openstack-helm-infra/grafana/values_overrides/containers.yaml
Steve Wilkerson 3a6df3b544 Grafana: Remove default dashboards from chart
This removes the default dashboards from the Grafana chart and
instead places them in the values_overrides directory, similar to
what was done for the Prometheus rules. As Grafana dashboards
will likely be heavily dependent upon end-user needs, the old
default dashboard configs should only be used as a reference
instead of opinionated defaults that are difficult to override.
The previous defaults made using specialized labels for dashboard
variables difficult, as they were making dangerous assumptions
about deployed namespaces and host fqdns. By removing the defaults
entirely, end users can define their own dashboards to meet their
specialized needs

Change-Id: I7def8df68371deda0b75a685363c8a73b818dd45
Signed-off-by: Steve Wilkerson <sw5822@att.com>
2019-12-09 13:39:13 +00:00

1701 lines
46 KiB
YAML

# NOTE(srwilkers): This overrides file provides a reference for a dashboard for
# container metrics, specific to each host
conf:
dashboards:
containers:
__inputs:
- name: DS_PROMETHEUS
label: Prometheus
description: ''
type: datasource
pluginId: prometheus
pluginName: Prometheus
__requires:
- type: panel
id: graph
name: Graph
version: ''
- type: panel
id: singlestat
name: Singlestat
version: ''
- type: grafana
id: grafana
name: Grafana
version: 3.1.1
- type: datasource
id: prometheus
name: Prometheus
version: 1.3.0
id:
title: Container Metrics (cAdvisor)
description: Monitors Kubernetes cluster using Prometheus. Shows overall cluster CPU
/ Memory / Filesystem usage as well as individual pod, containers, systemd services
statistics. Uses cAdvisor metrics only.
tags:
- kubernetes
style: dark
timezone: browser
editable: true
hideControls: false
sharedCrosshair: false
rows:
- collapse: false
editable: true
height: 200px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 1
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
thresholdLine: false
height: 200px
id: 32
isNew: true
legend:
alignAsTable: false
avg: true
current: true
max: false
min: false
rightSide: false
show: false
sideWidth: 200
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: false
targets:
- expr: sum (rate (container_network_receive_bytes_total{kubernetes_io_hostname=~"^$Node$"}[5m]))
interval: 10s
intervalFactor: 1
legendFormat: Received
metric: network
refId: A
step: 10
- expr: '- sum (rate (container_network_transmit_bytes_total{kubernetes_io_hostname=~"^$Node$"}[5m]))'
interval: 10s
intervalFactor: 1
legendFormat: Sent
metric: network
refId: B
step: 10
timeFrom:
timeShift:
title: Network I/O pressure
tooltip:
msResolution: false
shared: true
sort: 0
value_type: cumulative
transparent: false
type: graph
xaxis:
show: true
yaxes:
- format: Bps
label:
logBase: 1
max:
min:
show: true
- format: Bps
label:
logBase: 1
max:
min:
show: false
title: Network I/O pressure
- collapse: false
editable: true
height: 250px
panels:
- cacheTimeout:
colorBackground: false
colorValue: true
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
format: percent
gauge:
maxValue: 100
minValue: 0
show: true
thresholdLabels: false
thresholdMarkers: true
height: 180px
id: 4
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 4
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (container_memory_working_set_bytes{id="/",kubernetes_io_hostname=~"^$Node$"})
/ sum (machine_memory_bytes{kubernetes_io_hostname=~"^$Node$"}) * 100
interval: 10s
intervalFactor: 1
refId: A
step: 10
thresholds: 65, 90
title: Cluster memory usage
transparent: false
type: singlestat
valueFontSize: 80%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: true
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
format: percent
gauge:
maxValue: 100
minValue: 0
show: true
thresholdLabels: false
thresholdMarkers: true
height: 180px
id: 6
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 4
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (rate (container_cpu_usage_seconds_total{id="/",kubernetes_io_hostname=~"^$Node$"}[5m]))
/ sum (machine_cpu_cores{kubernetes_io_hostname=~"^$Node$"}) * 100
interval: 10s
intervalFactor: 1
refId: A
step: 10
thresholds: 65, 90
title: Cluster CPU usage (5m avg)
type: singlestat
valueFontSize: 80%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: true
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
format: percent
gauge:
maxValue: 100
minValue: 0
show: true
thresholdLabels: false
thresholdMarkers: true
height: 180px
id: 7
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 4
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (container_fs_usage_bytes{device=~"^/dev/[sv]da[0-9]$",id=~"/.+",kubernetes_io_hostname=~"^$Node$"})
/ sum (container_fs_limit_bytes{device=~"^/dev/[sv]da[0-9]$",id=~"/.+",kubernetes_io_hostname=~"^$Node$"})
* 100
interval: 10s
intervalFactor: 1
legendFormat: ''
metric: ''
refId: A
step: 10
thresholds: 65, 90
title: Cluster filesystem usage
type: singlestat
valueFontSize: 80%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
format: bytes
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
height: 1px
id: 9
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 20%
prefix: ''
prefixFontSize: 20%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (container_memory_working_set_bytes{id="/",kubernetes_io_hostname=~"^$Node$"})
interval: 10s
intervalFactor: 1
refId: A
step: 10
thresholds: ''
title: Used
type: singlestat
valueFontSize: 50%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
format: bytes
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
height: 1px
id: 10
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (machine_memory_bytes{kubernetes_io_hostname=~"^$Node$"})
interval: 10s
intervalFactor: 1
refId: A
step: 10
thresholds: ''
title: Total
type: singlestat
valueFontSize: 50%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
format: none
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
height: 1px
id: 11
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: " cores"
postfixFontSize: 30%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (rate (container_cpu_usage_seconds_total{id="/",kubernetes_io_hostname=~"^$Node$"}[5m]))
interval: 10s
intervalFactor: 1
refId: A
step: 10
thresholds: ''
title: Used
type: singlestat
valueFontSize: 50%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
format: none
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
height: 1px
id: 12
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: " cores"
postfixFontSize: 30%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (machine_cpu_cores{kubernetes_io_hostname=~"^$Node$"})
interval: 10s
intervalFactor: 1
refId: A
step: 10
thresholds: ''
title: Total
type: singlestat
valueFontSize: 50%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
format: bytes
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
height: 1px
id: 13
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (container_fs_usage_bytes{device=~"^/dev/[sv]da[0-9]$",id=~"/.+",kubernetes_io_hostname=~"^$Node$"})
interval: 10s
intervalFactor: 1
refId: A
step: 10
thresholds: ''
title: Used
type: singlestat
valueFontSize: 50%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- rgba(50, 172, 45, 0.97)
- rgba(237, 129, 40, 0.89)
- rgba(245, 54, 54, 0.9)
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
format: bytes
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
height: 1px
id: 14
interval:
isNew: true
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
targets:
- expr: sum (container_fs_limit_bytes{device=~"^/dev/[sv]da[0-9]$",id=~"/.+",kubernetes_io_hostname=~"^$Node$"})
interval: 10s
intervalFactor: 1
refId: A
step: 10
thresholds: ''
title: Total
type: singlestat
valueFontSize: 50%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
showTitle: false
title: Total usage
- collapse: false
editable: true
height: 250px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 3
editable: true
error: false
fill: 0
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
height: ''
id: 17
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: true
show: true
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: true
targets:
- expr: sum (rate (container_cpu_usage_seconds_total{image!="",name=~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (pod)
interval: 10s
intervalFactor: 1
legendFormat: "{{ pod }}"
metric: container_cpu
refId: A
step: 10
timeFrom:
timeShift:
title: Pods CPU usage (5m avg)
tooltip:
msResolution: true
shared: true
sort: 2
value_type: cumulative
transparent: false
type: graph
xaxis:
show: true
yaxes:
- format: none
label: cores
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
showTitle: false
title: Pods CPU usage
- collapse: true
editable: true
height: 250px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 3
editable: true
error: false
fill: 0
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
height: ''
id: 23
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: true
show: true
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: true
targets:
- expr: sum (rate (container_cpu_usage_seconds_total{systemd_service_name!="",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (systemd_service_name)
hide: false
interval: 10s
intervalFactor: 1
legendFormat: "{{ systemd_service_name }}"
metric: container_cpu
refId: A
step: 10
timeFrom:
timeShift:
title: System services CPU usage (5m avg)
tooltip:
msResolution: true
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: none
label: cores
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: System services CPU usage
- collapse: true
editable: true
height: 250px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 3
editable: true
error: false
fill: 0
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
height: ''
id: 24
isNew: true
legend:
alignAsTable: true
avg: true
current: true
hideEmpty: false
hideZero: false
max: false
min: false
rightSide: true
show: true
sideWidth:
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: true
targets:
- expr: sum (rate (container_cpu_usage_seconds_total{image!="",name=~"^k8s_.*",container!="POD",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (container, pod)
hide: false
interval: 10s
intervalFactor: 1
legendFormat: 'pod: {{ pod }} | {{ container }}'
metric: container_cpu
refId: A
step: 10
- expr: sum (rate (container_cpu_usage_seconds_total{image!="",name!~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (kubernetes_io_hostname, name, image)
hide: false
interval: 10s
intervalFactor: 1
legendFormat: 'docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})'
metric: container_cpu
refId: B
step: 10
- expr: sum (rate (container_cpu_usage_seconds_total{rkt_container_name!="",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (kubernetes_io_hostname, rkt_container_name)
interval: 10s
intervalFactor: 1
legendFormat: 'rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}'
metric: container_cpu
refId: C
step: 10
timeFrom:
timeShift:
title: Containers CPU usage (5m avg)
tooltip:
msResolution: true
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: none
label: cores
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: Containers CPU usage
- collapse: true
editable: true
height: 500px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 3
editable: true
error: false
fill: 0
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
id: 20
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: false
show: true
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: true
targets:
- expr: sum (rate (container_cpu_usage_seconds_total{id!="/",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (id)
hide: false
interval: 10s
intervalFactor: 1
legendFormat: "{{ id }}"
metric: container_cpu
refId: A
step: 10
timeFrom:
timeShift:
title: All processes CPU usage (5m avg)
tooltip:
msResolution: true
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: none
label: cores
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
repeat:
showTitle: false
title: All processes CPU usage
- collapse: false
editable: true
height: 250px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 0
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
id: 25
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: true
show: true
sideWidth: 200
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: true
targets:
- expr: sum (container_memory_working_set_bytes{image!="",name=~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"})
by (pod)
interval: 10s
intervalFactor: 1
legendFormat: "{{ pod }}"
metric: container_memory_usage:sort_desc
refId: A
step: 10
timeFrom:
timeShift:
title: Pods memory usage
tooltip:
msResolution: false
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: bytes
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: Pods memory usage
- collapse: true
editable: true
height: 250px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 0
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
id: 26
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: true
show: true
sideWidth: 200
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: true
targets:
- expr: sum (container_memory_working_set_bytes{systemd_service_name!="",kubernetes_io_hostname=~"^$Node$"})
by (systemd_service_name)
interval: 10s
intervalFactor: 1
legendFormat: "{{ systemd_service_name }}"
metric: container_memory_usage:sort_desc
refId: A
step: 10
timeFrom:
timeShift:
title: System services memory usage
tooltip:
msResolution: false
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: bytes
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: System services memory usage
- collapse: true
editable: true
height: 250px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 0
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
id: 27
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: true
show: true
sideWidth: 200
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: true
targets:
- expr: sum (container_memory_working_set_bytes{image!="",name=~"^k8s_.*",container!="POD",kubernetes_io_hostname=~"^$Node$"})
by (container, pod)
interval: 10s
intervalFactor: 1
legendFormat: 'pod: {{ pod }} | {{ container }}'
metric: container_memory_usage:sort_desc
refId: A
step: 10
- expr: sum (container_memory_working_set_bytes{image!="",name!~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"})
by (kubernetes_io_hostname, name, image)
interval: 10s
intervalFactor: 1
legendFormat: 'docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})'
metric: container_memory_usage:sort_desc
refId: B
step: 10
- expr: sum (container_memory_working_set_bytes{rkt_container_name!="",kubernetes_io_hostname=~"^$Node$"})
by (kubernetes_io_hostname, rkt_container_name)
interval: 10s
intervalFactor: 1
legendFormat: 'rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}'
metric: container_memory_usage:sort_desc
refId: C
step: 10
timeFrom:
timeShift:
title: Containers memory usage
tooltip:
msResolution: false
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: bytes
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: Containers memory usage
- collapse: true
editable: true
height: 500px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 0
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
id: 28
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: false
show: true
sideWidth: 200
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: true
targets:
- expr: sum (container_memory_working_set_bytes{id!="/",kubernetes_io_hostname=~"^$Node$"})
by (id)
interval: 10s
intervalFactor: 1
legendFormat: "{{ id }}"
metric: container_memory_usage:sort_desc
refId: A
step: 10
timeFrom:
timeShift:
title: All processes memory usage
tooltip:
msResolution: false
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: bytes
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: All processes memory usage
- collapse: false
editable: true
height: 250px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 1
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
id: 16
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: true
show: true
sideWidth: 200
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: false
targets:
- expr: sum (rate (container_network_receive_bytes_total{image!="",name=~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (pod)
interval: 10s
intervalFactor: 1
legendFormat: "-> {{ pod }}"
metric: network
refId: A
step: 10
- expr: '- sum (rate (container_network_transmit_bytes_total{image!="",name=~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (pod)'
interval: 10s
intervalFactor: 1
legendFormat: "<- {{ pod }}"
metric: network
refId: B
step: 10
timeFrom:
timeShift:
title: Pods network I/O (5m avg)
tooltip:
msResolution: false
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: Bps
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: Pods network I/O
- collapse: true
editable: true
height: 250px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 1
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
id: 30
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: true
show: true
sideWidth: 200
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: false
targets:
- expr: sum (rate (container_network_receive_bytes_total{image!="",name=~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (container, pod)
hide: false
interval: 10s
intervalFactor: 1
legendFormat: "-> pod: {{ pod }} | {{ container }}"
metric: network
refId: B
step: 10
- expr: '- sum (rate (container_network_transmit_bytes_total{image!="",name=~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (container, pod)'
hide: false
interval: 10s
intervalFactor: 1
legendFormat: "<- pod: {{ pod }} | {{ container }}"
metric: network
refId: D
step: 10
- expr: sum (rate (container_network_receive_bytes_total{image!="",name!~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (kubernetes_io_hostname, name, image)
hide: false
interval: 10s
intervalFactor: 1
legendFormat: "-> docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name
}})"
metric: network
refId: A
step: 10
- expr: '- sum (rate (container_network_transmit_bytes_total{image!="",name!~"^k8s_.*",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (kubernetes_io_hostname, name, image)'
hide: false
interval: 10s
intervalFactor: 1
legendFormat: "<- docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name
}})"
metric: network
refId: C
step: 10
- expr: sum (rate (container_network_transmit_bytes_total{rkt_container_name!="",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (kubernetes_io_hostname, rkt_container_name)
hide: false
interval: 10s
intervalFactor: 1
legendFormat: "-> rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name
}}"
metric: network
refId: E
step: 10
- expr: '- sum (rate (container_network_transmit_bytes_total{rkt_container_name!="",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (kubernetes_io_hostname, rkt_container_name)'
hide: false
interval: 10s
intervalFactor: 1
legendFormat: "<- rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name
}}"
metric: network
refId: F
step: 10
timeFrom:
timeShift:
title: Containers network I/O (5m avg)
tooltip:
msResolution: false
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: Bps
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: Containers network I/O
- collapse: true
editable: true
height: 500px
panels:
- aliasColors: {}
bars: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 1
grid:
threshold1:
threshold1Color: rgba(216, 200, 27, 0.27)
threshold2:
threshold2Color: rgba(234, 112, 112, 0.22)
id: 29
isNew: true
legend:
alignAsTable: true
avg: true
current: true
max: false
min: false
rightSide: false
show: true
sideWidth: 200
sort: current
sortDesc: true
total: false
values: true
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
span: 12
stack: false
steppedLine: false
targets:
- expr: sum (rate (container_network_receive_bytes_total{id!="/",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (id)
interval: 10s
intervalFactor: 1
legendFormat: "-> {{ id }}"
metric: network
refId: A
step: 10
- expr: '- sum (rate (container_network_transmit_bytes_total{id!="/",kubernetes_io_hostname=~"^$Node$"}[5m]))
by (id)'
interval: 10s
intervalFactor: 1
legendFormat: "<- {{ id }}"
metric: network
refId: B
step: 10
timeFrom:
timeShift:
title: All processes network I/O (5m avg)
tooltip:
msResolution: false
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
show: true
yaxes:
- format: Bps
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: false
title: All processes network I/O
time:
from: now-5m
to: now
timepicker:
refresh_intervals:
- 5s
- 10s
- 30s
- 1m
- 5m
- 15m
- 30m
- 1h
- 2h
- 1d
time_options:
- 5m
- 15m
- 1h
- 6h
- 12h
- 24h
- 2d
- 7d
- 30d
templating:
list:
- current:
text: Prometheus
value: Prometheus
hide: 0
label: Prometheus datasource
name: DS_PROMETHEUS
options: []
query: prometheus
refresh: 1
regex: ''
type: datasource
- allValue: ".*"
current: {}
datasource: "${DS_PROMETHEUS}"
hide: 0
includeAll: true
multi: false
name: Node
options: []
query: label_values(kubernetes_io_hostname)
refresh: 1
type: query
annotations:
list: []
refresh: 5m
schemaVersion: 12
version: 13
links: []
gnetId: 315