Make it possible to detemine WAL format at runtime

.dockerignore

@@ -0,0 +1,5 @@
+.git
+.vscode
+.circleci
+tmp_install
+compute_build

configure

@@ -717,6 +717,7 @@ with_libxml
 with_uuid
 with_readline
 with_systemd
+with_libseccomp
 with_selinux
 with_ldap
 with_krb_srvnam
@@ -864,6 +865,7 @@ with_bsd_auth
 with_ldap
 with_bonjour
 with_selinux
+with_libseccomp
 with_systemd
 with_readline
 with_libedit_preferred
@@ -1573,6 +1575,7 @@ Optional Packages:
   --with-ldap             build with LDAP support
   --with-bonjour          build with Bonjour support
   --with-selinux          build with SELinux support
+  --with-libseccomp       build with libseccomp support
   --with-systemd          build with systemd support
   --without-readline      do not use GNU Readline nor BSD Libedit for editing
   --with-libedit-preferred
@@ -8631,6 +8634,39 @@ fi
 { $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_selinux" >&5
 $as_echo "$with_selinux" >&6; }
 
+#
+# libseccomp
+#
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to build with libseccomp support" >&5
+$as_echo_n "checking whether to build with libseccomp support... " >&6; }
+
+
+
+# Check whether --with-libseccomp was given.
+if test "${with_libseccomp+set}" = set; then :
+  withval=$with_libseccomp;
+  case $withval in
+    yes)
+      :
+      ;;
+    no)
+      :
+      ;;
+    *)
+      as_fn_error $? "no argument expected for --with-libseccomp option" "$LINENO" 5
+      ;;
+  esac
+
+else
+  with_libseccomp=no
+
+fi
+
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_libseccomp" >&5
+$as_echo "$with_libseccomp" >&6; }
+
 #
 # Systemd
 #
@@ -14587,6 +14623,56 @@ else
 fi
 
 
+fi
+
+if test "$with_libseccomp" = yes ; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for seccomp_init in -lseccomp" >&5
+$as_echo_n "checking for seccomp_init in -lseccomp... " >&6; }
+if ${ac_cv_lib_seccomp_seccomp_init+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  ac_check_lib_save_LIBS=$LIBS
+LIBS="-lseccomp  $LIBS"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+/* Override any GCC internal prototype to avoid an error.
+   Use char because int might match the return type of a GCC
+   builtin and then its argument prototype would still apply.  */
+#ifdef __cplusplus
+extern "C"
+#endif
+char seccomp_init ();
+int
+main ()
+{
+return seccomp_init ();
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  ac_cv_lib_seccomp_seccomp_init=yes
+else
+  ac_cv_lib_seccomp_seccomp_init=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+LIBS=$ac_check_lib_save_LIBS
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_seccomp_seccomp_init" >&5
+$as_echo "$ac_cv_lib_seccomp_seccomp_init" >&6; }
+if test "x$ac_cv_lib_seccomp_seccomp_init" = xyes; then :
+  cat >>confdefs.h <<_ACEOF
+#define HAVE_LIBSECCOMP 1
+_ACEOF
+
+  LIBS="-lseccomp $LIBS"
+
+else
+  as_fn_error $? "library 'libseccomp' is required for Seccomp BPF support" "$LINENO" 5
+fi
+
 fi
 
 # for contrib/uuid-ossp

configure.ac

@@ -927,6 +927,14 @@ PGAC_ARG_BOOL(with, selinux, no, [build with SELinux support])
 AC_SUBST(with_selinux)
 AC_MSG_RESULT([$with_selinux])
 
+#
+# libseccomp
+#
+AC_MSG_CHECKING([whether to build with libseccomp support])
+PGAC_ARG_BOOL(with, libseccomp, no, [build with libseccomp support])
+AC_SUBST(with_libseccomp)
+AC_MSG_RESULT([$with_libseccomp])
+
 #
 # Systemd
 #
@@ -1613,6 +1621,11 @@ dnl If you want to use Apple's own Bonjour code on another platform,
 dnl just add -ldns_sd to LIBS manually.
 fi
 
+if test "$with_libseccomp" = yes ; then
+  AC_CHECK_LIB(seccomp, seccomp_init, [],
+               [AC_MSG_ERROR([library 'libseccomp' is required for Seccomp BPF support])])
+fi
+
 # for contrib/uuid-ossp
 if test "$with_uuid" = bsd ; then
   AC_CHECK_HEADERS(uuid.h,

contrib/pg_prewarm/autoprewarm.c

@@ -54,6 +54,7 @@
 #include "utils/rel.h"
 #include "utils/relfilenodemap.h"
 #include "utils/resowner.h"
+#include "utils/spccache.h"
 
 #define AUTOPREWARM_FILE "autoprewarm.blocks"
 
@@ -449,10 +450,12 @@ void
 autoprewarm_database_main(Datum main_arg)
 {
 	int			pos;
+	int			io_concurrency;
 	BlockInfoRecord *block_info;
 	Relation	rel = NULL;
 	BlockNumber nblocks = 0;
 	BlockInfoRecord *old_blk = NULL;
+	BlockInfoRecord *prefetch_blk = NULL;
 	dsm_segment *seg;
 
 	/* Establish signal handlers; once that's done, unblock signals. */
@@ -499,6 +502,7 @@ autoprewarm_database_main(Datum main_arg)
 		{
 			relation_close(rel, AccessShareLock);
 			rel = NULL;
+			io_concurrency = -1;
 			CommitTransactionCommand();
 		}
 
@@ -518,6 +522,8 @@ autoprewarm_database_main(Datum main_arg)
 
 			if (!rel)
 				CommitTransactionCommand();
+			else
+				io_concurrency = get_tablespace_maintenance_io_concurrency(rel->rd_rel->reltablespace);
 		}
 		if (!rel)
 		{
@@ -550,6 +556,35 @@ autoprewarm_database_main(Datum main_arg)
 			continue;
 		}
 
+		/* if prefetching is enabled for this relation */
+		if (io_concurrency > 0)
+		{
+			/* make prefetch_blk catch up */
+			if (blk > prefetch_blk)
+			{
+				prefetch_blk = blk;
+			}
+
+			/* now, prefetch all following blocks */
+			while (prefetch_blk <= &block_info[apw_state->prewarm_stop_idx])
+			{
+				/* unless they're of a different relfilenode */
+				if (prefetch_blk->filenode != blk->filenode ||
+					prefetch_blk->forknum != blk->forknum ||
+					prefetch_blk->blocknum >= nblocks)
+					break;
+
+				/* or unless they are more than io_concurrency blocks ahead */
+				if (blk + io_concurrency <= prefetch_blk)
+					break;
+
+				PrefetchBuffer(rel, prefetch_blk->forknum, prefetch_blk->blocknum);
+
+				/* continue with the next block */
+				prefetch_blk++;
+			}
+		}
+
 		/* Prewarm buffer. */
 		buf = ReadBufferExtended(rel, blk->forknum, blk->blocknum, RBM_NORMAL,
 								 NULL);

contrib/pg_prewarm/pg_prewarm.c

@@ -18,12 +18,14 @@
 #include "access/relation.h"
 #include "fmgr.h"
 #include "miscadmin.h"
+#include "optimizer/cost.h"
 #include "storage/bufmgr.h"
 #include "storage/smgr.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
+#include "utils/spccache.h"
 
 PG_MODULE_MAGIC;
 
@@ -183,14 +185,26 @@ pg_prewarm(PG_FUNCTION_ARGS)
 	}
 	else if (ptype == PREWARM_BUFFER)
 	{
+		BlockNumber prefetch_block = first_block;
+		Oid			nspOid;
+		int			io_concurrency;
+
+		nspOid = rel->rd_rel->reltablespace;
+		io_concurrency = get_tablespace_maintenance_io_concurrency(nspOid);
+
 		/*
 		 * In buffer mode, we actually pull the data into shared_buffers.
 		 */
 		for (block = first_block; block <= last_block; ++block)
 		{
-			Buffer		buf;
-
+			Buffer buf;
+			BlockNumber prefetch_stop = block + Min(last_block - block + 1,
+													io_concurrency);
 			CHECK_FOR_INTERRUPTS();
+			while (prefetch_block < prefetch_stop)
+			{
+				PrefetchBuffer(rel, forkNumber, prefetch_block++);
+			}
 			buf = ReadBufferExtended(rel, forkNumber, block, RBM_NORMAL, NULL);
 			ReleaseBuffer(buf);
 			++blocks_done;

contrib/pg_prewarm/pg_prewarm.control

@@ -3,3 +3,4 @@ comment = 'prewarm relation data'
 default_version = '1.2'
 module_pathname = '$libdir/pg_prewarm'
 relocatable = true
+trusted = true

src/Makefile.global.in

@@ -186,6 +186,7 @@ with_tcl	= @with_tcl@
 with_ssl	= @with_ssl@
 with_readline	= @with_readline@
 with_selinux	= @with_selinux@
+with_libseccomp = @with_libseccomp@
 with_systemd	= @with_systemd@
 with_gssapi	= @with_gssapi@
 with_krb_srvnam	= @with_krb_srvnam@

src/backend/access/brin/brin_xlog.c

@@ -69,7 +69,8 @@ brin_xlog_insert_update(XLogReaderState *record,
 	}
 
 	/* need this page's blkno to store in revmap */
-	regpgno = BufferGetBlockNumber(buffer);
+	//ZENITH XXX Don't use BufferGetBlockNumber because wal-redo doesn't pin buffer.
+	XLogRecGetBlockTag(record, 0, NULL, NULL, &regpgno);
 
 	/* insert the index item into the page */
 	if (action == BLK_NEEDS_REDO)

src/backend/access/gin/gininsert.c

@@ -335,6 +335,8 @@ ginbuild(Relation heap, Relation index, IndexInfo *indexInfo)
 		elog(ERROR, "index \"%s\" already contains data",
 			 RelationGetRelationName(index));
 
+	smgr_start_unlogged_build(index->rd_smgr);
+
 	initGinState(&buildstate.ginstate, index);
 	buildstate.indtuples = 0;
 	memset(&buildstate.buildStats, 0, sizeof(GinStatsData));
@@ -408,6 +410,8 @@ ginbuild(Relation heap, Relation index, IndexInfo *indexInfo)
 	buildstate.buildStats.nTotalPages = RelationGetNumberOfBlocks(index);
 	ginUpdateStats(index, &buildstate.buildStats, true);
 
+	smgr_finish_unlogged_build_phase_1(index->rd_smgr);
+
 	/*
 	 * We didn't write WAL records as we built the index, so if WAL-logging is
 	 * required, write all pages to the WAL now.
@@ -417,8 +421,12 @@ ginbuild(Relation heap, Relation index, IndexInfo *indexInfo)
 		log_newpage_range(index, MAIN_FORKNUM,
 						  0, RelationGetNumberOfBlocks(index),
 						  true);
+		SetLastWrittenLSNForBlockRange(XactLastRecEnd, index->rd_smgr->smgr_rnode.node, MAIN_FORKNUM, 0, RelationGetNumberOfBlocks(index));
+		SetLastWrittenLSNForRelation(XactLastRecEnd, index->rd_smgr->smgr_rnode.node, MAIN_FORKNUM);
 	}
 
+	smgr_end_unlogged_build(index->rd_smgr);
+
 	/*
 	 * Return statistics
 	 */

src/backend/access/gin/ginxlog.c

@@ -407,6 +407,7 @@ ginRedoSplit(XLogReaderState *record)
 				rootbuf;
 	bool		isLeaf = (data->flags & GIN_INSERT_ISLEAF) != 0;
 	bool		isRoot = (data->flags & GIN_SPLIT_ROOT) != 0;
+	XLogRedoAction action;
 
 	/*
 	 * First clear incomplete-split flag on child page if this finishes a
@@ -415,21 +416,27 @@ ginRedoSplit(XLogReaderState *record)
 	if (!isLeaf)
 		ginRedoClearIncompleteSplit(record, 3);
 
-	if (XLogReadBufferForRedo(record, 0, &lbuffer) != BLK_RESTORED)
+	action = XLogReadBufferForRedo(record, 0, &lbuffer);
+	if (action != BLK_RESTORED && action != BLK_DONE)
 		elog(ERROR, "GIN split record did not contain a full-page image of left page");
 
-	if (XLogReadBufferForRedo(record, 1, &rbuffer) != BLK_RESTORED)
+	action = XLogReadBufferForRedo(record, 1, &rbuffer);
+	if (action != BLK_RESTORED && action != BLK_DONE)
 		elog(ERROR, "GIN split record did not contain a full-page image of right page");
 
 	if (isRoot)
 	{
-		if (XLogReadBufferForRedo(record, 2, &rootbuf) != BLK_RESTORED)
+		action = XLogReadBufferForRedo(record, 2, &rootbuf);
+		if (action != BLK_RESTORED && action != BLK_DONE)
 			elog(ERROR, "GIN split record did not contain a full-page image of root page");
-		UnlockReleaseBuffer(rootbuf);
+		if (rootbuf != InvalidBuffer)
+			UnlockReleaseBuffer(rootbuf);
 	}
 
-	UnlockReleaseBuffer(rbuffer);
-	UnlockReleaseBuffer(lbuffer);
+	if (rbuffer != InvalidBuffer)
+		UnlockReleaseBuffer(rbuffer);
+	if (lbuffer != InvalidBuffer)
+		UnlockReleaseBuffer(lbuffer);
 }
 
 /*