Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

use alertmanager jobname for alertmanager dashboard panels #411

Merged
merged 3 commits into from
Oct 22, 2021
+29 −27
Merged

use alertmanager jobname for alertmanager dashboard panels #411

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7f7debe
use alertmanager jobname for alertmanager dashboard panels
aallawala Oct 18, 2021
ad49d11
add changelog entry
aallawala Oct 18, 2021
d804539
Update cortex-mixin/config.libsonnet
aallawala Oct 20, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,7 @@
* [ENHANCEMENT] Added `CortexKVStoreFailure` alert. #406
* [ENHANCEMENT] Use configured `ruler` jobname for ruler dashboard panels. #409
* [ENHANCEMENT] Add ability to override `datasource` for generated dashboards. #407
* [ENHANCEMENT] Use alertmanager jobname for alertmanager dashboard panels #411
* [BUGFIX] Fixed `CortexIngesterHasNotShippedBlocks` alert false positive in case an ingester instance had ingested samples in the past, then no traffic was received for a long period and then it started receiving samples again. #308
* [BUGFIX] Alertmanager: fixed `--alertmanager.cluster.peers` CLI flag passed to alertmanager when HA is enabled. #329
* [BUGFIX] Fixed `CortexInconsistentRuntimeConfig` metric. #335
Expand Down
1 change: 1 addition & 0 deletions cortex-mixin/config.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
store_gateway: '(store-gateway|cortex$)',
gateway: '(gateway|cortex-gw|cortex-gw-internal)',
compactor: 'compactor.*', // Match also custom compactor deployments.
alertmanager: 'alertmanager',
},

// Grouping labels, to uniquely identify and group by {jobs, clusters}
Expand Down
54 changes: 27 additions & 27 deletions cortex-mixin/dashboards/alertmanager.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,15 +11,15 @@ local utils = import 'mixin-utils/utils.libsonnet';
})
.addPanel(
$.panel('Total Alerts') +
$.statPanel('sum(cluster_job_%s:cortex_alertmanager_alerts:sum{%s})' % [$._config.per_instance_label, $.jobMatcher('alertmanager')], format='short')
$.statPanel('sum(cluster_job_%s:cortex_alertmanager_alerts:sum{%s})' % [$._config.per_instance_label, $.jobMatcher($._config.job_names.alertmanager)], format='short')
)
.addPanel(
$.panel('Total Silences') +
$.statPanel('sum(cluster_job_%s:cortex_alertmanager_silences:sum{%s})' % [$._config.per_instance_label, $.jobMatcher('alertmanager')], format='short')
$.statPanel('sum(cluster_job_%s:cortex_alertmanager_silences:sum{%s})' % [$._config.per_instance_label, $.jobMatcher($._config.job_names.alertmanager)], format='short')
)
.addPanel(
$.panel('Tenants') +
$.statPanel('max(cortex_alertmanager_tenants_discovered{%s})' % $.jobMatcher('alertmanager'), format='short')
$.statPanel('max(cortex_alertmanager_tenants_discovered{%s})' % $.jobMatcher($._config.job_names.alertmanager), format='short')
)
)
.addRow(
Expand All @@ -32,8 +32,8 @@ local utils = import 'mixin-utils/utils.libsonnet';
sum(cluster_job:cortex_alertmanager_alerts_received_total:rate5m{%s})
-
sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{%s})
||| % [$.jobMatcher('alertmanager'), $.jobMatcher('alertmanager')],
'sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{%s})' % $.jobMatcher('alertmanager'),
||| % [$.jobMatcher($._config.job_names.alertmanager), $.jobMatcher($._config.job_names.alertmanager)],
'sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{%s})' % $.jobMatcher($._config.job_names.alertmanager),
],
['success', 'failed']
)
Expand All @@ -49,8 +49,8 @@ local utils = import 'mixin-utils/utils.libsonnet';
sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{%s})
-
sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{%s})
||| % [$.jobMatcher('alertmanager'), $.jobMatcher('alertmanager')],
'sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{%s})' % $.jobMatcher('alertmanager'),
||| % [$.jobMatcher($._config.job_names.alertmanager), $.jobMatcher($._config.job_names.alertmanager)],
'sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{%s})' % $.jobMatcher($._config.job_names.alertmanager),
],
['success', 'failed']
)
Expand All @@ -66,15 +66,15 @@ local utils = import 'mixin-utils/utils.libsonnet';
sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{%s}) by(integration)
) > 0
or on () vector(0)
||| % [$.jobMatcher('alertmanager'), $.jobMatcher('alertmanager')],
'sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{%s}) by(integration)' % $.jobMatcher('alertmanager'),
||| % [$.jobMatcher($._config.job_names.alertmanager), $.jobMatcher($._config.job_names.alertmanager)],
'sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{%s}) by(integration)' % $.jobMatcher($._config.job_names.alertmanager),
],
['success - {{ integration }}', 'failed - {{ integration }}']
)
)
.addPanel(
$.panel('Latency') +
$.latencyPanel('cortex_alertmanager_notification_latency_seconds', '{%s}' % $.jobMatcher('alertmanager'))
$.latencyPanel('cortex_alertmanager_notification_latency_seconds', '{%s}' % $.jobMatcher($._config.job_names.alertmanager))
)
)
.addRow(
Expand All @@ -96,23 +96,23 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addPanel(
$.panel('Per %s Tenants' % $._config.per_instance_label) +
$.queryPanel(
'max by(%s) (cortex_alertmanager_tenants_owned{%s})' % [$._config.per_instance_label, $.jobMatcher('alertmanager')],
'max by(%s) (cortex_alertmanager_tenants_owned{%s})' % [$._config.per_instance_label, $.jobMatcher($._config.job_names.alertmanager)],
'{{%s}}' % $._config.per_instance_label
) +
$.stack
)
.addPanel(
$.panel('Per %s Alerts' % $._config.per_instance_label) +
$.queryPanel(
'sum by(%s) (cluster_job_%s:cortex_alertmanager_alerts:sum{%s})' % [$._config.per_instance_label, $._config.per_instance_label, $.jobMatcher('alertmanager')],
'sum by(%s) (cluster_job_%s:cortex_alertmanager_alerts:sum{%s})' % [$._config.per_instance_label, $._config.per_instance_label, $.jobMatcher($._config.job_names.alertmanager)],
'{{%s}}' % $._config.per_instance_label
) +
$.stack
)
.addPanel(
$.panel('Per %s Silences' % $._config.per_instance_label) +
$.queryPanel(
'sum by(%s) (cluster_job_%s:cortex_alertmanager_silences:sum{%s})' % [$._config.per_instance_label, $._config.per_instance_label, $.jobMatcher('alertmanager')],
'sum by(%s) (cluster_job_%s:cortex_alertmanager_silences:sum{%s})' % [$._config.per_instance_label, $._config.per_instance_label, $.jobMatcher($._config.job_names.alertmanager)],
'{{%s}}' % $._config.per_instance_label
) +
$.stack
Expand All @@ -128,23 +128,23 @@ local utils = import 'mixin-utils/utils.libsonnet';
sum(rate(cortex_alertmanager_sync_configs_total{%s}[$__rate_interval]))
-
sum(rate(cortex_alertmanager_sync_configs_failed_total{%s}[$__rate_interval]))
||| % [$.jobMatcher('alertmanager'), $.jobMatcher('alertmanager')],
'sum(rate(cortex_alertmanager_sync_configs_failed_total{%s}[$__rate_interval]))' % $.jobMatcher('alertmanager'),
||| % [$.jobMatcher($._config.job_names.alertmanager), $.jobMatcher($._config.job_names.alertmanager)],
'sum(rate(cortex_alertmanager_sync_configs_failed_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
],
['success', 'failed']
)
)
.addPanel(
$.panel('Syncs/sec (By Reason)') +
$.queryPanel(
'sum by(reason) (rate(cortex_alertmanager_sync_configs_total{%s}[$__rate_interval]))' % $.jobMatcher('alertmanager'),
'sum by(reason) (rate(cortex_alertmanager_sync_configs_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
'{{reason}}'
)
)
.addPanel(
$.panel('Ring Check Errors/sec') +
$.queryPanel(
'sum (rate(cortex_alertmanager_ring_check_errors_total{%s}[$__rate_interval]))' % $.jobMatcher('alertmanager'),
'sum (rate(cortex_alertmanager_ring_check_errors_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
'errors'
)
)
Expand All @@ -154,7 +154,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addPanel(
$.panel('Initial syncs /sec') +
$.queryPanel(
'sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{%s}[$__rate_interval]))' % $.jobMatcher('alertmanager'),
'sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
'{{outcome}}'
) + {
targets: [
Expand All @@ -167,7 +167,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
)
.addPanel(
$.panel('Initial sync duration') +
$.latencyPanel('cortex_alertmanager_state_initial_sync_duration_seconds', '{%s}' % $.jobMatcher('alertmanager')) + {
$.latencyPanel('cortex_alertmanager_state_initial_sync_duration_seconds', '{%s}' % $.jobMatcher($._config.job_names.alertmanager)) + {
targets: [
target {
interval: '1m',
Expand All @@ -184,8 +184,8 @@ local utils = import 'mixin-utils/utils.libsonnet';
sum(rate(cortex_alertmanager_state_fetch_replica_state_total{%s}[$__rate_interval]))
-
sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{%s}[$__rate_interval]))
||| % [$.jobMatcher('alertmanager'), $.jobMatcher('alertmanager')],
'sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{%s}[$__rate_interval]))' % $.jobMatcher('alertmanager'),
||| % [$.jobMatcher($._config.job_names.alertmanager), $.jobMatcher($._config.job_names.alertmanager)],
'sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
],
['success', 'failed']
) + {
Expand All @@ -208,8 +208,8 @@ local utils = import 'mixin-utils/utils.libsonnet';
sum(cluster_job:cortex_alertmanager_state_replication_total:rate5m{%s})
-
sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{%s})
||| % [$.jobMatcher('alertmanager'), $.jobMatcher('alertmanager')],
'sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{%s})' % $.jobMatcher('alertmanager'),
||| % [$.jobMatcher($._config.job_names.alertmanager), $.jobMatcher($._config.job_names.alertmanager)],
'sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{%s})' % $.jobMatcher($._config.job_names.alertmanager),
],
['success', 'failed']
)
Expand All @@ -222,8 +222,8 @@ local utils = import 'mixin-utils/utils.libsonnet';
sum(cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m{%s})
-
sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{%s})
||| % [$.jobMatcher('alertmanager'), $.jobMatcher('alertmanager')],
'sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{%s})' % $.jobMatcher('alertmanager'),
||| % [$.jobMatcher($._config.job_names.alertmanager), $.jobMatcher($._config.job_names.alertmanager)],
'sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{%s})' % $.jobMatcher($._config.job_names.alertmanager),
],
['success', 'failed']
)
Expand All @@ -236,8 +236,8 @@ local utils = import 'mixin-utils/utils.libsonnet';
sum(rate(cortex_alertmanager_state_persist_total{%s}[$__rate_interval]))
-
sum(rate(cortex_alertmanager_state_persist_failed_total{%s}[$__rate_interval]))
||| % [$.jobMatcher('alertmanager'), $.jobMatcher('alertmanager')],
'sum(rate(cortex_alertmanager_state_persist_failed_total{%s}[$__rate_interval]))' % $.jobMatcher('alertmanager'),
||| % [$.jobMatcher($._config.job_names.alertmanager), $.jobMatcher($._config.job_names.alertmanager)],
'sum(rate(cortex_alertmanager_state_persist_failed_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
],
['success', 'failed']
)
Expand Down