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

@@ -9,25 +9,15 @@ You can find an overview about all clusters
Some systems run with job exclusive nodes, others have node sharing enabled. Some systems run with job exclusive nodes, others have node sharing enabled.
There are CPU systems (Fritz, Meggie, Woody, TinyFat) as well as GPU accelerated There are CPU systems (Fritz, Meggie, Woody, TinyFat) as well as GPU accelerated
clusters (Alex, TinyGPU). clusters (Alex, Helma, TinyGPU).
NHR@FAU uses the following stack: NHR@FAU uses the following stack:
* `cc-metric-collector` as node agent * `cc-metric-collector`
* `cc-metric-store` as temporal metric time series cache. We use one instance
for all clusters.
* `cc-backend` * `cc-backend`
* A homegrown python script running on the management nodes for providing job * `cc-slurm-adapter`
meta data from Slurm
* Builtin sqlite database for job meta and user data (currently 50GB large)
* Job Archive without retention using compressed data.json files (around 700GB)
Currently all API use regular HTTP protocol, but we plan to switch to NATS for We use the following server with Ubuntu Linux:
all communication.
We also push the metric data to an InfluxDB instance for debugging purposes.
The backend and metric store run on the same dedicated Dell server running
Ubuntu Linux:
* Two Intel Xeon(R) Platinum 8352Y with 32 cores each * Two Intel Xeon(R) Platinum 8352Y with 32 cores each
* 512 GB Main memory capacity * 512 GB Main memory capacity

View File

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

View File

@@ -1,241 +1,77 @@
{ {
"addr": "0.0.0.0:443", "main": {
"stop-jobs-exceeding-walltime": 288000, "addr": "127.0.0.1:8050",
"short-running-jobs-duration": 300, "api-allowed-ips": ["*"],
"ldap": { "stop-jobs-exceeding-walltime":288000,
"url": "ldaps://hpcldap.rrze.uni-erlangen.de", "short-running-jobs-duration": 300,
"user_base": "ou=people,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de", "resampling": {
"search_dn": "cn=hpcmonitoring,ou=roadm,ou=profile,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de", "minimum-points": 600,
"user_bind": "uid={username},ou=people,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de", "trigger": 180,
"user_filter": "(&(objectclass=posixAccount))", "resolutions": [240, 60]
"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
}, },
"duration": { "nodestate-retention": {
"from": 0, "policy": "move",
"to": 86400 "target-kind": "file",
"target-path": "/opt/monitoring/cc-backend/var/nodestate-archive/"
}, },
"startTime": { "emission-constant": 317,
"from": "2022-01-01T00:00:00Z", "enable-job-taggers": true
"to": null
}
}
}, },
{ "cron": {
"name": "alex", "commit-job-worker": "1m",
"metricDataRepository": { "duration-worker": "5m",
"kind": "cc-metric-store", "footprint-worker": "10m"
"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
}
}
}, },
{ "archive": {
"name": "woody", "kind": "file",
"metricDataRepository": { "path": "./var/job-archive"
"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
}
}
}, },
{ "auth": {
"name": "tinyfat", "ldap": {
"metricDataRepository": { "url": "ldaps://hpcldap.rrze.uni-erlangen.de",
"kind": "cc-metric-store", "user-base": "ou=people,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
"url": "http://localhost:8082", "search-dn": "cn=hpcmonitoring,ou=roadm,ou=profile,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
"token": "-" "user-bind": "uid={username},ou=people,ou=hpc,dc=rrze,dc=uni-erlangen,dc=de",
}, "user-filter": "(&(objectclass=posixAccount))",
"filterRanges": { "sync-interval": "24h"
"numNodes": {
"from": 1,
"to": 1
}, },
"duration": { "jwts": {
"from": 0, "sync-user-on-login": true,
"to": 172800 "update-user-on-login": true,
}, "validate-user": false,
"startTime": { "max-age": "1h",
"from": "2020-01-01T00:00:00Z", "trusted-issuer": "https://portal.hpc.fau.de/"
"to": null
} }
}
}, },
{ "metric-store": {
"name": "tinygpu", "checkpoints": {
"metricDataRepository": { "file-format": "wal",
"kind": "cc-metric-store", "directory": "./var/metric-checkpoints"
"url": "http://localhost:8082",
"token": "-"
},
"filterRanges": {
"numNodes": {
"from": 1,
"to": 1
}, },
"duration": { "cleanup": {
"from": 0, "mode": "archive",
"to": 172800 "directory": "./var/metric-archive"
}, },
"startTime": { "nats-subscriptions": [
"from": "2020-01-01T00:00:00Z", {
"to": null "subscribe-to": "ccmetrics.>"
} }
} ],
"retention-in-memory": "24h",
"memory-cap": 200
}, },
{ "archive": {
"name": "meggie", "kind": "file",
"metricDataRepository": { "path": "./var/job-archive",
"kind": "cc-metric-store", "compression": 7,
"url": "http://localhost:8082", "retention": {
"token": "-" "policy": "none"
},
"filterRanges": {
"numNodes": {
"from": 1,
"to": 64
},
"duration": {
"from": 0,
"to": 86400
},
"startTime": {
"from": "2018-01-01T00:00:00Z",
"to": null
} }
} },
} "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"
]
}
}

View File

@@ -1,19 +0,0 @@
[Unit]
Description=ClusterCockpit In-Memory Timeseries Database for Fritz (cc-metric-store)
Documentation=https://github.com/ClusterCockpit/cc-metric-store
Wants=network-online.target
After=network-online.target
[Service]
Type=simple
User=clustercockpit
Group=clustercockpit
Restart=on-failure
RestartSec=30
TimeoutStopSec=100
WorkingDirectory=/opt/monitoring/cc-metric-store/fritz
ExecStart=/opt/monitoring/cc-metric-store/repo/cc-metric-store --config ./config.json
LimitNOFILE=500000
[Install]
WantedBy=multi-user.target

View File

@@ -1,180 +0,0 @@
{
"metrics": {
"clock": {
"frequency": 60,
"aggregation": "avg"
},
"cpu_idle": {
"frequency": 60,
"aggregation": "avg"
},
"cpu_iowait": {
"frequency": 60,
"aggregation": "avg"
},
"cpu_irq": {
"frequency": 60,
"aggregation": "avg"
},
"cpu_system": {
"frequency": 60,
"aggregation": "avg"
},
"cpu_user": {
"frequency": 60,
"aggregation": "avg"
},
"nv_mem_util": {
"frequency": 60,
"aggregation": "avg"
},
"nv_temp": {
"frequency": 60,
"aggregation": "avg"
},
"nv_sm_clock": {
"frequency": 60,
"aggregation": "avg"
},
"acc_utilization": {
"frequency": 60,
"aggregation": "avg"
},
"acc_mem_used": {
"frequency": 60,
"aggregation": "sum"
},
"acc_power": {
"frequency": 60,
"aggregation": "sum"
},
"flops_any": {
"frequency": 60,
"aggregation": "sum"
},
"flops_dp": {
"frequency": 60,
"aggregation": "sum"
},
"flops_sp": {
"frequency": 60,
"aggregation": "sum"
},
"ib_recv": {
"frequency": 60,
"aggregation": "sum"
},
"ib_xmit": {
"frequency": 60,
"aggregation": "sum"
},
"ib_recv_pkts": {
"frequency": 60,
"aggregation": "sum"
},
"ib_xmit_pkts": {
"frequency": 60,
"aggregation": "sum"
},
"cpu_power": {
"frequency": 60,
"aggregation": "sum"
},
"core_power": {
"frequency": 60,
"aggregation": "sum"
},
"mem_power": {
"frequency": 60,
"aggregation": "sum"
},
"ipc": {
"frequency": 60,
"aggregation": "avg"
},
"cpu_load": {
"frequency": 60,
"aggregation": null
},
"lustre_close": {
"frequency": 60,
"aggregation": null
},
"lustre_open": {
"frequency": 60,
"aggregation": null
},
"lustre_statfs": {
"frequency": 60,
"aggregation": null
},
"lustre_read_bytes": {
"frequency": 60,
"aggregation": null
},
"lustre_write_bytes": {
"frequency": 60,
"aggregation": null
},
"net_bw": {
"frequency": 60,
"aggregation": null
},
"file_bw": {
"frequency": 60,
"aggregation": null
},
"mem_bw": {
"frequency": 60,
"aggregation": "sum"
},
"mem_cached": {
"frequency": 60,
"aggregation": null
},
"mem_used": {
"frequency": 60,
"aggregation": null
},
"net_bytes_in": {
"frequency": 60,
"aggregation": null
},
"net_bytes_out": {
"frequency": 60,
"aggregation": null
},
"nfs4_read": {
"frequency": 60,
"aggregation": null
},
"nfs4_total": {
"frequency": 60,
"aggregation": null
},
"nfs4_write": {
"frequency": 60,
"aggregation": null
},
"vectorization_ratio": {
"frequency": 60,
"aggregation": "avg"
}
},
"checkpoints": {
"interval": "12h",
"directory": "/opt/monitoring/cc-metric-store/fritz/checkpoints",
"restore": "48h"
},
"archive": {
"interval": "50h",
"directory": "/opt/monitoring/cc-metric-store/fritz/archive"
},
"http-api": {
"address": "0.0.0.0:8082",
"https-cert-file": null,
"https-key-file": null
},
"retention-in-memory": "48h",
"jwt-public-key": "-"
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,357 +1,261 @@
{ {
"name": "meggie", "name": "meggie",
"metricConfig": [ "metricConfig": [
{ {
"name": "cpu_load", "name": "cpu_load",
"unit": { "unit": {
"base": "load" "base": "load"
}, },
"scope": "node", "scope": "node",
"aggregation": "avg", "aggregation": "avg",
"footprint": "avg", "footprint": "avg",
"timestep": 60, "timestep": 60,
"peak": 40, "peak": 40,
"normal": 20, "normal": 20,
"caution": 15, "caution": 15,
"alert": 10 "alert": 10
},
{
"name": "mem_used",
"unit": {
"base": "B",
"prefix": "G"
},
"scope": "node",
"aggregation": "sum",
"footprint": "max",
"timestep": 60,
"peak": 64,
"normal": 20,
"caution": 40,
"alert": 55
},
{
"name": "flops_any",
"unit": {
"base": "Flops/s",
"prefix": "G"
},
"scope": "node",
"aggregation": "sum",
"footprint": "avg",
"timestep": 60,
"peak": 1536,
"normal": 200,
"caution": 40,
"alert": 4
},
{
"name": "flops_sp",
"unit": {
"base": "Flops/s",
"prefix": "G"
},
"scope": "node",
"aggregation": "sum",
"timestep": 60,
"peak": 1536,
"normal": 100,
"caution": 20,
"alert": 2
},
{
"name": "flops_dp",
"unit": {
"base": "Flops/s",
"prefix": "G"
},
"scope": "node",
"aggregation": "sum",
"timestep": 60,
"peak": 768,
"normal": 50,
"caution": 10,
"alert": 2
},
{
"name": "mem_bw",
"unit": {
"base": "B/s",
"prefix": "G"
},
"scope": "node",
"aggregation": "sum",
"footprint": "avg",
"timestep": 60,
"peak": 140,
"normal": 70,
"caution": 20,
"alert": 5
},
{
"name": "clock",
"unit": {
"base": "Hz",
"prefix": "M"
},
"scope": "node",
"aggregation": "avg",
"timestep": 60,
"peak": 3000,
"normal": 2400,
"caution": 1800,
"alert": 1200
},
{
"name": "cpu_power",
"unit": {
"base": "W"
},
"scope": "socket",
"aggregation": "sum",
"energy": "power",
"timestep": 60,
"peak": 80,
"normal": 30,
"caution": 10,
"alert": 5
},
{
"name": "mem_power",
"unit": {
"base": "W"
},
"scope": "socket",
"aggregation": "sum",
"energy": "power",
"timestep": 60,
"peak": 100,
"normal": 50,
"caution": 20,
"alert": 10
},
{
"name": "ipc",
"unit": {
"base": "IPC"
},
"scope": "node",
"aggregation": "avg",
"timestep": 60,
"peak": 4,
"normal": 2,
"caution": 1,
"alert": 0.5
},
{
"name": "vectorization_ratio",
"unit": {
"base": ""
},
"scope": "hwthread",
"aggregation": "avg",
"timestep": 60,
"peak": 100,
"normal": 60,
"caution": 40,
"alert": 10
},
{
"name": "nfs4_read",
"unit": {
"base": "IOP",
"prefix": ""
},
"scope": "node",
"aggregation": "sum",
"timestep": 60,
"peak": 6,
"normal": 4,
"caution": 2,
"alert": 1
},
{
"name": "nfs4_total",
"unit": {
"base": "IOP",
"prefix": ""
},
"scope": "node",
"aggregation": "sum",
"timestep": 60,
"peak": 6,
"normal": 4,
"caution": 2,
"alert": 1
}
],
"subClusters": [
{
"name": "main",
"nodes": "m[0101-0164,0201-0264,0301-0364,0401-0464,0601-0676,0701-0776,0801-0872,0901-0972,1001-1072,1101-1172]",
"processorType": "Intel Broadwell",
"socketsPerNode": 2,
"coresPerSocket": 10,
"threadsPerCore": 1,
"flopRateScalar": {
"unit": {
"base": "F/s",
"prefix": "G"
}, },
"value": 96 {
}, "name": "mem_used",
"flopRateSimd": { "unit": {
"unit": { "base": "B",
"base": "F/s", "prefix": "G"
"prefix": "G" },
"scope": "node",
"aggregation": "sum",
"footprint": "max",
"timestep": 60,
"peak": 64,
"normal": 20,
"caution": 40,
"alert": 55
}, },
"value": 1536 {
}, "name": "flops_any",
"memoryBandwidth": { "unit": {
"unit": { "base": "Flops/s",
"base": "B/s", "prefix": "G"
"prefix": "G" },
"scope": "node",
"aggregation": "sum",
"footprint": "avg",
"timestep": 60,
"peak": 1536,
"normal": 200,
"caution": 40,
"alert": 4
}, },
"value": 140 {
}, "name": "flops_sp",
"topology": { "unit": {
"node": [ "base": "Flops/s",
0, "prefix": "G"
1, },
2, "scope": "node",
3, "aggregation": "sum",
4, "timestep": 60,
5, "peak": 1536,
6, "normal": 100,
7, "caution": 20,
8, "alert": 2
9, },
10, {
11, "name": "flops_dp",
12, "unit": {
13, "base": "Flops/s",
14, "prefix": "G"
15, },
16, "scope": "node",
17, "aggregation": "sum",
18, "timestep": 60,
19 "peak": 768,
], "normal": 50,
"socket": [ "caution": 10,
[ "alert": 2
0, },
1, {
2, "name": "net_bytes_in",
3, "unit": {
4, "base": "B/s"
5, },
6, "scope": "node",
7, "aggregation": "sum",
8, "timestep": 60,
9 "peak": 50000000,
], "normal": 10000000,
[ "caution": 5000,
10, "alert": 1000
11, },
12, {
13, "name": "net_bytes_out",
14, "unit": {
15, "base": "B/s"
16, },
17, "scope": "node",
18, "aggregation": "sum",
19 "timestep": 60,
] "peak": 50000000,
], "normal": 200000,
"memoryDomain": [ "caution": 5000,
[ "alert": 1000
0, },
1, {
2, "name": "mem_bw",
3, "unit": {
4, "base": "B/s",
5, "prefix": "G"
6, },
7, "scope": "node",
8, "aggregation": "sum",
9 "footprint": "avg",
], "timestep": 60,
[ "peak": 140,
10, "normal": 70,
11, "caution": 20,
12, "alert": 5
13, },
14, {
15, "name": "clock",
16, "unit": {
17, "base": "Hz",
18, "prefix": "M"
19 },
] "scope": "node",
], "aggregation": "avg",
"core": [ "timestep": 60,
[ "peak": 3000,
0 "normal": 2400,
], "caution": 1800,
[ "alert": 1200
1 },
], {
[ "name": "cpu_power",
2 "unit": {
], "base": "W"
[ },
3 "scope": "socket",
], "aggregation": "sum",
[ "energy": "power",
4 "timestep": 60,
], "peak": 80,
[ "normal": 30,
5 "caution": 10,
], "alert": 5
[ },
6 {
], "name": "mem_power",
[ "unit": {
7 "base": "W"
], },
[ "scope": "socket",
8 "aggregation": "sum",
], "energy": "power",
[ "timestep": 60,
9 "peak": 100,
], "normal": 50,
[ "caution": 20,
10 "alert": 10
], },
[ {
11 "name": "ipc",
], "unit": {
[ "base": "IPC"
12 },
], "scope": "node",
[ "aggregation": "avg",
13 "timestep": 60,
], "peak": 4,
[ "normal": 2,
14 "caution": 1,
], "alert": 0.5
[ },
15 {
], "name": "vectorization_ratio",
[ "unit": {
16 "base": ""
], },
[ "scope": "hwthread",
17 "aggregation": "avg",
], "timestep": 60,
[ "peak": 100,
18 "normal": 60,
], "caution": 40,
[ "alert": 10
19 },
] {
] "name": "nfs4_read",
} "unit": {
} "base": "IOP",
] "prefix": ""
},
"scope": "node",
"aggregation": "sum",
"timestep": 60,
"peak": 50000,
"normal": 10000,
"caution": 10,
"alert": 1
},
{
"name": "nfs4_total",
"unit": {
"base": "IOP",
"prefix": ""
},
"scope": "node",
"aggregation": "sum",
"timestep": 60,
"peak": 50000,
"normal": 10000,
"caution": 20,
"alert": 5
}
],
"subClusters": [
{
"name": "main",
"nodes": "m[0101-0164,0201-0264,0301-0364,0401-0464,0601-0676,0701-0776,0801-0872,0901-0972,1001-1072,1101-1172]",
"processorType": "Intel Broadwell",
"socketsPerNode": 2,
"coresPerSocket": 10,
"threadsPerCore": 1,
"flopRateScalar": {
"unit": {
"base": "F/s",
"prefix": "G"
},
"value": 96
},
"flopRateSimd": {
"unit": {
"base": "F/s",
"prefix": "G"
},
"value": 1536
},
"memoryBandwidth": {
"unit": {
"base": "B/s",
"prefix": "G"
},
"value": 140
},
"topology": {
"node": [
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19
],
"socket": [
[ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 ],
[ 10, 11, 12, 13, 14, 15, 16, 17, 18, 19 ]
],
"memoryDomain": [
[ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 ],
[ 10, 11, 12, 13, 14, 15, 16, 17, 18, 19 ]
],
"core": [
[ 0 ], [ 1 ], [ 2 ], [ 3 ], [ 4 ], [ 5 ], [ 6 ], [ 7 ], [ 8 ], [ 9 ], [ 10 ], [ 11 ], [ 12 ], [ 13 ], [ 14 ], [ 15 ], [ 16 ], [ 17 ], [ 18 ], [ 19 ]
]
}
}
]
} }

View File

@@ -178,9 +178,9 @@
"scope": "node", "scope": "node",
"aggregation": "sum", "aggregation": "sum",
"timestep": 60, "timestep": 60,
"peak": 6, "peak": 50000,
"normal": 4, "normal": 10000,
"caution": 2, "caution": 10,
"alert": 1 "alert": 1
}, },
{ {
@@ -192,9 +192,9 @@
"scope": "node", "scope": "node",
"aggregation": "sum", "aggregation": "sum",
"timestep": 60, "timestep": 60,
"peak": 6, "peak": 50000,
"normal": 4, "normal": 10000,
"caution": 2, "caution": 10,
"alert": 1 "alert": 1
}, },
{ {
@@ -206,10 +206,10 @@
"scope": "node", "scope": "node",
"aggregation": "sum", "aggregation": "sum",
"timestep": 60, "timestep": 60,
"peak": 6, "peak": 50000,
"normal": 4, "normal": 10000,
"caution": 2, "caution": 20,
"alert": 1 "alert": 5
} }
], ],
"subClusters": [ "subClusters": [

View File

@@ -86,6 +86,32 @@
"caution": 100, "caution": 100,
"alert": 50 "alert": 50
}, },
{
"name": "net_bytes_in",
"unit": {
"base": "B/s"
},
"scope": "node",
"aggregation": "sum",
"timestep": 60,
"peak": 50000000,
"normal": 10000000,
"caution": 5000,
"alert": 1000
},
{
"name": "net_bytes_out",
"unit": {
"base": "B/s"
},
"scope": "node",
"aggregation": "sum",
"timestep": 60,
"peak": 50000000,
"normal": 200000,
"caution": 5000,
"alert": 1000
},
{ {
"name": "mem_bw", "name": "mem_bw",
"unit": { "unit": {
@@ -197,14 +223,14 @@
"caution": 10000, "caution": 10000,
"alert": 5000, "alert": 5000,
"subClusters": [ "subClusters": [
{ {
"name": "a100", "name": "a100",
"peak": 160000, "peak": 160000,
"normal": 120000, "normal": 120000,
"caution": 80000, "caution": 80000,
"alert": 40000 "alert": 40000
}, },
{ {
"name": "v100", "name": "v100",
"peak": 128000, "peak": 128000,
"normal": 96000, "normal": 96000,
@@ -234,6 +260,7 @@
}, },
"scope": "accelerator", "scope": "accelerator",
"aggregation": "sum", "aggregation": "sum",
"energy": "power",
"timestep": 60, "timestep": 60,
"peak": 400, "peak": 400,
"normal": 200, "normal": 200,
@@ -290,9 +317,9 @@
"scope": "node", "scope": "node",
"aggregation": "sum", "aggregation": "sum",
"timestep": 60, "timestep": 60,
"peak": 6, "peak": 50000,
"normal": 4, "normal": 10000,
"caution": 2, "caution": 10,
"alert": 1 "alert": 1
}, },
{ {
@@ -304,9 +331,9 @@
"scope": "node", "scope": "node",
"aggregation": "sum", "aggregation": "sum",
"timestep": 60, "timestep": 60,
"peak": 6, "peak": 50000,
"normal": 4, "normal": 10000,
"caution": 2, "caution": 10,
"alert": 1 "alert": 1
}, },
{ {
@@ -318,10 +345,10 @@
"scope": "node", "scope": "node",
"aggregation": "sum", "aggregation": "sum",
"timestep": 60, "timestep": 60,
"peak": 6, "peak": 50000,
"normal": 4, "normal": 10000,
"caution": 2, "caution": 20,
"alert": 1 "alert": 5
} }
], ],
"subClusters": [ "subClusters": [

File diff suppressed because it is too large Load Diff