database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-02 09:02:37 +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

81
src/backend/utils/adt/ruleutils.c
View File

@ -35,6 +35,7 @@
#include "catalog/pg_operator.h"
#include "catalog/pg_partitioned_table.h"
#include "catalog/pg_proc.h"
#include "catalog/pg_statistic_ext.h"
#include "catalog/pg_trigger.h"
#include "catalog/pg_type.h"
#include "commands/defrem.h"
@ -317,6 +318,7 @@ static char *pg_get_indexdef_worker(Oid indexrelid, int colno,
const Oid *excludeOps,
bool attrsOnly, bool showTblSpc,
int prettyFlags, bool missing_ok);
static char *pg_get_statisticsext_worker(Oid statextid, bool missing_ok);
static char *pg_get_partkeydef_worker(Oid relid, int prettyFlags,
bool attrsOnly);
static char *pg_get_constraintdef_worker(Oid constraintId, bool fullCommand,
@ -1421,6 +1423,85 @@ pg_get_indexdef_worker(Oid indexrelid, int colno,
return buf.data;
}
/*
* pg_get_statisticsextdef
* Get the definition of an extended statistics object
*/
Datum
pg_get_statisticsextdef(PG_FUNCTION_ARGS)
{
Oid statextid = PG_GETARG_OID(0);
char *res;
res = pg_get_statisticsext_worker(statextid, true);
if (res == NULL)
PG_RETURN_NULL();
PG_RETURN_TEXT_P(string_to_text(res));
}
/*
* Internal workhorse to decompile an extended statistics object.
*/
static char *
pg_get_statisticsext_worker(Oid statextid, bool missing_ok)
{
Form_pg_statistic_ext statextrec;
Form_pg_class pgclassrec;
HeapTuple statexttup;
HeapTuple pgclasstup;
StringInfoData buf;
int colno;
statexttup = SearchSysCache1(STATEXTOID, ObjectIdGetDatum(statextid));
if (!HeapTupleIsValid(statexttup))
{
if (missing_ok)
return NULL;
elog(ERROR, "cache lookup failed for extended statistics %u", statextid);
}
statextrec = (Form_pg_statistic_ext) GETSTRUCT(statexttup);
pgclasstup = SearchSysCache1(RELOID, ObjectIdGetDatum(statextrec->starelid));
if (!HeapTupleIsValid(statexttup))
{
ReleaseSysCache(statexttup);
elog(ERROR, "cache lookup failed for relation %u", statextrec->starelid);
}
pgclassrec = (Form_pg_class) GETSTRUCT(pgclasstup);
initStringInfo(&buf);
appendStringInfo(&buf, "CREATE STATISTICS %s ON (",
quote_identifier(NameStr(statextrec->staname)));
for (colno = 0; colno < statextrec->stakeys.dim1; colno++)
{
AttrNumber attnum = statextrec->stakeys.values[colno];
char *attname;
if (colno > 0)
appendStringInfoString(&buf, ", ");
attname = get_relid_attribute_name(statextrec->starelid, attnum);
appendStringInfoString(&buf, quote_identifier(attname));
}
appendStringInfo(&buf, ") FROM %s",
quote_identifier(NameStr(pgclassrec->relname)));
ReleaseSysCache(statexttup);
ReleaseSysCache(pgclasstup);
return buf.data;
}
/*
* pg_get_partkeydef
*