Hotfix/code quality on benchmarks

.github/workflows/lint.yml

@@ -0,0 +1,55 @@
+name: Lint
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  linting:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.x'
+
+      - name: Cache virtualenv
+        uses: actions/cache@v4
+        with:
+          path: python-venv
+          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('requirements.txt') }}-${{ github.ref_name }}
+          restore-keys: |
+            venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('requirements.txt') }}-
+            venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-
+
+      - name: Install system packages
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libcurl4-openssl-dev
+
+      - name: Install Python dependencies (via install.py)
+        run: |
+          python3 install.py --no-aws --no-azure --no-gcp --no-openwhisk --no-local
+
+      - name: Black (check)
+        run: |
+          . python-venv/bin/activate
+          black benchmarks --check --config .black.toml
+
+      - name: Flake8 (lint)
+        run: |
+          . python-venv/bin/activate
+          # write to file and echo to stdout (requires flake8 with --tee support)
+          flake8 benchmarks --config=.flake8.cfg --tee --output-file flake-reports
+
+      - name: Upload flake report
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: flake-reports
+          path: flake-reports

.pre-commit-config.yaml

@@ -9,7 +9,7 @@ repos:
         entry: flake8
         args: ["--config=.flake8.cfg"]
         types: [python]
-        files: ^sebs/
+        files: ^(sebs/|benchmarks/)
   - repo: local
     hooks:
       - id: black-check-local
@@ -19,5 +19,12 @@ repos:
         entry: black
         args: ["--config=.black.toml", "--check", "--diff"]
         types: [python]
-        files: ^sebs/
+        files: ^(sebs/|benchmarks/)
+  # - repo: local
+  #   hooks:
+  #     - id: mypy-local
+  #       name: mypy (project venv)
+  #       language: system
+  #       entry: bash -lc 'python -m mypy --config-file=.mypy.ini sebs'
+  #       types: [python]
 

benchmarks/000.microbenchmarks/010.sleep/input.py

@@ -1,12 +1,11 @@
+size_generators = {"test": 1, "small": 100, "large": 1000}
 
-size_generators = {
-    'test' : 1,
-    'small' : 100,
-    'large': 1000
-}
 
 def buckets_count():
     return (0, 0)
 
-def generate_input(data_dir, size, benchmarks_bucket, input_paths, output_paths, upload_func, nosql_func):
-    return { 'sleep': size_generators[size] }
+
+def generate_input(
+    data_dir, size, benchmarks_bucket, input_paths, output_paths, upload_func, nosql_func
+):
+    return {"sleep": size_generators[size]}

benchmarks/000.microbenchmarks/010.sleep/python/function.py

@@ -1,9 +1,9 @@
-
 from time import sleep
 
+
 def handler(event):
 
     # start timing
-    sleep_time = event.get('sleep')
+    sleep_time = event.get("sleep")
     sleep(sleep_time)
-    return { 'result': sleep_time }
+    return {"result": sleep_time}

benchmarks/000.microbenchmarks/020.network-benchmark/input.py

@@ -2,10 +2,12 @@ def buckets_count():
     return 0, 1
 
 
-def generate_input(data_dir, size, benchmarks_bucket, input_paths, output_paths, upload_func, nosql_func):
+def generate_input(
+    data_dir, size, benchmarks_bucket, input_paths, output_paths, upload_func, nosql_func
+):
     return {
-        'bucket': {
-            'bucket': benchmarks_bucket,
-            'output': output_paths[0],
+        "bucket": {
+            "bucket": benchmarks_bucket,
+            "output": output_paths[0],
         },
     }

benchmarks/000.microbenchmarks/020.network-benchmark/python/function.py

@@ -1,27 +1,26 @@
 import csv
-import json
 import os.path
 import socket
 from datetime import datetime
-from time import sleep
 
 from . import storage
 
+
 def handler(event):
 
-    request_id = event['request-id']
-    address = event['server-address']
-    port = event['server-port']
-    repetitions = event['repetitions']
-    output_bucket = event.get('bucket').get('bucket')
-    output_prefix = event.get('bucket').get('output')
+    request_id = event["request-id"]
+    address = event["server-address"]
+    port = event["server-port"]
+    repetitions = event["repetitions"]
+    output_bucket = event.get("bucket").get("bucket")
+    output_prefix = event.get("bucket").get("output")
     times = []
     i = 0
     socket.setdefaulttimeout(3)
     server_socket = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
     server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
-    server_socket.bind(('', 0))
-    message = request_id.encode('utf-8')
+    server_socket.bind(("", 0))
+    message = request_id.encode("utf-8")
     adr = (address, port)
     consecutive_failures = 0
     while i < repetitions + 1:
@@ -43,16 +42,16 @@ def handler(event):
         consecutive_failures = 0
         server_socket.settimeout(2)
     server_socket.close()
-   
+
     if consecutive_failures != 5:
-        with open('/tmp/data.csv', 'w', newline='') as csvfile:
-            writer = csv.writer(csvfile, delimiter=',')
-            writer.writerow(["id", "client_send", "client_rcv"]) 
+        with open("/tmp/data.csv", "w", newline="") as csvfile:
+            writer = csv.writer(csvfile, delimiter=",")
+            writer.writerow(["id", "client_send", "client_rcv"])
             for row in times:
                 writer.writerow(row)
-      
+
         client = storage.storage.get_instance()
-        filename = 'results-{}.csv'.format(request_id)
-        key = client.upload(output_bucket, os.path.join(output_prefix, filename), '/tmp/data.csv')
+        filename = "results-{}.csv".format(request_id)
+        key = client.upload(output_bucket, os.path.join(output_prefix, filename), "/tmp/data.csv")
 
-    return { 'result': key }
+    return {"result": key}

benchmarks/000.microbenchmarks/030.clock-synchronization/input.py

@@ -1,12 +1,13 @@
-
-
 def buckets_count():
     return 0, 1
 
-def generate_input(data_dir, size, benchmarks_bucket, input_paths, output_paths, upload_func, nosql_func):
+
+def generate_input(
+    data_dir, size, benchmarks_bucket, input_paths, output_paths, upload_func, nosql_func
+):
     return {
-        'bucket': {
-            'bucket': benchmarks_bucket,
-            'output': output_paths[0],
+        "bucket": {
+            "bucket": benchmarks_bucket,
+            "output": output_paths[0],
         },
     }

benchmarks/000.microbenchmarks/030.clock-synchronization/python/function.py

@@ -1,28 +1,27 @@
 import csv
-import json
 import os
 import socket
 from datetime import datetime
-from time import sleep
 
 from . import storage
 
+
 def handler(event):
 
-    request_id = event['request-id']
-    address = event['server-address']
-    port = event['server-port']
-    repetitions = event['repetitions']
-    output_bucket = event.get('bucket').get('bucket')
-    output_prefix = event.get('bucket').get('output')
+    request_id = event["request-id"]
+    address = event["server-address"]
+    port = event["server-port"]
+    repetitions = event["repetitions"]
+    output_bucket = event.get("bucket").get("bucket")
+    output_prefix = event.get("bucket").get("output")
     times = []
     print("Starting communication with {}:{}".format(address, port))
     i = 0
     socket.setdefaulttimeout(4)
     server_socket = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
     server_socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
-    server_socket.bind(('', 0))
-    message = request_id.encode('utf-8')
+    server_socket.bind(("", 0))
+    message = request_id.encode("utf-8")
     adr = (address, port)
     consecutive_failures = 0
     measurements_not_smaller = 0
@@ -43,11 +42,13 @@ def handler(event):
         if i > 0:
             times.append([i, send_begin, recv_end])
         cur_time = recv_end - send_begin
-        print("Time {} Min Time {} NotSmaller {}".format(cur_time, cur_min, measurements_not_smaller))
+        print(
+            "Time {} Min Time {} NotSmaller {}".format(cur_time, cur_min, measurements_not_smaller)
+        )
         if cur_time > cur_min and cur_min > 0:
             measurements_not_smaller += 1
             if measurements_not_smaller == repetitions:
-                message = "stop".encode('utf-8')
+                message = "stop".encode("utf-8")
                 server_socket.sendto(message, adr)
                 break
         else:
@@ -57,18 +58,18 @@ def handler(event):
         consecutive_failures = 0
         server_socket.settimeout(4)
     server_socket.close()
-   
+
     if consecutive_failures != 5:
-        with open('/tmp/data.csv', 'w', newline='') as csvfile:
-            writer = csv.writer(csvfile, delimiter=',')
-            writer.writerow(["id", "client_send", "client_rcv"]) 
+        with open("/tmp/data.csv", "w", newline="") as csvfile:
+            writer = csv.writer(csvfile, delimiter=",")
+            writer.writerow(["id", "client_send", "client_rcv"])
             for row in times:
                 writer.writerow(row)
-      
+
         client = storage.storage.get_instance()
-        filename = 'results-{}.csv'.format(request_id)
-        key = client.upload(output_bucket, os.path.join(output_prefix, filename), '/tmp/data.csv')
+        filename = "results-{}.csv".format(request_id)
+        key = client.upload(output_bucket, os.path.join(output_prefix, filename), "/tmp/data.csv")
     else:
         key = None
 
-    return { 'result': {'bucket-key': key, 'timestamp':  event['income-timestamp']} }
+    return {"result": {"bucket-key": key, "timestamp": event["income-timestamp"]}}

benchmarks/000.microbenchmarks/040.server-reply/input.py

@@ -1,12 +1,11 @@
+size_generators = {"test": 1, "small": 100, "large": 1000}
 
-size_generators = {
-    'test' : 1,
-    'small' : 100,
-    'large': 1000
-}
 
 def buckets_count():
     return (0, 0)
 
-def generate_input(data_dir, size, benchmarks_bucket, input_paths, output_paths, upload_func, nosql_func):
-    return { 'sleep': size_generators[size] }
+
+def generate_input(
+    data_dir, size, benchmarks_bucket, input_paths, output_paths, upload_func, nosql_func
+):
+    return {"sleep": size_generators[size]}