OCPBUGS-12857: Add NaN handling for Stacked Graphs

[PeterYurkovich]

Issue:
https://issues.redhat.com/browse/OCPBUGS-12857

Analysis / Root cause:
There is a bug in stacked graphs for Victory charts for React. The bug occurs in their victory-stack package. An issue has been made and can be tracked FormidableLabs/victory#2844.

The root issue is a dataset which has dates in the x field and all null's in the y field. This causes a error to be thrown in the VictoryCharts, and leaves the chart looking like so:

Solution Description:
To get around this, for stacked charts we will be converting any NaN's returned from Prometheus to 0 rather than null. In order to help dashboard creators and power users to debug any problematic queries, we are also adding a console.warn to let them know about this conversion, while still showing the graph otherwise. This bug is being opened both here for the developer ta as well as in the monitoring-plugin repo for the admin tab openshift/monitoring-plugin#111

Screen shots:
Dashboard After Fix:

Test setup:
In order to test this PR, it is necessary to create a chart which responds with NaN values from Prometheus. To accomplish this we recreate one of the original locations that this bug was found, by applying an incomplete resource quota and then adding a dashboard with a stacked graph. After this bug was found, the original location has changed to being a line chart rather than a stacked chart. As such it is necessary to add both the resource quota and dashboard to reproduce the bug and then show the fix.

Resource Quota

Add the following Resource Quota to a namespace:

kind: ResourceQuota
apiVersion: v1
metadata:
  name: staging-workshop-quota
spec:
  hard:
    limits.cpu: '11'
    limits.memory: 15Gi
    pods: '12'

Reproduction Dashboard

Add the following dashboard to your cluster

kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    console.openshift.io/dashboard: 'true'
    console.openshift.io/odc-dashboard: 'true'
  name: failure-dashboard
  namespace: openshift-config-managed
data:
  etcd.json: |-
    {
      "annotations": {
        "list": [

        ]
      },
      "editable": true,
      "gnetId": null,
      "graphTooltip": 0,
      "hideControls": false,
      "links": [

      ],
      "refresh": "10s",
      "rows": [
          {
              "collapse": false,
              "height": "250px",
              "panels": [
                  {
                      "aliasColors": {

                      },
                      "bars": false,
                      "dashLength": 10,
                      "dashes": false,
                      "datasource": "$datasource",
                      "fill": 10,
                      "id": 3,
                      "interval": "1m",
                      "legend": {
                          "alignAsTable": true,
                          "avg": false,
                          "current": false,
                          "max": false,
                          "min": false,
                          "rightSide": true,
                          "show": true,
                          "total": false,
                          "values": false
                      },
                      "lines": true,
                      "linewidth": 0,
                      "links": [

                      ],
                      "nullPointMode": "null as zero",
                      "percentage": false,
                      "pointradius": 5,
                      "points": false,
                      "renderer": "flot",
                      "seriesOverrides": [
                          {
                              "alias": "quota - requests",
                              "color": "#F2495C",
                              "dashes": true,
                              "fill": 0,
                              "hiddenSeries": true,
                              "hideTooltip": true,
                              "legend": true,
                              "linewidth": 2,
                              "stack": false
                          },
                          {
                              "alias": "quota - limits",
                              "color": "#FF9830",
                              "dashes": true,
                              "fill": 0,
                              "hiddenSeries": true,
                              "hideTooltip": true,
                              "legend": true,
                              "linewidth": 2,
                              "stack": false
                          }
                      ],
                      "spaceLength": 10,
                      "span": 12,
                      "stack": true,
                      "steppedLine": false,
                      "targets": [
                          {
                              "expr": "sum(    container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}  * on(namespace,pod)    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
                              "format": "time_series",
                              "intervalFactor": 2,
                              "legendFormat": "{{workload}} - {{workload_type}}",
                              "legendLink": null,
                              "step": 10
                          },
                          {
                              "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
                              "format": "time_series",
                              "intervalFactor": 2,
                              "legendFormat": "quota - requests",
                              "legendLink": null,
                              "step": 10
                          },
                          {
                              "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
                              "format": "time_series",
                              "intervalFactor": 2,
                              "legendFormat": "quota - limits",
                              "legendLink": null,
                              "step": 10
                          }
                      ],
                      "thresholds": [

                      ],
                      "timeFrom": null,
                      "timeShift": null,
                      "title": "Memory Usage",
                      "tooltip": {
                          "shared": false,
                          "sort": 2,
                          "value_type": "individual"
                      },
                      "type": "graph",
                      "xaxis": {
                          "buckets": null,
                          "mode": "time",
                          "name": null,
                          "show": true,
                          "values": [

                          ]
                      },
                      "yaxes": [
                          {
                              "format": "bytes",
                              "label": null,
                              "logBase": 1,
                              "max": null,
                              "min": 0,
                              "show": true
                          },
                          {
                              "format": "short",
                              "label": null,
                              "logBase": 1,
                              "max": null,
                              "min": null,
                              "show": false
                          }
                      ]
                  }
              ],
              "repeat": null,
              "repeatIteration": null,
              "repeatRowId": null,
              "showTitle": true,
              "title": "Memory Usage",
              "titleSize": "h6"
          }
      ],
      "schemaVersion": 14,
      "style": "dark",
      "tags": [
          "kubernetes-mixin"
      ],
      "templating": {
          "list": [
              {
                  "current": {
                      "text": "default",
                      "value": "default"
                  },
                  "hide": 0,
                  "label": "Data Source",
                  "name": "datasource",
                  "options": [

                  ],
                  "query": "prometheus",
                  "refresh": 1,
                  "regex": "",
                  "type": "datasource"
              },
              {
                  "allValue": null,
                  "current": {
                      "text": "",
                      "value": ""
                  },
                  "datasource": "$datasource",
                  "hide": 2,
                  "includeAll": false,
                  "label": null,
                  "multi": false,
                  "name": "cluster",
                  "options": [

                  ],
                  "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
                  "refresh": 2,
                  "regex": "",
                  "sort": 1,
                  "tagValuesQuery": "",
                  "tags": [

                  ],
                  "tagsQuery": "",
                  "type": "query",
                  "useTags": false
              },
              {
                  "allValue": null,
                  "current": {
                      "text": "",
                      "value": ""
                  },
                  "datasource": "$datasource",
                  "hide": 0,
                  "includeAll": false,
                  "label": null,
                  "multi": false,
                  "name": "namespace",
                  "options": [

                  ],
                  "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
                  "refresh": 2,
                  "regex": "",
                  "sort": 1,
                  "tagValuesQuery": "",
                  "tags": [

                  ],
                  "tagsQuery": "",
                  "type": "query",
                  "useTags": false
              },
              {
                  "allValue": null,
                  "auto": false,
                  "auto_count": 30,
                  "auto_min": "10s",
                  "current": {
                      "text": "deployment",
                      "value": "deployment"
                  },
                  "datasource": "$datasource",
                  "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                  "hide": 0,
                  "includeAll": false,
                  "label": null,
                  "multi": false,
                  "name": "type",
                  "options": [

                  ],
                  "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                  "refresh": 2,
                  "regex": "",
                  "skipUrlSync": false,
                  "sort": 0,
                  "tagValuesQuery": "",
                  "tags": [

                  ],
                  "tagsQuery": "",
                  "type": "query",
                  "useTags": false
              }
          ]
      },
      "time": {
          "from": "now-1h",
          "to": "now"
      },
      "timepicker": {
          "refresh_intervals": [
              "30s"
          ],
          "time_options": [
              "1h"
          ]
      },
      "timezone": "UTC",
      "title": "Failure",
      "uid": "a87fb0d919ec0ea5f6543124e16c42a6",
      "version": 0
    }

Tested Browsers

• Chrome
• Firefox
• Safari
• Edge

[openshift-ci-robot]

@PeterYurkovich: This pull request references Jira Issue OCPBUGS-12854, which is invalid:

• expected the bug to be open, but it isn't
• expected the bug to target either version "4.16." or "openshift-4.16.", but it targets "4.13.0" instead
• expected the bug to be in one of the following states: NEW, ASSIGNED, POST, but it is Closed (Done) instead

Comment /jira refresh to re-evaluate validity if changes to the Jira bug are made, or edit the title of this pull request to link to a different bug.

The bug has been updated to refer to the pull request using the external bug tracker.

In response to this:

Issue:
https://issues.redhat.com/browse/OCPBUGS-12857

Analysis / Root cause:
There is a bug in stacked graphs for Victory charts for react. The bug occurs in their victory-stack package. An issue has been made and can be tracked FormidableLabs/victory#2844.

The root issue is a dataset which has dates in the x field and all null's in the y field. This causes a error to be thrown in the VictoryCharts, and leaves the chart looking like so:

Solution Description:
To get around this, for stacked charts we will be converting any NaN's returned from Prometheus to 0 rather than null. In order to help dashboard creators and power users to debug any problematic queries, we are also adding a console.warn to let them know about this conversion, while still showing the graph otherwise. This bug is being opened both here for the developer tab repo as well as in the monitoring-plugin for the admin tab openshift/monitoring-plugin#111

Screen shots:
Dashboard After Fix:

Test setup:
In order to test this PR, it is necessary to create a chart which responds with NaN values from Prometheus. To accomplish this we recreate one of the original locations that this bug was found, but applying an incomplete resource quota and then adding a dashboard with a stacked graph. After this bug was found, the original location has changed to being a line chart rather than a stacked chart and no longer shows as an empty chart. As such it is necessary to add both the resource quota and dashboard to reproduce the bug and then show the fix.

Resource Quota

Add the following Resource Quota to a namespace:

kind: ResourceQuota
apiVersion: v1
metadata:
 name: staging-workshop-quota
spec:
 hard:
   limits.cpu: '11'
   limits.memory: 15Gi
   pods: '12'

Reproduction Dashboard

Add the folling dashboard to your cluster

kind: ConfigMap
apiVersion: v1
metadata:
 labels:
   console.openshift.io/dashboard: 'true'
   console.openshift.io/odc-dashboard: 'true'
 name: failure-dashboard
 namespace: openshift-config-managed
data:
 etcd.json: |-
   {
     "annotations": {
       "list": [

       ]
     },
     "editable": true,
     "gnetId": null,
     "graphTooltip": 0,
     "hideControls": false,
     "links": [

     ],
     "refresh": "10s",
     "rows": [
         {
             "collapse": false,
             "height": "250px",
             "panels": [
                 {
                     "aliasColors": {

                     },
                     "bars": false,
                     "dashLength": 10,
                     "dashes": false,
                     "datasource": "$datasource",
                     "fill": 10,
                     "id": 3,
                     "interval": "1m",
                     "legend": {
                         "alignAsTable": true,
                         "avg": false,
                         "current": false,
                         "max": false,
                         "min": false,
                         "rightSide": true,
                         "show": true,
                         "total": false,
                         "values": false
                     },
                     "lines": true,
                     "linewidth": 0,
                     "links": [

                     ],
                     "nullPointMode": "null as zero",
                     "percentage": false,
                     "pointradius": 5,
                     "points": false,
                     "renderer": "flot",
                     "seriesOverrides": [
                         {
                             "alias": "quota - requests",
                             "color": "#F2495C",
                             "dashes": true,
                             "fill": 0,
                             "hiddenSeries": true,
                             "hideTooltip": true,
                             "legend": true,
                             "linewidth": 2,
                             "stack": false
                         },
                         {
                             "alias": "quota - limits",
                             "color": "#FF9830",
                             "dashes": true,
                             "fill": 0,
                             "hiddenSeries": true,
                             "hideTooltip": true,
                             "legend": true,
                             "linewidth": 2,
                             "stack": false
                         }
                     ],
                     "spaceLength": 10,
                     "span": 12,
                     "stack": true,
                     "steppedLine": false,
                     "targets": [
                         {
                             "expr": "sum(    container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}  * on(namespace,pod)    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "{{workload}} - {{workload_type}}",
                             "legendLink": null,
                             "step": 10
                         },
                         {
                             "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "quota - requests",
                             "legendLink": null,
                             "step": 10
                         },
                         {
                             "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "quota - limits",
                             "legendLink": null,
                             "step": 10
                         }
                     ],
                     "thresholds": [

                     ],
                     "timeFrom": null,
                     "timeShift": null,
                     "title": "Memory Usage",
                     "tooltip": {
                         "shared": false,
                         "sort": 2,
                         "value_type": "individual"
                     },
                     "type": "graph",
                     "xaxis": {
                         "buckets": null,
                         "mode": "time",
                         "name": null,
                         "show": true,
                         "values": [

                         ]
                     },
                     "yaxes": [
                         {
                             "format": "bytes",
                             "label": null,
                             "logBase": 1,
                             "max": null,
                             "min": 0,
                             "show": true
                         },
                         {
                             "format": "short",
                             "label": null,
                             "logBase": 1,
                             "max": null,
                             "min": null,
                             "show": false
                         }
                     ]
                 }
             ],
             "repeat": null,
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
             "title": "Memory Usage",
             "titleSize": "h6"
         }
     ],
     "schemaVersion": 14,
     "style": "dark",
     "tags": [
         "kubernetes-mixin"
     ],
     "templating": {
         "list": [
             {
                 "current": {
                     "text": "default",
                     "value": "default"
                 },
                 "hide": 0,
                 "label": "Data Source",
                 "name": "datasource",
                 "options": [

                 ],
                 "query": "prometheus",
                 "refresh": 1,
                 "regex": "",
                 "type": "datasource"
             },
             {
                 "allValue": null,
                 "current": {
                     "text": "",
                     "value": ""
                 },
                 "datasource": "$datasource",
                 "hide": 2,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "cluster",
                 "options": [

                 ],
                 "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
                 "refresh": 2,
                 "regex": "",
                 "sort": 1,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             },
             {
                 "allValue": null,
                 "current": {
                     "text": "",
                     "value": ""
                 },
                 "datasource": "$datasource",
                 "hide": 0,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "namespace",
                 "options": [

                 ],
                 "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
                 "refresh": 2,
                 "regex": "",
                 "sort": 1,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             },
             {
                 "allValue": null,
                 "auto": false,
                 "auto_count": 30,
                 "auto_min": "10s",
                 "current": {
                     "text": "deployment",
                     "value": "deployment"
                 },
                 "datasource": "$datasource",
                 "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                 "hide": 0,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "type",
                 "options": [

                 ],
                 "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                 "refresh": 2,
                 "regex": "",
                 "skipUrlSync": false,
                 "sort": 0,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             }
         ]
     },
     "time": {
         "from": "now-1h",
         "to": "now"
     },
     "timepicker": {
         "refresh_intervals": [
             "30s"
         ],
         "time_options": [
             "1h"
         ]
     },
     "timezone": "UTC",
     "title": "Failure",
     "uid": "a87fb0d919ec0ea5f6543124e16c42a6",
     "version": 0
   }

Tested Browsers

• Chrome
• Firefox
• Safari
• Edge

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository.

[openshift-ci-robot]

@PeterYurkovich: This pull request references Jira Issue OCPBUGS-12857, which is invalid:

• expected the bug to target the "4.16.0" version, but no target version was set

Comment /jira refresh to re-evaluate validity if changes to the Jira bug are made, or edit the title of this pull request to link to a different bug.

The bug has been updated to refer to the pull request using the external bug tracker.

In response to this:

Issue:
https://issues.redhat.com/browse/OCPBUGS-12857

Analysis / Root cause:
There is a bug in stacked graphs for Victory charts for react. The bug occurs in their victory-stack package. An issue has been made and can be tracked FormidableLabs/victory#2844.

The root issue is a dataset which has dates in the x field and all null's in the y field. This causes a error to be thrown in the VictoryCharts, and leaves the chart looking like so:

Solution Description:
To get around this, for stacked charts we will be converting any NaN's returned from Prometheus to 0 rather than null. In order to help dashboard creators and power users to debug any problematic queries, we are also adding a console.warn to let them know about this conversion, while still showing the graph otherwise. This bug is being opened both here for the developer tab repo as well as in the monitoring-plugin for the admin tab openshift/monitoring-plugin#111

Screen shots:
Dashboard After Fix:

Test setup:
In order to test this PR, it is necessary to create a chart which responds with NaN values from Prometheus. To accomplish this we recreate one of the original locations that this bug was found, but applying an incomplete resource quota and then adding a dashboard with a stacked graph. After this bug was found, the original location has changed to being a line chart rather than a stacked chart and no longer shows as an empty chart. As such it is necessary to add both the resource quota and dashboard to reproduce the bug and then show the fix.

Resource Quota

Add the following Resource Quota to a namespace:

kind: ResourceQuota
apiVersion: v1
metadata:
 name: staging-workshop-quota
spec:
 hard:
   limits.cpu: '11'
   limits.memory: 15Gi
   pods: '12'

Reproduction Dashboard

Add the following dashboard to your cluster

kind: ConfigMap
apiVersion: v1
metadata:
 labels:
   console.openshift.io/dashboard: 'true'
   console.openshift.io/odc-dashboard: 'true'
 name: failure-dashboard
 namespace: openshift-config-managed
data:
 etcd.json: |-
   {
     "annotations": {
       "list": [

       ]
     },
     "editable": true,
     "gnetId": null,
     "graphTooltip": 0,
     "hideControls": false,
     "links": [

     ],
     "refresh": "10s",
     "rows": [
         {
             "collapse": false,
             "height": "250px",
             "panels": [
                 {
                     "aliasColors": {

                     },
                     "bars": false,
                     "dashLength": 10,
                     "dashes": false,
                     "datasource": "$datasource",
                     "fill": 10,
                     "id": 3,
                     "interval": "1m",
                     "legend": {
                         "alignAsTable": true,
                         "avg": false,
                         "current": false,
                         "max": false,
                         "min": false,
                         "rightSide": true,
                         "show": true,
                         "total": false,
                         "values": false
                     },
                     "lines": true,
                     "linewidth": 0,
                     "links": [

                     ],
                     "nullPointMode": "null as zero",
                     "percentage": false,
                     "pointradius": 5,
                     "points": false,
                     "renderer": "flot",
                     "seriesOverrides": [
                         {
                             "alias": "quota - requests",
                             "color": "#F2495C",
                             "dashes": true,
                             "fill": 0,
                             "hiddenSeries": true,
                             "hideTooltip": true,
                             "legend": true,
                             "linewidth": 2,
                             "stack": false
                         },
                         {
                             "alias": "quota - limits",
                             "color": "#FF9830",
                             "dashes": true,
                             "fill": 0,
                             "hiddenSeries": true,
                             "hideTooltip": true,
                             "legend": true,
                             "linewidth": 2,
                             "stack": false
                         }
                     ],
                     "spaceLength": 10,
                     "span": 12,
                     "stack": true,
                     "steppedLine": false,
                     "targets": [
                         {
                             "expr": "sum(    container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}  * on(namespace,pod)    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "{{workload}} - {{workload_type}}",
                             "legendLink": null,
                             "step": 10
                         },
                         {
                             "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "quota - requests",
                             "legendLink": null,
                             "step": 10
                         },
                         {
                             "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "quota - limits",
                             "legendLink": null,
                             "step": 10
                         }
                     ],
                     "thresholds": [

                     ],
                     "timeFrom": null,
                     "timeShift": null,
                     "title": "Memory Usage",
                     "tooltip": {
                         "shared": false,
                         "sort": 2,
                         "value_type": "individual"
                     },
                     "type": "graph",
                     "xaxis": {
                         "buckets": null,
                         "mode": "time",
                         "name": null,
                         "show": true,
                         "values": [

                         ]
                     },
                     "yaxes": [
                         {
                             "format": "bytes",
                             "label": null,
                             "logBase": 1,
                             "max": null,
                             "min": 0,
                             "show": true
                         },
                         {
                             "format": "short",
                             "label": null,
                             "logBase": 1,
                             "max": null,
                             "min": null,
                             "show": false
                         }
                     ]
                 }
             ],
             "repeat": null,
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
             "title": "Memory Usage",
             "titleSize": "h6"
         }
     ],
     "schemaVersion": 14,
     "style": "dark",
     "tags": [
         "kubernetes-mixin"
     ],
     "templating": {
         "list": [
             {
                 "current": {
                     "text": "default",
                     "value": "default"
                 },
                 "hide": 0,
                 "label": "Data Source",
                 "name": "datasource",
                 "options": [

                 ],
                 "query": "prometheus",
                 "refresh": 1,
                 "regex": "",
                 "type": "datasource"
             },
             {
                 "allValue": null,
                 "current": {
                     "text": "",
                     "value": ""
                 },
                 "datasource": "$datasource",
                 "hide": 2,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "cluster",
                 "options": [

                 ],
                 "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
                 "refresh": 2,
                 "regex": "",
                 "sort": 1,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             },
             {
                 "allValue": null,
                 "current": {
                     "text": "",
                     "value": ""
                 },
                 "datasource": "$datasource",
                 "hide": 0,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "namespace",
                 "options": [

                 ],
                 "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
                 "refresh": 2,
                 "regex": "",
                 "sort": 1,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             },
             {
                 "allValue": null,
                 "auto": false,
                 "auto_count": 30,
                 "auto_min": "10s",
                 "current": {
                     "text": "deployment",
                     "value": "deployment"
                 },
                 "datasource": "$datasource",
                 "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                 "hide": 0,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "type",
                 "options": [

                 ],
                 "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                 "refresh": 2,
                 "regex": "",
                 "skipUrlSync": false,
                 "sort": 0,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             }
         ]
     },
     "time": {
         "from": "now-1h",
         "to": "now"
     },
     "timepicker": {
         "refresh_intervals": [
             "30s"
         ],
         "time_options": [
             "1h"
         ]
     },
     "timezone": "UTC",
     "title": "Failure",
     "uid": "a87fb0d919ec0ea5f6543124e16c42a6",
     "version": 0
   }

Tested Browsers

• Chrome
• Firefox
• Safari
• Edge

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository.

[PeterYurkovich]

/jira refresh

[openshift-ci-robot]

@PeterYurkovich: This pull request references Jira Issue OCPBUGS-12857, which is invalid:

• expected the bug to target the "4.16.0" version, but no target version was set

Comment /jira refresh to re-evaluate validity if changes to the Jira bug are made, or edit the title of this pull request to link to a different bug.

In response to this:

/jira refresh

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository.

[PeterYurkovich]

/jira refresh

[openshift-ci-robot]

@PeterYurkovich: This pull request references Jira Issue OCPBUGS-12857, which is invalid:

• expected the bug to target the "4.16.0" version, but no target version was set

Comment /jira refresh to re-evaluate validity if changes to the Jira bug are made, or edit the title of this pull request to link to a different bug.

In response to this:

/jira refresh

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository.

[PeterYurkovich]

/jira refresh

[openshift-ci-robot]

@PeterYurkovich: This pull request references Jira Issue OCPBUGS-12857, which is valid. The bug has been moved to the POST state.

3 validation(s) were run on this bug

• bug is open, matching expected state (open)
• bug target version (4.16.0) matches configured target version for branch (4.16.0)
• bug is in the state ASSIGNED, which is one of the valid states (NEW, ASSIGNED, POST)

Requesting review from QA contact:
/cc @juzhao

In response to this:

/jira refresh

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository.

[openshift-ci-robot]

@PeterYurkovich: This pull request references Jira Issue OCPBUGS-12857, which is valid.

3 validation(s) were run on this bug

• bug is open, matching expected state (open)
• bug target version (4.16.0) matches configured target version for branch (4.16.0)
• bug is in the state POST, which is one of the valid states (NEW, ASSIGNED, POST)

Requesting review from QA contact:
/cc @juzhao

In response to this:

Issue:
https://issues.redhat.com/browse/OCPBUGS-12857

Analysis / Root cause:
There is a bug in stacked graphs for Victory charts for React. The bug occurs in their victory-stack package. An issue has been made and can be tracked FormidableLabs/victory#2844.

The root issue is a dataset which has dates in the x field and all null's in the y field. This causes a error to be thrown in the VictoryCharts, and leaves the chart looking like so:

Solution Description:
To get around this, for stacked charts we will be converting any NaN's returned from Prometheus to 0 rather than null. In order to help dashboard creators and power users to debug any problematic queries, we are also adding a console.warn to let them know about this conversion, while still showing the graph otherwise. This bug is being opened both here for the developer tab repo as well as in the monitoring-plugin for the admin tab openshift/monitoring-plugin#111

Screen shots:
Dashboard After Fix:

Test setup:
In order to test this PR, it is necessary to create a chart which responds with NaN values from Prometheus. To accomplish this we recreate one of the original locations that this bug was found, but applying an incomplete resource quota and then adding a dashboard with a stacked graph. After this bug was found, the original location has changed to being a line chart rather than a stacked chart and no longer shows as an empty chart. As such it is necessary to add both the resource quota and dashboard to reproduce the bug and then show the fix.

Resource Quota

Add the following Resource Quota to a namespace:

kind: ResourceQuota
apiVersion: v1
metadata:
 name: staging-workshop-quota
spec:
 hard:
   limits.cpu: '11'
   limits.memory: 15Gi
   pods: '12'

Reproduction Dashboard

Add the following dashboard to your cluster

kind: ConfigMap
apiVersion: v1
metadata:
 labels:
   console.openshift.io/dashboard: 'true'
   console.openshift.io/odc-dashboard: 'true'
 name: failure-dashboard
 namespace: openshift-config-managed
data:
 etcd.json: |-
   {
     "annotations": {
       "list": [

       ]
     },
     "editable": true,
     "gnetId": null,
     "graphTooltip": 0,
     "hideControls": false,
     "links": [

     ],
     "refresh": "10s",
     "rows": [
         {
             "collapse": false,
             "height": "250px",
             "panels": [
                 {
                     "aliasColors": {

                     },
                     "bars": false,
                     "dashLength": 10,
                     "dashes": false,
                     "datasource": "$datasource",
                     "fill": 10,
                     "id": 3,
                     "interval": "1m",
                     "legend": {
                         "alignAsTable": true,
                         "avg": false,
                         "current": false,
                         "max": false,
                         "min": false,
                         "rightSide": true,
                         "show": true,
                         "total": false,
                         "values": false
                     },
                     "lines": true,
                     "linewidth": 0,
                     "links": [

                     ],
                     "nullPointMode": "null as zero",
                     "percentage": false,
                     "pointradius": 5,
                     "points": false,
                     "renderer": "flot",
                     "seriesOverrides": [
                         {
                             "alias": "quota - requests",
                             "color": "#F2495C",
                             "dashes": true,
                             "fill": 0,
                             "hiddenSeries": true,
                             "hideTooltip": true,
                             "legend": true,
                             "linewidth": 2,
                             "stack": false
                         },
                         {
                             "alias": "quota - limits",
                             "color": "#FF9830",
                             "dashes": true,
                             "fill": 0,
                             "hiddenSeries": true,
                             "hideTooltip": true,
                             "legend": true,
                             "linewidth": 2,
                             "stack": false
                         }
                     ],
                     "spaceLength": 10,
                     "span": 12,
                     "stack": true,
                     "steppedLine": false,
                     "targets": [
                         {
                             "expr": "sum(    container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}  * on(namespace,pod)    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "{{workload}} - {{workload_type}}",
                             "legendLink": null,
                             "step": 10
                         },
                         {
                             "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "quota - requests",
                             "legendLink": null,
                             "step": 10
                         },
                         {
                             "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "quota - limits",
                             "legendLink": null,
                             "step": 10
                         }
                     ],
                     "thresholds": [

                     ],
                     "timeFrom": null,
                     "timeShift": null,
                     "title": "Memory Usage",
                     "tooltip": {
                         "shared": false,
                         "sort": 2,
                         "value_type": "individual"
                     },
                     "type": "graph",
                     "xaxis": {
                         "buckets": null,
                         "mode": "time",
                         "name": null,
                         "show": true,
                         "values": [

                         ]
                     },
                     "yaxes": [
                         {
                             "format": "bytes",
                             "label": null,
                             "logBase": 1,
                             "max": null,
                             "min": 0,
                             "show": true
                         },
                         {
                             "format": "short",
                             "label": null,
                             "logBase": 1,
                             "max": null,
                             "min": null,
                             "show": false
                         }
                     ]
                 }
             ],
             "repeat": null,
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
             "title": "Memory Usage",
             "titleSize": "h6"
         }
     ],
     "schemaVersion": 14,
     "style": "dark",
     "tags": [
         "kubernetes-mixin"
     ],
     "templating": {
         "list": [
             {
                 "current": {
                     "text": "default",
                     "value": "default"
                 },
                 "hide": 0,
                 "label": "Data Source",
                 "name": "datasource",
                 "options": [

                 ],
                 "query": "prometheus",
                 "refresh": 1,
                 "regex": "",
                 "type": "datasource"
             },
             {
                 "allValue": null,
                 "current": {
                     "text": "",
                     "value": ""
                 },
                 "datasource": "$datasource",
                 "hide": 2,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "cluster",
                 "options": [

                 ],
                 "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
                 "refresh": 2,
                 "regex": "",
                 "sort": 1,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             },
             {
                 "allValue": null,
                 "current": {
                     "text": "",
                     "value": ""
                 },
                 "datasource": "$datasource",
                 "hide": 0,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "namespace",
                 "options": [

                 ],
                 "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
                 "refresh": 2,
                 "regex": "",
                 "sort": 1,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             },
             {
                 "allValue": null,
                 "auto": false,
                 "auto_count": 30,
                 "auto_min": "10s",
                 "current": {
                     "text": "deployment",
                     "value": "deployment"
                 },
                 "datasource": "$datasource",
                 "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                 "hide": 0,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "type",
                 "options": [

                 ],
                 "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                 "refresh": 2,
                 "regex": "",
                 "skipUrlSync": false,
                 "sort": 0,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             }
         ]
     },
     "time": {
         "from": "now-1h",
         "to": "now"
     },
     "timepicker": {
         "refresh_intervals": [
             "30s"
         ],
         "time_options": [
             "1h"
         ]
     },
     "timezone": "UTC",
     "title": "Failure",
     "uid": "a87fb0d919ec0ea5f6543124e16c42a6",
     "version": 0
   }

Tested Browsers

• Chrome
• Firefox
• Safari
• Edge

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository.

[openshift-ci]

@PeterYurkovich: all tests passed!

Full PR test history. Your PR dashboard.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository. I understand the commands that are listed here.

[jgbernalp]

/lgtm

[juzhao]

test along with along with openshift/monitoring-plugin#111, stacked Graphs is handling NaN well, steps see from https://issues.redhat.com/browse/OCPBUGS-12857

[juzhao]

/label qe-approved

[PeterYurkovich]

/assign @kyoto

[kyoto]

/approve

[openshift-ci]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: jgbernalp, kyoto, PeterYurkovich

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

• frontend/OWNERS [kyoto]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[openshift-ci-robot]

@PeterYurkovich: Jira Issue OCPBUGS-12857: All pull requests linked via external trackers have merged:

• openshift/console#13712
• openshift/monitoring-plugin#111

Jira Issue OCPBUGS-12857 has been moved to the MODIFIED state.

In response to this:

Issue:
https://issues.redhat.com/browse/OCPBUGS-12857

Analysis / Root cause:
There is a bug in stacked graphs for Victory charts for React. The bug occurs in their victory-stack package. An issue has been made and can be tracked FormidableLabs/victory#2844.

The root issue is a dataset which has dates in the x field and all null's in the y field. This causes a error to be thrown in the VictoryCharts, and leaves the chart looking like so:

Solution Description:
To get around this, for stacked charts we will be converting any NaN's returned from Prometheus to 0 rather than null. In order to help dashboard creators and power users to debug any problematic queries, we are also adding a console.warn to let them know about this conversion, while still showing the graph otherwise. This bug is being opened both here for the developer ta as well as in the monitoring-plugin repo for the admin tab openshift/monitoring-plugin#111

Screen shots:
Dashboard After Fix:

Test setup:
In order to test this PR, it is necessary to create a chart which responds with NaN values from Prometheus. To accomplish this we recreate one of the original locations that this bug was found, by applying an incomplete resource quota and then adding a dashboard with a stacked graph. After this bug was found, the original location has changed to being a line chart rather than a stacked chart. As such it is necessary to add both the resource quota and dashboard to reproduce the bug and then show the fix.

Resource Quota

Add the following Resource Quota to a namespace:

kind: ResourceQuota
apiVersion: v1
metadata:
 name: staging-workshop-quota
spec:
 hard:
   limits.cpu: '11'
   limits.memory: 15Gi
   pods: '12'

Reproduction Dashboard

Add the following dashboard to your cluster

kind: ConfigMap
apiVersion: v1
metadata:
 labels:
   console.openshift.io/dashboard: 'true'
   console.openshift.io/odc-dashboard: 'true'
 name: failure-dashboard
 namespace: openshift-config-managed
data:
 etcd.json: |-
   {
     "annotations": {
       "list": [

       ]
     },
     "editable": true,
     "gnetId": null,
     "graphTooltip": 0,
     "hideControls": false,
     "links": [

     ],
     "refresh": "10s",
     "rows": [
         {
             "collapse": false,
             "height": "250px",
             "panels": [
                 {
                     "aliasColors": {

                     },
                     "bars": false,
                     "dashLength": 10,
                     "dashes": false,
                     "datasource": "$datasource",
                     "fill": 10,
                     "id": 3,
                     "interval": "1m",
                     "legend": {
                         "alignAsTable": true,
                         "avg": false,
                         "current": false,
                         "max": false,
                         "min": false,
                         "rightSide": true,
                         "show": true,
                         "total": false,
                         "values": false
                     },
                     "lines": true,
                     "linewidth": 0,
                     "links": [

                     ],
                     "nullPointMode": "null as zero",
                     "percentage": false,
                     "pointradius": 5,
                     "points": false,
                     "renderer": "flot",
                     "seriesOverrides": [
                         {
                             "alias": "quota - requests",
                             "color": "#F2495C",
                             "dashes": true,
                             "fill": 0,
                             "hiddenSeries": true,
                             "hideTooltip": true,
                             "legend": true,
                             "linewidth": 2,
                             "stack": false
                         },
                         {
                             "alias": "quota - limits",
                             "color": "#FF9830",
                             "dashes": true,
                             "fill": 0,
                             "hiddenSeries": true,
                             "hideTooltip": true,
                             "legend": true,
                             "linewidth": 2,
                             "stack": false
                         }
                     ],
                     "spaceLength": 10,
                     "span": 12,
                     "stack": true,
                     "steppedLine": false,
                     "targets": [
                         {
                             "expr": "sum(    container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}  * on(namespace,pod)    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "{{workload}} - {{workload_type}}",
                             "legendLink": null,
                             "step": 10
                         },
                         {
                             "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "quota - requests",
                             "legendLink": null,
                             "step": 10
                         },
                         {
                             "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
                             "format": "time_series",
                             "intervalFactor": 2,
                             "legendFormat": "quota - limits",
                             "legendLink": null,
                             "step": 10
                         }
                     ],
                     "thresholds": [

                     ],
                     "timeFrom": null,
                     "timeShift": null,
                     "title": "Memory Usage",
                     "tooltip": {
                         "shared": false,
                         "sort": 2,
                         "value_type": "individual"
                     },
                     "type": "graph",
                     "xaxis": {
                         "buckets": null,
                         "mode": "time",
                         "name": null,
                         "show": true,
                         "values": [

                         ]
                     },
                     "yaxes": [
                         {
                             "format": "bytes",
                             "label": null,
                             "logBase": 1,
                             "max": null,
                             "min": 0,
                             "show": true
                         },
                         {
                             "format": "short",
                             "label": null,
                             "logBase": 1,
                             "max": null,
                             "min": null,
                             "show": false
                         }
                     ]
                 }
             ],
             "repeat": null,
             "repeatIteration": null,
             "repeatRowId": null,
             "showTitle": true,
             "title": "Memory Usage",
             "titleSize": "h6"
         }
     ],
     "schemaVersion": 14,
     "style": "dark",
     "tags": [
         "kubernetes-mixin"
     ],
     "templating": {
         "list": [
             {
                 "current": {
                     "text": "default",
                     "value": "default"
                 },
                 "hide": 0,
                 "label": "Data Source",
                 "name": "datasource",
                 "options": [

                 ],
                 "query": "prometheus",
                 "refresh": 1,
                 "regex": "",
                 "type": "datasource"
             },
             {
                 "allValue": null,
                 "current": {
                     "text": "",
                     "value": ""
                 },
                 "datasource": "$datasource",
                 "hide": 2,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "cluster",
                 "options": [

                 ],
                 "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
                 "refresh": 2,
                 "regex": "",
                 "sort": 1,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             },
             {
                 "allValue": null,
                 "current": {
                     "text": "",
                     "value": ""
                 },
                 "datasource": "$datasource",
                 "hide": 0,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "namespace",
                 "options": [

                 ],
                 "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
                 "refresh": 2,
                 "regex": "",
                 "sort": 1,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             },
             {
                 "allValue": null,
                 "auto": false,
                 "auto_count": 30,
                 "auto_min": "10s",
                 "current": {
                     "text": "deployment",
                     "value": "deployment"
                 },
                 "datasource": "$datasource",
                 "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                 "hide": 0,
                 "includeAll": false,
                 "label": null,
                 "multi": false,
                 "name": "type",
                 "options": [

                 ],
                 "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
                 "refresh": 2,
                 "regex": "",
                 "skipUrlSync": false,
                 "sort": 0,
                 "tagValuesQuery": "",
                 "tags": [

                 ],
                 "tagsQuery": "",
                 "type": "query",
                 "useTags": false
             }
         ]
     },
     "time": {
         "from": "now-1h",
         "to": "now"
     },
     "timepicker": {
         "refresh_intervals": [
             "30s"
         ],
         "time_options": [
             "1h"
         ]
     },
     "timezone": "UTC",
     "title": "Failure",
     "uid": "a87fb0d919ec0ea5f6543124e16c42a6",
     "version": 0
   }

Tested Browsers

• Chrome
• Firefox
• Safari
• Edge

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository.

[openshift-bot]

[ART PR BUILD NOTIFIER]

This PR has been included in build openshift-enterprise-console-container-v4.16.0-202404181209.p0.gbd85036.assembly.stream.el9 for distgit openshift-enterprise-console.
All builds following this will include this PR.