Skip to content

Commit aa4ee47

Browse files
DasomeoneDasomeone
authored
Merge branch 'master' into dasomeone/fix_ceph_bright_mode
2 parents d05f0fc + deb2c73 commit aa4ee47

File tree

9 files changed

+721
-8
lines changed

9 files changed

+721
-8
lines changed

‎apache-solr-mixin/dashboards/apache-solr-cluster-overview.libsonnet‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1653,7 +1653,7 @@ local getMatcher(cfg) = '%(solrSelector)s, solr_cluster=~"$solr_cluster"' % cfg;
16531653
refresh=2,
16541654
includeAll=true,
16551655
multi=true,
1656-
allValues='.+',
1656+
allValues='.*',
16571657
sort=1
16581658
),
16591659
template.new(

‎apache-solr-mixin/dashboards/apache-solr-query-performance.libsonnet‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1578,7 +1578,7 @@ local getMatcher(cfg) = '%(solrSelector)s, solr_cluster=~"$solr_cluster", base_u
15781578
refresh=2,
15791579
includeAll=true,
15801580
multi=true,
1581-
allValues='.+',
1581+
allValues='.*',
15821582
sort=1
15831583
),
15841584
template.new(

‎apache-solr-mixin/dashboards/apache-solr-resource-monitoring.libsonnet‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1059,7 +1059,7 @@ local dispatchesPanel(matcher) = {
10591059
},
10601060
};
10611061

1062-
local getMatcher(cfg) = '%(solrSelector)s, solr_cluster="$solr_cluster", base_url=~"$base_url"' % cfg;
1062+
local getMatcher(cfg) = '%(solrSelector)s, solr_cluster=~"$solr_cluster", base_url=~"$base_url"' % cfg;
10631063

10641064
{
10651065
grafanaDashboards+:: {

‎csp-mixin/alerts/azure-alerts.yml‎

Lines changed: 128 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ groups:
1111
service: 'Azure Virtual Machines'
1212
namespace: cloud-provider-azure
1313
annotations:
14-
summary: 'CPU utilization is too high.'
14+
summary: 'VM CPU utilization is too high.'
1515
description: 'The VM {{ $labels.resourceName }} is under heavy load and may become unresponsive.'
1616
dashboard_uid: '58f33c50e66c911b0ad8a25aa438a96e'
1717

@@ -22,9 +22,135 @@ groups:
2222
keep_firing_for: 10m
2323
labels:
2424
severity: critical
25-
service: 'Azure Virtual Machines.'
25+
service: 'Azure Virtual Machines'
2626
namespace: cloud-provider-azure
2727
annotations:
2828
summary: 'VM unavailable.'
2929
description: 'The VM {{ $labels.resourceName }} is not functioning or crashed, which may require immediate action.'
3030
dashboard_uid: '58f33c50e66c911b0ad8a25aa438a96e'
31+
32+
- alert: AzureDatabaseHighDtuConsumption
33+
expr: |
34+
avg by (job,resourceGroup,subscriptionName,resourceName) (azure_microsoft_sql_servers_databases_dtu_consumption_percent_average_percent{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}) > 90
35+
for: 10m
36+
keep_firing_for: 10m
37+
labels:
38+
severity: critical
39+
service: 'Azure SQL database'
40+
namespace: cloud-provider-azure
41+
annotations:
42+
summary: 'High database DTU consumption.'
43+
description: 'Check active queries and optimize indexes or consider scaling up DTUs to handle load in {{ $labels.resourceName }} database.'
44+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'
45+
46+
- alert: AzureDatabaseHighStorageUsage
47+
expr: |
48+
avg by (job,resourceGroup,subscriptionName,resourceName) (azure_microsoft_sql_servers_databases_storage_percent_maximum_percent{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}) > 95
49+
for: 15m
50+
keep_firing_for: 10m
51+
labels:
52+
severity: critical
53+
service: 'Azure SQL database'
54+
namespace: cloud-provider-azure
55+
annotations:
56+
summary: 'High database Storage usage.'
57+
description: 'Archive or delete old data, or scale up storage capacity in {{ $labels.resourceName }} database.'
58+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'
59+
60+
- alert: AzureDatabaseHighDeadlockCount
61+
expr: |
62+
sum by (job,resourceGroup,subscriptionName,resourceName) (rate(azure_microsoft_sql_servers_databases_deadlock_total_count{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}[5m])) > 5
63+
for: 10m
64+
keep_firing_for: 10m
65+
labels:
66+
severity: info
67+
service: 'Azure SQL database'
68+
namespace: cloud-provider-azure
69+
annotations:
70+
summary: 'High database Deadlock count.'
71+
description: 'Check {{ $labels.resourceName }} database logs for deadlock details and optimize affected queries.'
72+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'
73+
74+
- alert: AzureDatabaseHighUserCpuUsage
75+
expr: |
76+
avg by (job,resourceGroup,subscriptionName,resourceName) (azure_microsoft_sql_servers_databases_cpu_percent_average_percent{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}) > 90
77+
for: 10m
78+
keep_firing_for: 10m
79+
labels:
80+
severity: warning
81+
service: 'Azure SQL database'
82+
namespace: cloud-provider-azure
83+
annotations:
84+
summary: 'High database User CPU usage.'
85+
description: 'Identify high CPU queries on {{ $labels.resourceName }} database and optimize them.'
86+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'
87+
88+
- alert: AzureDatabaseHighSystemFailedConnections
89+
expr: |
90+
sum by (job,resourceGroup,subscriptionName,resourceName) (rate(azure_microsoft_sql_servers_databases_connection_failed_total_count{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}[5m])) > 10
91+
for: 5m
92+
keep_firing_for: 10m
93+
labels:
94+
severity: warning
95+
service: 'Azure SQL database'
96+
namespace: cloud-provider-azure
97+
annotations:
98+
summary: 'High number of database System Failed connections.'
99+
description: 'Check network problems, firewall restrictions or high resource consumption affecting application access to the {{ $labels.resourceName }} database.'
100+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'
101+
102+
- alert: AzureDatabaseHighUserFailedConnections
103+
expr: |
104+
sum by (job,resourceGroup,subscriptionName,resourceName) (rate(azure_microsoft_sql_servers_databases_connection_failed_user_error_total_count{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}[5m])) > 10
105+
for: 15m
106+
keep_firing_for: 10m
107+
labels:
108+
severity: warning
109+
service: 'Azure SQL database'
110+
namespace: cloud-provider-azure
111+
annotations:
112+
summary: 'High number of database User Failed connections.'
113+
description: 'Check for authentication problems, network configuration errors, firewall issues, or resource constraints, affecting database accessibility for users on database {{ $labels.resourceName }}.'
114+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'
115+
116+
- alert: AzureDatabaseHighWorkerUsage
117+
expr: |
118+
avg by (job,resourceGroup,subscriptionName,resourceName) (azure_microsoft_sql_servers_databases_workers_percent_average_percent{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}) > 60
119+
for: 5m
120+
keep_firing_for: 10m
121+
labels:
122+
severity: critical
123+
service: 'Azure SQL database'
124+
namespace: cloud-provider-azure
125+
annotations:
126+
summary: 'High database worker usage.'
127+
description: 'Look for long execution queries, review the number of concurrent queries and requests being sent to the database or check if there are any blocking sessions or deadlocks into the {{ $labels.resourceName }} database.'
128+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'
129+
130+
- alert: AzureDatabaseHighDataIoUsage
131+
expr: |
132+
avg by (job,resourceGroup,subscriptionName,resourceName) (azure_microsoft_sql_servers_databases_physical_data_read_percent_average_percent{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}) > 90
133+
for: 15m
134+
keep_firing_for: 10m
135+
labels:
136+
severity: info
137+
service: 'Azure SQL database'
138+
namespace: cloud-provider-azure
139+
annotations:
140+
summary: 'High database data IO usage.'
141+
description: 'Review queries with high read or write activity, check if there are missing indexes or inefficient indexes that result in full table scans and assess the volume of transactions into the {{ $labels.resourceName }} database.'
142+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'
143+
144+
- alert: AzureDatabaseLowTempdbLogSpace
145+
expr: |
146+
avg by (job,resourceGroup,subscriptionName,resourceName) (azure_microsoft_sql_servers_databases_tempdb_log_used_percent_average_percent{job=~".+",resourceGroup=~".+",subscriptionName=~".+",resourceName=~".+"}) > 60
147+
for: 5m
148+
keep_firing_for: 10m
149+
labels:
150+
severity: critical
151+
service: 'Azure SQL database'
152+
namespace: cloud-provider-azure
153+
annotations:
154+
summary: 'Low database tempdb log space.'
155+
description: 'Look for active sessions that might be using TempDB intensively, identify stored procedures or queries that create temporary tables or objects, and also look for long-running or memory-intensive queries that rely heavily on TempDB into the {{ $labels.resourceName }} database.'
156+
dashboard_uid: '82c5b6cf30db5b601c5cc3f5d8d4284d'

‎logs-lib/logs/variables.libsonnet‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@ function(
2121
)
2222
+ var.query.selectionOptions.withIncludeAll(
2323
value=true,
24-
customAllValue='.*'
24+
customAllValue='.+'
2525
)
2626
+ var.query.selectionOptions.withMulti()
2727
+ var.query.refresh.onTime()

‎mixin-utils/utils.libsonnet‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -180,10 +180,10 @@ local g = import 'grafana-builder/grafana.libsonnet';
180180

181181
// showClassicHistogramQuery wraps a query defined as map {classic: q, native: q}, and compares the classic query
182182
// to dashboard variable which should take -1 or +1 as values in order to hide or show the classic query.
183-
showClassicHistogramQuery(query, dashboard_variable='latency_metrics'):: '%s < ($%s * +Inf)' % [query.classic, dashboard_variable],
183+
showClassicHistogramQuery(query, dashboard_variable='latency_metrics'):: '(%s) and on() (vector($%s) == 1)' % [query.classic, dashboard_variable],
184184
// showNativeHistogramQuery wraps a query defined as map {classic: q, native: q}, and compares the native query
185185
// to dashboard variable which should take -1 or +1 as values in order to show or hide the native query.
186-
showNativeHistogramQuery(query, dashboard_variable='latency_metrics'):: '%s < ($%s * -Inf)' % [query.native, dashboard_variable],
186+
showNativeHistogramQuery(query, dashboard_variable='latency_metrics'):: '(%s) and on() (vector($%s) == -1)' % [query.native, dashboard_variable],
187187

188188
histogramRules(metric, labels, interval='1m', record_native=false)::
189189
local vars = {

‎static-exporter/README.md‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -43,3 +43,22 @@ local static_exporter = import 'github.com/grafana/jsonnet-libs/static-expoter/m
4343
]),
4444
}
4545
```
46+
47+
## Updating httpd.conf
48+
49+
There is a default httpd.conf that was added to this library.
50+
It was generated by running the following:
51+
52+
```
53+
docker run --rm httpd:2.4 cat /usr/local/apache2/conf/httpd.conf httpd.conf
54+
```
55+
56+
If there is a downstream change that requires updating this config file, run the above command and then add the following snippet to the `<Directory "/usr/local/apache2/htdocs"` block:
57+
58+
```
59+
<IfModule mod_headers.c>
60+
Header set Content-Type: "text/plain; version=0.0.4"
61+
</IfModule>
62+
```
63+
64+
This change adds a Header to the requests that enables Prometheus 3.x to scrape the static exporter.

0 commit comments

Comments
 (0)