github
/
node_exporter
mirror of https://github.com/prometheus/node_exporter
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

Merge pull request #2351 from grafana/vzhuravlev/macos 

Add darwin dashboard
pull/2365/head
Björn Rabenstein 3 years ago committed by GitHub
parent
5ea0a936cb 410e069471
commit
b5a2ad46e3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 358 additions and 263 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 255
      docs/node-mixin/dashboards/node.libsonnet
  2. 13
      docs/node-mixin/jsonnetfile.json
  3. 353
      docs/node-mixin/lib/prom-mixin.libsonnet

255
docs/node-mixin/dashboards/node.libsonnet
Unescape View File

@ -1,256 +1,7 @@
local grafana = import 'github.com/grafana/grafonnet-lib/grafonnet/grafana.libsonnet';
local dashboard = grafana.dashboard;
local row = grafana.row;
local prometheus = grafana.prometheus;
local template = grafana.template;
local graphPanel = grafana.graphPanel;
local promgrafonnet = import 'github.com/kubernetes-monitoring/kubernetes-mixin/lib/promgrafonnet/promgrafonnet.libsonnet';
local gauge = promgrafonnet.gauge;
{ {
local nodemixin = import '../lib/prom-mixin.libsonnet',
grafanaDashboards+:: { grafanaDashboards+:: {
'nodes.json': 'nodes.json': nodemixin.new(config=$._config, platform='Linux').dashboard,
local idleCPU = 'nodes-darwin.json': nodemixin.new(config=$._config, platform='Darwin').dashboard,
graphPanel.new(
'CPU Usage',
datasource='$datasource',
span=6,
format='percentunit',
max=1,
min=0,
stack=true,
)
.addTarget(prometheus.target(
|||
(
(1 - sum without (mode) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode=~"idle|iowait|steal", instance="$instance"}[$__rate_interval])))
/ ignoring(cpu) group_left
count without (cpu, mode) (node_cpu_seconds_total{%(nodeExporterSelector)s, mode="idle", instance="$instance"})
)
||| % $._config,
legendFormat='{{cpu}}',
intervalFactor=5,
));
local systemLoad =
graphPanel.new(
'Load Average',
datasource='$datasource',
span=6,
format='short',
min=0,
fill=0,
)
.addTarget(prometheus.target('node_load1{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='1m load average'))
.addTarget(prometheus.target('node_load5{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='5m load average'))
.addTarget(prometheus.target('node_load15{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='15m load average'))
.addTarget(prometheus.target('count(node_cpu_seconds_total{%(nodeExporterSelector)s, instance="$instance", mode="idle"})' % $._config, legendFormat='logical cores'));
local memoryGraph =
graphPanel.new(
'Memory Usage',
datasource='$datasource',
span=9,
format='bytes',
stack=true,
min=0,
)
.addTarget(prometheus.target(
|||
(
node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance"}
-
node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance"}
-
node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance"}
-
node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance"}
)
||| % $._config, legendFormat='memory used'
))
.addTarget(prometheus.target('node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='memory buffers'))
.addTarget(prometheus.target('node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='memory cached'))
.addTarget(prometheus.target('node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='memory free'));
// TODO: It would be nicer to have a gauge that gets a 0-1 range and displays it as a percentage 0%-100%.
// This needs to be added upstream in the promgrafonnet library and then changed here.
// NOTE: avg() is used to circumvent a label change caused by a node_exporter rollout.
local memoryGauge = gauge.new(
'Memory Usage',
|||
100 -
(
avg(node_memory_MemAvailable_bytes{%(nodeExporterSelector)s, instance="$instance"})
/
avg(node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance"})
* 100
)
||| % $._config,
).withLowerBeingBetter();
local diskIO =
graphPanel.new(
'Disk I/O',
datasource='$datasource',
span=6,
min=0,
fill=0,
)
// TODO: Does it make sense to have those three in the same panel?
.addTarget(prometheus.target(
'rate(node_disk_read_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(diskDeviceSelector)s}[$__rate_interval])' % $._config,
legendFormat='{{device}} read',
))
.addTarget(prometheus.target(
'rate(node_disk_written_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(diskDeviceSelector)s}[$__rate_interval])' % $._config,
legendFormat='{{device}} written',
))
.addTarget(prometheus.target(
'rate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(diskDeviceSelector)s}[$__rate_interval])' % $._config,
legendFormat='{{device}} io time',
)) +
{
seriesOverrides: [
{
alias: '/ read| written/',
yaxis: 1,
},
{
alias: '/ io time/',
yaxis: 2,
},
],
yaxes: [
self.yaxe(format='bytes'),
self.yaxe(format='s'),
],
};
// TODO: Somehow partition this by device while excluding read-only devices.
local diskSpaceUsage =
graphPanel.new(
'Disk Space Usage',
datasource='$datasource',
span=6,
format='bytes',
min=0,
fill=1,
stack=true,
)
.addTarget(prometheus.target(
|||
sum(
max by (device) (
node_filesystem_size_bytes{%(nodeExporterSelector)s, instance="$instance", %(fsSelector)s}
-
node_filesystem_avail_bytes{%(nodeExporterSelector)s, instance="$instance", %(fsSelector)s}
)
)
||| % $._config,
legendFormat='used',
))
.addTarget(prometheus.target(
|||
sum(
max by (device) (
node_filesystem_avail_bytes{%(nodeExporterSelector)s, instance="$instance", %(fsSelector)s}
)
)
||| % $._config,
legendFormat='available',
)) +
{
seriesOverrides: [
{
alias: 'used',
color: '#E0B400',
},
{
alias: 'available',
color: '#73BF69',
},
],
};
local networkReceived =
graphPanel.new(
'Network Received',
datasource='$datasource',
span=6,
format='bytes',
min=0,
fill=0,
)
.addTarget(prometheus.target(
'rate(node_network_receive_bytes_total{%(nodeExporterSelector)s, instance="$instance", device!="lo"}[$__rate_interval])' % $._config,
legendFormat='{{device}}',
));
local networkTransmitted =
graphPanel.new(
'Network Transmitted',
datasource='$datasource',
span=6,
format='bytes',
min=0,
fill=0,
)
.addTarget(prometheus.target(
'rate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, instance="$instance", device!="lo"}[$__rate_interval])' % $._config,
legendFormat='{{device}}',
));
dashboard.new(
'%sNodes' % $._config.dashboardNamePrefix,
time_from='now-1h',
tags=($._config.dashboardTags),
timezone='utc',
refresh='30s',
graphTooltip='shared_crosshair'
)
.addTemplate(
{
current: {
text: 'default',
value: 'default',
},
hide: 0,
label: 'Data Source',
name: 'datasource',
options: [],
query: 'prometheus',
refresh: 1,
regex: '',
type: 'datasource',
},
)
.addTemplate(
template.new(
'instance',
'$datasource',
'label_values(node_exporter_build_info{%(nodeExporterSelector)s}, instance)' % $._config,
refresh='time',
)
)
.addRow(
row.new()
.addPanel(idleCPU)
.addPanel(systemLoad)
)
.addRow(
row.new()
.addPanel(memoryGraph)
.addPanel(memoryGauge)
)
.addRow(
row.new()
.addPanel(diskIO)
.addPanel(diskSpaceUsage)
)
.addRow(
row.new()
.addPanel(networkReceived)
.addPanel(networkTransmitted)
),
}, },
} }

13
docs/node-mixin/jsonnetfile.json
Unescape View File

@ -13,17 +13,8 @@
{ {
"source": { "source": {
"git": { "git": {
"remote": "https://github.com/grafana/jsonnet-libs.git", "remote": "https://github.com/grafana/grafonnet-lib.git",
"subdir": "grafana-builder" "subdir": "grafonnet-7.0"
}
},
"version": "master"
},
{
"source": {
"git": {
"remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin.git",
"subdir": "lib/promgrafonnet"
} }
}, },
"version": "master" "version": "master"

353
docs/node-mixin/lib/prom-mixin.libsonnet
Unescape View File

@ -0,0 +1,353 @@
local grafana = import 'github.com/grafana/grafonnet-lib/grafonnet/grafana.libsonnet';
local dashboard = grafana.dashboard;
local row = grafana.row;
local prometheus = grafana.prometheus;
local template = grafana.template;
local graphPanel = grafana.graphPanel;
local grafana70 = import 'github.com/grafana/grafonnet-lib/grafonnet-7.0/grafana.libsonnet';
local gaugePanel = grafana70.panel.gauge;
{
new(config=null, platform=null):: {
local prometheusDatasourceTemplate = {
current: {
text: 'default',
value: 'default',
},
hide: 0,
label: 'Data Source',
name: 'datasource',
options: [],
query: 'prometheus',
refresh: 1,
regex: '',
type: 'datasource',
},
local instanceTemplatePrototype =
template.new(
'instance',
'$datasource',
'',
refresh='time',
label='Instance',
),
local instanceTemplate =
if platform == 'Darwin' then
instanceTemplatePrototype
{ query: 'label_values(node_uname_info{%(nodeExporterSelector)s, sysname="Darwin"}, instance)' % config }
else
instanceTemplatePrototype
{ query: 'label_values(node_uname_info{%(nodeExporterSelector)s, sysname!="Darwin"}, instance)' % config },
local idleCPU =
graphPanel.new(
'CPU Usage',
datasource='$datasource',
span=6,
format='percentunit',
max=1,
min=0,
stack=true,
)
.addTarget(prometheus.target(
|||
(
(1 - sum without (mode) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode=~"idle|iowait|steal", instance="$instance"}[$__rate_interval])))
/ ignoring(cpu) group_left
count without (cpu, mode) (node_cpu_seconds_total{%(nodeExporterSelector)s, mode="idle", instance="$instance"})
)
||| % config,
legendFormat='{{cpu}}',
intervalFactor=5,
)),
local systemLoad =
graphPanel.new(
'Load Average',
datasource='$datasource',
span=6,
format='short',
min=0,
fill=0,
)
.addTarget(prometheus.target('node_load1{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='1m load average'))
.addTarget(prometheus.target('node_load5{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='5m load average'))
.addTarget(prometheus.target('node_load15{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='15m load average'))
.addTarget(prometheus.target('count(node_cpu_seconds_total{%(nodeExporterSelector)s, instance="$instance", mode="idle"})' % config, legendFormat='logical cores')),
local memoryGraphPanelPrototype =
graphPanel.new(
'Memory Usage',
datasource='$datasource',
span=9,
format='bytes',
min=0,
),
local memoryGraph =
if platform == 'Linux' then
memoryGraphPanelPrototype { stack: true }
.addTarget(prometheus.target(
|||
(
node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance"}
-
node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance"}
-
node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance"}
-
node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance"}
)
||| % config,
legendFormat='memory used'
))
.addTarget(prometheus.target('node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='memory buffers'))
.addTarget(prometheus.target('node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='memory cached'))
.addTarget(prometheus.target('node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='memory free'))
else if platform == 'Darwin' then
// not useful to stack
memoryGraphPanelPrototype { stack: false }
.addTarget(prometheus.target('node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='Physical Memory'))
.addTarget(prometheus.target(
|||
(
node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance"} -
node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance"} +
node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance"} +
node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance"}
)
||| % config, legendFormat='Memory Used'
))
.addTarget(prometheus.target(
|||
(
node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance"} -
node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance"}
)
||| % config, legendFormat='App Memory'
))
.addTarget(prometheus.target('node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='Wired Memory'))
.addTarget(prometheus.target('node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance"}' % config, legendFormat='Compressed')),
// NOTE: avg() is used to circumvent a label change caused by a node_exporter rollout.
local memoryGaugePanelPrototype =
gaugePanel.new(
title='Memory Usage',
datasource='$datasource',
)
.addThresholdStep('rgba(50, 172, 45, 0.97)')
.addThresholdStep('rgba(237, 129, 40, 0.89)', 80)
.addThresholdStep('rgba(245, 54, 54, 0.9)', 90)
.setFieldConfig(max=100, min=0, unit='percent')
+ {
span: 3,
},
local memoryGauge =
if platform == 'Linux' then
memoryGaugePanelPrototype
.addTarget(prometheus.target(
|||
100 -
(
avg(node_memory_MemAvailable_bytes{%(nodeExporterSelector)s, instance="$instance"}) /
avg(node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance"})
* 100
)
||| % config,
))
else if platform == 'Darwin' then
memoryGaugePanelPrototype
.addTarget(prometheus.target(
|||
(
(
avg(node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance"}) -
avg(node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance"}) +
avg(node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance"}) +
avg(node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance"})
) /
avg(node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance"})
)
*
100
||| % config
)),
local diskIO =
graphPanel.new(
'Disk I/O',
datasource='$datasource',
span=6,
min=0,
fill=0,
)
// TODO: Does it make sense to have those three in the same panel?
.addTarget(prometheus.target(
'rate(node_disk_read_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(diskDeviceSelector)s}[$__rate_interval])' % config,
legendFormat='{{device}} read',
))
.addTarget(prometheus.target(
'rate(node_disk_written_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(diskDeviceSelector)s}[$__rate_interval])' % config,
legendFormat='{{device}} written',
))
.addTarget(prometheus.target(
'rate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(diskDeviceSelector)s}[$__rate_interval])' % config,
legendFormat='{{device}} io time',
)) +
{
seriesOverrides: [
{
alias: '/ read| written/',
yaxis: 1,
},
{
alias: '/ io time/',
yaxis: 2,
},
],
yaxes: [
self.yaxe(format='bytes'),
self.yaxe(format='s'),
],
},
// TODO: Somehow partition this by device while excluding read-only devices.
local diskSpaceUsage =
graphPanel.new(
'Disk Space Usage',
datasource='$datasource',
span=6,
format='bytes',
min=0,
fill=1,
stack=true,
)
.addTarget(prometheus.target(
|||
sum(
max by (device) (
node_filesystem_size_bytes{%(nodeExporterSelector)s, instance="$instance", %(fsSelector)s}
-
node_filesystem_avail_bytes{%(nodeExporterSelector)s, instance="$instance", %(fsSelector)s}
)
)
||| % config,
legendFormat='used',
))
.addTarget(prometheus.target(
|||
sum(
max by (device) (
node_filesystem_avail_bytes{%(nodeExporterSelector)s, instance="$instance", %(fsSelector)s}
)
)
||| % config,
legendFormat='available',
)) +
{
seriesOverrides: [
{
alias: 'used',
color: '#E0B400',
},
{
alias: 'available',
color: '#73BF69',
},
],
},
local networkReceived =
graphPanel.new(
'Network Received',
datasource='$datasource',
span=6,
format='bytes',
min=0,
fill=0,
)
.addTarget(prometheus.target(
'rate(node_network_receive_bytes_total{%(nodeExporterSelector)s, instance="$instance", device!="lo"}[$__rate_interval])' % config,
legendFormat='{{device}}',
)),
local networkTransmitted =
graphPanel.new(
'Network Transmitted',
datasource='$datasource',
span=6,
format='bytes',
min=0,
fill=0,
)
.addTarget(prometheus.target(
'rate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, instance="$instance", device!="lo"}[$__rate_interval])' % config,
legendFormat='{{device}}',
)),
local cpuRow =
row.new('CPU')
.addPanel(idleCPU)
.addPanel(systemLoad),
local memoryRow =
row.new('Memory')
.addPanel(memoryGraph)
.addPanel(memoryGauge),
local diskRow =
row.new('Disk')
.addPanel(diskIO)
.addPanel(diskSpaceUsage),
local networkRow =
row.new('Network')
.addPanel(networkReceived)
.addPanel(networkTransmitted),
local rows =
[
cpuRow,
memoryRow,
diskRow,
networkRow,
],
local templates =
[
prometheusDatasourceTemplate,
instanceTemplate,
],
dashboard: if platform == 'Linux' then
dashboard.new(
'%sNodes' % config.dashboardNamePrefix,
time_from='now-1h',
tags=(config.dashboardTags),
timezone='utc',
refresh='30s',
graphTooltip='shared_crosshair'
)
.addTemplates(templates)
.addRows(rows)
else if platform == 'Darwin' then
dashboard.new(
'%sMacOS' % config.dashboardNamePrefix,
time_from='now-1h',
tags=(config.dashboardTags),
timezone='utc',
refresh='30s',
graphTooltip='shared_crosshair'
)
.addTemplates(templates)
.addRows(rows),
},
}
Write Preview
Loading…
Cancel
Save