Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix: headroom dashboard available ops panel is broken #1720

Merged
merged 1 commit into from
Feb 13, 2023
Merged

fix: headroom dashboard available ops panel is broken #1720

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
315 changes: 156 additions & 159 deletions grafana/dashboards/cmode/headroom.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,178 +81,175 @@
"y": 0
},
"id": 43,
"panels": [
{
"datasource": "${DS_PROMETHEUS}",
"description": "A projection of the amount of available IOP/s each aggregate has with the current workloads before increased hockey stick style latencies are encountered.<br/><br/>This graph displays the difference between Aggregate Utilization and Peak Performance (Optimal Point) as Available Ops (aka Headroom). If the current Available utilization is very low or negative for an extended time, a performance remediation plan might be appropriate. A performance remediation plan might include setting QoS workload limits, moving volumes or LUNs to another storage controller, or expanding the storage cluster.<br/><br/>This graph displays aggregate with confidence factor greater than 1. The confidence factor is used to guage the accuracy of the optimal point for the given resource.Denoted by the following values:<br/>\n1 - Low - Seed value is used for optimal point. There's not enough data to predict optimal point.<br/>\n2 - Medium - Some data to extrapolate optimal point.<br/>\n3 - High - Substantial data which reaches or exceeds optimal point, thereby the \"optimal point\" is known. <br/>\n0 - Unknown - The resource is not available or is not in use, or there's an internal error such that the data cannot be retrieved. <br/>\nFor more details see \nhttps://kb.netapp.com/Advice_and_Troubleshooting/Data_Storage_Software/ONTAP_OS/Is_my_controller_overloaded%3F",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "iops"
"panels": [],
"title": "Available Ops",
"type": "row"
},
{
"datasource": "${DS_PROMETHEUS}",
"description": "A projection of the amount of available IOP/s each aggregate has with the current workloads before increased hockey stick style latencies are encountered.<br/><br/>This graph displays the difference between Aggregate Utilization and Peak Performance (Optimal Point) as Available Ops (aka Headroom). If the current Available utilization is very low or negative for an extended time, a performance remediation plan might be appropriate. A performance remediation plan might include setting QoS workload limits, moving volumes or LUNs to another storage controller, or expanding the storage cluster.<br/><br/>This graph displays aggregate with confidence factor greater than 1. The confidence factor is used to guage the accuracy of the optimal point for the given resource.Denoted by the following values:<br/>\n1 - Low - Seed value is used for optimal point. There's not enough data to predict optimal point.<br/>\n2 - Medium - Some data to extrapolate optimal point.<br/>\n3 - High - Substantial data which reaches or exceeds optimal point, thereby the \"optimal point\" is known. <br/>\n0 - Unknown - The resource is not available or is not in use, or there's an internal error such that the data cannot be retrieved. <br/>\nFor more details see \nhttps://kb.netapp.com/Advice_and_Troubleshooting/Data_Storage_Software/ONTAP_OS/Is_my_controller_overloaded%3F",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 1
},
"id": 45,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "bottom"
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"tooltip": {
"mode": "single",
"sort": "none"
"showPoints": "auto",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"targets": [
{
"exemplar": true,
"expr": "headroom_aggr_optimal_point_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",aggr=~\"$OptimalPointAggr\"} - headroom_aggr_current_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",aggr=~\"$OptimalPointAggr\"}",
"interval": "",
"legendFormat": "{{node}} - {{aggr}}",
"refId": "A"
}
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "iops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 1
},
"id": 45,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max"
],
"title": "Available Ops: Aggregate",
"type": "timeseries"
"displayMode": "table",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"datasource": "${DS_PROMETHEUS}",
"description": "A projection of the amount of available IOP/s each node has with the current workloads before increased hockey stick style latencies are encountered.<br/><br/>This graph displays the difference between CPU Utilization and Peak Performance (Optimal Point) as Available Ops (aka Headroom). If the current Available utilization is very low or negative for an extended time, a performance remediation plan might be appropriate. A performance remediation plan might include setting QoS workload limits, moving volumes or LUNs to another storage controller, or expanding the storage cluster.<br/><br/>This graph displays node with confidence factor greater than 1. The confidence factor is used to guage the accuracy of the optimal point for the given resource.Denoted by the following values:<br/>\n1 - Low - Seed value is used for optimal point. There's not enough data to predict optimal point.<br/>\n2 - Medium - Some data to extrapolate optimal point.<br/>\n3 - High - Substantial data which reaches or exceeds optimal point, thereby the \"optimal point\" is known. <br/>\n0 - Unknown - The resource is not available or is not in use, or there's an internal error such that the data cannot be retrieved. <br/>\nFor more details see\nhttps://kb.netapp.com/Advice_and_Troubleshooting/Data_Storage_Software/ONTAP_OS/Is_my_controller_overloaded%3F",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "iops"
"exemplar": true,
"expr": "headroom_aggr_optimal_point_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",aggr=~\"$OptimalPointAggr\"} - headroom_aggr_current_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",aggr=~\"$OptimalPointAggr\"}",
"interval": "",
"legendFormat": "{{node}} - {{aggr}}",
"refId": "A"
}
],
"title": "Available Ops: Aggregate",
"type": "timeseries"
},
{
"datasource": "${DS_PROMETHEUS}",
"description": "A projection of the amount of available IOP/s each node has with the current workloads before increased hockey stick style latencies are encountered.<br/><br/>This graph displays the difference between CPU Utilization and Peak Performance (Optimal Point) as Available Ops (aka Headroom). If the current Available utilization is very low or negative for an extended time, a performance remediation plan might be appropriate. A performance remediation plan might include setting QoS workload limits, moving volumes or LUNs to another storage controller, or expanding the storage cluster.<br/><br/>This graph displays node with confidence factor greater than 1. The confidence factor is used to guage the accuracy of the optimal point for the given resource.Denoted by the following values:<br/>\n1 - Low - Seed value is used for optimal point. There's not enough data to predict optimal point.<br/>\n2 - Medium - Some data to extrapolate optimal point.<br/>\n3 - High - Substantial data which reaches or exceeds optimal point, thereby the \"optimal point\" is known. <br/>\n0 - Unknown - The resource is not available or is not in use, or there's an internal error such that the data cannot be retrieved. <br/>\nFor more details see\nhttps://kb.netapp.com/Advice_and_Troubleshooting/Data_Storage_Software/ONTAP_OS/Is_my_controller_overloaded%3F",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 1
},
"id": 46,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "bottom"
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"tooltip": {
"mode": "single",
"sort": "none"
"showPoints": "auto",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"targets": [
{
"exemplar": true,
"expr": "headroom_cpu_optimal_point_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$OptimalPointCPU\"} - headroom_cpu_current_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$OptimalPointCPU\"}",
"interval": "",
"legendFormat": "{{node}}",
"refId": "A"
}
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "iops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 1
},
"id": 46,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max"
],
"title": "Available Ops: CPU",
"type": "timeseries"
"displayMode": "table",
"placement": "bottom"
},
"tooltip": {
"mode": "single"
}
},
"targets": [
{
"exemplar": true,
"expr": "headroom_cpu_optimal_point_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$OptimalPointCPU\"} - headroom_cpu_current_ops{datacenter=~\"$Datacenter\",cluster=~\"$Cluster\",node=~\"$OptimalPointCPU\"}",
"interval": "",
"legendFormat": "{{node}}",
"refId": "A"
}
],
"title": "Available Ops",
"type": "row"
"title": "Available Ops: CPU",
"type": "timeseries"
},
{
"collapsed": true,
Expand Down Expand Up @@ -2586,5 +2583,5 @@
"timezone": "",
"title": "ONTAP: Headroom",
"uid": "",
"version": 7
"version": 8
}