aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorTom Lane <tgl@sss.pgh.pa.us>2015-07-30 12:11:23 -0400
committerTom Lane <tgl@sss.pgh.pa.us>2015-07-30 12:11:23 -0400
commite91a1643ac723477d6ec2d47c8486cd0013660bb (patch)
treea8f0f8db85f184c3357f6d6cafb0df28a2710e0b
parent2e75be6660dbaaf2da09b98c54d47c9fe0ac8cfa (diff)
downloadpostgresql-e91a1643ac723477d6ec2d47c8486cd0013660bb.tar.gz
postgresql-e91a1643ac723477d6ec2d47c8486cd0013660bb.zip
Avoid some zero-divide hazards in the planner.
Although I think on all modern machines floating division by zero results in Infinity not SIGFPE, we still don't want infinities running around in the planner's costing estimates; too much risk of that leading to insane behavior. grouping_planner() failed to consider the possibility that final_rel might be known dummy and hence have zero rowcount. (I wonder if it would be better to set a rows estimate of 1 for dummy relations? But at least in the back branches, changing this convention seems like a bad idea, so I'll leave that for another day.) Make certain that get_variable_numdistinct() produces a nonzero result. The case that can be shown to be broken is with stadistinct < 0.0 and small ntuples; we did not prevent the result from rounding to zero. For good luck I applied clamp_row_est() to all the nonconstant return values. In ExecChooseHashTableSize(), Assert that we compute positive nbuckets and nbatch. I know of no reason to think this isn't the case, but it seems like a good safety check. Per reports from Piotr Stefaniak. Back-patch to all active branches.
-rw-r--r--src/backend/executor/nodeHash.c3
-rw-r--r--src/backend/optimizer/plan/planner.c6
-rw-r--r--src/backend/utils/adt/selfuncs.c10
3 files changed, 12 insertions, 7 deletions
diff --git a/src/backend/executor/nodeHash.c b/src/backend/executor/nodeHash.c
index 906cb46b658..ee9298a157f 100644
--- a/src/backend/executor/nodeHash.c
+++ b/src/backend/executor/nodeHash.c
@@ -542,6 +542,9 @@ ExecChooseHashTableSize(double ntuples, int tupwidth, bool useskew,
nbatch <<= 1;
}
+ Assert(nbuckets > 0);
+ Assert(nbatch > 0);
+
*numbuckets = nbuckets;
*numbatches = nbatch;
}
diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c
index 6ee411eec87..09d4ea12e87 100644
--- a/src/backend/optimizer/plan/planner.c
+++ b/src/backend/optimizer/plan/planner.c
@@ -1536,9 +1536,11 @@ grouping_planner(PlannerInfo *root, double tuple_fraction)
standard_qp_callback, &qp_extra);
/*
- * Extract rowcount and width estimates for use below.
+ * Extract rowcount and width estimates for use below. If final_rel
+ * has been proven dummy, its rows estimate will be zero; clamp it to
+ * one to avoid zero-divide in subsequent calculations.
*/
- path_rows = final_rel->rows;
+ path_rows = clamp_row_est(final_rel->rows);
path_width = final_rel->width;
/*
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index 64b6ae4838f..14b8c2ff545 100644
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -4632,8 +4632,8 @@ examine_simple_variable(PlannerInfo *root, Var *var,
* *isdefault: set to TRUE if the result is a default rather than based on
* anything meaningful.
*
- * NB: be careful to produce an integral result, since callers may compare
- * the result to exact integer counts.
+ * NB: be careful to produce a positive integral result, since callers may
+ * compare the result to exact integer counts, or might divide by it.
*/
double
get_variable_numdistinct(VariableStatData *vardata, bool *isdefault)
@@ -4709,7 +4709,7 @@ get_variable_numdistinct(VariableStatData *vardata, bool *isdefault)
* If we had an absolute estimate, use that.
*/
if (stadistinct > 0.0)
- return stadistinct;
+ return clamp_row_est(stadistinct);
/*
* Otherwise we need to get the relation size; punt if not available.
@@ -4730,7 +4730,7 @@ get_variable_numdistinct(VariableStatData *vardata, bool *isdefault)
* If we had a relative estimate, use that.
*/
if (stadistinct < 0.0)
- return floor((-stadistinct * ntuples) + 0.5);
+ return clamp_row_est(-stadistinct * ntuples);
/*
* With no data, estimate ndistinct = ntuples if the table is small, else
@@ -4738,7 +4738,7 @@ get_variable_numdistinct(VariableStatData *vardata, bool *isdefault)
* that the behavior isn't discontinuous.
*/
if (ntuples < DEFAULT_NUM_DISTINCT)
- return ntuples;
+ return clamp_row_est(ntuples);
*isdefault = true;
return DEFAULT_NUM_DISTINCT;