#include <math.h>
#include "catalog/pg_class.h"
+#include "foreign/fdwapi.h"
#include "nodes/nodeFuncs.h"
#ifdef OPTIMIZER_DEBUG
#include "nodes/print.h"
static void set_base_rel_sizes(PlannerInfo *root);
static void set_base_rel_pathlists(PlannerInfo *root);
static void set_rel_size(PlannerInfo *root, RelOptInfo *rel,
- Index rti, RangeTblEntry *rte);
+ Index rti, RangeTblEntry *rte);
static void set_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
static void set_plain_rel_size(PlannerInfo *root, RelOptInfo *rel,
- RangeTblEntry *rte);
+ RangeTblEntry *rte);
static void set_plain_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_foreign_size(PlannerInfo *root, RelOptInfo *rel,
- RangeTblEntry *rte);
+ RangeTblEntry *rte);
static void set_foreign_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_append_rel_size(PlannerInfo *root, RelOptInfo *rel,
- Index rti, RangeTblEntry *rte);
+ Index rti, RangeTblEntry *rte);
static void set_append_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
static void generate_mergeappend_paths(PlannerInfo *root, RelOptInfo *rel,
List *live_childrels,
- List *all_child_pathkeys,
- Relids required_outer);
+ List *all_child_pathkeys);
static List *accumulate_append_subpath(List *subpaths, Path *path);
static void set_dummy_rel_pathlist(RelOptInfo *rel);
static void set_subquery_pathlist(PlannerInfo *root, RelOptInfo *rel,
if (brel == NULL)
continue;
- Assert(brel->relid == rti); /* sanity check on array */
+ Assert(brel->relid == rti); /* sanity check on array */
/* ignore RTEs that are "other rels" */
if (brel->reloptkind != RELOPT_BASEREL)
*/
static void
set_rel_size(PlannerInfo *root, RelOptInfo *rel,
- Index rti, RangeTblEntry *rte)
+ Index rti, RangeTblEntry *rte)
{
if (rel->reloptkind == RELOPT_BASEREL &&
relation_excluded_by_constraints(root, rel, rte))
}
break;
case RTE_SUBQUERY:
+
/*
- * Subqueries don't support parameterized paths, so just go
- * ahead and build their paths immediately.
+ * Subqueries don't support making a choice between
+ * parameterized and unparameterized paths, so just go ahead
+ * and build their paths immediately.
*/
set_subquery_pathlist(root, rel, rti, rte);
break;
set_values_size_estimates(root, rel);
break;
case RTE_CTE:
+
/*
- * CTEs don't support parameterized paths, so just go ahead
- * and build their paths immediately.
+ * CTEs don't support making a choice between parameterized
+ * and unparameterized paths, so just go ahead and build their
+ * paths immediately.
*/
if (rte->self_reference)
set_worktable_pathlist(root, rel, rte);
static void
set_plain_rel_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
+ Relids required_outer;
+
+ /*
+ * We don't support pushing join clauses into the quals of a seqscan, but
+ * it could still have required parameterization due to LATERAL refs in
+ * its tlist. (That can only happen if the seqscan is on a relation
+ * pulled up out of a UNION ALL appendrel.)
+ */
+ required_outer = rel->lateral_relids;
+
/* Consider sequential scan */
- add_path(rel, create_seqscan_path(root, rel));
+ add_path(rel, create_seqscan_path(root, rel, required_outer));
/* Consider index scans */
create_index_paths(root, rel);
{
/* Mark rel with estimated output rows, width, etc */
set_foreign_size_estimates(root, rel);
+
+ /* Get FDW routine pointers for the rel */
+ rel->fdwroutine = GetFdwRoutineByRelId(rte->relid);
+
+ /* Let FDW adjust the size estimates, if it can */
+ rel->fdwroutine->GetForeignRelSize(root, rel, rte->relid);
}
/*
* set_foreign_pathlist
- * Build the (single) access path for a foreign table RTE
+ * Build access paths for a foreign table RTE
*/
static void
set_foreign_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
- /* Generate appropriate path */
- add_path(rel, (Path *) create_foreignscan_path(root, rel));
+ /* Call the FDW's GetForeignPaths function to generate path(s) */
+ rel->fdwroutine->GetForeignPaths(root, rel, rte->relid);
- /* Select cheapest path (pretty easy in this case...) */
+ /* Select cheapest path */
set_cheapest(rel);
}
* reconstitute the RestrictInfo layer.
*/
childquals = get_all_actual_clauses(rel->baserestrictinfo);
- childquals = (List *) adjust_appendrel_attrs((Node *) childquals,
+ childquals = (List *) adjust_appendrel_attrs(root,
+ (Node *) childquals,
appinfo);
childqual = eval_const_expressions(root, (Node *)
make_ands_explicit(childquals));
* CE failed, so finish copying/modifying targetlist and join quals.
*
* Note: the resulting childrel->reltargetlist may contain arbitrary
- * expressions, which normally would not occur in a reltargetlist.
- * That is okay because nothing outside of this routine will look at
- * the child rel's reltargetlist. We do have to cope with the case
- * while constructing attr_widths estimates below, though.
+ * expressions, which otherwise would not occur in a reltargetlist.
+ * Code that might be looking at an appendrel child must cope with
+ * such. Note in particular that "arbitrary expression" can include
+ * "Var belonging to another relation", due to LATERAL references.
*/
childrel->joininfo = (List *)
- adjust_appendrel_attrs((Node *) rel->joininfo,
+ adjust_appendrel_attrs(root,
+ (Node *) rel->joininfo,
appinfo);
childrel->reltargetlist = (List *)
- adjust_appendrel_attrs((Node *) rel->reltargetlist,
+ adjust_appendrel_attrs(root,
+ (Node *) rel->reltargetlist,
appinfo);
/*
/*
* It is possible that constraint exclusion detected a contradiction
- * within a child subquery, even though we didn't prove one above.
- * If so, we can skip this child.
+ * within a child subquery, even though we didn't prove one above. If
+ * so, we can skip this child.
*/
if (IS_DUMMY_REL(childrel))
continue;
/*
* Accumulate per-column estimates too. We need not do anything
- * for PlaceHolderVars in the parent list. If child expression
+ * for PlaceHolderVars in the parent list. If child expression
* isn't a Var, or we didn't record a width estimate for it, we
* have to fall back on a datatype-based estimate.
*
int pndx = parentvar->varattno - rel->min_attr;
int32 child_width = 0;
- if (IsA(childvar, Var))
+ if (IsA(childvar, Var) &&
+ ((Var *) childvar)->varno == childrel->relid)
{
- int cndx = ((Var *) childvar)->varattno - childrel->min_attr;
+ int cndx = ((Var *) childvar)->varattno - childrel->min_attr;
child_width = childrel->attr_widths[cndx];
}
int parentRTindex = rti;
List *live_childrels = NIL;
List *subpaths = NIL;
+ bool subpaths_valid = true;
List *all_child_pathkeys = NIL;
List *all_child_outers = NIL;
ListCell *l;
/*
* Generate access paths for each member relation, and remember the
- * cheapest path for each one. Also, identify all pathkeys (orderings)
+ * cheapest path for each one. Also, identify all pathkeys (orderings)
* and parameterizations (required_outer sets) available for the member
* relations.
*/
continue;
/*
- * Child is live, so add its cheapest access path to the Append path
- * we are constructing for the parent.
+ * Child is live, so add it to the live_childrels list for use below.
*/
- subpaths = accumulate_append_subpath(subpaths,
- childrel->cheapest_total_path);
-
- /* Remember which childrels are live, for logic below */
live_childrels = lappend(live_childrels, childrel);
+ /*
+ * If child has an unparameterized cheapest-total path, add that to
+ * the unparameterized Append path we are constructing for the parent.
+ * If not, there's no workable unparameterized path.
+ */
+ if (childrel->cheapest_total_path->param_info == NULL)
+ subpaths = accumulate_append_subpath(subpaths,
+ childrel->cheapest_total_path);
+ else
+ subpaths_valid = false;
+
/*
* Collect lists of all the available path orderings and
- * parameterizations for all the children. We use these as a
+ * parameterizations for all the children. We use these as a
* heuristic to indicate which sort orderings and parameterizations we
* should build Append and MergeAppend paths for.
*/
{
Path *childpath = (Path *) lfirst(lcp);
List *childkeys = childpath->pathkeys;
- Relids childouter = childpath->required_outer;
+ Relids childouter = PATH_REQ_OUTER(childpath);
/* Unsorted paths don't contribute to pathkey list */
if (childkeys != NIL)
/* Have we already seen this param set? */
foreach(lco, all_child_outers)
{
- Relids existing_outers = (Relids) lfirst(lco);
+ Relids existing_outers = (Relids) lfirst(lco);
if (bms_equal(existing_outers, childouter))
{
}
/*
- * Next, build an unordered, unparameterized Append path for the rel.
- * (Note: this is correct even if we have zero or one live subpath due to
- * constraint exclusion.)
+ * If we found unparameterized paths for all children, build an unordered,
+ * unparameterized Append path for the rel. (Note: this is correct even
+ * if we have zero or one live subpath due to constraint exclusion.)
*/
- add_path(rel, (Path *) create_append_path(rel, subpaths));
+ if (subpaths_valid)
+ add_path(rel, (Path *) create_append_path(rel, subpaths, NULL));
/*
- * Build unparameterized MergeAppend paths based on the collected list of
- * child pathkeys.
+ * Also build unparameterized MergeAppend paths based on the collected
+ * list of child pathkeys.
*/
- generate_mergeappend_paths(root, rel, live_childrels,
- all_child_pathkeys, NULL);
+ if (subpaths_valid)
+ generate_mergeappend_paths(root, rel, live_childrels,
+ all_child_pathkeys);
/*
- * Build Append and MergeAppend paths for each parameterization seen
- * among the child rels. (This may look pretty expensive, but in most
- * cases of practical interest, the child relations will tend to expose
- * the same parameterizations and pathkeys, so that not that many cases
- * actually get considered here.)
+ * Build Append paths for each parameterization seen among the child rels.
+ * (This may look pretty expensive, but in most cases of practical
+ * interest, the child rels will expose mostly the same parameterizations,
+ * so that not that many cases actually get considered here.)
+ *
+ * The Append node itself cannot enforce quals, so all qual checking must
+ * be done in the child paths. This means that to have a parameterized
+ * Append path, we must have the exact same parameterization for each
+ * child path; otherwise some children might be failing to check the
+ * moved-down quals. To make them match up, we can try to increase the
+ * parameterization of lesser-parameterized paths.
*/
foreach(l, all_child_outers)
{
- Relids required_outer = (Relids) lfirst(l);
+ Relids required_outer = (Relids) lfirst(l);
ListCell *lcr;
/* Select the child paths for an Append with this parameterization */
subpaths = NIL;
+ subpaths_valid = true;
foreach(lcr, live_childrels)
{
RelOptInfo *childrel = (RelOptInfo *) lfirst(lcr);
TOTAL_COST);
Assert(cheapest_total != NULL);
+ /* Children must have exactly the desired parameterization */
+ if (!bms_equal(PATH_REQ_OUTER(cheapest_total), required_outer))
+ {
+ cheapest_total = reparameterize_path(root, cheapest_total,
+ required_outer, 1.0);
+ if (cheapest_total == NULL)
+ {
+ subpaths_valid = false;
+ break;
+ }
+ }
+
subpaths = accumulate_append_subpath(subpaths, cheapest_total);
}
- add_path(rel, (Path *) create_append_path(rel, subpaths));
- /* And build parameterized MergeAppend paths */
- generate_mergeappend_paths(root, rel, live_childrels,
- all_child_pathkeys, required_outer);
+ if (subpaths_valid)
+ add_path(rel, (Path *)
+ create_append_path(rel, subpaths, required_outer));
}
/* Select cheapest paths */
* Generate MergeAppend paths for an append relation
*
* Generate a path for each ordering (pathkey list) appearing in
- * all_child_pathkeys. If required_outer isn't NULL, accept paths having
- * those relations as required outer relations.
+ * all_child_pathkeys.
*
* We consider both cheapest-startup and cheapest-total cases, ie, for each
* interesting ordering, collect all the cheapest startup subpaths and all the
* cheapest total paths, and build a MergeAppend path for each case.
+ *
+ * We don't currently generate any parameterized MergeAppend paths. While
+ * it would not take much more code here to do so, it's very unclear that it
+ * is worth the planning cycles to investigate such paths: there's little
+ * use for an ordered path on the inside of a nestloop. In fact, it's likely
+ * that the current coding of add_path would reject such paths out of hand,
+ * because add_path gives no credit for sort ordering of parameterized paths,
+ * and a parameterized MergeAppend is going to be more expensive than the
+ * corresponding parameterized Append path. If we ever try harder to support
+ * parameterized mergejoin plans, it might be worth adding support for
+ * parameterized MergeAppends to feed such joins. (See notes in
+ * optimizer/README for why that might not ever happen, though.)
*/
static void
generate_mergeappend_paths(PlannerInfo *root, RelOptInfo *rel,
List *live_childrels,
- List *all_child_pathkeys,
- Relids required_outer)
+ List *all_child_pathkeys)
{
ListCell *lcp;
cheapest_startup =
get_cheapest_path_for_pathkeys(childrel->pathlist,
pathkeys,
- required_outer,
+ NULL,
STARTUP_COST);
cheapest_total =
get_cheapest_path_for_pathkeys(childrel->pathlist,
pathkeys,
- required_outer,
+ NULL,
TOTAL_COST);
/*
* If we can't find any paths with the right order just use the
- * cheapest-total path; we'll have to sort it later. We can
- * use the cheapest path for the parameterization, though.
+ * cheapest-total path; we'll have to sort it later.
*/
if (cheapest_startup == NULL || cheapest_total == NULL)
{
- if (required_outer)
- cheapest_startup = cheapest_total =
- get_cheapest_path_for_pathkeys(childrel->pathlist,
- NIL,
- required_outer,
- TOTAL_COST);
- else
- cheapest_startup = cheapest_total =
- childrel->cheapest_total_path;
- Assert(cheapest_total != NULL);
+ cheapest_startup = cheapest_total =
+ childrel->cheapest_total_path;
+ /* Assert we do have an unparameterized path for this child */
+ Assert(cheapest_total->param_info == NULL);
}
/*
add_path(rel, (Path *) create_merge_append_path(root,
rel,
startup_subpaths,
- pathkeys));
+ pathkeys,
+ NULL));
if (startup_neq_total)
add_path(rel, (Path *) create_merge_append_path(root,
rel,
total_subpaths,
- pathkeys));
+ pathkeys,
+ NULL));
}
}
/* Discard any pre-existing paths; no further need for them */
rel->pathlist = NIL;
- add_path(rel, (Path *) create_append_path(rel, NIL));
+ add_path(rel, (Path *) create_append_path(rel, NIL, NULL));
/* Select cheapest path (pretty easy in this case...) */
set_cheapest(rel);
* set_subquery_pathlist
* Build the (single) access path for a subquery RTE
*
- * There's no need for a separate set_subquery_size phase, since we don't
- * support parameterized paths for subqueries.
+ * We don't currently support generating parameterized paths for subqueries
+ * by pushing join clauses down into them; it seems too expensive to re-plan
+ * the subquery multiple times to consider different alternatives. So the
+ * subquery will have exactly one path. (The path will be parameterized
+ * if the subquery contains LATERAL references, otherwise not.) Since there's
+ * no freedom of action here, there's no need for a separate set_subquery_size
+ * phase: we just make the path right away.
*/
static void
set_subquery_pathlist(PlannerInfo *root, RelOptInfo *rel,
{
Query *parse = root->parse;
Query *subquery = rte->subquery;
+ Relids required_outer;
bool *differentTypes;
double tuple_fraction;
PlannerInfo *subroot;
*/
subquery = copyObject(subquery);
+ /*
+ * If it's a LATERAL subquery, it might contain some Vars of the current
+ * query level, requiring it to be treated as parameterized, even though
+ * we don't support pushing down join quals into subqueries.
+ */
+ required_outer = rel->lateral_relids;
+
/* We need a workspace for keeping track of set-op type coercions */
differentTypes = (bool *)
palloc0((list_length(subquery->targetList) + 1) * sizeof(bool));
* pseudoconstant clauses; better to have the gating node above the
* subquery.
*
- * Also, if the sub-query has "security_barrier" flag, it means the
+ * Also, if the sub-query has the "security_barrier" flag, it means the
* sub-query originated from a view that must enforce row-level security.
- * We must not push down quals in order to avoid information leaks, either
- * via side-effects or error output.
+ * Then we must not push down quals that contain leaky functions.
*
* Non-pushed-down clauses will get evaluated as qpquals of the
* SubqueryScan node.
RestrictInfo *rinfo = (RestrictInfo *) lfirst(l);
Node *clause = (Node *) rinfo->clause;
- /*
- * XXX. You might wonder why we're testing rte->security_barrier
- * qual-by-qual here rather than hoisting the test up into the
- * surrounding if statement; after all, the answer will be the
- * same for all quals. The answer is that we expect to shortly
- * change this logic to allow pushing down some quals that use only
- * "leakproof" operators even through a security barrier.
- */
if (!rinfo->pseudoconstant &&
- !rte->security_barrier &&
+ (!rte->security_barrier ||
+ !contain_leaky_functions(clause)) &&
qual_is_pushdown_safe(subquery, rti, clause, differentTypes))
{
/* Push it down */
else
tuple_fraction = root->tuple_fraction;
+ /* plan_params should not be in use in current query level */
+ Assert(root->plan_params == NIL);
+
/* Generate the plan for the subquery */
rel->subplan = subquery_planner(root->glob, subquery,
root,
&subroot);
rel->subroot = subroot;
+ /* Isolate the params needed by this specific subplan */
+ rel->subplan_params = root->plan_params;
+ root->plan_params = NIL;
+
/*
- * It's possible that constraint exclusion proved the subquery empty.
- * If so, it's convenient to turn it back into a dummy path so that we
- * will recognize appropriate optimizations at this level.
+ * It's possible that constraint exclusion proved the subquery empty. If
+ * so, it's convenient to turn it back into a dummy path so that we will
+ * recognize appropriate optimizations at this level.
*/
if (is_dummy_plan(rel->subplan))
{
pathkeys = convert_subquery_pathkeys(root, rel, subroot->query_pathkeys);
/* Generate appropriate path */
- add_path(rel, create_subqueryscan_path(rel, pathkeys));
+ add_path(rel, create_subqueryscan_path(root, rel, pathkeys, required_outer));
/* Select cheapest path (pretty easy in this case...) */
set_cheapest(rel);
static void
set_function_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
+ Relids required_outer;
+
+ /*
+ * We don't support pushing join clauses into the quals of a function
+ * scan, but it could still have required parameterization due to LATERAL
+ * refs in the function expression.
+ */
+ required_outer = rel->lateral_relids;
+
/* Generate appropriate path */
- add_path(rel, create_functionscan_path(root, rel));
+ add_path(rel, create_functionscan_path(root, rel, required_outer));
/* Select cheapest path (pretty easy in this case...) */
set_cheapest(rel);
static void
set_values_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
+ Relids required_outer;
+
+ /*
+ * We don't support pushing join clauses into the quals of a values scan,
+ * but it could still have required parameterization due to LATERAL refs
+ * in the values expressions.
+ */
+ required_outer = rel->lateral_relids;
+
/* Generate appropriate path */
- add_path(rel, create_valuesscan_path(root, rel));
+ add_path(rel, create_valuesscan_path(root, rel, required_outer));
/* Select cheapest path (pretty easy in this case...) */
set_cheapest(rel);
* Build the (single) access path for a non-self-reference CTE RTE
*
* There's no need for a separate set_cte_size phase, since we don't
- * support parameterized paths for CTEs.
+ * support join-qual-parameterized paths for CTEs.
*/
static void
set_cte_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
int ndx;
ListCell *lc;
int plan_id;
+ Relids required_outer;
/*
* Find the referenced CTE, and locate the plan previously made for it.
/* Mark rel with estimated output rows, width, etc */
set_cte_size_estimates(root, rel, cteplan);
+ /*
+ * We don't support pushing join clauses into the quals of a CTE scan, but
+ * it could still have required parameterization due to LATERAL refs in
+ * its tlist. (That can only happen if the CTE scan is on a relation
+ * pulled up out of a UNION ALL appendrel.)
+ */
+ required_outer = rel->lateral_relids;
+
/* Generate appropriate path */
- add_path(rel, create_ctescan_path(root, rel));
+ add_path(rel, create_ctescan_path(root, rel, required_outer));
/* Select cheapest path (pretty easy in this case...) */
set_cheapest(rel);
* Build the (single) access path for a self-reference CTE RTE
*
* There's no need for a separate set_worktable_size phase, since we don't
- * support parameterized paths for CTEs.
+ * support join-qual-parameterized paths for CTEs.
*/
static void
set_worktable_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
Plan *cteplan;
PlannerInfo *cteroot;
Index levelsup;
+ Relids required_outer;
/*
* We need to find the non-recursive term's plan, which is in the plan
/* Mark rel with estimated output rows, width, etc */
set_cte_size_estimates(root, rel, cteplan);
+ /*
+ * We don't support pushing join clauses into the quals of a worktable
+ * scan, but it could still have required parameterization due to LATERAL
+ * refs in its tlist. (That can only happen if the worktable scan is on a
+ * relation pulled up out of a UNION ALL appendrel. I'm not sure this is
+ * actually possible given the restrictions on recursive references, but
+ * it's easy enough to support.)
+ */
+ required_outer = rel->lateral_relids;
+
/* Generate appropriate path */
- add_path(rel, create_worktablescan_path(root, rel));
+ add_path(rel, create_worktablescan_path(root, rel, required_outer));
/* Select cheapest path (pretty easy in this case...) */
set_cheapest(rel);
/*
* It would be unsafe to push down window function calls, but at least for
- * the moment we could never see any in a qual anyhow. (The same applies
+ * the moment we could never see any in a qual anyhow. (The same applies
* to aggregates, which we check for in pull_var_clause below.)
*/
Assert(!contain_window_function(qual));
printf("\tpath list:\n");
foreach(l, rel->pathlist)
print_path(root, lfirst(l), 1);
- printf("\n\tcheapest startup path:\n");
- print_path(root, rel->cheapest_startup_path, 1);
- printf("\n\tcheapest total path:\n");
- print_path(root, rel->cheapest_total_path, 1);
+ if (rel->cheapest_startup_path)
+ {
+ printf("\n\tcheapest startup path:\n");
+ print_path(root, rel->cheapest_startup_path, 1);
+ }
+ if (rel->cheapest_total_path)
+ {
+ printf("\n\tcheapest total path:\n");
+ print_path(root, rel->cheapest_total_path, 1);
+ }
printf("\n");
fflush(stdout);
}
projects / postgresql / blobdiff