grafana: update dashboards

Changed files: dashboards/Merlin7/General_Overview.json,dashboards/Merlin7/SLURM_Dashboard.json dashboards/Merlin7/SLURM_Dashboard__Users_.json
This commit is contained in:
gitea-actions[bot]
2026-04-21 11:00:42 +00:00
parent d31451a240
commit 5df3ef1ca2
3 changed files with 1132 additions and 839 deletions
+422 -106
View File
@@ -29,8 +29,8 @@
"x": 0,
"y": 0
},
"id": 8,
"title": "Node Status",
"id": 11,
"title": "Overview",
"type": "row"
},
{
@@ -38,45 +38,32 @@
"type": "prometheus",
"uid": "merlin-mimir"
},
"description": "Provides the current UP/DOWN status of nodes over a fixed window of 5 minutes. Note that the values might change massively during cluster instability, as the `up` value is only preserved for a fixed time before being \"forgotten\" by Prometheus.",
"description": "Green means UP, Red means DOWN",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
"mode": "continuous-RdYlGr"
},
"custom": {
"axisPlacement": "hidden",
"fillOpacity": 100,
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineWidth": 2
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"color": "red",
"value": 0
}
]
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "DOWN",
"scope": "series"
},
"properties": [
{
"id": "thresholds",
"value": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": 0
}
]
}
}
]
}
]
}
},
"gridPos": {
"h": 9,
@@ -85,6 +72,93 @@
"y": 1
},
"id": 1,
"options": {
"annotations": {
"clustering": -1,
"multiLane": false
},
"colWidth": 0.9,
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"rowHeight": 0.9,
"showValue": "never",
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "13.0.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum(up{job=\"integrations/unix\"}) / count(up{job=\"integrations/unix\"})",
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Cluster Status Timeline",
"type": "status-history"
},
{
"datasource": {
"type": "prometheus",
"uid": "merlin-mimir"
},
"description": "Checks individual node status",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"mappings": [
{
"options": {
"0": {
"color": "green",
"index": 0,
"text": "OK"
},
"1": {
"color": "yellow",
"index": 1,
"text": "ISSUE"
}
},
"type": "value"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
}
}
},
"gridPos": {
"h": 9,
"w": 8,
"x": 8,
"y": 1
},
"id": 7,
"options": {
"colorMode": "value",
"graphMode": "none",
@@ -93,7 +167,7 @@
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"last"
"lastNotNull"
],
"fields": "",
"values": false
@@ -110,9 +184,160 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "count(last_over_time(up{job=\"integrations/unix\"}[5m]) == 1)",
"expr": "hpe_redfish_clusterstor_node_health",
"instant": false,
"legendFormat": "UP",
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Storage Health",
"transformations": [
{
"id": "reduce",
"options": {
"reducers": [
"last"
]
}
}
],
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "merlin-mimir"
},
"description": "Checks if network jitter rises above a specific threshold",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"noValue": "DOWN",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": 0
}
]
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "PSI <-> CSCS",
"scope": "series"
},
"properties": [
{
"id": "mappings",
"value": [
{
"options": {
"from": 0.001,
"result": {
"color": "green",
"index": 0,
"text": "OK"
},
"to": 0.026
},
"type": "range"
},
{
"options": {
"from": 0.026,
"result": {
"color": "orange",
"index": 1,
"text": "UNSTABLE"
}
},
"type": "range"
}
]
}
]
},
{
"matcher": {
"id": "byName",
"options": "CSCS SSHOT",
"scope": "series"
},
"properties": [
{
"id": "mappings",
"value": [
{
"options": {
"from": 0.001,
"result": {
"color": "green",
"index": 0,
"text": "OK"
},
"to": 0.005
},
"type": "range"
},
{
"options": {
"from": 0.006,
"result": {
"color": "orange",
"index": 1,
"text": "UNSTABLE"
}
},
"type": "range"
}
]
}
]
}
]
},
"gridPos": {
"h": 9,
"w": 8,
"x": 16,
"y": 1
},
"id": 8,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "13.0.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "iperf3_received_jitter_ms{job=\"prometheus.scrape.iperf3_metrics\", instance=\"merlin7-admin01\"}",
"instant": false,
"legendFormat": "PSI <-> CSCS",
"range": true,
"refId": "A"
},
@@ -122,18 +347,104 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"exemplar": false,
"expr": "count(last_over_time(up{job=\"integrations/unix\"}[5m]) == 0)",
"format": "time_series",
"expr": "iperf3_received_jitter_ms{job=\"prometheus.scrape.iperf3_metrics\", instance=\"psistorn00\"}",
"instant": false,
"legendFormat": "DOWN",
"legendFormat": "CSCS SSHOT",
"range": true,
"refId": "B"
}
],
"title": "Node Up Status (5m)",
"title": "Network Status",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "merlin-mimir"
},
"description": "This panel uses the Alloy `up` information, which seems not to be very stable",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisPlacement": "auto",
"fillOpacity": 70,
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineWidth": 1
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": 0
}
]
}
}
},
"gridPos": {
"h": 9,
"w": 8,
"x": 0,
"y": 10
},
"id": 10,
"options": {
"annotations": {
"clustering": -1,
"multiLane": false
},
"colWidth": 0.9,
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"rowHeight": 0.9,
"showValue": "auto",
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "13.0.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "count by(instance) (up{job=\"integrations/unix\"} == 0)",
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Status History (DOWN)",
"type": "status-history"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 19
},
"id": 12,
"title": "Node Status",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
@@ -166,8 +477,8 @@
"gridPos": {
"h": 9,
"w": 8,
"x": 8,
"y": 1
"x": 0,
"y": 20
},
"id": 3,
"options": {
@@ -238,7 +549,7 @@
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
@@ -296,8 +607,8 @@
"gridPos": {
"h": 9,
"w": 8,
"x": 16,
"y": 1
"x": 8,
"y": 20
},
"id": 2,
"options": {
@@ -308,7 +619,7 @@
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"placement": "right",
"showLegend": true
},
"tooltip": {
@@ -325,9 +636,9 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "avg(node_load5{job=\"integrations/unix\",instance=~\"cn.*|gpu.*|login.*\"})",
"expr": "node_load1{job=\"integrations/unix\",instance=~\"cn.*|gpu.*|login.*\"}",
"instant": false,
"legendFormat": "Avg Load",
"legendFormat": "{{instance}}",
"range": true,
"refId": "A"
},
@@ -337,14 +648,15 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "avg(count without (cpu) (node_cpu_seconds_total{job=\"integrations/unix\", instance=~\"cn.*|gpu.*|login.*\", mode=\"idle\"}))",
"expr": "max(count without (cpu) (node_cpu_seconds_total{job=\"integrations/unix\", instance=~\"cn.*|gpu.*|login.*\", mode=\"idle\"}))",
"hide": true,
"instant": false,
"legendFormat": "Max Load",
"range": true,
"refId": "B"
}
],
"title": "Cluster Load (avg)",
"title": "Node Load (1m)",
"type": "timeseries"
},
{
@@ -353,9 +665,9 @@
"h": 1,
"w": 24,
"x": 0,
"y": 10
"y": 29
},
"id": 9,
"id": 13,
"title": "Network Status",
"type": "row"
},
@@ -422,7 +734,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 11
"y": 30
},
"id": 4,
"options": {
@@ -535,7 +847,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 11
"y": 30
},
"id": 5,
"options": {
@@ -579,9 +891,9 @@
"h": 1,
"w": 24,
"x": 0,
"y": 19
"y": 38
},
"id": 10,
"id": 14,
"title": "Storage Status",
"type": "row"
},
@@ -680,7 +992,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 20
"y": 39
},
"id": 6,
"options": {
@@ -740,61 +1052,75 @@
"color": {
"mode": "palette-classic"
},
"mappings": [
{
"options": {
"0": {
"color": "green",
"index": 0,
"text": "OK"
},
"1": {
"color": "yellow",
"index": 1,
"text": "ISSUE"
}
},
"type": "value"
"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": "never",
"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": "percent"
}
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 20
"y": 39
},
"id": 7,
"id": 9,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
"annotations": {
"clustering": -1,
"multiLane": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "right",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "13.0.0",
"targets": [
@@ -804,25 +1130,15 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "hpe_redfish_clusterstor_node_health",
"expr": "hpe_redfish_clusterstor_node_memoryutilization_percent",
"instant": false,
"legendFormat": "__auto",
"legendFormat": "{{hostname}}",
"range": true,
"refId": "A"
}
],
"title": "Storage Node(s) Health",
"transformations": [
{
"id": "reduce",
"options": {
"reducers": [
"last"
]
}
}
],
"type": "stat"
"title": "Memory Utilisation (%)",
"type": "timeseries"
}
],
"preload": false,
@@ -854,5 +1170,5 @@
"timezone": "browser",
"title": "General Overview",
"uid": "hacmpzr",
"version": 21
"version": 24
}
File diff suppressed because it is too large Load Diff
+106 -106
View File
@@ -104,7 +104,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_cpu_total{cluster=\"cpu_cluster\"} - slurm_node_cpu_alloc{cluster=\"cpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_cpu_total{cluster=\"cpu_cluster\"} - slurm_exporter_node_cpu_alloc{cluster=\"cpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -245,7 +245,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_cpu_total{cluster=\"gpu_cluster\"} - slurm_node_cpu_alloc{cluster=\"gpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_cpu_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_cpu_alloc{cluster=\"gpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -386,7 +386,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_cpu_total{cluster=\"gpu_cluster\"} - slurm_node_cpu_alloc{cluster=\"gpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_cpu_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_cpu_alloc{cluster=\"gpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -528,7 +528,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_gpus_total{cluster=\"gpu_cluster\"} - slurm_node_gpus_alloc{cluster=\"gpu_cluster\"}",
"expr": "slurm_exporter_node_gpus_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_gpus_alloc{cluster=\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -679,7 +679,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_mem_total{cluster=\"cpu_cluster\"} - slurm_node_mem_alloc{cluster=\"cpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_mem_total{cluster=\"cpu_cluster\"} - slurm_exporter_node_mem_alloc{cluster=\"cpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -825,7 +825,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_mem_total{cluster=\"gpu_cluster\"} - slurm_node_mem_alloc{cluster=\"gpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_mem_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_mem_alloc{cluster=\"gpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -971,7 +971,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_mem_total{cluster=\"gpu_cluster\"} - slurm_node_mem_alloc{cluster=\"gpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_mem_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_mem_alloc{cluster=\"gpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -1321,9 +1321,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_status{cluster=~\"cpu_cluster\"}",
"expr": "slurm_exporter_node_status{cluster=~\"cpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -1736,9 +1736,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_status{cluster=~\"gpu_cluster\"}",
"expr": "slurm_exporter_node_status{cluster=~\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -2151,9 +2151,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_status{cluster=~\"gpu_cluster\"}",
"expr": "slurm_exporter_node_status{cluster=~\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -2566,9 +2566,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_status{cluster=~\"cpu_cluster\"}",
"expr": "slurm_exporter_node_status{cluster=~\"cpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -2788,7 +2788,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "(sum by(__name__) (slurm_nodes_alloc{cluster=~\"cpu_cluster\"}) + sum by(__name__) (slurm_nodes_mix{cluster=~\"cpu_cluster\"}) + sum by(__name__) (slurm_nodes_comp{cluster=~\"cpu_cluster\"})) / sum by(__name__) (slurm_nodes_total{cluster=~\"cpu_cluster\"})",
"expr": "(sum by(__name__) (slurm_exporter_nodes_alloc{cluster=~\"cpu_cluster\"}) + sum by(__name__) (slurm_exporter_nodes_mix{cluster=~\"cpu_cluster\"}) + sum by(__name__) (slurm_exporter_nodes_comp{cluster=~\"cpu_cluster\"})) / sum by(__name__) (slurm_exporter_nodes_total{cluster=~\"cpu_cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -2803,7 +2803,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "(sum by(__name__) (slurm_nodes_alloc{cluster=~\"gpu_cluster\"}) + sum by(__name__) (slurm_nodes_mix{cluster=~\"gpu_cluster\"}) + sum by(__name__) (slurm_nodes_comp{cluster=~\"gpu_cluster\"})) / sum by(__name__) (slurm_nodes_total{cluster=~\"gpu_cluster\"})",
"expr": "(sum by(__name__) (slurm_exporter_nodes_alloc{cluster=~\"gpu_cluster\"}) + sum by(__name__) (slurm_exporter_nodes_mix{cluster=~\"gpu_cluster\"}) + sum by(__name__) (slurm_exporter_nodes_comp{cluster=~\"gpu_cluster\"})) / sum by(__name__) (slurm_exporter_nodes_total{cluster=~\"gpu_cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -3017,7 +3017,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_alloc{cluster=~\"cpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_alloc{cluster=~\"cpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Allocated",
@@ -3030,7 +3030,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_mix{cluster=~\"cpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_mix{cluster=~\"cpu_cluster\"})",
"intervalFactor": 2,
"legendFormat": "Mixed",
"range": true,
@@ -3042,7 +3042,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_idle{cluster=~\"cpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_idle{cluster=~\"cpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Idle",
@@ -3055,7 +3055,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_comp{cluster=~\"cpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_comp{cluster=~\"cpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Completing",
@@ -3068,7 +3068,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_planned{cluster=~\"cpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_planned{cluster=~\"cpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Planned",
@@ -3081,7 +3081,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_total{cluster=~\"cpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_total{cluster=~\"cpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Total",
@@ -3294,7 +3294,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_alloc{cluster=~\"gpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_alloc{cluster=~\"gpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Allocated",
@@ -3307,7 +3307,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_mix{cluster=~\"gpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_mix{cluster=~\"gpu_cluster\"})",
"intervalFactor": 2,
"legendFormat": "Mixed",
"range": true,
@@ -3319,7 +3319,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_idle{cluster=~\"gpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_idle{cluster=~\"gpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Idle",
@@ -3332,7 +3332,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_comp{cluster=~\"gpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_comp{cluster=~\"gpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Completing",
@@ -3345,7 +3345,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_planned{cluster=~\"gpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_planned{cluster=~\"gpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Planned",
@@ -3358,7 +3358,7 @@
"uid": "merlin-mimir"
},
"editorMode": "code",
"expr": "sum by(__name__) (slurm_nodes_total{cluster=~\"gpu_cluster\"})",
"expr": "sum by(__name__) (slurm_exporter_nodes_total{cluster=~\"gpu_cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Total",
@@ -3524,7 +3524,7 @@
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "slurm_nodes_down{cluster=~\"cpu_cluster|gpu_cluster\"} > 0",
"expr": "slurm_exporter_nodes_down{cluster=~\"cpu_cluster|gpu_cluster\"} > 0",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -3541,7 +3541,7 @@
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "slurm_nodes_drain{cluster=~\"cpu_cluster|gpu_cluster\"} > 0",
"expr": "slurm_exporter_nodes_drain{cluster=~\"cpu_cluster|gpu_cluster\"} > 0",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -3558,7 +3558,7 @@
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "slurm_nodes_fail{cluster=~\"cpu_cluster|gpu_cluster\"} > 0",
"expr": "slurm_exporter_nodes_fail{cluster=~\"cpu_cluster|gpu_cluster\"} > 0",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -3575,7 +3575,7 @@
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "slurm_nodes_err{cluster=~\"cpu_cluster|gpu_cluster\"} > 0",
"expr": "slurm_exporter_nodes_err{cluster=~\"cpu_cluster|gpu_cluster\"} > 0",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -4021,9 +4021,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_status{cluster=~\"cpu_cluster\"}",
"expr": "slurm_exporter_node_status{cluster=~\"cpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -4206,7 +4206,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_cpu_total{cluster=\"cpu_cluster\"} - slurm_node_cpu_alloc{cluster=\"cpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_cpu_total{cluster=\"cpu_cluster\"} - slurm_exporter_node_cpu_alloc{cluster=\"cpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -4222,7 +4222,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "round((max by(node) (slurm_node_mem_total{cluster=\"cpu_cluster\"} - slurm_node_mem_alloc{cluster=\"cpu_cluster\"}))/1000, 1)",
"expr": "round((max by(node) (slurm_exporter_node_mem_total{cluster=\"cpu_cluster\"} - slurm_exporter_node_mem_alloc{cluster=\"cpu_cluster\"}))/1000, 1)",
"instant": true,
"legendFormat": "{{node}}",
"range": false,
@@ -4468,9 +4468,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_cpus_alloc{cluster=\"cpu_cluster\"}",
"expr": "slurm_exporter_cpus_alloc{cluster=\"cpu_cluster\"}",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -4486,9 +4486,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_cpus_total{cluster=\"cpu_cluster\"}",
"expr": "slurm_exporter_cpus_total{cluster=\"cpu_cluster\"}",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -4569,9 +4569,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "sum by(partition) (slurm_queue_running{cluster=\"merlin7\"})",
"expr": "sum by(partition) (slurm_exporter_queue_running{cluster=\"merlin7\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -4685,7 +4685,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "slurm_partition_jobs_pending{cluster=\"cpu_cluster\"} > 0",
"expr": "slurm_exporter_partition_jobs_pending{cluster=\"cpu_cluster\"} > 0",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -4792,9 +4792,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_pending_time_limit_seconds{cluster=\"cpu_cluster\"}",
"expr": "slurm_exporter_job_pending_time_limit_seconds{cluster=\"cpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -4920,9 +4920,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"hourly\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"hourly\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -5029,9 +5029,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"daily\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"daily\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -5138,9 +5138,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"general\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"general\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -5247,9 +5247,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"interactive\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"interactive\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -5356,9 +5356,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"meg-short\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"meg-short\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -5465,9 +5465,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"meg-long\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"meg-long\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -5574,9 +5574,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"asa\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"asa\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -5683,9 +5683,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"mu3e\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"cpu_cluster\", partition=\"mu3e\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -6121,9 +6121,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_status{cluster=~\"gpu_cluster\"}",
"expr": "slurm_exporter_node_status{cluster=~\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -6306,7 +6306,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_gpus_total{cluster=\"gpu_cluster\"} - slurm_node_gpus_alloc{cluster=\"gpu_cluster\"}",
"expr": "slurm_exporter_node_gpus_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_gpus_alloc{cluster=\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -6439,7 +6439,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_cpu_total{cluster=\"gpu_cluster\"} - slurm_node_cpu_alloc{cluster=\"gpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_cpu_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_cpu_alloc{cluster=\"gpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -6572,7 +6572,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_mem_total{cluster=\"gpu_cluster\"} - slurm_node_mem_alloc{cluster=\"gpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_mem_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_mem_alloc{cluster=\"gpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -6694,9 +6694,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "sum by(partition) (slurm_queue_running{cluster=\"gmerlin7\"})",
"expr": "sum by(partition) (slurm_exporter_queue_running{cluster=\"gmerlin7\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -6821,7 +6821,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "slurm_partition_jobs_pending{cluster=\"gpu_cluster\"} > 0",
"expr": "slurm_exporter_partition_jobs_pending{cluster=\"gpu_cluster\"} > 0",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -6946,9 +6946,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_pending_time_limit_seconds{cluster=\"gpu_cluster\"}",
"expr": "slurm_exporter_job_pending_time_limit_seconds{cluster=\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -7096,9 +7096,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_gpus_alloc{cluster=\"gpu_cluster\", type=\"nvidia_a100-sxm4-80gb\"}",
"expr": "slurm_exporter_gpus_alloc{cluster=\"gpu_cluster\", type=\"nvidia_a100-sxm4-80gb\"}",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -7114,9 +7114,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_gpus_total{cluster=\"gpu_cluster\", type=\"nvidia_a100-sxm4-80gb\"}",
"expr": "slurm_exporter_gpus_total{cluster=\"gpu_cluster\", type=\"nvidia_a100-sxm4-80gb\"}",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -7200,9 +7200,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"a100-hourly\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"a100-hourly\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -7309,9 +7309,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"a100-daily\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"a100-daily\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -7418,9 +7418,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"a100-general\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"a100-general\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -7527,9 +7527,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"a100-interactive\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"a100-interactive\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -7967,7 +7967,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_status{cluster=~\"gpu_cluster\"}",
"expr": "slurm_exporter_node_status{cluster=~\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -8150,7 +8150,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "slurm_node_gpus_total{cluster=\"gpu_cluster\"} - slurm_node_gpus_alloc{cluster=\"gpu_cluster\"}",
"expr": "slurm_exporter_node_gpus_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_gpus_alloc{cluster=\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -8283,7 +8283,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_cpu_total{cluster=\"gpu_cluster\"} - slurm_node_cpu_alloc{cluster=\"gpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_cpu_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_cpu_alloc{cluster=\"gpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -8416,7 +8416,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "max by(node) (slurm_node_mem_total{cluster=\"gpu_cluster\"} - slurm_node_mem_alloc{cluster=\"gpu_cluster\"})",
"expr": "max by(node) (slurm_exporter_node_mem_total{cluster=\"gpu_cluster\"} - slurm_exporter_node_mem_alloc{cluster=\"gpu_cluster\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -8538,9 +8538,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "sum by(partition) (slurm_queue_running{cluster=\"gmerlin7\"})",
"expr": "sum by(partition) (slurm_exporter_queue_running{cluster=\"gmerlin7\"})",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -8665,7 +8665,7 @@
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "slurm_partition_jobs_pending{cluster=\"gpu_cluster\"} > 0",
"expr": "slurm_exporter_partition_jobs_pending{cluster=\"gpu_cluster\"} > 0",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -8790,9 +8790,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_pending_time_limit_seconds{cluster=\"gpu_cluster\"}",
"expr": "slurm_exporter_job_pending_time_limit_seconds{cluster=\"gpu_cluster\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -8940,9 +8940,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_gpus_alloc{cluster=\"gpu_cluster\", type=\"gh200\"}",
"expr": "slurm_exporter_gpus_alloc{cluster=\"gpu_cluster\", type=\"gh200\"}",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -8958,9 +8958,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_gpus_total{cluster=\"gpu_cluster\", type=\"gh200\"}",
"expr": "slurm_exporter_gpus_total{cluster=\"gpu_cluster\", type=\"gh200\"}",
"format": "time_series",
"fullMetaSearch": false,
"includeNullMetadata": true,
@@ -9044,9 +9044,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"gh-hourly\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"gh-hourly\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -9153,9 +9153,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"gh-daily\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"gh-daily\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -9262,9 +9262,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"gh-general\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"gh-general\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -9371,9 +9371,9 @@
"uid": "merlin-mimir"
},
"disableTextWrap": false,
"editorMode": "builder",
"editorMode": "code",
"exemplar": false,
"expr": "slurm_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"gh-interactive\"}",
"expr": "slurm_exporter_job_running_time_left_seconds{cluster=\"gpu_cluster\", partition=\"gh-interactive\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": true,
@@ -9436,5 +9436,5 @@
"timezone": "browser",
"title": "SLURM Dashboard (Users)",
"uid": "03bf2d39-1c0b-44f9-9c10-72ef164f29b6",
"version": 60
"version": 61
}