Morph pg_replication_slots.min_safe_lsn to safe_wal_size

The previous definition of the column was almost universally disliked,
so provide this updated definition which is more useful for monitoring
purposes: a large positive value is good, while zero or a negative value
means danger.  This should be operationally more convenient.

Backpatch to 13, where the new column to pg_replication_slots (and the
feature it represents) were added.

Author: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Author: Álvaro Herrera <alvherre@alvh.no-ip.org>
Reported-by: Fujii Masao <masao.fujii@oss.nttdata.com>
Discussion: https://postgr.es/m/9ddfbf8c-2f67-904d-44ed-cf8bc5916228@oss.nttdata.com

2 files changed, 12 insertions, 14 deletions

diff --git a/src/test/recovery/t/019_replslot_limit.pl b/src/test/recovery/t/019_replslot_limit.pl
index 7d22ae57201..af656c6902f 100644
--- a/src/test/recovery/t/019_replslot_limit.pl
+++ b/src/test/recovery/t/019_replslot_limit.pl
@@ -28,7 +28,7 @@ $node_master->safe_psql('postgres',
 
 # The slot state and remain should be null before the first connection
 my $result = $node_master->safe_psql('postgres',
-	"SELECT restart_lsn IS NULL, wal_status is NULL, min_safe_lsn is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
+	"SELECT restart_lsn IS NULL, wal_status is NULL, safe_wal_size is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
 );
 is($result, "t|t|t", 'check the state of non-reserved slot is "unknown"');
 
@@ -52,9 +52,9 @@ $node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
 # Stop standby
 $node_standby->stop;
 
-# Preparation done, the slot is the state "normal" now
+# Preparation done, the slot is the state "reserved" now
 $result = $node_master->safe_psql('postgres',
-	"SELECT wal_status, min_safe_lsn is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
+	"SELECT wal_status, safe_wal_size IS NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
 );
 is($result, "reserved|t", 'check the catching-up state');
 
@@ -64,7 +64,7 @@ $node_master->safe_psql('postgres', "CHECKPOINT;");
 
 # The slot is always "safe" when fitting max_wal_size
 $result = $node_master->safe_psql('postgres',
-	"SELECT wal_status, min_safe_lsn is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
+	"SELECT wal_status, safe_wal_size IS NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
 );
 is($result, "reserved|t",
 	'check that it is safe if WAL fits in max_wal_size');
@@ -74,7 +74,7 @@ $node_master->safe_psql('postgres', "CHECKPOINT;");
 
 # The slot is always "safe" when max_slot_wal_keep_size is not set
 $result = $node_master->safe_psql('postgres',
-	"SELECT wal_status, min_safe_lsn is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
+	"SELECT wal_status, safe_wal_size IS NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
 );
 is($result, "reserved|t", 'check that slot is working');
 
@@ -94,9 +94,7 @@ max_slot_wal_keep_size = ${max_slot_wal_keep_size_mb}MB
 ));
 $node_master->reload;
 
-# The slot is in safe state. The distance from the min_safe_lsn should
-# be as almost (max_slot_wal_keep_size - 1) times large as the segment
-# size
+# The slot is in safe state.
 
 $result = $node_master->safe_psql('postgres',
 	"SELECT wal_status FROM pg_replication_slots WHERE slot_name = 'rep1'");
@@ -110,7 +108,7 @@ $node_master->safe_psql('postgres', "CHECKPOINT;");
 $result = $node_master->safe_psql('postgres',
 	"SELECT wal_status FROM pg_replication_slots WHERE slot_name = 'rep1'");
 is($result, "reserved",
-	'check that min_safe_lsn gets close to the current LSN');
+	'check that safe_wal_size gets close to the current LSN');
 
 # The standby can reconnect to master
 $node_standby->start;
@@ -152,9 +150,9 @@ $node_master->safe_psql('postgres', "CHECKPOINT;");
 # Advance WAL again without checkpoint; remain goes to 0.
 advance_wal($node_master, 1);
 
-# Slot gets into 'unreserved' state
+# Slot gets into 'unreserved' state and safe_wal_size is negative
 $result = $node_master->safe_psql('postgres',
-	"SELECT wal_status, min_safe_lsn is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'"
+	"SELECT wal_status, safe_wal_size <= 0 FROM pg_replication_slots WHERE slot_name = 'rep1'"
 );
 is($result, "unreserved|t",
 	'check that the slot state changes to "unreserved"');
@@ -186,7 +184,7 @@ ok( find_in_log(
 
 # This slot should be broken
 $result = $node_master->safe_psql('postgres',
-	"SELECT slot_name, active, restart_lsn IS NULL, wal_status, min_safe_lsn FROM pg_replication_slots WHERE slot_name = 'rep1'"
+	"SELECT slot_name, active, restart_lsn IS NULL, wal_status, safe_wal_size FROM pg_replication_slots WHERE slot_name = 'rep1'"
 );
 is($result, "rep1|f|t|lost|",
 	'check that the slot became inactive and the state "lost" persists');
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index b813e322153..93bb2159ca8 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1464,8 +1464,8 @@ pg_replication_slots| SELECT l.slot_name,
     l.restart_lsn,
     l.confirmed_flush_lsn,
     l.wal_status,
-    l.min_safe_lsn
-   FROM (pg_get_replication_slots() l(slot_name, plugin, slot_type, datoid, temporary, active, active_pid, xmin, catalog_xmin, restart_lsn, confirmed_flush_lsn, wal_status, min_safe_lsn)
+    l.safe_wal_size
+   FROM (pg_get_replication_slots() l(slot_name, plugin, slot_type, datoid, temporary, active, active_pid, xmin, catalog_xmin, restart_lsn, confirmed_flush_lsn, wal_status, safe_wal_size)
      LEFT JOIN pg_database d ON ((l.datoid = d.oid)));
 pg_roles| SELECT pg_authid.rolname,
     pg_authid.rolsuper,