Activate rabbitmq metrics scrape in production & staging cluster
Deactivating the test-staging-rke2 scraping test in the first commit too.
This works hand-in-hand with [1] which deactivates the scraping from the static prometheus.
[1] swh/infra/puppet/puppet-swh-site!692 (merged)
make cc-helm-diff | colordiff
[cluster-components] Comparing changes between branches production and scrape-rabbitmq-metrics...
Your branch is up to date with 'origin/production'.
[cluster-components] Generate config in production branch for cluster-components/values/admin-rke2.yaml...
[cluster-components] Generate config in production branch for cluster-components/values/archive-production-rke2.yaml...
[cluster-components] Generate config in production branch for cluster-components/values/archive-staging-rke2.yaml...
[cluster-components] Generate config in production branch for cluster-components/values/gitlab-production.yaml...
[cluster-components] Generate config in production branch for cluster-components/values/gitlab-staging.yaml...
[cluster-components] Generate config in production branch for cluster-components/values/minikube.yaml...
[cluster-components] Generate config in production branch for cluster-components/values/rancher.yaml...
[cluster-components] Generate config in production branch for cluster-components/values/test-staging-rke2.yaml...
[cluster-components] Generate config in scrape-rabbitmq-metrics branch for cluster-components/values/admin-rke2.yaml...
[cluster-components] Generate config in scrape-rabbitmq-metrics branch for cluster-components/values/archive-production-rke2.yaml...
[cluster-components] Generate config in scrape-rabbitmq-metrics branch for cluster-components/values/archive-staging-rke2.yaml...
[cluster-components] Generate config in scrape-rabbitmq-metrics branch for cluster-components/values/gitlab-production.yaml...
[cluster-components] Generate config in scrape-rabbitmq-metrics branch for cluster-components/values/gitlab-staging.yaml...
[cluster-components] Generate config in scrape-rabbitmq-metrics branch for cluster-components/values/minikube.yaml...
[cluster-components] Generate config in scrape-rabbitmq-metrics branch for cluster-components/values/rancher.yaml...
[cluster-components] Generate config in scrape-rabbitmq-metrics branch for cluster-components/values/test-staging-rke2.yaml...
------------- diff for cluster-components/values/admin-rke2.yaml -------------
No differences
------------- diff for cluster-components/values/archive-production-rke2.yaml -------------
--- /tmp/swh-chart.cluster-components.AAGp8DlT/archive-production-rke2.yaml.before 2024-02-08 12:05:10.411115287 +0100
+++ /tmp/swh-chart.cluster-components.AAGp8DlT/archive-production-rke2.yaml.after 2024-02-08 12:05:11.699126184 +0100
@@ -18,20 +18,35 @@
name: cassandra-servers-svc
labels:
app: cassandra
spec:
type: ExternalName
externalName: "fake-url"
ports:
- name: jmx-exporter
port: 7070
targetPort: 7070
+ protocol: TCP---
+apiVersion: v1
+kind: Service
+metadata:
+ namespace: rabbitmq
+ name: rabbitmq-servers-svc
+ labels:
+ app: rabbitmq
+spec:
+ type: ExternalName
+ externalName: "fake-url"
+ ports:
+ - name: rabbitmq-metrics
+ port: 9419
+ targetPort: 9419
protocol: TCP
---
# Source: cluster-config/templates/alertmanager-config/config.yaml
apiVersion: monitoring.coreos.com/v1alpha1
kind: AlertmanagerConfig
metadata:
name: irc-relay-config
namespace: cattle-monitoring-system
spec:
route:
@@ -80,20 +95,34 @@
- ip: 192.168.100.184
- ip: 192.168.100.185
- ip: 192.168.100.186
- ip: 192.168.100.187
- ip: 192.168.100.188
- ip: 192.168.100.189
- ip: 192.168.100.190
ports:
- name: jmx-exporter
port: 7070
+ protocol: TCP---
+apiVersion: v1
+kind: Endpoints
+metadata:
+ namespace: rabbitmq
+ name: rabbitmq-servers-svc
+ labels:
+ app: rabbitmq
+subsets:
+ - addresses:
+ - ip: 192.168.100.104
+ ports:
+ - name: rabbitmq-metrics
+ port: 9419
protocol: TCP
---
# Source: cluster-config/templates/alerting/swh-alerting.yaml
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: swh-production.rules
namespace: cattle-monitoring-system
spec:
groups:
@@ -161,11 +190,35 @@
regex: 192.168.100.18(\d)(.*)
replacement: cassandra0$1.internal.softwareheritage.org$2
sourceLabels:
- __address__
targetLabel: __address__
- action: replace
regex: 192.168.100.19(\d)(.*)
replacement: cassandra1$1.internal.softwareheritage.org$2
sourceLabels:
- __address__
+ targetLabel: __address__---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+ namespace: rabbitmq
+ name: rabbitmq-servers-svc
+ labels:
+ app: rabbitmq
+spec:
+ selector:
+ matchLabels:
+ app: rabbitmq
+ namespaceSelector:
+ any: true
+ endpoints:
+ - port: rabbitmq-metrics
+ interval: 30s
+ honorLabels: true
+ relabelings:
+ - action: replace
+ regex: 192.168.100.104(.*)
+ replacement: saatchi.internal.softwareheritage.org$1
+ sourceLabels:
+ - __address__
targetLabel: __address__
------------- diff for cluster-components/values/archive-staging-rke2.yaml -------------
--- /tmp/swh-chart.cluster-components.AAGp8DlT/archive-staging-rke2.yaml.before 2024-02-08 12:05:10.487115930 +0100
+++ /tmp/swh-chart.cluster-components.AAGp8DlT/archive-staging-rke2.yaml.after 2024-02-08 12:05:11.767126759 +0100
@@ -74,20 +74,35 @@
name: cassandra-servers-svc
labels:
app: cassandra
spec:
type: ExternalName
externalName: "fake-url"
ports:
- name: jmx-exporter
port: 7070
targetPort: 7070
+ protocol: TCP---
+apiVersion: v1
+kind: Service
+metadata:
+ namespace: rabbitmq
+ name: rabbitmq-servers-svc
+ labels:
+ app: rabbitmq
+spec:
+ type: ExternalName
+ externalName: "fake-url"
+ ports:
+ - name: rabbitmq-metrics
+ port: 9419
+ targetPort: 9419
protocol: TCP
---
# Source: cluster-config/templates/svix/services.yaml
apiVersion: v1
kind: Service
metadata:
name: svix
namespace: svix-server
spec:
type: ClusterIP
@@ -253,20 +268,34 @@
labels:
app: cassandra
subsets:
- addresses:
- ip: 192.168.130.181
- ip: 192.168.130.182
- ip: 192.168.130.183
ports:
- name: jmx-exporter
port: 7070
+ protocol: TCP---
+apiVersion: v1
+kind: Endpoints
+metadata:
+ namespace: rabbitmq
+ name: rabbitmq-servers-svc
+ labels:
+ app: rabbitmq
+subsets:
+ - addresses:
+ - ip: 192.168.130.50
+ ports:
+ - name: rabbitmq-metrics
+ port: 9419
protocol: TCP
---
# Source: cluster-config/templates/alerting/swh-alerting.yaml
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: swh-staging.rules
namespace: cattle-monitoring-system
spec:
groups:
@@ -328,11 +357,35 @@
endpoints:
- port: jmx-exporter
interval: 30s
honorLabels: true
relabelings:
- action: replace
regex: 192.168.130.18(\d)(.*)
replacement: cassandra$1.internal.staging.swh.network$2
sourceLabels:
- __address__
+ targetLabel: __address__---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+ namespace: rabbitmq
+ name: rabbitmq-servers-svc
+ labels:
+ app: rabbitmq
+spec:
+ selector:
+ matchLabels:
+ app: rabbitmq
+ namespaceSelector:
+ any: true
+ endpoints:
+ - port: rabbitmq-metrics
+ interval: 30s
+ honorLabels: true
+ relabelings:
+ - action: replace
+ regex: 192.168.130.50(.*)
+ replacement: scheduler0.internal.staging.swh.network$1
+ sourceLabels:
+ - __address__
targetLabel: __address__
------------- diff for cluster-components/values/gitlab-production.yaml -------------
No differences
------------- diff for cluster-components/values/gitlab-staging.yaml -------------
No differences
------------- diff for cluster-components/values/minikube.yaml -------------
No differences
------------- diff for cluster-components/values/rancher.yaml -------------
No differences
------------- diff for cluster-components/values/test-staging-rke2.yaml -------------
--- /tmp/swh-chart.cluster-components.AAGp8DlT/test-staging-rke2.yaml.before 2024-02-08 12:05:11.547124897 +0100
+++ /tmp/swh-chart.cluster-components.AAGp8DlT/test-staging-rke2.yaml.after 2024-02-08 12:05:12.807135556 +0100
@@ -67,38 +67,20 @@
app: svix-postgres
ingress:
- from:
- podSelector:
matchLabels:
app: svix-server
ports:
- protocol: TCP
port: 5432
---
-# Source: cluster-config/templates/scrape-external-metrics/service.yaml
-# This defines a service to be monitored by the service monitor---
-apiVersion: v1
-kind: Service
-metadata:
- namespace: rabbitmq
- name: rabbitmq-servers-svc
- labels:
- app: rabbitmq
-spec:
- type: ExternalName
- externalName: "fake-url"
- ports:
- - name: rabbitmq-metrics
- port: 9419
- targetPort: 9419
- protocol: TCP
----
# Source: cluster-config/templates/svix/services.yaml
apiVersion: v1
kind: Service
metadata:
name: postgres
namespace: svix-server
spec:
type: ClusterIP
selector:
app: svix-postgres
@@ -352,20 +334,30 @@
backend:
service:
name: svix
port:
number: 8071
tls:
- hosts:
- svix-test.internal.staging.swh.network
secretName: swh-svix-crt
---
+# Source: cluster-config/templates/scrape-external-metrics/endpoints.yaml
+# This defines the external endpoints ips to connect to scrape metrics
+---
+# Source: cluster-config/templates/scrape-external-metrics/service-monitor.yaml
+# This defines the service-monitor to monitor the service which scrapes external metrics
+# This may redefine some metrics, see the relabeling configuration dict key
+---
+# Source: cluster-config/templates/scrape-external-metrics/service.yaml
+# This defines a service to be monitored by the service monitor
+---
# Source: cluster-config/templates/alertmanager-config/config.yaml
apiVersion: monitoring.coreos.com/v1alpha1
kind: AlertmanagerConfig
metadata:
name: irc-relay-config
namespace: cattle-monitoring-system
spec:
route:
groupBy: ['...']
groupWait: 31s
@@ -387,55 +379,10 @@
- sendResolved: true
url: https://alertmanager-irc-relay.internal.admin.swh.network/swh-sysadm
httpConfig:
basicAuth:
username:
key: user
name: alertmanager-irc-relay-config
password:
key: password
name: alertmanager-irc-relay-config
----
-# Source: cluster-config/templates/scrape-external-metrics/endpoints.yaml
-# This defines the external endpoints ips to connect to scrape metrics---
-apiVersion: v1
-kind: Endpoints
-metadata:
- namespace: rabbitmq
- name: rabbitmq-servers-svc
- labels:
- app: rabbitmq
-subsets:
- - addresses:
- - ip: 192.168.130.50
- ports:
- - name: rabbitmq-metrics
- port: 9419
- protocol: TCP
----
-# Source: cluster-config/templates/scrape-external-metrics/service-monitor.yaml
-# This defines the service-monitor to monitor the service which scrapes external metrics
-# This may redefine some metrics, see the relabeling configuration dict key---
-apiVersion: monitoring.coreos.com/v1
-kind: ServiceMonitor
-metadata:
- namespace: rabbitmq
- name: rabbitmq-servers-svc
- labels:
- app: rabbitmq
-spec:
- selector:
- matchLabels:
- app: rabbitmq
- namespaceSelector:
- any: true
- endpoints:
- - port: rabbitmq-metrics
- interval: 30s
- honorLabels: true
- relabelings:
- - action: replace
- regex: 192.168.130.50(.*)
- replacement: scheduler0.internal.staging.swh.network$1
- sourceLabels:
- - __address__
- targetLabel: __address__