[improvement](vectorized) Make bloom filter predicate run short-circuit logic (#8484)
The current BloomFilter runs vectorization predicate evaluate, but `evaluate_vec` interface is not implemented, so the RuntimeFilter does not play a role after it is pushed down to the storage layer.
And BF predicate computation cannot be automatically vectorized, thus making BloomFilter run short-circuit logic.
For SSB Q2.1，`enable_storage_vectorization = true;`
```
test before impl:
- Total: 36s164ms
- RowsVectorPredFiltered: 0
- RealRuntimeFilterType: bloomfilter
- HasPushDownToEngine: true
test after impl:
- Total: 2s345ms
- RowsVectorPredFiltered: 595.247102M (595247102)
- RealRuntimeFilterType: bloomfilter
- HasPushDownToEngine: true
```
diff --git a/be/src/olap/bloom_filter_predicate.h b/be/src/olap/bloom_filter_predicate.h
index ff3201c..c86e991 100644
--- a/be/src/olap/bloom_filter_predicate.h
+++ b/be/src/olap/bloom_filter_predicate.h
@@ -65,6 +65,8 @@
void evaluate(vectorized::IColumn& column, uint16_t* sel, uint16_t* size) const override;
+ bool is_bloom_filter_predicate() override { return true; }
+
private:
std::shared_ptr<IBloomFilterFuncBase> _filter;
SpecificFilter* _specific_filter; // owned by _filter
diff --git a/be/src/olap/column_predicate.h b/be/src/olap/column_predicate.h
index 6b1aa23..b356a9b 100644
--- a/be/src/olap/column_predicate.h
+++ b/be/src/olap/column_predicate.h
@@ -71,6 +71,8 @@
virtual bool is_in_predicate() { return false; }
+ virtual bool is_bloom_filter_predicate() { return false; }
+
protected:
uint32_t _column_id;
bool _opposite;
diff --git a/be/src/olap/rowset/segment_v2/segment_iterator.cpp b/be/src/olap/rowset/segment_v2/segment_iterator.cpp
index 6a8febb..16b4e74 100644
--- a/be/src/olap/rowset/segment_v2/segment_iterator.cpp
+++ b/be/src/olap/rowset/segment_v2/segment_iterator.cpp
@@ -613,7 +613,9 @@
_is_pred_column[cid] = true;
pred_column_ids.insert(cid);
- if (type == OLAP_FIELD_TYPE_VARCHAR || type == OLAP_FIELD_TYPE_CHAR || type == OLAP_FIELD_TYPE_STRING || predicate->is_in_predicate()) {
+ if (type == OLAP_FIELD_TYPE_VARCHAR || type == OLAP_FIELD_TYPE_CHAR
+ || type == OLAP_FIELD_TYPE_STRING || predicate->is_in_predicate()
+ || predicate->is_bloom_filter_predicate()) {
short_cir_pred_col_id_set.insert(cid);
_short_cir_eval_predicate.push_back(predicate);
_is_all_column_basic_type = false;
