Skip to content

fix(observability): Fix fastapi metrics. Add tags. Add minio metrics #96

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

Merged
alhendrickson merged 1 commit into from
Jun 10, 2026
Merged

fix(observability): Fix fastapi metrics. Add tags. Add minio metrics #96

Show file tree
Hide file tree
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
5 changes: 3 additions & 2 deletions helm-charts/cogstack-observability-helm/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,10 +110,11 @@ kubectl delete namespace observability
| kube-prometheus-stack.prometheus.prometheusSpec.scrapeConfigSelectorNilUsesHelmValues | bool | `false` | |
| kube-prometheus-stack.prometheus.prometheusSpec.serviceMonitorSelectorNilUsesHelmValues | bool | `false` | |
| nameOverride | string | `""` | |
| provisioning | object | `{"dashboards":{"availability":{"enabled":false},"enabled":true,"fastapi":{"enabled":true},"jupyterhub":{"enabled":false},"opensearch":{"enabled":true}}}` | Dashboards to be installed |
| provisioning | object | `{"dashboards":{"availability":{"enabled":false},"enabled":true,"fastapi":{"enabled":true},"jupyterhub":{"enabled":false},"minio":{"enabled":false},"opensearch":{"enabled":true}}}` | Dashboards to be installed |
| provisioning.dashboards.availability | object | `{"enabled":false}` | Availability dashboard shows uptime of services |
| provisioning.dashboards.fastapi | object | `{"enabled":true}` | FastAPI dashboard shows metrics from FastAPI services |
| provisioning.dashboards.fastapi | object | `{"enabled":true}` | FastAPI dashboard shows metrics from FastAPI services like Medcat Service |
| provisioning.dashboards.jupyterhub | object | `{"enabled":false}` | JupyterHub dashboard shows metrics from JupyterHub |
| provisioning.dashboards.minio | object | `{"enabled":false}` | Minio dashboard shows metrics from Minio |
| provisioning.dashboards.opensearch | object | `{"enabled":true}` | OpenSearch dashboard shows metrics from OpenSearch |

----------------------------------------------
Expand Down
2 changes: 1 addition & 1 deletion helm-charts/cogstack-observability-helm/dashboards/cogstack-availability.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1609,7 +1609,7 @@
},
"timepicker": {},
"timezone": "",
"title": "Cogstack Monitoring Dashboard",
"title": "Cogstack Availability",
"uid": "NEzutrbMk",
"version": 24,
"weekStart": ""
Expand Down
84 changes: 25 additions & 59 deletions helm-charts/cogstack-observability-helm/dashboards/fastapi-metrics.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(rate(http_requests_total[1m]))",
"expr": "sum(rate(http_requests_total{job=~\"$job\"}[1m]))",
"instant": true,
"interval": "",
"legendFormat": "",
Expand Down Expand Up @@ -199,7 +199,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "rate(http_requests_total[1m])",
"expr": "rate(http_requests_total{job=~\"$job\"}[1m])",
"interval": "",
"legendFormat": "{{path}}",
"range": true,
Expand Down Expand Up @@ -277,7 +277,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "sum by (handler) (rate(http_request_duration_seconds_sum{handler=\"/api/process\"}[1m])) / \r\nsum by (handler) (rate(http_request_duration_seconds_count{handler=\"/api/process\"}[1m]))",
"expr": "sum by (handler) (rate(http_request_duration_seconds_sum{job=~\"$job\",handler=\"/api/process\"}[1m])) / \r\nsum by (handler) (rate(http_request_duration_seconds_count{job=~\"$job\",handler=\"/api/process\"}[1m]))",
"instant": false,
"interval": "",
"legendFormat": "",
Expand Down Expand Up @@ -356,7 +356,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "(\r\n sum by (pod) (rate(http_request_duration_seconds_sum{handler=\"/api/process\"}[1m])) / \r\n sum by (pod) (rate(http_request_duration_seconds_count{handler=\"/api/process\"}[1m]))\r\n)",
"expr": "(\r\n sum by (pod) (rate(http_request_duration_seconds_sum{job=~\"$job\",handler=\"/api/process\"}[1m])) / \r\n sum by (pod) (rate(http_request_duration_seconds_count{job=~\"$job\",handler=\"/api/process\"}[1m]))\r\n)",
"instant": false,
"interval": "",
"legendFormat": "__auto",
Expand Down Expand Up @@ -427,28 +427,11 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(rate(http_requests_total{status=\"404\"}[60m]))",
"expr": "sum(increase(http_requests_total{job=~\"$job\",status=~\"4xx|5xx\"}[24h]))",
"interval": "",
"legendFormat": "",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "rate(http_requests_total{status=\"4xx\"}[1h])",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": false,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "B",
"useBackend": false
}
],
"timeFrom": "24h",
Expand Down Expand Up @@ -510,7 +493,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": true,
"expr": "http_requests_total{job=\"deid-medcat-service\"}",
"expr": "http_requests_total{job=~\"$job\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
Expand Down Expand Up @@ -638,7 +621,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "http_requests_total{path!=\"/metrics\"}",
"expr": "http_requests_total{job=~\"$job\",handler!=\"/metrics\"}",
"interval": "",
"legendFormat": "__auto",
"range": true,
Expand Down Expand Up @@ -739,7 +722,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(rate(http_requests_total{status=\"2xx\"}[60m])) / sum(rate(http_requests_total[60m]))",
"expr": "sum(rate(http_requests_total{job=~\"$job\",status=\"2xx\"}[60m])) / sum(rate(http_requests_total{job=~\"$job\"}[60m]))",
"interval": "",
"legendFormat": "__auto",
"range": true,
Expand Down Expand Up @@ -840,7 +823,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(rate(http_requests_total{status=\"4xx\"}[60m])) / sum(rate(http_requests_total[60m]))",
"expr": "sum(rate(http_requests_total{job=~\"$job\",status=\"4xx\"}[60m])) / sum(rate(http_requests_total{job=~\"$job\"}[60m]))",
"interval": "",
"legendFormat": "{{path}}",
"range": true,
Expand All @@ -853,7 +836,7 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "http_requests_total{status=\"4xx\"}",
"expr": "http_requests_total{job=~\"$job\",status=\"4xx\"}",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
Expand Down Expand Up @@ -957,7 +940,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[60m])) by (le))",
"expr": "histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket{job=~\"$job\"}[60m])) by (le))",
"interval": "",
"legendFormat": "{{path}}",
"range": true,
Expand Down Expand Up @@ -1052,7 +1035,7 @@
"targets": [
{
"editorMode": "code",
"expr": "sum by (pod) (\r\n rate(http_request_duration_seconds_sum{handler=\"/api/process\"}[1m])\r\n) / \r\nsum by (pod) (\r\n rate(http_request_duration_seconds_count{handler=\"/api/process\"}[1m])\r\n)",
"expr": "sum by (pod) (\r\n rate(http_request_duration_seconds_sum{job=~\"$job\",handler=\"/api/process\"}[1m])\r\n) / \r\nsum by (pod) (\r\n rate(http_request_duration_seconds_count{job=~\"$job\",handler=\"/api/process\"}[1m])\r\n)",
"legendFormat": "__auto",
"range": true,
"refId": "A"
Expand All @@ -1065,48 +1048,31 @@
"preload": false,
"refresh": "5s",
"schemaVersion": 41,
"tags": [],
"tags": [
"cogstack",
"apps"
],
"templating": {
"list": [
{
"current": {
"text": "",
"value": ""
"text": "All",
"value": "$__all"
},
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"definition": "label_values(fastapi_app_info{}, app_name)",
"includeAll": false,
"label": "Application Name",
"name": "app_name",
"options": [],
"definition": "label_values(http_requests_total, job)",
"includeAll": true,
"label": "Service",
"name": "job",
"query": {
"query": "label_values(fastapi_app_info{}, app_name)",
"query": "label_values(http_requests_total, job)",
"refId": "StandardVariableQuery"
},
"refresh": 1,
"regex": "",
"type": "query"
},
{
"current": {
"text": "",
"value": ""
},
"description": "query with keyword",
"label": "Log Query",
"name": "log_keyword",
"options": [
{
"selected": true,
"text": "",
"value": ""
}
],
"query": "",
"type": "textbox"
}
]
},
Expand All @@ -1116,7 +1082,7 @@
},
"timepicker": {},
"timezone": "",
"title": "FastAPI Observability",
"uid": "fastapi-observability",
"title": "FastAPI Metrics",
"uid": "fastapi-metrics",
"version": 8
}
4 changes: 2 additions & 2 deletions helm-charts/cogstack-observability-helm/dashboards/jupyterhub-metrics.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2166,7 +2166,7 @@
"preload": false,
"refresh": "",
"schemaVersion": 42,
"tags": [],
"tags": ["cogstack", "apps"],
"templating": {
"list": []
},
Expand All @@ -2176,7 +2176,7 @@
},
"timepicker": {},
"timezone": "",
"title": "JupyterHub Stats",
"title": "JupyterHub Metrics",
"uid": "jupyterhub",
"version": 2
}
Loading
Loading