Skip to content

refactor(silo): do not overly rely on std::ostream when writing to http buffer #1079

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
taepper merged 2 commits into from
Dec 4, 2025
Merged

refactor(silo): do not overly rely on std::ostream when writing to http buffer #1079

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b6720c9
refactor(silo): do not overly rely on std::ostream when writing to ht…
taepper Dec 2, 2025
c06fe84
refactor(silo): styling improvements
taepper Dec 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
66 changes: 41 additions & 25 deletions src/silo/query_engine/exec_node/ndjson_sink.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,8 @@
#include "silo/query_engine/exec_node/ndjson_sink.h"

#include <ios>
#include <string_view>

#include <arrow/acero/options.h>
#include <arrow/array.h>
#include <arrow/array/array_binary.h>
Expand All @@ -8,41 +11,53 @@
#include <nlohmann/json.hpp>

#include "evobench/evobench.hpp"
#include "silo/common/panic.h"
#include "silo/common/size_constants.h"

namespace silo::query_engine::exec_node {

namespace {

template <size_t BATCH_SIZE>
void writeChunked(std::ostream& output, std::string_view content) {
const size_t chunk_size = 8192;
for (size_t pos = 0; pos < content.size(); pos += chunk_size) {
size_t remaining_size = content.size() - pos;
size_t write_size = std::min(chunk_size, remaining_size);
output.write(content.data() + pos, static_cast<std::streamsize>(write_size));
output.flush(); // Flush after each small chunk
}
}
Comment thread
pflanze marked this conversation as resolved.

template <size_t BatchSize>
struct BatchedStringStream {
std::array<std::stringstream, BATCH_SIZE> streams;
std::array<std::stringstream, BatchSize> streams;

void operator<<(std::string_view bytes) {
for (size_t i = 0; i < BATCH_SIZE; ++i) {
for (size_t i = 0; i < BatchSize; ++i) {
streams[i] << bytes;
}
}

void operator>>(std::ostream& output) {
for (size_t i = 0; i < BATCH_SIZE; ++i) {
output << streams[i].rdbuf();
for (size_t i = 0; i < BatchSize; ++i) {
std::string content = std::move(streams[i]).str();
writeChunked(output, content);
}
}
};

template <size_t BATCH_SIZE>
template <size_t BatchSize>
class ArrayToJsonTypeVisitor : public arrow::ArrayVisitor {
BatchedStringStream<BATCH_SIZE>& output_stream;
BatchedStringStream<BatchSize>& output_stream;
size_t& row_base;

public:
ArrayToJsonTypeVisitor(BatchedStringStream<BATCH_SIZE>& output_stream, size_t& row_base)
ArrayToJsonTypeVisitor(BatchedStringStream<BatchSize>& output_stream, size_t& row_base)
: output_stream(output_stream),
row_base(row_base) {}

arrow::Status Visit(const arrow::Int32Array& array) override {
for (size_t i = 0; i < BATCH_SIZE; ++i) {
for (size_t i = 0; i < BatchSize; ++i) {
if (array.IsNull(row_base + i)) {
output_stream.streams.at(i) << "null";
} else {
Expand All @@ -53,7 +68,7 @@ class ArrayToJsonTypeVisitor : public arrow::ArrayVisitor {
}

arrow::Status Visit(const arrow::Int64Array& array) override {
for (size_t i = 0; i < BATCH_SIZE; ++i) {
for (size_t i = 0; i < BatchSize; ++i) {
if (array.IsNull(row_base + i)) {
output_stream.streams.at(i) << "null";
} else {
Expand All @@ -64,31 +79,31 @@ class ArrayToJsonTypeVisitor : public arrow::ArrayVisitor {
}

arrow::Status Visit(const arrow::DoubleArray& array) override {
for (size_t i = 0; i < BATCH_SIZE; ++i) {
for (size_t i = 0; i < BatchSize; ++i) {
if (array.IsNull(row_base + i)) {
output_stream.streams.at(i) << "null";
} else {
nlohmann::json j = array.GetView(row_base + i);
output_stream.streams.at(i) << j;
nlohmann::json json = array.GetView(row_base + i);
output_stream.streams.at(i) << json;
}
}
return arrow::Status::OK();
}

arrow::Status Visit(const arrow::FloatArray& array) override {
for (size_t i = 0; i < BATCH_SIZE; ++i) {
for (size_t i = 0; i < BatchSize; ++i) {
if (array.IsNull(row_base + i)) {
output_stream.streams.at(i) << "null";
} else {
nlohmann::json j = array.GetView(row_base + i);
output_stream.streams.at(i) << j;
nlohmann::json json = array.GetView(row_base + i);
output_stream.streams.at(i) << json;
}
}
return arrow::Status::OK();
}

arrow::Status Visit(const arrow::StringArray& array) override {
for (size_t i = 0; i < BATCH_SIZE; ++i) {
for (size_t i = 0; i < BatchSize; ++i) {
if (array.IsNull(row_base + i)) {
output_stream.streams.at(i) << "null";
} else {
Expand All @@ -101,7 +116,7 @@ class ArrayToJsonTypeVisitor : public arrow::ArrayVisitor {
}

arrow::Status Visit(const arrow::BooleanArray& array) override {
for (size_t i = 0; i < BATCH_SIZE; ++i) {
for (size_t i = 0; i < BatchSize; ++i) {
if (array.IsNull(row_base + i)) {
output_stream.streams.at(i) << "null";
} else {
Expand All @@ -112,18 +127,18 @@ class ArrayToJsonTypeVisitor : public arrow::ArrayVisitor {
}
};

template <size_t BATCH_SIZE>
template <size_t BatchSize>
void sendJsonLinesInBatches(
size_t& row_idx_base,
size_t row_count,
const std::vector<std::string>& prepared_column_strings_for_json_attributes,
const std::vector<std::shared_ptr<arrow::Array>>& column_arrays,
std::ostream& output_stream
) {
BatchedStringStream<BATCH_SIZE> ndjson_line_streams;
ArrayToJsonTypeVisitor<BATCH_SIZE> my_visitor(ndjson_line_streams, row_idx_base);
BatchedStringStream<BatchSize> ndjson_line_streams;
ArrayToJsonTypeVisitor<BatchSize> my_visitor(ndjson_line_streams, row_idx_base);
size_t column_count = column_arrays.size();
for (; row_idx_base + BATCH_SIZE <= row_count; row_idx_base += BATCH_SIZE) {
for (; row_idx_base + BatchSize <= row_count; row_idx_base += BatchSize) {
ndjson_line_streams << "{";
for (size_t column_idx = 0; column_idx < column_count; column_idx++) {
const auto& column_array = column_arrays.at(column_idx);
Expand All @@ -137,7 +152,7 @@ void sendJsonLinesInBatches(
ndjson_line_streams >> output_stream;
}
}
if constexpr (BATCH_SIZE > 1) {
if constexpr (BatchSize > 1) {
// Send remaining lines
sendJsonLinesInBatches<1>(
row_idx_base,
Expand All @@ -152,7 +167,7 @@ void sendJsonLinesInBatches(
} // namespace

arrow::Status writeBatchAsNdjson(
arrow::compute::ExecBatch batch,
const arrow::compute::ExecBatch& batch,
const std::shared_ptr<arrow::Schema>& schema,
std::ostream* output_stream
) {
Expand All @@ -168,8 +183,9 @@ arrow::Status writeBatchAsNdjson(
for (const auto& column_name : schema->fields()) {
nlohmann::json column_name_json = column_name->name();
std::string json_formatted_column_name;
if (!first_column)
if (!first_column) {
json_formatted_column_name += ",";
}
first_column = false;
json_formatted_column_name += column_name_json.dump();
json_formatted_column_name += ":";
Expand Down
4 changes: 1 addition & 3 deletions src/silo/query_engine/exec_node/ndjson_sink.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,12 +6,10 @@
#include <arrow/util/async_generator_fwd.h>
#include <spdlog/spdlog.h>

#include "silo/common/panic.h"

namespace silo::query_engine::exec_node {

arrow::Status writeBatchAsNdjson(
arrow::compute::ExecBatch batch,
const arrow::compute::ExecBatch& batch,
const std::shared_ptr<arrow::Schema>& schema,
std::ostream* output_stream
);
Expand Down