database/mariadb-columnstore-engine
1
0
Fork 0
mirror of https://github.com/mariadb-corporation/mariadb-columnstore-engine.git synced 2025-08-01 06:46:55 +03:00
Code Activity

MCOL-4580 extent elimination for dictionary-based text/varchar types

Browse Source 
The idea is relatively simple - encode prefixes of collated strings as
integers and use them to compute extents' ranges. Then we can eliminate
extents with strings.

The actual patch does have all the code there but miss one important
step: we do not keep collation index, we keep charset index. Because of
this, some of the tests in the bugfix suite fail and thus main
functionality is turned off.

The reason of this patch to be put into PR at all is that it contains
changes that made CHAR/VARCHAR columns unsigned. This change is needed in
vectorization work.
This commit is contained in:
Serguey Zefirov
2022-02-04 11:55:09 +00:00
parent a66a8dfabf
commit 53b9a2a0f9
54 changed files with 698 additions and 227 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
primitives/linux-port/dictionary.cpp
View File

@ -31,6 +31,7 @@ using namespace std;
#include "messageobj.h"
#include "exceptclasses.h"
#include "dataconvert.h"
#include "string_prefixes.h"
#include <sstream>
using namespace logging;
@ -391,8 +392,13 @@ void PrimitiveProcessor::nextSig(int NVALS, const PrimToken* tokens, p_DataValue
}
void PrimitiveProcessor::p_Dictionary(const DictInput* in, vector<uint8_t>* out, bool skipNulls,
#if defined(XXX_PRIMITIVES_TOKEN_RANGES_XXX)
uint32_t charsetNumber, boost::shared_ptr<DictEqualityFilter> eqFilter,
uint8_t eqOp, uint64_t minMax[2])
#else
uint32_t charsetNumber, boost::shared_ptr<DictEqualityFilter> eqFilter,
uint8_t eqOp)
#endif
{
PrimToken* outToken;
const DictFilterElement* filter = 0;
@ -437,6 +443,14 @@ void PrimitiveProcessor::p_Dictionary(const DictInput* in, vector<uint8_t>* out,
sigptr.len != -1;
nextSig(in->NVALS, in->tokens, &sigptr, in->OutputType, (in->InputFlags ? true : false), skipNulls))
{
#if defined(XXX_PRIMITIVES_TOKEN_RANGES_XXX)
if (minMax)
{
uint64_t v = encodeStringPrefix_check_null(sigptr.data, sigptr.len, charsetNumber);
minMax[1] = minMax[1] < v ? v : minMax[1];
minMax[0] = minMax[0] > v ? v : minMax[0];
}
#endif
// do aggregate processing
if (in->OutputType & OT_AGGREGATE)
{