wjones127 commented on code in PR #15101:
URL: https://github.com/apache/arrow/pull/15101#discussion_r1060970751
##########
cpp/src/parquet/arrow/reader_writer_benchmark.cc:
##########
@@ -197,6 +197,52 @@ BENCHMARK_TEMPLATE2(BM_WriteColumn, true, DoubleType);
BENCHMARK_TEMPLATE2(BM_WriteColumn, false, BooleanType);
BENCHMARK_TEMPLATE2(BM_WriteColumn, true, BooleanType);
+int32_t kInfiniteUniqueValues = -1;
+
+std::shared_ptr<::arrow::Table> RandomStringTable(int64_t length, int64_t
unique_values,
+ int64_t null_percentage) {
+ std::shared_ptr<::arrow::DataType> type = ::arrow::utf8();
+ std::shared_ptr<::arrow::Array> arr;
+ ::arrow::random::RandomArrayGenerator generator(500);
+ double null_probability = static_cast<double>(null_percentage) / 100.0;
+ if (unique_values == kInfiniteUniqueValues) {
+ arr = generator.String(length, /*min_length=*/3, /*max_length=*/32,
+ /*null_probability=*/null_probability);
+ } else {
+ arr = generator.StringWithRepeats(length, /*unique=*/unique_values,
+ /*min_length=*/3, /*max_length=*/32,
+ /*null_probability=*/null_probability);
+ }
+ return ::arrow::Table::Make(
+ ::arrow::schema({::arrow::field("column", type, null_percentage > 0)}),
{arr});
+}
+
+static void BM_WriteBinaryColumn(::benchmark::State& state) {
+ std::shared_ptr<::arrow::Table> table =
+ RandomStringTable(BENCHMARK_SIZE, state.range(1), state.range(0));
+
+ while (state.KeepRunning()) {
+ auto output = CreateOutputStream();
+ EXIT_NOT_OK(
+ WriteTable(*table, ::arrow::default_memory_pool(), output,
BENCHMARK_SIZE));
+ }
+
+ int64_t total_bytes = table->column(0)->chunk(0)->data()->buffers[1]->size();
+ state.SetItemsProcessed(BENCHMARK_SIZE * state.iterations());
+ state.SetBytesProcessed(total_bytes * state.iterations());
+}
+
+BENCHMARK(BM_WriteBinaryColumn)
+ ->Args({/*null_probability*/ 0, /*unique_values*/ 2})
+ ->Args({/*null_probability*/ 0, /*unique_values*/ 32})
+ ->Args({/*null_probability*/ 0, /*unique_values*/ kInfiniteUniqueValues})
+ ->Args({/*null_probability*/ 1, /*unique_values*/ 32})
+ ->Args({/*null_probability*/ 50, /*unique_values*/ 32})
+ ->Args({/*null_probability*/ 99, /*unique_values*/ 32})
+ ->Args({/*null_probability*/ 1, /*unique_values*/ kInfiniteUniqueValues})
+ ->Args({/*null_probability*/ 50, /*unique_values*/ kInfiniteUniqueValues})
+ ->Args({/*null_probability*/ 99, /*unique_values*/ kInfiniteUniqueValues});
Review Comment:
Good idea. If I do the same to the other benchmarks in the file, would that
break the continuity of their results in conbench?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
