Move node-mixin into docs directory

Signed-off-by: beorn7 <beorn@grafana.com>
This commit is contained in:
beorn7 2019-07-05 19:38:03 +02:00
commit 2df034c055
12 changed files with 0 additions and 0 deletions

View file

@ -0,0 +1,2 @@
(import 'node.libsonnet') +
(import 'use.libsonnet')

View file

@ -0,0 +1,170 @@
local grafana = import '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 '../lib/promgrafonnet/promgrafonnet.libsonnet';
local gauge = promgrafonnet.gauge;
{
grafanaDashboards+:: {
'nodes.json':
local idleCPU =
graphPanel.new(
'Idle CPU',
datasource='$datasource',
span=6,
format='percentunit',
max=100,
min=0,
)
.addTarget(prometheus.target(
|||
1 - avg by (cpu) (irate(node_cpu{%(nodeExporterSelector)s, mode="idle", instance="$instance"}[1m]))
||| % $._config,
legendFormat='{{cpu}}',
intervalFactor=10,
));
local systemLoad =
graphPanel.new(
'System load',
datasource='$datasource',
span=6,
format='percentunit',
)
.addTarget(prometheus.target('node_load1{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='load 1m'))
.addTarget(prometheus.target('node_load5{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='load 5m'))
.addTarget(prometheus.target('node_load15{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='load 15m'));
local memoryGraph =
graphPanel.new(
'Memory Usage',
datasource='$datasource',
span=9,
format='bytes',
)
.addTarget(prometheus.target(
|||
node_memory_MemTotal{%(nodeExporterSelector)s, instance="$instance"}
- node_memory_MemFree{%(nodeExporterSelector)s, instance="$instance"}
- node_memory_Buffers{%(nodeExporterSelector)s, instance="$instance"}
- node_memory_Cached{%(nodeExporterSelector)s, instance="$instance"}
||| % $._config, legendFormat='memory used'
))
.addTarget(prometheus.target('node_memory_Buffers{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='memory buffers'))
.addTarget(prometheus.target('node_memory_Cached{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='memory cached'))
.addTarget(prometheus.target('node_memory_MemFree{%(nodeExporterSelector)s, instance="$instance"}' % $._config, legendFormat='memory free'));
local memoryGauge = gauge.new(
'Memory Usage',
|||
node_memory_MemAvailable{%(nodeExporterSelector)s, instance="$instance"}
/
node_memory_MemTotal{%(nodeExporterSelector)s, instance="$instance"}
||| % $._config,
).withLowerBeingBetter();
local diskIO =
graphPanel.new(
'Disk I/O',
datasource='$datasource',
span=9,
)
.addTarget(prometheus.target('sum by (instance) (irate(node_disk_bytes_read_total{%(nodeExporterSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='read'))
.addTarget(prometheus.target('sum by (instance) (irate(node_disk_bytes_written_total{%(nodeExporterSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='written'))
.addTarget(prometheus.target('sum by (instance) (irate(node_disk_io_time_ms{%(nodeExporterSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='io time')) +
{
seriesOverrides: [
{
alias: 'read',
yaxis: 1,
},
{
alias: 'io time',
yaxis: 2,
},
],
yaxes: [
self.yaxe(format='bytes'),
self.yaxe(format='ms'),
],
};
local diskSpaceUsage = gauge.new(
'Disk Space Usage',
|||
1 - (
sum(node_filesystem_free{%(nodeExporterSelector)s, device!="rootfs", instance="$instance"}
/
sum(node_filesystem_size{%(nodeExporterSelector)s, device!="rootfs", instance="$instance"}
)
||| % $._config,
).withLowerBeingBetter();
local networkReceived =
graphPanel.new(
'Network Received',
datasource='$datasource',
span=6,
format='bytes',
)
.addTarget(prometheus.target('irate(node_network_receive_bytes{%(nodeExporterSelector)s, instance="$instance", device!~"lo"}[1m])' % $._config, legendFormat='{{device}}'));
local networkTransmitted =
graphPanel.new(
'Network Transmitted',
datasource='$datasource',
span=6,
format='bytes',
)
.addTarget(prometheus.target('irate(node_network_transmit_bytes{%(nodeExporterSelector)s, instance="$instance", device!~"lo"}[1m])' % $._config, legendFormat='{{device}}'));
dashboard.new('Nodes', time_from='now-1h')
.addTemplate(
{
current: {
text: 'Prometheus',
value: 'Prometheus',
},
hide: 0,
label: null,
name: 'datasource',
options: [],
query: 'prometheus',
refresh: 1,
regex: '',
type: 'datasource',
},
)
.addTemplate(
template.new(
'instance',
'$datasource',
'label_values(node_boot_time{%(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)
),
},
}

View file

@ -0,0 +1,151 @@
local g = import 'grafana-builder/grafana.libsonnet';
{
grafanaDashboards+:: {
'node-cluster-rsrc-use.json':
local legendLink = '%s/dashboard/file/k8s-node-rsrc-use.json' % $._config.grafana_prefix;
g.dashboard('USE Method / Cluster')
.addRow(
g.row('CPU')
.addPanel(
g.panel('CPU Utilisation') +
g.queryPanel('instance:node_cpu_utilisation:avg1m * instance:node_num_cpu:sum / scalar(sum(instance:node_num_cpu:sum))', '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
)
.addPanel(
g.panel('CPU Saturation (Load1)') +
g.queryPanel(|||
instance:node_cpu_saturation_load1: / scalar(sum(up{%(nodeExporterSelector)s}))
||| % $._config, '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
)
)
.addRow(
g.row('Memory')
.addPanel(
g.panel('Memory Utilisation') +
g.queryPanel('instance:node_memory_utilisation:ratio', '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
)
.addPanel(
g.panel('Memory Saturation (Swap I/O)') +
g.queryPanel('instance:node_memory_swap_io_bytes:sum_rate', '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes('Bps') },
)
)
.addRow(
g.row('Disk')
.addPanel(
g.panel('Disk IO Utilisation') +
// Full utilisation would be all disks on each node spending an average of
// 1 sec per second doing I/O, normalize by node count for stacked charts
g.queryPanel(|||
instance:node_disk_utilisation:sum_irate / scalar(sum(up{%(nodeExporterSelector)s}))
||| % $._config, '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
)
.addPanel(
g.panel('Disk IO Saturation') +
g.queryPanel(|||
instance:node_disk_saturation:sum_irate / scalar(sum(up{%(nodeExporterSelector)s}))
||| % $._config, '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
)
)
.addRow(
g.row('Network')
.addPanel(
g.panel('Net Utilisation (Transmitted)') +
g.queryPanel('instance:node_net_utilisation:sum_irate', '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes('Bps') },
)
.addPanel(
g.panel('Net Saturation (Dropped)') +
g.queryPanel('instance:node_net_saturation:sum_irate', '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes('Bps') },
)
)
.addRow(
g.row('Storage')
.addPanel(
g.panel('Disk Capacity') +
g.queryPanel('sum(max(node_filesystem_size_bytes{fstype=~"ext[24]"} - node_filesystem_free_bytes{fstype=~"ext[24]"}) by (device,instance,namespace)) by (instance,namespace) / scalar(sum(max(node_filesystem_size_bytes{fstype=~"ext[24]"}) by (device,instance,namespace)))', '{{instance}}', legendLink) +
g.stack +
{ yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
),
),
'node-rsrc-use.json':
g.dashboard('USE Method / Node')
.addTemplate('instance', 'up{%(nodeExporterSelector)s}' % $._config, 'instance')
.addRow(
g.row('CPU')
.addPanel(
g.panel('CPU Utilisation') +
g.queryPanel('instance:node_cpu_utilisation:avg1m{instance="$instance"}', 'Utilisation') +
{ yaxes: g.yaxes('percentunit') },
)
.addPanel(
g.panel('CPU Saturation (Load1)') +
g.queryPanel('instance:node_cpu_saturation_load1:{instance="$instance"}', 'Saturation') +
{ yaxes: g.yaxes('percentunit') },
)
)
.addRow(
g.row('Memory')
.addPanel(
g.panel('Memory Utilisation') +
g.queryPanel('instance:node_memory_utilisation:ratio{instance="$instance"}', 'Memory') +
{ yaxes: g.yaxes('percentunit') },
)
.addPanel(
g.panel('Memory Saturation (Swap I/O)') +
g.queryPanel('instance:node_memory_swap_io_bytes:sum_rate{instance="$instance"}', 'Swap IO') +
{ yaxes: g.yaxes('Bps') },
)
)
.addRow(
g.row('Disk')
.addPanel(
g.panel('Disk IO Utilisation') +
g.queryPanel('instance:node_disk_utilisation:sum_irate{instance="$instance"}', 'Utilisation') +
{ yaxes: g.yaxes('percentunit') },
)
.addPanel(
g.panel('Disk IO Saturation') +
g.queryPanel('instance:node_disk_saturation:sum_irate{instance="$instance"}', 'Saturation') +
{ yaxes: g.yaxes('percentunit') },
)
)
.addRow(
g.row('Net')
.addPanel(
g.panel('Net Utilisation (Transmitted)') +
g.queryPanel('instance:node_net_utilisation:sum_irate{instance="$instance"}', 'Utilisation') +
{ yaxes: g.yaxes('Bps') },
)
.addPanel(
g.panel('Net Saturation (Dropped)') +
g.queryPanel('instance:node_net_saturation:sum_irate{instance="$instance"}', 'Saturation') +
{ yaxes: g.yaxes('Bps') },
)
)
.addRow(
g.row('Disk')
.addPanel(
g.panel('Disk Utilisation') +
g.queryPanel('1 - sum(max by (device, node) (node_filesystem_free_bytes{fstype=~"ext[24]"})) / sum(max by (device, node) (node_filesystem_size_bytes{fstype=~"ext[24]"}))', 'Disk') +
{ yaxes: g.yaxes('percentunit') },
),
),
},
}