database/doris
2
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

[feature] Support pre-aggregation for quantile type (#8234)

Browse Source 
Add a new column-type to speed up the approximation of quantiles.
1. The  new column-type is named `quantile_state` with fixed aggregation function `quantile_union`, which stores the intermediate results of pre-aggregated approximation calculations for quantiles.
2. support pre-aggregation of new column-type and quantile_state related functions.
This commit is contained in:
spaces-x
2022-03-24 09:11:34 +08:00
committed by GitHub
parent 36c85d2f06
commit bea9a7ba4f
67 changed files with 1498 additions and 153 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
be/src/olap/column_vector.cpp
View File

@ -31,8 +31,8 @@ Status ColumnVectorBatch::resize(size_t new_cap) {
return Status::OK();
}
Status ColumnVectorBatch::create(size_t init_capacity, bool is_nullable, std::shared_ptr<const TypeInfo> type_info,
Field* field,
Status ColumnVectorBatch::create(size_t init_capacity, bool is_nullable,
std::shared_ptr<const TypeInfo> type_info, Field* field,
std::unique_ptr<ColumnVectorBatch>* column_vector_batch) {
if (is_scalar_type(type_info->type())) {
std::unique_ptr<ColumnVectorBatch> local;
@ -117,6 +117,11 @@ Status ColumnVectorBatch::create(size_t init_capacity, bool is_nullable, std::sh
local.reset(new ScalarColumnVectorBatch<CppTypeTraits<OLAP_FIELD_TYPE_OBJECT>::CppType>(
type_info, is_nullable));
break;
case OLAP_FIELD_TYPE_QUANTILE_STATE:
local.reset(new ScalarColumnVectorBatch<
CppTypeTraits<OLAP_FIELD_TYPE_QUANTILE_STATE>::CppType>(type_info,
is_nullable));
break;
default:
return Status::NotSupported("unsupported type for ColumnVectorBatch: " +
std::to_string(type_info->type()));
@ -139,8 +144,7 @@ Status ColumnVectorBatch::create(size_t init_capacity, bool is_nullable, std::sh
array_type_info->item_type_info(), field->get_sub_field(0), &elements));
std::unique_ptr<ColumnVectorBatch> offsets;
auto offsets_type_info =
get_scalar_type_info(FieldType::OLAP_FIELD_TYPE_UNSIGNED_INT);
auto offsets_type_info = get_scalar_type_info(FieldType::OLAP_FIELD_TYPE_UNSIGNED_INT);
RETURN_IF_ERROR(ColumnVectorBatch::create(init_capacity + 1, false, offsets_type_info,
nullptr, &offsets));
@ -160,8 +164,8 @@ Status ColumnVectorBatch::create(size_t init_capacity, bool is_nullable, std::sh
}
template <class ScalarType>
ScalarColumnVectorBatch<ScalarType>::ScalarColumnVectorBatch(std::shared_ptr<const TypeInfo> type_info,
bool is_nullable)
ScalarColumnVectorBatch<ScalarType>::ScalarColumnVectorBatch(
std::shared_ptr<const TypeInfo> type_info, bool is_nullable)
: ColumnVectorBatch(type_info, is_nullable), _data(0) {}
template <class ScalarType>
@ -176,7 +180,8 @@ Status ScalarColumnVectorBatch<ScalarType>::resize(size_t new_cap) {
return Status::OK();
}
ArrayColumnVectorBatch::ArrayColumnVectorBatch(std::shared_ptr<const TypeInfo> type_info, bool is_nullable,
ArrayColumnVectorBatch::ArrayColumnVectorBatch(std::shared_ptr<const TypeInfo> type_info,
bool is_nullable,
ScalarColumnVectorBatch<uint32_t>* offsets,
ColumnVectorBatch* elements)
: ColumnVectorBatch(type_info, is_nullable), _data(0) {