Use "template" data directory in tests

When running all (or just many) of our tests, a significant portion of both
CPU time and IO is spent running initdb. Most of those initdb runs don't
specify any options influencing properties of the created data directory.

Avoid most of that overhead by creating a "template" data directory, alongside
the temporary installation. Instead of running initdb, pg_regress and tap
tests can copy that data directory. When a tap test specifies options to
initdb, the template data directory is not used. That could be relaxed for
some options, but it's not clear it's worth the effort.

There unfortunately is some duplication between pg_regress.c and Cluster.pm,
but there are no easy ways of sharing that code without introducing additional
complexity.

Reviewed-by: Daniel Gustafsson <daniel@yesql.se>
Discussion: https://postgr.es/m/20220120021859.3zpsfqn4z7ob7afz@alap3.anarazel.de

3 files changed, 124 insertions, 36 deletions

diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index df9f721a41a..0b4ca0eb6ae 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -397,6 +397,25 @@ check: temp-install
 
 .PHONY: temp-install
 
+
+# prepend to path if already set, else just set it
+define add_to_path
+$(1)="$(if $($(1)),$(2):$$$(1),$(2))"
+endef
+
+# platform-specific environment variable to set shared library path
+# individual ports can override this later, this is the default name
+ld_library_path_var = LD_LIBRARY_PATH
+
+# with_temp_install_extra is for individual ports to define if they
+# need something more here. If not defined then the expansion does
+# nothing.
+with_temp_install = \
+	PATH="$(abs_top_builddir)/tmp_install$(bindir):$(CURDIR):$$PATH" \
+	$(call add_to_path,$(strip $(ld_library_path_var)),$(abs_top_builddir)/tmp_install$(libdir)) \
+	INITDB_TEMPLATE='$(abs_top_builddir)'/tmp_install/initdb-template \
+	$(with_temp_install_extra)
+
 temp-install: | submake-generated-headers
 ifndef NO_TEMP_INSTALL
 ifneq ($(abs_top_builddir),)
@@ -405,6 +424,8 @@ ifeq ($(MAKELEVEL),0)
 	$(MKDIR_P) '$(abs_top_builddir)'/tmp_install/log
 	$(MAKE) -C '$(top_builddir)' DESTDIR='$(abs_top_builddir)'/tmp_install install >'$(abs_top_builddir)'/tmp_install/log/install.log 2>&1
 	$(MAKE) -j1 $(if $(CHECKPREP_TOP),-C $(CHECKPREP_TOP),) checkprep >>'$(abs_top_builddir)'/tmp_install/log/install.log 2>&1
+
+	$(with_temp_install) initdb -A trust -N --no-instructions '$(abs_top_builddir)'/tmp_install/initdb-template >>'$(abs_top_builddir)'/tmp_install/log/initdb-template.log 2>&1
 endif
 endif
 endif
@@ -422,23 +443,6 @@ PG_PROVE_FLAGS = -I $(top_srcdir)/src/test/perl/ -I $(srcdir)
 # User-supplied prove flags such as --verbose can be provided in PROVE_FLAGS.
 PROVE_FLAGS =
 
-# prepend to path if already set, else just set it
-define add_to_path
-$(1)="$(if $($(1)),$(2):$$$(1),$(2))"
-endef
-
-# platform-specific environment variable to set shared library path
-# individual ports can override this later, this is the default name
-ld_library_path_var = LD_LIBRARY_PATH
-
-# with_temp_install_extra is for individual ports to define if they
-# need something more here. If not defined then the expansion does
-# nothing.
-with_temp_install = \
-	PATH="$(abs_top_builddir)/tmp_install$(bindir):$(CURDIR):$$PATH" \
-	$(call add_to_path,$(strip $(ld_library_path_var)),$(abs_top_builddir)/tmp_install$(libdir)) \
-	$(with_temp_install_extra)
-
 ifeq ($(enable_tap_tests),yes)
 
 ifndef PGXS
diff --git a/src/test/perl/PostgreSQL/Test/Cluster.pm b/src/test/perl/PostgreSQL/Test/Cluster.pm
index 41409ba1bed..426f94ff09c 100644
--- a/src/test/perl/PostgreSQL/Test/Cluster.pm
+++ b/src/test/perl/PostgreSQL/Test/Cluster.pm
@@ -522,8 +522,50 @@ sub init
 	mkdir $self->backup_dir;
 	mkdir $self->archive_dir;
 
-	PostgreSQL::Test::Utils::system_or_bail('initdb', '-D', $pgdata, '-A',
-		'trust', '-N', @{ $params{extra} });
+	# If available and if there aren't any parameters, use a previously
+	# initdb'd cluster as a template by copying it. For a lot of tests, that's
+	# substantially cheaper. Do so only if there aren't parameters, it doesn't
+	# seem worth figuring out whether they affect compatibility.
+	#
+	# There's very similar code in pg_regress.c, but we can't easily
+	# deduplicate it until we require perl at build time.
+	if (defined $params{extra} or !defined $ENV{INITDB_TEMPLATE})
+	{
+		note("initializing database system by running initdb");
+		PostgreSQL::Test::Utils::system_or_bail('initdb', '-D', $pgdata, '-A',
+			'trust', '-N', @{ $params{extra} });
+	}
+	else
+	{
+		my @copycmd;
+		my $expected_exitcode;
+
+		note("initializing database system by copying initdb template");
+
+		if ($PostgreSQL::Test::Utils::windows_os)
+		{
+			@copycmd = qw(robocopy /E /NJS /NJH /NFL /NDL /NP);
+			$expected_exitcode = 1;    # 1 denotes files were copied
+		}
+		else
+		{
+			@copycmd = qw(cp -a);
+			$expected_exitcode = 0;
+		}
+
+		@copycmd = (@copycmd, $ENV{INITDB_TEMPLATE}, $pgdata);
+
+		my $ret = PostgreSQL::Test::Utils::system_log(@copycmd);
+
+		# See http://perldoc.perl.org/perlvar.html#%24CHILD_ERROR
+		if ($ret & 127 or $ret >> 8 != $expected_exitcode)
+		{
+			BAIL_OUT(
+				sprintf("failed to execute command \"%s\": $ret",
+					join(" ", @copycmd)));
+		}
+	}
+
 	PostgreSQL::Test::Utils::system_or_bail($ENV{PG_REGRESS},
 		'--config-auth', $pgdata, @{ $params{auth_extra} });
 
diff --git a/src/test/regress/pg_regress.c b/src/test/regress/pg_regress.c
index b68632320a7..06674141a31 100644
--- a/src/test/regress/pg_regress.c
+++ b/src/test/regress/pg_regress.c
@@ -2295,6 +2295,7 @@ regression_main(int argc, char *argv[],
 		FILE	   *pg_conf;
 		const char *env_wait;
 		int			wait_seconds;
+		const char *initdb_template_dir;
 
 		/*
 		 * Prepare the temp instance
@@ -2316,25 +2317,66 @@ regression_main(int argc, char *argv[],
 		if (!directory_exists(buf))
 			make_directory(buf);
 
-		/* initdb */
 		initStringInfo(&cmd);
-		appendStringInfo(&cmd,
-						 "\"%s%sinitdb\" -D \"%s/data\" --no-clean --no-sync",
-						 bindir ? bindir : "",
-						 bindir ? "/" : "",
-						 temp_instance);
-		if (debug)
-			appendStringInfo(&cmd, " --debug");
-		if (nolocale)
-			appendStringInfo(&cmd, " --no-locale");
-		appendStringInfo(&cmd, " > \"%s/log/initdb.log\" 2>&1", outputdir);
-		fflush(NULL);
-		if (system(cmd.data))
+
+		/*
+		 * Create data directory.
+		 *
+		 * If available, use a previously initdb'd cluster as a template by
+		 * copying it. For a lot of tests, that's substantially cheaper.
+		 *
+		 * There's very similar code in Cluster.pm, but we can't easily de
+		 * duplicate it until we require perl at build time.
+		 */
+		initdb_template_dir = getenv("INITDB_TEMPLATE");
+		if (initdb_template_dir == NULL || nolocale || debug)
+		{
+			note("initializing database system by running initdb");
+
+			appendStringInfo(&cmd,
+							 "\"%s%sinitdb\" -D \"%s/data\" --no-clean --no-sync",
+							 bindir ? bindir : "",
+							 bindir ? "/" : "",
+							 temp_instance);
+			if (debug)
+				appendStringInfo(&cmd, " --debug");
+			if (nolocale)
+				appendStringInfo(&cmd, " --no-locale");
+			appendStringInfo(&cmd, " > \"%s/log/initdb.log\" 2>&1", outputdir);
+			fflush(NULL);
+			if (system(cmd.data))
+			{
+				bail("initdb failed\n"
+					 "# Examine \"%s/log/initdb.log\" for the reason.\n"
+					 "# Command was: %s",
+					 outputdir, cmd.data);
+			}
+		}
+		else
 		{
-			bail("initdb failed\n"
-				 "# Examine \"%s/log/initdb.log\" for the reason.\n"
-				 "# Command was: %s",
-				 outputdir, cmd.data);
+#ifndef WIN32
+			const char *copycmd = "cp -a \"%s\" \"%s/data\"";
+			int			expected_exitcode = 0;
+#else
+			const char *copycmd = "robocopy /E /NJS /NJH /NFL /NDL /NP \"%s\" \"%s/data\"";
+			int			expected_exitcode = 1;	/* 1 denotes files were copied */
+#endif
+
+			note("initializing database system by copying initdb template");
+
+			appendStringInfo(&cmd,
+							 copycmd,
+							 initdb_template_dir,
+							 temp_instance);
+			appendStringInfo(&cmd, " > \"%s/log/initdb.log\" 2>&1", outputdir);
+			fflush(NULL);
+			if (system(cmd.data) != expected_exitcode)
+			{
+				bail("copying of initdb template failed\n"
+					 "# Examine \"%s/log/initdb.log\" for the reason.\n"
+					 "# Command was: %s",
+					 outputdir, cmd.data);
+			}
 		}
 
 		pfree(cmd.data);