Temp collector from sysfs hwmon (#8)

* Add collector for hwmon temperature

* Comment out local tag overrides

* Add temperature collector to README

* Update temperature collector with own config parser
This commit is contained in:
Thomas Gruber
2021-11-25 18:19:09 +01:00
committed by GitHub
parent 1e7a75598e
commit 3997984714
4 changed files with 125 additions and 103 deletions

View File

@@ -11,16 +11,7 @@
"interval": 3,
"duration": 1,
"collectors": [
"loadavg",
"likwid",
"memstat",
"netstat",
"ibstat",
"lustrestat",
"cpustat",
"topprocs",
"nvidia",
"diskstat"
"tempstat"
],
"default_tags": {
"cluster": "testcluster"
@@ -29,101 +20,17 @@
"type": "none"
},
"collect_config": {
"netstat": {
"exclude_devices": [
"enp195s0f1",
"lo"
]
},
"ibstat": {
"exclude_devices": [
"mlx5_0",
"mlx5_1"
]
},
"likwid": {
"accessmode" : "accessdaemon",
"daemon_path" : "/apps/likwid/5.2.0/sbin",
"eventsets": [
{
"events": {
"FIXC1": "ACTUAL_CPU_CLOCK",
"FIXC2": "MAX_CPU_CLOCK",
"PMC0": "RETIRED_INSTRUCTIONS",
"PMC1": "CPU_CLOCKS_UNHALTED",
"PMC2": "RETIRED_SSE_AVX_FLOPS_ALL",
"PMC3": "MERGE",
"DFC0": "DRAM_CHANNEL_0",
"DFC1": "DRAM_CHANNEL_1",
"DFC2": "DRAM_CHANNEL_2",
"DFC3": "DRAM_CHANNEL_3"
},
"metrics": [
{
"name": "ipc",
"calc": "PMC0/PMC1",
"socket_scope": false,
"publish": true
},
{
"name": "flops_any",
"calc": "0.000001*PMC2/time",
"socket_scope": false,
"publish": true
},
{
"name": "clock_mhz",
"calc": "0.000001*(FIXC1/FIXC2)/inverseClock",
"socket_scope": false,
"publish": true
},
{
"name": "mem1",
"calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
"socket_scope": true,
"publish": false
}
]
"tempstat": {
"tag_override": {
"hwmon0" : {
"type" : "socket",
"type-id" : "0"
},
{
"events": {
"DFC0": "DRAM_CHANNEL_4",
"DFC1": "DRAM_CHANNEL_5",
"DFC2": "DRAM_CHANNEL_6",
"DFC3": "DRAM_CHANNEL_7",
"PWR0": "RAPL_CORE_ENERGY",
"PWR1": "RAPL_PKG_ENERGY"
},
"metrics": [
{
"name": "pwr_core",
"calc": "PWR0/time",
"socket_scope": false,
"publish": true
},
{
"name": "pwr_pkg",
"calc": "PWR1/time",
"socket_scope": true,
"publish": true
},
{
"name": "mem2",
"calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
"socket_scope": true,
"publish": false
}
]
"hwmon1" : {
"type" : "socket",
"type-id" : "1"
}
],
"globalmetrics": [
{
"name": "mem_bw",
"calc": "mem1+mem2",
"socket_scope": true,
"publish": true
}
]
}
}
}
}