openstack/openstack-helm-infra
Code Issues Proposed changes

Grafana: Remove default dashboards from chart

Browse Source 
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>
This commit is contained in:
Steve Wilkerson 2019-12-03 15:51:29 -06:00 committed by Steve Wilkerson
parent ac18e6acf9
commit 3a6df3b544
17 changed files with 17644 additions and 17593 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
grafana/templates/deployment.yaml
View File

@ -93,6 +93,8 @@ spec:
mountPath: /etc/grafana
- name: pod-screenshots-grafana
mountPath: /var/lib/grafana/png
- name: pod-dashboards-grafana
mountPath: /etc/grafana/dashboards
- name: pod-provisioning-grafana
mountPath: {{ .Values.conf.grafana.paths.provisioning }}
- name: grafana-bin
@ -126,6 +128,8 @@ spec:
emptyDir: {}
- name: pod-screenshots-grafana
emptyDir: {}
- name: pod-dashboards-grafana
emptyDir: {}
- name: pod-provisioning-grafana
emptyDir: {}
- name: grafana-bin

17587
grafana/values.yaml
View File

File diff suppressed because it is too large Load Diff

1050
grafana/values_overrides/calico.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

2487
grafana/values_overrides/ceph.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

1700
grafana/values_overrides/containers.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

1016
grafana/values_overrides/coredns.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

2631
grafana/values_overrides/elasticsearch.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

1561
grafana/values_overrides/kubernetes.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

619
grafana/values_overrides/nginx.yaml Normal file
View File

@ -0,0 +1,619 @@
# NOTE(srwilkers): This overrides file provides a reference for a dashboard for
# nginx
conf:
dashboards:
nginx_stats:
__inputs:
- name: prometheus
label: prometheus
description: ''
type: datasource
pluginId: prometheus
pluginName: Prometheus
__requires:
- type: grafana
id: grafana
name: Grafana
version: 4.5.2
- type: panel
id: graph
name: Graph
version: ''
- type: datasource
id: prometheus
name: Prometheus
version: 1.0.0
annotations:
list: []
description: Show stats from the hnlq715/nginx-vts-exporter.
editable: true
gnetId: 2949
graphTooltip: 0
hideControls: false
id:
links: []
refresh: 5m
rows:
- collapse: false
height: 250
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 7
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 12
stack: false
steppedLine: false
targets:
- expr: sum(nginx_upstream_responses_total{upstream=~"^$Upstream$"}) by (status_code,
upstream)
format: time_series
interval: ''
intervalFactor: 2
legendFormat: "{{ status_code }}.{{ upstream }}"
metric: nginx_upstream_response
refId: A
step: 4
thresholds: []
timeFrom:
timeShift:
title: HTTP Response Codes by Upstream
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: Dashboard Row
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 6
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: sum(irate(nginx_upstream_requests_total{upstream=~"^$Upstream$"}[5m]))
by (upstream)
format: time_series
interval: ''
intervalFactor: 2
legendFormat: "{{ upstream }}"
metric: nginx_upstream_requests
refId: A
step: 10
thresholds: []
timeFrom:
timeShift:
title: Upstream Requests rate
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 5
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: sum(irate(nginx_upstream_bytes_total{upstream=~"^$Upstream$"}[5m])) by
(direction, upstream)
format: time_series
interval: ''
intervalFactor: 2
legendFormat: "{{ direction }}.{{ upstream }}"
metric: nginx_upstream_bytes
refId: A
step: 10
thresholds: []
timeFrom:
timeShift:
title: Upstream Bytes Transfer rate
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: Dashboard Row
titleSize: h6
- collapse: false
height: 250px
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 1
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: sum(irate(nginx_connections_total[5m])) by (type)
format: time_series
intervalFactor: 2
legendFormat: "{{ type }}"
metric: nginx_server_connections
refId: A
step: 10
thresholds: []
timeFrom:
timeShift:
title: Overall Connections rate
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 4
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: sum(irate(nginx_cache_total{ server_zone=~"$ingress"}[5m])) by (server_zone,
type)
format: time_series
interval: ''
intervalFactor: 2
legendFormat: "{{ type }}.{{ server_zone }}"
metric: nginx_server_cache
refId: A
step: 10
thresholds: []
timeFrom:
timeShift:
title: Cache Action rate
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: Dashboard Row
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 3
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: sum(irate(nginx_requests_total{ server_zone=~"$ingress" }[5m])) by (server_zone)
format: time_series
interval: ''
intervalFactor: 2
legendFormat: "{{ server_zone }}"
metric: nginx_server_requests
refId: A
step: 10
thresholds: []
timeFrom:
timeShift:
title: Overall Requests rate
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 2
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: sum(irate(nginx_bytes_total{ server_zone=~"$ingress" }[5m])) by (direction,
server_zone)
format: time_series
intervalFactor: 2
legendFormat: "{{ direction }}.{{ server_zone }}"
metric: nginx_server_bytes
refId: A
step: 10
thresholds: []
timeFrom:
timeShift:
title: Overall Bytes Transferred rate
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: bytes
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: Dashboard Row
titleSize: h6
schemaVersion: 14
style: dark
tags:
- prometheus
- nginx
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: "${DS_PROMETHEUS}"
hide: 0
includeAll: false
label:
multi: true
name: Upstream
options: []
query: label_values(nginx_upstream_bytes_total, upstream)
refresh: 1
regex: ''
sort: 1
tagValuesQuery: ''
tags: []
tagsQuery: ''
type: query
useTags: false
- allValue:
current: {}
datasource: "${DS_PROMETHEUS}"
hide: 0
includeAll: false
label:
multi: true
name: ingress
options: []
query: label_values(nginx_bytes_total, server_zone)
refresh: 1
regex: "/^[^\\*_]+$/"
sort: 1
tagValuesQuery: ''
tags: []
tagsQuery: ''
type: query
useTags: false
time:
from: now-1h
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
timezone: browser
title: Nginx Stats
version: 13

755
grafana/values_overrides/nodes.yaml Normal file
View File

@ -0,0 +1,755 @@
# NOTE(srwilkers): This overrides file provides a reference for a dashboard for
# the status of all nodes in a deployment
conf:
dashboards:
nodes:
__inputs:
- name: prometheus
label: prometheus
description: ''
type: datasource
pluginId: prometheus
pluginName: Prometheus
__requires:
- type: grafana
id: grafana
name: Grafana
version: 4.4.1
- type: panel
id: graph
name: Graph
version: ''
- type: datasource
id: prometheus
name: Prometheus
version: 1.0.0
- type: panel
id: singlestat
name: Singlestat
version: ''
annotations:
list: []
description: Dashboard to get an overview of one server
editable: true
gnetId: 22
graphTooltip: 0
hideControls: false
id:
links: []
refresh: false
rows:
- collapse: false
height: 250px
panels:
- alerting: {}
aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
grid: {}
id: 3
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: 100 - (avg by (cpu) (irate(node_cpu{mode="idle", instance="$server"}[5m]))
* 100)
hide: false
intervalFactor: 10
legendFormat: "{{cpu}}"
refId: A
step: 50
thresholds: []
timeFrom:
timeShift:
title: Idle cpu
tooltip:
msResolution: false
shared: true
sort: 0
value_type: cumulative
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: percent
label: cpu usage
logBase: 1
max: 100
min: 0
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- alerting: {}
aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
grid: {}
id: 9
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: node_load1{instance="$server"}
intervalFactor: 4
legendFormat: load 1m
refId: A
step: 20
target: ''
- expr: node_load5{instance="$server"}
intervalFactor: 4
legendFormat: load 5m
refId: B
step: 20
target: ''
- expr: node_load15{instance="$server"}
intervalFactor: 4
legendFormat: load 15m
refId: C
step: 20
target: ''
thresholds: []
timeFrom:
timeShift:
title: System load
tooltip:
msResolution: false
shared: true
sort: 0
value_type: cumulative
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: percentunit
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: New row
titleSize: h6
- collapse: false
height: 250px
panels:
- alerting: {}
aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
grid: {}
id: 4
legend:
alignAsTable: false
avg: false
current: false
hideEmpty: false
hideZero: false
max: false
min: false
rightSide: false
show: true
total: false
values: false
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: node_memory_SwapFree{instance="172.17.0.1:9100",job="prometheus"}
yaxis: 2
spaceLength: 10
span: 9
stack: true
steppedLine: false
targets:
- expr: node_memory_MemTotal{instance="$server"} - node_memory_MemFree{instance="$server"}
- node_memory_Buffers{instance="$server"} - node_memory_Cached{instance="$server"}
hide: false
interval: ''
intervalFactor: 2
legendFormat: memory used
metric: ''
refId: C
step: 10
- expr: node_memory_Buffers{instance="$server"}
interval: ''
intervalFactor: 2
legendFormat: memory buffers
metric: ''
refId: E
step: 10
- expr: node_memory_Cached{instance="$server"}
intervalFactor: 2
legendFormat: memory cached
metric: ''
refId: F
step: 10
- expr: node_memory_MemFree{instance="$server"}
intervalFactor: 2
legendFormat: memory free
metric: ''
refId: D
step: 10
thresholds: []
timeFrom:
timeShift:
title: Memory usage
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: bytes
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- 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: "${DS_PROMETHEUS}"
editable: true
error: false
format: percent
gauge:
maxValue: 100
minValue: 0
show: true
thresholdLabels: false
thresholdMarkers: true
id: 5
interval:
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 3
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
tableColumn: ''
targets:
- expr: ((node_memory_MemTotal{instance="$server"} - node_memory_MemFree{instance="$server"} -
node_memory_Buffers{instance="$server"} - node_memory_Cached{instance="$server"})
/ node_memory_MemTotal{instance="$server"}) * 100
intervalFactor: 2
refId: A
step: 60
target: ''
thresholds: 80, 90
title: Memory usage
type: singlestat
valueFontSize: 80%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: avg
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: New row
titleSize: h6
- collapse: false
height: 250px
panels:
- alerting: {}
aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
grid: {}
id: 6
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: read
yaxis: 1
- alias: '{instance="172.17.0.1:9100"}'
yaxis: 2
- alias: io time
yaxis: 2
spaceLength: 10
span: 9
stack: false
steppedLine: false
targets:
- expr: sum by (instance) (rate(node_disk_bytes_read{instance="$server"}[2m]))
hide: false
intervalFactor: 4
legendFormat: read
refId: A
step: 20
target: ''
- expr: sum by (instance) (rate(node_disk_bytes_written{instance="$server"}[2m]))
intervalFactor: 4
legendFormat: written
refId: B
step: 20
- expr: sum by (instance) (rate(node_disk_io_time_ms{instance="$server"}[2m]))
intervalFactor: 4
legendFormat: io time
refId: C
step: 20
thresholds: []
timeFrom:
timeShift:
title: Disk I/O
tooltip:
msResolution: false
shared: true
sort: 0
value_type: cumulative
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: bytes
label:
logBase: 1
max:
min:
show: true
- format: ms
label:
logBase: 1
max:
min:
show: true
- 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: "${DS_PROMETHEUS}"
editable: true
error: false
format: percentunit
gauge:
maxValue: 1
minValue: 0
show: true
thresholdLabels: false
thresholdMarkers: true
id: 7
interval:
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 3
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
tableColumn: ''
targets:
- expr: (sum(node_filesystem_size{device!="rootfs",instance="$server"}) - sum(node_filesystem_free{device!="rootfs",instance="$server"}))
/ sum(node_filesystem_size{device!="rootfs",instance="$server"})
intervalFactor: 2
refId: A
step: 60
target: ''
thresholds: 0.75, 0.9
title: Disk space usage
type: singlestat
valueFontSize: 80%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: New row
titleSize: h6
- collapse: false
height: 250px
panels:
- alerting: {}
aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
grid: {}
id: 8
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: 'transmitted '
yaxis: 2
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: rate(node_network_receive_bytes{instance="$server",device!~"lo"}[5m])
hide: false
intervalFactor: 2
legendFormat: "{{device}}"
refId: A
step: 10
target: ''
thresholds: []
timeFrom:
timeShift:
title: Network received
tooltip:
msResolution: false
shared: true
sort: 0
value_type: cumulative
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: bytes
label:
logBase: 1
max:
min:
show: true
- format: bytes
label:
logBase: 1
max:
min:
show: true
- alerting: {}
aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
grid: {}
id: 10
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 2
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: 'transmitted '
yaxis: 2
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: rate(node_network_transmit_bytes{instance="$server",device!~"lo"}[5m])
hide: false
intervalFactor: 2
legendFormat: "{{device}}"
refId: B
step: 10
target: ''
thresholds: []
timeFrom:
timeShift:
title: Network transmitted
tooltip:
msResolution: false
shared: true
sort: 0
value_type: cumulative
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: bytes
label:
logBase: 1
max:
min:
show: true
- format: bytes
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: New row
titleSize: h6
schemaVersion: 14
style: dark
tags: []
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: "${DS_PROMETHEUS}"
hide: 0
includeAll: false
label: Server
multi: false
name: host
options: []
query: label_values(node_uname_info, nodename)
refresh: 1
regex: ''
sort: 0
tagValuesQuery: ''
tags: []
tagsQuery: ''
type: query
useTags: false
- allValue:
current: {}
datasource: "${DS_PROMETHEUS}"
hide: 2
includeAll: false
label: Instance
multi: false
name: server
options: []
query: label_values(node_uname_info{nodename="$host"}, instance)
refresh: 1
regex: ''
sort: 0
tagValuesQuery: ''
tags: []
tagsQuery: ''
type: query
useTags: false
time:
from: now-1h
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
timezone: browser
title: Nodes
version: 2
inputs:
- name: prometheus
pluginId: prometheus
type: datasource
value: prometheus
overwrite: true

3013
grafana/values_overrides/openstack.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

2795
grafana/values_overrides/prometheus.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

1
roles/osh-run-script/defaults/main.yaml
View File

@ -11,7 +11,6 @@
# limitations under the License.
osh_params:
openstack_release: newton
container_distro_name: ubuntu
container_distro_version: xenial
#feature_gates:

5
roles/osh-run-script/tasks/main.yaml
View File

@ -21,7 +21,6 @@
OSH_EXTRA_HELM_ARGS: "{{ zuul_osh_extra_helm_args_relative_path | default('') }}"
OSH_PATH: "{{ zuul_osh_relative_path | default('../openstack-helm/') }}"
OSH_INFRA_PATH: "{{ zuul_osh_infra_relative_path | default('../openstack-helm-infra/') }}"
OPENSTACK_RELEASE: "{{ osh_params.openstack_release }}"
CONTAINER_DISTRO_NAME: "{{ osh_params.container_distro_name }}"
CONTAINER_DISTRO_VERSION: "{{ osh_params.container_distro_version }}"
CONTAINER_DISTRO_NAME: "{{ osh_params.container_distro_name | default('') }}"
CONTAINER_DISTRO_VERSION: "{{ osh_params.container_distro_version | default('') }}"
FEATURE_GATES: "{{ osh_params.feature_gates | default('') }}"

3
tools/deployment/common/000-install-packages.sh
View File

@ -22,4 +22,5 @@ sudo apt-get install --no-install-recommends -y \
git \
make \
nmap \
curl
curl \
bc

7
tools/deployment/multinode/100-grafana.sh
View File

@ -19,10 +19,15 @@ set -xe
#NOTE: Lint and package chart
make grafana
FEATURE_GATES="calico,ceph,containers,coredns,elasticsearch,kubernetes,nginx,nodes,openstack,prometheus"
: ${OSH_INFRA_EXTRA_HELM_ARGS_GRAFANA:="$({ ./tools/deployment/common/get-values-overrides.sh grafana;} 2> /dev/null)"}
#NOTE: Deploy command
helm upgrade --install grafana ./grafana \
--namespace=osh-infra \
--set pod.replicas.grafana=2
--set pod.replicas.grafana=2 \
${OSH_INFRA_EXTRA_HELM_ARGS} \
${OSH_INFRA_EXTRA_HELM_ARGS_GRAFANA}
#NOTE: Wait for deploy
./tools/deployment/common/wait-for-pods.sh osh-infra

3
tools/deployment/osh-infra-monitoring/110-grafana.sh
View File

@ -19,7 +19,8 @@ set -xe
#NOTE: Lint and package chart
make grafana
: ${OSH_INFRA_EXTRA_HELM_ARGS_GRAFANA:="$(./tools/deployment/common/get-values-overrides.sh grafana)"}
FEATURE_GATES="calico,ceph,containers,coredns,elasticsearch,kubernetes,nginx,nodes,openstack,prometheus"
: ${OSH_INFRA_EXTRA_HELM_ARGS_GRAFANA:="$({ ./tools/deployment/common/get-values-overrides.sh grafana;} 2> /dev/null)"}
#NOTE: Deploy command
helm upgrade --install grafana ./grafana \