Skip to content

Use timeseriesPanel instead of panel when creating panels #58

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

Merged
merged 8 commits into from
Oct 23, 2024
Merged

Use timeseriesPanel instead of panel when creating panels #58

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
2c32038
Update jsonnet-libs to Fri Jul 19 12:51:49 2024
CharlieTLe Jul 21, 2024
cbf13ef
Use `timeseriesPanel` instead of `panel` when creating panels
CharlieTLe Jul 21, 2024
377f7b4
Merge branch 'main' into update-panel-to-timeseries-panel
friedrichg Aug 20, 2024
78e8e56
Merge branch 'main' into update-panel-to-timeseries-panel
CharlieTLe Sep 8, 2024
3ab33de
Merge branch 'main' into update-panel-to-timeseries-panel
CharlieTLe Oct 10, 2024
f6a9025
Add units to timeseries panel
CharlieTLe Oct 18, 2024
873b4fb
Merge branch 'main' into update-panel-to-timeseries-panel
friedrichg Oct 23, 2024
9680459
Update CHANGELOG.md
friedrichg Oct 23, 2024
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 @@ -7,6 +7,7 @@
* [CHANGE] Target 3M memory series per ingester instead of 1.5M
* [CHANGE] Update jsonnet-libs to Fri Jul 19 12:51:49 2024 #57
* [CHANGE] Increase CortexProvisioningTooManyWrites alert threshold to 160e3
* [CHANGE] Use `timeseriesPanel` instead of `panel` when creating panels #58
* [ENHANCEMENT] Configure `-ingester.client.grpc-compression` to be `snappy-block`
* [ENHANCEMENT] Support Grafana 11 in Cortex Service Scaling Dashboard
* [BUGFIX] Remove deprecated option `max_series_per_query`
Expand Down
42 changes: 21 additions & 21 deletions cortex-mixin/dashboards/alertmanager.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,22 +10,22 @@ local utils = import 'mixin-utils/utils.libsonnet';
showTitle: false,
})
.addPanel(
$.panel('Total Alerts') +
$.timeseriesPanel('Total Alerts') +
$.statPanel('sum(cluster_job_%s:cortex_alertmanager_alerts:sum{%s})' % [$._config.per_instance_label, $.jobMatcher($._config.job_names.alertmanager)], format='short')
)
.addPanel(
$.panel('Total Silences') +
$.timeseriesPanel('Total Silences') +
$.statPanel('sum(cluster_job_%s:cortex_alertmanager_silences:sum{%s})' % [$._config.per_instance_label, $.jobMatcher($._config.job_names.alertmanager)], format='short')
)
.addPanel(
$.panel('Tenants') +
$.timeseriesPanel('Tenants') +
$.statPanel('max(cortex_alertmanager_tenants_discovered{%s})' % $.jobMatcher($._config.job_names.alertmanager), format='short')
)
)
.addRow(
$.row('Alerts Received')
.addPanel(
$.panel('APS') +
$.timeseriesPanel('APS') +
$.queryPanel(
[
|||
Expand All @@ -42,7 +42,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('Alert Notifications')
.addPanel(
$.panel('NPS') +
$.timeseriesPanel('NPS') +
$.queryPanel(
[
|||
Expand All @@ -56,7 +56,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
)
)
.addPanel(
$.panel('NPS by integration') +
$.timeseriesPanel('NPS by integration') +
$.queryPanel(
[
|||
Expand All @@ -73,18 +73,18 @@ local utils = import 'mixin-utils/utils.libsonnet';
)
)
.addPanel(
$.panel('Latency') +
$.timeseriesPanel('Latency', unit='ms') +
$.latencyPanel('cortex_alertmanager_notification_latency_seconds', '{%s}' % $.jobMatcher($._config.job_names.alertmanager))
)
)
.addRow(
$.row('Configuration API (gateway) + Alertmanager UI')
.addPanel(
$.panel('QPS') +
$.timeseriesPanel('QPS') +
$.qpsPanel('cortex_request_duration_seconds_count{%s, route=~"api_v1_alerts|alertmanager"}' % $.jobMatcher($._config.job_names.gateway))
)
.addPanel(
$.panel('Latency') +
$.timeseriesPanel('Latency', unit='ms') +
utils.latencyRecordingRulePanel('cortex_request_duration_seconds', $.jobSelector($._config.job_names.gateway) + [utils.selector.re('route', 'api_v1_alerts|alertmanager')])
)
)
Expand All @@ -94,23 +94,23 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('Replication')
.addPanel(
$.panel('Per %s Tenants' % $._config.per_instance_label) +
$.timeseriesPanel('Per %s Tenants' % $._config.per_instance_label) +
$.queryPanel(
'max by(%s) (cortex_alertmanager_tenants_owned{%s})' % [$._config.per_instance_label, $.jobMatcher($._config.job_names.alertmanager)],
'{{%s}}' % $._config.per_instance_label
) +
$.stack
)
.addPanel(
$.panel('Per %s Alerts' % $._config.per_instance_label) +
$.timeseriesPanel('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, $.jobMatcher($._config.job_names.alertmanager)],
'{{%s}}' % $._config.per_instance_label
) +
$.stack
)
.addPanel(
$.panel('Per %s Silences' % $._config.per_instance_label) +
$.timeseriesPanel('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, $.jobMatcher($._config.job_names.alertmanager)],
'{{%s}}' % $._config.per_instance_label
Expand All @@ -121,7 +121,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('Tenant Configuration Sync')
.addPanel(
$.panel('Syncs/sec') +
$.timeseriesPanel('Syncs/sec') +
$.queryPanel(
[
|||
Expand All @@ -135,14 +135,14 @@ local utils = import 'mixin-utils/utils.libsonnet';
)
)
.addPanel(
$.panel('Syncs/sec (By Reason)') +
$.timeseriesPanel('Syncs/sec (By Reason)') +
$.queryPanel(
'sum by(reason) (rate(cortex_alertmanager_sync_configs_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
'{{reason}}'
)
)
.addPanel(
$.panel('Ring Check Errors/sec') +
$.timeseriesPanel('Ring Check Errors/sec') +
$.queryPanel(
'sum (rate(cortex_alertmanager_ring_check_errors_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
'errors'
Expand All @@ -152,7 +152,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('Sharding Initial State Sync')
.addPanel(
$.panel('Initial syncs /sec') +
$.timeseriesPanel('Initial syncs /sec') +
$.queryPanel(
'sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.alertmanager),
'{{outcome}}'
Expand All @@ -166,7 +166,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
}
)
.addPanel(
$.panel('Initial sync duration') +
$.timeseriesPanel('Initial sync duration', unit='s') +
$.latencyPanel('cortex_alertmanager_state_initial_sync_duration_seconds', '{%s}' % $.jobMatcher($._config.job_names.alertmanager)) + {
targets: [
target {
Expand All @@ -177,7 +177,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
}
)
.addPanel(
$.panel('Fetch state from other alertmanagers /sec') +
$.timeseriesPanel('Fetch state from other alertmanagers /sec') +
$.queryPanel(
[
|||
Expand All @@ -201,7 +201,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('Sharding Runtime State Sync')
.addPanel(
$.panel('Replicate state to other alertmanagers /sec') +
$.timeseriesPanel('Replicate state to other alertmanagers /sec') +
$.queryPanel(
[
|||
Expand All @@ -215,7 +215,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
)
)
.addPanel(
$.panel('Merge state from other alertmanagers /sec') +
$.timeseriesPanel('Merge state from other alertmanagers /sec') +
$.queryPanel(
[
|||
Expand All @@ -229,7 +229,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
)
)
.addPanel(
$.panel('Persist state to remote storage /sec') +
$.timeseriesPanel('Persist state to remote storage /sec') +
$.queryPanel(
[
|||
Expand Down
19 changes: 8 additions & 11 deletions cortex-mixin/dashboards/compactor.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@ local utils = import 'mixin-utils/utils.libsonnet';
'sum(rate(cortex_compactor_runs_failed_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.compactor)
) +
$.bars +
{ yaxes: $.yaxes('ops') } +
$.panelDescription(
'Per-instance runs',
|||
Expand All @@ -23,7 +22,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
),
)
.addPanel(
$.panel('Tenants compaction progress') +
$.timeseriesPanel('Tenants compaction progress') +
$.queryPanel(|||
(
cortex_compactor_tenants_processing_succeeded{%s} +
Expand All @@ -44,9 +43,8 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('')
.addPanel(
$.panel('Compacted blocks / sec') +
$.timeseriesPanel('Compacted blocks / sec', unit='ops') +
$.queryPanel('sum(rate(prometheus_tsdb_compactions_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.compactor), 'blocks') +
{ yaxes: $.yaxes('ops') } +
$.panelDescription(
'Compacted blocks / sec',
|||
Expand All @@ -55,7 +53,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
),
)
.addPanel(
$.panel('Per-block compaction duration') +
$.timeseriesPanel('Per-block compaction duration', unit='s') +
$.latencyPanel('prometheus_tsdb_compaction_duration_seconds', '{%s}' % $.jobMatcher($._config.job_names.compactor)) +
$.panelDescription(
'Per-block compaction duration',
Expand All @@ -68,11 +66,11 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('')
.addPanel(
$.panel('Average blocks / tenant') +
$.timeseriesPanel('Average blocks / tenant') +
$.queryPanel('avg(max by(user) (cortex_bucket_blocks_count{%s}))' % $.jobMatcher($._config.job_names.compactor), 'avg'),
)
.addPanel(
$.panel('Tenants with largest number of blocks') +
$.timeseriesPanel('Tenants with largest number of blocks') +
$.queryPanel('topk(10, max by(user) (cortex_bucket_blocks_count{%s}))' % $.jobMatcher($._config.job_names.compactor), '{{user}}') +
$.panelDescription(
'Tenants with largest number of blocks',
Expand All @@ -85,9 +83,8 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('Garbage Collector')
.addPanel(
$.panel('Blocks marked for deletion / sec') +
$.queryPanel('sum(rate(cortex_compactor_blocks_marked_for_deletion_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.compactor), 'blocks') +
{ yaxes: $.yaxes('ops') },
$.timeseriesPanel('Blocks marked for deletion / sec', unit='ops') +
$.queryPanel('sum(rate(cortex_compactor_blocks_marked_for_deletion_total{%s}[$__rate_interval]))' % $.jobMatcher($._config.job_names.compactor), 'blocks'),
)
.addPanel(
$.successFailurePanel(
Expand All @@ -111,7 +108,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
) + { yaxes: $.yaxes('ops') }
)
.addPanel(
$.panel('Metadata Sync Duration') +
$.timeseriesPanel('Metadata Sync Duration', unit='ms') +
// This metric tracks the duration of a per-tenant metadata sync.
$.latencyPanel('cortex_compactor_meta_sync_duration_seconds', '{%s}' % $.jobMatcher($._config.job_names.compactor)),
)
Expand Down
10 changes: 4 additions & 6 deletions cortex-mixin/dashboards/config.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,19 +8,17 @@ local utils = import 'mixin-utils/utils.libsonnet';
.addRow(
$.row('Startup config file')
.addPanel(
$.panel('Startup config file hashes') +
$.timeseriesPanel('Startup config file hashes', unit='instances') +
$.queryPanel('count(cortex_config_hash{%s}) by (sha256)' % $.namespaceMatcher(), 'sha256:{{sha256}}') +
$.stack +
{ yaxes: $.yaxes('instances') },
$.stack,
)
)
.addRow(
$.row('Runtime config file')
.addPanel(
$.panel('Runtime config file hashes') +
$.timeseriesPanel('Runtime config file hashes', unit='instances') +
$.queryPanel('count(cortex_runtime_config_hash{%s}) by (sha256)' % $.namespaceMatcher(), 'sha256:{{sha256}}') +
$.stack +
{ yaxes: $.yaxes('instances') },
$.stack,
)
),
}
Loading