database/openGauss-server
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

!2676 支持or表达式的谓词提取下推

Browse Source 
Merge pull request !2676 from 陈志凯/master
This commit is contained in:
opengauss-bot
2022-12-23 06:47:32 +00:00
committed by Gitee
parent 95f017db04 b15c245a18
commit c4ea9be231
15 changed files with 493 additions and 207 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/common/backend/utils/misc/guc/guc_sql.cpp
View File

@ -314,6 +314,7 @@ static const struct config_enum_entry sql_beta_options[] = {
{"predpush_same_level", PREDPUSH_SAME_LEVEL, false},
{"partition_fdw_on", PARTITION_FDW_ON, false},
{"disable_bitmap_cost_with_lossy_pages", DISABLE_BITMAP_COST_WITH_LOSSY_PAGES, false},
{"extract_pushdown_or_clause", EXTRACT_PUSHDOWN_OR_CLAUSE, false},
{NULL, 0, false}
};
@ -3971,4 +3972,4 @@ static void assign_sql_ignore_strategy(const char* newval, void* extra) {
}
}
u_sess->utils_cxt.sql_ignore_strategy_val = sql_ignore_strategy[0].val;
}
}

4
src/gausskernel/optimizer/path/Makefile
View File

@ -20,11 +20,11 @@ endif
ifeq ($(enable_multiple_nodes), yes)
OBJS = allpaths.o clausesel.o costsize.o equivclass.o indxpath.o \
joinpath.o joinrels.o orindxpath.o pathkeys.o tidpath.o streampath_base.o \
joinpath.o joinrels.o pathkeys.o tidpath.o streampath_base.o \
es_selectivity.o
else
OBJS = allpaths.o clausesel.o costsize.o equivclass.o indxpath.o \
joinpath.o joinrels.o orindxpath.o pathkeys.o tidpath.o \
joinpath.o joinrels.o pathkeys.o tidpath.o \
pgxcpath_single.o streampath_single.o streampath_base.o es_selectivity.o
endif

10
src/gausskernel/optimizer/path/allpaths.cpp
View File

@ -998,16 +998,6 @@ static void set_plain_rel_size(PlannerInfo* root, RelOptInfo* rel, RangeTblEntry
if (rte->tablesample == NULL) {
/* Mark rel with estimated output rows, width, etc */
set_baserel_size_estimates(root, rel);
/*
* Check to see if we can extract any restriction conditions from join
* quals that are OR-of-AND structures. If so, add them to the rel's
* restriction list, and redo the above steps.
*/
if (create_or_index_quals(root, rel)) {
check_partial_indexes(root, rel);
set_baserel_size_estimates(root, rel);
}
} else {
/* Sampled relation */
set_tablesample_rel_size(root, rel, rte);

2
src/gausskernel/optimizer/path/indxpath.cpp
View File

@ -1630,7 +1630,7 @@ static Path* choose_bitmap_and(PlannerInfo* root, RelOptInfo* rel, List* paths,
* we can remove this limitation. (But note that this also defends
* against flat-out duplicate input paths, which can happen because
* match_join_clauses_to_index will find the same OR join clauses that
* create_or_index_quals has pulled OR restriction clauses out of.)
* extract_restriction_or_clauses has pulled OR restriction clauses out of.)
*
* For the same reason, we reject AND combinations in which an index
* predicate clause duplicates another clause. Here we find it necessary

183
src/gausskernel/optimizer/path/orindxpath.cpp
View File

@ -1,183 +0,0 @@
/* -------------------------------------------------------------------------
*
* orindxpath.cpp
* Routines to find index paths that match a set of OR clauses
*
* Portions Copyright (c) 2020 Huawei Technologies Co.,Ltd.
* Portions Copyright (c) 1996-2012, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/gausskernel/optimizer/path/orindxpath.cpp
*
* -------------------------------------------------------------------------
*/
#include "postgres.h"
#include "knl/knl_variable.h"
#include "optimizer/cost.h"
#include "optimizer/paths.h"
#include "optimizer/restrictinfo.h"
/* ----------
* create_or_index_quals
* Examine join OR-of-AND quals to see if any useful restriction OR
* clauses can be extracted. If so, add them to the query.
*
* Although a join clause must reference other relations overall,
* an OR of ANDs clause might contain sub-clauses that reference just this
* relation and can be used to build a restriction clause.
* For example consider
* WHERE ((a.x = 42 AND b.y = 43) OR (a.x = 44 AND b.z = 45));
* We can transform this into
* WHERE ((a.x = 42 AND b.y = 43) OR (a.x = 44 AND b.z = 45))
* AND (a.x = 42 OR a.x = 44)
* AND (b.y = 43 OR b.z = 45);
* which opens the potential to build OR indexscans on a and b. In essence
* this is a partial transformation to CNF (AND of ORs format). It is not
* complete, however, because we do not unravel the original OR --- doing so
* would usually bloat the qualification expression to little gain.
*
* The added quals are partially redundant with the original OR, and therefore
* will cause the size of the joinrel to be underestimated when it is finally
* formed. (This would be true of a full transformation to CNF as well; the
* fault is not really in the transformation, but in clauselist_selectivity's
* inability to recognize redundant conditions.) To minimize the collateral
* damage, we want to minimize the number of quals added. Therefore we do
* not add every possible extracted restriction condition to the query.
* Instead, we search for the single restriction condition that generates
* the most useful (cheapest) OR indexscan, and add only that condition.
* This is a pretty ad-hoc heuristic, but quite useful.
*
* We can then compensate for the redundancy of the added qual by poking
* the recorded selectivity of the original OR clause, thereby ensuring
* the added qual doesn't change the estimated size of the joinrel when
* it is finally formed. This is a MAJOR HACK: it depends on the fact
* that clause selectivities are cached and on the fact that the same
* RestrictInfo node will appear in every joininfo list that might be used
* when the joinrel is formed. And it probably isn't right in cases where
* the size estimation is nonlinear (i.e., outer and IN joins). But it
* beats not doing anything.
*
* NOTE: one might think this messiness could be worked around by generating
* the indexscan path with a small path->rows value, and not touching the
* rel's baserestrictinfo or rel->rows. However, that does not work.
* The optimizer's fundamental design assumes that every general-purpose
* Path for a given relation generates the same number of rows. Without
* this assumption we'd not be able to optimize solely on the cost of Paths,
* but would have to take number of output rows into account as well.
* (The parameterized-paths stuff almost fixes this, but not quite...)
*
* 'rel' is the relation entry for which quals are to be created
*
* If successful, adds qual(s) to rel->baserestrictinfo and returns TRUE.
* If no quals available, returns FALSE and doesn't change rel.
*
* Note: check_partial_indexes() must have been run previously.
* ----------
*/
bool create_or_index_quals(PlannerInfo* root, RelOptInfo* rel)
{
BitmapOrPath* bestpath = NULL;
RestrictInfo* bestrinfo = NULL;
List* newrinfos = NIL;
RestrictInfo* or_rinfo = NULL;
Selectivity or_selec, orig_selec;
ListCell* i = NULL;
/* Skip the whole mess if no indexes */
if (rel->indexlist == NIL)
return false;
/*
* Find potentially interesting OR joinclauses. We can use any joinclause
* that is considered safe to move to this rel by the parameterized-path
* machinery, even though what we are going to do with it is not exactly a
* parameterized path.
*/
foreach (i, rel->joininfo) {
RestrictInfo* rinfo = (RestrictInfo*)lfirst(i);
if (restriction_is_or_clause(rinfo) && join_clause_is_movable_to(rinfo, rel->relid)) {
/*
* Use the generate_bitmap_or_paths() machinery to estimate the
* value of each OR clause. We can use regular restriction
* clauses along with the OR clause contents to generate
* indexquals. We pass restriction_only = true so that any
* sub-clauses that are actually joins will be ignored.
*/
List* orpaths = NIL;
ListCell* k = NULL;
orpaths = generate_bitmap_or_paths(root, rel, list_make1(rinfo), rel->baserestrictinfo, true);
IndexFeature indexFeature = getIndexFeature(rel->isPartitionedTable, (rel->bucketInfo != NULL));
if (indexFeature != NONFEATURED_INDEX) {
orpaths = list_concat(
orpaths,
GenerateBitmapOrPathsWithFeaturedIndex(root, rel, list_make1(rinfo), rel->baserestrictinfo, true,
indexFeature));
}
/* Locate the cheapest OR path */
foreach (k, orpaths) {
BitmapOrPath* path = (BitmapOrPath*)lfirst(k);
AssertEreport(IsA(path, BitmapOrPath), MOD_OPT, "Restriction information is incorrect");
if (bestpath == NULL || path->path.total_cost < bestpath->path.total_cost) {
bestpath = path;
bestrinfo = rinfo;
}
}
}
}
/* Fail if no suitable clauses found */
if (bestpath == NULL)
return false;
/*
* Convert the path's indexclauses structure to a RestrictInfo tree. We
* include any partial-index predicates so as to get a reasonable
* representation of what the path is actually scanning.
*/
newrinfos = make_restrictinfo_from_bitmapqual((Path*)bestpath, true, true);
/* It's possible we get back something other than a single OR clause */
if (list_length(newrinfos) != 1)
return false;
or_rinfo = (RestrictInfo*)linitial(newrinfos);
AssertEreport(IsA(or_rinfo, RestrictInfo), MOD_OPT, "Restriction clause does not contain OR");
if (!restriction_is_or_clause(or_rinfo))
return false;
/*
* OK, add it to the rel's restriction list.
*/
rel->baserestrictinfo = list_concat(rel->baserestrictinfo, newrinfos);
rel->baserestrict_min_security = Min(rel->baserestrict_min_security, or_rinfo->security_level);
/*
* Adjust the original OR clause's cached selectivity to compensate for
* the selectivity of the added (but redundant) lower-level qual. This
* should result in the join rel getting approximately the same rows
* estimate as it would have gotten without all these shenanigans. (XXX
* major hack alert ... this depends on the assumption that the
* selectivity will stay cached ...)
* we don't need cache the selectivity because the index's selectivity is not accurate.
*/
or_selec = clause_selectivity(root, (Node*)or_rinfo, 0, JOIN_INNER, NULL, false);
if (or_selec > 0 && or_selec < 1) {
orig_selec = clause_selectivity(root, (Node*)bestrinfo, 0, JOIN_INNER, NULL, false);
bestrinfo->norm_selec = orig_selec / or_selec;
/* clamp result to sane range */
if (bestrinfo->norm_selec > 1)
bestrinfo->norm_selec = 1;
/* It isn't an outer join clause, so no need to adjust outer_selec */
}
/* Tell caller to recompute partial index status and rowcount estimate */
return true;
}

9
src/gausskernel/optimizer/plan/planmain.cpp
View File

@ -33,6 +33,7 @@
#include "optimizer/planmain.h"
#include "optimizer/randomplan.h"
#include "optimizer/tlist.h"
#include "optimizer/orclauses.h"
#include "utils/selfuncs.h"
/* Local functions */
@ -235,6 +236,14 @@ RelOptInfo* query_planner(PlannerInfo* root, List* tlist,
*/
add_placeholders_to_base_rels(root);
/*
* Look for join OR clauses that we can extract single-relation
* restriction OR clauses from.
*/
if (ENABLE_SQL_BETA_FEATURE(EXTRACT_PUSHDOWN_OR_CLAUSE)) {
extract_restriction_or_clauses(root);
}
/*
* We should now have size estimates for every actual table involved in
* the query, and we also know which if any have been deleted from the

2
src/gausskernel/optimizer/util/Makefile
View File

@ -19,7 +19,7 @@ endif
SUBDIRS = learn
OBJS = clauses.o joininfo.o pathnode.o placeholder.o plancat.o predtest.o \
OBJS = clauses.o joininfo.o pathnode.o placeholder.o plancat.o predtest.o orclauses.o \
relnode.o restrictinfo.o tlist.o var.o pruningboundary.o pgxcship.o pruning.o randomplan.o optimizerdebug.o planmem_walker.o \
nodegroups.o plananalyzer.o optcommon.o dataskew.o joinskewinfo.o autoanalyzer.o bucketinfo.o bucketpruning.o subpartitionpruning.o

333
src/gausskernel/optimizer/util/orclauses.cpp Normal file
View File

@ -0,0 +1,333 @@
/*-------------------------------------------------------------------------
*
* orclauses.cpp
* Routines to extract restriction OR clauses from join OR clauses
*
* Portions Copyright (c) 2022 Huawei Technologies Co.,Ltd.
* Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/gausskernel/optimizer/util/orclauses.cpp
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/clauses.h"
#include "optimizer/cost.h"
#include "optimizer/orclauses.h"
#include "optimizer/restrictinfo.h"
static bool is_safe_restriction_clause_for(RestrictInfo *rinfo, RelOptInfo *rel);
static Expr *extract_or_clause(RestrictInfo *or_rinfo, RelOptInfo *rel);
static void consider_new_or_clause(PlannerInfo *root, RelOptInfo *rel, Expr *orclause, RestrictInfo *join_or_rinfo);
/*
* extract_restriction_or_clauses
* Examine join OR-of-AND clauses to see if any useful restriction OR
* clauses can be extracted. If so, add them to the query.
*
* Although a join clause must reference multiple relations overall,
* an OR of ANDs clause might contain sub-clauses that reference just one
* relation and can be used to build a restriction clause for that rel.
* For example consider
* WHERE ((a.x = 42 AND b.y = 43) OR (a.x = 44 AND b.z = 45));
* We can transform this into
* WHERE ((a.x = 42 AND b.y = 43) OR (a.x = 44 AND b.z = 45))
* AND (a.x = 42 OR a.x = 44)
* AND (b.y = 43 OR b.z = 45);
* which allows the latter clauses to be applied during the scans of a and b,
* perhaps as index qualifications, and in any case reducing the number of
* rows arriving at the join. In essence this is a partial transformation to
* CNF (AND of ORs format). It is not complete, however, because we do not
* unravel the original OR --- doing so would usually bloat the qualification
* expression to little gain.
*
* The added quals are partially redundant with the original OR, and therefore
* would cause the size of the joinrel to be underestimated when it is finally
* formed. (This would be true of a full transformation to CNF as well; the
* fault is not really in the transformation, but in clauselist_selectivity's
* inability to recognize redundant conditions.) We can compensate for this
* redundancy by changing the cached selectivity of the original OR clause,
* canceling out the (valid) reduction in the estimated sizes of the base
* relations so that the estimated joinrel size remains the same. This is
* a MAJOR HACK: it depends on the fact that clause selectivities are cached
* and on the fact that the same RestrictInfo node will appear in every
* joininfo list that might be used when the joinrel is formed.
* And it doesn't work in cases where the size estimation is nonlinear
* (i.e., outer and IN joins). But it beats not doing anything.
*
* We examine each base relation to see if join clauses associated with it
* contain extractable restriction conditions. If so, add those conditions
* to the rel's baserestrictinfo and update the cached selectivities of the
* join clauses. Note that the same join clause will be examined afresh
* from the point of view of each baserel that participates in it, so its
* cached selectivity may get updated multiple times.
*/
void extract_restriction_or_clauses(PlannerInfo *root)
{
Index rti;
/* Examine each baserel for potential join OR clauses */
for (rti = 1; (int)rti < root->simple_rel_array_size; rti++) {
RelOptInfo *rel = root->simple_rel_array[rti];
ListCell *lc = NULL;
/* there may be empty slots corresponding to non-baserel RTEs */
if (rel == NULL) {
continue;
}
Assert(rel->relid == rti); /* sanity check on array */
/* ignore RTEs that are "other rels" */
if (rel->reloptkind != RELOPT_BASEREL) {
continue;
}
/*
* Find potentially interesting OR joinclauses. We can use any
* joinclause that is considered safe to move to this rel by the
* parameterized-path machinery, even though what we are going to do
* with it is not exactly a parameterized path.
*
* However, it seems best to ignore clauses that have been marked
* redundant (by setting norm_selec > 1). That likely can't happen
* for OR clauses, but let's be safe.
*/
foreach(lc, rel->joininfo) {
RestrictInfo *rinfo = (RestrictInfo *) lfirst(lc);
if (restriction_is_or_clause(rinfo) && join_clause_is_movable_to(rinfo, rti) && rinfo->norm_selec <= 1) {
/* Try to extract a qual for this rel only */
Expr *orclause = extract_or_clause(rinfo, rel);
/*
* If successful, decide whether we want to use the clause,
* and insert it into the rel's restrictinfo list if so.
*/
if (orclause) {
consider_new_or_clause(root, rel, orclause, rinfo);
}
}
}
}
}
/*
* Is the given primitive (non-OR) RestrictInfo safe to move to the rel?
*/
static bool is_safe_restriction_clause_for(RestrictInfo *rinfo, RelOptInfo *rel)
{
/*
* We want clauses that mention the rel, and only the rel. So in
* particular pseudoconstant clauses can be rejected quickly. Then check
* the clause's Var membership.
*/
if (rinfo->pseudoconstant) {
return false;
}
if (!bms_equal(rinfo->clause_relids, rel->relids)) {
return false;
}
/* We don't want extra evaluations of any volatile functions */
if (contain_volatile_functions((Node *) rinfo->clause)) {
return false;
}
return true;
}
/*
* Try to extract a restriction clause mentioning only "rel" from the given
* join OR-clause.
*
* We must be able to extract at least one qual for this rel from each of
* the arms of the OR, else we can't use it.
*
* Returns an OR clause (not a RestrictInfo!) pertaining to rel, or NULL
* if no OR clause could be extracted.
*/
static Expr *extract_or_clause(RestrictInfo *or_rinfo, RelOptInfo *rel)
{
List *clauselist = NIL;
ListCell *lc = NULL;
/*
* Scan each arm of the input OR clause. Notice we descend into
* or_rinfo->orclause, which has RestrictInfo nodes embedded below the
* toplevel OR/AND structure. This is useful because we can use the info
* in those nodes to make is_safe_restriction_clause_for()'s checks
* cheaper. We'll strip those nodes from the returned tree, though,
* meaning that fresh ones will be built if the clause is accepted as a
* restriction clause. This might seem wasteful --- couldn't we re-use
* the existing RestrictInfos? But that'd require assuming that
* selectivity and other cached data is computed exactly the same way for
* a restriction clause as for a join clause, which seems undesirable.
*/
Assert(is_orclause(or_rinfo->orclause));
foreach(lc, ((BoolExpr *) or_rinfo->orclause)->args) {
Node *orarg = (Node *) lfirst(lc);
List *subclauses = NIL;
Node *subclause = NULL;
/* OR arguments should be ANDs or sub-RestrictInfos */
if (is_andclause(orarg)) {
List *andargs = ((BoolExpr *) orarg)->args;
ListCell *lc2 = NULL;
foreach(lc2, andargs) {
RestrictInfo *rinfo = lfirst_node(RestrictInfo, lc2);
if (restriction_is_or_clause(rinfo)) {
/*
* Recurse to deal with nested OR. Note we *must* recurse
* here, this isn't just overly-tense optimization: we
* have to descend far enough to find and strip all
* RestrictInfos in the expression.
*/
Expr *suborclause = extract_or_clause(rinfo, rel);
if (suborclause) {
subclauses = lappend(subclauses, suborclause);
}
} else if (is_safe_restriction_clause_for(rinfo, rel)) {
subclauses = lappend(subclauses, rinfo->clause);
}
}
} else {
RestrictInfo *rinfo = castNode(RestrictInfo, orarg);
Assert(!restriction_is_or_clause(rinfo));
if (is_safe_restriction_clause_for(rinfo, rel)) {
subclauses = lappend(subclauses, rinfo->clause);
}
}
/*
* If nothing could be extracted from this arm, we can't do anything
* with this OR clause.
*/
if (subclauses == NIL) {
return NULL;
}
/*
* OK, add subclause(s) to the result OR. If we found more than one,
* we need an AND node. But if we found only one, and it is itself an
* OR node, add its subclauses to the result instead; this is needed
* to preserve AND/OR flatness (ie, no OR directly underneath OR).
*/
subclause = (Node *) make_ands_explicit(subclauses);
if (is_orclause(subclause)) {
clauselist = list_concat(clauselist, ((BoolExpr *) subclause)->args);
} else {
clauselist = lappend(clauselist, subclause);
}
}
/*
* If we got a restriction clause from every arm, wrap them up in an OR
* node. (In theory the OR node might be unnecessary, if there was only
* one arm --- but then the input OR node was also redundant.)
*/
if (clauselist != NIL) {
return make_orclause(clauselist);
}
return NULL;
}
/*
* Consider whether a successfully-extracted restriction OR clause is
* actually worth using. If so, add it to the planner's data structures,
* and adjust the original join clause (join_or_rinfo) to compensate.
*/
static void consider_new_or_clause(PlannerInfo *root, RelOptInfo *rel, Expr *orclause, RestrictInfo *join_or_rinfo)
{
RestrictInfo *or_rinfo = NULL;
Selectivity or_selec, orig_selec;
/*
* Build a RestrictInfo from the new OR clause. We can assume it's valid
* as a base restriction clause.
*/
or_rinfo = make_restrictinfo(orclause, true, false, false, join_or_rinfo->security_level, NULL, NULL, NULL);
/*
* Estimate its selectivity. (We could have done this earlier, but doing
* it on the RestrictInfo representation allows the result to get cached,
* saving work later.)
*/
or_selec = clause_selectivity(root, (Node *) or_rinfo, 0, JOIN_INNER, NULL);
/*
* The clause is only worth adding to the query if it rejects a useful
* fraction of the base relation's rows; otherwise, it's just going to
* cause duplicate computation (since we will still have to check the
* original OR clause when the join is formed). Somewhat arbitrarily, we
* set the selectivity threshold at 0.9.
*/
if (or_selec > 0.9) {
return; /* forget it */
}
/*
* OK, add it to the rel's restriction-clause list.
*/
rel->baserestrictinfo = lappend(rel->baserestrictinfo, or_rinfo);
rel->baserestrict_min_security = Min(rel->baserestrict_min_security, or_rinfo->security_level);
/*
* Adjust the original join OR clause's cached selectivity to compensate
* for the selectivity of the added (but redundant) lower-level qual. This
* should result in the join rel getting approximately the same rows
* estimate as it would have gotten without all these shenanigans.
*
* XXX major hack alert: this depends on the assumption that the
* selectivity will stay cached.
*
* XXX another major hack: we adjust only norm_selec, the cached
* selectivity for JOIN_INNER semantics, even though the join clause
* might've been an outer-join clause. This is partly because we can't
* easily identify the relevant SpecialJoinInfo here, and partly because
* the linearity assumption we're making would fail anyway. (If it is an
* outer-join clause, "rel" must be on the nullable side, else we'd not
* have gotten here. So the computation of the join size is going to be
* quite nonlinear with respect to the size of "rel", so it's not clear
* how we ought to adjust outer_selec even if we could compute its
* original value correctly.)
*/
if (or_selec > 0) {
SpecialJoinInfo sjinfo;
/*
* Make up a SpecialJoinInfo for JOIN_INNER semantics. (Compare
* approx_tuple_count() in costsize.c.)
*/
sjinfo.type = T_SpecialJoinInfo;
sjinfo.min_lefthand = bms_difference(join_or_rinfo->clause_relids,
rel->relids);
sjinfo.min_righthand = rel->relids;
sjinfo.syn_lefthand = sjinfo.min_lefthand;
sjinfo.syn_righthand = sjinfo.min_righthand;
sjinfo.jointype = JOIN_INNER;
/* we don't bother trying to make the remaining fields valid */
sjinfo.lhs_strict = false;
sjinfo.delay_upper_joins = false;
sjinfo.join_quals = NIL;
/* Compute inner-join size */
orig_selec = clause_selectivity(root, (Node *) join_or_rinfo, 0, JOIN_INNER, &sjinfo);
/* And hack cached selectivity so join size remains the same */
join_or_rinfo->norm_selec = orig_selec / or_selec;
/* ensure result stays in sane range, in particular not "redundant" */
if (join_or_rinfo->norm_selec > 1) {
join_or_rinfo->norm_selec = 1;
}
/* as explained above, we don't touch outer_selec */
}
}

2
src/include/optimizer/clauses.h
View File

@ -20,6 +20,8 @@
#include "nodes/nodeFuncs.h"
#ifndef ENABLE_MULTIPLE_NODES
#define is_andclause(clause) \
((clause) != NULL && IsA(clause, BoolExpr) && (((const BoolExpr *)(clause))->boolop) == AND_EXPR)
#define is_orclause(clause) \
((clause) != NULL && IsA(clause, BoolExpr) && (((const BoolExpr *)(clause))->boolop) == OR_EXPR)
#define is_notclause(clause) \

21
src/include/optimizer/orclauses.h Normal file
View File

@ -0,0 +1,21 @@
/*-------------------------------------------------------------------------
*
* orclauses.h
* prototypes for orclauses.c.
*
* Portions Copyright (c) 2022, openGauss Contributors
* Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* src/include/optimizer/orclauses.h
*
*-------------------------------------------------------------------------
*/
#ifndef ORCLAUSES_H
#define ORCLAUSES_H
#include "nodes/relation.h"
extern void extract_restriction_or_clauses(PlannerInfo *root);
#endif /* ORCLAUSES_H */

7
src/include/optimizer/paths.h
View File

@ -79,13 +79,6 @@ inline bool CheckIndexPathUseGPI(IndexPath* ipath)
return ipath->indexinfo->isGlobal;
}
/*
* orindxpath.c
* additional routines for indexable OR clauses
*/
extern bool create_or_index_quals(PlannerInfo* root, RelOptInfo* rel);
/*
* tidpath.h
* routines to generate tid paths

3
src/include/utils/guc.h
View File

@ -418,7 +418,8 @@ typedef enum {
PLPGSQL_STREAM_FETCHALL = 4096, /* fetch all tuple when has stream sql under plpgsql's for-loop */
PREDPUSH_SAME_LEVEL = 8192, /* predpush same level */
PARTITION_FDW_ON = 16384, /* support create foreign table on partitioned table */
DISABLE_BITMAP_COST_WITH_LOSSY_PAGES = 32768 /* stop computing bitmap path cost with lossy pages */
DISABLE_BITMAP_COST_WITH_LOSSY_PAGES = 32768, /* stop computing bitmap path cost with lossy pages */
EXTRACT_PUSHDOWN_OR_CLAUSE = 65536 /* Extract restriction OR clauses. */
} sql_beta_param;
typedef enum {

88
src/test/regress/expected/extract_pushdown_or_clause.out Normal file
View File

@ -0,0 +1,88 @@
create table a(id1 int, id2 int);
create table b(id1 int, id2 int);
insert into a select n,n from generate_series(-5,5) n;
insert into b select n,n from generate_series(0,5) n;
explain(costs off) select count(*) from a inner join b on a.id1 > b.id1 where (sqrt(a.id1) < 10 and b.id2 < 10) or (sqrt(a.id1) > 5 and b.id2 > 0);
QUERY PLAN
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Aggregate
-> Nested Loop
Join Filter: ((a.id1 > b.id1) AND (((sqrt((a.id1)::double precision) < 10::double precision) AND (b.id2 < 10)) OR ((sqrt((a.id1)::double precision) > 5::double precision) AND (b.id2 > 0))))
-> Seq Scan on a
-> Materialize
-> Seq Scan on b
(6 rows)
select count(*) from a inner join b on a.id1 > b.id1 where (sqrt(a.id1) < 10 and b.id2 < 10) or (sqrt(a.id1) > 5 and b.id2 > 0);
count
-------
15
(1 row)
create table ta(id int,id1 int);
create table tb(id int,id1 int);
insert into ta values (1, 1);
insert into ta values (2, 2);
insert into ta values (3, 3);
insert into ta values (4, 4);
insert into tb values (1, 1);
insert into tb values (2, 2);
insert into tb values (3, 3);
insert into tb values (4, 4);
select * from ta,tb where (ta.id=1 and tb.id=2) or (ta.id=2 and tb.id=1);
id | id1 | id | id1
----+-----+----+-----
1 | 1 | 2 | 2
2 | 2 | 1 | 1
(2 rows)
explain(costs off) select * from ta,tb where (ta.id=1 and tb.id=2) or (ta.id=2 and tb.id=1);
QUERY PLAN
---------------------------------------------------------------------------------
Nested Loop
Join Filter: (((ta.id = 1) AND (tb.id = 2)) OR ((ta.id = 2) AND (tb.id = 1)))
-> Seq Scan on ta
-> Materialize
-> Seq Scan on tb
(5 rows)
set sql_beta_feature=extract_pushdown_or_clause;
explain(costs off) select count(*) from a inner join b on a.id1 > b.id1 where (sqrt(a.id1) < 10 and b.id2 < 10) or (sqrt(a.id1) > 5 and b.id2 > 0);
QUERY PLAN
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Aggregate
-> Nested Loop
Join Filter: ((a.id1 > b.id1) AND (((sqrt((a.id1)::double precision) < 10::double precision) AND (b.id2 < 10)) OR ((sqrt((a.id1)::double precision) > 5::double precision) AND (b.id2 > 0))))
-> Seq Scan on a
Filter: ((sqrt((id1)::double precision) < 10::double precision) OR (sqrt((id1)::double precision) > 5::double precision))
-> Materialize
-> Seq Scan on b
Filter: ((id2 < 10) OR (id2 > 0))
(8 rows)
select count(*) from a inner join b on a.id1 > b.id1 where (sqrt(a.id1) < 10 and b.id2 < 10) or (sqrt(a.id1) > 5 and b.id2 > 0);
ERROR: cannot take square root of a negative number
select * from ta,tb where (ta.id=1 and tb.id=2) or (ta.id=2 and tb.id=1);
id | id1 | id | id1
----+-----+----+-----
1 | 1 | 2 | 2
2 | 2 | 1 | 1
(2 rows)
explain(costs off) select * from ta,tb where (ta.id=1 and tb.id=2) or (ta.id=2 and tb.id=1);
QUERY PLAN
---------------------------------------------------------------------------------
Nested Loop
Join Filter: (((ta.id = 1) AND (tb.id = 2)) OR ((ta.id = 2) AND (tb.id = 1)))
-> Seq Scan on ta
Filter: ((id = 1) OR (id = 2))
-> Materialize
-> Seq Scan on tb
Filter: ((id = 2) OR (id = 1))
(7 rows)
drop table ta;
drop table tb;
drop table a;
drop table b;
set sql_beta_feature=none;

4
src/test/regress/parallel_schedule0
View File

@ -14,6 +14,8 @@ test: recovery_2pc_tools
test: sqlpatch_base
test: sqlpatch_func
test: extract_pushdown_or_clause
#wlm
test: workload_manager
@ -1042,4 +1044,4 @@ test: show_warnings
# partition expression key
test: partition_expr_key
test: alter_foreign_schema
test: alter_foreign_schema

29
src/test/regress/sql/extract_pushdown_or_clause.sql Normal file
View File

@ -0,0 +1,29 @@
create table a(id1 int, id2 int);
create table b(id1 int, id2 int);
insert into a select n,n from generate_series(-5,5) n;
insert into b select n,n from generate_series(0,5) n;
explain(costs off) select count(*) from a inner join b on a.id1 > b.id1 where (sqrt(a.id1) < 10 and b.id2 < 10) or (sqrt(a.id1) > 5 and b.id2 > 0);
select count(*) from a inner join b on a.id1 > b.id1 where (sqrt(a.id1) < 10 and b.id2 < 10) or (sqrt(a.id1) > 5 and b.id2 > 0);
create table ta(id int,id1 int);
create table tb(id int,id1 int);
insert into ta values (1, 1);
insert into ta values (2, 2);
insert into ta values (3, 3);
insert into ta values (4, 4);
insert into tb values (1, 1);
insert into tb values (2, 2);
insert into tb values (3, 3);
insert into tb values (4, 4);
select * from ta,tb where (ta.id=1 and tb.id=2) or (ta.id=2 and tb.id=1);
explain(costs off) select * from ta,tb where (ta.id=1 and tb.id=2) or (ta.id=2 and tb.id=1);
set sql_beta_feature=extract_pushdown_or_clause;
explain(costs off) select count(*) from a inner join b on a.id1 > b.id1 where (sqrt(a.id1) < 10 and b.id2 < 10) or (sqrt(a.id1) > 5 and b.id2 > 0);
select count(*) from a inner join b on a.id1 > b.id1 where (sqrt(a.id1) < 10 and b.id2 < 10) or (sqrt(a.id1) > 5 and b.id2 > 0);
select * from ta,tb where (ta.id=1 and tb.id=2) or (ta.id=2 and tb.id=1);
explain(costs off) select * from ta,tb where (ta.id=1 and tb.id=2) or (ta.id=2 and tb.id=1);
drop table ta;
drop table tb;
drop table a;
drop table b;
set sql_beta_feature=none;