public inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v56 5/6] Remove the GUC stats_temp_directory
4+ messages / 3 participants
[nested] [flat]

* [PATCH v56 5/6] Remove the GUC stats_temp_directory
@ 2020-09-29 13:59 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 4+ messages in thread

From: Kyotaro Horiguchi @ 2020-09-29 13:59 UTC (permalink / raw)

The new stats collection system doesn't need temporary directory, so
just remove it. pg_stat_statements modified to use pg_stat directory
to store its temporary files.  As the result basebackup copies the
pg_stat_statments' temporary file if exists.
---
 .../pg_stat_statements/pg_stat_statements.c   | 13 +++---
 doc/src/sgml/backup.sgml                      |  2 -
 doc/src/sgml/config.sgml                      | 19 --------
 doc/src/sgml/storage.sgml                     |  6 ---
 src/backend/postmaster/pgstat.c               | 10 -----
 src/backend/replication/basebackup.c          | 36 ----------------
 src/backend/utils/misc/guc.c                  | 43 -------------------
 src/backend/utils/misc/postgresql.conf.sample |  1 -
 src/bin/initdb/initdb.c                       |  1 -
 src/bin/pg_rewind/filemap.c                   |  7 ---
 src/include/pgstat.h                          |  3 --
 src/test/perl/PostgresNode.pm                 |  4 --
 12 files changed, 6 insertions(+), 139 deletions(-)

diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c
index 62cccbfa44..28279f97d5 100644
--- a/contrib/pg_stat_statements/pg_stat_statements.c
+++ b/contrib/pg_stat_statements/pg_stat_statements.c
@@ -89,14 +89,13 @@ PG_MODULE_MAGIC;
 #define PGSS_DUMP_FILE	PGSTAT_STAT_PERMANENT_DIRECTORY "/pg_stat_statements.stat"
 
 /*
- * Location of external query text file.  We don't keep it in the core
- * system's stats_temp_directory.  The core system can safely use that GUC
- * setting, because the statistics collector temp file paths are set only once
- * as part of changing the GUC, but pg_stat_statements has no way of avoiding
- * race conditions.  Besides, we only expect modest, infrequent I/O for query
- * strings, so placing the file on a faster filesystem is not compelling.
+ * Location of external query text file.  We don't keep it in the core system's
+ * pg_stats.  pg_stat_statements has no way of avoiding race conditions even if
+ * the directory were specified by a GUC.  Besides, we only expect modest,
+ * infrequent I/O for query strings, so placing the file on a faster filesystem
+ * is not compelling.
  */
-#define PGSS_TEXT_FILE	PG_STAT_TMP_DIR "/pgss_query_texts.stat"
+#define PGSS_TEXT_FILE	PGSTAT_STAT_PERMANENT_DIRECTORY "/pgss_query_texts.stat"
 
 /* Magic number identifying the stats file format */
 static const uint32 PGSS_FILE_HEADER = 0x20201218;
diff --git a/doc/src/sgml/backup.sgml b/doc/src/sgml/backup.sgml
index c5557d5444..875769a57e 100644
--- a/doc/src/sgml/backup.sgml
+++ b/doc/src/sgml/backup.sgml
@@ -1155,8 +1155,6 @@ SELECT pg_stop_backup();
     <filename>pg_snapshots/</filename>, <filename>pg_stat_tmp/</filename>,
     and <filename>pg_subtrans/</filename> (but not the directories themselves) can be
     omitted from the backup as they will be initialized on postmaster startup.
-    If <xref linkend="guc-stats-temp-directory"/> is set and is under the data
-    directory then the contents of that directory can also be omitted.
    </para>
 
    <para>
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 53d7dfda93..9a749447ec 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -7509,25 +7509,6 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
       </listitem>
      </varlistentry>
 
-     <varlistentry id="guc-stats-temp-directory" xreflabel="stats_temp_directory">
-      <term><varname>stats_temp_directory</varname> (<type>string</type>)
-      <indexterm>
-       <primary><varname>stats_temp_directory</varname> configuration parameter</primary>
-      </indexterm>
-      </term>
-      <listitem>
-       <para>
-        Sets the directory to store temporary statistics data in. This can be
-        a path relative to the data directory or an absolute path. The default
-        is <filename>pg_stat_tmp</filename>. Pointing this at a RAM-based
-        file system will decrease physical I/O requirements and can lead to
-        improved performance.
-        This parameter can only be set in the <filename>postgresql.conf</filename>
-        file or on the server command line.
-       </para>
-      </listitem>
-     </varlistentry>
-
      </variablelist>
     </sect2>
 
diff --git a/doc/src/sgml/storage.sgml b/doc/src/sgml/storage.sgml
index 3234adb639..6bac5e075e 100644
--- a/doc/src/sgml/storage.sgml
+++ b/doc/src/sgml/storage.sgml
@@ -120,12 +120,6 @@ Item
   subsystem</entry>
 </row>
 
-<row>
- <entry><filename>pg_stat_tmp</filename></entry>
- <entry>Subdirectory containing temporary files for the statistics
-  subsystem</entry>
-</row>
-
 <row>
  <entry><filename>pg_subtrans</filename></entry>
  <entry>Subdirectory containing subtransaction status data</entry>
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index 575ecdd502..c09fa026b9 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -99,16 +99,6 @@ bool		pgstat_track_counts = false;
 int			pgstat_track_functions = TRACK_FUNC_OFF;
 int			pgstat_track_activity_query_size = 1024;
 
-/* ----------
- * Built from GUC parameter
- * ----------
- */
-char      *pgstat_stat_directory = NULL;
-
-/* No longer used, but will be removed with GUC */
-char      *pgstat_stat_filename = NULL;
-char      *pgstat_stat_tmpname = NULL;
-
 /*
  * WAL usage counters saved from pgWALUsage at the previous call to
  * pgstat_report_wal(). This is used to calculate how much WAL usage
diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c
index fa7bdbcefa..f0d75f55bd 100644
--- a/src/backend/replication/basebackup.c
+++ b/src/backend/replication/basebackup.c
@@ -87,9 +87,6 @@ static int	basebackup_read_file(int fd, char *buf, size_t nbytes, off_t offset,
 /* Was the backup currently in-progress initiated in recovery mode? */
 static bool backup_started_in_recovery = false;
 
-/* Relative path of temporary statistics directory */
-static char *statrelpath = NULL;
-
 /*
  * Size of each block sent into the tar stream for larger files.
  */
@@ -152,13 +149,6 @@ struct exclude_list_item
  */
 static const char *const excludeDirContents[] =
 {
-	/*
-	 * Skip temporary statistics files. PG_STAT_TMP_DIR must be skipped even
-	 * when stats_temp_directory is set because PGSS_TEXT_FILE is always
-	 * created there.
-	 */
-	PG_STAT_TMP_DIR,
-
 	/*
 	 * It is generally not useful to backup the contents of this directory
 	 * even if the intention is to restore to another primary. See backup.sgml
@@ -261,7 +251,6 @@ perform_base_backup(basebackup_options *opt)
 	StringInfo	labelfile;
 	StringInfo	tblspc_map_file;
 	backup_manifest_info manifest;
-	int			datadirpathlen;
 	List	   *tablespaces = NIL;
 
 	backup_total = 0;
@@ -284,8 +273,6 @@ perform_base_backup(basebackup_options *opt)
 	Assert(CurrentResourceOwner == NULL);
 	CurrentResourceOwner = ResourceOwnerCreate(NULL, "base backup");
 
-	datadirpathlen = strlen(DataDir);
-
 	backup_started_in_recovery = RecoveryInProgress();
 
 	labelfile = makeStringInfo();
@@ -314,18 +301,6 @@ perform_base_backup(basebackup_options *opt)
 		tablespaceinfo *ti;
 		int			tblspc_streamed = 0;
 
-		/*
-		 * Calculate the relative path of temporary statistics directory in
-		 * order to skip the files which are located in that directory later.
-		 */
-		if (is_absolute_path(pgstat_stat_directory) &&
-			strncmp(pgstat_stat_directory, DataDir, datadirpathlen) == 0)
-			statrelpath = psprintf("./%s", pgstat_stat_directory + datadirpathlen + 1);
-		else if (strncmp(pgstat_stat_directory, "./", 2) != 0)
-			statrelpath = psprintf("./%s", pgstat_stat_directory);
-		else
-			statrelpath = pgstat_stat_directory;
-
 		/* Add a node for the base directory at the end */
 		ti = palloc0(sizeof(tablespaceinfo));
 		ti->size = -1;
@@ -1377,17 +1352,6 @@ sendDir(const char *path, int basepathlen, bool sizeonly, List *tablespaces,
 		if (excludeFound)
 			continue;
 
-		/*
-		 * Exclude contents of directory specified by statrelpath if not set
-		 * to the default (pg_stat_tmp) which is caught in the loop above.
-		 */
-		if (statrelpath != NULL && strcmp(pathbuf, statrelpath) == 0)
-		{
-			elog(DEBUG1, "contents of directory \"%s\" excluded from backup", statrelpath);
-			size += _tarWriteDir(pathbuf, basepathlen, &statbuf, sizeonly);
-			continue;
-		}
-
 		/*
 		 * We can skip pg_wal, the WAL segments need to be fetched from the
 		 * WAL archive anyway. But include it as an empty directory anyway, so
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index b22fa6b86e..99bca927ce 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -203,7 +203,6 @@ static bool check_autovacuum_work_mem(int *newval, void **extra, GucSource sourc
 static bool check_effective_io_concurrency(int *newval, void **extra, GucSource source);
 static bool check_maintenance_io_concurrency(int *newval, void **extra, GucSource source);
 static bool check_huge_page_size(int *newval, void **extra, GucSource source);
-static void assign_pgstat_temp_directory(const char *newval, void *extra);
 static bool check_application_name(char **newval, void **extra, GucSource source);
 static void assign_application_name(const char *newval, void *extra);
 static bool check_cluster_name(char **newval, void **extra, GucSource source);
@@ -560,8 +559,6 @@ char	   *HbaFileName;
 char	   *IdentFileName;
 char	   *external_pid_file;
 
-char	   *pgstat_temp_directory;
-
 char	   *application_name;
 
 int			tcp_keepalives_idle;
@@ -4365,17 +4362,6 @@ static struct config_string ConfigureNamesString[] =
 		NULL, NULL, NULL
 	},
 
-	{
-		{"stats_temp_directory", PGC_SIGHUP, STATS_ACTIVITY,
-			gettext_noop("Writes temporary statistics files to the specified directory."),
-			NULL,
-			GUC_SUPERUSER_ONLY
-		},
-		&pgstat_temp_directory,
-		PG_STAT_TMP_DIR,
-		check_canonical_path, assign_pgstat_temp_directory, NULL
-	},
-
 	{
 		{"synchronous_standby_names", PGC_SIGHUP, REPLICATION_PRIMARY,
 			gettext_noop("Number of synchronous standbys and list of names of potential synchronous ones."),
@@ -11781,35 +11767,6 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 	return true;
 }
 
-static void
-assign_pgstat_temp_directory(const char *newval, void *extra)
-{
-	/* check_canonical_path already canonicalized newval for us */
-	char	   *dname;
-	char	   *tname;
-	char	   *fname;
-
-	/* directory */
-	dname = guc_malloc(ERROR, strlen(newval) + 1);	/* runtime dir */
-	sprintf(dname, "%s", newval);
-
-	/* global stats */
-	tname = guc_malloc(ERROR, strlen(newval) + 12); /* /global.tmp */
-	sprintf(tname, "%s/global.tmp", newval);
-	fname = guc_malloc(ERROR, strlen(newval) + 13); /* /global.stat */
-	sprintf(fname, "%s/global.stat", newval);
-
-	if (pgstat_stat_directory)
-		free(pgstat_stat_directory);
-	pgstat_stat_directory = dname;
-	if (pgstat_stat_tmpname)
-		free(pgstat_stat_tmpname);
-	pgstat_stat_tmpname = tname;
-	if (pgstat_stat_filename)
-		free(pgstat_stat_filename);
-	pgstat_stat_filename = fname;
-}
-
 static bool
 check_application_name(char **newval, void **extra, GucSource source)
 {
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index b0e73024a1..92aace4208 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -589,7 +589,6 @@
 #track_wal_io_timing = off
 #track_functions = none			# none, pl, all
 #track_activity_query_size = 1024	# (change requires restart)
-#stats_temp_directory = 'pg_stat_tmp'
 
 
 # - Monitoring -
diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c
index 3c1cf78b4f..07a00b8d0d 100644
--- a/src/bin/initdb/initdb.c
+++ b/src/bin/initdb/initdb.c
@@ -219,7 +219,6 @@ static const char *const subdirs[] = {
 	"pg_replslot",
 	"pg_tblspc",
 	"pg_stat",
-	"pg_stat_tmp",
 	"pg_xact",
 	"pg_logical",
 	"pg_logical/snapshots",
diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 2618b4c957..ab5cb51de7 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -87,13 +87,6 @@ struct exclude_list_item
  */
 static const char *excludeDirContents[] =
 {
-	/*
-	 * Skip temporary statistics files. PG_STAT_TMP_DIR must be skipped even
-	 * when stats_temp_directory is set because PGSS_TEXT_FILE is always
-	 * created there.
-	 */
-	"pg_stat_tmp",				/* defined as PG_STAT_TMP_DIR */
-
 	/*
 	 * It is generally not useful to backup the contents of this directory
 	 * even if the intention is to restore to another primary. See backup.sgml
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index f4177eb284..e1c54e73f2 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -33,9 +33,6 @@
 #define PGSTAT_STAT_PERMANENT_FILENAME		"pg_stat/saved_stats"
 #define PGSTAT_STAT_PERMANENT_TMPFILE		"pg_stat/saved_stats.tmp"
 
-/* Default directory to store temporary statistics data in */
-#define PG_STAT_TMP_DIR                "pg_stat_tmp"
-
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
diff --git a/src/test/perl/PostgresNode.pm b/src/test/perl/PostgresNode.pm
index 9667f7667e..dd41a43b4e 100644
--- a/src/test/perl/PostgresNode.pm
+++ b/src/test/perl/PostgresNode.pm
@@ -455,10 +455,6 @@ sub init
 	print $conf TestLib::slurp_file($ENV{TEMP_CONFIG})
 	  if defined $ENV{TEMP_CONFIG};
 
-	# XXX Neutralize any stats_temp_directory in TEMP_CONFIG.  Nodes running
-	# concurrently must not share a stats_temp_directory.
-	print $conf "stats_temp_directory = 'pg_stat_tmp'\n";
-
 	if ($params{allows_streaming})
 	{
 		if ($params{allows_streaming} eq "logical")
-- 
2.27.0


----Next_Part(Tue_Mar_16_10_27_55_2021_500)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v56-0006-Exclude-pg_stat-directory-from-base-backup.patch"



^ permalink  raw  reply  [nested|flat] 4+ messages in thread

* Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs
@ 2023-03-24 20:12 Tom Lane <[email protected]>
  2023-07-07 17:42 ` Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs Daniel Verite <[email protected]>
  0 siblings, 1 reply; 4+ messages in thread

From: Tom Lane @ 2023-03-24 20:12 UTC (permalink / raw)
  To: Daniel Verite <[email protected]>; +Cc: pgsql-hackers; Robert Haas <[email protected]>; Jakub Wartak <[email protected]>

"Daniel Verite" <[email protected]> writes:
> PFA an updated patch.

This gives me several "-Wincompatible-pointer-types" warnings
(as are also reported by the cfbot):

common.c: In function 'ExecQueryAndProcessResults':
common.c:1686:24: warning: passing argument 1 of 'PrintQueryTuples' from incompatible pointer type [-Wincompatible-pointer-types]
       PrintQueryTuples(result_array, ntuples, &my_popt, tuples_fout);
                        ^~~~~~~~~~~~
common.c:679:35: note: expected 'const PGresult **' {aka 'const struct pg_result **'} but argument is of type 'PGresult **' {aka 'struct pg_result **'}
 PrintQueryTuples(const PGresult **result, int nresults, const printQueryOpt *opt,
                  ~~~~~~~~~~~~~~~~~^~~~~~
common.c:1720:24: warning: passing argument 1 of 'PrintQueryTuples' from incompatible pointer type [-Wincompatible-pointer-types]
       PrintQueryTuples(result_array, ntuples, &my_popt, tuples_fout);
                        ^~~~~~~~~~~~
common.c:679:35: note: expected 'const PGresult **' {aka 'const struct pg_result **'} but argument is of type 'PGresult **' {aka 'struct pg_result **'}
 PrintQueryTuples(const PGresult **result, int nresults, const printQueryOpt *opt,
                  ~~~~~~~~~~~~~~~~~^~~~~~

I think the cause is the inconsistency about whether PGresult pointers
are pointer-to-const or not.  Even without compiler warnings, I find
code like this very ugly:

-				success = PrintQueryTuples(result, opt, printQueryFout);
+				success = PrintQueryTuples((const PGresult**)&result, 1, opt, printQueryFout);

I think what you probably ought to do to avoid all that is to change
the arguments of PrintQueryResult and nearby routines to be "const
PGresult *result" not just "PGresult *result".

I find it sad that we can't get rid of ExecQueryUsingCursor().
Maybe a little effort towards reducing overhead in the single-row
mode would help?

			regards, tom lane






^ permalink  raw  reply  [nested|flat] 4+ messages in thread

* Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs
  2023-03-24 20:12 Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs Tom Lane <[email protected]>
@ 2023-07-07 17:42 ` Daniel Verite <[email protected]>
  2023-11-20 19:13   ` Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs Daniel Verite <[email protected]>
  0 siblings, 1 reply; 4+ messages in thread

From: Daniel Verite @ 2023-07-07 17:42 UTC (permalink / raw)
  To: Tom Lane <[email protected]>; +Cc: pgsql-hackers; Robert Haas <[email protected]>; Jakub Wartak <[email protected]>

	Tom Lane wrote:

> This gives me several "-Wincompatible-pointer-types" warnings
> [...]
> I think what you probably ought to do to avoid all that is to change
> the arguments of PrintQueryResult and nearby routines to be "const
> PGresult *result" not just "PGresult *result".

The const-ness issue that I ignored in the previous patch is that
while C is fine with passing T* to a function expecting const T*, it's
not okay with passing T** to a function expecting const T**,
or more generally converting T** to const T**.

When callers need to pass arrays of PGresult* instead of const
PGresult*, I've opted to remove the const qualifiers for the functions
that are concerned by this change.


PFA an updated patch.


Best regards,
-- 
Daniel Vérité
https://postgresql.verite.pro/
Twitter: @DanielVerite


Attachments:

  [text/x-patch] psql-fetchcount-single-row-mode-v3.diff (12.2K, ../../[email protected]/2-psql-fetchcount-single-row-mode-v3.diff)
  download | inline diff:
diff --git a/src/bin/psql/common.c b/src/bin/psql/common.c
index 5973df2e39..476a9770f0 100644
--- a/src/bin/psql/common.c
+++ b/src/bin/psql/common.c
@@ -372,6 +372,7 @@ AcceptResult(const PGresult *result, bool show_error)
 		{
 			case PGRES_COMMAND_OK:
 			case PGRES_TUPLES_OK:
+			case PGRES_SINGLE_TUPLE:
 			case PGRES_EMPTY_QUERY:
 			case PGRES_COPY_IN:
 			case PGRES_COPY_OUT:
@@ -695,7 +696,7 @@ PrintNotifications(void)
  * Returns true if successful, false otherwise.
  */
 static bool
-PrintQueryTuples(const PGresult *result, const printQueryOpt *opt,
+PrintQueryTuples(PGresult *result, const printQueryOpt *opt,
 				 FILE *printQueryFout)
 {
 	bool		ok = true;
@@ -1391,6 +1392,47 @@ DescribeQuery(const char *query, double *elapsed_msec)
 	return OK;
 }
 
+/*
+ * Check if an output stream for \g needs to be opened, and if
+ * yes, open it.
+ * Return false if an error occurred, true otherwise.
+ */
+static bool
+SetupGOutput(PGresult *result, FILE **gfile_fout, bool *is_pipe)
+{
+	ExecStatusType status = PQresultStatus(result);
+	if (pset.gfname != NULL &&			/* there is a \g file or program */
+		*gfile_fout == NULL &&           /* and it's not already opened */
+		(status == PGRES_TUPLES_OK ||
+		 status == PGRES_SINGLE_TUPLE ||
+		 status == PGRES_COPY_OUT))
+	{
+		if (openQueryOutputFile(pset.gfname, gfile_fout, is_pipe))
+		{
+			if (is_pipe)
+				disable_sigpipe_trap();
+		}
+		else
+			return false;
+	}
+	return true;
+}
+
+static void
+CloseGOutput(FILE *gfile_fout, bool is_pipe)
+{
+	/* close \g file if we opened it */
+	if (gfile_fout)
+	{
+		if (is_pipe)
+		{
+			SetShellResultVariables(pclose(gfile_fout));
+			restore_sigpipe_trap();
+		}
+		else
+			fclose(gfile_fout);
+	}
+}
 
 /*
  * ExecQueryAndProcessResults: utility function for use by SendQuery()
@@ -1422,10 +1464,18 @@ ExecQueryAndProcessResults(const char *query,
 	bool		success;
 	instr_time	before,
 				after;
+	int fetch_count = pset.fetch_count;
 	PGresult   *result;
+
 	FILE	   *gfile_fout = NULL;
 	bool		gfile_is_pipe = false;
 
+	PGresult   **result_array = NULL; /* to collect results in single row mode */
+	int64		total_tuples = 0;
+	int			ntuples;
+	int			flush_error = 0;
+	bool		is_pager = false;
+
 	if (timing)
 		INSTR_TIME_SET_CURRENT(before);
 	else
@@ -1448,6 +1498,33 @@ ExecQueryAndProcessResults(const char *query,
 		return -1;
 	}
 
+	/*
+	 * If FETCH_COUNT is set and the context allows it, use the single row
+	 * mode to fetch results and have no more than FETCH_COUNT rows in
+	 * memory.
+	 */
+	if (fetch_count > 0 && !pset.crosstab_flag && !pset.gexec_flag && !is_watch
+		&& !pset.gset_prefix && pset.show_all_results)
+	{
+		/*
+		 * The row-by-row fetch is not enabled when SHOW_ALL_RESULTS is false,
+		 * since we would need to accumulate all rows before knowing
+		 * whether they need to be discarded or displayed, which contradicts
+		 * FETCH_COUNT.
+		 */
+		if (!PQsetSingleRowMode(pset.db))
+		{
+			pg_log_warning("fetching results in single row mode is unavailable");
+			fetch_count = 0;
+		}
+		else
+		{
+			result_array = (PGresult**) pg_malloc(fetch_count * sizeof(PGresult*));
+		}
+	}
+	else
+		fetch_count = 0;		/* disable single-row mode */
+
 	/*
 	 * If SIGINT is sent while the query is processing, the interrupt will be
 	 * consumed.  The user's intention, though, is to cancel the entire watch
@@ -1467,6 +1544,8 @@ ExecQueryAndProcessResults(const char *query,
 		ExecStatusType result_status;
 		PGresult   *next_result;
 		bool		last;
+		/* whether the output starts before results are fully fetched */
+		bool		partial_display = false;
 
 		if (!AcceptResult(result, false))
 		{
@@ -1593,6 +1672,94 @@ ExecQueryAndProcessResults(const char *query,
 			success &= HandleCopyResult(&result, copy_stream);
 		}
 
+		if (fetch_count > 0 && result_status == PGRES_SINGLE_TUPLE)
+		{
+			FILE	   *tuples_fout = printQueryFout ? printQueryFout : stdout;
+			printQueryOpt my_popt = pset.popt;
+
+			ntuples = 0;
+			total_tuples = 0;
+			partial_display = true;
+
+			success = SetupGOutput(result, &gfile_fout, &gfile_is_pipe);
+			if (gfile_fout)
+				tuples_fout = gfile_fout;
+
+			/* initialize print options for partial table output */
+			my_popt.topt.start_table = true;
+			my_popt.topt.stop_table = false;
+			my_popt.topt.prior_records = 0;
+
+			while (success)
+			{
+				result_array[ntuples++] = result;
+				if (ntuples == fetch_count)
+				{
+					/* pager: open at most once per resultset */
+					if (tuples_fout == stdout && !is_pager)
+					{
+						tuples_fout = PageOutput(INT_MAX, &(my_popt.topt));
+						is_pager = true;
+					}
+					/* display the current chunk of results unless the output stream is not working */
+					if (!flush_error)
+					{
+						printQueryChunks(result_array, ntuples, &my_popt, tuples_fout,
+										 is_pager, pset.logfile);
+						flush_error = fflush(tuples_fout);
+					}
+					/* clear and reuse result_array */
+					for (int i=0; i < ntuples; i++)
+						PQclear(result_array[i]);
+					/* after the first result set, disallow header decoration */
+					my_popt.topt.start_table = false;
+					my_popt.topt.prior_records += ntuples;
+					total_tuples += ntuples;
+					ntuples = 0;
+				}
+
+				result = PQgetResult(pset.db);
+				if (result == NULL)
+				{
+					/*
+					 * Error. We expect a PGRES_TUPLES_OK result with
+					 * zero tuple in it to finish the row-by-row sequence.
+					 */
+					success = false;
+					break;
+				}
+
+				if (PQresultStatus(result) == PGRES_TUPLES_OK)
+				{
+					/*
+					 * The last row has been read. Display the last chunk of
+					 * results and the footer.
+					 */
+					my_popt.topt.stop_table = true;
+					if (!flush_error)
+					{
+						printQueryChunks(result_array, ntuples, &my_popt, tuples_fout,
+										 is_pager, pset.logfile);
+						flush_error = fflush(tuples_fout);
+					}
+					for (int i=0; i < ntuples; i++)
+						PQclear(result_array[i]);
+					total_tuples += ntuples;
+					ntuples = 0;
+
+					if (is_pager)
+					{
+						ClosePager(tuples_fout);
+					}
+
+					result = NULL;
+					break;
+				}
+			}
+		}
+		else
+			partial_display = false;
+
 		/*
 		 * Check PQgetResult() again.  In the typical case of a single-command
 		 * string, it will return NULL.  Otherwise, we'll have other results
@@ -1621,7 +1788,7 @@ ExecQueryAndProcessResults(const char *query,
 		}
 
 		/* this may or may not print something depending on settings */
-		if (result != NULL)
+		if (result != NULL && !partial_display)
 		{
 			/*
 			 * If results need to be printed into the file specified by \g,
@@ -1630,32 +1797,31 @@ ExecQueryAndProcessResults(const char *query,
 			 * tuple output, but it's still used for status output.
 			 */
 			FILE	   *tuples_fout = printQueryFout;
-			bool		do_print = true;
-
-			if (PQresultStatus(result) == PGRES_TUPLES_OK &&
-				pset.gfname)
-			{
-				if (gfile_fout == NULL)
-				{
-					if (openQueryOutputFile(pset.gfname,
-											&gfile_fout, &gfile_is_pipe))
-					{
-						if (gfile_is_pipe)
-							disable_sigpipe_trap();
-					}
-					else
-						success = do_print = false;
-				}
+			success = SetupGOutput(result, &gfile_fout, &gfile_is_pipe);
+			if (gfile_fout)
 				tuples_fout = gfile_fout;
-			}
-			if (do_print)
+			if (success)
 				success &= PrintQueryResult(result, last, opt,
 											tuples_fout, printQueryFout);
 		}
 
 		/* set variables on last result if all went well */
 		if (!is_watch && last && success)
+		{
 			SetResultVariables(result, true);
+			if (partial_display)
+			{
+				/*
+				 * fake SetResultVariables() as in ExecQueryUsingCursor().
+				 */
+				char		buf[32];
+
+				SetVariable(pset.vars, "ERROR", "false");
+				SetVariable(pset.vars, "SQLSTATE", "00000");
+				snprintf(buf, sizeof(buf), INT64_FORMAT, total_tuples);
+				SetVariable(pset.vars, "ROW_COUNT", buf);
+			}
+		}
 
 		ClearOrSaveResult(result);
 		result = next_result;
@@ -1667,17 +1833,10 @@ ExecQueryAndProcessResults(const char *query,
 		}
 	}
 
-	/* close \g file if we opened it */
-	if (gfile_fout)
-	{
-		if (gfile_is_pipe)
-		{
-			SetShellResultVariables(pclose(gfile_fout));
-			restore_sigpipe_trap();
-		}
-		else
-			fclose(gfile_fout);
-	}
+	CloseGOutput(gfile_fout, gfile_is_pipe);
+
+	if (result_array)
+		pg_free(result_array);
 
 	/* may need this to recover from conn loss during COPY */
 	if (!CheckConnection())
diff --git a/src/fe_utils/print.c b/src/fe_utils/print.c
index 7af1ccb6b5..35f4f3d398 100644
--- a/src/fe_utils/print.c
+++ b/src/fe_utils/print.c
@@ -3532,19 +3532,44 @@ printTable(const printTableContent *cont,
  * flog: if not null, also print the data there (for --log-file option)
  */
 void
-printQuery(const PGresult *result, const printQueryOpt *opt,
+printQuery(PGresult *result, const printQueryOpt *opt,
 		   FILE *fout, bool is_pager, FILE *flog)
+{
+	printQueryChunks(&result, 1, opt, fout, is_pager, flog);
+}
+
+/*
+ * Print the results of a query that may have been obtained by a
+ * succession of calls to PQgetResult in single-row mode.
+ *
+ * results: array of results of a successful query. They must have the same columns.
+ * nbresults: size of results
+ * opt: formatting options
+ * fout: where to print to
+ * is_pager: true if caller has already redirected fout to be a pager pipe
+ * flog: if not null, also print the data there (for --log-file option)
+ */
+void
+printQueryChunks(PGresult *results[], int nresults, const printQueryOpt *opt,
+				 FILE *fout, bool is_pager, FILE *flog)
 {
 	printTableContent cont;
 	int			i,
 				r,
 				c;
+	int			nrows = 0;		/* total number of rows */
+	int			ri;				/* index into results[] */
 
 	if (cancel_pressed)
 		return;
 
+	for (ri = 0; ri < nresults; ri++)
+	{
+		nrows += PQntuples(results[ri]);
+	}
+
 	printTableInit(&cont, &opt->topt, opt->title,
-				   PQnfields(result), PQntuples(result));
+				   (nresults > 0) ? PQnfields(results[0]) : 0, nrows);
 
 	/* Assert caller supplied enough translate_columns[] entries */
 	Assert(opt->translate_columns == NULL ||
@@ -3552,34 +3577,37 @@ printQuery(const PGresult *result, const printQueryOpt *opt,
 
 	for (i = 0; i < cont.ncolumns; i++)
 	{
-		printTableAddHeader(&cont, PQfname(result, i),
+		printTableAddHeader(&cont, PQfname(results[0], i),
 							opt->translate_header,
-							column_type_alignment(PQftype(result, i)));
+							column_type_alignment(PQftype(results[0], i)));
 	}
 
 	/* set cells */
-	for (r = 0; r < cont.nrows; r++)
+	for (ri = 0; ri < nresults; ri++)
 	{
-		for (c = 0; c < cont.ncolumns; c++)
+		for (r = 0; r < PQntuples(results[ri]); r++)
 		{
-			char	   *cell;
-			bool		mustfree = false;
-			bool		translate;
-
-			if (PQgetisnull(result, r, c))
-				cell = opt->nullPrint ? opt->nullPrint : "";
-			else
+			for (c = 0; c < cont.ncolumns; c++)
 			{
-				cell = PQgetvalue(result, r, c);
-				if (cont.aligns[c] == 'r' && opt->topt.numericLocale)
+				char	   *cell;
+				bool		mustfree = false;
+				bool		translate;
+
+				if (PQgetisnull(results[ri], r, c))
+					cell = opt->nullPrint ? opt->nullPrint : "";
+				else
 				{
-					cell = format_numeric_locale(cell);
-					mustfree = true;
+					cell = PQgetvalue(results[ri], r, c);
+					if (cont.aligns[c] == 'r' && opt->topt.numericLocale)
+					{
+						cell = format_numeric_locale(cell);
+						mustfree = true;
+					}
 				}
-			}
 
-			translate = (opt->translate_columns && opt->translate_columns[c]);
-			printTableAddCell(&cont, cell, translate, mustfree);
+				translate = (opt->translate_columns && opt->translate_columns[c]);
+				printTableAddCell(&cont, cell, translate, mustfree);
+			}
 		}
 	}
 
diff --git a/src/include/fe_utils/print.h b/src/include/fe_utils/print.h
index cc6652def9..4d73aad251 100644
--- a/src/include/fe_utils/print.h
+++ b/src/include/fe_utils/print.h
@@ -224,8 +224,11 @@ extern void printTableSetFooter(printTableContent *const content,
 extern void printTableCleanup(printTableContent *const content);
 extern void printTable(const printTableContent *cont,
 					   FILE *fout, bool is_pager, FILE *flog);
-extern void printQuery(const PGresult *result, const printQueryOpt *opt,
+extern void printQuery(PGresult *result, const printQueryOpt *opt,
 					   FILE *fout, bool is_pager, FILE *flog);
+extern void printQueryChunks(PGresult *results[], int nresults,
+							 const printQueryOpt *opt,
+							 FILE *fout, bool is_pager, FILE *flog);
 
 extern char column_type_alignment(Oid);
 


^ permalink  raw  reply  [nested|flat] 4+ messages in thread

* Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs
  2023-03-24 20:12 Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs Tom Lane <[email protected]>
  2023-07-07 17:42 ` Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs Daniel Verite <[email protected]>
@ 2023-11-20 19:13   ` Daniel Verite <[email protected]>
  0 siblings, 0 replies; 4+ messages in thread

From: Daniel Verite @ 2023-11-20 19:13 UTC (permalink / raw)
  To: pgsql-hackers

 Hi,

Here's a new version to improve the performance of FETCH_COUNT
and extend the cases when it can be used.

Patch 0001 adds a new mode in libpq to allow the app to retrieve
larger chunks of results than the single row of the row-by-row mode.
The maximum number of rows per PGresult is set by the user.

Patch 0002 uses that mode in psql and gets rid of the cursor
implementation as suggested upthread.

The performance numbers look good.
For a query retrieving 50M rows of about 200 bytes:
  select repeat('abc', 200) from generate_series(1,5000000)
/usr/bin/time -v psql -At -c $query reports these metrics
(medians of 5 runs):

  version  | fetch_count | clock_time | user_time | sys_time | max_rss_size
(kB) 
-----------+-------------+------------+-----------+----------+-------------------
 16-stable |	       0 |	 6.58 |      3.98 |	2.09 |		
3446276
 16-stable |	     100 |	 9.25 |      4.10 |	1.90 |		   
8768
 16-stable |	    1000 |	11.13 |      5.17 |	1.66 |		   
8904
 17-patch  |	       0 |	  6.5 |      3.94 |	2.09 |		
3442696
 17-patch  |	     100 |	    5 |      3.56 |	0.93 |		   
4096
 17-patch  |	    1000 |	 6.48 |      4.00 |	1.55 |		   
4344

Interestingly, retrieving by chunks of 100 rows appears to be a bit faster
than the default one big chunk. It means that independently
of using less memory, FETCH_COUNT implemented that way
would be a performance enhancement compared to both
not using it and using it in v16 with the cursor implementation.


Best regards,
-- 
Daniel Vérité
https://postgresql.verite.pro/
Twitter: @DanielVerite

From 766bbe84def2db494f646caeaf29eefeba893c1a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20V=C3=A9rit=C3=A9?= <[email protected]>
Date: Mon, 20 Nov 2023 17:24:55 +0100
Subject: [PATCH v4 1/2] Implement retrieval of results in chunks with libpq.

This mode is similar to the single-row mode except that chunks
of results contain up to N rows instead of a single row.
It is meant to reduce the overhead of the row-by-row allocations
for large result sets.
The mode is selected with PQsetChunkedRowsMode(int maxRows) and results
have the new status code PGRES_TUPLES_CHUNK.
---
 doc/src/sgml/libpq.sgml          |  96 +++++++++++++++++++------
 src/bin/pg_amcheck/pg_amcheck.c  |   1 +
 src/interfaces/libpq/exports.txt |   1 +
 src/interfaces/libpq/fe-exec.c   | 118 +++++++++++++++++++++++++------
 src/interfaces/libpq/libpq-fe.h  |   4 +-
 src/interfaces/libpq/libpq-int.h |   7 +-
 6 files changed, 183 insertions(+), 44 deletions(-)

diff --git a/doc/src/sgml/libpq.sgml b/doc/src/sgml/libpq.sgml
index ed88ac001a..8007bf67d8 100644
--- a/doc/src/sgml/libpq.sgml
+++ b/doc/src/sgml/libpq.sgml
@@ -3537,7 +3537,20 @@ ExecStatusType PQresultStatus(const PGresult *res);
             The <structname>PGresult</structname> contains a single result tuple
             from the current command.  This status occurs only when
             single-row mode has been selected for the query
-            (see <xref linkend="libpq-single-row-mode"/>).
+            (see <xref linkend="libpq-chunked-results-modes"/>).
+           </para>
+          </listitem>
+         </varlistentry>
+
+         <varlistentry id="libpq-pgres-tuples-chunk">
+          <term><literal>PGRES_TUPLES_CHUNK</literal></term>
+          <listitem>
+           <para>
+            The <structname>PGresult</structname> contains several tuples
+            from the current command. The count of tuples cannot exceed
+            the maximum passed to <xref linkend="libpq-PQsetChunkedRowsMode"/>.
+            This status occurs only when the chunked mode has been selected
+            for the query (see <xref linkend="libpq-chunked-results-modes"/>).
            </para>
           </listitem>
          </varlistentry>
@@ -5187,8 +5200,8 @@ PGresult *PQgetResult(PGconn *conn);
   <para>
    Another frequently-desired feature that can be obtained with
    <xref linkend="libpq-PQsendQuery"/> and <xref linkend="libpq-PQgetResult"/>
-   is retrieving large query results a row at a time.  This is discussed
-   in <xref linkend="libpq-single-row-mode"/>.
+   is retrieving large query results a limited number of rows at a time.  This is discussed
+   in <xref linkend="libpq-chunked-results-modes"/>.
   </para>
 
   <para>
@@ -5551,12 +5564,13 @@ int PQflush(PGconn *conn);
     </para>
 
     <para>
-     To enter single-row mode, call <function>PQsetSingleRowMode</function>
-     before retrieving results with <function>PQgetResult</function>.
-     This mode selection is effective only for the query currently
-     being processed. For more information on the use of
-     <function>PQsetSingleRowMode</function>,
-     refer to <xref linkend="libpq-single-row-mode"/>.
+     To enter single-row or chunked modes, call
+     respectively <function>PQsetSingleRowMode</function>
+     or <function>PQsetChunkedRowsMode</function> before retrieving results
+     with <function>PQgetResult</function>.  This mode selection is effective
+     only for the query currently being processed. For more information on the
+     use of these functions refer
+     to <xref linkend="libpq-chunked-results-modes" />.
     </para>
 
     <para>
@@ -5895,10 +5909,10 @@ UPDATE mytable SET x = x + 1 WHERE id = 42;
   </sect2>
  </sect1>
 
- <sect1 id="libpq-single-row-mode">
-  <title>Retrieving Query Results Row-by-Row</title>
+ <sect1 id="libpq-chunked-results-modes">
+  <title>Retrieving Query Results by chunks</title>
 
-  <indexterm zone="libpq-single-row-mode">
+  <indexterm zone="libpq-chunked-results-modes">
    <primary>libpq</primary>
    <secondary>single-row mode</secondary>
   </indexterm>
@@ -5909,13 +5923,15 @@ UPDATE mytable SET x = x + 1 WHERE id = 42;
    <structname>PGresult</structname>.  This can be unworkable for commands
    that return a large number of rows.  For such cases, applications can use
    <xref linkend="libpq-PQsendQuery"/> and <xref linkend="libpq-PQgetResult"/> in
-   <firstterm>single-row mode</firstterm>.  In this mode, the result row(s) are
-   returned to the application one at a time, as they are received from the
-   server.
+   <firstterm>single-row mode</firstterm> or <firstterm>chunked mode</firstterm>.
+   In these modes, the result row(s) are returned to the application one at a
+   time for the single-row mode and by chunks for the chunked mode, as they
+   are received from the server.
   </para>
 
   <para>
-   To enter single-row mode, call <xref linkend="libpq-PQsetSingleRowMode"/>
+   To enter these modes, call <xref linkend="libpq-PQsetSingleRowMode"/>
+    or <xref linkend="libpq-PQsetChunkedRowsMode"/>
    immediately after a successful call of <xref linkend="libpq-PQsendQuery"/>
    (or a sibling function).  This mode selection is effective only for the
    currently executing query.  Then call <xref linkend="libpq-PQgetResult"/>
@@ -5923,7 +5939,8 @@ UPDATE mytable SET x = x + 1 WHERE id = 42;
    linkend="libpq-async"/>.  If the query returns any rows, they are returned
    as individual <structname>PGresult</structname> objects, which look like
    normal query results except for having status code
-   <literal>PGRES_SINGLE_TUPLE</literal> instead of
+   <literal>PGRES_SINGLE_TUPLE</literal> for the single-row mode and
+   <literal>PGRES_TUPLES_CHUNK</literal> for the chunked mode, instead of
    <literal>PGRES_TUPLES_OK</literal>.  After the last row, or immediately if
    the query returns zero rows, a zero-row object with status
    <literal>PGRES_TUPLES_OK</literal> is returned; this is the signal that no
@@ -5936,9 +5953,9 @@ UPDATE mytable SET x = x + 1 WHERE id = 42;
   </para>
 
   <para>
-   When using pipeline mode, single-row mode needs to be activated for each
-   query in the pipeline before retrieving results for that query
-   with <function>PQgetResult</function>.
+   When using pipeline mode, the single-row or chunked mode need to be
+   activated for each query in the pipeline before retrieving results for that
+   query with <function>PQgetResult</function>.
    See <xref linkend="libpq-pipeline-mode"/> for more information.
   </para>
 
@@ -5972,14 +5989,49 @@ int PQsetSingleRowMode(PGconn *conn);
    </variablelist>
   </para>
 
+    <para>
+   <variablelist>
+    <varlistentry id="libpq-PQsetChunkedRowsMode">
+      <term><function>PQsetChunkedRowsMode</function>
+        <indexterm><primary>PQsetChunkedRowsMode</primary></indexterm></term>
+     <listitem>
+      <para>
+       Select the mode retrieving results in chunks for the currently-executing query.
+
+<synopsis>
+  int PQsetChunkedRowsMode(PGconn *conn,
+                           int maxRows);
+</synopsis>
+      </para>
+
+      <para>
+       This function is similar to <xref linkend="libpq-PQsetSingleRowMode"/>,
+       except that it can retrieve a user-specified number of rows
+       per call to <xref linkend="libpq-PQgetResult"/>, instead of a single row.
+       This function can only be called immediately after
+       <xref linkend="libpq-PQsendQuery"/> or one of its sibling functions,
+       before any other operation on the connection such as
+       <xref linkend="libpq-PQconsumeInput"/> or
+       <xref linkend="libpq-PQgetResult"/>.  If called at the correct time,
+       the function activates the chunked mode for the current query and
+       returns 1.  Otherwise the mode stays unchanged and the function
+       returns 0.  In any case, the mode reverts to normal after
+       completion of the current query.
+      </para>
+     </listitem>
+    </varlistentry>
+   </variablelist>
+  </para>
+
   <caution>
    <para>
     While processing a query, the server may return some rows and then
     encounter an error, causing the query to be aborted.  Ordinarily,
     <application>libpq</application> discards any such rows and reports only the
-    error.  But in single-row mode, those rows will have already been
+    error.  But in single-row or chunked modes, those rows will have already been
     returned to the application.  Hence, the application will see some
-    <literal>PGRES_SINGLE_TUPLE</literal> <structname>PGresult</structname>
+    <literal>PGRES_SINGLE_TUPLE</literal> or <literal>PGRES_TUPLES_CHUNK</literal>
+    <structname>PGresult</structname>
     objects followed by a <literal>PGRES_FATAL_ERROR</literal> object.  For
     proper transactional behavior, the application must be designed to
     discard or undo whatever has been done with the previously-processed
diff --git a/src/bin/pg_amcheck/pg_amcheck.c b/src/bin/pg_amcheck/pg_amcheck.c
index a6b3b56457..9c8a0916c7 100644
--- a/src/bin/pg_amcheck/pg_amcheck.c
+++ b/src/bin/pg_amcheck/pg_amcheck.c
@@ -989,6 +989,7 @@ should_processing_continue(PGresult *res)
 		case PGRES_COPY_IN:
 		case PGRES_COPY_BOTH:
 		case PGRES_SINGLE_TUPLE:
+		case PGRES_TUPLES_CHUNK:
 		case PGRES_PIPELINE_SYNC:
 		case PGRES_PIPELINE_ABORTED:
 			return false;
diff --git a/src/interfaces/libpq/exports.txt b/src/interfaces/libpq/exports.txt
index 850734ac96..ae7c84247b 100644
--- a/src/interfaces/libpq/exports.txt
+++ b/src/interfaces/libpq/exports.txt
@@ -191,3 +191,4 @@ PQclosePrepared           188
 PQclosePortal             189
 PQsendClosePrepared       190
 PQsendClosePortal         191
+PQsetChunkedRowsMode	  192
diff --git a/src/interfaces/libpq/fe-exec.c b/src/interfaces/libpq/fe-exec.c
index 04610ccf5e..2e96d1b538 100644
--- a/src/interfaces/libpq/fe-exec.c
+++ b/src/interfaces/libpq/fe-exec.c
@@ -41,7 +41,8 @@ char	   *const pgresStatus[] = {
 	"PGRES_COPY_BOTH",
 	"PGRES_SINGLE_TUPLE",
 	"PGRES_PIPELINE_SYNC",
-	"PGRES_PIPELINE_ABORTED"
+	"PGRES_PIPELINE_ABORTED",
+	"PGRES_TUPLES_CHUNK"
 };
 
 /* We return this if we're unable to make a PGresult at all */
@@ -82,7 +83,7 @@ static int	PQsendTypedCommand(PGconn *conn, char command, char type,
 static int	check_field_number(const PGresult *res, int field_num);
 static void pqPipelineProcessQueue(PGconn *conn);
 static int	pqPipelineFlush(PGconn *conn);
-
+static bool canChangeRowMode(PGconn *conn);
 
 /* ----------------
  * Space management for PGresult.
@@ -199,6 +200,7 @@ PQmakeEmptyPGresult(PGconn *conn, ExecStatusType status)
 			case PGRES_COPY_IN:
 			case PGRES_COPY_BOTH:
 			case PGRES_SINGLE_TUPLE:
+			case PGRES_TUPLES_CHUNK:
 				/* non-error cases */
 				break;
 			default:
@@ -910,8 +912,9 @@ pqPrepareAsyncResult(PGconn *conn)
 	/*
 	 * Replace conn->result with next_result, if any.  In the normal case
 	 * there isn't a next result and we're just dropping ownership of the
-	 * current result.  In single-row mode this restores the situation to what
-	 * it was before we created the current single-row result.
+	 * current result.  In single-row and chunked modes this restores the
+	 * situation to what it was before we created the current single-row or
+	 * chunk-of-rows result.
 	 */
 	conn->result = conn->next_result;
 	conn->error_result = false; /* next_result is never an error */
@@ -1197,10 +1200,11 @@ pqSaveParameterStatus(PGconn *conn, const char *name, const char *value)
  * (Such a string should already be translated via libpq_gettext().)
  * If it is left NULL, the error is presumed to be "out of memory".
  *
- * In single-row mode, we create a new result holding just the current row,
- * stashing the previous result in conn->next_result so that it becomes
- * active again after pqPrepareAsyncResult().  This allows the result metadata
- * (column descriptions) to be carried forward to each result row.
+ * In single-row or chunked mode, we create a new result holding just the
+ * current set of rows, stashing the previous result in conn->next_result so
+ * that it becomes active again after pqPrepareAsyncResult().  This allows the
+ * result metadata (column descriptions) to be carried forward to each result
+ * row.
  */
 int
 pqRowProcessor(PGconn *conn, const char **errmsgp)
@@ -1225,6 +1229,28 @@ pqRowProcessor(PGconn *conn, const char **errmsgp)
 		if (!res)
 			return 0;
 	}
+	else if (conn->rowsChunkSize > 0)
+	{
+		/*
+		 * In chunked mode, make a new PGresult that will hold N rows; the
+		 * original conn->result is left unchanged, as in the single-row mode.
+		 */
+		if (!conn->chunk_result)
+		{
+			/* Allocate and initialize the result to hold a chunk of rows */
+			res = PQcopyResult(res,
+							   PG_COPYRES_ATTRS | PG_COPYRES_EVENTS |
+							   PG_COPYRES_NOTICEHOOKS);
+			if (!res)
+				return 0;
+			/* Change result status to special chunk-of-rows value */
+			res->resultStatus = PGRES_TUPLES_CHUNK;
+			/* Keep this result to reuse for the next rows of the chunk */
+			conn->chunk_result = res;
+		}
+		else
+			res = conn->chunk_result;	/* Use the current chunk */
+	}
 
 	/*
 	 * Basically we just allocate space in the PGresult for each field and
@@ -1287,6 +1313,21 @@ pqRowProcessor(PGconn *conn, const char **errmsgp)
 		conn->asyncStatus = PGASYNC_READY_MORE;
 	}
 
+	/*
+	 * In chunked mode, if the count has reached the requested limit, make the
+	 * rows of the current chunk available immediately.
+	 */
+	else if (conn->rowsChunkSize > 0 && res->ntups >= conn->rowsChunkSize)
+	{
+		/* Stash old result for re-use later */
+		conn->next_result = conn->result;
+		conn->result = res;
+		/* Do not reuse that chunk of results */
+		conn->chunk_result = NULL;
+		/* And mark the result ready to return */
+		conn->asyncStatus = PGASYNC_READY_MORE;
+	}
+
 	return 1;
 
 fail:
@@ -1742,8 +1783,9 @@ PQsendQueryStart(PGconn *conn, bool newQuery)
 		 */
 		pqClearAsyncResult(conn);
 
-		/* reset single-row processing mode */
+		/* reset row-by-row and chunked processing modes */
 		conn->singleRowMode = false;
+		conn->rowsChunkSize = 0;
 	}
 
 	/* ready to send command message */
@@ -1927,25 +1969,51 @@ sendFailed:
  */
 int
 PQsetSingleRowMode(PGconn *conn)
+{
+	if (canChangeRowMode(conn))
+	{
+		conn->singleRowMode = true;
+		return 1;
+	}
+	else
+		return 0;
+}
+
+/*
+ * Select chunked results processing mode
+ */
+int
+PQsetChunkedRowsMode(PGconn *conn, int chunkSize)
+{
+	if (chunkSize >= 0 && canChangeRowMode(conn))
+	{
+		conn->rowsChunkSize = chunkSize;
+		return 1;
+	}
+	else
+		return 0;
+}
+
+static
+bool
+canChangeRowMode(PGconn *conn)
 {
 	/*
-	 * Only allow setting the flag when we have launched a query and not yet
-	 * received any results.
+	 * Only allow setting the row-by-row or by-chunks modes when we have
+	 * launched a query and not yet received any results.
 	 */
 	if (!conn)
-		return 0;
+		return false;
 	if (conn->asyncStatus != PGASYNC_BUSY)
-		return 0;
+		return false;
 	if (!conn->cmd_queue_head ||
 		(conn->cmd_queue_head->queryclass != PGQUERY_SIMPLE &&
 		 conn->cmd_queue_head->queryclass != PGQUERY_EXTENDED))
-		return 0;
+		return false;
 	if (pgHavePendingResult(conn))
-		return 0;
+		return false;
 
-	/* OK, set flag */
-	conn->singleRowMode = true;
-	return 1;
+	return true;
 }
 
 /*
@@ -2113,6 +2181,16 @@ PQgetResult(PGconn *conn)
 
 		case PGASYNC_READY:
 
+			/*
+			 * If there is a pending chunk of results, return it
+			 */
+			if (conn->chunk_result != NULL)
+			{
+				res = conn->chunk_result;
+				conn->chunk_result = NULL;
+				break;
+			}
+
 			/*
 			 * For any query type other than simple query protocol, we advance
 			 * the command queue here.  This is because for simple query
@@ -3151,10 +3229,10 @@ pqPipelineProcessQueue(PGconn *conn)
 	}
 
 	/*
-	 * Reset single-row processing mode.  (Client has to set it up for each
+	 * Reset processing mode in chunks.  (Client has to set it up for each
 	 * query, if desired.)
 	 */
-	conn->singleRowMode = false;
+	conn->rowsChunkSize = 0;
 
 	/*
 	 * If there are no further commands to process in the queue, get us in
diff --git a/src/interfaces/libpq/libpq-fe.h b/src/interfaces/libpq/libpq-fe.h
index 97762d56f5..002ed772c8 100644
--- a/src/interfaces/libpq/libpq-fe.h
+++ b/src/interfaces/libpq/libpq-fe.h
@@ -109,8 +109,9 @@ typedef enum
 	PGRES_COPY_BOTH,			/* Copy In/Out data transfer in progress */
 	PGRES_SINGLE_TUPLE,			/* single tuple from larger resultset */
 	PGRES_PIPELINE_SYNC,		/* pipeline synchronization point */
-	PGRES_PIPELINE_ABORTED		/* Command didn't run because of an abort
+	PGRES_PIPELINE_ABORTED,		/* Command didn't run because of an abort
 								 * earlier in a pipeline */
+	PGRES_TUPLES_CHUNK			/* set of tuples from larger resultset */
 } ExecStatusType;
 
 typedef enum
@@ -463,6 +464,7 @@ extern int	PQsendQueryPrepared(PGconn *conn,
 								const int *paramFormats,
 								int resultFormat);
 extern int	PQsetSingleRowMode(PGconn *conn);
+extern int	PQsetChunkedRowsMode(PGconn *conn, int chunkSize);
 extern PGresult *PQgetResult(PGconn *conn);
 
 /* Routines for managing an asynchronous query */
diff --git a/src/interfaces/libpq/libpq-int.h b/src/interfaces/libpq/libpq-int.h
index c745facfec..7786bd2435 100644
--- a/src/interfaces/libpq/libpq-int.h
+++ b/src/interfaces/libpq/libpq-int.h
@@ -431,6 +431,8 @@ struct pg_conn
 								 * sending semantics */
 	PGpipelineStatus pipelineStatus;	/* status of pipeline mode */
 	bool		singleRowMode;	/* return current query result row-by-row? */
+	int			rowsChunkSize;	/* non-zero to return query results by chunks
+								 * not exceeding that number of rows */
 	char		copy_is_binary; /* 1 = copy binary, 0 = copy text */
 	int			copy_already_done;	/* # bytes already returned in COPY OUT */
 	PGnotify   *notifyHead;		/* oldest unreported Notify msg */
@@ -536,7 +538,10 @@ struct pg_conn
 	 */
 	PGresult   *result;			/* result being constructed */
 	bool		error_result;	/* do we need to make an ERROR result? */
-	PGresult   *next_result;	/* next result (used in single-row mode) */
+	PGresult   *next_result;	/* next result (used in single-row and
+								 * by-chunks modes) */
+	PGresult   *chunk_result;	/* current chunk of results (limited to
+								 * rowsChunkSize) */
 
 	/* Assorted state for SASL, SSL, GSS, etc */
 	const pg_fe_sasl_mech *sasl;
-- 
2.34.1


From a5555f339d88ad2a77e567cfd249cb948871b796 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20V=C3=A9rit=C3=A9?= <[email protected]>
Date: Mon, 20 Nov 2023 18:42:41 +0100
Subject: [PATCH v4 2/2] Reimplement FETCH_COUNT with the chunked mode in libpq
 instead of cursors.

Cursors were used only when the command starts with the keyword "SELECT",
excluding queries that start with "WITH" or "UPDATE" or "INSERT" that
may also return large result sets.

Also, cursors imply more commands sent to the server (begin/declare cursor
/repeated fetch/close cursor/commit), whereas in chunked mode, only the actual
user query is sent, resulting in less round-trips.

This also fixes the bug that combined queries (query1 \; query2;) were
not correctly handled with FETCH_COUNT set, due to cursors not supporting
multiple queries.
---
 src/bin/psql/common.c              | 545 ++++++++++-------------------
 src/bin/psql/t/001_basic.pl        |   6 +-
 src/test/regress/expected/psql.out |   9 +-
 src/test/regress/sql/psql.sql      |   4 +-
 4 files changed, 196 insertions(+), 368 deletions(-)

diff --git a/src/bin/psql/common.c b/src/bin/psql/common.c
index daabf6f12b..adb915e5c2 100644
--- a/src/bin/psql/common.c
+++ b/src/bin/psql/common.c
@@ -31,7 +31,6 @@
 #include "settings.h"
 
 static bool DescribeQuery(const char *query, double *elapsed_msec);
-static bool ExecQueryUsingCursor(const char *query, double *elapsed_msec);
 static int	ExecQueryAndProcessResults(const char *query,
 									   double *elapsed_msec,
 									   bool *svpt_gone_p,
@@ -40,8 +39,6 @@ static int	ExecQueryAndProcessResults(const char *query,
 									   const printQueryOpt *opt,
 									   FILE *printQueryFout);
 static bool command_no_begin(const char *query);
-static bool is_select_command(const char *query);
-
 
 /*
  * openQueryOutputFile --- attempt to open a query output file
@@ -373,6 +370,7 @@ AcceptResult(const PGresult *result, bool show_error)
 		{
 			case PGRES_COMMAND_OK:
 			case PGRES_TUPLES_OK:
+			case PGRES_TUPLES_CHUNK:
 			case PGRES_EMPTY_QUERY:
 			case PGRES_COPY_IN:
 			case PGRES_COPY_OUT:
@@ -1131,16 +1129,10 @@ SendQuery(const char *query)
 		/* Describe query's result columns, without executing it */
 		OK = DescribeQuery(query, &elapsed_msec);
 	}
-	else if (pset.fetch_count <= 0 || pset.gexec_flag ||
-			 pset.crosstab_flag || !is_select_command(query))
-	{
-		/* Default fetch-it-all-and-print mode */
-		OK = (ExecQueryAndProcessResults(query, &elapsed_msec, &svpt_gone, false, 0, NULL, NULL) > 0);
-	}
 	else
 	{
-		/* Fetch-in-segments mode */
-		OK = ExecQueryUsingCursor(query, &elapsed_msec);
+		/* Default fetch-and-print mode */
+		OK = (ExecQueryAndProcessResults(query, &elapsed_msec, &svpt_gone, false, 0, NULL, NULL) > 0);
 	}
 
 	if (!OK && pset.echo == PSQL_ECHO_ERRORS)
@@ -1392,6 +1384,47 @@ DescribeQuery(const char *query, double *elapsed_msec)
 	return OK;
 }
 
+/*
+ * Check if an output stream for \g needs to be opened, and if
+ * yes, open it.
+ * Return false if an error occurred, true otherwise.
+ */
+static bool
+SetupGOutput(PGresult *result, FILE **gfile_fout, bool *is_pipe)
+{
+	ExecStatusType status = PQresultStatus(result);
+	if (pset.gfname != NULL &&			/* there is a \g file or program */
+		*gfile_fout == NULL &&           /* and it's not already opened */
+		(status == PGRES_TUPLES_OK ||
+		 status == PGRES_TUPLES_CHUNK ||
+		 status == PGRES_COPY_OUT))
+	{
+		if (openQueryOutputFile(pset.gfname, gfile_fout, is_pipe))
+		{
+			if (is_pipe)
+				disable_sigpipe_trap();
+		}
+		else
+			return false;
+	}
+	return true;
+}
+
+static void
+CloseGOutput(FILE *gfile_fout, bool is_pipe)
+{
+	/* close \g file if we opened it */
+	if (gfile_fout)
+	{
+		if (is_pipe)
+		{
+			SetShellResultVariables(pclose(gfile_fout));
+			restore_sigpipe_trap();
+		}
+		else
+			fclose(gfile_fout);
+	}
+}
 
 /*
  * ExecQueryAndProcessResults: utility function for use by SendQuery()
@@ -1424,10 +1457,16 @@ ExecQueryAndProcessResults(const char *query,
 	bool		return_early = false;
 	instr_time	before,
 				after;
+	int fetch_count = pset.fetch_count;
 	PGresult   *result;
+
 	FILE	   *gfile_fout = NULL;
 	bool		gfile_is_pipe = false;
 
+	int64		total_tuples = 0;
+	int			flush_error = 0;
+	bool		is_pager = false;
+
 	if (timing)
 		INSTR_TIME_SET_CURRENT(before);
 	else
@@ -1450,6 +1489,29 @@ ExecQueryAndProcessResults(const char *query,
 		return -1;
 	}
 
+	/*
+	 * If FETCH_COUNT is set and the context allows it, use the single row
+	 * mode to fetch results and have no more than FETCH_COUNT rows in
+	 * memory.
+	 */
+	if (fetch_count > 0 && !pset.crosstab_flag && !pset.gexec_flag && !is_watch
+		&& !pset.gset_prefix && pset.show_all_results)
+	{
+		/*
+		 * The row-by-chunks fetch is not enabled when SHOW_ALL_RESULTS is false,
+		 * since we would need to accumulate all rows before knowing
+		 * whether they need to be discarded or displayed, which contradicts
+		 * FETCH_COUNT.
+		 */
+		if (!PQsetChunkedRowsMode(pset.db, fetch_count))
+		{
+			pg_log_warning("fetching results in chunks mode is unavailable");
+			fetch_count = 0;
+		}
+	}
+	else
+		fetch_count = 0;		/* fetch one resultset per query */
+
 	/*
 	 * If SIGINT is sent while the query is processing, the interrupt will be
 	 * consumed.  The user's intention, though, is to cancel the entire watch
@@ -1473,6 +1535,8 @@ ExecQueryAndProcessResults(const char *query,
 		ExecStatusType result_status;
 		PGresult   *next_result;
 		bool		last;
+		/* whether the output starts before results are fully fetched */
+		bool		partial_display = false;
 
 		if (!AcceptResult(result, false))
 		{
@@ -1568,20 +1632,9 @@ ExecQueryAndProcessResults(const char *query,
 				}
 				else if (pset.gfname)
 				{
-					/* send to \g file, which we may have opened already */
-					if (gfile_fout == NULL)
-					{
-						if (openQueryOutputFile(pset.gfname,
-												&gfile_fout, &gfile_is_pipe))
-						{
-							if (gfile_is_pipe)
-								disable_sigpipe_trap();
-							copy_stream = gfile_fout;
-						}
-						else
-							success = false;
-					}
-					else
+					/* COPY followed by \g filename or \g |program */
+					success = SetupGOutput(result, &gfile_fout, &gfile_is_pipe);
+					if (success)
 						copy_stream = gfile_fout;
 				}
 				else
@@ -1599,6 +1652,90 @@ ExecQueryAndProcessResults(const char *query,
 			success &= HandleCopyResult(&result, copy_stream);
 		}
 
+		if (fetch_count > 0 && result_status == PGRES_TUPLES_CHUNK)
+		{
+			FILE	   *tuples_fout = printQueryFout ? printQueryFout : stdout;
+			printQueryOpt my_popt = pset.popt;
+
+			total_tuples = 0;
+			partial_display = true;
+
+			success = SetupGOutput(result, &gfile_fout, &gfile_is_pipe);
+			if (gfile_fout)
+				tuples_fout = gfile_fout;
+
+			/* initialize print options for partial table output */
+			my_popt.topt.start_table = true;
+			my_popt.topt.stop_table = false;
+			my_popt.topt.prior_records = 0;
+
+			while (success)
+			{
+				/* pager: open at most once per resultset */
+				if (tuples_fout == stdout && !is_pager)
+				{
+					tuples_fout = PageOutput(INT_MAX, &(my_popt.topt));
+					is_pager = true;
+				}
+				/* display the current chunk of results unless the output stream is not working */
+				if (!flush_error)
+				{
+					printQuery(result, &my_popt, tuples_fout, is_pager, pset.logfile);
+					flush_error = fflush(tuples_fout);
+				}
+
+				/* after the first result set, disallow header decoration */
+				my_popt.topt.start_table = false;
+				my_popt.topt.prior_records += PQntuples(result);
+				total_tuples += PQntuples(result);
+
+				ClearOrSaveResult(result);
+
+				result = PQgetResult(pset.db);
+				if (result == NULL)
+				{
+					/*
+					 * Error. We expect a PGRES_TUPLES_OK result with
+					 * zero tuple in it to finish the fetch sequence.
+					 */
+					success = false;
+					if (is_pager)
+						ClosePager(tuples_fout);
+					break;
+				}
+				else if (PQresultStatus(result) == PGRES_TUPLES_OK)
+				{
+					/*
+					 * The last row has been read. Display the footer.
+					 */
+					my_popt.topt.stop_table = true;
+					printQuery(result, &my_popt, tuples_fout, is_pager, pset.logfile);
+					total_tuples += PQntuples(result);
+
+					if (is_pager)
+						ClosePager(tuples_fout);
+					ClearOrSaveResult(result);
+					result = NULL;
+					break;
+				}
+				else if (PQresultStatus(result) != PGRES_TUPLES_CHUNK)
+				{
+					/*
+					 * Error. We expect either PGRES_TUPLES_CHUNK or
+					 * PGRES_TUPLES_OK.
+					 */
+					if (is_pager)
+						ClosePager(tuples_fout);
+					success = false;
+					AcceptResult(result, true); /* display error whenever appropriate */
+					SetResultVariables(result, success);
+					break;
+				}
+			}
+		}
+		else
+			partial_display = false;
+
 		/*
 		 * Check PQgetResult() again.  In the typical case of a single-command
 		 * string, it will return NULL.  Otherwise, we'll have other results
@@ -1627,7 +1764,7 @@ ExecQueryAndProcessResults(const char *query,
 		}
 
 		/* this may or may not print something depending on settings */
-		if (result != NULL)
+		if (result != NULL && !partial_display)
 		{
 			/*
 			 * If results need to be printed into the file specified by \g,
@@ -1636,32 +1773,33 @@ ExecQueryAndProcessResults(const char *query,
 			 * tuple output, but it's still used for status output.
 			 */
 			FILE	   *tuples_fout = printQueryFout;
-			bool		do_print = true;
-
-			if (PQresultStatus(result) == PGRES_TUPLES_OK &&
-				pset.gfname)
-			{
-				if (gfile_fout == NULL)
-				{
-					if (openQueryOutputFile(pset.gfname,
-											&gfile_fout, &gfile_is_pipe))
-					{
-						if (gfile_is_pipe)
-							disable_sigpipe_trap();
-					}
-					else
-						success = do_print = false;
-				}
+			success = SetupGOutput(result, &gfile_fout, &gfile_is_pipe);
+			if (gfile_fout)
 				tuples_fout = gfile_fout;
-			}
-			if (do_print)
+			if (success)
 				success &= PrintQueryResult(result, last, opt,
 											tuples_fout, printQueryFout);
 		}
 
 		/* set variables from last result */
 		if (!is_watch && last)
-			SetResultVariables(result, success);
+		{
+			if (!partial_display)
+				SetResultVariables(result, success);
+			else if (success)
+			{
+				/*
+				 * fake SetResultVariables(). If an error occurred when
+				 * retrieving chunks, these variables have been set already.
+				 */
+				char		buf[32];
+
+				SetVariable(pset.vars, "ERROR", "false");
+				SetVariable(pset.vars, "SQLSTATE", "00000");
+				snprintf(buf, sizeof(buf), INT64_FORMAT, total_tuples);
+				SetVariable(pset.vars, "ROW_COUNT", buf);
+			}
+		}
 
 		ClearOrSaveResult(result);
 		result = next_result;
@@ -1673,17 +1811,7 @@ ExecQueryAndProcessResults(const char *query,
 		}
 	}
 
-	/* close \g file if we opened it */
-	if (gfile_fout)
-	{
-		if (gfile_is_pipe)
-		{
-			SetShellResultVariables(pclose(gfile_fout));
-			restore_sigpipe_trap();
-		}
-		else
-			fclose(gfile_fout);
-	}
+	CloseGOutput(gfile_fout, gfile_is_pipe);
 
 	/* may need this to recover from conn loss during COPY */
 	if (!CheckConnection())
@@ -1696,274 +1824,6 @@ ExecQueryAndProcessResults(const char *query,
 }
 
 
-/*
- * ExecQueryUsingCursor: run a SELECT-like query using a cursor
- *
- * This feature allows result sets larger than RAM to be dealt with.
- *
- * Returns true if the query executed successfully, false otherwise.
- *
- * If pset.timing is on, total query time (exclusive of result-printing) is
- * stored into *elapsed_msec.
- */
-static bool
-ExecQueryUsingCursor(const char *query, double *elapsed_msec)
-{
-	bool		OK = true;
-	PGresult   *result;
-	PQExpBufferData buf;
-	printQueryOpt my_popt = pset.popt;
-	bool		timing = pset.timing;
-	FILE	   *fout;
-	bool		is_pipe;
-	bool		is_pager = false;
-	bool		started_txn = false;
-	int64		total_tuples = 0;
-	int			ntuples;
-	int			fetch_count;
-	char		fetch_cmd[64];
-	instr_time	before,
-				after;
-	int			flush_error;
-
-	*elapsed_msec = 0;
-
-	/* initialize print options for partial table output */
-	my_popt.topt.start_table = true;
-	my_popt.topt.stop_table = false;
-	my_popt.topt.prior_records = 0;
-
-	if (timing)
-		INSTR_TIME_SET_CURRENT(before);
-	else
-		INSTR_TIME_SET_ZERO(before);
-
-	/* if we're not in a transaction, start one */
-	if (PQtransactionStatus(pset.db) == PQTRANS_IDLE)
-	{
-		result = PQexec(pset.db, "BEGIN");
-		OK = AcceptResult(result, true) &&
-			(PQresultStatus(result) == PGRES_COMMAND_OK);
-		ClearOrSaveResult(result);
-		if (!OK)
-			return false;
-		started_txn = true;
-	}
-
-	/* Send DECLARE CURSOR */
-	initPQExpBuffer(&buf);
-	appendPQExpBuffer(&buf, "DECLARE _psql_cursor NO SCROLL CURSOR FOR\n%s",
-					  query);
-
-	result = PQexec(pset.db, buf.data);
-	OK = AcceptResult(result, true) &&
-		(PQresultStatus(result) == PGRES_COMMAND_OK);
-	if (!OK)
-		SetResultVariables(result, OK);
-	ClearOrSaveResult(result);
-	termPQExpBuffer(&buf);
-	if (!OK)
-		goto cleanup;
-
-	if (timing)
-	{
-		INSTR_TIME_SET_CURRENT(after);
-		INSTR_TIME_SUBTRACT(after, before);
-		*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
-	}
-
-	/*
-	 * In \gset mode, we force the fetch count to be 2, so that we will throw
-	 * the appropriate error if the query returns more than one row.
-	 */
-	if (pset.gset_prefix)
-		fetch_count = 2;
-	else
-		fetch_count = pset.fetch_count;
-
-	snprintf(fetch_cmd, sizeof(fetch_cmd),
-			 "FETCH FORWARD %d FROM _psql_cursor",
-			 fetch_count);
-
-	/* prepare to write output to \g argument, if any */
-	if (pset.gfname)
-	{
-		if (!openQueryOutputFile(pset.gfname, &fout, &is_pipe))
-		{
-			OK = false;
-			goto cleanup;
-		}
-		if (is_pipe)
-			disable_sigpipe_trap();
-	}
-	else
-	{
-		fout = pset.queryFout;
-		is_pipe = false;		/* doesn't matter */
-	}
-
-	/* clear any pre-existing error indication on the output stream */
-	clearerr(fout);
-
-	for (;;)
-	{
-		if (timing)
-			INSTR_TIME_SET_CURRENT(before);
-
-		/* get fetch_count tuples at a time */
-		result = PQexec(pset.db, fetch_cmd);
-
-		if (timing)
-		{
-			INSTR_TIME_SET_CURRENT(after);
-			INSTR_TIME_SUBTRACT(after, before);
-			*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
-		}
-
-		if (PQresultStatus(result) != PGRES_TUPLES_OK)
-		{
-			/* shut down pager before printing error message */
-			if (is_pager)
-			{
-				ClosePager(fout);
-				is_pager = false;
-			}
-
-			OK = AcceptResult(result, true);
-			Assert(!OK);
-			SetResultVariables(result, OK);
-			ClearOrSaveResult(result);
-			break;
-		}
-
-		if (pset.gset_prefix)
-		{
-			/* StoreQueryTuple will complain if not exactly one row */
-			OK = StoreQueryTuple(result);
-			ClearOrSaveResult(result);
-			break;
-		}
-
-		/*
-		 * Note we do not deal with \gdesc, \gexec or \crosstabview modes here
-		 */
-
-		ntuples = PQntuples(result);
-		total_tuples += ntuples;
-
-		if (ntuples < fetch_count)
-		{
-			/* this is the last result set, so allow footer decoration */
-			my_popt.topt.stop_table = true;
-		}
-		else if (fout == stdout && !is_pager)
-		{
-			/*
-			 * If query requires multiple result sets, hack to ensure that
-			 * only one pager instance is used for the whole mess
-			 */
-			fout = PageOutput(INT_MAX, &(my_popt.topt));
-			is_pager = true;
-		}
-
-		printQuery(result, &my_popt, fout, is_pager, pset.logfile);
-
-		ClearOrSaveResult(result);
-
-		/* after the first result set, disallow header decoration */
-		my_popt.topt.start_table = false;
-		my_popt.topt.prior_records += ntuples;
-
-		/*
-		 * Make sure to flush the output stream, so intermediate results are
-		 * visible to the client immediately.  We check the results because if
-		 * the pager dies/exits/etc, there's no sense throwing more data at
-		 * it.
-		 */
-		flush_error = fflush(fout);
-
-		/*
-		 * Check if we are at the end, if a cancel was pressed, or if there
-		 * were any errors either trying to flush out the results, or more
-		 * generally on the output stream at all.  If we hit any errors
-		 * writing things to the stream, we presume $PAGER has disappeared and
-		 * stop bothering to pull down more data.
-		 */
-		if (ntuples < fetch_count || cancel_pressed || flush_error ||
-			ferror(fout))
-			break;
-	}
-
-	if (pset.gfname)
-	{
-		/* close \g argument file/pipe */
-		if (is_pipe)
-		{
-			SetShellResultVariables(pclose(fout));
-			restore_sigpipe_trap();
-		}
-		else
-			fclose(fout);
-	}
-	else if (is_pager)
-	{
-		/* close transient pager */
-		ClosePager(fout);
-	}
-
-	if (OK)
-	{
-		/*
-		 * We don't have a PGresult here, and even if we did it wouldn't have
-		 * the right row count, so fake SetResultVariables().  In error cases,
-		 * we already set the result variables above.
-		 */
-		char		buf[32];
-
-		SetVariable(pset.vars, "ERROR", "false");
-		SetVariable(pset.vars, "SQLSTATE", "00000");
-		snprintf(buf, sizeof(buf), INT64_FORMAT, total_tuples);
-		SetVariable(pset.vars, "ROW_COUNT", buf);
-	}
-
-cleanup:
-	if (timing)
-		INSTR_TIME_SET_CURRENT(before);
-
-	/*
-	 * We try to close the cursor on either success or failure, but on failure
-	 * ignore the result (it's probably just a bleat about being in an aborted
-	 * transaction)
-	 */
-	result = PQexec(pset.db, "CLOSE _psql_cursor");
-	if (OK)
-	{
-		OK = AcceptResult(result, true) &&
-			(PQresultStatus(result) == PGRES_COMMAND_OK);
-		ClearOrSaveResult(result);
-	}
-	else
-		PQclear(result);
-
-	if (started_txn)
-	{
-		result = PQexec(pset.db, OK ? "COMMIT" : "ROLLBACK");
-		OK &= AcceptResult(result, true) &&
-			(PQresultStatus(result) == PGRES_COMMAND_OK);
-		ClearOrSaveResult(result);
-	}
-
-	if (timing)
-	{
-		INSTR_TIME_SET_CURRENT(after);
-		INSTR_TIME_SUBTRACT(after, before);
-		*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
-	}
-
-	return OK;
-}
-
-
 /*
  * Advance the given char pointer over white space and SQL comments.
  */
@@ -2243,43 +2103,6 @@ command_no_begin(const char *query)
 }
 
 
-/*
- * Check whether the specified command is a SELECT (or VALUES).
- */
-static bool
-is_select_command(const char *query)
-{
-	int			wordlen;
-
-	/*
-	 * First advance over any whitespace, comments and left parentheses.
-	 */
-	for (;;)
-	{
-		query = skip_white_space(query);
-		if (query[0] == '(')
-			query++;
-		else
-			break;
-	}
-
-	/*
-	 * Check word length (since "selectx" is not "select").
-	 */
-	wordlen = 0;
-	while (isalpha((unsigned char) query[wordlen]))
-		wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
-
-	if (wordlen == 6 && pg_strncasecmp(query, "select", 6) == 0)
-		return true;
-
-	if (wordlen == 6 && pg_strncasecmp(query, "values", 6) == 0)
-		return true;
-
-	return false;
-}
-
-
 /*
  * Test if the current user is a database superuser.
  */
diff --git a/src/bin/psql/t/001_basic.pl b/src/bin/psql/t/001_basic.pl
index 95f4e60ab2..62a5d0f383 100644
--- a/src/bin/psql/t/001_basic.pl
+++ b/src/bin/psql/t/001_basic.pl
@@ -161,7 +161,7 @@ psql_like(
 	'\errverbose with no previous error');
 
 # There are three main ways to run a query that might affect
-# \errverbose: The normal way, using a cursor by setting FETCH_COUNT,
+# \errverbose: The normal way, piecemeal retrieval using FETCH_COUNT,
 # and using \gdesc.  Test them all.
 
 like(
@@ -184,10 +184,10 @@ like(
 			"\\set FETCH_COUNT 1\nSELECT error;\n\\errverbose",
 			on_error_stop => 0))[2],
 	qr/\A^psql:<stdin>:2: ERROR:  .*$
-^LINE 2: SELECT error;$
+^LINE 1: SELECT error;$
 ^ *^.*$
 ^psql:<stdin>:3: error: ERROR:  [0-9A-Z]{5}: .*$
-^LINE 2: SELECT error;$
+^LINE 1: SELECT error;$
 ^ *^.*$
 ^LOCATION: .*$/m,
 	'\errverbose after FETCH_COUNT query with error');
diff --git a/src/test/regress/expected/psql.out b/src/test/regress/expected/psql.out
index 13e4f6db7b..aa53f11682 100644
--- a/src/test/regress/expected/psql.out
+++ b/src/test/regress/expected/psql.out
@@ -4754,7 +4754,7 @@ number of rows: 0
 last error message: syntax error at end of input
 \echo 'last error code:' :LAST_ERROR_SQLSTATE
 last error code: 42601
--- check row count for a cursor-fetched query
+-- check row count for a query with chunked results
 \set FETCH_COUNT 10
 select unique2 from tenk1 order by unique2 limit 19;
  unique2 
@@ -4786,7 +4786,7 @@ error: false
 error code: 00000
 \echo 'number of rows:' :ROW_COUNT
 number of rows: 19
--- cursor-fetched query with an error after the first group
+-- chunked results with an error after the first chunk
 select 1/(15-unique2) from tenk1 order by unique2 limit 19;
  ?column? 
 ----------
@@ -4800,6 +4800,11 @@ select 1/(15-unique2) from tenk1 order by unique2 limit 19;
         0
         0
         0
+        0
+        0
+        0
+        0
+        1
 ERROR:  division by zero
 \echo 'error:' :ERROR
 error: true
diff --git a/src/test/regress/sql/psql.sql b/src/test/regress/sql/psql.sql
index 695c72d866..3c4e6962ba 100644
--- a/src/test/regress/sql/psql.sql
+++ b/src/test/regress/sql/psql.sql
@@ -1160,14 +1160,14 @@ SELECT 4 AS \gdesc
 \echo 'last error message:' :LAST_ERROR_MESSAGE
 \echo 'last error code:' :LAST_ERROR_SQLSTATE
 
--- check row count for a cursor-fetched query
+-- check row count for a query with chunked results
 \set FETCH_COUNT 10
 select unique2 from tenk1 order by unique2 limit 19;
 \echo 'error:' :ERROR
 \echo 'error code:' :SQLSTATE
 \echo 'number of rows:' :ROW_COUNT
 
--- cursor-fetched query with an error after the first group
+-- chunked results with an error after the first chunk
 select 1/(15-unique2) from tenk1 order by unique2 limit 19;
 \echo 'error:' :ERROR
 \echo 'error code:' :SQLSTATE
-- 
2.34.1



Attachments:

  [text/plain] v4-0001-Implement-retrieval-of-results-in-chunks-with-lib.patch (17.9K, ../../[email protected]/2-v4-0001-Implement-retrieval-of-results-in-chunks-with-lib.patch)
  download | inline diff:
From 766bbe84def2db494f646caeaf29eefeba893c1a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20V=C3=A9rit=C3=A9?= <[email protected]>
Date: Mon, 20 Nov 2023 17:24:55 +0100
Subject: [PATCH v4 1/2] Implement retrieval of results in chunks with libpq.

This mode is similar to the single-row mode except that chunks
of results contain up to N rows instead of a single row.
It is meant to reduce the overhead of the row-by-row allocations
for large result sets.
The mode is selected with PQsetChunkedRowsMode(int maxRows) and results
have the new status code PGRES_TUPLES_CHUNK.
---
 doc/src/sgml/libpq.sgml          |  96 +++++++++++++++++++------
 src/bin/pg_amcheck/pg_amcheck.c  |   1 +
 src/interfaces/libpq/exports.txt |   1 +
 src/interfaces/libpq/fe-exec.c   | 118 +++++++++++++++++++++++++------
 src/interfaces/libpq/libpq-fe.h  |   4 +-
 src/interfaces/libpq/libpq-int.h |   7 +-
 6 files changed, 183 insertions(+), 44 deletions(-)

diff --git a/doc/src/sgml/libpq.sgml b/doc/src/sgml/libpq.sgml
index ed88ac001a..8007bf67d8 100644
--- a/doc/src/sgml/libpq.sgml
+++ b/doc/src/sgml/libpq.sgml
@@ -3537,7 +3537,20 @@ ExecStatusType PQresultStatus(const PGresult *res);
             The <structname>PGresult</structname> contains a single result tuple
             from the current command.  This status occurs only when
             single-row mode has been selected for the query
-            (see <xref linkend="libpq-single-row-mode"/>).
+            (see <xref linkend="libpq-chunked-results-modes"/>).
+           </para>
+          </listitem>
+         </varlistentry>
+
+         <varlistentry id="libpq-pgres-tuples-chunk">
+          <term><literal>PGRES_TUPLES_CHUNK</literal></term>
+          <listitem>
+           <para>
+            The <structname>PGresult</structname> contains several tuples
+            from the current command. The count of tuples cannot exceed
+            the maximum passed to <xref linkend="libpq-PQsetChunkedRowsMode"/>.
+            This status occurs only when the chunked mode has been selected
+            for the query (see <xref linkend="libpq-chunked-results-modes"/>).
            </para>
           </listitem>
          </varlistentry>
@@ -5187,8 +5200,8 @@ PGresult *PQgetResult(PGconn *conn);
   <para>
    Another frequently-desired feature that can be obtained with
    <xref linkend="libpq-PQsendQuery"/> and <xref linkend="libpq-PQgetResult"/>
-   is retrieving large query results a row at a time.  This is discussed
-   in <xref linkend="libpq-single-row-mode"/>.
+   is retrieving large query results a limited number of rows at a time.  This is discussed
+   in <xref linkend="libpq-chunked-results-modes"/>.
   </para>
 
   <para>
@@ -5551,12 +5564,13 @@ int PQflush(PGconn *conn);
     </para>
 
     <para>
-     To enter single-row mode, call <function>PQsetSingleRowMode</function>
-     before retrieving results with <function>PQgetResult</function>.
-     This mode selection is effective only for the query currently
-     being processed. For more information on the use of
-     <function>PQsetSingleRowMode</function>,
-     refer to <xref linkend="libpq-single-row-mode"/>.
+     To enter single-row or chunked modes, call
+     respectively <function>PQsetSingleRowMode</function>
+     or <function>PQsetChunkedRowsMode</function> before retrieving results
+     with <function>PQgetResult</function>.  This mode selection is effective
+     only for the query currently being processed. For more information on the
+     use of these functions refer
+     to <xref linkend="libpq-chunked-results-modes" />.
     </para>
 
     <para>
@@ -5895,10 +5909,10 @@ UPDATE mytable SET x = x + 1 WHERE id = 42;
   </sect2>
  </sect1>
 
- <sect1 id="libpq-single-row-mode">
-  <title>Retrieving Query Results Row-by-Row</title>
+ <sect1 id="libpq-chunked-results-modes">
+  <title>Retrieving Query Results by chunks</title>
 
-  <indexterm zone="libpq-single-row-mode">
+  <indexterm zone="libpq-chunked-results-modes">
    <primary>libpq</primary>
    <secondary>single-row mode</secondary>
   </indexterm>
@@ -5909,13 +5923,15 @@ UPDATE mytable SET x = x + 1 WHERE id = 42;
    <structname>PGresult</structname>.  This can be unworkable for commands
    that return a large number of rows.  For such cases, applications can use
    <xref linkend="libpq-PQsendQuery"/> and <xref linkend="libpq-PQgetResult"/> in
-   <firstterm>single-row mode</firstterm>.  In this mode, the result row(s) are
-   returned to the application one at a time, as they are received from the
-   server.
+   <firstterm>single-row mode</firstterm> or <firstterm>chunked mode</firstterm>.
+   In these modes, the result row(s) are returned to the application one at a
+   time for the single-row mode and by chunks for the chunked mode, as they
+   are received from the server.
   </para>
 
   <para>
-   To enter single-row mode, call <xref linkend="libpq-PQsetSingleRowMode"/>
+   To enter these modes, call <xref linkend="libpq-PQsetSingleRowMode"/>
+    or <xref linkend="libpq-PQsetChunkedRowsMode"/>
    immediately after a successful call of <xref linkend="libpq-PQsendQuery"/>
    (or a sibling function).  This mode selection is effective only for the
    currently executing query.  Then call <xref linkend="libpq-PQgetResult"/>
@@ -5923,7 +5939,8 @@ UPDATE mytable SET x = x + 1 WHERE id = 42;
    linkend="libpq-async"/>.  If the query returns any rows, they are returned
    as individual <structname>PGresult</structname> objects, which look like
    normal query results except for having status code
-   <literal>PGRES_SINGLE_TUPLE</literal> instead of
+   <literal>PGRES_SINGLE_TUPLE</literal> for the single-row mode and
+   <literal>PGRES_TUPLES_CHUNK</literal> for the chunked mode, instead of
    <literal>PGRES_TUPLES_OK</literal>.  After the last row, or immediately if
    the query returns zero rows, a zero-row object with status
    <literal>PGRES_TUPLES_OK</literal> is returned; this is the signal that no
@@ -5936,9 +5953,9 @@ UPDATE mytable SET x = x + 1 WHERE id = 42;
   </para>
 
   <para>
-   When using pipeline mode, single-row mode needs to be activated for each
-   query in the pipeline before retrieving results for that query
-   with <function>PQgetResult</function>.
+   When using pipeline mode, the single-row or chunked mode need to be
+   activated for each query in the pipeline before retrieving results for that
+   query with <function>PQgetResult</function>.
    See <xref linkend="libpq-pipeline-mode"/> for more information.
   </para>
 
@@ -5972,14 +5989,49 @@ int PQsetSingleRowMode(PGconn *conn);
    </variablelist>
   </para>
 
+    <para>
+   <variablelist>
+    <varlistentry id="libpq-PQsetChunkedRowsMode">
+      <term><function>PQsetChunkedRowsMode</function>
+        <indexterm><primary>PQsetChunkedRowsMode</primary></indexterm></term>
+     <listitem>
+      <para>
+       Select the mode retrieving results in chunks for the currently-executing query.
+
+<synopsis>
+  int PQsetChunkedRowsMode(PGconn *conn,
+                           int maxRows);
+</synopsis>
+      </para>
+
+      <para>
+       This function is similar to <xref linkend="libpq-PQsetSingleRowMode"/>,
+       except that it can retrieve a user-specified number of rows
+       per call to <xref linkend="libpq-PQgetResult"/>, instead of a single row.
+       This function can only be called immediately after
+       <xref linkend="libpq-PQsendQuery"/> or one of its sibling functions,
+       before any other operation on the connection such as
+       <xref linkend="libpq-PQconsumeInput"/> or
+       <xref linkend="libpq-PQgetResult"/>.  If called at the correct time,
+       the function activates the chunked mode for the current query and
+       returns 1.  Otherwise the mode stays unchanged and the function
+       returns 0.  In any case, the mode reverts to normal after
+       completion of the current query.
+      </para>
+     </listitem>
+    </varlistentry>
+   </variablelist>
+  </para>
+
   <caution>
    <para>
     While processing a query, the server may return some rows and then
     encounter an error, causing the query to be aborted.  Ordinarily,
     <application>libpq</application> discards any such rows and reports only the
-    error.  But in single-row mode, those rows will have already been
+    error.  But in single-row or chunked modes, those rows will have already been
     returned to the application.  Hence, the application will see some
-    <literal>PGRES_SINGLE_TUPLE</literal> <structname>PGresult</structname>
+    <literal>PGRES_SINGLE_TUPLE</literal> or <literal>PGRES_TUPLES_CHUNK</literal>
+    <structname>PGresult</structname>
     objects followed by a <literal>PGRES_FATAL_ERROR</literal> object.  For
     proper transactional behavior, the application must be designed to
     discard or undo whatever has been done with the previously-processed
diff --git a/src/bin/pg_amcheck/pg_amcheck.c b/src/bin/pg_amcheck/pg_amcheck.c
index a6b3b56457..9c8a0916c7 100644
--- a/src/bin/pg_amcheck/pg_amcheck.c
+++ b/src/bin/pg_amcheck/pg_amcheck.c
@@ -989,6 +989,7 @@ should_processing_continue(PGresult *res)
 		case PGRES_COPY_IN:
 		case PGRES_COPY_BOTH:
 		case PGRES_SINGLE_TUPLE:
+		case PGRES_TUPLES_CHUNK:
 		case PGRES_PIPELINE_SYNC:
 		case PGRES_PIPELINE_ABORTED:
 			return false;
diff --git a/src/interfaces/libpq/exports.txt b/src/interfaces/libpq/exports.txt
index 850734ac96..ae7c84247b 100644
--- a/src/interfaces/libpq/exports.txt
+++ b/src/interfaces/libpq/exports.txt
@@ -191,3 +191,4 @@ PQclosePrepared           188
 PQclosePortal             189
 PQsendClosePrepared       190
 PQsendClosePortal         191
+PQsetChunkedRowsMode	  192
diff --git a/src/interfaces/libpq/fe-exec.c b/src/interfaces/libpq/fe-exec.c
index 04610ccf5e..2e96d1b538 100644
--- a/src/interfaces/libpq/fe-exec.c
+++ b/src/interfaces/libpq/fe-exec.c
@@ -41,7 +41,8 @@ char	   *const pgresStatus[] = {
 	"PGRES_COPY_BOTH",
 	"PGRES_SINGLE_TUPLE",
 	"PGRES_PIPELINE_SYNC",
-	"PGRES_PIPELINE_ABORTED"
+	"PGRES_PIPELINE_ABORTED",
+	"PGRES_TUPLES_CHUNK"
 };
 
 /* We return this if we're unable to make a PGresult at all */
@@ -82,7 +83,7 @@ static int	PQsendTypedCommand(PGconn *conn, char command, char type,
 static int	check_field_number(const PGresult *res, int field_num);
 static void pqPipelineProcessQueue(PGconn *conn);
 static int	pqPipelineFlush(PGconn *conn);
-
+static bool canChangeRowMode(PGconn *conn);
 
 /* ----------------
  * Space management for PGresult.
@@ -199,6 +200,7 @@ PQmakeEmptyPGresult(PGconn *conn, ExecStatusType status)
 			case PGRES_COPY_IN:
 			case PGRES_COPY_BOTH:
 			case PGRES_SINGLE_TUPLE:
+			case PGRES_TUPLES_CHUNK:
 				/* non-error cases */
 				break;
 			default:
@@ -910,8 +912,9 @@ pqPrepareAsyncResult(PGconn *conn)
 	/*
 	 * Replace conn->result with next_result, if any.  In the normal case
 	 * there isn't a next result and we're just dropping ownership of the
-	 * current result.  In single-row mode this restores the situation to what
-	 * it was before we created the current single-row result.
+	 * current result.  In single-row and chunked modes this restores the
+	 * situation to what it was before we created the current single-row or
+	 * chunk-of-rows result.
 	 */
 	conn->result = conn->next_result;
 	conn->error_result = false; /* next_result is never an error */
@@ -1197,10 +1200,11 @@ pqSaveParameterStatus(PGconn *conn, const char *name, const char *value)
  * (Such a string should already be translated via libpq_gettext().)
  * If it is left NULL, the error is presumed to be "out of memory".
  *
- * In single-row mode, we create a new result holding just the current row,
- * stashing the previous result in conn->next_result so that it becomes
- * active again after pqPrepareAsyncResult().  This allows the result metadata
- * (column descriptions) to be carried forward to each result row.
+ * In single-row or chunked mode, we create a new result holding just the
+ * current set of rows, stashing the previous result in conn->next_result so
+ * that it becomes active again after pqPrepareAsyncResult().  This allows the
+ * result metadata (column descriptions) to be carried forward to each result
+ * row.
  */
 int
 pqRowProcessor(PGconn *conn, const char **errmsgp)
@@ -1225,6 +1229,28 @@ pqRowProcessor(PGconn *conn, const char **errmsgp)
 		if (!res)
 			return 0;
 	}
+	else if (conn->rowsChunkSize > 0)
+	{
+		/*
+		 * In chunked mode, make a new PGresult that will hold N rows; the
+		 * original conn->result is left unchanged, as in the single-row mode.
+		 */
+		if (!conn->chunk_result)
+		{
+			/* Allocate and initialize the result to hold a chunk of rows */
+			res = PQcopyResult(res,
+							   PG_COPYRES_ATTRS | PG_COPYRES_EVENTS |
+							   PG_COPYRES_NOTICEHOOKS);
+			if (!res)
+				return 0;
+			/* Change result status to special chunk-of-rows value */
+			res->resultStatus = PGRES_TUPLES_CHUNK;
+			/* Keep this result to reuse for the next rows of the chunk */
+			conn->chunk_result = res;
+		}
+		else
+			res = conn->chunk_result;	/* Use the current chunk */
+	}
 
 	/*
 	 * Basically we just allocate space in the PGresult for each field and
@@ -1287,6 +1313,21 @@ pqRowProcessor(PGconn *conn, const char **errmsgp)
 		conn->asyncStatus = PGASYNC_READY_MORE;
 	}
 
+	/*
+	 * In chunked mode, if the count has reached the requested limit, make the
+	 * rows of the current chunk available immediately.
+	 */
+	else if (conn->rowsChunkSize > 0 && res->ntups >= conn->rowsChunkSize)
+	{
+		/* Stash old result for re-use later */
+		conn->next_result = conn->result;
+		conn->result = res;
+		/* Do not reuse that chunk of results */
+		conn->chunk_result = NULL;
+		/* And mark the result ready to return */
+		conn->asyncStatus = PGASYNC_READY_MORE;
+	}
+
 	return 1;
 
 fail:
@@ -1742,8 +1783,9 @@ PQsendQueryStart(PGconn *conn, bool newQuery)
 		 */
 		pqClearAsyncResult(conn);
 
-		/* reset single-row processing mode */
+		/* reset row-by-row and chunked processing modes */
 		conn->singleRowMode = false;
+		conn->rowsChunkSize = 0;
 	}
 
 	/* ready to send command message */
@@ -1927,25 +1969,51 @@ sendFailed:
  */
 int
 PQsetSingleRowMode(PGconn *conn)
+{
+	if (canChangeRowMode(conn))
+	{
+		conn->singleRowMode = true;
+		return 1;
+	}
+	else
+		return 0;
+}
+
+/*
+ * Select chunked results processing mode
+ */
+int
+PQsetChunkedRowsMode(PGconn *conn, int chunkSize)
+{
+	if (chunkSize >= 0 && canChangeRowMode(conn))
+	{
+		conn->rowsChunkSize = chunkSize;
+		return 1;
+	}
+	else
+		return 0;
+}
+
+static
+bool
+canChangeRowMode(PGconn *conn)
 {
 	/*
-	 * Only allow setting the flag when we have launched a query and not yet
-	 * received any results.
+	 * Only allow setting the row-by-row or by-chunks modes when we have
+	 * launched a query and not yet received any results.
 	 */
 	if (!conn)
-		return 0;
+		return false;
 	if (conn->asyncStatus != PGASYNC_BUSY)
-		return 0;
+		return false;
 	if (!conn->cmd_queue_head ||
 		(conn->cmd_queue_head->queryclass != PGQUERY_SIMPLE &&
 		 conn->cmd_queue_head->queryclass != PGQUERY_EXTENDED))
-		return 0;
+		return false;
 	if (pgHavePendingResult(conn))
-		return 0;
+		return false;
 
-	/* OK, set flag */
-	conn->singleRowMode = true;
-	return 1;
+	return true;
 }
 
 /*
@@ -2113,6 +2181,16 @@ PQgetResult(PGconn *conn)
 
 		case PGASYNC_READY:
 
+			/*
+			 * If there is a pending chunk of results, return it
+			 */
+			if (conn->chunk_result != NULL)
+			{
+				res = conn->chunk_result;
+				conn->chunk_result = NULL;
+				break;
+			}
+
 			/*
 			 * For any query type other than simple query protocol, we advance
 			 * the command queue here.  This is because for simple query
@@ -3151,10 +3229,10 @@ pqPipelineProcessQueue(PGconn *conn)
 	}
 
 	/*
-	 * Reset single-row processing mode.  (Client has to set it up for each
+	 * Reset processing mode in chunks.  (Client has to set it up for each
 	 * query, if desired.)
 	 */
-	conn->singleRowMode = false;
+	conn->rowsChunkSize = 0;
 
 	/*
 	 * If there are no further commands to process in the queue, get us in
diff --git a/src/interfaces/libpq/libpq-fe.h b/src/interfaces/libpq/libpq-fe.h
index 97762d56f5..002ed772c8 100644
--- a/src/interfaces/libpq/libpq-fe.h
+++ b/src/interfaces/libpq/libpq-fe.h
@@ -109,8 +109,9 @@ typedef enum
 	PGRES_COPY_BOTH,			/* Copy In/Out data transfer in progress */
 	PGRES_SINGLE_TUPLE,			/* single tuple from larger resultset */
 	PGRES_PIPELINE_SYNC,		/* pipeline synchronization point */
-	PGRES_PIPELINE_ABORTED		/* Command didn't run because of an abort
+	PGRES_PIPELINE_ABORTED,		/* Command didn't run because of an abort
 								 * earlier in a pipeline */
+	PGRES_TUPLES_CHUNK			/* set of tuples from larger resultset */
 } ExecStatusType;
 
 typedef enum
@@ -463,6 +464,7 @@ extern int	PQsendQueryPrepared(PGconn *conn,
 								const int *paramFormats,
 								int resultFormat);
 extern int	PQsetSingleRowMode(PGconn *conn);
+extern int	PQsetChunkedRowsMode(PGconn *conn, int chunkSize);
 extern PGresult *PQgetResult(PGconn *conn);
 
 /* Routines for managing an asynchronous query */
diff --git a/src/interfaces/libpq/libpq-int.h b/src/interfaces/libpq/libpq-int.h
index c745facfec..7786bd2435 100644
--- a/src/interfaces/libpq/libpq-int.h
+++ b/src/interfaces/libpq/libpq-int.h
@@ -431,6 +431,8 @@ struct pg_conn
 								 * sending semantics */
 	PGpipelineStatus pipelineStatus;	/* status of pipeline mode */
 	bool		singleRowMode;	/* return current query result row-by-row? */
+	int			rowsChunkSize;	/* non-zero to return query results by chunks
+								 * not exceeding that number of rows */
 	char		copy_is_binary; /* 1 = copy binary, 0 = copy text */
 	int			copy_already_done;	/* # bytes already returned in COPY OUT */
 	PGnotify   *notifyHead;		/* oldest unreported Notify msg */
@@ -536,7 +538,10 @@ struct pg_conn
 	 */
 	PGresult   *result;			/* result being constructed */
 	bool		error_result;	/* do we need to make an ERROR result? */
-	PGresult   *next_result;	/* next result (used in single-row mode) */
+	PGresult   *next_result;	/* next result (used in single-row and
+								 * by-chunks modes) */
+	PGresult   *chunk_result;	/* current chunk of results (limited to
+								 * rowsChunkSize) */
 
 	/* Assorted state for SASL, SSL, GSS, etc */
 	const pg_fe_sasl_mech *sasl;
-- 
2.34.1



  [text/plain] v4-0002-Reimplement-FETCH_COUNT-with-the-chunked-mode-in-.patch (21.0K, ../../[email protected]/3-v4-0002-Reimplement-FETCH_COUNT-with-the-chunked-mode-in-.patch)
  download | inline diff:
From a5555f339d88ad2a77e567cfd249cb948871b796 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20V=C3=A9rit=C3=A9?= <[email protected]>
Date: Mon, 20 Nov 2023 18:42:41 +0100
Subject: [PATCH v4 2/2] Reimplement FETCH_COUNT with the chunked mode in libpq
 instead of cursors.

Cursors were used only when the command starts with the keyword "SELECT",
excluding queries that start with "WITH" or "UPDATE" or "INSERT" that
may also return large result sets.

Also, cursors imply more commands sent to the server (begin/declare cursor
/repeated fetch/close cursor/commit), whereas in chunked mode, only the actual
user query is sent, resulting in less round-trips.

This also fixes the bug that combined queries (query1 \; query2;) were
not correctly handled with FETCH_COUNT set, due to cursors not supporting
multiple queries.
---
 src/bin/psql/common.c              | 545 ++++++++++-------------------
 src/bin/psql/t/001_basic.pl        |   6 +-
 src/test/regress/expected/psql.out |   9 +-
 src/test/regress/sql/psql.sql      |   4 +-
 4 files changed, 196 insertions(+), 368 deletions(-)

diff --git a/src/bin/psql/common.c b/src/bin/psql/common.c
index daabf6f12b..adb915e5c2 100644
--- a/src/bin/psql/common.c
+++ b/src/bin/psql/common.c
@@ -31,7 +31,6 @@
 #include "settings.h"
 
 static bool DescribeQuery(const char *query, double *elapsed_msec);
-static bool ExecQueryUsingCursor(const char *query, double *elapsed_msec);
 static int	ExecQueryAndProcessResults(const char *query,
 									   double *elapsed_msec,
 									   bool *svpt_gone_p,
@@ -40,8 +39,6 @@ static int	ExecQueryAndProcessResults(const char *query,
 									   const printQueryOpt *opt,
 									   FILE *printQueryFout);
 static bool command_no_begin(const char *query);
-static bool is_select_command(const char *query);
-
 
 /*
  * openQueryOutputFile --- attempt to open a query output file
@@ -373,6 +370,7 @@ AcceptResult(const PGresult *result, bool show_error)
 		{
 			case PGRES_COMMAND_OK:
 			case PGRES_TUPLES_OK:
+			case PGRES_TUPLES_CHUNK:
 			case PGRES_EMPTY_QUERY:
 			case PGRES_COPY_IN:
 			case PGRES_COPY_OUT:
@@ -1131,16 +1129,10 @@ SendQuery(const char *query)
 		/* Describe query's result columns, without executing it */
 		OK = DescribeQuery(query, &elapsed_msec);
 	}
-	else if (pset.fetch_count <= 0 || pset.gexec_flag ||
-			 pset.crosstab_flag || !is_select_command(query))
-	{
-		/* Default fetch-it-all-and-print mode */
-		OK = (ExecQueryAndProcessResults(query, &elapsed_msec, &svpt_gone, false, 0, NULL, NULL) > 0);
-	}
 	else
 	{
-		/* Fetch-in-segments mode */
-		OK = ExecQueryUsingCursor(query, &elapsed_msec);
+		/* Default fetch-and-print mode */
+		OK = (ExecQueryAndProcessResults(query, &elapsed_msec, &svpt_gone, false, 0, NULL, NULL) > 0);
 	}
 
 	if (!OK && pset.echo == PSQL_ECHO_ERRORS)
@@ -1392,6 +1384,47 @@ DescribeQuery(const char *query, double *elapsed_msec)
 	return OK;
 }
 
+/*
+ * Check if an output stream for \g needs to be opened, and if
+ * yes, open it.
+ * Return false if an error occurred, true otherwise.
+ */
+static bool
+SetupGOutput(PGresult *result, FILE **gfile_fout, bool *is_pipe)
+{
+	ExecStatusType status = PQresultStatus(result);
+	if (pset.gfname != NULL &&			/* there is a \g file or program */
+		*gfile_fout == NULL &&           /* and it's not already opened */
+		(status == PGRES_TUPLES_OK ||
+		 status == PGRES_TUPLES_CHUNK ||
+		 status == PGRES_COPY_OUT))
+	{
+		if (openQueryOutputFile(pset.gfname, gfile_fout, is_pipe))
+		{
+			if (is_pipe)
+				disable_sigpipe_trap();
+		}
+		else
+			return false;
+	}
+	return true;
+}
+
+static void
+CloseGOutput(FILE *gfile_fout, bool is_pipe)
+{
+	/* close \g file if we opened it */
+	if (gfile_fout)
+	{
+		if (is_pipe)
+		{
+			SetShellResultVariables(pclose(gfile_fout));
+			restore_sigpipe_trap();
+		}
+		else
+			fclose(gfile_fout);
+	}
+}
 
 /*
  * ExecQueryAndProcessResults: utility function for use by SendQuery()
@@ -1424,10 +1457,16 @@ ExecQueryAndProcessResults(const char *query,
 	bool		return_early = false;
 	instr_time	before,
 				after;
+	int fetch_count = pset.fetch_count;
 	PGresult   *result;
+
 	FILE	   *gfile_fout = NULL;
 	bool		gfile_is_pipe = false;
 
+	int64		total_tuples = 0;
+	int			flush_error = 0;
+	bool		is_pager = false;
+
 	if (timing)
 		INSTR_TIME_SET_CURRENT(before);
 	else
@@ -1450,6 +1489,29 @@ ExecQueryAndProcessResults(const char *query,
 		return -1;
 	}
 
+	/*
+	 * If FETCH_COUNT is set and the context allows it, use the single row
+	 * mode to fetch results and have no more than FETCH_COUNT rows in
+	 * memory.
+	 */
+	if (fetch_count > 0 && !pset.crosstab_flag && !pset.gexec_flag && !is_watch
+		&& !pset.gset_prefix && pset.show_all_results)
+	{
+		/*
+		 * The row-by-chunks fetch is not enabled when SHOW_ALL_RESULTS is false,
+		 * since we would need to accumulate all rows before knowing
+		 * whether they need to be discarded or displayed, which contradicts
+		 * FETCH_COUNT.
+		 */
+		if (!PQsetChunkedRowsMode(pset.db, fetch_count))
+		{
+			pg_log_warning("fetching results in chunks mode is unavailable");
+			fetch_count = 0;
+		}
+	}
+	else
+		fetch_count = 0;		/* fetch one resultset per query */
+
 	/*
 	 * If SIGINT is sent while the query is processing, the interrupt will be
 	 * consumed.  The user's intention, though, is to cancel the entire watch
@@ -1473,6 +1535,8 @@ ExecQueryAndProcessResults(const char *query,
 		ExecStatusType result_status;
 		PGresult   *next_result;
 		bool		last;
+		/* whether the output starts before results are fully fetched */
+		bool		partial_display = false;
 
 		if (!AcceptResult(result, false))
 		{
@@ -1568,20 +1632,9 @@ ExecQueryAndProcessResults(const char *query,
 				}
 				else if (pset.gfname)
 				{
-					/* send to \g file, which we may have opened already */
-					if (gfile_fout == NULL)
-					{
-						if (openQueryOutputFile(pset.gfname,
-												&gfile_fout, &gfile_is_pipe))
-						{
-							if (gfile_is_pipe)
-								disable_sigpipe_trap();
-							copy_stream = gfile_fout;
-						}
-						else
-							success = false;
-					}
-					else
+					/* COPY followed by \g filename or \g |program */
+					success = SetupGOutput(result, &gfile_fout, &gfile_is_pipe);
+					if (success)
 						copy_stream = gfile_fout;
 				}
 				else
@@ -1599,6 +1652,90 @@ ExecQueryAndProcessResults(const char *query,
 			success &= HandleCopyResult(&result, copy_stream);
 		}
 
+		if (fetch_count > 0 && result_status == PGRES_TUPLES_CHUNK)
+		{
+			FILE	   *tuples_fout = printQueryFout ? printQueryFout : stdout;
+			printQueryOpt my_popt = pset.popt;
+
+			total_tuples = 0;
+			partial_display = true;
+
+			success = SetupGOutput(result, &gfile_fout, &gfile_is_pipe);
+			if (gfile_fout)
+				tuples_fout = gfile_fout;
+
+			/* initialize print options for partial table output */
+			my_popt.topt.start_table = true;
+			my_popt.topt.stop_table = false;
+			my_popt.topt.prior_records = 0;
+
+			while (success)
+			{
+				/* pager: open at most once per resultset */
+				if (tuples_fout == stdout && !is_pager)
+				{
+					tuples_fout = PageOutput(INT_MAX, &(my_popt.topt));
+					is_pager = true;
+				}
+				/* display the current chunk of results unless the output stream is not working */
+				if (!flush_error)
+				{
+					printQuery(result, &my_popt, tuples_fout, is_pager, pset.logfile);
+					flush_error = fflush(tuples_fout);
+				}
+
+				/* after the first result set, disallow header decoration */
+				my_popt.topt.start_table = false;
+				my_popt.topt.prior_records += PQntuples(result);
+				total_tuples += PQntuples(result);
+
+				ClearOrSaveResult(result);
+
+				result = PQgetResult(pset.db);
+				if (result == NULL)
+				{
+					/*
+					 * Error. We expect a PGRES_TUPLES_OK result with
+					 * zero tuple in it to finish the fetch sequence.
+					 */
+					success = false;
+					if (is_pager)
+						ClosePager(tuples_fout);
+					break;
+				}
+				else if (PQresultStatus(result) == PGRES_TUPLES_OK)
+				{
+					/*
+					 * The last row has been read. Display the footer.
+					 */
+					my_popt.topt.stop_table = true;
+					printQuery(result, &my_popt, tuples_fout, is_pager, pset.logfile);
+					total_tuples += PQntuples(result);
+
+					if (is_pager)
+						ClosePager(tuples_fout);
+					ClearOrSaveResult(result);
+					result = NULL;
+					break;
+				}
+				else if (PQresultStatus(result) != PGRES_TUPLES_CHUNK)
+				{
+					/*
+					 * Error. We expect either PGRES_TUPLES_CHUNK or
+					 * PGRES_TUPLES_OK.
+					 */
+					if (is_pager)
+						ClosePager(tuples_fout);
+					success = false;
+					AcceptResult(result, true); /* display error whenever appropriate */
+					SetResultVariables(result, success);
+					break;
+				}
+			}
+		}
+		else
+			partial_display = false;
+
 		/*
 		 * Check PQgetResult() again.  In the typical case of a single-command
 		 * string, it will return NULL.  Otherwise, we'll have other results
@@ -1627,7 +1764,7 @@ ExecQueryAndProcessResults(const char *query,
 		}
 
 		/* this may or may not print something depending on settings */
-		if (result != NULL)
+		if (result != NULL && !partial_display)
 		{
 			/*
 			 * If results need to be printed into the file specified by \g,
@@ -1636,32 +1773,33 @@ ExecQueryAndProcessResults(const char *query,
 			 * tuple output, but it's still used for status output.
 			 */
 			FILE	   *tuples_fout = printQueryFout;
-			bool		do_print = true;
-
-			if (PQresultStatus(result) == PGRES_TUPLES_OK &&
-				pset.gfname)
-			{
-				if (gfile_fout == NULL)
-				{
-					if (openQueryOutputFile(pset.gfname,
-											&gfile_fout, &gfile_is_pipe))
-					{
-						if (gfile_is_pipe)
-							disable_sigpipe_trap();
-					}
-					else
-						success = do_print = false;
-				}
+			success = SetupGOutput(result, &gfile_fout, &gfile_is_pipe);
+			if (gfile_fout)
 				tuples_fout = gfile_fout;
-			}
-			if (do_print)
+			if (success)
 				success &= PrintQueryResult(result, last, opt,
 											tuples_fout, printQueryFout);
 		}
 
 		/* set variables from last result */
 		if (!is_watch && last)
-			SetResultVariables(result, success);
+		{
+			if (!partial_display)
+				SetResultVariables(result, success);
+			else if (success)
+			{
+				/*
+				 * fake SetResultVariables(). If an error occurred when
+				 * retrieving chunks, these variables have been set already.
+				 */
+				char		buf[32];
+
+				SetVariable(pset.vars, "ERROR", "false");
+				SetVariable(pset.vars, "SQLSTATE", "00000");
+				snprintf(buf, sizeof(buf), INT64_FORMAT, total_tuples);
+				SetVariable(pset.vars, "ROW_COUNT", buf);
+			}
+		}
 
 		ClearOrSaveResult(result);
 		result = next_result;
@@ -1673,17 +1811,7 @@ ExecQueryAndProcessResults(const char *query,
 		}
 	}
 
-	/* close \g file if we opened it */
-	if (gfile_fout)
-	{
-		if (gfile_is_pipe)
-		{
-			SetShellResultVariables(pclose(gfile_fout));
-			restore_sigpipe_trap();
-		}
-		else
-			fclose(gfile_fout);
-	}
+	CloseGOutput(gfile_fout, gfile_is_pipe);
 
 	/* may need this to recover from conn loss during COPY */
 	if (!CheckConnection())
@@ -1696,274 +1824,6 @@ ExecQueryAndProcessResults(const char *query,
 }
 
 
-/*
- * ExecQueryUsingCursor: run a SELECT-like query using a cursor
- *
- * This feature allows result sets larger than RAM to be dealt with.
- *
- * Returns true if the query executed successfully, false otherwise.
- *
- * If pset.timing is on, total query time (exclusive of result-printing) is
- * stored into *elapsed_msec.
- */
-static bool
-ExecQueryUsingCursor(const char *query, double *elapsed_msec)
-{
-	bool		OK = true;
-	PGresult   *result;
-	PQExpBufferData buf;
-	printQueryOpt my_popt = pset.popt;
-	bool		timing = pset.timing;
-	FILE	   *fout;
-	bool		is_pipe;
-	bool		is_pager = false;
-	bool		started_txn = false;
-	int64		total_tuples = 0;
-	int			ntuples;
-	int			fetch_count;
-	char		fetch_cmd[64];
-	instr_time	before,
-				after;
-	int			flush_error;
-
-	*elapsed_msec = 0;
-
-	/* initialize print options for partial table output */
-	my_popt.topt.start_table = true;
-	my_popt.topt.stop_table = false;
-	my_popt.topt.prior_records = 0;
-
-	if (timing)
-		INSTR_TIME_SET_CURRENT(before);
-	else
-		INSTR_TIME_SET_ZERO(before);
-
-	/* if we're not in a transaction, start one */
-	if (PQtransactionStatus(pset.db) == PQTRANS_IDLE)
-	{
-		result = PQexec(pset.db, "BEGIN");
-		OK = AcceptResult(result, true) &&
-			(PQresultStatus(result) == PGRES_COMMAND_OK);
-		ClearOrSaveResult(result);
-		if (!OK)
-			return false;
-		started_txn = true;
-	}
-
-	/* Send DECLARE CURSOR */
-	initPQExpBuffer(&buf);
-	appendPQExpBuffer(&buf, "DECLARE _psql_cursor NO SCROLL CURSOR FOR\n%s",
-					  query);
-
-	result = PQexec(pset.db, buf.data);
-	OK = AcceptResult(result, true) &&
-		(PQresultStatus(result) == PGRES_COMMAND_OK);
-	if (!OK)
-		SetResultVariables(result, OK);
-	ClearOrSaveResult(result);
-	termPQExpBuffer(&buf);
-	if (!OK)
-		goto cleanup;
-
-	if (timing)
-	{
-		INSTR_TIME_SET_CURRENT(after);
-		INSTR_TIME_SUBTRACT(after, before);
-		*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
-	}
-
-	/*
-	 * In \gset mode, we force the fetch count to be 2, so that we will throw
-	 * the appropriate error if the query returns more than one row.
-	 */
-	if (pset.gset_prefix)
-		fetch_count = 2;
-	else
-		fetch_count = pset.fetch_count;
-
-	snprintf(fetch_cmd, sizeof(fetch_cmd),
-			 "FETCH FORWARD %d FROM _psql_cursor",
-			 fetch_count);
-
-	/* prepare to write output to \g argument, if any */
-	if (pset.gfname)
-	{
-		if (!openQueryOutputFile(pset.gfname, &fout, &is_pipe))
-		{
-			OK = false;
-			goto cleanup;
-		}
-		if (is_pipe)
-			disable_sigpipe_trap();
-	}
-	else
-	{
-		fout = pset.queryFout;
-		is_pipe = false;		/* doesn't matter */
-	}
-
-	/* clear any pre-existing error indication on the output stream */
-	clearerr(fout);
-
-	for (;;)
-	{
-		if (timing)
-			INSTR_TIME_SET_CURRENT(before);
-
-		/* get fetch_count tuples at a time */
-		result = PQexec(pset.db, fetch_cmd);
-
-		if (timing)
-		{
-			INSTR_TIME_SET_CURRENT(after);
-			INSTR_TIME_SUBTRACT(after, before);
-			*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
-		}
-
-		if (PQresultStatus(result) != PGRES_TUPLES_OK)
-		{
-			/* shut down pager before printing error message */
-			if (is_pager)
-			{
-				ClosePager(fout);
-				is_pager = false;
-			}
-
-			OK = AcceptResult(result, true);
-			Assert(!OK);
-			SetResultVariables(result, OK);
-			ClearOrSaveResult(result);
-			break;
-		}
-
-		if (pset.gset_prefix)
-		{
-			/* StoreQueryTuple will complain if not exactly one row */
-			OK = StoreQueryTuple(result);
-			ClearOrSaveResult(result);
-			break;
-		}
-
-		/*
-		 * Note we do not deal with \gdesc, \gexec or \crosstabview modes here
-		 */
-
-		ntuples = PQntuples(result);
-		total_tuples += ntuples;
-
-		if (ntuples < fetch_count)
-		{
-			/* this is the last result set, so allow footer decoration */
-			my_popt.topt.stop_table = true;
-		}
-		else if (fout == stdout && !is_pager)
-		{
-			/*
-			 * If query requires multiple result sets, hack to ensure that
-			 * only one pager instance is used for the whole mess
-			 */
-			fout = PageOutput(INT_MAX, &(my_popt.topt));
-			is_pager = true;
-		}
-
-		printQuery(result, &my_popt, fout, is_pager, pset.logfile);
-
-		ClearOrSaveResult(result);
-
-		/* after the first result set, disallow header decoration */
-		my_popt.topt.start_table = false;
-		my_popt.topt.prior_records += ntuples;
-
-		/*
-		 * Make sure to flush the output stream, so intermediate results are
-		 * visible to the client immediately.  We check the results because if
-		 * the pager dies/exits/etc, there's no sense throwing more data at
-		 * it.
-		 */
-		flush_error = fflush(fout);
-
-		/*
-		 * Check if we are at the end, if a cancel was pressed, or if there
-		 * were any errors either trying to flush out the results, or more
-		 * generally on the output stream at all.  If we hit any errors
-		 * writing things to the stream, we presume $PAGER has disappeared and
-		 * stop bothering to pull down more data.
-		 */
-		if (ntuples < fetch_count || cancel_pressed || flush_error ||
-			ferror(fout))
-			break;
-	}
-
-	if (pset.gfname)
-	{
-		/* close \g argument file/pipe */
-		if (is_pipe)
-		{
-			SetShellResultVariables(pclose(fout));
-			restore_sigpipe_trap();
-		}
-		else
-			fclose(fout);
-	}
-	else if (is_pager)
-	{
-		/* close transient pager */
-		ClosePager(fout);
-	}
-
-	if (OK)
-	{
-		/*
-		 * We don't have a PGresult here, and even if we did it wouldn't have
-		 * the right row count, so fake SetResultVariables().  In error cases,
-		 * we already set the result variables above.
-		 */
-		char		buf[32];
-
-		SetVariable(pset.vars, "ERROR", "false");
-		SetVariable(pset.vars, "SQLSTATE", "00000");
-		snprintf(buf, sizeof(buf), INT64_FORMAT, total_tuples);
-		SetVariable(pset.vars, "ROW_COUNT", buf);
-	}
-
-cleanup:
-	if (timing)
-		INSTR_TIME_SET_CURRENT(before);
-
-	/*
-	 * We try to close the cursor on either success or failure, but on failure
-	 * ignore the result (it's probably just a bleat about being in an aborted
-	 * transaction)
-	 */
-	result = PQexec(pset.db, "CLOSE _psql_cursor");
-	if (OK)
-	{
-		OK = AcceptResult(result, true) &&
-			(PQresultStatus(result) == PGRES_COMMAND_OK);
-		ClearOrSaveResult(result);
-	}
-	else
-		PQclear(result);
-
-	if (started_txn)
-	{
-		result = PQexec(pset.db, OK ? "COMMIT" : "ROLLBACK");
-		OK &= AcceptResult(result, true) &&
-			(PQresultStatus(result) == PGRES_COMMAND_OK);
-		ClearOrSaveResult(result);
-	}
-
-	if (timing)
-	{
-		INSTR_TIME_SET_CURRENT(after);
-		INSTR_TIME_SUBTRACT(after, before);
-		*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
-	}
-
-	return OK;
-}
-
-
 /*
  * Advance the given char pointer over white space and SQL comments.
  */
@@ -2243,43 +2103,6 @@ command_no_begin(const char *query)
 }
 
 
-/*
- * Check whether the specified command is a SELECT (or VALUES).
- */
-static bool
-is_select_command(const char *query)
-{
-	int			wordlen;
-
-	/*
-	 * First advance over any whitespace, comments and left parentheses.
-	 */
-	for (;;)
-	{
-		query = skip_white_space(query);
-		if (query[0] == '(')
-			query++;
-		else
-			break;
-	}
-
-	/*
-	 * Check word length (since "selectx" is not "select").
-	 */
-	wordlen = 0;
-	while (isalpha((unsigned char) query[wordlen]))
-		wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
-
-	if (wordlen == 6 && pg_strncasecmp(query, "select", 6) == 0)
-		return true;
-
-	if (wordlen == 6 && pg_strncasecmp(query, "values", 6) == 0)
-		return true;
-
-	return false;
-}
-
-
 /*
  * Test if the current user is a database superuser.
  */
diff --git a/src/bin/psql/t/001_basic.pl b/src/bin/psql/t/001_basic.pl
index 95f4e60ab2..62a5d0f383 100644
--- a/src/bin/psql/t/001_basic.pl
+++ b/src/bin/psql/t/001_basic.pl
@@ -161,7 +161,7 @@ psql_like(
 	'\errverbose with no previous error');
 
 # There are three main ways to run a query that might affect
-# \errverbose: The normal way, using a cursor by setting FETCH_COUNT,
+# \errverbose: The normal way, piecemeal retrieval using FETCH_COUNT,
 # and using \gdesc.  Test them all.
 
 like(
@@ -184,10 +184,10 @@ like(
 			"\\set FETCH_COUNT 1\nSELECT error;\n\\errverbose",
 			on_error_stop => 0))[2],
 	qr/\A^psql:<stdin>:2: ERROR:  .*$
-^LINE 2: SELECT error;$
+^LINE 1: SELECT error;$
 ^ *^.*$
 ^psql:<stdin>:3: error: ERROR:  [0-9A-Z]{5}: .*$
-^LINE 2: SELECT error;$
+^LINE 1: SELECT error;$
 ^ *^.*$
 ^LOCATION: .*$/m,
 	'\errverbose after FETCH_COUNT query with error');
diff --git a/src/test/regress/expected/psql.out b/src/test/regress/expected/psql.out
index 13e4f6db7b..aa53f11682 100644
--- a/src/test/regress/expected/psql.out
+++ b/src/test/regress/expected/psql.out
@@ -4754,7 +4754,7 @@ number of rows: 0
 last error message: syntax error at end of input
 \echo 'last error code:' :LAST_ERROR_SQLSTATE
 last error code: 42601
--- check row count for a cursor-fetched query
+-- check row count for a query with chunked results
 \set FETCH_COUNT 10
 select unique2 from tenk1 order by unique2 limit 19;
  unique2 
@@ -4786,7 +4786,7 @@ error: false
 error code: 00000
 \echo 'number of rows:' :ROW_COUNT
 number of rows: 19
--- cursor-fetched query with an error after the first group
+-- chunked results with an error after the first chunk
 select 1/(15-unique2) from tenk1 order by unique2 limit 19;
  ?column? 
 ----------
@@ -4800,6 +4800,11 @@ select 1/(15-unique2) from tenk1 order by unique2 limit 19;
         0
         0
         0
+        0
+        0
+        0
+        0
+        1
 ERROR:  division by zero
 \echo 'error:' :ERROR
 error: true
diff --git a/src/test/regress/sql/psql.sql b/src/test/regress/sql/psql.sql
index 695c72d866..3c4e6962ba 100644
--- a/src/test/regress/sql/psql.sql
+++ b/src/test/regress/sql/psql.sql
@@ -1160,14 +1160,14 @@ SELECT 4 AS \gdesc
 \echo 'last error message:' :LAST_ERROR_MESSAGE
 \echo 'last error code:' :LAST_ERROR_SQLSTATE
 
--- check row count for a cursor-fetched query
+-- check row count for a query with chunked results
 \set FETCH_COUNT 10
 select unique2 from tenk1 order by unique2 limit 19;
 \echo 'error:' :ERROR
 \echo 'error code:' :SQLSTATE
 \echo 'number of rows:' :ROW_COUNT
 
--- cursor-fetched query with an error after the first group
+-- chunked results with an error after the first chunk
 select 1/(15-unique2) from tenk1 order by unique2 limit 19;
 \echo 'error:' :ERROR
 \echo 'error code:' :SQLSTATE
-- 
2.34.1



^ permalink  raw  reply  [nested|flat] 4+ messages in thread

end of thread, other threads:[~2023-11-20 19:13 UTC | newest]

Thread overview: 4+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-09-29 13:59 [PATCH v56 5/6] Remove the GUC stats_temp_directory Kyotaro Horiguchi <[email protected]>
2023-03-24 20:12 Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs Tom Lane <[email protected]>
2023-07-07 17:42 ` Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs Daniel Verite <[email protected]>
2023-11-20 19:13   ` Re: psql's FETCH_COUNT (cursor) is not being respected for CTEs Daniel Verite <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox