",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "instance_id",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_acs_kvstore_cpu_usage_average,instance_id)",
+        "multi": false
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_cpu_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "CPU平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "09903231-6557-42be-9cf3-2873878e9bf2",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_memory_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "内存平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "37447883-ad79-46bc-888a-1be2835c1c64",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_connection_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "连接数平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "c9735607-3f24-44a7-bbf1-3ad39441c5c9",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "93a4c8a6-ac23-4e26-8a38-781ec1668820",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_failed_count_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": ""
+          }
+        ],
+        "name": "失败统计平均使用率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "b516e7dc-8022-409d-b907-18c4143df891",
+        "layout": {
+          "h": 5,
+          "w": 24,
+          "x": 0,
+          "y": 8,
+          "i": "b516e7dc-8022-409d-b907-18c4143df891",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_kvstore_intranet_in_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "legend": "in"
+          },
+          {
+            "expr": "sum(aliyun_acs_kvstore_intranet_out_average{instance_id=\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "out"
+          }
+        ],
+        "name": "网络流量",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "bitsSI"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/dashboards/slb.json

@@ -0,0 +1,376 @@
+{
+  "name": "阿里云SLB",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "instance_id",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_acs_slb_dashboard_active_connection_average ,instance_id)",
+        "multi": true,
+        "allOption": true
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "aa8b2623-1e14-43cd-a3c4-33944a61fcc5",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "aa8b2623-1e14-43cd-a3c4-33944a61fcc5",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "datasourceName": "Default",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_instance_qps_utilization_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} QPS使用率 "
+          }
+        ],
+        "name": "七层实例QPS使用率(%)",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "b2002c63-8f0b-436c-b765-5bb65191f3c2",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "b2002c63-8f0b-436c-b765-5bb65191f3c2",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_upstream_code4xx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 状态码 4xx "
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_upstream_code5xx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "{{instance_id}} 状态码 5xx "
+          }
+        ],
+        "name": "7层协议实例Upstream状态码分布",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "71028d82-4804-468f-92f4-3444953b22cc",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "71028d82-4804-468f-92f4-3444953b22cc",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_instance_new_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 新建连接数"
+          }
+        ],
+        "name": "新建连接数",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "25f90635-ff68-4dc2-bfb0-c6634f0e6867",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "25f90635-ff68-4dc2-bfb0-c6634f0e6867",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_active_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 活跃连接数"
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_inactive_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "{{instance_id}} 非活跃连接数"
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_max_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "C",
+            "legend": "{{instance_id}} 最大活跃连接数"
+          }
+        ],
+        "name": "并发连接数",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "fde27e57-bdd6-4fd6-b3c0-75222f736d3b",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 8,
+          "i": "fde27e57-bdd6-4fd6-b3c0-75222f736d3b",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_packet_rx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 接受数据包数"
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_packet_tx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "{{instance_id}} 发送数据包数"
+          }
+        ],
+        "name": "数据包数",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "none"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "a0fd47db-0b49-4b71-ae16-b4108324e35a",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 8,
+          "i": "a0fd47db-0b49-4b71-ae16-b4108324e35a",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_acs_slb_dashboard_instance_traffic_rx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}} 出流量"
+          },
+          {
+            "expr": "sum(aliyun_acs_slb_dashboard_instance_traffic_tx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "refId": "B",
+            "legend": "{{instance_id}} 入流量"
+          }
+        ],
+        "name": "流量",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {
+            "util": "bitsSI"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/dashboards/waf.json

@@ -0,0 +1,346 @@
+{
+  "name": "阿里云WAF",
+  "tags": "",
+  "ident": "",
+  "configs": {
+    "var": [
+      {
+        "name": "instance_id",
+        "type": "query",
+        "datasource": {
+          "cate": "prometheus"
+        },
+        "definition": "label_values(aliyun_waf_qps_ratio_maximum,instance_id)",
+        "multi": true,
+        "allOption": true
+      }
+    ],
+    "panels": [
+      {
+        "type": "timeseries",
+        "id": "ec46b990-faf5-4ed7-a791-bbac5df91636",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 0,
+          "i": "ec46b990-faf5-4ed7-a791-bbac5df91636",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_4xx_ratio_wafv3_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "4xx 环比率V3"
+          }
+        ],
+        "name": "4xx 环比率V3",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "efc75e62-5e75-470d-b12b-a98ca44b268a",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 0,
+          "i": "584b5a3c-2b7a-4e11-bee5-c2ed8661933e",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_5xx_ratio_wafv3_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "5xx 环比率V3"
+          }
+        ],
+        "name": "5xx 环比率V3",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "79aefa1b-5e50-4c0c-980d-e5523b859509",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 4,
+          "i": "fc875397-c1a4-4713-b564-09abf852bcf3",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_4xx_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "4xx 环比率"
+          }
+        ],
+        "name": "4xx 环比率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "60c211d4-d51a-4681-b23b-ec8cc5dce7fe",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 4,
+          "i": "946be0db-32a3-48ea-9473-88fdfa77201d",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_5xx_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "5xx 环比率"
+          }
+        ],
+        "name": "5xx 环比率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "0de9271c-7b19-4003-ae56-2e273b4b99c4",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 0,
+          "y": 8,
+          "i": "0de9271c-7b19-4003-ae56-2e273b4b99c4",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_qps_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}}QPS 环比增长率"
+          }
+        ],
+        "name": "QPS环比增长率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      },
+      {
+        "type": "timeseries",
+        "id": "ccf2ffc1-6f22-4a13-b795-68072c077e1f",
+        "layout": {
+          "h": 4,
+          "w": 12,
+          "x": 12,
+          "y": 8,
+          "i": "d0320716-f704-4b6e-8671-b58fb77a5d7c",
+          "isResizable": true
+        },
+        "version": "2.0.0",
+        "datasourceCate": "prometheus",
+        "targets": [
+          {
+            "refId": "A",
+            "expr": "sum(aliyun_waf_qps_ratio_down_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
+            "legend": "{{instance_id}}QPS 环比下降率"
+          }
+        ],
+        "name": "QPS环比下降率",
+        "maxPerRow": 4,
+        "options": {
+          "tooltip": {
+            "mode": "all",
+            "sort": "none"
+          },
+          "legend": {
+            "displayMode": "hidden"
+          },
+          "standardOptions": {},
+          "thresholds": {
+            "steps": [
+              {
+                "color": "#634CD9",
+                "value": null,
+                "type": "base"
+              }
+            ]
+          }
+        },
+        "custom": {
+          "drawStyle": "lines",
+          "lineInterpolation": "smooth",
+          "spanNulls": false,
+          "lineWidth": 1,
+          "fillOpacity": 0.5,
+          "gradientMode": "none",
+          "stack": "off",
+          "scaleDistribution": {
+            "type": "linear"
+          }
+        }
+      }
+    ],
+    "version": "2.0.0"
+  }
+}

integrations/AliYun/markdown/README.md

@@ -0,0 +1,70 @@
+# aliyun plugin
+
+## 简介
+
+使用[categraf](https://github.com/flashcatcloud/categraf)中[aliyun](https://github.com/flashcatcloud/categraf/tree/main/inputs/aliyun)插件拉取阿里云云监控的数据（通过 OpenAPI）。
+
+## 授权
+
+获取凭证 [https://usercenter.console.aliyun.com/#/manage/ak](https://usercenter.console.aliyun.com/#/manage/ak)
+RAM 用户授权。RAM 用户调用云监控 API 前，需要所属的阿里云账号将权限策略授予对应的 RAM 用户，参见 [RAM 用户权限](https://help.aliyun.com/document_detail/43170.html?spm=a2c4g.11186623.0.0.30c841feqsoAAn)。
+可以在 [授权页面](https://ram.console.aliyun.com/permissions) 新增授权，选择对应的用户，授予云监控只读权限 `AliyunCloudMonitorReadOnlyAccess`, 并为授予权限的用户创建accessKey 即可。
+
+## Categraf中conf/input.aliyun/cloud.toml配置文件：
+
+```toml
+# # categraf采集周期，阿里云指标的粒度一般是60秒，建议设置不要少于60秒
+interval = 120
+[[instances]]
+## 阿里云资源所处的region
+## endpoint region 参考 https://help.aliyun.com/document_detail/28616.html#section-72p-xhs-6qt
+region="cn-beijing"
+endpoint="metrics.cn-hangzhou.aliyuncs.com"
+## 填入你的access_key_id
+access_key_id=""
+## 填入你的access_key_secret
+access_key_secret=""
+
+## 可能无法获取当前最新指标，这个指标是指监控指标的截止时间距离现在多久
+delay="50m"
+## 阿里云指标的最小粒度，60s 是推荐值，再小了部分指标不支持
+period="60s"
+## 指标所属的namespace ,为空，则表示所有空间指标都要采集
+## namespace 参考 https://help.aliyun.com/document_detail/163515.htm?spm=a2c4g.11186623.0.0.44d65c58mhgNw3
+namespaces=["acs_ecs_dashboard"]
+## 过滤某个namespace下的一个或多个指标
+## metric name 参考 https://help.aliyun.com/document_detail/163515.htm?spm=a2c4g.11186623.0.0.401d15c73Z0dZh
+## 参考页面中的Metric Id 填入下面的metricName ,页面中包含中文的Metric Name对应接口中的Description
+[[instances.metric_filters]]
+namespace=""
+metric_names=["cpu_cores","vm.TcpCount", "cpu_idle"]
+
+# 阿里云查询指标接口的QPS是50， 这里默认设置为一半
+ratelimit=25
+# 查询指定namesapce指标后, namespace/metric_name等meta信息会缓存起来，catch_ttl 是指标的缓存时间
+catch_ttl="1h"
+# 每次请求阿里云endpoint的超时时间
+timeout="5s"
+```
+
+## 效果图
+
+### aliyun ecs
+
+![ecs](http://download.flashcat.cloud/uPic/R6LOcO.jpg)
+
+### aliyun rds
+
+![rds](http://download.flashcat.cloud/uPic/rds.png)
+
+### aliyun redis
+
+![redis](http://download.flashcat.cloud/uPic/redis.png)
+
+### aliyun slb
+
+![slb](http://download.flashcat.cloud/uPic/slb.png)
+
+### aliyun waf
+
+![waf](http://download.flashcat.cloud/uPic/waf.png)