Skip to content

Commit a1b8a35

Browse files
Remove deprovisioning metrics from OOB Karpenter Dashboard (DataDog#21410)
* Remove deprovisioning metrics from OOB Karpenter Dashboard * Remove deprovisioning metrics from OOB Karpenter Dashboard * Mark deprovisioning metrics as deprecated in v1+ * Undoing changes to fixtures and test * Reverting changes to metrics.py * Removing changelog
1 parent e33918b commit a1b8a35

2 files changed

Lines changed: 11 additions & 207 deletions

File tree

karpenter/assets/dashboards/karpenter_overview.json

Lines changed: 0 additions & 196 deletions
Original file line numberDiff line numberDiff line change
@@ -1334,202 +1334,6 @@
13341334
"y": 33
13351335
}
13361336
},
1337-
{
1338-
"definition": {
1339-
"background_color": "vivid_purple",
1340-
"layout_type": "ordered",
1341-
"show_title": true,
1342-
"title": "Deprovisioning Metrics",
1343-
"type": "group",
1344-
"widgets": [
1345-
{
1346-
"definition": {
1347-
"background_color": "purple",
1348-
"content": "Karpenter dynamically removes and adds nodes based on resource utilization. The following metrics collectively offer insights into the frequency and efficiency of the de-provisioning process.",
1349-
"font_size": "14",
1350-
"has_padding": true,
1351-
"show_tick": false,
1352-
"text_align": "left",
1353-
"tick_edge": "left",
1354-
"tick_pos": "50%",
1355-
"type": "note",
1356-
"vertical_align": "top"
1357-
},
1358-
"id": 7092919505065922,
1359-
"layout": {
1360-
"height": 1,
1361-
"width": 12,
1362-
"x": 0,
1363-
"y": 0
1364-
}
1365-
},
1366-
{
1367-
"definition": {
1368-
"legend_columns": [
1369-
"avg",
1370-
"min",
1371-
"max",
1372-
"value",
1373-
"sum"
1374-
],
1375-
"legend_layout": "auto",
1376-
"requests": [
1377-
{
1378-
"display_type": "bars",
1379-
"formulas": [
1380-
{
1381-
"alias": "Deprovisioning Actions",
1382-
"formula": "query1"
1383-
}
1384-
],
1385-
"queries": [
1386-
{
1387-
"data_source": "metrics",
1388-
"name": "query1",
1389-
"query": "sum:karpenter.deprovisioning.actions_performed.count{$kube_cluster_name} by {action,deprovisioner,kube_cluster_name}.as_count()"
1390-
}
1391-
],
1392-
"response_format": "timeseries",
1393-
"style": {
1394-
"line_type": "solid",
1395-
"line_width": "normal",
1396-
"palette": "dog_classic"
1397-
}
1398-
}
1399-
],
1400-
"show_legend": true,
1401-
"time": {},
1402-
"title": "Deprovisioning Actions Performed by Action and Deprovisioner",
1403-
"title_align": "left",
1404-
"title_size": "16",
1405-
"type": "timeseries"
1406-
},
1407-
"id": 4460672494144284,
1408-
"layout": {
1409-
"height": 3,
1410-
"width": 4,
1411-
"x": 0,
1412-
"y": 1
1413-
}
1414-
},
1415-
{
1416-
"definition": {
1417-
"legend_columns": [
1418-
"avg",
1419-
"min",
1420-
"max",
1421-
"value",
1422-
"sum"
1423-
],
1424-
"legend_layout": "auto",
1425-
"requests": [
1426-
{
1427-
"display_type": "line",
1428-
"formulas": [
1429-
{
1430-
"alias": "Average Evaluation Latency",
1431-
"formula": "query1 / query2"
1432-
}
1433-
],
1434-
"queries": [
1435-
{
1436-
"data_source": "metrics",
1437-
"name": "query1",
1438-
"query": "sum:karpenter.deprovisioning.evaluation.duration_seconds.sum{$kube_cluster_name} by {method,kube_cluster_name}.as_count()"
1439-
},
1440-
{
1441-
"data_source": "metrics",
1442-
"name": "query2",
1443-
"query": "sum:karpenter.deprovisioning.evaluation.duration_seconds.count{$kube_cluster_name} by {method,kube_cluster_name}.as_count()"
1444-
}
1445-
],
1446-
"response_format": "timeseries",
1447-
"style": {
1448-
"line_type": "solid",
1449-
"line_width": "normal",
1450-
"palette": "dog_classic"
1451-
}
1452-
}
1453-
],
1454-
"show_legend": true,
1455-
"time": {},
1456-
"title": "Deprovisioning Evaluation Latency by Method",
1457-
"title_align": "left",
1458-
"title_size": "16",
1459-
"type": "timeseries"
1460-
},
1461-
"id": 5737522605496062,
1462-
"layout": {
1463-
"height": 3,
1464-
"width": 4,
1465-
"x": 4,
1466-
"y": 1
1467-
}
1468-
},
1469-
{
1470-
"definition": {
1471-
"legend_columns": [
1472-
"avg",
1473-
"min",
1474-
"max",
1475-
"value",
1476-
"sum"
1477-
],
1478-
"legend_layout": "auto",
1479-
"requests": [
1480-
{
1481-
"display_type": "line",
1482-
"formulas": [
1483-
{
1484-
"alias": "Average Replacement Latency",
1485-
"formula": "query1 / query2"
1486-
}
1487-
],
1488-
"queries": [
1489-
{
1490-
"data_source": "metrics",
1491-
"name": "query1",
1492-
"query": "sum:karpenter.deprovisioning.replacement.machine.initialized_seconds.sum{$kube_cluster_name} by {kube_cluster_name}.as_count()"
1493-
},
1494-
{
1495-
"data_source": "metrics",
1496-
"name": "query2",
1497-
"query": "sum:karpenter.deprovisioning.replacement.machine.initialized_seconds.count{$kube_cluster_name} by {kube_cluster_name}.as_count()"
1498-
}
1499-
],
1500-
"response_format": "timeseries",
1501-
"style": {
1502-
"line_type": "solid",
1503-
"line_width": "normal",
1504-
"palette": "dog_classic"
1505-
}
1506-
}
1507-
],
1508-
"show_legend": true,
1509-
"time": {},
1510-
"title": "Deprovisioning Replacement Latency",
1511-
"title_align": "left",
1512-
"title_size": "16",
1513-
"type": "timeseries"
1514-
},
1515-
"id": 7590042850476366,
1516-
"layout": {
1517-
"height": 3,
1518-
"width": 4,
1519-
"x": 8,
1520-
"y": 1
1521-
}
1522-
}
1523-
]
1524-
},
1525-
"id": 649626635889086,
1526-
"layout": {
1527-
"height": 5,
1528-
"width": 12,
1529-
"x": 0,
1530-
"y": 38
1531-
}
1532-
},
15331337
{
15341338
"definition": {
15351339
"background_color": "vivid_purple",

karpenter/metadata.csv

Lines changed: 11 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -38,16 +38,16 @@ karpenter.controller.runtime.reconcile.time_seconds.sum,count,,second,,The sum o
3838
karpenter.controller.runtime.reconcile_errors.count,count,,error,,The count of reconciliation errors per controller,0,karpenter,,,
3939
karpenter.controller.runtime.reconcile_panics.count,count,,,,Total number of reconciliation panics per controller,0,karpenter,,,
4040
karpenter.controller.runtime.terminal.reconcile.errors.count,count,,,,Total number of terminal reconciliation errors per controller,0,karpenter,,,
41-
karpenter.deprovisioning.actions_performed.count,count,,execution,,The count of deprovisioning actions performed. Labeled by deprovisioner,0,karpenter,,,
42-
karpenter.deprovisioning.consolidation_timeouts,gauge,,timeout,,Number of times the Consolidation algorithm has reached a timeout. Labeled by consolidation type,0,karpenter,,,
43-
karpenter.deprovisioning.eligible_machines,gauge,,,,Number of machines eligible for deprovisioning by Karpenter. Labeled by deprovisioner,0,karpenter,,,
44-
karpenter.deprovisioning.evaluation.duration_seconds.bucket,count,,,,The count of observations in the deprovisioning evaluation histogram by `upper_bound` buckets,0,karpenter,,,
45-
karpenter.deprovisioning.evaluation.duration_seconds.count,count,,,,The count of observations in the deprovisioning evaluation histogram,0,karpenter,,,
46-
karpenter.deprovisioning.evaluation.duration_seconds.sum,count,,second,,The sum of the duration of the deprovisioning evaluation process in seconds,0,karpenter,,,
47-
karpenter.deprovisioning.replacement.machine.initialized_seconds.bucket,count,,,,The count of the observation in the replacement machine histogram by `upper_bound` buckets,0,karpenter,,,
48-
karpenter.deprovisioning.replacement.machine.initialized_seconds.count,count,,,,The count of the observation in the replacement machine histogram,0,karpenter,,,
49-
karpenter.deprovisioning.replacement.machine.initialized_seconds.sum,count,,second,,The sum of the time required for a replacement machine to become initialized,0,karpenter,,,
50-
karpenter.deprovisioning.replacement.machine.launch.failure_counter.count,count,,attempt,,The count of times that Karpenter failed to launch a replacement node for deprovisioning. Labeled by deprovisioner,0,karpenter,,,
41+
karpenter.deprovisioning.actions_performed.count,count,,execution,,The count of deprovisioning actions performed. Labeled by deprovisioner (Deprecated in v1.0+),0,karpenter,,,
42+
karpenter.deprovisioning.consolidation_timeouts,gauge,,timeout,,Number of times the Consolidation algorithm has reached a timeout. Labeled by consolidation type (Deprecated in v1.0+),0,karpenter,,,
43+
karpenter.deprovisioning.eligible_machines,gauge,,,,Number of machines eligible for deprovisioning by Karpenter. Labeled by deprovisioner (Deprecated in v1.0+),0,karpenter,,,
44+
karpenter.deprovisioning.evaluation.duration_seconds.bucket,count,,,,The count of observations in the deprovisioning evaluation histogram by `upper_bound` buckets (Deprecated in v1.0+),0,karpenter,,,
45+
karpenter.deprovisioning.evaluation.duration_seconds.count,count,,,,The count of observations in the deprovisioning evaluation histogram (Deprecated in v1.0+),0,karpenter,,,
46+
karpenter.deprovisioning.evaluation.duration_seconds.sum,count,,second,,The sum of the duration of the deprovisioning evaluation process in seconds (Deprecated in v1.0+),0,karpenter,,,
47+
karpenter.deprovisioning.replacement.machine.initialized_seconds.bucket,count,,,,The count of the observation in the replacement machine histogram by `upper_bound` buckets (Deprecated in v1.0+),0,karpenter,,,
48+
karpenter.deprovisioning.replacement.machine.initialized_seconds.count,count,,,,The count of the observation in the replacement machine histogram (Deprecated in v1.0+),0,karpenter,,,
49+
karpenter.deprovisioning.replacement.machine.initialized_seconds.sum,count,,second,,The sum of the time required for a replacement machine to become initialized (Deprecated in v1.0+),0,karpenter,,,
50+
karpenter.deprovisioning.replacement.machine.launch.failure_counter.count,count,,attempt,,The count of times that Karpenter failed to launch a replacement node for deprovisioning. Labeled by deprovisioner (Deprecated in v1.0+),0,karpenter,,,
5151
karpenter.disruption.actions_performed.count,count,,execution,,The count of disruption actions performed. Labeled by disruption method,0,karpenter,,,
5252
karpenter.disruption.budgets.allowed_disruptions,gauge,,node,,"The number of nodes for a given NodePool that can be disrupted at a point in time. Labeled by NodePool. Note that allowed disruptions can change very rapidly, as new nodes may be created and others may be deleted at any point.",0,karpenter,,,
5353
karpenter.disruption.consolidation_timeouts.count,count,,timeout,,The count of times the Consolidation algorithm has reached a timeout. Labeled by consolidation type,0,karpenter,,,
@@ -181,4 +181,4 @@ karpenter.workqueue.work.duration_seconds.count,count,,,,The count of observatio
181181
karpenter.workqueue.work.duration_seconds.sum,count,,second,,The sum of the amount of seconds spent processing an item from workqueue takes,0,karpenter,,,
182182
karpenter.workqueue_adds.count,count,,,,The count of adds handled by workqueue,0,karpenter,,,
183183
karpenter.workqueue_depth,gauge,,,,Current depth of workqueue,0,karpenter,,,
184-
karpenter.workqueue_retries.count,count,,attempt,,The count of retries handled by workqueue,0,karpenter,,,
184+
karpenter.workqueue_retries.count,count,,attempt,,The count of retries handled by workqueue,0,karpenter,,,

0 commit comments

Comments
 (0)