PostgreSQL在何处处理 sql查询之四十七
再次上溯：
/*-------------------- * subquery_planner * Invokes the planner on a subquery. We recurse to here for each * sub-SELECT found in the query tree. * * glob is the global state for the current planner run. * parse is the querytree produced by the parser & rewriter. * parent_root is the immediate parent Query's info (NULL at the top level). * hasRecursion is true if this is a recursive WITH query. * tuple_fraction is the fraction of tuples we expect will be retrieved. * tuple_fraction is interpreted as explained for grouping_planner, below. * * If subroot isn't NULL, we pass back the query's final PlannerInfo struct; * among other things this tells the output sort ordering of the plan. * * Basically, this routine does the stuff that should only be done once * per Query object. It then calls grouping_planner. At one time, * grouping_planner could be invoked recursively on the same Query object; * that's not currently true, but we keep the separation between the two * routines anyway, in case we need it again someday. * * subquery_planner will be called recursively to handle sub-Query nodes * found within the query's expressions and rangetable. * * Returns a query plan. *-------------------- */ Plan * subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root, bool hasRecursion, double tuple_fraction, PlannerInfo **subroot) { int num_old_subplans = list_length(glob->subplans); PlannerInfo *root; Plan *plan; List *newHaving; bool hasOuterJoins; ListCell *l; /* Create a PlannerInfo data structure for this subquery */ root = makeNode(PlannerInfo); root->parse = parse; root->glob = glob; root->query_level = parent_root ? parent_root->query_level + 1 : 1; root->parent_root = parent_root; root->plan_params = NIL; root->planner_cxt = CurrentMemoryContext; root->init_plans = NIL; root->cte_plan_ids = NIL; root->eq_classes = NIL; root->append_rel_list = NIL; root->rowMarks = NIL; root->hasInheritedTarget = false; root->hasRecursion = hasRecursion; if (hasRecursion) root->wt_param_id = SS_assign_special_param(root); else root->wt_param_id = -1; root->non_recursive_plan = NULL; /* * If there is a WITH list, process each WITH query and build an initplan * SubPlan structure for it. */ if (parse->cteList) SS_process_ctes(root); /* * Look for ANY and EXISTS SubLinks in WHERE and JOIN/ON clauses, and try * to transform them into joins. Note that this step does not descend * into subqueries; if we pull up any subqueries below, their SubLinks are * processed just before pulling them up. */ if (parse->hasSubLinks) pull_up_sublinks(root); /* * Scan the rangetable for set-returning functions, and inline them if * possible (producing subqueries that might get pulled up next). * Recursion issues here are handled in the same way as for SubLinks. */ inline_set_returning_functions(root); /* * Check to see if any subqueries in the jointree can be merged into this * query. */ parse->jointree = (FromExpr *) pull_up_subqueries(root, (Node *) parse->jointree, NULL, NULL); /* * If this is a simple UNION ALL query, flatten it into an appendrel. We * do this now because it requires applying pull_up_subqueries to the leaf * queries of the UNION ALL, which weren't touched above because they * weren't referenced by the jointree (they will be after we do this). */ if (parse->setOperations) flatten_simple_union_all(root); /* * Detect whether any rangetable entries are RTE_JOIN kind; if not, we can * avoid the expense of doing flatten_join_alias_vars(). Also check for * outer joins --- if none, we can skip reduce_outer_joins(). This must be * done after we have done pull_up_subqueries, of course. */ root->hasJoinRTEs = false; hasOuterJoins = false; foreach(l, parse->rtable) { RangeTblEntry *rte = (RangeTblEntry *) lfirst(l); if (rte->rtekind == RTE_JOIN) { root->hasJoinRTEs = true; if (IS_OUTER_JOIN(rte->jointype)) { hasOuterJoins = true; /* Can quit scanning once we find an outer join */ break; } } } /* * Preprocess RowMark information. We need to do this after subquery * pullup (so that all non-inherited RTEs are present) and before * inheritance expansion (so that the info is available for * expand_inherited_tables to examine and modify). */ preprocess_rowmarks(root); /* * Expand any rangetable entries that are inheritance sets into "append * relations". This can add entries to the rangetable, but they must be * plain base relations not joins, so it's OK (and marginally more * efficient) to do it after checking for join RTEs. We must do it after * pulling up subqueries, else we'd fail to handle inherited tables in * subqueries. */ expand_inherited_tables(root); /* * Set hasHavingQual to remember if HAVING clause is present. Needed * because preprocess_expression will reduce a constant-true condition to * an empty qual list ... but "HAVING TRUE" is not a semantic no-op. */ root->hasHavingQual = (parse->havingQual != NULL); /* Clear this flag; might get set in distribute_qual_to_rels */ root->hasPseudoConstantQuals = false; /* * Do expression preprocessing on targetlist and quals, as well as other * random expressions in the querytree. Note that we do not need to * handle sort/group expressions explicitly, because they are actually * part of the targetlist. */ parse->targetList = (List *) preprocess_expression(root, (Node *) parse->targetList, EXPRKIND_TARGET); parse->returningList = (List *) preprocess_expression(root, (Node *) parse->returningList, EXPRKIND_TARGET); preprocess_qual_conditions(root, (Node *) parse->jointree); parse->havingQual = preprocess_expression(root, parse->havingQual, EXPRKIND_QUAL); foreach(l, parse->windowClause) { WindowClause *wc = (WindowClause *) lfirst(l); /* partitionClause/orderClause are sort/group expressions */ wc->startOffset = preprocess_expression(root, wc->startOffset, EXPRKIND_LIMIT); wc->endOffset = preprocess_expression(root, wc->endOffset, EXPRKIND_LIMIT); } parse->limitOffset = preprocess_expression(root, parse->limitOffset, EXPRKIND_LIMIT); parse->limitCount = preprocess_expression(root, parse->limitCount, EXPRKIND_LIMIT); root->append_rel_list = (List *) preprocess_expression(root, (Node *) root->append_rel_list, EXPRKIND_APPINFO); /* Also need to preprocess expressions for function and values RTEs */ foreach(l, parse->rtable) { RangeTblEntry *rte = (RangeTblEntry *) lfirst(l); if (rte->rtekind == RTE_FUNCTION) rte->funcexpr = preprocess_expression(root, rte->funcexpr, EXPRKIND_RTFUNC); else if (rte->rtekind == RTE_VALUES) rte->values_lists = (List *) preprocess_expression(root, (Node *) rte->values_lists, EXPRKIND_VALUES); } /* * In some cases we may want to transfer a HAVING clause into WHERE. We * cannot do so if the HAVING clause contains aggregates (obviously) or * volatile functions (since a HAVING clause is supposed to be executed * only once per group). Also, it may be that the clause is so expensive * to execute that we're better off doing it only once per group, despite * the loss of selectivity. This is hard to estimate short of doing the * entire planning process twice, so we use a heuristic: clauses * containing subplans are left in HAVING. Otherwise, we move or copy the * HAVING clause into WHERE, in hopes of eliminating tuples before * aggregation instead of after. * * If the query has explicit grouping then we can simply move such a * clause into WHERE; any group that fails the clause will not be in the * output because none of its tuples will reach the grouping or * aggregation stage. Otherwise we must have a degenerate (variable-free) * HAVING clause, which we put in WHERE so that query_planner() can use it * in a gating Result node, but also keep in HAVING to ensure that we * don't emit a bogus aggregated row. (This could be done better, but it * seems not worth optimizing.) * * Note that both havingQual and parse->jointree->quals are in * implicitly-ANDed-list form at this point, even though they are declared * as Node *. */ newHaving = NIL; foreach(l, (List *) parse->havingQual) { Node *havingclause = (Node *) lfirst(l); if (contain_agg_clause(havingclause) || contain_volatile_functions(havingclause) || contain_subplans(havingclause)) { /* keep it in HAVING */ newHaving = lappend(newHaving, havingclause); } else if (parse->groupClause) { /* move it to WHERE */ parse->jointree->quals = (Node *) lappend((List *) parse->jointree->quals, havingclause); } else { /* put a copy in WHERE, keep it in HAVING */ parse->jointree->quals = (Node *) lappend((List *) parse->jointree->quals, copyObject(havingclause)); newHaving = lappend(newHaving, havingclause); } } parse->havingQual = (Node *) newHaving; /* * If we have any outer joins, try to reduce them to plain inner joins. * This step is most easily done after we've done expression * preprocessing. */ if (hasOuterJoins) reduce_outer_joins(root); /* * Do the main planning. If we have an inherited target relation, that * needs special processing, else go straight to grouping_planner. */ if (parse->resultRelation && rt_fetch(parse->resultRelation, parse->rtable)->inh) plan = inheritance_planner(root); else { plan = grouping_planner(root, tuple_fraction); /* If it's not SELECT, we need a ModifyTable node */ if (parse->commandType != CMD_SELECT) { List *returningLists; List *rowMarks; /* * Set up the RETURNING list-of-lists, if needed. */ if (parse->returningList) returningLists = list_make1(parse->returningList); else returningLists = NIL; /* * If there was a FOR UPDATE/SHARE clause, the LockRows node will * have dealt with fetching non-locked marked rows, else we need * to have ModifyTable do that. */ if (parse->rowMarks) rowMarks = NIL; else rowMarks = root->rowMarks; plan = (Plan *) make_modifytable(parse->commandType, parse->canSetTag, list_make1_int(parse->resultRelation), list_make1(plan), returningLists, rowMarks, SS_assign_special_param(root)); } } /* * If any subplans were generated, or if there are any parameters to worry * about, build initPlan list and extParam/allParam sets for plan nodes, * and attach the initPlans to the top plan node. */ if (list_length(glob->subplans) != num_old_subplans || root->glob->nParamExec > 0) SS_finalize_plan(root, plan, true); /* Return internal info if caller wants it */ if (subroot) *subroot = root; return plan; }
上溯
PlannedStmt * standard_planner(Query *parse, int cursorOptions, ParamListInfo boundParams) { PlannedStmt *result; PlannerGlobal *glob; double tuple_fraction; PlannerInfo *root; Plan *top_plan; ListCell *lp, *lr; /* Cursor options may come from caller or from DECLARE CURSOR stmt */ if (parse->utilityStmt && IsA(parse->utilityStmt, DeclareCursorStmt)) cursorOptions |= ((DeclareCursorStmt *) parse->utilityStmt)->options; /* * Set up global state for this planner invocation. This data is needed * across all levels of sub-Query that might exist in the given command, * so we keep it in a separate struct that's linked to by each per-Query * PlannerInfo. */ glob = makeNode(PlannerGlobal); glob->boundParams = boundParams; glob->subplans = NIL; glob->subroots = NIL; glob->rewindPlanIDs = NULL; glob->finalrtable = NIL; glob->finalrowmarks = NIL; glob->resultRelations = NIL; glob->relationOids = NIL; glob->invalItems = NIL; glob->nParamExec = 0; glob->lastPHId = 0; glob->lastRowMarkId = 0; glob->transientPlan = false; /* Determine what fraction of the plan is likely to be scanned */ if (cursorOptions & CURSOR_OPT_FAST_PLAN) { /* * We have no real idea how many tuples the user will ultimately FETCH * from a cursor, but it is often the case that he doesn't want 'em * all, or would prefer a fast-start plan anyway so that he can * process some of the tuples sooner. Use a GUC parameter to decide * what fraction to optimize for. */ tuple_fraction = cursor_tuple_fraction; /* * We document cursor_tuple_fraction as simply being a fraction, which * means the edge cases 0 and 1 have to be treated specially here. We * convert 1 to 0 ("all the tuples") and 0 to a very small fraction. */ if (tuple_fraction >= 1.0) tuple_fraction = 0.0; else if (tuple_fraction <= 0.0) tuple_fraction = 1e-10; } else { /* Default assumption is we need all the tuples */ tuple_fraction = 0.0; } /* primary planning entry point (may recurse for subqueries) */ top_plan = subquery_planner(glob, parse, NULL, false, tuple_fraction, &root); /* * If creating a plan for a scrollable cursor, make sure it can run * backwards on demand. Add a Material node at the top at need. */ if (cursorOptions & CURSOR_OPT_SCROLL) { if (!ExecSupportsBackwardScan(top_plan)) top_plan = materialize_finished_plan(top_plan); } /* final cleanup of the plan */ Assert(glob->finalrtable == NIL); Assert(glob->finalrowmarks == NIL); Assert(glob->resultRelations == NIL); top_plan = set_plan_references(root, top_plan); /* ... and the subplans (both regular subplans and initplans) */ Assert(list_length(glob->subplans) == list_length(glob->subroots)); forboth(lp, glob->subplans, lr, glob->subroots) { Plan *subplan = (Plan *) lfirst(lp); PlannerInfo *subroot = (PlannerInfo *) lfirst(lr); lfirst(lp) = set_plan_references(subroot, subplan); } /* build the PlannedStmt result */ result = makeNode(PlannedStmt); result->commandType = parse->commandType; result->queryId = parse->queryId; result->hasReturning = (parse->returningList != NIL); result->hasModifyingCTE = parse->hasModifyingCTE; result->canSetTag = parse->canSetTag; result->transientPlan = glob->transientPlan; result->planTree = top_plan; result->rtable = glob->finalrtable; result->resultRelations = glob->resultRelations; result->utilityStmt = parse->utilityStmt; result->subplans = glob->subplans; result->rewindPlanIDs = glob->rewindPlanIDs; result->rowMarks = glob->finalrowmarks; result->relationOids = glob->relationOids; result->invalItems = glob->invalItems; result->nParamExec = glob->nParamExec; return result; }
再上溯：
/***************************************************************************** * * Query optimizer entry point * * To support loadable plugins that monitor or modify planner behavior, * we provide a hook variable that lets a plugin get control before and * after the standard planning process. The plugin would normally call * standard_planner(). * * Note to plugin authors: standard_planner() scribbles on its Query input, * so you'd better copy that data structure if you want to plan more than once. * *****************************************************************************/ PlannedStmt * planner(Query *parse, int cursorOptions, ParamListInfo boundParams) { PlannedStmt *result; if (planner_hook) result = (*planner_hook) (parse, cursorOptions, boundParams); else result = standard_planner(parse, cursorOptions, boundParams); return result; }
对 standard_planner 分析：
/* * Query - * Parse analysis turns all statements into a Query tree * for further processing by the rewriter and planner. * * Utility statements (i.e. non-optimizable statements) have the * utilityStmt field set, and the Query itself is mostly dummy. * DECLARE CURSOR is a special case: it is represented like a SELECT, * but the original DeclareCursorStmt is stored in utilityStmt. * * Planning converts a Query tree into a Plan tree headed by a PlannedStmt * node --- the Query structure is not used by the executor. */ typedef struct Query { NodeTag type; CmdType commandType; /* select|insert|update|delete|utility */ QuerySource querySource; /* where did I come from? */ uint32 queryId; /* query identifier (can be set by plugins) */ bool canSetTag; /* do I set the command result tag? */ Node *utilityStmt; /* non-null if this is DECLARE CURSOR or a * non-optimizable statement */ int resultRelation; /* rtable index of target relation for * INSERT/UPDATE/DELETE; 0 for SELECT */ bool hasAggs; /* has aggregates in tlist or havingQual */ bool hasWindowFuncs; /* has window functions in tlist */ bool hasSubLinks; /* has subquery SubLink */ bool hasDistinctOn; /* distinctClause is from DISTINCT ON */ bool hasRecursive; /* WITH RECURSIVE was specified */ bool hasModifyingCTE; /* has INSERT/UPDATE/DELETE in WITH */ bool hasForUpdate; /* FOR UPDATE or FOR SHARE was specified */ List *cteList; /* WITH list (of CommonTableExpr's) */ List *rtable; /* list of range table entries */ FromExpr *jointree; /* table join tree (FROM and WHERE clauses) */ List *targetList; /* target list (of TargetEntry) */ List *returningList; /* return-values list (of TargetEntry) */ List *groupClause; /* a list of SortGroupClause's */ Node *havingQual; /* qualifications applied to groups */ List *windowClause; /* a list of WindowClause's */ List *distinctClause; /* a list of SortGroupClause's */ List *sortClause; /* a list of SortGroupClause's */ Node *limitOffset; /* # of result tuples to skip (int8 expr) */ Node *limitCount; /* # of result tuples to return (int8 expr) */ List *rowMarks; /* a list of RowMarkClause's */ Node *setOperations; /* set-operation tree if this is top level of * a UNION/INTERSECT/EXCEPT query */ List *constraintDeps; /* a list of pg_constraint OIDs that the query * depends on to be semantically valid */ } Query;
一点一点地分析吧：
if (parse->utilityStmt && IsA(parse->utilityStmt, DeclareCursorStmt)) cursorOptions |= ((DeclareCursorStmt *) parse->utilityStmt)->options;
parse->utilityStmt 是false，所以不成立。
再接着：
/* * Set up global state for this planner invocation. This data is needed * across all levels of sub-Query that might exist in the given command, * so we keep it in a separate struct that's linked to by each per-Query * PlannerInfo. */ glob = makeNode(PlannerGlobal); glob->boundParams = boundParams; glob->subplans = NIL; glob->subroots = NIL; glob->rewindPlanIDs = NULL; glob->finalrtable = NIL; glob->finalrowmarks = NIL; glob->resultRelations = NIL; glob->relationOids = NIL; glob->invalItems = NIL; glob->nParamExec = 0; glob->lastPHId = 0; glob->lastRowMarkId = 0; glob->transientPlan = false;
这一段只是设置了一个初始化好的 PlannerGlobal 指针。
#define newNode(size, tag) \ ( \ AssertMacro((size) >= sizeof(Node)), /* need the tag, at least */ \ newNodeMacroHolder = (Node *) palloc0fast(size), \ newNodeMacroHolder->type = (tag), \ newNodeMacroHolder \ ) #endif /* __GNUC__ */ #define makeNode(_type_) ((_type_ *) newNode(sizeof(_type_),T_##_type_))
接下来，对于我的SQL : select id, val from tst04 where id>1 ，
cursorOPtion 是false，所以不成立，变成：
if (cursorOptions & CURSOR_OPT_FAST_PLAN) { ... } else { /* Default assumption is we need all the tuples */ tuple_fraction = 0.0; }
接下来：
/* primary planning entry point (may recurse for subqueries) */ top_plan = subquery_planner(glob, parse, NULL, false, tuple_fraction, &root);
