Merge pull request #65 from flashcatcloud/kongfei_develop

fix redis mode compare problem

Chart.yaml

@@ -27,7 +27,7 @@ sources:
 maintainers:
 - email: contact-us@flashcat.cloud
   name: flashcatcloud
-version: 0.1.2
+version: 0.1.3
 apiVersion: v1
-appVersion: 5.9.4
+appVersion: 5.9.6
 icon: https://raw.githubusercontent.com/flashcatcloud/n9e-helm/master/n9e-icon.png

dashboards/n9e_server.json

@@ -0,0 +1,232 @@
+{
+    "name": "夜莺大盘",
+    "tags": "",
+    "configs": {
+        "var": [],
+        "panels": [
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "rate(n9e_server_samples_received_total[1m])"
+                    }
+                ],
+                "name": "每秒接收的数据点个数",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 0,
+                    "i": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4",
+                    "isResizable": true
+                },
+                "id": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "rate(n9e_server_alerts_total[10m])"
+                    }
+                ],
+                "name": "每秒产生的告警事件个数",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 0,
+                    "i": "47fc6252-9cc8-4b53-8e27-0c5c59a47269",
+                    "isResizable": true
+                },
+                "id": "f70dcb8b-b58b-4ef9-9e48-f230d9e17140"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_alert_queue_size"
+                    }
+                ],
+                "name": "告警事件内存队列长度",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 4,
+                    "i": "ad1af16c-de0c-45f4-8875-cea4e85d51d0",
+                    "isResizable": true
+                },
+                "id": "caf23e58-d907-42b0-9ed6-722c8c6f3c5f"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_http_request_duration_seconds_sum/n9e_server_http_request_duration_seconds_count"
+                    }
+                ],
+                "name": "数据接收接口平均响应时间（单位：秒）",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "noraml"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 4,
+                    "i": "64c3abc2-404c-4462-a82f-c109a21dac91",
+                    "isResizable": true
+                },
+                "id": "6b8d2db1-efca-4b9e-b429-57a9d2272bc5"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_sample_queue_size"
+                    }
+                ],
+                "name": "内存数据队列长度",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 8,
+                    "i": "1c7da942-58c2-40dc-b42f-983e4a35b89b",
+                    "isResizable": true
+                },
+                "id": "bd41677d-40d3-482e-bb6e-fbd25df46d87"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "avg(n9e_server_forward_duration_seconds_sum/n9e_server_forward_duration_seconds_count)"
+                    }
+                ],
+                "name": "数据发往TSDB平均耗时（单位：秒）",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "noraml"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 8,
+                    "i": "eed94a0b-954f-48ac-82e5-a2eada1c8a3d",
+                    "isResizable": true
+                },
+                "id": "c8642e72-f384-46a5-8410-1e6be2953c3c"
+            }
+        ],
+        "version": "2.0.0"
+    }
+}

scripts/a-n9e.sql

@@ -123,7 +123,10 @@ insert into `role_operation`(role_name, operation) values('Standard', '/job-tpls
 insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks');
 insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks/add');
 insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks/put');
-
+insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules');
+insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/add');
+insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/put');
+insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/del');
 
 -- for alert_rule | collect_rule | mute | dashboard grouping
 CREATE TABLE `busi_group` (
@@ -341,6 +344,25 @@ CREATE TABLE `metric_view` (
 
 insert into metric_view(name, cate, configs) values('Host View', 0, '{"filters":[{"oper":"=","label":"__name__","value":"cpu_usage_idle"}],"dynamicLabels":[],"dimensionLabels":[{"label":"ident","value":""}]}');
 
+CREATE TABLE `recording_rule` (
+    `id` bigint unsigned not null auto_increment,
+    `group_id` bigint not null default '0' comment 'group_id',
+    `cluster` varchar(128) not null,
+    `name` varchar(255) not null comment 'new metric name',
+    `note` varchar(255) not null comment 'rule note',
+    `disabled` tinyint(1) not null comment '0:enabled 1:disabled',
+    `prom_ql` varchar(8192) not null comment 'promql',
+    `prom_eval_interval` int not null comment 'evaluate interval',
+    `append_tags` varchar(255) default '' comment 'split by space: service=n9e mod=api',
+    `create_at` bigint default '0',
+    `create_by` varchar(64) default '',
+    `update_at` bigint default '0',
+    `update_by` varchar(64) default '',
+    PRIMARY KEY (`id`),
+    KEY `group_id` (`group_id`),
+    KEY `update_at` (`update_at`)
+) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
+
 CREATE TABLE `alert_aggr_view` (
     `id` bigint unsigned not null auto_increment,
     `name` varchar(191) not null default '',
@@ -380,6 +402,7 @@ CREATE TABLE `alert_cur_event` (
     `notify_cur_number` int not null default 0 comment '',
     `target_ident` varchar(191) not null default '' comment 'target ident, also in tags',
     `target_note` varchar(191) not null default '' comment 'target note',
+    `first_trigger_time` bigint,
     `trigger_time` bigint not null,
     `trigger_value` varchar(255) not null,
     `tags` varchar(1024) not null default '' comment 'merge data_tags rule_tags, split by ,,',
@@ -414,6 +437,7 @@ CREATE TABLE `alert_his_event` (
     `notify_cur_number` int not null default 0 comment '',
     `target_ident` varchar(191) not null default '' comment 'target ident, also in tags',
     `target_note` varchar(191) not null default '' comment 'target note',
+    `first_trigger_time` bigint,
     `trigger_time` bigint not null,
     `trigger_value` varchar(255) not null,
     `recover_time` bigint not null default 0,

templates/_helpers.tpl

@@ -240,6 +240,12 @@ app: "{{ template "nightingale.name" . }}"
   {{- end }}
 {{- end -}}
 
+{{- define "nightingale.redis.mode" -}}
+  {{- with .Values.redis }}
+    {{- ternary "standalone" .external.mode (eq .type "internal") }}
+  {{- end }}
+{{- end -}}
+
 /*scheme://[redis:password@]host:port[/master_set]*/
 {{- define "nightingale.redis.url" -}}
   {{- with .Values.redis }}

templates/categraf/daemonset.yaml

@@ -15,7 +15,6 @@
 #
 */}}
 {{- if eq .Values.categraf.type "internal" -}}
-{{- $categraf := .Values.persistence.persistentVolumeClaim.telgraf -}}
 apiVersion: apps/v1
 kind: DaemonSet
 metadata:
@@ -38,6 +37,10 @@ spec:
 {{ toYaml .Values.categraf.podAnnotations | indent 8 }}
 {{- end }} 
     spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       affinity:
         nodeAffinity:
           requiredDuringSchedulingIgnoredDuringExecution:
@@ -93,8 +96,10 @@ spec:
               name: input-net
             - mountPath: /etc/categraf/conf/input.netstat
               name: input-netstat
+            {{- if and ( eq .Values.categraf.type "internal") ( .Values.categraf.internal.docker_socket) }}
             - mountPath: /etc/categraf/conf/input.docker
               name: input-docker
+            {{- end }}
             - mountPath: /etc/categraf/conf/input.kubernetes
               name: input-kubernetes
             - mountPath: /etc/categraf/conf/input.prometheus
@@ -115,8 +120,10 @@ spec:
             - mountPath: /hostfs
               name: hostrofs
               readOnly: true
+            {{- if and ( eq .Values.categraf.type "internal") ( .Values.categraf.internal.docker_socket) }}
             - name: docker-socket
               mountPath: {{ trimPrefix "unix://" .Values.categraf.internal.docker_socket }}
+            {{- end }}
       volumes:
         - name: categraf-config
           configMap:
@@ -144,9 +151,11 @@ spec:
         - name: input-netstat
           configMap:
             name: input-netstat
+        {{- if and ( eq .Values.categraf.type "internal") ( .Values.categraf.internal.docker_socket) }}
         - name: input-docker
           configMap:
             name: input-docker
+        {{- end }}
         - name: input-kubernetes
           configMap:
             name: input-kubernetes
@@ -174,8 +183,10 @@ spec:
         - name: hostroutmp
           hostPath:
             path: /var/run/utmp
+        {{- if and ( eq .Values.categraf.type "internal") ( .Values.categraf.internal.docker_socket) }}
         - name: docker-socket
           hostPath:
             path: {{ trimPrefix "unix://" .Values.categraf.internal.docker_socket }}
             type: Socket
+        {{- end }}
 {{- end -}}

templates/categraf/docker.yaml

@@ -15,6 +15,7 @@
 #
 */}}
 {{- if eq .Values.categraf.type "internal" -}}
+{{- if .Values.categraf.internal.docker_socket -}}
 apiVersion: v1
 kind: ConfigMap
 metadata:
@@ -22,4 +23,5 @@ metadata:
 data:
 {{ (.Files.Glob "categraf/conf/input.docker/*.toml").AsConfig | indent 2 }}
 {{- end -}}
+{{- end -}}
 

templates/database/statefulset.yaml

@@ -73,6 +73,7 @@ spec:
         - mountPath: /var/lib/mysql/
           name: database-data
         - mountPath: /etc/my.cnf
+          subPath: my.cnf
           name: database-config
         - mountPath: /docker-entrypoint-initdb.d
           name: database-initdb-config

templates/nserver/conf-cm.yaml

@@ -87,8 +87,9 @@ data:
     [Redis]
     Address = "{{ template "nightingale.redis.addr" . }}"
     Password = "{{ template "nightingale.redis.password" . }}"
+    RedisType = "{{ template "nightingale.redis.mode"}}"
     [DB]
-    DSN="{{ template "nightingale.database.username" . }}:{{ template "nightingale.database.rawPassword" . }}@tcp({{ template "nightingale.database" . }}:{{ template "nightingale.database.servicePort" . }})/{{ template "nightingale.database.name" . }}?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
+    DSN="{{ template "nightingale.database.username" . }}:{{ template "nightingale.database.rawPassword" . }}@tcp({{ template "nightingale.database.host" . }}:{{ template "nightingale.database.port" . }})/{{ template "nightingale.database.name" . }}?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
     Debug = false
     DBType = "mysql"
     MaxLifetime = 7200
@@ -116,8 +117,8 @@ data:
     Url = "http://{{ template "nightingale.prometheus.host" . }}:{{ template "nightingale.prometheus.servicePort" . }}/api/v1/write"
     BasicAuthUser = "{{ template "nightingale.prometheus.username" . }}"
     BasicAuthPass = "{{ template "nightingale.prometheus.rawPassword" . }}"
-    Timeout = 30000
-    DialTimeout = 10000
+    Timeout = 10000
+    DialTimeout = 3000
     TLSHandshakeTimeout = 30000
     ExpectContinueTimeout = 1000
     IdleConnTimeout = 90000

templates/nserver/deployment.yaml

@@ -38,6 +38,10 @@ spec:
 {{ toYaml .Values.nserver.podAnnotations | indent 8 }}
 {{- end }}
     spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       containers:
         - args:
             - /app/n9e
@@ -62,7 +66,7 @@ spec:
               name: nserver-template
             - mountPath: /app/etc/script
               name: nserver-script
-      hostname: nserver
+      # hostname: nserver
       restartPolicy: Always
       volumes:
         - name: nserver-config

templates/nwebapi/conf-cm.yaml

@@ -27,6 +27,8 @@ data:
     MetricsYamlFile = "/app/etc/metrics.yaml"
     BuiltinAlertsDir = "/app/etc/alerts"
     BuiltinDashboardsDir = "/app/etc/dashboards"
+    ClustersFrom = "config"
+    ClustersFromAPIs = []
     [[NotifyChannels]]
     Label = "邮箱"
     Key = "email"
@@ -69,6 +71,10 @@ data:
     AccessExpired = 1500
     RefreshExpired = 10080
     RedisKeyPrefix = "/jwt/"
+    [ProxyAuth]
+    Enable = false
+    HeaderUserNameKey = "X-User-Name"
+    DefaultRoles = ["Standard"]
     [BasicAuth]
     user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
     [AnonymousAccess]
@@ -105,8 +111,9 @@ data:
     [Redis]
     Address = "{{ template "nightingale.redis.addr" . }}"
     Password = "{{ template "nightingale.redis.password" . }}"
+    RedisType = "{{ template "nightingale.redis.mode" . }}"
     [DB]
-    DSN = "{{ template "nightingale.database.username" . }}:{{ template "nightingale.database.rawPassword" . }}@tcp({{ template "nightingale.database" . }}:{{ template "nightingale.database.servicePort" . }})/{{ template "nightingale.database.name" . }}?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
+    DSN = "{{ template "nightingale.database.username" . }}:{{ template "nightingale.database.rawPassword" . }}@tcp({{ template "nightingale.database.host" . }}:{{ template "nightingale.database.port" . }})/{{ template "nightingale.database.name" . }}?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
     Debug = true
     DBType = "mysql"
     MaxLifetime = 7200
@@ -119,17 +126,15 @@ data:
     BasicAuthUser = ""
     BasicAuthPass = ""
     Timeout = 30000
-    DialTimeout = 10000
-    TLSHandshakeTimeout = 30000
-    ExpectContinueTimeout = 1000
-    IdleConnTimeout = 90000
-    KeepAlive = 30000
-    MaxConnsPerHost = 0
-    MaxIdleConns = 100
+    DialTimeout = 3000
     MaxIdleConnsPerHost = 100
     [Ibex]
     Address = "http://ibex:10090"
     BasicAuthUser = "ibex"
     BasicAuthPass = "ibex"
     Timeout = 3000
+    [TargetMetrics]
+    TargetUp = '''max(max_over_time(target_up{ident=~"(%s)"}[%dm])) by (ident)'''
+    LoadPerCore = '''max(max_over_time(system_load_norm_1{ident=~"(%s)"}[%dm])) by (ident)'''
+    MemUtil = '''100-max(max_over_time(mem_available_percent{ident=~"(%s)"}[%dm])) by (ident)'''
 {{- end -}}

templates/nwebapi/deployment.yaml

@@ -38,6 +38,10 @@ spec:
 {{ toYaml .Values.nwebapi.podAnnotations | indent 8 }}
 {{- end }}
     spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       containers:
       - args:
         - /app/n9e

templates/prometheus/statefulset.yaml

@@ -36,6 +36,10 @@ spec:
 {{ include "nightingale.labels" . | indent 8 }}
         component: prometheus
     spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       containers:
       - args:
           - --config.file=/etc/prometheus/prometheus.yml

tpl/README.md

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

values.yaml

@@ -162,6 +162,7 @@ redis:
     addr: "192.168.0.2:6379"
     sentinelMasterSet: ""
     password: ""
+    mode: "standalone"
   podAnnotations: {}
 
 prometheus:
@@ -192,11 +193,14 @@ categraf:
     automountServiceAccountToken: false
     image:
       repository: flashcatcloud/categraf
-      tag: v0.1.12
+      tag: latest
     nodeSelector: {}
     tolerations: []
     affinity: {}
     priorityClassName:
+    ## Parm: categraf.internal.docker_socket  Desc: the path of docker socket on kubelet node.
+    ## "unix:///var/run/docker.sock" is default, if your kubernetes runtime is container or others, empty this variable.
+    ## docker_socket: ""
     docker_socket: unix:///var/run/docker.sock
   external:
     host: "192.168.0.3"
@@ -211,8 +215,8 @@ nwebapi:
     serviceAccountName: ""
     automountServiceAccountToken: false
     image:
-      repository: docker.io/ulric2019/nightingale
-      tag: 5.9.4
+      repository: flashcatcloud/nightingale
+      tag: 5.10.3
     nodeSelector: {}
     tolerations: []
     affinity: {}
@@ -229,8 +233,8 @@ nserver:
     serviceAccountName: ""
     automountServiceAccountToken: false
     image:
-      repository: docker.io/ulric2019/nightingale
-      tag: 5.9.4
+      repository: flashcatcloud/nightingale
+      tag: 5.10.3
     nodeSelector: {}
     tolerations: []
     affinity: {}