1996-07-09 08:22:35 +02:00
|
|
|
/*-------------------------------------------------------------------------
|
|
|
|
*
|
1999-02-14 00:22:53 +01:00
|
|
|
* cost.h
|
1997-09-07 07:04:48 +02:00
|
|
|
* prototypes for costsize.c and clausesel.c.
|
1996-07-09 08:22:35 +02:00
|
|
|
*
|
|
|
|
*
|
2019-01-02 18:44:25 +01:00
|
|
|
* Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
|
2000-01-26 06:58:53 +01:00
|
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
1996-07-09 08:22:35 +02:00
|
|
|
*
|
2010-09-20 22:08:53 +02:00
|
|
|
* src/include/optimizer/cost.h
|
1996-07-09 08:22:35 +02:00
|
|
|
*
|
|
|
|
*-------------------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
#ifndef COST_H
|
|
|
|
#define COST_H
|
|
|
|
|
2019-01-29 22:49:25 +01:00
|
|
|
#include "nodes/pathnodes.h"
|
2002-11-21 01:42:20 +01:00
|
|
|
#include "nodes/plannodes.h"
|
1997-11-26 02:14:33 +01:00
|
|
|
|
2002-11-21 01:42:20 +01:00
|
|
|
|
2000-01-23 03:07:00 +01:00
|
|
|
/* defaults for costsize.c's Cost parameters */
|
2000-02-15 21:49:31 +01:00
|
|
|
/* NB: cost-estimation code should use the variables, not these constants! */
|
2001-01-24 19:37:31 +01:00
|
|
|
/* If you change these, update backend/utils/misc/postgresql.sample.conf */
|
2006-06-05 04:49:58 +02:00
|
|
|
#define DEFAULT_SEQ_PAGE_COST 1.0
|
2000-02-15 21:49:31 +01:00
|
|
|
#define DEFAULT_RANDOM_PAGE_COST 4.0
|
2000-04-12 19:17:23 +02:00
|
|
|
#define DEFAULT_CPU_TUPLE_COST 0.01
|
2006-06-05 05:03:42 +02:00
|
|
|
#define DEFAULT_CPU_INDEX_TUPLE_COST 0.005
|
2000-02-15 21:49:31 +01:00
|
|
|
#define DEFAULT_CPU_OPERATOR_COST 0.0025
|
Add a Gather executor node.
A Gather executor node runs any number of copies of a plan in an equal
number of workers and merges all of the results into a single tuple
stream. It can also run the plan itself, if the workers are
unavailable or haven't started up yet. It is intended to work with
the Partial Seq Scan node which will be added in future commits.
It could also be used to implement parallel query of a different sort
by itself, without help from Partial Seq Scan, if the single_copy mode
is used. In that mode, a worker executes the plan, and the parallel
leader does not, merely collecting the worker's results. So, a Gather
node could be inserted into a plan to split the execution of that plan
across two processes. Nested Gather nodes aren't currently supported,
but we might want to add support for that in the future.
There's nothing in the planner to actually generate Gather nodes yet,
so it's not quite time to break out the champagne. But we're getting
close.
Amit Kapila. Some designs suggestions were provided by me, and I also
reviewed the patch. Single-copy mode, documentation, and other minor
changes also by me.
2015-10-01 01:23:36 +02:00
|
|
|
#define DEFAULT_PARALLEL_TUPLE_COST 0.1
|
|
|
|
#define DEFAULT_PARALLEL_SETUP_COST 1000.0
|
2000-01-23 03:07:00 +01:00
|
|
|
|
2014-05-09 03:11:47 +02:00
|
|
|
#define DEFAULT_EFFECTIVE_CACHE_SIZE 524288 /* measured in pages */
|
2014-05-09 02:49:38 +02:00
|
|
|
|
2009-01-07 23:40:49 +01:00
|
|
|
typedef enum
|
|
|
|
{
|
2009-06-11 16:49:15 +02:00
|
|
|
CONSTRAINT_EXCLUSION_OFF, /* do not use c_e */
|
|
|
|
CONSTRAINT_EXCLUSION_ON, /* apply c_e to all rels */
|
Phase 2 of pgindent updates.
Change pg_bsd_indent to follow upstream rules for placement of comments
to the right of code, and remove pgindent hack that caused comments
following #endif to not obey the general rule.
Commit e3860ffa4dd0dad0dd9eea4be9cc1412373a8c89 wasn't actually using
the published version of pg_bsd_indent, but a hacked-up version that
tried to minimize the amount of movement of comments to the right of
code. The situation of interest is where such a comment has to be
moved to the right of its default placement at column 33 because there's
code there. BSD indent has always moved right in units of tab stops
in such cases --- but in the previous incarnation, indent was working
in 8-space tab stops, while now it knows we use 4-space tabs. So the
net result is that in about half the cases, such comments are placed
one tab stop left of before. This is better all around: it leaves
more room on the line for comment text, and it means that in such
cases the comment uniformly starts at the next 4-space tab stop after
the code, rather than sometimes one and sometimes two tabs after.
Also, ensure that comments following #endif are indented the same
as comments following other preprocessor commands such as #else.
That inconsistency turns out to have been self-inflicted damage
from a poorly-thought-through post-indent "fixup" in pgindent.
This patch is much less interesting than the first round of indent
changes, but also bulkier, so I thought it best to separate the effects.
Discussion: https://postgr.es/m/E1dAmxK-0006EE-1r@gemulon.postgresql.org
Discussion: https://postgr.es/m/30527.1495162840@sss.pgh.pa.us
2017-06-21 21:18:54 +02:00
|
|
|
CONSTRAINT_EXCLUSION_PARTITION /* apply c_e to otherrels only */
|
2017-06-21 20:39:04 +02:00
|
|
|
} ConstraintExclusionType;
|
2009-01-07 23:40:49 +01:00
|
|
|
|
1999-07-15 17:21:54 +02:00
|
|
|
|
1996-07-09 08:22:35 +02:00
|
|
|
/*
|
1999-02-14 00:22:53 +01:00
|
|
|
* prototypes for costsize.c
|
1997-09-07 07:04:48 +02:00
|
|
|
* routines to compute costs and sizes
|
|
|
|
*/
|
2000-01-23 00:50:30 +01:00
|
|
|
|
2019-01-29 21:48:51 +01:00
|
|
|
/* parameter variables and flags (see also optimizer.h) */
|
2018-02-09 21:54:45 +01:00
|
|
|
extern PGDLLIMPORT Cost disable_cost;
|
2018-04-26 20:47:16 +02:00
|
|
|
extern PGDLLIMPORT int max_parallel_workers_per_gather;
|
2018-02-09 21:54:45 +01:00
|
|
|
extern PGDLLIMPORT bool enable_seqscan;
|
|
|
|
extern PGDLLIMPORT bool enable_indexscan;
|
|
|
|
extern PGDLLIMPORT bool enable_indexonlyscan;
|
|
|
|
extern PGDLLIMPORT bool enable_bitmapscan;
|
|
|
|
extern PGDLLIMPORT bool enable_tidscan;
|
|
|
|
extern PGDLLIMPORT bool enable_sort;
|
|
|
|
extern PGDLLIMPORT bool enable_hashagg;
|
|
|
|
extern PGDLLIMPORT bool enable_nestloop;
|
|
|
|
extern PGDLLIMPORT bool enable_material;
|
|
|
|
extern PGDLLIMPORT bool enable_mergejoin;
|
|
|
|
extern PGDLLIMPORT bool enable_hashjoin;
|
|
|
|
extern PGDLLIMPORT bool enable_gathermerge;
|
2018-02-16 16:33:59 +01:00
|
|
|
extern PGDLLIMPORT bool enable_partitionwise_join;
|
Implement partition-wise grouping/aggregation.
If the partition keys of input relation are part of the GROUP BY
clause, all the rows belonging to a given group come from a single
partition. This allows aggregation/grouping over a partitioned
relation to be broken down * into aggregation/grouping on each
partition. This should be no worse, and often better, than the normal
approach.
If the GROUP BY clause does not contain all the partition keys, we can
still perform partial aggregation for each partition and then finalize
aggregation after appending the partial results. This is less certain
to be a win, but it's still useful.
Jeevan Chalke, Ashutosh Bapat, Robert Haas. The larger patch series
of which this patch is a part was also reviewed and tested by Antonin
Houska, Rajkumar Raghuwanshi, David Rowley, Dilip Kumar, Konstantin
Knizhnik, Pascal Legrand, and Rafia Sabih.
Discussion: http://postgr.es/m/CAM2+6=V64_xhstVHie0Rz=KPEQnLJMZt_e314P0jaT_oJ9MR8A@mail.gmail.com
2018-03-22 17:49:48 +01:00
|
|
|
extern PGDLLIMPORT bool enable_partitionwise_aggregate;
|
2018-02-09 21:54:45 +01:00
|
|
|
extern PGDLLIMPORT bool enable_parallel_append;
|
|
|
|
extern PGDLLIMPORT bool enable_parallel_hash;
|
2018-04-23 22:57:43 +02:00
|
|
|
extern PGDLLIMPORT bool enable_partition_pruning;
|
2018-04-26 20:47:16 +02:00
|
|
|
extern PGDLLIMPORT int constraint_exclusion;
|
1996-07-09 08:22:35 +02:00
|
|
|
|
2006-06-06 19:59:58 +02:00
|
|
|
extern double index_pages_fetched(double tuples_fetched, BlockNumber pages,
|
2006-10-04 02:30:14 +02:00
|
|
|
double index_pages, PlannerInfo *root);
|
Revise parameterized-path mechanism to fix assorted issues.
This patch adjusts the treatment of parameterized paths so that all paths
with the same parameterization (same set of required outer rels) for the
same relation will have the same rowcount estimate. We cache the rowcount
estimates to ensure that property, and hopefully save a few cycles too.
Doing this makes it practical for add_path_precheck to operate without
a rowcount estimate: it need only assume that paths with different
parameterizations never dominate each other, which is close enough to
true anyway for coarse filtering, because normally a more-parameterized
path should yield fewer rows thanks to having more join clauses to apply.
In add_path, we do the full nine yards of comparing rowcount estimates
along with everything else, so that we can discard parameterized paths that
don't actually have an advantage. This fixes some issues I'd found with
add_path rejecting parameterized paths on the grounds that they were more
expensive than not-parameterized ones, even though they yielded many fewer
rows and hence would be cheaper once subsequent joining was considered.
To make the same-rowcounts assumption valid, we have to require that any
parameterized path enforce *all* join clauses that could be obtained from
the particular set of outer rels, even if not all of them are useful for
indexing. This is required at both base scans and joins. It's a good
thing anyway since the net impact is that join quals are checked at the
lowest practical level in the join tree. Hence, discard the original
rather ad-hoc mechanism for choosing parameterization joinquals, and build
a better one that has a more principled rule for when clauses can be moved.
The original rule was actually buggy anyway for lack of knowledge about
which relations are part of an outer join's outer side; getting this right
requires adding an outer_relids field to RestrictInfo.
2012-04-19 21:52:46 +02:00
|
|
|
extern void cost_seqscan(Path *path, PlannerInfo *root, RelOptInfo *baserel,
|
2016-01-20 20:29:22 +01:00
|
|
|
ParamPathInfo *param_info);
|
Redesign tablesample method API, and do extensive code review.
The original implementation of TABLESAMPLE modeled the tablesample method
API on index access methods, which wasn't a good choice because, without
specialized DDL commands, there's no way to build an extension that can
implement a TSM. (Raw inserts into system catalogs are not an acceptable
thing to do, because we can't undo them during DROP EXTENSION, nor will
pg_upgrade behave sanely.) Instead adopt an API more like procedural
language handlers or foreign data wrappers, wherein the only SQL-level
support object needed is a single handler function identified by having
a special return type. This lets us get rid of the supporting catalog
altogether, so that no custom DDL support is needed for the feature.
Adjust the API so that it can support non-constant tablesample arguments
(the original coding assumed we could evaluate the argument expressions at
ExecInitSampleScan time, which is undesirable even if it weren't outright
unsafe), and discourage sampling methods from looking at invisible tuples.
Make sure that the BERNOULLI and SYSTEM methods are genuinely repeatable
within and across queries, as required by the SQL standard, and deal more
honestly with methods that can't support that requirement.
Make a full code-review pass over the tablesample additions, and fix
assorted bugs, omissions, infelicities, and cosmetic issues (such as
failure to put the added code stanzas in a consistent ordering).
Improve EXPLAIN's output of tablesample plans, too.
Back-patch to 9.5 so that we don't have to support the original API
in production.
2015-07-25 20:39:00 +02:00
|
|
|
extern void cost_samplescan(Path *path, PlannerInfo *root, RelOptInfo *baserel,
|
|
|
|
ParamPathInfo *param_info);
|
2011-12-25 01:03:21 +01:00
|
|
|
extern void cost_index(IndexPath *path, PlannerInfo *root,
|
2017-02-15 19:53:24 +01:00
|
|
|
double loop_count, bool partial_path);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void cost_bitmap_heap_scan(Path *path, PlannerInfo *root, RelOptInfo *baserel,
|
Revise parameterized-path mechanism to fix assorted issues.
This patch adjusts the treatment of parameterized paths so that all paths
with the same parameterization (same set of required outer rels) for the
same relation will have the same rowcount estimate. We cache the rowcount
estimates to ensure that property, and hopefully save a few cycles too.
Doing this makes it practical for add_path_precheck to operate without
a rowcount estimate: it need only assume that paths with different
parameterizations never dominate each other, which is close enough to
true anyway for coarse filtering, because normally a more-parameterized
path should yield fewer rows thanks to having more join clauses to apply.
In add_path, we do the full nine yards of comparing rowcount estimates
along with everything else, so that we can discard parameterized paths that
don't actually have an advantage. This fixes some issues I'd found with
add_path rejecting parameterized paths on the grounds that they were more
expensive than not-parameterized ones, even though they yielded many fewer
rows and hence would be cheaper once subsequent joining was considered.
To make the same-rowcounts assumption valid, we have to require that any
parameterized path enforce *all* join clauses that could be obtained from
the particular set of outer rels, even if not all of them are useful for
indexing. This is required at both base scans and joins. It's a good
thing anyway since the net impact is that join quals are checked at the
lowest practical level in the join tree. Hence, discard the original
rather ad-hoc mechanism for choosing parameterization joinquals, and build
a better one that has a more principled rule for when clauses can be moved.
The original rule was actually buggy anyway for lack of knowledge about
which relations are part of an outer join's outer side; getting this right
requires adding an outer_relids field to RestrictInfo.
2012-04-19 21:52:46 +02:00
|
|
|
ParamPathInfo *param_info,
|
2012-01-28 01:26:38 +01:00
|
|
|
Path *bitmapqual, double loop_count);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void cost_bitmap_and_node(BitmapAndPath *path, PlannerInfo *root);
|
|
|
|
extern void cost_bitmap_or_node(BitmapOrPath *path, PlannerInfo *root);
|
2005-04-22 23:58:32 +02:00
|
|
|
extern void cost_bitmap_tree_node(Path *path, Cost *cost, Selectivity *selec);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void cost_tidscan(Path *path, PlannerInfo *root,
|
2012-08-27 04:48:55 +02:00
|
|
|
RelOptInfo *baserel, List *tidquals, ParamPathInfo *param_info);
|
Make the upper part of the planner work by generating and comparing Paths.
I've been saying we needed to do this for more than five years, and here it
finally is. This patch removes the ever-growing tangle of spaghetti logic
that grouping_planner() used to use to try to identify the best plan for
post-scan/join query steps. Now, there is (nearly) independent
consideration of each execution step, and entirely separate construction of
Paths to represent each of the possible ways to do that step. We choose
the best Path or set of Paths using the same add_path() logic that's been
used inside query_planner() for years.
In addition, this patch removes the old restriction that subquery_planner()
could return only a single Plan. It now returns a RelOptInfo containing a
set of Paths, just as query_planner() does, and the parent query level can
use each of those Paths as the basis of a SubqueryScanPath at its level.
This allows finding some optimizations that we missed before, wherein a
subquery was capable of returning presorted data and thereby avoiding a
sort in the parent level, making the overall cost cheaper even though
delivering sorted output was not the cheapest plan for the subquery in
isolation. (A couple of regression test outputs change in consequence of
that. However, there is very little change in visible planner behavior
overall, because the point of this patch is not to get immediate planning
benefits but to create the infrastructure for future improvements.)
There is a great deal left to do here. This patch unblocks a lot of
planner work that was basically impractical in the old code structure,
such as allowing FDWs to implement remote aggregation, or rewriting
plan_set_operations() to allow consideration of multiple implementation
orders for set operations. (The latter will likely require a full
rewrite of plan_set_operations(); what I've done here is only to fix it
to return Paths not Plans.) I have also left unfinished some localized
refactoring in createplan.c and planner.c, because it was not necessary
to get this patch to a working state.
Thanks to Robert Haas, David Rowley, and Amit Kapila for review.
2016-03-07 21:58:22 +01:00
|
|
|
extern void cost_subqueryscan(SubqueryScanPath *path, PlannerInfo *root,
|
2012-06-10 21:20:04 +02:00
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void cost_functionscan(Path *path, PlannerInfo *root,
|
2012-08-08 01:02:54 +02:00
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info);
|
2017-03-08 16:39:37 +01:00
|
|
|
extern void cost_tableexprscan(Path *path, PlannerInfo *root,
|
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info);
|
2006-08-02 03:59:48 +02:00
|
|
|
extern void cost_valuesscan(Path *path, PlannerInfo *root,
|
2012-08-12 22:01:26 +02:00
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info);
|
2017-03-08 16:39:37 +01:00
|
|
|
extern void cost_tablefuncscan(Path *path, PlannerInfo *root,
|
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info);
|
2012-08-27 04:48:55 +02:00
|
|
|
extern void cost_ctescan(Path *path, PlannerInfo *root,
|
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info);
|
2017-04-01 06:17:18 +02:00
|
|
|
extern void cost_namedtuplestorescan(Path *path, PlannerInfo *root,
|
2017-05-17 22:31:56 +02:00
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info);
|
In the planner, replace an empty FROM clause with a dummy RTE.
The fact that "SELECT expression" has no base relations has long been a
thorn in the side of the planner. It makes it hard to flatten a sub-query
that looks like that, or is a trivial VALUES() item, because the planner
generally uses relid sets to identify sub-relations, and such a sub-query
would have an empty relid set if we flattened it. prepjointree.c contains
some baroque logic that works around this in certain special cases --- but
there is a much better answer. We can replace an empty FROM clause with a
dummy RTE that acts like a table of one row and no columns, and then there
are no such corner cases to worry about. Instead we need some logic to
get rid of useless dummy RTEs, but that's simpler and covers more cases
than what was there before.
For really trivial cases, where the query is just "SELECT expression" and
nothing else, there's a hazard that adding the extra RTE makes for a
noticeable slowdown; even though it's not much processing, there's not
that much for the planner to do overall. However testing says that the
penalty is very small, close to the noise level. In more complex queries,
this is able to find optimizations that we could not find before.
The new RTE type is called RTE_RESULT, since the "scan" plan type it
gives rise to is a Result node (the same plan we produced for a "SELECT
expression" query before). To avoid confusion, rename the old ResultPath
path type to GroupResultPath, reflecting that it's only used in degenerate
grouping cases where we know the query produces just one grouped row.
(It wouldn't work to unify the two cases, because there are different
rules about where the associated quals live during query_planner.)
Note: although this touches readfuncs.c, I don't think a catversion
bump is required, because the added case can't occur in stored rules,
only plans.
Patch by me, reviewed by David Rowley and Mark Dilger
Discussion: https://postgr.es/m/15944.1521127664@sss.pgh.pa.us
2019-01-28 23:54:10 +01:00
|
|
|
extern void cost_resultscan(Path *path, PlannerInfo *root,
|
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info);
|
Make the upper part of the planner work by generating and comparing Paths.
I've been saying we needed to do this for more than five years, and here it
finally is. This patch removes the ever-growing tangle of spaghetti logic
that grouping_planner() used to use to try to identify the best plan for
post-scan/join query steps. Now, there is (nearly) independent
consideration of each execution step, and entirely separate construction of
Paths to represent each of the possible ways to do that step. We choose
the best Path or set of Paths using the same add_path() logic that's been
used inside query_planner() for years.
In addition, this patch removes the old restriction that subquery_planner()
could return only a single Plan. It now returns a RelOptInfo containing a
set of Paths, just as query_planner() does, and the parent query level can
use each of those Paths as the basis of a SubqueryScanPath at its level.
This allows finding some optimizations that we missed before, wherein a
subquery was capable of returning presorted data and thereby avoiding a
sort in the parent level, making the overall cost cheaper even though
delivering sorted output was not the cheapest plan for the subquery in
isolation. (A couple of regression test outputs change in consequence of
that. However, there is very little change in visible planner behavior
overall, because the point of this patch is not to get immediate planning
benefits but to create the infrastructure for future improvements.)
There is a great deal left to do here. This patch unblocks a lot of
planner work that was basically impractical in the old code structure,
such as allowing FDWs to implement remote aggregation, or rewriting
plan_set_operations() to allow consideration of multiple implementation
orders for set operations. (The latter will likely require a full
rewrite of plan_set_operations(); what I've done here is only to fix it
to return Paths not Plans.) I have also left unfinished some localized
refactoring in createplan.c and planner.c, because it was not necessary
to get this patch to a working state.
Thanks to Robert Haas, David Rowley, and Amit Kapila for review.
2016-03-07 21:58:22 +01:00
|
|
|
extern void cost_recursive_union(Path *runion, Path *nrterm, Path *rterm);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void cost_sort(Path *path, PlannerInfo *root,
|
2007-05-04 03:13:45 +02:00
|
|
|
List *pathkeys, Cost input_cost, double tuples, int width,
|
2010-10-08 02:00:28 +02:00
|
|
|
Cost comparison_cost, int sort_mem,
|
2007-05-04 03:13:45 +02:00
|
|
|
double limit_tuples);
|
Support Parallel Append plan nodes.
When we create an Append node, we can spread out the workers over the
subplans instead of piling on to each subplan one at a time, which
should typically be a bit more efficient, both because the startup
cost of any plan executed entirely by one worker is paid only once and
also because of reduced contention. We can also construct Append
plans using a mix of partial and non-partial subplans, which may allow
for parallelism in places that otherwise couldn't support it.
Unfortunately, this patch doesn't handle the important case of
parallelizing UNION ALL by running each branch in a separate worker;
the executor infrastructure is added here, but more planner work is
needed.
Amit Khandekar, Robert Haas, Amul Sul, reviewed and tested by
Ashutosh Bapat, Amit Langote, Rafia Sabih, Amit Kapila, and
Rajkumar Raghuwanshi.
Discussion: http://postgr.es/m/CAJ3gD9dy0K_E8r727heqXoBmWZ83HwLFwdcaSSmBQ1+S+vRuUQ@mail.gmail.com
2017-12-05 23:28:39 +01:00
|
|
|
extern void cost_append(AppendPath *path);
|
2010-10-14 22:56:39 +02:00
|
|
|
extern void cost_merge_append(Path *path, PlannerInfo *root,
|
|
|
|
List *pathkeys, int n_streams,
|
|
|
|
Cost input_startup_cost, Cost input_total_cost,
|
|
|
|
double tuples);
|
2002-11-30 06:21:03 +01:00
|
|
|
extern void cost_material(Path *path,
|
2009-09-13 00:12:09 +02:00
|
|
|
Cost input_startup_cost, Cost input_total_cost,
|
|
|
|
double tuples, int width);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void cost_agg(Path *path, PlannerInfo *root,
|
2011-04-24 22:55:20 +02:00
|
|
|
AggStrategy aggstrategy, const AggClauseCosts *aggcosts,
|
2003-08-04 02:43:34 +02:00
|
|
|
int numGroupCols, double numGroups,
|
2017-11-02 16:24:12 +01:00
|
|
|
List *quals,
|
2003-08-04 02:43:34 +02:00
|
|
|
Cost input_startup_cost, Cost input_total_cost,
|
|
|
|
double input_tuples);
|
2008-12-28 19:54:01 +01:00
|
|
|
extern void cost_windowagg(Path *path, PlannerInfo *root,
|
2011-04-24 22:55:20 +02:00
|
|
|
List *windowFuncs, int numPartCols, int numOrderCols,
|
2008-12-28 19:54:01 +01:00
|
|
|
Cost input_startup_cost, Cost input_total_cost,
|
|
|
|
double input_tuples);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void cost_group(Path *path, PlannerInfo *root,
|
2003-08-04 02:43:34 +02:00
|
|
|
int numGroupCols, double numGroups,
|
2017-11-02 16:24:12 +01:00
|
|
|
List *quals,
|
2003-08-04 02:43:34 +02:00
|
|
|
Cost input_startup_cost, Cost input_total_cost,
|
|
|
|
double input_tuples);
|
2012-01-28 01:26:38 +01:00
|
|
|
extern void initial_cost_nestloop(PlannerInfo *root,
|
|
|
|
JoinCostWorkspace *workspace,
|
|
|
|
JoinType jointype,
|
|
|
|
Path *outer_path, Path *inner_path,
|
2017-04-08 04:20:03 +02:00
|
|
|
JoinPathExtraData *extra);
|
2012-01-28 01:26:38 +01:00
|
|
|
extern void final_cost_nestloop(PlannerInfo *root, NestPath *path,
|
|
|
|
JoinCostWorkspace *workspace,
|
2017-04-08 04:20:03 +02:00
|
|
|
JoinPathExtraData *extra);
|
2012-01-28 01:26:38 +01:00
|
|
|
extern void initial_cost_mergejoin(PlannerInfo *root,
|
|
|
|
JoinCostWorkspace *workspace,
|
|
|
|
JoinType jointype,
|
|
|
|
List *mergeclauses,
|
|
|
|
Path *outer_path, Path *inner_path,
|
|
|
|
List *outersortkeys, List *innersortkeys,
|
2017-04-08 04:20:03 +02:00
|
|
|
JoinPathExtraData *extra);
|
2012-01-28 01:26:38 +01:00
|
|
|
extern void final_cost_mergejoin(PlannerInfo *root, MergePath *path,
|
|
|
|
JoinCostWorkspace *workspace,
|
2017-04-08 04:20:03 +02:00
|
|
|
JoinPathExtraData *extra);
|
2012-01-28 01:26:38 +01:00
|
|
|
extern void initial_cost_hashjoin(PlannerInfo *root,
|
|
|
|
JoinCostWorkspace *workspace,
|
|
|
|
JoinType jointype,
|
|
|
|
List *hashclauses,
|
|
|
|
Path *outer_path, Path *inner_path,
|
Add parallel-aware hash joins.
Introduce parallel-aware hash joins that appear in EXPLAIN plans as Parallel
Hash Join with Parallel Hash. While hash joins could already appear in
parallel queries, they were previously always parallel-oblivious and had a
partial subplan only on the outer side, meaning that the work of the inner
subplan was duplicated in every worker.
After this commit, the planner will consider using a partial subplan on the
inner side too, using the Parallel Hash node to divide the work over the
available CPU cores and combine its results in shared memory. If the join
needs to be split into multiple batches in order to respect work_mem, then
workers process different batches as much as possible and then work together
on the remaining batches.
The advantages of a parallel-aware hash join over a parallel-oblivious hash
join used in a parallel query are that it:
* avoids wasting memory on duplicated hash tables
* avoids wasting disk space on duplicated batch files
* divides the work of building the hash table over the CPUs
One disadvantage is that there is some communication between the participating
CPUs which might outweigh the benefits of parallelism in the case of small
hash tables. This is avoided by the planner's existing reluctance to supply
partial plans for small scans, but it may be necessary to estimate
synchronization costs in future if that situation changes. Another is that
outer batch 0 must be written to disk if multiple batches are required.
A potential future advantage of parallel-aware hash joins is that right and
full outer joins could be supported, since there is a single set of matched
bits for each hashtable, but that is not yet implemented.
A new GUC enable_parallel_hash is defined to control the feature, defaulting
to on.
Author: Thomas Munro
Reviewed-By: Andres Freund, Robert Haas
Tested-By: Rafia Sabih, Prabhat Sahu
Discussion:
https://postgr.es/m/CAEepm=2W=cOkiZxcg6qiFQP-dHUe09aqTrEMM7yJDrHMhDv_RA@mail.gmail.com
https://postgr.es/m/CAEepm=37HKyJ4U6XOLi=JgfSHM3o6B-GaeO-6hkOmneTDkH+Uw@mail.gmail.com
2017-12-21 08:39:21 +01:00
|
|
|
JoinPathExtraData *extra,
|
|
|
|
bool parallel_hash);
|
2012-01-28 01:26:38 +01:00
|
|
|
extern void final_cost_hashjoin(PlannerInfo *root, HashPath *path,
|
|
|
|
JoinCostWorkspace *workspace,
|
2017-04-08 04:20:03 +02:00
|
|
|
JoinPathExtraData *extra);
|
Add a Gather executor node.
A Gather executor node runs any number of copies of a plan in an equal
number of workers and merges all of the results into a single tuple
stream. It can also run the plan itself, if the workers are
unavailable or haven't started up yet. It is intended to work with
the Partial Seq Scan node which will be added in future commits.
It could also be used to implement parallel query of a different sort
by itself, without help from Partial Seq Scan, if the single_copy mode
is used. In that mode, a worker executes the plan, and the parallel
leader does not, merely collecting the worker's results. So, a Gather
node could be inserted into a plan to split the execution of that plan
across two processes. Nested Gather nodes aren't currently supported,
but we might want to add support for that in the future.
There's nothing in the planner to actually generate Gather nodes yet,
so it's not quite time to break out the champagne. But we're getting
close.
Amit Kapila. Some designs suggestions were provided by me, and I also
reviewed the patch. Single-copy mode, documentation, and other minor
changes also by me.
2015-10-01 01:23:36 +02:00
|
|
|
extern void cost_gather(GatherPath *path, PlannerInfo *root,
|
2016-03-21 14:20:53 +01:00
|
|
|
RelOptInfo *baserel, ParamPathInfo *param_info, double *rows);
|
2019-01-29 21:48:51 +01:00
|
|
|
extern void cost_gather_merge(GatherMergePath *path, PlannerInfo *root,
|
|
|
|
RelOptInfo *rel, ParamPathInfo *param_info,
|
|
|
|
Cost input_startup_cost, Cost input_total_cost,
|
|
|
|
double *rows);
|
2008-08-22 02:16:04 +02:00
|
|
|
extern void cost_subplan(PlannerInfo *root, SubPlan *subplan, Plan *plan);
|
2007-02-22 23:00:26 +01:00
|
|
|
extern void cost_qual_eval(QualCost *cost, List *quals, PlannerInfo *root);
|
|
|
|
extern void cost_qual_eval_node(QualCost *cost, Node *qual, PlannerInfo *root);
|
2012-01-28 01:26:38 +01:00
|
|
|
extern void compute_semi_anti_join_factors(PlannerInfo *root,
|
2018-04-20 22:00:47 +02:00
|
|
|
RelOptInfo *joinrel,
|
2012-01-28 01:26:38 +01:00
|
|
|
RelOptInfo *outerrel,
|
|
|
|
RelOptInfo *innerrel,
|
|
|
|
JoinType jointype,
|
|
|
|
SpecialJoinInfo *sjinfo,
|
|
|
|
List *restrictlist,
|
|
|
|
SemiAntiJoinFactors *semifactors);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void set_baserel_size_estimates(PlannerInfo *root, RelOptInfo *rel);
|
Revise parameterized-path mechanism to fix assorted issues.
This patch adjusts the treatment of parameterized paths so that all paths
with the same parameterization (same set of required outer rels) for the
same relation will have the same rowcount estimate. We cache the rowcount
estimates to ensure that property, and hopefully save a few cycles too.
Doing this makes it practical for add_path_precheck to operate without
a rowcount estimate: it need only assume that paths with different
parameterizations never dominate each other, which is close enough to
true anyway for coarse filtering, because normally a more-parameterized
path should yield fewer rows thanks to having more join clauses to apply.
In add_path, we do the full nine yards of comparing rowcount estimates
along with everything else, so that we can discard parameterized paths that
don't actually have an advantage. This fixes some issues I'd found with
add_path rejecting parameterized paths on the grounds that they were more
expensive than not-parameterized ones, even though they yielded many fewer
rows and hence would be cheaper once subsequent joining was considered.
To make the same-rowcounts assumption valid, we have to require that any
parameterized path enforce *all* join clauses that could be obtained from
the particular set of outer rels, even if not all of them are useful for
indexing. This is required at both base scans and joins. It's a good
thing anyway since the net impact is that join quals are checked at the
lowest practical level in the join tree. Hence, discard the original
rather ad-hoc mechanism for choosing parameterization joinquals, and build
a better one that has a more principled rule for when clauses can be moved.
The original rule was actually buggy anyway for lack of knowledge about
which relations are part of an outer join's outer side; getting this right
requires adding an outer_relids field to RestrictInfo.
2012-04-19 21:52:46 +02:00
|
|
|
extern double get_parameterized_baserel_size(PlannerInfo *root,
|
2012-06-10 21:20:04 +02:00
|
|
|
RelOptInfo *rel,
|
|
|
|
List *param_clauses);
|
Revise parameterized-path mechanism to fix assorted issues.
This patch adjusts the treatment of parameterized paths so that all paths
with the same parameterization (same set of required outer rels) for the
same relation will have the same rowcount estimate. We cache the rowcount
estimates to ensure that property, and hopefully save a few cycles too.
Doing this makes it practical for add_path_precheck to operate without
a rowcount estimate: it need only assume that paths with different
parameterizations never dominate each other, which is close enough to
true anyway for coarse filtering, because normally a more-parameterized
path should yield fewer rows thanks to having more join clauses to apply.
In add_path, we do the full nine yards of comparing rowcount estimates
along with everything else, so that we can discard parameterized paths that
don't actually have an advantage. This fixes some issues I'd found with
add_path rejecting parameterized paths on the grounds that they were more
expensive than not-parameterized ones, even though they yielded many fewer
rows and hence would be cheaper once subsequent joining was considered.
To make the same-rowcounts assumption valid, we have to require that any
parameterized path enforce *all* join clauses that could be obtained from
the particular set of outer rels, even if not all of them are useful for
indexing. This is required at both base scans and joins. It's a good
thing anyway since the net impact is that join quals are checked at the
lowest practical level in the join tree. Hence, discard the original
rather ad-hoc mechanism for choosing parameterization joinquals, and build
a better one that has a more principled rule for when clauses can be moved.
The original rule was actually buggy anyway for lack of knowledge about
which relations are part of an outer join's outer side; getting this right
requires adding an outer_relids field to RestrictInfo.
2012-04-19 21:52:46 +02:00
|
|
|
extern double get_parameterized_joinrel_size(PlannerInfo *root,
|
2012-06-10 21:20:04 +02:00
|
|
|
RelOptInfo *rel,
|
2016-06-18 21:22:34 +02:00
|
|
|
Path *outer_path,
|
|
|
|
Path *inner_path,
|
2012-06-10 21:20:04 +02:00
|
|
|
SpecialJoinInfo *sjinfo,
|
|
|
|
List *restrict_clauses);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void set_joinrel_size_estimates(PlannerInfo *root, RelOptInfo *rel,
|
2000-04-12 19:17:23 +02:00
|
|
|
RelOptInfo *outer_rel,
|
|
|
|
RelOptInfo *inner_rel,
|
2008-08-14 20:48:00 +02:00
|
|
|
SpecialJoinInfo *sjinfo,
|
2000-04-12 19:17:23 +02:00
|
|
|
List *restrictlist);
|
2011-09-03 21:35:12 +02:00
|
|
|
extern void set_subquery_size_estimates(PlannerInfo *root, RelOptInfo *rel);
|
2005-06-06 00:32:58 +02:00
|
|
|
extern void set_function_size_estimates(PlannerInfo *root, RelOptInfo *rel);
|
2006-08-02 03:59:48 +02:00
|
|
|
extern void set_values_size_estimates(PlannerInfo *root, RelOptInfo *rel);
|
2008-10-04 23:56:55 +02:00
|
|
|
extern void set_cte_size_estimates(PlannerInfo *root, RelOptInfo *rel,
|
Make the upper part of the planner work by generating and comparing Paths.
I've been saying we needed to do this for more than five years, and here it
finally is. This patch removes the ever-growing tangle of spaghetti logic
that grouping_planner() used to use to try to identify the best plan for
post-scan/join query steps. Now, there is (nearly) independent
consideration of each execution step, and entirely separate construction of
Paths to represent each of the possible ways to do that step. We choose
the best Path or set of Paths using the same add_path() logic that's been
used inside query_planner() for years.
In addition, this patch removes the old restriction that subquery_planner()
could return only a single Plan. It now returns a RelOptInfo containing a
set of Paths, just as query_planner() does, and the parent query level can
use each of those Paths as the basis of a SubqueryScanPath at its level.
This allows finding some optimizations that we missed before, wherein a
subquery was capable of returning presorted data and thereby avoiding a
sort in the parent level, making the overall cost cheaper even though
delivering sorted output was not the cheapest plan for the subquery in
isolation. (A couple of regression test outputs change in consequence of
that. However, there is very little change in visible planner behavior
overall, because the point of this patch is not to get immediate planning
benefits but to create the infrastructure for future improvements.)
There is a great deal left to do here. This patch unblocks a lot of
planner work that was basically impractical in the old code structure,
such as allowing FDWs to implement remote aggregation, or rewriting
plan_set_operations() to allow consideration of multiple implementation
orders for set operations. (The latter will likely require a full
rewrite of plan_set_operations(); what I've done here is only to fix it
to return Paths not Plans.) I have also left unfinished some localized
refactoring in createplan.c and planner.c, because it was not necessary
to get this patch to a working state.
Thanks to Robert Haas, David Rowley, and Amit Kapila for review.
2016-03-07 21:58:22 +01:00
|
|
|
double cte_rows);
|
2017-03-08 16:39:37 +01:00
|
|
|
extern void set_tablefunc_size_estimates(PlannerInfo *root, RelOptInfo *rel);
|
2017-04-01 06:17:18 +02:00
|
|
|
extern void set_namedtuplestore_size_estimates(PlannerInfo *root, RelOptInfo *rel);
|
In the planner, replace an empty FROM clause with a dummy RTE.
The fact that "SELECT expression" has no base relations has long been a
thorn in the side of the planner. It makes it hard to flatten a sub-query
that looks like that, or is a trivial VALUES() item, because the planner
generally uses relid sets to identify sub-relations, and such a sub-query
would have an empty relid set if we flattened it. prepjointree.c contains
some baroque logic that works around this in certain special cases --- but
there is a much better answer. We can replace an empty FROM clause with a
dummy RTE that acts like a table of one row and no columns, and then there
are no such corner cases to worry about. Instead we need some logic to
get rid of useless dummy RTEs, but that's simpler and covers more cases
than what was there before.
For really trivial cases, where the query is just "SELECT expression" and
nothing else, there's a hazard that adding the extra RTE makes for a
noticeable slowdown; even though it's not much processing, there's not
that much for the planner to do overall. However testing says that the
penalty is very small, close to the noise level. In more complex queries,
this is able to find optimizations that we could not find before.
The new RTE type is called RTE_RESULT, since the "scan" plan type it
gives rise to is a Result node (the same plan we produced for a "SELECT
expression" query before). To avoid confusion, rename the old ResultPath
path type to GroupResultPath, reflecting that it's only used in degenerate
grouping cases where we know the query produces just one grouped row.
(It wouldn't work to unify the two cases, because there are different
rules about where the associated quals live during query_planner.)
Note: although this touches readfuncs.c, I don't think a catversion
bump is required, because the added case can't occur in stored rules,
only plans.
Patch by me, reviewed by David Rowley and Mark Dilger
Discussion: https://postgr.es/m/15944.1521127664@sss.pgh.pa.us
2019-01-28 23:54:10 +01:00
|
|
|
extern void set_result_size_estimates(PlannerInfo *root, RelOptInfo *rel);
|
2011-02-20 06:17:18 +01:00
|
|
|
extern void set_foreign_size_estimates(PlannerInfo *root, RelOptInfo *rel);
|
Make the upper part of the planner work by generating and comparing Paths.
I've been saying we needed to do this for more than five years, and here it
finally is. This patch removes the ever-growing tangle of spaghetti logic
that grouping_planner() used to use to try to identify the best plan for
post-scan/join query steps. Now, there is (nearly) independent
consideration of each execution step, and entirely separate construction of
Paths to represent each of the possible ways to do that step. We choose
the best Path or set of Paths using the same add_path() logic that's been
used inside query_planner() for years.
In addition, this patch removes the old restriction that subquery_planner()
could return only a single Plan. It now returns a RelOptInfo containing a
set of Paths, just as query_planner() does, and the parent query level can
use each of those Paths as the basis of a SubqueryScanPath at its level.
This allows finding some optimizations that we missed before, wherein a
subquery was capable of returning presorted data and thereby avoiding a
sort in the parent level, making the overall cost cheaper even though
delivering sorted output was not the cheapest plan for the subquery in
isolation. (A couple of regression test outputs change in consequence of
that. However, there is very little change in visible planner behavior
overall, because the point of this patch is not to get immediate planning
benefits but to create the infrastructure for future improvements.)
There is a great deal left to do here. This patch unblocks a lot of
planner work that was basically impractical in the old code structure,
such as allowing FDWs to implement remote aggregation, or rewriting
plan_set_operations() to allow consideration of multiple implementation
orders for set operations. (The latter will likely require a full
rewrite of plan_set_operations(); what I've done here is only to fix it
to return Paths not Plans.) I have also left unfinished some localized
refactoring in createplan.c and planner.c, because it was not necessary
to get this patch to a working state.
Thanks to Robert Haas, David Rowley, and Amit Kapila for review.
2016-03-07 21:58:22 +01:00
|
|
|
extern PathTarget *set_pathtarget_cost_width(PlannerInfo *root, PathTarget *target);
|
2017-01-27 22:22:11 +01:00
|
|
|
extern double compute_bitmap_pages(PlannerInfo *root, RelOptInfo *baserel,
|
Phase 3 of pgindent updates.
Don't move parenthesized lines to the left, even if that means they
flow past the right margin.
By default, BSD indent lines up statement continuation lines that are
within parentheses so that they start just to the right of the preceding
left parenthesis. However, traditionally, if that resulted in the
continuation line extending to the right of the desired right margin,
then indent would push it left just far enough to not overrun the margin,
if it could do so without making the continuation line start to the left of
the current statement indent. That makes for a weird mix of indentations
unless one has been completely rigid about never violating the 80-column
limit.
This behavior has been pretty universally panned by Postgres developers.
Hence, disable it with indent's new -lpl switch, so that parenthesized
lines are always lined up with the preceding left paren.
This patch is much less interesting than the first round of indent
changes, but also bulkier, so I thought it best to separate the effects.
Discussion: https://postgr.es/m/E1dAmxK-0006EE-1r@gemulon.postgresql.org
Discussion: https://postgr.es/m/30527.1495162840@sss.pgh.pa.us
2017-06-21 21:35:54 +02:00
|
|
|
Path *bitmapqual, int loop_count, Cost *cost, double *tuple);
|
1996-07-09 08:22:35 +02:00
|
|
|
|
Phase 2 of pgindent updates.
Change pg_bsd_indent to follow upstream rules for placement of comments
to the right of code, and remove pgindent hack that caused comments
following #endif to not obey the general rule.
Commit e3860ffa4dd0dad0dd9eea4be9cc1412373a8c89 wasn't actually using
the published version of pg_bsd_indent, but a hacked-up version that
tried to minimize the amount of movement of comments to the right of
code. The situation of interest is where such a comment has to be
moved to the right of its default placement at column 33 because there's
code there. BSD indent has always moved right in units of tab stops
in such cases --- but in the previous incarnation, indent was working
in 8-space tab stops, while now it knows we use 4-space tabs. So the
net result is that in about half the cases, such comments are placed
one tab stop left of before. This is better all around: it leaves
more room on the line for comment text, and it means that in such
cases the comment uniformly starts at the next 4-space tab stop after
the code, rather than sometimes one and sometimes two tabs after.
Also, ensure that comments following #endif are indented the same
as comments following other preprocessor commands such as #else.
That inconsistency turns out to have been self-inflicted damage
from a poorly-thought-through post-indent "fixup" in pgindent.
This patch is much less interesting than the first round of indent
changes, but also bulkier, so I thought it best to separate the effects.
Discussion: https://postgr.es/m/E1dAmxK-0006EE-1r@gemulon.postgresql.org
Discussion: https://postgr.es/m/30527.1495162840@sss.pgh.pa.us
2017-06-21 21:18:54 +02:00
|
|
|
#endif /* COST_H */
|