Skip to content
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

GH-37655: [C++] Allow joins of large tables in Acero #37709

Closed
wants to merge 8 commits into from
Closed

GH-37655: [C++] Allow joins of large tables in Acero #37709

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8bb1ee9
Solve issue #37655
oliviermeslin Sep 13, 2023
80cd210
Add the new argument to swiss_join_internal.h
oliviermeslin Oct 5, 2023
608778a
A code line should not be more than 90 characters long
oliviermeslin Oct 10, 2023
a851b06
Update cpp/src/arrow/acero/swiss_join.cc
oliviermeslin Oct 12, 2023
9715485
Change the order of the arguments and the name of the new argument
oliviermeslin Oct 12, 2023
0ebf92e
Adapt swiss_join.cc to the new Status
oliviermeslin Oct 12, 2023
04eb7cb
Minor lint fix
raulcd Oct 13, 2023
4dd6d67
Merge branch 'main' into issue-37655
oliviermeslin Oct 16, 2023
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
9 changes: 5 additions & 4 deletions cpp/src/arrow/acero/swiss_join.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -440,7 +440,8 @@ void RowArray::DebugPrintToFile(const char* filename, bool print_sorted) const {
Status RowArrayMerge::PrepareForMerge(RowArray* target,
const std::vector<RowArray*>& sources,
std::vector<int64_t>* first_target_row_id,
MemoryPool* pool) {
MemoryPool* pool,
bool check_key_size) {
ARROW_DCHECK(!sources.empty());

ARROW_DCHECK(sources[0]->is_initialized_);
Expand Down Expand Up @@ -473,7 +474,7 @@ Status RowArrayMerge::PrepareForMerge(RowArray* target,
(*first_target_row_id)[sources.size()] = num_rows;
}

if (num_bytes > std::numeric_limits<uint32_t>::max()) {
if (check_key_size && num_bytes > std::numeric_limits<uint32_t>::max()) {
return Status::Invalid(
"There are more than 2^32 bytes of key data. Acero cannot "
"process a join of this magnitude");
Expand Down Expand Up @@ -1331,7 +1332,7 @@ Status SwissTableForJoinBuild::PreparePrtnMerge() {
partition_keys[i] = prtn_states_[i].keys.keys();
}
RETURN_NOT_OK(RowArrayMerge::PrepareForMerge(target_->map_.keys(), partition_keys,
&partition_keys_first_row_id_, pool_));
&partition_keys_first_row_id_, pool_, true));
oliviermeslin marked this conversation as resolved.
Show resolved Hide resolved

// 2. SwissTable:
//
Expand All @@ -1354,7 +1355,7 @@ Status SwissTableForJoinBuild::PreparePrtnMerge() {
}
RETURN_NOT_OK(RowArrayMerge::PrepareForMerge(&target_->payloads_, partition_payloads,
&partition_payloads_first_row_id_,
pool_));
pool_, false));
}

// Check if we have duplicate keys
Expand Down
2 changes: 1 addition & 1 deletion cpp/src/arrow/acero/swiss_join_internal.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,7 +161,7 @@ class RowArrayMerge {
//
static Status PrepareForMerge(RowArray* target, const std::vector<RowArray*>& sources,
std::vector<int64_t>* first_target_row_id,
MemoryPool* pool);
MemoryPool* pool, bool check_key_size);
oliviermeslin marked this conversation as resolved.
Show resolved Hide resolved

// Copy rows from source array to target array.
// Both arrays must have the same row metadata.
Expand Down
Loading