github-actions[bot] commented on code in PR #16166:
URL: https://github.com/apache/doris/pull/16166#discussion_r1090130844
##########
be/src/vec/exec/join/process_hash_table_probe_impl.h:
##########
@@ -208,123 +207,179 @@ Status
ProcessHashTableProbe<JoinOpType>::do_process(HashTableType& hash_table_c
bool all_match_one = true;
int last_probe_index = probe_index;
+ size_t probe_size = 0;
+ auto& probe_row_match_iter = hash_table_ctx.probe_row_match_iter;
{
SCOPED_TIMER(_search_hashtable_timer);
- while (probe_index < probe_rows) {
- if constexpr (ignore_null && need_null_map_for_probe) {
- if ((*null_map)[probe_index]) {
- if constexpr (probe_all) {
- _items_counts[probe_index++] = (uint32_t)1;
- // only full outer / left outer need insert the data
of right table
- if (LIKELY(current_offset < _build_block_rows.size()))
{
- _build_block_offsets[current_offset] = -1;
- _build_block_rows[current_offset] = -1;
- } else {
- _build_block_offsets.emplace_back(-1);
- _build_block_rows.emplace_back(-1);
- }
- ++current_offset;
+ if constexpr (!is_right_semi_anti_join) {
+ // handle ramaining matched rows from last probe row
+ if (probe_row_match_iter.ok()) {
+ for (; probe_row_match_iter.ok() && current_offset <
_batch_size;
+ ++probe_row_match_iter) {
+ if (LIKELY(current_offset < _build_block_rows.size())) {
+ _build_block_offsets[current_offset] =
probe_row_match_iter->block_offset;
+ _build_block_rows[current_offset] =
probe_row_match_iter->row_num;
} else {
- _items_counts[probe_index++] = (uint32_t)0;
+
_build_block_offsets.emplace_back(probe_row_match_iter->block_offset);
+
_build_block_rows.emplace_back(probe_row_match_iter->row_num);
}
- all_match_one = false;
- continue;
- }
- }
- int last_offset = current_offset;
- auto find_result =
- !need_null_map_for_probe
- ? key_getter.find_key(hash_table_ctx.hash_table,
probe_index, *_arena)
- : (*null_map)[probe_index]
- ?
decltype(key_getter.find_key(hash_table_ctx.hash_table, probe_index,
- *_arena)) {nullptr,
false}
- : key_getter.find_key(hash_table_ctx.hash_table,
probe_index, *_arena);
- if (probe_index + PREFETCH_STEP < probe_rows)
- key_getter.template prefetch<true>(hash_table_ctx.hash_table,
- probe_index +
PREFETCH_STEP, *_arena);
-
- if constexpr (JoinOpType == TJoinOp::LEFT_ANTI_JOIN ||
- JoinOpType == TJoinOp::NULL_AWARE_LEFT_ANTI_JOIN) {
- if (is_mark_join) {
++current_offset;
-
assert_cast<doris::vectorized::ColumnVector<UInt8>&>(*mcol[mcol.size() - 1])
- .get_data()
- .template push_back(!find_result.is_found());
- } else {
- if (!find_result.is_found()) {
- ++current_offset;
- }
}
- } else if constexpr (JoinOpType == TJoinOp::LEFT_SEMI_JOIN) {
- if (is_mark_join) {
- ++current_offset;
-
assert_cast<doris::vectorized::ColumnVector<UInt8>&>(*mcol[mcol.size() - 1])
- .get_data()
- .template push_back(find_result.is_found());
- } else {
- if (find_result.is_found()) {
- ++current_offset;
- }
+ all_match_one &= (current_offset == 1);
+ _items_counts[probe_index] = current_offset;
+ if (!probe_row_match_iter.ok()) {
+ ++probe_index;
}
- } else {
- DCHECK(!is_mark_join);
- if (find_result.is_found()) {
- auto& mapped = find_result.get_mapped();
- // TODO: Iterators are currently considered to be a heavy
operation and have a certain impact on performance.
- // We should rethink whether to use this iterator mode in
the future. Now just opt the one row case
- if (mapped.get_row_count() == 1) {
- if constexpr (std::is_same_v<Mapped,
RowRefListWithFlag>) {
- mapped.visited = true;
- }
+ probe_size = 1;
+ }
+ }
- if constexpr (!is_right_semi_anti_join) {
+ if (current_offset < _batch_size) {
+ while (probe_index < probe_rows) {
+ if constexpr (ignore_null && need_null_map_for_probe) {
+ if ((*null_map)[probe_index]) {
+ if constexpr (probe_all) {
+ _items_counts[probe_index++] = (uint32_t)1;
+ // only full outer / left outer need insert the
data of right table
if (LIKELY(current_offset <
_build_block_rows.size())) {
- _build_block_offsets[current_offset] =
mapped.block_offset;
- _build_block_rows[current_offset] =
mapped.row_num;
+ _build_block_offsets[current_offset] = -1;
+ _build_block_rows[current_offset] = -1;
} else {
-
_build_block_offsets.emplace_back(mapped.block_offset);
- _build_block_rows.emplace_back(mapped.row_num);
+ _build_block_offsets.emplace_back(-1);
+ _build_block_rows.emplace_back(-1);
}
++current_offset;
+ } else {
+ _items_counts[probe_index++] = (uint32_t)0;
}
+ all_match_one = false;
+ if constexpr (probe_all) {
+ if (current_offset >= _batch_size) {
+ break;
+ }
+ }
+ continue;
+ }
+ }
+ int last_offset = current_offset;
+ auto find_result = !need_null_map_for_probe
+ ?
key_getter.find_key(hash_table_ctx.hash_table,
+ probe_index,
*_arena)
+ : (*null_map)[probe_index]
+ ?
decltype(key_getter.find_key(hash_table_ctx.hash_table,
+
probe_index,
+
*_arena)) {nullptr, false}
+ :
key_getter.find_key(hash_table_ctx.hash_table,
+ probe_index,
*_arena);
+ if (probe_index + PREFETCH_STEP < probe_rows)
Review Comment:
warning: statement should be inside braces
[readability-braces-around-statements]
```suggestion
if (probe_index + PREFETCH_STEP < probe_rows) {
```
be/src/vec/exec/join/process_hash_table_probe_impl.h:275:
```diff
- probe_index +
PREFETCH_STEP, *_arena);
+ probe_index +
PREFETCH_STEP, *_arena);
+ }
```
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
