production: Migrate rpc counters to dynamic infra
This is destined to replace the current rpc service running on counters1.i.s.o [1] Its configuration matches the one in ^ [2]
In terms of resource, i've used the same configuration (2 workers with 1 thread each). But i've doubled the nb of replicas. So we've got a bit more than currently in the static infra.
[2] production configuration
root@counters1:~# cat /etc/softwareheritage/counters/server.yml
---
counters:
cls: redis
host: localhost:6379
history:
cls: prometheus
prometheus_host: thanos.internal.admin.swh.network
prometheus_port: 19191
live_data_start: 1618415227
cache_base_directory: "/srv/softwareheritage/counters"
interval: 12h
labels:
environment: production[1] helm diff
[swh] Comparing changes between branches production and migrate-rpc-counters (per environment)...
Your branch is ahead of 'origin/production' by 1 commit.
(use "git push" to publish your local commits)
[swh] Generate config in production branch for environment staging, namespace swh...
[swh] Generate config in production branch for environment staging, namespace swh-cassandra...
[swh] Generate config in production branch for environment staging, namespace swh-cassandra-next-version...
[swh] Generate config in migrate-rpc-counters branch for environment staging...
[swh] Generate config in migrate-rpc-counters branch for environment staging...
[swh] Generate config in migrate-rpc-counters branch for environment staging...
Your branch is ahead of 'origin/production' by 1 commit.
(use "git push" to publish your local commits)
[swh] Generate config in production branch for environment production, namespace swh...
[swh] Generate config in production branch for environment production, namespace swh-cassandra...
[swh] Generate config in production branch for environment production, namespace swh-cassandra-next-version...
[swh] Generate config in migrate-rpc-counters branch for environment production...
[swh] Generate config in migrate-rpc-counters branch for environment production...
[swh] Generate config in migrate-rpc-counters branch for environment production...
------------- diff for environment staging namespace swh -------------
No differences
------------- diff for environment staging namespace swh-cassandra -------------
No differences
------------- diff for environment staging namespace swh-cassandra-next-version -------------
No differences
------------- diff for environment production namespace swh -------------
--- /tmp/swh-chart.swh.0IXfXlzL/production-swh.before 2024-02-07 14:54:53.476307371 +0100
+++ /tmp/swh-chart.swh.0IXfXlzL/production-swh.after 2024-02-07 14:54:54.000306413 +0100
@@ -646,20 +646,41 @@
- directory
- origin
- origin_visit
- origin_visit_status
- release
- revision
- skipped_content
- snapshot
prefix: swh.journal.objects
---
+# Source: swh/templates/counters/rpc-configmap.yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+ namespace: swh
+ name: counters-rpc-configuration-template
+data:
+ config.yml.template: |
+ counters:
+ cls: redis
+ host: counters1.internal.softwareheritage.org:6379
+ history:
+ cls: prometheus
+ interval: 12h
+ labels:
+ environment: production
+ live_data_start: 1618415227
+ prometheus_host: thanos.internal.admin.swh.network
+ prometheus_port: 19191
+ cache_base_directory: /srv/softwareheritage/counters
+---
# Source: swh/templates/counters/script-utils.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: script-utils
namespace: swh
data:
refresh-counters-cache.sh: |
#!/bin/bash
@@ -17396,20 +17417,37 @@
namespace: default
spec:
ports:
- name: http
port: 443
protocol: TCP
targetPort: 9443
selector:
app: keda-admission-webhooks
---
+# Source: swh/templates/counters/rpc-service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+ name: counters-rpc
+ namespace: swh
+ labels:
+ app: counters-rpc
+spec:
+ type: ClusterIP
+ selector:
+ app: counters-rpc
+ ports:
+ - port: 5011
+ targetPort: 5011
+ name: rpc
+---
# Source: swh/templates/deposit/service.yaml
apiVersion: v1
kind: Service
metadata:
name: deposit
namespace: swh
labels:
app: deposit
spec:
type: ClusterIP
@@ -17421,20 +17459,30 @@
name: rpc
- port: 80
targetPort: 80
name: webstatic
---
# Source: swh/templates/external-services/cname.yaml
apiVersion: v1
kind: Service
metadata:
+ name: counters-rpc-ingress
+ namespace: swh
+spec:
+ type: ExternalName
+ externalName: archive-production-rke2-ingress-nginx-controller.ingress-nginx.svc.cluster.local
+---
+# Source: swh/templates/external-services/cname.yaml
+apiVersion: v1
+kind: Service
+metadata:
name: indexer-storage-read-only-rpc-ingress
namespace: swh
spec:
type: ExternalName
externalName: archive-production-rke2-ingress-nginx-controller.ingress-nginx.svc.cluster.local
---
# Source: swh/templates/external-services/cname.yaml
apiVersion: v1
kind: Service
metadata:
@@ -19116,20 +19164,171 @@
configMap:
name: counters-journal-client-configuration-template
items:
- key: "config.yml.template"
path: "config.yml.template"
- name: config-utils
configMap:
name: config-utils
defaultMode: 0555
---
+# Source: swh/templates/counters/rpc-deployment.yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+ namespace: swh
+ name: counters-rpc
+ labels:
+ app: counters-rpc
+spec:
+ revisionHistoryLimit: 2
+ replicas: 2
+ selector:
+ matchLabels:
+ app: counters-rpc
+ strategy:
+ type: RollingUpdate
+ rollingUpdate:
+ maxSurge: 1
+ template:
+ metadata:
+ labels:
+ app: counters-rpc
+ annotations:
+ checksum/configmap: 598be262c2cfe9c36bf0fe7e2b9195bd93e318b1af8b8be246dead7ad2d2eef8
+ checksum/script-utils: 790f42f6e7c10aa1b8c44024b4f7b5525af8871e533b5c378f9cdbf34e4d015c
+ spec:
+ affinity:
+ nodeAffinity:
+ requiredDuringSchedulingIgnoredDuringExecution:
+ nodeSelectorTerms:
+ - matchExpressions:
+ - key: swh/rpc
+ operator: In
+ values:
+ - "true"
+ priorityClassName: swh-frontend-rpc
+
+ initContainers:
+ - name: prepare-configuration
+ image: container-registry.softwareheritage.org/swh/infra/swh-apps/utils:20231211.1
+ imagePullPolicy: IfNotPresent
+ command:
+ - /entrypoints/prepare-configuration.sh
+ volumeMounts:
+ - name: configuration
+ mountPath: /etc/swh
+ - name: configuration-template
+ mountPath: /etc/swh/configuration-template
+ - name: config-utils
+ mountPath: /entrypoints
+ readOnly: true
+ env:
+
+
+ - name: fetch-static-history
+ image: container-registry.softwareheritage.org/swh/infra/swh-apps/utils:20231211.1
+ imagePullPolicy: IfNotPresent
+ command:
+ - /entrypoints/fetch-static-history.sh
+ args:
+ - /srv/softwareheritage/counters/static_history.json
+ volumeMounts:
+ - name: script-utils
+ mountPath: /entrypoints
+ readOnly: true
+ - name: staticdata
+ mountPath: /srv/softwareheritage/counters
+ containers:
+ - name: counters-rpc
+ # Workaround until we have a way to define distributed volumes
+ # This initializes the history cache file
+ lifecycle:
+ postStart:
+ exec:
+ command:
+ - /entrypoints/refresh-counters-cache.sh
+ - history.json
+ - static_history.json
+ - localhost:5011
+ resources:
+ requests:
+ memory: 512Mi
+ cpu: 500m
+ image: container-registry.softwareheritage.org/swh/infra/swh-apps/counters:20240202.1
+ imagePullPolicy: IfNotPresent
+ ports:
+ - containerPort: 5011
+ name: rpc
+ readinessProbe:
+ httpGet:
+ path: /
+ port: rpc
+ initialDelaySeconds: 15
+ failureThreshold: 30
+ periodSeconds: 5
+ livenessProbe:
+ tcpSocket:
+ port: rpc
+ initialDelaySeconds: 10
+ periodSeconds: 5
+ command:
+ - /bin/bash
+ args:
+ - -c
+ - /opt/swh/entrypoint.sh
+ env:
+ - name: THREADS
+ value: "1"
+ - name: WORKERS
+ value: "2"
+ - name: TIMEOUT
+ value: "10"
+ - name: STATSD_HOST
+ value: prometheus-statsd-exporter
+ - name: STATSD_PORT
+ value: "9125"
+ - name: LOG_LEVEL
+ value: INFO
+ volumeMounts:
+ - name: configuration
+ mountPath: /etc/swh
+ - name: staticdata
+ mountPath: /srv/softwareheritage/counters
+ - name: script-utils
+ mountPath: /entrypoints
+ readOnly: true
+ volumes:
+ - name: configuration
+ emptyDir: {}
+ - name: staticdata
+ emptyDir: {}
+ - name: configuration-template
+ configMap:
+ name: counters-rpc-configuration-template
+ items:
+ - key: "config.yml.template"
+ path: "config.yml.template"
+ - name: config-utils
+ configMap:
+ name: config-utils
+ defaultMode: 0555
+ - name: script-utils
+ configMap:
+ name: script-utils
+ defaultMode: 0555
+ items:
+ - key: "fetch-static-history.sh"
+ path: "fetch-static-history.sh"
+ - key: "refresh-counters-cache.sh"
+ path: "refresh-counters-cache.sh"
+---
# Source: swh/templates/deposit/deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
namespace: swh
name: deposit
labels:
app: deposit
spec:
revisionHistoryLimit: 2
@@ -34681,20 +34880,62 @@
path: "config.yml.template"
- name: pgservice-configuration-template
configMap:
name: pgservice-archive-configuration-template
items:
- key: "pg-service-conf"
path: "pg_service.conf"
restartPolicy: OnFailure
---
+# Source: swh/templates/counters/rpc-ingress.yaml
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+ namespace: swh
+ name: counters-rpc-ingress-default
+ labels:
+ app: counters-rpc
+ endpoint-definition: default
+ annotations:
+ nginx.ingress.kubernetes.io/service-upstream: "true"
+ nginx.ingress.kubernetes.io/whitelist-source-range: 10.42.0.0/16,10.43.0.0/16,127.0.0.0/8,192.168.100.0/24,192.168.101.0/24,192.168.200.0/22
+ nginx.ingress.kubernetes.io/proxy-body-size: 4G
+ nginx.ingress.kubernetes.io/proxy-connect-timeout: "90"
+ nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
+ nginx.ingress.kubernetes.io/proxy-request-buffering: "on"
+ nginx.ingress.kubernetes.io/proxy-send-timeout: "90"
+
+spec:
+ rules:
+ - host: counters-rpc-ingress
+ http:
+ paths:
+ - path: /
+ pathType: Prefix
+ backend:
+ service:
+ name: counters-rpc
+ port:
+ number: 5011
+
+ - host: counters.internal.softwareheritage.org
+ http:
+ paths:
+ - path: /
+ pathType: Prefix
+ backend:
+ service:
+ name: counters-rpc
+ port:
+ number: 5011
+---
# Source: swh/templates/deposit/ingress.yaml
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
namespace: swh
name: deposit-ingress-authenticated
labels:
app: deposit
endpoint-definition: authenticated
annotations:
------------- diff for environment production namespace swh-cassandra -------------
--- /tmp/swh-chart.swh.0IXfXlzL/production-swh-cassandra.before 2024-02-07 14:54:53.652307049 +0100
+++ /tmp/swh-chart.swh.0IXfXlzL/production-swh-cassandra.after 2024-02-07 14:54:54.172306098 +0100
@@ -11198,20 +11198,30 @@
port: 443
protocol: TCP
targetPort: 9443
selector:
app: keda-admission-webhooks
---
# Source: swh/templates/external-services/cname.yaml
apiVersion: v1
kind: Service
metadata:
+ name: counters-rpc-ingress
+ namespace: swh-cassandra
+spec:
+ type: ExternalName
+ externalName: archive-production-rke2-ingress-nginx-controller.ingress-nginx.svc.cluster.local
+---
+# Source: swh/templates/external-services/cname.yaml
+apiVersion: v1
+kind: Service
+metadata:
name: indexer-storage-read-only-rpc-ingress
namespace: swh-cassandra
spec:
type: ExternalName
externalName: archive-production-rke2-ingress-nginx-controller.ingress-nginx.svc.cluster.local
---
# Source: swh/templates/external-services/cname.yaml
apiVersion: v1
kind: Service
metadata:Depends on !335 (merged)