github-actions[bot] commented on code in PR #36250:
URL: https://github.com/apache/doris/pull/36250#discussion_r1637786545
##########
be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:
##########
@@ -98,6 +98,36 @@ size_t
PartitionedHashJoinSinkLocalState::revocable_mem_size(RuntimeState* state
return mem_size;
}
+size_t PartitionedHashJoinSinkLocalState::estimate_memory(vectorized::Block*
block,
+ bool eos) const {
+ size_t estimated_size = block->allocated_bytes();
+ if (!_shared_state->need_to_spill) {
+ size_t build_side_rows = block != nullptr ? block->rows() : 0;
+ if (_shared_state->inner_shared_state) {
+ auto inner_sink_state_ =
_shared_state->inner_runtime_state->get_sink_local_state();
+ if (inner_sink_state_) {
+ auto inner_sink_state =
+
assert_cast<HashJoinBuildSinkLocalState*>(inner_sink_state_);
+ estimated_size += inner_sink_state->_build_side_mem_used;
+ build_side_rows += inner_sink_state->_build_side_rows;
+ }
+ }
+
+ if (build_side_rows > 0 && eos) {
+ /// here template argument(`StringRef`) is insignificant
+ size_t bucket_count =
JoinHashTable<StringRef>::calc_bucket_size(build_side_rows);
+ // see `JoinHashTable::first`
+ estimated_size += (bucket_count + 1) * sizeof(uint32_t);
+ // `JoinHashTable::next`
+ estimated_size += build_side_rows * sizeof(uint32_t);
+ // `JoinHashTable::visited`
+ estimated_size += build_side_rows * sizeof(uint8_t);
+ }
+ }
+
+ return estimated_size;
+}
+
Status
PartitionedHashJoinSinkLocalState::_revoke_unpartitioned_block(RuntimeState*
state) {
Review Comment:
warning: function '_revoke_unpartitioned_block' has cognitive complexity of
59 (threshold 50) [readability-function-cognitive-complexity]
```cpp
Status
PartitionedHashJoinSinkLocalState::_revoke_unpartitioned_block(RuntimeState*
state) {
^
```
<details>
<summary>Additional context</summary>
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:138:** +1,
including nesting penalty of 0, nesting level increased to 1
```cpp
if (inner_sink_state_) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:143:** +1,
including nesting penalty of 0, nesting level increased to 1
```cpp
if (build_blocks.empty()) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:160:**
nesting level increased to 1
```cpp
auto spill_func = [build_blocks = std::move(build_blocks), state,
num_slots,
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:175:**
nesting level increased to 2
```cpp
[](std::vector<uint32_t>& indices) {
indices.reserve(reserved_size); });
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:177:**
nesting level increased to 2
```cpp
auto flush_rows = [&state,
this](std::unique_ptr<vectorized::MutableBlock>& partition_block,
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:182:** +3,
including nesting penalty of 2, nesting level increased to 3
```cpp
if (!status.ok()) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:192:** +2,
including nesting penalty of 1, nesting level increased to 2
```cpp
for (size_t block_idx = 0; block_idx != build_blocks.size();
++block_idx) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:195:** +3,
including nesting penalty of 2, nesting level increased to 3
```cpp
if (UNLIKELY(build_block.empty())) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:199:** +3,
including nesting penalty of 2, nesting level increased to 3
```cpp
if (build_block.columns() > num_slots) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:209:** +3,
including nesting penalty of 2, nesting level increased to 3
```cpp
for (size_t i = 0; i != build_block.rows(); ++i) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:213:** +3,
including nesting penalty of 2, nesting level increased to 3
```cpp
for (uint32_t partition_idx = 0; partition_idx !=
p._partition_count; ++partition_idx) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:219:** +4,
including nesting penalty of 3, nesting level increased to 4
```cpp
if (UNLIKELY(!partition_block)) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:227:** +4,
including nesting penalty of 3, nesting level increased to 4
```cpp
if (!st.ok()) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:237:** +4,
including nesting penalty of 3, nesting level increased to 4
```cpp
if (partition_block->rows() >= reserved_size ||
is_last_block) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:237:** +1
```cpp
if (partition_block->rows() >= reserved_size ||
is_last_block) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:238:** +5,
including nesting penalty of 4, nesting level increased to 5
```cpp
if (!flush_rows(partition_block, spilling_stream)) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:252:**
nesting level increased to 1
```cpp
auto exception_catch_func = [spill_func, shared_state_holder,
execution_context, state,
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:257:** +2,
including nesting penalty of 1, nesting level increased to 2
```cpp
if (shared_state_sptr) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:260:** +2,
including nesting penalty of 1, nesting level increased to 2
```cpp
if (!shared_state_sptr || !execution_context_lock ||
state->is_cancelled()) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:260:** +1
```cpp
if (!shared_state_sptr || !execution_context_lock ||
state->is_cancelled()) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:265:**
nesting level increased to 2
```cpp
auto status = [&]() {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:266:** +3,
including nesting penalty of 2, nesting level increased to 3
```cpp
RETURN_IF_CATCH_EXCEPTION(spill_func());
^
```
**be/src/common/exception.h:89:** expanded from macro
'RETURN_IF_CATCH_EXCEPTION'
```cpp
do {
\
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:266:** +4,
including nesting penalty of 3, nesting level increased to 4
```cpp
RETURN_IF_CATCH_EXCEPTION(spill_func());
^
```
**be/src/common/exception.h:94:** expanded from macro
'RETURN_IF_CATCH_EXCEPTION'
```cpp
} catch (const doris::Exception& e) {
\
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:266:** +5,
including nesting penalty of 4, nesting level increased to 5
```cpp
RETURN_IF_CATCH_EXCEPTION(spill_func());
^
```
**be/src/common/exception.h:95:** expanded from macro
'RETURN_IF_CATCH_EXCEPTION'
```cpp
if (e.code() == doris::ErrorCode::MEM_ALLOC_FAILED) {
\
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:270:** +2,
including nesting penalty of 1, nesting level increased to 2
```cpp
if (!status.ok()) {
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:280:** +1,
including nesting penalty of 0, nesting level increased to 1
```cpp
DBUG_EXECUTE_IF(
^
```
**be/src/util/debug_points.h:36:** expanded from macro 'DBUG_EXECUTE_IF'
```cpp
if (UNLIKELY(config::enable_debug_points)) {
\
^
```
**be/src/pipeline/exec/partitioned_hash_join_sink_operator.cpp:280:** +2,
including nesting penalty of 1, nesting level increased to 2
```cpp
DBUG_EXECUTE_IF(
^
```
**be/src/util/debug_points.h:38:** expanded from macro 'DBUG_EXECUTE_IF'
```cpp
if (dp) {
\
^
```
</details>
--
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: commits-unsubscr...@doris.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org
