Update to v0.5.0

Update python package and documentation from v0.4.2 to v0.5.0

[ committed by @mellis13 ]
[ reviewed by @ashao ]

.github/workflows/build_docs.yml

@@ -55,12 +55,12 @@ jobs:
           cp -r doc-branch/docs/* ./docs/
           rm -rf doc-branch
 
-      - name: build documentation with docker
+      - name: Build documentation with docker
         run: make docks
 
       - name: Commit files
         run: |
-          git add -A
+          git add -Af
           git config --local user.email "action@github.com"
           git config --local user.name "GitHub Action"
           git commit -m "Update develop documentation"

.github/workflows/release.yml

@@ -53,7 +53,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-20.04, macos-10.15]
+        os: [ubuntu-20.04, macos-12]
 
     steps:
       - uses: actions/checkout@v2
@@ -123,4 +123,4 @@ jobs:
         with:
           user: __token__
           password: ${{ secrets.PYPI }}
-          #repository_url: https://test.pypi.org/legacy/
+          #repository_url: https://test.pypi.org/legacy/

.github/workflows/run_tests.yml

@@ -49,13 +49,13 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-10.15, ubuntu-20.04] # Operating systems
+        os: [macos-12, ubuntu-20.04] # Operating systems
         compiler: [8] # GNU compiler version
         rai: [1.2.5, 1.2.7] # Redis AI versions
         py_v: [3.8, 3.9, '3.10'] # Python versions
         exclude:
           # Do not build with Redis AI 1.2.5 on MacOS
-          - os: macos-10.15
+          - os: macos-12
             rai: 1.2.5
           # Do not build Redis AI 1.2.5 with py3.10
           # as wheels for dependecies are not availble
@@ -128,3 +128,10 @@ jobs:
         with:
           fail_ci_if_error: true
           files: ./coverage.xml
+
+      - name: Run mypy
+        # TF 2.6.2 has a dep conflict with new mypy versions
+        if: (matrix.rai != '1.2.5')
+        run: |
+          python -m pip install .[mypy]
+          make check-mypy

.gitignore

@@ -7,6 +7,7 @@ __pycache__
 htmlcov
 smartsim.egg-info
 tests/test_output
+docs/*
 
 # Dependencies
 smartsim/_core/.third-party

.wci.yml

@@ -22,8 +22,8 @@
     language: Python
 
     release:
-      version: 0.4.2
-      date: 2023-04-12
+      version: 0.5.0
+      date: 2023-07-06
 
     documentation:
       general: https://www.craylabs.org/docs/overview.html

MANIFEST.in

@@ -1,4 +1,3 @@
-include requirements.txt
 include Makefile
 graft smartsim/
 

Makefile

@@ -107,6 +107,12 @@ check-lint:
 	@pylint --rcfile=.pylintrc ./smartsim
 
 
+# help: check-mypy                     - run static type check
+.PHONY: check-mypy
+check-mypy:
+	@mypy --config-file=./pyproject.toml
+
+
 # help:
 # help: Documentation
 # help: -------

README.md

@@ -99,8 +99,8 @@ before using it on your system. Each tutorial is a Jupyter notebook that can be
 which will run a jupyter lab with the tutorials, SmartSim, and SmartRedis installed.
 
 ```bash
-docker pull ghcr.io/craylabs/smartsim-tutorials:v0.4.2
-docker run -p 8888:8888 ghcr.io/craylabs/smartsim-tutorials:v0.4.2
+docker pull ghcr.io/craylabs/smartsim-tutorials:v0.4.1
+docker run -p 8888:8888 ghcr.io/craylabs/smartsim-tutorials:v0.4.1
 # click on link to open jupyter lab
 ```
 
@@ -452,7 +452,7 @@ which will run a jupyter lab with the tutorials, SmartSim, and SmartRedis instal
 
 ```bash
 docker pull ghcr.io/craylabs/smartsim-tutorials:v1
-docker run -p 8888:8888 ghcr.io/craylabs/smartsim-tutorials:v0.4.2
+docker run -p 8888:8888 ghcr.io/craylabs/smartsim-tutorials:v0.4.1
 ```
 Each of the following examples can be found in the
 [SmartSim documentation](https://www.craylabs.org/docs/tutorials/getting_started/getting_started.html).

conftest.py

@@ -27,7 +27,6 @@
 import json
 import os
 import inspect
-import shutil
 import pytest
 import psutil
 import shutil
@@ -44,13 +43,15 @@
 from smartsim._core.config import CONFIG
 from smartsim.error import SSConfigError
 from subprocess import run
+import sys
 
 
 # Globals, yes, but its a testing file
 test_path = os.path.dirname(os.path.abspath(__file__))
 test_dir = os.path.join(test_path, "tests", "test_output")
 test_launcher = CONFIG.test_launcher
 test_device = CONFIG.test_device
+test_num_gpus = CONFIG.test_num_gpus
 test_nic = CONFIG.test_interface
 test_alloc_specs_path = os.getenv("SMARTSIM_TEST_ALLOC_SPEC_SHEET_PATH", None)
 test_port = CONFIG.test_port
@@ -73,6 +74,7 @@ def print_test_configuration():
     global test_nic
     global test_alloc_specs_path
     global test_port
+
     print("TEST_SMARTSIM_LOCATION:", smartsim.__path__)
     print("TEST_PATH:", test_path)
     print("TEST_LAUNCHER:", test_launcher)
@@ -511,7 +513,7 @@ def _test_dir_path(caller_function, caller_fspath):
         return dir_path
 
     @staticmethod
-    def get_test_dir(caller_function=None, caller_fspath=None):
+    def get_test_dir(caller_function=None, caller_fspath=None, level=1):
         """Get path to test output.
 
         This function should be called without arguments from within
@@ -530,7 +532,7 @@ def get_test_dir(caller_function=None, caller_fspath=None):
         :rtype: str
         """
         if not caller_function or not caller_fspath:
-            caller_frame = inspect.stack()[1]
+            caller_frame = inspect.stack()[level]
             caller_fspath = caller_frame.filename
             caller_function = caller_frame.function
 
@@ -541,7 +543,7 @@ def get_test_dir(caller_function=None, caller_fspath=None):
         return dir_path
 
     @staticmethod
-    def make_test_dir(caller_function=None, caller_fspath=None):
+    def make_test_dir(caller_function=None, caller_fspath=None, level=1):
         """Create test output directory and return path to it.
 
         This function should be called without arguments from within
@@ -558,7 +560,7 @@ def make_test_dir(caller_function=None, caller_fspath=None):
         :rtype: str
         """
         if not caller_function or not caller_fspath:
-            caller_frame = inspect.stack()[1]
+            caller_frame = inspect.stack()[level]
             caller_fspath = caller_frame.filename
             caller_function = caller_frame.function
 
@@ -591,3 +593,38 @@ class MLUtils:
     def get_test_device():
         global test_device
         return test_device
+
+    @staticmethod
+    def get_test_num_gpus():
+        return test_num_gpus
+
+@pytest.fixture
+def coloutils():
+    return ColoUtils
+
+class ColoUtils:
+    def setup_test_colo(fileutils, db_type, exp, db_args):
+        """Setup things needed for setting up the colo pinning tests"""
+        # get test setup
+        test_dir = fileutils.make_test_dir(level=2)
+        sr_test_script = fileutils.get_test_conf_path("send_data_local_smartredis.py")
+
+        # Create an app with a colo_db which uses 1 db_cpu
+        colo_settings = exp.create_run_settings(exe=sys.executable, exe_args=sr_test_script)
+        colo_model = exp.create_model(f"colocated_model", colo_settings)
+        colo_model.set_path(test_dir)
+
+        if db_type in ['tcp', "deprecated"]:
+            db_args["port"] = 6780
+            db_args["ifname"] = "lo"
+
+        colocate_fun = {
+            "tcp": colo_model.colocate_db_tcp,
+            "deprecated": colo_model.colocate_db,
+            "uds":colo_model.colocate_db_uds
+        }
+        colocate_fun[db_type](**db_args)
+        # assert model will launch with colocated db
+        assert colo_model.colocated
+        # Check to make sure that limit_db_cpus made it into the colo settings
+        return colo_model

doc/_static/version_names.json

@@ -1,14 +1,16 @@
 {
     "version_names":[
         "develop (unstable)",
-        "0.4.2 (stable)",
+        "0.5.0 (stable)",
+        "0.4.2",
         "0.4.1",
         "0.4.0",
         "0.3.2"
     ],
     "version_urls": [
         "https://www.craylabs.org/develop/overview.html",
         "https://www.craylabs.org/docs/overview.html",
+        "https://www.craylabs.org/docs/versions/0.4.2/overview.html",
         "https://www.craylabs.org/docs/versions/0.4.1/overview.html",
         "https://www.craylabs.org/docs/versions/0.4.0/overview.html",
         "https://www.craylabs.org/docs/versions/0.3.2/overview.html"

doc/api/smartsim_api.rst

@@ -431,6 +431,10 @@ Model
    Model.colocate_db
    Model.colocate_db_tcp
    Model.colocate_db_uds
+   Model.colocated
+   Model.add_ml_model
+   Model.add_script
+   Model.add_function
    Model.params_to_args
    Model.register_incoming_entity
    Model.enable_key_prefixing
@@ -451,12 +455,15 @@ Ensemble
 .. autosummary::
 
    Ensemble.__init__
-   Ensemble.models
    Ensemble.add_model
+   Ensemble.add_ml_model
+   Ensemble.add_script
+   Ensemble.add_function
    Ensemble.attach_generator_files
-   Ensemble.register_incoming_entity
    Ensemble.enable_key_prefixing
+   Ensemble.models
    Ensemble.query_key_prefixing
+   Ensemble.register_incoming_entity
 
 .. autoclass:: Ensemble
    :members:

doc/changelog.rst

@@ -11,6 +11,98 @@ Jump to :ref:`SmartRedis Changelog <changelog>`
 SmartSim
 ========
 
+0.5.0
+------------------
+
+Released on 6 July 2023
+
+Description
+
+A full list of changes and detailed notes can be found below:
+
+- Update SmartRedis dependency to v0.4.1
+- Fix tests for db models and scripts
+- Fix add_ml_model() and add_script() documentation, tests, and code
+- Remove `requirements.txt` and other places where dependencies were defined
+- Replace `limit_app_cpus` with `limit_db_cpus` for co-located orchestrators
+- Remove wait time associated with Experiment launch summary
+- Update and rename Redis conf file
+- Migrate from redis-py-cluster to redis-py
+- Update full test suite to not require a TF wheel at test time
+- Update doc strings
+- Remove deprecated code
+- Relax the coloredlogs version
+- Update Fortran tutorials for SmartRedis
+- Add support for multiple network interface binding in Orchestrator and Colocated DBs
+- Add typehints and static analysis
+
+Detailed notes
+
+- Updates SmartRedis to the most current release (PR316_)
+- Fixes and enhancements to documentation (PR317_, PR314_, PR287_)
+- Various fixes and enhancements to the test suite (PR315_, PR312_, PR310_, PR302_, PR283_)
+- Fix a defect in the tests related to database models and scripts that was
+  causing key collisions when testing on workload managers (PR313_)
+- Remove `requirements.txt` and other places where dependencies were defined. (PR307_)
+- Fix defect where dictionaries used to create run settings can be changed
+  unexpectedly due to copy-by-ref (PR305_)
+- The underlying code for Model.add_ml_model() and Model.add_script() was fixed
+  to correctly handle multi-GPU configurations.  Tests were updated to run on
+  non-local launchers.  Documentation was updated and fixed.  Also, the default
+  testing interface has been changed to lo instead of ipogif. (PR304_)
+- Typehints have been added. A makefile target `make check-mypy` executes static
+  analysis with mypy. (PR295_, PR301_, PR303_)
+- Replace `limit_app_cpus` with `limit_db_cpus` for co-located orchestrators.
+  This resolves some incorrect behavior/assumptions about how the application
+  would be pinned.  Instead, users should directly specify the binding options in
+  their application using the options appropriate for their launcher (PR306_)
+- Simplify code in `random_permutations` parameter generation strategy (PR300_)
+- Remove wait time associated with Experiment launch summary (PR298_)
+- Update Redis conf file to conform with Redis v7.0.5 conf file (PR293_)
+- Migrate from redis-py-cluster to redis-py for cluster status checks (PR292_)
+- Update full test suite to no longer require a tensorflow wheel to be available at test time. (PR291_)
+- Correct spelling of colocated in doc strings (PR290_)
+- Deprecated launcher-specific orchestrators, constants, and ML
+  utilities were removed. (PR289_)
+- Relax the coloredlogs version to be greater than 10.0 (PR288_)
+- Update the Github Actions runner image from `macos-10.15`` to `macos-12``. The
+  former began deprecation in May 2022 and was finally removed in May 2023. (PR285_)
+- The Fortran tutorials had not been fully updated to show how to handle
+  return/error codes. These have now all been updated. (PR284_)
+- Orchestrator and Colocated DB now accept a list of interfaces to bind to. The
+  argument name is still `interface` for backward compatibility reasons. (PR281_)
+- Typehints have been added to public APIs. A makefile target to execute static
+  analysis with mypy is available `make check-mypy`. (PR295_)
+
+.. _PR317: https://github.com/CrayLabs/SmartSim/pull/317
+.. _PR316: https://github.com/CrayLabs/SmartSim/pull/316
+.. _PR315: https://github.com/CrayLabs/SmartSim/pull/314
+.. _PR314: https://github.com/CrayLabs/SmartSim/pull/314
+.. _PR313: https://github.com/CrayLabs/SmartSim/pull/313
+.. _PR312: https://github.com/CrayLabs/SmartSim/pull/312
+.. _PR310: https://github.com/CrayLabs/SmartSim/pull/310
+.. _PR307: https://github.com/CrayLabs/SmartSim/pull/307
+.. _PR306: https://github.com/CrayLabs/SmartSim/pull/306
+.. _PR305: https://github.com/CrayLabs/SmartSim/pull/305
+.. _PR304: https://github.com/CrayLabs/SmartSim/pull/304
+.. _PR303: https://github.com/CrayLabs/SmartSim/pull/303
+.. _PR302: https://github.com/CrayLabs/SmartSim/pull/302
+.. _PR301: https://github.com/CrayLabs/SmartSim/pull/301
+.. _PR300: https://github.com/CrayLabs/SmartSim/pull/300
+.. _PR298: https://github.com/CrayLabs/SmartSim/pull/298
+.. _PR295: https://github.com/CrayLabs/SmartSim/pull/295
+.. _PR293: https://github.com/CrayLabs/SmartSim/pull/293
+.. _PR292: https://github.com/CrayLabs/SmartSim/pull/292
+.. _PR291: https://github.com/CrayLabs/SmartSim/pull/291
+.. _PR290: https://github.com/CrayLabs/SmartSim/pull/290
+.. _PR289: https://github.com/CrayLabs/SmartSim/pull/289
+.. _PR288: https://github.com/CrayLabs/SmartSim/pull/288
+.. _PR287: https://github.com/CrayLabs/SmartSim/pull/287
+.. _PR285: https://github.com/CrayLabs/SmartSim/pull/285
+.. _PR284: https://github.com/CrayLabs/SmartSim/pull/284
+.. _PR283: https://github.com/CrayLabs/SmartSim/pull/283
+.. _PR281: https://github.com/CrayLabs/SmartSim/pull/281
+
 0.4.2
 -----
 
@@ -24,10 +116,10 @@ support to allow users to colocate their models with an orchestrator using
 Unix domain sockets and support for launching models as batch jobs.
 
 Additionally, SmartSim has updated its tool chains to provide a better user
-experience. Notably, SmarSim can now be used with Python 3.10, Redis 7.0.5, and 
+experience. Notably, SmarSim can now be used with Python 3.10, Redis 7.0.5, and
 RedisAI 1.2.7. Furthermore, SmartSim now utilizes SmartRedis's aggregation lists to
 streamline the use and extension of ML data loaders, making working with popular
-machine learning frameworks in SmartSim a breeze. 
+machine learning frameworks in SmartSim a breeze.
 
 A full list of changes and detailed notes can be found below:
 
@@ -64,9 +156,9 @@ Detailed Notes
 - Fix bug in colocated database entrypoint stemming from uninitialized variables. This bug affects PyTorch models being loaded into the database. (PR237_)
 - The release of RedisAI 1.2.7 allows us to update support for recent versions of PyTorch, Tensorflow, and ONNX (PR234_)
 - Make installation of correct Torch backend more reliable according to instruction from PyTorch
-- In addition to TCP, add UDS support for colocating an orchestrator with models. Methods 
+- In addition to TCP, add UDS support for colocating an orchestrator with models. Methods
   `Model.colocate_db_tcp` and `Model.colocate_db_uds` were added to expose this functionality.
-  The `Model.colocate_db` method remains and uses TCP for backward compatibility (PR246_) 
+  The `Model.colocate_db` method remains and uses TCP for backward compatibility (PR246_)
 
 .. _PR270: https://github.com/CrayLabs/SmartSim/pull/270
 .. _PR264: https://github.com/CrayLabs/SmartSim/pull/264