Update mixin dashboards and alerts for new remote write label names.

Signed-off-by: Callum Styan <callumstyan@gmail.com>
This commit is contained in:
Callum Styan 2020-04-08 12:56:00 -07:00
parent 9a21fdcd1b
commit 5400e71b91
2 changed files with 22 additions and 22 deletions

View file

@ -187,7 +187,7 @@
}, },
annotations: { annotations: {
summary: 'Prometheus fails to send samples to remote storage.', summary: 'Prometheus fails to send samples to remote storage.',
description: 'Prometheus %(prometheusName)s failed to send {{ printf "%%.1f" $value }}%% of the samples to {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.' % $._config, description: 'Prometheus %(prometheusName)s failed to send {{ printf "%%.1f" $value }}%% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}' % $._config,
}, },
}, },
{ {
@ -208,7 +208,7 @@
}, },
annotations: { annotations: {
summary: 'Prometheus remote write is behind.', summary: 'Prometheus remote write is behind.',
description: 'Prometheus %(prometheusName)s remote write is {{ printf "%%.1f" $value }}s behind for {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.' % $._config, description: 'Prometheus %(prometheusName)s remote write is {{ printf "%%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.' % $._config,
}, },
}, },
{ {
@ -228,7 +228,7 @@
}, },
annotations: { annotations: {
summary: 'Prometheus remote write desired shards calculation wants to run more than configured max shards.', summary: 'Prometheus remote write desired shards calculation wants to run more than configured max shards.',
description: 'Prometheus %(prometheusName)s remote write desired shards calculation wants to run {{ $value }} shards, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%%s",%(prometheusSelector)s}` $labels.instance | query | first | value }}.' % $._config, description: 'Prometheus %(prometheusName)s remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%%s",%(prometheusSelector)s}` $labels.instance | query | first | value }}.' % $._config,
}, },
}, },
{ {

View file

@ -110,10 +110,10 @@ local template = grafana.template;
( (
prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~"$cluster", instance=~"$instance"} prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~"$cluster", instance=~"$instance"}
- -
ignoring(queue) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~"$cluster", instance=~"$instance"} ignoring(remote_name, url) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~"$cluster", instance=~"$instance"}
) )
|||, |||,
legendFormat='{{cluster}}:{{instance}}-{{queue}}', legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}',
)); ));
local timestampComparisonRate = local timestampComparisonRate =
@ -127,10 +127,10 @@ local template = grafana.template;
( (
rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~"$cluster", instance=~"$instance"}[5m]) rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~"$cluster", instance=~"$instance"}[5m])
- -
ignoring (queue) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~"$cluster", instance=~"$instance"}[5m]) ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~"$cluster", instance=~"$instance"}[5m])
) )
|||, |||,
legendFormat='{{cluster}}:{{instance}}-{{queue}}', legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}',
)); ));
local samplesRate = local samplesRate =
@ -144,11 +144,11 @@ local template = grafana.template;
rate( rate(
prometheus_remote_storage_samples_in_total{cluster=~"$cluster", instance=~"$instance"}[5m]) prometheus_remote_storage_samples_in_total{cluster=~"$cluster", instance=~"$instance"}[5m])
- -
ignoring(queue) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m]) ignoring(remote_name, url) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m])
- -
rate(prometheus_remote_storage_dropped_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m]) rate(prometheus_remote_storage_dropped_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m])
|||, |||,
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local currentShards = local currentShards =
@ -160,7 +160,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'prometheus_remote_storage_shards{cluster=~"$cluster", instance=~"$instance"}', 'prometheus_remote_storage_shards{cluster=~"$cluster", instance=~"$instance"}',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local maxShards = local maxShards =
@ -171,7 +171,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'prometheus_remote_storage_shards_max{cluster=~"$cluster", instance=~"$instance"}', 'prometheus_remote_storage_shards_max{cluster=~"$cluster", instance=~"$instance"}',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local minShards = local minShards =
@ -182,7 +182,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'prometheus_remote_storage_shards_min{cluster=~"$cluster", instance=~"$instance"}', 'prometheus_remote_storage_shards_min{cluster=~"$cluster", instance=~"$instance"}',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local desiredShards = local desiredShards =
@ -193,7 +193,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'prometheus_remote_storage_shards_desired{cluster=~"$cluster", instance=~"$instance"}', 'prometheus_remote_storage_shards_desired{cluster=~"$cluster", instance=~"$instance"}',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local shardsCapacity = local shardsCapacity =
@ -204,7 +204,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'prometheus_remote_storage_shard_capacity{cluster=~"$cluster", instance=~"$instance"}', 'prometheus_remote_storage_shard_capacity{cluster=~"$cluster", instance=~"$instance"}',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
@ -216,7 +216,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'prometheus_remote_storage_pending_samples{cluster=~"$cluster", instance=~"$instance"}', 'prometheus_remote_storage_pending_samples{cluster=~"$cluster", instance=~"$instance"}',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local walSegment = local walSegment =
@ -240,7 +240,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'prometheus_wal_watcher_current_segment{cluster=~"$cluster", instance=~"$instance"}', 'prometheus_wal_watcher_current_segment{cluster=~"$cluster", instance=~"$instance"}',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{consumer}}'
)); ));
local droppedSamples = local droppedSamples =
@ -251,7 +251,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'rate(prometheus_remote_storage_dropped_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m])', 'rate(prometheus_remote_storage_dropped_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m])',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local failedSamples = local failedSamples =
@ -262,7 +262,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'rate(prometheus_remote_storage_failed_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m])', 'rate(prometheus_remote_storage_failed_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m])',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local retriedSamples = local retriedSamples =
@ -273,7 +273,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'rate(prometheus_remote_storage_retried_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m])', 'rate(prometheus_remote_storage_retried_samples_total{cluster=~"$cluster", instance=~"$instance"}[5m])',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
local enqueueRetries = local enqueueRetries =
@ -284,7 +284,7 @@ local template = grafana.template;
) )
.addTarget(prometheus.target( .addTarget(prometheus.target(
'rate(prometheus_remote_storage_enqueue_retries_total{cluster=~"$cluster", instance=~"$instance"}[5m])', 'rate(prometheus_remote_storage_enqueue_retries_total{cluster=~"$cluster", instance=~"$instance"}[5m])',
legendFormat='{{cluster}}:{{instance}}-{{queue}}' legendFormat='{{cluster}}:{{instance}} {{remote_name}}:{{url}}'
)); ));
dashboard.new('Prometheus Remote Write', dashboard.new('Prometheus Remote Write',
@ -331,9 +331,9 @@ local template = grafana.template;
) )
.addTemplate( .addTemplate(
template.new( template.new(
'queue', 'url',
'$datasource', '$datasource',
'label_values(prometheus_remote_storage_shards{cluster=~"$cluster", instance=~"$instance"}, queue)' % $._config, 'label_values(prometheus_remote_storage_shards{cluster=~"$cluster", instance=~"$instance"}, url)' % $._config,
refresh='time', refresh='time',
includeAll=true, includeAll=true,
) )