add hll partial/merge functions

This commit is contained in:
Ganlin Zhao 2022-06-09 13:31:33 +08:00
parent d1a0ab2445
commit 8e65f1e426
3 changed files with 45 additions and 5 deletions

View File

@ -126,7 +126,9 @@ int32_t getHistogramInfoSize();
bool getHLLFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv); bool getHLLFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv);
int32_t hllFunction(SqlFunctionCtx* pCtx); int32_t hllFunction(SqlFunctionCtx* pCtx);
int32_t hllFunctionMerge(SqlFunctionCtx* pCtx);
int32_t hllFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock); int32_t hllFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
int32_t hllPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock);
int32_t getHLLInfoSize(); int32_t getHLLInfoSize();
bool getStateFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv); bool getStateFuncEnv(struct SFunctionNode* pFunc, SFuncExecEnv* pEnv);

View File

@ -1509,20 +1509,20 @@ const SBuiltinFuncDefinition funcMgtBuiltins[] = {
.name = "_hyperloglog_partial", .name = "_hyperloglog_partial",
.type = FUNCTION_TYPE_HYPERLOGLOG_PARTIAL, .type = FUNCTION_TYPE_HYPERLOGLOG_PARTIAL,
.classification = FUNC_MGT_AGG_FUNC, .classification = FUNC_MGT_AGG_FUNC,
.translateFunc = translateHLL, .translateFunc = translateHLLPartial,
.getEnvFunc = getHLLFuncEnv, .getEnvFunc = getHLLFuncEnv,
.initFunc = functionSetup, .initFunc = functionSetup,
.processFunc = hllFunction, .processFunc = hllFunction,
.finalizeFunc = hllFinalize .finalizeFunc = hllPartialFinalize
}, },
{ {
.name = "_hyperloglog_merge", .name = "_hyperloglog_merge",
.type = FUNCTION_TYPE_HYPERLOGLOG_MERGE, .type = FUNCTION_TYPE_HYPERLOGLOG_MERGE,
.classification = FUNC_MGT_AGG_FUNC, .classification = FUNC_MGT_AGG_FUNC,
.translateFunc = translateHLL, .translateFunc = translateHLLMerge,
.getEnvFunc = getHLLFuncEnv, .getEnvFunc = getHLLFuncEnv,
.initFunc = functionSetup, .initFunc = functionSetup,
.processFunc = hllFunction, .processFunc = hllFunctionMerge,
.finalizeFunc = hllFinalize .finalizeFunc = hllFinalize
}, },
{ {

View File

@ -3411,7 +3411,6 @@ int32_t histogramFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
} }
int32_t histogramPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) { int32_t histogramPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
SResultRowEntryInfo* pResInfo = GET_RES_INFO(pCtx);
SHistoFuncInfo* pInfo = GET_ROWCELL_INTERBUF(GET_RES_INFO(pCtx)); SHistoFuncInfo* pInfo = GET_ROWCELL_INTERBUF(GET_RES_INFO(pCtx));
int32_t resultBytes = getHistogramInfoSize(); int32_t resultBytes = getHistogramInfoSize();
char *res = taosMemoryCalloc(resultBytes + VARSTR_HEADER_SIZE, sizeof(char)); char *res = taosMemoryCalloc(resultBytes + VARSTR_HEADER_SIZE, sizeof(char));
@ -3557,6 +3556,27 @@ int32_t hllFunction(SqlFunctionCtx *pCtx) {
return TSDB_CODE_SUCCESS; return TSDB_CODE_SUCCESS;
} }
int32_t hllFunctionMerge(SqlFunctionCtx *pCtx) {
SInputColumnInfoData* pInput = &pCtx->input;
SColumnInfoData* pCol = pInput->pData[0];
ASSERT(pCol->info.type == TSDB_DATA_TYPE_BINARY);
SHLLInfo* pInfo = GET_ROWCELL_INTERBUF(GET_RES_INFO(pCtx));
int32_t start = pInput->startRowIndex;
char* data = colDataGetData(pCol, start);
SHLLInfo* pInputInfo = (SHLLInfo *)varDataVal(data);
for (int32_t k = 0; k < HLL_BUCKETS; ++k) {
if (pInfo->buckets[k] < pInputInfo->buckets[k]) {
pInputInfo->buckets[k] = pInfo->buckets[k];
}
}
SET_VAL(GET_RES_INFO(pCtx), 1, 1);
return TSDB_CODE_SUCCESS;
}
int32_t hllFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) { int32_t hllFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
SResultRowEntryInfo *pInfo = GET_RES_INFO(pCtx); SResultRowEntryInfo *pInfo = GET_RES_INFO(pCtx);
@ -3569,6 +3589,24 @@ int32_t hllFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
return functionFinalize(pCtx, pBlock); return functionFinalize(pCtx, pBlock);
} }
int32_t hllPartialFinalize(SqlFunctionCtx* pCtx, SSDataBlock* pBlock) {
SResultRowEntryInfo* pResInfo = GET_RES_INFO(pCtx);
SHLLInfo* pInfo = GET_ROWCELL_INTERBUF(GET_RES_INFO(pCtx));
int32_t resultBytes = getHLLInfoSize();
char *res = taosMemoryCalloc(resultBytes + VARSTR_HEADER_SIZE, sizeof(char));
memcpy(varDataVal(res), pInfo, resultBytes);
varDataSetLen(res, resultBytes);
int32_t slotId = pCtx->pExpr->base.resSchema.slotId;
SColumnInfoData* pCol = taosArrayGet(pBlock->pDataBlock, slotId);
colDataAppend(pCol, pBlock->info.rows, res, false);
taosMemoryFree(res);
return pResInfo->numOfRes;
}
bool getStateFuncEnv(SFunctionNode* UNUSED_PARAM(pFunc), SFuncExecEnv* pEnv) { bool getStateFuncEnv(SFunctionNode* UNUSED_PARAM(pFunc), SFuncExecEnv* pEnv) {
pEnv->calcMemSize = sizeof(SStateInfo); pEnv->calcMemSize = sizeof(SStateInfo);
return true; return true;