enh: improve filter performance

This commit is contained in:
dapan1121 2023-06-05 10:47:15 +08:00
parent ddd3a53e56
commit 532e02fb2a
3 changed files with 25 additions and 11 deletions

View File

@ -178,6 +178,7 @@ int32_t getJsonValueLen(const char* data);
int32_t colDataSetVal(SColumnInfoData* pColumnInfoData, uint32_t rowIndex, const char* pData, bool isNull);
int32_t colDataAppend(SColumnInfoData* pColumnInfoData, uint32_t rowIndex, const char* pData, bool isNull);
int32_t colDataReassignVal(SColumnInfoData* pColumnInfoData, uint32_t dstRowIdx, uint32_t srcRowIdx, const char* pData);
int32_t colDataSetNItems(SColumnInfoData* pColumnInfoData, uint32_t rowIndex, const char* pData, uint32_t numOfRows, bool trimValue);
int32_t colDataMergeCol(SColumnInfoData* pColumnInfoData, int32_t numOfRow1, int32_t* capacity,
const SColumnInfoData* pSource, int32_t numOfRow2);

View File

@ -126,6 +126,29 @@ int32_t colDataSetVal(SColumnInfoData* pColumnInfoData, uint32_t rowIndex, const
return 0;
}
int32_t colDataReassignVal(SColumnInfoData* pColumnInfoData, uint32_t dstRowIdx, uint32_t srcRowIdx, const char* pData) {
int32_t type = pColumnInfoData->info.type;
if (IS_VAR_DATA_TYPE(type)) {
int32_t dataLen = 0;
if (type == TSDB_DATA_TYPE_JSON) {
dataLen = getJsonValueLen(pData);
} else {
dataLen = varDataTLen(pData);
}
SVarColAttr* pAttr = &pColumnInfoData->varmeta;
uint32_t len = pColumnInfoData->varmeta.length;
pColumnInfoData->varmeta.offset[dstRowIdx] = pColumnInfoData->varmeta.offset[srcRowIdx];
} else {
memcpy(pColumnInfoData->pData + pColumnInfoData->info.bytes * dstRowIdx, pData, pColumnInfoData->info.bytes);
colDataClearNull_f(pColumnInfoData->nullbitmap, dstRowIdx);
}
return 0;
}
int32_t colDataReserve(SColumnInfoData* pColumnInfoData, size_t newSize) {
if (!IS_VAR_DATA_TYPE(pColumnInfoData->info.type)) {
return TSDB_CODE_SUCCESS;

View File

@ -573,18 +573,8 @@ void extractQualifiedTupleByFilterResult(SSDataBlock* pBlock, const SColumnInfoD
if (colDataIsNull_var(pDst, j)) {
colDataSetNull_var(pDst, numOfRows);
} else {
// fix address sanitizer error. p1 may point to memory that will change during realloc of colDataSetVal, first copy it to p2
char* p1 = colDataGetVarData(pDst, j);
int32_t len = 0;
if (pDst->info.type == TSDB_DATA_TYPE_JSON) {
len = getJsonValueLen(p1);
} else {
len = varDataTLen(p1);
}
char* p2 = taosMemoryMalloc(len);
memcpy(p2, p1, len);
colDataSetVal(pDst, numOfRows, p2, false);
taosMemoryFree(p2);
colDataReassignVal(pDst, numOfRows, j, p1);
}
numOfRows += 1;
j += 1;