During online checkpoints, insert XLOG_CHECKPOINT_REDO at redo point.

This allows tools that read the WAL sequentially to identify (possible)
redo points when they're reached, rather than only being able to
detect them in retrospect when XLOG_CHECKPOINT_ONLINE is found, possibly
much later in the WAL stream. There are other possible applications as
well; see the discussion links below.

Any redo location that precedes the checkpoint location should now point
to an XLOG_CHECKPOINT_REDO record, so add a cross-check to verify this.

While adjusting the code in CreateCheckPoint() for this patch, I made it
call WALInsertLockAcquireExclusive a bit later than before, since there
appears to be no need for it to be held while checking whether the system
is idle, whether this is an end-of-recovery checkpoint, or what the current
timeline is.

Bump XLOG_PAGE_MAGIC.

Patch by me, based in part on earlier work from Dilip Kumar. Review by
Dilip Kumar, Amit Kapila, Andres Freund, and Michael Paquier.

Discussion: http://postgr.es/m/CA+TgmoYy-Vc6G9QKcAKNksCa29cv__czr+N9X_QCxEfQVpp_8w@mail.gmail.com
Discussion: http://postgr.es/m/20230614194717.jyuw3okxup4cvtbt%40awork3.anarazel.de
Discussion: http://postgr.es/m/CA+hUKG+b2ego8=YNW2Ohe9QmSiReh1-ogrv8V_WZpJTqP3O+2w@mail.gmail.com

2 files changed, 21 insertions, 2 deletions

diff --git a/contrib/pg_walinspect/expected/pg_walinspect.out b/contrib/pg_walinspect/expected/pg_walinspect.out
index a8f4c91060e..c010eed8c5d 100644
--- a/contrib/pg_walinspect/expected/pg_walinspect.out
+++ b/contrib/pg_walinspect/expected/pg_walinspect.out
@@ -127,9 +127,20 @@ SELECT COUNT(*) >= 1 AS ok FROM pg_get_wal_block_info(:'wal_lsn3', :'wal_lsn4')
  t
 (1 row)
 
--- Force full-page image on the next update.
+-- Force a checkpoint so that the next update will log a full-page image.
 SELECT pg_current_wal_lsn() AS wal_lsn5 \gset
 CHECKPOINT;
+-- Verify that an XLOG_CHECKPOINT_REDO record begins at precisely the redo LSN
+-- of the checkpoint we just performed.
+SELECT redo_lsn FROM pg_control_checkpoint() \gset
+SELECT start_lsn = :'redo_lsn'::pg_lsn AS same_lsn, resource_manager,
+    record_type FROM pg_get_wal_record_info(:'redo_lsn');
+ same_lsn | resource_manager |   record_type   
+----------+------------------+-----------------
+ t        | XLOG             | CHECKPOINT_REDO
+(1 row)
+
+-- This update should produce a full-page image because of the checkpoint.
 UPDATE sample_tbl SET col1 = col1 + 1 WHERE col1 = 2;
 SELECT pg_current_wal_lsn() AS wal_lsn6 \gset
 -- Check if we get FPI from WAL record.
diff --git a/contrib/pg_walinspect/sql/pg_walinspect.sql b/contrib/pg_walinspect/sql/pg_walinspect.sql
index f987ca31c45..1e64a22d29a 100644
--- a/contrib/pg_walinspect/sql/pg_walinspect.sql
+++ b/contrib/pg_walinspect/sql/pg_walinspect.sql
@@ -80,9 +80,17 @@ SELECT pg_current_wal_lsn() AS wal_lsn4 \gset
 SELECT COUNT(*) >= 1 AS ok FROM pg_get_wal_block_info(:'wal_lsn3', :'wal_lsn4')
   WHERE relfilenode = :'sample_tbl_oid' AND block_data IS NOT NULL;
 
--- Force full-page image on the next update.
+-- Force a checkpoint so that the next update will log a full-page image.
 SELECT pg_current_wal_lsn() AS wal_lsn5 \gset
 CHECKPOINT;
+
+-- Verify that an XLOG_CHECKPOINT_REDO record begins at precisely the redo LSN
+-- of the checkpoint we just performed.
+SELECT redo_lsn FROM pg_control_checkpoint() \gset
+SELECT start_lsn = :'redo_lsn'::pg_lsn AS same_lsn, resource_manager,
+    record_type FROM pg_get_wal_record_info(:'redo_lsn');
+
+-- This update should produce a full-page image because of the checkpoint.
 UPDATE sample_tbl SET col1 = col1 + 1 WHERE col1 = 2;
 SELECT pg_current_wal_lsn() AS wal_lsn6 \gset
 -- Check if we get FPI from WAL record.