Merge branch 'main' into aswanson-nr-patch-2

alert-policies/amazon-sagemaker/HighModelInvocationErrors.yml

@@ -5,7 +5,7 @@ description: |+
 
 type: STATIC
 nrql:
-  query: "SELECT count(`aws.sagemaker.InvocationModelErrors`) as 'Query' FROM Metric"
+  query: "SELECT sum(`aws.sagemaker.InvocationModelErrors`) as 'Query' FROM Metric"
 
 # Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
 valueFunction: SINGLE_VALUE
@@ -24,4 +24,4 @@ terms:
 
 # Duration after which a violation automatically closes
 # Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
-violationTimeLimitSeconds: 86400
+violationTimeLimitSeconds: 86400

alert-policies/nvidia-gpu/HighMemoryUtilization.yml

@@ -0,0 +1,27 @@
+name: High GPU Memory Utilization
+
+description: |+
+  This alert is triggered when the Nvidia GPU memory utilization is above 90%.
+
+type: STATIC
+nrql:
+  query: "SELECT latest(utilization.memory.percent) FROM NvidiaGpuSample"
+
+# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+  - priority: CRITICAL
+    # Operator used to compare against the threshold.
+    operator: ABOVE
+    # Value that triggers a violation
+    threshold: 90
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

dashboards/nvidia-gpu/nvidia-gpu.json

@@ -0,0 +1,190 @@
+{
+    "name": "Nvidia GPU Monitoring",
+    "description": null,
+    "pages": [
+      {
+        "name": "Nvidia GPU Monitoring",
+        "description": null,
+        "widgets": [
+          {
+            "visualization": {
+              "id": "viz.markdown"
+            },
+            "layout": {
+              "column": 1,
+              "row": 1,
+              "height": 1,
+              "width": 4
+            },
+            "title": "",
+            "rawConfiguration": {
+              "text": "[![NVIDIA SMI](https://logos-download.com/wp-content/uploads/2016/10/Nvidia_logo.png)](https://developer.nvidia.com/nvidia-system-management-interface)\n"
+            }
+          },
+          {
+            "visualization": {
+              "id": "viz.billboard"
+            },
+            "layout": {
+              "column": 5,
+              "row": 1,
+              "height": 3,
+              "width": 2
+            },
+            "title": "Current Clock Speeds",
+            "rawConfiguration": {
+              "dataFormatters": [],
+              "nrqlQueries": [
+                {
+                  "accountId": 123,
+                  "query": "FROM NvidiaGpuSample SELECT latest(clocks.current.memory.MHz) as 'Memory MHz', latest(clocks.current.graphics.MHz) as 'Graphics MHz', latest(clocks.current.video.MHz) as 'Video MHz', latest(clocks.current.sm.MHz) as 'SM MHz' "
+                }
+              ],
+              "thresholds": []
+            }
+          },
+          {
+            "visualization": {
+              "id": "viz.line"
+            },
+            "layout": {
+              "column": 7,
+              "row": 1,
+              "height": 3,
+              "width": 6
+            },
+            "title": "Current Clock MHz",
+            "rawConfiguration": {
+              "legend": {
+                "enabled": true
+              },
+              "nrqlQueries": [
+                {
+                  "accountId": 123,
+                  "query": "FROM NvidiaGpuSample SELECT latest(clocks.current.memory.MHz) as 'Memory MHz', latest(clocks.current.graphics.MHz) as 'Graphics MHz', latest(clocks.current.video.MHz) as 'Video MHz', latest(clocks.current.sm.MHz) as 'SM MHz' TIMESERIES"
+                }
+              ],
+              "yAxisLeft": {
+                "zero": true
+              }
+            }
+          },
+          {
+            "visualization": {
+              "id": "viz.bar"
+            },
+            "layout": {
+              "column": 1,
+              "row": 2,
+              "height": 2,
+              "width": 4
+            },
+            "title": "Select GPU",
+            "rawConfiguration": {
+              "facet": {
+                "showOtherSeries": false
+              },
+              "nrqlQueries": [
+                {
+                  "accountId": 123,
+                  "query": "FROM NvidiaGpuSample SELECT latest(name) FACET pci.device_id, hostname "
+                }
+              ]
+            }
+          },
+          {
+            "visualization": {
+              "id": "viz.billboard"
+            },
+            "layout": {
+              "column": 1,
+              "row": 4,
+              "height": 3,
+              "width": 2
+            },
+            "title": "Temps",
+            "rawConfiguration": {
+              "dataFormatters": [],
+              "nrqlQueries": [
+                {
+                  "accountId": 123,
+                  "query": "FROM NvidiaGpuSample SELECT  latest(temperature.gpu) as 'GPU Temp', latest(temperature.memory) as 'Memory Temp', latest(fan.speed.percent) as 'Fan speed %'"
+                }
+              ],
+              "thresholds": []
+            }
+          },
+          {
+            "visualization": {
+              "id": "viz.billboard"
+            },
+            "layout": {
+              "column": 3,
+              "row": 4,
+              "height": 3,
+              "width": 2
+            },
+            "title": "Power Usage",
+            "rawConfiguration": {
+              "dataFormatters": [],
+              "nrqlQueries": [
+                {
+                  "accountId": 123,
+                  "query": "FROM NvidiaGpuSample SELECT latest(power.draw.watts) as 'Power Draw Watts', latest(`power.limit.watts`) as 'Power Limit Watts', latest(power.draw.watts)/latest(`power.limit.watts`) * 100 as 'Power usage %'"
+                }
+              ],
+              "thresholds": []
+            }
+          },
+          {
+            "visualization": {
+              "id": "viz.billboard"
+            },
+            "layout": {
+              "column": 5,
+              "row": 4,
+              "height": 3,
+              "width": 2
+            },
+            "title": "Memory Usage",
+            "rawConfiguration": {
+              "dataFormatters": [],
+              "nrqlQueries": [
+                {
+                  "accountId": 123,
+                  "query": "FROM NvidiaGpuSample SELECT  latest(memory.free.MiB) as 'Memory Free MiB', latest(memory.used.MiB) as 'Memory Used MiB', latest(memory.total.MiB) as 'Memory Total MiB'"
+                }
+              ],
+              "thresholds": []
+            }
+          },
+          {
+            "visualization": {
+              "id": "viz.line"
+            },
+            "layout": {
+              "column": 7,
+              "row": 4,
+              "height": 3,
+              "width": 6
+            },
+            "title": "Utilization",
+            "rawConfiguration": {
+              "legend": {
+                "enabled": true
+              },
+              "nrqlQueries": [
+                {
+                  "accountId": 123,
+                  "query": "FROM NvidiaGpuSample SELECT latest(memory.used.MiB/memory.total.MiB) * 100 as 'Memory Used %', latest(utilization.gpu.percent) as 'GPU Utilization %', latest(power.draw.watts)/latest(`power.limit.watts`)*100 as 'Power Usage %', latest(fan.speed.percent) as 'Fan Speed %' TIMESERIES"
+                }
+              ],
+              "yAxisLeft": {
+                "zero": true
+              }
+            }
+          }
+        ]
+      }
+    ]
+  }

data-sources/dojo/config.yml

@@ -4,6 +4,9 @@ description: |
   With New Relic, monitor your Dojo solution to get full visibility into the core web vitals performance of your application or website.
 install:
   primary:
-    link:
-      url: https://docs.newrelic.com/docs/infrastructure/host-integrations/host-integrations-list/dojo-io-integration/
+    nerdlet:
+      nerdletId: marketplace.install-data-source
+      nerdletState:
+        dataSourceId: dojo
+      requiresAccount: false
 icon: logo.png

data-sources/flutter-web/config.yml

@@ -5,9 +5,11 @@ description: |
 icon: logo.png
 install:
   primary:
-    link:
-      url: https://docs.newrelic.com/docs/infrastructure/host-integrations/host-integrations-list/browser-monitoring-integrations/flutter-web-integration/
-
+    nerdlet:
+      nerdletId: marketplace.install-data-source
+      nerdletState:
+        dataSourceId: flutter-web
+      requiresAccount: false
 keywords:
   - flutter
   - flutter web application

data-sources/jfrog-platform/config.yml

@@ -4,5 +4,5 @@ description: Observe JFrog Platform and gain insights using New Relic Observabil
 install:
   primary:
     link:
-      url: https://github.com/jfrog/log-analytics-newrelic
+      url: https://jfrog.com/help/r/jfrog-platform-administration-documentation/new-relic
 icon: icon.svg

data-sources/jira-errors-inbox/config.yml

@@ -3,6 +3,9 @@ displayName: Atlassian Jira for Errors Inbox
 description: Integrated errors inbox with Atlassian Jira (cloud) to easily create tickets for your errors.
 install:
   primary:
-    link:
-      url: https://docs.newrelic.com/docs/errors-inbox/errors-inbox/#jira
+    nerdlet:
+      nerdletId: marketplace.install-data-source
+      nerdletState:
+        dataSourceId: jira-errors-inbox
+      requiresAccount: false
 icon: logo.svg

data-sources/nextcloud/config.yml

@@ -4,6 +4,9 @@ description: |
   Use our infrastructure agent and the Prometheus open metric integration to monitor the performance of the processes on your Nextcloud server.
 install:
   primary:
-    link:
-      url: https://docs.newrelic.com/docs/infrastructure/host-integrations/host-integrations-list/nextcloud-integration/
+    nerdlet:
+      nerdletId: marketplace.install-data-source
+      nerdletState:
+        dataSourceId: nextcloud
+      requiresAccount: false
 icon: logo.png

data-sources/nvidia-gpu/config.yml

@@ -0,0 +1,19 @@
+id: nvidia-gpu
+displayName: Nvidia GPUs
+description: |
+  Monitor Nvidia GPUs based on the Nvidia SMI utility.
+
+install:
+  primary:
+    link:
+      url: https://docs.newrelic.com/docs/infrastructure/host-integrations/host-integrations-list/nvidia-gpu-integration/
+
+icon: logo.png
+
+keywords:
+  - infrastructure
+  - nvidia
+  - gpu
+
+categoryTerms:
+  - infrastructure

data-sources/shopify/config.yml

@@ -0,0 +1,17 @@
+id: shopify
+displayName: Shopify
+description: |
+  Shopify is a website building tool. You can use New Relic's browser agent to monitor your websites created in Shopify.
+icon: logo.png
+install:
+  primary:
+    link:
+      url: https://docs.newrelic.com/docs/browser/browser-monitoring/installation/install-browser-monitoring-agent/
+keywords:
+  - traffic
+  - browser
+  - agent
+  - web app
+  - newrelic partner
+categoryTerms:
+  - newrelic partner

install/third-party/jfrog-platform/install.yml

@@ -11,4 +11,4 @@ target:
 install:
   mode: link
   destination:
-    url: https://github.com/jfrog/log-analytics-newrelic
+    url: https://jfrog.com/help/r/jfrog-platform-administration-documentation/new-relic