@@ -94,26 +94,26 @@ local utils = import 'mixin-utils/utils.libsonnet';
94
94
.addRow(
95
95
$.row('Replication' )
96
96
.addPanel(
97
- $.panel('Tenants (By Instance)' ) +
97
+ $.panel('Per %s Tenants' % $._config.per_instance_label ) +
98
98
$.queryPanel(
99
- 'sum by(pod ) (cortex_alertmanager_tenants_owned{%s})' % $. jobMatcher('alertmanager' ),
100
- '{{pod }}'
99
+ 'max by(%s ) (cortex_alertmanager_tenants_owned{%s})' % [$._config.per_instance_label, $. jobMatcher('alertmanager' )] ,
100
+ '{{%s }}' % $._config.per_instance_label
101
101
) +
102
102
$.stack
103
103
)
104
104
.addPanel(
105
- $.panel('Alerts (By Instance)' ) +
105
+ $.panel('Per %s Alerts' % $._config.per_instance_label ) +
106
106
$.queryPanel(
107
- 'sum by(pod ) (cortex_alertmanager_alerts{%s})' % $. jobMatcher('alertmanager' ),
108
- '{{pod }}'
107
+ 'sum by(%s ) (cortex_alertmanager_alerts{%s})' % [$._config.per_instance_label, $. jobMatcher('alertmanager' )] ,
108
+ '{{%s }}' % $._config.per_instance_label
109
109
) +
110
110
$.stack
111
111
)
112
112
.addPanel(
113
- $.panel('Silences (By Instance)' ) +
113
+ $.panel('Per %s Silences' % $._config.per_instance_label ) +
114
114
$.queryPanel(
115
- 'sum by(pod ) (cortex_alertmanager_silences{%s})' % $. jobMatcher('alertmanager' ),
116
- '{{pod }}'
115
+ 'sum by(%s ) (cortex_alertmanager_silences{%s})' % [$._config.per_instance_label, $. jobMatcher('alertmanager' )] ,
116
+ '{{%s }}' % $._config.per_instance_label
117
117
) +
118
118
$.stack
119
119
)
@@ -150,37 +150,20 @@ local utils = import 'mixin-utils/utils.libsonnet';
150
150
)
151
151
)
152
152
.addRow(
153
- $.row('Sharding Initial State Sync' )
153
+ $.row('Sharding Runtime State Sync' )
154
154
.addPanel(
155
155
$.panel('Syncs/sec' ) +
156
- $.queryPanel(
157
- [
158
- |||
159
- sum(rate(cortex_alertmanager_state_initial_sync_total{%s}[$__rate_interval]))
160
- -
161
- sum(rate(cortex_alertmanager_state_initial_sync_completed_total{outcome="failed",%s}[$__rate_interval]))
162
- ||| % [$.jobMatcher('alertmanager' ), $.jobMatcher('alertmanager' )],
163
- 'sum(rate(cortex_alertmanager_state_initial_sync_completed_total{outcome="failed",%s}[$__rate_interval]))' % $.jobMatcher('alertmanager' ),
164
- ],
165
- ['success' , 'failed' ]
166
- )
167
- )
168
- .addPanel(
169
- $.panel('Syncs/sec (By Outcome)' ) +
170
156
$.queryPanel(
171
157
'sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{%s}[$__rate_interval]))' % $.jobMatcher('alertmanager' ),
172
158
'{{outcome}}'
173
159
)
174
160
)
175
161
.addPanel(
176
- $.panel('Duration ' ) +
177
- utils.latencyRecordingRulePanel ('cortex_alertmanager_state_initial_sync_duration_seconds' , $.jobSelector ('alertmanager' ))
162
+ $.panel('Sync duration ' ) +
163
+ $.latencyPanel ('cortex_alertmanager_state_initial_sync_duration_seconds' , '{%s}' % $.jobMatcher ('alertmanager' ))
178
164
)
179
- )
180
- .addRow(
181
- $.row('Sharding State Operations' )
182
165
.addPanel(
183
- $.panel('Replica Fetches /sec' ) +
166
+ $.panel('Fetch state from other alertmanagers /sec' ) +
184
167
$.queryPanel(
185
168
[
186
169
|||
@@ -193,8 +176,11 @@ local utils = import 'mixin-utils/utils.libsonnet';
193
176
['success' , 'failed' ]
194
177
)
195
178
)
179
+ )
180
+ .addRow(
181
+ $.row('Sharding State Operations' )
196
182
.addPanel(
197
- $.panel('Replica Updates /sec' ) +
183
+ $.panel('Replicate state to other alertmanagers /sec' ) +
198
184
$.queryPanel(
199
185
[
200
186
|||
@@ -208,7 +194,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
208
194
)
209
195
)
210
196
.addPanel(
211
- $.panel('Partial Merges /sec' ) +
197
+ $.panel('Merge state from other alertmanagers /sec' ) +
212
198
$.queryPanel(
213
199
[
214
200
|||
@@ -222,7 +208,7 @@ local utils = import 'mixin-utils/utils.libsonnet';
222
208
)
223
209
)
224
210
.addPanel(
225
- $.panel('Remote Storage Persists /sec' ) +
211
+ $.panel('Persist state to remote storage /sec' ) +
226
212
$.queryPanel(
227
213
[
228
214
|||
0 commit comments