mirror of
https://github.com/prometheus/node_exporter.git
synced 2024-12-27 14:39:53 -08:00
node-mixin: Fix various straight-forward issues in the USE dashboards
- Normalize cluster memory utilisation. - Fix missing `1m` in memory saturation. - Have both disk-related row next to each other instead with the network row in between. - Correctly render transmit network traffic as negative, using `seriesOverrides` and `min: null` for the y-axis. - Make panel and row naming consistent. - Remove legend where it would just display a single entry with exactly the title of the panel. - Fix metric name in individual node CPU Saturation panel. - Break up disk space utilisation by device in the panel for an individual node. NB: All of that doesn't touch any more subtle issues captured in the various TODOs. Signed-off-by: beorn7 <beorn@grafana.com>
This commit is contained in:
beorn7
parent
697c2deed5
commit
f350aaf87e
|
|
@ -42,19 +42,80 @@ local g = import 'grafana-builder/grafana.libsonnet';
|
||||||
g.row('Memory')
|
g.row('Memory')
|
||||||
.addPanel(
|
.addPanel(
|
||||||
g.panel('Memory Utilisation') +
|
g.panel('Memory Utilisation') +
|
||||||
g.queryPanel('instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s}' % $._config, '{{instance}}', legendLink) +
|
g.queryPanel(|||
|
||||||
|
(
|
||||||
|
instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s}
|
||||||
|
/ ignoring (instance) group_left
|
||||||
|
count without (instance) (instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s})
|
||||||
|
)
|
||||||
|
||| % $._config, '{{instance}}', legendLink) +
|
||||||
g.stack +
|
g.stack +
|
||||||
{ yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
|
{ yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
|
||||||
)
|
)
|
||||||
.addPanel(
|
.addPanel(
|
||||||
g.panel('Memory Saturation (Swapped Pages)') +
|
g.panel('Memory Saturation (Swapped Pages)') +
|
||||||
g.queryPanel('instance:node_memory_swap_io_pages:rate{%(nodeExporterSelector)s}' % $._config, '{{instance}}', legendLink) +
|
g.queryPanel('instance:node_memory_swap_io_pages:rate1m{%(nodeExporterSelector)s}' % $._config, '{{instance}}', legendLink) +
|
||||||
g.stack +
|
g.stack +
|
||||||
{ yaxes: g.yaxes('rps') },
|
{ yaxes: g.yaxes('rps') },
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
.addRow(
|
.addRow(
|
||||||
g.row('Disk')
|
g.row('Network')
|
||||||
|
.addPanel(
|
||||||
|
g.panel('Net Utilisation (Bytes Receive/Transmit)') +
|
||||||
|
g.queryPanel(
|
||||||
|
[
|
||||||
|
'instance:node_network_receive_bytes_excluding_lo:rate1m{%(nodeExporterSelector)s}' % $._config,
|
||||||
|
'instance:node_network_transmit_bytes_excluding_lo:rate1m{%(nodeExporterSelector)s}' % $._config,
|
||||||
|
],
|
||||||
|
['{{instance}} Receive', '{{instance}} Transmit'],
|
||||||
|
legendLink,
|
||||||
|
) +
|
||||||
|
g.stack +
|
||||||
|
{
|
||||||
|
yaxes: g.yaxes({ format: 'Bps', min: null }),
|
||||||
|
seriesOverrides: [
|
||||||
|
{
|
||||||
|
alias: '/ Receive/',
|
||||||
|
stack: 'A',
|
||||||
|
},
|
||||||
|
{
|
||||||
|
alias: '/ Transmit/',
|
||||||
|
stack: 'B',
|
||||||
|
transform: 'negative-Y',
|
||||||
|
},
|
||||||
|
],
|
||||||
|
},
|
||||||
|
)
|
||||||
|
.addPanel(
|
||||||
|
g.panel('Net Saturation (Drops Receive/Transmit)') +
|
||||||
|
g.queryPanel(
|
||||||
|
[
|
||||||
|
'instance:node_network_receive_drop_excluding_lo:rate1m{%(nodeExporterSelector)s}' % $._config,
|
||||||
|
'instance:node_network_transmit_drop_excluding_lo:rate1m{%(nodeExporterSelector)s}' % $._config,
|
||||||
|
],
|
||||||
|
['{{instance}} Receive', '{{instance}} Transmit'],
|
||||||
|
legendLink,
|
||||||
|
) +
|
||||||
|
g.stack +
|
||||||
|
{
|
||||||
|
yaxes: g.yaxes({ format: 'rps', min: null }),
|
||||||
|
seriesOverrides: [
|
||||||
|
{
|
||||||
|
alias: '/ Receive/',
|
||||||
|
stack: 'A',
|
||||||
|
},
|
||||||
|
{
|
||||||
|
alias: '/ Transmit/',
|
||||||
|
stack: 'B',
|
||||||
|
transform: 'negative-Y',
|
||||||
|
},
|
||||||
|
],
|
||||||
|
},
|
||||||
|
)
|
||||||
|
)
|
||||||
|
.addRow(
|
||||||
|
g.row('Disk IO')
|
||||||
.addPanel(
|
.addPanel(
|
||||||
g.panel('Disk IO Utilisation') +
|
g.panel('Disk IO Utilisation') +
|
||||||
// Full utilisation would be all disks on each node spending an average of
|
// Full utilisation would be all disks on each node spending an average of
|
||||||
|
|
@ -85,36 +146,7 @@ local g = import 'grafana-builder/grafana.libsonnet';
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
.addRow(
|
.addRow(
|
||||||
g.row('Network')
|
g.row('Disk Space')
|
||||||
.addPanel(
|
|
||||||
g.panel('Net Utilisation (Bytes Receive/Transmit)') +
|
|
||||||
g.queryPanel(
|
|
||||||
[
|
|
||||||
'instance:node_network_receive_bytes_excluding_lo:rate1m{%(nodeExporterSelector)s}' % $._config,
|
|
||||||
'-instance:node_network_transmit_bytes_excluding_lo:rate1m{%(nodeExporterSelector)s}' % $._config,
|
|
||||||
],
|
|
||||||
['{{instance}} Receive', '{{instance}} Transmit'],
|
|
||||||
legendLink,
|
|
||||||
) +
|
|
||||||
g.stack +
|
|
||||||
{ yaxes: g.yaxes('Bps') },
|
|
||||||
)
|
|
||||||
.addPanel(
|
|
||||||
g.panel('Net Saturation (Drops Receive/Transmit)') +
|
|
||||||
g.queryPanel(
|
|
||||||
[
|
|
||||||
'instance:node_network_receive_drop_excluding_lo:rate1m{%(nodeExporterSelector)s}' % $._config,
|
|
||||||
'-instance:node_network_transmit_drop_excluding_lo:rate1m{%(nodeExporterSelector)s}' % $._config,
|
|
||||||
],
|
|
||||||
['{{instance}} Receive', '{{instance}} Transmit'],
|
|
||||||
legendLink,
|
|
||||||
) +
|
|
||||||
g.stack +
|
|
||||||
{ yaxes: g.yaxes('rps') },
|
|
||||||
)
|
|
||||||
)
|
|
||||||
.addRow(
|
|
||||||
g.row('Storage')
|
|
||||||
.addPanel(
|
.addPanel(
|
||||||
g.panel('Disk Space Utilisation') +
|
g.panel('Disk Space Utilisation') +
|
||||||
g.queryPanel(|||
|
g.queryPanel(|||
|
||||||
|
|
@ -145,14 +177,20 @@ local g = import 'grafana-builder/grafana.libsonnet';
|
||||||
.addPanel(
|
.addPanel(
|
||||||
g.panel('CPU Utilisation') +
|
g.panel('CPU Utilisation') +
|
||||||
g.queryPanel('instance:node_cpu_utilisation:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Utilisation') +
|
g.queryPanel('instance:node_cpu_utilisation:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Utilisation') +
|
||||||
{ yaxes: g.yaxes('percentunit') },
|
{
|
||||||
|
yaxes: g.yaxes('percentunit'),
|
||||||
|
legend+: { show: false },
|
||||||
|
},
|
||||||
)
|
)
|
||||||
.addPanel(
|
.addPanel(
|
||||||
// TODO: Is this a useful panel? At least there should be some explanation how load
|
// TODO: Is this a useful panel? At least there should be some explanation how load
|
||||||
// average relates to the "CPU saturation" in the title.
|
// average relates to the "CPU saturation" in the title.
|
||||||
g.panel('CPU Saturation (Load1)') +
|
g.panel('CPU Saturation (Load1 per CPU)') +
|
||||||
g.queryPanel('instance:node_cpu_saturation_load1:{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Saturation') +
|
g.queryPanel('instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Saturation') +
|
||||||
{ yaxes: g.yaxes('percentunit') },
|
{
|
||||||
|
yaxes: g.yaxes('percentunit'),
|
||||||
|
legend+: { show: false },
|
||||||
|
},
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
.addRow(
|
.addRow(
|
||||||
|
|
@ -165,20 +203,10 @@ local g = import 'grafana-builder/grafana.libsonnet';
|
||||||
.addPanel(
|
.addPanel(
|
||||||
g.panel('Memory Saturation (pages swapped per second)') +
|
g.panel('Memory Saturation (pages swapped per second)') +
|
||||||
g.queryPanel('instance:node_memory_swap_io_pages:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Swap IO') +
|
g.queryPanel('instance:node_memory_swap_io_pages:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Swap IO') +
|
||||||
{ yaxes: g.yaxes('short') },
|
{
|
||||||
)
|
yaxes: g.yaxes('short'),
|
||||||
)
|
legend+: { show: false },
|
||||||
.addRow(
|
},
|
||||||
g.row('Disk')
|
|
||||||
.addPanel(
|
|
||||||
g.panel('Disk IO Utilisation') +
|
|
||||||
g.queryPanel('instance_device:node_disk_io_time_seconds:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Utilisation {{device}}') +
|
|
||||||
{ yaxes: g.yaxes('percentunit') },
|
|
||||||
)
|
|
||||||
.addPanel(
|
|
||||||
g.panel('Disk IO Saturation') +
|
|
||||||
g.queryPanel('instance_device:node_disk_io_time_weighted_seconds:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Saturation {{device}}') +
|
|
||||||
{ yaxes: g.yaxes('percentunit') },
|
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
.addRow(
|
.addRow(
|
||||||
|
|
@ -188,37 +216,79 @@ local g = import 'grafana-builder/grafana.libsonnet';
|
||||||
g.queryPanel(
|
g.queryPanel(
|
||||||
[
|
[
|
||||||
'instance:node_network_receive_bytes_excluding_lo:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config,
|
'instance:node_network_receive_bytes_excluding_lo:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config,
|
||||||
'-instance:node_network_transmit_bytes_excluding_lo:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config,
|
'instance:node_network_transmit_bytes_excluding_lo:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config,
|
||||||
],
|
],
|
||||||
['Receive', 'Transmit'],
|
['Receive', 'Transmit'],
|
||||||
) +
|
) +
|
||||||
{ yaxes: g.yaxes('Bps') },
|
{
|
||||||
|
yaxes: g.yaxes({ format: 'Bps', min: null }),
|
||||||
|
seriesOverrides: [
|
||||||
|
{
|
||||||
|
alias: '/Receive/',
|
||||||
|
stack: 'A',
|
||||||
|
},
|
||||||
|
{
|
||||||
|
alias: '/Transmit/',
|
||||||
|
stack: 'B',
|
||||||
|
transform: 'negative-Y',
|
||||||
|
},
|
||||||
|
],
|
||||||
|
},
|
||||||
)
|
)
|
||||||
.addPanel(
|
.addPanel(
|
||||||
g.panel('Net Saturation (Drops Receive/Transmit)') +
|
g.panel('Net Saturation (Drops Receive/Transmit)') +
|
||||||
g.queryPanel(
|
g.queryPanel(
|
||||||
[
|
[
|
||||||
'instance:node_network_receive_drop_excluding_lo:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config,
|
'instance:node_network_receive_drop_excluding_lo:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config,
|
||||||
'-instance:node_network_transmit_drop_excluding_lo:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config,
|
'instance:node_network_transmit_drop_excluding_lo:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config,
|
||||||
],
|
],
|
||||||
['Receive drops', 'Transmit drops'],
|
['Receive drops', 'Transmit drops'],
|
||||||
) +
|
) +
|
||||||
{ yaxes: g.yaxes('rps') },
|
{
|
||||||
|
yaxes: g.yaxes({ format: 'rps', min: null }),
|
||||||
|
seriesOverrides: [
|
||||||
|
{
|
||||||
|
alias: '/Receive/',
|
||||||
|
stack: 'A',
|
||||||
|
},
|
||||||
|
{
|
||||||
|
alias: '/Transmit/',
|
||||||
|
stack: 'B',
|
||||||
|
transform: 'negative-Y',
|
||||||
|
},
|
||||||
|
],
|
||||||
|
},
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
.addRow(
|
.addRow(
|
||||||
g.row('Disk')
|
g.row('Disk IO')
|
||||||
.addPanel(
|
.addPanel(
|
||||||
g.panel('Disk Utilisation') +
|
g.panel('Disk IO Utilisation') +
|
||||||
|
g.queryPanel('instance_device:node_disk_io_time_seconds:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, '{{device}}') +
|
||||||
|
{ yaxes: g.yaxes('percentunit') },
|
||||||
|
)
|
||||||
|
.addPanel(
|
||||||
|
g.panel('Disk IO Saturation') +
|
||||||
|
g.queryPanel('instance_device:node_disk_io_time_weighted_seconds:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, '{{device}}') +
|
||||||
|
{ yaxes: g.yaxes('percentunit') },
|
||||||
|
)
|
||||||
|
)
|
||||||
|
.addRow(
|
||||||
|
g.row('Disk Space')
|
||||||
|
.addPanel(
|
||||||
|
g.panel('Disk Space Utilisation') +
|
||||||
g.queryPanel(|||
|
g.queryPanel(|||
|
||||||
1 -
|
1 -
|
||||||
(
|
(
|
||||||
sum(max without (mountpoint, fstype) (node_filesystem_avail_bytes{%(nodeExporterSelector)s, %(fsSelector)s}))
|
max without (mountpoint, fstype) (node_filesystem_avail_bytes{%(nodeExporterSelector)s, %(fsSelector)s, instance="$instance"}})
|
||||||
/
|
/
|
||||||
sum(max without (mountpoint, fstype) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s}))
|
max without (mountpoint, fstype) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, instance="$instance"}})
|
||||||
)
|
)
|
||||||
||| % $._config, 'Disk') +
|
||| % $._config, '{{device}}') +
|
||||||
{ yaxes: g.yaxes('percentunit') },
|
{
|
||||||
|
yaxes: g.yaxes('percentunit'),
|
||||||
|
legend+: { show: false },
|
||||||
|
},
|
||||||
),
|
),
|
||||||
),
|
),
|
||||||
},
|
},
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue