aboutsummaryrefslogtreecommitdiff
path: root/src/backend/utils/adt/selfuncs.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/backend/utils/adt/selfuncs.c')
-rw-r--r--src/backend/utils/adt/selfuncs.c38
1 files changed, 38 insertions, 0 deletions
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index 2e3fab6a958..e6837869cf6 100644
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -113,6 +113,7 @@
#include "catalog/pg_statistic.h"
#include "catalog/pg_statistic_ext.h"
#include "executor/executor.h"
+#include "executor/nodeAgg.h"
#include "miscadmin.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
@@ -3428,6 +3429,43 @@ estimate_hash_bucket_stats(PlannerInfo *root, Node *hashkey, double nbuckets,
ReleaseVariableStats(vardata);
}
+/*
+ * estimate_hashagg_tablesize
+ * estimate the number of bytes that a hash aggregate hashtable will
+ * require based on the agg_costs, path width and number of groups.
+ *
+ * We return the result as "double" to forestall any possible overflow
+ * problem in the multiplication by dNumGroups.
+ *
+ * XXX this may be over-estimating the size now that hashagg knows to omit
+ * unneeded columns from the hashtable. Also for mixed-mode grouping sets,
+ * grouping columns not in the hashed set are counted here even though hashagg
+ * won't store them. Is this a problem?
+ */
+double
+estimate_hashagg_tablesize(Path *path, const AggClauseCosts *agg_costs,
+ double dNumGroups)
+{
+ Size hashentrysize;
+
+ /* Estimate per-hash-entry space at tuple width... */
+ hashentrysize = MAXALIGN(path->pathtarget->width) +
+ MAXALIGN(SizeofMinimalTupleHeader);
+
+ /* plus space for pass-by-ref transition values... */
+ hashentrysize += agg_costs->transitionSpace;
+ /* plus the per-hash-entry overhead */
+ hashentrysize += hash_agg_entry_size(agg_costs->numAggs);
+
+ /*
+ * Note that this disregards the effect of fill-factor and growth policy
+ * of the hash table. That's probably ok, given that the default
+ * fill-factor is relatively high. It'd be hard to meaningfully factor in
+ * "double-in-size" growth policies here.
+ */
+ return hashentrysize * dNumGroups;
+}
+
/*-------------------------------------------------------------------------
*