Tom Lane b14953932d Revise FDW planning API, again.
Further reflection shows that a single callback isn't very workable if we
desire to let FDWs generate multiple Paths, because that forces the FDW to
do all work necessary to generate a valid Plan node for each Path.  Instead
split the former PlanForeignScan API into three steps: GetForeignRelSize,
GetForeignPaths, GetForeignPlan.  We had already bit the bullet of breaking
the 9.1 FDW API for 9.2, so this shouldn't cause very much additional pain,
and it's substantially more flexible for complex FDWs.

Add an fdw_private field to RelOptInfo so that the new functions can save
state there rather than possibly having to recalculate information two or
three times.

In addition, we'd not thought through what would be needed to allow an FDW
to set up subexpressions of its choice for runtime execution.  We could
treat ForeignScan.fdw_private as an executable expression but that seems
likely to break existing FDWs unnecessarily (in particular, it would
restrict the set of node types allowable in fdw_private to those supported
by expression_tree_walker).  Instead, invent a separate field fdw_exprs
which will receive the postprocessing appropriate for expression trees.
(One field is enough since it can be a list of expressions; also, we assume
the corresponding expression state tree(s) will be held within fdw_state,
so we don't need to add anything to ForeignScanState.)

Per review of Hanada Shigeru's pgsql_fdw patch.  We may need to tweak this
further as we continue to work on that patch, but to me it feels a lot
closer to being right now.
2012-03-09 12:49:25 -05:00

670 lines
19 KiB
C

/*-------------------------------------------------------------------------
*
* relnode.c
* Relation-node lookup/construction routines
*
* Portions Copyright (c) 1996-2012, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/optimizer/util/relnode.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "optimizer/cost.h"
#include "optimizer/pathnode.h"
#include "optimizer/paths.h"
#include "optimizer/placeholder.h"
#include "optimizer/plancat.h"
#include "utils/hsearch.h"
typedef struct JoinHashEntry
{
Relids join_relids; /* hash key --- MUST BE FIRST */
RelOptInfo *join_rel;
} JoinHashEntry;
static void build_joinrel_tlist(PlannerInfo *root, RelOptInfo *joinrel,
RelOptInfo *input_rel);
static List *build_joinrel_restrictlist(PlannerInfo *root,
RelOptInfo *joinrel,
RelOptInfo *outer_rel,
RelOptInfo *inner_rel);
static void build_joinrel_joinlist(RelOptInfo *joinrel,
RelOptInfo *outer_rel,
RelOptInfo *inner_rel);
static List *subbuild_joinrel_restrictlist(RelOptInfo *joinrel,
List *joininfo_list,
List *new_restrictlist);
static List *subbuild_joinrel_joinlist(RelOptInfo *joinrel,
List *joininfo_list,
List *new_joininfo);
/*
* setup_simple_rel_arrays
* Prepare the arrays we use for quickly accessing base relations.
*/
void
setup_simple_rel_arrays(PlannerInfo *root)
{
Index rti;
ListCell *lc;
/* Arrays are accessed using RT indexes (1..N) */
root->simple_rel_array_size = list_length(root->parse->rtable) + 1;
/* simple_rel_array is initialized to all NULLs */
root->simple_rel_array = (RelOptInfo **)
palloc0(root->simple_rel_array_size * sizeof(RelOptInfo *));
/* simple_rte_array is an array equivalent of the rtable list */
root->simple_rte_array = (RangeTblEntry **)
palloc0(root->simple_rel_array_size * sizeof(RangeTblEntry *));
rti = 1;
foreach(lc, root->parse->rtable)
{
RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
root->simple_rte_array[rti++] = rte;
}
}
/*
* build_simple_rel
* Construct a new RelOptInfo for a base relation or 'other' relation.
*/
RelOptInfo *
build_simple_rel(PlannerInfo *root, int relid, RelOptKind reloptkind)
{
RelOptInfo *rel;
RangeTblEntry *rte;
/* Rel should not exist already */
Assert(relid > 0 && relid < root->simple_rel_array_size);
if (root->simple_rel_array[relid] != NULL)
elog(ERROR, "rel %d already exists", relid);
/* Fetch RTE for relation */
rte = root->simple_rte_array[relid];
Assert(rte != NULL);
rel = makeNode(RelOptInfo);
rel->reloptkind = reloptkind;
rel->relids = bms_make_singleton(relid);
rel->rows = 0;
rel->width = 0;
rel->reltargetlist = NIL;
rel->pathlist = NIL;
rel->cheapest_startup_path = NULL;
rel->cheapest_total_path = NULL;
rel->cheapest_unique_path = NULL;
rel->cheapest_parameterized_paths = NIL;
rel->relid = relid;
rel->rtekind = rte->rtekind;
/* min_attr, max_attr, attr_needed, attr_widths are set below */
rel->indexlist = NIL;
rel->pages = 0;
rel->tuples = 0;
rel->allvisfrac = 0;
rel->subplan = NULL;
rel->subroot = NULL;
rel->fdwroutine = NULL;
rel->fdw_private = NULL;
rel->baserestrictinfo = NIL;
rel->baserestrictcost.startup = 0;
rel->baserestrictcost.per_tuple = 0;
rel->joininfo = NIL;
rel->has_eclass_joins = false;
/* Check type of rtable entry */
switch (rte->rtekind)
{
case RTE_RELATION:
/* Table --- retrieve statistics from the system catalogs */
get_relation_info(root, rte->relid, rte->inh, rel);
break;
case RTE_SUBQUERY:
case RTE_FUNCTION:
case RTE_VALUES:
case RTE_CTE:
/*
* Subquery, function, or values list --- set up attr range and
* arrays
*
* Note: 0 is included in range to support whole-row Vars
*/
rel->min_attr = 0;
rel->max_attr = list_length(rte->eref->colnames);
rel->attr_needed = (Relids *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(Relids));
rel->attr_widths = (int32 *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(int32));
break;
default:
elog(ERROR, "unrecognized RTE kind: %d",
(int) rte->rtekind);
break;
}
/* Save the finished struct in the query's simple_rel_array */
root->simple_rel_array[relid] = rel;
/*
* If this rel is an appendrel parent, recurse to build "other rel"
* RelOptInfos for its children. They are "other rels" because they are
* not in the main join tree, but we will need RelOptInfos to plan access
* to them.
*/
if (rte->inh)
{
ListCell *l;
foreach(l, root->append_rel_list)
{
AppendRelInfo *appinfo = (AppendRelInfo *) lfirst(l);
/* append_rel_list contains all append rels; ignore others */
if (appinfo->parent_relid != relid)
continue;
(void) build_simple_rel(root, appinfo->child_relid,
RELOPT_OTHER_MEMBER_REL);
}
}
return rel;
}
/*
* find_base_rel
* Find a base or other relation entry, which must already exist.
*/
RelOptInfo *
find_base_rel(PlannerInfo *root, int relid)
{
RelOptInfo *rel;
Assert(relid > 0);
if (relid < root->simple_rel_array_size)
{
rel = root->simple_rel_array[relid];
if (rel)
return rel;
}
elog(ERROR, "no relation entry for relid %d", relid);
return NULL; /* keep compiler quiet */
}
/*
* build_join_rel_hash
* Construct the auxiliary hash table for join relations.
*/
static void
build_join_rel_hash(PlannerInfo *root)
{
HTAB *hashtab;
HASHCTL hash_ctl;
ListCell *l;
/* Create the hash table */
MemSet(&hash_ctl, 0, sizeof(hash_ctl));
hash_ctl.keysize = sizeof(Relids);
hash_ctl.entrysize = sizeof(JoinHashEntry);
hash_ctl.hash = bitmap_hash;
hash_ctl.match = bitmap_match;
hash_ctl.hcxt = CurrentMemoryContext;
hashtab = hash_create("JoinRelHashTable",
256L,
&hash_ctl,
HASH_ELEM | HASH_FUNCTION | HASH_COMPARE | HASH_CONTEXT);
/* Insert all the already-existing joinrels */
foreach(l, root->join_rel_list)
{
RelOptInfo *rel = (RelOptInfo *) lfirst(l);
JoinHashEntry *hentry;
bool found;
hentry = (JoinHashEntry *) hash_search(hashtab,
&(rel->relids),
HASH_ENTER,
&found);
Assert(!found);
hentry->join_rel = rel;
}
root->join_rel_hash = hashtab;
}
/*
* find_join_rel
* Returns relation entry corresponding to 'relids' (a set of RT indexes),
* or NULL if none exists. This is for join relations.
*/
RelOptInfo *
find_join_rel(PlannerInfo *root, Relids relids)
{
/*
* Switch to using hash lookup when list grows "too long". The threshold
* is arbitrary and is known only here.
*/
if (!root->join_rel_hash && list_length(root->join_rel_list) > 32)
build_join_rel_hash(root);
/*
* Use either hashtable lookup or linear search, as appropriate.
*
* Note: the seemingly redundant hashkey variable is used to avoid taking
* the address of relids; unless the compiler is exceedingly smart, doing
* so would force relids out of a register and thus probably slow down the
* list-search case.
*/
if (root->join_rel_hash)
{
Relids hashkey = relids;
JoinHashEntry *hentry;
hentry = (JoinHashEntry *) hash_search(root->join_rel_hash,
&hashkey,
HASH_FIND,
NULL);
if (hentry)
return hentry->join_rel;
}
else
{
ListCell *l;
foreach(l, root->join_rel_list)
{
RelOptInfo *rel = (RelOptInfo *) lfirst(l);
if (bms_equal(rel->relids, relids))
return rel;
}
}
return NULL;
}
/*
* build_join_rel
* Returns relation entry corresponding to the union of two given rels,
* creating a new relation entry if none already exists.
*
* 'joinrelids' is the Relids set that uniquely identifies the join
* 'outer_rel' and 'inner_rel' are relation nodes for the relations to be
* joined
* 'sjinfo': join context info
* 'restrictlist_ptr': result variable. If not NULL, *restrictlist_ptr
* receives the list of RestrictInfo nodes that apply to this
* particular pair of joinable relations.
*
* restrictlist_ptr makes the routine's API a little grotty, but it saves
* duplicated calculation of the restrictlist...
*/
RelOptInfo *
build_join_rel(PlannerInfo *root,
Relids joinrelids,
RelOptInfo *outer_rel,
RelOptInfo *inner_rel,
SpecialJoinInfo *sjinfo,
List **restrictlist_ptr)
{
RelOptInfo *joinrel;
List *restrictlist;
/*
* See if we already have a joinrel for this set of base rels.
*/
joinrel = find_join_rel(root, joinrelids);
if (joinrel)
{
/*
* Yes, so we only need to figure the restrictlist for this particular
* pair of component relations.
*/
if (restrictlist_ptr)
*restrictlist_ptr = build_joinrel_restrictlist(root,
joinrel,
outer_rel,
inner_rel);
return joinrel;
}
/*
* Nope, so make one.
*/
joinrel = makeNode(RelOptInfo);
joinrel->reloptkind = RELOPT_JOINREL;
joinrel->relids = bms_copy(joinrelids);
joinrel->rows = 0;
joinrel->width = 0;
joinrel->reltargetlist = NIL;
joinrel->pathlist = NIL;
joinrel->cheapest_startup_path = NULL;
joinrel->cheapest_total_path = NULL;
joinrel->cheapest_unique_path = NULL;
joinrel->cheapest_parameterized_paths = NIL;
joinrel->relid = 0; /* indicates not a baserel */
joinrel->rtekind = RTE_JOIN;
joinrel->min_attr = 0;
joinrel->max_attr = 0;
joinrel->attr_needed = NULL;
joinrel->attr_widths = NULL;
joinrel->indexlist = NIL;
joinrel->pages = 0;
joinrel->tuples = 0;
joinrel->allvisfrac = 0;
joinrel->subplan = NULL;
joinrel->subroot = NULL;
joinrel->fdwroutine = NULL;
joinrel->fdw_private = NULL;
joinrel->baserestrictinfo = NIL;
joinrel->baserestrictcost.startup = 0;
joinrel->baserestrictcost.per_tuple = 0;
joinrel->joininfo = NIL;
joinrel->has_eclass_joins = false;
/*
* Create a new tlist containing just the vars that need to be output from
* this join (ie, are needed for higher joinclauses or final output).
*
* NOTE: the tlist order for a join rel will depend on which pair of outer
* and inner rels we first try to build it from. But the contents should
* be the same regardless.
*/
build_joinrel_tlist(root, joinrel, outer_rel);
build_joinrel_tlist(root, joinrel, inner_rel);
add_placeholders_to_joinrel(root, joinrel);
/*
* Construct restrict and join clause lists for the new joinrel. (The
* caller might or might not need the restrictlist, but I need it anyway
* for set_joinrel_size_estimates().)
*/
restrictlist = build_joinrel_restrictlist(root, joinrel,
outer_rel, inner_rel);
if (restrictlist_ptr)
*restrictlist_ptr = restrictlist;
build_joinrel_joinlist(joinrel, outer_rel, inner_rel);
/*
* This is also the right place to check whether the joinrel has any
* pending EquivalenceClass joins.
*/
joinrel->has_eclass_joins = has_relevant_eclass_joinclause(root, joinrel);
/*
* Set estimates of the joinrel's size.
*/
set_joinrel_size_estimates(root, joinrel, outer_rel, inner_rel,
sjinfo, restrictlist);
/*
* Add the joinrel to the query's joinrel list, and store it into the
* auxiliary hashtable if there is one. NB: GEQO requires us to append
* the new joinrel to the end of the list!
*/
root->join_rel_list = lappend(root->join_rel_list, joinrel);
if (root->join_rel_hash)
{
JoinHashEntry *hentry;
bool found;
hentry = (JoinHashEntry *) hash_search(root->join_rel_hash,
&(joinrel->relids),
HASH_ENTER,
&found);
Assert(!found);
hentry->join_rel = joinrel;
}
/*
* Also, if dynamic-programming join search is active, add the new joinrel
* to the appropriate sublist. Note: you might think the Assert on number
* of members should be for equality, but some of the level 1 rels might
* have been joinrels already, so we can only assert <=.
*/
if (root->join_rel_level)
{
Assert(root->join_cur_level > 0);
Assert(root->join_cur_level <= bms_num_members(joinrel->relids));
root->join_rel_level[root->join_cur_level] =
lappend(root->join_rel_level[root->join_cur_level], joinrel);
}
return joinrel;
}
/*
* build_joinrel_tlist
* Builds a join relation's target list from an input relation.
* (This is invoked twice to handle the two input relations.)
*
* The join's targetlist includes all Vars of its member relations that
* will still be needed above the join. This subroutine adds all such
* Vars from the specified input rel's tlist to the join rel's tlist.
*
* We also compute the expected width of the join's output, making use
* of data that was cached at the baserel level by set_rel_width().
*/
static void
build_joinrel_tlist(PlannerInfo *root, RelOptInfo *joinrel,
RelOptInfo *input_rel)
{
Relids relids = joinrel->relids;
ListCell *vars;
foreach(vars, input_rel->reltargetlist)
{
Node *origvar = (Node *) lfirst(vars);
Var *var;
RelOptInfo *baserel;
int ndx;
/*
* Ignore PlaceHolderVars in the input tlists; we'll make our own
* decisions about whether to copy them.
*/
if (IsA(origvar, PlaceHolderVar))
continue;
/*
* We can't run into any child RowExprs here, but we could find a
* whole-row Var with a ConvertRowtypeExpr atop it.
*/
var = (Var *) origvar;
while (!IsA(var, Var))
{
if (IsA(var, ConvertRowtypeExpr))
var = (Var *) ((ConvertRowtypeExpr *) var)->arg;
else
elog(ERROR, "unexpected node type in reltargetlist: %d",
(int) nodeTag(var));
}
/* Get the Var's original base rel */
baserel = find_base_rel(root, var->varno);
/* Is it still needed above this joinrel? */
ndx = var->varattno - baserel->min_attr;
if (bms_nonempty_difference(baserel->attr_needed[ndx], relids))
{
/* Yup, add it to the output */
joinrel->reltargetlist = lappend(joinrel->reltargetlist, origvar);
joinrel->width += baserel->attr_widths[ndx];
}
}
}
/*
* build_joinrel_restrictlist
* build_joinrel_joinlist
* These routines build lists of restriction and join clauses for a
* join relation from the joininfo lists of the relations it joins.
*
* These routines are separate because the restriction list must be
* built afresh for each pair of input sub-relations we consider, whereas
* the join list need only be computed once for any join RelOptInfo.
* The join list is fully determined by the set of rels making up the
* joinrel, so we should get the same results (up to ordering) from any
* candidate pair of sub-relations. But the restriction list is whatever
* is not handled in the sub-relations, so it depends on which
* sub-relations are considered.
*
* If a join clause from an input relation refers to base rels still not
* present in the joinrel, then it is still a join clause for the joinrel;
* we put it into the joininfo list for the joinrel. Otherwise,
* the clause is now a restrict clause for the joined relation, and we
* return it to the caller of build_joinrel_restrictlist() to be stored in
* join paths made from this pair of sub-relations. (It will not need to
* be considered further up the join tree.)
*
* In many case we will find the same RestrictInfos in both input
* relations' joinlists, so be careful to eliminate duplicates.
* Pointer equality should be a sufficient test for dups, since all
* the various joinlist entries ultimately refer to RestrictInfos
* pushed into them by distribute_restrictinfo_to_rels().
*
* 'joinrel' is a join relation node
* 'outer_rel' and 'inner_rel' are a pair of relations that can be joined
* to form joinrel.
*
* build_joinrel_restrictlist() returns a list of relevant restrictinfos,
* whereas build_joinrel_joinlist() stores its results in the joinrel's
* joininfo list. One or the other must accept each given clause!
*
* NB: Formerly, we made deep(!) copies of each input RestrictInfo to pass
* up to the join relation. I believe this is no longer necessary, because
* RestrictInfo nodes are no longer context-dependent. Instead, just include
* the original nodes in the lists made for the join relation.
*/
static List *
build_joinrel_restrictlist(PlannerInfo *root,
RelOptInfo *joinrel,
RelOptInfo *outer_rel,
RelOptInfo *inner_rel)
{
List *result;
/*
* Collect all the clauses that syntactically belong at this level,
* eliminating any duplicates (important since we will see many of the
* same clauses arriving from both input relations).
*/
result = subbuild_joinrel_restrictlist(joinrel, outer_rel->joininfo, NIL);
result = subbuild_joinrel_restrictlist(joinrel, inner_rel->joininfo, result);
/*
* Add on any clauses derived from EquivalenceClasses. These cannot be
* redundant with the clauses in the joininfo lists, so don't bother
* checking.
*/
result = list_concat(result,
generate_join_implied_equalities(root,
joinrel,
outer_rel,
inner_rel));
return result;
}
static void
build_joinrel_joinlist(RelOptInfo *joinrel,
RelOptInfo *outer_rel,
RelOptInfo *inner_rel)
{
List *result;
/*
* Collect all the clauses that syntactically belong above this level,
* eliminating any duplicates (important since we will see many of the
* same clauses arriving from both input relations).
*/
result = subbuild_joinrel_joinlist(joinrel, outer_rel->joininfo, NIL);
result = subbuild_joinrel_joinlist(joinrel, inner_rel->joininfo, result);
joinrel->joininfo = result;
}
static List *
subbuild_joinrel_restrictlist(RelOptInfo *joinrel,
List *joininfo_list,
List *new_restrictlist)
{
ListCell *l;
foreach(l, joininfo_list)
{
RestrictInfo *rinfo = (RestrictInfo *) lfirst(l);
if (bms_is_subset(rinfo->required_relids, joinrel->relids))
{
/*
* This clause becomes a restriction clause for the joinrel, since
* it refers to no outside rels. Add it to the list, being
* careful to eliminate duplicates. (Since RestrictInfo nodes in
* different joinlists will have been multiply-linked rather than
* copied, pointer equality should be a sufficient test.)
*/
new_restrictlist = list_append_unique_ptr(new_restrictlist, rinfo);
}
else
{
/*
* This clause is still a join clause at this level, so we ignore
* it in this routine.
*/
}
}
return new_restrictlist;
}
static List *
subbuild_joinrel_joinlist(RelOptInfo *joinrel,
List *joininfo_list,
List *new_joininfo)
{
ListCell *l;
foreach(l, joininfo_list)
{
RestrictInfo *rinfo = (RestrictInfo *) lfirst(l);
if (bms_is_subset(rinfo->required_relids, joinrel->relids))
{
/*
* This clause becomes a restriction clause for the joinrel, since
* it refers to no outside rels. So we can ignore it in this
* routine.
*/
}
else
{
/*
* This clause is still a join clause at this level, so add it to
* the new joininfo list, being careful to eliminate duplicates.
* (Since RestrictInfo nodes in different joinlists will have been
* multiply-linked rather than copied, pointer equality should be
* a sufficient test.)
*/
new_joininfo = list_append_unique_ptr(new_joininfo, rinfo);
}
}
return new_joininfo;
}