/*------------------------------------------------------------------------- * * pathnode.c * Routines to manipulate pathlists and create path nodes * * Portions Copyright (c) 1996-2015, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * * * IDENTIFICATION * src/backend/optimizer/util/pathnode.c * *------------------------------------------------------------------------- */ #include "postgres.h" #include #include "miscadmin.h" #include "nodes/nodeFuncs.h" #include "optimizer/clauses.h" #include "optimizer/cost.h" #include "optimizer/pathnode.h" #include "optimizer/paths.h" #include "optimizer/planmain.h" #include "optimizer/restrictinfo.h" #include "optimizer/var.h" #include "parser/parsetree.h" #include "utils/lsyscache.h" #include "utils/selfuncs.h" typedef enum { COSTS_EQUAL, /* path costs are fuzzily equal */ COSTS_BETTER1, /* first path is cheaper than second */ COSTS_BETTER2, /* second path is cheaper than first */ COSTS_DIFFERENT /* neither path dominates the other on cost */ } PathCostComparison; /* * STD_FUZZ_FACTOR is the normal fuzz factor for compare_path_costs_fuzzily. * XXX is it worth making this user-controllable? It provides a tradeoff * between planner runtime and the accuracy of path cost comparisons. */ #define STD_FUZZ_FACTOR 1.01 static List *translate_sub_tlist(List *tlist, int relid); /***************************************************************************** * MISC. PATH UTILITIES *****************************************************************************/ /* * compare_path_costs * Return -1, 0, or +1 according as path1 is cheaper, the same cost, * or more expensive than path2 for the specified criterion. */ int compare_path_costs(Path *path1, Path *path2, CostSelector criterion) { if (criterion == STARTUP_COST) { if (path1->startup_cost < path2->startup_cost) return -1; if (path1->startup_cost > path2->startup_cost) return +1; /* * If paths have the same startup cost (not at all unlikely), order * them by total cost. */ if (path1->total_cost < path2->total_cost) return -1; if (path1->total_cost > path2->total_cost) return +1; } else { if (path1->total_cost < path2->total_cost) return -1; if (path1->total_cost > path2->total_cost) return +1; /* * If paths have the same total cost, order them by startup cost. */ if (path1->startup_cost < path2->startup_cost) return -1; if (path1->startup_cost > path2->startup_cost) return +1; } return 0; } /* * compare_path_fractional_costs * Return -1, 0, or +1 according as path1 is cheaper, the same cost, * or more expensive than path2 for fetching the specified fraction * of the total tuples. * * If fraction is <= 0 or > 1, we interpret it as 1, ie, we select the * path with the cheaper total_cost. */ int compare_fractional_path_costs(Path *path1, Path *path2, double fraction) { Cost cost1, cost2; if (fraction <= 0.0 || fraction >= 1.0) return compare_path_costs(path1, path2, TOTAL_COST); cost1 = path1->startup_cost + fraction * (path1->total_cost - path1->startup_cost); cost2 = path2->startup_cost + fraction * (path2->total_cost - path2->startup_cost); if (cost1 < cost2) return -1; if (cost1 > cost2) return +1; return 0; } /* * compare_path_costs_fuzzily * Compare the costs of two paths to see if either can be said to * dominate the other. * * We use fuzzy comparisons so that add_path() can avoid keeping both of * a pair of paths that really have insignificantly different cost. * * The fuzz_factor argument must be 1.0 plus delta, where delta is the * fraction of the smaller cost that is considered to be a significant * difference. For example, fuzz_factor = 1.01 makes the fuzziness limit * be 1% of the smaller cost. * * The two paths are said to have "equal" costs if both startup and total * costs are fuzzily the same. Path1 is said to be better than path2 if * it has fuzzily better startup cost and fuzzily no worse total cost, * or if it has fuzzily better total cost and fuzzily no worse startup cost. * Path2 is better than path1 if the reverse holds. Finally, if one path * is fuzzily better than the other on startup cost and fuzzily worse on * total cost, we just say that their costs are "different", since neither * dominates the other across the whole performance spectrum. * * This function also enforces a policy rule that paths for which the relevant * one of parent->consider_startup and parent->consider_param_startup is false * cannot survive comparisons solely on the grounds of good startup cost, so * we never return COSTS_DIFFERENT when that is true for the total-cost loser. * (But if total costs are fuzzily equal, we compare startup costs anyway, * in hopes of eliminating one path or the other.) */ static PathCostComparison compare_path_costs_fuzzily(Path *path1, Path *path2, double fuzz_factor) { #define CONSIDER_PATH_STARTUP_COST(p) \ ((p)->param_info == NULL ? (p)->parent->consider_startup : (p)->parent->consider_param_startup) /* * Check total cost first since it's more likely to be different; many * paths have zero startup cost. */ if (path1->total_cost > path2->total_cost * fuzz_factor) { /* path1 fuzzily worse on total cost */ if (CONSIDER_PATH_STARTUP_COST(path1) && path2->startup_cost > path1->startup_cost * fuzz_factor) { /* ... but path2 fuzzily worse on startup, so DIFFERENT */ return COSTS_DIFFERENT; } /* else path2 dominates */ return COSTS_BETTER2; } if (path2->total_cost > path1->total_cost * fuzz_factor) { /* path2 fuzzily worse on total cost */ if (CONSIDER_PATH_STARTUP_COST(path2) && path1->startup_cost > path2->startup_cost * fuzz_factor) { /* ... but path1 fuzzily worse on startup, so DIFFERENT */ return COSTS_DIFFERENT; } /* else path1 dominates */ return COSTS_BETTER1; } /* fuzzily the same on total cost ... */ if (path1->startup_cost > path2->startup_cost * fuzz_factor) { /* ... but path1 fuzzily worse on startup, so path2 wins */ return COSTS_BETTER2; } if (path2->startup_cost > path1->startup_cost * fuzz_factor) { /* ... but path2 fuzzily worse on startup, so path1 wins */ return COSTS_BETTER1; } /* fuzzily the same on both costs */ return COSTS_EQUAL; #undef CONSIDER_PATH_STARTUP_COST } /* * set_cheapest * Find the minimum-cost paths from among a relation's paths, * and save them in the rel's cheapest-path fields. * * cheapest_total_path is normally the cheapest-total-cost unparameterized * path; but if there are no unparameterized paths, we assign it to be the * best (cheapest least-parameterized) parameterized path. However, only * unparameterized paths are considered candidates for cheapest_startup_path, * so that will be NULL if there are no unparameterized paths. * * The cheapest_parameterized_paths list collects all parameterized paths * that have survived the add_path() tournament for this relation. (Since * add_path ignores pathkeys for a parameterized path, these will be paths * that have best cost or best row count for their parameterization.) * cheapest_parameterized_paths always includes the cheapest-total * unparameterized path, too, if there is one; the users of that list find * it more convenient if that's included. * * This is normally called only after we've finished constructing the path * list for the rel node. */ void set_cheapest(RelOptInfo *parent_rel) { Path *cheapest_startup_path; Path *cheapest_total_path; Path *best_param_path; List *parameterized_paths; ListCell *p; Assert(IsA(parent_rel, RelOptInfo)); if (parent_rel->pathlist == NIL) elog(ERROR, "could not devise a query plan for the given query"); cheapest_startup_path = cheapest_total_path = best_param_path = NULL; parameterized_paths = NIL; foreach(p, parent_rel->pathlist) { Path *path = (Path *) lfirst(p); int cmp; if (path->param_info) { /* Parameterized path, so add it to parameterized_paths */ parameterized_paths = lappend(parameterized_paths, path); /* * If we have an unparameterized cheapest-total, we no longer care * about finding the best parameterized path, so move on. */ if (cheapest_total_path) continue; /* * Otherwise, track the best parameterized path, which is the one * with least total cost among those of the minimum * parameterization. */ if (best_param_path == NULL) best_param_path = path; else { switch (bms_subset_compare(PATH_REQ_OUTER(path), PATH_REQ_OUTER(best_param_path))) { case BMS_EQUAL: /* keep the cheaper one */ if (compare_path_costs(path, best_param_path, TOTAL_COST) < 0) best_param_path = path; break; case BMS_SUBSET1: /* new path is less-parameterized */ best_param_path = path; break; case BMS_SUBSET2: /* old path is less-parameterized, keep it */ break; case BMS_DIFFERENT: /* * This means that neither path has the least possible * parameterization for the rel. We'll sit on the old * path until something better comes along. */ break; } } } else { /* Unparameterized path, so consider it for cheapest slots */ if (cheapest_total_path == NULL) { cheapest_startup_path = cheapest_total_path = path; continue; } /* * If we find two paths of identical costs, try to keep the * better-sorted one. The paths might have unrelated sort * orderings, in which case we can only guess which might be * better to keep, but if one is superior then we definitely * should keep that one. */ cmp = compare_path_costs(cheapest_startup_path, path, STARTUP_COST); if (cmp > 0 || (cmp == 0 && compare_pathkeys(cheapest_startup_path->pathkeys, path->pathkeys) == PATHKEYS_BETTER2)) cheapest_startup_path = path; cmp = compare_path_costs(cheapest_total_path, path, TOTAL_COST); if (cmp > 0 || (cmp == 0 && compare_pathkeys(cheapest_total_path->pathkeys, path->pathkeys) == PATHKEYS_BETTER2)) cheapest_total_path = path; } } /* Add cheapest unparameterized path, if any, to parameterized_paths */ if (cheapest_total_path) parameterized_paths = lcons(cheapest_total_path, parameterized_paths); /* * If there is no unparameterized path, use the best parameterized path as * cheapest_total_path (but not as cheapest_startup_path). */ if (cheapest_total_path == NULL) cheapest_total_path = best_param_path; Assert(cheapest_total_path != NULL); parent_rel->cheapest_startup_path = cheapest_startup_path; parent_rel->cheapest_total_path = cheapest_total_path; parent_rel->cheapest_unique_path = NULL; /* computed only if needed */ parent_rel->cheapest_parameterized_paths = parameterized_paths; } /* * add_path * Consider a potential implementation path for the specified parent rel, * and add it to the rel's pathlist if it is worthy of consideration. * A path is worthy if it has a better sort order (better pathkeys) or * cheaper cost (on either dimension), or generates fewer rows, than any * existing path that has the same or superset parameterization rels. * * We also remove from the rel's pathlist any old paths that are dominated * by new_path --- that is, new_path is cheaper, at least as well ordered, * generates no more rows, and requires no outer rels not required by the * old path. * * In most cases, a path with a superset parameterization will generate * fewer rows (since it has more join clauses to apply), so that those two * figures of merit move in opposite directions; this means that a path of * one parameterization can seldom dominate a path of another. But such * cases do arise, so we make the full set of checks anyway. * * There are two policy decisions embedded in this function, along with * its sibling add_path_precheck. First, we treat all parameterized paths * as having NIL pathkeys, so that they cannot win comparisons on the * basis of sort order. This is to reduce the number of parameterized * paths that are kept; see discussion in src/backend/optimizer/README. * * Second, we only consider cheap startup cost to be interesting if * parent_rel->consider_startup is true for an unparameterized path, or * parent_rel->consider_param_startup is true for a parameterized one. * Again, this allows discarding useless paths sooner. * * The pathlist is kept sorted by total_cost, with cheaper paths * at the front. Within this routine, that's simply a speed hack: * doing it that way makes it more likely that we will reject an inferior * path after a few comparisons, rather than many comparisons. * However, add_path_precheck relies on this ordering to exit early * when possible. * * NOTE: discarded Path objects are immediately pfree'd to reduce planner * memory consumption. We dare not try to free the substructure of a Path, * since much of it may be shared with other Paths or the query tree itself; * but just recycling discarded Path nodes is a very useful savings in * a large join tree. We can recycle the List nodes of pathlist, too. * * BUT: we do not pfree IndexPath objects, since they may be referenced as * children of BitmapHeapPaths as well as being paths in their own right. * * 'parent_rel' is the relation entry to which the path corresponds. * 'new_path' is a potential path for parent_rel. * * Returns nothing, but modifies parent_rel->pathlist. */ void add_path(RelOptInfo *parent_rel, Path *new_path) { bool accept_new = true; /* unless we find a superior old path */ ListCell *insert_after = NULL; /* where to insert new item */ List *new_path_pathkeys; ListCell *p1; ListCell *p1_prev; ListCell *p1_next; /* * This is a convenient place to check for query cancel --- no part of the * planner goes very long without calling add_path(). */ CHECK_FOR_INTERRUPTS(); /* Pretend parameterized paths have no pathkeys, per comment above */ new_path_pathkeys = new_path->param_info ? NIL : new_path->pathkeys; /* * Loop to check proposed new path against old paths. Note it is possible * for more than one old path to be tossed out because new_path dominates * it. * * We can't use foreach here because the loop body may delete the current * list cell. */ p1_prev = NULL; for (p1 = list_head(parent_rel->pathlist); p1 != NULL; p1 = p1_next) { Path *old_path = (Path *) lfirst(p1); bool remove_old = false; /* unless new proves superior */ PathCostComparison costcmp; PathKeysComparison keyscmp; BMS_Comparison outercmp; p1_next = lnext(p1); /* * Do a fuzzy cost comparison with standard fuzziness limit. */ costcmp = compare_path_costs_fuzzily(new_path, old_path, STD_FUZZ_FACTOR); /* * If the two paths compare differently for startup and total cost, * then we want to keep both, and we can skip comparing pathkeys and * required_outer rels. If they compare the same, proceed with the * other comparisons. Row count is checked last. (We make the tests * in this order because the cost comparison is most likely to turn * out "different", and the pathkeys comparison next most likely. As * explained above, row count very seldom makes a difference, so even * though it's cheap to compare there's not much point in checking it * earlier.) */ if (costcmp != COSTS_DIFFERENT) { /* Similarly check to see if either dominates on pathkeys */ List *old_path_pathkeys; old_path_pathkeys = old_path->param_info ? NIL : old_path->pathkeys; keyscmp = compare_pathkeys(new_path_pathkeys, old_path_pathkeys); if (keyscmp != PATHKEYS_DIFFERENT) { switch (costcmp) { case COSTS_EQUAL: outercmp = bms_subset_compare(PATH_REQ_OUTER(new_path), PATH_REQ_OUTER(old_path)); if (keyscmp == PATHKEYS_BETTER1) { if ((outercmp == BMS_EQUAL || outercmp == BMS_SUBSET1) && new_path->rows <= old_path->rows) remove_old = true; /* new dominates old */ } else if (keyscmp == PATHKEYS_BETTER2) { if ((outercmp == BMS_EQUAL || outercmp == BMS_SUBSET2) && new_path->rows >= old_path->rows) accept_new = false; /* old dominates new */ } else /* keyscmp == PATHKEYS_EQUAL */ { if (outercmp == BMS_EQUAL) { /* * Same pathkeys and outer rels, and fuzzily * the same cost, so keep just one; to decide * which, first check rows and then do a fuzzy * cost comparison with very small fuzz limit. * (We used to do an exact cost comparison, * but that results in annoying * platform-specific plan variations due to * roundoff in the cost estimates.) If things * are still tied, arbitrarily keep only the * old path. Notice that we will keep only * the old path even if the less-fuzzy * comparison decides the startup and total * costs compare differently. */ if (new_path->rows < old_path->rows) remove_old = true; /* new dominates old */ else if (new_path->rows > old_path->rows) accept_new = false; /* old dominates new */ else if (compare_path_costs_fuzzily(new_path, old_path, 1.0000000001) == COSTS_BETTER1) remove_old = true; /* new dominates old */ else accept_new = false; /* old equals or * dominates new */ } else if (outercmp == BMS_SUBSET1 && new_path->rows <= old_path->rows) remove_old = true; /* new dominates old */ else if (outercmp == BMS_SUBSET2 && new_path->rows >= old_path->rows) accept_new = false; /* old dominates new */ /* else different parameterizations, keep both */ } break; case COSTS_BETTER1: if (keyscmp != PATHKEYS_BETTER2) { outercmp = bms_subset_compare(PATH_REQ_OUTER(new_path), PATH_REQ_OUTER(old_path)); if ((outercmp == BMS_EQUAL || outercmp == BMS_SUBSET1) && new_path->rows <= old_path->rows) remove_old = true; /* new dominates old */ } break; case COSTS_BETTER2: if (keyscmp != PATHKEYS_BETTER1) { outercmp = bms_subset_compare(PATH_REQ_OUTER(new_path), PATH_REQ_OUTER(old_path)); if ((outercmp == BMS_EQUAL || outercmp == BMS_SUBSET2) && new_path->rows >= old_path->rows) accept_new = false; /* old dominates new */ } break; case COSTS_DIFFERENT: /* * can't get here, but keep this case to keep compiler * quiet */ break; } } } /* * Remove current element from pathlist if dominated by new. */ if (remove_old) { parent_rel->pathlist = list_delete_cell(parent_rel->pathlist, p1, p1_prev); /* * Delete the data pointed-to by the deleted cell, if possible */ if (!IsA(old_path, IndexPath)) pfree(old_path); /* p1_prev does not advance */ } else { /* new belongs after this old path if it has cost >= old's */ if (new_path->total_cost >= old_path->total_cost) insert_after = p1; /* p1_prev advances */ p1_prev = p1; } /* * If we found an old path that dominates new_path, we can quit * scanning the pathlist; we will not add new_path, and we assume * new_path cannot dominate any other elements of the pathlist. */ if (!accept_new) break; } if (accept_new) { /* Accept the new path: insert it at proper place in pathlist */ if (insert_after) lappend_cell(parent_rel->pathlist, insert_after, new_path); else parent_rel->pathlist = lcons(new_path, parent_rel->pathlist); } else { /* Reject and recycle the new path */ if (!IsA(new_path, IndexPath)) pfree(new_path); } } /* * add_path_precheck * Check whether a proposed new path could possibly get accepted. * We assume we know the path's pathkeys and parameterization accurately, * and have lower bounds for its costs. * * Note that we do not know the path's rowcount, since getting an estimate for * that is too expensive to do before prechecking. We assume here that paths * of a superset parameterization will generate fewer rows; if that holds, * then paths with different parameterizations cannot dominate each other * and so we can simply ignore existing paths of another parameterization. * (In the infrequent cases where that rule of thumb fails, add_path will * get rid of the inferior path.) * * At the time this is called, we haven't actually built a Path structure, * so the required information has to be passed piecemeal. */ bool add_path_precheck(RelOptInfo *parent_rel, Cost startup_cost, Cost total_cost, List *pathkeys, Relids required_outer) { List *new_path_pathkeys; bool consider_startup; ListCell *p1; /* Pretend parameterized paths have no pathkeys, per add_path policy */ new_path_pathkeys = required_outer ? NIL : pathkeys; /* Decide whether new path's startup cost is interesting */ consider_startup = required_outer ? parent_rel->consider_param_startup : parent_rel->consider_startup; foreach(p1, parent_rel->pathlist) { Path *old_path = (Path *) lfirst(p1); PathKeysComparison keyscmp; /* * We are looking for an old_path with the same parameterization (and * by assumption the same rowcount) that dominates the new path on * pathkeys as well as both cost metrics. If we find one, we can * reject the new path. * * Cost comparisons here should match compare_path_costs_fuzzily. */ if (total_cost > old_path->total_cost * STD_FUZZ_FACTOR) { /* new path can win on startup cost only if consider_startup */ if (startup_cost > old_path->startup_cost * STD_FUZZ_FACTOR || !consider_startup) { /* new path loses on cost, so check pathkeys... */ List *old_path_pathkeys; old_path_pathkeys = old_path->param_info ? NIL : old_path->pathkeys; keyscmp = compare_pathkeys(new_path_pathkeys, old_path_pathkeys); if (keyscmp == PATHKEYS_EQUAL || keyscmp == PATHKEYS_BETTER2) { /* new path does not win on pathkeys... */ if (bms_equal(required_outer, PATH_REQ_OUTER(old_path))) { /* Found an old path that dominates the new one */ return false; } } } } else { /* * Since the pathlist is sorted by total_cost, we can stop looking * once we reach a path with a total_cost larger than the new * path's. */ break; } } return true; } /***************************************************************************** * PATH NODE CREATION ROUTINES *****************************************************************************/ /* * create_seqscan_path * Creates a path corresponding to a sequential scan, returning the * pathnode. */ Path * create_seqscan_path(PlannerInfo *root, RelOptInfo *rel, Relids required_outer) { Path *pathnode = makeNode(Path); pathnode->pathtype = T_SeqScan; pathnode->parent = rel; pathnode->param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->pathkeys = NIL; /* seqscan has unordered result */ cost_seqscan(pathnode, root, rel, pathnode->param_info); return pathnode; } /* * create_samplescan_path * Creates a path node for a sampled table scan. */ Path * create_samplescan_path(PlannerInfo *root, RelOptInfo *rel, Relids required_outer) { Path *pathnode = makeNode(Path); pathnode->pathtype = T_SampleScan; pathnode->parent = rel; pathnode->param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->pathkeys = NIL; /* samplescan has unordered result */ cost_samplescan(pathnode, root, rel, pathnode->param_info); return pathnode; } /* * create_index_path * Creates a path node for an index scan. * * 'index' is a usable index. * 'indexclauses' is a list of RestrictInfo nodes representing clauses * to be used as index qual conditions in the scan. * 'indexclausecols' is an integer list of index column numbers (zero based) * the indexclauses can be used with. * 'indexorderbys' is a list of bare expressions (no RestrictInfos) * to be used as index ordering operators in the scan. * 'indexorderbycols' is an integer list of index column numbers (zero based) * the ordering operators can be used with. * 'pathkeys' describes the ordering of the path. * 'indexscandir' is ForwardScanDirection or BackwardScanDirection * for an ordered index, or NoMovementScanDirection for * an unordered index. * 'indexonly' is true if an index-only scan is wanted. * 'required_outer' is the set of outer relids for a parameterized path. * 'loop_count' is the number of repetitions of the indexscan to factor into * estimates of caching behavior. * * Returns the new path node. */ IndexPath * create_index_path(PlannerInfo *root, IndexOptInfo *index, List *indexclauses, List *indexclausecols, List *indexorderbys, List *indexorderbycols, List *pathkeys, ScanDirection indexscandir, bool indexonly, Relids required_outer, double loop_count) { IndexPath *pathnode = makeNode(IndexPath); RelOptInfo *rel = index->rel; List *indexquals, *indexqualcols; pathnode->path.pathtype = indexonly ? T_IndexOnlyScan : T_IndexScan; pathnode->path.parent = rel; pathnode->path.param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->path.pathkeys = pathkeys; /* Convert clauses to indexquals the executor can handle */ expand_indexqual_conditions(index, indexclauses, indexclausecols, &indexquals, &indexqualcols); /* Fill in the pathnode */ pathnode->indexinfo = index; pathnode->indexclauses = indexclauses; pathnode->indexquals = indexquals; pathnode->indexqualcols = indexqualcols; pathnode->indexorderbys = indexorderbys; pathnode->indexorderbycols = indexorderbycols; pathnode->indexscandir = indexscandir; cost_index(pathnode, root, loop_count); return pathnode; } /* * create_bitmap_heap_path * Creates a path node for a bitmap scan. * * 'bitmapqual' is a tree of IndexPath, BitmapAndPath, and BitmapOrPath nodes. * 'required_outer' is the set of outer relids for a parameterized path. * 'loop_count' is the number of repetitions of the indexscan to factor into * estimates of caching behavior. * * loop_count should match the value used when creating the component * IndexPaths. */ BitmapHeapPath * create_bitmap_heap_path(PlannerInfo *root, RelOptInfo *rel, Path *bitmapqual, Relids required_outer, double loop_count) { BitmapHeapPath *pathnode = makeNode(BitmapHeapPath); pathnode->path.pathtype = T_BitmapHeapScan; pathnode->path.parent = rel; pathnode->path.param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->path.pathkeys = NIL; /* always unordered */ pathnode->bitmapqual = bitmapqual; cost_bitmap_heap_scan(&pathnode->path, root, rel, pathnode->path.param_info, bitmapqual, loop_count); return pathnode; } /* * create_bitmap_and_path * Creates a path node representing a BitmapAnd. */ BitmapAndPath * create_bitmap_and_path(PlannerInfo *root, RelOptInfo *rel, List *bitmapquals) { BitmapAndPath *pathnode = makeNode(BitmapAndPath); pathnode->path.pathtype = T_BitmapAnd; pathnode->path.parent = rel; pathnode->path.param_info = NULL; /* not used in bitmap trees */ pathnode->path.pathkeys = NIL; /* always unordered */ pathnode->bitmapquals = bitmapquals; /* this sets bitmapselectivity as well as the regular cost fields: */ cost_bitmap_and_node(pathnode, root); return pathnode; } /* * create_bitmap_or_path * Creates a path node representing a BitmapOr. */ BitmapOrPath * create_bitmap_or_path(PlannerInfo *root, RelOptInfo *rel, List *bitmapquals) { BitmapOrPath *pathnode = makeNode(BitmapOrPath); pathnode->path.pathtype = T_BitmapOr; pathnode->path.parent = rel; pathnode->path.param_info = NULL; /* not used in bitmap trees */ pathnode->path.pathkeys = NIL; /* always unordered */ pathnode->bitmapquals = bitmapquals; /* this sets bitmapselectivity as well as the regular cost fields: */ cost_bitmap_or_node(pathnode, root); return pathnode; } /* * create_tidscan_path * Creates a path corresponding to a scan by TID, returning the pathnode. */ TidPath * create_tidscan_path(PlannerInfo *root, RelOptInfo *rel, List *tidquals, Relids required_outer) { TidPath *pathnode = makeNode(TidPath); pathnode->path.pathtype = T_TidScan; pathnode->path.parent = rel; pathnode->path.param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->path.pathkeys = NIL; /* always unordered */ pathnode->tidquals = tidquals; cost_tidscan(&pathnode->path, root, rel, tidquals, pathnode->path.param_info); return pathnode; } /* * create_append_path * Creates a path corresponding to an Append plan, returning the * pathnode. * * Note that we must handle subpaths = NIL, representing a dummy access path. */ AppendPath * create_append_path(RelOptInfo *rel, List *subpaths, Relids required_outer) { AppendPath *pathnode = makeNode(AppendPath); ListCell *l; pathnode->path.pathtype = T_Append; pathnode->path.parent = rel; pathnode->path.param_info = get_appendrel_parampathinfo(rel, required_outer); pathnode->path.pathkeys = NIL; /* result is always considered * unsorted */ pathnode->subpaths = subpaths; /* * We don't bother with inventing a cost_append(), but just do it here. * * Compute rows and costs as sums of subplan rows and costs. We charge * nothing extra for the Append itself, which perhaps is too optimistic, * but since it doesn't do any selection or projection, it is a pretty * cheap node. If you change this, see also make_append(). */ pathnode->path.rows = 0; pathnode->path.startup_cost = 0; pathnode->path.total_cost = 0; foreach(l, subpaths) { Path *subpath = (Path *) lfirst(l); pathnode->path.rows += subpath->rows; if (l == list_head(subpaths)) /* first node? */ pathnode->path.startup_cost = subpath->startup_cost; pathnode->path.total_cost += subpath->total_cost; /* All child paths must have same parameterization */ Assert(bms_equal(PATH_REQ_OUTER(subpath), required_outer)); } return pathnode; } /* * create_merge_append_path * Creates a path corresponding to a MergeAppend plan, returning the * pathnode. */ MergeAppendPath * create_merge_append_path(PlannerInfo *root, RelOptInfo *rel, List *subpaths, List *pathkeys, Relids required_outer) { MergeAppendPath *pathnode = makeNode(MergeAppendPath); Cost input_startup_cost; Cost input_total_cost; ListCell *l; pathnode->path.pathtype = T_MergeAppend; pathnode->path.parent = rel; pathnode->path.param_info = get_appendrel_parampathinfo(rel, required_outer); pathnode->path.pathkeys = pathkeys; pathnode->subpaths = subpaths; /* * Apply query-wide LIMIT if known and path is for sole base relation. * (Handling this at this low level is a bit klugy.) */ if (bms_equal(rel->relids, root->all_baserels)) pathnode->limit_tuples = root->limit_tuples; else pathnode->limit_tuples = -1.0; /* * Add up the sizes and costs of the input paths. */ pathnode->path.rows = 0; input_startup_cost = 0; input_total_cost = 0; foreach(l, subpaths) { Path *subpath = (Path *) lfirst(l); pathnode->path.rows += subpath->rows; if (pathkeys_contained_in(pathkeys, subpath->pathkeys)) { /* Subpath is adequately ordered, we won't need to sort it */ input_startup_cost += subpath->startup_cost; input_total_cost += subpath->total_cost; } else { /* We'll need to insert a Sort node, so include cost for that */ Path sort_path; /* dummy for result of cost_sort */ cost_sort(&sort_path, root, pathkeys, subpath->total_cost, subpath->parent->tuples, subpath->parent->width, 0.0, work_mem, pathnode->limit_tuples); input_startup_cost += sort_path.startup_cost; input_total_cost += sort_path.total_cost; } /* All child paths must have same parameterization */ Assert(bms_equal(PATH_REQ_OUTER(subpath), required_outer)); } /* Now we can compute total costs of the MergeAppend */ cost_merge_append(&pathnode->path, root, pathkeys, list_length(subpaths), input_startup_cost, input_total_cost, rel->tuples); return pathnode; } /* * create_result_path * Creates a path representing a Result-and-nothing-else plan. * This is only used for the case of a query with an empty jointree. */ ResultPath * create_result_path(List *quals) { ResultPath *pathnode = makeNode(ResultPath); pathnode->path.pathtype = T_Result; pathnode->path.parent = NULL; pathnode->path.param_info = NULL; /* there are no other rels... */ pathnode->path.pathkeys = NIL; pathnode->quals = quals; /* Hardly worth defining a cost_result() function ... just do it */ pathnode->path.rows = 1; pathnode->path.startup_cost = 0; pathnode->path.total_cost = cpu_tuple_cost; /* * In theory we should include the qual eval cost as well, but at present * that doesn't accomplish much except duplicate work that will be done * again in make_result; since this is only used for degenerate cases, * nothing interesting will be done with the path cost values... */ return pathnode; } /* * create_material_path * Creates a path corresponding to a Material plan, returning the * pathnode. */ MaterialPath * create_material_path(RelOptInfo *rel, Path *subpath) { MaterialPath *pathnode = makeNode(MaterialPath); Assert(subpath->parent == rel); pathnode->path.pathtype = T_Material; pathnode->path.parent = rel; pathnode->path.param_info = subpath->param_info; pathnode->path.pathkeys = subpath->pathkeys; pathnode->subpath = subpath; cost_material(&pathnode->path, subpath->startup_cost, subpath->total_cost, subpath->rows, rel->width); return pathnode; } /* * create_unique_path * Creates a path representing elimination of distinct rows from the * input data. Distinct-ness is defined according to the needs of the * semijoin represented by sjinfo. If it is not possible to identify * how to make the data unique, NULL is returned. * * If used at all, this is likely to be called repeatedly on the same rel; * and the input subpath should always be the same (the cheapest_total path * for the rel). So we cache the result. */ UniquePath * create_unique_path(PlannerInfo *root, RelOptInfo *rel, Path *subpath, SpecialJoinInfo *sjinfo) { UniquePath *pathnode; Path sort_path; /* dummy for result of cost_sort */ Path agg_path; /* dummy for result of cost_agg */ MemoryContext oldcontext; int numCols; /* Caller made a mistake if subpath isn't cheapest_total ... */ Assert(subpath == rel->cheapest_total_path); Assert(subpath->parent == rel); /* ... or if SpecialJoinInfo is the wrong one */ Assert(sjinfo->jointype == JOIN_SEMI); Assert(bms_equal(rel->relids, sjinfo->syn_righthand)); /* If result already cached, return it */ if (rel->cheapest_unique_path) return (UniquePath *) rel->cheapest_unique_path; /* If it's not possible to unique-ify, return NULL */ if (!(sjinfo->semi_can_btree || sjinfo->semi_can_hash)) return NULL; /* * We must ensure path struct and subsidiary data are allocated in main * planning context; otherwise GEQO memory management causes trouble. */ oldcontext = MemoryContextSwitchTo(root->planner_cxt); pathnode = makeNode(UniquePath); pathnode->path.pathtype = T_Unique; pathnode->path.parent = rel; pathnode->path.param_info = subpath->param_info; /* * Assume the output is unsorted, since we don't necessarily have pathkeys * to represent it. (This might get overridden below.) */ pathnode->path.pathkeys = NIL; pathnode->subpath = subpath; pathnode->in_operators = sjinfo->semi_operators; pathnode->uniq_exprs = sjinfo->semi_rhs_exprs; /* * If the input is a relation and it has a unique index that proves the * semi_rhs_exprs are unique, then we don't need to do anything. Note * that relation_has_unique_index_for automatically considers restriction * clauses for the rel, as well. */ if (rel->rtekind == RTE_RELATION && sjinfo->semi_can_btree && relation_has_unique_index_for(root, rel, NIL, sjinfo->semi_rhs_exprs, sjinfo->semi_operators)) { pathnode->umethod = UNIQUE_PATH_NOOP; pathnode->path.rows = rel->rows; pathnode->path.startup_cost = subpath->startup_cost; pathnode->path.total_cost = subpath->total_cost; pathnode->path.pathkeys = subpath->pathkeys; rel->cheapest_unique_path = (Path *) pathnode; MemoryContextSwitchTo(oldcontext); return pathnode; } /* * If the input is a subquery whose output must be unique already, then we * don't need to do anything. The test for uniqueness has to consider * exactly which columns we are extracting; for example "SELECT DISTINCT * x,y" doesn't guarantee that x alone is distinct. So we cannot check for * this optimization unless semi_rhs_exprs consists only of simple Vars * referencing subquery outputs. (Possibly we could do something with * expressions in the subquery outputs, too, but for now keep it simple.) */ if (rel->rtekind == RTE_SUBQUERY) { RangeTblEntry *rte = planner_rt_fetch(rel->relid, root); if (query_supports_distinctness(rte->subquery)) { List *sub_tlist_colnos; sub_tlist_colnos = translate_sub_tlist(sjinfo->semi_rhs_exprs, rel->relid); if (sub_tlist_colnos && query_is_distinct_for(rte->subquery, sub_tlist_colnos, sjinfo->semi_operators)) { pathnode->umethod = UNIQUE_PATH_NOOP; pathnode->path.rows = rel->rows; pathnode->path.startup_cost = subpath->startup_cost; pathnode->path.total_cost = subpath->total_cost; pathnode->path.pathkeys = subpath->pathkeys; rel->cheapest_unique_path = (Path *) pathnode; MemoryContextSwitchTo(oldcontext); return pathnode; } } } /* Estimate number of output rows */ pathnode->path.rows = estimate_num_groups(root, sjinfo->semi_rhs_exprs, rel->rows, NULL); numCols = list_length(sjinfo->semi_rhs_exprs); if (sjinfo->semi_can_btree) { /* * Estimate cost for sort+unique implementation */ cost_sort(&sort_path, root, NIL, subpath->total_cost, rel->rows, rel->width, 0.0, work_mem, -1.0); /* * Charge one cpu_operator_cost per comparison per input tuple. We * assume all columns get compared at most of the tuples. (XXX * probably this is an overestimate.) This should agree with * make_unique. */ sort_path.total_cost += cpu_operator_cost * rel->rows * numCols; } if (sjinfo->semi_can_hash) { /* * Estimate the overhead per hashtable entry at 64 bytes (same as in * planner.c). */ int hashentrysize = rel->width + 64; if (hashentrysize * pathnode->path.rows > work_mem * 1024L) { /* * We should not try to hash. Hack the SpecialJoinInfo to * remember this, in case we come through here again. */ sjinfo->semi_can_hash = false; } else cost_agg(&agg_path, root, AGG_HASHED, NULL, numCols, pathnode->path.rows, subpath->startup_cost, subpath->total_cost, rel->rows); } if (sjinfo->semi_can_btree && sjinfo->semi_can_hash) { if (agg_path.total_cost < sort_path.total_cost) pathnode->umethod = UNIQUE_PATH_HASH; else pathnode->umethod = UNIQUE_PATH_SORT; } else if (sjinfo->semi_can_btree) pathnode->umethod = UNIQUE_PATH_SORT; else if (sjinfo->semi_can_hash) pathnode->umethod = UNIQUE_PATH_HASH; else { /* we can get here only if we abandoned hashing above */ MemoryContextSwitchTo(oldcontext); return NULL; } if (pathnode->umethod == UNIQUE_PATH_HASH) { pathnode->path.startup_cost = agg_path.startup_cost; pathnode->path.total_cost = agg_path.total_cost; } else { pathnode->path.startup_cost = sort_path.startup_cost; pathnode->path.total_cost = sort_path.total_cost; } rel->cheapest_unique_path = (Path *) pathnode; MemoryContextSwitchTo(oldcontext); return pathnode; } /* * create_gather_path * * Creates a path corresponding to a gather scan, returning the * pathnode. */ GatherPath * create_gather_path(PlannerInfo *root, RelOptInfo *rel, Path *subpath, Relids required_outer, int nworkers) { GatherPath *pathnode = makeNode(GatherPath); pathnode->path.pathtype = T_Gather; pathnode->path.parent = rel; pathnode->path.param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->path.pathkeys = NIL; /* Gather has unordered result */ pathnode->subpath = subpath; pathnode->num_workers = nworkers; cost_gather(pathnode, root, rel, pathnode->path.param_info); return pathnode; } /* * translate_sub_tlist - get subquery column numbers represented by tlist * * The given targetlist usually contains only Vars referencing the given relid. * Extract their varattnos (ie, the column numbers of the subquery) and return * as an integer List. * * If any of the tlist items is not a simple Var, we cannot determine whether * the subquery's uniqueness condition (if any) matches ours, so punt and * return NIL. */ static List * translate_sub_tlist(List *tlist, int relid) { List *result = NIL; ListCell *l; foreach(l, tlist) { Var *var = (Var *) lfirst(l); if (!var || !IsA(var, Var) || var->varno != relid) return NIL; /* punt */ result = lappend_int(result, var->varattno); } return result; } /* * create_subqueryscan_path * Creates a path corresponding to a sequential scan of a subquery, * returning the pathnode. */ Path * create_subqueryscan_path(PlannerInfo *root, RelOptInfo *rel, List *pathkeys, Relids required_outer) { Path *pathnode = makeNode(Path); pathnode->pathtype = T_SubqueryScan; pathnode->parent = rel; pathnode->param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->pathkeys = pathkeys; cost_subqueryscan(pathnode, root, rel, pathnode->param_info); return pathnode; } /* * create_functionscan_path * Creates a path corresponding to a sequential scan of a function, * returning the pathnode. */ Path * create_functionscan_path(PlannerInfo *root, RelOptInfo *rel, List *pathkeys, Relids required_outer) { Path *pathnode = makeNode(Path); pathnode->pathtype = T_FunctionScan; pathnode->parent = rel; pathnode->param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->pathkeys = pathkeys; cost_functionscan(pathnode, root, rel, pathnode->param_info); return pathnode; } /* * create_valuesscan_path * Creates a path corresponding to a scan of a VALUES list, * returning the pathnode. */ Path * create_valuesscan_path(PlannerInfo *root, RelOptInfo *rel, Relids required_outer) { Path *pathnode = makeNode(Path); pathnode->pathtype = T_ValuesScan; pathnode->parent = rel; pathnode->param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->pathkeys = NIL; /* result is always unordered */ cost_valuesscan(pathnode, root, rel, pathnode->param_info); return pathnode; } /* * create_ctescan_path * Creates a path corresponding to a scan of a non-self-reference CTE, * returning the pathnode. */ Path * create_ctescan_path(PlannerInfo *root, RelOptInfo *rel, Relids required_outer) { Path *pathnode = makeNode(Path); pathnode->pathtype = T_CteScan; pathnode->parent = rel; pathnode->param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->pathkeys = NIL; /* XXX for now, result is always unordered */ cost_ctescan(pathnode, root, rel, pathnode->param_info); return pathnode; } /* * create_worktablescan_path * Creates a path corresponding to a scan of a self-reference CTE, * returning the pathnode. */ Path * create_worktablescan_path(PlannerInfo *root, RelOptInfo *rel, Relids required_outer) { Path *pathnode = makeNode(Path); pathnode->pathtype = T_WorkTableScan; pathnode->parent = rel; pathnode->param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->pathkeys = NIL; /* result is always unordered */ /* Cost is the same as for a regular CTE scan */ cost_ctescan(pathnode, root, rel, pathnode->param_info); return pathnode; } /* * create_foreignscan_path * Creates a path corresponding to a scan of a foreign table or * a foreign join, returning the pathnode. * * This function is never called from core Postgres; rather, it's expected * to be called by the GetForeignPaths or GetForeignJoinPaths function of * a foreign data wrapper. We make the FDW supply all fields of the path, * since we do not have any way to calculate them in core. */ ForeignPath * create_foreignscan_path(PlannerInfo *root, RelOptInfo *rel, double rows, Cost startup_cost, Cost total_cost, List *pathkeys, Relids required_outer, List *fdw_private) { ForeignPath *pathnode = makeNode(ForeignPath); pathnode->path.pathtype = T_ForeignScan; pathnode->path.parent = rel; pathnode->path.param_info = get_baserel_parampathinfo(root, rel, required_outer); pathnode->path.rows = rows; pathnode->path.startup_cost = startup_cost; pathnode->path.total_cost = total_cost; pathnode->path.pathkeys = pathkeys; pathnode->fdw_private = fdw_private; return pathnode; } /* * calc_nestloop_required_outer * Compute the required_outer set for a nestloop join path * * Note: result must not share storage with either input */ Relids calc_nestloop_required_outer(Path *outer_path, Path *inner_path) { Relids outer_paramrels = PATH_REQ_OUTER(outer_path); Relids inner_paramrels = PATH_REQ_OUTER(inner_path); Relids required_outer; /* inner_path can require rels from outer path, but not vice versa */ Assert(!bms_overlap(outer_paramrels, inner_path->parent->relids)); /* easy case if inner path is not parameterized */ if (!inner_paramrels) return bms_copy(outer_paramrels); /* else, form the union ... */ required_outer = bms_union(outer_paramrels, inner_paramrels); /* ... and remove any mention of now-satisfied outer rels */ required_outer = bms_del_members(required_outer, outer_path->parent->relids); /* maintain invariant that required_outer is exactly NULL if empty */ if (bms_is_empty(required_outer)) { bms_free(required_outer); required_outer = NULL; } return required_outer; } /* * calc_non_nestloop_required_outer * Compute the required_outer set for a merge or hash join path * * Note: result must not share storage with either input */ Relids calc_non_nestloop_required_outer(Path *outer_path, Path *inner_path) { Relids outer_paramrels = PATH_REQ_OUTER(outer_path); Relids inner_paramrels = PATH_REQ_OUTER(inner_path); Relids required_outer; /* neither path can require rels from the other */ Assert(!bms_overlap(outer_paramrels, inner_path->parent->relids)); Assert(!bms_overlap(inner_paramrels, outer_path->parent->relids)); /* form the union ... */ required_outer = bms_union(outer_paramrels, inner_paramrels); /* we do not need an explicit test for empty; bms_union gets it right */ return required_outer; } /* * create_nestloop_path * Creates a pathnode corresponding to a nestloop join between two * relations. * * 'joinrel' is the join relation. * 'jointype' is the type of join required * 'workspace' is the result from initial_cost_nestloop * 'sjinfo' is extra info about the join for selectivity estimation * 'semifactors' contains valid data if jointype is SEMI or ANTI * 'outer_path' is the outer path * 'inner_path' is the inner path * 'restrict_clauses' are the RestrictInfo nodes to apply at the join * 'pathkeys' are the path keys of the new join path * 'required_outer' is the set of required outer rels * * Returns the resulting path node. */ NestPath * create_nestloop_path(PlannerInfo *root, RelOptInfo *joinrel, JoinType jointype, JoinCostWorkspace *workspace, SpecialJoinInfo *sjinfo, SemiAntiJoinFactors *semifactors, Path *outer_path, Path *inner_path, List *restrict_clauses, List *pathkeys, Relids required_outer) { NestPath *pathnode = makeNode(NestPath); Relids inner_req_outer = PATH_REQ_OUTER(inner_path); /* * If the inner path is parameterized by the outer, we must drop any * restrict_clauses that are due to be moved into the inner path. We have * to do this now, rather than postpone the work till createplan time, * because the restrict_clauses list can affect the size and cost * estimates for this path. */ if (bms_overlap(inner_req_outer, outer_path->parent->relids)) { Relids inner_and_outer = bms_union(inner_path->parent->relids, inner_req_outer); List *jclauses = NIL; ListCell *lc; foreach(lc, restrict_clauses) { RestrictInfo *rinfo = (RestrictInfo *) lfirst(lc); if (!join_clause_is_movable_into(rinfo, inner_path->parent->relids, inner_and_outer)) jclauses = lappend(jclauses, rinfo); } restrict_clauses = jclauses; } pathnode->path.pathtype = T_NestLoop; pathnode->path.parent = joinrel; pathnode->path.param_info = get_joinrel_parampathinfo(root, joinrel, outer_path, inner_path, sjinfo, required_outer, &restrict_clauses); pathnode->path.pathkeys = pathkeys; pathnode->jointype = jointype; pathnode->outerjoinpath = outer_path; pathnode->innerjoinpath = inner_path; pathnode->joinrestrictinfo = restrict_clauses; final_cost_nestloop(root, pathnode, workspace, sjinfo, semifactors); return pathnode; } /* * create_mergejoin_path * Creates a pathnode corresponding to a mergejoin join between * two relations * * 'joinrel' is the join relation * 'jointype' is the type of join required * 'workspace' is the result from initial_cost_mergejoin * 'sjinfo' is extra info about the join for selectivity estimation * 'outer_path' is the outer path * 'inner_path' is the inner path * 'restrict_clauses' are the RestrictInfo nodes to apply at the join * 'pathkeys' are the path keys of the new join path * 'required_outer' is the set of required outer rels * 'mergeclauses' are the RestrictInfo nodes to use as merge clauses * (this should be a subset of the restrict_clauses list) * 'outersortkeys' are the sort varkeys for the outer relation * 'innersortkeys' are the sort varkeys for the inner relation */ MergePath * create_mergejoin_path(PlannerInfo *root, RelOptInfo *joinrel, JoinType jointype, JoinCostWorkspace *workspace, SpecialJoinInfo *sjinfo, Path *outer_path, Path *inner_path, List *restrict_clauses, List *pathkeys, Relids required_outer, List *mergeclauses, List *outersortkeys, List *innersortkeys) { MergePath *pathnode = makeNode(MergePath); pathnode->jpath.path.pathtype = T_MergeJoin; pathnode->jpath.path.parent = joinrel; pathnode->jpath.path.param_info = get_joinrel_parampathinfo(root, joinrel, outer_path, inner_path, sjinfo, required_outer, &restrict_clauses); pathnode->jpath.path.pathkeys = pathkeys; pathnode->jpath.jointype = jointype; pathnode->jpath.outerjoinpath = outer_path; pathnode->jpath.innerjoinpath = inner_path; pathnode->jpath.joinrestrictinfo = restrict_clauses; pathnode->path_mergeclauses = mergeclauses; pathnode->outersortkeys = outersortkeys; pathnode->innersortkeys = innersortkeys; /* pathnode->materialize_inner will be set by final_cost_mergejoin */ final_cost_mergejoin(root, pathnode, workspace, sjinfo); return pathnode; } /* * create_hashjoin_path * Creates a pathnode corresponding to a hash join between two relations. * * 'joinrel' is the join relation * 'jointype' is the type of join required * 'workspace' is the result from initial_cost_hashjoin * 'sjinfo' is extra info about the join for selectivity estimation * 'semifactors' contains valid data if jointype is SEMI or ANTI * 'outer_path' is the cheapest outer path * 'inner_path' is the cheapest inner path * 'restrict_clauses' are the RestrictInfo nodes to apply at the join * 'required_outer' is the set of required outer rels * 'hashclauses' are the RestrictInfo nodes to use as hash clauses * (this should be a subset of the restrict_clauses list) */ HashPath * create_hashjoin_path(PlannerInfo *root, RelOptInfo *joinrel, JoinType jointype, JoinCostWorkspace *workspace, SpecialJoinInfo *sjinfo, SemiAntiJoinFactors *semifactors, Path *outer_path, Path *inner_path, List *restrict_clauses, Relids required_outer, List *hashclauses) { HashPath *pathnode = makeNode(HashPath); pathnode->jpath.path.pathtype = T_HashJoin; pathnode->jpath.path.parent = joinrel; pathnode->jpath.path.param_info = get_joinrel_parampathinfo(root, joinrel, outer_path, inner_path, sjinfo, required_outer, &restrict_clauses); /* * A hashjoin never has pathkeys, since its output ordering is * unpredictable due to possible batching. XXX If the inner relation is * small enough, we could instruct the executor that it must not batch, * and then we could assume that the output inherits the outer relation's * ordering, which might save a sort step. However there is considerable * downside if our estimate of the inner relation size is badly off. For * the moment we don't risk it. (Note also that if we wanted to take this * seriously, joinpath.c would have to consider many more paths for the * outer rel than it does now.) */ pathnode->jpath.path.pathkeys = NIL; pathnode->jpath.jointype = jointype; pathnode->jpath.outerjoinpath = outer_path; pathnode->jpath.innerjoinpath = inner_path; pathnode->jpath.joinrestrictinfo = restrict_clauses; pathnode->path_hashclauses = hashclauses; /* final_cost_hashjoin will fill in pathnode->num_batches */ final_cost_hashjoin(root, pathnode, workspace, sjinfo, semifactors); return pathnode; } /* * reparameterize_path * Attempt to modify a Path to have greater parameterization * * We use this to attempt to bring all child paths of an appendrel to the * same parameterization level, ensuring that they all enforce the same set * of join quals (and thus that that parameterization can be attributed to * an append path built from such paths). Currently, only a few path types * are supported here, though more could be added at need. We return NULL * if we can't reparameterize the given path. * * Note: we intentionally do not pass created paths to add_path(); it would * possibly try to delete them on the grounds of being cost-inferior to the * paths they were made from, and we don't want that. Paths made here are * not necessarily of general-purpose usefulness, but they can be useful * as members of an append path. */ Path * reparameterize_path(PlannerInfo *root, Path *path, Relids required_outer, double loop_count) { RelOptInfo *rel = path->parent; /* Can only increase, not decrease, path's parameterization */ if (!bms_is_subset(PATH_REQ_OUTER(path), required_outer)) return NULL; switch (path->pathtype) { case T_SeqScan: return create_seqscan_path(root, rel, required_outer); case T_SampleScan: return (Path *) create_samplescan_path(root, rel, required_outer); case T_IndexScan: case T_IndexOnlyScan: { IndexPath *ipath = (IndexPath *) path; IndexPath *newpath = makeNode(IndexPath); /* * We can't use create_index_path directly, and would not want * to because it would re-compute the indexqual conditions * which is wasted effort. Instead we hack things a bit: * flat-copy the path node, revise its param_info, and redo * the cost estimate. */ memcpy(newpath, ipath, sizeof(IndexPath)); newpath->path.param_info = get_baserel_parampathinfo(root, rel, required_outer); cost_index(newpath, root, loop_count); return (Path *) newpath; } case T_BitmapHeapScan: { BitmapHeapPath *bpath = (BitmapHeapPath *) path; return (Path *) create_bitmap_heap_path(root, rel, bpath->bitmapqual, required_outer, loop_count); } case T_SubqueryScan: return create_subqueryscan_path(root, rel, path->pathkeys, required_outer); default: break; } return NULL; }