First version moved to bzkf org

.github/workflows/benchmark.yaml

@@ -0,0 +1,33 @@
+name: benchmark
+
+on:
+  workflow_dispatch: {}
+
+permissions: read-all
+
+jobs:
+  benchmark:
+    runs-on: ubuntu-24.04
+    env:
+      SYNTHEA_POPULATION_SIZE: "100"
+    steps:
+      - name: Checkout
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
+        with:
+          fetch-depth: 0
+
+      - name: Install Task
+        uses: arduino/setup-task@b91d5d2c96a56797b48ac1e0e89220bf64044611 # v2.0.0
+        with:
+          version: "3.38.0"
+
+      - name: Run benchmark
+        run: |
+          task run
+
+      - name: Upload results
+        uses: actions/upload-artifact@0b2256b8c012f0828dc542b3febcab082c67f72b # v4.3.4
+        with:
+          name: benchmark-results
+          path: |
+            src/results/

.gitignore

@@ -0,0 +1,186 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python
+
+*.jar
+output/
+blazectl
+
+
+results/
+spark-tmp/
+
+synthea/

.sqlfluff

@@ -0,0 +1,8 @@
+[sqlfluff]
+dialect = trino
+max_line_length = 120
+# RF01 doesn't really work with structs.
+exclude_rules = RF01
+
+[sqlfluff:rules:capitalisation.identifiers]
+extended_capitalisation_policy = lower

.vscode/launch.json

@@ -0,0 +1,16 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python Debugger: Current File",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "cwd": "${workspaceFolder}/src"
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "sqlfluff.executablePath": ".venv/bin/sqlfluff"
+}

README.md

@@ -1 +1,11 @@
-# analytics-on-fhir-benchmark
+# Analytics on FHIR Benchmark
+
+## Setup
+
+```sh
+git clone https://github.com/bzkf/analytics-on-fhir-benchmark.git
+cd analytics-on-fhir-benchmark/
+./setup.sh
+
+task run
+```

Taskfile.yaml

@@ -0,0 +1,81 @@
+version: "3"
+
+env:
+  SYNTHEA_POPULATION_SIZE: 1000
+
+vars:
+  # only here as a comment. not yet used to loop through all at once.
+  SYNTHEA_POPULATION_SIZES:
+    - 1000
+    - 5000
+    - 10000
+    - 50000
+    - 100000
+
+tasks:
+  install-dependencies:
+    cmds:
+      - curl -LO https://github.com/synthetichealth/synthea/releases/download/master-branch-latest/synthea-with-dependencies.jar
+      - curl -LO https://repo1.maven.org/maven2/io/trino/trino-cli/453/trino-cli-453-executable.jar
+      - curl -LO https://github.com/samply/blazectl/releases/download/v0.16.0/blazectl-0.16.0-linux-amd64.tar.gz
+      - tar xzf blazectl-0.16.0-linux-amd64.tar.gz
+      - rm blazectl-0.16.0-linux-amd64.tar.gz
+      - ./blazectl --version
+      - pip install -r requirements.txt
+    generates:
+      - synthea-with-dependencies.jar
+      - blazectl
+      - trino-cli-453-executable.jar
+
+  # TODO: could use a task loop to generate synthea data for all sizes at once.
+  generate-fhir-data:
+    cmds:
+      - java -jar synthea-with-dependencies.jar -s 20240711 -cs 20240711 -r 20240711 -p "${SYNTHEA_POPULATION_SIZE}" -c config/synthea.properties --exporter.baseDirectory="./synthea/output-${SYNTHEA_POPULATION_SIZE}/bulk" --exporter.fhir.bulk_data="true"
+      - java -jar synthea-with-dependencies.jar -s 20240711 -cs 20240711 -r 20240711 -p "${SYNTHEA_POPULATION_SIZE}" -c config/synthea.properties --exporter.baseDirectory="./synthea/output-${SYNTHEA_POPULATION_SIZE}/transactions" --exporter.fhir.bulk_data="false"
+
+  start-servers:
+    cmds:
+      - docker compose -f compose.blaze.yaml -f compose.pathling.yaml -f compose.trino.yaml up -d
+      # after the import is done, we no longer need the pathling server itself
+      - docker compose -f compose.pathling.yaml stop pathling
+
+  upload-fhir-data:
+    cmds:
+      # blaze
+      # hospitalInformation & practitionerInformation are required for referential integrity.
+      - curl -X POST --header 'Content-Type:application/fhir+json' --data @"$(find synthea/output-${SYNTHEA_POPULATION_SIZE}/transactions/fhir/ -name 'hospitalInformation*.json')" --url 'http://localhost:8084/fhir'
+      - curl -X POST --header 'Content-Type:application/fhir+json' --data @"$(find synthea/output-${SYNTHEA_POPULATION_SIZE}/transactions/fhir/ -name 'practitionerInformation*.json')" --url 'http://localhost:8084/fhir'
+      - ./blazectl upload --concurrency 32 synthea/output-${SYNTHEA_POPULATION_SIZE}/transactions/fhir/ --server http://localhost:8084/fhir
+      # hapi fhir jpa
+      # - curl -X POST --header 'Content-Type:application/fhir+json' --data @"$(find output/transactions/fhir/ -name 'hospitalInformation*.json')" --url 'http://localhost:8084/fhir'
+      # - curl -X POST --header 'Content-Type:application/fhir+json' --data @"$(find output/transactions/fhir/ -name 'practitionerInformation*.json')" --url 'http://localhost:8084/fhir'
+      # - ./blazectl upload output/transactions/fhir/ --server http://localhost:8084/fhir
+
+  remove-local-synthea-files:
+    cmds:
+      - rm -r synthea/
+
+  run-benchmarks:
+    dir: src/
+    cmds:
+      - python main.py
+
+  draw-plots:
+    dir: src/
+    cmds:
+      - python plot.py
+
+  run:
+    cmds:
+      - task: install-dependencies
+      - task: generate-fhir-data
+      - task: start-servers
+      - task: upload-fhir-data
+      - task: remove-local-synthea-files
+      - task: run-benchmarks
+      - task: draw-plots
+      - task: clean
+
+  clean:
+    cmds:
+      - docker compose -f compose.blaze.yaml -f compose.pathling.yaml -f compose.trino.yaml down -v --remove-orphans

compose.blaze.yaml

@@ -0,0 +1,35 @@
+services:
+  blaze:
+    image: docker.io/samply/blaze:0.29.3@sha256:47527f478ef2ddf932f4e5c882c0266ac179d7a2fc37ed66868d079698541da3
+    environment:
+      JAVA_TOOL_OPTIONS: "-Xmx64g"
+      BASE_URL: "http://localhost:8083"
+    volumes:
+      - "blaze-data:/app/data"
+    ports:
+      - "127.0.0.1:8083:8080"
+
+  wait-for-blaze:
+    image: docker.io/curlimages/curl:8.8.0@sha256:73e4d532ea62d7505c5865b517d3704966ffe916609bedc22af6833dc9969bcd
+    ipc: none
+    security_opt:
+      - "no-new-privileges:true"
+    cap_drop:
+      - ALL
+    privileged: false
+    restart: "no"
+    environment:
+      BLAZE_SERVER_URL: http://blaze:8080
+    entrypoint: ["/bin/sh", "-c"]
+    command:
+      - |
+        until [ "$(curl -s -o /dev/null -L -w "%{http_code}" "$$BLAZE_SERVER_URL/fhir/metadata")" == "200" ]; do
+            echo "$(date): Waiting for blaze server @ $$BLAZE_SERVER_URL to be up";
+            sleep 5;
+        done;
+    depends_on:
+      blaze:
+        condition: service_started
+
+volumes:
+  blaze-data: {}