Alvaro Herrera wrote:
> * I'm not terribly happy with the header organization. I think
> VacAttrStats should be in its own (new) src/include/statistics/analyze.h
> for example (which cleans up a bunch of existing stuff a bit)
I tried this and it doesn't actually do any good. Patch attached, which
I intend to throw away. The main problem is that most files interested
in analyze stuff also wants to do vacuum_delay_point, or access
default_statistics_target, both of which are declared in vacuum.h, so
these files have to include vacuum.h anyway.
In order to achieve anything worthwhile we'd have to do a three-way
split I think, and that's more trouble that this is worth.
--
Álvaro Herrera https://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Remote DBA, Training & Services
commit db618933b50f5f2b29b3a79325d43883cb1af521[m
Author: Alvaro Herrera <alvhe...@alvh.no-ip.org>
AuthorDate: Mon Mar 20 18:51:11 2017 -0300
CommitDate: Mon Mar 20 19:11:36 2017 -0300
Header reorganization: move stuff to statistics/analyze.h
diff --git a/contrib/postgres_fdw/postgres_fdw.c
b/contrib/postgres_fdw/postgres_fdw.c
index e8cb2d0..9101ed1 100644
--- a/contrib/postgres_fdw/postgres_fdw.c
+++ b/contrib/postgres_fdw/postgres_fdw.c
@@ -17,6 +17,7 @@
#include "access/htup_details.h"
#include "access/sysattr.h"
#include "catalog/pg_class.h"
+#include "catalog/pg_type.h"
#include "commands/defrem.h"
#include "commands/explain.h"
#include "commands/vacuum.h"
diff --git a/src/backend/access/hash/hash.c b/src/backend/access/hash/hash.c
index cfcec34..9475591 100644
--- a/src/backend/access/hash/hash.c
+++ b/src/backend/access/hash/hash.c
@@ -22,6 +22,7 @@
#include "access/hash_xlog.h"
#include "access/relscan.h"
#include "catalog/index.h"
+#include "catalog/pg_type.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "optimizer/plancat.h"
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index b91df98..ca8235e 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -39,6 +39,7 @@
#include "parser/parse_relation.h"
#include "pgstat.h"
#include "postmaster/autovacuum.h"
+#include "statistics/analyze.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "storage/proc.h"
diff --git a/src/backend/postmaster/autovacuum.c
b/src/backend/postmaster/autovacuum.c
index 33ca749..5b8d072 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -74,6 +74,7 @@
#include "catalog/dependency.h"
#include "catalog/namespace.h"
#include "catalog/pg_database.h"
+#include "catalog/pg_statistic.h"
#include "commands/dbcommands.h"
#include "commands/vacuum.h"
#include "lib/ilist.h"
diff --git a/src/backend/tsearch/ts_typanalyze.c
b/src/backend/tsearch/ts_typanalyze.c
index 017435c..30f7f26 100644
--- a/src/backend/tsearch/ts_typanalyze.c
+++ b/src/backend/tsearch/ts_typanalyze.c
@@ -16,6 +16,7 @@
#include "access/hash.h"
#include "catalog/pg_operator.h"
#include "commands/vacuum.h"
+#include "statistics/analyze.h"
#include "tsearch/ts_type.h"
#include "utils/builtins.h"
diff --git a/src/backend/utils/adt/array_typanalyze.c
b/src/backend/utils/adt/array_typanalyze.c
index 85b7a43..1a7a5ef 100644
--- a/src/backend/utils/adt/array_typanalyze.c
+++ b/src/backend/utils/adt/array_typanalyze.c
@@ -22,6 +22,7 @@
#include "utils/datum.h"
#include "utils/lsyscache.h"
#include "utils/typcache.h"
+#include "statistics/analyze.h"
/*
diff --git a/src/backend/utils/adt/rangetypes_typanalyze.c
b/src/backend/utils/adt/rangetypes_typanalyze.c
index a8d585ce..5f7a160 100644
--- a/src/backend/utils/adt/rangetypes_typanalyze.c
+++ b/src/backend/utils/adt/rangetypes_typanalyze.c
@@ -29,6 +29,7 @@
#include "utils/builtins.h"
#include "utils/lsyscache.h"
#include "utils/rangetypes.h"
+#include "statistics/analyze.h"
static int float8_qsort_cmp(const void *a1, const void *a2);
static int range_bound_qsort_cmp(const void *a1, const void *a2, void
*arg);
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 4feb26a..c61753d 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -34,6 +34,7 @@
#include "access/xact.h"
#include "access/xlog_internal.h"
#include "catalog/namespace.h"
+#include "catalog/pg_type.h"
#include "commands/async.h"
#include "commands/prepare.h"
#include "commands/user.h"
diff --git a/src/include/commands/vacuum.h b/src/include/commands/vacuum.h
index 541c2fa..26fa238 100644
--- a/src/include/commands/vacuum.h
+++ b/src/include/commands/vacuum.h
@@ -14,122 +14,13 @@
#ifndef VACUUM_H
#define VACUUM_H
-#include "access/htup.h"
-#include "catalog/pg_statistic.h"
-#include "catalog/pg_type.h"
#include "nodes/parsenodes.h"
+#include "storage/block.h"
#include "storage/buf.h"
#include "storage/lock.h"
#include "utils/relcache.h"
-/*----------
- * ANALYZE builds one of these structs for each attribute (column) that is
- * to be analyzed. The struct and subsidiary data are in anl_context,
- * so they live until the end of the ANALYZE operation.
- *
- * The type-specific typanalyze function is passed a pointer to this struct
- * and must return TRUE to continue analysis, FALSE to skip analysis of this
- * column. In the TRUE case it must set the compute_stats and minrows fields,
- * and can optionally set extra_data to pass additional info to compute_stats.
- * minrows is its request for the minimum number of sample rows to be gathered
- * (but note this request might not be honored, eg if there are fewer rows
- * than that in the table).
- *
- * The compute_stats routine will be called after sample rows have been
- * gathered. Aside from this struct, it is passed:
- * fetchfunc: a function for accessing the column values from the
- * sample rows
- * samplerows: the number of sample tuples
- * totalrows: estimated total number of rows in relation
- * The fetchfunc may be called with rownum running from 0 to samplerows-1.
- * It returns a Datum and an isNull flag.
- *
- * compute_stats should set stats_valid TRUE if it is able to compute
- * any useful statistics. If it does, the remainder of the struct holds
- * the information to be stored in a pg_statistic row for the column. Be
- * careful to allocate any pointed-to data in anl_context, which will NOT
- * be CurrentMemoryContext when compute_stats is called.
- *
- * Note: for the moment, all comparisons done for statistical purposes
- * should use the database's default collation (DEFAULT_COLLATION_OID).
- * This might change in some future release.
- *----------
- */
-typedef struct VacAttrStats *VacAttrStatsP;
-
-typedef Datum (*AnalyzeAttrFetchFunc) (VacAttrStatsP stats, int rownum,
-
bool *isNull);
-
-typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
-
AnalyzeAttrFetchFunc fetchfunc,
-
int samplerows,
-
double totalrows);
-
-typedef struct VacAttrStats
-{
- /*
- * These fields are set up by the main ANALYZE code before invoking the
- * type-specific typanalyze function.
- *
- * Note: do not assume that the data being analyzed has the same
datatype
- * shown in attr, ie do not trust attr->atttypid, attlen, etc. This is
- * because some index opclasses store a different type than the
underlying
- * column/expression. Instead use attrtypid, attrtypmod, and attrtype
for
- * information about the datatype being fed to the typanalyze function.
- */
- Form_pg_attribute attr; /* copy of pg_attribute row for column
*/
- Oid attrtypid; /* type of data being
analyzed */
- int32 attrtypmod; /* typmod of data being
analyzed */
- Form_pg_type attrtype; /* copy of pg_type row for attrtypid */
- MemoryContext anl_context; /* where to save long-lived data */
-
- /*
- * These fields must be filled in by the typanalyze routine, unless it
- * returns FALSE.
- */
- AnalyzeAttrComputeStatsFunc compute_stats; /* function pointer */
- int minrows; /* Minimum # of rows
wanted for stats */
- void *extra_data; /* for extra type-specific data */
-
- /*
- * These fields are to be filled in by the compute_stats routine. (They
- * are initialized to zero when the struct is created.)
- */
- bool stats_valid;
- float4 stanullfrac; /* fraction of entries that are NULL */
- int32 stawidth; /* average width of column
values */
- float4 stadistinct; /* # distinct values */
- int16 stakind[STATISTIC_NUM_SLOTS];
- Oid staop[STATISTIC_NUM_SLOTS];
- int numnumbers[STATISTIC_NUM_SLOTS];
- float4 *stanumbers[STATISTIC_NUM_SLOTS];
- int numvalues[STATISTIC_NUM_SLOTS];
- Datum *stavalues[STATISTIC_NUM_SLOTS];
-
- /*
- * These fields describe the stavalues[n] element types. They will be
- * initialized to match attrtypid, but a custom typanalyze function
might
- * want to store an array of something other than the analyzed column's
- * elements. It should then overwrite these fields.
- */
- Oid statypid[STATISTIC_NUM_SLOTS];
- int16 statyplen[STATISTIC_NUM_SLOTS];
- bool statypbyval[STATISTIC_NUM_SLOTS];
- char statypalign[STATISTIC_NUM_SLOTS];
-
- /*
- * These fields are private to the main ANALYZE code and should not be
- * looked at by type-specific functions.
- */
- int tupattnum; /* attribute number
within tuples */
- HeapTuple *rows; /* access info for std fetch
function */
- TupleDesc tupDesc;
- Datum *exprvals; /* access info for index fetch function
*/
- bool *exprnulls;
- int rowstride;
-} VacAttrStats;
-
/*
* Parameters customizing behavior of VACUUM and ANALYZE.
*/
@@ -196,7 +87,6 @@ extern void lazy_vacuum_rel(Relation onerel, int options,
extern void analyze_rel(Oid relid, RangeVar *relation, int options,
VacuumParams *params, List *va_cols, bool in_outer_xact,
BufferAccessStrategy bstrategy);
-extern bool std_typanalyze(VacAttrStats *stats);
/* in utils/misc/sampling.c --- duplicate of declarations in utils/sampling.h
*/
extern double anl_random_fract(void);
diff --git a/src/include/statistics/analyze.h b/src/include/statistics/analyze.h
new file mode 100644
index 0000000..e3fa969
--- /dev/null
+++ b/src/include/statistics/analyze.h
@@ -0,0 +1,134 @@
+/*-------------------------------------------------------------------------
+ *
+ * analyze.h
+ * header file for postgres's ANALYZE statistics
+ *
+ *
+ * Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/statistics/analyze.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef STATISTICS_ANALYZE_H
+#define STATISTICS_ANALYZE_H
+
+#include "access/htup.h"
+#include "access/tupdesc.h"
+#include "catalog/pg_attribute.h"
+#include "catalog/pg_statistic.h"
+#include "catalog/pg_type.h"
+#include "nodes/parsenodes.h"
+
+
+/*----------
+ * ANALYZE builds one of these structs for each attribute (column) that is
+ * to be analyzed. The struct and subsidiary data are in anl_context,
+ * so they live until the end of the ANALYZE operation.
+ *
+ * The type-specific typanalyze function is passed a pointer to this struct
+ * and must return TRUE to continue analysis, FALSE to skip analysis of this
+ * column. In the TRUE case it must set the compute_stats and minrows fields,
+ * and can optionally set extra_data to pass additional info to compute_stats.
+ * minrows is its request for the minimum number of sample rows to be gathered
+ * (but note this request might not be honored, eg if there are fewer rows
+ * than that in the table).
+ *
+ * The compute_stats routine will be called after sample rows have been
+ * gathered. Aside from this struct, it is passed:
+ * fetchfunc: a function for accessing the column values from the
+ * sample rows
+ * samplerows: the number of sample tuples
+ * totalrows: estimated total number of rows in relation
+ * The fetchfunc may be called with rownum running from 0 to samplerows-1.
+ * It returns a Datum and an isNull flag.
+ *
+ * compute_stats should set stats_valid TRUE if it is able to compute
+ * any useful statistics. If it does, the remainder of the struct holds
+ * the information to be stored in a pg_statistic row for the column. Be
+ * careful to allocate any pointed-to data in anl_context, which will NOT
+ * be CurrentMemoryContext when compute_stats is called.
+ *
+ * Note: for the moment, all comparisons done for statistical purposes
+ * should use the database's default collation (DEFAULT_COLLATION_OID).
+ * This might change in some future release.
+ *----------
+ */
+typedef struct VacAttrStats *VacAttrStatsP;
+
+typedef Datum (*AnalyzeAttrFetchFunc) (VacAttrStatsP stats, int rownum,
+
bool *isNull);
+
+typedef void (*AnalyzeAttrComputeStatsFunc) (VacAttrStatsP stats,
+
AnalyzeAttrFetchFunc fetchfunc,
+
int samplerows,
+
double totalrows);
+
+typedef struct VacAttrStats
+{
+ /*
+ * These fields are set up by the main ANALYZE code before invoking the
+ * type-specific typanalyze function.
+ *
+ * Note: do not assume that the data being analyzed has the same
datatype
+ * shown in attr, ie do not trust attr->atttypid, attlen, etc. This is
+ * because some index opclasses store a different type than the
underlying
+ * column/expression. Instead use attrtypid, attrtypmod, and attrtype
for
+ * information about the datatype being fed to the typanalyze function.
+ */
+ Form_pg_attribute attr; /* copy of pg_attribute row for column
*/
+ Oid attrtypid; /* type of data being
analyzed */
+ int32 attrtypmod; /* typmod of data being
analyzed */
+ Form_pg_type attrtype; /* copy of pg_type row for attrtypid */
+ MemoryContext anl_context; /* where to save long-lived data */
+
+ /*
+ * These fields must be filled in by the typanalyze routine, unless it
+ * returns FALSE.
+ */
+ AnalyzeAttrComputeStatsFunc compute_stats; /* function pointer */
+ int minrows; /* Minimum # of rows
wanted for stats */
+ void *extra_data; /* for extra type-specific data */
+
+ /*
+ * These fields are to be filled in by the compute_stats routine. (They
+ * are initialized to zero when the struct is created.)
+ */
+ bool stats_valid;
+ float4 stanullfrac; /* fraction of entries that are NULL */
+ int32 stawidth; /* average width of column
values */
+ float4 stadistinct; /* # distinct values */
+ int16 stakind[STATISTIC_NUM_SLOTS];
+ Oid staop[STATISTIC_NUM_SLOTS];
+ int numnumbers[STATISTIC_NUM_SLOTS];
+ float4 *stanumbers[STATISTIC_NUM_SLOTS];
+ int numvalues[STATISTIC_NUM_SLOTS];
+ Datum *stavalues[STATISTIC_NUM_SLOTS];
+
+ /*
+ * These fields describe the stavalues[n] element types. They will be
+ * initialized to match attrtypid, but a custom typanalyze function
might
+ * want to store an array of something other than the analyzed column's
+ * elements. It should then overwrite these fields.
+ */
+ Oid statypid[STATISTIC_NUM_SLOTS];
+ int16 statyplen[STATISTIC_NUM_SLOTS];
+ bool statypbyval[STATISTIC_NUM_SLOTS];
+ char statypalign[STATISTIC_NUM_SLOTS];
+
+ /*
+ * These fields are private to the main ANALYZE code and should not be
+ * looked at by type-specific functions.
+ */
+ int tupattnum; /* attribute number
within tuples */
+ HeapTuple *rows; /* access info for std fetch
function */
+ TupleDesc tupDesc;
+ Datum *exprvals; /* access info for index fetch function
*/
+ bool *exprnulls;
+ int rowstride;
+} VacAttrStats;
+
+extern bool std_typanalyze(VacAttrStats *stats);
+
+#endif /* STATISTICS_ANALYZE_H */
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
