Address review comments, batch 2

Signed-off-by: beorn7 <beorn@grafana.com>
This commit is contained in:
beorn7 2019-07-16 21:18:17 +02:00
commit a92d1d7889
5 changed files with 68 additions and 45 deletions

View file

@ -20,8 +20,9 @@ local gauge = promgrafonnet.gauge;
min=0,
)
.addTarget(prometheus.target(
// TODO: Consider using `${__interval}` as range and a 1m min step.
|||
1 - avg by (cpu) (irate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode="idle", instance="$instance"}[1m]))
1 - avg by (cpu) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode="idle", instance="$instance"}[1m]))
||| % $._config,
legendFormat='{{cpu}}',
intervalFactor=10,
@ -81,9 +82,10 @@ local gauge = promgrafonnet.gauge;
datasource='$datasource',
span=9,
)
.addTarget(prometheus.target('sum by (instance) (irate(node_disk_read_bytes_total{%(nodeExporterSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='read'))
.addTarget(prometheus.target('sum by (instance) (irate(node_disk_written_bytes_total{%(nodeExporterSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='written'))
.addTarget(prometheus.target('sum by (instance) (irate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='io time')) +
// TODO: Consider using `${__interval}` as range and a 1m min step.
.addTarget(prometheus.target('sum by (instance, device) (rate(node_disk_read_bytes_total{%(nodeExporterSelector)s, %(diskDeviceSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='{{device}} read'))
.addTarget(prometheus.target('sum by (instance, device) (rate(node_disk_written_bytes_total{%(nodeExporterSelector)s, %(diskDeviceSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='{{device}} written'))
.addTarget(prometheus.target('sum by (instance, device) (rate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, %(diskDeviceSelector)s, instance="$instance"}[1m]))' % $._config, legendFormat='{{device}} io time')) +
{
seriesOverrides: [
{
@ -122,7 +124,8 @@ local gauge = promgrafonnet.gauge;
span=6,
format='bytes',
)
.addTarget(prometheus.target('irate(node_network_receive_bytes_total{%(nodeExporterSelector)s, instance="$instance", device!="lo"}[1m])' % $._config, legendFormat='{{device}}'));
// TODO: Consider using `${__interval}` as range and a 1m min step.
.addTarget(prometheus.target('rate(node_network_receive_bytes_total{%(nodeExporterSelector)s, instance="$instance", device!="lo"}[1m])' % $._config, legendFormat='{{device}}'));
local networkTransmitted =
graphPanel.new(
@ -131,7 +134,8 @@ local gauge = promgrafonnet.gauge;
span=6,
format='bytes',
)
.addTarget(prometheus.target('irate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, instance="$instance", device!="lo"}[1m])' % $._config, legendFormat='{{device}}'));
// TODO: Consider using `${__interval}` as range and a 1m min step.
.addTarget(prometheus.target('rate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, instance="$instance", device!="lo"}[1m])' % $._config, legendFormat='{{device}}'));
dashboard.new('Nodes', time_from='now-1h')
.addTemplate(

View file

@ -12,7 +12,7 @@ local g = import 'grafana-builder/grafana.libsonnet';
g.panel('CPU Utilisation') +
g.queryPanel(|||
(
instance:node_cpu_utilisation:avg1m
instance:node_cpu_utilisation:avg_rate1m
*
instance:node_num_cpu:sum
/ ignoring (instance) group_left
@ -60,9 +60,9 @@ local g = import 'grafana-builder/grafana.libsonnet';
// 1 second per second doing I/O, normalize by metric cardinality for stacked charts.
g.queryPanel(|||
(
instance:node_disk_utilisation:sum_irate
instance:node_disk_io_time:sum_rate1m
/ ignoring (instance) group_left
count without (instance) (instance:node_disk_utilisation:sum_irate)
count without (instance) (instance:node_disk_io_time:sum_rate1m)
)
|||, '{{instance}}', legendLink) +
g.stack +
@ -72,9 +72,9 @@ local g = import 'grafana-builder/grafana.libsonnet';
g.panel('Disk IO Saturation') +
g.queryPanel(|||
(
instance:node_disk_saturation:sum_irate
instance:node_disk_io_time_weighted:sum_rate1m
/ ignoring (instance) group_left
count without (instance) (instance:node_disk_saturation:sum_irate)
count without (instance) (instance:node_disk_io_time_weighted:sum_rate1m)
)
|||, '{{instance}}', legendLink) +
g.stack +
@ -127,7 +127,7 @@ local g = import 'grafana-builder/grafana.libsonnet';
g.row('CPU')
.addPanel(
g.panel('CPU Utilisation') +
g.queryPanel('instance:node_cpu_utilisation:avg1m{instance="$instance"}', 'Utilisation') +
g.queryPanel('instance:node_cpu_utilisation:avg_rate1m{instance="$instance"}', 'Utilisation') +
{ yaxes: g.yaxes('percentunit') },
)
.addPanel(
@ -145,7 +145,7 @@ local g = import 'grafana-builder/grafana.libsonnet';
)
.addPanel(
g.panel('Memory Saturation (pages swapped per second)') +
g.queryPanel('instance:node_memory_swap_io_pages:sum_rate{instance="$instance"}', 'Swap IO') +
g.queryPanel('instance:node_memory_swap_io_pages:rate1m{instance="$instance"}', 'Swap IO') +
{ yaxes: g.yaxes('short') },
)
)
@ -153,26 +153,32 @@ local g = import 'grafana-builder/grafana.libsonnet';
g.row('Disk')
.addPanel(
g.panel('Disk IO Utilisation') +
g.queryPanel('instance:node_disk_utilisation:sum_irate{instance="$instance"}', 'Utilisation') +
g.queryPanel('instance:node_disk_io_time:sum_rate1m{instance="$instance"}', 'Utilisation') +
{ yaxes: g.yaxes('percentunit') },
)
.addPanel(
g.panel('Disk IO Saturation') +
g.queryPanel('instance:node_disk_saturation:sum_irate{instance="$instance"}', 'Saturation') +
g.queryPanel('instance:node_disk_io_time_weighted:sum_rate1m{instance="$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="$instance"}', 'Utilisation') +
g.panel('Net Utilisation (Bytes Receive/Transmit)') +
g.queryPanel(
['node_network_receive_bytes_total{instance="$instance"}', '-node_network_transmit_bytes_total{instance="$instance"}'],
['Receive', 'Transmit'],
) +
{ yaxes: g.yaxes('Bps') },
)
.addPanel(
g.panel('Net Saturation (Dropped)') +
g.queryPanel('instance:node_net_saturation:sum_irate{instance="$instance"}', 'Saturation') +
{ yaxes: g.yaxes('Bps') },
g.panel('Net Saturation (Drops Receive/Transmit)') +
g.queryPanel(
['node_network_receive_drop_total{instance="$instance"}', '-node_network_transmit_drop_total{instance="$instance"}'],
['Receive drops', 'Transmit drops'],
) +
{ yaxes: g.yaxes('rps') },
)
)
.addRow(