Update config for v1.5.0

This commit is contained in:
Jan Eitzinger
2026-03-04 14:57:11 +01:00
parent 8c8c40b547
commit bd22bfe5e6
13 changed files with 4091 additions and 6825 deletions

View File

@@ -1,18 +1,20 @@
[Unit]
Description=ClusterCockpit Web Server
Documentation=https://clustercockpit.org
Description=ClusterCockpit Backend
Documentation=https://github.com/ClusterCockpit/cc-backend
Wants=network-online.target
After=network-online.target
After=mariadb.service mysql.service
[Service]
WorkingDirectory=/opt/monitoring/cc-backend
Type=notify
User=clustercockpit
Group=clustercockpit
NotifyAccess=all
Restart=on-failure
RestartSec=30
TimeoutStopSec=100
ExecStart=/opt/monitoring/cc-backend/cc-backend -loglevel info -server -config ./config.json
TimeoutStartSec=200
TimeoutStopSec=200
ExecStart=/opt/monitoring/cc-backend/cc-backend -loglevel info -server -config ./config.json
[Install]
WantedBy=multi-user.target

View File

@@ -1,241 +1,77 @@
{
"addr": "0.0.0.0:443",
"stop-jobs-exceeding-walltime": 288000,
"short-running-jobs-duration": 300,
"ldap": {
"url": "ldaps://hpcldap.rrze.uni-erlangen.de",
"user_base": "ou=people,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
"search_dn": "cn=hpcmonitoring,ou=roadm,ou=profile,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
"user_bind": "uid={username},ou=people,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
"user_filter": "(&(objectclass=posixAccount))",
"sync_interval": "24h"
},
"jwts": {
"syncUserOnLogin": true,
"updateUserOnLogin": true,
"trustedIssuer": "https://portal.hpc.fau.de/",
"validateUser": false,
"max-age": "168h"
},
"https-cert-file": "/etc/letsencrypt/live/monitoring.nhr.fau.de/fullchain.pem",
"https-key-file": "/etc/letsencrypt/live/monitoring.nhr.fau.de/privkey.pem",
"user": "clustercockpit",
"group": "clustercockpit",
"archive": {
"kind": "file",
"path": "./var/job-archive",
"compression": 7,
"retention": {
"policy": "none"
}
},
"enable-resampling": {
"trigger": 30,
"resolutions": [
600,
300,
120,
60
]
},
"emission-constant": 317,
"ui-defaults": {
"analysis_view_histogramMetrics": [
"flops_any",
"mem_bw",
"mem_used"
],
"analysis_view_scatterPlotMetrics": [
[
"flops_any",
"mem_bw"
],
[
"flops_any",
"cpu_load"
],
[
"cpu_load",
"mem_bw"
]
],
"job_view_nodestats_selectedMetrics": [
"flops_any",
"mem_bw",
"mem_used"
],
"job_view_polarPlotMetrics": [
"flops_any",
"mem_bw",
"mem_used"
],
"job_view_selectedMetrics": [
"flops_any",
"mem_bw",
"mem_used"
],
"job_view_showFootprint": true,
"job_list_usePaging": false,
"plot_general_colorBackground": true,
"plot_general_colorscheme": [
"#00bfff",
"#0000ff",
"#ff00ff",
"#ff0000",
"#ff8000",
"#ffff00",
"#80ff00"
],
"plot_general_lineWidth": 3,
"plot_list_jobsPerPage": 10,
"plot_list_selectedMetrics": [
"cpu_load",
"mem_used",
"flops_any",
"mem_bw"
],
"plot_view_plotsPerRow": 3,
"plot_view_showPolarplot": true,
"plot_view_showRoofline": true,
"plot_view_showStatTable": true,
"system_view_selectedMetric": "cpu_load",
"analysis_view_selectedTopEntity": "user",
"analysis_view_selectedTopCategory": "totalWalltime",
"status_view_selectedTopUserCategory": "totalJobs",
"status_view_selectedTopProjectCategory": "totalJobs"
},
"clusters": [
{
"name": "fritz",
"metricDataRepository": {
"kind": "cc-metric-store",
"url": "http://localhost:8082",
"token": "-"
},
"filterRanges": {
"numNodes": {
"from": 1,
"to": 64
"main": {
"addr": "127.0.0.1:8050",
"api-allowed-ips": ["*"],
"stop-jobs-exceeding-walltime":288000,
"short-running-jobs-duration": 300,
"resampling": {
"minimum-points": 600,
"trigger": 180,
"resolutions": [240, 60]
},
"duration": {
"from": 0,
"to": 86400
"nodestate-retention": {
"policy": "move",
"target-kind": "file",
"target-path": "/opt/monitoring/cc-backend/var/nodestate-archive/"
},
"startTime": {
"from": "2022-01-01T00:00:00Z",
"to": null
}
}
"emission-constant": 317,
"enable-job-taggers": true
},
{
"name": "alex",
"metricDataRepository": {
"kind": "cc-metric-store",
"url": "http://localhost:8082",
"token": "-"
},
"filterRanges": {
"numNodes": {
"from": 1,
"to": 64
},
"duration": {
"from": 0,
"to": 86400
},
"startTime": {
"from": "2022-01-01T00:00:00Z",
"to": null
}
}
"cron": {
"commit-job-worker": "1m",
"duration-worker": "5m",
"footprint-worker": "10m"
},
{
"name": "woody",
"metricDataRepository": {
"kind": "cc-metric-store",
"url": "http://localhost:8082",
"token": "-"
},
"filterRanges": {
"numNodes": {
"from": 1,
"to": 1
},
"duration": {
"from": 0,
"to": 172800
},
"startTime": {
"from": "2020-01-01T00:00:00Z",
"to": null
}
}
"archive": {
"kind": "file",
"path": "./var/job-archive"
},
{
"name": "tinyfat",
"metricDataRepository": {
"kind": "cc-metric-store",
"url": "http://localhost:8082",
"token": "-"
},
"filterRanges": {
"numNodes": {
"from": 1,
"to": 1
"auth": {
"ldap": {
"url": "ldaps://hpcldap.rrze.uni-erlangen.de",
"user-base": "ou=people,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
"search-dn": "cn=hpcmonitoring,ou=roadm,ou=profile,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
"user-bind": "uid={username},ou=people,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
"user-filter": "(&(objectclass=posixAccount))",
"sync-interval": "24h"
},
"duration": {
"from": 0,
"to": 172800
},
"startTime": {
"from": "2020-01-01T00:00:00Z",
"to": null
"jwts": {
"sync-user-on-login": true,
"update-user-on-login": true,
"validate-user": false,
"max-age": "1h",
"trusted-issuer": "https://portal.hpc.fau.de/"
}
}
},
{
"name": "tinygpu",
"metricDataRepository": {
"kind": "cc-metric-store",
"url": "http://localhost:8082",
"token": "-"
},
"filterRanges": {
"numNodes": {
"from": 1,
"to": 1
"metric-store": {
"checkpoints": {
"file-format": "wal",
"directory": "./var/metric-checkpoints"
},
"duration": {
"from": 0,
"to": 172800
"cleanup": {
"mode": "archive",
"directory": "./var/metric-archive"
},
"startTime": {
"from": "2020-01-01T00:00:00Z",
"to": null
}
}
"nats-subscriptions": [
{
"subscribe-to": "ccmetrics.>"
}
],
"retention-in-memory": "24h",
"memory-cap": 200
},
{
"name": "meggie",
"metricDataRepository": {
"kind": "cc-metric-store",
"url": "http://localhost:8082",
"token": "-"
},
"filterRanges": {
"numNodes": {
"from": 1,
"to": 64
},
"duration": {
"from": 0,
"to": 86400
},
"startTime": {
"from": "2018-01-01T00:00:00Z",
"to": null
"archive": {
"kind": "file",
"path": "./var/job-archive",
"compression": 7,
"retention": {
"policy": "none"
}
}
}
]
},
"nats": {
"address": "nats://monitoring.nhr.fau.de:4222",
"username": "metricstore",
"password": "XXX"
},
"ui-file": "uiConfig.json"
}

View File

@@ -0,0 +1,59 @@
{
"job-view": {
"show-polar-plot":true,
"show-footprint": true,
"show-roofline": true,
"show-stat-table": true
},
"metric-config": {
"job-list-metrics": ["cpu_load", "flops_any", "mem_bw", "mem_used"],
"job-view-plot-metrics": ["cpu_load", "cpu_user", "flops_any", "mem_bw", "mem_used", "clock", "ipc", "cpu_power", "nfs4_total"],
"job-view-table-metrics": ["mem_bw", "flops_any", "mem_used"],
"clusters": [
{
"name": "fritz",
"job-view-plot-metrics": ["cpu_load", "cpu_user", "flops_any", "vectorization_ratio", "mem_bw", "mem_used", "flops_dp", "flops_sp", "ib_recv", "ib_xmit", "clock", "ipc", "cpu_power", "mem_power", "nfs4_total"]
},
{
"name": "alex",
"job-list-metrics": ["acc_utilization", "acc_mem_used", "cpu_load", "flops_any", "mem_bw", "mem_used"],
"job-view-plot-metrics": ["acc_utilization", "nv_mem_util", "acc_mem_used", "acc_power", "nv_sm_clock", "nv_temp", "cpu_load", "cpu_user", "flops_any", "mem_bw", "mem_used", "clock", "ipc", "cpu_power", "nfs4_total"],
"job-view-table-metrics": ["acc_utilization", "mem_bw", "flops_any", "mem_used"]
},
{
"name": "tinygpu",
"job-list-metrics": ["acc_utilization", "acc_mem_used", "cpu_load", "flops_any", "mem_bw", "mem_used"],
"job-view-plot-metrics": ["acc_utilization", "nv_mem_util", "acc_mem_used", "acc_power", "nv_sm_clock", "nv_temp", "cpu_load", "cpu_user", "flops_any", "mem_bw", "mem_used", "clock", "ipc", "cpu_power", "nfs4_total"],
"job-view-table-metrics": ["acc_utilization", "mem_bw", "flops_any", "mem_used"]
},
{
"name": "helma",
"job-list-metrics": ["acc_utilization", "acc_mem_used", "cpu_load", "flops_any", "mem_bw", "mem_used"],
"job-view-plot-metrics": ["acc_utilization", "nv_mem_util", "acc_mem_used", "acc_power", "nv_sm_clock", "nv_temp", "cpu_load", "cpu_user", "flops_any", "mem_bw", "mem_used", "clock", "ipc", "cpu_power", "ib_recv", "ib_xmit", "nfs4_total"],
"job-view-table-metrics": ["acc_utilization", "mem_bw", "flops_any", "mem_used"],
"sub-clusters": [
{
"name": "cpu",
"job-list-metrics": ["cpu_load", "flops_any", "mem_bw", "mem_used"],
"job-view-plot-metrics": [ "cpu_load", "cpu_user", "flops_any", "mem_bw", "mem_used", "clock", "ipc", "cpu_power", "flops_dp", "flops_sp", "ib_recv", "ib_xmit", "nfs4_total"],
"job-view-table-metrics": ["mem_bw", "flops_any", "mem_used"]
}
]
}
]
},
"plot-configuration": {
"plots-per-row": 3,
"color-background": true,
"line-width": 3,
"color-scheme": [
"#00bfff",
"#0000ff",
"#ff00ff",
"#ff0000",
"#ff8000",
"#ffff00",
"#80ff00"
]
}
}