Allow on-line enabling and disabling of data checksums

This makes it possible to turn checksums on in a live cluster, without
the previous need for dump/reload or logical replication (and to turn it
off).

Enabling checkusm starts a background process in the form of a
launcher/worker combination that goes through the entire database and
recalculates checksums on each and every page. Only when all pages have
been checksummed are they fully enabled in the cluster. Any failure of
the process will revert to checksums off and the process has to be
started.

This adds a new WAL record that indicates the state of checksums, so
the process works across replicated clusters.

Authors: Magnus Hagander and Daniel Gustafsson
Review: Tomas Vondra, Michael Banck, Heikki Linnakangas, Andrey Borodin

1 files changed, 59 insertions, 0 deletions

diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 316edbe3c58..b76b2688911 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -24,6 +24,7 @@
 #include "catalog/pg_type.h"
 #include "funcapi.h"
 #include "miscadmin.h"
+#include "postmaster/checksumhelper.h"
 #include "replication/walreceiver.h"
 #include "storage/smgr.h"
 #include "utils/builtins.h"
@@ -698,3 +699,61 @@ pg_backup_start_time(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(xtime);
 }
+
+/*
+ * Disables checksums for the cluster, unless already disabled.
+ *
+ * Has immediate effect - the checksums are set to off right away.
+ */
+Datum
+disable_data_checksums(PG_FUNCTION_ARGS)
+{
+	/*
+	 * If we don't need to write new checksums, then clearly they are already
+	 * disabled.
+	 */
+	if (!DataChecksumsNeedWrite())
+		ereport(ERROR,
+				(errmsg("data checksums already disabled")));
+
+	ShutdownChecksumHelperIfRunning();
+
+	SetDataChecksumsOff();
+
+	PG_RETURN_VOID();
+}
+
+/*
+ * Enables checksums for the cluster, unless already enabled.
+ *
+ * Supports vacuum-like cost-based throttling, to limit system load.
+ * Starts a background worker that updates checksums on existing data.
+ */
+Datum
+enable_data_checksums(PG_FUNCTION_ARGS)
+{
+	int			cost_delay = PG_GETARG_INT32(0);
+	int			cost_limit = PG_GETARG_INT32(1);
+
+	if (cost_delay < 0)
+		ereport(ERROR,
+				(errmsg("cost delay cannot be less than zero")));
+	if (cost_limit <= 0)
+		ereport(ERROR,
+				(errmsg("cost limit must be a positive value")));
+
+	/*
+	 * Allow state change from "off" or from "inprogress", since this is how
+	 * we restart the worker if necessary.
+	 */
+	if (DataChecksumsNeedVerify())
+		ereport(ERROR,
+				(errmsg("data checksums already enabled")));
+
+	SetDataChecksumsInProgress();
+	if (!StartChecksumHelperLauncher(cost_delay, cost_limit))
+		ereport(ERROR,
+				(errmsg("failed to start checksum helper process")));
+
+	PG_RETURN_VOID();
+}