Cleanup

Author: giohappy

.env.sample

@@ -1,17 +1,12 @@
 COMPOSE_PROJECT_NAME={{project_name}}
-# See https://github.com/containers/podman/issues/13889
-# DOCKER_BUILDKIT=0
 DOCKER_ENV=production
-# See https://github.com/geosolutions-it/geonode-generic/issues/28
-# to see why we force API version to 1.24
-DOCKER_API_VERSION="1.24"
 BACKUPS_VOLUME_DRIVER=local
 
-GEONODE_BASE_IMAGE_VERSION=master
-NGINX_BASE_IMAGE_VERSION=1.26.3-latest
+GEONODE_BASE_IMAGE_VERSION=5.0.x
+NGINX_BASE_IMAGE_VERSION=1.28.0-v1
 LETSENCRYPT_BASE_IMAGE_VERSION=2.6.0-latest
-GEOSERVER_BASE_IMAGE_VERSION=2.24.4-latest
-GEOSERVER_DATA_BASE_IMAGE_VERSION=2.24.4-latest
+GEOSERVER_BASE_IMAGE_VERSION=2.27.3-latest
+GEOSERVER_DATA_BASE_IMAGE_VERSION=2.27.3-latest
 POSTGRES_BASE_IMAGE_VERSION=15-3.5-latest
 
 C_FORCE_ROOT=1
@@ -200,18 +195,8 @@ API_LIMIT_PER_PAGE=1000
 # GIS Client
 GEONODE_CLIENT_LAYER_PREVIEW_LIBRARY=mapstore
 MAPBOX_ACCESS_TOKEN=
-BING_API_KEY=
 GOOGLE_API_KEY=
 
-# Monitoring
-MONITORING_ENABLED=False
-MONITORING_DATA_TTL=365
-USER_ANALYTICS_ENABLED=True
-USER_ANALYTICS_GZIP=True
-CENTRALIZED_DASHBOARD_ENABLED=False
-MONITORING_SERVICE_NAME=local-geonode
-MONITORING_HOST_NAME=geonode
-
 # Other Options/Contribs
 MODIFY_TOPICCATEGORY=True
 AVATAR_GRAVATAR_SSL=True
@@ -223,19 +208,7 @@ FAVORITE_ENABLED=True
 RESOURCE_PUBLISHING=False
 ADMIN_MODERATE_UPLOADS=False
 
-# LDAP
-LDAP_ENABLED=False
-LDAP_SERVER_URL=ldap://<the_ldap_server>
-LDAP_BIND_DN=uid=ldapinfo,cn=users,dc=ad,dc=example,dc=org
-LDAP_BIND_PASSWORD=<something_secret>
-LDAP_USER_SEARCH_DN=dc=ad,dc=example,dc=org
-LDAP_USER_SEARCH_FILTERSTR=(&(uid=%(user)s)(objectClass=person))
-LDAP_GROUP_SEARCH_DN=cn=groups,dc=ad,dc=example,dc=org
-LDAP_GROUP_SEARCH_FILTERSTR=(|(cn=abt1)(cn=abt2)(cn=abt3)(cn=abt4)(cn=abt5)(cn=abt6))
-LDAP_GROUP_PROFILE_MEMBER_ATTR=uniqueMember
-
 # CELERY
-
 # expressed in KB
 # CELERY__MAX_MEMORY_PER_CHILD="200000"
 # ##
@@ -249,6 +222,9 @@ LDAP_GROUP_PROFILE_MEMBER_ATTR=uniqueMember
 # CELERY__LOG_FILE="/var/log/celery.log"
 # CELERY__WORKER_NAME="worker1@%h"
 
+HARVESTING_MONITOR_ENABLED=True
+HARVESTING_MONITOR_DELAY=60
+
 # PostgreSQL
 POSTGRESQL_MAX_CONNECTIONS=200
 

.override_dev_env.sample

@@ -10,16 +10,9 @@ RUN sed -i -e 's/# C.UTF-8 UTF-8/C.UTF-8 UTF-8/' /etc/locale.gen && \
 ENV LC_ALL C.UTF-8
 ENV LANG C.UTF-8
 
-# add bower and grunt command
 COPY src /usr/src/{{project_name}}/
 WORKDIR /usr/src/{{project_name}}
 
-#COPY src/monitoring-cron /etc/cron.d/monitoring-cron
-#RUN chmod 0644 /etc/cron.d/monitoring-cron
-#RUN crontab /etc/cron.d/monitoring-cron
-#RUN touch /var/log/cron.log
-#RUN service cron start
-
 COPY src/wait-for-databases.sh /usr/bin/wait-for-databases
 RUN chmod +x /usr/bin/wait-for-databases
 RUN chmod +x /usr/src/{{project_name}}/tasks.py \
@@ -31,22 +24,11 @@ RUN chmod +x /usr/bin/celery-commands
 COPY src/celery-cmd /usr/bin/celery-cmd
 RUN chmod +x /usr/bin/celery-cmd
 
-# Install "geonode-contribs" apps
-# RUN cd /usr/src; git clone https://github.com/GeoNode/geonode-contribs.git -b master
-# Install logstash and centralized dashboard dependencies
-# RUN cd /usr/src/geonode-contribs/geonode-logstash; pip install --upgrade  -e . \
-#     cd /usr/src/geonode-contribs/ldap; pip install --upgrade  -e .
-
 RUN yes w | pip install --src /usr/src -r requirements.txt &&\
     yes w | pip install -e .
 
-# Cleanup apt update lists
 RUN apt-get autoremove --purge &&\
     apt-get clean &&\
     rm -rf /var/lib/apt/lists/*
 
-# Export ports
 EXPOSE 8000
-
-# We provide no command or entrypoint as this image can be used to serve the django project or run celery tasks
-# ENTRYPOINT /usr/src/{{project_name}}/entrypoint.sh

Dockerfile

@@ -147,45 +147,6 @@ To setup your project follow these instructions:
       } 
       ```
 
-### Start your server
-*Skip this part if you want to run the project using Docker instead* see [Start your server using Docker](#start-your-server-using-docker)
-
-1. Setup the Python Dependencies
-
-    **NOTE**: *Important: modify your `requirements.txt` file, by adding the `GeoNode` branch before continue!*
-
-    (see [Hints: Configuring `requirements.txt`](#hints-configuring-requirementstxt))
-
-    ```bash
-    cd src
-    pip install -r requirements.txt --upgrade
-    pip install -e . --upgrade
-
-    # Install GDAL Utilities for Python
-    pip install pygdal=="`gdal-config --version`.*"
-
-    # Dev scripts
-    mv ../.override_dev_env.sample ../.override_dev_env
-    mv manage_dev.sh.sample manage_dev.sh
-    mv paver_dev.sh.sample paver_dev.sh
-
-    source ../.override_dev_env
-
-    # Using the Default Settings
-    sh ./paver_dev.sh reset
-    sh ./paver_dev.sh setup
-    sh ./paver_dev.sh sync
-    sh ./paver_dev.sh start
-    ```
-
-2. Access GeoNode from browser
-
-    **NOTE**: default admin user is ``admin`` (with pw: ``admin``)
-
-    ```bash
-    http://localhost:8000/
-    ```
-
 ### Start your server using Docker
 
 You need Docker 1.12 or higher, get the latest stable official release for your platform.
@@ -330,4 +291,3 @@ POSTGRESQL_MAX_CONNECTIONS=200
 ```
 
 In this case PostgreSQL will run accepting 200 maximum connections.
-

README.md

@@ -6,17 +6,65 @@ CELERY_APP=${CELERY_APP:-"geonode.celery_app:app"}
 CELERY__STATE_DB=${CELERY__STATE_DB:-"/mnt/volumes/statics/worker@%h.state"}
 # expressed in KB
 CELERY__MAX_MEMORY_PER_CHILD=${CELERY__MAX_MEMORY_PER_CHILD:-"200000"}
-CELERY__AUTOSCALE_VALUES=${CELERY__AUTOSCALE_VALUES:-"15,10"}
+CELERY__AUTOSCALE_VALUES=${CELERY__AUTOSCALE_VALUES:-"10,5"}
 CELERY__MAX_TASKS_PER_CHILD=${CELERY__MAX_TASKS_PER_CHILD:-"10"}
-CELERY__OPTS=${CELERY__OPTS:-"--without-gossip --without-mingle -Ofair -B -E"}
-CELERY__BEAT_SCHEDULE=${CELERY__BEAT_SCHEDULE:-"celery.beat:PersistentScheduler"}
-CELERY__LOG_LEVEL=${CELERY__LOG_LEVEL:-"INFO"}
+CELERY__OPTS=${CELERY__OPTS:-"--without-gossip --without-mingle -Ofair -E"}
+CELERY__LOG_LEVEL=${CELERY__LOG_LEVEL:-"ERROR"}
 CELERY__LOG_FILE=${CELERY__LOG_FILE:-"/var/log/celery.log"}
 CELERY__WORKER_NAME=${CELERY__WORKER_NAME:-"worker1@%h"}
 CELERY__WORKER_CONCURRENCY=${CELERY__WORKER_CONCURRENCY:-"4"}
 
+# Celery beat settings
+CELERY__BEAT_SCHEDULE=${CELERY__BEAT_SCHEDULE:-"celery.beat:PersistentScheduler"}
+CELERY__BEAT_LOG=${CELERY__BEAT_LOG:-"/var/log/celery_beat.log"}
+
+# Harvester settings
+CELERY__HARVESTER_WORKER_NAME=${CELERY__HARVESTER_WORKER_NAME:-"harvesting_worker@%h"}
+CELERY__HARVESTER_CONCURRENCY=${CELERY__HARVESTER_CONCURRENCY:-"10"}
+CELERY__HARVESTER_AUTOSCALE_VALUES=${CELERY__HARVESTER_AUTOSCALE_VALUES:-"15,10"}
+CELERY__HARVESTER_MAX_MEMORY_PER_CHILD=${CELERY__MAX_MEMORY_PER_CHILD:-"500000"}
+
+# --- FIX: Remove stale Beat pidfile before starting beat ---
+BEAT_PIDFILE="/tmp/celerybeat.pid"
+
+if [ -f "$BEAT_PIDFILE" ]; then
+    PID=$(cat "$BEAT_PIDFILE" 2>/dev/null)
+
+    # If PID exists and is running → warn but continue (avoid killing)
+    if kill -0 "$PID" 2>/dev/null; then
+        echo "WARNING: Celery Beat seems to be running already (PID $PID). Removing stale pidfile anyway."
+    else
+        echo "Removing stale Celery Beat pidfile: $BEAT_PIDFILE"
+    fi
+
+    rm -f "$BEAT_PIDFILE"
+fi
+# --- END FIX ---
+
+echo "Starting Celery Beat..."
+$CELERY_BIN -A $CELERY_APP beat --scheduler=$CELERY__BEAT_SCHEDULE \
+    --loglevel=$CELERY__LOG_LEVEL -f $CELERY__BEAT_LOG --pidfile=/tmp/celerybeat.pid &
+
+echo "Starting Default Celery Worker..."
 $CELERY_BIN -A $CELERY_APP worker --autoscale=$CELERY__AUTOSCALE_VALUES \
     --max-memory-per-child=$CELERY__MAX_MEMORY_PER_CHILD $CELERY__OPTS \
-    --statedb=$CELERY__STATE_DB --scheduler=$CELERY__BEAT_SCHEDULE \
+    --statedb=$CELERY__STATE_DB \
     --loglevel=$CELERY__LOG_LEVEL -n $CELERY__WORKER_NAME -f $CELERY__LOG_FILE \
-    --concurrency=$CELERY__WORKER_CONCURRENCY --max-tasks-per-child=$CELERY__MAX_TASKS_PER_CHILD
+    --concurrency=$CELERY__WORKER_CONCURRENCY --max-tasks-per-child=$CELERY__MAX_TASKS_PER_CHILD \
+    -X harvesting &
+
+echo "Starting Harvester Celery Worker..."
+$CELERY_BIN -A $CELERY_APP worker -Q harvesting \
+    --autoscale=$CELERY__HARVESTER_AUTOSCALE_VALUES \
+    --max-memory-per-child=$CELERY__HARVESTER_MAX_MEMORY_PER_CHILD \
+    --loglevel=$CELERY__LOG_LEVEL \
+    -n $CELERY__HARVESTER_WORKER_NAME \
+    --concurrency=$CELERY__HARVESTER_CONCURRENCY \
+    -f $CELERY__LOG_FILE &
+
+# Wait for any process to exit
+wait -n
+
+# Exit with the status of the process that exited first
+# Docker will restart the container if this is non-zero (i.e., a failure)
+exit $?