Skip to content

Commit 01f6d5f

Browse files
sap-coutantmsap-coutantm
committed
Added Node Overview dashboard
- Display datas related to the nodes according to the job table - Linked to Cluster Inspector and Node Inspector
1 parent c5fa56e commit 01f6d5f

1 file changed

Lines changed: 267 additions & 0 deletions

File tree

‎deploy/infrabox/grafana/dashboards/nodes_overview.json‎

Lines changed: 267 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,267 @@
1+
{
2+
"annotations": {
3+
"list": [
4+
{
5+
"builtIn": 1,
6+
"datasource": "-- Grafana --",
7+
"enable": true,
8+
"hide": true,
9+
"iconColor": "rgba(0, 211, 255, 1)",
10+
"name": "Annotations & Alerts",
11+
"type": "dashboard"
12+
}
13+
]
14+
},
15+
"description": "A quick overview of the differents nodes refered by the jobs in the PostGres DB",
16+
"editable": true,
17+
"gnetId": null,
18+
"graphTooltip": 0,
19+
"id": 8,
20+
"links": [],
21+
"panels": [
22+
{
23+
"columns": [],
24+
"datasource": "infrabox",
25+
"description": "A list of all the Nodes refereed by the jobs in the DB.\n\n(TR) means the value is computed for the specified Time Range according to the specified end_date of the inspected jobs.",
26+
"fontSize": "100%",
27+
"gridPos": {
28+
"h": 24,
29+
"w": 24,
30+
"x": 0,
31+
"y": 0
32+
},
33+
"id": 2,
34+
"links": [],
35+
"pageSize": null,
36+
"scroll": true,
37+
"showHeader": true,
38+
"sort": {
39+
"col": 3,
40+
"desc": true
41+
},
42+
"styles": [
43+
{
44+
"$$hashKey": "object:897",
45+
"alias": "Cluster",
46+
"colorMode": null,
47+
"colors": [
48+
"rgba(245, 54, 54, 0.9)",
49+
"rgba(237, 129, 40, 0.89)",
50+
"rgba(50, 172, 45, 0.97)"
51+
],
52+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
53+
"decimals": 2,
54+
"link": true,
55+
"linkTooltip": "Inspect",
56+
"linkUrl": "d/phgvzfHmz/cluster-inspector?orgId=1&var-cluster=${__cell}",
57+
"mappingType": 1,
58+
"pattern": "cluster_name",
59+
"sanitize": false,
60+
"thresholds": [],
61+
"type": "string",
62+
"unit": "short"
63+
},
64+
{
65+
"$$hashKey": "object:927",
66+
"alias": "Node",
67+
"colorMode": null,
68+
"colors": [
69+
"rgba(245, 54, 54, 0.9)",
70+
"rgba(237, 129, 40, 0.89)",
71+
"rgba(50, 172, 45, 0.97)"
72+
],
73+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
74+
"decimals": 2,
75+
"link": true,
76+
"linkTooltip": "Inspect",
77+
"linkUrl": "d/09c0DMdiz/node-inspector?orgId=1&var-node_name=${__cell}",
78+
"mappingType": 1,
79+
"pattern": "node_name",
80+
"thresholds": [],
81+
"type": "string",
82+
"unit": "short"
83+
},
84+
{
85+
"$$hashKey": "object:959",
86+
"alias": "Running Jobs",
87+
"colorMode": null,
88+
"colors": [
89+
"rgba(245, 54, 54, 0.9)",
90+
"rgba(237, 129, 40, 0.89)",
91+
"rgba(50, 172, 45, 0.97)"
92+
],
93+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
94+
"decimals": 0,
95+
"mappingType": 1,
96+
"pattern": "jobs_runnings",
97+
"thresholds": [],
98+
"type": "number",
99+
"unit": "none"
100+
},
101+
{
102+
"$$hashKey": "object:972",
103+
"alias": "Scheduled Jobs",
104+
"colorMode": null,
105+
"colors": [
106+
"rgba(245, 54, 54, 0.9)",
107+
"rgba(237, 129, 40, 0.89)",
108+
"rgba(50, 172, 45, 0.97)"
109+
],
110+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
111+
"decimals": 0,
112+
"mappingType": 1,
113+
"pattern": "jobs_scheduled",
114+
"thresholds": [],
115+
"type": "number",
116+
"unit": "short"
117+
},
118+
{
119+
"$$hashKey": "object:1210",
120+
"alias": "Queued Jobs",
121+
"colorMode": null,
122+
"colors": [
123+
"rgba(245, 54, 54, 0.9)",
124+
"rgba(237, 129, 40, 0.89)",
125+
"rgba(50, 172, 45, 0.97)"
126+
],
127+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
128+
"decimals": 0,
129+
"mappingType": 1,
130+
"pattern": "jobs_queued",
131+
"thresholds": [],
132+
"type": "number",
133+
"unit": "short"
134+
},
135+
{
136+
"$$hashKey": "object:1223",
137+
"alias": "Failed Jobs (TR)",
138+
"colorMode": null,
139+
"colors": [
140+
"rgba(245, 54, 54, 0.9)",
141+
"rgba(237, 129, 40, 0.89)",
142+
"rgba(50, 172, 45, 0.97)"
143+
],
144+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
145+
"decimals": 0,
146+
"mappingType": 1,
147+
"pattern": "failed_jobs_tr",
148+
"thresholds": [],
149+
"type": "number",
150+
"unit": "short"
151+
},
152+
{
153+
"$$hashKey": "object:1402",
154+
"alias": "'Finished' Rate (TR)",
155+
"colorMode": "value",
156+
"colors": [
157+
"rgba(245, 54, 54, 0.9)",
158+
"rgba(237, 129, 40, 0.89)",
159+
"rgba(50, 172, 45, 0.97)"
160+
],
161+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
162+
"decimals": 1,
163+
"mappingType": 1,
164+
"pattern": "finished_rate_tr",
165+
"thresholds": [
166+
"0.8",
167+
"0.9"
168+
],
169+
"type": "number",
170+
"unit": "percentunit"
171+
},
172+
{
173+
"$$hashKey": "object:1415",
174+
"alias": "'Error' Rate (TR)",
175+
"colorMode": "value",
176+
"colors": [
177+
"rgba(50, 172, 45, 0.97)",
178+
"rgba(237, 129, 40, 0.89)",
179+
"rgba(245, 54, 54, 0.9)"
180+
],
181+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
182+
"decimals": 2,
183+
"mappingType": 1,
184+
"pattern": "error_rate_tr",
185+
"thresholds": [
186+
"0.05",
187+
"0.1"
188+
],
189+
"type": "number",
190+
"unit": "percentunit"
191+
},
192+
{
193+
"$$hashKey": "object:1558",
194+
"alias": "'Failure' Rate (TR)",
195+
"colorMode": "value",
196+
"colors": [
197+
"rgba(50, 172, 45, 0.97)",
198+
"rgba(237, 129, 40, 0.89)",
199+
"rgba(245, 54, 54, 0.9)"
200+
],
201+
"dateFormat": "YYYY-MM-DD HH:mm:ss",
202+
"decimals": 2,
203+
"mappingType": 1,
204+
"pattern": "failure_rate_tr",
205+
"thresholds": [
206+
"0.1",
207+
"0.2"
208+
],
209+
"type": "number",
210+
"unit": "percentunit"
211+
}
212+
],
213+
"targets": [
214+
{
215+
"$$hashKey": "object:555",
216+
"alias": "",
217+
"format": "table",
218+
"hide": false,
219+
"rawSql": "SELECT\n\tj.cluster_name,\n\tj.node_name,\n\tcount(j.id) filter (where j.state = 'running') as jobs_runnings,\n\tcount(j.id) filter (where j.state = 'scheduled') as jobs_scheduled,\n\tcount(j.id) filter (where j.state = 'queued') as jobs_queued,\n\tcount(j.id) filter (where (j.state IN ('failure', 'error')) and $__timeFilter(j.end_date)) as failed_jobs_tr,\n\tCASE\n\t count(j.id) filter (where j.state NOT IN ('running', 'scheduled', 'queued') and $__timeFilter(j.end_date))\n\tWHEN\n\t 0\n\tTHEN\n\t\tNULL\n\tELSE \n\t\t(count(j.id) filter (where (j.state = 'finished' and $__timeFilter(j.end_date))))::float / (count(j.id) filter (where j.state NOT IN ('running', 'scheduled', 'queued') and $__timeFilter(j.end_date)))::float\n\tEND as finished_rate_tr,\n\tCASE\n\t count(j.id) filter (where j.state NOT IN ('running', 'scheduled', 'queued') and $__timeFilter(j.end_date))\n\tWHEN\n\t 0\n\tTHEN\n\t\tNULL\n\tELSE \n\t\t(count(j.id) filter (where (j.state = 'error' and $__timeFilter(j.end_date))))::float / (count(j.id) filter (where j.state NOT IN ('running', 'scheduled', 'queued') and $__timeFilter(j.end_date)))::float\n\tEND as error_rate_tr,\n\tCASE\n\t count(j.id) filter (where j.state NOT IN ('running', 'scheduled', 'queued') and $__timeFilter(j.end_date))\n\tWHEN\n\t 0\n\tTHEN\n\t\tNULL\n\tELSE \n\t\t(count(j.id) filter (where (j.state = 'failure' and $__timeFilter(j.end_date))))::float / (count(j.id) filter (where j.state NOT IN ('running', 'scheduled', 'queued') and $__timeFilter(j.end_date)))::float\n\tEND as failure_rate_tr\nFROM\n\tjob j\nWHERE \n j.node_name is not null\nGROUP BY\n\tj.cluster_name, j.node_name",
220+
"refId": "A"
221+
}
222+
],
223+
"title": "Node List",
224+
"transform": "table",
225+
"type": "table"
226+
}
227+
],
228+
"schemaVersion": 16,
229+
"style": "dark",
230+
"tags": [],
231+
"templating": {
232+
"list": []
233+
},
234+
"time": {
235+
"from": "now-3h",
236+
"to": "now"
237+
},
238+
"timepicker": {
239+
"refresh_intervals": [
240+
"5s",
241+
"10s",
242+
"30s",
243+
"1m",
244+
"5m",
245+
"15m",
246+
"30m",
247+
"1h",
248+
"2h",
249+
"1d"
250+
],
251+
"time_options": [
252+
"5m",
253+
"15m",
254+
"1h",
255+
"6h",
256+
"12h",
257+
"24h",
258+
"2d",
259+
"7d",
260+
"30d"
261+
]
262+
},
263+
"timezone": "",
264+
"title": "Nodes Overview",
265+
"uid": "u_5vkIdiz",
266+
"version": 2
267+
}

0 commit comments

Comments
 (0)