diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index bad1f445e42..b10b48c3b55 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -6826,8 +6826,9 @@ SELECT pg_stat_get_backend_pid(s.backendid) AS pid,
        <structfield>backup_total</structfield> <type>bigint</type>
       </para>
       <para>
-       Total amount of data that will be streamed. This is estimated and
-       reported as of the beginning of
+       Total amount of data that will be streamed. This counts archive data
+       before any server-side compression. The estimate is reported as of
+       the beginning of the
        <literal>streaming database files</literal> phase. Note that
        this is only an approximation since the database
        may change during <literal>streaming database files</literal> phase
@@ -6846,7 +6847,8 @@ SELECT pg_stat_get_backend_pid(s.backendid) AS pid,
        <structfield>backup_streamed</structfield> <type>bigint</type>
       </para>
       <para>
-       Amount of data streamed. This counter only advances
+       Amount of data streamed. This counts archive data before any server-side
+       compression. This counter only advances
        when the phase is <literal>streaming database files</literal> or
        <literal>transferring wal files</literal>.
       </para></entry>
diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml
index e030b55186c..60d749aa358 100644
--- a/doc/src/sgml/protocol.sgml
+++ b/doc/src/sgml/protocol.sgml
@@ -2901,8 +2901,10 @@ psql "dbname=postgres replication=database" -c "IDENTIFY_SYSTEM;"
          <term><literal>size</literal> (<type>int8</type>)</term>
          <listitem>
           <para>
-           The approximate size of the tablespace, in kilobytes (1024 bytes),
-           if progress report has been requested; otherwise it's null.
+           The approximate size of the archive that will be generated for the
+           tablespace, in kilobytes (1024 bytes), if progress report has been
+           requested; otherwise it's null. This size is measured before any
+           server-side compression.
           </para>
          </listitem>
         </varlistentry>
@@ -3000,8 +3002,9 @@ psql "dbname=postgres replication=database" -c "IDENTIFY_SYSTEM;"
           <varlistentry>
            <term>Int64</term>
            <listitem><para>
-            The number of bytes from the current tablespace for which
-            processing has been completed.
+            The cumulative number of bytes processed across all tablespaces
+            since the backup began. This counts archive data before any
+            server-side compression.
            </para></listitem>
           </varlistentry>
          </variablelist>
diff --git a/doc/src/sgml/ref/pg_basebackup.sgml b/doc/src/sgml/ref/pg_basebackup.sgml
index 04323af0b35..7f57fdf09d5 100644
--- a/doc/src/sgml/ref/pg_basebackup.sgml
+++ b/doc/src/sgml/ref/pg_basebackup.sgml
@@ -663,8 +663,8 @@ PostgreSQL documentation
         always being <literal>NULL</literal>.
        </para>
        <para>
-        Without this option, the backup will start by enumerating
-        the size of the entire database, and then go back and send
+        Without this option, the backup will start by estimating the total
+        amount of data that will be streamed, and then go back and send
         the actual contents. This may make the backup take slightly
         longer, and in particular it will take longer before the first
         data is sent. This option is useful to avoid such estimation
diff --git a/src/include/backup/basebackup_sink.h b/src/include/backup/basebackup_sink.h
index a1cd24ce814..b024b1a3791 100644
--- a/src/include/backup/basebackup_sink.h
+++ b/src/include/backup/basebackup_sink.h
@@ -51,10 +51,12 @@ typedef struct bbsink_ops bbsink_ops;
  * 'tablespace_num' is the index of the current tablespace within the list
  * stored in 'tablespaces'.
  *
- * 'bytes_done' is the number of bytes read so far from $PGDATA.
+ * 'bytes_done' is the number of bytes of archive data generated so far. This
+ * is counted before any server-side compression.
  *
- * 'bytes_total' is the total number of bytes estimated to be present in
- * $PGDATA, if we have estimated this.
+ * 'bytes_total' is the total number of bytes of archive data estimated to be
+ * generated, if we have estimated this. The estimate is for data before any
+ * server-side compression.
  *
  * 'bytes_total_is_valid' is true if and only if a proper estimate has been
  * stored into 'bytes_total'.