diff --git a/alerts/Merlin7/LoginNodeLoadHigh.json b/alerts/Merlin7/LoginNodeLoadHigh.json index b63e003..5c94696 100644 --- a/alerts/Merlin7/LoginNodeLoadHigh.json +++ b/alerts/Merlin7/LoginNodeLoadHigh.json @@ -3,7 +3,7 @@ "name": null, "namespace": "default", "uid": null, - "resourceVersion": "15", + "resourceVersion": "16", "labels": { "grafana.app/folder": "bf7geueotdmgwc", "grafana.com/group": "5m-check-interval", @@ -12,9 +12,9 @@ "annotations": { "grafana.app/folder": "bf7geueotdmgwc", "grafana.app/updatedBy": "ff52p5ojz4b28c", - "grafana.app/updatedTimestamp": "2026-07-10T06:59:14Z", + "grafana.app/updatedTimestamp": "2026-07-16T12:20:07Z", "grafana.com/provenance": "", - "grafana.com/updateTimestamp": "2026-07-10T06:59:14Z", + "grafana.com/updateTimestamp": "2026-07-16T12:20:07Z", "grafana.com/updatedBy": "ff52p5ojz4b28c" } }, diff --git a/dashboards/Merlin7/Merlin7_Slurm_Native_OpenMetrics.json b/dashboards/Merlin7/Merlin7_Slurm_Native_OpenMetrics.json index 314336a..da6f5c9 100644 --- a/dashboards/Merlin7/Merlin7_Slurm_Native_OpenMetrics.json +++ b/dashboards/Merlin7/Merlin7_Slurm_Native_OpenMetrics.json @@ -1069,7 +1069,11 @@ "multiLane": false }, "legend": { - "calcs": [], + "calcs": [ + "min", + "max", + "mean" + ], "displayMode": "list", "placement": "bottom", "showLegend": true @@ -1970,7 +1974,7 @@ "type": "timeseries" }, { - "collapsed": true, + "collapsed": false, "gridPos": { "h": 1, "w": 24, @@ -1978,930 +1982,928 @@ "y": 30 }, "id": 129, - "panels": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "bars", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "normal" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - } - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 31 - }, - "id": 116, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "multi", - "sort": "desc" - } - }, - "pluginVersion": "13.0.2", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_running{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "Jobs running per user", - "type": "timeseries" - }, - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "bars", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "normal" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - } - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 31 - }, - "id": 122, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "multi", - "sort": "desc" - } - }, - "pluginVersion": "13.0.2", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_cpus_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"} ", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "CPUs allocated per user", - "type": "timeseries" - }, - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "bars", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "normal" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - } - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 39 - }, - "id": 120, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "multi", - "sort": "desc" - } - }, - "pluginVersion": "13.0.1+security-01", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_pending{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "Pending jobs per user", - "type": "timeseries" - }, - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "bars", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "normal" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - }, - "unit": "mbytes" - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 39 - }, - "id": 119, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "multi", - "sort": "desc" - } - }, - "pluginVersion": "13.0.1+security-01", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_memory_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "Allocated memory per user", - "type": "timeseries" - }, - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "line", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "none" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - } - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 47 - }, - "id": 117, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "multi", - "sort": "desc" - } - }, - "pluginVersion": "13.0.1+security-01", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_cpus_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"} / slurm_user_jobs_running{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "Users' avg CPUs per job", - "type": "timeseries" - }, - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "line", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "none" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - }, - "unit": "mbytes" - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 47 - }, - "id": 118, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "multi", - "sort": "desc" - } - }, - "pluginVersion": "13.0.1+security-01", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_memory_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"} / slurm_user_jobs_running{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "Users' avg. memory per Job", - "type": "timeseries" - }, - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "bars", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "normal" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - } - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 55 - }, - "id": 121, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "single", - "sort": "none" - } - }, - "pluginVersion": "13.0.1+security-01", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_failed{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "Failed jobs per user", - "type": "timeseries" - }, - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "line", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "none" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - }, - "unit": "mbytes" - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 55 - }, - "id": 124, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "multi", - "sort": "desc" - } - }, - "pluginVersion": "13.0.1+security-01", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_memory_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"} / slurm_user_jobs_cpus_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "Users' avg. memory per alloc. CPU", - "type": "timeseries" - }, - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisBorderShow": false, - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "barWidthFactor": 0.6, - "drawStyle": "bars", - "fillOpacity": 0, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "insertNulls": false, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "auto", - "showValues": false, - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "normal" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green", - "value": 0 - }, - { - "color": "red", - "value": 80 - } - ] - } - } - }, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 63 - }, - "id": 123, - "options": { - "annotations": { - "clustering": -1, - "multiLane": false - }, - "legend": { - "calcs": [], - "displayMode": "list", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "hideZeros": false, - "mode": "single", - "sort": "none" - } - }, - "pluginVersion": "13.0.1+security-01", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "merlin-mimir" - }, - "editorMode": "code", - "expr": "slurm_user_jobs_cancelled{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", - "instant": false, - "legendFormat": "{{username}}", - "range": true, - "refId": "A" - } - ], - "title": "Cancelled jobs per user", - "type": "timeseries" - } - ], "title": "user monitoring", "type": "row" }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "bars", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 31 + }, + "id": 116, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "13.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_running{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "Jobs running per user", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "bars", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 31 + }, + "id": 122, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "13.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_cpus_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"} ", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "CPUs allocated per user", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "bars", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 39 + }, + "id": 120, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "13.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_pending{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "Pending jobs per user", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "bars", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "mbytes" + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 39 + }, + "id": 119, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "13.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_memory_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "Allocated memory per user", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 47 + }, + "id": 117, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "13.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_cpus_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"} / slurm_user_jobs_running{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "Users' avg CPUs per job", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "mbytes" + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 47 + }, + "id": 118, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "13.0.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_memory_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"} / slurm_user_jobs_running{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "Users' avg. memory per Job", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "bars", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 55 + }, + "id": 121, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + }, + "pluginVersion": "13.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_failed{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "Failed jobs per user", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "mbytes" + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 55 + }, + "id": 124, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "13.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_memory_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"} / slurm_user_jobs_cpus_alloc{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "Users' avg. memory per alloc. CPU", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "bars", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + } + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 63 + }, + "id": 123, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + }, + "pluginVersion": "13.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "merlin-mimir" + }, + "editorMode": "code", + "expr": "slurm_user_jobs_cancelled{slurm_cluster=\"$slurm_cluster\",instance=~\".*01\"}", + "instant": false, + "legendFormat": "{{username}}", + "range": true, + "refId": "A" + } + ], + "title": "Cancelled jobs per user", + "type": "timeseries" + }, { "collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 31 + "y": 71 }, "id": 130, "panels": [ @@ -2989,7 +2991,7 @@ "h": 8, "w": 12, "x": 0, - "y": 32 + "y": 72 }, "id": 20, "options": { @@ -3121,7 +3123,7 @@ "h": 8, "w": 12, "x": 12, - "y": 32 + "y": 72 }, "id": 21, "options": { @@ -3239,7 +3241,7 @@ "h": 8, "w": 12, "x": 0, - "y": 40 + "y": 80 }, "id": 22, "options": { @@ -3346,7 +3348,7 @@ "h": 8, "w": 12, "x": 12, - "y": 40 + "y": 80 }, "id": 23, "options": { @@ -3393,7 +3395,7 @@ "h": 1, "w": 24, "x": 0, - "y": 32 + "y": 72 }, "id": 131, "panels": [ @@ -3460,7 +3462,7 @@ "h": 8, "w": 8, "x": 0, - "y": 33 + "y": 73 }, "id": 30, "options": { @@ -3560,7 +3562,7 @@ "h": 8, "w": 8, "x": 8, - "y": 33 + "y": 73 }, "id": 31, "options": { @@ -3661,7 +3663,7 @@ "h": 8, "w": 8, "x": 16, - "y": 33 + "y": 73 }, "id": 32, "options": { @@ -3708,7 +3710,7 @@ "h": 1, "w": 24, "x": 0, - "y": 33 + "y": 73 }, "id": 132, "panels": [ @@ -3775,7 +3777,7 @@ "h": 8, "w": 12, "x": 12, - "y": 34 + "y": 74 }, "id": 11, "options": { @@ -3866,7 +3868,7 @@ "h": 1, "w": 24, "x": 0, - "y": 34 + "y": 74 }, "id": 133, "panels": [ @@ -3934,7 +3936,7 @@ "h": 8, "w": 8, "x": 0, - "y": 35 + "y": 75 }, "id": 50, "options": { @@ -4067,7 +4069,7 @@ "h": 8, "w": 8, "x": 8, - "y": 35 + "y": 75 }, "id": 51, "options": { @@ -4200,7 +4202,7 @@ "h": 8, "w": 8, "x": 16, - "y": 35 + "y": 75 }, "id": 52, "options": { @@ -4334,7 +4336,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 83 }, "id": 53, "options": { @@ -4434,7 +4436,7 @@ "h": 8, "w": 12, "x": 12, - "y": 43 + "y": 83 }, "id": 54, "options": { @@ -4555,5 +4557,5 @@ "timezone": "browser", "title": "Merlin7 Slurm Native OpenMetrics", "uid": "de7rpsq1merlin7slurm1", - "version": 29 + "version": 32 } diff --git a/receivers/Merlin_Alarms.json b/receivers/Merlin_Alarms.json index 3ae3756..33e3c02 100644 --- a/receivers/Merlin_Alarms.json +++ b/receivers/Merlin_Alarms.json @@ -12,7 +12,7 @@ "grafana.com/access/canWrite": "true", "grafana.com/canUse": "true", "grafana.com/inUse/routes": "1", - "grafana.com/inUse/rules": "3" + "grafana.com/inUse/rules": "2" } }, "spec": {