From bc07feecf1b356a03a42003fa9e806802119d08d Mon Sep 17 00:00:00 2001 From: "dgrowley@gmail.com" Date: Thu, 2 Jul 2020 16:06:36 +1200 Subject: [PATCH v4 1/3] Allow estimate_num_groups() to pass back further details about the estimation Here we add a new output parameter to estimate_num_groups() to allow it to set a flags variable with some bits to allow it to pass back additional details to the caller which may be useful for decision making. For now, the only new flag is one which indicates if the estimation fell back on using the hard-coded constants in any part of the estimation. Callers may like to change their behavior if this is set, and this gives them the ability to do so. Callers may pass the flag pointer as NULL if they have no interest in any of the flags. We're not adding any actual usages of these flags here. Some follow-up commits will make use of this feature. --- contrib/postgres_fdw/postgres_fdw.c | 2 +- src/backend/optimizer/path/costsize.c | 3 ++- src/backend/optimizer/path/indxpath.c | 1 + src/backend/optimizer/plan/planner.c | 10 ++++++---- src/backend/optimizer/prep/prepunion.c | 1 + src/backend/optimizer/util/pathnode.c | 1 + src/backend/utils/adt/selfuncs.c | 21 ++++++++++++++++++++- src/include/utils/selfuncs.h | 11 ++++++++++- 8 files changed, 42 insertions(+), 8 deletions(-) diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..70f6fa2493 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -2960,7 +2960,7 @@ estimate_path_cost_size(PlannerInfo *root, numGroups = estimate_num_groups(root, get_sortgrouplist_exprs(root->parse->groupClause, fpinfo->grouped_tlist), - input_rows, NULL); + input_rows, NULL, NULL); /* * Get the retrieved_rows and rows estimates. If there are HAVING diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c index 4ff3c7a2fd..97758dc41c 100644 --- a/src/backend/optimizer/path/costsize.c +++ b/src/backend/optimizer/path/costsize.c @@ -1865,7 +1865,8 @@ cost_incremental_sort(Path *path, /* Estimate number of groups with equal presorted keys. */ if (!unknown_varno) - input_groups = estimate_num_groups(root, presortedExprs, input_tuples, NULL); + input_groups = estimate_num_groups(root, presortedExprs, input_tuples, + NULL, NULL); group_tuples = input_tuples / input_groups; group_input_run_cost = input_run_cost / input_groups; diff --git a/src/backend/optimizer/path/indxpath.c b/src/backend/optimizer/path/indxpath.c index 2a50272da6..ca3132d9b7 100644 --- a/src/backend/optimizer/path/indxpath.c +++ b/src/backend/optimizer/path/indxpath.c @@ -2073,6 +2073,7 @@ adjust_rowcount_for_semijoins(PlannerInfo *root, nunique = estimate_num_groups(root, sjinfo->semi_rhs_exprs, nraw, + NULL, NULL); if (rowcount > nunique) rowcount = nunique; diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c index 4131019fc9..de30550bef 100644 --- a/src/backend/optimizer/plan/planner.c +++ b/src/backend/optimizer/plan/planner.c @@ -3719,7 +3719,8 @@ get_number_of_groups(PlannerInfo *root, double numGroups = estimate_num_groups(root, groupExprs, path_rows, - &gset); + &gset, + NULL); gs->numGroups = numGroups; rollup->numGroups += numGroups; @@ -3744,7 +3745,8 @@ get_number_of_groups(PlannerInfo *root, double numGroups = estimate_num_groups(root, groupExprs, path_rows, - &gset); + &gset, + NULL); gs->numGroups = numGroups; gd->dNumHashGroups += numGroups; @@ -3760,7 +3762,7 @@ get_number_of_groups(PlannerInfo *root, target_list); dNumGroups = estimate_num_groups(root, groupExprs, path_rows, - NULL); + NULL, NULL); } } else if (parse->groupingSets) @@ -4777,7 +4779,7 @@ create_distinct_paths(PlannerInfo *root, parse->targetList); numDistinctRows = estimate_num_groups(root, distinctExprs, cheapest_input_path->rows, - NULL); + NULL, NULL); } /* diff --git a/src/backend/optimizer/prep/prepunion.c b/src/backend/optimizer/prep/prepunion.c index 951aed80e7..7e9df9461e 100644 --- a/src/backend/optimizer/prep/prepunion.c +++ b/src/backend/optimizer/prep/prepunion.c @@ -338,6 +338,7 @@ recurse_set_operations(Node *setOp, PlannerInfo *root, *pNumGroups = estimate_num_groups(subroot, get_tlist_exprs(subquery->targetList, false), subpath->rows, + NULL, NULL); } } diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c index e845a4b1ae..37d6d293c3 100644 --- a/src/backend/optimizer/util/pathnode.c +++ b/src/backend/optimizer/util/pathnode.c @@ -1656,6 +1656,7 @@ create_unique_path(PlannerInfo *root, RelOptInfo *rel, Path *subpath, pathnode->path.rows = estimate_num_groups(root, sjinfo->semi_rhs_exprs, rel->rows, + NULL, NULL); numCols = list_length(sjinfo->semi_rhs_exprs); diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c index be08eb4814..2c5bfaf628 100644 --- a/src/backend/utils/adt/selfuncs.c +++ b/src/backend/utils/adt/selfuncs.c @@ -3238,6 +3238,7 @@ typedef struct Node *var; /* might be an expression, not just a Var */ RelOptInfo *rel; /* relation it belongs to */ double ndistinct; /* # distinct values */ + bool isdefault; /* true if DEFAULT_NUM_DISTINCT was used */ } GroupVarInfo; static List * @@ -3284,6 +3285,7 @@ add_unique_group_var(PlannerInfo *root, List *varinfos, varinfo->var = var; varinfo->rel = vardata->rel; varinfo->ndistinct = ndistinct; + varinfo->isdefault = isdefault; varinfos = lappend(varinfos, varinfo); return varinfos; } @@ -3308,6 +3310,11 @@ add_unique_group_var(PlannerInfo *root, List *varinfos, * pgset - NULL, or a List** pointing to a grouping set to filter the * groupExprs against * + * Outputs: + * flags - When passed as non-NULL, the function sets bits in this + * parameter to provide further details to callers about some + * assumptions which were made when performing the estimation. + * * Given the lack of any cross-correlation statistics in the system, it's * impossible to do anything really trustworthy with GROUP BY conditions * involving multiple Vars. We should however avoid assuming the worst @@ -3355,7 +3362,7 @@ add_unique_group_var(PlannerInfo *root, List *varinfos, */ double estimate_num_groups(PlannerInfo *root, List *groupExprs, double input_rows, - List **pgset) + List **pgset, int *flags) { List *varinfos = NIL; double srf_multiplier = 1.0; @@ -3363,6 +3370,10 @@ estimate_num_groups(PlannerInfo *root, List *groupExprs, double input_rows, ListCell *l; int i; + /* Zero the flags output parameter, if set */ + if (flags != NULL) + *flags = 0; + /* * We don't ever want to return an estimate of zero groups, as that tends * to lead to division-by-zero and other unpleasantness. The input_rows @@ -3566,6 +3577,14 @@ estimate_num_groups(PlannerInfo *root, List *groupExprs, double input_rows, if (relmaxndistinct < varinfo2->ndistinct) relmaxndistinct = varinfo2->ndistinct; relvarcount++; + + /* + * When varinfo2's isdefault is set then we'd better mark + * that fact in the selectivity flags variable. + */ + if (flags != NULL && varinfo2->isdefault) + *flags |= SELFLAG_USED_DEFAULT; + } /* we're done with this relation */ diff --git a/src/include/utils/selfuncs.h b/src/include/utils/selfuncs.h index 7ac4a06391..455e1343ee 100644 --- a/src/include/utils/selfuncs.h +++ b/src/include/utils/selfuncs.h @@ -65,6 +65,14 @@ p = 1.0; \ } while (0) +/* + * A set of flags which some selectivity estimation functions can pass back to + * callers to provide further details about some assumptions which were made + * during the estimation. + */ +#define SELFLAG_USED_DEFAULT (1 << 0) /* Estimation fell back on one of + * the DEFAULTs as defined above. + */ /* Return data from examine_variable and friends */ typedef struct VariableStatData @@ -194,7 +202,8 @@ extern void mergejoinscansel(PlannerInfo *root, Node *clause, Selectivity *rightstart, Selectivity *rightend); extern double estimate_num_groups(PlannerInfo *root, List *groupExprs, - double input_rows, List **pgset); + double input_rows, List **pgset, + int *flags); extern void estimate_hash_bucket_stats(PlannerInfo *root, Node *hashkey, double nbuckets, -- 2.25.1