xxq250
/
homework-jianmu
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Merge pull request #21597 from taosdata/enh/TD-24586 

enh: optimize filter performance
This commit is contained in:
dapan1121 2023-06-08 09:05:56 +08:00 committed by GitHub
parent 240a78253d 47c891fbc5
commit 6c74282946
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 107 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
include/common/tcommon.h
View File

@ -231,6 +231,7 @@ typedef struct SColumnInfoData {
};
SColumnInfo info; // column info
bool hasNull; // if current column data has null value.
bool reassigned; // if current column data is reassigned.
} SColumnInfoData;
typedef struct SQueryTableDataCond {

1
include/common/tdatablock.h
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);

97
source/common/src/tdatablock.c
View File

@ -23,6 +23,20 @@
int32_t colDataGetLength(const SColumnInfoData* pColumnInfoData, int32_t numOfRows) {
if (IS_VAR_DATA_TYPE(pColumnInfoData->info.type)) {
if (pColumnInfoData->reassigned) {
int32_t totalSize = 0;
for (int32_t row = 0; row < numOfRows; ++row) {
char* pColData = pColumnInfoData->pData + pColumnInfoData->varmeta.offset[row];
int32_t colSize = 0;
if (pColumnInfoData->info.type == TSDB_DATA_TYPE_JSON) {
colSize = getJsonValueLen(pColData);
} else {
colSize = varDataTLen(pColData);
}
totalSize += colSize;
}
return totalSize;
}
return pColumnInfoData->varmeta.length;
} else {
if (pColumnInfoData->info.type == TSDB_DATA_TYPE_NULL) {
@ -126,6 +140,29 @@ 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;
pColumnInfoData->varmeta.offset[dstRowIdx] = pColumnInfoData->varmeta.offset[srcRowIdx];
pColumnInfoData->reassigned = true;
} 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;
@ -580,8 +617,22 @@ int32_t blockDataToBuf(char* buf, const SSDataBlock* pBlock) {
*(int32_t*)pStart = dataSize;
pStart += sizeof(int32_t);
memcpy(pStart, pCol->pData, dataSize);
pStart += dataSize;
if (pCol->reassigned && IS_VAR_DATA_TYPE(pCol->info.type)) {
for (int32_t row = 0; row < numOfRows; ++row) {
char* pColData = pCol->pData + pCol->varmeta.offset[row];
int32_t colSize = 0;
if (pCol->info.type == TSDB_DATA_TYPE_JSON) {
colSize = getJsonValueLen(pColData);
} else {
colSize = varDataTLen(pColData);
}
memcpy(pStart, pColData, colSize);
pStart += colSize;
}
} else {
memcpy(pStart, pCol->pData, dataSize);
pStart += dataSize;
}
}
return 0;
@ -1741,7 +1792,20 @@ int32_t tEncodeDataBlock(void** buf, const SSDataBlock* pBlock) {
int32_t len = colDataGetLength(pColData, rows);
tlen += taosEncodeFixedI32(buf, len);
tlen += taosEncodeBinary(buf, pColData->pData, len);
if (pColData->reassigned && IS_VAR_DATA_TYPE(pColData->info.type)) {
for (int32_t row = 0; row < rows; ++row) {
char* pData = pColData->pData + pColData->varmeta.offset[row];
int32_t colSize = 0;
if (pColData->info.type == TSDB_DATA_TYPE_JSON) {
colSize = getJsonValueLen(pData);
} else {
colSize = varDataTLen(pData);
}
tlen += taosEncodeBinary(buf, pData, colSize);
}
} else {
tlen += taosEncodeBinary(buf, pColData->pData, len);
}
}
return tlen;
}
@ -2502,12 +2566,29 @@ int32_t blockEncode(const SSDataBlock* pBlock, char* data, int32_t numOfCols) {
data += metaSize;
dataLen += metaSize;
colSizes[col] = colDataGetLength(pColRes, numOfRows);
dataLen += colSizes[col];
if (pColRes->pData != NULL) {
memmove(data, pColRes->pData, colSizes[col]);
if (pColRes->reassigned && IS_VAR_DATA_TYPE(pColRes->info.type)) {
colSizes[col] = 0;
for (int32_t row = 0; row < numOfRows; ++row) {
char* pColData = pColRes->pData + pColRes->varmeta.offset[row];
int32_t colSize = 0;
if (pColRes->info.type == TSDB_DATA_TYPE_JSON) {
colSize = getJsonValueLen(pColData);
} else {
colSize = varDataTLen(pColData);
}
colSizes[col] += colSize;
dataLen += colSize;
memmove(data, pColData, colSize);
data += colSize;
}
} else {
colSizes[col] = colDataGetLength(pColRes, numOfRows);
dataLen += colSizes[col];
if (pColRes->pData != NULL) {
memmove(data, pColRes->pData, colSizes[col]);
}
data += colSizes[col];
}
data += colSizes[col];
colSizes[col] = htonl(colSizes[col]);
// uError("blockEncode col bytes:%d, type:%d, size:%d, htonl size:%d", pColRes->info.bytes, pColRes->info.type, htonl(colSizes[col]), colSizes[col]);

13
source/libs/executor/src/executorInt.c
View File

@ -562,7 +562,6 @@ void extractQualifiedTupleByFilterResult(SSDataBlock* pBlock, const SColumnInfoD
int32_t numOfRows = 0;
if (IS_VAR_DATA_TYPE(pDst->info.type)) {
int32_t j = 0;
pDst->varmeta.length = 0;
while (j < totalRows) {
if (pIndicator[j] == 0) {
@ -573,18 +572,8 @@ 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;

16
source/libs/function/src/tudf.c
View File

@ -791,7 +791,21 @@ int32_t convertDataBlockToUdfDataBlock(SSDataBlock *block, SUdfDataBlock *udfBlo
memcpy(udfCol->colData.varLenCol.varOffsets, col->varmeta.offset, udfCol->colData.varLenCol.varOffsetsLen);
udfCol->colData.varLenCol.payloadLen = colDataGetLength(col, udfBlock->numOfRows);
udfCol->colData.varLenCol.payload = taosMemoryMalloc(udfCol->colData.varLenCol.payloadLen);
memcpy(udfCol->colData.varLenCol.payload, col->pData, udfCol->colData.varLenCol.payloadLen);
if (col->reassigned) {
for (int32_t row = 0; row < udfCol->colData.numOfRows; ++row) {
char* pColData = col->pData + col->varmeta.offset[row];
int32_t colSize = 0;
if (col->info.type == TSDB_DATA_TYPE_JSON) {
colSize = getJsonValueLen(pColData);
} else {
colSize = varDataTLen(pColData);
}
memcpy(udfCol->colData.varLenCol.payload, pColData, colSize);
udfCol->colData.varLenCol.payload += colSize;
}
} else {
memcpy(udfCol->colData.varLenCol.payload, col->pData, udfCol->colData.varLenCol.payloadLen);
}
} else {
udfCol->colData.fixLenCol.nullBitmapLen = BitmapLen(udfCol->colData.numOfRows);
int32_t bitmapLen = udfCol->colData.fixLenCol.nullBitmapLen;