database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-10-29 22:49:41 +03:00
Code Activity

Implement multivariate n-distinct coefficients

Browse Source 
Add support for explicitly declared statistic objects (CREATE
STATISTICS), allowing collection of statistics on more complex
combinations that individual table columns.  Companion commands DROP
STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are
added too.  All this DDL has been designed so that more statistic types
can be added later on, such as multivariate most-common-values and
multivariate histograms between columns of a single table, leaving room
for permitting columns on multiple tables, too, as well as expressions.

This commit only adds support for collection of n-distinct coefficient
on user-specified sets of columns in a single table.  This is useful to
estimate number of distinct groups in GROUP BY and DISTINCT clauses;
estimation errors there can cause over-allocation of memory in hashed
aggregates, for instance, so it's a worthwhile problem to solve.  A new
special pseudo-type pg_ndistinct is used.

(num-distinct estimation was deemed sufficiently useful by itself that
this is worthwhile even if no further statistic types are added
immediately; so much so that another version of essentially the same
functionality was submitted by Kyotaro Horiguchi:
https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp
though this commit does not use that code.)

Author: Tomas Vondra.  Some code rework by Álvaro.
Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes,
    Ideriha Takeshi
Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz
    https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql
This commit is contained in:
Alvaro Herrera
2017-03-24 14:06:10 -03:00
parent f120b614e0
commit 7b504eb282
77 changed files with 3599 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
src/backend/parser/gram.y
View File

@@ -257,7 +257,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
ConstraintsSetStmt CopyStmt CreateAsStmt CreateCastStmt
CreateDomainStmt CreateExtensionStmt CreateGroupStmt CreateOpClassStmt
CreateOpFamilyStmt AlterOpFamilyStmt CreatePLangStmt
CreateSchemaStmt CreateSeqStmt CreateStmt CreateTableSpaceStmt
CreateSchemaStmt CreateSeqStmt CreateStmt CreateStatsStmt CreateTableSpaceStmt
CreateFdwStmt CreateForeignServerStmt CreateForeignTableStmt
CreateAssertStmt CreateTransformStmt CreateTrigStmt CreateEventTrigStmt
CreateUserStmt CreateUserMappingStmt CreateRoleStmt CreatePolicyStmt
@@ -874,6 +874,7 @@ stmt :
| CreateSeqStmt
| CreateStmt
| CreateSubscriptionStmt
| CreateStatsStmt
| CreateTableSpaceStmt
| CreateTransformStmt
| CreateTrigStmt
@@ -3747,6 +3748,35 @@ OptConsTableSpace: USING INDEX TABLESPACE name { $$ = $4; }
ExistingIndex: USING INDEX index_name { $$ = $3; }
;
/*****************************************************************************
*
* QUERY :
* CREATE STATISTICS stats_name WITH (options) ON (columns) FROM relname
*
*****************************************************************************/
CreateStatsStmt: CREATE STATISTICS any_name opt_reloptions ON '(' columnList ')' FROM qualified_name
{
CreateStatsStmt *n = makeNode(CreateStatsStmt);
n->defnames = $3;
n->relation = $10;
n->keys = $7;
n->options = $4;
n->if_not_exists = false;
$$ = (Node *)n;
}
| CREATE STATISTICS IF_P NOT EXISTS any_name opt_reloptions ON '(' columnList ')' FROM qualified_name
{
CreateStatsStmt *n = makeNode(CreateStatsStmt);
n->defnames = $6;
n->relation = $13;
n->keys = $10;
n->options = $7;
n->if_not_exists = true;
$$ = (Node *)n;
}
;
/*****************************************************************************
*
@@ -6042,6 +6072,7 @@ drop_type_any_name:
| FOREIGN TABLE { $$ = OBJECT_FOREIGN_TABLE; }
| COLLATION { $$ = OBJECT_COLLATION; }
| CONVERSION_P { $$ = OBJECT_CONVERSION; }
| STATISTICS { $$ = OBJECT_STATISTIC_EXT; }
| TEXT_P SEARCH PARSER { $$ = OBJECT_TSPARSER; }
| TEXT_P SEARCH DICTIONARY { $$ = OBJECT_TSDICTIONARY; }
| TEXT_P SEARCH TEMPLATE { $$ = OBJECT_TSTEMPLATE; }
@@ -6119,7 +6150,7 @@ opt_restart_seqs:
* EXTENSION | EVENT TRIGGER | FOREIGN DATA WRAPPER |
* FOREIGN TABLE | INDEX | [PROCEDURAL] LANGUAGE |
* MATERIALIZED VIEW | POLICY | ROLE | SCHEMA | SEQUENCE |
* SERVER | TABLE | TABLESPACE |
* SERVER | STATISTICS | TABLE | TABLESPACE |
* TEXT SEARCH CONFIGURATION | TEXT SEARCH DICTIONARY |
* TEXT SEARCH PARSER | TEXT SEARCH TEMPLATE | TYPE |
* VIEW] <objname> |
@@ -6288,6 +6319,7 @@ comment_type_any_name:
COLUMN { $$ = OBJECT_COLUMN; }
| INDEX { $$ = OBJECT_INDEX; }
| SEQUENCE { $$ = OBJECT_SEQUENCE; }
| STATISTICS { $$ = OBJECT_STATISTIC_EXT; }
| TABLE { $$ = OBJECT_TABLE; }
| VIEW { $$ = OBJECT_VIEW; }
| MATERIALIZED VIEW { $$ = OBJECT_MATVIEW; }
@@ -8428,6 +8460,15 @@ RenameStmt: ALTER AGGREGATE aggregate_with_argtypes RENAME TO name
n->missing_ok = false;
$$ = (Node *)n;
}
| ALTER STATISTICS any_name RENAME TO name
{
RenameStmt *n = makeNode(RenameStmt);
n->renameType = OBJECT_STATISTIC_EXT;
n->object = (Node *) $3;
n->newname = $6;
n->missing_ok = false;
$$ = (Node *)n;
}
| ALTER TEXT_P SEARCH PARSER any_name RENAME TO name
{
RenameStmt *n = makeNode(RenameStmt);
@@ -8643,6 +8684,15 @@ AlterObjectSchemaStmt:
n->missing_ok = true;
$$ = (Node *)n;
}
| ALTER STATISTICS any_name SET SCHEMA name
{
AlterObjectSchemaStmt *n = makeNode(AlterObjectSchemaStmt);
n->objectType = OBJECT_STATISTIC_EXT;
n->object = (Node *) $3;
n->newschema = $6;
n->missing_ok = false;
$$ = (Node *)n;
}
| ALTER TEXT_P SEARCH PARSER any_name SET SCHEMA name
{
AlterObjectSchemaStmt *n = makeNode(AlterObjectSchemaStmt);
@@ -8906,6 +8956,14 @@ AlterOwnerStmt: ALTER AGGREGATE aggregate_with_argtypes OWNER TO RoleSpec
n->newowner = $6;
$$ = (Node *)n;
}
| ALTER STATISTICS any_name OWNER TO RoleSpec
{
AlterOwnerStmt *n = makeNode(AlterOwnerStmt);
n->objectType = OBJECT_STATISTIC_EXT;
n->object = (Node *) $3;
n->newowner = $6;
$$ = (Node *)n;
}
| ALTER TEXT_P SEARCH DICTIONARY any_name OWNER TO RoleSpec
{
AlterOwnerStmt *n = makeNode(AlterOwnerStmt);