Merge pull request #10 from JGCRI/develop

Releasing v0.6.0

.github/workflows/documentation.yml

@@ -0,0 +1,27 @@
+name: documentation
+
+on: [push, pull_request, workflow_dispatch]
+
+permissions:
+  contents: write
+
+jobs:
+  docs:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+      - name: Install dependencies
+        run: |
+          pip install sphinx sphinx_rtd_theme myst_parser
+      - name: Sphinx build
+        run: |
+          sphinx-build docs _build
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
+        with:
+          publish_branch: gh-pages
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: _build/
+          force_orphan: true

.gitignore

@@ -8,5 +8,6 @@ communicator/src/communicator
 containers/
 config_dict.yaml
 cache/
+docs/_build/
 logs/
 .vscode/

.readthedocs.yaml

@@ -0,0 +1,22 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version, and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.12"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+   configuration: docs/conf.py
+
+# Optionally, but recommended,
+# declare the Python requirements required to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+    install:
+    - requirements: docs/requirements.txt

README.md

@@ -1,5 +1,5 @@
 # Scalable 
-[v0.5.7](https://github.com/JGCRI/scalable/tree/0.5.7)
+[v0.6.0](https://github.com/JGCRI/scalable/tree/0.6.0)
 
 Scalable is a Python library which aids in running complex workflows on HPCs by orchestrating multiple containers, requesting appropriate HPC jobs to the scheduler, and providing a python environment for distributed computing. It's designed to be primarily used with JGCRI Climate Models but can be easily adapted for any arbitrary uses.
 
@@ -80,9 +80,9 @@ cluster.add_container(tag="osiris", cpus=8, memory="20G", dirs={"/rcfs/projects/
 Before launching the workers, the configuration of worker or container targets needs to be specified. The containers to be launched as workers need to be first added by specifying their tag, number of cpu cores they need, the memory they would need, and the directory on the HPC Host to bind to the containers so that these directories are accessible by the container.
 
 ```python
-cluster.add_worker(n=3, tag="gcam")
-cluster.add_worker(n=2, tag="stitches")
-cluster.add_worker(n=3, tag="osiris")
+cluster.add_workers(n=3, tag="gcam")
+cluster.add_workers(n=2, tag="stitches")
+cluster.add_workers(n=3, tag="osiris")
 ```
 
 Launching workers on the cluster can be done by just adding workers to the cluster. This call will only be successful if the tags used have also had containers with the same tag added beforehand. Removing workers is similarly as easy.
@@ -156,12 +156,12 @@ def func3(param):
 
 ```
 
-In the example above, the functions will wait 5, 3, and 10 seconds for the first time they are computed. However, their results will be cached due to the decorator and so, if the functions are ran again with the same arguments, their results are going to be returned from memory instead and they wouldn't sleep. There are arguments which directly can be given to the cacheable decorator. **It is always recommended to specify the return type and the type of arguments for each use.** This ensures expected functioning of the module and for correct caching. --TODO--
+In the example above, the functions will wait 5, 3, and 10 seconds for the first time they are computed. However, their results will be cached due to the decorator and so, if the functions are ran again with the same arguments, their results are going to be returned from memory instead and they wouldn't sleep. There are arguments which directly can be given to the cacheable decorator. **It is always recommended to specify the return type and the type of arguments for each use.** This ensures expected functioning of the module and for correct caching.
 
 ## Contact
 
-For any contribution, questions, or requests, please feel free to [open an issue](https://github.com/JGCRI/scalable/issues) or contact us directly:
-**Shashank Lamba** [[email protected]](mailto:[email protected])
+For any contribution, questions, or requests, please feel free to [open an issue](https://github.com/JGCRI/scalable/issues) or contact us directly:\
+**Shashank Lamba** [[email protected]](mailto:[email protected])\
 **Pralit Patel** [[email protected]](mailto:[email protected])
 
 ## [License](https://github.com/JGCRI/scalable/blob/master/LICENSE.md)

communicator/src/communicator.go

@@ -17,26 +17,28 @@ import (
 // Changing CONNECTION_TYPE is not recommended
 
 const (
-	DEFAULT_HOST    = "0.0.0.0"
-	DEFAULT_PORT    = "1919"
-	CONNECTION_TYPE = "tcp"
+	DEFAULT_HOST     = "0.0.0.0"
+	DEFAULT_PORT     = "1919"
+	CONNECTION_TYPE  = "tcp"
+	NUM_PORT_RETRIES = 5
 )
 
 var BUFFER_LEN = 5120
 
 func main() {
 	arguments := os.Args[1:]
 	listen_port := DEFAULT_PORT
-	if len(arguments) > 1 {
-		listen_port = arguments[1]
-	} else if len(arguments) == 0 {
-		fmt.Println("Either -s or -c option needed")
+	argslen := len(arguments)
+	if argslen == 0 {
+		fmt.Println("Either -s or -c option needed. Use -h for help.")
 		gracefulExit()
+	} else if argslen > 1 {
+		listen_port = arguments[1]
 	}
 	if arguments[0] == "-s" {
 		loop := 0
 		server, err := net.Listen(CONNECTION_TYPE, DEFAULT_HOST+":"+listen_port)
-		for err != nil && loop < 5 && len(arguments) <= 1 {
+		for err != nil && loop < NUM_PORT_RETRIES && argslen <= 1 {
 			listen_port = strconv.Itoa(rand.Intn(40000-2000) + 2000)
 			server, err = net.Listen(CONNECTION_TYPE, DEFAULT_HOST+":"+listen_port)
 			loop++
@@ -119,6 +121,13 @@ func main() {
 			received += read
 		}
 		fmt.Print(output.String())
+	} else if arguments[0] == "-h" {
+		fmt.Println("Usage: communicator [OPTION] [PORT]")
+		fmt.Println("Options:")
+		fmt.Println("  -s\t\tStart server")
+		fmt.Println("  -c\t\tStart client")
+		fmt.Println("  -h\t\tShow help")
+		fmt.Println("PORT is optional and defaults to 1919 for server use.")
 	} else {
 		fmt.Println("Invalid option")
 		gracefulExit()
@@ -141,7 +150,7 @@ func handleRequest(client net.Conn) {
 	buffer := make([]byte, BUFFER_LEN)
 	received := 0
 	flag := 0
-	for received < len(lenBuffer) {
+	for received < len(lenBuffer) && received < BUFFER_LEN {
 		read, err := client.Read(lenBuffer[received:])
 		if err != nil {
 			clientClose(err, client)
@@ -230,7 +239,7 @@ func handleRequest(client net.Conn) {
 		return
 	}
 	sent = 0
-	for sent < len(lastOutput.String()) {
+	for sent < len(lastOutput.String()) && sent < BUFFER_LEN {
 		wrote, err := client.Write(([]byte(lastOutput.String()))[sent:])
 		if err != nil {
 			clientClose(err, client)

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/caching.rst

@@ -0,0 +1,17 @@
+Caching
+=======
+
+.. autofunction:: scalable.cacheable
+
+.. autoclass:: scalable.GenericType
+    :exclude-members: __init__
+
+.. autoclass:: scalable.FileType
+
+.. autoclass:: scalable.DirType
+
+.. autoclass:: scalable.ValueType
+
+.. autoclass:: scalable.ObjectType
+
+.. autoclass:: scalable.UtilityType

docs/conf.py

@@ -0,0 +1,45 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath('..'))
+sys.path.insert(0, os.path.abspath('../scalable'))
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+project = 'Scalable'
+copyright = '2024, Joint Global Change Research Institute'
+author = 'Shashank Lamba, Pralit Patel'
+release = '0.6.0'
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = ["sphinx.ext.autodoc", "sphinx.ext.todo", "sphinx.ext.viewcode", "sphinx.ext.napoleon"]
+
+templates_path = ['_templates']
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+autodoc_default_options = {
+    'members': True,
+    'undoc-members': True,
+    'private-members': False,
+    'special-members': '__init__',
+    'inherited-members': False,
+    'show-inheritance': False,
+    'no-index': True,
+}
+
+# add_module_names = False
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = 'sphinx_rtd_theme'
+html_static_path = ['_static']
+html_css_files = ['custom.css']

docs/functions.rst

@@ -0,0 +1,15 @@
+Submitting Functions
+====================
+
+.. autoclass:: scalable.ScalableClient
+    :exclude-members: submit, map, get_versions, cancel, close
+
+.. autofunction:: scalable.ScalableClient.submit
+
+.. autofunction:: scalable.ScalableClient.map
+
+.. autofunction:: scalable.ScalableClient.get_versions
+
+.. autofunction:: scalable.ScalableClient.cancel
+
+.. autofunction:: scalable.ScalableClient.close

docs/index.rst

@@ -0,0 +1,48 @@
+.. Scalable documentation master file, created by
+   sphinx-quickstart on Thu Aug 22 10:55:42 2024.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Scalable Documentation
+======================
+
+Scalable is a Python library for running complex workflows on HPC systems
+efficiently and with minimal manual intervention. It uses a dask backend and a 
+range of custom programs to achieve this. The figure below shows the general 
+architecture of Scalable.
+
+.. image:: images/scalable_architecture.png
+   :align: center
+
+These questions can help answering if Scalable would be useful for you:
+
+* Is your workflow ran on a HPC system and takes a significant amount of time?
+* Does your workflow involve pipelines, where outputs from certain functions or 
+  models are passed as inputs to other functions or models?
+* Do you want the hardware allocation to be done automatically?
+
+
+Scalable could be useful if one of more of the above questions are affirmative.
+To incorporate the ability to run functions under different environments, 
+docker containers can be used. A Dockerfile with multiple targets can be used
+to make multiple containers, each with different installed libraries and models.
+When adding workers to cluster, it can be specified how many workers of
+each type should be added.
+
+Contents:
+---------
+
+.. toctree::
+   :maxdepth: 1
+
+   workers
+
+.. toctree::
+   :maxdepth: 1
+
+   caching
+
+.. toctree::
+   :maxdepth: 1
+
+   functions

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/requirements.txt

@@ -0,0 +1,2 @@
+sphinx-rtd-theme
+scalable

docs/workers.rst

@@ -0,0 +1,16 @@
+Worker Management
+=================
+
+
+.. autoclass:: scalable.SlurmCluster
+   :exclude-members: close, job_cls, set_default_request_quantity
+
+.. autofunction:: scalable.SlurmCluster.add_container
+
+.. autofunction:: scalable.SlurmCluster.add_workers
+
+.. autofunction:: scalable.SlurmCluster.remove_workers
+
+.. autofunction:: scalable.SlurmCluster.close
+
+.. autofunction:: scalable.SlurmCluster.set_default_request_quantity

pyproject.toml

@@ -25,6 +25,8 @@ dependencies = [
     "joblib >= 1.3.2",
     "xxhash >= 3.4.1",
     "versioneer >= 0.29",
+    "numpy >= 1.26.4", 
+    "pandas >= 2.2.3"
 ]
 classifiers = [
     "Development Status :: 4 - Beta",
@@ -48,7 +50,6 @@ test = [
 
 [project.urls]
 "Github" = "https://github.com/JGCRI/scalable/tree/master/scalable"
-"Homepage" = "https://www.pnnl.gov"
 
 [project.scripts]
 scalable_bootstrap = "scalable.utilities:run_bootstrap"