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

1 files changed, 59 insertions, 17 deletions

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);