openstack-helm-infra/grafana/values_overrides/prometheus.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

2796 lines
74 KiB
YAML

# NOTE(srwilkers): This overrides file provides a reference for a dashboard for
# Prometheus
conf:
dashboards:
prometheus:
__inputs:
- name: DS_PROMETHEUS
label: Prometheus
description: Prometheus which you want to monitor
type: datasource
pluginId: prometheus
pluginName: Prometheus
__requires:
- type: grafana
id: grafana
name: Grafana
version: 4.6.0
- type: panel
id: graph
name: Graph
version: ''
- type: datasource
id: prometheus
name: Prometheus
version: 1.0.0
- type: panel
id: singlestat
name: Singlestat
version: ''
- type: panel
id: text
name: Text
version: ''
annotations:
list:
- builtIn: 1
datasource: "-- Grafana --"
enable: true
hide: true
iconColor: rgba(0, 211, 255, 1)
name: Annotations & Alerts
type: dashboard
- datasource: "${DS_PROMETHEUS}"
enable: true
expr: count(sum(up{instance="$instance"}) by (instance) < 1)
hide: false
iconColor: rgb(250, 44, 18)
limit: 100
name: downage
showIn: 0
step: 30s
tagKeys: instance
textFormat: prometheus down
titleFormat: Downage
type: alert
- datasource: "${DS_PROMETHEUS}"
enable: true
expr: sum(changes(prometheus_config_last_reload_success_timestamp_seconds[10m]))
by (instance)
hide: false
iconColor: "#fceaca"
limit: 100
name: Reload
showIn: 0
step: 5m
tagKeys: instance
tags: []
titleFormat: Reload
type: tags
description: Dashboard for monitoring of Prometheus v2.x.x
editable: true
gnetId: 3681
graphTooltip: 1
hideControls: false
id:
links:
- icon: info
tags: []
targetBlank: true
title: 'Dashboard''s Github '
tooltip: Github repo of this dashboard
type: link
url: https://github.com/FUSAKLA/Prometheus2-grafana-dashboard
- icon: doc
tags: []
targetBlank: true
title: Prometheus Docs
tooltip: ''
type: link
url: http://prometheus.io/docs/introduction/overview/
refresh: 5m
rows:
- collapse: false
height: 161
panels:
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- "#299c46"
- rgba(237, 129, 40, 0.89)
- "#bf1b00"
datasource: "${DS_PROMETHEUS}"
decimals: 1
format: s
gauge:
maxValue: 1000000
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
id: 41
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: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
tableColumn: ''
targets:
- expr: time() - process_start_time_seconds{instance="$instance"}
format: time_series
instant: false
intervalFactor: 2
refId: A
thresholds: ''
title: Uptime
type: singlestat
valueFontSize: 80%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: true
colors:
- "#299c46"
- rgba(237, 129, 40, 0.89)
- "#bf1b00"
datasource: "${DS_PROMETHEUS}"
format: short
gauge:
maxValue: 1000000
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
id: 42
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: 4
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: true
tableColumn: ''
targets:
- expr: prometheus_tsdb_head_series{instance="$instance"}
format: time_series
instant: false
intervalFactor: 2
refId: A
thresholds: '500000,800000,1000000'
title: Total count of time series
type: singlestat
valueFontSize: 150%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- "#299c46"
- rgba(237, 129, 40, 0.89)
- "#d44a3a"
datasource: "${DS_PROMETHEUS}"
format: none
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
id: 48
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: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
tableColumn: version
targets:
- expr: prometheus_build_info{instance="$instance"}
format: table
instant: true
intervalFactor: 2
refId: A
thresholds: ''
title: Version
type: singlestat
valueFontSize: 80%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: avg
- cacheTimeout:
colorBackground: false
colorValue: false
colors:
- "#299c46"
- rgba(237, 129, 40, 0.89)
- "#d44a3a"
datasource: "${DS_PROMETHEUS}"
decimals: 2
format: ms
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
id: 49
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: 2
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
tableColumn: ''
targets:
- expr: prometheus_tsdb_head_max_time{instance="$instance"} - prometheus_tsdb_head_min_time{instance="$instance"}
format: time_series
instant: true
intervalFactor: 2
refId: A
thresholds: ''
title: Actual head block length
type: singlestat
valueFontSize: 80%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: current
- content: <img src="https://cdn.worldvectorlogo.com/logos/prometheus.svg"/ height="140px">
height: ''
id: 50
links: []
mode: html
span: 1
title: ''
transparent: true
type: text
- cacheTimeout:
colorBackground: false
colorValue: true
colors:
- "#e6522c"
- rgba(237, 129, 40, 0.89)
- "#299c46"
datasource: "${DS_PROMETHEUS}"
decimals: 1
format: none
gauge:
maxValue: 100
minValue: 0
show: false
thresholdLabels: false
thresholdMarkers: true
id: 52
interval:
links: []
mappingType: 1
mappingTypes:
- name: value to text
value: 1
- name: range to text
value: 2
maxDataPoints: 100
nullPointMode: connected
nullText:
postfix: ''
postfixFontSize: 50%
prefix: ''
prefixFontSize: 50%
rangeMaps:
- from: 'null'
text: N/A
to: 'null'
span: 1
sparkline:
fillColor: rgba(31, 118, 189, 0.18)
full: false
lineColor: rgb(31, 120, 193)
show: false
tableColumn: ''
targets:
- expr: '2'
format: time_series
intervalFactor: 2
refId: A
thresholds: '10,20'
title: ''
transparent: true
type: singlestat
valueFontSize: 200%
valueMaps:
- op: "="
text: N/A
value: 'null'
valueName: avg
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: Header instance info
titleSize: h6
- collapse: false
height: '250'
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 15
legend:
avg: true
current: false
max: false
min: false
show: false
total: false
values: true
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: true
steppedLine: false
targets:
- expr: max(prometheus_engine_query_duration_seconds{instance="$instance"}) by
(instance, slice)
format: time_series
intervalFactor: 1
legendFormat: max duration for {{slice}}
metric: prometheus_local_storage_rushed_mode
refId: A
step: 900
thresholds: []
timeFrom:
timeShift:
title: Query elapsed time
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: s
label: ''
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 17
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(increase(prometheus_tsdb_head_series_created_total{instance="$instance"}[$aggregation_interval]))
by (instance)
format: time_series
intervalFactor: 2
legendFormat: created on {{ instance }}
metric: prometheus_local_storage_maintain_series_duration_seconds_count
refId: A
step: 1800
- expr: sum(increase(prometheus_tsdb_head_series_removed_total{instance="$instance"}[$aggregation_interval]))
by (instance) * -1
format: time_series
intervalFactor: 2
legendFormat: removed on {{ instance }}
refId: B
thresholds: []
timeFrom:
timeShift:
title: Head series created/deleted
tooltip:
msResolution: false
shared: true
sort: 2
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:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 13
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(increase(prometheus_target_scrapes_exceeded_sample_limit_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: exceeded_sample_limit on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: A
step: 1800
- expr: sum(increase(prometheus_target_scrapes_sample_duplicate_timestamp_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: duplicate_timestamp on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: B
step: 1800
- expr: sum(increase(prometheus_target_scrapes_sample_out_of_bounds_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: out_of_bounds on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: C
step: 1800
- expr: sum(increase(prometheus_target_scrapes_sample_out_of_order_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: out_of_order on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: D
step: 1800
- expr: sum(increase(prometheus_rule_evaluation_failures_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: rule_evaluation_failure on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: G
step: 1800
- expr: sum(increase(prometheus_tsdb_compactions_failed_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: tsdb_compactions_failed on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: K
step: 1800
- expr: sum(increase(prometheus_tsdb_reloads_failures_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: tsdb_reloads_failures on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: L
step: 1800
- expr: sum(increase(prometheus_tsdb_head_series_not_found{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: head_series_not_found on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: N
step: 1800
- expr: sum(increase(prometheus_evaluator_iterations_missed_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: evaluator_iterations_missed on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: O
step: 1800
- expr: sum(increase(prometheus_evaluator_iterations_skipped_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: evaluator_iterations_skipped on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: P
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Prometheus errors
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: false
title: Main info
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
description: ''
editable: true
error: false
fill: 1
grid: {}
id: 25
legend:
alignAsTable: true
avg: true
current: true
max: true
min: false
show: false
sort: max
sortDesc: true
total: false
values: true
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: prometheus_target_interval_length_seconds{instance="$instance",quantile="0.99"}
- 60
format: time_series
interval: 2m
intervalFactor: 1
legendFormat: "{{instance}}"
metric: ''
refId: A
step: 300
thresholds: []
timeFrom:
timeShift:
title: Scrape delay (counts with 1m scrape interval)
tooltip:
msResolution: false
shared: true
sort: 2
value_type: cumulative
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: s
logBase: 1
max:
min:
show: true
- format: short
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 14
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: Queue length
yaxis: 2
spaceLength: 10
span: 6
stack: false
steppedLine: false
targets:
- expr: sum(prometheus_evaluator_duration_seconds{instance="$instance"}) by (instance,
quantile)
format: time_series
intervalFactor: 2
legendFormat: Queue length
metric: prometheus_local_storage_indexing_queue_length
refId: B
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Rule evaulation duration
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: s
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min: '0'
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: true
title: Scrape & rule duration
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 18
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(increase(http_requests_total{instance="$instance"}[$aggregation_interval]))
by (instance, handler) > 0
format: time_series
intervalFactor: 2
legendFormat: "{{ handler }} on {{ instance }}"
metric: ''
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Request count
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: none
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 16
legend:
avg: false
current: false
hideEmpty: true
hideZero: true
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: max(sum(http_request_duration_microseconds{instance="$instance"}) by (instance,
handler, quantile)) by (instance, handler) > 0
format: time_series
hide: false
intervalFactor: 2
legendFormat: "{{ handler }} on {{ instance }}"
refId: B
thresholds: []
timeFrom:
timeShift:
title: Request duration per handler
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: µs
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 19
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(increase(http_request_size_bytes{instance="$instance", quantile="0.99"}[$aggregation_interval]))
by (instance, handler) > 0
format: time_series
hide: false
intervalFactor: 2
legendFormat: "{{ handler }} in {{ instance }}"
refId: B
thresholds: []
timeFrom:
timeShift:
title: Request size by handler
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: bytes
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Allocated bytes: "#F9BA8F"
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max count collector: "#bf1b00"
Max count harvester: "#bf1b00"
Max to persist: "#3F6833"
RSS: "#890F02"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 8
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: "/Max.*/"
fill: 0
linewidth: 2
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(prometheus_engine_queries{instance="$instance"}) by (instance, handler)
format: time_series
intervalFactor: 2
legendFormat: 'Current count '
metric: last
refId: A
step: 1800
- expr: sum(prometheus_engine_queries_concurrent_max{instance="$instance"}) by
(instance, handler)
format: time_series
intervalFactor: 2
legendFormat: Max count
metric: last
refId: B
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Cont of concurent queries
tooltip:
msResolution: false
shared: true
sort: 2
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: true
title: Requests & queries
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors:
Alert queue capacity on o collector: "#bf1b00"
Alert queue capacity on o harvester: "#bf1b00"
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 20
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: "/.*capacity.*/"
fill: 0
linewidth: 2
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(prometheus_notifications_queue_capacity{instance="$instance"})by (instance)
format: time_series
intervalFactor: 2
legendFormat: 'Alert queue capacity '
metric: prometheus_local_storage_checkpoint_last_size_bytes
refId: A
step: 1800
- expr: sum(prometheus_notifications_queue_length{instance="$instance"})by (instance)
format: time_series
intervalFactor: 2
legendFormat: 'Alert queue size on '
metric: prometheus_local_storage_checkpoint_last_size_bytes
refId: B
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Alert queue size
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: bytes
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 21
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(prometheus_notifications_alertmanagers_discovered{instance="$instance"})
by (instance)
format: time_series
intervalFactor: 2
legendFormat: Checkpoint chunks written/s
metric: prometheus_local_storage_checkpoint_series_chunks_written_sum
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Count of discovered alertmanagers
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: none
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 39
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(increase(prometheus_notifications_dropped_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: notifications_dropped on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: F
step: 1800
- expr: sum(increase(prometheus_rule_evaluation_failures_total{rule_type="alerting",instance="$instance"}[$aggregation_interval]))
by (rule_type,instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: rule_evaluation_failures on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Alerting errors
tooltip:
msResolution: false
shared: true
sort: 2
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: true
title: Alerting
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 45
legend:
avg: false
current: false
max: false
min: false
show: true
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: increase(prometheus_target_sync_length_seconds_count{scrape_job="kubernetes-service-endpoints"}[$aggregation_interval])
format: time_series
intervalFactor: 2
legendFormat: Count of target synces
refId: A
step: 240
thresholds: []
timeFrom:
timeShift:
title: Kubernetes SD sync count
tooltip:
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:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 46
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(increase(prometheus_target_scrapes_exceeded_sample_limit_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: exceeded_sample_limit on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: A
step: 1800
- expr: sum(increase(prometheus_sd_file_read_errors_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
interval: ''
intervalFactor: 2
legendFormat: sd_file_read_error on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: E
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Service discovery errors
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: true
title: Service discovery
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 36
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(increase(prometheus_tsdb_reloads_total{instance="$instance"}[30m]))
by (instance)
format: time_series
intervalFactor: 2
legendFormat: "{{ instance }}"
refId: A
thresholds: []
timeFrom:
timeShift:
title: Reloaded block from disk
tooltip:
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 5
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(prometheus_tsdb_blocks_loaded{instance="$instance"}) by (instance)
format: time_series
intervalFactor: 2
legendFormat: Loaded data blocks
metric: prometheus_local_storage_memory_chunkdescs
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Loaded data blocks
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 3
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: prometheus_tsdb_head_series{instance="$instance"}
format: time_series
intervalFactor: 2
legendFormat: Time series count
metric: prometheus_local_storage_memory_series
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Time series total count
tooltip:
msResolution: false
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 1
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(rate(prometheus_tsdb_head_samples_appended_total{instance="$instance"}[$aggregation_interval]))
by (instance)
format: time_series
intervalFactor: 2
legendFormat: samples/s {{instance}}
metric: prometheus_local_storage_ingested_samples_total
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Samples Appended per second
tooltip:
msResolution: false
shared: true
sort: 2
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: true
title: TSDB stats
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
To persist: "#9AC48A"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 2
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: "/Max.*/"
fill: 0
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(prometheus_tsdb_head_chunks{instance="$instance"}) by (instance)
format: time_series
hide: false
intervalFactor: 2
legendFormat: Head chunk count
metric: prometheus_local_storage_memory_chunks
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Head chunks count
tooltip:
msResolution: false
shared: true
sort: 2
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
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 35
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: max(prometheus_tsdb_head_max_time{instance="$instance"}) by (instance)
- min(prometheus_tsdb_head_min_time{instance="$instance"}) by (instance)
format: time_series
intervalFactor: 2
legendFormat: "{{ instance }}"
refId: A
thresholds: []
timeFrom:
timeShift:
title: Length of head block
tooltip:
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: ms
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 4
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(rate(prometheus_tsdb_head_chunks_created_total{instance="$instance"}[$aggregation_interval]))
by (instance)
format: time_series
intervalFactor: 2
legendFormat: created on {{ instance }}
refId: B
- expr: sum(rate(prometheus_tsdb_head_chunks_removed_total{instance="$instance"}[$aggregation_interval]))
by (instance) * -1
format: time_series
intervalFactor: 2
legendFormat: deleted on {{ instance }}
refId: C
thresholds: []
timeFrom:
timeShift:
title: Head Chunks Created/Deleted per second
tooltip:
msResolution: false
shared: true
sort: 2
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: true
title: Head block stats
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 33
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(increase(prometheus_tsdb_compaction_duration_sum{instance="$instance"}[30m])
/ increase(prometheus_tsdb_compaction_duration_count{instance="$instance"}[30m]))
by (instance)
format: time_series
intervalFactor: 2
legendFormat: "{{ instance }}"
refId: B
thresholds: []
timeFrom:
timeShift:
title: Compaction duration
tooltip:
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: s
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 34
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(prometheus_tsdb_head_gc_duration_seconds{instance="$instance"}) by
(instance, quantile)
format: time_series
intervalFactor: 2
legendFormat: "{{ quantile }} on {{ instance }}"
refId: A
thresholds: []
timeFrom:
timeShift:
title: Go Garbage collection duration
tooltip:
shared: true
sort: 0
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: s
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 37
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(prometheus_tsdb_wal_truncate_duration_seconds{instance="$instance"})
by (instance, quantile)
format: time_series
intervalFactor: 2
legendFormat: "{{ quantile }} on {{ instance }}"
refId: A
thresholds: []
timeFrom:
timeShift:
title: WAL truncate duration seconds
tooltip:
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
fill: 1
id: 38
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: connected
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 3
stack: false
steppedLine: false
targets:
- expr: sum(tsdb_wal_fsync_duration_seconds{instance="$instance"}) by (instance,
quantile)
format: time_series
intervalFactor: 2
legendFormat: "{{ quantile }} {{ instance }}"
refId: A
thresholds: []
timeFrom:
timeShift:
title: WAL fsync duration seconds
tooltip:
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: s
label:
logBase: 1
max:
min:
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: true
title: Data maintenance
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors:
Allocated bytes: "#7EB26D"
Allocated bytes - 1m max: "#BF1B00"
Allocated bytes - 1m min: "#BF1B00"
Allocated bytes - 5m max: "#BF1B00"
Allocated bytes - 5m min: "#BF1B00"
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
RSS: "#447EBC"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
decimals:
editable: true
error: false
fill: 1
id: 6
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides:
- alias: "/-/"
fill: 0
- alias: collector heap size
color: "#E0752D"
fill: 0
linewidth: 2
- alias: collector kubernetes memory limit
color: "#BF1B00"
fill: 0
linewidth: 3
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(process_resident_memory_bytes{instance="$instance"}) by (instance)
format: time_series
hide: false
intervalFactor: 2
legendFormat: Total resident memory - {{instance}}
metric: process_resident_memory_bytes
refId: B
step: 1800
- expr: sum(go_memstats_alloc_bytes{instance="$instance"}) by (instance)
format: time_series
hide: false
intervalFactor: 2
legendFormat: Total llocated bytes - {{instance}}
metric: go_memstats_alloc_bytes
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Memory
tooltip:
msResolution: false
shared: true
sort: 2
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
- aliasColors:
Allocated bytes: "#F9BA8F"
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
RSS: "#890F02"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 7
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: rate(go_memstats_alloc_bytes_total{instance="$instance"}[$aggregation_interval])
format: time_series
intervalFactor: 2
legendFormat: Allocated Bytes/s
metric: go_memstats_alloc_bytes
refId: A
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Allocations per second
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: bytes
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
- aliasColors: {}
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
decimals: 2
editable: true
error: false
fill: 1
id: 9
legend:
alignAsTable: false
avg: false
current: false
hideEmpty: false
max: false
min: false
rightSide: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 4
stack: false
steppedLine: false
targets:
- expr: sum(rate(process_cpu_seconds_total{instance="$instance"}[$aggregation_interval]))
by (instance)
format: time_series
intervalFactor: 2
legendFormat: CPU/s
metric: prometheus_local_storage_ingested_samples_total
refId: B
step: 1800
thresholds: []
timeFrom:
timeShift:
title: CPU per second
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values:
- avg
yaxes:
- format: none
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: true
title: RAM&CPU
titleSize: h6
- collapse: false
height: 250
panels:
- aliasColors:
Chunks: "#1F78C1"
Chunks to persist: "#508642"
Max chunks: "#052B51"
Max to persist: "#3F6833"
bars: false
dashLength: 10
dashes: false
datasource: "${DS_PROMETHEUS}"
editable: true
error: false
fill: 1
id: 47
legend:
avg: false
current: false
max: false
min: false
show: false
total: false
values: false
lines: true
linewidth: 1
links: []
nullPointMode: 'null'
percentage: false
pointradius: 5
points: false
renderer: flot
seriesOverrides: []
spaceLength: 10
span: 12
stack: false
steppedLine: false
targets:
- expr: sum(increase(net_conntrack_dialer_conn_failed_total{instance="$instance"}[$aggregation_interval]))
by (instance) > 0
format: time_series
hide: false
interval: ''
intervalFactor: 2
legendFormat: conntrack_dialer_conn_failed on {{ instance }}
metric: prometheus_local_storage_chunk_ops_total
refId: M
step: 1800
thresholds: []
timeFrom:
timeShift:
title: Net errors
tooltip:
msResolution: false
shared: true
sort: 2
value_type: individual
type: graph
xaxis:
buckets:
mode: time
name:
show: true
values: []
yaxes:
- format: short
label:
logBase: 1
max:
min: '0'
show: true
- format: short
label:
logBase: 1
max:
min:
show: true
repeat:
repeatIteration:
repeatRowId:
showTitle: true
title: Contrac errors
titleSize: h6
schemaVersion: 14
style: dark
tags:
- prometheus
templating:
list:
- auto: true
auto_count: 30
auto_min: 2m
current:
text: auto
value: "$__auto_interval"
hide: 0
label: aggregation intarval
name: aggregation_interval
options:
- selected: true
text: auto
value: "$__auto_interval"
- selected: false
text: 1m
value: 1m
- selected: false
text: 10m
value: 10m
- selected: false
text: 30m
value: 30m
- selected: false
text: 1h
value: 1h
- selected: false
text: 6h
value: 6h
- selected: false
text: 12h
value: 12h
- selected: false
text: 1d
value: 1d
- selected: false
text: 7d
value: 7d
- selected: false
text: 14d
value: 14d
- selected: false
text: 30d
value: 30d
query: 1m,10m,30m,1h,6h,12h,1d,7d,14d,30d
refresh: 2
type: interval
- allValue:
current: {}
datasource: "${DS_PROMETHEUS}"
hide: 0
includeAll: false
label: Instance
multi: false
name: instance
options: []
query: label_values(prometheus_build_info, instance)
refresh: 2
regex: ''
sort: 2
tagValuesQuery: ''
tags: []
tagsQuery: ''
type: query
useTags: false
- current:
text: Prometheus
value: Prometheus
hide: 0
label: Prometheus datasource
name: DS_PROMETHEUS
options: []
query: prometheus
refresh: 1
regex: ''
type: datasource
- current:
text: influxdb(heapster) - kokura
value: influxdb(heapster) - kokura
hide: 0
label: InfluxDB datasource
name: influx_datasource
options: []
query: influxdb
refresh: 1
regex: ''
type: datasource
time:
from: now-7d
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: Prometheus2.0 (v1.0.0 by FUSAKLA)
version: 8