Merge branch 'main' of github.com:ccfos/nightingale

* Maintain consistency between encryption and decryption methods

* Maintain consistency between encryption and decryption methods

* Maintain consistency between encryption and decryption methods

* optimize code

* 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
@@ -40,8 +44,11 @@ _test
 /n9e
 /docker/pub
 /docker/n9e
-/docker/mysqldata
-/etc.local
+/docker/compose-bridge/mysqldata
+/docker/compose-host-network/mysqldata
+/docker/compose-postgres/pgdata
+/etc.local*
+/front/statik/statik.go
 
 .alerts
 .idea

.goreleaser.yaml

@@ -2,6 +2,7 @@ before:
   hooks:
     # You may remove this if you don't use go modules.
     - go mod tidy
+    - go install github.com/rakyll/statik
 
 snapshot:
   name_template: '{{ .Tag }}'
@@ -14,7 +15,8 @@ builds:
   - id: build
     hooks:
       pre:
-       - ./fe.sh
+      - cmd: sh -x ./fe.sh
+        output: true
     main: ./cmd/center/
     binary: n9e
     env:
@@ -40,22 +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:
@@ -72,8 +61,7 @@ archives:
     builds:
       - build
       - build-cli
-      - build-alert
-      - build-pushgw
+      - build-edge
     format: tar.gz
     format_overrides:
       - goos: windows
@@ -83,7 +71,6 @@ archives:
     files:
       - docker/*
       - etc/*
-      - pub/*
       - integrations/*
       - cli/*
       - n9e.sql
@@ -103,7 +90,6 @@ dockers:
       - build
     dockerfile: docker/Dockerfile.goreleaser
     extra_files:
-      - pub
       - etc
       - integrations
     use: buildx
@@ -117,7 +103,6 @@ dockers:
       - build
     dockerfile: docker/Dockerfile.goreleaser.arm64
     extra_files:
-      - pub
       - etc
       - integrations
     use: buildx

Makefile

@@ -1,4 +1,4 @@
-.PHONY: start build
+.PHONY: prebuild build
 
 ROOT:=$(shell pwd -P)
 GIT_COMMIT:=$(shell git --work-tree ${ROOT}  rev-parse 'HEAD^{commit}')
@@ -6,27 +6,35 @@ _GIT_VERSION:=$(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: build
+all: prebuild build
+
+prebuild:
+	echo "begin download and embed the front-end file..."
+	sh fe.sh
+	echo "front-end file download and embedding completed."
 
 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
 
 build-pushgw:
 	go build -ldflags "-w -s -X github.com/ccfos/nightingale/v6/pkg/version.Version=$(RELEASE_VERSION)" -o n9e-pushgw ./cmd/pushgw/main.go
 
-build-cli:
+build-cli: 
 	go build -ldflags "-w -s -X github.com/ccfos/nightingale/v6/pkg/version.Version=$(RELEASE_VERSION)" -o n9e-cli ./cmd/cli/main.go
 
 run:
 	nohup ./n9e > n9e.log 2>&1 &
 
-run_alert:
+run-alert:
 	nohup ./n9e-alert > n9e-alert.log 2>&1 &
 
-run_pushgw:
+run-pushgw:
 	nohup ./n9e-pushgw > n9e-pushgw.log 2>&1 &
 
 release:

README.md

@@ -20,117 +20,77 @@
 <img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"/>
 </p>
 <p align="center">
-  <b>All-in-one</b> 的开源观测平台 <br/>
-  <b>开箱即用</b>，集数据采集、可视化、监控告警于一体 <br/>
-  推荐升级您的 <b>Prometheus + AlertManager + Grafana + ELK + Jaeger</b> 组合方案到夜莺！
+  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)
 
 
+## 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**.
 
-- **开箱即用**
-  - 支持 Docker、Helm Chart、云服务等多种部署方式，集数据采集、监控告警、可视化为一体，内置多种监控仪表盘、快捷视图、告警规则模板，导入即可快速使用，**大幅降低云原生监控系统的建设成本、学习成本、使用成本**；
-- **专业告警**
-  - 可视化的告警配置和管理，支持丰富的告警规则，提供屏蔽规则、订阅规则的配置能力，支持告警多种送达渠道，支持告警自愈、告警事件管理等；
-  - **推荐您使用夜莺的同时，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、协同，让告警的触达既高效，又确保告警处理不遗漏、做到件件有回响**。
-- **云原生**
-  - 以交钥匙的方式快速构建企业级的云原生监控体系，支持 [Categraf](https://github.com/flashcatcloud/categraf)、Telegraf、Grafana-agent 等多种采集器，支持 Prometheus、VictoriaMetrics、M3DB、ElasticSearch、Jaeger 等多种数据源，兼容支持导入 Grafana 仪表盘，**与云原生生态无缝集成**；
-- **高性能 高可用**
-  - 得益于夜莺的多数据源管理引擎，和夜莺引擎侧优秀的架构设计，借助于高性能时序库，可以满足数亿时间线的采集、存储、告警分析场景，节省大量成本；
-  - 夜莺监控组件均可水平扩展，无单点，已在上千家企业部署落地，经受了严苛的生产实践检验。众多互联网头部公司，夜莺集群机器达百台，处理数亿级时间线，重度使用夜莺监控；
-- **灵活扩展 中心化管理**
-  - 夜莺监控，可部署在 1 核 1G 的云主机，可在上百台机器集群化部署，可运行在 K8s 中；也可将时序库、告警引擎等组件下沉到各机房、各 Region，兼顾边缘部署和中心化统一管理，**解决数据割裂，缺乏统一视图的难题**；
-- **开放社区**
-  - 托管于[中国计算机学会开源发展委员会](https://www.ccf.org.cn/kyfzwyh/)，有[快猫星云](https://flashcat.cloud)和众多公司的持续投入，和数千名社区用户的积极参与，以及夜莺监控项目清晰明确的定位，都保证了夜莺开源社区健康、长久的发展。活跃、专业的社区用户也在持续迭代和沉淀更多的最佳实践于产品中；
 
-## 使用场景
-1. **如果您希望在一个平台中，统一管理和查看 Metrics、Logging、Tracing 数据，推荐你使用夜莺**：
-   - 请参考阅读：[不止于监控，夜莺 V6 全新升级为开源观测平台](http://flashcat.cloud/blog/nightingale-v6-release/)
-2. **如果您在使用 Prometheus 过程中，有以下的一个或者多个需求场景，推荐您无缝升级到夜莺**：
-   - Prometheus、Alertmanager、Grafana 等多个系统较为割裂，缺乏统一视图，无法开箱即用;
-   - 通过修改配置文件来管理 Prometheus、Alertmanager 的方式，学习曲线大，协同有难度;
-   - 数据量过大而无法扩展您的 Prometheus 集群；
-   - 生产环境运行多套 Prometheus 集群，面临管理和使用成本高的问题；
-3. **如果您在使用 Zabbix，有以下的场景，推荐您升级到夜莺**：
-   - 监控的数据量太大，希望有更好的扩展解决方案；
-   - 学习曲线高，多人多团队模式下，希望有更好的协同使用效率；
-   - 微服务和云原生架构下，监控数据的生命周期多变、监控数据维度基数高，Zabbix 数据模型不易适配；
-   - 了解更多Zabbix和夜莺监控的对比，推荐您进一步阅读[Zabbix 和夜莺监控选型对比](https://flashcat.cloud/blog/zabbx-vs-nightingale/)
-4. **如果您在使用 [Open-Falcon](https://github.com/open-falcon/falcon-plus)，我们推荐您升级到夜莺：**
-   - 关于 Open-Falcon 和夜莺的详细介绍，请参考阅读：[云原生监控的十个特点和趋势](http://flashcat.cloud/blog/10-trends-of-cloudnative-monitoring/)
-   - 监控系统和可观测平台的区别，请参考阅读：[从监控系统到可观测平台，Gap有多大
-](https://flashcat.cloud/blog/gap-of-monitoring-to-o11y/)
-5. **我们推荐您使用 [Categraf](https://github.com/flashcatcloud/categraf) 作为首选的监控数据采集器**：
-   - [Categraf](https://github.com/flashcatcloud/categraf) 是夜莺监控的默认采集器，采用开放插件机制和 All-in-one 的设计理念，同时支持 metric、log、trace、event 的采集。Categraf 不仅可以采集 CPU、内存、网络等系统层面的指标，也集成了众多开源组件的采集能力，支持K8s生态。Categraf 内置了对应的仪表盘和告警规则，开箱即用。
+#### If you are using Prometheus and have one or more of the following requirement scenarios, it is recommended that you upgrade to Nightingale:
 
-## 文档
+- 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;
 
-[English Doc](https://n9e.github.io/) |  [中文文档](https://flashcat.cloud/docs/)
+#### If you are using Zabbix and have the following scenarios, it is recommended that you upgrade to Nightingale:
 
-## 产品示意图
+- 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
 
-## 夜莺架构
+## Architecture
 
-夜莺监控可以接收各种采集器上报的监控数据（比如 [Categraf](https://github.com/flashcatcloud/categraf)、telegraf、grafana-agent、Prometheus），并写入多种流行的时序数据库中（可以支持Prometheus、M3DB、VictoriaMetrics、Thanos、TDEngine等），提供告警规则、屏蔽规则、订阅规则的配置能力，提供监控数据的查看能力，提供告警自愈机制（告警触发之后自动回调某个webhook地址或者执行某个脚本），提供历史告警事件的存储管理、分组查看的能力。
+<img src="doc/img/arch-product.png" width="600">
 
-### 中心汇聚式部署方案
+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.
 
-![中心汇聚式部署方案](https://download.flashcat.cloud/ulric/20230327133406.png)
+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/).
 
-夜莺只有一个模块，就是 n9e，可以部署多个 n9e 实例组成集群，n9e 依赖 2 个存储，数据库、Redis，数据库可以使用 MySQL 或 Postgres，自己按需选用。
+**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)
 
-n9e 提供的是 HTTP 接口，前面负载均衡可以是 4 层的，也可以是 7 层的。一般就选用 Nginx 就可以了。
 
-n9e 这个模块接收到数据之后，需要转发给后端的时序库，相关配置是：
-
-```toml
-[Pushgw]
-LabelRewrite = true
-[[Pushgw.Writers]] 
-Url = "http://127.0.0.1:9090/api/v1/write"
-```
-
-> 注意：虽然数据源可以在页面配置了，但是上报转发链路，还是需要在配置文件指定。
-
-所有机房的 agent（ 比如 Categraf、Telegraf、 Grafana-agent、Datadog-agent ），都直接推数据给 n9e，这个架构最为简单，维护成本最低。当然，前提是要求机房之间网络链路比较好，一般有专线。如果网络链路不好，则要使用下面的部署方式了。
-
-### 边缘下沉式混杂部署方案
-
-![边缘下沉式混杂部署方案](https://download.flashcat.cloud/ulric/20230327135615.png)
-
-这个图尝试解释 3 种不同的情形，比如 A 机房和中心网络链路很好，Categraf 可以直接汇报数据给中心 n9e 模块，另一个机房网络链路不好，就需要把时序库下沉部署，时序库下沉了，对应的告警引擎和转发网关也都要跟随下沉，这样数据不会跨机房传输，比较稳定。但是心跳还是需要往中心心跳，要不然在对象列表里看不到机器的 CPU、内存使用率。还有的时候，可能是接入的一个已有的 Prometheus，数据采集没有走 Categraf，那此时只需要把 Prometheus 作为数据源接入夜莺即可，可以在夜莺里看图、配告警规则，但是就是在对象列表里看不到，也不能使用告警自愈的功能，问题也不大，核心功能都不受影响。
-
-边缘机房，下沉部署时序库、告警引擎、转发网关的时候，要注意，告警引擎需要依赖数据库，因为要同步告警规则，转发网关也要依赖数据库，因为要注册对象到数据库里去，需要打通相关网络，告警引擎和转发网关都不用Redis，所以无需为 Redis 打通网络。 
-
-### VictoriaMetrics 集群架构
-<img src="doc/img/install-vm.png" width="600">
-
-如果单机版本的时序数据库（比如 Prometheus） 性能有瓶颈或容灾较差，我们推荐使用 [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics)，VictoriaMetrics 架构较为简单，性能优异，易于部署和运维，架构图如上。VictoriaMetrics 更详尽的文档，还请参考其[官网](https://victoriametrics.com/)。
-
-## 夜莺社区
-
-开源项目要更有生命力，离不开开放的治理架构和源源不断的开发者和用户共同参与，我们致力于建立开放、中立的开源治理架构，吸纳更多来自企业、高校等各方面对云原生监控感兴趣、有热情的开发者，一起打造有活力的夜莺开源社区。关于《夜莺开源项目和社区治理架构（草案）》，请查阅 [COMMUNITY GOVERNANCE](./doc/community-governance.md).
-
-**我们欢迎您以各种方式参与到夜莺开源项目和开源社区中来，工作包括不限于**：
-- 补充和完善文档 => [n9e.github.io](https://n9e.github.io/)
-- 分享您在使用夜莺监控过程中的最佳实践和经验心得 => [文章分享](https://flashcat.cloud/docs/content/flashcat-monitor/nightingale/share/)
-- 提交产品建议 =》 [github issue](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Ffeature&template=enhancement.md)
-- 提交代码，让夜莺监控更快、更稳、更好用 => [github pull request](https://github.com/didi/nightingale/pulls)
-
-**尊重、认可和记录每一位贡献者的工作**是夜莺开源社区的第一指导原则，我们提倡**高效的提问**，这既是对开发者时间的尊重，也是对整个社区知识沉淀的贡献：
-- 提问之前请先查阅 [FAQ](https://www.gitlink.org.cn/ccfos/nightingale/wiki/faq) 
-- 我们使用[论坛](https://answer.flashcat.cloud/)进行交流，有问题可以到这里搜索、提问
-- 我们也推荐你加入微信群，和其他夜莺用户交流经验 (请先加好友：[picobyte](https://www.gitlink.org.cn/UlricQin/gist/tree/master/self.jpeg) 备注：夜莺加群+姓名+公司)
+**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
-
-您可以通过在 **[Who is Using Nightingale](https://github.com/ccfos/nightingale/issues/897)** 登记您的使用情况，分享您的使用经验。
+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)
@@ -141,8 +101,4 @@ Url = "http://127.0.0.1:9090/api/v1/write"
 </a>
 
 ## License
-[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)
-
-## 加入交流群
-
-<img src="doc/img/wecom.png" width="120">
+[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)

README_en.md

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

README_zh.md

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

alert/aconf/conf.go

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

alert/alert.go

@@ -15,6 +15,7 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/router"
 	"github.com/ccfos/nightingale/v6/alert/sender"
 	"github.com/ccfos/nightingale/v6/conf"
+	"github.com/ccfos/nightingale/v6/dumper"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
@@ -23,7 +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/storage"
+	"github.com/ccfos/nightingale/v6/tdengine"
 )
 
 func Initialize(configDir string, cryptoKey string) (func(), error) {
@@ -37,36 +38,31 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 		return nil, err
 	}
 
-	db, err := storage.New(config.DB)
-	if err != nil {
-		return nil, err
-	}
-	ctx := ctx.NewContext(context.Background(), db)
-
-	redis, err := storage.NewRedis(config.Redis)
-	if err != nil {
-		return nil, err
-	}
+	ctx := ctx.NewContext(context.Background(), nil, false, config.CenterApi)
 
 	syncStats := memsto.NewSyncStats()
 	alertStats := astats.NewSyncStats()
 
-	targetCache := memsto.NewTargetCache(ctx, syncStats, redis)
+	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)
 	dsCache := memsto.NewDatasourceCache(ctx, syncStats)
+	userCache := memsto.NewUserCache(ctx, syncStats)
+	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
 
 	promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
+	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, false)
+	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)
 
@@ -77,27 +73,26 @@ 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, isCenter bool) {
-	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)
 
 	go models.InitNotifyConfig(ctx, alertc.Alerting.TemplatesDir)
 
-	naming := naming.NewNaming(ctx, alertc.Heartbeat, isCenter)
+	naming := naming.NewNaming(ctx, alertc.Heartbeat)
 
 	writers := writer.NewWriters(pushgwc)
 	record.NewScheduler(alertc, recordingRuleCache, promClients, writers, alertStats)
 
-	eval.NewScheduler(isCenter, 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

@@ -8,6 +8,7 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/queue"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/poster"
 
 	"github.com/toolkits/pkg/concurrent/semaphore"
 	"github.com/toolkits/pkg/logger"
@@ -60,6 +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)
 	}
@@ -82,78 +90,22 @@ func (e *Consumer) consumeOne(event *models.AlertCurEvent) {
 }
 
 func (e *Consumer) persist(event *models.AlertCurEvent) {
-	has, err := models.AlertCurEventExists(e.ctx, "hash=?", event.Hash)
-	if err != nil {
-		logger.Errorf("event_persist_check_exists_fail: %v rule_id=%d hash=%s", err, event.RuleId, event.Hash)
+	if event.Status != 0 {
 		return
 	}
 
-	his := event.ToHis(e.ctx)
-
-	// 不管是告警还是恢复，全量告警里都要记录
-	if err := his.Add(e.ctx); err != nil {
-		logger.Errorf(
-			"event_persist_his_fail: %v rule_id=%d cluster:%s hash=%s tags=%v timestamp=%d value=%s",
-			err,
-			event.RuleId,
-			event.Cluster,
-			event.Hash,
-			event.TagsJSON,
-			event.TriggerTime,
-			event.TriggerValue,
-		)
-	}
-
-	if has {
-		// 活跃告警表中有记录，删之
-		err = models.AlertCurEventDelByHash(e.ctx, event.Hash)
+	if !e.ctx.IsCenter {
+		event.DB2FE()
+		var err error
+		event.Id, err = poster.PostByUrlsWithResp[int64](e.ctx, "/v1/n9e/event-persist", event)
 		if err != nil {
-			logger.Errorf("event_del_cur_fail: %v hash=%s", err, event.Hash)
-			return
+			logger.Errorf("event:%+v persist err:%v", event, err)
 		}
-
-		if !event.IsRecovered {
-			// 恢复事件，从活跃告警列表彻底删掉，告警事件，要重新加进来新的event
-			// use his id as cur id
-			event.Id = his.Id
-			if event.Id > 0 {
-				if err := event.Add(e.ctx); err != nil {
-					logger.Errorf(
-						"event_persist_cur_fail: %v rule_id=%d cluster:%s hash=%s tags=%v timestamp=%d value=%s",
-						err,
-						event.RuleId,
-						event.Cluster,
-						event.Hash,
-						event.TagsJSON,
-						event.TriggerTime,
-						event.TriggerValue,
-					)
-				}
-			}
-		}
-
 		return
 	}
 
-	if event.IsRecovered {
-		// alert_cur_event表里没有数据，表示之前没告警，结果现在报了恢复，神奇....理论上不应该出现的
-		return
-	}
-
-	// use his id as cur id
-	event.Id = his.Id
-	if event.Id > 0 {
-		if err := event.Add(e.ctx); err != nil {
-			logger.Errorf(
-				"event_persist_cur_fail: %v rule_id=%d cluster:%s hash=%s tags=%v timestamp=%d value=%s",
-				err,
-				event.RuleId,
-				event.Cluster,
-				event.Hash,
-				event.TagsJSON,
-				event.TriggerTime,
-				event.TriggerValue,
-			)
-		}
+	err := models.EventPersist(e.ctx, event)
+	if err != nil {
+		logger.Errorf("event%+v persist err:%v", event, err)
 	}
 }

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"
@@ -28,10 +29,13 @@ type Dispatch struct {
 
 	alerting aconf.Alerting
 
-	senders map[string]sender.Sender
-	tpls    map[string]*template.Template
+	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
 }
@@ -39,7 +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,
@@ -50,10 +54,13 @@ func NewDispatch(alertRuleCache *memsto.AlertRuleCacheType, userCache *memsto.Us
 
 		alerting: alerting,
 
-		senders: make(map[string]sender.Sender),
-		tpls:    make(map[string]*template.Template),
+		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
 }
@@ -61,7 +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
@@ -81,17 +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 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
 }
@@ -132,7 +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 {
@@ -159,45 +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.Warningf("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.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

@@ -12,11 +12,12 @@ 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"
 )
 
 type Scheduler struct {
-	isCenter bool
 	// key: hash
 	alertRules map[string]*AlertRuleWorker
 
@@ -30,7 +31,8 @@ type Scheduler struct {
 	alertMuteCache  *memsto.AlertMuteCacheType
 	datasourceCache *memsto.DatasourceCacheType
 
-	promClients *prom.PromClientMap
+	promClients     *prom.PromClientMap
+	tdengineClients *tdengine.TdengineClientMap
 
 	naming *naming.Naming
 
@@ -38,11 +40,10 @@ type Scheduler struct {
 	stats *astats.Stats
 }
 
-func NewScheduler(isCenter bool, 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 {
+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, tdengineClients *tdengine.TdengineClientMap, naming *naming.Naming, ctx *ctx.Context, stats *astats.Stats) *Scheduler {
 	scheduler := &Scheduler{
-		isCenter:   isCenter,
 		aconf:      aconf,
 		alertRules: make(map[string]*AlertRuleWorker),
 
@@ -54,8 +55,9 @@ func NewScheduler(isCenter bool, aconf aconf.Alert, externalProcessors *process.
 		alertMuteCache:  alertMuteCache,
 		datasourceCache: datasourceCache,
 
-		promClients: promClients,
-		naming:      naming,
+		promClients:     promClients,
+		tdengineClients: tdengineClients,
+		naming:          naming,
 
 		ctx:   ctx,
 		stats: stats,
@@ -87,8 +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
@@ -99,22 +104,27 @@ 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.isCenter {
+		} else if rule.IsHostRule() && s.ctx.IsCenter {
 			// all host rule will be processed by center instance
 			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
@@ -130,7 +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
 	}
@@ -105,11 +118,15 @@ 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() {
-	logger.Infof("%s stopped", arw.Key())
+	logger.Infof("rule_eval %s stopped", arw.Key())
 	close(arw.quit)
 }
 
@@ -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

@@ -1,6 +1,7 @@
 package naming
 
 import (
+	"errors"
 	"sync"
 
 	"github.com/toolkits/pkg/consistent"
@@ -15,7 +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 {
@@ -39,8 +40,8 @@ func RebuildConsistentHashRing(datasourceId int64, nodes []string) {
 }
 
 func (chr *DatasourceHashRingType) GetNode(datasourceId int64, pk string) (string, error) {
-	chr.RLock()
-	defer chr.RUnlock()
+	chr.Lock()
+	defer chr.Unlock()
 	_, exists := chr.Rings[datasourceId]
 	if !exists {
 		chr.Rings[datasourceId] = NewConsistentHashRing(int32(NodeReplicas), []string{})
@@ -52,14 +53,27 @@ 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 {
-		logger.Debugf("datasource id:%d pk:%s failed to get node from hashring:%v", datasourceId, pk, 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
 	}
 	return node == currentNode
 }
 
 func (chr *DatasourceHashRingType) Set(datasourceId int64, r *consistent.Consistent) {
-	chr.RLock()
-	defer chr.RUnlock()
+	chr.Lock()
+	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

@@ -9,6 +9,7 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/aconf"
 	"github.com/ccfos/nightingale/v6/models"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
+	"github.com/ccfos/nightingale/v6/pkg/poster"
 
 	"github.com/toolkits/pkg/logger"
 )
@@ -16,14 +17,12 @@ import (
 type Naming struct {
 	ctx             *ctx.Context
 	heartbeatConfig aconf.HeartbeatConfig
-	isCenter        bool
 }
 
-func NewNaming(ctx *ctx.Context, heartbeat aconf.HeartbeatConfig, isCenter bool) *Naming {
+func NewNaming(ctx *ctx.Context, heartbeat aconf.HeartbeatConfig) *Naming {
 	naming := &Naming{
 		ctx:             ctx,
 		heartbeatConfig: heartbeat,
-		isCenter:        isCenter,
 	}
 	naming.Heartbeats()
 	return naming
@@ -45,6 +44,10 @@ func (n *Naming) Heartbeats() error {
 }
 
 func (n *Naming) loopDeleteInactiveInstances() {
+	if !n.ctx.IsCenter {
+		return
+	}
+
 	interval := time.Duration(10) * time.Minute
 	for {
 		time.Sleep(interval)
@@ -74,7 +77,7 @@ func (n *Naming) heartbeat() error {
 	var err error
 
 	// 在页面上维护实例和集群的对应关系
-	datasourceIds, err = models.GetDatasourceIdsByClusterName(n.ctx, n.heartbeatConfig.EngineName)
+	datasourceIds, err = models.GetDatasourceIdsByEngineName(n.ctx, n.heartbeatConfig.EngineName)
 	if err != nil {
 		return err
 	}
@@ -93,6 +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 {
@@ -112,7 +125,7 @@ func (n *Naming) heartbeat() error {
 		localss[datasourceIds[i]] = newss
 	}
 
-	if n.isCenter {
+	if n.ctx.IsCenter {
 		// 如果是中心节点，还需要处理 host 类型的告警规则，host 类型告警规则，和数据源无关，想复用下数据源的 hash ring，想用一个虚假的数据源 id 来处理
 		// if is center node, we need to handle host type alerting rules, host type alerting rules are not related to datasource, we want to reuse the hash ring of datasource, we want to use a fake datasource id to handle it
 		err := models.AlertingEngineHeartbeatWithCluster(n.ctx, n.heartbeatConfig.Endpoint, n.heartbeatConfig.EngineName, HostDatasource)
@@ -146,6 +159,21 @@ func (n *Naming) ActiveServers(datasourceId int64) ([]string, error) {
 		return nil, fmt.Errorf("cluster is empty")
 	}
 
+	if !n.ctx.IsCenter {
+		lst, err := poster.GetByUrls[[]string](n.ctx, "/v1/n9e/servers-active?dsid="+fmt.Sprintf("%d", datasourceId))
+		return lst, err
+	}
+
 	// 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()
@@ -113,13 +124,12 @@ func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inh
 	// 这些信息的修改是不会引起worker restart的，但是确实会影响告警处理逻辑
 	// 所以，这里直接从memsto.AlertRuleCache中获取并覆盖
 	p.inhibit = inhibit
-	p.rule = p.atertRuleCache.Get(p.rule.Id)
-	cachedRule := p.rule
+	cachedRule := p.atertRuleCache.Get(p.rule.Id)
 	if cachedRule == nil {
 		logger.Errorf("rule not found %+v", anomalyPoints)
 		return
 	}
-
+	p.rule = cachedRule
 	now := time.Now().Unix()
 	alertingKeys := map[string]struct{}{}
 
@@ -131,9 +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)
 	}
@@ -175,6 +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
@@ -228,6 +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)
 }
 
@@ -285,9 +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)
@@ -297,11 +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
@@ -310,7 +332,6 @@ func (p *Processor) fireEvent(event *models.AlertCurEvent) {
 					return
 				} else {
 					event.NotifyCurNumber = fired.NotifyCurNumber + 1
-					event.FirstTriggerTime = fired.FirstTriggerTime
 					p.pushEventToQueue(event)
 				}
 			}
@@ -318,6 +339,7 @@ func (p *Processor) fireEvent(event *models.AlertCurEvent) {
 	} else {
 		event.NotifyCurNumber = 1
 		event.FirstTriggerTime = event.TriggerTime
+		p.HandleFireEventHook(event)
 		p.pushEventToQueue(event)
 	}
 }
@@ -328,7 +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)
@@ -338,7 +359,7 @@ func (p *Processor) pushEventToQueue(e *models.AlertCurEvent) {
 func (p *Processor) RecoverAlertCurEventFromDb() {
 	p.pendings = NewAlertCurEventMap(nil)
 
-	curEvents, err := models.AlertCurEventGetByRuleIdAndCluster(p.ctx, p.rule.Id, p.datasourceId)
+	curEvents, err := models.AlertCurEventGetByRuleIdAndDsId(p.ctx, p.rule.Id, p.datasourceId)
 	if err != nil {
 		logger.Errorf("recover event from db for rule:%s failed, err:%s", p.Key(), err)
 		p.fires = NewAlertCurEventMap(nil)
@@ -406,7 +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 = ""
 	}
 }
 
@@ -433,7 +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

@@ -39,15 +39,16 @@ 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)
 	service.POST("/make-event", rt.makeEvent)
 }
 

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)
@@ -83,6 +81,14 @@ func (rt *Router) pushEventToQueue(c *gin.Context) {
 	ginx.NewRender(c).Message(nil)
 }
 
+func (rt *Router) eventPersist(c *gin.Context) {
+	var event *models.AlertCurEvent
+	ginx.BindJSON(c, &event)
+	event.FE2DB()
+	err := models.EventPersist(rt.Ctx, event)
+	ginx.NewRender(c).Data(event.Id, err)
+}
+
 type eventForm struct {
 	Alert         bool                  `json:"alert"`
 	AnomalyPoints []common.AnomalyPoint `json:"vectors"`

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, 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
@@ -23,7 +26,7 @@ func SendCallbacks(ctx *ctx.Context, urls []string, event *models.AlertCurEvent,
 
 		if strings.HasPrefix(url, "${ibex}") {
 			if !event.IsRecovered {
-				handleIbex(ctx, url, event, targetCache, ibexConf)
+				handleIbex(ctx, url, event, targetCache, userCache, ibexConf)
 			}
 			continue
 		}
@@ -32,11 +35,13 @@ 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(rule_id=%d url=%s) fail, resp: %s, err: %v, code: %d", event.RuleId, url, string(resp), err, code)
+			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(rule_id=%d url=%s) succ, resp: %s, code: %d", event.RuleId, url, string(resp), code)
+			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"`
@@ -60,7 +66,7 @@ type TaskCreateReply struct {
 	Dat int64  `json:"dat"` // task.id
 }
 
-func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, ibexConf aconf.Ibex) {
+func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, userCache *memsto.UserCacheType, ibexConf aconf.Ibex) {
 	arr := strings.Split(url, "/")
 
 	var idstr string
@@ -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
@@ -103,7 +109,7 @@ func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targe
 
 	// check perm
 	// tpl.GroupId - host - account 三元组校验权限
-	can, err := canDoIbex(ctx, tpl.UpdateBy, tpl, host, targetCache)
+	can, err := canDoIbex(ctx, tpl.UpdateBy, tpl, host, targetCache, userCache)
 	if err != nil {
 		logger.Errorf("event_callback_ibex: check perm fail: %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},
@@ -176,12 +207,8 @@ func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targe
 	}
 }
 
-func canDoIbex(ctx *ctx.Context, username string, tpl *models.TaskTpl, host string, targetCache *memsto.TargetCacheType) (bool, error) {
-	user, err := models.UserGetByUsername(ctx, username)
-	if err != nil {
-		return false, err
-	}
-
+func canDoIbex(ctx *ctx.Context, username string, tpl *models.TaskTpl, host string, targetCache *memsto.TargetCacheType, userCache *memsto.UserCacheType) (bool, error) {
+	user := userCache.GetByUsername(username)
 	if user != nil && user.IsAdmin() {
 		return true, nil
 	}

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) {
@@ -96,14 +100,16 @@ var mailQuit = make(chan struct{})
 func RestartEmailSender(smtp aconf.SMTPConfig) {
 	close(mailQuit)
 	mailQuit = make(chan struct{})
-	StartEmailSender(smtp)
+	startEmailSender(smtp)
 }
 
-func StartEmailSender(smtp aconf.SMTPConfig) {
+func InitEmailSender(smtp aconf.SMTPConfig) {
 	mailch = make(chan *gomail.Message, 100000)
+	startEmailSender(smtp)
+}
 
+func startEmailSender(smtp aconf.SMTPConfig) {
 	conf := smtp
-
 	if conf.Host == "" || conf.Port == 0 {
 		logger.Warning("SMTP configurations invalid")
 		return

alert/sender/feishu.go

@@ -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
@@ -35,7 +38,8 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript) {
 		if file.IsExist(fpath) {
 			oldContent, err := file.ToString(fpath)
 			if err != nil {
-				logger.Errorf("event_notify: read script file err: %v", err)
+				logger.Errorf("event_script_notify_fail: read script file err: %v", err)
+				stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 				return
 			}
 
@@ -47,13 +51,15 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript) {
 		if rewrite {
 			_, err := file.WriteString(fpath, config.Content)
 			if err != nil {
-				logger.Errorf("event_notify: write script file err: %v", err)
+				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_notify: chmod script file err: %v", err)
+				logger.Errorf("event_script_notify_fail: chmod script file err: %v", err)
+				stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 				return
 			}
 		}
@@ -70,7 +76,7 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript) {
 
 	err := startCmd(cmd)
 	if err != nil {
-		logger.Errorf("event_notify: run cmd err: %v", err)
+		logger.Errorf("event_script_notify_fail: run cmd err: %v", err)
 		return
 	}
 
@@ -78,20 +84,21 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript) {
 
 	if isTimeout {
 		if err == nil {
-			logger.Errorf("event_notify: timeout and killed process %s", fpath)
+			logger.Errorf("event_script_notify_fail: timeout and killed process %s", fpath)
 		}
 
 		if err != nil {
-			logger.Errorf("event_notify: kill process %s occur error %v", fpath, err)
+			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_notify: exec script %s occur error: %v, output: %s", fpath, err, buf.String())
+		logger.Errorf("event_script_notify_fail: exec script %s occur error: %v, output: %s", fpath, err, buf.String())
+		stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
 		return
 	}
 
-	logger.Infof("event_notify: exec %s output: %s", fpath, buf.String())
+	logger.Infof("event_script_notify_ok: exec %s output: %s", fpath, buf.String())
 }

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:
@@ -41,22 +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
@@ -50,19 +51,21 @@ 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 {
-			logger.Warningf("WebhookCallError, ruleId: [%d], eventId: [%d], url: [%s], error: [%s]", event.RuleId, event.Id, conf.Url, err)
+			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
 		}
 
 		var body []byte
 		if resp.Body != nil {
 			defer resp.Body.Close()
-			body, _ = ioutil.ReadAll(resp.Body)
+			body, _ = io.ReadAll(resp.Body)
 		}
 
-		logger.Debugf("alertingWebhook done, url: %s, response code: %d, body: %s", conf.Url, resp.StatusCode, string(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

@@ -1,19 +1,14 @@
 package cconf
 
-import (
-	"github.com/gin-gonic/gin"
-)
-
 type Center struct {
 	Plugins                []Plugin
-	BasicAuth              gin.Accounts
 	MetricsYamlFile        string
 	OpsYamlFile            string
 	BuiltinIntegrationsDir string
 	I18NHeaderKey          string
 	MetricDesc             MetricDescType
-	TargetMetrics          map[string]string
 	AnonymousAccess        AnonymousAccess
+	UseFileAssets          bool
 }
 
 type Plugin struct {

center/cconf/metric.go

@@ -4,7 +4,6 @@ import (
 	"path"
 
 	"github.com/toolkits/pkg/file"
-	"github.com/toolkits/pkg/runner"
 )
 
 // metricDesc , As load map happens before read map, there is no necessary to use concurrent map for metric desc store
@@ -33,10 +32,10 @@ func GetMetricDesc(lang, metric string) string {
 	return MetricDesc.CommonDesc[metric]
 }
 
-func LoadMetricsYaml(metricsYamlFile string) error {
+func LoadMetricsYaml(configDir, metricsYamlFile string) error {
 	fp := metricsYamlFile
 	if fp == "" {
-		fp = path.Join(runner.Cwd, "etc", "metrics.yaml")
+		fp = path.Join(configDir, "metrics.yaml")
 	}
 	if !file.IsExist(fp) {
 		return nil

center/cconf/ops.go

@@ -1,10 +1,11 @@
 package cconf
 
 import (
+	"fmt"
 	"path"
 
 	"github.com/toolkits/pkg/file"
-	"github.com/toolkits/pkg/runner"
+	"gopkg.in/yaml.v2"
 )
 
 var Operations = Operation{}
@@ -19,10 +20,10 @@ type Ops struct {
 	Ops   []string `yaml:"ops" json:"ops"`
 }
 
-func LoadOpsYaml(opsYamlFile string) error {
+func LoadOpsYaml(configDir string, opsYamlFile string) error {
 	fp := opsYamlFile
 	if fp == "" {
-		fp = path.Join(runner.Cwd, "etc", "ops.yaml")
+		fp = path.Join(configDir, "ops.yaml")
 	}
 	if !file.IsExist(fp) {
 		return nil
@@ -37,3 +38,134 @@ 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"
+
+- name: user
+  cname: 用户管理
+  ops:
+  - "/users"
+  - "/user-groups"
+  - "/user-groups/add"
+  - "/user-groups/put"
+  - "/user-groups/del"
+
+- 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/version"
+  - "/help/servers"
+  - "/help/source"
+  - "/help/sso"
+  - "/help/notification-tpls"
+  - "/help/notification-settings"
+  - "/help/migrate"
+`
+)

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/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 +8,24 @@ import (
 	"github.com/ccfos/nightingale/v6/alert/astats"
 	"github.com/ccfos/nightingale/v6/alert/process"
 	"github.com/ccfos/nightingale/v6/center/cconf"
+	"github.com/ccfos/nightingale/v6/center/cstats"
 	"github.com/ccfos/nightingale/v6/center/metas"
 	"github.com/ccfos/nightingale/v6/center/sso"
 	"github.com/ccfos/nightingale/v6/conf"
+	"github.com/ccfos/nightingale/v6/dumper"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
+	"github.com/ccfos/nightingale/v6/models/migrate"
 	"github.com/ccfos/nightingale/v6/pkg/ctx"
 	"github.com/ccfos/nightingale/v6/pkg/httpx"
 	"github.com/ccfos/nightingale/v6/pkg/i18nx"
 	"github.com/ccfos/nightingale/v6/pkg/logx"
+	"github.com/ccfos/nightingale/v6/pkg/version"
 	"github.com/ccfos/nightingale/v6/prom"
 	"github.com/ccfos/nightingale/v6/pushgw/idents"
 	"github.com/ccfos/nightingale/v6/pushgw/writer"
 	"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"
@@ -33,22 +38,27 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 		return nil, fmt.Errorf("failed to init config: %v", err)
 	}
 
-	cconf.LoadMetricsYaml(config.Center.MetricsYamlFile)
-	cconf.LoadOpsYaml(config.Center.OpsYamlFile)
+	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)
+	ctx := ctx.NewContext(context.Background(), db, true)
 	models.InitRoot(ctx)
+	migrate.Migrate(db)
+	httpx.InitRSAConfig(&config.HTTP.RSA)
 
 	redis, err := storage.NewRedis(config.Redis)
 	if err != nil {
@@ -56,7 +66,7 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	}
 
 	metas := metas.New(redis)
-	idents := idents.New(db)
+	idents := idents.New(ctx)
 
 	syncStats := memsto.NewSyncStats()
 	alertStats := astats.NewSyncStats()
@@ -69,16 +79,22 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
 	alertMuteCache := memsto.NewAlertMuteCache(ctx, syncStats)
 	alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
 	notifyConfigCache := memsto.NewNotifyConfigCache(ctx)
+	userCache := memsto.NewUserCache(ctx, syncStats)
+	userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
 
 	promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
+	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, true)
+	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 +102,7 @@ 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

@@ -12,15 +12,22 @@ import (
 	"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/front/statik"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"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/toolkits/pkg/runner"
+	"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 +37,22 @@ 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
+
+	DatasourceCheckHook func(*gin.Context) bool
 }
 
 func New(httpConfig httpx.Config, center cconf.Center, operations cconf.Operation, ds *memsto.DatasourceCacheType, ncc *memsto.NotifyConfigCacheType,
-	pc *prom.PromClientMap, redis storage.Redis, sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, tc *memsto.TargetCacheType) *Router {
+	pc *prom.PromClientMap, 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,
@@ -46,11 +60,17 @@ 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,
+
+		DatasourceCheckHook: func(ctx *gin.Context) bool { return false },
 	}
 }
 
@@ -89,38 +109,57 @@ func languageDetector(i18NHeaderKey string) gin.HandlerFunc {
 	}
 }
 
-func (rt *Router) configNoRoute(r *gin.Engine) {
+func (rt *Router) configNoRoute(r *gin.Engine, fs *http.FileSystem) {
 	r.NoRoute(func(c *gin.Context) {
 		arr := strings.Split(c.Request.URL.Path, ".")
 		suffix := arr[len(arr)-1]
+
 		switch suffix {
-		case "png", "jpeg", "jpg", "svg", "ico", "gif", "css", "js", "html", "htm", "gz", "zip", "map":
-			cwdarr := []string{"/"}
-			if runtime.GOOS == "windows" {
-				cwdarr[0] = ""
+		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...))
 			}
-			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:
-			cwdarr := []string{"/"}
-			if runtime.GOOS == "windows" {
-				cwdarr[0] = ""
+			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...))
 			}
-			cwdarr = append(cwdarr, strings.Split(runner.Cwd, "/")...)
-			cwdarr = append(cwdarr, "pub")
-			cwdarr = append(cwdarr, "index.html")
-			c.File(path.Join(cwdarr...))
 		}
 	})
 }
 
 func (rt *Router) Config(r *gin.Engine) {
+
 	r.Use(stat())
 	r.Use(languageDetector(rt.Center.I18NHeaderKey))
 	r.Use(aop.Recovery())
 
+	statikFS, err := fs.New()
+	if err != nil {
+		logger.Errorf("cannot create statik fs: %v", err)
+	}
+
+	if !rt.Center.UseFileAssets {
+		r.StaticFS("/pub", statikFS)
+	}
+
 	pagesPrefix := "/api/n9e"
 	pages := r.Group(pagesPrefix)
 	{
@@ -130,24 +169,45 @@ 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)
+
+			pages.GET("/sql-template", rt.QuerySqlTemplate)
 		} 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.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.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)
 		pages.GET("/auth/callback", rt.loginCallback)
 		pages.GET("/auth/callback/cas", rt.loginCallbackCas)
 		pages.GET("/auth/callback/oauth", rt.loginCallbackOAuth)
+		pages.GET("/auth/perms", rt.allPerms)
 
 		pages.GET("/metrics/desc", rt.metricsDescGetFile)
 		pages.POST("/metrics/desc", rt.metricsDescGetMap)
@@ -208,6 +268,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.GET("/builtin-boards-cates", rt.auth(), rt.user(), rt.builtinBoardCateGets)
 		pages.POST("/builtin-boards-detail", rt.auth(), rt.user(), rt.builtinBoardDetailGets)
 		pages.GET("/integrations/icon/:cate/:name", rt.builtinIcon)
+		pages.GET("/integrations/makedown/:cate", rt.builtinMarkdown)
 
 		pages.GET("/busi-group/:id/boards", rt.auth(), rt.user(), rt.perm("/dashboards"), rt.bgro(), rt.boardGets)
 		pages.POST("/busi-group/:id/boards", rt.auth(), rt.user(), rt.perm("/dashboards/add"), rt.bgrw(), rt.boardAdd)
@@ -233,6 +294,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.PUT("/busi-group/:id/alert-rules/fields", rt.auth(), rt.user(), rt.perm("/alert-rules/put"), rt.bgrw(), rt.alertRulePutFields)
 		pages.PUT("/busi-group/:id/alert-rule/:arid", rt.auth(), rt.user(), rt.perm("/alert-rules/put"), rt.alertRulePutByFE)
 		pages.GET("/alert-rule/:arid", rt.auth(), rt.user(), rt.perm("/alert-rules"), rt.alertRuleGet)
+		pages.PUT("/busi-group/alert-rule/validate", rt.auth(), rt.user(), rt.perm("/alert-rules/put"), rt.alertRuleValidation)
 
 		pages.GET("/busi-group/:id/recording-rules", rt.auth(), rt.user(), rt.perm("/recording-rules"), rt.recordingRuleGets)
 		pages.POST("/busi-group/:id/recording-rules", rt.auth(), rt.user(), rt.perm("/recording-rules/add"), rt.bgrw(), rt.recordingRuleAddByFE)
@@ -242,6 +304,7 @@ func (rt *Router) Config(r *gin.Engine) {
 		pages.PUT("/busi-group/:id/recording-rules/fields", rt.auth(), rt.user(), rt.perm("/recording-rules/put"), rt.recordingRulePutFields)
 
 		pages.GET("/busi-group/:id/alert-mutes", rt.auth(), rt.user(), rt.perm("/alert-mutes"), rt.bgro(), rt.alertMuteGetsByBG)
+		pages.POST("/busi-group/:id/alert-mutes/preview", rt.auth(), rt.user(), rt.perm("/alert-mutes/add"), rt.bgrw(), rt.alertMutePreview)
 		pages.POST("/busi-group/:id/alert-mutes", rt.auth(), rt.user(), rt.perm("/alert-mutes/add"), rt.bgrw(), rt.alertMuteAdd)
 		pages.DELETE("/busi-group/:id/alert-mutes", rt.auth(), rt.user(), rt.perm("/alert-mutes/del"), rt.bgrw(), rt.alertMuteDel)
 		pages.PUT("/busi-group/:id/alert-mute/:amid", rt.auth(), rt.user(), rt.perm("/alert-mutes/put"), rt.alertMutePutByFE)
@@ -267,6 +330,7 @@ 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)
@@ -303,11 +367,13 @@ func (rt *Router) Config(r *gin.Engine) {
 
 		pages.GET("/role/:id/ops", rt.auth(), rt.admin(), rt.operationOfRole)
 		pages.PUT("/role/:id/ops", rt.auth(), rt.admin(), rt.roleBindOperation)
-		pages.GET("operation", rt.operations)
+		pages.GET("/operation", rt.operations)
 
 		pages.GET("/notify-tpls", rt.auth(), rt.admin(), rt.notifyTplGets)
 		pages.PUT("/notify-tpl/content", rt.auth(), rt.admin(), rt.notifyTplUpdateContent)
 		pages.PUT("/notify-tpl", rt.auth(), rt.admin(), rt.notifyTplUpdate)
+		pages.POST("/notify-tpl", rt.auth(), rt.admin(), rt.notifyTplAdd)
+		pages.DELETE("/notify-tpl/:id", rt.auth(), rt.admin(), rt.notifyTplDel)
 		pages.POST("/notify-tpl/preview", rt.auth(), rt.admin(), rt.notifyTplPreview)
 
 		pages.GET("/sso-configs", rt.auth(), rt.admin(), rt.ssoConfigGets)
@@ -327,19 +393,48 @@ func (rt *Router) Config(r *gin.Engine) {
 
 		pages.GET("/notify-config", rt.auth(), rt.admin(), rt.notifyConfigGet)
 		pages.PUT("/notify-config", rt.auth(), rt.admin(), rt.notifyConfigPut)
+		pages.PUT("/smtp-config-test", rt.auth(), rt.admin(), rt.attemptSendEmail)
+
+		pages.GET("/es-index-pattern", rt.auth(), rt.esIndexPatternGet)
+		pages.GET("/es-index-pattern-list", rt.auth(), rt.esIndexPatternGetList)
+		pages.POST("/es-index-pattern", rt.auth(), rt.admin(), rt.esIndexPatternAdd)
+		pages.PUT("/es-index-pattern", rt.auth(), rt.admin(), rt.esIndexPatternPut)
+		pages.DELETE("/es-index-pattern", rt.auth(), rt.admin(), rt.esIndexPatternDel)
+
+		pages.GET("/user-variable-configs", rt.auth(), rt.admin(), rt.userVariableConfigGets)
+		pages.POST("/user-variable-config", rt.auth(), rt.admin(), rt.userVariableConfigAdd)
+		pages.PUT("/user-variable-config/:id", rt.auth(), rt.admin(), rt.userVariableConfigPut)
+		pages.DELETE("/user-variable-config/:id", rt.auth(), rt.admin(), rt.userVariableConfigDel)
+
+		pages.GET("/config", rt.auth(), rt.admin(), rt.configGetByKey)
+		pages.PUT("/config", rt.auth(), rt.admin(), rt.configPutByKey)
+
 	}
 
-	if rt.HTTP.Service.Enable {
+	r.GET("/api/n9e/versions", func(c *gin.Context) {
+		v := version.Version
+		lastIndex := strings.LastIndex(version.Version, "-")
+		if lastIndex != -1 {
+			v = version.Version[:lastIndex]
+		}
+
+		ginx.NewRender(c).Data(gin.H{"version": v, "github_verison": version.GithubVersion.Load().(string)}, nil)
+	})
+
+	if rt.HTTP.APIForService.Enable {
 		service := r.Group("/v1/n9e")
-		if len(rt.HTTP.Service.BasicAuth) > 0 {
-			service.Use(gin.BasicAuth(rt.HTTP.Service.BasicAuth))
+		if len(rt.HTTP.APIForService.BasicAuth) > 0 {
+			service.Use(gin.BasicAuth(rt.HTTP.APIForService.BasicAuth))
 		}
 		{
 			service.Any("/prometheus/*url", rt.dsProxy)
 			service.POST("/users", rt.userAddPost)
 			service.GET("/users", rt.userFindAll)
 
-			service.GET("/targets", rt.targetGets)
+			service.GET("/user-groups", rt.userGroupGetsByService)
+			service.GET("/user-group-members", rt.userGroupMemberGetsByService)
+
+			service.GET("/targets", rt.targetGetsByService)
 			service.GET("/targets/tags", rt.targetGetTags)
 			service.POST("/targets/tags", rt.targetBindTagsByService)
 			service.DELETE("/targets/tags", rt.targetUnbindTagsByService)
@@ -351,36 +446,58 @@ func (rt *Router) Config(r *gin.Engine) {
 			service.GET("/alert-rule/:arid", rt.alertRuleGet)
 			service.GET("/alert-rules", rt.alertRulesGetByService)
 
+			service.GET("/alert-subscribes", rt.alertSubscribeGetsByService)
+
+			service.GET("/busi-groups", rt.busiGroupGetsByService)
+
+			service.GET("/datasources", rt.datasourceGetsByService)
+			service.GET("/datasource-ids", rt.getDatasourceIds)
+			service.POST("/server-heartbeat", rt.serverHeartbeat)
+			service.GET("/servers-active", rt.serversActive)
+
+			service.GET("/recording-rules", rt.recordingRuleGetsByService)
+
 			service.GET("/alert-mutes", rt.alertMuteGets)
 			service.POST("/alert-mutes", rt.alertMuteAddByService)
 			service.DELETE("/alert-mutes", rt.alertMuteDel)
 
 			service.GET("/alert-cur-events", rt.alertCurEventsList)
+			service.GET("/alert-cur-events-get-by-rid", rt.alertCurEventsGetByRid)
 			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)
 			service.PUT("/configs", rt.configsPut)
 			service.POST("/configs", rt.configsPost)
 			service.DELETE("/configs", rt.configsDel)
 
 			service.POST("/conf-prop/encrypt", rt.confPropEncrypt)
 			service.POST("/conf-prop/decrypt", rt.confPropDecrypt)
+
+			service.GET("/statistic", rt.statistic)
+
+			service.GET("/notify-tpls", rt.notifyTplGets)
+
+			service.POST("/task-record-add", rt.taskRecordAdd)
 		}
 	}
 
-	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)
 		}
 	}
 
-	rt.configNoRoute(r)
+	rt.configNoRoute(r, &statikFS)
+
 }
 
 func Render(c *gin.Context, data, msg interface{}) {

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"
 
@@ -128,6 +129,13 @@ func (rt *Router) alertCurEventsCardDetails(c *gin.Context) {
 	ginx.NewRender(c).Data(list, err)
 }
 
+// alertCurEventsGetByRid
+func (rt *Router) alertCurEventsGetByRid(c *gin.Context) {
+	rid := ginx.QueryInt64(c, "rid")
+	dsId := ginx.QueryInt64(c, "dsid")
+	ginx.NewRender(c).Data(models.AlertCurEventGetByRuleIdAndDsId(rt.Ctx, rid, dsId))
+}
+
 // 列表方式，拉取活跃告警
 func (rt *Router) alertCurEventsList(c *gin.Context) {
 	stime, etime := getTimeRange(c)
@@ -175,10 +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 {
@@ -186,8 +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) {
@@ -201,3 +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"
 
@@ -27,7 +28,12 @@ func (rt *Router) alertRuleGets(c *gin.Context) {
 }
 
 func (rt *Router) alertRulesGetByService(c *gin.Context) {
-	prods := strings.Split(ginx.QueryStr(c, "prods", ""), ",")
+	prods := []string{}
+	prodStr := ginx.QueryStr(c, "prods", "")
+	if prodStr != "" {
+		prods = strings.Split(ginx.QueryStr(c, "prods", ""), ",")
+	}
+
 	query := ginx.QueryStr(c, "query", "")
 	algorithm := ginx.QueryStr(c, "algorithm", "")
 	cluster := ginx.QueryStr(c, "cluster", "")
@@ -266,3 +272,54 @@ func (rt *Router) alertRuleGet(c *gin.Context) {
 
 	ginx.NewRender(c).Data(ar, err)
 }
+
+// pre validation before save rule
+func (rt *Router) alertRuleValidation(c *gin.Context) {
+	var f models.AlertRule //new
+	ginx.BindJSON(c, &f)
+
+	if len(f.NotifyChannelsJSON) > 0 && len(f.NotifyGroupsJSON) > 0 { //Validation NotifyChannels
+		ngids := make([]int64, 0, len(f.NotifyChannelsJSON))
+		for i := range f.NotifyGroupsJSON {
+			id, _ := strconv.ParseInt(f.NotifyGroupsJSON[i], 10, 64)
+			ngids = append(ngids, id)
+		}
+		userGroups := rt.UserGroupCache.GetByUserGroupIds(ngids)
+		uids := make([]int64, 0)
+		for i := range userGroups {
+			uids = append(uids, userGroups[i].UserIds...)
+		}
+		users := rt.UserCache.GetByUserIds(uids)
+		//If any users have a certain notify channel's token, it will be okay. Otherwise, this notify channel is absent of tokens.
+		ancs := make([]string, 0, len(f.NotifyChannelsJSON)) //absent Notify Channels
+		for i := range f.NotifyChannelsJSON {
+			flag := true
+			//ignore non-default channels
+			switch f.NotifyChannelsJSON[i] {
+			case models.Dingtalk, models.Wecom, models.Feishu, models.Mm,
+				models.Telegram, models.Email, models.FeishuCard:
+				// do nothing
+			default:
+				continue
+			}
+			//default channels
+			for ui := range users {
+				if _, b := users[ui].ExtractToken(f.NotifyChannelsJSON[i]); b {
+					flag = false
+					break
+				}
+			}
+			if flag {
+				ancs = append(ancs, f.NotifyChannelsJSON[i])
+			}
+		}
+
+		if len(ancs) > 0 {
+			ginx.NewRender(c).Message("All users are missing notify channel configurations. Please check for missing tokens (each channel should be configured with at least one user). %s", ancs)
+			return
+		}
+
+	}
+
+	ginx.NewRender(c).Message("")
+}

center/router/router_alert_subscribe.go

@@ -14,21 +14,18 @@ import (
 func (rt *Router) alertSubscribeGets(c *gin.Context) {
 	bgid := ginx.UrlParamInt64(c, "id")
 	lst, err := models.AlertSubscribeGets(rt.Ctx, bgid)
-	if err == nil {
-		ugcache := make(map[int64]*models.UserGroup)
-		for i := 0; i < len(lst); i++ {
-			ginx.Dangerous(lst[i].FillUserGroups(rt.Ctx, ugcache))
-		}
+	ginx.Dangerous(err)
 
-		rulecache := make(map[int64]string)
-		for i := 0; i < len(lst); i++ {
-			ginx.Dangerous(lst[i].FillRuleName(rt.Ctx, rulecache))
-		}
+	ugcache := make(map[int64]*models.UserGroup)
+	rulecache := make(map[int64]string)
 
-		for i := 0; i < len(lst); i++ {
-			ginx.Dangerous(lst[i].FillDatasourceIds(rt.Ctx))
-		}
+	for i := 0; i < len(lst); i++ {
+		ginx.Dangerous(lst[i].FillUserGroups(rt.Ctx, ugcache))
+		ginx.Dangerous(lst[i].FillRuleName(rt.Ctx, rulecache))
+		ginx.Dangerous(lst[i].FillDatasourceIds(rt.Ctx))
+		ginx.Dangerous(lst[i].DB2FE())
 	}
+
 	ginx.NewRender(c).Data(lst, err)
 }
 
@@ -83,6 +80,9 @@ func (rt *Router) alertSubscribePut(c *gin.Context) {
 			rt.Ctx,
 			"name",
 			"disabled",
+			"prod",
+			"cate",
+			"datasource_ids",
 			"cluster",
 			"rule_id",
 			"tags",
@@ -96,7 +96,9 @@ func (rt *Router) alertSubscribePut(c *gin.Context) {
 			"webhooks",
 			"for_duration",
 			"redefine_webhooks",
-			"datasource_ids",
+			"severities",
+			"extra_config",
+			"busi_groups",
 		))
 	}
 
@@ -110,3 +112,8 @@ func (rt *Router) alertSubscribeDel(c *gin.Context) {
 
 	ginx.NewRender(c).Message(models.AlertSubscribeDel(rt.Ctx, f.Ids))
 }
+
+func (rt *Router) alertSubscribeGetsByService(c *gin.Context) {
+	lst, err := models.AlertSubscribeGetsByService(rt.Ctx)
+	ginx.NewRender(c).Data(lst, err)
+}

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_busi_group.go

@@ -123,6 +123,11 @@ func (rt *Router) busiGroupGets(c *gin.Context) {
 	ginx.NewRender(c).Data(lst, err)
 }
 
+func (rt *Router) busiGroupGetsByService(c *gin.Context) {
+	lst, err := models.BusiGroupGetAll(rt.Ctx)
+	ginx.NewRender(c).Data(lst, err)
+}
+
 // 这个接口只有在活跃告警页面才调用，获取各个BG的活跃告警数量
 func (rt *Router) busiGroupAlertingsGets(c *gin.Context) {
 	ids := ginx.QueryStr(c, "ids", "")

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_configs.go

@@ -20,6 +20,17 @@ func (rt *Router) configGet(c *gin.Context) {
 	ginx.NewRender(c).Data(configs, err)
 }
 
+func (rt *Router) configGetByKey(c *gin.Context) {
+	config, err := models.ConfigsGet(rt.Ctx, ginx.QueryStr(c, "key"))
+	ginx.NewRender(c).Data(config, err)
+}
+
+func (rt *Router) configPutByKey(c *gin.Context) {
+	var f models.Configs
+	ginx.BindJSON(c, &f)
+	ginx.NewRender(c).Message(models.ConfigsSet(rt.Ctx, f.Ckey, f.Cval))
+}
+
 func (rt *Router) configsDel(c *gin.Context) {
 	var f idsForm
 	ginx.BindJSON(c, &f)

center/router/router_datasource.go

@@ -3,8 +3,10 @@ package router
 import (
 	"crypto/tls"
 	"fmt"
+	"io"
 	"net/http"
 	"net/url"
+	"strings"
 
 	"github.com/ccfos/nightingale/v6/models"
 
@@ -24,6 +26,11 @@ type listReq struct {
 }
 
 func (rt *Router) datasourceList(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req listReq
 	ginx.BindJSON(c, &req)
 
@@ -35,6 +42,12 @@ func (rt *Router) datasourceList(c *gin.Context) {
 	Render(c, list, err)
 }
 
+func (rt *Router) datasourceGetsByService(c *gin.Context) {
+	typ := ginx.QueryStr(c, "typ", "")
+	lst, err := models.GetDatasourcesGetsBy(rt.Ctx, typ, "", "", "")
+	ginx.NewRender(c).Data(lst, err)
+}
+
 type datasourceBrief struct {
 	Id         int64  `json:"id"`
 	Name       string `json:"name"`
@@ -58,6 +71,11 @@ func (rt *Router) datasourceBriefs(c *gin.Context) {
 }
 
 func (rt *Router) datasourceUpsert(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	username := Username(c)
@@ -98,6 +116,10 @@ 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{
@@ -116,10 +138,33 @@ func DatasourceCheck(ds models.Datasource) error {
 	if ds.PluginType == models.PROMETHEUS {
 		subPath := "/api/v1/query"
 		query := url.Values{}
-		query.Add("query", "1+1")
+		if ds.HTTPJson.IsLoki() {
+			subPath = "/api/v1/labels"
+		} 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)
@@ -143,13 +188,19 @@ 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.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	err := req.Get(rt.Ctx)
@@ -157,6 +208,11 @@ func (rt *Router) datasourceGet(c *gin.Context) {
 }
 
 func (rt *Router) datasourceUpdataStatus(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var req models.Datasource
 	ginx.BindJSON(c, &req)
 	username := Username(c)
@@ -166,12 +222,24 @@ func (rt *Router) datasourceUpdataStatus(c *gin.Context) {
 }
 
 func (rt *Router) datasourceDel(c *gin.Context) {
+	if rt.DatasourceCheckHook(c) {
+		Render(c, []int{}, nil)
+		return
+	}
+
 	var ids []int64
 	ginx.BindJSON(c, &ids)
 	err := models.DatasourceDel(rt.Ctx, ids)
 	Render(c, nil, err)
 }
 
+func (rt *Router) getDatasourceIds(c *gin.Context) {
+	name := ginx.QueryStr(c, "name")
+	datasourceIds, err := models.GetDatasourceIdsByEngineName(rt.Ctx, name)
+
+	ginx.NewRender(c).Data(datasourceIds, err)
+}
+
 func Username(c *gin.Context) string {
 
 	return c.MustGet("username").(string)

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

@@ -17,6 +17,41 @@ import (
 
 const defaultLimit = 300
 
+func (rt *Router) statistic(c *gin.Context) {
+	name := ginx.QueryStr(c, "name")
+	var model interface{}
+	var err error
+	var statistics *models.Statistics
+	switch name {
+	case "alert_mute":
+		model = models.AlertMute{}
+	case "alert_rule":
+		model = models.AlertRule{}
+	case "alert_subscribe":
+		model = models.AlertSubscribe{}
+	case "busi_group":
+		model = models.BusiGroup{}
+	case "recording_rule":
+		model = models.RecordingRule{}
+	case "target":
+		model = models.Target{}
+	case "user":
+		model = models.User{}
+	case "user_group":
+		model = models.UserGroup{}
+	case "datasource":
+		// datasource update_at is different from others
+		statistics, err = models.DatasourceStatistics(rt.Ctx)
+		ginx.NewRender(c).Data(statistics, err)
+		return
+	default:
+		ginx.Bomb(http.StatusBadRequest, "invalid name")
+	}
+
+	statistics, err = models.StatisticsGet(rt.Ctx, model)
+	ginx.NewRender(c).Data(statistics, err)
+}
+
 func queryDatasourceIds(c *gin.Context) []int64 {
 	datasourceIds := ginx.QueryStr(c, "datasource_ids", "")
 	datasourceIds = strings.ReplaceAll(datasourceIds, ",", " ")

center/router/router_heartbeat.go

@@ -4,12 +4,14 @@ import (
 	"compress/gzip"
 	"encoding/json"
 	"io/ioutil"
+	"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) {
@@ -35,16 +37,30 @@ 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 gid != 0 {
-		target, has := rt.TargetCache.Get(req.Hostname)
-		if has && target.GroupId != gid {
-			err = models.TargetUpdateBgid(rt.Ctx, []string{req.Hostname}, gid, false)
+	if target, has := rt.TargetCache.Get(req.Hostname); has && target != nil {
+		var defGid int64 = -1
+		gid := ginx.QueryInt64(c, "gid", defGid)
+		hostIpStr := strings.TrimSpace(req.HostIp)
+		if gid == defGid { //set gid value from cache
+			gid = target.GroupId
+		}
+		logger.Debugf("heartbeat gid: %v, host_ip: '%v', target: %v", gid, hostIpStr, *target)
+		if gid != target.GroupId || hostIpStr != target.HostIp { // if either gid or host_ip has a new value
+			err = models.TargetUpdateHostIpAndBgid(rt.Ctx, req.Hostname, hostIpStr, gid)
 		}
 	}
 

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

@@ -5,6 +5,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/ccfos/nightingale/v6/alert/common"
 	"github.com/ccfos/nightingale/v6/models"
 
 	"github.com/gin-gonic/gin"
@@ -21,7 +22,7 @@ func (rt *Router) alertMuteGetsByBG(c *gin.Context) {
 
 func (rt *Router) alertMuteGets(c *gin.Context) {
 	prods := strings.Fields(ginx.QueryStr(c, "prods", ""))
-	bgid := ginx.QueryInt64(c, "bgid", 0)
+	bgid := ginx.QueryInt64(c, "bgid", -1)
 	query := ginx.QueryStr(c, "query", "")
 	lst, err := models.AlertMuteGets(rt.Ctx, prods, bgid, query)
 
@@ -29,16 +30,41 @@ func (rt *Router) alertMuteGets(c *gin.Context) {
 }
 
 func (rt *Router) alertMuteAdd(c *gin.Context) {
+
 	var f models.AlertMute
 	ginx.BindJSON(c, &f)
 
 	username := c.MustGet("username").(string)
 	f.CreateBy = username
 	f.GroupId = ginx.UrlParamInt64(c, "id")
-
 	ginx.NewRender(c).Message(f.Add(rt.Ctx))
 }
 
+// Preview events (alert_cur_event) that match the mute strategy based on the following criteria:
+// business group ID (group_id, group_id), product (prod, rule_prod),
+// alert event severity (severities, severity), and event tags (tags, tags).
+// For products of type not 'host', also consider the category (cate, cate) and datasource ID (datasource_ids, datasource_id).
+func (rt *Router) alertMutePreview(c *gin.Context) {
+	//Generally the match of events would be less.
+
+	var f models.AlertMute
+	ginx.BindJSON(c, &f)
+	f.GroupId = ginx.UrlParamInt64(c, "id")
+	ginx.Dangerous(f.Verify()) //verify and parse tags json to ITags
+	events, err := models.AlertCurEventGetsFromAlertMute(rt.Ctx, &f)
+	ginx.Dangerous(err)
+
+	matchEvents := make([]*models.AlertCurEvent, 0, len(events))
+	for i := 0; i < len(events); i++ {
+		events[i].DB2Mem()
+		if common.MatchTags(events[i].TagsMap, f.ITags) {
+			matchEvents = append(matchEvents, events[i])
+		}
+	}
+	ginx.NewRender(c).Data(matchEvents, err)
+
+}
+
 func (rt *Router) alertMuteAddByService(c *gin.Context) {
 	var f models.AlertMute
 	ginx.BindJSON(c, &f)

center/router/router_notify_config.go

@@ -2,15 +2,17 @@ package router
 
 import (
 	"encoding/json"
+	"strings"
 
 	"github.com/ccfos/nightingale/v6/alert/aconf"
 	"github.com/ccfos/nightingale/v6/alert/sender"
 	"github.com/ccfos/nightingale/v6/memsto"
 	"github.com/ccfos/nightingale/v6/models"
-	"github.com/pelletier/go-toml/v2"
 
 	"github.com/gin-gonic/gin"
+	"github.com/pelletier/go-toml/v2"
 	"github.com/toolkits/pkg/ginx"
+	"github.com/toolkits/pkg/str"
 )
 
 func (rt *Router) webhookGets(c *gin.Context) {
@@ -30,9 +32,12 @@ func (rt *Router) webhookPuts(c *gin.Context) {
 	var webhooks []models.Webhook
 	ginx.BindJSON(c, &webhooks)
 	for i := 0; i < len(webhooks); i++ {
-		for k, v := range webhooks[i].HeaderMap {
-			webhooks[i].Headers = append(webhooks[i].Headers, k)
-			webhooks[i].Headers = append(webhooks[i].Headers, v)
+		webhooks[i].Headers = []string{}
+		if len(webhooks[i].HeaderMap) > 0 {
+			for k, v := range webhooks[i].HeaderMap {
+				webhooks[i].Headers = append(webhooks[i].Headers, k)
+				webhooks[i].Headers = append(webhooks[i].Headers, v)
+			}
 		}
 	}
 
@@ -175,16 +180,42 @@ func (rt *Router) notifyConfigPut(c *gin.Context) {
 
 	if f.Ckey == models.SMTP {
 		// 重置邮件发送器
-		var smtp aconf.SMTPConfig
-		err := toml.Unmarshal([]byte(f.Cval), &smtp)
-		ginx.Dangerous(err)
-
-		if smtp.Host == "" || smtp.Port == 0 {
-			ginx.Bomb(200, "smtp host or port can not be empty")
-		}
+		smtp := smtpValidate(f.Cval)
 
 		go sender.RestartEmailSender(smtp)
 	}
 
 	ginx.NewRender(c).Message(nil)
 }
+
+func smtpValidate(smtpStr string) aconf.SMTPConfig {
+	var smtp aconf.SMTPConfig
+	ginx.Dangerous(toml.Unmarshal([]byte(smtpStr), &smtp))
+
+	if smtp.Host == "" || smtp.Port == 0 {
+		ginx.Bomb(200, "smtp host or port can not be empty")
+	}
+	return smtp
+}
+
+type form struct {
+	models.Configs
+	Email string `json:"email"`
+}
+
+// After configuring the aconf.SMTPConfig, users can choose to perform a test. In this test, the function attempts to send an email
+func (rt *Router) attemptSendEmail(c *gin.Context) {
+	var f form
+	ginx.BindJSON(c, &f)
+
+	if f.Email = strings.TrimSpace(f.Email); f.Email == "" || !str.IsMail(f.Email) {
+		ginx.Bomb(200, "email(%s) invalid", f.Email)
+	}
+
+	if f.Ckey != models.SMTP {
+		ginx.Bomb(200, "config(%v) invalid", f)
+	}
+	smtp := smtpValidate(f.Cval)
+	ginx.NewRender(c).Message(sender.SendEmail("Email test", "email content", []string{f.Email}, smtp))
+
+}

center/router/router_notify_tpl.go

@@ -5,16 +5,30 @@ import (
 	"encoding/json"
 	"fmt"
 	"html/template"
+	"strings"
 
 	"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)
 }
@@ -22,11 +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))
 }
@@ -34,20 +44,39 @@ 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
 	}
-	if _, err := template.New(f.Channel).Funcs(tplx.TemplateFuncMap).Parse(f.Content); err != nil {
+
+	var defs = []string{
+		"{{$labels := .TagsMap}}",
+		"{{$value := .TriggerValue}}",
+	}
+	text := strings.Join(append(defs, f.Content), "")
+
+	if _, err := template.New(f.Channel).Funcs(tplx.TemplateFuncMap).Parse(text); err != nil {
 		return fmt.Errorf("notify template verify illegal:%s", err.Error())
 	}
 
@@ -57,17 +86,34 @@ 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)
 
-	tpl, err := template.New(f.Channel).Funcs(tplx.TemplateFuncMap).Parse(f.Content)
+	var defs = []string{
+		"{{$labels := .TagsMap}}",
+		"{{$value := .TriggerValue}}",
+	}
+	text := strings.Join(append(defs, f.Content), "")
+	tpl, err := template.New(f.Channel).Funcs(tplx.TemplateFuncMap).Parse(text)
 	ginx.Dangerous(err)
 
+	event.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
+		}
+
+		event.TagsMap[arr[0]] = arr[1]
+	}
+
 	var body bytes.Buffer
 	var ret string
 	if err := tpl.Execute(&body, event); err != nil {
@@ -78,3 +124,25 @@ func (rt *Router) notifyTplPreview(c *gin.Context) {
 
 	ginx.NewRender(c).Data(ret, nil)
 }
+
+// add new notify template
+func (rt *Router) notifyTplAdd(c *gin.Context) {
+	var f models.NotifyTpl
+	ginx.BindJSON(c, &f)
+	f.Channel = strings.TrimSpace(f.Channel)
+	ginx.Dangerous(templateValidate(f))
+
+	count, err := models.NotifyTplCountByChannel(rt.Ctx, f.Channel)
+	ginx.Dangerous(err)
+	if count != 0 {
+		ginx.Bomb(200, "Refuse to create duplicate channel(unique)")
+	}
+	ginx.NewRender(c).Message(f.Create(rt.Ctx))
+}
+
+// delete notify template, not allowed to delete the system defaults(models.DefaultChannels)
+func (rt *Router) notifyTplDel(c *gin.Context) {
+	f := new(models.NotifyTpl)
+	id := ginx.UrlParamInt64(c, "id")
+	ginx.NewRender(c).Message(f.NotifyTplDelete(rt.Ctx, id))
+}

center/router/router_proxy.go

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

center/router/router_recording_rule.go

@@ -19,6 +19,11 @@ func (rt *Router) recordingRuleGets(c *gin.Context) {
 	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)
+}
+
 func (rt *Router) recordingRuleGet(c *gin.Context) {
 	rrid := ginx.UrlParamInt64(c, "rrid")
 

center/router/router_role.go

@@ -83,3 +83,18 @@ func (rt *Router) roleGets(c *gin.Context) {
 	lst, err := models.RoleGetsAll(rt.Ctx)
 	ginx.NewRender(c).Data(lst, err)
 }
+
+func (rt *Router) allPerms(c *gin.Context) {
+	roles, err := models.RoleGetsAll(rt.Ctx)
+	ginx.Dangerous(err)
+	m := make(map[string][]string)
+	for _, r := range roles {
+		lst, err := models.OperationsOfRole(rt.Ctx, strings.Fields(r.Name))
+		if err != nil {
+			continue
+		}
+		m[r.Name] = lst
+	}
+
+	ginx.NewRender(c).Data(m, err)
+}

center/router/router_server.go

@@ -1,6 +1,8 @@
 package router
 
 import (
+	"time"
+
 	"github.com/ccfos/nightingale/v6/models"
 
 	"github.com/gin-gonic/gin"
@@ -16,3 +18,23 @@ func (rt *Router) serverClustersGet(c *gin.Context) {
 	list, err := models.AlertingEngineGetsClusters(rt.Ctx, "")
 	ginx.NewRender(c).Data(list, err)
 }
+
+func (rt *Router) serverHeartbeat(c *gin.Context) {
+	var req models.HeartbeatInfo
+	ginx.BindJSON(c, &req)
+	err := models.AlertingEngineHeartbeatWithCluster(rt.Ctx, req.Instance, req.EngineCluster, req.DatasourceId)
+	ginx.NewRender(c).Message(err)
+}
+
+func (rt *Router) serversActive(c *gin.Context) {
+	datasourceId := ginx.QueryInt64(c, "dsid")
+	engineName := ginx.QueryStr(c, "engine_name", "")
+	if engineName != "" {
+		servers, err := models.AlertingEngineGetsInstances(rt.Ctx, "engine_cluster = ? and clock > ?", engineName, time.Now().Unix()-30)
+		ginx.NewRender(c).Data(servers, err)
+		return
+	}
+
+	servers, err := models.AlertingEngineGetsInstances(rt.Ctx, "datasource_id = ? and clock > ?", datasourceId, time.Now().Unix()-30)
+	ginx.NewRender(c).Data(servers, err)
+}

center/router/router_target.go

@@ -45,12 +45,32 @@ func (rt *Router) targetGets(c *gin.Context) {
 	bgid := ginx.QueryInt64(c, "bgid", -1)
 	query := ginx.QueryStr(c, "query", "")
 	limit := ginx.QueryInt(c, "limit", 30)
+	downtime := ginx.QueryInt64(c, "downtime", 0)
 	dsIds := queryDatasourceIds(c)
 
-	total, err := models.TargetTotal(rt.Ctx, bgid, dsIds, query)
+	var bgids []int64
+	var err error
+	if bgid == -1 {
+		user := c.MustGet("user").(*models.User)
+		if !user.IsAdmin() {
+			// 如果是非 admin 用户，全部对象的情况，找到用户有权限的业务组
+			userGroupIds, err := models.MyGroupIds(rt.Ctx, user.Id)
+			ginx.Dangerous(err)
+
+			bgids, err = models.BusiGroupIds(rt.Ctx, userGroupIds)
+			ginx.Dangerous(err)
+
+			// 将未分配业务组的对象也加入到列表中
+			bgids = append(bgids, 0)
+		}
+	} else {
+		bgids = append(bgids, bgid)
+	}
+
+	total, err := models.TargetTotal(rt.Ctx, bgids, dsIds, query, downtime)
 	ginx.Dangerous(err)
 
-	list, err := models.TargetGets(rt.Ctx, bgid, dsIds, query, limit, ginx.Offset(c, limit))
+	list, err := models.TargetGets(rt.Ctx, bgids, dsIds, query, downtime, limit, ginx.Offset(c, limit))
 	ginx.Dangerous(err)
 
 	if err == nil {
@@ -61,6 +81,12 @@ func (rt *Router) targetGets(c *gin.Context) {
 		for i := 0; i < len(list); i++ {
 			ginx.Dangerous(list[i].FillGroup(rt.Ctx, cache))
 			keys = append(keys, models.WrapIdent(list[i].Ident))
+
+			if now.Unix()-list[i].UpdateAt < 60 {
+				list[i].TargetUp = 2
+			} else if now.Unix()-list[i].UpdateAt < 180 {
+				list[i].TargetUp = 1
+			}
 		}
 
 		if len(keys) > 0 {
@@ -80,10 +106,6 @@ func (rt *Router) targetGets(c *gin.Context) {
 			}
 
 			for i := 0; i < len(list); i++ {
-				if now.Unix()-list[i].UpdateAt < 120 {
-					list[i].TargetUp = 1
-				}
-
 				if meta, ok := metaMap[list[i].Ident]; ok {
 					list[i].FillMeta(meta)
 				} else {
@@ -101,6 +123,11 @@ func (rt *Router) targetGets(c *gin.Context) {
 	}, nil)
 }
 
+func (rt *Router) targetGetsByService(c *gin.Context) {
+	lst, err := models.TargetGetsAll(rt.Ctx)
+	ginx.NewRender(c).Data(lst, err)
+}
+
 func (rt *Router) targetGetTags(c *gin.Context) {
 	idents := ginx.QueryStr(c, "idents", "")
 	idents = strings.ReplaceAll(idents, ",", " ")

center/router/router_task.go

@@ -92,6 +92,7 @@ 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")
@@ -120,6 +121,12 @@ func (f *taskForm) HandleFH(fh string) {
 	f.Title = f.Title + " FH: " + fh
 }
 
+func (rt *Router) taskRecordAdd(c *gin.Context) {
+	var f *models.TaskRecord
+	ginx.BindJSON(c, &f)
+	ginx.NewRender(c).Message(f.Add(rt.Ctx))
+}
+
 func (rt *Router) taskAdd(c *gin.Context) {
 	var f taskForm
 	ginx.BindJSON(c, &f)

center/router/router_task_tpl.go

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

center/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

@@ -12,19 +12,8 @@ import (
 )
 
 func (rt *Router) userFindAll(c *gin.Context) {
-	limit := ginx.QueryInt(c, "limit", 20)
-	query := ginx.QueryStr(c, "query", "")
-
-	total, err := models.UserTotal(rt.Ctx, query)
-	ginx.Dangerous(err)
-
-	list, err := models.UserGets(rt.Ctx, query, limit, ginx.Offset(c, limit))
-	ginx.Dangerous(err)
-
-	ginx.NewRender(c).Data(gin.H{
-		"list":  list,
-		"total": total,
-	}, nil)
+	list, err := models.UserGetAll(rt.Ctx)
+	ginx.NewRender(c).Data(list, err)
 }
 
 func (rt *Router) userGets(c *gin.Context) {

center/router/router_user_group.go

@@ -29,6 +29,17 @@ func (rt *Router) userGroupGets(c *gin.Context) {
 	ginx.NewRender(c).Data(lst, err)
 }
 
+func (rt *Router) userGroupGetsByService(c *gin.Context) {
+	lst, err := models.UserGroupGetAll(rt.Ctx)
+	ginx.NewRender(c).Data(lst, err)
+}
+
+// user group member get by service
+func (rt *Router) userGroupMemberGetsByService(c *gin.Context) {
+	members, err := models.UserGroupMemberGetAll(rt.Ctx)
+	ginx.NewRender(c).Data(members, err)
+}
+
 type userGroupForm struct {
 	Name string `json:"name" binding:"required"`
 	Note string `json:"note"`

center/router/router_user_variable_config.go

@@ -0,0 +1,45 @@
+package router
+
+import (
+	"strings"
+
+	"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
+	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)
+	//update external config. needs to make sure not plaintext for an encrypted type config
+	//updating with struct it will update all fields ("ckey", "cval", "note", "encrypted"), not non-zero fields.
+	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)
+
+	if configs != nil && configs.External == models.ConfigExternal {
+		ginx.NewRender(context).Message(models.ConfigsDel(rt.Ctx, []int64{id}))
+	} else {
+		ginx.NewRender(context).Message(nil)
+	}
+}

center/sso/init.go

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

cli/upgrade/upgrade.go

@@ -18,9 +18,9 @@ func Upgrade(configFile string) error {
 		return err
 	}
 
-	ctx := ctx.NewContext(context.Background(), db)
+	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

@@ -8,12 +8,18 @@ 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';
 
 alter table `chart_share` add datasource_id bigint unsigned not null default 0;
-alter table `chart_share` drop dashboard_id;
 
 alter table `alert_rule` add datasource_ids varchar(255) not null default '';
 alter table `alert_rule` add rule_config text not null comment 'rule_config';

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 +1,80 @@
+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 {
+		alertStats := astats.NewSyncStats()
+		dsCache := memsto.NewDatasourceCache(ctx, syncStats)
+		alertMuteCache := memsto.NewAlertMuteCache(ctx, syncStats)
+		alertRuleCache := memsto.NewAlertRuleCache(ctx, syncStats)
+		notifyConfigCache := memsto.NewNotifyConfigCache(ctx)
+		userCache := memsto.NewUserCache(ctx, syncStats)
+		userGroupCache := memsto.NewUserGroupCache(ctx, syncStats)
+
+		promClients := prom.NewPromClient(ctx, config.Alert.Heartbeat)
+		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

@@ -2,6 +2,7 @@ package conf
 
 import (
 	"fmt"
+	"net"
 	"os"
 	"strings"
 
@@ -16,17 +17,25 @@ import (
 )
 
 type ConfigType struct {
-	Global GlobalConfig
-	Log    logx.Config
-	HTTP   httpx.Config
-	DB     ormx.DBConfig
-	Redis  storage.RedisConfig
+	Global    GlobalConfig
+	Log       logx.Config
+	HTTP      httpx.Config
+	DB        ormx.DBConfig
+	Redis     storage.RedisConfig
+	CenterApi CenterApi
 
 	Pushgw pconf.Pushgw
 	Alert  aconf.Alert
 	Center cconf.Center
 }
 
+type CenterApi struct {
+	Addrs         []string
+	BasicAuthUser string
+	BasicAuthPass string
+	Timeout       int64
+}
+
 type GlobalConfig struct {
 	RunMode string
 }
@@ -39,7 +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)
@@ -49,28 +58,36 @@ func InitConfig(configDir, cryptoKey string) (*ConfigType, error) {
 
 	if config.Alert.Heartbeat.IP == "" {
 		// auto detect
-		// config.Alert.Heartbeat.IP = fmt.Sprint(GetOutboundIP())
-		// 自动获取IP在有些环境下容易出错，这里用hostname+pid来作唯一标识
+		config.Alert.Heartbeat.IP = fmt.Sprint(GetOutboundIP())
+		if config.Alert.Heartbeat.IP == "" {
+			hostname, err := os.Hostname()
+			if err != nil {
+				fmt.Println("failed to get hostname:", err)
+				os.Exit(1)
+			}
 
-		hostname, err := os.Hostname()
-		if err != nil {
-			fmt.Println("failed to get hostname:", err)
-			os.Exit(1)
+			if strings.Contains(hostname, "localhost") {
+				fmt.Println("Warning! hostname contains substring localhost, setting a more unique hostname is recommended")
+			}
+
+			config.Alert.Heartbeat.IP = hostname
 		}
-
-		if strings.Contains(hostname, "localhost") {
-			fmt.Println("Warning! hostname contains substring localhost, setting a more unique hostname is recommended")
-		}
-
-		config.Alert.Heartbeat.IP = hostname
-
-		// if config.Alert.Heartbeat.IP == "" {
-		// 	fmt.Println("heartbeat ip auto got is blank")
-		// 	os.Exit(1)
-		// }
 	}
 
 	config.Alert.Heartbeat.Endpoint = fmt.Sprintf("%s:%d", config.Alert.Heartbeat.IP, config.HTTP.Port)
 
 	return config, nil
 }
+
+func GetOutboundIP() net.IP {
+	conn, err := net.Dial("udp", "223.5.5.5:80")
+	if err != nil {
+		fmt.Println("auto get outbound ip fail:", err)
+		return []byte{}
+	}
+	defer conn.Close()
+
+	localAddr := conn.LocalAddr().(*net.UDPAddr)
+
+	return localAddr.IP
+}

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/README.bak.md

@@ -0,0 +1,147 @@
+<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">
+  <b>All-in-one</b> 的开源观测平台 <br/>
+  <b>开箱即用</b>，集数据采集、可视化、监控告警于一体 <br/>
+  推荐升级您的 <b>Prometheus + AlertManager + Grafana + ELK + Jaeger</b> 组合方案到夜莺！
+</p>
+
+[English](./README_en.md) | [中文](./README.md)
+
+
+
+## 功能和特点
+
+- **开箱即用**
+  - 支持 Docker、Helm Chart、云服务等多种部署方式，集数据采集、监控告警、可视化为一体，内置多种监控仪表盘、快捷视图、告警规则模板，导入即可快速使用，**大幅降低云原生监控系统的建设成本、学习成本、使用成本**；
+- **专业告警**
+  - 可视化的告警配置和管理，支持丰富的告警规则，提供屏蔽规则、订阅规则的配置能力，支持告警多种送达渠道，支持告警自愈、告警事件管理等；
+  - **推荐您使用夜莺的同时，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、协同，让告警的触达既高效，又确保告警处理不遗漏、做到件件有回响**。
+- **云原生**
+  - 以交钥匙的方式快速构建企业级的云原生监控体系，支持 [Categraf](https://github.com/flashcatcloud/categraf)、Telegraf、Grafana-agent 等多种采集器，支持 Prometheus、VictoriaMetrics、M3DB、ElasticSearch、Jaeger 等多种数据源，兼容支持导入 Grafana 仪表盘，**与云原生生态无缝集成**；
+- **高性能 高可用**
+  - 得益于夜莺的多数据源管理引擎，和夜莺引擎侧优秀的架构设计，借助于高性能时序库，可以满足数亿时间线的采集、存储、告警分析场景，节省大量成本；
+  - 夜莺监控组件均可水平扩展，无单点，已在上千家企业部署落地，经受了严苛的生产实践检验。众多互联网头部公司，夜莺集群机器达百台，处理数亿级时间线，重度使用夜莺监控；
+- **灵活扩展 中心化管理**
+  - 夜莺监控，可部署在 1 核 1G 的云主机，可在上百台机器集群化部署，可运行在 K8s 中；也可将时序库、告警引擎等组件下沉到各机房、各 Region，兼顾边缘部署和中心化统一管理，**解决数据割裂，缺乏统一视图的难题**；
+- **开放社区**
+  - 托管于[中国计算机学会开源发展委员会](https://www.ccf.org.cn/kyfzwyh/)，有[快猫星云](https://flashcat.cloud)和众多公司的持续投入，和数千名社区用户的积极参与，以及夜莺监控项目清晰明确的定位，都保证了夜莺开源社区健康、长久的发展。活跃、专业的社区用户也在持续迭代和沉淀更多的最佳实践于产品中；
+
+## 使用场景
+1. **如果您希望在一个平台中，统一管理和查看 Metrics、Logging、Tracing 数据，推荐你使用夜莺**：
+   - 请参考阅读：[不止于监控，夜莺 V6 全新升级为开源观测平台](http://flashcat.cloud/blog/nightingale-v6-release/)
+2. **如果您在使用 Prometheus 过程中，有以下的一个或者多个需求场景，推荐您无缝升级到夜莺**：
+   - Prometheus、Alertmanager、Grafana 等多个系统较为割裂，缺乏统一视图，无法开箱即用;
+   - 通过修改配置文件来管理 Prometheus、Alertmanager 的方式，学习曲线大，协同有难度;
+   - 数据量过大而无法扩展您的 Prometheus 集群；
+   - 生产环境运行多套 Prometheus 集群，面临管理和使用成本高的问题；
+3. **如果您在使用 Zabbix，有以下的场景，推荐您升级到夜莺**：
+   - 监控的数据量太大，希望有更好的扩展解决方案；
+   - 学习曲线高，多人多团队模式下，希望有更好的协同使用效率；
+   - 微服务和云原生架构下，监控数据的生命周期多变、监控数据维度基数高，Zabbix 数据模型不易适配；
+   - 了解更多Zabbix和夜莺监控的对比，推荐您进一步阅读[Zabbix 和夜莺监控选型对比](https://flashcat.cloud/blog/zabbx-vs-nightingale/)
+4. **如果您在使用 [Open-Falcon](https://github.com/open-falcon/falcon-plus)，我们推荐您升级到夜莺：**
+   - 关于 Open-Falcon 和夜莺的详细介绍，请参考阅读：[云原生监控的十个特点和趋势](http://flashcat.cloud/blog/10-trends-of-cloudnative-monitoring/)
+   - 监控系统和可观测平台的区别，请参考阅读：[从监控系统到可观测平台，Gap有多大
+](https://flashcat.cloud/blog/gap-of-monitoring-to-o11y/)
+5. **我们推荐您使用 [Categraf](https://github.com/flashcatcloud/categraf) 作为首选的监控数据采集器**：
+   - [Categraf](https://github.com/flashcatcloud/categraf) 是夜莺监控的默认采集器，采用开放插件机制和 All-in-one 的设计理念，同时支持 metric、log、trace、event 的采集。Categraf 不仅可以采集 CPU、内存、网络等系统层面的指标，也集成了众多开源组件的采集能力，支持K8s生态。Categraf 内置了对应的仪表盘和告警规则，开箱即用。
+
+## 文档
+
+[English Doc](https://n9e.github.io/) |  [中文文档](https://flashcat.cloud/docs/)
+
+## 产品示意图
+
+https://user-images.githubusercontent.com/792850/216888712-2565fcea-9df5-47bd-a49e-d60af9bd76e8.mp4
+
+## 夜莺架构
+
+夜莺监控可以接收各种采集器上报的监控数据（比如 [Categraf](https://github.com/flashcatcloud/categraf)、telegraf、grafana-agent、Prometheus），并写入多种流行的时序数据库中（可以支持Prometheus、M3DB、VictoriaMetrics、Thanos、TDEngine等），提供告警规则、屏蔽规则、订阅规则的配置能力，提供监控数据的查看能力，提供告警自愈机制（告警触发之后自动回调某个webhook地址或者执行某个脚本），提供历史告警事件的存储管理、分组查看的能力。
+
+### 中心汇聚式部署方案
+
+![中心汇聚式部署方案](https://download.flashcat.cloud/ulric/20230327133406.png)
+
+夜莺只有一个模块，就是 n9e，可以部署多个 n9e 实例组成集群，n9e 依赖 2 个存储，数据库、Redis，数据库可以使用 MySQL 或 Postgres，自己按需选用。
+
+n9e 提供的是 HTTP 接口，前面负载均衡可以是 4 层的，也可以是 7 层的。一般就选用 Nginx 就可以了。
+
+n9e 这个模块接收到数据之后，需要转发给后端的时序库，相关配置是：
+
+```toml
+[Pushgw]
+LabelRewrite = true
+[[Pushgw.Writers]] 
+Url = "http://127.0.0.1:9090/api/v1/write"
+```
+
+> 注意：虽然数据源可以在页面配置了，但是上报转发链路，还是需要在配置文件指定。
+
+所有机房的 agent（ 比如 Categraf、Telegraf、 Grafana-agent、Datadog-agent ），都直接推数据给 n9e，这个架构最为简单，维护成本最低。当然，前提是要求机房之间网络链路比较好，一般有专线。如果网络链路不好，则要使用下面的部署方式了。
+
+### 边缘下沉式混杂部署方案
+
+![边缘下沉式混杂部署方案](https://download.flashcat.cloud/ulric/20230327135615.png)
+
+这个图尝试解释 3 种不同的情形，比如 A 机房和中心网络链路很好，Categraf 可以直接汇报数据给中心 n9e 模块，另一个机房网络链路不好，就需要把时序库下沉部署，时序库下沉了，对应的告警引擎和转发网关也都要跟随下沉，这样数据不会跨机房传输，比较稳定。但是心跳还是需要往中心心跳，要不然在对象列表里看不到机器的 CPU、内存使用率。还有的时候，可能是接入的一个已有的 Prometheus，数据采集没有走 Categraf，那此时只需要把 Prometheus 作为数据源接入夜莺即可，可以在夜莺里看图、配告警规则，但是就是在对象列表里看不到，也不能使用告警自愈的功能，问题也不大，核心功能都不受影响。
+
+边缘机房，下沉部署时序库、告警引擎、转发网关的时候，要注意，告警引擎需要依赖数据库，因为要同步告警规则，转发网关也要依赖数据库，因为要注册对象到数据库里去，需要打通相关网络，告警引擎和转发网关都不用Redis，所以无需为 Redis 打通网络。 
+
+### VictoriaMetrics 集群架构
+<img src="doc/img/install-vm.png" width="600">
+
+如果单机版本的时序数据库（比如 Prometheus） 性能有瓶颈或容灾较差，我们推荐使用 [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics)，VictoriaMetrics 架构较为简单，性能优异，易于部署和运维，架构图如上。VictoriaMetrics 更详尽的文档，还请参考其[官网](https://victoriametrics.com/)。
+
+## 夜莺社区
+
+开源项目要更有生命力，离不开开放的治理架构和源源不断的开发者和用户共同参与，我们致力于建立开放、中立的开源治理架构，吸纳更多来自企业、高校等各方面对云原生监控感兴趣、有热情的开发者，一起打造有活力的夜莺开源社区。关于《夜莺开源项目和社区治理架构（草案）》，请查阅 [COMMUNITY GOVERNANCE](./doc/community-governance.md).
+
+**我们欢迎您以各种方式参与到夜莺开源项目和开源社区中来，工作包括不限于**：
+- 补充和完善文档 => [n9e.github.io](https://n9e.github.io/)
+- 分享您在使用夜莺监控过程中的最佳实践和经验心得 => [文章分享](https://flashcat.cloud/docs/content/flashcat-monitor/nightingale/share/)
+- 提交产品建议 =》 [github issue](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Ffeature&template=enhancement.md)
+- 提交代码，让夜莺监控更快、更稳、更好用 => [github pull request](https://github.com/didi/nightingale/pulls)
+
+**尊重、认可和记录每一位贡献者的工作**是夜莺开源社区的第一指导原则，我们提倡**高效的提问**，这既是对开发者时间的尊重，也是对整个社区知识沉淀的贡献：
+- 提问之前请先查阅 [FAQ](https://www.gitlink.org.cn/ccfos/nightingale/wiki/faq) 
+- 我们使用[论坛](https://answer.flashcat.cloud/)进行交流，有问题可以到这里搜索、提问
+
+
+## Who is using Nightingale
+
+您可以通过在 **[Who is Using Nightingale](https://github.com/ccfos/nightingale/issues/897)** 登记您的使用情况，分享您的使用经验。
+
+## 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)
+
+## 加入交流群
+
+<img src="doc/img/wecom.png" width="120">

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

@@ -4,8 +4,7 @@ FROM python:3-slim
 WORKDIR /app
 ADD n9e /app
 ADD http://download.flashcat.cloud/wait /wait
-RUN mkdir -p /app/pub && chmod +x /wait
-ADD pub /app/pub/
+RUN chmod +x /wait
 RUN chmod +x n9e
 
 EXPOSE 17000

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
-ADD pub /app/pub/
+RUN pip install requests
 
 EXPOSE 17000
 

docker/Dockerfile.goreleaser.arm64

@@ -5,8 +5,6 @@ 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_aarch64 /wait
-ADD pub /app/pub/
 
 EXPOSE 17000
 

docker/build.sh

@@ -10,7 +10,6 @@ echo "tag: ${tag}"
 
 rm -rf n9e pub
 cp ../n9e .
-cp -r ../pub .
 
 docker build -t nightingale:${tag} .
 

docker/categraf/conf/input.kernel_vmstat/kernel_vmstat.toml

@@ -1,124 +0,0 @@
-# # collect interval
-# interval = 15
-
-# file: /proc/vmstat
-[white_list]
-oom_kill = 1
-nr_free_pages = 0
-nr_alloc_batch = 0
-nr_inactive_anon = 0
-nr_active_anon = 0
-nr_inactive_file = 0
-nr_active_file = 0
-nr_unevictable = 0
-nr_mlock = 0
-nr_anon_pages = 0
-nr_mapped = 0
-nr_file_pages = 0
-nr_dirty = 0
-nr_writeback = 0
-nr_slab_reclaimable = 0
-nr_slab_unreclaimable = 0
-nr_page_table_pages = 0
-nr_kernel_stack = 0
-nr_unstable = 0
-nr_bounce = 0
-nr_vmscan_write = 0
-nr_vmscan_immediate_reclaim = 0
-nr_writeback_temp = 0
-nr_isolated_anon = 0
-nr_isolated_file = 0
-nr_shmem = 0
-nr_dirtied = 0
-nr_written = 0
-numa_hit = 0
-numa_miss = 0
-numa_foreign = 0
-numa_interleave = 0
-numa_local = 0
-numa_other = 0
-workingset_refault = 0
-workingset_activate = 0
-workingset_nodereclaim = 0
-nr_anon_transparent_hugepages = 0
-nr_free_cma = 0
-nr_dirty_threshold = 0
-nr_dirty_background_threshold = 0
-pgpgin = 0
-pgpgout = 0
-pswpin = 0
-pswpout = 0
-pgalloc_dma = 0
-pgalloc_dma32 = 0
-pgalloc_normal = 0
-pgalloc_movable = 0
-pgfree = 0
-pgactivate = 0
-pgdeactivate = 0
-pgfault = 0
-pgmajfault = 0
-pglazyfreed = 0
-pgrefill_dma = 0
-pgrefill_dma32 = 0
-pgrefill_normal = 0
-pgrefill_movable = 0
-pgsteal_kswapd_dma = 0
-pgsteal_kswapd_dma32 = 0
-pgsteal_kswapd_normal = 0
-pgsteal_kswapd_movable = 0
-pgsteal_direct_dma = 0
-pgsteal_direct_dma32 = 0
-pgsteal_direct_normal = 0
-pgsteal_direct_movable = 0
-pgscan_kswapd_dma = 0
-pgscan_kswapd_dma32 = 0
-pgscan_kswapd_normal = 0
-pgscan_kswapd_movable = 0
-pgscan_direct_dma = 0
-pgscan_direct_dma32 = 0
-pgscan_direct_normal = 0
-pgscan_direct_movable = 0
-pgscan_direct_throttle = 0
-zone_reclaim_failed = 0
-pginodesteal = 0
-slabs_scanned = 0
-kswapd_inodesteal = 0
-kswapd_low_wmark_hit_quickly = 0
-kswapd_high_wmark_hit_quickly = 0
-pageoutrun = 0
-allocstall = 0
-pgrotated = 0
-drop_pagecache = 0
-drop_slab = 0
-numa_pte_updates = 0
-numa_huge_pte_updates = 0
-numa_hint_faults = 0
-numa_hint_faults_local = 0
-numa_pages_migrated = 0
-pgmigrate_success = 0
-pgmigrate_fail = 0
-compact_migrate_scanned = 0
-compact_free_scanned = 0
-compact_isolated = 0
-compact_stall = 0
-compact_fail = 0
-compact_success = 0
-htlb_buddy_alloc_success = 0
-htlb_buddy_alloc_fail = 0
-unevictable_pgs_culled = 0
-unevictable_pgs_scanned = 0
-unevictable_pgs_rescued = 0
-unevictable_pgs_mlocked = 0
-unevictable_pgs_munlocked = 0
-unevictable_pgs_cleared = 0
-unevictable_pgs_stranded = 0
-thp_fault_alloc = 0
-thp_fault_fallback = 0
-thp_collapse_alloc = 0
-thp_collapse_alloc_failed = 0
-thp_split = 0
-thp_zero_page_alloc = 0
-thp_zero_page_alloc_failed = 0
-balloon_inflate = 0
-balloon_deflate = 0
-balloon_migrate = 0

docker/compose-bridge/docker-compose.yaml

@@ -0,0 +1,131 @@
+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 "/wait && /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
+    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"
+]