refactor: change sql-template api

* add gorm logger

* add gorm logger implement, slow log save to warning-level file

* optimize gorm logger

* optimize code

---------

Co-authored-by: shardingHe <wangzihe@flashcat.cloud>

.gitignore

@@ -30,7 +30,11 @@ _test
 /dist
 /etc/*.local.yml
 /etc/*.local.conf
+/etc/rsa/*
 /etc/plugins/*.local.yml
+/etc/script/rules.yaml
+/etc/script/alert-rules.json
+/etc/script/record-rules.json
 /data*
 /tarball
 /run
@@ -40,9 +44,12 @@ _test
 /n9e
 /docker/pub
 /docker/n9e
-/docker/mysqldata
-/docker/experience_pg_vm/pgdata
+/docker/compose-bridge/mysqldata
+/docker/compose-host-network/mysqldata
+/docker/compose-postgres/pgdata
 /etc.local*
+/front/statik/statik.go
+/docker/compose-bridge/etc-nightingale/rsa/
 
 .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

@@ -1,6 +1,6 @@
 <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>
+    <img src="doc/img/Nightingale_L_V.png" alt="nightingale - cloud native monitoring" width="240" /></a>
 </p>
 
 <p align="center">
@@ -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_L_V.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"
@@ -23,6 +24,7 @@ import (
 	"github.com/ccfos/nightingale/v6/prom"
 	"github.com/ccfos/nightingale/v6/pushgw/pconf"
 	"github.com/ccfos/nightingale/v6/pushgw/writer"
+	"github.com/ccfos/nightingale/v6/tdengine"
 )
 
 func Initialize(configDir string, cryptoKey string) (func(), error) {
@@ -41,22 +43,27 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	syncStats := memsto.NewSyncStats()
 	alertStats := astats.NewSyncStats()
 
+	configCache := memsto.NewConfigCache(ctx, syncStats, nil, "")
 	targetCache := memsto.NewTargetCache(ctx, syncStats, nil)
 	busiGroupCache := memsto.NewBusiGroupCache(ctx, syncStats)
 	alertMuteCache := memsto.NewAlertMuteCache(ctx, syncStats)
 	alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
-	notifyConfigCache := memsto.NewNotifyConfigCache(ctx)
+	notifyConfigCache := memsto.NewNotifyConfigCache(ctx, configCache)
 	dsCache := memsto.NewDatasourceCache(ctx, syncStats)
+	userCache := memsto.NewUserCache(ctx, syncStats)
+	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
 
-	promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
+	promClients := prom.NewPromClient(ctx)
+	tdengineClients := tdengine.NewTdengineClient(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, tdengineClients, 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 +74,8 @@ 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, tdendgineClients *tdengine.TdengineClientMap, userCache *memsto.UserCacheType, userGroupCache *memsto.UserGroupCacheType) {
 	alertSubscribeCache := memsto.NewAlertSubscribeCache(ctx, syncStats)
 	recordingRuleCache := memsto.NewRecordingRuleCache(ctx, syncStats)
 
@@ -80,14 +86,14 @@ func Start(alertc aconf.Alert, pushgwc pconf.Pushgw, syncStats *memsto.Stats, al
 	writers := writer.NewWriters(pushgwc)
 	record.NewScheduler(alertc, recordingRuleCache, promClients, writers, alertStats)
 
-	eval.NewScheduler(alertc, externalProcessors, alertRuleCache, targetCache, busiGroupCache, alertMuteCache, datasourceCache, promClients, naming, ctx, alertStats)
+	eval.NewScheduler(alertc, externalProcessors, alertRuleCache, targetCache, busiGroupCache, alertMuteCache, datasourceCache, promClients, tdendgineClients, naming, ctx, alertStats)
 
-	dp := dispatch.NewDispatch(alertRuleCache, userCache, userGroupCache, alertSubscribeCache, targetCache, notifyConfigCache, alertc.Alerting, ctx)
+	dp := dispatch.NewDispatch(alertRuleCache, userCache, userGroupCache, alertSubscribeCache, targetCache, notifyConfigCache, alertc.Alerting, ctx, alertStats)
 	consumer := dispatch.NewConsumer(alertc.Alerting, ctx, dp)
 
 	go dp.ReloadTpls()
 	go consumer.LoopConsume()
 
 	go queue.ReportQueueSize(alertStats)
-	go sender.StartEmailSender(notifyConfigCache.GetSMTP()) // todo
+	go sender.InitEmailSender(notifyConfigCache.GetSMTP())
 }

alert/astats/stats.go

@@ -10,22 +10,52 @@ const (
 )
 
 type Stats struct {
-	CounterSampleTotal   *prometheus.CounterVec
-	CounterAlertsTotal   *prometheus.CounterVec
-	GaugeAlertQueueSize  prometheus.Gauge
-	GaugeSampleQueueSize *prometheus.GaugeVec
-	RequestDuration      *prometheus.HistogramVec
-	ForwardDuration      *prometheus.HistogramVec
+	AlertNotifyTotal            *prometheus.CounterVec
+	AlertNotifyErrorTotal       *prometheus.CounterVec
+	CounterAlertsTotal          *prometheus.CounterVec
+	GaugeAlertQueueSize         prometheus.Gauge
+	CounterRuleEval             *prometheus.CounterVec
+	CounterQueryDataErrorTotal  *prometheus.CounterVec
+	CounterRecordEval           *prometheus.CounterVec
+	CounterRecordEvalErrorTotal *prometheus.CounterVec
+	CounterMuteTotal            *prometheus.CounterVec
 }
 
 func NewSyncStats() *Stats {
-	// 从各个接收接口接收到的监控数据总量
-	CounterSampleTotal := prometheus.NewCounterVec(prometheus.CounterOpts{
+	CounterRuleEval := prometheus.NewCounterVec(prometheus.CounterOpts{
 		Namespace: namespace,
 		Subsystem: subsystem,
-		Name:      "samples_received_total",
-		Help:      "Total number samples received.",
-	}, []string{"cluster", "channel"})
+		Name:      "rule_eval_total",
+		Help:      "Number of rule eval.",
+	}, []string{})
+
+	CounterRecordEval := prometheus.NewCounterVec(prometheus.CounterOpts{
+		Namespace: namespace,
+		Subsystem: subsystem,
+		Name:      "record_eval_total",
+		Help:      "Number of record eval.",
+	}, []string{})
+
+	CounterRecordEvalErrorTotal := prometheus.NewCounterVec(prometheus.CounterOpts{
+		Namespace: namespace,
+		Subsystem: subsystem,
+		Name:      "record_eval_error_total",
+		Help:      "Number of record eval error.",
+	}, []string{})
+
+	AlertNotifyTotal := prometheus.NewCounterVec(prometheus.CounterOpts{
+		Namespace: namespace,
+		Subsystem: subsystem,
+		Name:      "alert_notify_total",
+		Help:      "Number of send msg.",
+	}, []string{"channel"})
+
+	AlertNotifyErrorTotal := prometheus.NewCounterVec(prometheus.CounterOpts{
+		Namespace: namespace,
+		Subsystem: subsystem,
+		Name:      "alert_notify_error_total",
+		Help:      "Number of send msg.",
+	}, []string{"channel"})
 
 	// 产生的告警总量
 	CounterAlertsTotal := prometheus.NewCounterVec(prometheus.CounterOpts{
@@ -33,7 +63,7 @@ func NewSyncStats() *Stats {
 		Subsystem: subsystem,
 		Name:      "alerts_total",
 		Help:      "Total number alert events.",
-	}, []string{"cluster"})
+	}, []string{"cluster", "type", "busi_group"})
 
 	// 内存中的告警事件队列的长度
 	GaugeAlertQueueSize := prometheus.NewGauge(prometheus.GaugeOpts{
@@ -43,51 +73,41 @@ func NewSyncStats() *Stats {
 		Help:      "The size of alert queue.",
 	})
 
-	// 数据转发队列，各个队列的长度
-	GaugeSampleQueueSize := prometheus.NewGaugeVec(prometheus.GaugeOpts{
+	CounterQueryDataErrorTotal := prometheus.NewCounterVec(prometheus.CounterOpts{
 		Namespace: namespace,
 		Subsystem: subsystem,
-		Name:      "sample_queue_size",
-		Help:      "The size of sample queue.",
-	}, []string{"cluster", "channel_number"})
+		Name:      "query_data_error_total",
+		Help:      "Number of query data error.",
+	}, []string{"datasource"})
 
-	// 一些重要的请求，比如接收数据的请求，应该统计一下延迟情况
-	RequestDuration := prometheus.NewHistogramVec(
-		prometheus.HistogramOpts{
-			Namespace: namespace,
-			Subsystem: subsystem,
-			Buckets:   []float64{.01, .1, 1},
-			Name:      "http_request_duration_seconds",
-			Help:      "HTTP request latencies in seconds.",
-		}, []string{"code", "path", "method"},
-	)
-
-	// 发往后端TSDB，延迟如何
-	ForwardDuration := prometheus.NewHistogramVec(
-		prometheus.HistogramOpts{
-			Namespace: namespace,
-			Subsystem: subsystem,
-			Buckets:   []float64{.1, 1, 10},
-			Name:      "forward_duration_seconds",
-			Help:      "Forward samples to TSDB. latencies in seconds.",
-		}, []string{"cluster", "channel_number"},
-	)
+	CounterMuteTotal := prometheus.NewCounterVec(prometheus.CounterOpts{
+		Namespace: namespace,
+		Subsystem: subsystem,
+		Name:      "mute_total",
+		Help:      "Number of mute.",
+	}, []string{"group"})
 
 	prometheus.MustRegister(
-		CounterSampleTotal,
 		CounterAlertsTotal,
 		GaugeAlertQueueSize,
-		GaugeSampleQueueSize,
-		RequestDuration,
-		ForwardDuration,
+		AlertNotifyTotal,
+		AlertNotifyErrorTotal,
+		CounterRuleEval,
+		CounterQueryDataErrorTotal,
+		CounterRecordEval,
+		CounterRecordEvalErrorTotal,
+		CounterMuteTotal,
 	)
 
 	return &Stats{
-		CounterSampleTotal:   CounterSampleTotal,
-		CounterAlertsTotal:   CounterAlertsTotal,
-		GaugeAlertQueueSize:  GaugeAlertQueueSize,
-		GaugeSampleQueueSize: GaugeSampleQueueSize,
-		RequestDuration:      RequestDuration,
-		ForwardDuration:      ForwardDuration,
+		CounterAlertsTotal:          CounterAlertsTotal,
+		GaugeAlertQueueSize:         GaugeAlertQueueSize,
+		AlertNotifyTotal:            AlertNotifyTotal,
+		AlertNotifyErrorTotal:       AlertNotifyErrorTotal,
+		CounterRuleEval:             CounterRuleEval,
+		CounterQueryDataErrorTotal:  CounterQueryDataErrorTotal,
+		CounterRecordEval:           CounterRecordEval,
+		CounterRecordEvalErrorTotal: CounterRecordEvalErrorTotal,
+		CounterMuteTotal:            CounterMuteTotal,
 	}
 }

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

@@ -61,6 +61,13 @@ func (e *Consumer) consume(events []interface{}, sema *semaphore.Semaphore) {
 func (e *Consumer) consumeOne(event *models.AlertCurEvent) {
 	LogEvent(event, "consume")
 
+	eventType := "alert"
+	if event.IsRecovered {
+		eventType = "recovery"
+	}
+
+	e.dispatch.astats.CounterAlertsTotal.WithLabelValues(event.Cluster, eventType, event.GroupName).Inc()
+
 	if err := event.ParseRule("rule_name"); err != nil {
 		event.RuleName = fmt.Sprintf("failed to parse rule name: %v", err)
 	}
@@ -83,11 +90,16 @@ 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)
+		var err error
+		event.Id, err = poster.PostByUrlsWithResp[int64](e.ctx, "/v1/n9e/event-persist", event)
 		if err != nil {
-			logger.Errorf("event%+v persist err:%v", event, err)
+			logger.Errorf("event:%+v persist err:%v", event, err)
 		}
 		return
 	}

alert/dispatch/dispatch.go

@@ -9,6 +9,7 @@ import (
 	"time"
 
 	"github.com/ccfos/nightingale/v6/alert/aconf"
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/alert/common"
 	"github.com/ccfos/nightingale/v6/alert/sender"
 	"github.com/ccfos/nightingale/v6/memsto"
@@ -28,11 +29,13 @@ 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
+	ctx    *ctx.Context
+	astats *astats.Stats
 
 	RwLock sync.RWMutex
 }
@@ -40,7 +43,7 @@ type Dispatch struct {
 // 创建一个 Notify 实例
 func NewDispatch(alertRuleCache *memsto.AlertRuleCacheType, userCache *memsto.UserCacheType, userGroupCache *memsto.UserGroupCacheType,
 	alertSubscribeCache *memsto.AlertSubscribeCacheType, targetCache *memsto.TargetCacheType, notifyConfigCache *memsto.NotifyConfigCacheType,
-	alerting aconf.Alerting, ctx *ctx.Context) *Dispatch {
+	alerting aconf.Alerting, ctx *ctx.Context, astats *astats.Stats) *Dispatch {
 	notify := &Dispatch{
 		alertRuleCache:      alertRuleCache,
 		userCache:           userCache,
@@ -51,11 +54,13 @@ 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,
+		ctx:    ctx,
+		astats: astats,
 	}
 	return notify
 }
@@ -63,7 +68,7 @@ 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 +88,24 @@ 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 +146,7 @@ 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 {
@@ -167,45 +173,73 @@ 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.astats)
+			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
-	sender.SendCallbacks(e.ctx, notifyTarget.ToCallbackList(), event, e.targetCache, e.userCache, e.notifyConfigCache.GetIbex())
+	sender.SendCallbacks(e.ctx, notifyTarget.ToCallbackList(), event, e.targetCache, e.userCache, e.notifyConfigCache.GetIbex(), e.astats)
 
 	// handle global webhooks
-	sender.SendWebhooks(notifyTarget.ToWebhookList(), event)
+	sender.SendWebhooks(notifyTarget.ToWebhookList(), event, e.astats)
 
 	// handle plugin call
-	go sender.MayPluginNotify(e.genNoticeBytes(event), e.notifyConfigCache.GetNotifyScript())
+	go sender.MayPluginNotify(e.genNoticeBytes(event), e.notifyConfigCache.GetNotifyScript(), e.astats)
 }
 
 type Notice struct {

alert/eval/alert_rule.go

@@ -12,6 +12,8 @@ import (
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/prom"
+	"github.com/ccfos/nightingale/v6/tdengine"
+
 	"github.com/toolkits/pkg/logger"
 )
 
@@ -29,7 +31,8 @@ type Scheduler struct {
 	alertMuteCache  *memsto.AlertMuteCacheType
 	datasourceCache *memsto.DatasourceCacheType
 
-	promClients *prom.PromClientMap
+	promClients     *prom.PromClientMap
+	tdengineClients *tdengine.TdengineClientMap
 
 	naming *naming.Naming
 
@@ -38,8 +41,8 @@ type Scheduler struct {
 }
 
 func NewScheduler(aconf aconf.Alert, externalProcessors *process.ExternalProcessorsType, arc *memsto.AlertRuleCacheType, targetCache *memsto.TargetCacheType,
-	busiGroupCache *memsto.BusiGroupCacheType, alertMuteCache *memsto.AlertMuteCacheType, datasourceCache *memsto.DatasourceCacheType, promClients *prom.PromClientMap, naming *naming.Naming,
-	ctx *ctx.Context, stats *astats.Stats) *Scheduler {
+	busiGroupCache *memsto.BusiGroupCacheType, alertMuteCache *memsto.AlertMuteCacheType, datasourceCache *memsto.DatasourceCacheType,
+	promClients *prom.PromClientMap, tdengineClients *tdengine.TdengineClientMap, naming *naming.Naming, ctx *ctx.Context, stats *astats.Stats) *Scheduler {
 	scheduler := &Scheduler{
 		aconf:      aconf,
 		alertRules: make(map[string]*AlertRuleWorker),
@@ -52,8 +55,9 @@ func NewScheduler(aconf aconf.Alert, externalProcessors *process.ExternalProcess
 		alertMuteCache:  alertMuteCache,
 		datasourceCache: datasourceCache,
 
-		promClients: promClients,
-		naming:      naming,
+		promClients:     promClients,
+		tdengineClients: tdengineClients,
+		naming:          naming,
 
 		ctx:   ctx,
 		stats: stats,
@@ -85,8 +89,11 @@ func (s *Scheduler) syncAlertRules() {
 		if rule == nil {
 			continue
 		}
-		if rule.IsPrometheusRule() {
+
+		ruleType := rule.GetRuleType()
+		if rule.IsPrometheusRule() || rule.IsLokiRule() || rule.IsTdengineRule() {
 			datasourceIds := s.promClients.Hit(rule.DatasourceIdsJson)
+			datasourceIds = append(datasourceIds, s.tdengineClients.Hit(rule.DatasourceIdsJson)...)
 			for _, dsId := range datasourceIds {
 				if !naming.DatasourceHashRing.IsHit(dsId, fmt.Sprintf("%d", rule.Id), s.aconf.Heartbeat.Endpoint) {
 					continue
@@ -97,13 +104,18 @@ func (s *Scheduler) syncAlertRules() {
 					continue
 				}
 
+				if ds.PluginType != ruleType {
+					logger.Debugf("datasource %d category is %s not %s", dsId, ds.PluginType, ruleType)
+					continue
+				}
+
 				if ds.Status != "enabled" {
 					logger.Debugf("datasource %d status is %s", dsId, ds.Status)
 					continue
 				}
-				processor := process.NewProcessor(rule, dsId, s.alertRuleCache, s.targetCache, s.busiGroupCache, s.alertMuteCache, s.datasourceCache, s.promClients, s.ctx, s.stats)
+				processor := process.NewProcessor(rule, dsId, s.alertRuleCache, s.targetCache, s.busiGroupCache, s.alertMuteCache, s.datasourceCache, s.ctx, s.stats)
 
-				alertRule := NewAlertRuleWorker(rule, dsId, processor, s.promClients, s.ctx)
+				alertRule := NewAlertRuleWorker(rule, dsId, processor, s.promClients, s.tdengineClients, s.ctx)
 				alertRuleWorkers[alertRule.Hash()] = alertRule
 			}
 		} else if rule.IsHostRule() && s.ctx.IsCenter {
@@ -111,8 +123,8 @@ func (s *Scheduler) syncAlertRules() {
 			if !naming.DatasourceHashRing.IsHit(naming.HostDatasource, fmt.Sprintf("%d", rule.Id), s.aconf.Heartbeat.Endpoint) {
 				continue
 			}
-			processor := process.NewProcessor(rule, 0, s.alertRuleCache, s.targetCache, s.busiGroupCache, s.alertMuteCache, s.datasourceCache, s.promClients, s.ctx, s.stats)
-			alertRule := NewAlertRuleWorker(rule, 0, processor, s.promClients, s.ctx)
+			processor := process.NewProcessor(rule, 0, s.alertRuleCache, s.targetCache, s.busiGroupCache, s.alertMuteCache, s.datasourceCache, s.ctx, s.stats)
+			alertRule := NewAlertRuleWorker(rule, 0, processor, s.promClients, s.tdengineClients, s.ctx)
 			alertRuleWorkers[alertRule.Hash()] = alertRule
 		} else {
 			// 如果 rule 不是通过 prometheus engine 来告警的，则创建为 externalRule
@@ -128,7 +140,7 @@ func (s *Scheduler) syncAlertRules() {
 					logger.Debugf("datasource %d status is %s", dsId, ds.Status)
 					continue
 				}
-				processor := process.NewProcessor(rule, dsId, s.alertRuleCache, s.targetCache, s.busiGroupCache, s.alertMuteCache, s.datasourceCache, s.promClients, s.ctx, s.stats)
+				processor := process.NewProcessor(rule, dsId, s.alertRuleCache, s.targetCache, s.busiGroupCache, s.alertMuteCache, s.datasourceCache, s.ctx, s.stats)
 				externalRuleWorkers[processor.Key()] = processor
 			}
 		}

alert/eval/eval.go

@@ -11,8 +11,11 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/process"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/hash"
+	"github.com/ccfos/nightingale/v6/pkg/parser"
 	promsdk "github.com/ccfos/nightingale/v6/pkg/prom"
 	"github.com/ccfos/nightingale/v6/prom"
+	"github.com/ccfos/nightingale/v6/tdengine"
 
 	"github.com/toolkits/pkg/logger"
 	"github.com/toolkits/pkg/str"
@@ -28,19 +31,21 @@ type AlertRuleWorker struct {
 
 	processor *process.Processor
 
-	promClients *prom.PromClientMap
-	ctx         *ctx.Context
+	promClients     *prom.PromClientMap
+	tdengineClients *tdengine.TdengineClientMap
+	ctx             *ctx.Context
 }
 
-func NewAlertRuleWorker(rule *models.AlertRule, datasourceId int64, processor *process.Processor, promClients *prom.PromClientMap, ctx *ctx.Context) *AlertRuleWorker {
+func NewAlertRuleWorker(rule *models.AlertRule, datasourceId int64, processor *process.Processor, promClients *prom.PromClientMap, tdengineClients *tdengine.TdengineClientMap, ctx *ctx.Context) *AlertRuleWorker {
 	arw := &AlertRuleWorker{
 		datasourceId: datasourceId,
 		quit:         make(chan struct{}),
 		rule:         rule,
 		processor:    processor,
 
-		promClients: promClients,
-		ctx:         ctx,
+		promClients:     promClients,
+		tdengineClients: tdengineClients,
+		ctx:             ctx,
 	}
 
 	return arw
@@ -69,14 +74,16 @@ 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)
 			}
 		}
 	}()
@@ -85,17 +92,23 @@ func (arw *AlertRuleWorker) Start() {
 func (arw *AlertRuleWorker) Eval() {
 	cachedRule := arw.rule
 	if cachedRule == nil {
-		//logger.Errorf("rule_eval:%s rule not found", arw.Key())
+		// logger.Errorf("rule_eval:%s rule not found", arw.Key())
 		return
 	}
+	arw.processor.Stats.CounterRuleEval.WithLabelValues().Inc()
 
 	typ := cachedRule.GetRuleType()
-	var lst []common.AnomalyPoint
+	var anomalyPoints []common.AnomalyPoint
+	var recoverPoints []common.AnomalyPoint
 	switch typ {
 	case models.PROMETHEUS:
-		lst = arw.GetPromAnomalyPoint(cachedRule.RuleConfig)
+		anomalyPoints = arw.GetPromAnomalyPoint(cachedRule.RuleConfig)
 	case models.HOST:
-		lst = arw.GetHostAnomalyPoint(cachedRule.RuleConfig)
+		anomalyPoints = arw.GetHostAnomalyPoint(cachedRule.RuleConfig)
+	case models.TDENGINE:
+		anomalyPoints, recoverPoints = arw.GetTdengineAnomalyPoint(cachedRule, arw.processor.DatasourceId())
+	case models.LOKI:
+		anomalyPoints = arw.GetPromAnomalyPoint(cachedRule.RuleConfig)
 	default:
 		return
 	}
@@ -105,7 +118,11 @@ func (arw *AlertRuleWorker) Eval() {
 		return
 	}
 
-	arw.processor.Handle(lst, "inner", arw.inhibit)
+	arw.processor.Handle(anomalyPoints, "inner", arw.inhibit)
+	for _, point := range recoverPoints {
+		str := fmt.Sprintf("%v", point.Value)
+		arw.processor.RecoverSingle(process.Hash(cachedRule.Id, arw.processor.DatasourceId(), point), point.Timestamp, &str)
+	}
 }
 
 func (arw *AlertRuleWorker) Stop() {
@@ -151,11 +168,13 @@ func (arw *AlertRuleWorker) GetPromAnomalyPoint(ruleConfig string) []common.Anom
 		value, warnings, err := readerClient.Query(context.Background(), promql, time.Now())
 		if err != nil {
 			logger.Errorf("rule_eval:%s promql:%s, error:%v", arw.Key(), promql, err)
+			arw.processor.Stats.CounterQueryDataErrorTotal.WithLabelValues(fmt.Sprintf("%d", arw.datasourceId)).Inc()
 			continue
 		}
 
 		if len(warnings) > 0 {
 			logger.Errorf("rule_eval:%s promql:%s, warnings:%v", arw.Key(), promql, warnings)
+			arw.processor.Stats.CounterQueryDataErrorTotal.WithLabelValues(fmt.Sprintf("%d", arw.datasourceId)).Inc()
 			continue
 		}
 
@@ -163,12 +182,118 @@ 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...)
 	}
 	return lst
 }
 
+func (arw *AlertRuleWorker) GetTdengineAnomalyPoint(rule *models.AlertRule, dsId int64) ([]common.AnomalyPoint, []common.AnomalyPoint) {
+	// 获取查询和规则判断条件
+	points := []common.AnomalyPoint{}
+	recoverPoints := []common.AnomalyPoint{}
+	ruleConfig := strings.TrimSpace(rule.RuleConfig)
+	if ruleConfig == "" {
+		logger.Warningf("rule_eval:%d promql is blank", rule.Id)
+		return points, recoverPoints
+	}
+
+	var ruleQuery models.RuleQuery
+	err := json.Unmarshal([]byte(ruleConfig), &ruleQuery)
+	if err != nil {
+		logger.Warningf("rule_eval:%d promql parse error:%s", rule.Id, err.Error())
+		return points, recoverPoints
+	}
+
+	arw.inhibit = ruleQuery.Inhibit
+	if len(ruleQuery.Queries) > 0 {
+		seriesStore := make(map[uint64]*models.DataResp)
+		seriesTagIndex := make(map[uint64][]uint64)
+
+		for _, query := range ruleQuery.Queries {
+			cli := arw.tdengineClients.GetCli(dsId)
+			if cli == nil {
+				logger.Warningf("rule_eval:%d tdengine client is nil", rule.Id)
+				continue
+			}
+
+			series, err := cli.Query(query)
+			if err != nil {
+				logger.Warningf("rule_eval rid:%d query data error: %v", rule.Id, err)
+				continue
+			}
+
+			//  此条日志很重要，是告警判断的现场值
+			logger.Debugf("rule_eval rid:%d req:%+v resp:%+v", rule.Id, query, series)
+			for i := 0; i < len(series); i++ {
+				serieHash := hash.GetHash(series[i].Metric, series[i].Ref)
+				tagHash := hash.GetTagHash(series[i].Metric)
+				seriesStore[serieHash] = series[i]
+
+				// 将曲线按照相同的 tag 分组
+				if _, exists := seriesTagIndex[tagHash]; !exists {
+					seriesTagIndex[tagHash] = make([]uint64, 0)
+				}
+				seriesTagIndex[tagHash] = append(seriesTagIndex[tagHash], serieHash)
+			}
+		}
+
+		// 判断
+		for _, trigger := range ruleQuery.Triggers {
+			for _, seriesHash := range seriesTagIndex {
+				m := make(map[string]float64)
+				var ts int64
+				var sample *models.DataResp
+				var value float64
+				for _, serieHash := range seriesHash {
+					series, exists := seriesStore[serieHash]
+					if !exists {
+						logger.Warningf("rule_eval rid:%d series:%+v not found", rule.Id, series)
+						continue
+					}
+					t, v, exists := series.Last()
+					if !exists {
+						logger.Warningf("rule_eval rid:%d series:%+v value not found", rule.Id, series)
+						continue
+					}
+
+					if !strings.Contains(trigger.Exp, "$"+series.Ref) {
+						// 表达式中不包含该变量
+						continue
+					}
+
+					m["$"+series.Ref] = v
+					m["$"+series.Ref+"."+series.MetricName()] = v
+					ts = int64(t)
+					sample = series
+					value = v
+				}
+				isTriggered := parser.Calc(trigger.Exp, m)
+				//  此条日志很重要，是告警判断的现场值
+				logger.Debugf("rule_eval rid:%d trigger:%+v exp:%s res:%v m:%v", rule.Id, trigger, trigger.Exp, isTriggered, m)
+
+				point := common.AnomalyPoint{
+					Key:       sample.MetricName(),
+					Labels:    sample.Metric,
+					Timestamp: int64(ts),
+					Value:     value,
+					Severity:  trigger.Severity,
+					Triggered: isTriggered,
+				}
+
+				if isTriggered {
+					points = append(points, point)
+				} else {
+					recoverPoints = append(recoverPoints, point)
+				}
+			}
+		}
+	}
+
+	return points, recoverPoints
+}
+
 func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) []common.AnomalyPoint {
 	var lst []common.AnomalyPoint
 	var severity int
@@ -198,6 +323,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) []common.Anom
 			targets, err := models.MissTargetGetsByFilter(arw.ctx, query, t)
 			if err != nil {
 				logger.Errorf("rule_eval:%s query:%v, error:%v", arw.Key(), query, err)
+				arw.processor.Stats.CounterQueryDataErrorTotal.WithLabelValues(fmt.Sprintf("%d", arw.datasourceId)).Inc()
 				continue
 			}
 			for _, target := range targets {
@@ -219,6 +345,7 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) []common.Anom
 			targets, err := models.TargetGetsByFilter(arw.ctx, query, 0, 0)
 			if err != nil {
 				logger.Errorf("rule_eval:%s query:%v, error:%v", arw.Key(), query, err)
+				arw.processor.Stats.CounterQueryDataErrorTotal.WithLabelValues(fmt.Sprintf("%d", arw.datasourceId)).Inc()
 				continue
 			}
 			var targetMap = make(map[string]*models.Target)
@@ -250,12 +377,14 @@ func (arw *AlertRuleWorker) GetHostAnomalyPoint(ruleConfig string) []common.Anom
 			count, err := models.MissTargetCountByFilter(arw.ctx, query, t)
 			if err != nil {
 				logger.Errorf("rule_eval:%s query:%v, error:%v", arw.Key(), query, err)
+				arw.processor.Stats.CounterQueryDataErrorTotal.WithLabelValues(fmt.Sprintf("%d", arw.datasourceId)).Inc()
 				continue
 			}
 
 			total, err := models.TargetCountByFilter(arw.ctx, query)
 			if err != nil {
 				logger.Errorf("rule_eval:%s query:%v, error:%v", arw.Key(), query, err)
+				arw.processor.Stats.CounterQueryDataErrorTotal.WithLabelValues(fmt.Sprintf("%d", arw.datasourceId)).Inc()
 				continue
 			}
 			pct := float64(count) / float64(total) * 100

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 {
@@ -53,10 +53,8 @@ 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 {
-			logger.Debugf("rule id:%s is not work, datasource id:%d failed to get node from hashring:%v", pk, datasourceId, err)
+		if !errors.Is(err, consistent.ErrEmptyCircle) {
+			logger.Errorf("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
 
@@ -65,7 +69,11 @@ type Processor struct {
 
 	promClients *prom.PromClientMap
 	ctx         *ctx.Context
-	stats       *astats.Stats
+	Stats       *astats.Stats
+
+	HandleFireEventHook    HandleEventFunc
+	HandleRecoverEventHook HandleEventFunc
+	EventMuteHook          EventMuteHookFunc
 }
 
 func (p *Processor) Key() string {
@@ -86,7 +94,7 @@ func (p *Processor) Hash() string {
 }
 
 func NewProcessor(rule *models.AlertRule, datasourceId int64, atertRuleCache *memsto.AlertRuleCacheType, targetCache *memsto.TargetCacheType,
-	busiGroupCache *memsto.BusiGroupCacheType, alertMuteCache *memsto.AlertMuteCacheType, datasourceCache *memsto.DatasourceCacheType, promClients *prom.PromClientMap, ctx *ctx.Context,
+	busiGroupCache *memsto.BusiGroupCacheType, alertMuteCache *memsto.AlertMuteCacheType, datasourceCache *memsto.DatasourceCacheType, ctx *ctx.Context,
 	stats *astats.Stats) *Processor {
 
 	p := &Processor{
@@ -99,9 +107,12 @@ func NewProcessor(rule *models.AlertRule, datasourceId int64, atertRuleCache *me
 		atertRuleCache:  atertRuleCache,
 		datasourceCache: datasourceCache,
 
-		promClients: promClients,
-		ctx:         ctx,
-		stats:       stats,
+		ctx:   ctx,
+		Stats: stats,
+
+		HandleFireEventHook:    func(event *models.AlertCurEvent) {},
+		HandleRecoverEventHook: func(event *models.AlertCurEvent) {},
+		EventMuteHook:          func(event *models.AlertCurEvent) bool { return false },
 	}
 
 	p.mayHandleGroup()
@@ -130,9 +141,15 @@ func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inh
 		hash := event.Hash
 		alertingKeys[hash] = struct{}{}
 		if mute.IsMuted(cachedRule, event, p.TargetCache, p.alertMuteCache) {
+			p.Stats.CounterMuteTotal.WithLabelValues(event.GroupName).Inc()
 			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)
 	}
 }
@@ -327,7 +350,6 @@ func (p *Processor) pushEventToQueue(e *models.AlertCurEvent) {
 		p.fires.Set(e.Hash, e)
 	}
 
-	p.stats.CounterAlertsTotal.WithLabelValues(fmt.Sprintf("%d", e.DatasourceId)).Inc()
 	dispatch.LogEvent(e, "push_queue")
 	if !queue.EventQueue.PushFront(e) {
 		logger.Warningf("event_push_queue: queue is full, event:%+v", e)
@@ -405,7 +427,13 @@ func (p *Processor) mayHandleIdent() {
 		if target, exists := p.TargetCache.Get(ident); exists {
 			p.target = target.Ident
 			p.targetNote = target.Note
+		} else {
+			p.target = ident
+			p.targetNote = ""
 		}
+	} else {
+		p.target = ""
+		p.targetNote = ""
 	}
 }
 
@@ -432,7 +460,7 @@ 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

@@ -6,6 +6,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/prom"
 	"github.com/ccfos/nightingale/v6/pushgw/writer"
@@ -18,18 +19,18 @@ type RecordRuleContext struct {
 	datasourceId int64
 	quit         chan struct{}
 
-	rule *models.RecordingRule
-	// writers     *writer.WritersType
+	rule        *models.RecordingRule
 	promClients *prom.PromClientMap
+	stats       *astats.Stats
 }
 
-func NewRecordRuleContext(rule *models.RecordingRule, datasourceId int64, promClients *prom.PromClientMap, writers *writer.WritersType) *RecordRuleContext {
+func NewRecordRuleContext(rule *models.RecordingRule, datasourceId int64, promClients *prom.PromClientMap, writers *writer.WritersType, stats *astats.Stats) *RecordRuleContext {
 	return &RecordRuleContext{
 		datasourceId: datasourceId,
 		quit:         make(chan struct{}),
 		rule:         rule,
 		promClients:  promClients,
-		//writers:      writers,
+		stats:        stats,
 	}
 }
 
@@ -54,20 +55,23 @@ 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)
 			}
 		}
 	}()
 }
 
 func (rrc *RecordRuleContext) Eval() {
+	rrc.stats.CounterRecordEval.WithLabelValues().Inc()
 	promql := strings.TrimSpace(rrc.rule.PromQl)
 	if promql == "" {
 		logger.Errorf("eval:%s promql is blank", rrc.Key())
@@ -76,17 +80,20 @@ func (rrc *RecordRuleContext) Eval() {
 
 	if rrc.promClients.IsNil(rrc.datasourceId) {
 		logger.Errorf("eval:%s reader client is nil", rrc.Key())
+		rrc.stats.CounterRecordEvalErrorTotal.WithLabelValues().Inc()
 		return
 	}
 
 	value, warnings, err := rrc.promClients.GetCli(rrc.datasourceId).Query(context.Background(), promql, time.Now())
 	if err != nil {
 		logger.Errorf("eval:%s promql:%s, error:%v", rrc.Key(), promql, err)
+		rrc.stats.CounterRecordEvalErrorTotal.WithLabelValues().Inc()
 		return
 	}
 
 	if len(warnings) > 0 {
 		logger.Errorf("eval:%s promql:%s, warnings:%v", rrc.Key(), promql, warnings)
+		rrc.stats.CounterRecordEvalErrorTotal.WithLabelValues().Inc()
 		return
 	}
 

alert/record/sample.go

@@ -15,7 +15,7 @@ const (
 	LabelName = "__name__"
 )
 
-func ConvertToTimeSeries(value model.Value, rule *models.RecordingRule) (lst []*prompb.TimeSeries) {
+func ConvertToTimeSeries(value model.Value, rule *models.RecordingRule) (lst []prompb.TimeSeries) {
 	switch value.Type() {
 	case model.ValVector:
 		items, ok := value.(model.Vector)
@@ -31,7 +31,7 @@ func ConvertToTimeSeries(value model.Value, rule *models.RecordingRule) (lst []*
 			s.Timestamp = time.Unix(item.Timestamp.Unix(), 0).UnixNano() / 1e6
 			s.Value = float64(item.Value)
 			l := labelsToLabelsProto(item.Metric, rule)
-			lst = append(lst, &prompb.TimeSeries{
+			lst = append(lst, prompb.TimeSeries{
 				Labels:  l,
 				Samples: []prompb.Sample{s},
 			})
@@ -63,7 +63,7 @@ func ConvertToTimeSeries(value model.Value, rule *models.RecordingRule) (lst []*
 					Value:     float64(v.Value),
 				})
 			}
-			lst = append(lst, &prompb.TimeSeries{
+			lst = append(lst, prompb.TimeSeries{
 				Labels:  l,
 				Samples: slst,
 			})
@@ -78,7 +78,7 @@ func ConvertToTimeSeries(value model.Value, rule *models.RecordingRule) (lst []*
 			return
 		}
 
-		lst = append(lst, &prompb.TimeSeries{
+		lst = append(lst, prompb.TimeSeries{
 			Labels:  nil,
 			Samples: []prompb.Sample{{Value: float64(item.Value), Timestamp: time.Unix(item.Timestamp.Unix(), 0).UnixNano() / 1e6}},
 		})
@@ -89,9 +89,9 @@ func ConvertToTimeSeries(value model.Value, rule *models.RecordingRule) (lst []*
 	return
 }
 
-func labelsToLabelsProto(labels model.Metric, rule *models.RecordingRule) (result []*prompb.Label) {
+func labelsToLabelsProto(labels model.Metric, rule *models.RecordingRule) (result []prompb.Label) {
 	//name
-	nameLs := &prompb.Label{
+	nameLs := prompb.Label{
 		Name:  LabelName,
 		Value: rule.Name,
 	}
@@ -101,7 +101,7 @@ func labelsToLabelsProto(labels model.Metric, rule *models.RecordingRule) (resul
 			continue
 		}
 		if model.LabelNameRE.MatchString(string(k)) {
-			result = append(result, &prompb.Label{
+			result = append(result, prompb.Label{
 				Name:  string(k),
 				Value: string(v),
 			})
@@ -111,7 +111,7 @@ func labelsToLabelsProto(labels model.Metric, rule *models.RecordingRule) (resul
 		for _, v := range rule.AppendTagsJSON {
 			index := strings.Index(v, "=")
 			if model.LabelNameRE.MatchString(v[:index]) {
-				result = append(result, &prompb.Label{
+				result = append(result, prompb.Label{
 					Name:  v[:index],
 					Value: v[index+1:],
 				})

alert/record/scheduler.go

@@ -72,7 +72,7 @@ func (s *Scheduler) syncRecordRules() {
 				continue
 			}
 
-			recordRule := NewRecordRuleContext(rule, dsId, s.promClients, s.writers)
+			recordRule := NewRecordRuleContext(rule, dsId, s.promClients, s.writers, s.stats)
 			recordRules[recordRule.Hash()] = recordRule
 		}
 	}

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/router/router_event.go

@@ -72,8 +72,6 @@ func (rt *Router) pushEventToQueue(c *gin.Context) {
 	event.NotifyChannels = strings.Join(event.NotifyChannelsJSON, " ")
 	event.NotifyGroups = strings.Join(event.NotifyGroupsJSON, " ")
 
-	rt.AlertStats.CounterAlertsTotal.WithLabelValues(event.Cluster).Inc()
-
 	dispatch.LogEvent(event, "http_push_queue")
 	if !queue.EventQueue.PushFront(event) {
 		msg := fmt.Sprintf("event:%+v push_queue err: queue is full", event)
@@ -87,7 +85,8 @@ func (rt *Router) eventPersist(c *gin.Context) {
 	var event *models.AlertCurEvent
 	ginx.BindJSON(c, &event)
 	event.FE2DB()
-	ginx.NewRender(c).Message(models.EventPersist(rt.Ctx, event))
+	err := models.EventPersist(rt.Ctx, event)
+	ginx.NewRender(c).Data(event.Id, err)
 }
 
 type eventForm struct {

alert/sender/callback.go

@@ -1,11 +1,13 @@
 package sender
 
 import (
+	"encoding/json"
 	"strconv"
 	"strings"
 	"time"
 
 	"github.com/ccfos/nightingale/v6/alert/aconf"
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
@@ -15,7 +17,8 @@ import (
 	"github.com/toolkits/pkg/logger"
 )
 
-func SendCallbacks(ctx *ctx.Context, urls []string, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, userCache *memsto.UserCacheType, ibexConf aconf.Ibex) {
+func SendCallbacks(ctx *ctx.Context, urls []string, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, userCache *memsto.UserCacheType,
+	ibexConf aconf.Ibex, stats *astats.Stats) {
 	for _, url := range urls {
 		if url == "" {
 			continue
@@ -32,9 +35,11 @@ func SendCallbacks(ctx *ctx.Context, urls []string, event *models.AlertCurEvent,
 			url = "http://" + url
 		}
 
+		stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
 		resp, code, err := poster.PostJSON(url, 5*time.Second, event, 3)
 		if err != nil {
 			logger.Errorf("event_callback_fail(rule_id=%d url=%s), resp: %s, err: %v, code: %d", event.RuleId, url, string(resp), err, code)
+			stats.AlertNotifyErrorTotal.WithLabelValues("rule_callback").Inc()
 		} else {
 			logger.Infof("event_callback_succ(rule_id=%d url=%s), resp: %s, code: %d", event.RuleId, url, string(resp), code)
 		}
@@ -50,6 +55,7 @@ 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 +96,7 @@ 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 +120,30 @@ 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 +154,7 @@ 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

@@ -5,6 +5,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/poster"
 
@@ -32,7 +33,7 @@ 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 +41,7 @@ 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 +50,7 @@ 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 +58,7 @@ 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{
@@ -66,7 +67,8 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
 				},
 			}
 		}
-		ds.doSend(url, body)
+
+		doSend(url, body, models.Dingtalk, ctx.Stats)
 	}
 }
 
@@ -81,7 +83,7 @@ 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)
@@ -90,11 +92,14 @@ func (ds *DingtalkSender) extract(users []*models.User) ([]string, []string) {
 	return urls, ats
 }
 
-func (ds *DingtalkSender) doSend(url string, body dingtalk) {
+func doSend(url string, body interface{}, channel string, stats *astats.Stats) {
+	stats.AlertNotifyTotal.WithLabelValues(channel).Inc()
+
 	res, code, err := poster.PostJSON(url, time.Second*5, body, 3)
 	if err != nil {
-		logger.Errorf("dingtalk_sender: result=fail url=%s code=%d error=%v response=%s", url, code, err, string(res))
+		logger.Errorf("%s_sender: result=fail url=%s code=%d error=%v response=%s", channel, url, code, err, string(res))
+		stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 	} else {
-		logger.Infof("dingtalk_sender: result=succ url=%s code=%d response=%s", url, code, string(res))
+		logger.Infof("%s_sender: result=succ url=%s code=%d response=%s", channel, url, code, string(res))
 	}
 }

alert/sender/email.go

@@ -2,6 +2,7 @@ package sender
 
 import (
 	"crypto/tls"
+	"errors"
 	"html/template"
 	"time"
 
@@ -22,19 +23,21 @@ 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)
+
+	ctx.Stats.AlertNotifyTotal.WithLabelValues(models.Email).Add(float64(len(tos)))
 }
 
 func extract(users []*models.User) []string {
@@ -47,7 +50,7 @@ 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 +67,9 @@ 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) {
@@ -96,19 +100,21 @@ 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
 	}
-	logger.Infof("start email sender... %+v", conf)
+	logger.Infof("start email sender... conf.Host:%+v,conf.Port:%+v", conf.Host, conf.Port)
 
 	d := gomail.NewDialer(conf.Host, conf.Port, conf.User, conf.Pass)
 	if conf.InsecureSkipVerify {

alert/sender/feishu.go

@@ -3,12 +3,8 @@ package sender
 import (
 	"html/template"
 	"strings"
-	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
-	"github.com/ccfos/nightingale/v6/pkg/poster"
-
-	"github.com/toolkits/pkg/logger"
 )
 
 type feishuContent struct {
@@ -31,11 +27,11 @@ 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",
@@ -49,7 +45,7 @@ func (fs *FeishuSender) Send(ctx MessageContext) {
 				IsAtAll:   false,
 			}
 		}
-		fs.doSend(url, body)
+		doSend(url, body, models.Feishu, ctx.Stats)
 	}
 }
 
@@ -63,7 +59,7 @@ 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)
@@ -71,12 +67,3 @@ func (fs *FeishuSender) extract(users []*models.User) ([]string, []string) {
 	}
 	return urls, ats
 }
-
-func (fs *FeishuSender) doSend(url string, body feishu) {
-	res, code, err := poster.PostJSON(url, time.Second*5, body, 3)
-	if err != nil {
-		logger.Errorf("feishu_sender: result=fail url=%s code=%d error=%v response=%s", url, code, err, string(res))
-	} else {
-		logger.Infof("feishu_sender: result=succ url=%s code=%d response=%s", url, code, string(res))
-	}
-}

alert/sender/feishucard.go

@@ -0,0 +1,131 @@
+package sender
+
+import (
+	"fmt"
+	"html/template"
+	"strings"
+
+	"github.com/ccfos/nightingale/v6/models"
+)
+
+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 {
+		doSend(url, body, models.FeishuCard, ctx.Stats)
+	}
+}
+
+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
+}

alert/sender/mm.go

@@ -4,10 +4,9 @@ import (
 	"html/template"
 	"net/url"
 	"strings"
-	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/models"
-	"github.com/ccfos/nightingale/v6/pkg/poster"
 
 	"github.com/toolkits/pkg/logger"
 )
@@ -15,6 +14,7 @@ import (
 type MatterMostMessage struct {
 	Text   string
 	Tokens []string
+	Stats  *astats.Stats
 }
 
 type mm struct {
@@ -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
 	}
 
@@ -36,11 +36,12 @@ 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,
 		Tokens: urls,
+		Stats:  ctx.Stats,
 	})
 }
 
@@ -87,13 +88,7 @@ func SendMM(message MatterMostMessage) {
 				Username: username,
 				Text:     txt + message.Text,
 			}
-
-			res, code, err := poster.PostJSON(ur, time.Second*5, body, 3)
-			if err != nil {
-				logger.Errorf("mm_sender: result=fail url=%s code=%d error=%v response=%s", ur, code, err, string(res))
-			} else {
-				logger.Infof("mm_sender: result=succ url=%s code=%d response=%s", ur, code, string(res))
-			}
+			doSend(ur, body, models.Mm, message.Stats)
 		}
 	}
 }

alert/sender/plugin.go

@@ -6,6 +6,7 @@ import (
 	"os/exec"
 	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/models"
 
 	"github.com/toolkits/pkg/file"
@@ -13,20 +14,22 @@ import (
 	"github.com/toolkits/pkg/sys"
 )
 
-func MayPluginNotify(noticeBytes []byte, notifyScript models.NotifyScript) {
+func MayPluginNotify(noticeBytes []byte, notifyScript models.NotifyScript, stats *astats.Stats) {
 	if len(noticeBytes) == 0 {
 		return
 	}
-	alertingCallScript(noticeBytes, notifyScript)
+	alertingCallScript(noticeBytes, notifyScript, stats)
 }
 
-func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript) {
+func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript, stats *astats.Stats) {
 	// not enable or no notify.py? do nothing
 	config := notifyScript
 	if !config.Enable || config.Content == "" {
 		return
 	}
 
+	channel := "script"
+	stats.AlertNotifyTotal.WithLabelValues(channel).Inc()
 	fpath := ".notify_scriptt"
 	if config.Type == 1 {
 		fpath = config.Content
@@ -36,6 +39,7 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript) {
 			oldContent, err := file.ToString(fpath)
 			if err != nil {
 				logger.Errorf("event_script_notify_fail: read script file err: %v", err)
+				stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 				return
 			}
 
@@ -48,12 +52,14 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript) {
 			_, err := file.WriteString(fpath, config.Content)
 			if err != nil {
 				logger.Errorf("event_script_notify_fail: write script file err: %v", err)
+				stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 				return
 			}
 
 			err = os.Chmod(fpath, 0777)
 			if err != nil {
 				logger.Errorf("event_script_notify_fail: chmod script file err: %v", err)
+				stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 				return
 			}
 		}
@@ -83,13 +89,14 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript) {
 
 		if err != nil {
 			logger.Errorf("event_script_notify_fail: kill process %s occur error %v", fpath, err)
+			stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 		}
-
 		return
 	}
 
 	if err != nil {
 		logger.Errorf("event_script_notify_fail: exec script %s occur error: %v, output: %s", fpath, err, buf.String())
+		stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 		return
 	}
 

alert/sender/sender.go

@@ -5,6 +5,7 @@ import (
 	"html/template"
 
 	"github.com/ccfos/nightingale/v6/alert/aconf"
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
 )
@@ -17,13 +18,14 @@ 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
+		Stats  *astats.Stats
 	}
 )
 
-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 +33,10 @@ 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 +45,33 @@ 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, stats *astats.Stats) MessageContext {
 	users := userCache.GetByUserIds(uids)
 	return MessageContext{
-		Rule:  rule,
-		Event: event,
-		Users: users,
+		Rule:   rule,
+		Events: events,
+		Users:  users,
+		Stats:  stats,
 	}
 }
 
-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

@@ -3,10 +3,9 @@ package sender
 import (
 	"html/template"
 	"strings"
-	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/models"
-	"github.com/ccfos/nightingale/v6/pkg/poster"
 
 	"github.com/toolkits/pkg/logger"
 )
@@ -14,6 +13,7 @@ import (
 type TelegramMessage struct {
 	Text   string
 	Tokens []string
+	Stats  *astats.Stats
 }
 
 type telegram struct {
@@ -26,15 +26,16 @@ 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,
 		Tokens: tokens,
+		Stats:  ctx.Stats,
 	})
 }
 
@@ -55,7 +56,7 @@ 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], "/")
@@ -72,11 +73,6 @@ func SendTelegram(message TelegramMessage) {
 			Text:      message.Text,
 		}
 
-		res, code, err := poster.PostJSON(url, time.Second*5, body, 3)
-		if err != nil {
-			logger.Errorf("telegram_sender: result=fail url=%s code=%d error=%v response=%s", url, code, err, string(res))
-		} else {
-			logger.Infof("telegram_sender: result=succ url=%s code=%d response=%s", url, code, string(res))
-		}
+		doSend(url, body, models.Telegram, message.Stats)
 	}
 }

alert/sender/webhook.go

@@ -3,16 +3,17 @@ package sender
 import (
 	"bytes"
 	"encoding/json"
-	"io/ioutil"
+	"io"
 	"net/http"
 	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/models"
 
 	"github.com/toolkits/pkg/logger"
 )
 
-func SendWebhooks(webhooks []*models.Webhook, event *models.AlertCurEvent) {
+func SendWebhooks(webhooks []*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
 	for _, conf := range webhooks {
 		if conf.Url == "" || !conf.Enable {
 			continue
@@ -50,9 +51,11 @@ func SendWebhooks(webhooks []*models.Webhook, event *models.AlertCurEvent) {
 			Timeout: time.Duration(conf.Timeout) * time.Second,
 		}
 
+		stats.AlertNotifyTotal.WithLabelValues("webhook").Inc()
 		var resp *http.Response
 		resp, err = client.Do(req)
 		if err != nil {
+			stats.AlertNotifyErrorTotal.WithLabelValues("webhook").Inc()
 			logger.Errorf("event_webhook_fail, ruleId: [%d], eventId: [%d], url: [%s], error: [%s]", event.RuleId, event.Id, conf.Url, err)
 			continue
 		}
@@ -60,7 +63,7 @@ func SendWebhooks(webhooks []*models.Webhook, event *models.AlertCurEvent) {
 		var body []byte
 		if resp.Body != nil {
 			defer resp.Body.Close()
-			body, _ = ioutil.ReadAll(resp.Body)
+			body, _ = io.ReadAll(resp.Body)
 		}
 
 		logger.Debugf("event_webhook_succ, url: %s, response code: %d, body: %s", conf.Url, resp.StatusCode, string(body))

alert/sender/wecom.go

@@ -3,12 +3,8 @@ package sender
 import (
 	"html/template"
 	"strings"
-	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
-	"github.com/ccfos/nightingale/v6/pkg/poster"
-
-	"github.com/toolkits/pkg/logger"
 )
 
 type wecomMarkdown struct {
@@ -25,11 +21,11 @@ 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",
@@ -37,7 +33,7 @@ func (ws *WecomSender) Send(ctx MessageContext) {
 				Content: message,
 			},
 		}
-		ws.doSend(url, body)
+		doSend(url, body, models.Wecom, ctx.Stats)
 	}
 }
 
@@ -46,7 +42,7 @@ 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)
@@ -54,12 +50,3 @@ func (ws *WecomSender) extract(users []*models.User) []string {
 	}
 	return urls
 }
-
-func (ws *WecomSender) doSend(url string, body wecom) {
-	res, code, err := poster.PostJSON(url, time.Second*5, body, 3)
-	if err != nil {
-		logger.Errorf("wecom_sender: result=fail url=%s code=%d error=%v response=%s", url, code, err, string(res))
-	} else {
-		logger.Infof("wecom_sender: result=succ url=%s code=%d response=%s", url, code, string(res))
-	}
-}

center/cconf/conf.go

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

center/cconf/ops.go

@@ -1,9 +1,11 @@
 package cconf
 
 import (
+	"fmt"
 	"path"
 
 	"github.com/toolkits/pkg/file"
+	"gopkg.in/yaml.v2"
 )
 
 var Operations = Operation{}
@@ -36,3 +38,142 @@ func GetAllOps(ops []Ops) []string {
 	}
 	return ret
 }
+
+func MergeOperationConf() error {
+	opsBuiltIn := Operation{}
+	err := yaml.Unmarshal([]byte(builtInOps), &opsBuiltIn)
+	if err != nil {
+		return fmt.Errorf("cannot parse builtInOps: %s", err.Error())
+	}
+	configOpsMap := make(map[string]struct{})
+	for _, op := range Operations.Ops {
+		configOpsMap[op.Name] = struct{}{}
+	}
+	//If the opBu.Name is not a constant in the target (Operations.Ops), add Ops from the built-in options
+	for _, opBu := range opsBuiltIn.Ops {
+		if _, has := configOpsMap[opBu.Name]; !has {
+			Operations.Ops = append(Operations.Ops, opBu)
+		}
+	}
+	return nil
+}
+
+const (
+	builtInOps = `
+ops:
+- name: dashboards
+  cname: 仪表盘
+  ops:
+    - "/dashboards"
+    - "/dashboards/add"
+    - "/dashboards/put"
+    - "/dashboards/del"
+    - "/dashboards-built-in"
+
+- name: alert
+  cname: 告警规则
+  ops:
+    - "/alert-rules"
+    - "/alert-rules/add"
+    - "/alert-rules/put"
+    - "/alert-rules/del"
+    - "/alert-rules-built-in"
+- name: alert-mutes
+  cname: 告警静默管理
+  ops:
+    - "/alert-mutes"
+    - "/alert-mutes/add"
+    - "/alert-mutes/put"
+    - "/alert-mutes/del"
+  
+- name: alert-subscribes
+  cname: 告警订阅管理
+  ops:
+    - "/alert-subscribes"
+    - "/alert-subscribes/add"
+    - "/alert-subscribes/put"
+    - "/alert-subscribes/del"
+
+- name: alert-events  
+  cname: 告警事件管理
+  ops:
+    - "/alert-cur-events"
+    - "/alert-cur-events/del"
+    - "/alert-his-events" 
+
+- name: recording-rules
+  cname: 记录规则管理
+  ops:
+    - "/recording-rules"
+    - "/recording-rules/add"
+    - "/recording-rules/put"
+    - "/recording-rules/del"
+
+- name: metric
+  cname: 时序指标
+  ops:
+  - "/metric/explorer"
+  - "/object/explorer"
+
+- name: log
+  cname: 日志分析
+  ops:
+  - "/log/explorer"
+  - "/log/index-patterns"
+
+- name: targets
+  cname: 基础设施
+  ops:
+    - "/targets"
+    - "/targets/add"
+    - "/targets/put"
+    - "/targets/del"
+
+- name: job
+  cname: 任务管理
+  ops:
+    - "/job-tpls"
+    - "/job-tpls/add"
+    - "/job-tpls/put"
+    - "/job-tpls/del"
+    - "/job-tasks"
+    - "/job-tasks/add"
+    - "/job-tasks/put"
+    - "/ibex-settings"
+
+- name: user
+  cname: 用户管理
+  ops:
+  - "/users"
+  - "/user-groups"
+  - "/user-groups/add"
+  - "/user-groups/put"
+  - "/user-groups/del"
+
+- name: permissions
+  cname: 权限管理
+  ops:
+  - "/permissions"
+
+- name: busi-groups
+  cname: 业务分组管理
+  ops:
+  - "/busi-groups"
+  - "/busi-groups/add"
+  - "/busi-groups/put"
+  - "/busi-groups/del"
+
+- name: system
+  cname: 系统信息
+  ops:
+  - "/help/variable-configs"
+  - "/help/version"
+  - "/help/servers"
+  - "/help/source"
+  - "/help/sso"
+  - "/help/notification-tpls"
+  - "/help/notification-settings"
+  - "/help/migrate"
+  - "/site-settings"
+`
+)

center/cconf/plugin.go

@@ -15,8 +15,14 @@ var Plugins = []Plugin{
 	},
 	{
 		Id:       3,
-		Category: "logging",
-		Type:     "jaeger",
-		TypeName: "Jaeger",
+		Category: "loki",
+		Type:     "loki",
+		TypeName: "Loki",
+	},
+	{
+		Id:       4,
+		Category: "timeseries",
+		Type:     "tdengine",
+		TypeName: "TDengine",
 	},
 }

center/cconf/rsa/rsa_conf.go

@@ -0,0 +1,105 @@
+package rsa
+
+import (
+	"os"
+
+	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/httpx"
+	"github.com/ccfos/nightingale/v6/pkg/secu"
+
+	"github.com/pkg/errors"
+	"github.com/toolkits/pkg/file"
+	"github.com/toolkits/pkg/logger"
+)
+
+func InitRSAConfig(ctx *ctx.Context, rsaConfig *httpx.RSAConfig) error {
+
+	// 1.Load RSA keys from Database
+	rsaPassWord, err := models.ConfigsGet(ctx, models.RSA_PASSWORD)
+	if err != nil {
+		return errors.WithMessagef(err, "cannot query config(%s)", models.RSA_PASSWORD)
+	}
+	privateKeyVal, err := models.ConfigsGet(ctx, models.RSA_PRIVATE_KEY)
+	if err != nil {
+		return errors.WithMessagef(err, "cannot query config(%s)", models.RSA_PRIVATE_KEY)
+	}
+	publicKeyVal, err := models.ConfigsGet(ctx, models.RSA_PUBLIC_KEY)
+	if err != nil {
+		return errors.WithMessagef(err, "cannot query config(%s)", models.RSA_PUBLIC_KEY)
+	}
+	if rsaPassWord != "" && privateKeyVal != "" && publicKeyVal != "" {
+		rsaConfig.RSAPassWord = rsaPassWord
+		rsaConfig.RSAPrivateKey = []byte(privateKeyVal)
+		rsaConfig.RSAPublicKey = []byte(publicKeyVal)
+		return nil
+	}
+
+	// 2.Read RSA configuration from file if exists
+	if file.IsExist(rsaConfig.RSAPrivateKeyPath) && file.IsExist(rsaConfig.RSAPublicKeyPath) {
+		//password already read from config
+		rsaConfig.RSAPrivateKey, rsaConfig.RSAPublicKey, err = readConfigFile(rsaConfig)
+		if err != nil {
+			return errors.WithMessage(err, "failed to read rsa config from file")
+		}
+		return nil
+	}
+	// 3.Generate RSA keys if not exist
+	rsaConfig.RSAPassWord, rsaConfig.RSAPrivateKey, rsaConfig.RSAPublicKey, err = initRSAKeyPairs(ctx, rsaConfig.RSAPassWord)
+	if err != nil {
+		return errors.WithMessage(err, "failed to generate rsa key pair")
+	}
+	return nil
+}
+
+func initRSAKeyPairs(ctx *ctx.Context, rsaPassWord string) (password string, privateByte, publicByte []byte, err error) {
+
+	// Generate RSA keys
+
+	// Generate RSA password
+	if rsaPassWord != "" {
+		logger.Debug("Using existing RSA password")
+		password = rsaPassWord
+		err = models.ConfigsSet(ctx, models.RSA_PASSWORD, password)
+		if err != nil {
+			err = errors.WithMessagef(err, "failed to set config(%s)", models.RSA_PASSWORD)
+			return
+		}
+	} else {
+		password, err = models.InitRSAPassWord(ctx)
+		if err != nil {
+			err = errors.WithMessage(err, "failed to generate rsa password")
+			return
+		}
+	}
+	privateByte, publicByte, err = secu.GenerateRsaKeyPair(password)
+	if err != nil {
+		err = errors.WithMessage(err, "failed to generate rsa key pair")
+		return
+	}
+	// Save generated RSA keys
+	err = models.ConfigsSet(ctx, models.RSA_PRIVATE_KEY, string(privateByte))
+	if err != nil {
+		err = errors.WithMessagef(err, "failed to set config(%s)", models.RSA_PRIVATE_KEY)
+		return
+	}
+	err = models.ConfigsSet(ctx, models.RSA_PUBLIC_KEY, string(publicByte))
+	if err != nil {
+		err = errors.WithMessagef(err, "failed to set config(%s)", models.RSA_PUBLIC_KEY)
+		return
+	}
+	return
+}
+
+func readConfigFile(rsaConfig *httpx.RSAConfig) (privateBuf, publicBuf []byte, err error) {
+	publicBuf, err = os.ReadFile(rsaConfig.RSAPublicKeyPath)
+	if err != nil {
+		err = errors.WithMessagef(err, "could not read RSAPublicKeyPath %q", rsaConfig.RSAPublicKeyPath)
+		return
+	}
+	privateBuf, err = os.ReadFile(rsaConfig.RSAPrivateKeyPath)
+	if err != nil {
+		err = errors.WithMessagef(err, "could not read RSAPrivateKeyPath %q", rsaConfig.RSAPrivateKeyPath)
+	}
+	return
+}

center/cconf/sql_tpl.go

@@ -0,0 +1,15 @@
+package cconf
+
+var TDengineSQLTpl = map[string]string{
+	"load5":                "SELECT _wstart as ts, last(load5) FROM $database.system WHERE host = '$server' and _ts >= $from and _ts <= $to interval($interval) fill(null)",
+	"process_total":        "SELECT _wstart as ts, last(total) FROM $database.processes WHERE host = '$server' and _ts >= $from and _ts <= $to interval($interval) fill(null)",
+	"thread_total":         "SELECT _wstart as ts, last(total) FROM $database.threads WHERE host = '$server' and _ts >= $from and _ts <= $to interval($interval) fill(null)",
+	"cpu_idle":             "SELECT _wstart as ts, last(usage_idle) * -1 + 100 FROM $database.cpu WHERE (host = '$server' and cpu = 'cpu-total') and _ts >= $from and _ts <= $to interval($interval) fill(null)",
+	"mem_used_percent":     "SELECT _wstart as ts, last(used_percent) FROM $database.mem WHERE (host = '$server') and _ts >= $from and _ts <= $to interval($interval) fill(null)",
+	"disk_used_percent":    "SELECT _wstart as ts, last(used_percent) FROM $database.disk WHERE (host = '$server' and path = '/') and _ts >= $from and _ts <= $to interval($interval) fill(null)",
+	"cpu_context_switches": "select ts, derivative(context_switches, 1s, 0) as context FROM (SELECT _wstart as ts, avg(context_switches) as context_switches FROM $database.kernel WHERE host = '$server' and _ts >= $from and _ts <= $to interval($interval) )",
+	"tcp":                  "SELECT _wstart as ts, avg(tcp_close) as CLOSED, avg(tcp_close_wait) as CLOSE_WAIT, avg(tcp_closing) as CLOSING, avg(tcp_established) as ESTABLISHED, avg(tcp_fin_wait1) as FIN_WAIT1, avg(tcp_fin_wait2) as FIN_WAIT2, avg(tcp_last_ack) as LAST_ACK, avg(tcp_syn_recv) as SYN_RECV, avg(tcp_syn_sent) as SYN_SENT, avg(tcp_time_wait) as TIME_WAIT FROM $database.netstat WHERE host = '$server' and _ts >= $from and _ts <= $to interval($interval)",
+	"net_bytes_recv":       "SELECT _wstart as ts, derivative(bytes_recv,1s, 1) as bytes_in FROM $database.net WHERE host = '$server' and interface = '$netif' and _ts >= $from and _ts <= $to group by tbname",
+	"net_bytes_sent":       "SELECT _wstart as ts, derivative(bytes_sent,1s, 1) as bytes_out FROM $database.net WHERE host = '$server' and interface = '$netif' and _ts >= $from and _ts <= $to group by tbname",
+	"disk_total":           "SELECT _wstart as ts, avg(total) AS total, avg(used) as used FROM $database.disk WHERE   path = '$mountpoint' and _ts >= $from and _ts <= $to  interval($interval) group by host",
+}

center/center.go

@@ -8,19 +8,25 @@ 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/cconf/rsa"
+	"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"
 	"github.com/ccfos/nightingale/v6/storage"
+	"github.com/ccfos/nightingale/v6/tdengine"
 
 	alertrt "github.com/ccfos/nightingale/v6/alert/router"
 	centerrt "github.com/ccfos/nightingale/v6/center/router"
@@ -36,21 +42,31 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	cconf.LoadMetricsYaml(configDir, config.Center.MetricsYamlFile)
 	cconf.LoadOpsYaml(configDir, config.Center.OpsYamlFile)
 
+	cconf.MergeOperationConf()
+
 	logxClean, err := logx.Init(config.Log)
 	if err != nil {
 		return nil, err
 	}
 
-	i18nx.Init()
+	i18nx.Init(configDir)
+	cstats.Init()
 
 	db, err := storage.New(config.DB)
 	if err != nil {
 		return nil, err
 	}
 	ctx := ctx.NewContext(context.Background(), db, true)
+	migrate.Migrate(db)
 	models.InitRoot(ctx)
 
-	redis, err := storage.NewRedis(config.Redis)
+	err = rsa.InitRSAConfig(ctx, &config.HTTP.RSA)
+	if err != nil {
+		return nil, err
+	}
+
+	var redis storage.Redis
+	redis, err = storage.NewRedis(config.Redis)
 	if err != nil {
 		return nil, err
 	}
@@ -63,22 +79,29 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 
 	sso := sso.Init(config.Center, ctx)
 
+	configCache := memsto.NewConfigCache(ctx, syncStats, config.HTTP.RSA.RSAPrivateKey, config.HTTP.RSA.RSAPassWord)
 	busiGroupCache := memsto.NewBusiGroupCache(ctx, syncStats)
 	targetCache := memsto.NewTargetCache(ctx, syncStats, redis)
 	dsCache := memsto.NewDatasourceCache(ctx, syncStats)
 	alertMuteCache := memsto.NewAlertMuteCache(ctx, syncStats)
 	alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
-	notifyConfigCache := memsto.NewNotifyConfigCache(ctx)
+	notifyConfigCache := memsto.NewNotifyConfigCache(ctx, configCache)
+	userCache := memsto.NewUserCache(ctx, syncStats)
+	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
 
-	promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
+	promClients := prom.NewPromClient(ctx)
+	tdengineClients := tdengine.NewTdengineClient(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, tdengineClients, userCache, userGroupCache)
 
 	writers := writer.NewWriters(config.Pushgw)
 
+	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, tdengineClients,
+		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 +109,7 @@ 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 +17,17 @@ 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/ccfos/nightingale/v6/tdengine"
 
 	"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 {
@@ -30,15 +37,18 @@ type Router struct {
 	DatasourceCache   *memsto.DatasourceCacheType
 	NotifyConfigCache *memsto.NotifyConfigCacheType
 	PromClients       *prom.PromClientMap
+	TdendgineClients  *tdengine.TdengineClientMap
 	Redis             storage.Redis
 	MetaSet           *metas.Set
+	IdentSet          *idents.Set
 	TargetCache       *memsto.TargetCacheType
 	Sso               *sso.SsoClient
+	UserCache         *memsto.UserCacheType
+	UserGroupCache    *memsto.UserGroupCacheType
 	Ctx               *ctx.Context
 }
 
-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 {
+func New(httpConfig httpx.Config, center cconf.Center, operations cconf.Operation, ds *memsto.DatasourceCacheType, ncc *memsto.NotifyConfigCacheType, pc *prom.PromClientMap, tdendgineClients *tdengine.TdengineClientMap, 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,
@@ -46,10 +56,14 @@ func New(httpConfig httpx.Config, center cconf.Center, operations cconf.Operatio
 		DatasourceCache:   ds,
 		NotifyConfigCache: ncc,
 		PromClients:       pc,
+		TdendgineClients:  tdendgineClients,
 		Redis:             redis,
 		MetaSet:           metaSet,
+		IdentSet:          idents,
 		TargetCache:       tc,
 		Sso:               sso,
+		UserCache:         uc,
+		UserGroupCache:    ugc,
 		Ctx:               ctx,
 	}
 }
@@ -95,10 +109,32 @@ 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 +149,10 @@ 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)
@@ -124,18 +163,38 @@ func (rt *Router) Config(r *gin.Engine) {
 			pages.POST("/query-range-batch", rt.promBatchQueryRange)
 			pages.POST("/query-instant-batch", rt.promBatchQueryInstant)
 			pages.GET("/datasource/brief", rt.datasourceBriefs)
+
+			pages.POST("/ds-query", rt.QueryData)
+			pages.POST("/logs-query", rt.QueryLog)
+
+			pages.POST("/tdengine-databases", rt.tdengineDatabases)
+			pages.POST("/tdengine-tables", rt.tdengineTables)
+			pages.POST("/tdengine-columns", rt.tdengineColumns)
+
 		} else {
 			pages.Any("/proxy/:id/*url", rt.auth(), rt.dsProxy)
 			pages.POST("/query-range-batch", rt.auth(), rt.promBatchQueryRange)
 			pages.POST("/query-instant-batch", rt.auth(), rt.promBatchQueryInstant)
-			pages.GET("/datasource/brief", rt.auth(), rt.datasourceBriefs)
+			pages.GET("/datasource/brief", rt.auth(), rt.user(), rt.datasourceBriefs)
+
+			pages.POST("/ds-query", rt.auth(), rt.QueryData)
+			pages.POST("/logs-query", rt.auth(), rt.QueryLog)
+
+			pages.POST("/tdengine-databases", rt.auth(), rt.tdengineDatabases)
+			pages.POST("/tdengine-tables", rt.auth(), rt.tdengineTables)
+			pages.POST("/tdengine-columns", rt.auth(), rt.tdengineColumns)
 		}
 
+		pages.GET("/sql-template", rt.QuerySqlTemplate)
 		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)
@@ -203,7 +262,9 @@ 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-groups/boards", rt.auth(), rt.user(), rt.perm("/dashboards"), rt.boardGetsByGids)
 		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)
 		pages.POST("/busi-group/:id/board/:bid/clone", rt.auth(), rt.user(), rt.perm("/dashboards/add"), rt.bgrw(), rt.boardClone)
@@ -221,6 +282,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/alert-rules/builtin/alerts-cates", rt.auth(), rt.user(), rt.builtinAlertCateGets)
 		pages.GET("/alert-rules/builtin/list", rt.auth(), rt.user(), rt.builtinAlertRules)
 
+		pages.GET("/busi-groups/alert-rules", rt.auth(), rt.user(), rt.perm("/alert-rules"), rt.alertRuleGetsByGids)
 		pages.GET("/busi-group/:id/alert-rules", rt.auth(), rt.user(), rt.perm("/alert-rules"), rt.alertRuleGets)
 		pages.POST("/busi-group/:id/alert-rules", rt.auth(), rt.user(), rt.perm("/alert-rules/add"), rt.bgrw(), rt.alertRuleAddByFE)
 		pages.POST("/busi-group/:id/alert-rules/import", rt.auth(), rt.user(), rt.perm("/alert-rules/add"), rt.bgrw(), rt.alertRuleAddByImport)
@@ -228,7 +290,9 @@ 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-groups/recording-rules", rt.auth(), rt.user(), rt.perm("/recording-rules"), rt.recordingRuleGetsByGids)
 		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)
 		pages.DELETE("/busi-group/:id/recording-rules", rt.auth(), rt.user(), rt.perm("/recording-rules/del"), rt.bgrw(), rt.recordingRuleDel)
@@ -236,12 +300,15 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/recording-rule/:rrid", rt.auth(), rt.user(), rt.perm("/recording-rules"), rt.recordingRuleGet)
 		pages.PUT("/busi-group/:id/recording-rules/fields", rt.auth(), rt.user(), rt.perm("/recording-rules/put"), rt.recordingRulePutFields)
 
+		pages.GET("/busi-groups/alert-mutes", rt.auth(), rt.user(), rt.perm("/alert-mutes"), rt.alertMuteGetsByGids)
 		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)
 		pages.PUT("/busi-group/:id/alert-mutes/fields", rt.auth(), rt.user(), rt.perm("/alert-mutes/put"), rt.bgrw(), rt.alertMutePutFields)
 
+		pages.GET("/busi-groups/alert-subscribes", rt.auth(), rt.user(), rt.perm("/alert-subscribes"), rt.alertSubscribeGetsByGids)
 		pages.GET("/busi-group/:id/alert-subscribes", rt.auth(), rt.user(), rt.perm("/alert-subscribes"), rt.bgro(), rt.alertSubscribeGets)
 		pages.GET("/alert-subscribe/:sid", rt.auth(), rt.user(), rt.perm("/alert-subscribes"), rt.alertSubscribeGet)
 		pages.POST("/busi-group/:id/alert-subscribes", rt.auth(), rt.user(), rt.perm("/alert-subscribes/add"), rt.bgrw(), rt.alertSubscribeAdd)
@@ -262,12 +329,14 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.POST("/alert-cur-events/card/details", rt.auth(), rt.alertCurEventsCardDetails)
 		pages.GET("/alert-his-events/list", rt.auth(), rt.alertHisEventsList)
 		pages.DELETE("/alert-cur-events", rt.auth(), rt.user(), rt.perm("/alert-cur-events/del"), rt.alertCurEventDel)
+		pages.GET("/alert-cur-events/stats", rt.auth(), rt.alertCurEventsStatistics)
 
 		pages.GET("/alert-aggr-views", rt.auth(), rt.alertAggrViewGets)
 		pages.DELETE("/alert-aggr-views", rt.auth(), rt.user(), rt.alertAggrViewDel)
 		pages.POST("/alert-aggr-views", rt.auth(), rt.user(), rt.alertAggrViewAdd)
 		pages.PUT("/alert-aggr-views", rt.auth(), rt.user(), rt.alertAggrViewPut)
 
+		pages.GET("/busi-groups/task-tpls", rt.auth(), rt.user(), rt.perm("/job-tpls"), rt.taskTplGetsByGids)
 		pages.GET("/busi-group/:id/task-tpls", rt.auth(), rt.user(), rt.perm("/job-tpls"), rt.bgro(), rt.taskTplGets)
 		pages.POST("/busi-group/:id/task-tpls", rt.auth(), rt.user(), rt.perm("/job-tpls/add"), rt.bgrw(), rt.taskTplAdd)
 		pages.DELETE("/busi-group/:id/task-tpl/:tid", rt.auth(), rt.user(), rt.perm("/job-tpls/del"), rt.bgrw(), rt.taskTplDel)
@@ -276,6 +345,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/busi-group/:id/task-tpl/:tid", rt.auth(), rt.user(), rt.perm("/job-tpls"), rt.bgro(), rt.taskTplGet)
 		pages.PUT("/busi-group/:id/task-tpl/:tid", rt.auth(), rt.user(), rt.perm("/job-tpls/put"), rt.bgrw(), rt.taskTplPut)
 
+		pages.GET("/busi-groups/tasks", rt.auth(), rt.user(), rt.perm("/job-tasks"), rt.taskGetsByGids)
 		pages.GET("/busi-group/:id/tasks", rt.auth(), rt.user(), rt.perm("/job-tasks"), rt.bgro(), rt.taskGets)
 		pages.POST("/busi-group/:id/tasks", rt.auth(), rt.user(), rt.perm("/job-tasks/add"), rt.bgrw(), rt.taskAdd)
 		pages.GET("/busi-group/:id/task/*url", rt.auth(), rt.user(), rt.perm("/job-tasks"), rt.taskProxy)
@@ -284,7 +354,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/servers", rt.auth(), rt.admin(), rt.serversGet)
 		pages.GET("/server-clusters", rt.auth(), rt.admin(), rt.serverClustersGet)
 
-		pages.POST("/datasource/list", rt.auth(), rt.datasourceList)
+		pages.POST("/datasource/list", rt.auth(), rt.user(), rt.datasourceList)
 		pages.POST("/datasource/plugin/list", rt.auth(), rt.pluginList)
 		pages.POST("/datasource/upsert", rt.auth(), rt.admin(), rt.datasourceUpsert)
 		pages.POST("/datasource/desc", rt.auth(), rt.admin(), rt.datasourceGet)
@@ -300,34 +370,71 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.PUT("/role/:id/ops", rt.auth(), rt.admin(), rt.roleBindOperation)
 		pages.GET("/operation", rt.operations)
 
-		pages.GET("/notify-tpls", rt.auth(), rt.admin(), rt.notifyTplGets)
+		pages.GET("/notify-tpls", rt.auth(), rt.user(), rt.perm("/help/notification-tpls"), 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)
 		pages.PUT("/sso-config", rt.auth(), rt.admin(), rt.ssoConfigUpdate)
 
-		pages.GET("/webhooks", rt.auth(), rt.admin(), rt.webhookGets)
+		pages.GET("/webhooks", rt.auth(), rt.user(), rt.webhookGets)
 		pages.PUT("/webhooks", rt.auth(), rt.admin(), rt.webhookPuts)
 
-		pages.GET("/notify-script", rt.auth(), rt.admin(), rt.notifyScriptGet)
+		pages.GET("/notify-script", rt.auth(), rt.user(), rt.perm("/help/notification-settings"), rt.notifyScriptGet)
 		pages.PUT("/notify-script", rt.auth(), rt.admin(), rt.notifyScriptPut)
 
-		pages.GET("/notify-channel", rt.auth(), rt.admin(), rt.notifyChannelGets)
+		pages.GET("/notify-channel", rt.auth(), rt.user(), rt.perm("/help/notification-settings"), rt.notifyChannelGets)
 		pages.PUT("/notify-channel", rt.auth(), rt.admin(), rt.notifyChannelPuts)
 
-		pages.GET("/notify-contact", rt.auth(), rt.admin(), rt.notifyContactGets)
+		pages.GET("/notify-contact", rt.auth(), rt.user(), rt.perm("/help/notification-settings"), rt.notifyContactGets)
 		pages.PUT("/notify-contact", rt.auth(), rt.admin(), rt.notifyContactPuts)
 
-		pages.GET("/notify-config", rt.auth(), rt.admin(), rt.notifyConfigGet)
+		pages.GET("/notify-config", rt.auth(), rt.user(), rt.perm("/help/notification-settings"), 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)
+
+		pages.GET("/user-variable-configs", rt.auth(), rt.user(), rt.perm("/help/variable-configs"), rt.userVariableConfigGets)
+		pages.POST("/user-variable-config", rt.auth(), rt.user(), rt.perm("/help/variable-configs"), rt.userVariableConfigAdd)
+		pages.PUT("/user-variable-config/:id", rt.auth(), rt.user(), rt.perm("/help/variable-configs"), rt.userVariableConfigPut)
+		pages.DELETE("/user-variable-config/:id", rt.auth(), rt.user(), rt.perm("/help/variable-configs"), rt.userVariableConfigDel)
+
+		pages.GET("/config", rt.auth(), rt.admin(), rt.configGetByKey)
+		pages.PUT("/config", rt.auth(), rt.admin(), rt.configPutByKey)
+		pages.GET("/site-info", rt.siteInfo)
+
+		// for admin api
+		pages.GET("/user/busi-groups", rt.auth(), rt.admin(), rt.userBusiGroupsGets)
+
 	}
 
-	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]
+		}
+
+		gv := version.GithubVersion.Load()
+		if gv != nil {
+			ginx.NewRender(c).Data(gin.H{"version": v, "github_verison": gv.(string)}, nil)
+		} else {
+			ginx.NewRender(c).Data(gin.H{"version": v, "github_verison": ""}, 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 +476,8 @@ 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)
@@ -384,14 +493,16 @@ func (rt *Router) Config(r *gin.Engine) {
 			service.GET("/notify-tpls", rt.notifyTplGets)
 
 			service.POST("/task-record-add", rt.taskRecordAdd)
+
+			service.GET("/user-variable/decrypt", rt.userVariableGetDecryptByService)
 		}
 	}
 
-	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

@@ -4,6 +4,7 @@ import (
 	"net/http"
 	"sort"
 	"strings"
+	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
 
@@ -182,10 +183,19 @@ 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 +203,6 @@ 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) {
@@ -208,3 +216,8 @@ func (rt *Router) alertCurEventGet(c *gin.Context) {
 
 	ginx.NewRender(c).Data(event, nil)
 }
+
+func (rt *Router) alertCurEventsStatistics(c *gin.Context) {
+
+	ginx.NewRender(c).Data(models.AlertCurEventStatistics(rt.Ctx, time.Now()), nil)
+}

center/router/router_alert_rule.go

@@ -2,6 +2,7 @@ package router
 
 import (
 	"net/http"
+	"strconv"
 	"strings"
 	"time"
 
@@ -10,6 +11,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/i18n"
+	"github.com/toolkits/pkg/str"
 )
 
 // Return all, front-end search and paging
@@ -26,6 +28,27 @@ func (rt *Router) alertRuleGets(c *gin.Context) {
 	ginx.NewRender(c).Data(ars, err)
 }
 
+func (rt *Router) alertRuleGetsByGids(c *gin.Context) {
+	gids := str.IdsInt64(ginx.QueryStr(c, "gids"), ",")
+	if len(gids) == 0 {
+		ginx.NewRender(c, http.StatusBadRequest).Message("arg(gids) is empty")
+		return
+	}
+	for _, gid := range gids {
+		rt.bgroCheck(c, gid)
+	}
+
+	ars, err := models.AlertRuleGetsByBGIds(rt.Ctx, gids)
+	if err == nil {
+		cache := make(map[int64]*models.UserGroup)
+		for i := 0; i < len(ars); i++ {
+			ars[i].FillNotifyGroups(rt.Ctx, cache)
+			ars[i].FillSeverities()
+		}
+	}
+	ginx.NewRender(c).Data(ars, err)
+}
+
 func (rt *Router) alertRulesGetByService(c *gin.Context) {
 	prods := []string{}
 	prodStr := ginx.QueryStr(c, "prods", "")
@@ -271,3 +294,54 @@ 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

@@ -8,27 +8,52 @@ import (
 
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/str"
 )
 
 // Return all, front-end search and paging
 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)
+}
+
+func (rt *Router) alertSubscribeGetsByGids(c *gin.Context) {
+	gids := str.IdsInt64(ginx.QueryStr(c, "gids"), ",")
+	if len(gids) == 0 {
+		ginx.NewRender(c, http.StatusBadRequest).Message("arg(gids) is empty")
+		return
+	}
+
+	for _, gid := range gids {
+		rt.bgroCheck(c, gid)
+	}
+
+	lst, err := models.AlertSubscribeGetsByBGIds(rt.Ctx, gids)
+	ginx.Dangerous(err)
+
+	ugcache := make(map[int64]*models.UserGroup)
+	rulecache := make(map[int64]string)
+
+	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 +108,9 @@ func (rt *Router) alertSubscribePut(c *gin.Context) {
 			rt.Ctx,
 			"name",
 			"disabled",
+			"prod",
+			"cate",
+			"datasource_ids",
 			"cluster",
 			"rule_id",
 			"tags",
@@ -96,7 +124,10 @@ func (rt *Router) alertSubscribePut(c *gin.Context) {
 			"webhooks",
 			"for_duration",
 			"redefine_webhooks",
-			"datasource_ids",
+			"severities",
+			"extra_config",
+			"busi_groups",
+			"note",
 		))
 	}
 

center/router/router_board.go

@@ -9,6 +9,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"github.com/google/uuid"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/str"
 )
 
 type boardForm struct {
@@ -207,12 +208,24 @@ func (rt *Router) boardGets(c *gin.Context) {
 	ginx.NewRender(c).Data(boards, err)
 }
 
+func (rt *Router) boardGetsByGids(c *gin.Context) {
+	gids := str.IdsInt64(ginx.QueryStr(c, "gids"), ",")
+	query := ginx.QueryStr(c, "query", "")
+
+	for _, gid := range gids {
+		rt.bgroCheck(c, gid)
+	}
+
+	boards, err := models.BoardGetsByBGIds(rt.Ctx, gids, query)
+	ginx.NewRender(c).Data(boards, err)
+}
+
 func (rt *Router) boardClone(c *gin.Context) {
 	me := c.MustGet("user").(*models.User)
 	bo := rt.Board(ginx.UrlParamInt64(c, "bid"))
 
 	newBoard := &models.Board{
-		Name:     bo.Name + " Copy",
+		Name:     bo.Name + " Cloned",
 		Tags:     bo.Tags,
 		GroupId:  bo.GroupId,
 		CreateBy: me.Username,

center/router/router_builtin.go

@@ -78,7 +78,7 @@ func (rt *Router) builtinBoardCateGets(c *gin.Context) {
 	}
 
 	me := c.MustGet("user").(*models.User)
-	buildinFavoritesMap, err := models.BuiltinCateGetByUserId(rt.Ctx, me.Id)
+	builtinFavoritesMap, err := models.BuiltinCateGetByUserId(rt.Ctx, me.Id)
 	if err != nil {
 		logger.Warningf("get builtin favorites fail: %v", err)
 	}
@@ -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 {
@@ -114,7 +117,7 @@ func (rt *Router) builtinBoardCateGets(c *gin.Context) {
 		}
 		boardCate.Boards = boards
 
-		if _, ok := buildinFavoritesMap[dir]; ok {
+		if _, ok := builtinFavoritesMap[dir]; ok {
 			boardCate.Favorite = true
 		}
 
@@ -170,7 +173,7 @@ func (rt *Router) builtinAlertCateGets(c *gin.Context) {
 	}
 
 	me := c.MustGet("user").(*models.User)
-	buildinFavoritesMap, err := models.BuiltinCateGetByUserId(rt.Ctx, me.Id)
+	builtinFavoritesMap, err := models.BuiltinCateGetByUserId(rt.Ctx, me.Id)
 	if err != nil {
 		logger.Warningf("get builtin favorites fail: %v", err)
 	}
@@ -207,7 +210,7 @@ func (rt *Router) builtinAlertCateGets(c *gin.Context) {
 			alertCate.IconUrl = fmt.Sprintf("/api/n9e/integrations/icon/%s/%s", dir, iconFiles[0])
 		}
 
-		if _, ok := buildinFavoritesMap[dir]; ok {
+		if _, ok := builtinFavoritesMap[dir]; ok {
 			alertCate.Favorite = true
 		}
 
@@ -230,7 +233,7 @@ func (rt *Router) builtinAlertRules(c *gin.Context) {
 	}
 
 	me := c.MustGet("user").(*models.User)
-	buildinFavoritesMap, err := models.BuiltinCateGetByUserId(rt.Ctx, me.Id)
+	builtinFavoritesMap, err := models.BuiltinCateGetByUserId(rt.Ctx, me.Id)
 	if err != nil {
 		logger.Warningf("get builtin favorites fail: %v", err)
 	}
@@ -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 {
@@ -268,7 +274,7 @@ func (rt *Router) builtinAlertRules(c *gin.Context) {
 			alertCate.IconUrl = fmt.Sprintf("/api/n9e/integrations/icon/%s/%s", dir, iconFiles[0])
 		}
 
-		if _, ok := buildinFavoritesMap[dir]; ok {
+		if _, ok := builtinFavoritesMap[dir]; ok {
 			alertCate.Favorite = true
 		}
 
@@ -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_config.go

@@ -62,3 +62,8 @@ func (rt *Router) contactKeysGets(c *gin.Context) {
 
 	ginx.NewRender(c).Data(labelAndKeys, nil)
 }
+
+func (rt *Router) siteInfo(c *gin.Context) {
+	config, err := models.ConfigsGet(rt.Ctx, "site_info")
+	ginx.NewRender(c).Data(config, err)
+}

center/router/router_configs.go

@@ -2,6 +2,7 @@ package router
 
 import (
 	"github.com/ccfos/nightingale/v6/models"
+	"time"
 
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
@@ -25,28 +26,49 @@ func (rt *Router) configGetByKey(c *gin.Context) {
 	ginx.NewRender(c).Data(config, err)
 }
 
+func (rt *Router) configPutByKey(c *gin.Context) {
+	var f models.Configs
+	ginx.BindJSON(c, &f)
+	username := c.MustGet("username").(string)
+	ginx.NewRender(c).Message(models.ConfigsSetWithUname(rt.Ctx, f.Ckey, f.Cval, username))
+}
+
 func (rt *Router) configsDel(c *gin.Context) {
 	var f idsForm
 	ginx.BindJSON(c, &f)
 	ginx.NewRender(c).Message(models.ConfigsDel(rt.Ctx, f.Ids))
 }
 
-func (rt *Router) configsPut(c *gin.Context) {
+func (rt *Router) configsPut(c *gin.Context) { //for APIForService
 	var arr []models.Configs
 	ginx.BindJSON(c, &arr)
-
+	username := c.GetString("user")
+	if username == "" {
+		username = "default"
+	}
+	now := time.Now().Unix()
 	for i := 0; i < len(arr); i++ {
+		arr[i].UpdateBy = username
+		arr[i].UpdateAt = now
 		ginx.Dangerous(arr[i].Update(rt.Ctx))
 	}
 
 	ginx.NewRender(c).Message(nil)
 }
 
-func (rt *Router) configsPost(c *gin.Context) {
+func (rt *Router) configsPost(c *gin.Context) { //for APIForService
 	var arr []models.Configs
 	ginx.BindJSON(c, &arr)
-
+	username := c.GetString("user")
+	if username == "" {
+		username = "default"
+	}
+	now := time.Now().Unix()
 	for i := 0; i < len(arr); i++ {
+		arr[i].CreateBy = username
+		arr[i].UpdateBy = username
+		arr[i].CreateAt = now
+		arr[i].UpdateAt = now
 		ginx.Dangerous(arr[i].Add(rt.Ctx))
 	}
 

center/router/router_datasource.go

@@ -3,6 +3,7 @@ package router
 import (
 	"crypto/tls"
 	"fmt"
+	"io"
 	"net/http"
 	"net/url"
 	"strings"
@@ -25,6 +26,11 @@ type listReq struct {
 }
 
 func (rt *Router) datasourceList(c *gin.Context) {
+	if rt.DatasourceCache.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req listReq
 	ginx.BindJSON(c, &req)
 
@@ -32,8 +38,10 @@ func (rt *Router) datasourceList(c *gin.Context) {
 	category := req.Category
 	name := req.Name
 
+	user := c.MustGet("user").(*models.User)
+
 	list, err := models.GetDatasourcesGetsBy(rt.Ctx, typ, category, name, "")
-	Render(c, list, err)
+	Render(c, rt.DatasourceCache.DatasourceFilter(list, user), err)
 }
 
 func (rt *Router) datasourceGetsByService(c *gin.Context) {
@@ -42,29 +50,33 @@ func (rt *Router) datasourceGetsByService(c *gin.Context) {
 	ginx.NewRender(c).Data(lst, err)
 }
 
-type datasourceBrief struct {
-	Id         int64  `json:"id"`
-	Name       string `json:"name"`
-	PluginType string `json:"plugin_type"`
-}
-
 func (rt *Router) datasourceBriefs(c *gin.Context) {
-	var dss []datasourceBrief
+	var dss []*models.Datasource
 	list, err := models.GetDatasourcesGetsBy(rt.Ctx, "", "", "", "")
 	ginx.Dangerous(err)
 
 	for i := range list {
-		dss = append(dss, datasourceBrief{
+		dss = append(dss, &models.Datasource{
 			Id:         list[i].Id,
 			Name:       list[i].Name,
 			PluginType: list[i].PluginType,
 		})
 	}
 
+	if !rt.Center.AnonymousAccess.PromQuerier {
+		user := c.MustGet("user").(*models.User)
+		dss = rt.DatasourceCache.DatasourceFilter(dss, user)
+	}
+
 	ginx.NewRender(c).Data(dss, err)
 }
 
 func (rt *Router) datasourceUpsert(c *gin.Context) {
+	if rt.DatasourceCache.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	username := Username(c)
@@ -94,7 +106,7 @@ func (rt *Router) datasourceUpsert(c *gin.Context) {
 		}
 		err = req.Add(rt.Ctx)
 	} else {
-		err = req.Update(rt.Ctx, "name", "description", "cluster_name", "settings", "http", "auth", "updated_by", "updated_at")
+		err = req.Update(rt.Ctx, "name", "description", "cluster_name", "settings", "http", "auth", "updated_by", "updated_at", "is_default")
 	}
 
 	Render(c, nil, err)
@@ -105,6 +117,10 @@ 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 +139,33 @@ 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)
+		}
+	} else if ds.PluginType == models.TDENGINE {
+		fullURL = fmt.Sprintf("%s/rest/sql", ds.HTTPJson.Url)
+		req, err = http.NewRequest("POST", fullURL, strings.NewReader("show databases"))
+		if err != nil {
+			logger.Errorf("Error creating request: %v", err)
+			return fmt.Errorf("request url:%s failed", fullURL)
+		}
+	}
+
+	if ds.PluginType == models.LOKI {
+		subPath := "/api/v1/labels"
+
+		fullURL = fmt.Sprintf("%s%s", ds.HTTPJson.Url, subPath)
+
+		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)
@@ -156,13 +189,19 @@ func DatasourceCheck(ds models.Datasource) error {
 
 	if resp.StatusCode != 200 {
 		logger.Errorf("Error making request: %v\n", resp.StatusCode)
-		return fmt.Errorf("request url:%s failed code:%d", fullURL, resp.StatusCode)
+		body, _ := io.ReadAll(resp.Body)
+		return fmt.Errorf("request url:%s failed code:%d body:%s", fullURL, resp.StatusCode, string(body))
 	}
 
 	return nil
 }
 
 func (rt *Router) datasourceGet(c *gin.Context) {
+	if rt.DatasourceCache.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	err := req.Get(rt.Ctx)
@@ -170,6 +209,11 @@ func (rt *Router) datasourceGet(c *gin.Context) {
 }
 
 func (rt *Router) datasourceUpdataStatus(c *gin.Context) {
+	if rt.DatasourceCache.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	username := Username(c)
@@ -179,6 +223,11 @@ func (rt *Router) datasourceUpdataStatus(c *gin.Context) {
 }
 
 func (rt *Router) datasourceDel(c *gin.Context) {
+	if rt.DatasourceCache.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.EsIndexPattern
+	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.EsIndexPattern
+	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.EsIndexPattern
+	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_funcs.go

@@ -44,6 +44,10 @@ func (rt *Router) statistic(c *gin.Context) {
 		statistics, err = models.DatasourceStatistics(rt.Ctx)
 		ginx.NewRender(c).Data(statistics, err)
 		return
+	case "user_variable":
+		statistics, err = models.ConfigsUserVariableStatistics(rt.Ctx)
+		ginx.NewRender(c).Data(statistics, err)
+		return
 	default:
 		ginx.Bomb(http.StatusBadRequest, "invalid name")
 	}

center/router/router_heartbeat.go

@@ -4,12 +4,15 @@ import (
 	"compress/gzip"
 	"encoding/json"
 	"io/ioutil"
+	"sort"
+	"strings"
 	"time"
 
 	"github.com/ccfos/nightingale/v6/models"
 
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/logger"
 )
 
 func (rt *Router) heartbeat(c *gin.Context) {
@@ -35,17 +38,52 @@ 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)
+	if target, has := rt.TargetCache.Get(req.Hostname); has && target != nil {
+		gid := ginx.QueryInt64(c, "gid", 0)
+		hostIp := strings.TrimSpace(req.HostIp)
 
-	if gid != 0 {
-		target, has := rt.TargetCache.Get(req.Hostname)
-		if has && target.GroupId != gid {
-			err = models.TargetUpdateBgid(rt.Ctx, []string{req.Hostname}, gid, false)
+		filed := make(map[string]interface{})
+		if gid != 0 && gid != target.GroupId {
+			filed["group_id"] = gid
 		}
+
+		if hostIp != "" && hostIp != target.HostIp {
+			filed["host_ip"] = hostIp
+		}
+
+		if len(req.GlobalLabels) > 0 {
+			lst := []string{}
+			for k, v := range req.GlobalLabels {
+				lst = append(lst, k+"="+v)
+			}
+			sort.Strings(lst)
+			labels := strings.Join(lst, " ")
+			if target.Tags != labels {
+				filed["tags"] = labels
+			}
+		}
+
+		if len(filed) > 0 {
+			err := target.UpdateFieldsMap(rt.Ctx, filed)
+			if err != nil {
+				logger.Errorf("update target fields failed, err: %v", err)
+			}
+		}
+		logger.Debugf("heartbeat field:%+v target: %v", filed, *target)
 	}
 
 	ginx.NewRender(c).Message(err)

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")
@@ -207,7 +230,7 @@ func (rt *Router) loginCallback(c *gin.Context) {
 
 	ret, err := rt.Sso.OIDC.Callback(rt.Redis, c.Request.Context(), code, state)
 	if err != nil {
-		logger.Debugf("sso.callback() get ret %+v error %v", ret, err)
+		logger.Errorf("sso_callback fail. code:%s, state:%s, get ret: %+v. error: %v", code, state, ret, err)
 		ginx.NewRender(c).Data(CallbackOutput{}, err)
 		return
 	}
@@ -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 len(rt.HTTP.RSA.RSAPublicKey) > 0 {
+		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

@@ -5,10 +5,12 @@ import (
 	"strings"
 	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/common"
 	"github.com/ccfos/nightingale/v6/models"
 
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/str"
 )
 
 // Return all, front-end search and paging
@@ -19,6 +21,22 @@ func (rt *Router) alertMuteGetsByBG(c *gin.Context) {
 	ginx.NewRender(c).Data(lst, err)
 }
 
+func (rt *Router) alertMuteGetsByGids(c *gin.Context) {
+	gids := str.IdsInt64(ginx.QueryStr(c, "gids"), ",")
+	if len(gids) == 0 {
+		ginx.NewRender(c, http.StatusBadRequest).Message("arg(gids) is empty")
+		return
+	}
+
+	for _, gid := range gids {
+		rt.bgroCheck(c, gid)
+	}
+
+	lst, err := models.AlertMuteGetsByBGIds(rt.Ctx, gids)
+
+	ginx.NewRender(c).Data(lst, err)
+}
+
 func (rt *Router) alertMuteGets(c *gin.Context) {
 	prods := strings.Fields(ginx.QueryStr(c, "prods", ""))
 	bgid := ginx.QueryInt64(c, "bgid", -1)
@@ -29,16 +47,41 @@ 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 +2,19 @@ package router
 
 import (
 	"encoding/json"
+	"fmt"
+	"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/ccfos/nightingale/v6/pkg/tplx"
 
 	"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) {
@@ -41,8 +45,8 @@ func (rt *Router) webhookPuts(c *gin.Context) {
 
 	data, err := json.Marshal(webhooks)
 	ginx.Dangerous(err)
-
-	ginx.NewRender(c).Message(models.ConfigsSet(rt.Ctx, models.WEBHOOKKEY, string(data)))
+	username := c.MustGet("username").(string)
+	ginx.NewRender(c).Message(models.ConfigsSetWithUname(rt.Ctx, models.WEBHOOKKEY, string(data), username))
 }
 
 func (rt *Router) notifyScriptGet(c *gin.Context) {
@@ -65,8 +69,8 @@ func (rt *Router) notifyScriptPut(c *gin.Context) {
 
 	data, err := json.Marshal(notifyScript)
 	ginx.Dangerous(err)
-
-	ginx.NewRender(c).Message(models.ConfigsSet(rt.Ctx, models.NOTIFYSCRIPT, string(data)))
+	username := c.MustGet("username").(string)
+	ginx.NewRender(c).Message(models.ConfigsSetWithUname(rt.Ctx, models.NOTIFYSCRIPT, string(data), username))
 }
 
 func (rt *Router) notifyChannelGets(c *gin.Context) {
@@ -101,8 +105,8 @@ func (rt *Router) notifyChannelPuts(c *gin.Context) {
 
 	data, err := json.Marshal(notifyChannels)
 	ginx.Dangerous(err)
-
-	ginx.NewRender(c).Message(models.ConfigsSet(rt.Ctx, models.NOTIFYCHANNEL, string(data)))
+	username := c.MustGet("username").(string)
+	ginx.NewRender(c).Message(models.ConfigsSetWithUname(rt.Ctx, models.NOTIFYCHANNEL, string(data), username))
 }
 
 func (rt *Router) notifyContactGets(c *gin.Context) {
@@ -137,8 +141,8 @@ func (rt *Router) notifyContactPuts(c *gin.Context) {
 
 	data, err := json.Marshal(notifyContacts)
 	ginx.Dangerous(err)
-
-	ginx.NewRender(c).Message(models.ConfigsSet(rt.Ctx, models.NOTIFYCONTACT, string(data)))
+	username := c.MustGet("username").(string)
+	ginx.NewRender(c).Message(models.ConfigsSetWithUname(rt.Ctx, models.NOTIFYCONTACT, string(data), username))
 }
 
 func (rt *Router) notifyConfigGet(c *gin.Context) {
@@ -158,10 +162,12 @@ func (rt *Router) notifyConfigGet(c *gin.Context) {
 func (rt *Router) notifyConfigPut(c *gin.Context) {
 	var f models.Configs
 	ginx.BindJSON(c, &f)
+	userVariableMap := rt.NotifyConfigCache.ConfigCache.Get()
+	text := tplx.ReplaceTemplateUseText(f.Ckey, f.Cval, userVariableMap)
 	switch f.Ckey {
 	case models.SMTP:
 		var smtp aconf.SMTPConfig
-		err := toml.Unmarshal([]byte(f.Cval), &smtp)
+		err := toml.Unmarshal([]byte(text), &smtp)
 		ginx.Dangerous(err)
 	case models.IBEX:
 		var ibex aconf.Ibex
@@ -170,24 +176,55 @@ func (rt *Router) notifyConfigPut(c *gin.Context) {
 	default:
 		ginx.Bomb(200, "key %s can not modify", f.Ckey)
 	}
-
-	err := models.ConfigsSet(rt.Ctx, f.Ckey, f.Cval)
-	if err != nil {
-		ginx.Bomb(200, err.Error())
-	}
-
+	username := c.MustGet("username").(string)
+	//insert or update build-in config
+	ginx.Dangerous(models.ConfigsSetWithUname(rt.Ctx, f.Ckey, f.Cval, username))
 	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, errSmtp := SmtpValidate(text)
+		ginx.Dangerous(errSmtp)
 		go sender.RestartEmailSender(smtp)
 	}
 
 	ginx.NewRender(c).Message(nil)
 }
+func SmtpValidate(text string) (aconf.SMTPConfig, error) {
+	var smtp aconf.SMTPConfig
+	var err error
+
+	err = toml.Unmarshal([]byte(text), &smtp)
+	if err != nil {
+		return smtp, err
+	}
+	if smtp.Host == "" || smtp.Port == 0 {
+		return smtp, fmt.Errorf("smtp host or port can not be empty")
+	}
+	return smtp, err
+}
+
+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)
+	}
+	userVariableMap := rt.NotifyConfigCache.ConfigCache.Get()
+	text := tplx.ReplaceTemplateUseText(f.Ckey, f.Cval, userVariableMap)
+	smtp, err := SmtpValidate(text)
+	ginx.Dangerous(err)
+
+	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

@@ -3,39 +3,51 @@ 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/ccfos/nightingale/v6/prom"
 	"github.com/gin-gonic/gin"
 	"github.com/prometheus/common/model"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/logger"
 )
 
-type queryFormItem struct {
+type QueryFormItem struct {
 	Start int64  `json:"start" binding:"required"`
 	End   int64  `json:"end" binding:"required"`
 	Step  int64  `json:"step" binding:"required"`
 	Query string `json:"query" binding:"required"`
 }
 
-type batchQueryForm struct {
+type BatchQueryForm struct {
 	DatasourceId int64           `json:"datasource_id" binding:"required"`
-	Queries      []queryFormItem `json:"queries" binding:"required"`
+	Queries      []QueryFormItem `json:"queries" binding:"required"`
 }
 
 func (rt *Router) promBatchQueryRange(c *gin.Context) {
-	var f batchQueryForm
+	var f BatchQueryForm
 	ginx.Dangerous(c.BindJSON(&f))
 
-	cli := rt.PromClients.GetCli(f.DatasourceId)
+	lst, err := PromBatchQueryRange(rt.PromClients, f)
+	ginx.NewRender(c).Data(lst, err)
+}
 
+func PromBatchQueryRange(pc *prom.PromClientMap, f BatchQueryForm) ([]model.Value, error) {
 	var lst []model.Value
 
+	cli := pc.GetCli(f.DatasourceId)
+	if cli == nil {
+		return lst, fmt.Errorf("no such datasource id: %d", f.DatasourceId)
+	}
+
 	for _, item := range f.Queries {
 		r := pkgprom.Range{
 			Start: time.Unix(item.Start, 0),
@@ -44,15 +56,16 @@ func (rt *Router) promBatchQueryRange(c *gin.Context) {
 		}
 
 		resp, _, err := cli.QueryRange(context.Background(), item.Query, r)
-		ginx.Dangerous(err)
+		if err != nil {
+			return lst, err
+		}
 
 		lst = append(lst, resp)
 	}
-
-	ginx.NewRender(c).Data(lst, nil)
+	return lst, nil
 }
 
-type batchInstantForm struct {
+type BatchInstantForm struct {
 	DatasourceId int64             `json:"datasource_id" binding:"required"`
 	Queries      []InstantFormItem `json:"queries" binding:"required"`
 }
@@ -63,21 +76,31 @@ type InstantFormItem struct {
 }
 
 func (rt *Router) promBatchQueryInstant(c *gin.Context) {
-	var f batchInstantForm
+	var f BatchInstantForm
 	ginx.Dangerous(c.BindJSON(&f))
 
-	cli := rt.PromClients.GetCli(f.DatasourceId)
+	lst, err := PromBatchQueryInstant(rt.PromClients, f)
+	ginx.NewRender(c).Data(lst, err)
+}
 
+func PromBatchQueryInstant(pc *prom.PromClientMap, f BatchInstantForm) ([]model.Value, error) {
 	var lst []model.Value
 
+	cli := pc.GetCli(f.DatasourceId)
+	if cli == nil {
+		logger.Warningf("no such datasource id: %d", f.DatasourceId)
+		return lst, fmt.Errorf("no such datasource id: %d", f.DatasourceId)
+	}
+
 	for _, item := range f.Queries {
 		resp, _, err := cli.Query(context.Background(), item.Query, time.Unix(item.Time, 0))
-		ginx.Dangerous(err)
+		if err != nil {
+			return lst, err
+		}
 
 		lst = append(lst, resp)
 	}
-
-	ginx.NewRender(c).Data(lst, nil)
+	return lst, nil
 }
 
 func (rt *Router) dsProxy(c *gin.Context) {
@@ -139,21 +162,77 @@ 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 {
+			logger.Warningf("proxy path:%s unauthorized access ", c.Request.URL.Path)
+			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_recording_rule.go

@@ -11,6 +11,7 @@ import (
 
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/str"
 )
 
 func (rt *Router) recordingRuleGets(c *gin.Context) {
@@ -19,6 +20,21 @@ func (rt *Router) recordingRuleGets(c *gin.Context) {
 	ginx.NewRender(c).Data(ars, err)
 }
 
+func (rt *Router) recordingRuleGetsByGids(c *gin.Context) {
+	gids := str.IdsInt64(ginx.QueryStr(c, "gids"), ",")
+	if len(gids) == 0 {
+		ginx.NewRender(c, http.StatusBadRequest).Message("arg(gids) is empty")
+		return
+	}
+
+	for _, gid := range gids {
+		rt.bgroCheck(c, gid)
+	}
+
+	ars, err := models.RecordingRuleGetsByBGIds(rt.Ctx, gids)
+	ginx.NewRender(c).Data(ars, err)
+}
+
 func (rt *Router) recordingRuleGetsByService(c *gin.Context) {
 	ars, err := models.RecordingRuleEnabledGets(rt.Ctx)
 	ginx.NewRender(c).Data(ars, err)

center/router/router_role.go

@@ -4,6 +4,7 @@ import (
 	"net/http"
 	"strings"
 
+	"github.com/ccfos/nightingale/v6/center/cconf"
 	"github.com/ccfos/nightingale/v6/models"
 
 	"github.com/gin-gonic/gin"
@@ -17,6 +18,15 @@ func (rt *Router) rolesGets(c *gin.Context) {
 
 func (rt *Router) permsGets(c *gin.Context) {
 	user := c.MustGet("user").(*models.User)
+	if user.IsAdmin() {
+		var lst []string
+		for _, ops := range cconf.Operations.Ops {
+			lst = append(lst, ops.Ops...)
+		}
+		ginx.NewRender(c).Data(lst, nil)
+		return
+	}
+
 	lst, err := models.OperationsOfRole(rt.Ctx, strings.Fields(user.Roles))
 	ginx.NewRender(c).Data(lst, err)
 }

center/router/router_role_operation.go

@@ -3,9 +3,11 @@ package router
 import (
 	"net/http"
 
+	"github.com/ccfos/nightingale/v6/center/cconf"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/gin-gonic/gin"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/i18n"
 )
 
 func (rt *Router) operationOfRole(c *gin.Context) {
@@ -16,6 +18,15 @@ func (rt *Router) operationOfRole(c *gin.Context) {
 		ginx.Bomb(http.StatusOK, "role not found")
 	}
 
+	if role.Name == "Admin" {
+		var lst []string
+		for _, ops := range cconf.Operations.Ops {
+			lst = append(lst, ops.Ops...)
+		}
+		ginx.NewRender(c).Data(lst, nil)
+		return
+	}
+
 	ops, err := models.OperationsOfRole(rt.Ctx, []string{role.Name})
 	ginx.NewRender(c).Data(ops, err)
 }
@@ -39,5 +50,11 @@ func (rt *Router) roleBindOperation(c *gin.Context) {
 }
 
 func (rt *Router) operations(c *gin.Context) {
-	ginx.NewRender(c).Data(rt.Operations.Ops, nil)
+	var ops []cconf.Ops
+	for _, v := range rt.Operations.Ops {
+		v.Cname = i18n.Sprintf(c.GetHeader("X-Language"), v.Cname)
+		ops = append(ops, v)
+	}
+
+	ginx.NewRender(c).Data(ops, nil)
 }

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

@@ -15,6 +15,7 @@ import (
 	"github.com/prometheus/common/model"
 	"github.com/toolkits/pkg/ginx"
 	"github.com/toolkits/pkg/logger"
+	"github.com/toolkits/pkg/str"
 )
 
 type TargetQuery struct {
@@ -42,15 +43,32 @@ func (rt *Router) targetGetsByHostFilter(c *gin.Context) {
 }
 
 func (rt *Router) targetGets(c *gin.Context) {
-	bgid := ginx.QueryInt64(c, "bgid", -1)
+	bgids := str.IdsInt64(ginx.QueryStr(c, "gids", ""), ",")
 	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 err error
+	if len(bgids) == 0 {
+		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)
+		}
+	}
+
+	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 +79,12 @@ 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 +104,6 @@ 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.go

@@ -30,10 +30,46 @@ func (rt *Router) taskGets(c *gin.Context) {
 
 	beginTime := time.Now().Unix() - days*24*3600
 
-	total, err := models.TaskRecordTotal(rt.Ctx, bgid, beginTime, creator, query)
+	total, err := models.TaskRecordTotal(rt.Ctx, []int64{bgid}, beginTime, creator, query)
 	ginx.Dangerous(err)
 
-	list, err := models.TaskRecordGets(rt.Ctx, bgid, beginTime, creator, query, limit, ginx.Offset(c, limit))
+	list, err := models.TaskRecordGets(rt.Ctx, []int64{bgid}, beginTime, creator, query, limit, ginx.Offset(c, limit))
+	ginx.Dangerous(err)
+
+	ginx.NewRender(c).Data(gin.H{
+		"total": total,
+		"list":  list,
+	}, nil)
+}
+
+func (rt *Router) taskGetsByGids(c *gin.Context) {
+	gids := str.IdsInt64(ginx.QueryStr(c, "gids"), ",")
+	if len(gids) == 0 {
+		ginx.NewRender(c, http.StatusBadRequest).Message("arg(gids) is empty")
+		return
+	}
+
+	for _, gid := range gids {
+		rt.bgroCheck(c, gid)
+	}
+
+	mine := ginx.QueryBool(c, "mine", false)
+	days := ginx.QueryInt64(c, "days", 7)
+	limit := ginx.QueryInt(c, "limit", 20)
+	query := ginx.QueryStr(c, "query", "")
+	user := c.MustGet("user").(*models.User)
+
+	creator := ""
+	if mine {
+		creator = user.Username
+	}
+
+	beginTime := time.Now().Unix() - days*24*3600
+
+	total, err := models.TaskRecordTotal(rt.Ctx, gids, beginTime, creator, query)
+	ginx.Dangerous(err)
+
+	list, err := models.TaskRecordGets(rt.Ctx, gids, beginTime, creator, query, limit, ginx.Offset(c, limit))
 	ginx.Dangerous(err)
 
 	ginx.NewRender(c).Data(gin.H{
@@ -92,6 +128,7 @@ func (f *taskForm) Verify() error {
 	if f.Script == "" {
 		return fmt.Errorf("arg(script) is required")
 	}
+	f.Script = strings.Replace(f.Script, "\r\n", "\n", -1)
 
 	if str.Dangerous(f.Args) {
 		return fmt.Errorf("arg(args) is dangerous")

center/router/router_task_tpl.go

@@ -18,10 +18,36 @@ func (rt *Router) taskTplGets(c *gin.Context) {
 	limit := ginx.QueryInt(c, "limit", 20)
 	groupId := ginx.UrlParamInt64(c, "id")
 
-	total, err := models.TaskTplTotal(rt.Ctx, groupId, query)
+	total, err := models.TaskTplTotal(rt.Ctx, []int64{groupId}, query)
 	ginx.Dangerous(err)
 
-	list, err := models.TaskTplGets(rt.Ctx, groupId, query, limit, ginx.Offset(c, limit))
+	list, err := models.TaskTplGets(rt.Ctx, []int64{groupId}, query, limit, ginx.Offset(c, limit))
+	ginx.Dangerous(err)
+
+	ginx.NewRender(c).Data(gin.H{
+		"total": total,
+		"list":  list,
+	}, nil)
+}
+
+func (rt *Router) taskTplGetsByGids(c *gin.Context) {
+	query := ginx.QueryStr(c, "query", "")
+	limit := ginx.QueryInt(c, "limit", 20)
+
+	gids := str.IdsInt64(ginx.QueryStr(c, "gids"), ",")
+	if len(gids) == 0 {
+		ginx.NewRender(c, http.StatusBadRequest).Message("arg(gids) is empty")
+		return
+	}
+
+	for _, gid := range gids {
+		rt.bgroCheck(c, gid)
+	}
+
+	total, err := models.TaskTplTotal(rt.Ctx, gids, query)
+	ginx.Dangerous(err)
+
+	list, err := models.TaskTplGets(rt.Ctx, gids, query, limit, ginx.Offset(c, limit))
 	ginx.Dangerous(err)
 
 	ginx.NewRender(c).Data(gin.H{
@@ -48,6 +74,19 @@ 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/router/router_tdengine.go

@@ -0,0 +1,117 @@
+package router
+
+import (
+	"net/http"
+
+	"github.com/ccfos/nightingale/v6/center/cconf"
+	"github.com/ccfos/nightingale/v6/models"
+
+	"github.com/gin-gonic/gin"
+	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/logger"
+)
+
+type databasesQueryForm struct {
+	Cate         string `json:"cate" form:"cate"`
+	DatasourceId int64  `json:"datasource_id" form:"datasource_id"`
+}
+
+func (rt *Router) tdengineDatabases(c *gin.Context) {
+	var f databasesQueryForm
+	ginx.BindJSON(c, &f)
+
+	tdClient := rt.TdendgineClients.GetCli(f.DatasourceId)
+	if tdClient == nil {
+		ginx.NewRender(c, http.StatusNotFound).Message("No such datasource")
+		return
+	}
+
+	databases, err := tdClient.GetDatabases()
+	ginx.NewRender(c).Data(databases, err)
+}
+
+type tablesQueryForm struct {
+	Cate         string `json:"cate"`
+	DatasourceId int64  `json:"datasource_id" `
+	Database     string `json:"db"`
+	IsStable     bool   `json:"is_stable"`
+}
+
+// get tdengine tables
+func (rt *Router) tdengineTables(c *gin.Context) {
+	var f tablesQueryForm
+	ginx.BindJSON(c, &f)
+
+	tdClient := rt.TdendgineClients.GetCli(f.DatasourceId)
+	if tdClient == nil {
+		ginx.NewRender(c, http.StatusNotFound).Message("No such datasource")
+		return
+	}
+
+	tables, err := tdClient.GetTables(f.Database, f.IsStable)
+	ginx.NewRender(c).Data(tables, err)
+}
+
+type columnsQueryForm struct {
+	Cate         string `json:"cate"`
+	DatasourceId int64  `json:"datasource_id" `
+	Database     string `json:"db"`
+	Table        string `json:"table"`
+}
+
+// get tdengine columns
+func (rt *Router) tdengineColumns(c *gin.Context) {
+	var f columnsQueryForm
+	ginx.BindJSON(c, &f)
+
+	tdClient := rt.TdendgineClients.GetCli(f.DatasourceId)
+	if tdClient == nil {
+		ginx.NewRender(c, http.StatusNotFound).Message("No such datasource")
+		return
+	}
+
+	columns, err := tdClient.GetColumns(f.Database, f.Table)
+	ginx.NewRender(c).Data(columns, err)
+}
+
+func (rt *Router) QueryData(c *gin.Context) {
+	var f models.QueryParam
+	ginx.BindJSON(c, &f)
+
+	var resp []*models.DataResp
+	var err error
+	tdClient := rt.TdendgineClients.GetCli(f.DatasourceId)
+	for _, q := range f.Querys {
+		datas, err := tdClient.Query(q)
+		ginx.Dangerous(err)
+		resp = append(resp, datas...)
+	}
+
+	ginx.NewRender(c).Data(resp, err)
+}
+
+func (rt *Router) QueryLog(c *gin.Context) {
+	var f models.QueryParam
+	ginx.BindJSON(c, &f)
+
+	tdClient := rt.TdendgineClients.GetCli(f.DatasourceId)
+	if len(f.Querys) == 0 {
+		ginx.Bomb(200, "querys is empty")
+		return
+	}
+
+	data, err := tdClient.QueryLog(f.Querys[0])
+	logger.Debugf("tdengine query:%s result: %+v", f.Querys[0], data)
+	ginx.NewRender(c).Data(data, err)
+}
+
+// query sql template
+func (rt *Router) QuerySqlTemplate(c *gin.Context) {
+	cate := ginx.QueryStr(c, "cate")
+	m := make(map[string]string)
+	switch cate {
+	case models.TDENGINE:
+		m = cconf.TDengineSQLTpl
+	}
+	ginx.NewRender(c).Data(m, nil)
+}

center/router/router_user.go

@@ -11,6 +11,28 @@ import (
 	"github.com/toolkits/pkg/ginx"
 )
 
+func (rt *Router) userBusiGroupsGets(c *gin.Context) {
+	userid := ginx.QueryInt64(c, "userid", 0)
+	username := ginx.QueryStr(c, "username", "")
+
+	if userid == 0 && username == "" {
+		ginx.Bomb(http.StatusBadRequest, "userid or username required")
+	}
+
+	var user *models.User
+	var err error
+	if userid > 0 {
+		user, err = models.UserGetById(rt.Ctx, userid)
+	} else {
+		user, err = models.UserGetByUsername(rt.Ctx, username)
+	}
+
+	ginx.Dangerous(err)
+
+	groups, err := user.BusiGroups(rt.Ctx, 10000, "")
+	ginx.NewRender(c).Data(groups, err)
+}
+
 func (rt *Router) userFindAll(c *gin.Context) {
 	list, err := models.UserGetAll(rt.Ctx)
 	ginx.NewRender(c).Data(list, err)

center/router/router_user_variable_config.go

@@ -0,0 +1,70 @@
+package router
+
+import (
+	"strings"
+	"time"
+
+	"github.com/ccfos/nightingale/v6/models"
+
+	"github.com/gin-gonic/gin"
+	"github.com/toolkits/pkg/ginx"
+)
+
+func (rt *Router) userVariableConfigGets(context *gin.Context) {
+	userVariables, err := models.ConfigsGetUserVariable(rt.Ctx)
+	ginx.NewRender(context).Data(userVariables, err)
+}
+func (rt *Router) userVariableConfigAdd(context *gin.Context) {
+	var f models.Configs
+	ginx.BindJSON(context, &f)
+	f.Ckey = strings.TrimSpace(f.Ckey)
+	//insert external config. needs to make sure not plaintext for an encrypted type config
+	username := context.MustGet("username").(string)
+	now := time.Now().Unix()
+	f.CreateBy = username
+	f.UpdateBy = username
+	f.CreateAt = now
+	f.UpdateAt = now
+	ginx.NewRender(context).Message(models.ConfigsUserVariableInsert(rt.Ctx, f))
+
+}
+
+func (rt *Router) userVariableConfigPut(context *gin.Context) {
+	var f models.Configs
+	ginx.BindJSON(context, &f)
+	f.Id = ginx.UrlParamInt64(context, "id")
+	f.Ckey = strings.TrimSpace(f.Ckey)
+	f.UpdateBy = context.MustGet("username").(string)
+	f.UpdateAt = time.Now().Unix()
+
+	user := context.MustGet("user").(*models.User)
+	if !user.IsAdmin() && f.CreateBy != user.Username {
+		// only admin or creator can update
+		ginx.Bomb(403, "no permission")
+	}
+
+	ginx.NewRender(context).Message(models.ConfigsUserVariableUpdate(rt.Ctx, f))
+}
+
+func (rt *Router) userVariableConfigDel(context *gin.Context) {
+	id := ginx.UrlParamInt64(context, "id")
+	configs, err := models.ConfigGet(rt.Ctx, id)
+	ginx.Dangerous(err)
+
+	user := context.MustGet("user").(*models.User)
+	if !user.IsAdmin() && configs.CreateBy != user.Username {
+		// only admin or creator can delete
+		ginx.Bomb(403, "no permission")
+	}
+
+	if configs != nil && configs.External == models.ConfigExternal {
+		ginx.NewRender(context).Message(models.ConfigsDel(rt.Ctx, []int64{id}))
+	} else {
+		ginx.NewRender(context).Message(nil)
+	}
+}
+
+func (rt *Router) userVariableGetDecryptByService(context *gin.Context) {
+	decryptMap, decryptErr := models.ConfigUserVariableGetDecryptMap(rt.Ctx, rt.HTTP.RSA.RSAPrivateKey, rt.HTTP.RSA.RSAPassWord)
+	ginx.NewRender(context).Data(decryptMap, decryptErr)
+}

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
@@ -67,6 +69,7 @@ Email = 'email'
 const CAS = `
 Enable = false
 SsoAddr = 'https://cas.example.com/cas/'
+# LoginPath = ''
 RedirectURL = 'http://127.0.0.1:18000/callback/cas'
 DisplayName = 'CAS登录'
 CoverAttributes = 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/center/main.go

@@ -12,6 +12,7 @@ import (
 	"github.com/ccfos/nightingale/v6/pkg/osx"
 	"github.com/ccfos/nightingale/v6/pkg/version"
 
+	"github.com/toolkits/pkg/net/tcpx"
 	"github.com/toolkits/pkg/runner"
 )
 
@@ -31,6 +32,8 @@ func main() {
 
 	printEnv()
 
+	tcpx.WaitHosts()
+
 	cleanFunc, err := center.Initialize(*configDir, *cryptoKey)
 	if err != nil {
 		log.Fatalln("failed to initialize:", err)

cmd/edge/edge.go

@@ -0,0 +1,81 @@
+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"
+	"github.com/ccfos/nightingale/v6/tdengine"
+
+	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 {
+		configCache := memsto.NewConfigCache(ctx, syncStats, nil, "")
+		alertStats := astats.NewSyncStats()
+		dsCache := memsto.NewDatasourceCache(ctx, syncStats)
+		alertMuteCache := memsto.NewAlertMuteCache(ctx, syncStats)
+		alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
+		notifyConfigCache := memsto.NewNotifyConfigCache(ctx, configCache)
+		userCache := memsto.NewUserCache(ctx, syncStats)
+		userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
+
+		promClients := prom.NewPromClient(ctx)
+		tdengineClients := tdengine.NewTdengineClient(ctx, config.Alert.Heartbeat)
+		externalProcessors := process.NewExternalProcessors()
+
+		alert.Start(config.Alert, config.Pushgw, syncStats, alertStats, externalProcessors, targetCache, busiGroupCache, alertMuteCache,
+			alertRuleCache, notifyConfigCache, dsCache, ctx, promClients, tdengineClients, 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/.dockerignore

@@ -1,7 +1,5 @@
-ibexetc
+compose-host-network
+compose-postgres
+compose-bridge
 initsql
-mysqletc
-n9eetc
-prometc
 build.sh
-docker-compose.yaml

docker/Dockerfile.goreleaser

@@ -5,8 +5,7 @@ WORKDIR /app
 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 pip install requests
 
 EXPOSE 17000
 

docker/Dockerfile.goreleaser.arm64

@@ -1,4 +1,3 @@
-FROM flashcatcloud/toolbox:v0.0.1 as toolbox
 FROM --platform=$TARGETPLATFORM python:3-slim
 
 
@@ -6,7 +5,6 @@ WORKDIR /app
 ADD n9e /app/
 ADD etc /app/
 ADD integrations /app/integrations/
-COPY --chmod=755  --from=toolbox /toolbox/wait_aarch64 /wait
 
 EXPOSE 17000
 

docker/compose-bridge/docker-compose.yaml

@@ -0,0 +1,132 @@
+version: "3.7"
+
+networks:
+  nightingale:
+    driver: bridge
+
+services:
+  mysql:
+    image: "mysql:8"
+    container_name: mysql
+    hostname: mysql
+    restart: always
+    environment:
+      TZ: Asia/Shanghai
+      MYSQL_ROOT_PASSWORD: 1234
+    volumes:
+      - ./mysqldata:/var/lib/mysql/
+      - ../initsql:/docker-entrypoint-initdb.d/
+      - ./etc-mysql/my.cnf:/etc/my.cnf
+    networks:
+      - nightingale
+    ports:
+      - "3306:3306"
+
+  redis:
+    image: "redis:6.2"
+    container_name: redis
+    hostname: redis
+    restart: always
+    environment:
+      TZ: Asia/Shanghai
+    networks:
+      - nightingale
+    ports:
+      - "6379:6379"
+
+  # prometheus:
+  #   image: prom/prometheus
+  #   container_name: prometheus
+  #   hostname: prometheus
+  #   restart: always
+  #   environment:
+  #     TZ: Asia/Shanghai
+  #   volumes:
+  #     - ./etc-prometheus:/etc/prometheus
+  #   command:
+  #     - "--config.file=/etc/prometheus/prometheus.yml"
+  #     - "--storage.tsdb.path=/prometheus"
+  #     - "--web.console.libraries=/usr/share/prometheus/console_libraries"
+  #     - "--web.console.templates=/usr/share/prometheus/consoles"
+  #     - "--enable-feature=remote-write-receiver"
+  #     - "--query.lookback-delta=2m"
+  #   networks:
+  #     - nightingale
+  #   ports:
+  #     - "9090:9090"
+
+  victoriametrics:
+    image: victoriametrics/victoria-metrics:v1.79.12
+    container_name: victoriametrics
+    hostname: victoriametrics
+    restart: always
+    environment:
+      TZ: Asia/Shanghai
+    ports:
+      - "8428:8428"
+    networks:
+      - nightingale
+    command:
+      - "--loggerTimezone=Asia/Shanghai"
+
+  ibex:
+    image: flashcatcloud/ibex:v1.2.0
+    container_name: ibex
+    hostname: ibex
+    restart: always
+    environment:
+      GIN_MODE: release
+      TZ: Asia/Shanghai
+      WAIT_HOSTS: mysql:3306
+    volumes:
+      - ./etc-ibex:/app/etc
+    networks:
+      - nightingale
+    ports:
+      - "10090:10090"
+      - "20090:20090"
+    depends_on:
+      - mysql
+    command: >
+      sh -c "/app/ibex server"
+
+  nightingale:
+    image: flashcatcloud/nightingale:latest
+    container_name: nightingale
+    hostname: nightingale
+    restart: always
+    environment:
+      GIN_MODE: release
+      TZ: Asia/Shanghai
+      WAIT_HOSTS: mysql:3306, redis:6379
+    volumes:
+      - ./etc-nightingale:/app/etc
+    networks:
+      - nightingale
+    ports:
+      - "17000:17000"
+    depends_on:
+      - mysql
+      - redis
+      - victoriametrics
+    command: >
+      sh -c "/app/n9e"
+
+  categraf:
+    image: "flashcatcloud/categraf:latest"
+    container_name: "categraf"
+    hostname: "categraf01"
+    restart: always
+    environment:
+      TZ: Asia/Shanghai
+      HOST_PROC: /hostfs/proc
+      HOST_SYS: /hostfs/sys
+      HOST_MOUNT_PREFIX: /hostfs
+      WAIT_HOSTS: nightingale:17000, ibex:20090
+    volumes:
+      - ./etc-categraf:/etc/categraf/conf
+      - /:/hostfs
+    networks:
+      - nightingale
+    depends_on:
+      - nightingale

docker/compose-bridge/etc-categraf/config.toml

@@ -0,0 +1,83 @@
+[global]
+# whether print configs
+print_configs = false
+
+# add label(agent_hostname) to series
+# "" -> auto detect hostname
+# "xx" -> use specified string xx
+# "$hostname" -> auto detect hostname
+# "$ip" -> auto detect ip
+# "$hostname-$ip" -> auto detect hostname and ip to replace the vars
+hostname = "$HOSTNAME"
+
+# will not add label(agent_hostname) if true
+omit_hostname = false
+
+# s | ms
+precision = "ms"
+
+# global collect interval
+interval = 15
+
+[global.labels]
+source="categraf"
+# region = "shanghai"
+# env = "localhost"
+
+[writer_opt]
+# default: 2000
+batch = 2000
+# channel(as queue) size
+chan_size = 10000
+
+[[writers]]
+url = "http://nightingale:17000/prometheus/v1/write"
+
+# Basic auth username
+basic_auth_user = ""
+
+# Basic auth password
+basic_auth_pass = ""
+
+# timeout settings, unit: ms
+timeout = 5000
+dial_timeout = 2500
+max_idle_conns_per_host = 100
+
+[http]
+enable = false
+address = ":9100"
+print_access = false
+run_mode = "release"
+
+[heartbeat]
+enable = true
+
+# report os version cpu.util mem.util metadata
+url = "http://nightingale:17000/v1/n9e/heartbeat"
+
+# interval, unit: s
+interval = 10
+
+# Basic auth username
+basic_auth_user = ""
+
+# Basic auth password
+basic_auth_pass = ""
+
+## Optional headers
+# headers = ["X-From", "categraf", "X-Xyz", "abc"]
+
+# timeout settings, unit: ms
+timeout = 5000
+dial_timeout = 2500
+max_idle_conns_per_host = 100
+
+[ibex]
+enable = true
+## ibex flush interval
+interval = "1000ms"
+## n9e ibex server rpc address
+servers = ["ibex:20090"]
+## temp script dir
+meta_dir = "./meta"

docker/compose-bridge/etc-categraf/input.disk/disk.toml

@@ -0,0 +1,10 @@
+# # collect interval
+# interval = 15
+
+# # By default stats will be gathered for all mount points.
+# # Set mount_points will restrict the stats to only the specified mount points.
+mount_points = ["/"]
+
+# Ignore mount points by filesystem type.
+ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs", "nsfs"]
+

docker/compose-bridge/etc-categraf/input.prometheus/prometheus.toml

@@ -0,0 +1,4 @@
+[[instances]]
+urls = [
+    "http://nightingale:17000/metrics"
+]

docker/compose-bridge/etc-ibex/server.conf

@@ -0,0 +1,97 @@
+# debug, release
+RunMode = "release"
+
+[Log]
+# log write dir
+Dir = "logs-server"
+# 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]
+Enable = true
+# http listening address
+Host = "0.0.0.0"
+# http listening port
+Port = 10090
+# https cert file path
+CertFile = ""
+# https key file path
+KeyFile = ""
+# whether print access log
+PrintAccessLog = true
+# whether enable pprof
+PProf = false
+# 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
+
+[BasicAuth]
+# using when call apis
+ibex = "ibex"
+
+[RPC]
+Listen = "0.0.0.0:20090"
+
+[Heartbeat]
+# auto detect if blank
+IP = ""
+# unit: ms
+Interval = 1000
+
+[Output]
+# database | remote
+ComeFrom = "database"
+AgtdPort = 2090
+
+[Gorm]
+# enable debug mode or not
+Debug = false
+# mysql postgres
+DBType = "mysql"
+# unit: s
+MaxLifetime = 7200
+# max open connections
+MaxOpenConns = 150
+# max idle connections
+MaxIdleConns = 50
+# table prefix
+TablePrefix = ""
+
+[MySQL]
+# mysql address host:port
+Address = "mysql:3306"
+# mysql username
+User = "root"
+# mysql password
+Password = "1234"
+# database name
+DBName = "ibex"
+# connection params
+Parameters = "charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
+
+[Postgres]
+# pg address host:port
+Address = "postgres:5432"
+# pg user
+User = "root"
+# pg password
+Password = "1234"
+# database name
+DBName = "ibex"
+# ssl mode
+SSLMode = "disable"