Skip to content
This repository has been archived by the owner on Feb 23, 2023. It is now read-only.

Commit

Permalink
Reworked system failure collection
Browse files Browse the repository at this point in the history 
Retain failure history

Annotations for both failure discovery as well as failure resolution
  • Loading branch information
@DustinBragg @lmprice
DustinBragg authored and lmprice committed Oct 10, 2019
1 parent 5fd52fb commit a8de95f
Show file tree
Hide file tree
Showing 5 changed files with 231 additions and 62 deletions.
32 changes: 30 additions & 2 deletions ansible/dashboards/Disk View Dashboard.json
View file
Original file line number Diff line number Diff line change
@@ -1,15 +1,43 @@
{
"dashboard": {
"annotations": {
"list": [
{
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
},
{
"datasource": "WSP",
"enable": true,
"hide": false,
"iconColor": "#C4162A",
"limit": 100,
"name": "Failure Discovered",
"query": "SELECT name_of,type_of FROM (SELECT name_of,type_of,active FROM \"failures\" WHERE (\"sys_name\" =~ /^$System$/) AND $timeFilter GROUP BY \"sys_name\", \"failure_type\", \"object_type\" LIMIT 25) WHERE (\"active\" = 'True')",
"showIn": 0,
"tags": [],
"tagsColumn": "type_of",
"textColumn": "name_of",
"type": "tags"
},
{
"datasource": "WSP",
"enable": true,
"hide": false,
"iconColor": "#56A64B",
"limit": 100,
"name": "Failure Resolved",
"query": "SELECT name_of,type_of FROM (SELECT name_of,type_of,active FROM \"failures\" WHERE (\"sys_name\" =~ /^$System$/) AND $timeFilter GROUP BY \"sys_name\", \"failure_type\", \"object_type\" LIMIT 25) WHERE (\"active\" = 'False')",
"showIn": 0,
"tags": [],
"tagsColumn": "type_of",
"textColumn": "name_of",
"type": "tags"
}
]
},
Expand Down
68 changes: 59 additions & 9 deletions ansible/dashboards/System View Dashboard.json
View file
Original file line number Diff line number Diff line change
@@ -1,15 +1,43 @@
{
"dashboard": {
"annotations": {
"list": [
{
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
},
{
"datasource": "WSP",
"enable": true,
"hide": false,
"iconColor": "#C4162A",
"limit": 100,
"name": "Failure Discovered",
"query": "SELECT name_of,type_of FROM (SELECT name_of,type_of,active FROM \"failures\" WHERE (\"sys_name\" =~ /^$System$/) AND $timeFilter GROUP BY \"sys_name\", \"failure_type\", \"object_type\" LIMIT 25) WHERE (\"active\" = 'True')",
"showIn": 0,
"tags": [],
"tagsColumn": "type_of",
"textColumn": "name_of",
"type": "tags"
},
{
"datasource": "WSP",
"enable": true,
"hide": false,
"iconColor": "#56A64B",
"limit": 100,
"name": "Failure Resolved",
"query": "SELECT name_of,type_of FROM (SELECT name_of,type_of,active FROM \"failures\" WHERE (\"sys_name\" =~ /^$System$/) AND $timeFilter GROUP BY \"sys_name\", \"failure_type\", \"object_type\" LIMIT 25) WHERE (\"active\" = 'False')",
"showIn": 0,
"tags": [],
"tagsColumn": "type_of",
"textColumn": "name_of",
"type": "tags"
}
]
},
Expand Down Expand Up @@ -1561,7 +1589,7 @@
"h": 10,
"w": 9,
"x": 15,
"y": 29
"y": 26
},
"id": 24,
"links": [],
Expand All @@ -1575,7 +1603,7 @@
},
"styles": [
{
"alias": "Pull Time",
"alias": "Discovery Time",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
Expand Down Expand Up @@ -1661,6 +1689,22 @@
"thresholds": [],
"type": "hidden",
"unit": "short"
},
{
"alias": "",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"mappingType": 1,
"pattern": "active",
"thresholds": [],
"type": "hidden",
"unit": "short"
}
],
"targets": [
Expand Down Expand Up @@ -1688,15 +1732,15 @@
"measurement": "failures",
"orderByTime": "ASC",
"policy": "default",
"query": "SELECT \"id\", \"location\", \"description\" FROM \"major_event_log\" WHERE (\"sys_name\" =~ /^$System$/) GROUP BY \"sys_name\"",
"rawQuery": false,
"query": "SELECT * FROM (SELECT last(\"name_of\"),active FROM \"failures\" WHERE (\"sys_name\" =~ /^$System$/) AND $timeFilter GROUP BY \"sys_name\", \"failure_type\", \"object_type\") WHERE (\"active\" = 'True')",
"rawQuery": true,
"refId": "A",
"resultFormat": "table",
"select": [
[
{
"params": [
"value"
"name_of"
],
"type": "field"
},
Expand All @@ -1711,6 +1755,12 @@
"key": "sys_name",
"operator": "=~",
"value": "/^$System$/"
},
{
"condition": "AND",
"key": "active",
"operator": "=",
"value": "True"
}
]
}
Expand Down Expand Up @@ -1740,14 +1790,14 @@
]
},
"datasource": "WSP",
"definition": "SHOW TAG VALUES FROM \"major_event_log\" WITH KEY = \"sys_name\"",
"definition": "SHOW TAG VALUES FROM \"disks\" WITH KEY = \"sys_name\"",
"hide": 0,
"includeAll": false,
"label": null,
"multi": true,
"name": "System",
"options": [],
"query": "SHOW TAG VALUES FROM \"major_event_log\" WITH KEY = \"sys_name\"",
"query": "SHOW TAG VALUES FROM \"disks\" WITH KEY = \"sys_name\"",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
Expand Down
32 changes: 30 additions & 2 deletions ansible/dashboards/Volume View Dashboard.json
View file
Original file line number Diff line number Diff line change
@@ -1,15 +1,43 @@
{
"dashboard": {
"annotations": {
"list": [
{
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
},
{
"datasource": "WSP",
"enable": true,
"hide": false,
"iconColor": "#C4162A",
"limit": 100,
"name": "Failure Discovered",
"query": "SELECT name_of,type_of FROM (SELECT name_of,type_of,active FROM \"failures\" WHERE (\"sys_name\" =~ /^$System$/) AND $timeFilter GROUP BY \"sys_name\", \"failure_type\", \"object_type\" LIMIT 25) WHERE (\"active\" = 'True')",
"showIn": 0,
"tags": [],
"tagsColumn": "type_of",
"textColumn": "name_of",
"type": "tags"
},
{
"datasource": "WSP",
"enable": true,
"hide": false,
"iconColor": "#56A64B",
"limit": 100,
"name": "Failure Resolved",
"query": "SELECT name_of,type_of FROM (SELECT name_of,type_of,active FROM \"failures\" WHERE (\"sys_name\" =~ /^$System$/) AND $timeFilter GROUP BY \"sys_name\", \"failure_type\", \"object_type\" LIMIT 25) WHERE (\"active\" = 'False')",
"showIn": 0,
"tags": [],
"tagsColumn": "type_of",
"textColumn": "name_of",
"type": "tags"
}
]
},
Expand Down
Loading

0 comments on commit a8de95f

Please sign in to comment.