Redesign archive modules

A new callback named startup_cb, called shortly after a module is
loaded, is added.  This makes possible the initialization of any
additional state data required by a module.  This initial state data can
be saved in a ArchiveModuleState, that is now passed down to all the
callbacks that can be defined in a module.  With this design, it is
possible to have a per-module state, aimed at opening the door to the
support of more than one archive module.

The initialization of the callbacks is changed so as
_PG_archive_module_init() does not anymore give in input a
ArchiveModuleCallbacks that a module has to fill in with callback
definitions.  Instead, a module now needs to return a const
ArchiveModuleCallbacks.

All the structure and callback definitions of archive modules are moved
into their own header, named archive_module.h, from pgarch.h.
Command-based archiving follows the same line, with a new set of files
named shell_archive.{c,h}.

There are a few more items that are under discussion to improve the
design of archive modules, like the fact that basic_archive calls
sigsetjmp() by itself to define its own error handling flow.  These will
be adjusted later, the changes done here cover already a good portion
of what has been discussed.

Any modules created for v15 will need to be adjusted to this new
design.

Author: Nathan Bossart
Reviewed-by: Andres Freund
Discussion: https://postgr.es/m/20230130194810.6fztfgbn32e7qarj@awork3.anarazel.de

1 files changed, 140 insertions, 0 deletions

diff --git a/src/backend/archive/shell_archive.c b/src/backend/archive/shell_archive.c
new file mode 100644
index 0000000000..157ca4c751
--- /dev/null
+++ b/src/backend/archive/shell_archive.c
@@ -0,0 +1,140 @@
+/*-------------------------------------------------------------------------
+ *
+ * shell_archive.c
+ *
+ * This archiving function uses a user-specified shell command (the
+ * archive_command GUC) to copy write-ahead log files.  It is used as the
+ * default, but other modules may define their own custom archiving logic.
+ *
+ * Copyright (c) 2022-2023, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/archive/shell_archive.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include <sys/wait.h>
+
+#include "access/xlog.h"
+#include "archive/archive_module.h"
+#include "archive/shell_archive.h"
+#include "common/percentrepl.h"
+#include "pgstat.h"
+
+static bool shell_archive_configured(ArchiveModuleState *state);
+static bool shell_archive_file(ArchiveModuleState *state,
+							   const char *file,
+							   const char *path);
+static void shell_archive_shutdown(ArchiveModuleState *state);
+
+static const ArchiveModuleCallbacks shell_archive_callbacks = {
+	.startup_cb = NULL,
+	.check_configured_cb = shell_archive_configured,
+	.archive_file_cb = shell_archive_file,
+	.shutdown_cb = shell_archive_shutdown
+};
+
+const ArchiveModuleCallbacks *
+shell_archive_init(void)
+{
+	return &shell_archive_callbacks;
+}
+
+static bool
+shell_archive_configured(ArchiveModuleState *state)
+{
+	return XLogArchiveCommand[0] != '\0';
+}
+
+static bool
+shell_archive_file(ArchiveModuleState *state, const char *file,
+				   const char *path)
+{
+	char	   *xlogarchcmd;
+	char	   *nativePath = NULL;
+	int			rc;
+
+	if (path)
+	{
+		nativePath = pstrdup(path);
+		make_native_path(nativePath);
+	}
+
+	xlogarchcmd = replace_percent_placeholders(XLogArchiveCommand,
+											   "archive_command", "fp",
+											   file, nativePath);
+
+	if (nativePath)
+		pfree(nativePath);
+
+	ereport(DEBUG3,
+			(errmsg_internal("executing archive command \"%s\"",
+							 xlogarchcmd)));
+
+	fflush(NULL);
+	pgstat_report_wait_start(WAIT_EVENT_ARCHIVE_COMMAND);
+	rc = system(xlogarchcmd);
+	pgstat_report_wait_end();
+
+	if (rc != 0)
+	{
+		/*
+		 * If either the shell itself, or a called command, died on a signal,
+		 * abort the archiver.  We do this because system() ignores SIGINT and
+		 * SIGQUIT while waiting; so a signal is very likely something that
+		 * should have interrupted us too.  Also die if the shell got a hard
+		 * "command not found" type of error.  If we overreact it's no big
+		 * deal, the postmaster will just start the archiver again.
+		 */
+		int			lev = wait_result_is_any_signal(rc, true) ? FATAL : LOG;
+
+		if (WIFEXITED(rc))
+		{
+			ereport(lev,
+					(errmsg("archive command failed with exit code %d",
+							WEXITSTATUS(rc)),
+					 errdetail("The failed archive command was: %s",
+							   xlogarchcmd)));
+		}
+		else if (WIFSIGNALED(rc))
+		{
+#if defined(WIN32)
+			ereport(lev,
+					(errmsg("archive command was terminated by exception 0x%X",
+							WTERMSIG(rc)),
+					 errhint("See C include file \"ntstatus.h\" for a description of the hexadecimal value."),
+					 errdetail("The failed archive command was: %s",
+							   xlogarchcmd)));
+#else
+			ereport(lev,
+					(errmsg("archive command was terminated by signal %d: %s",
+							WTERMSIG(rc), pg_strsignal(WTERMSIG(rc))),
+					 errdetail("The failed archive command was: %s",
+							   xlogarchcmd)));
+#endif
+		}
+		else
+		{
+			ereport(lev,
+					(errmsg("archive command exited with unrecognized status %d",
+							rc),
+					 errdetail("The failed archive command was: %s",
+							   xlogarchcmd)));
+		}
+
+		return false;
+	}
+
+	pfree(xlogarchcmd);
+
+	elog(DEBUG1, "archived write-ahead log file \"%s\"", file);
+	return true;
+}
+
+static void
+shell_archive_shutdown(ArchiveModuleState *state)
+{
+	elog(DEBUG1, "archiver process shutting down");
+}