refactor: simplify throughput calculations and improve function documentation

Author: chandra-siri

tests/perf/microbenchmarks/_utils.py

@@ -43,12 +43,11 @@ def publish_benchmark_extra_info(
 
     object_size = params.file_size_bytes
     num_files = params.num_files
-    min_throughput = (object_size / (1024 * 1024) * num_files) / benchmark.stats["max"]
-    max_throughput = (object_size / (1024 * 1024) * num_files) / benchmark.stats["min"]
-    mean_throughput = (object_size / (1024 * 1024) * num_files) / benchmark.stats["mean"]
-    median_throughput = (
-        object_size / (1024 * 1024) * num_files
-    ) / benchmark.stats["median"]
+    total_uploaded_mib = (object_size / (1024 * 1024) * num_files)
+    min_throughput = total_uploaded_mib / benchmark.stats["max"]
+    max_throughput = total_uploaded_mib / benchmark.stats["min"]
+    mean_throughput = total_uploaded_mib / benchmark.stats["mean"]
+    median_throughput = total_uploaded_mib / benchmark.stats["median"]
 
     benchmark.extra_info["throughput_MiB_s_min"] = min_throughput
     benchmark.extra_info["throughput_MiB_s_max"] = max_throughput
@@ -62,7 +61,7 @@ def publish_benchmark_extra_info(
     print(f"  Median: {median_throughput:.2f} (approx, from median time)")
 
     if true_times:
-        throughputs = [(object_size / (1024 * 1024) * num_files) / t for t in true_times]
+        throughputs = [total_uploaded_mib / t for t in true_times]
         true_min_throughput = min(throughputs)
         true_max_throughput = max(throughputs)
         true_mean_throughput = statistics.mean(throughputs)

tests/perf/microbenchmarks/conftest.py

@@ -111,8 +111,7 @@ def _upload_worker(args):
 
 def _create_files(num_files, bucket_name, bucket_type, object_size, chunk_size=1024 * 1024 * 1024):
     """
-    1. using upload_appendable_object implement this and return a list of file names.
-    TODO: adapt this to REGIONAL BUCKETS as well.
+    Create/Upload objects for benchmarking and return a list of their names.
     """
     object_names = [
         f"{_OBJECT_NAME_PREFIX}-{uuid.uuid4().hex[:5]}" for _ in range(num_files)

tests/perf/microbenchmarks/reads/test_reads.py

@@ -318,7 +318,6 @@ def _download_files_worker(files_to_download, other_params, chunks, bucket_type)
             result = download_files_using_mrd_multi_coro(
                 loop, client, files_to_download, other_params, chunks
             )
-            # logging.info(f"downloading complete for ")
         finally:
             tasks = asyncio.all_tasks(loop=loop)
             for task in tasks: