Skip WAL for new relfilenodes, under wal_level=minimal.

Until now, only selected bulk operations (e.g. COPY) did this.  If a
given relfilenode received both a WAL-skipping COPY and a WAL-logged
operation (e.g. INSERT), recovery could lose tuples from the COPY.  See
src/backend/access/transam/README section "Skipping WAL for New
RelFileNode" for the new coding rules.  Maintainers of table access
methods should examine that section.

To maintain data durability, just before commit, we choose between an
fsync of the relfilenode and copying its contents to WAL.  A new GUC,
wal_skip_threshold, guides that choice.  If this change slows a workload
that creates small, permanent relfilenodes under wal_level=minimal, try
adjusting wal_skip_threshold.  Users setting a timeout on COMMIT may
need to adjust that timeout, and log_min_duration_statement analysis
will reflect time consumption moving to COMMIT from commands like COPY.

Internally, this requires a reliable determination of whether
RollbackAndReleaseCurrentSubTransaction() would unlink a relation's
current relfilenode.  Introduce rd_firstRelfilenodeSubid.  Amend the
specification of rd_createSubid such that the field is zero when a new
rel has an old rd_node.  Make relcache.c retain entries for certain
dropped relations until end of transaction.

Bump XLOG_PAGE_MAGIC, since this introduces XLOG_GIST_ASSIGN_LSN.
Future servers accept older WAL, so this bump is discretionary.

Kyotaro Horiguchi, reviewed (in earlier, similar versions) by Robert
Haas.  Heikki Linnakangas and Michael Paquier implemented earlier
designs that materially clarified the problem.  Reviewed, in earlier
designs, by Andrew Dunstan, Andres Freund, Alvaro Herrera, Tom Lane,
Fujii Masao, and Simon Riggs.  Reported by Martijn van Oosterhout.

Discussion: https://postgr.es/m/20150702220524.GA9392@svana.org

1 files changed, 22 insertions, 4 deletions

diff --git a/src/backend/access/transam/parallel.c b/src/backend/access/transam/parallel.c
index df06e7d1743..29057f389e2 100644
--- a/src/backend/access/transam/parallel.c
+++ b/src/backend/access/transam/parallel.c
@@ -23,6 +23,7 @@
 #include "catalog/index.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_enum.h"
+#include "catalog/storage.h"
 #include "commands/async.h"
 #include "executor/execParallel.h"
 #include "libpq/libpq.h"
@@ -71,9 +72,10 @@
 #define PARALLEL_KEY_TRANSACTION_STATE		UINT64CONST(0xFFFFFFFFFFFF0008)
 #define PARALLEL_KEY_ENTRYPOINT				UINT64CONST(0xFFFFFFFFFFFF0009)
 #define PARALLEL_KEY_SESSION_DSM			UINT64CONST(0xFFFFFFFFFFFF000A)
-#define PARALLEL_KEY_REINDEX_STATE			UINT64CONST(0xFFFFFFFFFFFF000B)
-#define PARALLEL_KEY_RELMAPPER_STATE		UINT64CONST(0xFFFFFFFFFFFF000C)
-#define PARALLEL_KEY_ENUMBLACKLIST			UINT64CONST(0xFFFFFFFFFFFF000D)
+#define PARALLEL_KEY_PENDING_SYNCS			UINT64CONST(0xFFFFFFFFFFFF000B)
+#define PARALLEL_KEY_REINDEX_STATE			UINT64CONST(0xFFFFFFFFFFFF000C)
+#define PARALLEL_KEY_RELMAPPER_STATE		UINT64CONST(0xFFFFFFFFFFFF000D)
+#define PARALLEL_KEY_ENUMBLACKLIST			UINT64CONST(0xFFFFFFFFFFFF000E)
 
 /* Fixed-size parallel state. */
 typedef struct FixedParallelState
@@ -206,6 +208,7 @@ InitializeParallelDSM(ParallelContext *pcxt)
 	Size		tsnaplen = 0;
 	Size		asnaplen = 0;
 	Size		tstatelen = 0;
+	Size		pendingsyncslen = 0;
 	Size		reindexlen = 0;
 	Size		relmapperlen = 0;
 	Size		enumblacklistlen = 0;
@@ -258,6 +261,8 @@ InitializeParallelDSM(ParallelContext *pcxt)
 		tstatelen = EstimateTransactionStateSpace();
 		shm_toc_estimate_chunk(&pcxt->estimator, tstatelen);
 		shm_toc_estimate_chunk(&pcxt->estimator, sizeof(dsm_handle));
+		pendingsyncslen = EstimatePendingSyncsSpace();
+		shm_toc_estimate_chunk(&pcxt->estimator, pendingsyncslen);
 		reindexlen = EstimateReindexStateSpace();
 		shm_toc_estimate_chunk(&pcxt->estimator, reindexlen);
 		relmapperlen = EstimateRelationMapSpace();
@@ -265,7 +270,7 @@ InitializeParallelDSM(ParallelContext *pcxt)
 		enumblacklistlen = EstimateEnumBlacklistSpace();
 		shm_toc_estimate_chunk(&pcxt->estimator, enumblacklistlen);
 		/* If you add more chunks here, you probably need to add keys. */
-		shm_toc_estimate_keys(&pcxt->estimator, 10);
+		shm_toc_estimate_keys(&pcxt->estimator, 11);
 
 		/* Estimate space need for error queues. */
 		StaticAssertStmt(BUFFERALIGN(PARALLEL_ERROR_QUEUE_SIZE) ==
@@ -337,6 +342,7 @@ InitializeParallelDSM(ParallelContext *pcxt)
 		char	   *tsnapspace;
 		char	   *asnapspace;
 		char	   *tstatespace;
+		char	   *pendingsyncsspace;
 		char	   *reindexspace;
 		char	   *relmapperspace;
 		char	   *error_queue_space;
@@ -381,6 +387,12 @@ InitializeParallelDSM(ParallelContext *pcxt)
 		SerializeTransactionState(tstatelen, tstatespace);
 		shm_toc_insert(pcxt->toc, PARALLEL_KEY_TRANSACTION_STATE, tstatespace);
 
+		/* Serialize pending syncs. */
+		pendingsyncsspace = shm_toc_allocate(pcxt->toc, pendingsyncslen);
+		SerializePendingSyncs(pendingsyncslen, pendingsyncsspace);
+		shm_toc_insert(pcxt->toc, PARALLEL_KEY_PENDING_SYNCS,
+					   pendingsyncsspace);
+
 		/* Serialize reindex state. */
 		reindexspace = shm_toc_allocate(pcxt->toc, reindexlen);
 		SerializeReindexState(reindexlen, reindexspace);
@@ -1242,6 +1254,7 @@ ParallelWorkerMain(Datum main_arg)
 	char	   *tsnapspace;
 	char	   *asnapspace;
 	char	   *tstatespace;
+	char	   *pendingsyncsspace;
 	char	   *reindexspace;
 	char	   *relmapperspace;
 	char	   *enumblacklistspace;
@@ -1423,6 +1436,11 @@ ParallelWorkerMain(Datum main_arg)
 	SetTempNamespaceState(fps->temp_namespace_id,
 						  fps->temp_toast_namespace_id);
 
+	/* Restore pending syncs. */
+	pendingsyncsspace = shm_toc_lookup(toc, PARALLEL_KEY_PENDING_SYNCS,
+									   false);
+	RestorePendingSyncs(pendingsyncsspace);
+
 	/* Restore reindex state. */
 	reindexspace = shm_toc_lookup(toc, PARALLEL_KEY_REINDEX_STATE, false);
 	RestoreReindexState(reindexspace);