pg_stat_progress_basebackup_v3.patch

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 8839699079..7068f82ff7 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -376,6 +376,14 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
       </entry>
      </row>
 
+     <row>
+      <entry><structname>pg_stat_progress_basebackup</structname><indexterm><primary>pg_stat_progress_basebackup</primary></indexterm></entry>
+      <entry>One row for each WAL sender process streaming a base backup,
+       showing current progress.
+       See <xref linkend='basebackup-progress-reporting'/>.
+      </entry>
+     </row>
+
     </tbody>
    </tgroup>
   </table>
@@ -3515,7 +3523,10 @@ SELECT pg_stat_get_backend_pid(s.backendid) AS pid,
    certain commands during command execution.  Currently, the only commands
    which support progress reporting are <command>ANALYZE</command>,
    <command>CLUSTER</command>,
-   <command>CREATE INDEX</command>, and <command>VACUUM</command>.
+   <command>CREATE INDEX</command>, <command>VACUUM</command>,
+   and <xref linkend="protocol-replication-base-backup"/> (i.e., replication
+   command that <xref linkend="app-pgbasebackup"/> issues to take
+   a base backup).
    This may be expanded in the future.
   </para>
 
@@ -4316,6 +4327,143 @@ SELECT pg_stat_get_backend_pid(s.backendid) AS pid,
    </tbody>
    </tgroup>
   </table>
+ </sect2>
+
+ <sect2 id="basebackup-progress-reporting">
+  <title>Base Backup Progress Reporting</title>
+
+  <para>
+   Whenever <application>pg_basebackup</application> is taking a base
+   backup, the <structname>pg_stat_progress_basebackup</structname>
+   view will contain a row for each WAL sender process that is currently
+   running <command>BASE_BACKUP</command> replication command
+   and streaming the backup. The tables below describe the information
+   that will be reported and provide information about how to interpret it.
+  </para>
+
+  <table id="pg-stat-progress-basebackup-view" xreflabel="pg_stat_progress_basebackup">
+   <title><structname>pg_stat_progress_basebackup</structname> View</title>
+   <tgroup cols="3">
+    <thead>
+    <row>
+      <entry>Column</entry>
+      <entry>Type</entry>
+      <entry>Description</entry>
+     </row>
+    </thead>
+
+   <tbody>
+    <row>
+     <entry><structfield>pid</structfield></entry>
+     <entry><type>integer</type></entry>
+     <entry>Process ID of a WAL sender process.</entry>
+    </row>
+    <row>
+     <entry><structfield>phase</structfield></entry>
+     <entry><type>text</type></entry>
+     <entry>Current processing phase. See <xref linkend="basebackup-phases" />.</entry>
+    </row>
+    <row>
+     <entry><structfield>backup_total</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+      Total amount of data that will be streamed. If progress reporting
+      is not enabled in <application>pg_basebackup</application>
+      (i.e., <literal>--progress</literal> option is not specified),
+      this is <literal>0</literal>. Otherwise, this is estimated and
+      reported as of the beginning of <literal>streaming backup</literal>
+      phase. Note that this is only an approximation since the database
+      may change during <literal>streaming backup</literal> phase
+      and WAL log may be included in the backup later. This is always
+      the same value as <structfield>backup_streamed</structfield>
+      once the amount of data streamed exceeds the estimated
+      total size.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>backup_streamed</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+      Amount of data streamed. This counter only advances
+      when the phase is <literal>streaming backup</literal> or
+      <literal>transfering wal</literal>.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>tablespaces_total</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+      Total number of tablespaces that will be streamed.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>tablespaces_streamed</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+      Number of tablespaces streamed. This counter only
+      advances when the phase is <literal>streaming backup</literal>.
+     </entry>
+    </row>
+   </tbody>
+   </tgroup>
+  </table>
+
+  <table id="basebackup-phases">
+   <title>Base backup phases</title>
+   <tgroup cols="2">
+    <thead>
+     <row>
+      <entry>Phase</entry>
+      <entry>Description</entry>
+     </row>
+    </thead>
+    <tbody>
+     <row>
+      <entry><literal>initializing</literal></entry>
+      <entry>
+       The WAL sender process is preparing to begin the backup.
+       This phase is expected to be very brief.
+      </entry>
+     </row>
+     <row>
+      <entry><literal>starting backup</literal></entry>
+      <entry>
+       The WAL sender process is currently performing
+       <function>pg_start_backup</function> and setting up for
+       taking a base backup.
+      </entry>
+     </row>
+     <row>
+      <entry><literal>streaming backup</literal></entry>
+      <entry>
+       The WAL sender process is currently streaming a base backup.
+      </entry>
+     </row>
+     <row>
+      <entry><literal>stopping backup</literal></entry>
+      <entry>
+       The WAL sender process is currently performing
+       <function>pg_stop_backup</function> and finishing the backup.
+       If either <literal>--wal-method=none</literal> or
+       <literal>--wal-method=stream</literal> is specified in
+       <application>pg_basebackup</application>, the backup will end
+       when this phase is completed.
+      </entry>
+     </row>
+     <row>
+      <entry><literal>transferring wal</literal></entry>
+      <entry>
+       The WAL sender process is currently transferring all WAL logs
+       generated during the backup. This phase occurs after
+       <literal>stopping backup</literal> phase if
+       <literal>--wal-method=fetch</literal> is specified in
+       <application>pg_basebackup</application>. The backup will end
+       when this phase is completed.
+      </entry>
+     </row>
+    </tbody>
+   </tgroup>
+  </table>
 
  </sect2>
  </sect1>
diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml
index 80275215e0..f139ba0231 100644
--- a/doc/src/sgml/protocol.sgml
+++ b/doc/src/sgml/protocol.sgml
@@ -2465,7 +2465,7 @@ The commands accepted in replication mode are:
     </listitem>
   </varlistentry>
 
-  <varlistentry>
+  <varlistentry id="protocol-replication-base-backup" xreflabel="BASE_BACKUP">
     <term><literal>BASE_BACKUP</literal> [ <literal>LABEL</literal> <replaceable>'label'</replaceable> ] [ <literal>PROGRESS</literal> ] [ <literal>FAST</literal> ] [ <literal>WAL</literal> ] [ <literal>NOWAIT</literal> ] [ <literal>MAX_RATE</literal> <replaceable>rate</replaceable> ] [ <literal>TABLESPACE_MAP</literal> ] [ <literal>NOVERIFY_CHECKSUMS</literal> ]
      <indexterm><primary>BASE_BACKUP</primary></indexterm>
     </term>
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index c9e6060035..c2779381cf 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1059,6 +1059,21 @@ CREATE VIEW pg_stat_progress_create_index AS
     FROM pg_stat_get_progress_info('CREATE INDEX') AS S
         LEFT JOIN pg_database D ON S.datid = D.oid;
 
+CREATE VIEW pg_stat_progress_basebackup AS
+    SELECT
+        S.pid AS pid,
+        CASE S.param1 WHEN 0 THEN 'initializing'
+                      WHEN 1 THEN 'starting backup'
+                      WHEN 2 THEN 'streaming backup'
+                      WHEN 3 THEN 'stopping backup'
+                      WHEN 4 THEN 'transferring wal'
+                      END AS phase,
+	S.param2 AS backup_total,
+	S.param3 AS backup_streamed,
+	S.param4 AS tablespaces_total,
+	S.param5 AS tablespaces_streamed
+    FROM pg_stat_get_progress_info('BASEBACKUP') AS S;
+
 CREATE VIEW pg_user_mappings AS
     SELECT
         U.oid       AS umid,
diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c
index dea8aab45e..ec013fea04 100644
--- a/src/backend/replication/basebackup.c
+++ b/src/backend/replication/basebackup.c
@@ -19,6 +19,7 @@
 #include "access/xlog_internal.h"	/* for pg_start/stop_backup */
 #include "catalog/pg_type.h"
 #include "common/file_perm.h"
+#include "commands/progress.h"
 #include "lib/stringinfo.h"
 #include "libpq/libpq.h"
 #include "libpq/pqformat.h"
@@ -70,6 +71,7 @@ static void parse_basebackup_options(List *options, basebackup_options *opt);
 static void SendXlogRecPtrResult(XLogRecPtr ptr, TimeLineID tli);
 static int	compareWalFileNames(const ListCell *a, const ListCell *b);
 static void throttle(size_t increment);
+static void	update_basebackup_progress(int64 delta);
 static bool is_checksummed_file(const char *fullpath, const char *filename);
 
 /* Was the backup currently in-progress initiated in recovery mode? */
@@ -121,6 +123,12 @@ static long long int total_checksum_failures;
 /* Do not verify checksums. */
 static bool noverify_checksums = false;
 
+/* Total amount of backup data that will be streamed */
+static int64	backup_total = 0;
+
+/* Amount of backup data already streamed */
+static int64	backup_streamed = 0;
+
 /*
  * The contents of these directories are removed or recreated during server
  * start so they are not included in backups.  The directories themselves are
@@ -232,6 +240,8 @@ perform_base_backup(basebackup_options *opt)
 	int			datadirpathlen;
 	List	   *tablespaces = NIL;
 
+	pgstat_progress_start_command(PROGRESS_COMMAND_BASEBACKUP, InvalidOid);
+
 	datadirpathlen = strlen(DataDir);
 
 	backup_started_in_recovery = RecoveryInProgress();
@@ -241,6 +251,8 @@ perform_base_backup(basebackup_options *opt)
 
 	total_checksum_failures = 0;
 
+	pgstat_progress_update_param(PROGRESS_BASEBACKUP_PHASE,
+								 PROGRESS_BASEBACKUP_PHASE_START_BACKUP);
 	startptr = do_pg_start_backup(opt->label, opt->fastcheckpoint, &starttli,
 								  labelfile, &tablespaces,
 								  tblspc_map_file,
@@ -257,6 +269,7 @@ perform_base_backup(basebackup_options *opt)
 	{
 		ListCell   *lc;
 		tablespaceinfo *ti;
+		int		tblspc_streamed = 0;
 
 		SendXlogRecPtrResult(startptr, starttli);
 
@@ -358,8 +371,14 @@ perform_base_backup(basebackup_options *opt)
 			}
 			else
 				pq_putemptymessage('c');	/* CopyDone */
+
+			tblspc_streamed++;
+			pgstat_progress_update_param(PROGRESS_BASEBACKUP_TBLSPC_STREAMED,
+										 tblspc_streamed);
 		}
 
+		pgstat_progress_update_param(PROGRESS_BASEBACKUP_PHASE,
+									 PROGRESS_BASEBACKUP_PHASE_STOP_BACKUP);
 		endptr = do_pg_stop_backup(labelfile->data, !opt->nowait, &endtli);
 	}
 	PG_END_ENSURE_ERROR_CLEANUP(do_pg_abort_backup, BoolGetDatum(false));
@@ -385,6 +404,9 @@ perform_base_backup(basebackup_options *opt)
 		ListCell   *lc;
 		TimeLineID	tli;
 
+		pgstat_progress_update_param(PROGRESS_BASEBACKUP_PHASE,
+									 PROGRESS_BASEBACKUP_PHASE_TRANSFER_WAL);
+
 		/*
 		 * I'd rather not worry about timelines here, so scan pg_wal and
 		 * include all WAL files in the range between 'startptr' and 'endptr',
@@ -534,6 +556,7 @@ perform_base_backup(basebackup_options *opt)
 				if (pq_putmessage('d', buf, cnt))
 					ereport(ERROR,
 							(errmsg("base backup could not send data, aborting backup")));
+				update_basebackup_progress(cnt);
 
 				len += cnt;
 				throttle(cnt);
@@ -609,6 +632,7 @@ perform_base_backup(basebackup_options *opt)
 				 errmsg("checksum verification failure during base backup")));
 	}
 
+	pgstat_progress_end_command();
 }
 
 /*
@@ -837,7 +861,10 @@ SendBackupHeader(List *tablespaces)
 			pq_sendbytes(&buf, ti->path, len);
 		}
 		if (ti->size >= 0)
+		{
 			send_int8_string(&buf, ti->size / 1024);
+			backup_total += ti->size;
+		}
 		else
 			pq_sendint32(&buf, -1); /* NULL */
 
@@ -846,6 +873,13 @@ SendBackupHeader(List *tablespaces)
 
 	/* Send a CommandComplete message */
 	pq_puttextmessage('C', "SELECT");
+
+	pgstat_progress_update_param(PROGRESS_BASEBACKUP_BACKUP_TOTAL,
+								 backup_total);
+	pgstat_progress_update_param(PROGRESS_BASEBACKUP_TBLSPC_TOTAL,
+								 list_length(tablespaces));
+	pgstat_progress_update_param(PROGRESS_BASEBACKUP_PHASE,
+								 PROGRESS_BASEBACKUP_PHASE_STREAM_BACKUP);
 }
 
 /*
@@ -935,6 +969,7 @@ sendFileWithContent(const char *filename, const char *content)
 	_tarWriteHeader(filename, NULL, &statbuf, false);
 	/* Send the contents as a CopyData message */
 	pq_putmessage('d', content, len);
+	update_basebackup_progress(len);
 
 	/* Pad to 512 byte boundary, per tar format requirements */
 	pad = ((len + 511) & ~511) - len;
@@ -944,6 +979,7 @@ sendFileWithContent(const char *filename, const char *content)
 
 		MemSet(buf, 0, pad);
 		pq_putmessage('d', buf, pad);
+		update_basebackup_progress(pad);
 	}
 }
 
@@ -1540,6 +1576,7 @@ sendFile(const char *readfilename, const char *tarfilename, struct stat *statbuf
 		if (pq_putmessage('d', buf, cnt))
 			ereport(ERROR,
 					(errmsg("base backup could not send data, aborting backup")));
+		update_basebackup_progress(cnt);
 
 		len += cnt;
 		throttle(cnt);
@@ -1565,6 +1602,7 @@ sendFile(const char *readfilename, const char *tarfilename, struct stat *statbuf
 		{
 			cnt = Min(sizeof(buf), statbuf->st_size - len);
 			pq_putmessage('d', buf, cnt);
+			update_basebackup_progress(cnt);
 			len += cnt;
 			throttle(cnt);
 		}
@@ -1579,6 +1617,7 @@ sendFile(const char *readfilename, const char *tarfilename, struct stat *statbuf
 	{
 		MemSet(buf, 0, pad);
 		pq_putmessage('d', buf, pad);
+		update_basebackup_progress(pad);
 	}
 
 	FreeFile(fp);
@@ -1633,6 +1672,7 @@ _tarWriteHeader(const char *filename, const char *linktarget,
 		}
 
 		pq_putmessage('d', h, sizeof(h));
+		update_basebackup_progress(sizeof(h));
 	}
 
 	return sizeof(h);
@@ -1730,3 +1770,30 @@ throttle(size_t increment)
 	 */
 	throttled_last = GetCurrentTimestamp();
 }
+
+/*
+ * Increment the counter for the amount of data already streamed
+ * by the given number of bytes, and update the progress report for
+ * pg_stat_progress_basebackup.
+ */
+static void
+update_basebackup_progress(int64 delta)
+{
+	backup_streamed += delta;
+
+	/*
+	 * Avoid overflowing past 100% or the full size. This may make the total
+	 * size number change as we approach the end of the backup (the estimate
+	 * will always be wrong if WAL is included), but that's better than having
+	 * the done column be bigger than the total.
+	 */
+	if (backup_total > 0 && backup_streamed > backup_total)
+	{
+		backup_total = backup_streamed;
+		pgstat_progress_update_param(PROGRESS_BASEBACKUP_BACKUP_TOTAL,
+									 backup_total);
+	}
+
+	pgstat_progress_update_param(PROGRESS_BASEBACKUP_BACKUP_STREAMED,
+								 backup_streamed);
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 7b2da2b36f..8fd0b16c9d 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -474,6 +474,8 @@ pg_stat_get_progress_info(PG_FUNCTION_ARGS)
 		cmdtype = PROGRESS_COMMAND_CLUSTER;
 	else if (pg_strcasecmp(cmd, "CREATE INDEX") == 0)
 		cmdtype = PROGRESS_COMMAND_CREATE_INDEX;
+	else if (pg_strcasecmp(cmd, "BASEBACKUP") == 0)
+		cmdtype = PROGRESS_COMMAND_BASEBACKUP;
 	else
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
diff --git a/src/include/commands/progress.h b/src/include/commands/progress.h
index 12e9d3d42f..15693f2da0 100644
--- a/src/include/commands/progress.h
+++ b/src/include/commands/progress.h
@@ -119,4 +119,17 @@
 #define PROGRESS_SCAN_BLOCKS_TOTAL				15
 #define PROGRESS_SCAN_BLOCKS_DONE				16
 
+/* Progress parameters for pg_basebackup */
+#define PROGRESS_BASEBACKUP_PHASE						0
+#define PROGRESS_BASEBACKUP_BACKUP_TOTAL			1
+#define PROGRESS_BASEBACKUP_BACKUP_STREAMED			2
+#define PROGRESS_BASEBACKUP_TBLSPC_TOTAL				3
+#define PROGRESS_BASEBACKUP_TBLSPC_STREAMED			4
+
+/* Phases of pg_basebackup (as advertised via PROGRESS_BASEBACKUP_PHASE) */
+#define PROGRESS_BASEBACKUP_PHASE_START_BACKUP		1
+#define PROGRESS_BASEBACKUP_PHASE_STREAM_BACKUP		2
+#define PROGRESS_BASEBACKUP_PHASE_STOP_BACKUP		3
+#define PROGRESS_BASEBACKUP_PHASE_TRANSFER_WAL		4
+
 #endif
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index aecb6013f0..62e547aa24 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -958,7 +958,8 @@ typedef enum ProgressCommandType
 	PROGRESS_COMMAND_VACUUM,
 	PROGRESS_COMMAND_ANALYZE,
 	PROGRESS_COMMAND_CLUSTER,
-	PROGRESS_COMMAND_CREATE_INDEX
+	PROGRESS_COMMAND_CREATE_INDEX,
+	PROGRESS_COMMAND_BASEBACKUP
 } ProgressCommandType;
 
 #define PGSTAT_NUM_PROGRESS_PARAM	20
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index 2ab2115fa1..f5404a4c54 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1875,6 +1875,20 @@ pg_stat_progress_analyze| SELECT s.pid,
     (s.param8)::oid AS current_child_table_relid
    FROM (pg_stat_get_progress_info('ANALYZE'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20)
      LEFT JOIN pg_database d ON ((s.datid = d.oid)));
+pg_stat_progress_basebackup| SELECT s.pid,
+        CASE s.param1
+            WHEN 0 THEN 'initializing'::text
+            WHEN 1 THEN 'starting backup'::text
+            WHEN 2 THEN 'streaming backup'::text
+            WHEN 3 THEN 'stopping backup'::text
+            WHEN 4 THEN 'transferring wal'::text
+            ELSE NULL::text
+        END AS phase,
+    s.param2 AS backup_total,
+    s.param3 AS backup_streamed,
+    s.param4 AS tablespaces_total,
+    s.param5 AS tablespaces_streamed
+   FROM pg_stat_get_progress_info('BASEBACKUP'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20);
 pg_stat_progress_cluster| SELECT s.pid,
     s.datid,
     d.datname,