Fix prepull script (#98)

* use desired_number_scheduled instead of hardcoded

* fix prepull daemon watch

* remove dev notebook

* use label

.gitignore

@@ -6,3 +6,165 @@ utils/prepull-deployment-manifest.yaml
 utils/prepull-daemon-manifest.yaml
 **/nohup.out
 **/prepull.log
+
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

utils/prepull_images.py

@@ -5,6 +5,7 @@
 import json
 import logging
 from random import randint
+import time
 
 import yaml
 import kubernetes
@@ -66,6 +67,7 @@ def prepull_deployment(namespace, images_to_prepull=None):
     manifest = build_manifest(kind="Deployment",
                               images_to_prepull=images_to_prepull)
     label_name = "prepull-deployment-" + str(randint(100000, 999999))
+    manifest["metadata"]["labels"]["name"] = label_name
     manifest["spec"]["template"]["metadata"]["labels"]["name"] = label_name
     manifest["spec"]["selector"]["matchLabels"]["name"] = label_name
     kube_apps_api.create_namespaced_deployment(namespace=namespace,
@@ -75,7 +77,8 @@ def prepull_deployment(namespace, images_to_prepull=None):
     w = kubernetes.watch.Watch()
     for event in w.stream(kube_core_api.list_namespaced_pod,
                           namespace=namespace,
-                          label_selector=f"name={label_name}"
+                          label_selector=f"name={label_name}",
+                          timeout_seconds=0
                           ):
         pod_state = event['object'].status.phase
         if pod_state == "Running":
@@ -89,18 +92,33 @@ def prepull_daemon(namespace, images_to_prepull=None):
     manifest = build_manifest(kind="DaemonSet",
                               images_to_prepull=images_to_prepull)
     label_name = "prepull-daemonset-" + str(randint(100000, 999999))
+    manifest["metadata"]["labels"]["name"] = label_name
     manifest["spec"]["template"]["metadata"]["labels"]["name"] = label_name
     manifest["spec"]["selector"]["matchLabels"]["name"] = label_name
     kube_apps_api.create_namespaced_daemon_set(namespace=namespace,
                                                body=manifest)
 
-    # Wait for all daemons to be in Running state and remove the DaemonSet
+    # Get total number of daemons that will be launched
+    time.sleep(5)  # Let the daemonset set itself up
+    daemon_info = kube_apps_api.list_namespaced_daemon_set(namespace=namespace,
+                                                           label_selector=f"name={label_name}")
+    n_daemons_total = daemon_info.to_dict()["items"][0]["status"]["desired_number_scheduled"]
+
+    # Wait for all daemons to be in Running state
+    counter_n_daemons_ready = 0
     w = kubernetes.watch.Watch()
     for event in w.stream(kube_apps_api.list_namespaced_daemon_set,
                           namespace=namespace,
-                          label_selector=f"name={label_name}"):
+                          label_selector=f"name={label_name}",
+                          timeout_seconds=0
+                          ):
         n_daemons_ready = event['object'].status.number_ready
-        if n_daemons_ready == 11:
+
+        if n_daemons_ready > counter_n_daemons_ready:
+            logging.info(f'{n_daemons_ready}/{n_daemons_total} daemons done.')
+            counter_n_daemons_ready = n_daemons_ready
+
+        if n_daemons_ready == n_daemons_total:
             w.stop()
             break
 
@@ -109,12 +127,12 @@ def prepull_images(namespace, images_to_prepull=None):
     """Full prepull procedure."""
     # 1st step : create a Deployment to pull the images in the global registry cache once
     logging.info('1st step : Deployment')
-    prepull_deployment(namespace=NAMESPACE, images_to_prepull=images_to_prepull)
+    prepull_deployment(namespace=namespace, images_to_prepull=images_to_prepull)
 
     # 2nd step : create a DaemonSet to pull the images in each worker's local cache
     logging.info('2nd step : DaemonSet')
-    prepull_daemon(namespace=NAMESPACE, images_to_prepull=images_to_prepull)
-    
+    prepull_daemon(namespace=namespace, images_to_prepull=images_to_prepull)
+
     logging.info('Prepull job done')
 
 

utils/prepull_images.sh

@@ -7,7 +7,8 @@ pip install kubernetes
 
 KUBERNETES_NAMESPACE=`cat /var/run/secrets/kubernetes.io/serviceaccount/namespace`
 
-# IMAGES_TO_PREPULL='inseefrlab/onyxia-vscode-python:py3.10.9'
+# 
+# IMAGES_TO_PREPULL='inseefrlab/onyxia-jupyter-python:py3.11.4,inseefrlab/onyxia-jupyter-python:py3.10.12'
 python prepull_images.py $KUBERNETES_NAMESPACE $IMAGES_TO_PREPULL
 
 kubectl delete deployments.apps --ignore-not-found=true prepull

utils/prepull_template.yaml

@@ -5,7 +5,7 @@ kind: ""
 metadata:
   name: prepull
   labels:
-    name: prepull
+    name: ""
 spec:
   selector:
     matchLabels: