Add the "snapshot too old" feature

This feature is controlled by a new old_snapshot_threshold GUC.  A
value of -1 disables the feature, and that is the default.  The
value of 0 is just intended for testing.  Above that it is the
number of minutes a snapshot can reach before pruning and vacuum
are allowed to remove dead tuples which the snapshot would
otherwise protect.  The xmin associated with a transaction ID does
still protect dead tuples.  A connection which is using an "old"
snapshot does not get an error unless it accesses a page modified
recently enough that it might not be able to produce accurate
results.

This is similar to the Oracle feature, and we use the same SQLSTATE
and error message for compatibility.

4 files changed, 53 insertions, 0 deletions

diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index 9874c3eaa04..c664984d0a1 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -4114,3 +4114,43 @@ IssuePendingWritebacks(WritebackContext *context)
 
 	context->nr_pending = 0;
 }
+
+
+/*
+ * Check whether the given snapshot is too old to have safely read the given
+ * page from the given table.  If so, throw a "snapshot too old" error.
+ *
+ * This test generally needs to be performed after every BufferGetPage() call
+ * that is executed as part of a scan.  It is not needed for calls made for
+ * modifying the page (for example, to position to the right place to insert a
+ * new index tuple or for vacuuming).  To minimize errors of omission, the
+ * BufferGetPage() macro accepts parameters to specify whether the test should
+ * be run, and supply the necessary snapshot and relation parameters.  See the
+ * declaration of BufferGetPage() for more details.
+ *
+ * Note that a NULL snapshot argument is allowed and causes a fast return
+ * without error; this is to support call sites which can be called from
+ * either scans or index modification areas.
+ *
+ * For best performance, keep the tests that are fastest and/or most likely to
+ * exclude a page from old snapshot testing near the front.
+ */
+extern Page
+TestForOldSnapshot(Snapshot snapshot, Relation relation, Page page)
+{
+	Assert(relation != NULL);
+
+	if (old_snapshot_threshold >= 0
+	 && (snapshot) != NULL
+	 && (snapshot)->satisfies == HeapTupleSatisfiesMVCC
+	 && !XLogRecPtrIsInvalid((snapshot)->lsn)
+	 && PageGetLSN(page) > (snapshot)->lsn
+	 && !IsCatalogRelation(relation)
+	 && !RelationIsAccessibleInLogicalDecoding(relation)
+	 && (snapshot)->whenTaken < GetOldSnapshotThresholdTimestamp())
+		ereport(ERROR,
+				(errcode(ERRCODE_SNAPSHOT_TOO_OLD),
+				 errmsg("snapshot too old")));
+
+	return page;
+}
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 36a04fc5708..c04b17fa8ea 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -43,6 +43,7 @@
 #include "storage/procsignal.h"
 #include "storage/sinvaladt.h"
 #include "storage/spin.h"
+#include "utils/snapmgr.h"
 
 
 shmem_startup_hook_type shmem_startup_hook = NULL;
@@ -136,6 +137,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
 		size = add_size(size, SyncScanShmemSize());
 		size = add_size(size, AsyncShmemSize());
@@ -247,6 +249,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
 	/*
 	 * Set up other modules that need some shared memory space
 	 */
+	SnapMgrInit();
 	BTreeShmemInit();
 	SyncScanShmemInit();
 	AsyncShmemInit();
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index 01cfa9d5f90..5bc9fd6595e 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -1759,6 +1759,15 @@ GetSnapshotData(Snapshot snapshot)
 	snapshot->regd_count = 0;
 	snapshot->copied = false;
 
+	/*
+	 * Capture the current time and WAL stream location in case this snapshot
+	 * becomes old enough to need to fall back on the special "old snapshot"
+	 * logic.
+	 */
+	snapshot->lsn = GetXLogInsertRecPtr();
+	snapshot->whenTaken = GetSnapshotCurrentTimestamp();
+	MaintainOldSnapshotTimeMapping(snapshot->whenTaken, xmin);
+
 	return snapshot;
 }
 
diff --git a/src/backend/storage/lmgr/lwlocknames.txt b/src/backend/storage/lmgr/lwlocknames.txt
index c557cb68d0b..f8996cd21a5 100644
--- a/src/backend/storage/lmgr/lwlocknames.txt
+++ b/src/backend/storage/lmgr/lwlocknames.txt
@@ -46,3 +46,4 @@ CommitTsControlLock					38
 CommitTsLock						39
 ReplicationOriginLock				40
 MultiXactTruncationLock				41
+OldSnapshotTimeMapLock				42