Compare commits

...

105 Commits

Author SHA1 Message Date
ning
73f9548242 Merge branch 'main' of github.com:ccfos/nightingale 2024-08-13 10:59:39 +08:00
ning
7c91e51c08 fix: edge record notify 2024-08-13 10:59:17 +08:00
qinguoyi
a4867c406d fix:get configcache return nil need exit (#2094) 2024-08-12 19:52:22 +08:00
qinguoyi
bfea83ae75 fix: alert_cur_event return unmarshal json err (#2090) 2024-08-12 13:06:58 +08:00
Yening Qin
7a2832c377 fix: process recover duration (#2092) 2024-08-12 13:04:08 +08:00
ning
3f6c54a712 refactor: subscribe not run ibex and script 2024-08-09 17:42:48 +08:00
Yening Qin
1bb590ce6d feat: support record event notify detail (#2088)
* feat: record alert notification (#2045)

* record notification

---------

Co-authored-by: wenbo <bupt.lwb@gmail.com>
Co-authored-by: wenbo <1027758873@qq.com>
2024-08-09 17:06:49 +08:00
ning
656326458f refactor: event add task tpl name 2024-08-08 22:41:51 +08:00
Yening Qin
c6ab3ad2b3 feat: alert rule support import promethues alert rule (#2080) (#2085)
Co-authored-by: flashbo <36443248+lwb0214@users.noreply.github.com>
2024-08-07 16:05:10 +08:00
Yening Qin
d050cf72e9 Update elasticsearch_by_categraf.json 2024-08-06 16:42:49 +08:00
ning
084cc1893e docs: update migrate sql 2024-08-06 14:54:40 +08:00
Yening Qin
cd01123b59 feat: alert rule support add task tpl (#2079) 2024-08-05 17:54:23 +08:00
ning
23ce84d41c refactor: optimize event relabel process 2024-08-05 11:43:21 +08:00
Yening Qin
4764cc2419 feat: alert rule batch update support annotations (#2074)
* feat: batch update annotation (#2072)

* fix: annotations_del

---------

Co-authored-by: Xu Bin <140785332+Reditiny@users.noreply.github.com>
2024-08-02 13:05:11 +08:00
ning
da66401576 docs: update tpl doc 2024-08-02 11:17:53 +08:00
ning
0024c9d99c docs: add migrate sql 2024-08-01 18:56:16 +08:00
flashbo
96d3b48f10 feat: target add os type (#2071) 2024-08-01 17:08:59 +08:00
Yening Qin
6a0e7a810f refactor: webhook notify support batch send events (#2070) 2024-08-01 15:25:39 +08:00
Yening Qin
5b2513b7a1 feat: support lark and larkcard notify channel (#2061)
* feat: support lark notify channel (#2056)

Co-authored-by: flashbo <36443248+lwb0214@users.noreply.github.com>
Co-authored-by: wenbo <1027758873@qq.com>
2024-07-27 21:21:43 +08:00
ning
7cec16eaf0 update center router init 2024-07-26 14:59:40 +08:00
ning
17dbb3ec77 code refactor 2024-07-25 12:06:10 +08:00
ning
00822c8404 refactor: add ibex enable check 2024-07-25 11:39:43 +08:00
ning
55de30d6c7 refactor: update mute rule api 2024-07-24 11:37:38 +08:00
Yening Qin
8b7dbed27e refactor: modify heartbeat api (#2051) 2024-07-24 11:23:56 +08:00
Dan218
71b8fa27d0 feat: Provide optional style for buildTargetWhere (#2038) 2024-07-24 11:12:17 +08:00
ning
31174d719e refactor: event relabel 2024-07-22 11:45:17 +08:00
ning
5b5bb22ffd fix: event relable process tagsmap 2024-07-22 10:46:29 +08:00
ning
e98fe9ea2e refactor: HandleTSFunc 2024-07-21 15:28:06 +08:00
ning
32e9ded393 refactor: server-clusters api perm 2024-07-21 11:04:35 +08:00
ning
8293ca20be refactor: assets file support md 2024-07-18 15:07:47 +08:00
Yening Qin
6c4ddfc349 refactor: update languageDetector (#2043) 2024-07-18 14:13:48 +08:00
ning
cd0c478515 refactor: event relabel add default value 2024-07-17 22:48:50 +08:00
Yening Qin
2cd25ac0e5 fix: optimize event recovery inhibit (#2042) 2024-07-17 22:30:31 +08:00
ning
bb99ba3d1c update sql 2024-07-17 11:57:20 +08:00
Yening Qin
64405dca5d feat: alert event support relabel (#2041) 2024-07-17 10:30:29 +08:00
ulricqin
69ea9ca8f8 Update README.md 2024-07-17 09:39:00 +08:00
ulricqin
41d0f2fcda Update README.md 2024-07-17 09:36:30 +08:00
710leo
93df1c0fbc docs: add perm point 2024-07-16 23:44:30 +08:00
flashbo
86e952788d refactor: targets get api support backend sorting (#2034)
Co-authored-by: wenbo <bupt.lwb@gmail.com>
2024-07-16 23:38:04 +08:00
ning
e890f2616f refactor: change webhook sleep time 2024-07-13 14:38:32 +08:00
yanli
6c2ee584e5 refactor: MetricDesc defaults to Chinese (#2032) 2024-07-12 21:50:51 +08:00
Dan218
5f07fc3010 Feat: Add skip Verify Insecure ssl/tls in sendWebhook (#2030) 2024-07-12 10:38:33 +08:00
ning
20fa310ba9 refactor: sync team to duty 2024-07-08 17:54:59 +08:00
ning
0e3b08be9a feat: ldap support defaultTeams 2024-07-08 17:35:39 +08:00
ning
b7d971d7c8 refactor: add alert rule pure api 2024-07-08 17:10:31 +08:00
ning
4373ae7f0b code refactor 2024-07-05 10:40:27 +08:00
dependabot[bot]
053325a691 build(deps): bump golang.org/x/image from 0.13.0 to 0.18.0 (#2017) 2024-07-04 17:56:36 +08:00
ning
c54267aa3a refactor: webhook support retry 2024-07-04 17:49:16 +08:00
ning
74dc430886 add migrate sql 2024-07-04 15:45:22 +08:00
Yening Qin
dc79ee4687 feat: recording rule support cron pattern (#2025) 2024-07-04 11:23:48 +08:00
shardingHe
e154c946e6 docs: add dashboard for aliyun-mysql (#2020)
* add dashboard for aliyun-mysql

* Update mysql.json

---------

Co-authored-by: shardingHe <wangzihe@flashcat.cloud>
Co-authored-by: ulricqin <ulricqin@qq.com>
2024-07-03 11:41:50 +08:00
ning
08bfc0b388 refactor: add callbak log 2024-07-01 15:15:19 +08:00
ning
5338270aef feat: encrypt pass 2024-06-27 17:07:19 +08:00
Ulric Qin
00550ba2c7 add redis dashboard 2024-06-27 10:55:23 +08:00
Ulric Qin
c58bec23bf login fail count 2024-06-26 17:04:22 +08:00
ning
a5b77be0ab fix: recovered event id 2024-06-26 11:57:27 +08:00
Yening Qin
f529681c35 fix: embedded-dashboards api perm (#2012) 2024-06-25 18:13:13 +08:00
Ulric Qin
e3042dd6d5 Merge branch 'main' of github.com:ccfos/nightingale 2024-06-25 17:39:48 +08:00
Ulric Qin
1ebab4fcb0 add mysql dashboard 2024-06-25 17:39:15 +08:00
ning
ccf38b6da7 docs: update clickhouse integrations 2024-06-25 16:48:12 +08:00
Ulric Qin
9a0a687727 Merge branch 'main' of github.com:ccfos/nightingale 2024-06-25 16:42:59 +08:00
Ulric Qin
d00510978d add mysql dashboard 2024-06-25 16:42:40 +08:00
ning
9b478d98fd refactor: checkout heartbeat global label 2024-06-25 15:09:29 +08:00
ning
4845ca5bdb refactor: update compose sql 2024-06-22 00:33:45 +08:00
Yening Qin
a844d2b091 fix: use postgresql (#2008) 2024-06-21 18:13:58 +08:00
Ulric Qin
69ca7f3b93 validate heartbeat hostname 2024-06-21 17:51:44 +08:00
Ulric Qin
b9c6c33ceb refactor extractIdentFromTimeSeries 2024-06-21 17:43:43 +08:00
Ulric Qin
5099d3c040 add ignore_host querystring 2024-06-21 12:36:45 +08:00
Ulric Qin
e34f8ac701 Merge branch 'main' of github.com:ccfos/nightingale 2024-06-21 12:25:08 +08:00
Ulric Qin
ab82a6f910 modify ignore_ident logic 2024-06-21 12:24:54 +08:00
小炒肉
57f8bd3612 feat: callbackURL Parse Template (#2001)
Co-authored-by: zhihuanzhu <zhihuanzhu@deeproute.ai>
2024-06-19 14:46:06 +08:00
ning
8ab96e2cea refactor: add more mute log 2024-06-17 19:17:51 +08:00
ning
0a2e23c285 refactor: update users api 2024-06-17 17:09:33 +08:00
小炒肉
5c1d4077e2 fix: feishucard ats (#1997)
Co-authored-by: zhihuanzhu <zhihuanzhu@deeproute.ai>
2024-06-17 15:14:27 +08:00
Zoe
2a46d9f98e docs: add clickhouse alerts,dashboards,metrics (#1994) 2024-06-17 11:28:17 +08:00
Ulric Qin
ce5c213593 Merge branch 'main' of github.com:ccfos/nightingale 2024-06-14 19:03:01 +08:00
ning
771a8d121b refactor: change recovery event last_eval_time 2024-06-14 16:13:44 +08:00
Ulric Qin
af88b0e283 Merge branch 'main' of github.com:ccfos/nightingale 2024-06-14 15:27:24 +08:00
Ulric Qin
8e5d7f2a5b update dingtalk tpl 2024-06-14 15:27:06 +08:00
Yening Qin
1a22211a5d feat: oidc support default team (#1995) 2024-06-14 12:00:21 +08:00
Yening Qin
0a0049c6fb feat: callback support send event to im and remove alert subrule callback resend (#1992)
* feat: Callback operation adds IM connection function (#1984)

* refactor: change alert sub callback

---------

Co-authored-by: Yang Zhiyan <101268302+Yziyan@users.noreply.github.com>
2024-06-14 00:38:02 +08:00
Ulric Qin
1b56ebe62e Merge branch 'main' of github.com:ccfos/nightingale 2024-06-13 15:54:39 +08:00
Ulric Qin
a5e92b95b0 add link in github issue template 2024-06-13 15:54:24 +08:00
ulricqin
8e9d06d43e Update README.md 2024-06-13 15:03:04 +08:00
Ulric Qin
ab289de785 update github issue template 2024-06-13 12:32:47 +08:00
Ulric Qin
8667b7743a Merge branch 'main' of github.com:ccfos/nightingale 2024-06-13 12:21:10 +08:00
Ulric Qin
45b9436f69 update github issue template 2024-06-13 12:20:56 +08:00
ning
3d03bcf329 docs: add perm point 2024-06-11 19:10:04 +08:00
ning
1851601889 refactor: get usergroups service api 2024-06-07 20:07:13 +08:00
ning
fa9745decf refactor: update event api 2024-06-06 17:55:08 +08:00
ning
6f007deeaa refactor: change get list api 2024-06-06 16:42:17 +08:00
ning
8fad705065 fix: edge alert use ibex 2024-06-06 16:07:18 +08:00
ning
675076779e refactor: ibex migrate add charset 2024-06-06 12:13:22 +08:00
710leo
b9e78eee22 docs: change action 2024-06-05 22:26:26 +08:00
710leo
2219584abb docs: change action 2024-06-05 22:16:42 +08:00
710leo
ebe31fd6bc docs: change action 2024-06-05 22:12:12 +08:00
nīng
95ca69e170 docs: change action 2024-06-05 22:04:56 +08:00
nīng
ef1b5d8d16 docs: change action 2024-06-05 21:51:23 +08:00
ning
5b375cf037 docs: change action 2024-06-05 19:42:39 +08:00
ning
108b729cae Merge branch 'main' of github.com:ccfos/nightingale 2024-06-05 18:11:44 +08:00
ning
a385972fa9 refactor: add some i18n 2024-06-05 18:11:31 +08:00
yuweizzz
98a0a9d94c feat: support sqlite (#1978)
* demo sqlite
2024-06-05 17:28:56 +08:00
ning
c79eec648d fix: n9e-edge ibex 2024-06-05 17:12:52 +08:00
Yening Qin
603eadd1f2 feat: alert event support recovery value (#1982)
* feature: the alert response event supports query recovery values (#1975)

* refactor: rule note use

---------

Co-authored-by: Yang Zhiyan <101268302+Yziyan@users.noreply.github.com>
2024-06-05 17:01:31 +08:00
Yening Qin
61a2f552be refactor: integration init (#1981) 2024-06-05 15:14:01 +08:00
271 changed files with 122563 additions and 92058 deletions

View File

@@ -1,67 +0,0 @@
name: Bug Report
description: Report a bug encountered while running Nightingale
labels: ["kind/bug"]
body:
- type: markdown
attributes:
value: |
Thanks for taking time to fill out this bug report!
The more detailed the form is filled in, the easier the problem will be solved.
- type: textarea
id: config
attributes:
label: Your config.toml
description: Place config in the toml code section. This will be automatically formatted into toml, so no need for backticks.
render: toml
validations:
required: true
- type: textarea
id: logs
attributes:
label: Relevant logs
description: categraf | telegraf | n9e | prometheus | chrome request/response ...
render: text
validations:
required: true
- type: input
id: system-info
attributes:
label: System info
description: Include nightingale version, operating system, and other relevant details
placeholder: ex. n9e 5.9.2, n9e-fe 5.5.0, categraf 0.1.0, Ubuntu 20.04, Docker 20.10.8
validations:
required: true
- type: textarea
id: reproduce
attributes:
label: Steps to reproduce
description: Describe the steps to reproduce the bug.
value: |
1.
2.
3.
...
validations:
required: true
- type: textarea
id: expected-behavior
attributes:
label: Expected behavior
description: Describe what you expected to happen when you performed the above steps.
validations:
required: true
- type: textarea
id: actual-behavior
attributes:
label: Actual behavior
description: Describe what actually happened when you performed the above steps.
validations:
required: true
- type: textarea
id: additional-info
attributes:
label: Additional info
description: Include gist of relevant config, logs, etc.
validations:
required: false

33
.github/ISSUE_TEMPLATE/question.yml vendored Normal file
View File

@@ -0,0 +1,33 @@
name: Bug Report & Usage Question
description: Reporting a bug or asking a question about how to use Nightingale
labels: []
body:
- type: markdown
attributes:
value: |
The more detailed the form is filled in, the easier the problem will be solved.
提供的信息越详细,问题解决的可能性就越大。另外, 提问之前请先搜索历史 issue (包括 close 的), 以免重复提问。
- type: textarea
id: question
attributes:
label: Question and Steps to reproduce
description: Describe your question and steps to reproduce the bug. 描述问题以及复现步骤
validations:
required: true
- type: textarea
id: logs
attributes:
label: Relevant logs and configurations
description: Relevant logs and configurations. 报错日志([查看方法](https://flashcat.cloud/docs/content/flashcat-monitor/nightingale-v6/faq/how-to-check-logs/))以及各个相关组件的配置信息
render: text
validations:
required: true
- type: textarea
id: system-info
attributes:
label: Version
description: Include nightingale version, operating system, and other relevant details. 请告知夜莺的版本、操作系统的版本、CPU架构等信息
validations:
required: true

View File

@@ -26,7 +26,8 @@ jobs:
- name: Run GoReleaser
uses: goreleaser/goreleaser-action@v3
with:
version: latest
distribution: goreleaser
version: '~> v1'
args: release --rm-dist
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

View File

@@ -36,7 +36,7 @@
## 快速开始
- 👉[文档中心](https://flashcat.cloud/docs/) | [下载中心](https://flashcat.cloud/download/nightingale/)
- ❤️[报告 Bug](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&projects=&template=bug_report.yml)
- ❤️[报告 Bug](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=&projects=&template=question.yml)
- ℹ️为了提供更快速的访问体验,上述文档和下载站点托管于 [FlashcatCloud](https://flashcat.cloud)
## 功能特点
@@ -78,22 +78,12 @@
![边缘部署模式](https://download.flashcat.cloud/ulric/20240222102119.png)
## 近期计划
- [ ] 仪表盘:支持内嵌 Grafana
- [ ] 告警规则:通知时支持配置过滤标签,避免告警事件中一堆不重要的标签
- [ ] 告警规则:支持配置恢复时的 Promql告警恢复通知也可以带上恢复时的值了
- [ ] 机器管理自定义标签拆分管理agent 自动上报的标签和用户在页面自定义的标签分开管理,对于 agent 自动上报的标签,以 agent 为准,直接覆盖服务端 DB 中的数据
- [ ] 机器管理:机器支持角色字段,即无头标签,用于描述混部场景
- [ ] 机器管理:把业务组的 busigroup 标签迁移到机器的属性里,让机器支持挂到多个业务组
- [ ] 告警规则:增加 Host Metrics 类别,支持按照业务组、角色、标签等筛选机器,规则 promql 支持变量,支持在机器颗粒度配置变量值
- [ ] 告警通知:重构整个通知逻辑,引入事件处理的 pipeline支持对告警事件做自定义处理和灵活分派
## 交流渠道
- 报告Bug优先推荐提交[夜莺GitHub Issue](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&projects=&template=bug_report.yml)
- 推荐完整浏览[夜莺文档站点](https://flashcat.cloud/docs/content/flashcat-monitor/nightingale-v7/introduction/),了解更多信息
- 推荐搜索关注夜莺公众号,第一时间获取社区动态:`夜莺监控Nightingale`
- 日常答疑、技术分享、用户之间的交流,统一使用知识星球,大伙可以免费加入交流,[入口在这里](https://download.flashcat.cloud/ulric/20240319095409.png)
- 日常问题交流推荐加入[知识星球](https://download.flashcat.cloud/ulric/20240319095409.png),也可以加我微信 `picobyte`,备注:`夜莺加群-<公司>-<姓名>` 拉入微信群,不过研发人员主要是关注 github issue 和星球,微信群关注较少
## 广受关注
[![Stargazers over time](https://api.star-history.com/svg?repos=ccfos/nightingale&type=Date)](https://star-history.com/#ccfos/nightingale&Date)

View File

@@ -32,6 +32,7 @@ type Alerting struct {
Timeout int64
TemplatesDir string
NotifyConcurrency int
WebhookBatchSend bool
}
type CallPlugin struct {

View File

@@ -106,11 +106,11 @@ func Start(alertc aconf.Alert, pushgwc pconf.Pushgw, syncStats *memsto.Stats, al
busiGroupCache, alertMuteCache, datasourceCache, promClients, tdendgineClients, naming, ctx, alertStats)
dp := dispatch.NewDispatch(alertRuleCache, userCache, userGroupCache, alertSubscribeCache, targetCache, notifyConfigCache, taskTplsCache, alertc.Alerting, ctx, alertStats)
consumer := dispatch.NewConsumer(alertc.Alerting, ctx, dp)
consumer := dispatch.NewConsumer(alertc.Alerting, ctx, dp, promClients)
go dp.ReloadTpls()
go consumer.LoopConsume()
go queue.ReportQueueSize(alertStats)
go sender.InitEmailSender(notifyConfigCache)
go sender.InitEmailSender(ctx, notifyConfigCache)
}

View File

@@ -1,14 +1,19 @@
package dispatch
import (
"encoding/json"
"fmt"
"strings"
"time"
"github.com/ccfos/nightingale/v6/alert/aconf"
"github.com/ccfos/nightingale/v6/alert/common"
"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"
promsdk "github.com/ccfos/nightingale/v6/pkg/prom"
"github.com/ccfos/nightingale/v6/prom"
"github.com/toolkits/pkg/concurrent/semaphore"
"github.com/toolkits/pkg/logger"
@@ -18,15 +23,17 @@ type Consumer struct {
alerting aconf.Alerting
ctx *ctx.Context
dispatch *Dispatch
dispatch *Dispatch
promClients *prom.PromClientMap
}
// 创建一个 Consumer 实例
func NewConsumer(alerting aconf.Alerting, ctx *ctx.Context, dispatch *Dispatch) *Consumer {
func NewConsumer(alerting aconf.Alerting, ctx *ctx.Context, dispatch *Dispatch, promClients *prom.PromClientMap) *Consumer {
return &Consumer{
alerting: alerting,
ctx: ctx,
dispatch: dispatch,
alerting: alerting,
ctx: ctx,
dispatch: dispatch,
promClients: promClients,
}
}
@@ -73,17 +80,19 @@ func (e *Consumer) consumeOne(event *models.AlertCurEvent) {
event.RuleName = fmt.Sprintf("failed to parse rule name: %v", err)
}
if err := event.ParseRule("rule_note"); err != nil {
logger.Warningf("ruleid:%d failed to parse rule note: %v", event.RuleId, err)
event.RuleNote = fmt.Sprintf("failed to parse rule note: %v", err)
}
if err := event.ParseRule("annotations"); err != nil {
logger.Warningf("ruleid:%d failed to parse annotations: %v", event.RuleId, err)
event.Annotations = fmt.Sprintf("failed to parse annotations: %v", err)
event.AnnotationsJSON["error"] = event.Annotations
}
e.queryRecoveryVal(event)
if err := event.ParseRule("rule_note"); err != nil {
logger.Warningf("ruleid:%d failed to parse rule note: %v", event.RuleId, err)
event.RuleNote = fmt.Sprintf("failed to parse rule note: %v", err)
}
e.persist(event)
if event.IsRecovered && event.NotifyRecovered == 0 {
@@ -115,3 +124,68 @@ func (e *Consumer) persist(event *models.AlertCurEvent) {
e.dispatch.Astats.CounterRuleEvalErrorTotal.WithLabelValues(fmt.Sprintf("%v", event.DatasourceId), "persist_event").Inc()
}
}
func (e *Consumer) queryRecoveryVal(event *models.AlertCurEvent) {
if !event.IsRecovered {
return
}
// If the event is a recovery event, execute the recovery_promql query
promql, ok := event.AnnotationsJSON["recovery_promql"]
if !ok {
return
}
promql = strings.TrimSpace(promql)
if promql == "" {
logger.Warningf("rule_eval:%s promql is blank", getKey(event))
return
}
if e.promClients.IsNil(event.DatasourceId) {
logger.Warningf("rule_eval:%s error reader client is nil", getKey(event))
return
}
readerClient := e.promClients.GetCli(event.DatasourceId)
var warnings promsdk.Warnings
value, warnings, err := readerClient.Query(e.ctx.Ctx, promql, time.Now())
if err != nil {
logger.Errorf("rule_eval:%s promql:%s, error:%v", getKey(event), promql, err)
event.AnnotationsJSON["recovery_promql_error"] = fmt.Sprintf("promql:%s error:%v", promql, err)
b, err := json.Marshal(event.AnnotationsJSON)
if err != nil {
event.AnnotationsJSON = make(map[string]string)
event.AnnotationsJSON["error"] = fmt.Sprintf("failed to parse annotations: %v", err)
} else {
event.Annotations = string(b)
}
return
}
if len(warnings) > 0 {
logger.Errorf("rule_eval:%s promql:%s, warnings:%v", getKey(event), promql, warnings)
}
anomalyPoints := common.ConvertAnomalyPoints(value)
if len(anomalyPoints) == 0 {
logger.Warningf("rule_eval:%s promql:%s, result is empty", getKey(event), promql)
event.AnnotationsJSON["recovery_promql_error"] = fmt.Sprintf("promql:%s error:%s", promql, "result is empty")
} else {
event.AnnotationsJSON["recovery_value"] = fmt.Sprintf("%v", anomalyPoints[0].Value)
}
b, err := json.Marshal(event.AnnotationsJSON)
if err != nil {
event.AnnotationsJSON = make(map[string]string)
event.AnnotationsJSON["error"] = fmt.Sprintf("failed to parse annotations: %v", err)
} else {
event.Annotations = string(b)
}
}
func getKey(event *models.AlertCurEvent) string {
return common.RuleKey(event.DatasourceId, event.RuleId)
}

View File

@@ -4,7 +4,9 @@ import (
"bytes"
"encoding/json"
"html/template"
"net/url"
"strconv"
"strings"
"sync"
"time"
@@ -31,6 +33,7 @@ type Dispatch struct {
alerting aconf.Alerting
Senders map[string]sender.Sender
CallBacks map[string]sender.CallBacker
tpls map[string]*template.Template
ExtraSenders map[string]sender.Sender
BeforeSenderHook func(*models.AlertCurEvent) bool
@@ -97,6 +100,21 @@ func (e *Dispatch) relaodTpls() error {
models.Mm: sender.NewSender(models.Mm, tmpTpls),
models.Telegram: sender.NewSender(models.Telegram, tmpTpls),
models.FeishuCard: sender.NewSender(models.FeishuCard, tmpTpls),
models.Lark: sender.NewSender(models.Lark, tmpTpls),
models.LarkCard: sender.NewSender(models.LarkCard, tmpTpls),
}
// domain -> Callback()
callbacks := map[string]sender.CallBacker{
models.DingtalkDomain: sender.NewCallBacker(models.DingtalkDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
models.WecomDomain: sender.NewCallBacker(models.WecomDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
models.FeishuDomain: sender.NewCallBacker(models.FeishuDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
models.TelegramDomain: sender.NewCallBacker(models.TelegramDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
models.FeishuCardDomain: sender.NewCallBacker(models.FeishuCardDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
models.IbexDomain: sender.NewCallBacker(models.IbexDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
models.LarkDomain: sender.NewCallBacker(models.LarkDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
models.DefaultDomain: sender.NewCallBacker(models.DefaultDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
models.LarkCardDomain: sender.NewCallBacker(models.LarkCardDomain, e.targetCache, e.userCache, e.taskTplsCache, tmpTpls),
}
e.RwLock.RLock()
@@ -108,6 +126,7 @@ func (e *Dispatch) relaodTpls() error {
e.RwLock.Lock()
e.tpls = tmpTpls
e.Senders = senders
e.CallBacks = callbacks
e.RwLock.Unlock()
return nil
}
@@ -148,7 +167,7 @@ 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)
go e.Send(rule, event, notifyTarget, isSubscribe)
// 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 {
@@ -219,11 +238,12 @@ func (e *Dispatch) handleSub(sub *models.AlertSubscribe, event models.AlertCurEv
e.HandleEventNotify(&event, true)
}
func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, notifyTarget *NotifyTarget) {
func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, notifyTarget *NotifyTarget, isSubscribe bool) {
needSend := e.BeforeSenderHook(event)
if needSend {
for channel, uids := range notifyTarget.ToChannelUserMap() {
msgCtx := sender.BuildMessageContext(rule, []*models.AlertCurEvent{event}, uids, e.userCache, e.Astats)
msgCtx := sender.BuildMessageContext(e.ctx, rule, []*models.AlertCurEvent{event},
uids, e.userCache, e.Astats)
e.RwLock.RLock()
s := e.Senders[channel]
e.RwLock.RUnlock()
@@ -243,13 +263,93 @@ func (e *Dispatch) Send(rule *models.AlertRule, event *models.AlertCurEvent, not
}
// handle event callbacks
sender.SendCallbacks(e.ctx, notifyTarget.ToCallbackList(), event, e.targetCache, e.userCache, e.taskTplsCache, e.Astats)
e.SendCallbacks(rule, notifyTarget, event)
// handle global webhooks
sender.SendWebhooks(notifyTarget.ToWebhookList(), event, e.Astats)
if e.alerting.WebhookBatchSend {
sender.BatchSendWebhooks(e.ctx, notifyTarget.ToWebhookList(), event, e.Astats)
} else {
sender.SingleSendWebhooks(e.ctx, notifyTarget.ToWebhookList(), event, e.Astats)
}
// handle plugin call
go sender.MayPluginNotify(e.genNoticeBytes(event), e.notifyConfigCache.GetNotifyScript(), e.Astats)
if !isSubscribe {
// handle ibex callbacks
e.HandleIbex(rule, event)
// handle plugin call
go sender.MayPluginNotify(e.ctx, e.genNoticeBytes(event), e.notifyConfigCache.
GetNotifyScript(), e.Astats, event)
}
}
func (e *Dispatch) SendCallbacks(rule *models.AlertRule, notifyTarget *NotifyTarget, event *models.AlertCurEvent) {
uids := notifyTarget.ToUidList()
urls := notifyTarget.ToCallbackList()
for _, urlStr := range urls {
if len(urlStr) == 0 {
continue
}
cbCtx := sender.BuildCallBackContext(e.ctx, urlStr, rule, []*models.AlertCurEvent{event}, uids, e.userCache, e.alerting.WebhookBatchSend, e.Astats)
if strings.HasPrefix(urlStr, "${ibex}") {
e.CallBacks[models.IbexDomain].CallBack(cbCtx)
continue
}
if !(strings.HasPrefix(urlStr, "http://") || strings.HasPrefix(urlStr, "https://")) {
cbCtx.CallBackURL = "http://" + urlStr
}
parsedURL, err := url.Parse(urlStr)
if err != nil {
logger.Errorf("SendCallbacks: failed to url.Parse(urlStr=%s): %v", urlStr, err)
continue
}
// process feishu card
if parsedURL.Host == models.FeishuDomain && parsedURL.Query().Get("card") == "1" {
e.CallBacks[models.FeishuCardDomain].CallBack(cbCtx)
continue
}
// process lark card
if parsedURL.Host == models.LarkDomain && parsedURL.Query().Get("card") == "1" {
e.CallBacks[models.LarkCardDomain].CallBack(cbCtx)
continue
}
callBacker, ok := e.CallBacks[parsedURL.Host]
if ok {
callBacker.CallBack(cbCtx)
} else {
e.CallBacks[models.DefaultDomain].CallBack(cbCtx)
}
}
}
func (e *Dispatch) HandleIbex(rule *models.AlertRule, event *models.AlertCurEvent) {
// 解析 RuleConfig 字段
var ruleConfig struct {
TaskTpls []*models.Tpl `json:"task_tpls"`
}
json.Unmarshal([]byte(rule.RuleConfig), &ruleConfig)
for _, t := range ruleConfig.TaskTpls {
if t.TplId == 0 {
continue
}
if len(t.Host) == 0 {
sender.CallIbex(e.ctx, t.TplId, event.TargetIdent,
e.taskTplsCache, e.targetCache, e.userCache, event)
continue
}
for _, host := range t.Host {
sender.CallIbex(e.ctx, t.TplId, host,
e.taskTplsCache, e.targetCache, e.userCache, event)
}
}
}
type Notice struct {

View File

@@ -79,11 +79,35 @@ func (s *NotifyTarget) ToCallbackList() []string {
func (s *NotifyTarget) ToWebhookList() []*models.Webhook {
webhooks := make([]*models.Webhook, 0, len(s.webhooks))
for _, wh := range s.webhooks {
if wh.Batch == 0 {
wh.Batch = 1000
}
if wh.Timeout == 0 {
wh.Timeout = 10
}
if wh.RetryCount == 0 {
wh.RetryCount = 10
}
if wh.RetryInterval == 0 {
wh.RetryInterval = 10
}
webhooks = append(webhooks, wh)
}
return webhooks
}
func (s *NotifyTarget) ToUidList() []int64 {
uids := make([]int64, len(s.userMap))
for uid, _ := range s.userMap {
uids = append(uids, uid)
}
return uids
}
// Dispatch 抽象由告警事件到信息接收者的路由策略
// rule: 告警规则
// event: 告警事件

View File

@@ -143,19 +143,22 @@ func (arw *AlertRuleWorker) Eval() {
if p.Severity > point.Severity {
hash := process.Hash(cachedRule.Id, arw.processor.DatasourceId(), p)
arw.processor.DeleteProcessEvent(hash)
models.AlertCurEventDelByHash(arw.ctx, hash)
pointsMap[tagHash] = point
}
}
now := time.Now().Unix()
for _, point := range pointsMap {
str := fmt.Sprintf("%v", point.Value)
arw.processor.RecoverSingle(process.Hash(cachedRule.Id, arw.processor.DatasourceId(), point), point.Timestamp, &str)
arw.processor.RecoverSingle(process.Hash(cachedRule.Id, arw.processor.DatasourceId(), point), now, &str)
}
} else {
now := time.Now().Unix()
for _, point := range recoverPoints {
str := fmt.Sprintf("%v", point.Value)
arw.processor.RecoverSingle(process.Hash(cachedRule.Id, arw.processor.DatasourceId(), point), point.Timestamp, &str)
arw.processor.RecoverSingle(process.Hash(cachedRule.Id, arw.processor.DatasourceId(), point), now, &str)
}
}

View File

@@ -12,28 +12,28 @@ import (
"github.com/toolkits/pkg/logger"
)
func IsMuted(rule *models.AlertRule, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, alertMuteCache *memsto.AlertMuteCacheType) bool {
func IsMuted(rule *models.AlertRule, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, alertMuteCache *memsto.AlertMuteCacheType) (bool, string) {
if rule.Disabled == 1 {
return true
return true, "rule disabled"
}
if TimeSpanMuteStrategy(rule, event) {
return true
return true, "rule is not effective for period of time"
}
if IdentNotExistsMuteStrategy(rule, event, targetCache) {
return true
return true, "ident not exists mute"
}
if BgNotMatchMuteStrategy(rule, event, targetCache) {
return true
return true, "bg not match mute"
}
if EventMuteStrategy(event, alertMuteCache) {
return true
return true, "match mute rule"
}
return false
return false, ""
}
// 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

View File

@@ -18,6 +18,9 @@ import (
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/ccfos/nightingale/v6/pkg/tplx"
"github.com/ccfos/nightingale/v6/pushgw/writer"
"github.com/prometheus/prometheus/prompb"
"github.com/toolkits/pkg/logger"
"github.com/toolkits/pkg/str"
)
@@ -50,10 +53,11 @@ type Processor struct {
datasourceId int64
EngineName string
rule *models.AlertRule
fires *AlertCurEventMap
pendings *AlertCurEventMap
inhibit bool
rule *models.AlertRule
fires *AlertCurEventMap
pendings *AlertCurEventMap
pendingsUseByRecover *AlertCurEventMap
inhibit bool
tagsMap map[string]string
tagsArr []string
@@ -145,9 +149,10 @@ func (p *Processor) Handle(anomalyPoints []common.AnomalyPoint, from string, inh
// 如果 event 被 mute 了,本质也是 fire 的状态,这里无论如何都添加到 alertingKeys 中,防止 fire 的事件自动恢复了
hash := event.Hash
alertingKeys[hash] = struct{}{}
if mute.IsMuted(cachedRule, event, p.TargetCache, p.alertMuteCache) {
isMuted, detail := mute.IsMuted(cachedRule, event, p.TargetCache, p.alertMuteCache)
if isMuted {
p.Stats.CounterMuteTotal.WithLabelValues(event.GroupName).Inc()
logger.Debugf("rule_eval:%s event:%v is muted", p.Key(), event)
logger.Debugf("rule_eval:%s event:%v is muted, detail:%s", p.Key(), event, detail)
continue
}
@@ -217,9 +222,57 @@ func (p *Processor) BuildEvent(anomalyPoint common.AnomalyPoint, from string, no
} else {
event.LastEvalTime = event.TriggerTime
}
// 生成事件之后,立马进程 relabel 处理
Relabel(p.rule, event)
return event
}
func Relabel(rule *models.AlertRule, event *models.AlertCurEvent) {
if rule == nil {
return
}
if len(rule.EventRelabelConfig) == 0 {
return
}
// need to keep the original label
event.OriginalTags = event.Tags
event.OriginalTagsJSON = make([]string, len(event.TagsJSON))
labels := make([]prompb.Label, len(event.TagsJSON))
for i, tag := range event.TagsJSON {
label := strings.SplitN(tag, "=", 2)
event.OriginalTagsJSON[i] = tag
labels[i] = prompb.Label{Name: label[0], Value: label[1]}
}
for i := 0; i < len(rule.EventRelabelConfig); i++ {
if rule.EventRelabelConfig[i].Replacement == "" {
rule.EventRelabelConfig[i].Replacement = "$1"
}
if rule.EventRelabelConfig[i].Separator == "" {
rule.EventRelabelConfig[i].Separator = ";"
}
if rule.EventRelabelConfig[i].Regex == "" {
rule.EventRelabelConfig[i].Regex = "(.*)"
}
}
// relabel process
relabels := writer.Process(labels, rule.EventRelabelConfig...)
event.TagsJSON = make([]string, len(relabels))
event.TagsMap = make(map[string]string, len(relabels))
for i, label := range relabels {
event.TagsJSON[i] = fmt.Sprintf("%s=%s", label.Name, label.Value)
event.TagsMap[label.Name] = label.Value
}
event.Tags = strings.Join(event.TagsJSON, ",,")
}
func (p *Processor) HandleRecover(alertingKeys map[string]struct{}, now int64, inhibit bool) {
for _, hash := range p.pendings.Keys() {
if _, has := alertingKeys[hash]; has {
@@ -270,6 +323,7 @@ func (p *Processor) HandleRecoverEvent(hashArr []string, now int64, inhibit bool
// hash 对应的恢复事件的被抑制了,把之前的事件删除
p.fires.Delete(e.Hash)
p.pendings.Delete(e.Hash)
models.AlertCurEventDelByHash(p.ctx, e.Hash)
eventMap[event.Tags] = *event
}
}
@@ -289,11 +343,22 @@ func (p *Processor) RecoverSingle(hash string, now int64, value *string, values
if !has {
return
}
// 如果配置了留观时长,就不能立马恢复了
if cachedRule.RecoverDuration > 0 && now-event.LastEvalTime < cachedRule.RecoverDuration {
logger.Debugf("rule_eval:%s event:%v not recover", p.Key(), event)
return
if cachedRule.RecoverDuration > 0 {
lastPendingEvent, has := p.pendingsUseByRecover.Get(hash)
if !has {
// 说明没有产生过异常点,就不需要恢复了
logger.Debugf("rule_eval:%s event:%v do not has pending event, not recover", p.Key(), event)
return
}
if now-lastPendingEvent.LastEvalTime < cachedRule.RecoverDuration {
logger.Debugf("rule_eval:%s event:%v not recover", p.Key(), event)
return
}
}
if value != nil {
event.TriggerValue = *value
if len(values) > 0 {
@@ -305,6 +370,7 @@ func (p *Processor) RecoverSingle(hash string, now int64, value *string, values
// 我确实无法分辨是prom中有值但是未满足阈值所以没返回还是prom中确实丢了一些点导致没有数据可以返回尴尬
p.fires.Delete(hash)
p.pendings.Delete(hash)
p.pendingsUseByRecover.Delete(hash)
// 可能是因为调整了promql才恢复的所以事件里边要体现最新的promql否则用户会比较困惑
// 当然其实rule的各个字段都可能发生变化了都更新一下吧
@@ -336,9 +402,11 @@ func (p *Processor) handleEvent(events []*models.AlertCurEvent) {
preEvent, has := p.pendings.Get(event.Hash)
if has {
p.pendings.UpdateLastEvalTime(event.Hash, event.LastEvalTime)
p.pendingsUseByRecover.UpdateLastEvalTime(event.Hash, event.LastEvalTime)
preTriggerTime = preEvent.TriggerTime
} else {
p.pendings.Set(event.Hash, event)
p.pendingsUseByRecover.Set(event.Hash, event)
preTriggerTime = event.TriggerTime
}
@@ -424,6 +492,7 @@ func (p *Processor) pushEventToQueue(e *models.AlertCurEvent) {
func (p *Processor) RecoverAlertCurEventFromDb() {
p.pendings = NewAlertCurEventMap(nil)
p.pendingsUseByRecover = NewAlertCurEventMap(nil)
curEvents, err := models.AlertCurEventGetByRuleIdAndDsId(p.ctx, p.rule.Id, p.datasourceId)
if err != nil {
@@ -523,6 +592,7 @@ func (p *Processor) mayHandleGroup() {
func (p *Processor) DeleteProcessEvent(hash string) {
p.fires.Delete(hash)
p.pendings.Delete(hash)
p.pendingsUseByRecover.Delete(hash)
}
func labelMapToArr(m map[string]string) []string {

View File

@@ -10,6 +10,7 @@ import (
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/prom"
"github.com/ccfos/nightingale/v6/pushgw/writer"
"github.com/robfig/cron/v3"
"github.com/toolkits/pkg/logger"
"github.com/toolkits/pkg/str"
@@ -19,19 +20,35 @@ type RecordRuleContext struct {
datasourceId int64
quit chan struct{}
scheduler *cron.Cron
rule *models.RecordingRule
promClients *prom.PromClientMap
stats *astats.Stats
}
func NewRecordRuleContext(rule *models.RecordingRule, datasourceId int64, promClients *prom.PromClientMap, writers *writer.WritersType, stats *astats.Stats) *RecordRuleContext {
return &RecordRuleContext{
rrc := &RecordRuleContext{
datasourceId: datasourceId,
quit: make(chan struct{}),
rule: rule,
promClients: promClients,
stats: stats,
}
if rule.CronPattern == "" && rule.PromEvalInterval != 0 {
rule.CronPattern = fmt.Sprintf("@every %ds", rule.PromEvalInterval)
}
rrc.scheduler = cron.New(cron.WithSeconds())
_, err := rrc.scheduler.AddFunc(rule.CronPattern, func() {
rrc.Eval()
})
if err != nil {
logger.Errorf("add cron pattern error: %v", err)
}
return rrc
}
func (rrc *RecordRuleContext) Key() string {
@@ -39,9 +56,9 @@ func (rrc *RecordRuleContext) Key() string {
}
func (rrc *RecordRuleContext) Hash() string {
return str.MD5(fmt.Sprintf("%d_%d_%s_%d",
return str.MD5(fmt.Sprintf("%d_%s_%s_%d",
rrc.rule.Id,
rrc.rule.PromEvalInterval,
rrc.rule.CronPattern,
rrc.rule.PromQl,
rrc.datasourceId,
))
@@ -51,23 +68,7 @@ func (rrc *RecordRuleContext) Prepare() {}
func (rrc *RecordRuleContext) Start() {
logger.Infof("eval:%s started", rrc.Key())
interval := rrc.rule.PromEvalInterval
if interval <= 0 {
interval = 10
}
ticker := time.NewTicker(time.Duration(interval) * time.Second)
go func() {
defer ticker.Stop()
for {
select {
case <-rrc.quit:
return
case <-ticker.C:
rrc.Eval()
}
}
}()
rrc.scheduler.Start()
}
func (rrc *RecordRuleContext) Eval() {
@@ -109,5 +110,8 @@ func (rrc *RecordRuleContext) Eval() {
func (rrc *RecordRuleContext) Stop() {
logger.Infof("%s stopped", rrc.Key())
c := rrc.scheduler.Stop()
<-c.Done()
close(rrc.quit)
}

View File

@@ -1,9 +1,8 @@
package sender
import (
"encoding/json"
"fmt"
"strconv"
"html/template"
"net/url"
"strings"
"time"
@@ -13,38 +12,175 @@ import (
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/ccfos/nightingale/v6/pkg/poster"
imodels "github.com/flashcatcloud/ibex/src/models"
"github.com/flashcatcloud/ibex/src/storage"
"github.com/toolkits/pkg/logger"
)
func SendCallbacks(ctx *ctx.Context, urls []string, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, userCache *memsto.UserCacheType,
taskTplCache *memsto.TaskTplCache, stats *astats.Stats) {
for _, url := range urls {
if url == "" {
continue
}
if strings.HasPrefix(url, "${ibex}") {
if !event.IsRecovered {
handleIbex(ctx, url, event, targetCache, userCache, taskTplCache)
}
continue
}
if !(strings.HasPrefix(url, "http://") || strings.HasPrefix(url, "https://")) {
url = "http://" + url
}
stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
resp, code, err := poster.PostJSON(url, 5*time.Second, event, 3)
if err != nil {
logger.Errorf("event_callback_fail(rule_id=%d url=%s), resp: %s, err: %v, code: %d", event.RuleId, url, string(resp), err, code)
stats.AlertNotifyErrorTotal.WithLabelValues("rule_callback").Inc()
} else {
logger.Infof("event_callback_succ(rule_id=%d url=%s), resp: %s, code: %d", event.RuleId, url, string(resp), code)
}
type (
// CallBacker 进行回调的接口
CallBacker interface {
CallBack(ctx CallBackContext)
}
// CallBackContext 回调时所需的上下文
CallBackContext struct {
Ctx *ctx.Context
CallBackURL string
Users []*models.User
Rule *models.AlertRule
Events []*models.AlertCurEvent
Stats *astats.Stats
BatchSend bool
}
DefaultCallBacker struct{}
)
func BuildCallBackContext(ctx *ctx.Context, callBackURL string, rule *models.AlertRule, events []*models.AlertCurEvent,
uids []int64, userCache *memsto.UserCacheType, batchSend bool, stats *astats.Stats) CallBackContext {
users := userCache.GetByUserIds(uids)
newCallBackUrl, _ := events[0].ParseURL(callBackURL)
return CallBackContext{
Ctx: ctx,
CallBackURL: newCallBackUrl,
Rule: rule,
Events: events,
Users: users,
BatchSend: batchSend,
Stats: stats,
}
}
func ExtractAtsParams(rawURL string) []string {
ans := make([]string, 0, 1)
parsedURL, err := url.Parse(rawURL)
if err != nil {
logger.Errorf("ExtractAtsParams(url=%s), err: %v", rawURL, err)
return ans
}
queryParams := parsedURL.Query()
atParam := queryParams.Get("ats")
if atParam == "" {
return ans
}
// Split the atParam by comma and return the result as a slice
return strings.Split(atParam, ",")
}
func NewCallBacker(
key string,
targetCache *memsto.TargetCacheType,
userCache *memsto.UserCacheType,
taskTplCache *memsto.TaskTplCache,
tpls map[string]*template.Template,
) CallBacker {
switch key {
case models.IbexDomain: // Distribute to Ibex
return &IbexCallBacker{
targetCache: targetCache,
userCache: userCache,
taskTplCache: taskTplCache,
}
case models.DefaultDomain: // default callback
return &DefaultCallBacker{}
case models.DingtalkDomain:
return &DingtalkSender{tpl: tpls[models.Dingtalk]}
case models.WecomDomain:
return &WecomSender{tpl: tpls[models.Wecom]}
case models.FeishuDomain:
return &FeishuSender{tpl: tpls[models.Feishu]}
case models.FeishuCardDomain:
return &FeishuCardSender{tpl: tpls[models.FeishuCard]}
//case models.Mm:
// return &MmSender{tpl: tpls[models.Mm]}
case models.TelegramDomain:
return &TelegramSender{tpl: tpls[models.Telegram]}
case models.LarkDomain:
return &LarkSender{tpl: tpls[models.Lark]}
case models.LarkCardDomain:
return &LarkCardSender{tpl: tpls[models.LarkCard]}
}
return nil
}
func (c *DefaultCallBacker) CallBack(ctx CallBackContext) {
if len(ctx.CallBackURL) == 0 || len(ctx.Events) == 0 {
return
}
event := ctx.Events[0]
if ctx.BatchSend {
webhookConf := &models.Webhook{
Type: models.RuleCallback,
Enable: true,
Url: ctx.CallBackURL,
Timeout: 5,
RetryCount: 3,
RetryInterval: 10,
Batch: 1000,
}
PushCallbackEvent(ctx.Ctx, webhookConf, event, ctx.Stats)
return
}
ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
resp, code, err := poster.PostJSON(ctx.CallBackURL, 5*time.Second, event, 3)
if err != nil {
logger.Errorf("event_callback_fail(rule_id=%d url=%s), event:%+v, resp: %s, err: %v, code: %d",
event.RuleId, ctx.CallBackURL, event, string(resp), err, code)
ctx.Stats.AlertNotifyErrorTotal.WithLabelValues("rule_callback").Inc()
} else {
logger.Infof("event_callback_succ(rule_id=%d url=%s), event:%+v, resp: %s, code: %d",
event.RuleId, ctx.CallBackURL, event, string(resp), code)
}
}
func doSendAndRecord(ctx *ctx.Context, url, token string, body interface{}, channel string,
stats *astats.Stats, event *models.AlertCurEvent) {
res, err := doSend(url, body, channel, stats)
NotifyRecord(ctx, event, channel, token, res, err)
}
func NotifyRecord(ctx *ctx.Context, evt *models.AlertCurEvent, channel, target, res string, err error) {
noti := models.NewNotificationRecord(evt, channel, target)
if err != nil {
noti.SetStatus(models.NotiStatusFailure)
noti.SetDetails(err.Error())
} else if res != "" {
noti.SetDetails(string(res))
}
if !ctx.IsCenter {
_, err := poster.PostByUrlsWithResp[int64](ctx, "/v1/n9e/notify-record", noti)
if err != nil {
logger.Errorf("add noti:%v failed, err: %v", noti, err)
}
return
}
if err := noti.Add(ctx); err != nil {
logger.Errorf("add noti:%v failed, err: %v", noti, err)
}
}
func doSend(url string, body interface{}, channel string, stats *astats.Stats) (string, error) {
stats.AlertNotifyTotal.WithLabelValues(channel).Inc()
res, code, err := poster.PostJSON(url, time.Second*5, body, 3)
if err != nil {
logger.Errorf("%s_sender: result=fail url=%s code=%d error=%v req:%v response=%s", channel, url, code, err, body, string(res))
stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
return "", err
}
logger.Infof("%s_sender: result=succ url=%s code=%d req:%v response=%s", channel, url, code, body, string(res))
return string(res), nil
}
type TaskCreateReply struct {
@@ -52,225 +188,26 @@ type TaskCreateReply struct {
Dat int64 `json:"dat"` // task.id
}
func handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent, targetCache *memsto.TargetCacheType, userCache *memsto.UserCacheType,
taskTplCache *memsto.TaskTplCache) {
if imodels.DB() == nil {
logger.Warning("event_callback_ibex: db is nil")
return
}
func PushCallbackEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
CallbackEventQueueLock.RLock()
queue := CallbackEventQueue[webhook.Url]
CallbackEventQueueLock.RUnlock()
arr := strings.Split(url, "/")
var idstr string
var host string
if len(arr) > 1 {
idstr = arr[1]
}
if len(arr) > 2 {
host = arr[2]
}
id, err := strconv.ParseInt(idstr, 10, 64)
if err != nil {
logger.Errorf("event_callback_ibex: failed to parse url: %s", url)
return
}
if host == "" {
// 用户在callback url中没有传入host就从event中解析
host = event.TargetIdent
}
if host == "" {
logger.Error("event_callback_ibex: failed to get host")
return
}
tpl := taskTplCache.Get(id)
if tpl == nil {
logger.Errorf("event_callback_ibex: no such tpl(%d)", id)
return
}
// check perm
// tpl.GroupId - host - account 三元组校验权限
can, err := canDoIbex(tpl.UpdateBy, tpl, host, targetCache, userCache)
if err != nil {
logger.Errorf("event_callback_ibex: check perm fail: %v", err)
return
}
if !can {
logger.Errorf("event_callback_ibex: user(%s) no permission", tpl.UpdateBy)
return
}
tagsMap := make(map[string]string)
for i := 0; i < len(event.TagsJSON); i++ {
pair := strings.TrimSpace(event.TagsJSON[i])
if pair == "" {
continue
if queue == nil {
queue = &WebhookQueue{
list: NewSafeListLimited(QueueMaxSize),
closeCh: make(chan struct{}),
}
arr := strings.Split(pair, "=")
if len(arr) != 2 {
continue
}
CallbackEventQueueLock.Lock()
CallbackEventQueue[webhook.Url] = queue
CallbackEventQueueLock.Unlock()
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
StartConsumer(ctx, queue, webhook.Batch, webhook, stats)
}
// call ibex
in := models.TaskForm{
Title: tpl.Title + " FH: " + host,
Account: tpl.Account,
Batch: tpl.Batch,
Tolerance: tpl.Tolerance,
Timeout: tpl.Timeout,
Pause: tpl.Pause,
Script: tpl.Script,
Args: tpl.Args,
Stdin: string(tags),
Action: "start",
Creator: tpl.UpdateBy,
Hosts: []string{host},
AlertTriggered: true,
}
id, err = TaskAdd(in, tpl.UpdateBy, ctx.IsCenter)
if err != nil {
logger.Errorf("event_callback_ibex: call ibex fail: %v", err)
return
}
// write db
record := models.TaskRecord{
Id: id,
EventId: event.Id,
GroupId: tpl.GroupId,
Title: in.Title,
Account: in.Account,
Batch: in.Batch,
Tolerance: in.Tolerance,
Timeout: in.Timeout,
Pause: in.Pause,
Script: in.Script,
Args: in.Args,
CreateAt: time.Now().Unix(),
CreateBy: in.Creator,
}
if err = record.Add(ctx); err != nil {
logger.Errorf("event_callback_ibex: persist task_record fail: %v", err)
succ := queue.list.PushFront(event)
if !succ {
logger.Warningf("Write channel(%s) full, current channel size: %d event:%v", webhook.Url, queue.list.Len(), event)
}
}
func canDoIbex(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
}
target, has := targetCache.Get(host)
if !has {
return false, nil
}
return target.GroupId == tpl.GroupId, nil
}
func TaskAdd(f models.TaskForm, authUser string, isCenter bool) (int64, error) {
hosts := cleanHosts(f.Hosts)
if len(hosts) == 0 {
return 0, fmt.Errorf("arg(hosts) empty")
}
taskMeta := &imodels.TaskMeta{
Title: f.Title,
Account: f.Account,
Batch: f.Batch,
Tolerance: f.Tolerance,
Timeout: f.Timeout,
Pause: f.Pause,
Script: f.Script,
Args: f.Args,
Stdin: f.Stdin,
Creator: f.Creator,
}
err := taskMeta.CleanFields()
if err != nil {
return 0, err
}
taskMeta.HandleFH(hosts[0])
// 任务类型分为"告警规则触发"和"n9e center用户下发"两种;
// 边缘机房"告警规则触发"的任务不需要规划并且它可能是失联的无法使用db资源所以放入redis缓存中直接下发给agentd执行
if !isCenter && f.AlertTriggered {
if err := taskMeta.Create(); err != nil {
// 当网络不连通时生成唯一的id防止边缘机房中不同任务的id相同
// 方法是redis自增id去防止同一个机房的不同n9e edge生成的id相同
// 但没法防止不同边缘机房生成同样的id所以生成id的数据不会上报存入数据库只用于闭环执行。
taskMeta.Id, err = storage.IdGet()
if err != nil {
return 0, err
}
}
taskHost := imodels.TaskHost{
Id: taskMeta.Id,
Host: hosts[0],
Status: "running",
}
if err = taskHost.Create(); err != nil {
logger.Warningf("task_add_fail: authUser=%s title=%s err=%s", authUser, taskMeta.Title, err.Error())
}
// 缓存任务元信息和待下发的任务
err = taskMeta.Cache(hosts[0])
if err != nil {
return 0, err
}
} else {
// 如果是中心机房,还是保持之前的逻辑
err = taskMeta.Save(hosts, f.Action)
if err != nil {
return 0, err
}
}
logger.Infof("task_add_succ: authUser=%s title=%s", authUser, taskMeta.Title)
return taskMeta.Id, nil
}
func cleanHosts(formHosts []string) []string {
cnt := len(formHosts)
arr := make([]string, 0, cnt)
for i := 0; i < cnt; i++ {
item := strings.TrimSpace(formHosts[i])
if item == "" {
continue
}
if strings.HasPrefix(item, "#") {
continue
}
arr = append(arr, item)
}
return arr
}

View File

@@ -3,13 +3,8 @@ 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"
)
type dingtalkMarkdown struct {
@@ -28,6 +23,10 @@ type dingtalk struct {
At dingtalkAt `json:"at"`
}
var (
_ CallBacker = (*DingtalkSender)(nil)
)
type DingtalkSender struct {
tpl *template.Template
}
@@ -37,13 +36,13 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
return
}
urls, ats := ds.extract(ctx.Users)
urls, ats, tokens := ds.extract(ctx.Users)
if len(urls) == 0 {
return
}
message := BuildTplMessage(models.Dingtalk, ds.tpl, ctx.Events)
for _, url := range urls {
for i, url := range urls {
var body dingtalk
// NoAt in url
if strings.Contains(url, "noat=1") {
@@ -68,14 +67,47 @@ func (ds *DingtalkSender) Send(ctx MessageContext) {
}
}
doSend(url, body, models.Dingtalk, ctx.Stats)
doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Dingtalk, ctx.Stats, ctx.Events[0])
}
}
func (ds *DingtalkSender) CallBack(ctx CallBackContext) {
if len(ctx.Events) == 0 || len(ctx.CallBackURL) == 0 {
return
}
body := dingtalk{
Msgtype: "markdown",
Markdown: dingtalkMarkdown{
Title: ctx.Events[0].RuleName,
},
}
ats := ExtractAtsParams(ctx.CallBackURL)
message := BuildTplMessage(models.Dingtalk, ds.tpl, ctx.Events)
if len(ats) > 0 {
body.Markdown.Text = message + "\n@" + strings.Join(ats, "@")
body.At = dingtalkAt{
AtMobiles: ats,
IsAtAll: false,
}
} else {
// NoAt in url
body.Markdown.Text = message
}
doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body,
"callback", ctx.Stats, ctx.Events[0])
ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
}
// extract urls and ats from Users
func (ds *DingtalkSender) extract(users []*models.User) ([]string, []string) {
func (ds *DingtalkSender) extract(users []*models.User) ([]string, []string, []string) {
urls := make([]string, 0, len(users))
ats := make([]string, 0, len(users))
tokens := make([]string, 0, len(users))
for _, user := range users {
if user.Phone != "" {
@@ -87,19 +119,8 @@ func (ds *DingtalkSender) extract(users []*models.User) ([]string, []string) {
url = "https://oapi.dingtalk.com/robot/send?access_token=" + token
}
urls = append(urls, url)
tokens = append(tokens, token)
}
}
return urls, ats
}
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("%s_sender: result=fail url=%s code=%d error=%v req:%v response=%s", channel, url, code, err, body, string(res))
stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
} else {
logger.Infof("%s_sender: result=succ url=%s code=%d req:%v response=%s", channel, url, code, body, string(res))
}
return urls, ats, tokens
}

View File

@@ -9,13 +9,14 @@ import (
"github.com/ccfos/nightingale/v6/alert/aconf"
"github.com/ccfos/nightingale/v6/memsto"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/toolkits/pkg/logger"
"gopkg.in/gomail.v2"
)
var mailch chan *gomail.Message
var mailch chan *EmailContext
type EmailSender struct {
subjectTpl *template.Template
@@ -23,6 +24,11 @@ type EmailSender struct {
smtp aconf.SMTPConfig
}
type EmailContext struct {
event *models.AlertCurEvent
mail *gomail.Message
}
func (es *EmailSender) Send(ctx MessageContext) {
if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
return
@@ -36,7 +42,7 @@ func (es *EmailSender) Send(ctx MessageContext) {
subject = ctx.Events[0].RuleName
}
content := BuildTplMessage(models.Email, es.contentTpl, ctx.Events)
es.WriteEmail(subject, content, tos)
es.WriteEmail(subject, content, tos, ctx.Events[0])
ctx.Stats.AlertNotifyTotal.WithLabelValues(models.Email).Add(float64(len(tos)))
}
@@ -73,7 +79,8 @@ func SendEmail(subject, content string, tos []string, stmp aconf.SMTPConfig) err
return nil
}
func (es *EmailSender) WriteEmail(subject, content string, tos []string) {
func (es *EmailSender) WriteEmail(subject, content string, tos []string,
event *models.AlertCurEvent) {
m := gomail.NewMessage()
m.SetHeader("From", es.smtp.From)
@@ -81,7 +88,7 @@ func (es *EmailSender) WriteEmail(subject, content string, tos []string) {
m.SetHeader("Subject", subject)
m.SetBody("text/html", content)
mailch <- m
mailch <- &EmailContext{event, m}
}
func dialSmtp(d *gomail.Dialer) gomail.SendCloser {
@@ -104,22 +111,22 @@ func dialSmtp(d *gomail.Dialer) gomail.SendCloser {
var mailQuit = make(chan struct{})
func RestartEmailSender(smtp aconf.SMTPConfig) {
func RestartEmailSender(ctx *ctx.Context, smtp aconf.SMTPConfig) {
// Notify internal start exit
mailQuit <- struct{}{}
startEmailSender(smtp)
startEmailSender(ctx, smtp)
}
var smtpConfig aconf.SMTPConfig
func InitEmailSender(ncc *memsto.NotifyConfigCacheType) {
mailch = make(chan *gomail.Message, 100000)
go updateSmtp(ncc)
func InitEmailSender(ctx *ctx.Context, ncc *memsto.NotifyConfigCacheType) {
mailch = make(chan *EmailContext, 100000)
go updateSmtp(ctx, ncc)
smtpConfig = ncc.GetSMTP()
startEmailSender(smtpConfig)
startEmailSender(ctx, smtpConfig)
}
func updateSmtp(ncc *memsto.NotifyConfigCacheType) {
func updateSmtp(ctx *ctx.Context, ncc *memsto.NotifyConfigCacheType) {
for {
time.Sleep(1 * time.Minute)
smtp := ncc.GetSMTP()
@@ -127,12 +134,12 @@ func updateSmtp(ncc *memsto.NotifyConfigCacheType) {
smtpConfig.Pass != smtp.Pass || smtpConfig.User != smtp.User || smtpConfig.Port != smtp.Port ||
smtpConfig.InsecureSkipVerify != smtp.InsecureSkipVerify { //diff
smtpConfig = smtp
RestartEmailSender(smtp)
RestartEmailSender(ctx, smtp)
}
}
}
func startEmailSender(smtp aconf.SMTPConfig) {
func startEmailSender(ctx *ctx.Context, smtp aconf.SMTPConfig) {
conf := smtp
if conf.Host == "" || conf.Port == 0 {
logger.Warning("SMTP configurations invalid")
@@ -167,7 +174,8 @@ func startEmailSender(smtp aconf.SMTPConfig) {
}
open = true
}
if err := gomail.Send(s, m); err != nil {
var err error
if err = gomail.Send(s, m.mail); err != nil {
logger.Errorf("email_sender: failed to send: %s", err)
// close and retry
@@ -184,11 +192,16 @@ func startEmailSender(smtp aconf.SMTPConfig) {
}
open = true
if err := gomail.Send(s, m); err != nil {
if err = gomail.Send(s, m.mail); err != nil {
logger.Errorf("email_sender: failed to retry send: %s", err)
}
} else {
logger.Infof("email_sender: result=succ subject=%v to=%v", m.GetHeader("Subject"), m.GetHeader("To"))
logger.Infof("email_sender: result=succ subject=%v to=%v",
m.mail.GetHeader("Subject"), m.mail.GetHeader("To"))
}
for _, to := range m.mail.GetHeader("To") {
NotifyRecord(ctx, m.event, models.Email, to, "", err)
}
size++

View File

@@ -1,6 +1,7 @@
package sender
import (
"fmt"
"html/template"
"strings"
@@ -22,17 +23,49 @@ type feishu struct {
At feishuAt `json:"at"`
}
var (
_ CallBacker = (*FeishuSender)(nil)
)
type FeishuSender struct {
tpl *template.Template
}
func (fs *FeishuSender) CallBack(ctx CallBackContext) {
if len(ctx.Events) == 0 || len(ctx.CallBackURL) == 0 {
return
}
ats := ExtractAtsParams(ctx.CallBackURL)
message := BuildTplMessage(models.Feishu, fs.tpl, ctx.Events)
if len(ats) > 0 {
atTags := ""
for _, at := range ats {
atTags += fmt.Sprintf("<at user_id=\"%s\"></at> ", at)
}
message = atTags + message
}
body := feishu{
Msgtype: "text",
Content: feishuContent{
Text: message,
},
}
doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
ctx.Stats, ctx.Events[0])
ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
}
func (fs *FeishuSender) Send(ctx MessageContext) {
if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
return
}
urls, ats := fs.extract(ctx.Users)
urls, ats, tokens := fs.extract(ctx.Users)
message := BuildTplMessage(models.Feishu, fs.tpl, ctx.Events)
for _, url := range urls {
for i, url := range urls {
body := feishu{
Msgtype: "text",
Content: feishuContent{
@@ -45,13 +78,14 @@ func (fs *FeishuSender) Send(ctx MessageContext) {
IsAtAll: false,
}
}
doSend(url, body, models.Feishu, ctx.Stats)
doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Feishu, ctx.Stats, ctx.Events[0])
}
}
func (fs *FeishuSender) extract(users []*models.User) ([]string, []string) {
func (fs *FeishuSender) extract(users []*models.User) ([]string, []string, []string) {
urls := make([]string, 0, len(users))
ats := make([]string, 0, len(users))
tokens := make([]string, 0, len(users))
for _, user := range users {
if user.Phone != "" {
@@ -63,7 +97,8 @@ func (fs *FeishuSender) extract(users []*models.User) ([]string, []string) {
url = "https://open.feishu.cn/open-apis/bot/v2/hook/" + token
}
urls = append(urls, url)
tokens = append(tokens, token)
}
}
return urls, ats
return urls, ats, tokens
}

View File

@@ -3,6 +3,7 @@ package sender
import (
"fmt"
"html/template"
"net/url"
"strings"
"github.com/ccfos/nightingale/v6/models"
@@ -91,11 +92,57 @@ var (
}
)
func (fs *FeishuCardSender) CallBack(ctx CallBackContext) {
if len(ctx.Events) == 0 || len(ctx.CallBackURL) == 0 {
return
}
ats := ExtractAtsParams(ctx.CallBackURL)
message := BuildTplMessage(models.FeishuCard, fs.tpl, ctx.Events)
if len(ats) > 0 {
atTags := ""
for _, at := range ats {
if strings.Contains(at, "@") {
atTags += fmt.Sprintf("<at email=\"%s\" ></at>", at)
} else {
atTags += fmt.Sprintf("<at id=\"%s\" ></at>", at)
}
}
message = atTags + message
}
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
// This is to be compatible with the feishucard interface, if with query string parameters, the request will fail
// Remove query parameters from the URL,
parsedURL, err := url.Parse(ctx.CallBackURL)
if err != nil {
return
}
parsedURL.RawQuery = ""
doSendAndRecord(ctx.Ctx, parsedURL.String(), parsedURL.String(), body, "callback",
ctx.Stats, ctx.Events[0])
}
func (fs *FeishuCardSender) Send(ctx MessageContext) {
if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
return
}
urls, _ := fs.extract(ctx.Users)
urls, tokens := fs.extract(ctx.Users)
message := BuildTplMessage(models.FeishuCard, fs.tpl, ctx.Events)
color := "red"
lowerUnicode := strings.ToLower(message)
@@ -110,14 +157,15 @@ func (fs *FeishuCardSender) Send(ctx MessageContext) {
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)
for i, url := range urls {
doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.FeishuCard,
ctx.Stats, ctx.Events[0])
}
}
func (fs *FeishuCardSender) extract(users []*models.User) ([]string, []string) {
urls := make([]string, 0, len(users))
ats := make([]string, 0)
tokens := make([]string, 0, len(users))
for i := range users {
if token, has := users[i].ExtractToken(models.FeishuCard); has {
url := token
@@ -125,7 +173,8 @@ func (fs *FeishuCardSender) extract(users []*models.User) ([]string, []string) {
url = "https://open.feishu.cn/open-apis/bot/v2/hook/" + strings.TrimSpace(token)
}
urls = append(urls, url)
tokens = append(tokens, token)
}
}
return urls, ats
return urls, tokens
}

270
alert/sender/ibex.go Normal file
View File

@@ -0,0 +1,270 @@
// @Author: Ciusyan 6/5/24
package sender
import (
"encoding/json"
"fmt"
"strconv"
"strings"
"time"
"github.com/ccfos/nightingale/v6/memsto"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
imodels "github.com/flashcatcloud/ibex/src/models"
"github.com/flashcatcloud/ibex/src/storage"
"github.com/toolkits/pkg/logger"
)
var (
_ CallBacker = (*IbexCallBacker)(nil)
)
type IbexCallBacker struct {
targetCache *memsto.TargetCacheType
userCache *memsto.UserCacheType
taskTplCache *memsto.TaskTplCache
}
func (c *IbexCallBacker) CallBack(ctx CallBackContext) {
if len(ctx.CallBackURL) == 0 || len(ctx.Events) == 0 {
return
}
event := ctx.Events[0]
if event.IsRecovered {
return
}
c.handleIbex(ctx.Ctx, ctx.CallBackURL, event)
}
func (c *IbexCallBacker) handleIbex(ctx *ctx.Context, url string, event *models.AlertCurEvent) {
if imodels.DB() == nil && ctx.IsCenter {
logger.Warning("event_callback_ibex: db is nil")
return
}
arr := strings.Split(url, "/")
var idstr string
var host string
if len(arr) > 1 {
idstr = arr[1]
}
if len(arr) > 2 {
host = arr[2]
}
id, err := strconv.ParseInt(idstr, 10, 64)
if err != nil {
logger.Errorf("event_callback_ibex: failed to parse url: %s", url)
return
}
if host == "" {
// 用户在callback url中没有传入host就从event中解析
host = event.TargetIdent
}
if host == "" {
logger.Error("event_callback_ibex: failed to get host")
return
}
CallIbex(ctx, id, host, c.taskTplCache, c.targetCache, c.userCache, event)
}
func CallIbex(ctx *ctx.Context, id int64, host string,
taskTplCache *memsto.TaskTplCache, targetCache *memsto.TargetCacheType,
userCache *memsto.UserCacheType, event *models.AlertCurEvent) {
tpl := taskTplCache.Get(id)
if tpl == nil {
logger.Errorf("event_callback_ibex: no such tpl(%d)", id)
return
}
// check perm
// tpl.GroupId - host - account 三元组校验权限
can, err := canDoIbex(tpl.UpdateBy, tpl, host, targetCache, userCache)
if err != nil {
logger.Errorf("event_callback_ibex: check perm fail: %v", err)
return
}
if !can {
logger.Errorf("event_callback_ibex: user(%s) no permission", tpl.UpdateBy)
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 := models.TaskForm{
Title: tpl.Title + " FH: " + host,
Account: tpl.Account,
Batch: tpl.Batch,
Tolerance: tpl.Tolerance,
Timeout: tpl.Timeout,
Pause: tpl.Pause,
Script: tpl.Script,
Args: tpl.Args,
Stdin: string(tags),
Action: "start",
Creator: tpl.UpdateBy,
Hosts: []string{host},
AlertTriggered: true,
}
id, err = TaskAdd(in, tpl.UpdateBy, ctx.IsCenter)
if err != nil {
logger.Errorf("event_callback_ibex: call ibex fail: %v", err)
return
}
// write db
record := models.TaskRecord{
Id: id,
EventId: event.Id,
GroupId: tpl.GroupId,
Title: in.Title,
Account: in.Account,
Batch: in.Batch,
Tolerance: in.Tolerance,
Timeout: in.Timeout,
Pause: in.Pause,
Script: in.Script,
Args: in.Args,
CreateAt: time.Now().Unix(),
CreateBy: in.Creator,
}
if err = record.Add(ctx); err != nil {
logger.Errorf("event_callback_ibex: persist task_record fail: %v", err)
}
}
func canDoIbex(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
}
target, has := targetCache.Get(host)
if !has {
return false, nil
}
return target.GroupId == tpl.GroupId, nil
}
func TaskAdd(f models.TaskForm, authUser string, isCenter bool) (int64, error) {
hosts := cleanHosts(f.Hosts)
if len(hosts) == 0 {
return 0, fmt.Errorf("arg(hosts) empty")
}
taskMeta := &imodels.TaskMeta{
Title: f.Title,
Account: f.Account,
Batch: f.Batch,
Tolerance: f.Tolerance,
Timeout: f.Timeout,
Pause: f.Pause,
Script: f.Script,
Args: f.Args,
Stdin: f.Stdin,
Creator: f.Creator,
}
err := taskMeta.CleanFields()
if err != nil {
return 0, err
}
taskMeta.HandleFH(hosts[0])
// 任务类型分为"告警规则触发"和"n9e center用户下发"两种;
// 边缘机房"告警规则触发"的任务不需要规划并且它可能是失联的无法使用db资源所以放入redis缓存中直接下发给agentd执行
if !isCenter && f.AlertTriggered {
if err := taskMeta.Create(); err != nil {
// 当网络不连通时生成唯一的id防止边缘机房中不同任务的id相同
// 方法是redis自增id去防止同一个机房的不同n9e edge生成的id相同
// 但没法防止不同边缘机房生成同样的id所以生成id的数据不会上报存入数据库只用于闭环执行。
taskMeta.Id, err = storage.IdGet()
if err != nil {
return 0, err
}
}
taskHost := imodels.TaskHost{
Id: taskMeta.Id,
Host: hosts[0],
Status: "running",
}
if err = taskHost.Create(); err != nil {
logger.Warningf("task_add_fail: authUser=%s title=%s err=%s", authUser, taskMeta.Title, err.Error())
}
// 缓存任务元信息和待下发的任务
err = taskMeta.Cache(hosts[0])
if err != nil {
return 0, err
}
} else {
// 如果是中心机房,还是保持之前的逻辑
err = taskMeta.Save(hosts, f.Action)
if err != nil {
return 0, err
}
}
logger.Infof("task_add_succ: authUser=%s title=%s", authUser, taskMeta.Title)
return taskMeta.Id, nil
}
func cleanHosts(formHosts []string) []string {
cnt := len(formHosts)
arr := make([]string, 0, cnt)
for i := 0; i < cnt; i++ {
item := strings.TrimSpace(formHosts[i])
if item == "" {
continue
}
if strings.HasPrefix(item, "#") {
continue
}
arr = append(arr, item)
}
return arr
}

65
alert/sender/lark.go Normal file
View File

@@ -0,0 +1,65 @@
package sender
import (
"html/template"
"strings"
"github.com/ccfos/nightingale/v6/models"
)
var (
_ CallBacker = (*LarkSender)(nil)
)
type LarkSender struct {
tpl *template.Template
}
func (lk *LarkSender) CallBack(ctx CallBackContext) {
if len(ctx.Events) == 0 || len(ctx.CallBackURL) == 0 {
return
}
body := feishu{
Msgtype: "text",
Content: feishuContent{
Text: BuildTplMessage(models.Lark, lk.tpl, ctx.Events),
},
}
doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
ctx.Stats, ctx.Events[0])
ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
}
func (lk *LarkSender) Send(ctx MessageContext) {
if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
return
}
urls := lk.extract(ctx.Users)
message := BuildTplMessage(models.Lark, lk.tpl, ctx.Events)
for _, url := range urls {
body := feishu{
Msgtype: "text",
Content: feishuContent{
Text: message,
},
}
doSend(url, body, models.Lark, ctx.Stats)
}
}
func (lk *LarkSender) extract(users []*models.User) []string {
urls := make([]string, 0, len(users))
for _, user := range users {
if token, has := user.ExtractToken(models.Lark); has {
url := token
if !strings.HasPrefix(token, "https://") && !strings.HasPrefix(token, "http://") {
url = "https://open.larksuite.com/open-apis/bot/v2/hook/" + token
}
urls = append(urls, url)
}
}
return urls
}

99
alert/sender/larkcard.go Normal file
View File

@@ -0,0 +1,99 @@
package sender
import (
"fmt"
"html/template"
"net/url"
"strings"
"github.com/ccfos/nightingale/v6/models"
)
type LarkCardSender struct {
tpl *template.Template
}
func (fs *LarkCardSender) CallBack(ctx CallBackContext) {
if len(ctx.Events) == 0 || len(ctx.CallBackURL) == 0 {
return
}
ats := ExtractAtsParams(ctx.CallBackURL)
message := BuildTplMessage(models.LarkCard, fs.tpl, ctx.Events)
if len(ats) > 0 {
atTags := ""
for _, at := range ats {
if strings.Contains(at, "@") {
atTags += fmt.Sprintf("<at email=\"%s\" ></at>", at)
} else {
atTags += fmt.Sprintf("<at id=\"%s\" ></at>", at)
}
}
message = atTags + message
}
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
// This is to be compatible with the Larkcard interface, if with query string parameters, the request will fail
// Remove query parameters from the URL,
parsedURL, err := url.Parse(ctx.CallBackURL)
if err != nil {
return
}
parsedURL.RawQuery = ""
doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
ctx.Stats, ctx.Events[0])
}
func (fs *LarkCardSender) Send(ctx MessageContext) {
if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
return
}
urls, _ := fs.extract(ctx.Users)
message := BuildTplMessage(models.LarkCard, 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.LarkCard, ctx.Stats)
}
}
func (fs *LarkCardSender) 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.Lark); has {
url := token
if !strings.HasPrefix(token, "https://") && !strings.HasPrefix(token, "http://") {
url = "https://open.larksuite.com/open-apis/bot/v2/hook/" + strings.TrimSpace(token)
}
urls = append(urls, url)
}
}
return urls, ats
}

View File

@@ -7,6 +7,7 @@ import (
"github.com/ccfos/nightingale/v6/alert/astats"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/toolkits/pkg/logger"
)
@@ -38,11 +39,26 @@ func (ms *MmSender) Send(ctx MessageContext) {
}
message := BuildTplMessage(models.Mm, ms.tpl, ctx.Events)
SendMM(MatterMostMessage{
SendMM(ctx.Ctx, MatterMostMessage{
Text: message,
Tokens: urls,
Stats: ctx.Stats,
})
}, ctx.Events[0])
}
func (ms *MmSender) CallBack(ctx CallBackContext) {
if len(ctx.Events) == 0 || len(ctx.CallBackURL) == 0 {
return
}
message := BuildTplMessage(models.Mm, ms.tpl, ctx.Events)
SendMM(ctx.Ctx, MatterMostMessage{
Text: message,
Tokens: []string{ctx.CallBackURL},
Stats: ctx.Stats,
}, ctx.Events[0])
ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
}
func (ms *MmSender) extract(users []*models.User) []string {
@@ -55,7 +71,7 @@ func (ms *MmSender) extract(users []*models.User) []string {
return tokens
}
func SendMM(message MatterMostMessage) {
func SendMM(ctx *ctx.Context, message MatterMostMessage, event *models.AlertCurEvent) {
for i := 0; i < len(message.Tokens); i++ {
u, err := url.Parse(message.Tokens[i])
if err != nil {
@@ -88,7 +104,7 @@ func SendMM(message MatterMostMessage) {
Username: username,
Text: txt + message.Text,
}
doSend(ur, body, models.Mm, message.Stats)
doSendAndRecord(ctx, ur, message.Tokens[i], body, models.Mm, message.Stats, event)
}
}
}

View File

@@ -2,26 +2,30 @@ package sender
import (
"bytes"
"fmt"
"os"
"os/exec"
"time"
"github.com/ccfos/nightingale/v6/alert/astats"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/toolkits/pkg/file"
"github.com/toolkits/pkg/logger"
"github.com/toolkits/pkg/sys"
)
func MayPluginNotify(noticeBytes []byte, notifyScript models.NotifyScript, stats *astats.Stats) {
func MayPluginNotify(ctx *ctx.Context, noticeBytes []byte, notifyScript models.NotifyScript,
stats *astats.Stats, event *models.AlertCurEvent) {
if len(noticeBytes) == 0 {
return
}
alertingCallScript(noticeBytes, notifyScript, stats)
alertingCallScript(ctx, noticeBytes, notifyScript, stats, event)
}
func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript, stats *astats.Stats) {
func alertingCallScript(ctx *ctx.Context, stdinBytes []byte, notifyScript models.NotifyScript,
stats *astats.Stats, event *models.AlertCurEvent) {
// not enable or no notify.py? do nothing
config := notifyScript
if !config.Enable || config.Content == "" {
@@ -81,6 +85,7 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript, sta
}
err, isTimeout := sys.WrapTimeout(cmd, time.Duration(config.Timeout)*time.Second)
NotifyRecord(ctx, event, channel, cmd.String(), "", buildErr(err, isTimeout))
if isTimeout {
if err == nil {
@@ -102,3 +107,11 @@ func alertingCallScript(stdinBytes []byte, notifyScript models.NotifyScript, sta
logger.Infof("event_script_notify_ok: exec %s output: %s", fpath, buf.String())
}
func buildErr(err error, isTimeout bool) error {
if err == nil && !isTimeout {
return nil
} else {
return fmt.Errorf("is_timeout: %v, err: %v", isTimeout, err)
}
}

View File

@@ -8,6 +8,7 @@ import (
"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"
)
type (
@@ -22,6 +23,7 @@ type (
Rule *models.AlertRule
Events []*models.AlertCurEvent
Stats *astats.Stats
Ctx *ctx.Context
}
)
@@ -41,17 +43,23 @@ func NewSender(key string, tpls map[string]*template.Template, smtp ...aconf.SMT
return &MmSender{tpl: tpls[models.Mm]}
case models.Telegram:
return &TelegramSender{tpl: tpls[models.Telegram]}
case models.Lark:
return &LarkSender{tpl: tpls[models.Lark]}
case models.LarkCard:
return &LarkCardSender{tpl: tpls[models.LarkCard]}
}
return nil
}
func BuildMessageContext(rule *models.AlertRule, events []*models.AlertCurEvent, uids []int64, userCache *memsto.UserCacheType, stats *astats.Stats) MessageContext {
func BuildMessageContext(ctx *ctx.Context, rule *models.AlertRule, events []*models.AlertCurEvent,
uids []int64, userCache *memsto.UserCacheType, stats *astats.Stats) MessageContext {
users := userCache.GetByUserIds(uids)
return MessageContext{
Rule: rule,
Events: events,
Users: users,
Stats: stats,
Ctx: ctx,
}
}

View File

@@ -6,6 +6,7 @@ import (
"github.com/ccfos/nightingale/v6/alert/astats"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/toolkits/pkg/logger"
)
@@ -21,10 +22,29 @@ type telegram struct {
Text string `json:"text"`
}
var (
_ CallBacker = (*TelegramSender)(nil)
)
type TelegramSender struct {
tpl *template.Template
}
func (ts *TelegramSender) CallBack(ctx CallBackContext) {
if len(ctx.Events) == 0 || len(ctx.CallBackURL) == 0 {
return
}
message := BuildTplMessage(models.Telegram, ts.tpl, ctx.Events)
SendTelegram(ctx.Ctx, TelegramMessage{
Text: message,
Tokens: []string{ctx.CallBackURL},
Stats: ctx.Stats,
}, ctx.Events[0])
ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
}
func (ts *TelegramSender) Send(ctx MessageContext) {
if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
return
@@ -32,11 +52,11 @@ func (ts *TelegramSender) Send(ctx MessageContext) {
tokens := ts.extract(ctx.Users)
message := BuildTplMessage(models.Telegram, ts.tpl, ctx.Events)
SendTelegram(TelegramMessage{
SendTelegram(ctx.Ctx, TelegramMessage{
Text: message,
Tokens: tokens,
Stats: ctx.Stats,
})
}, ctx.Events[0])
}
func (ts *TelegramSender) extract(users []*models.User) []string {
@@ -49,7 +69,7 @@ func (ts *TelegramSender) extract(users []*models.User) []string {
return tokens
}
func SendTelegram(message TelegramMessage) {
func SendTelegram(ctx *ctx.Context, message TelegramMessage, event *models.AlertCurEvent) {
for i := 0; i < len(message.Tokens); i++ {
if !strings.Contains(message.Tokens[i], "/") && !strings.HasPrefix(message.Tokens[i], "https://") {
logger.Errorf("telegram_sender: result=fail invalid token=%s", message.Tokens[i])
@@ -73,6 +93,6 @@ func SendTelegram(message TelegramMessage) {
Text: message.Text,
}
doSend(url, body, models.Telegram, message.Stats)
doSendAndRecord(ctx, url, message.Tokens[i], body, models.Telegram, message.Stats, event)
}
}

View File

@@ -2,70 +2,184 @@ package sender
import (
"bytes"
"crypto/tls"
"encoding/json"
"fmt"
"io"
"net/http"
"sync"
"time"
"github.com/ccfos/nightingale/v6/alert/astats"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/toolkits/pkg/logger"
)
func SendWebhooks(webhooks []*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
for _, conf := range webhooks {
if conf.Url == "" || !conf.Enable {
continue
}
bs, err := json.Marshal(event)
if err != nil {
continue
}
func sendWebhook(webhook *models.Webhook, event interface{}, stats *astats.Stats) (bool, string, error) {
channel := "webhook"
if webhook.Type == models.RuleCallback {
channel = "callback"
}
bf := bytes.NewBuffer(bs)
conf := webhook
if conf.Url == "" || !conf.Enable {
return false, "", nil
}
bs, err := json.Marshal(event)
if err != nil {
logger.Errorf("%s alertingWebhook failed to marshal event:%+v err:%v", channel, event, err)
return false, "", err
}
req, err := http.NewRequest("POST", conf.Url, bf)
if err != nil {
logger.Warning("alertingWebhook failed to new request", err)
continue
}
bf := bytes.NewBuffer(bs)
req.Header.Set("Content-Type", "application/json")
if conf.BasicAuthUser != "" && conf.BasicAuthPass != "" {
req.SetBasicAuth(conf.BasicAuthUser, conf.BasicAuthPass)
}
req, err := http.NewRequest("POST", conf.Url, bf)
if err != nil {
logger.Warningf("%s alertingWebhook failed to new reques event:%s err:%v", channel, string(bs), err)
return true, "", err
}
if len(conf.Headers) > 0 && len(conf.Headers)%2 == 0 {
for i := 0; i < len(conf.Headers); i += 2 {
if conf.Headers[i] == "host" || conf.Headers[i] == "Host" {
req.Host = conf.Headers[i+1]
continue
}
req.Header.Set(conf.Headers[i], conf.Headers[i+1])
req.Header.Set("Content-Type", "application/json")
if conf.BasicAuthUser != "" && conf.BasicAuthPass != "" {
req.SetBasicAuth(conf.BasicAuthUser, conf.BasicAuthPass)
}
if len(conf.Headers) > 0 && len(conf.Headers)%2 == 0 {
for i := 0; i < len(conf.Headers); i += 2 {
if conf.Headers[i] == "host" || conf.Headers[i] == "Host" {
req.Host = conf.Headers[i+1]
continue
}
req.Header.Set(conf.Headers[i], conf.Headers[i+1])
}
}
insecureSkipVerify := false
if webhook != nil {
insecureSkipVerify = webhook.SkipVerify
}
client := http.Client{
Timeout: time.Duration(conf.Timeout) * time.Second,
Transport: &http.Transport{
TLSClientConfig: &tls.Config{InsecureSkipVerify: insecureSkipVerify},
},
}
// todo add skip verify
client := http.Client{
Timeout: time.Duration(conf.Timeout) * time.Second,
stats.AlertNotifyTotal.WithLabelValues(channel).Inc()
var resp *http.Response
var body []byte
resp, err = client.Do(req)
if err != nil {
stats.AlertNotifyErrorTotal.WithLabelValues(channel).Inc()
logger.Errorf("event_%s_fail, event:%s, url: [%s], error: [%s]", channel, string(bs), conf.Url, err)
return true, "", err
}
if resp.Body != nil {
defer resp.Body.Close()
body, _ = io.ReadAll(resp.Body)
}
if resp.StatusCode == 429 {
logger.Errorf("event_%s_fail, url: %s, response code: %d, body: %s event:%s", channel, conf.Url, resp.StatusCode, string(body), string(bs))
return true, string(body), fmt.Errorf("status code is 429")
}
logger.Debugf("event_%s_succ, url: %s, response code: %d, body: %s event:%s", channel, conf.Url, resp.StatusCode, string(body), string(bs))
return false, string(body), nil
}
func SingleSendWebhooks(ctx *ctx.Context, webhooks []*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
for _, conf := range webhooks {
retryCount := 0
for retryCount < 3 {
needRetry, res, err := sendWebhook(conf, event, stats)
NotifyRecord(ctx, event, "webhook", conf.Url, res, err)
if !needRetry {
break
}
retryCount++
time.Sleep(time.Minute * 1 * time.Duration(retryCount))
}
stats.AlertNotifyTotal.WithLabelValues("webhook").Inc()
var resp *http.Response
resp, err = client.Do(req)
if err != nil {
stats.AlertNotifyErrorTotal.WithLabelValues("webhook").Inc()
logger.Errorf("event_webhook_fail, ruleId: [%d], eventId: [%d], url: [%s], error: [%s]", event.RuleId, event.Id, conf.Url, err)
continue
}
var body []byte
if resp.Body != nil {
defer resp.Body.Close()
body, _ = io.ReadAll(resp.Body)
}
logger.Debugf("event_webhook_succ, url: %s, response code: %d, body: %s event:%+v", conf.Url, resp.StatusCode, string(body), event)
}
}
func BatchSendWebhooks(ctx *ctx.Context, webhooks []*models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
for _, conf := range webhooks {
logger.Infof("push event:%+v to queue:%v", event, conf)
PushEvent(ctx, conf, event, stats)
}
}
var EventQueue = make(map[string]*WebhookQueue)
var CallbackEventQueue = make(map[string]*WebhookQueue)
var CallbackEventQueueLock sync.RWMutex
var EventQueueLock sync.RWMutex
const QueueMaxSize = 100000
type WebhookQueue struct {
list *SafeListLimited
closeCh chan struct{}
}
func PushEvent(ctx *ctx.Context, webhook *models.Webhook, event *models.AlertCurEvent, stats *astats.Stats) {
EventQueueLock.RLock()
queue := EventQueue[webhook.Url]
EventQueueLock.RUnlock()
if queue == nil {
queue = &WebhookQueue{
list: NewSafeListLimited(QueueMaxSize),
closeCh: make(chan struct{}),
}
EventQueueLock.Lock()
EventQueue[webhook.Url] = queue
EventQueueLock.Unlock()
StartConsumer(ctx, queue, webhook.Batch, webhook, stats)
}
succ := queue.list.PushFront(event)
if !succ {
stats.AlertNotifyErrorTotal.WithLabelValues("push_event_queue").Inc()
logger.Warningf("Write channel(%s) full, current channel size: %d event:%v", webhook.Url, queue.list.Len(), event)
}
}
func StartConsumer(ctx *ctx.Context, queue *WebhookQueue, popSize int, webhook *models.Webhook, stats *astats.Stats) {
for {
select {
case <-queue.closeCh:
logger.Infof("event queue:%v closed", queue)
return
default:
events := queue.list.PopBack(popSize)
if len(events) == 0 {
time.Sleep(time.Millisecond * 400)
continue
}
retryCount := 0
for retryCount < webhook.RetryCount {
needRetry, res, err := sendWebhook(webhook, events, stats)
if !needRetry {
break
}
go RecordEvents(ctx, webhook, events, stats, res, err)
retryCount++
time.Sleep(time.Second * time.Duration(webhook.RetryInterval) * time.Duration(retryCount))
}
}
}
}
func RecordEvents(ctx *ctx.Context, webhook *models.Webhook, events []*models.AlertCurEvent, stats *astats.Stats, res string, err error) {
for _, event := range events {
time.Sleep(time.Millisecond * 10)
NotifyRecord(ctx, event, "webhook", webhook.Url, res, err)
}
}

View File

@@ -0,0 +1,111 @@
package sender
import (
"container/list"
"sync"
"github.com/ccfos/nightingale/v6/models"
)
type SafeList struct {
sync.RWMutex
L *list.List
}
func NewSafeList() *SafeList {
return &SafeList{L: list.New()}
}
func (sl *SafeList) PushFront(v interface{}) *list.Element {
sl.Lock()
e := sl.L.PushFront(v)
sl.Unlock()
return e
}
func (sl *SafeList) PushFrontBatch(vs []interface{}) {
sl.Lock()
for _, item := range vs {
sl.L.PushFront(item)
}
sl.Unlock()
}
func (sl *SafeList) PopBack(max int) []*models.AlertCurEvent {
sl.Lock()
count := sl.L.Len()
if count == 0 {
sl.Unlock()
return []*models.AlertCurEvent{}
}
if count > max {
count = max
}
items := make([]*models.AlertCurEvent, 0, count)
for i := 0; i < count; i++ {
item := sl.L.Remove(sl.L.Back())
sample, ok := item.(*models.AlertCurEvent)
if ok {
items = append(items, sample)
}
}
sl.Unlock()
return items
}
func (sl *SafeList) RemoveAll() {
sl.Lock()
sl.L.Init()
sl.Unlock()
}
func (sl *SafeList) Len() int {
sl.RLock()
size := sl.L.Len()
sl.RUnlock()
return size
}
// SafeList with Limited Size
type SafeListLimited struct {
maxSize int
SL *SafeList
}
func NewSafeListLimited(maxSize int) *SafeListLimited {
return &SafeListLimited{SL: NewSafeList(), maxSize: maxSize}
}
func (sll *SafeListLimited) PopBack(max int) []*models.AlertCurEvent {
return sll.SL.PopBack(max)
}
func (sll *SafeListLimited) PushFront(v interface{}) bool {
if sll.SL.Len() >= sll.maxSize {
return false
}
sll.SL.PushFront(v)
return true
}
func (sll *SafeListLimited) PushFrontBatch(vs []interface{}) bool {
if sll.SL.Len() >= sll.maxSize {
return false
}
sll.SL.PushFrontBatch(vs)
return true
}
func (sll *SafeListLimited) RemoveAll() {
sll.SL.RemoveAll()
}
func (sll *SafeListLimited) Len() int {
return sll.SL.Len()
}

View File

@@ -16,29 +16,52 @@ type wecom struct {
Markdown wecomMarkdown `json:"markdown"`
}
var (
_ CallBacker = (*WecomSender)(nil)
)
type WecomSender struct {
tpl *template.Template
}
func (ws *WecomSender) CallBack(ctx CallBackContext) {
if len(ctx.Events) == 0 || len(ctx.CallBackURL) == 0 {
return
}
message := BuildTplMessage(models.Wecom, ws.tpl, ctx.Events)
body := wecom{
Msgtype: "markdown",
Markdown: wecomMarkdown{
Content: message,
},
}
doSendAndRecord(ctx.Ctx, ctx.CallBackURL, ctx.CallBackURL, body, "callback",
ctx.Stats, ctx.Events[0])
ctx.Stats.AlertNotifyTotal.WithLabelValues("rule_callback").Inc()
}
func (ws *WecomSender) Send(ctx MessageContext) {
if len(ctx.Users) == 0 || len(ctx.Events) == 0 {
return
}
urls := ws.extract(ctx.Users)
urls, tokens := ws.extract(ctx.Users)
message := BuildTplMessage(models.Wecom, ws.tpl, ctx.Events)
for _, url := range urls {
for i, url := range urls {
body := wecom{
Msgtype: "markdown",
Markdown: wecomMarkdown{
Content: message,
},
}
doSend(url, body, models.Wecom, ctx.Stats)
doSendAndRecord(ctx.Ctx, url, tokens[i], body, models.Wecom, ctx.Stats, ctx.Events[0])
}
}
func (ws *WecomSender) extract(users []*models.User) []string {
func (ws *WecomSender) extract(users []*models.User) ([]string, []string) {
urls := make([]string, 0, len(users))
tokens := make([]string, 0, len(users))
for _, user := range users {
if token, has := user.ExtractToken(models.Wecom); has {
url := token
@@ -46,7 +69,8 @@ func (ws *WecomSender) extract(users []*models.User) []string {
url = "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=" + token
}
urls = append(urls, url)
tokens = append(tokens, token)
}
}
return urls
return urls, tokens
}

View File

@@ -13,6 +13,7 @@ type Center struct {
UseFileAssets bool
FlashDuty FlashDuty
EventHistoryGroupView bool
CleanNotifyRecordDay int
}
type Plugin struct {

View File

@@ -18,20 +18,28 @@ var MetricDesc MetricDescType
// GetMetricDesc , if metric is not registered, empty string will be returned
func GetMetricDesc(lang, metric string) string {
var m map[string]string
if lang == "zh" {
m = MetricDesc.Zh
} else {
switch lang {
case "en":
m = MetricDesc.En
default:
m = MetricDesc.Zh
}
if m != nil {
if desc, has := m[metric]; has {
if desc, ok := m[metric]; ok {
return desc
}
}
return MetricDesc.CommonDesc[metric]
}
if MetricDesc.CommonDesc != nil {
if desc, ok := MetricDesc.CommonDesc[metric]; ok {
return desc
}
}
return ""
}
func LoadMetricsYaml(configDir, metricsYamlFile string) error {
fp := metricsYamlFile
if fp == "" {

View File

@@ -76,6 +76,9 @@ ops:
- "/dashboards/add"
- "/dashboards/put"
- "/dashboards/del"
- "/embedded-dashboards/put"
- "/embedded-dashboards"
- "/public-dashboards"
- name: alert
cname: 告警规则

View File

@@ -16,6 +16,7 @@ import (
centerrt "github.com/ccfos/nightingale/v6/center/router"
"github.com/ccfos/nightingale/v6/center/sso"
"github.com/ccfos/nightingale/v6/conf"
"github.com/ccfos/nightingale/v6/cron"
"github.com/ccfos/nightingale/v6/dumper"
"github.com/ccfos/nightingale/v6/memsto"
"github.com/ccfos/nightingale/v6/models"
@@ -106,8 +107,10 @@ func Initialize(configDir string, cryptoKey string) (func(), error) {
go version.GetGithubVersion()
go cron.CleanNotifyRecord(ctx, config.Center.CleanNotifyRecordDay)
alertrtRouter := alertrt.New(config.HTTP, config.Alert, alertMuteCache, targetCache, busiGroupCache, alertStats, ctx, externalProcessors)
centerRouter := centerrt.New(config.HTTP, config.Center, config.Alert, cconf.Operations, dsCache, notifyConfigCache, promClients, tdengineClients,
centerRouter := centerrt.New(config.HTTP, config.Center, config.Alert, config.Ibex, cconf.Operations, dsCache, notifyConfigCache, promClients, tdengineClients,
redis, sso, ctx, metas, idents, targetCache, userCache, userGroupCache)
pushgwRouter := pushgwrt.New(config.HTTP, config.Pushgw, config.Alert, targetCache, busiGroupCache, idents, metas, writers, ctx)

View File

@@ -4,15 +4,17 @@ import (
"encoding/json"
"path"
"strings"
"time"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/toolkits/pkg/file"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/logger"
"github.com/toolkits/pkg/runner"
)
const SYSTEM = "system"
func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
fp := builtinIntegrationsDir
if fp == "" {
@@ -21,7 +23,10 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
// var fileList []string
dirList, err := file.DirsUnder(fp)
ginx.Dangerous(err)
if err != nil {
logger.Warning("read builtin component dir fail ", err)
return
}
for _, dir := range dirList {
// components icon
@@ -58,11 +63,47 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
exists, _ := models.BuiltinComponentExists(ctx, &component)
if !exists {
err = component.Add(ctx, "system")
err = component.Add(ctx, SYSTEM)
if err != nil {
logger.Warning("add builtin component fail ", component, err)
continue
}
} else {
old, err := models.BuiltinComponentGet(ctx, "ident = ?", component.Ident)
if err != nil {
logger.Warning("get builtin component fail ", component, err)
continue
}
if old == nil {
logger.Warning("get builtin component nil ", component)
continue
}
if old.UpdatedBy == SYSTEM {
now := time.Now().Unix()
old.CreatedAt = now
old.UpdatedAt = now
old.Readme = component.Readme
old.UpdatedBy = SYSTEM
err = models.DB(ctx).Model(old).Select("*").Updates(old).Error
if err != nil {
logger.Warning("update builtin component fail ", old, err)
}
}
}
// delete uuid is emtpy
err = models.DB(ctx).Exec("delete from builtin_payloads where uuid = 0 and type != 'collect' and (updated_by = 'system' or updated_by = '')").Error
if err != nil {
logger.Warning("delete builtin payloads fail ", err)
}
// delete builtin metrics uuid is emtpy
err = models.DB(ctx).Exec("delete from builtin_metrics where uuid = 0 and (updated_by = 'system' or updated_by = '')").Error
if err != nil {
logger.Warning("delete builtin metrics fail ", err)
}
// alerts
@@ -83,7 +124,15 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
continue
}
newAlerts := []models.AlertRule{}
writeAlertFileFlag := false
for _, alert := range alerts {
if alert.UUID == 0 {
writeAlertFileFlag = true
alert.UUID = time.Now().UnixNano()
}
newAlerts = append(newAlerts, alert)
content, err := json.Marshal(alert)
if err != nil {
logger.Warning("marshal builtin alert fail ", alert, err)
@@ -98,40 +147,47 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
Name: alert.Name,
Tags: alert.AppendTags,
Content: string(content),
UUID: alert.UUID,
}
exists, err := models.BuiltinPayloadExists(ctx, &builtinAlert)
old, err := models.BuiltinPayloadGet(ctx, "uuid = ?", alert.UUID)
if err != nil {
logger.Warning("check builtin alert exists fail ", builtinAlert, err)
logger.Warning("get builtin alert fail ", builtinAlert, err)
continue
}
if exists {
old, err := models.BuiltinPayloadGet(ctx, "type = ? AND component = ? AND name = ? AND cate = ?", builtinAlert.Type, builtinAlert.Component, builtinAlert.Name, builtinAlert.Cate)
if old == nil {
err := builtinAlert.Add(ctx, SYSTEM)
if err != nil {
logger.Warning("get builtin alert fail ", builtinAlert, err)
continue
}
if old.CreatedAt != old.UpdatedAt {
// 模板已经被修改过,不再更新
continue
}
// 先删除旧的 再添加新的
err = models.BuiltinPayloadDels(ctx, []int64{old.ID})
if err != nil {
logger.Warning("delete old builtin alert fail ", old, err)
continue
logger.Warning("add builtin alert fail ", builtinAlert, err)
}
continue
}
err = builtinAlert.Add(ctx, "system")
if err != nil {
logger.Warningf("add builtin alert:%+v fail %v", builtinAlert, err)
continue
if old.UpdatedBy == SYSTEM {
old.Content = string(content)
old.Name = alert.Name
old.Tags = alert.AppendTags
err = models.DB(ctx).Model(old).Select("*").Updates(old).Error
if err != nil {
logger.Warningf("update builtin alert:%+v fail %v", builtinAlert, err)
}
}
}
if writeAlertFileFlag {
bs, err = json.MarshalIndent(newAlerts, "", " ")
if err != nil {
logger.Warning("marshal builtin alerts fail ", newAlerts, err)
continue
}
_, err = file.WriteBytes(fp, bs)
if err != nil {
logger.Warning("write builtin alerts file fail ", f, err)
}
}
}
}
@@ -153,6 +209,21 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
continue
}
if dashboard.UUID == 0 {
dashboard.UUID = time.Now().UnixNano()
// 补全文件中的 uuid
bs, err = json.MarshalIndent(dashboard, "", " ")
if err != nil {
logger.Warning("marshal builtin dashboard fail ", dashboard, err)
continue
}
_, err = file.WriteBytes(fp, bs)
if err != nil {
logger.Warning("write builtin dashboard file fail ", f, err)
}
}
content, err := json.Marshal(dashboard)
if err != nil {
logger.Warning("marshal builtin dashboard fail ", dashboard, err)
@@ -166,38 +237,31 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
Name: dashboard.Name,
Tags: dashboard.Tags,
Content: string(content),
UUID: dashboard.UUID,
}
exists, err := models.BuiltinPayloadExists(ctx, &builtinDashboard)
old, err := models.BuiltinPayloadGet(ctx, "uuid = ?", dashboard.UUID)
if err != nil {
logger.Warning("check builtin dashboard exists fail ", builtinDashboard, err)
logger.Warning("get builtin alert fail ", builtinDashboard, err)
continue
}
if exists {
old, err := models.BuiltinPayloadGet(ctx, "type = ? AND component = ? AND name = ? AND cate = ?", builtinDashboard.Type, builtinDashboard.Component, builtinDashboard.Name, builtinDashboard.Cate)
if old == nil {
err := builtinDashboard.Add(ctx, SYSTEM)
if err != nil {
logger.Warning("get builtin dashboard fail ", builtinDashboard, err)
continue
}
if old.CreatedAt != old.UpdatedAt {
// 模板已经被修改过,不再更新
continue
}
// delete old
err = models.BuiltinPayloadDels(ctx, []int64{old.ID})
if err != nil {
logger.Warning("delete old builtin dashboard fail ", old, err)
continue
logger.Warning("add builtin alert fail ", builtinDashboard, err)
}
continue
}
err = builtinDashboard.Add(ctx, "system")
if err != nil {
logger.Warning("add builtin dashboard fail ", builtinDashboard, err)
continue
if old.UpdatedBy == SYSTEM {
old.Content = string(content)
old.Name = dashboard.Name
old.Tags = dashboard.Tags
err = models.DB(ctx).Model(old).Select("*").Updates(old).Error
if err != nil {
logger.Warningf("update builtin alert:%+v fail %v", builtinDashboard, err)
}
}
}
} else if err != nil {
@@ -216,40 +280,64 @@ func Init(ctx *ctx.Context, builtinIntegrationsDir string) {
}
metrics := []models.BuiltinMetric{}
newMetrics := []models.BuiltinMetric{}
err = json.Unmarshal(bs, &metrics)
if err != nil {
logger.Warning("parse builtin component metrics file fail", f, err)
continue
}
writeMetricFileFlag := false
for _, metric := range metrics {
exists, err := models.BuiltinMetricExists(ctx, &metric)
if metric.UUID == 0 {
writeMetricFileFlag = true
metric.UUID = time.Now().UnixNano()
}
newMetrics = append(newMetrics, metric)
old, err := models.BuiltinMetricGet(ctx, "uuid = ?", metric.UUID)
if err != nil {
logger.Warning("check builtin metric exists fail", metric, err)
logger.Warning("get builtin metrics fail ", metric, err)
continue
}
if exists {
old, err := models.BuiltinMetricGet(ctx, "lang = ? and collector = ? and typ = ? and name = ?", metric.Lang, metric.Collector, metric.Typ, metric.Name)
if old == nil {
err := metric.Add(ctx, SYSTEM)
if err != nil {
logger.Warning("get builtin metric fail", metric, err)
continue
}
// delete old
err = models.BuiltinMetricDels(ctx, []int64{old.ID})
if err != nil {
logger.Warningf("delete old builtin metric fail %v %v", old, err)
continue
logger.Warning("add builtin metrics fail ", metric, err)
}
continue
}
err = metric.Add(ctx, "system")
if err != nil {
logger.Warning("add builtin metric fail", metric, err)
continue
if old.UpdatedBy == SYSTEM {
old.Collector = metric.Collector
old.Typ = metric.Typ
old.Name = metric.Name
old.Unit = metric.Unit
old.Note = metric.Note
old.Lang = metric.Lang
old.Expression = metric.Expression
err = models.DB(ctx).Model(old).Select("*").Updates(old).Error
if err != nil {
logger.Warningf("update builtin metric:%+v fail %v", metric, err)
}
}
}
if writeMetricFileFlag {
bs, err = json.MarshalIndent(newMetrics, "", " ")
if err != nil {
logger.Warning("marshal builtin metrics fail ", newMetrics, err)
continue
}
_, err = file.WriteBytes(fp, bs)
if err != nil {
logger.Warning("write builtin metrics file fail ", f, err)
}
}
}
} else if err != nil {
logger.Warningf("read builtin component metrics dir fail %s %v", component.Ident, err)
@@ -273,4 +361,5 @@ type BuiltinBoard struct {
Bgids []int64 `json:"bgids" gorm:"-"`
BuiltIn int `json:"built_in"` // 0: false, 1: true
Hide int `json:"hide"` // 0: false, 1: true
UUID int64 `json:"uuid"`
}

View File

@@ -13,6 +13,7 @@ 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/conf"
_ "github.com/ccfos/nightingale/v6/front/statik"
"github.com/ccfos/nightingale/v6/memsto"
"github.com/ccfos/nightingale/v6/pkg/aop"
@@ -34,6 +35,7 @@ import (
type Router struct {
HTTP httpx.Config
Center cconf.Center
Ibex conf.Ibex
Alert aconf.Alert
Operations cconf.Operation
DatasourceCache *memsto.DatasourceCacheType
@@ -48,13 +50,15 @@ type Router struct {
UserCache *memsto.UserCacheType
UserGroupCache *memsto.UserGroupCacheType
Ctx *ctx.Context
HeartbeatHook HeartbeatHookFunc
}
func New(httpConfig httpx.Config, center cconf.Center, alert aconf.Alert, operations cconf.Operation, ds *memsto.DatasourceCacheType, ncc *memsto.NotifyConfigCacheType, pc *prom.PromClientMap, tdendgineClients *tdengine.TdengineClientMap, redis storage.Redis, sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, idents *idents.Set, tc *memsto.TargetCacheType, uc *memsto.UserCacheType, ugc *memsto.UserGroupCacheType) *Router {
func New(httpConfig httpx.Config, center cconf.Center, alert aconf.Alert, ibex conf.Ibex, operations cconf.Operation, ds *memsto.DatasourceCacheType, ncc *memsto.NotifyConfigCacheType, pc *prom.PromClientMap, tdendgineClients *tdengine.TdengineClientMap, redis storage.Redis, sso *sso.SsoClient, ctx *ctx.Context, metaSet *metas.Set, idents *idents.Set, tc *memsto.TargetCacheType, uc *memsto.UserCacheType, ugc *memsto.UserGroupCacheType) *Router {
return &Router{
HTTP: httpConfig,
Center: center,
Alert: alert,
Ibex: ibex,
Operations: operations,
DatasourceCache: ds,
NotifyConfigCache: ncc,
@@ -68,6 +72,7 @@ func New(httpConfig httpx.Config, center cconf.Center, alert aconf.Alert, operat
UserCache: uc,
UserGroupCache: ugc,
Ctx: ctx,
HeartbeatHook: func(ident string) map[string]interface{} { return nil },
}
}
@@ -91,7 +96,9 @@ func languageDetector(i18NHeaderKey string) gin.HandlerFunc {
if headerKey != "" {
lang := c.GetHeader(headerKey)
if lang != "" {
if strings.HasPrefix(lang, "zh") {
if strings.HasPrefix(lang, "zh_HK") {
c.Request.Header.Set("X-Language", "zh_HK")
} else if strings.HasPrefix(lang, "zh") {
c.Request.Header.Set("X-Language", "zh_CN")
} else if strings.HasPrefix(lang, "en") {
c.Request.Header.Set("X-Language", "en")
@@ -112,7 +119,7 @@ func (rt *Router) configNoRoute(r *gin.Engine, fs *http.FileSystem) {
suffix := arr[len(arr)-1]
switch suffix {
case "png", "jpeg", "jpg", "svg", "ico", "gif", "css", "js", "html", "htm", "gz", "zip", "map", "ttf":
case "png", "jpeg", "jpg", "svg", "ico", "gif", "css", "js", "html", "htm", "gz", "zip", "map", "ttf", "md":
if !rt.Center.UseFileAssets {
c.FileFromFS(c.Request.URL.Path, *fs)
} else {
@@ -308,11 +315,15 @@ func (rt *Router) Config(r *gin.Engine) {
pages.GET("/busi-group/:id/alert-rules", rt.auth(), rt.user(), rt.perm("/alert-rules"), rt.alertRuleGets)
pages.POST("/busi-group/:id/alert-rules", rt.auth(), rt.user(), rt.perm("/alert-rules/add"), rt.bgrw(), rt.alertRuleAddByFE)
pages.POST("/busi-group/:id/alert-rules/import", rt.auth(), rt.user(), rt.perm("/alert-rules/add"), rt.bgrw(), rt.alertRuleAddByImport)
pages.POST("/busi-group/:id/alert-rules/import-prom-rule", rt.auth(),
rt.user(), rt.perm("/alert-rules/add"), rt.bgrw(), rt.alertRuleAddByImportPromRule)
pages.DELETE("/busi-group/:id/alert-rules", rt.auth(), rt.user(), rt.perm("/alert-rules/del"), rt.bgrw(), rt.alertRuleDel)
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.GET("/alert-rule/:arid/pure", rt.auth(), rt.user(), rt.perm("/alert-rules"), rt.alertRulePureGet)
pages.PUT("/busi-group/alert-rule/validate", rt.auth(), rt.user(), rt.perm("/alert-rules/put"), rt.alertRuleValidation)
pages.POST("/relabel-test", rt.auth(), rt.user(), rt.relabelTest)
pages.GET("/busi-groups/recording-rules", rt.auth(), rt.user(), rt.perm("/recording-rules"), rt.recordingRuleGetsByGids)
pages.GET("/busi-group/:id/recording-rules", rt.auth(), rt.user(), rt.perm("/recording-rules"), rt.recordingRuleGets)
@@ -341,9 +352,11 @@ func (rt *Router) Config(r *gin.Engine) {
if rt.Center.AnonymousAccess.AlertDetail {
pages.GET("/alert-cur-event/:eid", rt.alertCurEventGet)
pages.GET("/alert-his-event/:eid", rt.alertHisEventGet)
pages.GET("/event-notify-records/:eid", rt.notificationRecordList)
} else {
pages.GET("/alert-cur-event/:eid", rt.auth(), rt.user(), rt.alertCurEventGet)
pages.GET("/alert-his-event/:eid", rt.auth(), rt.user(), rt.alertHisEventGet)
pages.GET("/event-notify-records/:eid", rt.auth(), rt.user(), rt.notificationRecordList)
}
// card logic
@@ -372,8 +385,8 @@ func (rt *Router) Config(r *gin.Engine) {
pages.GET("/busi-group/:id/tasks", rt.auth(), rt.user(), rt.perm("/job-tasks"), rt.bgro(), rt.taskGets)
pages.POST("/busi-group/:id/tasks", rt.auth(), rt.user(), rt.perm("/job-tasks/add"), rt.bgrw(), rt.taskAdd)
pages.GET("/servers", rt.auth(), rt.user(), rt.perm("/help/servers"), rt.serversGet)
pages.GET("/server-clusters", rt.auth(), rt.user(), rt.perm("/help/servers"), rt.serverClustersGet)
pages.GET("/servers", rt.auth(), rt.user(), rt.serversGet)
pages.GET("/server-clusters", rt.auth(), rt.user(), rt.serverClustersGet)
pages.POST("/datasource/list", rt.auth(), rt.user(), rt.datasourceList)
pages.POST("/datasource/plugin/list", rt.auth(), rt.pluginList)
@@ -423,6 +436,9 @@ func (rt *Router) Config(r *gin.Engine) {
pages.PUT("/es-index-pattern", rt.auth(), rt.admin(), rt.esIndexPatternPut)
pages.DELETE("/es-index-pattern", rt.auth(), rt.admin(), rt.esIndexPatternDel)
pages.GET("/embedded-dashboards", rt.auth(), rt.user(), rt.perm("/embedded-dashboards"), rt.embeddedDashboardsGet)
pages.PUT("/embedded-dashboards", rt.auth(), rt.user(), rt.perm("/embedded-dashboards/put"), rt.embeddedDashboardsPut)
pages.GET("/user-variable-configs", rt.auth(), rt.user(), rt.perm("/help/variable-configs"), rt.userVariableConfigGets)
pages.POST("/user-variable-config", rt.auth(), rt.user(), rt.perm("/help/variable-configs"), rt.userVariableConfigAdd)
pages.PUT("/user-variable-config/:id", rt.auth(), rt.user(), rt.perm("/help/variable-configs"), rt.userVariableConfigPut)
@@ -539,6 +555,7 @@ func (rt *Router) Config(r *gin.Engine) {
service.GET("/targets-of-alert-rule", rt.targetsOfAlertRule)
service.POST("/notify-record", rt.notificationRecordAdd)
}
}

View File

@@ -222,6 +222,11 @@ func (rt *Router) alertCurEventGet(c *gin.Context) {
rt.bgroCheck(c, event.GroupId)
}
ruleConfig, needReset := models.FillRuleConfigTplName(rt.Ctx, event.RuleConfig)
if needReset {
event.RuleConfigJson = ruleConfig
}
ginx.NewRender(c).Data(event, nil)
}

View File

@@ -87,15 +87,27 @@ func (rt *Router) alertHisEventGet(c *gin.Context) {
rt.bgroCheck(c, event.GroupId)
}
ruleConfig, needReset := models.FillRuleConfigTplName(rt.Ctx, event.RuleConfig)
if needReset {
event.RuleConfigJson = ruleConfig
}
ginx.NewRender(c).Data(event, err)
}
func GetBusinessGroupIds(c *gin.Context, ctx *ctx.Context, eventHistoryGroupView bool) ([]int64, error) {
bgid := ginx.QueryInt64(c, "bgid", 0)
var bgids []int64
user := c.MustGet("user").(*models.User)
if !eventHistoryGroupView || user.IsAdmin() {
if !eventHistoryGroupView || strings.HasPrefix(c.Request.URL.Path, "/v1") {
if bgid > 0 {
return []int64{bgid}, nil
}
return bgids, nil
}
user := c.MustGet("user").(*models.User)
if user.IsAdmin() {
if bgid > 0 {
return []int64{bgid}, nil
}

View File

@@ -1,14 +1,19 @@
package router
import (
"encoding/json"
"fmt"
"net/http"
"strconv"
"strings"
"time"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pushgw/pconf"
"github.com/ccfos/nightingale/v6/pushgw/writer"
"github.com/gin-gonic/gin"
"github.com/prometheus/prometheus/prompb"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/i18n"
"github.com/toolkits/pkg/str"
@@ -42,7 +47,7 @@ func (rt *Router) alertRuleGetsByGids(c *gin.Context) {
ginx.Dangerous(err)
if len(gids) == 0 {
ginx.Bomb(http.StatusForbidden, "forbidden")
ginx.NewRender(c).Data([]int{}, nil)
return
}
}
@@ -121,6 +126,25 @@ func (rt *Router) alertRuleAddByImport(c *gin.Context) {
ginx.NewRender(c).Data(reterr, nil)
}
func (rt *Router) alertRuleAddByImportPromRule(c *gin.Context) {
username := c.MustGet("username").(string)
type PromRule struct {
Groups []models.PromRuleGroup `yaml:"groups"`
}
var pr PromRule
ginx.Dangerous(c.BindYAML(&pr))
if len(pr.Groups) == 0 {
ginx.Bomb(http.StatusBadRequest, "input yaml is empty")
}
lst := models.DealPromGroup(pr.Groups)
bgid := ginx.UrlParamInt64(c, "id")
err := rt.alertRuleAdd(lst, username, bgid, c.GetHeader("X-Language"))
ginx.NewRender(c).Data(err, nil)
}
func (rt *Router) alertRuleAddByService(c *gin.Context) {
var lst []models.AlertRule
ginx.BindJSON(c, &lst)
@@ -271,6 +295,32 @@ func (rt *Router) alertRulePutFields(c *gin.Context) {
continue
}
if f.Action == "annotations_add" {
if annotations, has := f.Fields["annotations"]; has {
annotationsMap := annotations.(map[string]interface{})
for k, v := range annotationsMap {
ar.AnnotationsJSON[k] = v.(string)
}
b, err := json.Marshal(ar.AnnotationsJSON)
ginx.Dangerous(err)
ginx.Dangerous(ar.UpdateFieldsMap(rt.Ctx, map[string]interface{}{"annotations": string(b)}))
continue
}
}
if f.Action == "annotations_del" {
if annotations, has := f.Fields["annotations"]; has {
annotationsKeys := annotations.(map[string]interface{})
for key := range annotationsKeys {
delete(ar.AnnotationsJSON, key)
}
b, err := json.Marshal(ar.AnnotationsJSON)
ginx.Dangerous(err)
ginx.Dangerous(ar.UpdateFieldsMap(rt.Ctx, map[string]interface{}{"annotations": string(b)}))
continue
}
}
if f.Action == "callback_add" {
// 增加一个 callback 地址
if callbacks, has := f.Fields["callbacks"]; has {
@@ -316,6 +366,20 @@ func (rt *Router) alertRuleGet(c *gin.Context) {
ginx.NewRender(c).Data(ar, err)
}
func (rt *Router) alertRulePureGet(c *gin.Context) {
arid := ginx.UrlParamInt64(c, "arid")
ar, err := models.AlertRuleGetById(rt.Ctx, arid)
ginx.Dangerous(err)
if ar == nil {
ginx.NewRender(c, http.StatusNotFound).Message("No such AlertRule")
return
}
ginx.NewRender(c).Data(ar, err)
}
// pre validation before save rule
func (rt *Router) alertRuleValidation(c *gin.Context) {
var f models.AlertRule //new
@@ -388,3 +452,50 @@ func (rt *Router) alertRuleCallbacks(c *gin.Context) {
ginx.NewRender(c).Data(callbacks, nil)
}
type alertRuleTestForm struct {
Configs []*pconf.RelabelConfig `json:"configs"`
Tags []string `json:"tags"`
}
func (rt *Router) relabelTest(c *gin.Context) {
var f alertRuleTestForm
ginx.BindJSON(c, &f)
if len(f.Tags) == 0 || len(f.Configs) == 0 {
ginx.Bomb(http.StatusBadRequest, "relabel config is empty")
}
labels := make([]prompb.Label, len(f.Tags))
for i, tag := range f.Tags {
label := strings.Split(tag, "=")
if len(label) != 2 {
ginx.Bomb(http.StatusBadRequest, "tag:%s format error", tag)
}
labels[i] = prompb.Label{Name: label[0], Value: label[1]}
}
for i := 0; i < len(f.Configs); i++ {
if f.Configs[i].Replacement == "" {
f.Configs[i].Replacement = "$1"
}
if f.Configs[i].Separator == "" {
f.Configs[i].Separator = ";"
}
if f.Configs[i].Regex == "" {
f.Configs[i].Regex = "(.*)"
}
}
relabels := writer.Process(labels, f.Configs...)
var tags []string
for _, label := range relabels {
tags = append(tags, fmt.Sprintf("%s=%s", label.Name, label.Value))
}
ginx.NewRender(c).Data(tags, nil)
}

View File

@@ -44,7 +44,7 @@ func (rt *Router) alertSubscribeGetsByGids(c *gin.Context) {
ginx.Dangerous(err)
if len(gids) == 0 {
ginx.Bomb(http.StatusForbidden, "forbidden")
ginx.NewRender(c).Data([]int{}, nil)
return
}
}

View File

@@ -272,7 +272,7 @@ func (rt *Router) boardGetsByGids(c *gin.Context) {
ginx.Dangerous(err)
if len(gids) == 0 {
ginx.Bomb(http.StatusForbidden, "forbidden")
ginx.NewRender(c).Data([]int{}, nil)
return
}
}

View File

@@ -2,11 +2,13 @@ package router
import (
"net/http"
"time"
"github.com/ccfos/nightingale/v6/models"
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/i18n"
)
// single or import
@@ -27,8 +29,9 @@ func (rt *Router) builtinMetricsAdd(c *gin.Context) {
reterr := make(map[string]string)
for i := 0; i < count; i++ {
lst[i].Lang = lang
lst[i].UUID = time.Now().UnixNano()
if err := lst[i].Add(rt.Ctx, username); err != nil {
reterr[lst[i].Name] = err.Error()
reterr[lst[i].Name] = i18n.Sprintf(c.GetHeader("X-Language"), err.Error())
}
}
ginx.NewRender(c).Data(reterr, nil)

View File

@@ -4,16 +4,19 @@ import (
"encoding/json"
"net/http"
"strings"
"time"
"github.com/ccfos/nightingale/v6/models"
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/i18n"
)
type Board struct {
Name string `json:"name"`
Tags string `json:"tags"`
Configs interface{} `json:"configs"`
UUID int64 `json:"uuid"`
}
func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
@@ -38,6 +41,10 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
}
for _, rule := range alertRules {
if rule.UUID == 0 {
rule.UUID = time.Now().UnixNano()
}
contentBytes, err := json.Marshal(rule)
if err != nil {
reterr[rule.Name] = err.Error()
@@ -50,13 +57,14 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
Cate: lst[i].Cate,
Name: rule.Name,
Tags: rule.AppendTags,
UUID: rule.UUID,
Content: string(contentBytes),
CreatedBy: username,
UpdatedBy: username,
}
if err := bp.Add(rt.Ctx, username); err != nil {
reterr[bp.Name] = err.Error()
reterr[bp.Name] = i18n.Sprintf(c.GetHeader("X-Language"), err.Error())
}
}
continue
@@ -68,19 +76,24 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
continue
}
if alertRule.UUID == 0 {
alertRule.UUID = time.Now().UnixNano()
}
bp := models.BuiltinPayload{
Type: lst[i].Type,
Component: lst[i].Component,
Cate: lst[i].Cate,
Name: alertRule.Name,
Tags: alertRule.AppendTags,
UUID: alertRule.UUID,
Content: lst[i].Content,
CreatedBy: username,
UpdatedBy: username,
}
if err := bp.Add(rt.Ctx, username); err != nil {
reterr[bp.Name] = err.Error()
reterr[bp.Name] = i18n.Sprintf(c.GetHeader("X-Language"), err.Error())
}
} else if lst[i].Type == "dashboard" {
if strings.HasPrefix(strings.TrimSpace(lst[i].Content), "[") {
@@ -91,6 +104,10 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
}
for _, dashboard := range dashboards {
if dashboard.UUID == 0 {
dashboard.UUID = time.Now().UnixNano()
}
contentBytes, err := json.Marshal(dashboard)
if err != nil {
reterr[dashboard.Name] = err.Error()
@@ -103,13 +120,14 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
Cate: lst[i].Cate,
Name: dashboard.Name,
Tags: dashboard.Tags,
UUID: dashboard.UUID,
Content: string(contentBytes),
CreatedBy: username,
UpdatedBy: username,
}
if err := bp.Add(rt.Ctx, username); err != nil {
reterr[bp.Name] = err.Error()
reterr[bp.Name] = i18n.Sprintf(c.GetHeader("X-Language"), err.Error())
}
}
continue
@@ -117,27 +135,32 @@ func (rt *Router) builtinPayloadsAdd(c *gin.Context) {
dashboard := Board{}
if err := json.Unmarshal([]byte(lst[i].Content), &dashboard); err != nil {
reterr[lst[i].Name] = err.Error()
reterr[lst[i].Name] = i18n.Sprintf(c.GetHeader("X-Language"), err.Error())
continue
}
if dashboard.UUID == 0 {
dashboard.UUID = time.Now().UnixNano()
}
bp := models.BuiltinPayload{
Type: lst[i].Type,
Component: lst[i].Component,
Cate: lst[i].Cate,
Name: dashboard.Name,
Tags: dashboard.Tags,
UUID: dashboard.UUID,
Content: lst[i].Content,
CreatedBy: username,
UpdatedBy: username,
}
if err := bp.Add(rt.Ctx, username); err != nil {
reterr[bp.Name] = err.Error()
reterr[bp.Name] = i18n.Sprintf(c.GetHeader("X-Language"), err.Error())
}
} else {
if err := lst[i].Add(rt.Ctx, username); err != nil {
reterr[lst[i].Name] = err.Error()
reterr[lst[i].Name] = i18n.Sprintf(c.GetHeader("X-Language"), err.Error())
}
}

View File

@@ -1,13 +1,16 @@
package router
import (
"github.com/ccfos/nightingale/v6/models"
"time"
"github.com/ccfos/nightingale/v6/models"
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
)
const EMBEDDEDDASHBOARD = "embedded-dashboards"
func (rt *Router) configsGet(c *gin.Context) {
prefix := ginx.QueryStr(c, "prefix", "")
limit := ginx.QueryInt(c, "limit", 10)
@@ -33,6 +36,18 @@ func (rt *Router) configPutByKey(c *gin.Context) {
ginx.NewRender(c).Message(models.ConfigsSetWithUname(rt.Ctx, f.Ckey, f.Cval, username))
}
func (rt *Router) embeddedDashboardsGet(c *gin.Context) {
config, err := models.ConfigsGet(rt.Ctx, EMBEDDEDDASHBOARD)
ginx.NewRender(c).Data(config, err)
}
func (rt *Router) embeddedDashboardsPut(c *gin.Context) {
var f models.Configs
ginx.BindJSON(c, &f)
username := c.MustGet("username").(string)
ginx.NewRender(c).Message(models.ConfigsSetWithUname(rt.Ctx, EMBEDDEDDASHBOARD, f.Cval, username))
}
func (rt *Router) configsDel(c *gin.Context) {
var f idsForm
ginx.BindJSON(c, &f)

View File

@@ -3,19 +3,33 @@ package router
import (
"compress/gzip"
"encoding/json"
"errors"
"io/ioutil"
"sort"
"strings"
"time"
"github.com/ccfos/nightingale/v6/center/metas"
"github.com/ccfos/nightingale/v6/memsto"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/ccfos/nightingale/v6/pushgw/idents"
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/logger"
)
type HeartbeatHookFunc func(ident string) map[string]interface{}
func (rt *Router) heartbeat(c *gin.Context) {
req, err := HandleHeartbeat(c, rt.Ctx, rt.Alert.Heartbeat.EngineName, rt.MetaSet, rt.IdentSet, rt.TargetCache)
ginx.Dangerous(err)
m := rt.HeartbeatHook(req.Hostname)
ginx.NewRender(c).Data(m, err)
}
func HandleHeartbeat(c *gin.Context, ctx *ctx.Context, engineName string, metaSet *metas.Set, identSet *idents.Set, targetCache *memsto.TargetCacheType) (models.HostMeta, error) {
var bs []byte
var err error
var r *gzip.Reader
@@ -24,7 +38,7 @@ func (rt *Router) heartbeat(c *gin.Context) {
r, err = gzip.NewReader(c.Request.Body)
if err != nil {
c.String(400, err.Error())
return
return req, err
}
defer r.Close()
bs, err = ioutil.ReadAll(r)
@@ -32,11 +46,19 @@ func (rt *Router) heartbeat(c *gin.Context) {
} else {
defer c.Request.Body.Close()
bs, err = ioutil.ReadAll(c.Request.Body)
ginx.Dangerous(err)
if err != nil {
return req, err
}
}
err = json.Unmarshal(bs, &req)
ginx.Dangerous(err)
if err != nil {
return req, err
}
if req.Hostname == "" {
return req, errors.New("hostname is required")
}
// maybe from pushgw
if req.Offset == 0 {
@@ -48,51 +70,69 @@ func (rt *Router) heartbeat(c *gin.Context) {
}
if req.EngineName == "" {
req.EngineName = rt.Alert.Heartbeat.EngineName
req.EngineName = engineName
}
rt.MetaSet.Set(req.Hostname, req)
metaSet.Set(req.Hostname, req)
var items = make(map[string]struct{})
items[req.Hostname] = struct{}{}
rt.IdentSet.MSet(items)
identSet.MSet(items)
if target, has := rt.TargetCache.Get(req.Hostname); has && target != nil {
if target, has := targetCache.Get(req.Hostname); has && target != nil {
gid := ginx.QueryInt64(c, "gid", 0)
hostIp := strings.TrimSpace(req.HostIp)
filed := make(map[string]interface{})
field := make(map[string]interface{})
if gid != 0 && gid != target.GroupId {
filed["group_id"] = gid
field["group_id"] = gid
}
if hostIp != "" && hostIp != target.HostIp {
filed["host_ip"] = hostIp
field["host_ip"] = hostIp
}
if len(req.GlobalLabels) > 0 {
tagsMap := target.GetTagsMap()
tagNeedUpdate := false
for k, v := range req.GlobalLabels {
if v == "" {
continue
}
if tagv, ok := tagsMap[k]; !ok || tagv != v {
tagNeedUpdate = true
tagsMap[k] = v
}
}
if tagNeedUpdate {
lst := []string{}
for k, v := range req.GlobalLabels {
for k, v := range tagsMap {
lst = append(lst, k+"="+v)
}
sort.Strings(lst)
labels := strings.Join(lst, " ")
if target.Tags != labels {
filed["tags"] = labels
}
labels := strings.Join(lst, " ") + " "
field["tags"] = labels
}
if req.EngineName != "" && req.EngineName != target.EngineName {
filed["engine_name"] = req.EngineName
field["engine_name"] = req.EngineName
}
if len(filed) > 0 {
err := target.UpdateFieldsMap(rt.Ctx, filed)
if req.AgentVersion != "" && req.AgentVersion != target.AgentVersion {
field["agent_version"] = req.AgentVersion
}
if req.OS != "" && req.OS != target.OS {
field["os"] = req.OS
}
if len(field) > 0 {
err := target.UpdateFieldsMap(ctx, field)
if err != nil {
logger.Errorf("update target fields failed, err: %v", err)
}
}
logger.Debugf("heartbeat field:%+v target: %v", filed, *target)
logger.Debugf("heartbeat field:%+v target: %v", field, *target)
}
ginx.NewRender(c).Message(err)
return req, nil
}

View File

@@ -55,12 +55,12 @@ func (rt *Router) loginPost(c *gin.Context) {
var err error
lc := rt.Sso.LDAP.Copy()
if lc.Enable {
user, err = ldapx.LdapLogin(rt.Ctx, f.Username, authPassWord, lc.DefaultRoles, lc)
user, err = ldapx.LdapLogin(rt.Ctx, f.Username, authPassWord, lc.DefaultRoles, lc.DefaultTeams, lc)
if err != nil {
logger.Debugf("ldap login failed: %v username: %s", err, f.Username)
var errLoginInN9e error
// to use n9e as the minimum guarantee for login
if user, errLoginInN9e = models.PassLogin(rt.Ctx, f.Username, authPassWord); errLoginInN9e != nil {
if user, errLoginInN9e = models.PassLogin(rt.Ctx, rt.Redis, f.Username, authPassWord); errLoginInN9e != nil {
ginx.NewRender(c).Message("ldap login failed: %v; n9e login failed: %v", err, errLoginInN9e)
return
}
@@ -68,7 +68,7 @@ func (rt *Router) loginPost(c *gin.Context) {
user.RolesLst = strings.Fields(user.Roles)
}
} else {
user, err = models.PassLogin(rt.Ctx, f.Username, authPassWord)
user, err = models.PassLogin(rt.Ctx, rt.Redis, f.Username, authPassWord)
ginx.Dangerous(err)
}
@@ -262,6 +262,15 @@ func (rt *Router) loginCallback(c *gin.Context) {
user.FullSsoFields("oidc", ret.Username, ret.Nickname, ret.Phone, ret.Email, rt.Sso.OIDC.DefaultRoles)
// create user from oidc
ginx.Dangerous(user.Add(rt.Ctx))
if len(rt.Sso.OIDC.DefaultTeams) > 0 {
for _, gid := range rt.Sso.OIDC.DefaultTeams {
err = models.UserGroupMemberAdd(rt.Ctx, gid, user.Id)
if err != nil {
logger.Errorf("user:%v UserGroupMemberAdd: %s", user, err)
}
}
}
}
// set user login state

View File

@@ -35,7 +35,7 @@ func (rt *Router) alertMuteGetsByGids(c *gin.Context) {
ginx.Dangerous(err)
if len(gids) == 0 {
ginx.Bomb(http.StatusForbidden, "forbidden")
ginx.NewRender(c).Data([]int{}, nil)
return
}
}
@@ -95,7 +95,8 @@ func (rt *Router) alertMuteAddByService(c *gin.Context) {
var f models.AlertMute
ginx.BindJSON(c, &f)
ginx.NewRender(c).Message(f.Add(rt.Ctx))
err := f.Add(rt.Ctx)
ginx.NewRender(c).Data(f.Id, err)
}
func (rt *Router) alertMuteDel(c *gin.Context) {

View File

@@ -0,0 +1,205 @@
package router
import (
"strings"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/logger"
)
type NotificationResponse struct {
SubRules []SubRule `json:"sub_rules"`
Notifies map[string][]Record `json:"notifies"`
}
type SubRule struct {
SubID int64 `json:"sub_id"`
Notifies map[string][]Record `json:"notifies"`
}
type Notify struct {
Channel string `json:"channel"`
Records []Record `json:"records"`
}
type Record struct {
Target string `json:"target"`
Username string `json:"username"`
Status int `json:"status"`
Detail string `json:"detail"`
}
// notificationRecordAdd
func (rt *Router) notificationRecordAdd(c *gin.Context) {
var req models.NotificaitonRecord
ginx.BindJSON(c, &req)
err := req.Add(rt.Ctx)
ginx.NewRender(c).Data(req.Id, err)
}
func (rt *Router) notificationRecordList(c *gin.Context) {
eid := ginx.UrlParamInt64(c, "eid")
lst, err := models.NotificaitonRecordsGetByEventId(rt.Ctx, eid)
ginx.Dangerous(err)
response := buildNotificationResponse(rt.Ctx, lst)
ginx.NewRender(c).Data(response, nil)
}
func buildNotificationResponse(ctx *ctx.Context, nl []*models.NotificaitonRecord) NotificationResponse {
response := NotificationResponse{
SubRules: []SubRule{},
Notifies: make(map[string][]Record),
}
subRuleMap := make(map[int64]*SubRule)
// Collect all group IDs
groupIdSet := make(map[int64]struct{})
// map[SubId]map[Channel]map[Target]index
filter := make(map[int64]map[string]map[string]int)
for i, n := range nl {
// 对相同的 channel-target 进行合并
for _, gid := range n.GetGroupIds(ctx) {
groupIdSet[gid] = struct{}{}
}
if _, exists := filter[n.SubId]; !exists {
filter[n.SubId] = make(map[string]map[string]int)
}
if _, exists := filter[n.SubId][n.Channel]; !exists {
filter[n.SubId][n.Channel] = make(map[string]int)
}
idx, exists := filter[n.SubId][n.Channel][n.Target]
if !exists {
filter[n.SubId][n.Channel][n.Target] = i
} else {
if nl[idx].Status < n.Status {
nl[idx].Status = n.Status
}
nl[idx].Details = nl[idx].Details + ", " + n.Details
nl[i] = nil
}
}
// Fill usernames only once
usernameByTarget := fillUserNames(ctx, groupIdSet)
for _, n := range nl {
if n == nil {
continue
}
m := usernameByTarget[n.Target]
usernames := make([]string, 0, len(m))
for k := range m {
usernames = append(usernames, k)
}
if !checkChannel(n.Channel) {
// Hide sensitive information
n.Target = replaceLastEightChars(n.Target)
}
record := Record{
Target: n.Target,
Status: n.Status,
Detail: n.Details,
}
record.Username = strings.Join(usernames, ",")
if n.SubId > 0 {
// Handle SubRules
subRule, ok := subRuleMap[n.SubId]
if !ok {
newSubRule := &SubRule{
SubID: n.SubId,
}
newSubRule.Notifies = make(map[string][]Record)
newSubRule.Notifies[n.Channel] = []Record{record}
subRuleMap[n.SubId] = newSubRule
} else {
if _, exists := subRule.Notifies[n.Channel]; !exists {
subRule.Notifies[n.Channel] = []Record{record}
} else {
subRule.Notifies[n.Channel] = append(subRule.Notifies[n.Channel], record)
}
}
continue
}
if response.Notifies == nil {
response.Notifies = make(map[string][]Record)
}
if _, exists := response.Notifies[n.Channel]; !exists {
response.Notifies[n.Channel] = []Record{record}
} else {
response.Notifies[n.Channel] = append(response.Notifies[n.Channel], record)
}
}
for _, subRule := range subRuleMap {
response.SubRules = append(response.SubRules, *subRule)
}
return response
}
// check channel is one of the following: tx-sms, tx-voice, ali-sms, ali-voice, email, script
func checkChannel(channel string) bool {
switch channel {
case "tx-sms", "tx-voice", "ali-sms", "ali-voice", "email", "script":
return true
}
return false
}
func replaceLastEightChars(s string) string {
if len(s) <= 8 {
return strings.Repeat("*", len(s))
}
return s[:len(s)-8] + strings.Repeat("*", 8)
}
func fillUserNames(ctx *ctx.Context, groupIdSet map[int64]struct{}) map[string]map[string]struct{} {
userNameByTarget := make(map[string]map[string]struct{})
gids := make([]int64, 0, len(groupIdSet))
for gid := range groupIdSet {
gids = append(gids, gid)
}
users, err := models.UsersGetByGroupIds(ctx, gids)
if err != nil {
logger.Errorf("UsersGetByGroupIds failed, err: %v", err)
return userNameByTarget
}
for _, user := range users {
logger.Warningf("user: %s", user.Username)
for _, ch := range models.DefaultChannels {
target, exist := user.ExtractToken(ch)
if exist {
if _, ok := userNameByTarget[target]; !ok {
userNameByTarget[target] = make(map[string]struct{})
}
userNameByTarget[target][user.Username] = struct{}{}
}
}
}
return userNameByTarget
}

View File

@@ -90,7 +90,8 @@ func (rt *Router) notifyChannelPuts(c *gin.Context) {
var notifyChannels []models.NotifyChannel
ginx.BindJSON(c, &notifyChannels)
channels := []string{models.Dingtalk, models.Wecom, models.Feishu, models.Mm, models.Telegram, models.Email}
channels := []string{models.Dingtalk, models.Wecom, models.Feishu, models.Mm, models.Telegram,
models.Email, models.Lark, models.LarkCard}
m := make(map[string]struct{})
for _, v := range notifyChannels {
@@ -126,7 +127,8 @@ func (rt *Router) notifyContactPuts(c *gin.Context) {
var notifyContacts []models.NotifyContact
ginx.BindJSON(c, &notifyContacts)
keys := []string{models.DingtalkKey, models.WecomKey, models.FeishuKey, models.MmKey, models.TelegramKey}
keys := []string{models.DingtalkKey, models.WecomKey, models.FeishuKey, models.MmKey,
models.TelegramKey, models.LarkKey}
m := make(map[string]struct{})
for _, v := range notifyContacts {
@@ -180,7 +182,7 @@ func (rt *Router) notifyConfigPut(c *gin.Context) {
smtp, errSmtp := SmtpValidate(text)
ginx.Dangerous(errSmtp)
go sender.RestartEmailSender(smtp)
go sender.RestartEmailSender(rt.Ctx, smtp)
}
ginx.NewRender(c).Message(nil)

View File

@@ -34,7 +34,7 @@ func (rt *Router) recordingRuleGetsByGids(c *gin.Context) {
ginx.Dangerous(err)
if len(gids) == 0 {
ginx.Bomb(http.StatusForbidden, "forbidden")
ginx.NewRender(c).Data([]int{}, nil)
return
}
}

View File

@@ -4,9 +4,11 @@ import (
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/flashduty"
"github.com/ccfos/nightingale/v6/pkg/ormx"
"github.com/ccfos/nightingale/v6/pkg/secu"
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/logger"
)
func (rt *Router) selfProfileGet(c *gin.Context) {
@@ -58,5 +60,25 @@ func (rt *Router) selfPasswordPut(c *gin.Context) {
var f selfPasswordForm
ginx.BindJSON(c, &f)
user := c.MustGet("user").(*models.User)
ginx.NewRender(c).Message(user.ChangePassword(rt.Ctx, f.OldPass, f.NewPass))
newPassWord := f.NewPass
oldPassWord := f.OldPass
if rt.HTTP.RSA.OpenRSA {
var err error
newPassWord, err = secu.Decrypt(f.NewPass, rt.HTTP.RSA.RSAPrivateKey, rt.HTTP.RSA.RSAPassWord)
if err != nil {
logger.Errorf("RSA Decrypt failed: %v username: %s", err, user.Username)
ginx.NewRender(c).Message(err)
return
}
oldPassWord, err = secu.Decrypt(f.OldPass, rt.HTTP.RSA.RSAPrivateKey, rt.HTTP.RSA.RSAPassWord)
if err != nil {
logger.Errorf("RSA Decrypt failed: %v username: %s", err, user.Username)
ginx.NewRender(c).Message(err)
return
}
}
ginx.NewRender(c).Message(user.ChangePassword(rt.Ctx, oldPassWord, newPassWord))
}

View File

@@ -49,6 +49,9 @@ func (rt *Router) targetGets(c *gin.Context) {
downtime := ginx.QueryInt64(c, "downtime", 0)
dsIds := queryDatasourceIds(c)
order := ginx.QueryStr(c, "order", "ident")
desc := ginx.QueryBool(c, "desc", false)
var err error
if len(bgids) == 0 {
user := c.MustGet("user").(*models.User)
@@ -62,11 +65,17 @@ func (rt *Router) targetGets(c *gin.Context) {
bgids = append(bgids, 0)
}
}
total, err := models.TargetTotal(rt.Ctx, bgids, dsIds, query, downtime)
options := []models.BuildTargetWhereOption{
models.BuildTargetWhereWithBgids(bgids),
models.BuildTargetWhereWithDsIds(dsIds),
models.BuildTargetWhereWithQuery(query),
models.BuildTargetWhereWithDowntime(downtime),
}
total, err := models.TargetTotal(rt.Ctx, options...)
ginx.Dangerous(err)
list, err := models.TargetGets(rt.Ctx, bgids, dsIds, query, downtime, limit, ginx.Offset(c, limit))
list, err := models.TargetGets(rt.Ctx, limit,
ginx.Offset(c, limit), order, desc, options...)
ginx.Dangerous(err)
if err == nil {

View File

@@ -1,7 +1,6 @@
package router
import (
"net/http"
"time"
"github.com/ccfos/nightingale/v6/alert/sender"
@@ -9,6 +8,7 @@ import (
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/i18n"
"github.com/toolkits/pkg/str"
)
@@ -53,7 +53,7 @@ func (rt *Router) taskGetsByGids(c *gin.Context) {
ginx.Dangerous(err)
if len(gids) == 0 {
ginx.Bomb(http.StatusForbidden, "forbidden")
ginx.NewRender(c).Data([]int{}, nil)
return
}
}
@@ -105,6 +105,11 @@ func (rt *Router) taskRecordAdd(c *gin.Context) {
}
func (rt *Router) taskAdd(c *gin.Context) {
if !rt.Ibex.Enable {
ginx.Bomb(400, i18n.Sprintf(c.GetHeader("X-Language"), "This functionality has not been enabled. Please contact the system administrator to activate it."))
return
}
var f models.TaskForm
ginx.BindJSON(c, &f)

View File

@@ -10,6 +10,7 @@ import (
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/i18n"
"github.com/toolkits/pkg/str"
)
@@ -47,7 +48,7 @@ func (rt *Router) taskTplGetsByGids(c *gin.Context) {
ginx.Dangerous(err)
if len(gids) == 0 {
ginx.Bomb(http.StatusForbidden, "forbidden")
ginx.NewRender(c).Data([]int{}, nil)
return
}
}
@@ -118,6 +119,11 @@ type taskTplForm struct {
}
func (rt *Router) taskTplAdd(c *gin.Context) {
if !rt.Ibex.Enable {
ginx.Bomb(400, i18n.Sprintf(c.GetHeader("X-Language"), "This functionality has not been enabled. Please contact the system administrator to activate it."))
return
}
var f taskTplForm
ginx.BindJSON(c, &f)
@@ -190,6 +196,13 @@ func (rt *Router) taskTplDel(c *gin.Context) {
return
}
ids, err := models.GetAlertRuleIdsByTaskId(rt.Ctx, tid)
ginx.Dangerous(err)
if len(ids) > 0 {
ginx.NewRender(c).Message("can't del this task tpl, used by alert rule ids(%v) ", ids)
return
}
ginx.NewRender(c).Message(tpl.Del(rt.Ctx))
}

View File

@@ -7,9 +7,11 @@ import (
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/flashduty"
"github.com/ccfos/nightingale/v6/pkg/ormx"
"github.com/ccfos/nightingale/v6/pkg/secu"
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/logger"
)
func (rt *Router) userBusiGroupsGets(c *gin.Context) {
@@ -46,6 +48,7 @@ func (rt *Router) userGets(c *gin.Context) {
order := ginx.QueryStr(c, "order", "username")
desc := ginx.QueryBool(c, "desc", false)
rt.UserCache.UpdateUsersLastActiveTime()
total, err := models.UserTotal(rt.Ctx, query, stime, etime)
ginx.Dangerous(err)
@@ -76,7 +79,18 @@ func (rt *Router) userAddPost(c *gin.Context) {
var f userAddForm
ginx.BindJSON(c, &f)
password, err := models.CryptoPass(rt.Ctx, f.Password)
authPassWord := f.Password
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
}
password, err := models.CryptoPass(rt.Ctx, authPassWord)
ginx.Dangerous(err)
if len(f.Roles) == 0 {
@@ -177,7 +191,18 @@ func (rt *Router) userPasswordPut(c *gin.Context) {
target := User(rt.Ctx, ginx.UrlParamInt64(c, "id"))
cryptoPass, err := models.CryptoPass(rt.Ctx, f.Password)
authPassWord := f.Password
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, target.Username)
ginx.NewRender(c).Message(err)
return
}
authPassWord = decPassWord
}
cryptoPass, err := models.CryptoPass(rt.Ctx, authPassWord)
ginx.Dangerous(err)
ginx.NewRender(c).Message(target.UpdatePassword(rt.Ctx, cryptoPass, c.MustGet("username").(string)))

View File

@@ -10,6 +10,7 @@ import (
"github.com/gin-gonic/gin"
"github.com/toolkits/pkg/ginx"
"github.com/toolkits/pkg/logger"
"github.com/toolkits/pkg/str"
)
func (rt *Router) checkBusiGroupPerm(c *gin.Context) {
@@ -31,8 +32,36 @@ func (rt *Router) userGroupGets(c *gin.Context) {
}
func (rt *Router) userGroupGetsByService(c *gin.Context) {
lst, err := models.UserGroupGetAll(rt.Ctx)
ginx.NewRender(c).Data(lst, err)
ids := str.IdsInt64(ginx.QueryStr(c, "ids", ""))
if len(ids) == 0 {
lst, err := models.UserGroupGetAll(rt.Ctx)
ginx.Dangerous(err)
for i := 0; i < len(lst); i++ {
ids, err := models.MemberIds(rt.Ctx, lst[i].Id)
ginx.Dangerous(err)
lst[i].Users, err = models.UserGetsByIds(rt.Ctx, ids)
ginx.Dangerous(err)
}
ginx.NewRender(c).Data(lst, err)
return
}
lst := make([]models.UserGroup, 0)
for _, id := range ids {
ug := UserGroup(rt.Ctx, id)
ids, err := models.MemberIds(rt.Ctx, ug.Id)
ginx.Dangerous(err)
ug.Users, err = models.UserGetsByIds(rt.Ctx, ids)
ginx.Dangerous(err)
lst = append(lst, *ug)
}
ginx.NewRender(c).Data(lst, nil)
}
// user group member get by service

View File

@@ -1,6 +1,7 @@
package sso
import (
"fmt"
"log"
"time"
@@ -145,7 +146,7 @@ func Init(center cconf.Center, ctx *ctx.Context, configCache *memsto.ConfigCache
}
}
if configCache == nil {
logger.Error("configCache is nil, sso initialization failed")
log.Fatalln(fmt.Errorf("configCache is nil, sso initialization failed"))
}
ssoClient.configCache = configCache
userVariableMap := configCache.Get()

View File

@@ -0,0 +1,41 @@
package cron
import (
"time"
"github.com/ccfos/nightingale/v6/models"
"github.com/ccfos/nightingale/v6/pkg/ctx"
"github.com/robfig/cron/v3"
"github.com/toolkits/pkg/logger"
)
func cleanNotifyRecord(ctx *ctx.Context, day int) {
lastWeek := time.Now().Unix() - 86400*int64(day)
err := models.DB(ctx).Model(&models.NotificaitonRecord{}).Where("created_at < ?", lastWeek).Delete(&models.NotificaitonRecord{}).Error
if err != nil {
logger.Errorf("Failed to clean notify record: %v", err)
}
}
// 每天凌晨1点执行清理任务
func CleanNotifyRecord(ctx *ctx.Context, day int) {
c := cron.New()
if day < 1 {
day = 7
}
// 使用cron表达式设置每天凌晨1点执行
_, err := c.AddFunc("0 1 * * *", func() {
cleanNotifyRecord(ctx, day)
})
if err != nil {
logger.Errorf("Failed to add clean notify record cron job: %v", err)
return
}
// 启动cron任务
c.Start()
}

View File

@@ -78,6 +78,6 @@ enable = true
## ibex flush interval
interval = "1000ms"
## n9e ibex server rpc address
servers = ["ibex:20090"]
servers = ["nightingale:20090"]
## temp script dir
meta_dir = "./meta"

View File

@@ -8,7 +8,7 @@ CREATE TABLE users (
portrait varchar(255) not null default '',
roles varchar(255) not null,
contacts varchar(1024),
maintainer boolean not null default false,
maintainer int not null default 0,
belong varchar(16) not null default '',
last_active_time bigint not null default 0,
create_at bigint not null default 0,
@@ -60,8 +60,8 @@ CREATE TABLE configs (
ckey varchar(191) not null,
cval text not null default '',
note varchar(1024) not null default '',
external boolean not null default false,
encrypted boolean not null default false,
external int not null default 0,
encrypted int not null default 0,
create_at bigint not null default 0,
create_by varchar(64) not null default '',
update_at bigint not null default 0,
@@ -378,7 +378,7 @@ COMMENT ON COLUMN alert_mute.disabled IS '0:enabled 1:disabled';
CREATE TABLE alert_subscribe (
id bigserial,
name varchar(255) not null default '',
disabled boolean not null default false,
disabled int not null default 0,
group_id bigint not null default 0,
prod varchar(255) not null default '',
cate varchar(128) not null,
@@ -397,7 +397,7 @@ CREATE TABLE alert_subscribe (
rule_ids VARCHAR(1024) DEFAULT '',
webhooks text not null,
extra_config text not null,
redefine_webhooks boolean default false,
redefine_webhooks int default 0,
for_duration bigint not null default 0,
create_at bigint not null default 0,
create_by varchar(64) not null default '',
@@ -744,7 +744,7 @@ CREATE TABLE datasource
status varchar(255) not null default '',
http varchar(4096) not null default '',
auth varchar(8192) not null default '',
is_default smallint not null default 0,
is_default boolean not null default false,
created_at bigint not null default 0,
created_by varchar(64) not null default '',
updated_at bigint not null default 0,
@@ -845,7 +845,7 @@ CREATE TABLE metric_filter (
update_by VARCHAR(191) NOT NULL DEFAULT ''
);
CREATE INDEX idx_name ON metric_filter (name);
CREATE INDEX idx_metric_filter_name ON metric_filter (name);
CREATE TABLE board_busigroup (
busi_group_id BIGINT NOT NULL DEFAULT 0,
@@ -870,6 +870,7 @@ CREATE INDEX idx_ident ON builtin_components (ident);
CREATE TABLE builtin_payloads (
id BIGSERIAL PRIMARY KEY,
type VARCHAR(191) NOT NULL,
uuid BIGINT NOT NULL DEFAULT 0,
component VARCHAR(191) NOT NULL,
cate VARCHAR(191) NOT NULL,
name VARCHAR(191) NOT NULL,
@@ -882,6 +883,6 @@ CREATE TABLE builtin_payloads (
);
CREATE INDEX idx_component ON builtin_payloads (component);
CREATE INDEX idx_name ON builtin_payloads (name);
CREATE INDEX idx_builtin_payloads_name ON builtin_payloads (name);
CREATE INDEX idx_cate ON builtin_payloads (cate);
CREATE INDEX idx_type ON builtin_payloads (type);

View File

@@ -1,11 +1,25 @@
#### {{if .IsRecovered}}<font color="#008800">S{{.Severity}} - Recovered - {{.RuleName}}</font>{{else}}<font color="#FF0000">S{{.Severity}} - Triggered - {{.RuleName}}</font>{{end}}
#### {{if .IsRecovered}}<font color="#008800">💚{{.RuleName}}</font>{{else}}<font color="#FF0000">💔{{.RuleName}}</font>{{end}}
---
- **规则标题**: {{.RuleName}}{{if .RuleNote}}
- **规则备注**: {{.RuleNote}}{{end}}
- **监控指标**: {{.TagsJSON}}
- {{if .IsRecovered}}**恢复时间**{{timeformat .LastEvalTime}}{{else}}**触发时间**: {{timeformat .TriggerTime}}
- **触发时值**: {{.TriggerValue}}{{end}}
- **发送时间**: {{timestamp}}
{{$time_duration := sub now.Unix .FirstTriggerTime }}{{if .IsRecovered}}{{$time_duration = sub .LastEvalTime .FirstTriggerTime }}{{end}}
- **告警级别**: {{.Severity}}
{{- if .RuleNote}}
- **规则备注**: {{.RuleNote}}
{{- end}}
{{- if not .IsRecovered}}
- **当次触发时值**: {{.TriggerValue}}
- **当次触发时间**: {{timeformat .TriggerTime}}
- **告警持续时长**: {{humanizeDurationInterface $time_duration}}
{{- else}}
{{- if .AnnotationsJSON.recovery_value}}
- **恢复时值**: {{formatDecimal .AnnotationsJSON.recovery_value 4}}
{{- end}}
- **恢复时间**: {{timeformat .LastEvalTime}}
- **告警持续时长**: {{humanizeDurationInterface $time_duration}}
{{- end}}
- **告警事件标签**:
{{- range $key, $val := .TagsMap}}
{{- if ne $key "rulename" }}
- `{{$key}}`: `{{$val}}`
{{- end}}
{{- end}}

View File

@@ -366,6 +366,7 @@ CREATE TABLE `target` (
`host_ip` varchar(15) default '' COMMENT 'IPv4 string',
`agent_version` varchar(255) default '' COMMENT 'agent version',
`engine_name` varchar(255) default '' COMMENT 'engine_name',
`os` VARCHAR(31) DEFAULT '' COMMENT 'os type',
`update_at` bigint not null default 0,
PRIMARY KEY (`id`),
UNIQUE KEY (`ident`),
@@ -397,6 +398,7 @@ CREATE TABLE `recording_rule` (
`disabled` tinyint(1) not null default 0 comment '0:enabled 1:disabled',
`prom_ql` varchar(8192) not null comment 'promql',
`prom_eval_interval` int not null comment 'evaluate interval',
`cron_pattern` varchar(255) default '' comment 'cron pattern',
`append_tags` varchar(255) default '' comment 'split by space: service=n9e mod=api',
`query_configs` text not null comment 'query configs',
`create_at` bigint default '0',
@@ -440,7 +442,7 @@ CREATE TABLE `alert_cur_event` (
`prom_for_duration` int not null comment 'prometheus for, unit:s',
`prom_ql` varchar(8192) not null comment 'promql',
`prom_eval_interval` int not null comment 'evaluate interval',
`callbacks` varchar(255) not null default '' comment 'split by space: http://a.com/api/x http://a.com/api/y',
`callbacks` varchar(2048) not null default '' comment 'split by space: http://a.com/api/x http://a.com/api/y',
`runbook_url` varchar(255),
`notify_recovered` tinyint(1) not null comment 'whether notify when recovery',
`notify_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
@@ -455,6 +457,7 @@ CREATE TABLE `alert_cur_event` (
`annotations` text not null comment 'annotations',
`rule_config` text not null comment 'annotations',
`tags` varchar(1024) not null default '' comment 'merge data_tags rule_tags, split by ,,',
`original_tags` text comment 'labels key=val,,k2=v2',
PRIMARY KEY (`id`),
KEY (`hash`),
KEY (`rule_id`),
@@ -480,7 +483,7 @@ CREATE TABLE `alert_his_event` (
`prom_for_duration` int not null comment 'prometheus for, unit:s',
`prom_ql` varchar(8192) not null comment 'promql',
`prom_eval_interval` int not null comment 'evaluate interval',
`callbacks` varchar(255) not null default '' comment 'split by space: http://a.com/api/x http://a.com/api/y',
`callbacks` varchar(2048) not null default '' comment 'split by space: http://a.com/api/x http://a.com/api/y',
`runbook_url` varchar(255),
`notify_recovered` tinyint(1) not null comment 'whether notify when recovery',
`notify_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
@@ -494,6 +497,7 @@ CREATE TABLE `alert_his_event` (
`recover_time` bigint not null default 0,
`last_eval_time` bigint not null default 0 comment 'for time filter',
`tags` varchar(1024) not null default '' comment 'merge data_tags rule_tags, split by ,,',
`original_tags` text comment 'labels key=val,,k2=v2',
`annotations` text not null comment 'annotations',
`rule_config` text not null comment 'annotations',
PRIMARY KEY (`id`),
@@ -524,6 +528,7 @@ CREATE TABLE `builtin_components` (
CREATE TABLE `builtin_payloads` (
`id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '''unique identifier''',
`uuid` bigint(20) NOT NULL COMMENT '''uuid of payload''',
`type` varchar(191) NOT NULL COMMENT '''type of payload''',
`component` varchar(191) NOT NULL COMMENT '''component of payload''',
`cate` varchar(191) NOT NULL COMMENT '''category of payload''',
@@ -538,9 +543,22 @@ CREATE TABLE `builtin_payloads` (
KEY `idx_component` (`component`),
KEY `idx_name` (`name`),
KEY `idx_cate` (`cate`),
KEY `idx_uuid` (`uuid`),
KEY `idx_type` (`type`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE TABLE notification_record (
`id` BIGINT PRIMARY KEY AUTO_INCREMENT,
`event_id` BIGINT NOT NULL,
`sub_id` BIGINT NOT NULL,
`channel` VARCHAR(255) NOT NULL,
`status` TINYINT NOT NULL DEFAULT 0,
`target` VARCHAR(1024) NOT NULL,
`details` VARCHAR(2048),
`created_at` BIGINT NOT NULL,
INDEX idx_evt (event_id)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
CREATE TABLE `task_tpl`
(
`id` int unsigned NOT NULL AUTO_INCREMENT,

1777
docker/initsql/sqlite.sql Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -56,6 +56,7 @@ CREATE TABLE `builtin_components` (
CREATE TABLE `builtin_payloads` (
`id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '''unique identifier''',
`uuid` bigint(20) NOT NULL COMMENT '''uuid of payload''',
`type` varchar(191) NOT NULL COMMENT '''type of payload''',
`component` varchar(191) NOT NULL COMMENT '''component of payload''',
`cate` varchar(191) NOT NULL COMMENT '''category of payload''',
@@ -70,8 +71,32 @@ CREATE TABLE `builtin_payloads` (
KEY `idx_component` (`component`),
KEY `idx_name` (`name`),
KEY `idx_cate` (`cate`),
KEY `idx_uuid` (`uuid`),
KEY `idx_type` (`type`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
/* v7.0.0-beta.7 */
ALTER TABLE users ADD COLUMN last_active_time BIGINT NOT NULL DEFAULT 0;
ALTER TABLE users ADD COLUMN last_active_time BIGINT NOT NULL DEFAULT 0;
/* v7.0.0-beta.13 */
ALTER TABLE recording_rule ADD COLUMN cron_pattern VARCHAR(255) DEFAULT '' COMMENT 'cron pattern';
/* v7.0.0-beta.14 */
ALTER TABLE alert_cur_event ADD COLUMN original_tags TEXT COMMENT 'labels key=val,,k2=v2';
ALTER TABLE alert_his_event ADD COLUMN original_tags TEXT COMMENT 'labels key=val,,k2=v2';
/* v7.1.0 */
ALTER TABLE target ADD COLUMN os VARCHAR(31) DEFAULT '' COMMENT 'os type';
/* v7.2.0 */
CREATE TABLE notification_record (
`id` BIGINT PRIMARY KEY AUTO_INCREMENT,
`event_id` BIGINT NOT NULL,
`sub_id` BIGINT NOT NULL,
`channel` VARCHAR(255) NOT NULL,
`status` TINYINT NOT NULL DEFAULT 0,
`target` VARCHAR(1024) NOT NULL,
`details` VARCHAR(2048),
`created_at` BIGINT NOT NULL,
INDEX idx_evt (event_id)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;

View File

@@ -75,10 +75,11 @@ OpenRSA = false
[DB]
# postgres: host=%s port=%s user=%s dbname=%s password=%s sslmode=%s
# postgres: DSN="host=127.0.0.1 port=5432 user=root dbname=n9e_v6 password=1234 sslmode=disable"
DSN="root:1234@tcp(127.0.0.1:3306)/n9e_v6?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
# sqlite: DSN="/path/to/filename.db"
DSN = "root:1234@tcp(127.0.0.1:3306)/n9e_v6?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
# enable debug mode or not
Debug = false
# mysql postgres
# mysql postgres sqlite
DBType = "mysql"
# unit: s
MaxLifetime = 7200

11
go.mod
View File

@@ -8,7 +8,7 @@ require (
github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc
github.com/dgrijalva/jwt-go v3.2.0+incompatible
github.com/expr-lang/expr v1.16.1
github.com/flashcatcloud/ibex v1.3.3
github.com/flashcatcloud/ibex v1.3.5
github.com/gin-contrib/pprof v1.4.0
github.com/gin-gonic/gin v1.9.1
github.com/go-ldap/ldap/v3 v3.4.4
@@ -39,7 +39,8 @@ require (
gopkg.in/yaml.v2 v2.4.0
gorm.io/driver/mysql v1.4.4
gorm.io/driver/postgres v1.4.5
gorm.io/gorm v1.24.2
gorm.io/driver/sqlite v1.5.5
gorm.io/gorm v1.25.7-0.20240204074919-46816ad31dde
)
require (
@@ -77,12 +78,14 @@ require (
github.com/josharian/intern v1.0.0 // indirect
github.com/klauspost/cpuid/v2 v2.2.4 // indirect
github.com/leodido/go-urn v1.2.4 // indirect
github.com/mattn/go-sqlite3 v1.14.17 // indirect
github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
github.com/modern-go/reflect2 v1.0.2 // indirect
github.com/pquerna/cachecontrol v0.1.0 // indirect
github.com/prometheus/client_model v0.4.0 // indirect
github.com/prometheus/procfs v0.11.0 // indirect
github.com/robfig/cron/v3 v3.0.1
github.com/tidwall/match v1.1.1 // indirect
github.com/tidwall/pretty v1.2.0 // indirect
github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
@@ -91,10 +94,10 @@ require (
go.uber.org/automaxprocs v1.5.2 // indirect
golang.org/x/arch v0.3.0 // indirect
golang.org/x/crypto v0.21.0 // indirect
golang.org/x/image v0.13.0 // indirect
golang.org/x/image v0.18.0 // indirect
golang.org/x/net v0.23.0 // indirect
golang.org/x/sys v0.18.0 // indirect
golang.org/x/text v0.14.0 // indirect
golang.org/x/text v0.16.0 // indirect
google.golang.org/appengine v1.6.7 // indirect
google.golang.org/protobuf v1.33.0 // indirect
gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc // indirect

23
go.sum
View File

@@ -47,8 +47,8 @@ github.com/fatih/camelcase v1.0.0 h1:hxNvNX/xYBp0ovncs8WyWZrOrpBNub/JfaMvbURyft8
github.com/fatih/camelcase v1.0.0/go.mod h1:yN2Sb0lFhZJUdVvtELVWefmrXpuZESvPmqwoZc+/fpc=
github.com/fatih/structs v1.1.0 h1:Q7juDM0QtcnhCpeyLGQKyg4TOIghuNXrkL32pHAUMxo=
github.com/fatih/structs v1.1.0/go.mod h1:9NiDSp5zOcgEDl+j00MP/WkGVPOlPRLejGD8Ga6PJ7M=
github.com/flashcatcloud/ibex v1.3.3 h1:1Bxk5sgpsq4+e9bMchucGttg8Sw4KEpZy9tctFfj/cE=
github.com/flashcatcloud/ibex v1.3.3/go.mod h1:T8hbMUySK2q6cXUaYp0AUVeKkU9Od2LjzwmB5lmTRBM=
github.com/flashcatcloud/ibex v1.3.5 h1:8GOOf5+aJT0TP/MC6izz7CO5JKJSdKVFBwL0vQp93Nc=
github.com/flashcatcloud/ibex v1.3.5/go.mod h1:T8hbMUySK2q6cXUaYp0AUVeKkU9Od2LjzwmB5lmTRBM=
github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
github.com/garyburd/redigo v1.6.2/go.mod h1:NR3MbYisc3/PwhQ00EMzDiPmrwpPxAn5GI05/YaO1SY=
@@ -209,6 +209,8 @@ github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Ky
github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/mattn/go-sqlite3 v1.14.17 h1:mCRHCLDUBXgpKAqIKsaAaAsrAlbkeomtRFKXh2L6YIM=
github.com/mattn/go-sqlite3 v1.14.17/go.mod h1:2eHXhiwb8IkHr+BDWZGa96P6+rkvnG63S2DGjv9HUNg=
github.com/matttproud/golang_protobuf_extensions v1.0.4 h1:mmDVorXM7PCGKw94cs5zkfA9PSy5pEvNWRP0ET0TIVo=
github.com/matttproud/golang_protobuf_extensions v1.0.4/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
@@ -248,6 +250,8 @@ github.com/rakyll/statik v0.1.7 h1:OF3QCZUuyPxuGEP7B4ypUa7sB/iHtqOTDYZXGM8KOdQ=
github.com/rakyll/statik v0.1.7/go.mod h1:AlZONWzMtEnMs7W4e/1LURLiI49pIMmp6V9Unghqrcc=
github.com/redis/go-redis/v9 v9.0.2 h1:BA426Zqe/7r56kCcvxYLWe1mkaz71LKF77GwgFzSxfE=
github.com/redis/go-redis/v9 v9.0.2/go.mod h1:/xDTe9EF1LM61hek62Poq2nzQSGj0xSrEtEHbBQevps=
github.com/robfig/cron/v3 v3.0.1 h1:WdRxkvbJztn8LMz/QEvLN5sBU+xKpSqwwUO1Pjr4qDs=
github.com/robfig/cron/v3 v3.0.1/go.mod h1:eQICP3HwyT7UooqI/z+Ov+PtYAWygg1TEWWzGIFLtro=
github.com/robfig/go-cache v0.0.0-20130306151617-9fc39e0dbf62/go.mod h1:65XQgovT59RWatovFwnwocoUxiI/eENTnOY5GK3STuY=
github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
@@ -338,8 +342,9 @@ golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
golang.org/x/exp v0.0.0-20230713183714-613f0c0eb8a1 h1:MGwJjxBy0HJshjDNfLsYO8xppfqWlA5ZT9OhtUUhTNw=
golang.org/x/exp v0.0.0-20230713183714-613f0c0eb8a1/go.mod h1:FXUEEKJgO7OQYeo8N01OfiKP8RXMtf6e8aTskBGqWdc=
golang.org/x/image v0.13.0 h1:3cge/F/QTkNLauhf2QoE9zp+7sr+ZcL4HnoZmdwg9sg=
golang.org/x/image v0.13.0/go.mod h1:6mmbMOeV28HuMTgA6OSRkdXKYw/t5W9Uwn2Yv1r3Yxk=
golang.org/x/image v0.18.0 h1:jGzIakQa/ZXI1I0Fxvaa9W7yP25TqT6cHIHn+6CqvSQ=
golang.org/x/image v0.18.0/go.mod h1:4yyo5vMFQjVjUcVk4jEQcU9MGy/rulF5WvUILseCM2E=
golang.org/x/lint v0.0.0-20190930215403-16217165b5de/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKGUJ2LatrhH/nqhxcFungHvyanc=
golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
@@ -370,7 +375,7 @@ golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJ
golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.3.0 h1:ftCYgMx6zT/asHUrPw8BLLscYtGznsLAnjq5RH9P66E=
golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -412,8 +417,8 @@ golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
golang.org/x/text v0.8.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
golang.org/x/tools v0.0.0-20190425163242-31fd60d6bfdc/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
@@ -464,9 +469,11 @@ gorm.io/driver/mysql v1.4.4 h1:MX0K9Qvy0Na4o7qSC/YI7XxqUw5KDw01umqgID+svdQ=
gorm.io/driver/mysql v1.4.4/go.mod h1:BCg8cKI+R0j/rZRQxeKis/forqRwRSYOR8OM3Wo6hOM=
gorm.io/driver/postgres v1.4.5 h1:mTeXTTtHAgnS9PgmhN2YeUbazYpLhUI1doLnw42XUZc=
gorm.io/driver/postgres v1.4.5/go.mod h1:GKNQYSJ14qvWkvPwXljMGehpKrhlDNsqYRr5HnYGncg=
gorm.io/driver/sqlite v1.5.5 h1:7MDMtUZhV065SilG62E0MquljeArQZNfJnjd9i9gx3E=
gorm.io/driver/sqlite v1.5.5/go.mod h1:6NgQ7sQWAIFsPrJJl1lSNSu2TABh0ZZ/zm5fosATavE=
gorm.io/gorm v1.23.8/go.mod h1:l2lP/RyAtc1ynaTjFksBde/O8v9oOGIApu2/xRitmZk=
gorm.io/gorm v1.24.1-0.20221019064659-5dd2bb482755/go.mod h1:DVrVomtaYTbqs7gB/x2uVvqnXzv0nqjB396B8cG4dBA=
gorm.io/gorm v1.24.2 h1:9wR6CFD+G8nOusLdvkZelOEhpJVwwHzpQOUM+REd6U0=
gorm.io/gorm v1.24.2/go.mod h1:DVrVomtaYTbqs7gB/x2uVvqnXzv0nqjB396B8cG4dBA=
gorm.io/gorm v1.25.7-0.20240204074919-46816ad31dde h1:9DShaph9qhkIYw7QF91I/ynrr4cOO2PZra2PFD7Mfeg=
gorm.io/gorm v1.25.7-0.20240204074919-46816ad31dde/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg=
rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,95 +1,106 @@
{
"id": 0,
"group_id": 0,
"name": "ARMS-DB",
"tags": "ARMS",
"ident": "",
"tags": "ARMS",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"version": "3.0.0",
"links": [],
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"type": "query",
"name": "service",
"definition": "label_values(arms_system_cpu_idle,service)",
"allOption": false,
"multi": false,
"reg": "",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
}
},
{
"type": "query",
"name": "instance",
"definition": "label_values(arms_db_requests_count{service=\"$service\"},endpoint)",
"allOption": false,
"multi": false,
"reg": "",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
}
},
{
"type": "query",
"name": "db",
"definition": "label_values(arms_db_requests_count{endpoint=\"${instance}\"},destId)",
"allValue": ".*",
"allOption": true,
"multi": false,
"reg": "",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
}
}
],
"panels": [
{
"version": "3.0.0",
"id": "bd8c0aac-06df-4b2d-9456-cad8e7389499",
"type": "row",
"name": "概览(DB级别)",
"collapsed": true,
"id": "bd8c0aac-06df-4b2d-9456-cad8e7389499",
"layout": {
"h": 1,
"i": "bd8c0aac-06df-4b2d-9456-cad8e7389499",
"w": 24,
"x": 0,
"y": 0,
"i": "bd8c0aac-06df-4b2d-9456-cad8e7389499"
"y": 0
},
"panels": []
"name": "概览(DB级别)",
"panels": [],
"type": "row",
"version": "3.0.0"
},
{
"version": "3.0.0",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "8d2da301-e5e8-4b2f-9b31-59aa0835c312",
"type": "timeseries",
"layout": {
"h": 8,
"i": "8d2da301-e5e8-4b2f-9b31-59aa0835c312",
"w": 12,
"x": 0,
"y": 1
},
"links": [],
"maxPerRow": 4,
"name": "请求数/每分钟",
"links": [],
"layout": {
"h": 8,
"w": 12,
"x": 0,
"y": 1,
"i": "8d2da301-e5e8-4b2f-9b31-59aa0835c312"
"options": {
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"refId": "B",
"expr": "sum by (callType) (sum_over_time(arms_db_requests_count{endpoint=\"${instance}\",destId=~\"${db}\"}[1m]))",
"legend": "{{callType}}入口"
"legend": "{{callType}}入口",
"refId": "B"
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "ab2b0969-50e7-4e4b-962a-58be133e6aef",
"layout": {
"h": 8,
"i": "ab2b0969-50e7-4e4b-962a-58be133e6aef",
"w": 12,
"x": 12,
"y": 1
},
"links": [],
"maxPerRow": 4,
"name": "响应时间/每分钟",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
@@ -97,101 +108,50 @@
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
},
{
"version": "3.0.0",
"id": "ab2b0969-50e7-4e4b-962a-58be133e6aef",
"type": "timeseries",
"name": "响应时间/每分钟",
"links": [],
"layout": {
"h": 8,
"w": 12,
"x": 12,
"y": 1,
"i": "ab2b0969-50e7-4e4b-962a-58be133e6aef"
},
"targets": [
{
"refId": "A",
"expr": "sum by (callType) (sum_over_time(arms_db_requests_seconds{endpoint=\"$instance\",destId=~\"^$db$\"}[1m]))/sum by (callType) (sum_over_time(arms_db_requests_count{endpoint=\"$instance\",destId=~\"^$db$\"}[1m]))",
"legend": "{{callType}}入口"
"legend": "{{callType}}入口",
"refId": "A"
}
],
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"type": "timeseries",
"version": "3.0.0"
},
{
"version": "3.0.0",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "6bd5d219-0a94-4f90-b2e0-93ed3eeca9f0",
"type": "timeseries",
"name": "错误数/每分钟",
"links": [],
"layout": {
"h": 8,
"i": "6bd5d219-0a94-4f90-b2e0-93ed3eeca9f0",
"w": 12,
"x": 0,
"y": 9,
"i": "6bd5d219-0a94-4f90-b2e0-93ed3eeca9f0"
"y": 9
},
"targets": [
{
"refId": "A",
"expr": "sum by (callType) (sum_over_time(arms_db_requests_error_count{endpoint=\"$instance\",destId=~\"$db\"}[1m]))",
"legend": "{{callType}}入口"
}
],
"links": [],
"maxPerRow": 4,
"name": "错误数/每分钟",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
@@ -199,56 +159,51 @@
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"targets": [
{
"expr": "sum by (callType) (sum_over_time(arms_db_requests_error_count{endpoint=\"$instance\",destId=~\"$db\"}[1m]))",
"legend": "{{callType}}入口",
"refId": "A"
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"version": "3.0.0",
"id": "d9093b86-5796-471a-a28c-fe1d8daf1721",
"type": "timeseries",
"name": "性能一览/每分钟",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"description": "针对所有SQL的聚和指标",
"links": [],
"id": "d9093b86-5796-471a-a28c-fe1d8daf1721",
"layout": {
"h": 8,
"i": "d9093b86-5796-471a-a28c-fe1d8daf1721",
"w": 12,
"x": 12,
"y": 9,
"i": "d9093b86-5796-471a-a28c-fe1d8daf1721"
"y": 9
},
"targets": [
{
"refId": "A",
"expr": "sum(sum_over_time(arms_db_requests_count{endpoint=\"$instance\",destId=~\"$db\"}[1m]))",
"legend": "请求次数"
},
{
"refId": "B",
"expr": "sum(sum_over_time(arms_db_requests_seconds{endpoint=\"$instance\",destId=~\"$db\"}[1m]))/sum(sum_over_time(arms_db_requests_count{endpoint=\"$instance\",destId=~\"$db\"}[1m]))",
"legend": "平均耗时"
}
],
"links": [],
"maxPerRow": 4,
"name": "性能一览/每分钟",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
@@ -256,25 +211,82 @@
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"targets": [
{
"expr": "sum(sum_over_time(arms_db_requests_count{endpoint=\"$instance\",destId=~\"$db\"}[1m]))",
"legend": "请求次数",
"refId": "A"
},
{
"expr": "sum(sum_over_time(arms_db_requests_seconds{endpoint=\"$instance\",destId=~\"$db\"}[1m]))/sum(sum_over_time(arms_db_requests_count{endpoint=\"$instance\",destId=~\"$db\"}[1m]))",
"legend": "平均耗时",
"refId": "B"
}
],
"type": "timeseries",
"version": "3.0.0"
}
]
}
}
],
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"allOption": false,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(arms_system_cpu_idle,service)",
"multi": false,
"name": "service",
"reg": "",
"type": "query"
},
{
"allOption": false,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(arms_db_requests_count{service=\"$service\"},endpoint)",
"multi": false,
"name": "instance",
"reg": "",
"type": "query"
},
{
"allOption": true,
"allValue": ".*",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(arms_db_requests_count{endpoint=\"${instance}\"},destId)",
"multi": false,
"name": "db",
"reg": "",
"type": "query"
}
],
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327092680000
}

View File

@@ -1,7 +1,13 @@
{
"id": 0,
"group_id": 0,
"name": "阿里云 ARMS-JVM-SERVICE",
"tags": "JVM ARMS",
"ident": "",
"tags": "JVM ARMS",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
@@ -770,14 +776,14 @@
"type": "datasource"
},
{
"name": "service",
"label": "service",
"type": "query",
"datasource": {
"cate": "prometheus",
"value": "${prom}"
},
"definition": "label_values(arms_jvm_buffer_pool_count, service)"
"definition": "label_values(arms_jvm_buffer_pool_count, service)",
"label": "service",
"name": "service",
"type": "query"
},
{
"datasource": {
@@ -791,5 +797,11 @@
}
],
"version": "3.0.0"
}
}
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327094704000
}

View File

@@ -1,337 +1,304 @@
{
"id": 0,
"group_id": 0,
"name": "ARMS-Machine",
"tags": "ARMS",
"ident": "",
"tags": "ARMS",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"version": "3.0.0",
"links": [],
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"type": "query",
"name": "service",
"definition": "label_values(arms_system_cpu_idle,service)",
"allOption": false,
"multi": false,
"reg": "",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
}
},
{
"type": "query",
"name": "host",
"definition": "label_values(arms_system_cpu_idle{service=\"$service\"},host)",
"allValue": "*",
"allOption": false,
"multi": false,
"reg": "",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
}
}
],
"panels": [
{
"version": "3.0.0",
"id": "8865eacb-f0f6-45fa-912a-8494907c48d6",
"type": "row",
"name": "系统信息",
"collapsed": true,
"id": "8865eacb-f0f6-45fa-912a-8494907c48d6",
"layout": {
"h": 1,
"i": "8865eacb-f0f6-45fa-912a-8494907c48d6",
"w": 24,
"x": 0,
"y": 0,
"i": "8865eacb-f0f6-45fa-912a-8494907c48d6"
"y": 0
},
"panels": []
"name": "系统信息",
"panels": [],
"type": "row",
"version": "3.0.0"
},
{
"version": "3.0.0",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "7fd3186b-6190-44c7-ad05-1c81993f27c9",
"type": "timeseries",
"layout": {
"h": 9,
"i": "7fd3186b-6190-44c7-ad05-1c81993f27c9",
"w": 24,
"x": 0,
"y": 1
},
"links": [],
"maxPerRow": 4,
"name": "CPU",
"links": [],
"layout": {
"h": 9,
"w": 24,
"x": 0,
"y": 1,
"i": "7fd3186b-6190-44c7-ad05-1c81993f27c9"
"options": {
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"refId": "A",
"expr": "max(arms_system_cpu_system{host=~\"$host\"})",
"legend": "系统CPU使用率"
"legend": "系统CPU使用率",
"refId": "A"
},
{
"refId": "B",
"expr": "max(arms_system_cpu_io_wait{host=~\"$host\"})",
"legend": "等待IO完成的CPU使用率"
"legend": "等待IO完成的CPU使用率",
"refId": "B"
},
{
"refId": "C",
"expr": "max(arms_system_cpu_user{host=~\"$host\"})",
"legend": "用户CPU使用率"
"legend": "用户CPU使用率",
"refId": "C"
},
{
"refId": "D",
"expr": "max(arms_system_cpu_system{host=\"$host\"})+max(arms_system_cpu_io_wait{host=~\"$host\"})+max(arms_system_cpu_user{host=\"$host\"})",
"legend": "总和"
"legend": "总和",
"refId": "D"
}
],
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"type": "timeseries",
"version": "3.0.0"
},
{
"version": "3.0.0",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "60fc127b-b565-40de-9346-860062d5ea58",
"type": "timeseries",
"layout": {
"h": 9,
"i": "60fc127b-b565-40de-9346-860062d5ea58",
"w": 24,
"x": 0,
"y": 10
},
"links": [],
"maxPerRow": 4,
"name": "内存",
"links": [],
"layout": {
"h": 9,
"w": 24,
"x": 0,
"y": 10,
"i": "60fc127b-b565-40de-9346-860062d5ea58"
"options": {
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"refId": "A",
"expr": "max(arms_system_mem_used_bytes{host=\"$host\"})",
"legend": "系统的已经使用的内存"
"legend": "系统的已经使用的内存",
"refId": "A"
},
{
"refId": "C",
"expr": "max(arms_system_mem_total_bytes{host=\"$host\"})",
"legend": "总和"
"legend": "总和",
"refId": "C"
},
{
"refId": "D",
"expr": "max(arms_system_mem_buffers_bytes{host=\"$host\"})",
"legend": "系统的BufferCache的内存数"
"legend": "系统的BufferCache的内存数",
"refId": "D"
},
{
"refId": "E",
"expr": "max(arms_system_mem_cached_bytes{host=\"$host\"})",
"legend": "系统的PageCache里的内存数"
"legend": "系统的PageCache里的内存数",
"refId": "E"
},
{
"refId": "B",
"expr": "max(arms_system_mem_free_bytes{host=\"$host\"})",
"legend": "系统的空闲内存"
"legend": "系统的空闲内存",
"refId": "B"
}
],
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"type": "timeseries",
"version": "3.0.0"
},
{
"version": "3.0.0",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "5229fd8c-3e26-44e6-a091-145c3caef46f",
"type": "timeseries",
"layout": {
"h": 9,
"i": "5229fd8c-3e26-44e6-a091-145c3caef46f",
"w": 24,
"x": 0,
"y": 19
},
"links": [],
"maxPerRow": 4,
"name": "负载",
"links": [],
"layout": {
"h": 9,
"w": 24,
"x": 0,
"y": 19,
"i": "5229fd8c-3e26-44e6-a091-145c3caef46f"
"options": {
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"refId": "A",
"expr": "max(arms_system_load{host=\"$host\"})",
"legend": "负载"
"legend": "负载",
"refId": "A"
}
],
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"type": "timeseries",
"version": "3.0.0"
},
{
"version": "3.0.0",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "60872e48-5445-4ee1-b0a2-19be72b6f737",
"type": "timeseries",
"layout": {
"h": 9,
"i": "60872e48-5445-4ee1-b0a2-19be72b6f737",
"w": 24,
"x": 0,
"y": 28
},
"links": [],
"maxPerRow": 4,
"name": "磁盘",
"links": [],
"layout": {
"h": 9,
"w": 24,
"x": 0,
"y": 28,
"i": "60872e48-5445-4ee1-b0a2-19be72b6f737"
"options": {
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"refId": "A",
"expr": "max(arms_system_disk_free_bytes{host=\"$host\"})",
"legend": "可用磁盘容量"
"legend": "可用磁盘容量",
"refId": "A"
},
{
"refId": "B",
"expr": "max(arms_system_disk_total_bytes{host=\"$host\"})",
"legend": "总磁盘容量"
"legend": "总磁盘容量",
"refId": "B"
},
{
"refId": "C",
"expr": "max(arms_system_disk_total_bytes{host=~\"$host\"})-max(arms_system_disk_free_bytes{host=~\"$host\"})",
"legend": "已使用磁盘容量"
"legend": "已使用磁盘容量",
"refId": "C"
}
],
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"type": "timeseries",
"version": "3.0.0"
},
{
"version": "3.0.0",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "517cc410-c4a0-4923-a902-3c102f06cd0c",
"type": "timeseries",
"name": "网络流量(Byte)/每分钟",
"links": [],
"layout": {
"h": 9,
"i": "517cc410-c4a0-4923-a902-3c102f06cd0c",
"w": 24,
"x": 0,
"y": 37,
"i": "517cc410-c4a0-4923-a902-3c102f06cd0c"
"y": 37
},
"targets": [
{
"refId": "A",
"expr": "max(max_over_time(arms_system_net_in_bytes{host=~\"$host\"}[1m]))",
"legend": "网络接收的字节数"
},
{
"refId": "B",
"expr": "max(max_over_time(arms_system_net_out_bytes{host=~\"$host\"}[1m]))",
"legend": "网络发送的字节数"
}
],
"links": [],
"maxPerRow": 4,
"name": "网络流量(Byte)/每分钟",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
@@ -339,65 +306,55 @@
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"targets": [
{
"expr": "max(max_over_time(arms_system_net_in_bytes{host=~\"$host\"}[1m]))",
"legend": "网络接收的字节数",
"refId": "A"
},
{
"expr": "max(max_over_time(arms_system_net_out_bytes{host=~\"$host\"}[1m]))",
"legend": "网络发送的字节数",
"refId": "B"
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"version": "3.0.0",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "linear",
"lineWidth": 2,
"stack": "off",
"version": "3.0.0"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "752d89ce-1136-4ddf-b4b9-1a232a8840db",
"type": "timeseries",
"name": "网络数据包(个)/每分钟",
"links": [],
"layout": {
"h": 9,
"i": "752d89ce-1136-4ddf-b4b9-1a232a8840db",
"w": 24,
"x": 0,
"y": 46,
"i": "752d89ce-1136-4ddf-b4b9-1a232a8840db"
"y": 46
},
"targets": [
{
"refId": "A",
"expr": "max(max_over_time(arms_system_net_in_packets{host=~\"$host\"}[1m]))",
"legend": "网络接收的报文数"
},
{
"refId": "C",
"expr": "max(max_over_time(arms_system_net_out_packets{host=~\"$host\"}[1m]))",
"legend": "网络发送的报文数"
},
{
"refId": "D",
"expr": "max(max_over_time(arms_system_net_in_errs{host=~\"$host\"}[1m]))",
"legend": "网络接收的错误数"
},
{
"refId": "E",
"expr": "max(max_over_time(arms_system_net_out_errs{host=~\"$host\"}[1m]))",
"legend": "网络丢弃报文数"
}
],
"links": [],
"maxPerRow": 4,
"name": "网络数据包(个)/每分钟",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
@@ -405,25 +362,80 @@
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"custom": {
"version": "3.0.0",
"drawStyle": "lines",
"lineInterpolation": "linear",
"fillOpacity": 0.3,
"stack": "off",
"lineWidth": 2,
"gradientMode": "opacity"
},
"maxPerRow": 4,
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}"
"targets": [
{
"expr": "max(max_over_time(arms_system_net_in_packets{host=~\"$host\"}[1m]))",
"legend": "网络接收的报文数",
"refId": "A"
},
{
"expr": "max(max_over_time(arms_system_net_out_packets{host=~\"$host\"}[1m]))",
"legend": "网络发送的报文数",
"refId": "C"
},
{
"expr": "max(max_over_time(arms_system_net_in_errs{host=~\"$host\"}[1m]))",
"legend": "网络接收的错误数",
"refId": "D"
},
{
"expr": "max(max_over_time(arms_system_net_out_errs{host=~\"$host\"}[1m]))",
"legend": "网络丢弃报文数",
"refId": "E"
}
],
"type": "timeseries",
"version": "3.0.0"
}
]
}
}
],
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"allOption": false,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(arms_system_cpu_idle,service)",
"multi": false,
"name": "service",
"reg": "",
"type": "query"
},
{
"allOption": false,
"allValue": "*",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(arms_system_cpu_idle{service=\"$service\"},host)",
"multi": false,
"name": "host",
"reg": "",
"type": "query"
}
],
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327098444000
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,352 +1,364 @@
{
"name": "阿里云CDN",
"tags": "CDN",
"ident": "",
"configs": {
"var": [
{
"name": "datasource",
"label": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"name": "instance_id",
"label": "instance_id",
"type": "query",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_cdn_qps_isp_value, instance_id)"
}
],
"panels": [
{
"type": "timeseries",
"id": "0430c7e9-7372-45e3-9bb2-c5939baf6bfa",
"layout": {
"h": 4,
"w": 8,
"x": 0,
"y": 0,
"i": "0430c7e9-7372-45e3-9bb2-c5939baf6bfa",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"refId": "A",
"expr": "aliyun_acs_cdn_bps_isp_value{instance_id=\"$instance_id\"}",
"legend": "峰值 {{instance_id}"
},
{
"expr": "aliyun_acs_cdn_internet_out_average{instance_id=\"$instance_id\"}",
"refId": "B",
"legend": "均值 {{instance_id}}"
}
"id": 0,
"group_id": 0,
"name": "阿里云CDN",
"ident": "",
"tags": "CDN",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": true,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "0430c7e9-7372-45e3-9bb2-c5939baf6bfa",
"layout": {
"h": 4,
"i": "0430c7e9-7372-45e3-9bb2-c5939baf6bfa",
"isResizable": true,
"w": 8,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "网络带宽(bits/s)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_cdn_bps_isp_value{instance_id=\"$instance_id\"}",
"legend": "峰值 {{instance_id}",
"refId": "A"
},
{
"expr": "aliyun_acs_cdn_internet_out_average{instance_id=\"$instance_id\"}",
"legend": "均值 {{instance_id}}",
"refId": "B"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "b438ae81-3dfc-4ed8-b66f-262a4b507e4b",
"layout": {
"h": 4,
"i": "b438ae81-3dfc-4ed8-b66f-262a4b507e4b",
"isResizable": true,
"w": 8,
"x": 8,
"y": 0
},
"maxPerRow": 4,
"name": "下行流量(bytes)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_cdn_internet_out_isp_value{instance_id=\"$instance_id\"}",
"legend": "{{instance_id}}",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "af0874c7-3123-437a-93bc-448f6de8b43b",
"layout": {
"h": 4,
"i": "c6e41c04-d591-4117-bdf1-5dc6e1f4c084",
"isResizable": true,
"w": 8,
"x": 16,
"y": 0
},
"maxPerRow": 4,
"name": "每秒访问次数(个)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_cdn_qps_isp_value{instance_id=\"$instance_id\"}",
"legend": "{{instance_id}}",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": true,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "ec8fcf96-1691-4e45-9a5f-2f183021b434",
"layout": {
"h": 4,
"i": "ec8fcf96-1691-4e45-9a5f-2f183021b434",
"isResizable": true,
"w": 8,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "边缘状态码4XX占比(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_cdn_code4xx_isp_value{instance_id=\"$instance_id\"}",
"legend": "峰值{{instance_id}}",
"refId": "A"
},
{
"expr": "aliyun_acs_cdn_bps_average{instance_id=\"$instance_id\"}",
"legend": "均值 {{instance_id}}",
"refId": "B"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": true,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "25b6e3fa-f6dd-4452-8025-3c7d9a9a592c",
"layout": {
"h": 4,
"i": "e884b781-1bd4-476c-a807-a68a6417764e",
"isResizable": true,
"w": 8,
"x": 8,
"y": 4
},
"maxPerRow": 4,
"name": "边缘状态码5XX占比(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_cdn_code5xx_isp_value{instance_id=\"$instance_id\"}",
"legend": "峰值{{instance_id}}",
"refId": "A"
},
{
"expr": "aliyun_acs_cdn_bps_average{instance_id=\"$instance_id\"}",
"legend": "均值 {{instance_id}}",
"refId": "B"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
"var": [
{
"definition": "prometheus",
"label": "datasource",
"name": "datasource",
"type": "datasource"
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_cdn_qps_isp_value, instance_id)",
"label": "instance_id",
"name": "instance_id",
"type": "query"
}
],
"name": "网络带宽(bits/s)",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": true,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
},
{
"type": "timeseries",
"id": "b438ae81-3dfc-4ed8-b66f-262a4b507e4b",
"layout": {
"h": 4,
"w": 8,
"x": 8,
"y": 0,
"i": "b438ae81-3dfc-4ed8-b66f-262a4b507e4b",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"refId": "A",
"expr": "aliyun_acs_cdn_internet_out_isp_value{instance_id=\"$instance_id\"}",
"legend": "{{instance_id}}"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "下行流量(bytes)",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
},
{
"type": "timeseries",
"id": "af0874c7-3123-437a-93bc-448f6de8b43b",
"layout": {
"h": 4,
"w": 8,
"x": 16,
"y": 0,
"i": "c6e41c04-d591-4117-bdf1-5dc6e1f4c084",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"refId": "A",
"expr": "aliyun_acs_cdn_qps_isp_value{instance_id=\"$instance_id\"}",
"legend": "{{instance_id}}"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "每秒访问次数(个)",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
},
{
"type": "timeseries",
"id": "ec8fcf96-1691-4e45-9a5f-2f183021b434",
"layout": {
"h": 4,
"w": 8,
"x": 0,
"y": 4,
"i": "ec8fcf96-1691-4e45-9a5f-2f183021b434",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"refId": "A",
"expr": "aliyun_acs_cdn_code4xx_isp_value{instance_id=\"$instance_id\"}",
"legend": "峰值{{instance_id}}"
},
{
"expr": "aliyun_acs_cdn_bps_average{instance_id=\"$instance_id\"}",
"refId": "B",
"legend": "均值 {{instance_id}}"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "边缘状态码4XX占比(%)",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": true,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
},
{
"type": "timeseries",
"id": "25b6e3fa-f6dd-4452-8025-3c7d9a9a592c",
"layout": {
"h": 4,
"w": 8,
"x": 8,
"y": 4,
"i": "e884b781-1bd4-476c-a807-a68a6417764e",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"refId": "A",
"expr": "aliyun_acs_cdn_code5xx_isp_value{instance_id=\"$instance_id\"}",
"legend": "峰值{{instance_id}}"
},
{
"expr": "aliyun_acs_cdn_bps_average{instance_id=\"$instance_id\"}",
"refId": "B",
"legend": "均值 {{instance_id}}"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "边缘状态码5XX占比(%)",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": true,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
}
],
"version": "3.0.0"
}
}
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327104499000
}

View File

@@ -1,324 +1,336 @@
{
"name": "阿里云ECS",
"tags": "",
"ident": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"id": "8606d5ad-c3c7-4b1d-86bf-474d3302ee17",
"layout": {
"h": 4,
"i": "8606d5ad-c3c7-4b1d-86bf-474d3302ee17",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "CPU平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_cpu_utilization_average{ident=~\"$ident\"}) by (ident,instance_id)",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"id": "c7034fe3-5521-4867-a8bd-429767cc03a2",
"layout": {
"h": 4,
"i": "55404296-0bd9-409d-aeaf-e9c7cceea0dd",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "内存平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_memory_usedutilization_average{ident=~\"$ident\"}) by (ident,instance_id)",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"id": "e4c11925-b359-4edb-9269-4bdd4d230224",
"layout": {
"h": 4,
"i": "0c7b3a5a-ef12-4349-be9b-7a245bf01418",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "系统负载[5m]",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_load_5m_average{ident=~\"$ident\"}) by (ident,instance_id)",
"legend": "{{ident}} {{instance_id}} 5分钟负载",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"id": "388d4da6-eb1f-48f1-955d-37579809dfec",
"layout": {
"h": 4,
"i": "5abea3d2-ea82-4bdb-a4f0-4dd1316c0377",
"isResizable": true,
"w": 12,
"x": 12,
"y": 5
},
"maxPerRow": 4,
"name": "磁盘平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_diskusage_utilization_average{ident=~\"$ident\"}) by (ident,instance_id)",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "f8d19cc9-0168-4c13-b9a9-c7980eced974",
"layout": {
"h": 4,
"i": "f8d19cc9-0168-4c13-b9a9-c7980eced974",
"w": 12,
"x": 0,
"y": 9
},
"maxPerRow": 4,
"name": "网络流量",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "bitsSI"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_intranet_in_average{ident=~\"$ident\"}) by (ident,instance_id)",
"legend": "主机:{{ident}} 实例ID: {{instance_id}} 入流量",
"refId": "A",
"step": 300,
"time": {
"end": "now",
"start": "now-5m"
"id": 0,
"group_id": 0,
"name": "阿里云ECS",
"ident": "",
"tags": "",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"datasourceValue": "${datasource}",
"id": "8606d5ad-c3c7-4b1d-86bf-474d3302ee17",
"layout": {
"h": 4,
"i": "8606d5ad-c3c7-4b1d-86bf-474d3302ee17",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "CPU平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_cpu_utilization_average{ident=~\"$ident\"}) by (ident,instance_id)",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"datasourceValue": "${datasource}",
"id": "c7034fe3-5521-4867-a8bd-429767cc03a2",
"layout": {
"h": 4,
"i": "55404296-0bd9-409d-aeaf-e9c7cceea0dd",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "内存平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_memory_usedutilization_average{ident=~\"$ident\"}) by (ident,instance_id)",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"datasourceValue": "${datasource}",
"id": "e4c11925-b359-4edb-9269-4bdd4d230224",
"layout": {
"h": 4,
"i": "0c7b3a5a-ef12-4349-be9b-7a245bf01418",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "系统负载[5m]",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_load_5m_average{ident=~\"$ident\"}) by (ident,instance_id)",
"legend": "{{ident}} {{instance_id}} 5分钟负载",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"datasourceValue": "${datasource}",
"id": "388d4da6-eb1f-48f1-955d-37579809dfec",
"layout": {
"h": 4,
"i": "5abea3d2-ea82-4bdb-a4f0-4dd1316c0377",
"isResizable": true,
"w": 12,
"x": 12,
"y": 5
},
"maxPerRow": 4,
"name": "磁盘平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_diskusage_utilization_average{ident=~\"$ident\"}) by (ident,instance_id)",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "f8d19cc9-0168-4c13-b9a9-c7980eced974",
"layout": {
"h": 4,
"i": "f8d19cc9-0168-4c13-b9a9-c7980eced974",
"w": 12,
"x": 0,
"y": 9
},
"maxPerRow": 4,
"name": "网络流量",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "bitsSI"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_ecs_dashboard_intranet_in_average{ident=~\"$ident\"}) by (ident,instance_id)",
"legend": "主机:{{ident}} 实例ID: {{instance_id}} 入流量",
"refId": "A",
"step": 300,
"time": {
"end": "now",
"start": "now-5m"
}
},
{
"expr": "sum(aliyun_acs_ecs_dashboard_intranet_out_average{ident=~\"$ident\"}) by (ident,instance_id)",
"legend": "主机:{{ident}} 实例ID: {{instance_id}} 出流量",
"refId": "B",
"step": 300,
"time": {
"end": "now",
"start": "now-5m"
}
}
],
"type": "timeseries",
"version": "2.0.0"
}
},
{
"expr": "sum(aliyun_acs_ecs_dashboard_intranet_out_average{ident=~\"$ident\"}) by (ident,instance_id)",
"legend": "主机:{{ident}} 实例ID: {{instance_id}} 出流量",
"refId": "B",
"step": 300,
"time": {
"end": "now",
"start": "now-5m"
}
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
}
],
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_ecs_dashboard_cpu_utilization_average,ident)",
"multi": true,
"name": "ident",
"type": "query"
}
],
"version": "3.0.0"
}
}
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_ecs_dashboard_cpu_utilization_average,ident)",
"multi": true,
"name": "ident",
"type": "query"
}
],
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327106006000
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,474 +1,486 @@
{
"name": "MSE监控大盘",
"tags": "",
"ident": "MSE-Monitor",
"configs": {
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"name": "envoy_clusterid",
"label": "envoy_clusterid",
"type": "query",
"hide": false,
"definition": "label_values(envoy_cluster_bind_errors, envoy_clusterid)",
"multi": false,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
}
}
],
"panels": [
{
"type": "stat",
"id": "aba69dc0-5a11-4bcd-add9-335b5a677bee",
"layout": {
"h": 5,
"w": 6,
"x": 0,
"y": 0,
"i": "aba69dc0-5a11-4bcd-add9-335b5a677bee",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": 7,
"targets": [
{
"refId": "A",
"expr": "sum(delta(envoy_http_rq_total{envoy_clusterid=\"$envoy_clusterid\"}[1m]))"
}
"id": 0,
"group_id": 0,
"name": "MSE监控大盘",
"ident": "MSE-Monitor",
"tags": "",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
"custom": {
"calc": "lastNotNull",
"colSpan": 1,
"colorMode": "value",
"graphMode": "none",
"textMode": "valueAndName",
"textSize": {},
"valueField": "Value"
},
"datasourceCate": "prometheus",
"datasourceValue": 7,
"id": "aba69dc0-5a11-4bcd-add9-335b5a677bee",
"layout": {
"h": 5,
"i": "aba69dc0-5a11-4bcd-add9-335b5a677bee",
"isResizable": true,
"w": 6,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "PV一分钟",
"options": {
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
}
},
"targets": [
{
"expr": "sum(delta(envoy_http_rq_total{envoy_clusterid=\"$envoy_clusterid\"}[1m]))",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "stat",
"version": "3.0.0"
},
{
"custom": {
"calc": "lastNotNull",
"detailName": "详情",
"legengPosition": "right"
},
"datasourceCate": "prometheus",
"datasourceValue": 7,
"id": "e34a272e-6125-4afa-a2c1-80d7d9078673",
"layout": {
"h": 5,
"i": "116a5607-5860-426e-a560-d3241da88b57",
"isResizable": true,
"w": 9,
"x": 6,
"y": 0
},
"maxPerRow": 4,
"name": "请求成功率",
"options": {
"standardOptions": {
"decimals": 0,
"util": "percentUnit"
}
},
"targets": [
{
"expr": "sum(delta(envoy_http_downstream_rq{envoy_clusterid=\"$envoy_clusterid\"}[3m])) by (response_code_class)",
"legend": "",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "pie",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": 7,
"id": "a8917108-58a6-479a-8ec4-571f1b5a79c2",
"layout": {
"h": 5,
"i": "9be66a1f-c0bb-47dc-a3c0-ad43b588789b",
"isResizable": true,
"w": 9,
"x": 15,
"y": 0
},
"maxPerRow": 4,
"name": "请求量(一分钟)",
"options": {
"legend": {
"displayMode": "list"
},
"standardOptions": {
"util": "bytesSI"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(delta(envoy_http_downstream_cx_rx_bytes_total{envoy_clusterid=\"$envoy_clusterid\"}[1m]))",
"legend": "",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": 7,
"id": "1b102bee-ccc9-49a0-a1d1-cc097bb6a987",
"layout": {
"h": 6,
"i": "1b102bee-ccc9-49a0-a1d1-cc097bb6a987",
"isResizable": true,
"w": 8,
"x": 0,
"y": 5
},
"maxPerRow": 4,
"name": "平均延迟",
"options": {
"legend": {
"displayMode": "list"
},
"standardOptions": {
"util": "milliseconds"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(rate(envoy_http_downstream_rq_time_sum{envoy_clusterid=\"$envoy_clusterid\"}[10m])) / sum(rate(envoy_http_downstream_rq_time_count{envoy_clusterid=\"$envoy_clusterid\"}[10m]))",
"legend": "",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": 7,
"id": "b432fc11-2f9d-4b72-826b-6ca787401859",
"layout": {
"h": 6,
"i": "ea4c1073-07d3-4adc-a4d3-4812cc55ad7c",
"isResizable": true,
"w": 8,
"x": 8,
"y": 5
},
"maxPerRow": 4,
"name": "P95",
"options": {
"legend": {
"displayMode": "list"
},
"standardOptions": {
"util": "milliseconds"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "histogram_quantile(0.95, sum(rate(envoy_http_downstream_rq_time_bucket{envoy_clusterid=\"$envoy_clusterid\"}[10m])) by (le, service))",
"legend": "",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": 7,
"id": "9062d707-d8a7-4a93-82e5-46f6059e8d70",
"layout": {
"h": 6,
"i": "d36246b9-4a9c-4ab0-9171-c5ac330be0ca",
"isResizable": true,
"w": 8,
"x": 16,
"y": 5
},
"maxPerRow": 4,
"name": "QPS",
"options": {
"legend": {
"displayMode": "list"
},
"standardOptions": {
"util": "none"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(irate(envoy_http_downstream_rq{envoy_clusterid=\"$envoy_clusterid\"}[2m]))",
"legend": "",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"baseColor": "#9470FF",
"calc": "lastNotNull",
"serieWidth": 40,
"sortOrder": "desc"
},
"datasourceCate": "prometheus",
"datasourceValue": 7,
"id": "c3f64cfd-adb2-4316-bb84-55f88ed513a3",
"layout": {
"h": 6,
"i": "807c34f9-bd61-4da3-ad88-41bb3e045605",
"isResizable": true,
"w": 24,
"x": 0,
"y": 11
},
"maxPerRow": 4,
"name": "Top Service Request",
"options": {
"standardOptions": {}
},
"targets": [
{
"expr": "label_replace(label_replace(topk(10, sum(delta(envoy_cluster_upstream_rq_total{envoy_clusterid=\"$envoy_clusterid\", cluster_name=~\"outbound_([0-9]+)_(.*)_(.*).svc.cluster.local$\", cluster_name!~\".*waf-proxy.static\", cluster_name!~\"outbound_([0-9]+)_(.*)_kubernetes.default.svc.cluster.local\", cluster_name!~\"outbound_([0-9]+)_(.*)_(.*).kube-system.svc.cluster.local\", cluster_name!~\"outbound_([0-9]+)_(.*)_(.*).arms-prom.svc.cluster.local\"}[1m])) by (cluster_name)), \"service_name\", \"$3\", \"cluster_name\", \"outbound_([0-9]+)_(.*)_(.*).svc.cluster.local$\"), \"port\", \"$1\", \"cluster_name\", \"outbound_([0-9]+)_(.*)_(.*).svc.cluster.local$\")",
"legend": "{{service_name}}:{{port}}",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "barGauge",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": 7,
"id": "8df57678-ff19-4b63-b768-4dad3f12222b",
"layout": {
"h": 5,
"i": "44f413ba-3262-4ccf-a4b1-c1165bafaaff",
"isResizable": true,
"w": 24,
"x": 0,
"y": 17
},
"maxPerRow": 4,
"name": "Top Service RT",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "milliseconds"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "label_replace(label_replace(avg(delta(envoy_cluster_upstream_rq_time_sum{envoy_clusterid=\"$envoy_clusterid\", cluster_name=~\"outbound_([0-9]+)_(.*)_(.*)$\"}[3m])) by (cluster_name) / avg(delta(envoy_cluster_upstream_rq_time_count{envoy_clusterid=\"$envoy_clusterid\", cluster_name=~\"outbound_([0-9]+)_(.*)_(.*)$\"}[1m])) by (cluster_name), \"service_name\", \"$3\", \"cluster_name\", \"outbound_([0-9]+)_(.*)_(.*)$\"), \"port\", \"$1\", \"cluster_name\", \"outbound_([0-9]+)_(.*)_(.*)$\")",
"legend": "{{service_name}}:{{port}}",
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(envoy_cluster_bind_errors, envoy_clusterid)",
"hide": false,
"label": "envoy_clusterid",
"multi": false,
"name": "envoy_clusterid",
"type": "query"
}
],
"name": "PV一分钟",
"maxPerRow": 4,
"custom": {
"textMode": "valueAndName",
"graphMode": "none",
"colorMode": "value",
"calc": "lastNotNull",
"valueField": "Value",
"colSpan": 1,
"textSize": {}
},
"options": {
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
},
"standardOptions": {}
}
},
{
"type": "pie",
"id": "e34a272e-6125-4afa-a2c1-80d7d9078673",
"layout": {
"h": 5,
"w": 9,
"x": 6,
"y": 0,
"i": "116a5607-5860-426e-a560-d3241da88b57",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": 7,
"targets": [
{
"refId": "A",
"expr": "sum(delta(envoy_http_downstream_rq{envoy_clusterid=\"$envoy_clusterid\"}[3m])) by (response_code_class)",
"legend": ""
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "请求成功率",
"maxPerRow": 4,
"custom": {
"calc": "lastNotNull",
"legengPosition": "right",
"detailName": "详情"
},
"options": {
"standardOptions": {
"util": "percentUnit",
"decimals": 0
}
}
},
{
"type": "timeseries",
"id": "a8917108-58a6-479a-8ec4-571f1b5a79c2",
"layout": {
"h": 5,
"w": 9,
"x": 15,
"y": 0,
"i": "9be66a1f-c0bb-47dc-a3c0-ad43b588789b",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": 7,
"targets": [
{
"refId": "A",
"expr": "sum(delta(envoy_http_downstream_cx_rx_bytes_total{envoy_clusterid=\"$envoy_clusterid\"}[1m]))",
"legend": ""
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "请求量(一分钟)",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "list"
},
"standardOptions": {
"util": "bytesSI"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
},
{
"type": "timeseries",
"id": "1b102bee-ccc9-49a0-a1d1-cc097bb6a987",
"layout": {
"h": 6,
"w": 8,
"x": 0,
"y": 5,
"i": "1b102bee-ccc9-49a0-a1d1-cc097bb6a987",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": 7,
"targets": [
{
"refId": "A",
"expr": "sum(rate(envoy_http_downstream_rq_time_sum{envoy_clusterid=\"$envoy_clusterid\"}[10m])) / sum(rate(envoy_http_downstream_rq_time_count{envoy_clusterid=\"$envoy_clusterid\"}[10m]))",
"legend": ""
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "平均延迟",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "list"
},
"standardOptions": {
"util": "milliseconds"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
},
{
"type": "timeseries",
"id": "b432fc11-2f9d-4b72-826b-6ca787401859",
"layout": {
"h": 6,
"w": 8,
"x": 8,
"y": 5,
"i": "ea4c1073-07d3-4adc-a4d3-4812cc55ad7c",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": 7,
"targets": [
{
"refId": "A",
"expr": "histogram_quantile(0.95, sum(rate(envoy_http_downstream_rq_time_bucket{envoy_clusterid=\"$envoy_clusterid\"}[10m])) by (le, service))",
"legend": ""
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "P95",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "list"
},
"standardOptions": {
"util": "milliseconds"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
},
{
"type": "timeseries",
"id": "9062d707-d8a7-4a93-82e5-46f6059e8d70",
"layout": {
"h": 6,
"w": 8,
"x": 16,
"y": 5,
"i": "d36246b9-4a9c-4ab0-9171-c5ac330be0ca",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": 7,
"targets": [
{
"refId": "A",
"expr": "sum(irate(envoy_http_downstream_rq{envoy_clusterid=\"$envoy_clusterid\"}[2m]))",
"legend": ""
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "QPS",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "list"
},
"standardOptions": {
"util": "none"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
},
{
"type": "barGauge",
"id": "c3f64cfd-adb2-4316-bb84-55f88ed513a3",
"layout": {
"h": 6,
"w": 24,
"x": 0,
"y": 11,
"i": "807c34f9-bd61-4da3-ad88-41bb3e045605",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": 7,
"targets": [
{
"refId": "A",
"expr": "label_replace(label_replace(topk(10, sum(delta(envoy_cluster_upstream_rq_total{envoy_clusterid=\"$envoy_clusterid\", cluster_name=~\"outbound_([0-9]+)_(.*)_(.*).svc.cluster.local$\", cluster_name!~\".*waf-proxy.static\", cluster_name!~\"outbound_([0-9]+)_(.*)_kubernetes.default.svc.cluster.local\", cluster_name!~\"outbound_([0-9]+)_(.*)_(.*).kube-system.svc.cluster.local\", cluster_name!~\"outbound_([0-9]+)_(.*)_(.*).arms-prom.svc.cluster.local\"}[1m])) by (cluster_name)), \"service_name\", \"$3\", \"cluster_name\", \"outbound_([0-9]+)_(.*)_(.*).svc.cluster.local$\"), \"port\", \"$1\", \"cluster_name\", \"outbound_([0-9]+)_(.*)_(.*).svc.cluster.local$\")",
"legend": "{{service_name}}:{{port}}"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "Top Service Request",
"maxPerRow": 4,
"custom": {
"calc": "lastNotNull",
"baseColor": "#9470FF",
"serieWidth": 40,
"sortOrder": "desc"
},
"options": {
"standardOptions": {}
}
},
{
"type": "timeseries",
"id": "8df57678-ff19-4b63-b768-4dad3f12222b",
"layout": {
"h": 5,
"w": 24,
"x": 0,
"y": 17,
"i": "44f413ba-3262-4ccf-a4b1-c1165bafaaff",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": 7,
"targets": [
{
"refId": "A",
"expr": "label_replace(label_replace(avg(delta(envoy_cluster_upstream_rq_time_sum{envoy_clusterid=\"$envoy_clusterid\", cluster_name=~\"outbound_([0-9]+)_(.*)_(.*)$\"}[3m])) by (cluster_name) / avg(delta(envoy_cluster_upstream_rq_time_count{envoy_clusterid=\"$envoy_clusterid\", cluster_name=~\"outbound_([0-9]+)_(.*)_(.*)$\"}[1m])) by (cluster_name), \"service_name\", \"$3\", \"cluster_name\", \"outbound_([0-9]+)_(.*)_(.*)$\"), \"port\", \"$1\", \"cluster_name\", \"outbound_([0-9]+)_(.*)_(.*)$\")",
"legend": "{{service_name}}:{{port}}"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "Top Service RT",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "milliseconds"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
}
}
],
"version": "3.0.0"
}
}
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327111860000
}

View File

@@ -0,0 +1,971 @@
{
"name": "阿里云MySQL",
"tags": "阿里云 mysql",
"ident": "",
"configs": {
"panels": [
{
"type": "row",
"id": "1cb8caf3-ef35-4572-9ecc-71b9f063a685",
"name": "关键指标",
"collapsed": true,
"layout": {
"h": 1,
"w": 24,
"x": 0,
"y": 0,
"i": "1cb8caf3-ef35-4572-9ecc-71b9f063a685",
"isResizable": false
},
"panels": []
},
{
"type": "timeseries",
"id": "5aad17df-354e-40de-a643-61da6668939b",
"layout": {
"h": 5,
"w": 24,
"x": 0,
"y": 1,
"i": "fcf9515d-3a56-4596-8b3a-d7d8631aa218",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_MySQL_SlowQueries{instanceName=\"$instance\"}",
"legend": "{{instanceName}}",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "每秒慢查询数量(countS)",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "row",
"id": "2b3a816e-94e2-4c9d-9bb8-770c458033db",
"name": "基础指标",
"collapsed": true,
"layout": {
"h": 1,
"w": 24,
"x": 0,
"y": 6,
"i": "2b3a816e-94e2-4c9d-9bb8-770c458033db",
"isResizable": false
},
"panels": []
},
{
"type": "timeseries",
"id": "12d4a674-6d09-4b02-aa4f-d767531bd368",
"layout": {
"h": 4,
"w": 8,
"x": 0,
"y": 7,
"i": "baba4778-b950-4224-9dac-9ecda041f93b",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_CpuUsage{instanceName=\"$instance\"}",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "CPU使用率",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "55b17951-a4ae-46a7-a2d7-57db1414f6ff",
"layout": {
"h": 4,
"w": 8,
"x": 8,
"y": 7,
"i": "c4c248bd-21fb-4485-8235-f50640116e65",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_MemoryUsage{instanceName=\"$instance\"}",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "内存使用率",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "02c6af68-0e59-4f62-b0e8-80a9a9d0df82",
"layout": {
"h": 4,
"w": 8,
"x": 16,
"y": 7,
"i": "51cf9211-5e76-4176-b1ec-42929ccc6803",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_DiskUsage{instanceName=\"$instance\"}",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "磁盘使用率",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "b72c5032-1ea0-4c87-9cfd-d21b374680f1",
"layout": {
"h": 4,
"w": 8,
"x": 0,
"y": 11,
"i": "b72c5032-1ea0-4c87-9cfd-d21b374680f1",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_MySQL_ActiveSessions{instanceName=\"$instance\"}",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "活跃连接数",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "b518c9c4-f0e8-4712-ab67-be4521eeff0c",
"layout": {
"h": 4,
"w": 8,
"x": 8,
"y": 11,
"i": "ff589719-6072-488d-819d-6e080a6f3c60",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_ConnectionUsage{instanceName=\"$instance\"}",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "连接数使用率",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "86c1f728-ac1e-402b-bea6-2e3979f472c3",
"layout": {
"h": 4,
"w": 8,
"x": 16,
"y": 11,
"i": "5d673c5d-1fbb-4df4-9ece-c991d053ca34",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_IOPSUsage{instanceName=\"$instance\"} ",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "IOPS使用率",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off",
"standardOptions": {
"util": "percent"
}
}
}
]
},
{
"type": "timeseries",
"id": "dc874418-8d11-409c-96e8-e48fac2f6e20",
"layout": {
"h": 4,
"w": 8,
"x": 0,
"y": 15,
"i": "86915dd4-990c-41ba-b048-3da301d97327",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_MySQL_NetworkInNew{instanceName=\"$instance\"}/ 8",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "网络流入带宽",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {
"util": "bytesSecIEC"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "b979878a-81a6-4c0d-960d-22a736d00655",
"layout": {
"h": 4,
"w": 8,
"x": 8,
"y": 15,
"i": "86f9e07f-85dc-44e0-8245-ca0a9b0dfa81",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_MySQL_NetworkOutNew{instanceName=\"$instance\"}/ 8",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "网络流出带宽",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {
"util": "bytesSecIEC"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "row",
"id": "6d896a20-bf04-4dc7-94da-1394ef109848",
"name": "性能指标",
"collapsed": true,
"layout": {
"h": 1,
"w": 24,
"x": 0,
"y": 19,
"i": "6d896a20-bf04-4dc7-94da-1394ef109848",
"isResizable": false
},
"panels": []
},
{
"type": "timeseries",
"id": "2e545b2b-130b-4829-a2d2-ee5305c302aa",
"layout": {
"h": 4,
"w": 8,
"x": 0,
"y": 20,
"i": "13dceb72-9e9d-483d-86d2-b192debdcece",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_MySQL_QPS{instanceName=\"$instance\"}",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "QPS",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {
"util": "reqps"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "0299da4b-d779-4ed7-9cd5-096f43181b2e",
"layout": {
"h": 4,
"w": 8,
"x": 8,
"y": 20,
"i": "2b23c24e-b6f9-44f5-8151-2d5a7585c31a",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_MySQL_TPS{instanceName=\"$instance\"}",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "TPS",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {
"util": "reqps"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "56a0e345-1d4d-4051-a3cf-738bea220f96",
"layout": {
"h": 4,
"w": 8,
"x": 16,
"y": 20,
"i": "d1752ed4-f4a1-4c4b-854f-1c2ef01b34a4",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"targets": [
{
"expr": "AliyunRds_MySQL_IbufUseRatio{instanceName=\"$instance\"}",
"legend": "",
"refId": "A",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "BP利用率",
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden",
"behaviour": "showItem"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"spanNulls": false,
"lineWidth": 2,
"fillOpacity": 0.3,
"gradientMode": "opacity",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
}
],
"var": [
{
"name": "datasource",
"label": "datasource",
"type": "datasource",
"hide": false,
"definition": "prometheus"
},
{
"name": "instance",
"label": "",
"type": "query",
"hide": false,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(AliyunRds_MySQL_SlowQueries, instanceName)"
}
],
"version": "3.0.0"
},
"uuid": 1717556327098444000
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,334 +1,346 @@
{
"name": "阿里云RDS",
"tags": "",
"ident": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"layout": {
"h": 4,
"i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "CPU平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_cpu_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
"id": 0,
"group_id": 0,
"name": "阿里云RDS",
"ident": "",
"tags": "",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"layout": {
"h": 4,
"i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "CPU平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_cpu_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
"layout": {
"h": 4,
"i": "09903231-6557-42be-9cf3-2873878e9bf2",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "内存平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_memory_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "37447883-ad79-46bc-888a-1be2835c1c64",
"layout": {
"h": 4,
"i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "磁盘平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_disk_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c9735607-3f24-44a7-bbf1-3ad39441c5c9",
"layout": {
"h": 4,
"i": "93a4c8a6-ac23-4e26-8a38-781ec1668820",
"isResizable": true,
"w": 12,
"x": 12,
"y": 4
},
"maxPerRow": 4,
"name": "IOPS平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_iops_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "b516e7dc-8022-409d-b907-18c4143df891",
"layout": {
"h": 5,
"i": "b516e7dc-8022-409d-b907-18c4143df891",
"isResizable": true,
"w": 24,
"x": 0,
"y": 8
},
"maxPerRow": 4,
"name": "SQL执行量",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_delete_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "delete",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_insert_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "insert",
"refId": "B"
},
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_insert_select_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "insert_select",
"refId": "C"
},
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_update_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "update",
"refId": "D"
},
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_select_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "select",
"refId": "E"
}
],
"type": "timeseries",
"version": "2.0.0"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
"layout": {
"h": 4,
"i": "09903231-6557-42be-9cf3-2873878e9bf2",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "内存平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_memory_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_rds_dashboard_cpu_usage_average,name)",
"multi": false,
"name": "name",
"type": "query"
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_rds_dashboard_cpu_usage_average{name=\"$name\"},instance_id)",
"multi": false,
"name": "instance_id",
"type": "query"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "37447883-ad79-46bc-888a-1be2835c1c64",
"layout": {
"h": 4,
"i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "磁盘平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_disk_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c9735607-3f24-44a7-bbf1-3ad39441c5c9",
"layout": {
"h": 4,
"i": "93a4c8a6-ac23-4e26-8a38-781ec1668820",
"isResizable": true,
"w": 12,
"x": 12,
"y": 4
},
"maxPerRow": 4,
"name": "IOPS平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_iops_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "b516e7dc-8022-409d-b907-18c4143df891",
"layout": {
"h": 5,
"i": "b516e7dc-8022-409d-b907-18c4143df891",
"isResizable": true,
"w": 24,
"x": 0,
"y": 8
},
"maxPerRow": 4,
"name": "SQL执行量",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_delete_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "delete",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_insert_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "insert",
"refId": "B"
},
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_insert_select_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "insert_select",
"refId": "C"
},
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_update_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "update",
"refId": "D"
},
{
"expr": "sum(aliyun_acs_rds_dashboard_my_sql_com_select_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "select",
"refId": "E"
}
],
"type": "timeseries",
"version": "2.0.0"
}
],
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"name": "name",
"type": "query",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_rds_dashboard_cpu_usage_average,name)",
"multi": false
},
{
"name": "instance_id",
"type": "query",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_rds_dashboard_cpu_usage_average{name=\"$name\"},instance_id)",
"multi": false
}
],
"version": "3.0.0"
}
}
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327125143000
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,319 +1,331 @@
{
"name": "阿里云REDIS",
"tags": "",
"ident": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"layout": {
"h": 4,
"i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "CPU平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_cpu_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
"id": 0,
"group_id": 0,
"name": "阿里云REDIS",
"ident": "",
"tags": "",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"layout": {
"h": 4,
"i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "CPU平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_cpu_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
"layout": {
"h": 4,
"i": "09903231-6557-42be-9cf3-2873878e9bf2",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "内存平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_memory_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "37447883-ad79-46bc-888a-1be2835c1c64",
"layout": {
"h": 4,
"i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "连接数平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_connection_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c9735607-3f24-44a7-bbf1-3ad39441c5c9",
"layout": {
"h": 4,
"i": "93a4c8a6-ac23-4e26-8a38-781ec1668820",
"isResizable": true,
"w": 12,
"x": 12,
"y": 4
},
"maxPerRow": 4,
"name": "失败统计平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_failed_count_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "b516e7dc-8022-409d-b907-18c4143df891",
"layout": {
"h": 5,
"i": "b516e7dc-8022-409d-b907-18c4143df891",
"isResizable": true,
"w": 24,
"x": 0,
"y": 8
},
"maxPerRow": 4,
"name": "网络流量",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "bitsSI"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_intranet_in_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "in",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_kvstore_intranet_out_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "out",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
"layout": {
"h": 4,
"i": "09903231-6557-42be-9cf3-2873878e9bf2",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "内存平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_memory_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_kvstore_cpu_usage_average,name)",
"multi": false,
"name": "name",
"type": "query"
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_kvstore_cpu_usage_average{name=\"$name\"},instance_id)",
"multi": false,
"name": "instance_id",
"type": "query"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "37447883-ad79-46bc-888a-1be2835c1c64",
"layout": {
"h": 4,
"i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "连接数平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_connection_usage_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c9735607-3f24-44a7-bbf1-3ad39441c5c9",
"layout": {
"h": 4,
"i": "93a4c8a6-ac23-4e26-8a38-781ec1668820",
"isResizable": true,
"w": 12,
"x": 12,
"y": 4
},
"maxPerRow": 4,
"name": "失败统计平均使用率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_failed_count_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "b516e7dc-8022-409d-b907-18c4143df891",
"layout": {
"h": 5,
"i": "b516e7dc-8022-409d-b907-18c4143df891",
"isResizable": true,
"w": 24,
"x": 0,
"y": 8
},
"maxPerRow": 4,
"name": "网络流量",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "bitsSI"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_kvstore_intranet_in_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "in",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_kvstore_intranet_out_average{instance_id=\"$instance_id\"}) by (instance_id)",
"legend": "out",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0"
}
],
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"name": "name",
"type": "query",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_kvstore_cpu_usage_average,name)",
"multi": false
},
{
"name": "instance_id",
"type": "query",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_kvstore_cpu_usage_average{name=\"$name\"},instance_id)",
"multi": false
}
],
"version": "3.0.0"
}
}
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327128561000
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,437 +1,449 @@
{
"name": "阿里云REDIS_N",
"tags": "",
"ident": "",
"configs": {
"panels": [
{
"collapsed": false,
"id": "2c38fd30-4c4c-40a9-ad4a-5c945db32947",
"layout": {
"h": 1,
"i": "2c38fd30-4c4c-40a9-ad4a-5c945db32947",
"isResizable": false,
"w": 24,
"x": 0,
"y": 0
},
"name": "默认分组",
"type": "row"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"layout": {
"h": 4,
"i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"isResizable": true,
"w": 8,
"x": 0,
"y": 1
},
"maxPerRow": 4,
"name": "CPU 使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_cpu_usage_average{instance_id=\"$instance_id\"}",
"instant": false,
"legend": "",
"refId": "A",
"step": 120
}
"id": 0,
"group_id": 0,
"name": "阿里云REDIS_N",
"ident": "",
"tags": "",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
"collapsed": false,
"id": "2c38fd30-4c4c-40a9-ad4a-5c945db32947",
"layout": {
"h": 1,
"i": "2c38fd30-4c4c-40a9-ad4a-5c945db32947",
"isResizable": false,
"w": 24,
"x": 0,
"y": 0
},
"name": "默认分组",
"type": "row"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"layout": {
"h": 4,
"i": "01f4d444-aa2d-466d-9615-c76baf60a40c",
"isResizable": true,
"w": 8,
"x": 0,
"y": 1
},
"maxPerRow": 4,
"name": "CPU 使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_cpu_usage_average{instance_id=\"$instance_id\"}",
"instant": false,
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
"layout": {
"h": 4,
"i": "09903231-6557-42be-9cf3-2873878e9bf2",
"isResizable": true,
"w": 8,
"x": 8,
"y": 1
},
"maxPerRow": 4,
"name": "内存使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_memory_usage_average{instance_id=\"$instance_id\"}",
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "37447883-ad79-46bc-888a-1be2835c1c64",
"layout": {
"h": 4,
"i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
"isResizable": true,
"w": 8,
"x": 16,
"y": 1
},
"maxPerRow": 4,
"name": "连接数使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_connection_usage_average{instance_id=\"$instance_id\"}",
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "2d1c8cdf-538e-48b5-8563-358f242825e5",
"layout": {
"h": 4,
"i": "764e188d-d728-44a0-a79d-133d957df9a9",
"isResizable": true,
"w": 8,
"x": 0,
"y": 5
},
"maxPerRow": 4,
"name": "流入带宽使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_intranet_in_ratio_average{instance_id=\"$instance_id\"}",
"instant": false,
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "0577dc0f-887a-4a54-9100-ef5e5e7443a0",
"layout": {
"h": 4,
"i": "93955b6b-620c-4407-908c-01ba4f544fef",
"isResizable": true,
"w": 8,
"x": 8,
"y": 5
},
"maxPerRow": 4,
"name": "流出带宽使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_intranet_out_ratio_average{instance_id=\"$instance_id\"}",
"instant": false,
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "a83bd550-3866-4225-9c09-08dd77e1b281",
"layout": {
"h": 4,
"i": "7b4d509b-1a8d-4f6a-9df4-f14116c4b9eb",
"isResizable": true,
"w": 8,
"x": 16,
"y": 5
},
"maxPerRow": 4,
"name": "连接数使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_connection_usage_average{instance_id=\"$instance_id\"}",
"instant": false,
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_kvstore_cpu_usage_average,name)",
"multi": false,
"name": "name",
"type": "query"
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_kvstore_cpu_usage_average,instance_id)",
"multi": false,
"name": "instance_id",
"type": "query"
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "c43eb882-915f-4c38-a0b5-8f33c21ab44a",
"layout": {
"h": 4,
"i": "09903231-6557-42be-9cf3-2873878e9bf2",
"isResizable": true,
"w": 8,
"x": 8,
"y": 1
},
"maxPerRow": 4,
"name": "内存使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_memory_usage_average{instance_id=\"$instance_id\"}",
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "37447883-ad79-46bc-888a-1be2835c1c64",
"layout": {
"h": 4,
"i": "378a5a26-c28e-4612-af09-f82ec2e11d80",
"isResizable": true,
"w": 8,
"x": 16,
"y": 1
},
"maxPerRow": 4,
"name": "连接数使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_connection_usage_average{instance_id=\"$instance_id\"}",
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "2d1c8cdf-538e-48b5-8563-358f242825e5",
"layout": {
"h": 4,
"i": "764e188d-d728-44a0-a79d-133d957df9a9",
"isResizable": true,
"w": 8,
"x": 0,
"y": 5
},
"maxPerRow": 4,
"name": "流入带宽使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_intranet_in_ratio_average{instance_id=\"$instance_id\"}",
"instant": false,
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "0577dc0f-887a-4a54-9100-ef5e5e7443a0",
"layout": {
"h": 4,
"i": "93955b6b-620c-4407-908c-01ba4f544fef",
"isResizable": true,
"w": 8,
"x": 8,
"y": 5
},
"maxPerRow": 4,
"name": "流出带宽使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "percent"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_intranet_out_ratio_average{instance_id=\"$instance_id\"}",
"instant": false,
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "a83bd550-3866-4225-9c09-08dd77e1b281",
"layout": {
"h": 4,
"i": "7b4d509b-1a8d-4f6a-9df4-f14116c4b9eb",
"isResizable": true,
"w": 8,
"x": 16,
"y": 5
},
"maxPerRow": 4,
"name": "连接数使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "aliyun_acs_kvstore_connection_usage_average{instance_id=\"$instance_id\"}",
"instant": false,
"legend": "",
"refId": "A",
"step": 120
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
}
],
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"name": "name",
"type": "query",
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_kvstore_cpu_usage_average,name)",
"multi": false
},
{
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_kvstore_cpu_usage_average,instance_id)",
"multi": false,
"name": "instance_id",
"type": "query"
}
],
"version": "3.0.0"
}
}
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327133348000
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,388 +1,400 @@
{
"name": "阿里云SLB",
"tags": "",
"ident": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"id": "aa8b2623-1e14-43cd-a3c4-33944a61fcc5",
"layout": {
"h": 4,
"i": "aa8b2623-1e14-43cd-a3c4-33944a61fcc5",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "七层实例QPS使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_instance_qps_utilization_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} QPS使用率 ",
"refId": "A"
}
"id": 0,
"group_id": 0,
"name": "阿里云SLB",
"ident": "",
"tags": "",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceName": "Default",
"datasourceValue": "${datasource}",
"id": "aa8b2623-1e14-43cd-a3c4-33944a61fcc5",
"layout": {
"h": 4,
"i": "aa8b2623-1e14-43cd-a3c4-33944a61fcc5",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "七层实例QPS使用率(%)",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_instance_qps_utilization_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} QPS使用率 ",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "b2002c63-8f0b-436c-b765-5bb65191f3c2",
"layout": {
"h": 4,
"i": "b2002c63-8f0b-436c-b765-5bb65191f3c2",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "7层协议实例Upstream状态码分布",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_upstream_code4xx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 状态码 4xx ",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_upstream_code5xx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 状态码 5xx ",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "71028d82-4804-468f-92f4-3444953b22cc",
"layout": {
"h": 4,
"i": "71028d82-4804-468f-92f4-3444953b22cc",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "新建连接数",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_instance_new_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 新建连接数",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "25f90635-ff68-4dc2-bfb0-c6634f0e6867",
"layout": {
"h": 4,
"i": "25f90635-ff68-4dc2-bfb0-c6634f0e6867",
"isResizable": true,
"w": 12,
"x": 12,
"y": 4
},
"maxPerRow": 4,
"name": "并发连接数",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_active_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 活跃连接数",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_inactive_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 非活跃连接数",
"refId": "B"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_max_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 最大活跃连接数",
"refId": "C"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "fde27e57-bdd6-4fd6-b3c0-75222f736d3b",
"layout": {
"h": 4,
"i": "fde27e57-bdd6-4fd6-b3c0-75222f736d3b",
"isResizable": true,
"w": 12,
"x": 0,
"y": 8
},
"maxPerRow": 4,
"name": "数据包数",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "none"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_packet_rx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 接受数据包数",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_packet_tx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 发送数据包数",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "a0fd47db-0b49-4b71-ae16-b4108324e35a",
"layout": {
"h": 4,
"i": "a0fd47db-0b49-4b71-ae16-b4108324e35a",
"isResizable": true,
"w": 12,
"x": 12,
"y": 8
},
"maxPerRow": 4,
"name": "流量",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "bitsSI"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_instance_traffic_rx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 出流量",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_instance_traffic_tx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 入流量",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "b2002c63-8f0b-436c-b765-5bb65191f3c2",
"layout": {
"h": 4,
"i": "b2002c63-8f0b-436c-b765-5bb65191f3c2",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "7层协议实例Upstream状态码分布",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_upstream_code4xx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 状态码 4xx ",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_upstream_code5xx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 状态码 5xx ",
"refId": "B"
}
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_slb_dashboard_active_connection_average ,instance_id)",
"multi": true,
"name": "instance_id",
"type": "query"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "71028d82-4804-468f-92f4-3444953b22cc",
"layout": {
"h": 4,
"i": "71028d82-4804-468f-92f4-3444953b22cc",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "新建连接数",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_instance_new_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 新建连接数",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "25f90635-ff68-4dc2-bfb0-c6634f0e6867",
"layout": {
"h": 4,
"i": "25f90635-ff68-4dc2-bfb0-c6634f0e6867",
"isResizable": true,
"w": 12,
"x": 12,
"y": 4
},
"maxPerRow": 4,
"name": "并发连接数",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_active_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 活跃连接数",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_inactive_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 非活跃连接数",
"refId": "B"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_max_connection_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 最大活跃连接数",
"refId": "C"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "fde27e57-bdd6-4fd6-b3c0-75222f736d3b",
"layout": {
"h": 4,
"i": "fde27e57-bdd6-4fd6-b3c0-75222f736d3b",
"isResizable": true,
"w": 12,
"x": 0,
"y": 8
},
"maxPerRow": 4,
"name": "数据包数",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "none"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_packet_rx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 接受数据包数",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_packet_tx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 发送数据包数",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "a0fd47db-0b49-4b71-ae16-b4108324e35a",
"layout": {
"h": 4,
"i": "a0fd47db-0b49-4b71-ae16-b4108324e35a",
"isResizable": true,
"w": 12,
"x": 12,
"y": 8
},
"maxPerRow": 4,
"name": "流量",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "bitsSI"
},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_acs_slb_dashboard_instance_traffic_rx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 出流量",
"refId": "A"
},
{
"expr": "sum(aliyun_acs_slb_dashboard_instance_traffic_tx_average{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}} 入流量",
"refId": "B"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
}
],
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_acs_slb_dashboard_active_connection_average ,instance_id)",
"multi": true,
"name": "instance_id",
"type": "query"
}
],
"version": "3.0.0"
}
}
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327138375000
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,358 +1,370 @@
{
"name": "阿里云WAF",
"tags": "",
"ident": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "ec46b990-faf5-4ed7-a791-bbac5df91636",
"layout": {
"h": 4,
"i": "ec46b990-faf5-4ed7-a791-bbac5df91636",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "4xx 环比率V3",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_4xx_ratio_wafv3_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "4xx 环比率V3",
"refId": "A"
}
"id": 0,
"group_id": 0,
"name": "阿里云WAF",
"ident": "",
"tags": "",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"panels": [
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "ec46b990-faf5-4ed7-a791-bbac5df91636",
"layout": {
"h": 4,
"i": "ec46b990-faf5-4ed7-a791-bbac5df91636",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"maxPerRow": 4,
"name": "4xx 环比率V3",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_4xx_ratio_wafv3_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "4xx 环比率V3",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "efc75e62-5e75-470d-b12b-a98ca44b268a",
"layout": {
"h": 4,
"i": "584b5a3c-2b7a-4e11-bee5-c2ed8661933e",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "5xx 环比率V3",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_5xx_ratio_wafv3_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "5xx 环比率V3",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "79aefa1b-5e50-4c0c-980d-e5523b859509",
"layout": {
"h": 4,
"i": "fc875397-c1a4-4713-b564-09abf852bcf3",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "4xx 环比率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_4xx_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "4xx 环比率",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "60c211d4-d51a-4681-b23b-ec8cc5dce7fe",
"layout": {
"h": 4,
"i": "946be0db-32a3-48ea-9473-88fdfa77201d",
"isResizable": true,
"w": 12,
"x": 12,
"y": 4
},
"maxPerRow": 4,
"name": "5xx 环比率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_5xx_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "5xx 环比率",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "0de9271c-7b19-4003-ae56-2e273b4b99c4",
"layout": {
"h": 4,
"i": "0de9271c-7b19-4003-ae56-2e273b4b99c4",
"isResizable": true,
"w": 12,
"x": 0,
"y": 8
},
"maxPerRow": 4,
"name": "QPS环比增长率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_qps_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}}QPS 环比增长率",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${datasource}",
"id": "ccf2ffc1-6f22-4a13-b795-68072c077e1f",
"layout": {
"h": 4,
"i": "d0320716-f704-4b6e-8671-b58fb77a5d7c",
"isResizable": true,
"w": 12,
"x": 12,
"y": 8
},
"maxPerRow": 4,
"name": "QPS环比下降率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_qps_ratio_down_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}}QPS 环比下降率",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "efc75e62-5e75-470d-b12b-a98ca44b268a",
"layout": {
"h": 4,
"i": "584b5a3c-2b7a-4e11-bee5-c2ed8661933e",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"maxPerRow": 4,
"name": "5xx 环比率V3",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_5xx_ratio_wafv3_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "5xx 环比率V3",
"refId": "A"
}
"var": [
{
"definition": "prometheus",
"name": "datasource",
"type": "datasource"
},
{
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_waf_qps_ratio_maximum,instance_id)",
"multi": true,
"name": "instance_id",
"type": "query"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "79aefa1b-5e50-4c0c-980d-e5523b859509",
"layout": {
"h": 4,
"i": "fc875397-c1a4-4713-b564-09abf852bcf3",
"isResizable": true,
"w": 12,
"x": 0,
"y": 4
},
"maxPerRow": 4,
"name": "4xx 环比率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_4xx_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "4xx 环比率",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "60c211d4-d51a-4681-b23b-ec8cc5dce7fe",
"layout": {
"h": 4,
"i": "946be0db-32a3-48ea-9473-88fdfa77201d",
"isResizable": true,
"w": 12,
"x": 12,
"y": 4
},
"maxPerRow": 4,
"name": "5xx 环比率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_5xx_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "5xx 环比率",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "0de9271c-7b19-4003-ae56-2e273b4b99c4",
"layout": {
"h": 4,
"i": "0de9271c-7b19-4003-ae56-2e273b4b99c4",
"isResizable": true,
"w": 12,
"x": 0,
"y": 8
},
"maxPerRow": 4,
"name": "QPS环比增长率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_qps_ratio_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}}QPS 环比增长率",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
},
{
"custom": {
"drawStyle": "lines",
"fillOpacity": 0.3,
"gradientMode": "opacity",
"lineInterpolation": "smooth",
"lineWidth": 2,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"id": "ccf2ffc1-6f22-4a13-b795-68072c077e1f",
"layout": {
"h": 4,
"i": "d0320716-f704-4b6e-8671-b58fb77a5d7c",
"isResizable": true,
"w": 12,
"x": 12,
"y": 8
},
"maxPerRow": 4,
"name": "QPS环比下降率",
"options": {
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {
"steps": [
{
"color": "#634CD9",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "none"
}
},
"targets": [
{
"expr": "sum(aliyun_waf_qps_ratio_down_maximum{instance_id=~\"$instance_id\"}) by (instance_id)",
"legend": "{{instance_id}}QPS 环比下降率",
"refId": "A"
}
],
"type": "timeseries",
"version": "2.0.0",
"datasourceValue": "${datasource}"
}
],
"var": [
{
"name": "datasource",
"type": "datasource",
"definition": "prometheus"
},
{
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${datasource}"
},
"definition": "label_values(aliyun_waf_qps_ratio_maximum,instance_id)",
"multi": true,
"name": "instance_id",
"type": "query"
}
],
"version": "3.0.0"
}
}
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327142143000
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,226 +1,238 @@
{
"id": 0,
"group_id": 0,
"name": "Group Metrics",
"tags": "",
"ident": "automq-group-metrics",
"tags": "",
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"configs": {
"version": "3.0.0",
"links": [],
"var": [
"panels": [
{
"name": "TSDB",
"type": "datasource",
"hide": false,
"definition": "prometheus"
"custom": {
"drawStyle": "lines",
"fillOpacity": 0,
"gradientMode": "none",
"lineInterpolation": "linear",
"lineWidth": 1,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${TSDB}",
"id": "cac8a249-bb61-4c2d-bc90-91a7dac58f3b",
"layout": {
"h": 5,
"i": "cac8a249-bb61-4c2d-bc90-91a7dac58f3b",
"isResizable": true,
"w": 12,
"x": 0,
"y": 0
},
"links": [],
"maxPerRow": 4,
"name": "Consumer Throughput",
"options": {
"legend": {
"behaviour": "showItem",
"displayMode": "hidden",
"placement": "bottom"
},
"standardOptions": {
"util": "none"
},
"thresholds": {
"steps": [
{
"color": "#73BF69",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "desc"
},
"valueMappings": []
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
],
"targets": [
{
"expr": "sum by(consumer_group, topic, partition) (rate(kafka_group_commit_offset{job=\"$cluster_id\", consumer_group=~\"$group_id\", topic=~\"$topic\", partition=~\"$partition\"}[$__rate_interval]))",
"legend": "{{consumer_group}}#{{topic}}-{{partition}}",
"maxDataPoints": 240,
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
},
{
"name": "cluster_id",
"type": "query",
"custom": {
"drawStyle": "lines",
"fillOpacity": 0,
"gradientMode": "none",
"lineInterpolation": "linear",
"lineWidth": 1,
"scaleDistribution": {
"type": "linear"
},
"spanNulls": false,
"stack": "off"
},
"datasourceCate": "prometheus",
"datasourceValue": "${TSDB}",
"id": "fc0afd7c-0161-4ee4-88de-81c74f432769",
"layout": {
"h": 5,
"i": "12e7bb88-2851-44ea-a311-44ebcdb0e7b7",
"isResizable": true,
"w": 12,
"x": 12,
"y": 0
},
"links": [],
"maxPerRow": 4,
"name": "Consumer Lag",
"options": {
"legend": {
"behaviour": "showItem",
"displayMode": "hidden",
"placement": "bottom"
},
"standardOptions": {
"util": "none"
},
"thresholds": {
"steps": [
{
"color": "#73BF69",
"type": "base",
"value": null
}
]
},
"tooltip": {
"mode": "all",
"sort": "desc"
},
"valueMappings": []
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
],
"targets": [
{
"expr": "sum by(topic) (max by(topic, partition) (kafka_log_end_offset{job=\"$cluster_id\", topic=~\"$topic\", partition=~\"$partition\"}))\n- on(topic) group_left(consumer_group)\nsum by(consumer_group, topic) (max by(consumer_group, topic, partition) (kafka_group_commit_offset{job=\"$cluster_id\", consumer_group=~\"$group_id\", topic=~\"$topic\", partition=~\"$partition\"}))",
"legend": "{{consumer_group}}#{{topic}}-{{partition}}",
"maxDataPoints": 240,
"refId": "A"
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"type": "timeseries",
"version": "3.0.0"
}
],
"var": [
{
"definition": "prometheus",
"hide": false,
"name": "TSDB",
"type": "datasource"
},
{
"datasource": {
"cate": "prometheus",
"value": "${TSDB}"
},
"definition": "label_values(process_runtime_jvm_cpu_utilization_ratio,job)",
"hide": false,
"multi": false,
"name": "cluster_id",
"reg": "",
"multi": false
"type": "query"
},
{
"name": "group_id",
"type": "query",
"hide": false,
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${TSDB}"
},
"definition": "label_values(kafka_group_commit_offset,consumer_group)",
"reg": "",
"hide": false,
"multi": true,
"allOption": true
"name": "group_id",
"reg": "",
"type": "query"
},
{
"name": "topic",
"type": "query",
"hide": false,
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${TSDB}"
},
"definition": "label_values(kafka_group_commit_offset,topic)",
"reg": "",
"hide": false,
"multi": true,
"allOption": true
"name": "topic",
"reg": "",
"type": "query"
},
{
"name": "partition",
"type": "query",
"hide": false,
"allOption": true,
"datasource": {
"cate": "prometheus",
"value": "${TSDB}"
},
"definition": "label_values(kafka_group_commit_offset,partition)",
"reg": "",
"hide": false,
"multi": true,
"allOption": true
"name": "partition",
"reg": "",
"type": "query"
}
],
"panels": [
{
"type": "timeseries",
"id": "cac8a249-bb61-4c2d-bc90-91a7dac58f3b",
"layout": {
"h": 5,
"w": 12,
"x": 0,
"y": 0,
"i": "cac8a249-bb61-4c2d-bc90-91a7dac58f3b",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${TSDB}",
"targets": [
{
"refId": "A",
"expr": "sum by(consumer_group, topic, partition) (rate(kafka_group_commit_offset{job=\"$cluster_id\", consumer_group=~\"$group_id\", topic=~\"$topic\", partition=~\"$partition\"}[$__rate_interval]))",
"legend": "{{consumer_group}}#{{topic}}-{{partition}}",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "Consumer Throughput",
"links": [],
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "desc"
},
"legend": {
"displayMode": "hidden",
"placement": "bottom",
"behaviour": "showItem"
},
"valueMappings": [],
"standardOptions": {
"util": "none"
},
"thresholds": {
"steps": [
{
"color": "#73BF69",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "linear",
"spanNulls": false,
"lineWidth": 1,
"fillOpacity": 0,
"gradientMode": "none",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
},
{
"type": "timeseries",
"id": "fc0afd7c-0161-4ee4-88de-81c74f432769",
"layout": {
"h": 5,
"w": 12,
"x": 12,
"y": 0,
"i": "12e7bb88-2851-44ea-a311-44ebcdb0e7b7",
"isResizable": true
},
"version": "3.0.0",
"datasourceCate": "prometheus",
"datasourceValue": "${TSDB}",
"targets": [
{
"refId": "A",
"expr": "sum by(topic) (max by(topic, partition) (kafka_log_end_offset{job=\"$cluster_id\", topic=~\"$topic\", partition=~\"$partition\"}))\n- on(topic) group_left(consumer_group)\nsum by(consumer_group, topic) (max by(consumer_group, topic, partition) (kafka_group_commit_offset{job=\"$cluster_id\", consumer_group=~\"$group_id\", topic=~\"$topic\", partition=~\"$partition\"}))",
"legend": "{{consumer_group}}#{{topic}}-{{partition}}",
"maxDataPoints": 240
}
],
"transformations": [
{
"id": "organize",
"options": {}
}
],
"name": "Consumer Lag",
"links": [],
"maxPerRow": 4,
"options": {
"tooltip": {
"mode": "all",
"sort": "desc"
},
"legend": {
"displayMode": "hidden",
"placement": "bottom",
"behaviour": "showItem"
},
"valueMappings": [],
"standardOptions": {
"util": "none"
},
"thresholds": {
"steps": [
{
"color": "#73BF69",
"value": null,
"type": "base"
}
]
}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "linear",
"spanNulls": false,
"lineWidth": 1,
"fillOpacity": 0,
"gradientMode": "none",
"stack": "off",
"scaleDistribution": {
"type": "linear"
}
},
"overrides": [
{
"matcher": {
"id": "byFrameRefID"
},
"properties": {
"rightYAxisDisplay": "off"
}
}
]
}
]
}
"version": "3.0.0"
},
"public": 0,
"public_cate": 0,
"bgids": null,
"built_in": 0,
"hide": 0,
"uuid": 1717556327172992000
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,361 @@
[
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Categraf ZooKeeper故障",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "avg(clickhouse_metrics_zoo_keeper_session ) != 1",
"severity": 2
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153856411000
},
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Categraf 内存使用",
"note": "内存使用报警",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
1,
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "clickhouse_metrics_memory_tracking / clickhouse_asynchronous_metrics_os_memory_total * 100 \u003e 90",
"severity": 1
},
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "clickhouse_metrics_memory_tracking/ clickhouse_asynchronous_metrics_os_memory_total * 100 \u003e 80",
"severity": 2
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153858877000
},
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Categraf 磁盘使用",
"note": "磁盘使用报警",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
1,
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "clickhouse_asynchronous_metrics_disk_available_default / (clickhouse_asynchronous_metrics_disk_available_default + clickhouse_asynchronous_metrics_disk_used_default) * 100 \u003c 10",
"severity": 1
},
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "clickhouse_asynchronous_metrics_disk_available_default / (clickhouse_asynchronous_metrics_disk_available_default + clickhouse_asynchronous_metrics_disk_used_default) * 100 \u003c 20",
"severity": 2
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153860224000
},
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Categraf 网络故障",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
3,
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "clickhouse_metrics_network_send \u003e 250 or clickhouse_metrics_network_receive \u003e 250",
"severity": 2
},
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "clickhouse_metrics_network_send \u003e 250 or clickhouse_metrics_network_receive \u003e 250",
"severity": 3
},
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "increase(clickhouse_metrics_interserver_connection[5m]) \u003e 0",
"severity": 3
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153861525000
}
]

View File

@@ -0,0 +1,521 @@
[
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Exporter 认证错误",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
2,
3
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "increase(ClickHouseErrorMetric_AUTHENTICATION_FAILED[5m]) \u003e 0",
"severity": 2
},
{
"prom_ql": "increase(ClickHouseErrorMetric_RESOURCE_ACCESS_DENIED[5m]) \u003e 0",
"severity": 3
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153863782000
},
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Exporter ZooKeeper故障",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"prom_ql": "avg(ClickHouseMetrics_ZooKeeperSession) != 1",
"severity": 2
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153865298000
},
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Exporter 内存使用",
"note": "内存使用报警",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
1,
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "ClickHouseMetrics_MemoryTracking / ClickHouseAsyncMetrics_OSMemoryTotal * 100 \u003e 90",
"severity": 1
},
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "ClickHouseMetrics_MemoryTracking / ClickHouseAsyncMetrics_OSMemoryTotal * 100 \u003e 80",
"severity": 2
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153866296000
},
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Exporter 副本错误",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
1,
3
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"prom_ql": "ClickHouseErrorMetric_ALL_REPLICAS_ARE_STALE == 1 or ClickHouseErrorMetric_ALL_REPLICAS_LOST == 1",
"severity": 1
},
{
"prom_ql": " ClickHouseErrorMetric_NO_AVAILABLE_REPLICA == 1",
"severity": 1
},
{
"prom_ql": " ClickHouseErrorMetric_TOO_FEW_LIVE_REPLICAS == 1",
"severity": 3
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153867268000
},
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Exporter 磁盘使用",
"note": "磁盘使用报警",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
1,
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "ClickHouseAsyncMetrics_DiskAvailable_default / (ClickHouseAsyncMetrics_DiskAvailable_default + ClickHouseAsyncMetrics_DiskUsed_default) * 100 \u003c 10",
"severity": 1
},
{
"keys": {
"labelKey": "",
"valueKey": ""
},
"prom_ql": "ClickHouseAsyncMetrics_DiskAvailable_default / (ClickHouseAsyncMetrics_DiskAvailable_default + ClickHouseAsyncMetrics_DiskUsed_default) * 100 \u003c 20",
"severity": 2
},
{
"prom_ql": "ClickHouseAsyncMetrics_DiskAvailable_backups / (ClickHouseAsyncMetrics_DiskAvailable_backups + ClickHouseAsyncMetrics_DiskUsed_backups) * 100 \u003c 20",
"severity": 2
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153868363000
},
{
"id": 0,
"group_id": 0,
"cate": "prometheus",
"datasource_ids": [
0
],
"cluster": "",
"name": "ClickHouse Exporter 网络故障",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 0,
"severities": [
2,
3
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"queries": [
{
"prom_ql": "ClickHouseMetrics_NetworkSend \u003e 250 or ClickHouseMetrics_NetworkReceive \u003e 250",
"severity": 2
},
{
"prom_ql": "ClickHouseMetrics_NetworkSend \u003e 250 or ClickHouseMetrics_NetworkReceive \u003e 250",
"severity": 3
},
{
"prom_ql": "increase(ClickHouseMetrics_InterserverConnection[5m]) \u003e 0",
"severity": 3
}
]
},
"prom_eval_interval": 30,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "00:00",
"enable_etimes": [
"00:00"
],
"enable_days_of_week": [
"0",
"1",
"2",
"3",
"4",
"5",
"6"
],
"enable_days_of_weeks": [
[
"0",
"1",
"2",
"3",
"4",
"5",
"6"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_groups_obj": null,
"notify_groups": null,
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [],
"annotations": {},
"extra_config": null,
"create_at": 0,
"create_by": "",
"update_at": 0,
"update_by": "",
"uuid": 1719305153869486000
}
]

Some files were not shown because too many files have changed in this diff Show More