Merge branch 'main' into codespaces

* main:
  New depencies for XGboost added
  add workflow to build codespace container
  Bump scipy from 1.11.3 to 1.11.4 (#548)
  Bump psycopg[binary] from 3.1.12 to 3.1.13 (#549)
  Fomantic update to 2.9.3 (#547)
  Allow digits in env var keys (#541)
  Hardware info root mac (#544)
  Trying if ref works
  Bump pydantic from 2.5.0 to 2.5.1 (#539)
  Adds the citation file (#537)
  HOG returned after mutliple loops
  Info button now works for page 2+ task coalitions
  Bump pydantic from 2.4.2 to 2.5.0 (#538)
  TDP typo
  Bump pandas from 2.1.2 to 2.1.3 (#534)
  Makes the root_hardware_info root writable only
  Hog API Fix for broken payload (#532)
  Adding report url instead of just ID (#531)
  Makes error optional except if there is data we need (#530)

.github/workflows/tests-vm-pr.yml

@@ -14,7 +14,7 @@ jobs:
       - name: 'Checkout repository'
         uses: actions/checkout@v4
         with:
-          ref: ${{ github.event.pull_request.head.ref }}
+          ref: ${{ github.ref }}
           submodules: 'true'
 
       - name: Eco CI Energy Estimation - Initialize

.gitignore

@@ -17,3 +17,4 @@ test-config.yml
 tests/structure.sql
 tools/sgx_enable
 venv/
+lib/hardware_info_root.py

CITATION.cff

@@ -0,0 +1,30 @@
+cff-version: 1.2.0
+title: Green Metrics Tool
+message: >-
+  If you use this software, please cite it using the
+  metadata from this file.
+type: software
+authors:
+  - given-names: Arne
+    family-names: Tarara
+    email: [email protected]
+    affiliation: Green Coding Berlin
+  - given-names: Dan
+    family-names: Mateas
+    email: [email protected]
+    affiliation: Green Coding Berlin
+  - given-names: Geerd-Dietger
+    family-names: Hoffmann
+    email: [email protected]
+    affiliation: Green Coding Berlin
+repository-code: 'https://github.com/green-coding-berlin/green-metrics-tool'
+url: 'https://www.green-coding.berlin/'
+repository: 'https://github.com/green-coding-berlin/'
+abstract: >-
+  The Green Metrics Tool is a developer tool indented for
+  measuring the energy and CO2 consumption of software
+  through a software life cycle analysis (SLCA).
+keywords:
+  - Green Coding
+  - 'Software Life Cycle Assessment '
+license: AGPL-3.0-or-later

api/main.py

@@ -19,7 +19,7 @@
 from starlette.responses import RedirectResponse
 from starlette.exceptions import HTTPException as StarletteHTTPException
 
-from pydantic import BaseModel
+from pydantic import BaseModel, ValidationError
 
 import anybadge
 
@@ -576,6 +576,48 @@ def replace_nan_with_zero(obj):
     return obj
 
 
+def validate_measurement_data(data):
+    required_top_level_fields = [
+        'coalitions', 'all_tasks', 'elapsed_ns', 'processor', 'thermal_pressure'
+    ]
+    for field in required_top_level_fields:
+        if field not in data:
+            raise ValueError(f"Missing required field: {field}")
+
+    # Validate 'coalitions' structure
+    if not isinstance(data['coalitions'], list):
+        raise ValueError("Expected 'coalitions' to be a list")
+
+    for coalition in data['coalitions']:
+        required_coalition_fields = [
+            'name', 'tasks', 'energy_impact_per_s', 'cputime_ms_per_s',
+            'diskio_bytesread', 'diskio_byteswritten', 'intr_wakeups', 'idle_wakeups'
+        ]
+        for field in required_coalition_fields:
+            if field not in coalition:
+                raise ValueError(f"Missing required coalition field: {field}")
+            if field == 'tasks' and not isinstance(coalition['tasks'], list):
+                raise ValueError(f"Expected 'tasks' to be a list in coalition: {coalition['name']}")
+
+    # Validate 'all_tasks' structure
+    if 'energy_impact_per_s' not in data['all_tasks']:
+        raise ValueError("Missing 'energy_impact_per_s' in 'all_tasks'")
+
+    # Validate 'processor' structure based on the processor type
+    processor_fields = data['processor'].keys()
+    if 'ane_energy' in processor_fields:
+        required_processor_fields = ['combined_power', 'cpu_energy', 'gpu_energy', 'ane_energy']
+    elif 'package_joules' in processor_fields:
+        required_processor_fields = ['package_joules', 'cpu_joules', 'igpu_watts']
+    else:
+        raise ValueError("Unknown processor type")
+
+    for field in required_processor_fields:
+        if field not in processor_fields:
+            raise ValueError(f"Missing required processor field: {field}")
+
+    # All checks passed
+    return True
 
 @app.post('/v1/hog/add')
 async def hog_add(measurements: List[HogMeasurement]):
@@ -591,9 +633,16 @@ async def hog_add(measurements: List[HogMeasurement]):
         #Check if the data is valid, if not this will throw an exception and converted into a request by the middleware
         try:
             _ = Measurement(**measurement_data)
-        except RequestValidationError as exc:
-            print(f"Caught Exception {exc}")
+        except (ValidationError, RequestValidationError) as exc:
+            print(f"Caught Exception in Measurement() {exc.__class__.__name__} {exc}")
             print(f"Errors are: {exc.errors()}")
+            if GlobalConfig().config['admin']['no_emails'] is False:
+                email_helpers.send_admin_email('Hog parsing error', str(exc))
+
+        try:
+            validate_measurement_data(measurement_data)
+        except ValueError as exc:
+            print(f"Caught Exception in validate_measurement_data() {exc.__class__.__name__} {exc}")
             raise exc
 
         coalitions = []
@@ -752,7 +801,7 @@ async def hog_add(measurements: List[HogMeasurement]):
                 )
                 DB().fetch_one(query=query, params=params)
 
-        return Response(status_code=204) # No-Content
+    return Response(status_code=204) # No-Content
 
 
 @app.get('/v1/hog/top_processes')

docker/requirements.txt

@@ -1,10 +1,10 @@
 gunicorn==21.2.0
-psycopg[binary]==3.1.12
+psycopg[binary]==3.1.13
 fastapi==0.104.1
 uvicorn[standard]==0.24.0.post1
-pandas==2.1.2
+pandas==2.1.3
 PyYAML==6.0.1
 anybadge==1.14.0
 orjson==3.9.10
-scipy==1.11.3
+scipy==1.11.4
 schema==0.7.5