Alena0704 commented on code in PR #1719:
URL: https://github.com/apache/cloudberry/pull/1719#discussion_r3206577638
##########
src/backend/gporca/libgpopt/src/base/CUtils.cpp:
##########
@@ -978,6 +978,180 @@ CUtils::FHasCTEAnchor(CExpression *pexpr)
return false;
}
+// return CTEConsumers' and a set of CTEProducers' CTE ids in the given subtree
+void
+CUtils::CollectConsumersAndProducers(CMemoryPool *mp, CExpression *pexpr,
+
ULongPtrArray *cteConsumers,
+
UlongCteIdHashSet *cteProducerSet)
+{
+ COperator *pop = pexpr->Pop();
+
+ if (COperator::EopPhysicalCTEConsumer == pop->Eopid())
+ {
+ cteConsumers->Append(GPOS_NEW(mp) ULONG(
+ CPhysicalCTEConsumer::PopConvert(pop)->UlCTEId()));
+ }
+ else if (COperator::EopPhysicalCTEProducer == pop->Eopid())
+ {
+ cteProducerSet->Insert(GPOS_NEW(mp) ULONG(
+ CPhysicalCTEProducer::PopConvert(pop)->UlCTEId()));
+ }
+
+ for (ULONG ul = 0; ul < pexpr->Arity(); ul++)
+ {
+ CExpression *pexprChild = (*pexpr)[ul];
+
+ if (!pexprChild->Pop()->FScalar())
+ {
+ CollectConsumersAndProducers(mp, pexprChild,
cteConsumers,
+
cteProducerSet);
+ }
+ }
+}
+
+BOOL
+CUtils::hasUnpairedCTEConsumer(CMemoryPool *mp, CExpression *pexpr)
+{
+ BOOL hasUnpairedConsumer = false;
+
+ ULongPtrArray *cteConsumers = GPOS_NEW(mp) ULongPtrArray(mp);
+ UlongCteIdHashSet *cteProducerSet = GPOS_NEW(mp) UlongCteIdHashSet(mp);
+
+ CollectConsumersAndProducers(mp, pexpr, cteConsumers, cteProducerSet);
+
+ // check if every consumer's producer is in ProducerSet
+ for (ULONG ul = 0; ul < cteConsumers->Size(); ul++)
+ {
+ if (!cteProducerSet->Contains((*cteConsumers)[ul]))
+ {
+ hasUnpairedConsumer = true;
+ break;
+ }
+ }
+ cteConsumers->Release();
+ cteProducerSet->Release();
+
+ return hasUnpairedConsumer;
+}
+
+// True if the distribution is replicated-like.
+static BOOL
+FReplicatedLikeDistribution(CDistributionSpec::EDistributionType edt)
+{
+ return (CDistributionSpec::EdtStrictReplicated == edt ||
+ CDistributionSpec::EdtTaintedReplicated == edt ||
+ CDistributionSpec::EdtUniversal == edt);
+}
+
+struct SCTEInfo
+{
+ ULONG cteId;
+ ULONG sliceId;
+
+ SCTEInfo(ULONG cte_id, ULONG slice_id) : cteId(cte_id),
sliceId(slice_id)
+ {
+ }
+};
+
+typedef CDynamicPtrArray<SCTEInfo, CleanupDelete<SCTEInfo> > CTEInfoArray;
+
+// Walk the physical tree, recording the slice id of every replicated
+// CTE Producer and every CTE Consumer. Slices are delimited by Motion
+// nodes: each non-scalar child of a Motion lives in a fresh slice --
+// same motId-stack idea as in apply_shareinput_xslice.
+static void
+CollectCTESlices(CMemoryPool *mp, CExpression *pexpr, ULONG curSlice,
+ ULONG *pNextSlice, CTEInfoArray *prodInfos,
+ CTEInfoArray *consInfos)
+{
+ COperator *pop = pexpr->Pop();
+
+ if (COperator::EopPhysicalCTEProducer == pop->Eopid())
+ {
+ // Producer's distribution comes from its only child -- inspect
+ // it there. Skip non-replicated Producers; they cannot trigger
+ // the cross-slice issue we are checking for.
+ GPOS_ASSERT(1 == pexpr->Arity());
+ CExpression *pexprChild = (*pexpr)[0];
+ CDrvdPropPlan *pdpplan =
+ CDrvdPropPlan::Pdpplan(pexprChild->PdpDerive());
+
+ if (FReplicatedLikeDistribution(pdpplan->Pds()->Edt()))
+ {
+ prodInfos->Append(GPOS_NEW(mp) SCTEInfo(
+
CPhysicalCTEProducer::PopConvert(pop)->UlCTEId(), curSlice));
+ }
+ }
+ else if (COperator::EopPhysicalCTEConsumer == pop->Eopid())
+ {
+ // Consumer is a leaf -- record (cteId, curSlice) and let the
+ // caller decide later, once the whole tree has been walked.
+ consInfos->Append(GPOS_NEW(mp) SCTEInfo(
+ CPhysicalCTEConsumer::PopConvert(pop)->UlCTEId(),
curSlice));
+ }
+
+ BOOL isMotion = CUtils::FPhysicalMotion(pop);
+
+ for (ULONG ul = 0; ul < pexpr->Arity(); ul++)
+ {
+ CExpression *pexprChild = (*pexpr)[ul];
+
+ if (pexprChild->Pop()->FScalar())
+ {
+ continue;
+ }
+
+ ULONG childSlice = curSlice;
+ if (isMotion)
+ {
+ (*pNextSlice)++;
+ childSlice = *pNextSlice;
+ }
+
+ CollectCTESlices(mp, pexprChild, childSlice, pNextSlice,
prodInfos,
+ consInfos);
+ }
+}
+
+BOOL
+CUtils::FHasCrossSliceReplicatedCTEConsumer(CMemoryPool *mp, CExpression
*pexpr)
+{
+ if (NULL == pexpr)
+ {
+ return false;
+ }
+
+ CTEInfoArray *prodInfos = GPOS_NEW(mp) CTEInfoArray(mp);
+ CTEInfoArray *consInfos = GPOS_NEW(mp) CTEInfoArray(mp);
+ ULONG nextSlice = 0;
+
+ CollectCTESlices(mp, pexpr, 0 /*curSlice*/, &nextSlice, prodInfos,
+ consInfos);
+
+ BOOL cross = false;
+
+ for (ULONG ic = 0; ic < consInfos->Size(); ic++)
+ {
+ SCTEInfo *cons = (*consInfos)[ic];
+
+ for (ULONG ip = 0; ip < prodInfos->Size(); ip++)
+ {
+ SCTEInfo *prod = (*prodInfos)[ip];
+ if (prod->cteId == cons->cteId && prod->sliceId !=
cons->sliceId)
+ {
+ cross = true;
+ goto lExit;
Review Comment:
Agree. As I understood it might be dangerous since we can jump over object
construction or skip destructors. I replaced it with the a small function that
uses a plain return true for the early exit.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
