agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v3 2/5] Refactor pg_rewind for more clear decision making.
5+ messages / 2 participants
[nested] [flat]

* [PATCH v3 2/5] Refactor pg_rewind for more clear decision making.
@ 2020-08-19 12:34 Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 5+ messages in thread

From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw)

Deciding what to do with each file is now a separate step after all the
necessary information has been gathered. It is more clear that way.
Previously, the decision-making was divided between process_source_file()
and process_target_file(), and it was a bit hard to piece together what the
overall rules were.
---
 src/bin/pg_rewind/copy_fetch.c  |  14 +-
 src/bin/pg_rewind/file_ops.c    |  16 +-
 src/bin/pg_rewind/filemap.c     | 558 +++++++++++++++++---------------
 src/bin/pg_rewind/filemap.h     |  69 ++--
 src/bin/pg_rewind/libpq_fetch.c |  12 +-
 src/bin/pg_rewind/parsexlog.c   |   2 +-
 src/bin/pg_rewind/pg_rewind.c   |   8 +-
 7 files changed, 373 insertions(+), 306 deletions(-)

diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c
index 1edab5f186..18fad32600 100644
--- a/src/bin/pg_rewind/copy_fetch.c
+++ b/src/bin/pg_rewind/copy_fetch.c
@@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map)
 	for (i = 0; i < map->narray; i++)
 	{
 		entry = map->array[i];
-		execute_pagemap(&entry->pagemap, entry->path);
+		execute_pagemap(&entry->target_modified_pages, entry->path);
 
 		switch (entry->action)
 		{
@@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map)
 				break;
 
 			case FILE_ACTION_COPY:
-				rewind_copy_file_range(entry->path, 0, entry->newsize, true);
+				rewind_copy_file_range(entry->path, 0, entry->source_size, true);
 				break;
 
 			case FILE_ACTION_TRUNCATE:
-				truncate_target_file(entry->path, entry->newsize);
+				truncate_target_file(entry->path, entry->source_size);
 				break;
 
 			case FILE_ACTION_COPY_TAIL:
-				rewind_copy_file_range(entry->path, entry->oldsize,
-									   entry->newsize, false);
+				rewind_copy_file_range(entry->path, entry->target_size,
+									   entry->source_size, false);
 				break;
 
 			case FILE_ACTION_CREATE:
@@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map)
 			case FILE_ACTION_REMOVE:
 				remove_target(entry);
 				break;
+
+			case FILE_ACTION_UNDECIDED:
+				pg_fatal("no action decided for \"%s\"", entry->path);
+				break;
 		}
 	}
 
diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c
index 55439db20b..ec37d0b2e0 100644
--- a/src/bin/pg_rewind/file_ops.c
+++ b/src/bin/pg_rewind/file_ops.c
@@ -126,8 +126,9 @@ void
 remove_target(file_entry_t *entry)
 {
 	Assert(entry->action == FILE_ACTION_REMOVE);
+	Assert(entry->target_exists);
 
-	switch (entry->type)
+	switch (entry->target_type)
 	{
 		case FILE_TYPE_DIRECTORY:
 			remove_target_dir(entry->path);
@@ -140,6 +141,10 @@ remove_target(file_entry_t *entry)
 		case FILE_TYPE_SYMLINK:
 			remove_target_symlink(entry->path);
 			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("undefined file type for \"%s\"", entry->path);
+			break;
 	}
 }
 
@@ -147,21 +152,26 @@ void
 create_target(file_entry_t *entry)
 {
 	Assert(entry->action == FILE_ACTION_CREATE);
+	Assert(!entry->target_exists);
 
-	switch (entry->type)
+	switch (entry->source_type)
 	{
 		case FILE_TYPE_DIRECTORY:
 			create_target_dir(entry->path);
 			break;
 
 		case FILE_TYPE_SYMLINK:
-			create_target_symlink(entry->path, entry->link_target);
+			create_target_symlink(entry->path, entry->source_link_target);
 			break;
 
 		case FILE_TYPE_REGULAR:
 			/* can't happen. Regular files are created with open_target_file. */
 			pg_fatal("invalid action (CREATE) for regular file");
 			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("undefined file type for \"%s\"", entry->path);
+			break;
 	}
 }
 
diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 1abc257177..6d19d2be61 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path);
 static char *datasegpath(RelFileNode rnode, ForkNumber forknum,
 						 BlockNumber segno);
 static int	path_cmp(const void *a, const void *b);
+
+static file_entry_t *get_filemap_entry(const char *path, bool create);
 static int	final_filemap_cmp(const void *a, const void *b);
 static void filemap_list_to_array(filemap_t *map);
 static bool check_file_excluded(const char *path, bool is_source);
@@ -146,6 +148,65 @@ filemap_create(void)
 	filemap = map;
 }
 
+/* Look up or create entry for 'path' */
+static file_entry_t *
+get_filemap_entry(const char *path, bool create)
+{
+	filemap_t  *map = filemap;
+	file_entry_t *entry;
+	file_entry_t **e;
+	file_entry_t key;
+	file_entry_t *key_ptr;
+
+	if (map->array)
+	{
+		key.path = (char *) path;
+		key_ptr = &key;
+		e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
+					path_cmp);
+	}
+	else
+		e = NULL;
+
+	if (e)
+		entry = *e;
+	else if (!create)
+		entry = NULL;
+	else
+	{
+		/* Create a new entry for this file */
+		entry = pg_malloc(sizeof(file_entry_t));
+		entry->path = pg_strdup(path);
+		entry->isrelfile = isRelDataFile(path);
+		entry->action = FILE_ACTION_UNDECIDED;
+
+		entry->target_exists = false;
+		entry->target_type = FILE_TYPE_UNDEFINED;
+		entry->target_size = 0;
+		entry->target_link_target = NULL;
+		entry->target_modified_pages.bitmap = NULL;
+		entry->target_modified_pages.bitmapsize = 0;
+
+		entry->source_exists = false;
+		entry->source_type = FILE_TYPE_UNDEFINED;
+		entry->source_size = 0;
+		entry->source_link_target = NULL;
+
+		entry->next = NULL;
+
+		if (map->last)
+		{
+			map->last->next = entry;
+			map->last = entry;
+		}
+		else
+			map->first = map->last = entry;
+		map->nlist++;
+	}
+
+	return entry;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -154,25 +215,12 @@ filemap_create(void)
  * exists in the target and whether the size matches.
  */
 void
-process_source_file(const char *path, file_type_t type, size_t newsize,
+process_source_file(const char *path, file_type_t type, size_t size,
 					const char *link_target)
 {
-	bool		exists;
-	char		localpath[MAXPGPATH];
-	struct stat statbuf;
-	filemap_t  *map = filemap;
-	file_action_t action = FILE_ACTION_NONE;
-	size_t		oldsize = 0;
 	file_entry_t *entry;
 
-	Assert(map->array == NULL);
-
-	/*
-	 * Skip any files matching the exclusion filters. This has the effect to
-	 * remove all those files on the target.
-	 */
-	if (check_file_excluded(path, true))
-		return;
+	Assert(filemap->array == NULL);
 
 	/*
 	 * Pretend that pg_wal is a directory, even if it's really a symlink. We
@@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
 	if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK)
 		type = FILE_TYPE_DIRECTORY;
 
-	/*
-	 * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source.
-	 * This has the effect that all temporary files in the destination will be
-	 * removed.
-	 */
-	if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL)
-		return;
-	if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL)
-		return;
-
 	/*
 	 * sanity check: a filename that looks like a data file better be a
 	 * regular file
@@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
 	if (type != FILE_TYPE_REGULAR && isRelDataFile(path))
 		pg_fatal("data file \"%s\" in source is not a regular file", path);
 
-	snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path);
-
-	/* Does the corresponding file exist in the target data dir? */
-	if (lstat(localpath, &statbuf) < 0)
-	{
-		if (errno != ENOENT)
-			pg_fatal("could not stat file \"%s\": %m",
-					 localpath);
-
-		exists = false;
-	}
-	else
-		exists = true;
-
-	switch (type)
-	{
-		case FILE_TYPE_DIRECTORY:
-			if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0)
-			{
-				/* it's a directory in source, but not in target. Strange.. */
-				pg_fatal("\"%s\" is not a directory", localpath);
-			}
-
-			if (!exists)
-				action = FILE_ACTION_CREATE;
-			else
-				action = FILE_ACTION_NONE;
-			oldsize = 0;
-			break;
-
-		case FILE_TYPE_SYMLINK:
-			if (exists &&
-#ifndef WIN32
-				!S_ISLNK(statbuf.st_mode)
-#else
-				!pgwin32_is_junction(localpath)
-#endif
-				)
-			{
-				/*
-				 * It's a symbolic link in source, but not in target.
-				 * Strange..
-				 */
-				pg_fatal("\"%s\" is not a symbolic link", localpath);
-			}
-
-			if (!exists)
-				action = FILE_ACTION_CREATE;
-			else
-				action = FILE_ACTION_NONE;
-			oldsize = 0;
-			break;
-
-		case FILE_TYPE_REGULAR:
-			if (exists && !S_ISREG(statbuf.st_mode))
-				pg_fatal("\"%s\" is not a regular file", localpath);
-
-			if (!exists || !isRelDataFile(path))
-			{
-				/*
-				 * File exists in source, but not in target. Or it's a
-				 * non-data file that we have no special processing for. Copy
-				 * it in toto.
-				 *
-				 * An exception: PG_VERSIONs should be identical, but avoid
-				 * overwriting it for paranoia.
-				 */
-				if (pg_str_endswith(path, "PG_VERSION"))
-				{
-					action = FILE_ACTION_NONE;
-					oldsize = statbuf.st_size;
-				}
-				else
-				{
-					action = FILE_ACTION_COPY;
-					oldsize = 0;
-				}
-			}
-			else
-			{
-				/*
-				 * It's a data file that exists in both.
-				 *
-				 * If it's larger in target, we can truncate it. There will
-				 * also be a WAL record of the truncation in the source
-				 * system, so WAL replay would eventually truncate the target
-				 * too, but we might as well do it now.
-				 *
-				 * If it's smaller in the target, it means that it has been
-				 * truncated in the target, or enlarged in the source, or
-				 * both. If it was truncated in the target, we need to copy
-				 * the missing tail from the source system. If it was enlarged
-				 * in the source system, there will be WAL records in the
-				 * source system for the new blocks, so we wouldn't need to
-				 * copy them here. But we don't know which scenario we're
-				 * dealing with, and there's no harm in copying the missing
-				 * blocks now, so do it now.
-				 *
-				 * If it's the same size, do nothing here. Any blocks modified
-				 * in the target will be copied based on parsing the target
-				 * system's WAL, and any blocks modified in the source will be
-				 * updated after rewinding, when the source system's WAL is
-				 * replayed.
-				 */
-				oldsize = statbuf.st_size;
-				if (oldsize < newsize)
-					action = FILE_ACTION_COPY_TAIL;
-				else if (oldsize > newsize)
-					action = FILE_ACTION_TRUNCATE;
-				else
-					action = FILE_ACTION_NONE;
-			}
-			break;
-	}
-
-	/* Create a new entry for this file */
-	entry = pg_malloc(sizeof(file_entry_t));
-	entry->path = pg_strdup(path);
-	entry->type = type;
-	entry->action = action;
-	entry->oldsize = oldsize;
-	entry->newsize = newsize;
-	entry->link_target = link_target ? pg_strdup(link_target) : NULL;
-	entry->next = NULL;
-	entry->pagemap.bitmap = NULL;
-	entry->pagemap.bitmapsize = 0;
-	entry->isrelfile = isRelDataFile(path);
-
-	if (map->last)
-	{
-		map->last->next = entry;
-		map->last = entry;
-	}
-	else
-		map->first = map->last = entry;
-	map->nlist++;
+	/* Remember this source file */
+	entry = get_filemap_entry(path, true);
+	entry->source_exists = true;
+	entry->source_type = type;
+	entry->source_size = size;
+	entry->source_link_target = link_target ? pg_strdup(link_target) : NULL;
 }
 
 /*
@@ -345,12 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
  * deletion.
  */
 void
-process_target_file(const char *path, file_type_t type, size_t oldsize,
+process_target_file(const char *path, file_type_t type, size_t size,
 					const char *link_target)
 {
-	bool		exists;
-	file_entry_t key;
-	file_entry_t *key_ptr;
 	filemap_t  *map = filemap;
 	file_entry_t *entry;
 
@@ -377,120 +282,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize,
 	}
 
 	/*
-	 * Like in process_source_file, pretend that xlog is always a  directory.
+	 * Like in process_source_file, pretend that pg_wal is always a directory.
 	 */
 	if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK)
 		type = FILE_TYPE_DIRECTORY;
 
-	key.path = (char *) path;
-	key_ptr = &key;
-	exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
-					  path_cmp) != NULL);
-
-	/* Remove any file or folder that doesn't exist in the source system. */
-	if (!exists)
-	{
-		entry = pg_malloc(sizeof(file_entry_t));
-		entry->path = pg_strdup(path);
-		entry->type = type;
-		entry->action = FILE_ACTION_REMOVE;
-		entry->oldsize = oldsize;
-		entry->newsize = 0;
-		entry->link_target = link_target ? pg_strdup(link_target) : NULL;
-		entry->next = NULL;
-		entry->pagemap.bitmap = NULL;
-		entry->pagemap.bitmapsize = 0;
-		entry->isrelfile = isRelDataFile(path);
-
-		if (map->last == NULL)
-			map->first = entry;
-		else
-			map->last->next = entry;
-		map->last = entry;
-		map->nlist++;
-	}
-	else
-	{
-		/*
-		 * We already handled all files that exist in the source system in
-		 * process_source_file().
-		 */
-	}
+	/* Remember this target file */
+	entry = get_filemap_entry(path, true);
+	entry->target_exists = true;
+	entry->target_type = type;
+	entry->target_size = size;
+	entry->target_link_target = link_target ? pg_strdup(link_target) : NULL;
 }
 
 /*
  * This callback gets called while we read the WAL in the target, for every
- * block that have changed in the target system. It makes note of all the
+ * block that have changed in the target system.  It makes note of all the
  * changed blocks in the pagemap of the file.
+ *
+ * NOTE: All the files on both systems must have already been added to the
+ * file map!
  */
 void
-process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno)
+process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode,
+								BlockNumber blkno)
 {
 	char	   *path;
-	file_entry_t key;
-	file_entry_t *key_ptr;
 	file_entry_t *entry;
 	BlockNumber blkno_inseg;
 	int			segno;
-	filemap_t  *map = filemap;
-	file_entry_t **e;
 
-	Assert(map->array);
+	Assert(filemap->array);
 
 	segno = blkno / RELSEG_SIZE;
 	blkno_inseg = blkno % RELSEG_SIZE;
 
 	path = datasegpath(rnode, forknum, segno);
-
-	key.path = (char *) path;
-	key_ptr = &key;
-
-	e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
-				path_cmp);
-	if (e)
-		entry = *e;
-	else
-		entry = NULL;
+	entry = get_filemap_entry(path, false);
 	pfree(path);
 
 	if (entry)
 	{
+		int64		end_offset;
+
 		Assert(entry->isrelfile);
 
-		switch (entry->action)
-		{
-			case FILE_ACTION_NONE:
-			case FILE_ACTION_TRUNCATE:
-				/* skip if we're truncating away the modified block anyway */
-				if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize)
-					datapagemap_add(&entry->pagemap, blkno_inseg);
-				break;
-
-			case FILE_ACTION_COPY_TAIL:
-
-				/*
-				 * skip the modified block if it is part of the "tail" that
-				 * we're copying anyway.
-				 */
-				if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize)
-					datapagemap_add(&entry->pagemap, blkno_inseg);
-				break;
-
-			case FILE_ACTION_COPY:
-			case FILE_ACTION_REMOVE:
-				break;
-
-			case FILE_ACTION_CREATE:
-				pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path);
-		}
+		if (entry->target_type != FILE_TYPE_REGULAR)
+			pg_fatal("unexpected page modification for directory or symbolic link \"%s\"",
+					 entry->path);
+
+		/*
+		 * If the block beyond the EOF in the source system, no need to
+		 * remember it now, because we're going to truncate it away from the
+		 * target anyway. Also no need to remember the block if it's beyond
+		 * the current EOF in the target system; we will copy it over with the
+		 * "tail" from the source system, anyway.
+		 */
+		end_offset = (blkno_inseg + 1) * BLCKSZ;
+		if (end_offset <= entry->source_size &&
+			end_offset <= entry->target_size)
+			datapagemap_add(&entry->target_modified_pages, blkno_inseg);
 	}
 	else
 	{
 		/*
 		 * If we don't have any record of this file in the file map, it means
-		 * that it's a relation that doesn't exist in the source system, and
-		 * it was subsequently removed in the target system, too. We can
-		 * safely ignore it.
+		 * that it's a relation that doesn't exist in the source system.  It
+		 * could exist in the target system; we haven't moved the target-only
+		 * entries from the linked list to the array yet!  But in any case, if
+		 * it doesn't exist in the source it will be removed from the target
+		 * too, and we can safely ignore it.
 		 */
 	}
 }
@@ -581,16 +442,6 @@ filemap_list_to_array(filemap_t *map)
 	map->first = map->last = NULL;
 }
 
-void
-filemap_finalize(void)
-{
-	filemap_t  *map = filemap;
-
-	filemap_list_to_array(map);
-	qsort(map->array, map->narray, sizeof(file_entry_t *),
-		  final_filemap_cmp);
-}
-
 static const char *
 action_to_str(file_action_t action)
 {
@@ -631,26 +482,26 @@ calculate_totals(void)
 	{
 		entry = map->array[i];
 
-		if (entry->type != FILE_TYPE_REGULAR)
+		if (entry->source_type != FILE_TYPE_REGULAR)
 			continue;
 
-		map->total_size += entry->newsize;
+		map->total_size += entry->source_size;
 
 		if (entry->action == FILE_ACTION_COPY)
 		{
-			map->fetch_size += entry->newsize;
+			map->fetch_size += entry->source_size;
 			continue;
 		}
 
 		if (entry->action == FILE_ACTION_COPY_TAIL)
-			map->fetch_size += (entry->newsize - entry->oldsize);
+			map->fetch_size += (entry->source_size - entry->target_size);
 
-		if (entry->pagemap.bitmapsize > 0)
+		if (entry->target_modified_pages.bitmapsize > 0)
 		{
 			datapagemap_iterator_t *iter;
 			BlockNumber blk;
 
-			iter = datapagemap_iterate(&entry->pagemap);
+			iter = datapagemap_iterate(&entry->target_modified_pages);
 			while (datapagemap_next(iter, &blk))
 				map->fetch_size += BLCKSZ;
 
@@ -670,13 +521,13 @@ print_filemap(void)
 	{
 		entry = map->array[i];
 		if (entry->action != FILE_ACTION_NONE ||
-			entry->pagemap.bitmapsize > 0)
+			entry->target_modified_pages.bitmapsize > 0)
 		{
 			pg_log_debug("%s (%s)", entry->path,
 						 action_to_str(entry->action));
 
-			if (entry->pagemap.bitmapsize > 0)
-				datapagemap_print(&entry->pagemap);
+			if (entry->target_modified_pages.bitmapsize > 0)
+				datapagemap_print(&entry->target_modified_pages);
 		}
 	}
 	fflush(stdout);
@@ -825,3 +676,180 @@ final_filemap_cmp(const void *a, const void *b)
 	else
 		return strcmp(fa->path, fb->path);
 }
+
+/*
+ * Decide what action to perform to a file.
+ */
+static file_action_t
+decide_file_action(file_entry_t *entry)
+{
+	const char *path = entry->path;
+
+	/*
+	 * Don't touch the control file. It is handled specially, after copying
+	 * all the other files.
+	 */
+	if (strcmp(path, "global/pg_control") == 0)
+		return FILE_ACTION_NONE;
+
+	/*
+	 * Remove all files matching the exclusion filters in the target.
+	 */
+	if (check_file_excluded(path, true))
+	{
+		if (entry->target_exists)
+			return FILE_ACTION_REMOVE;
+		else
+			return FILE_ACTION_NONE;
+	}
+
+	/*
+	 * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.*
+	 * in the target.
+	 */
+	if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL ||
+		strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL)
+	{
+		if (entry->target_exists)
+			return FILE_ACTION_REMOVE;
+		else
+			return FILE_ACTION_NONE;
+	}
+
+	/*
+	 * Handle cases where the file is missing from one of the systems.
+	 */
+	if (!entry->target_exists && entry->source_exists)
+	{
+		/*
+		 * File exists in source, but not in target. Copy it in toto. (If it's
+		 * a relation data file, WAL replay after rewinding should re-create
+		 * it anyway. But there's no harm in copying it now.)
+		 */
+		switch (entry->source_type)
+		{
+			case FILE_TYPE_DIRECTORY:
+			case FILE_TYPE_SYMLINK:
+				return FILE_ACTION_CREATE;
+			case FILE_TYPE_REGULAR:
+				return FILE_ACTION_COPY;
+			case FILE_TYPE_UNDEFINED:
+				pg_fatal("unknown file type for \"%s\"", entry->path);
+				break;
+		}
+	}
+	else if (entry->target_exists && !entry->source_exists)
+	{
+		/* File exists in target, but not source. Remove it. */
+		return FILE_ACTION_REMOVE;
+	}
+	else if (!entry->target_exists && !entry->source_exists)
+	{
+		/*
+		 * Doesn't exist in either server. Why does it have an entry in the
+		 * first place??
+		 */
+		return FILE_ACTION_NONE;
+	}
+
+	/*
+	 * Otherwise, the file exists on both systems
+	 */
+	Assert(entry->target_exists && entry->source_exists);
+
+	if (entry->source_type != entry->target_type)
+	{
+		/* But it's a different kind of object. Strange.. */
+		pg_fatal("file \"%s\" is of different type in source and target", entry->path);
+	}
+
+	/*
+	 * PG_VERSION files should be identical on both systems, but avoid
+	 * overwriting them for paranoia.
+	 */
+	if (pg_str_endswith(entry->path, "PG_VERSION"))
+		return FILE_ACTION_NONE;
+
+	switch (entry->source_type)
+	{
+		case FILE_TYPE_DIRECTORY:
+			return FILE_ACTION_NONE;
+
+		case FILE_TYPE_SYMLINK:
+			/* FIXME: Check if it points to the same target? */
+			return FILE_ACTION_NONE;
+
+		case FILE_TYPE_REGULAR:
+			if (!entry->isrelfile)
+			{
+				/*
+				 * It's a non-data file that we have no special processing
+				 * for. Copy it in toto.
+				 */
+				return FILE_ACTION_COPY;
+			}
+			else
+			{
+				/*
+				 * It's a data file that exists in both systems.
+				 *
+				 * If it's larger in target, we can truncate it. There will
+				 * also be a WAL record of the truncation in the source
+				 * system, so WAL replay would eventually truncate the target
+				 * too, but we might as well do it now.
+				 *
+				 * If it's smaller in the target, it means that it has been
+				 * truncated in the target, or enlarged in the source, or
+				 * both. If it was truncated in the target, we need to copy
+				 * the missing tail from the source system. If it was enlarged
+				 * in the source system, there will be WAL records in the
+				 * source system for the new blocks, so we wouldn't need to
+				 * copy them here. But we don't know which scenario we're
+				 * dealing with, and there's no harm in copying the missing
+				 * blocks now, so do it now.
+				 *
+				 * If it's the same size, do nothing here. Any blocks modified
+				 * in the target will be copied based on parsing the target
+				 * system's WAL, and any blocks modified in the source will be
+				 * updated after rewinding, when the source system's WAL is
+				 * replayed.
+				 */
+				if (entry->target_size < entry->source_size)
+					return FILE_ACTION_COPY_TAIL;
+				else if (entry->target_size > entry->source_size)
+					return FILE_ACTION_TRUNCATE;
+				else
+					return FILE_ACTION_NONE;
+			}
+			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("unknown file type for \"%s\"", path);
+			break;
+	}
+
+	/* unreachable */
+	pg_fatal("could not decide what to do with file \"%s\"", path);
+}
+
+/*
+ * Decide what to do with each file.
+ */
+void
+filemap_finalize()
+{
+	int			i;
+
+	filemap_list_to_array(filemap);
+
+	for (i = 0; i < filemap->narray; i++)
+	{
+		file_entry_t *entry = filemap->array[i];
+
+		entry->action = decide_file_action(entry);
+	}
+
+	/* Sort the actions to the order that they should be performed */
+	qsort(filemap->array, filemap->narray, sizeof(file_entry_t *),
+		  final_filemap_cmp);
+}
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 0cb7425170..a5e8df57f4 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -14,17 +14,21 @@
 
 /*
  * For every file found in the local or remote system, we have a file entry
- * which says what we are going to do with the file. For relation files,
- * there is also a page map, marking pages in the file that were changed
- * locally.
- *
- * The enum values are sorted in the order we want actions to be processed.
+ * that contains information about the file on both systems.  For relation
+ * files, there is also a page map that marks pages in the file that were
+ * changed in the target after the last common checkpoint.  Each entry also
+ * contains an 'action' field, which says what we are going to do with the
+ * file.
  */
+
+/* these enum values are sorted in the order we want actions to be processed */
 typedef enum
 {
+	FILE_ACTION_UNDECIDED = 0,	/* not decided yet */
+
 	FILE_ACTION_CREATE,			/* create local directory or symbolic link */
 	FILE_ACTION_COPY,			/* copy whole file, overwriting if exists */
-	FILE_ACTION_COPY_TAIL,		/* copy tail from 'oldsize' to 'newsize' */
+	FILE_ACTION_COPY_TAIL,		/* copy tail from 'source_size' to 'target_size' */
 	FILE_ACTION_NONE,			/* no action (we might still copy modified
 								 * blocks based on the parsed WAL) */
 	FILE_ACTION_TRUNCATE,		/* truncate local file to 'newsize' bytes */
@@ -33,6 +37,8 @@ typedef enum
 
 typedef enum
 {
+	FILE_TYPE_UNDEFINED = 0,
+
 	FILE_TYPE_REGULAR,
 	FILE_TYPE_DIRECTORY,
 	FILE_TYPE_SYMLINK
@@ -41,19 +47,30 @@ typedef enum
 typedef struct file_entry_t
 {
 	char	   *path;
-	file_type_t type;
-
-	file_action_t action;
-
-	/* for a regular file */
-	size_t		oldsize;
-	size_t		newsize;
 	bool		isrelfile;		/* is it a relation data file? */
 
-	datapagemap_t pagemap;
+	/*
+	 * Status of the file in the target.
+	 */
+	bool		target_exists;
+	file_type_t target_type;
+	size_t		target_size; /* for a regular file */
+	char	   *target_link_target; /* for a symlink */
 
-	/* for a symlink */
-	char	   *link_target;
+	datapagemap_t target_modified_pages;
+
+	/*
+	 * Status of the file in the source.
+	 */
+	bool		source_exists;
+	file_type_t source_type;
+	size_t		source_size;
+	char	   *source_link_target; /* for a symlink */
+
+	/*
+	 * What will we do to the file?
+	 */
+	file_action_t action;
 
 	struct file_entry_t *next;
 } file_entry_t;
@@ -70,20 +87,19 @@ typedef struct filemap_t
 
 	/*
 	 * After processing all the remote files, the entries in the linked list
-	 * are moved to this array. After processing local files, too, all the
+	 * are moved to this array.  After processing local files, too, all the
 	 * local entries are added to the array by filemap_finalize, and sorted in
-	 * the final order. After filemap_finalize, all the entries are in the
+	 * the final order.  After filemap_finalize, all the entries are in the
 	 * array, and the linked list is empty.
 	 */
 	file_entry_t **array;
 	int			narray;			/* current length of array */
 
 	/*
-	 * Summary information. total_size is the total size of the source
-	 * cluster, and fetch_size is the number of bytes that needs to be copied.
+	 * Summary information.
 	 */
-	uint64		total_size;
-	uint64		fetch_size;
+	uint64		total_size;		/* total size of the source cluster */
+	uint64		fetch_size;		/* number of bytes that needs to be copied */
 } filemap_t;
 
 extern filemap_t *filemap;
@@ -94,11 +110,12 @@ extern void print_filemap(void);
 
 /* Functions for populating the filemap */
 extern void process_source_file(const char *path, file_type_t type,
-								size_t newsize, const char *link_target);
+								size_t size, const char *link_target);
 extern void process_target_file(const char *path, file_type_t type,
-								size_t newsize, const char *link_target);
-extern void process_block_change(ForkNumber forknum, RelFileNode rnode,
-								 BlockNumber blkno);
+								size_t size, const char *link_target);
+extern void process_target_wal_block_change(ForkNumber forknum,
+											RelFileNode rnode,
+											BlockNumber blkno);
 extern void filemap_finalize(void);
 
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c
index bf4dfc23b9..7fc9161b8c 100644
--- a/src/bin/pg_rewind/libpq_fetch.c
+++ b/src/bin/pg_rewind/libpq_fetch.c
@@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map)
 		entry = map->array[i];
 
 		/* If this is a relation file, copy the modified blocks */
-		execute_pagemap(&entry->pagemap, entry->path);
+		execute_pagemap(&entry->target_modified_pages, entry->path);
 
 		switch (entry->action)
 		{
@@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map)
 			case FILE_ACTION_COPY:
 				/* Truncate the old file out of the way, if any */
 				open_target_file(entry->path, true);
-				fetch_file_range(entry->path, 0, entry->newsize);
+				fetch_file_range(entry->path, 0, entry->source_size);
 				break;
 
 			case FILE_ACTION_TRUNCATE:
-				truncate_target_file(entry->path, entry->newsize);
+				truncate_target_file(entry->path, entry->source_size);
 				break;
 
 			case FILE_ACTION_COPY_TAIL:
-				fetch_file_range(entry->path, entry->oldsize, entry->newsize);
+				fetch_file_range(entry->path, entry->target_size, entry->source_size);
 				break;
 
 			case FILE_ACTION_REMOVE:
@@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map)
 			case FILE_ACTION_CREATE:
 				create_target(entry);
 				break;
+
+			case FILE_ACTION_UNDECIDED:
+				pg_fatal("no action decided for \"%s\"", entry->path);
+				break;
 		}
 	}
 
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 2229c86f9a..2baeb74ae9 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record)
 		if (forknum != MAIN_FORKNUM)
 			continue;
 
-		process_block_change(forknum, rnode, blkno);
+		process_target_wal_block_change(forknum, rnode, blkno);
 	}
 }
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 5a7ab764db..e0ed1759cb 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -369,7 +369,7 @@ main(int argc, char **argv)
 				chkpttli);
 
 	/*
-	 * Build the filemap, by comparing the source and target data directories.
+	 * Collect information about all files in the target and source systems.
 	 */
 	filemap_create();
 	if (showprogress)
@@ -390,8 +390,12 @@ main(int argc, char **argv)
 		pg_log_info("reading WAL in target");
 	extractPageMap(datadir_target, chkptrec, lastcommontliIndex,
 				   ControlFile_target.checkPoint, restore_command);
+
+	/*
+	 * We have collected all information we need from both systems. Decide
+	 * what to do with each file.
+	 */
 	filemap_finalize();
-
 	if (showprogress)
 		calculate_totals();
 
-- 
2.18.4


----Next_Part(Fri_Sep_18_16_41_50_2020_369)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v2_5-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch"



^ permalink  raw  reply  [nested|flat] 5+ messages in thread

* [PATCH 2/5] Refactor pg_rewind for more clear decision making.
@ 2020-08-19 12:34 Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 5+ messages in thread

From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw)

Deciding what to do with each file is now a separate step after all the
necessary information has been gathered. It is more clear that way.
Previously, the decision-making was divided between process_source_file()
and process_target_file(), and it was a bit hard to piece together what the
overall rules were.
---
 src/bin/pg_rewind/copy_fetch.c  |  14 +-
 src/bin/pg_rewind/file_ops.c    |  16 +-
 src/bin/pg_rewind/filemap.c     | 514 ++++++++++++++++----------------
 src/bin/pg_rewind/filemap.h     |  67 +++--
 src/bin/pg_rewind/libpq_fetch.c |  12 +-
 src/bin/pg_rewind/parsexlog.c   |   2 +-
 src/bin/pg_rewind/pg_rewind.c   |   8 +-
 7 files changed, 332 insertions(+), 301 deletions(-)

diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c
index 1edab5f1867..18fad32600e 100644
--- a/src/bin/pg_rewind/copy_fetch.c
+++ b/src/bin/pg_rewind/copy_fetch.c
@@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map)
 	for (i = 0; i < map->narray; i++)
 	{
 		entry = map->array[i];
-		execute_pagemap(&entry->pagemap, entry->path);
+		execute_pagemap(&entry->target_modified_pages, entry->path);
 
 		switch (entry->action)
 		{
@@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map)
 				break;
 
 			case FILE_ACTION_COPY:
-				rewind_copy_file_range(entry->path, 0, entry->newsize, true);
+				rewind_copy_file_range(entry->path, 0, entry->source_size, true);
 				break;
 
 			case FILE_ACTION_TRUNCATE:
-				truncate_target_file(entry->path, entry->newsize);
+				truncate_target_file(entry->path, entry->source_size);
 				break;
 
 			case FILE_ACTION_COPY_TAIL:
-				rewind_copy_file_range(entry->path, entry->oldsize,
-									   entry->newsize, false);
+				rewind_copy_file_range(entry->path, entry->target_size,
+									   entry->source_size, false);
 				break;
 
 			case FILE_ACTION_CREATE:
@@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map)
 			case FILE_ACTION_REMOVE:
 				remove_target(entry);
 				break;
+
+			case FILE_ACTION_UNDECIDED:
+				pg_fatal("no action decided for \"%s\"", entry->path);
+				break;
 		}
 	}
 
diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c
index 55439db20ba..ec37d0b2e0d 100644
--- a/src/bin/pg_rewind/file_ops.c
+++ b/src/bin/pg_rewind/file_ops.c
@@ -126,8 +126,9 @@ void
 remove_target(file_entry_t *entry)
 {
 	Assert(entry->action == FILE_ACTION_REMOVE);
+	Assert(entry->target_exists);
 
-	switch (entry->type)
+	switch (entry->target_type)
 	{
 		case FILE_TYPE_DIRECTORY:
 			remove_target_dir(entry->path);
@@ -140,6 +141,10 @@ remove_target(file_entry_t *entry)
 		case FILE_TYPE_SYMLINK:
 			remove_target_symlink(entry->path);
 			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("undefined file type for \"%s\"", entry->path);
+			break;
 	}
 }
 
@@ -147,21 +152,26 @@ void
 create_target(file_entry_t *entry)
 {
 	Assert(entry->action == FILE_ACTION_CREATE);
+	Assert(!entry->target_exists);
 
-	switch (entry->type)
+	switch (entry->source_type)
 	{
 		case FILE_TYPE_DIRECTORY:
 			create_target_dir(entry->path);
 			break;
 
 		case FILE_TYPE_SYMLINK:
-			create_target_symlink(entry->path, entry->link_target);
+			create_target_symlink(entry->path, entry->source_link_target);
 			break;
 
 		case FILE_TYPE_REGULAR:
 			/* can't happen. Regular files are created with open_target_file. */
 			pg_fatal("invalid action (CREATE) for regular file");
 			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("undefined file type for \"%s\"", entry->path);
+			break;
 	}
 }
 
diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 1879257b66a..431e8e760e0 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path);
 static char *datasegpath(RelFileNode rnode, ForkNumber forknum,
 						 BlockNumber segno);
 static int	path_cmp(const void *a, const void *b);
+
+static file_entry_t *get_filemap_entry(const char *path, bool create);
 static int	final_filemap_cmp(const void *a, const void *b);
 static void filemap_list_to_array(filemap_t *map);
 static bool check_file_excluded(const char *path, bool is_source);
@@ -146,6 +148,65 @@ filemap_create(void)
 	filemap = map;
 }
 
+/* Look up or create entry for 'path' */
+static file_entry_t *
+get_filemap_entry(const char *path, bool create)
+{
+	filemap_t  *map = filemap;
+	file_entry_t *entry;
+	file_entry_t **e;
+	file_entry_t key;
+	file_entry_t *key_ptr;
+
+	if (map->array)
+	{
+		key.path = (char *) path;
+		key_ptr = &key;
+		e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
+					path_cmp);
+	}
+	else
+		e = NULL;
+
+	if (e)
+		entry = *e;
+	else if (!create)
+		entry = NULL;
+	else
+	{
+		/* Create a new entry for this file */
+		entry = pg_malloc(sizeof(file_entry_t));
+		entry->path = pg_strdup(path);
+		entry->isrelfile = isRelDataFile(path);
+		entry->action = FILE_ACTION_UNDECIDED;
+
+		entry->target_exists = false;
+		entry->target_type = FILE_TYPE_UNDEFINED;
+		entry->target_size = 0;
+		entry->target_link_target = NULL;
+		entry->target_modified_pages.bitmap = NULL;
+		entry->target_modified_pages.bitmapsize = 0;
+
+		entry->source_exists = false;
+		entry->source_type = FILE_TYPE_UNDEFINED;
+		entry->source_size = 0;
+		entry->source_link_target = NULL;
+
+		entry->next = NULL;
+
+		if (map->last)
+		{
+			map->last->next = entry;
+			map->last = entry;
+		}
+		else
+			map->first = map->last = entry;
+		map->nlist++;
+	}
+
+	return entry;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -154,18 +215,19 @@ filemap_create(void)
  * exists in the target and whether the size matches.
  */
 void
-process_source_file(const char *path, file_type_t type, size_t newsize,
+process_source_file(const char *path, file_type_t type, size_t size,
 					const char *link_target)
 {
-	bool		exists;
-	char		localpath[MAXPGPATH];
-	struct stat statbuf;
-	filemap_t  *map = filemap;
-	file_action_t action = FILE_ACTION_NONE;
-	size_t		oldsize = 0;
 	file_entry_t *entry;
 
-	Assert(map->array == NULL);
+	Assert(filemap->array == NULL);
+
+	/*
+	 * Skip the control file. It is handled specially, after copying all the
+	 * other files.
+	 */
+	if (strcmp(path, "global/pg_control") == 0)
+		return;
 
 	/*
 	 * Skip any files matching the exclusion filters. This has the effect to
@@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
 	if (type != FILE_TYPE_REGULAR && isRelDataFile(path))
 		pg_fatal("data file \"%s\" in source is not a regular file", path);
 
-	snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path);
-
-	/* Does the corresponding file exist in the target data dir? */
-	if (lstat(localpath, &statbuf) < 0)
-	{
-		if (errno != ENOENT)
-			pg_fatal("could not stat file \"%s\": %m",
-					 localpath);
-
-		exists = false;
-	}
-	else
-		exists = true;
-
-	switch (type)
-	{
-		case FILE_TYPE_DIRECTORY:
-			if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0)
-			{
-				/* it's a directory in source, but not in target. Strange.. */
-				pg_fatal("\"%s\" is not a directory", localpath);
-			}
-
-			if (!exists)
-				action = FILE_ACTION_CREATE;
-			else
-				action = FILE_ACTION_NONE;
-			oldsize = 0;
-			break;
-
-		case FILE_TYPE_SYMLINK:
-			if (exists &&
-#ifndef WIN32
-				!S_ISLNK(statbuf.st_mode)
-#else
-				!pgwin32_is_junction(localpath)
-#endif
-				)
-			{
-				/*
-				 * It's a symbolic link in source, but not in target.
-				 * Strange..
-				 */
-				pg_fatal("\"%s\" is not a symbolic link", localpath);
-			}
-
-			if (!exists)
-				action = FILE_ACTION_CREATE;
-			else
-				action = FILE_ACTION_NONE;
-			oldsize = 0;
-			break;
-
-		case FILE_TYPE_REGULAR:
-			if (exists && !S_ISREG(statbuf.st_mode))
-				pg_fatal("\"%s\" is not a regular file", localpath);
-
-			if (!exists || !isRelDataFile(path))
-			{
-				/*
-				 * File exists in source, but not in target. Or it's a
-				 * non-data file that we have no special processing for. Copy
-				 * it in toto.
-				 *
-				 * An exception: PG_VERSIONs should be identical, but avoid
-				 * overwriting it for paranoia.
-				 */
-				if (pg_str_endswith(path, "PG_VERSION"))
-				{
-					action = FILE_ACTION_NONE;
-					oldsize = statbuf.st_size;
-				}
-				else
-				{
-					action = FILE_ACTION_COPY;
-					oldsize = 0;
-				}
-			}
-			else
-			{
-				/*
-				 * It's a data file that exists in both.
-				 *
-				 * If it's larger in target, we can truncate it. There will
-				 * also be a WAL record of the truncation in the source
-				 * system, so WAL replay would eventually truncate the target
-				 * too, but we might as well do it now.
-				 *
-				 * If it's smaller in the target, it means that it has been
-				 * truncated in the target, or enlarged in the source, or
-				 * both. If it was truncated in the target, we need to copy
-				 * the missing tail from the source system. If it was enlarged
-				 * in the source system, there will be WAL records in the
-				 * source system for the new blocks, so we wouldn't need to
-				 * copy them here. But we don't know which scenario we're
-				 * dealing with, and there's no harm in copying the missing
-				 * blocks now, so do it now.
-				 *
-				 * If it's the same size, do nothing here. Any blocks modified
-				 * in the target will be copied based on parsing the target
-				 * system's WAL, and any blocks modified in the source will be
-				 * updated after rewinding, when the source system's WAL is
-				 * replayed.
-				 */
-				oldsize = statbuf.st_size;
-				if (oldsize < newsize)
-					action = FILE_ACTION_COPY_TAIL;
-				else if (oldsize > newsize)
-					action = FILE_ACTION_TRUNCATE;
-				else
-					action = FILE_ACTION_NONE;
-			}
-			break;
-	}
-
-	/* Create a new entry for this file */
-	entry = pg_malloc(sizeof(file_entry_t));
-	entry->path = pg_strdup(path);
-	entry->type = type;
-	entry->action = action;
-	entry->oldsize = oldsize;
-	entry->newsize = newsize;
-	entry->link_target = link_target ? pg_strdup(link_target) : NULL;
-	entry->next = NULL;
-	entry->pagemap.bitmap = NULL;
-	entry->pagemap.bitmapsize = 0;
-	entry->isrelfile = isRelDataFile(path);
-
-	if (map->last)
-	{
-		map->last->next = entry;
-		map->last = entry;
-	}
-	else
-		map->first = map->last = entry;
-	map->nlist++;
+	/* Remember this source file */
+	entry = get_filemap_entry(path, true);
+	entry->source_exists = true;
+	entry->source_type = type;
+	entry->source_size = size;
+	entry->source_link_target = link_target ? pg_strdup(link_target) : NULL;
 }
 
 /*
@@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
  * deletion.
  */
 void
-process_target_file(const char *path, file_type_t type, size_t oldsize,
+process_target_file(const char *path, file_type_t type, size_t size,
 					const char *link_target)
 {
-	bool		exists;
-	char		localpath[MAXPGPATH];
-	struct stat statbuf;
-	file_entry_t key;
-	file_entry_t *key_ptr;
 	filemap_t  *map = filemap;
 	file_entry_t *entry;
 
+	/*
+	 * Skip the control file. It is handled specially, after copying all the
+	 * other files.
+	 */
+	if (strcmp(path, "global/pg_control") == 0)
+		return;
+
 	/*
 	 * Do not apply any exclusion filters here.  This has advantage to remove
 	 * from the target data folder all paths which have been filtered out from
 	 * the source data folder when processing the source files.
 	 */
-
-	snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path);
-	if (lstat(localpath, &statbuf) < 0)
-	{
-		if (errno != ENOENT)
-			pg_fatal("could not stat file \"%s\": %m",
-					 localpath);
-
-		exists = false;
-	}
-
 	if (map->array == NULL)
 	{
 		/* on first call, initialize lookup array */
@@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize,
 	}
 
 	/*
-	 * Like in process_source_file, pretend that xlog is always a  directory.
+	 * Like in process_source_file, pretend that pg_wal is always a directory.
 	 */
 	if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK)
 		type = FILE_TYPE_DIRECTORY;
 
-	key.path = (char *) path;
-	key_ptr = &key;
-	exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
-					  path_cmp) != NULL);
-
-	/* Remove any file or folder that doesn't exist in the source system. */
-	if (!exists)
-	{
-		entry = pg_malloc(sizeof(file_entry_t));
-		entry->path = pg_strdup(path);
-		entry->type = type;
-		entry->action = FILE_ACTION_REMOVE;
-		entry->oldsize = oldsize;
-		entry->newsize = 0;
-		entry->link_target = link_target ? pg_strdup(link_target) : NULL;
-		entry->next = NULL;
-		entry->pagemap.bitmap = NULL;
-		entry->pagemap.bitmapsize = 0;
-		entry->isrelfile = isRelDataFile(path);
-
-		if (map->last == NULL)
-			map->first = entry;
-		else
-			map->last->next = entry;
-		map->last = entry;
-		map->nlist++;
-	}
-	else
-	{
-		/*
-		 * We already handled all files that exist in the source system in
-		 * process_source_file().
-		 */
-	}
+	/* Remember this target file */
+	entry = get_filemap_entry(path, true);
+	entry->target_exists = true;
+	entry->target_type = type;
+	entry->target_size = size;
+	entry->target_link_target = link_target ? pg_strdup(link_target) : NULL;
 }
 
 /*
  * This callback gets called while we read the WAL in the target, for every
- * block that have changed in the target system. It makes note of all the
+ * block that have changed in the target system.  It makes note of all the
  * changed blocks in the pagemap of the file.
+ *
+ * NOTE: All the files on both systems must have already been added to the
+ * file map!
  */
 void
-process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno)
+process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode,
+								BlockNumber blkno)
 {
 	char	   *path;
-	file_entry_t key;
-	file_entry_t *key_ptr;
 	file_entry_t *entry;
 	BlockNumber blkno_inseg;
 	int			segno;
-	filemap_t  *map = filemap;
-	file_entry_t **e;
 
-	Assert(map->array);
+	Assert(filemap->array);
 
 	segno = blkno / RELSEG_SIZE;
 	blkno_inseg = blkno % RELSEG_SIZE;
 
 	path = datasegpath(rnode, forknum, segno);
-
-	key.path = (char *) path;
-	key_ptr = &key;
-
-	e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
-				path_cmp);
-	if (e)
-		entry = *e;
-	else
-		entry = NULL;
+	entry = get_filemap_entry(path, false);
 	pfree(path);
 
 	if (entry)
 	{
+		int64		end_offset;
+
 		Assert(entry->isrelfile);
 
-		switch (entry->action)
-		{
-			case FILE_ACTION_NONE:
-			case FILE_ACTION_TRUNCATE:
-				/* skip if we're truncating away the modified block anyway */
-				if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize)
-					datapagemap_add(&entry->pagemap, blkno_inseg);
-				break;
-
-			case FILE_ACTION_COPY_TAIL:
-
-				/*
-				 * skip the modified block if it is part of the "tail" that
-				 * we're copying anyway.
-				 */
-				if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize)
-					datapagemap_add(&entry->pagemap, blkno_inseg);
-				break;
-
-			case FILE_ACTION_COPY:
-			case FILE_ACTION_REMOVE:
-				break;
-
-			case FILE_ACTION_CREATE:
-				pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path);
-		}
+		if (entry->target_type != FILE_TYPE_REGULAR)
+			pg_fatal("unexpected page modification for directory or symbolic link \"%s\"",
+					 entry->path);
+
+		/*
+		 * If the block beyond the EOF in the source system, no need to
+		 * remember it now, because we're going to truncate it away from the
+		 * target anyway. Also no need to remember the block if it's beyond
+		 * the current EOF in the target system; we will copy it over with the
+		 * "tail" from the source system, anyway.
+		 */
+		end_offset = (blkno_inseg + 1) * BLCKSZ;
+		if (end_offset <= entry->source_size &&
+			end_offset <= entry->target_size)
+			datapagemap_add(&entry->target_modified_pages, blkno_inseg);
 	}
 	else
 	{
 		/*
 		 * If we don't have any record of this file in the file map, it means
-		 * that it's a relation that doesn't exist in the source system, and
-		 * it was subsequently removed in the target system, too. We can
-		 * safely ignore it.
+		 * that it's a relation that doesn't exist in the source system.  It
+		 * could exist in the target system; we haven't moved the target-only
+		 * entries from the linked list to the array yet!  But in any case, if
+		 * it doesn't exist in the source it will be removed from the target
+		 * too, and we can safely ignore it.
 		 */
 	}
 }
@@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map)
 	map->first = map->last = NULL;
 }
 
-void
-filemap_finalize(void)
-{
-	filemap_t  *map = filemap;
-
-	filemap_list_to_array(map);
-	qsort(map->array, map->narray, sizeof(file_entry_t *),
-		  final_filemap_cmp);
-}
-
 static const char *
 action_to_str(file_action_t action)
 {
@@ -643,26 +512,26 @@ calculate_totals(void)
 	{
 		entry = map->array[i];
 
-		if (entry->type != FILE_TYPE_REGULAR)
+		if (entry->source_type != FILE_TYPE_REGULAR)
 			continue;
 
-		map->total_size += entry->newsize;
+		map->total_size += entry->source_size;
 
 		if (entry->action == FILE_ACTION_COPY)
 		{
-			map->fetch_size += entry->newsize;
+			map->fetch_size += entry->source_size;
 			continue;
 		}
 
 		if (entry->action == FILE_ACTION_COPY_TAIL)
-			map->fetch_size += (entry->newsize - entry->oldsize);
+			map->fetch_size += (entry->source_size - entry->target_size);
 
-		if (entry->pagemap.bitmapsize > 0)
+		if (entry->target_modified_pages.bitmapsize > 0)
 		{
 			datapagemap_iterator_t *iter;
 			BlockNumber blk;
 
-			iter = datapagemap_iterate(&entry->pagemap);
+			iter = datapagemap_iterate(&entry->target_modified_pages);
 			while (datapagemap_next(iter, &blk))
 				map->fetch_size += BLCKSZ;
 
@@ -682,13 +551,13 @@ print_filemap(void)
 	{
 		entry = map->array[i];
 		if (entry->action != FILE_ACTION_NONE ||
-			entry->pagemap.bitmapsize > 0)
+			entry->target_modified_pages.bitmapsize > 0)
 		{
 			pg_log_debug("%s (%s)", entry->path,
 						 action_to_str(entry->action));
 
-			if (entry->pagemap.bitmapsize > 0)
-				datapagemap_print(&entry->pagemap);
+			if (entry->target_modified_pages.bitmapsize > 0)
+				datapagemap_print(&entry->target_modified_pages);
 		}
 	}
 	fflush(stdout);
@@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b)
 	else
 		return strcmp(fa->path, fb->path);
 }
+
+/*
+ * Decide what to do with each file.
+ */
+void
+filemap_finalize()
+{
+	int			i;
+
+	filemap_list_to_array(filemap);
+
+	for (i = 0; i < filemap->narray; i++)
+	{
+		file_entry_t *entry = filemap->array[i];
+		file_action_t action;
+
+		if (!entry->target_exists && entry->source_exists)
+		{
+			/*
+			 * File exists in source, but not in target. Copy
+			 * it in toto. (If it's a relation data file, WAL replay
+			 * after rewinding should re-create it anyway. But there's
+			 * no harm in copying it now.)
+			 */
+			if (entry->source_type == FILE_TYPE_DIRECTORY ||
+				entry->source_type == FILE_TYPE_SYMLINK)
+			{
+				action = FILE_ACTION_CREATE;
+			}
+			else
+				action = FILE_ACTION_COPY;
+		}
+		else if (entry->target_exists && !entry->source_exists)
+		{
+			/* Delete file from target */
+			action = FILE_ACTION_REMOVE;
+		}
+		else if (entry->target_exists && entry->source_exists)
+		{
+			/* File exists in both systems */
+			if (entry->source_type != entry->target_type)
+			{
+				/* But it's a different kind of object. Strange.. */
+				pg_fatal("file \"%s\" is of different type in source and target", entry->path);
+			}
+
+			switch (entry->source_type)
+			{
+				case FILE_TYPE_DIRECTORY:
+					action = FILE_ACTION_NONE;
+					break;
+
+				case FILE_TYPE_SYMLINK:
+					// FIXME: Check if it points to the same target?
+					action = FILE_ACTION_NONE;
+					break;
+
+				case FILE_TYPE_REGULAR:
+					if (!entry->isrelfile)
+					{
+						/*
+						 * It's a non-data file that we have no special processing for. Copy
+						 * it in toto.
+						 *
+						 * An exception: PG_VERSIONs should be identical, but avoid
+						 * overwriting it for paranoia.
+						 */
+						if (!pg_str_endswith(entry->path, "PG_VERSION"))
+							action = FILE_ACTION_COPY;
+						else
+							action = FILE_ACTION_NONE;
+					}
+					else
+					{
+						/*
+						 * It's a data file that exists in both systems.
+						 *
+						 * If it's larger in target, we can truncate it. There will
+						 * also be a WAL record of the truncation in the source
+						 * system, so WAL replay would eventually truncate the target
+						 * too, but we might as well do it now.
+						 *
+						 * If it's smaller in the target, it means that it has been
+						 * truncated in the target, or enlarged in the source, or
+						 * both. If it was truncated in the target, we need to copy
+						 * the missing tail from the source system. If it was enlarged
+						 * in the source system, there will be WAL records in the
+						 * source system for the new blocks, so we wouldn't need to
+						 * copy them here. But we don't know which scenario we're
+						 * dealing with, and there's no harm in copying the missing
+						 * blocks now, so do it now.
+						 *
+						 * If it's the same size, do nothing here. Any blocks modified
+						 * in the target will be copied based on parsing the target
+						 * system's WAL, and any blocks modified in the source will be
+						 * updated after rewinding, when the source system's WAL is
+						 * replayed.
+						 */
+						if (entry->target_size < entry->source_size)
+							action = FILE_ACTION_COPY_TAIL;
+						else if (entry->target_size > entry->source_size)
+							action = FILE_ACTION_TRUNCATE;
+						else
+							action = FILE_ACTION_NONE;
+					}
+					break;
+				case FILE_TYPE_UNDEFINED:
+					pg_fatal("unknown file type for \"%s\"", entry->path);
+					break;
+			}
+		}
+		else
+		{
+			/* Doesn't exist in either server. Why does it have an entry at all?? */
+			action = FILE_ACTION_NONE;
+		}
+		entry->action = action;
+	}
+
+	/* Sort the actions to the order that they should be performed */
+	qsort(filemap->array, filemap->narray, sizeof(file_entry_t *),
+		  final_filemap_cmp);
+}
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 0cb7425170c..a5e8df57f40 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -14,17 +14,21 @@
 
 /*
  * For every file found in the local or remote system, we have a file entry
- * which says what we are going to do with the file. For relation files,
- * there is also a page map, marking pages in the file that were changed
- * locally.
- *
- * The enum values are sorted in the order we want actions to be processed.
+ * that contains information about the file on both systems.  For relation
+ * files, there is also a page map that marks pages in the file that were
+ * changed in the target after the last common checkpoint.  Each entry also
+ * contains an 'action' field, which says what we are going to do with the
+ * file.
  */
+
+/* these enum values are sorted in the order we want actions to be processed */
 typedef enum
 {
+	FILE_ACTION_UNDECIDED = 0,	/* not decided yet */
+
 	FILE_ACTION_CREATE,			/* create local directory or symbolic link */
 	FILE_ACTION_COPY,			/* copy whole file, overwriting if exists */
-	FILE_ACTION_COPY_TAIL,		/* copy tail from 'oldsize' to 'newsize' */
+	FILE_ACTION_COPY_TAIL,		/* copy tail from 'source_size' to 'target_size' */
 	FILE_ACTION_NONE,			/* no action (we might still copy modified
 								 * blocks based on the parsed WAL) */
 	FILE_ACTION_TRUNCATE,		/* truncate local file to 'newsize' bytes */
@@ -33,6 +37,8 @@ typedef enum
 
 typedef enum
 {
+	FILE_TYPE_UNDEFINED = 0,
+
 	FILE_TYPE_REGULAR,
 	FILE_TYPE_DIRECTORY,
 	FILE_TYPE_SYMLINK
@@ -41,19 +47,30 @@ typedef enum
 typedef struct file_entry_t
 {
 	char	   *path;
-	file_type_t type;
+	bool		isrelfile;		/* is it a relation data file? */
 
-	file_action_t action;
+	/*
+	 * Status of the file in the target.
+	 */
+	bool		target_exists;
+	file_type_t target_type;
+	size_t		target_size; /* for a regular file */
+	char	   *target_link_target; /* for a symlink */
 
-	/* for a regular file */
-	size_t		oldsize;
-	size_t		newsize;
-	bool		isrelfile;		/* is it a relation data file? */
+	datapagemap_t target_modified_pages;
 
-	datapagemap_t pagemap;
+	/*
+	 * Status of the file in the source.
+	 */
+	bool		source_exists;
+	file_type_t source_type;
+	size_t		source_size;
+	char	   *source_link_target; /* for a symlink */
 
-	/* for a symlink */
-	char	   *link_target;
+	/*
+	 * What will we do to the file?
+	 */
+	file_action_t action;
 
 	struct file_entry_t *next;
 } file_entry_t;
@@ -70,20 +87,19 @@ typedef struct filemap_t
 
 	/*
 	 * After processing all the remote files, the entries in the linked list
-	 * are moved to this array. After processing local files, too, all the
+	 * are moved to this array.  After processing local files, too, all the
 	 * local entries are added to the array by filemap_finalize, and sorted in
-	 * the final order. After filemap_finalize, all the entries are in the
+	 * the final order.  After filemap_finalize, all the entries are in the
 	 * array, and the linked list is empty.
 	 */
 	file_entry_t **array;
 	int			narray;			/* current length of array */
 
 	/*
-	 * Summary information. total_size is the total size of the source
-	 * cluster, and fetch_size is the number of bytes that needs to be copied.
+	 * Summary information.
 	 */
-	uint64		total_size;
-	uint64		fetch_size;
+	uint64		total_size;		/* total size of the source cluster */
+	uint64		fetch_size;		/* number of bytes that needs to be copied */
 } filemap_t;
 
 extern filemap_t *filemap;
@@ -94,11 +110,12 @@ extern void print_filemap(void);
 
 /* Functions for populating the filemap */
 extern void process_source_file(const char *path, file_type_t type,
-								size_t newsize, const char *link_target);
+								size_t size, const char *link_target);
 extern void process_target_file(const char *path, file_type_t type,
-								size_t newsize, const char *link_target);
-extern void process_block_change(ForkNumber forknum, RelFileNode rnode,
-								 BlockNumber blkno);
+								size_t size, const char *link_target);
+extern void process_target_wal_block_change(ForkNumber forknum,
+											RelFileNode rnode,
+											BlockNumber blkno);
 extern void filemap_finalize(void);
 
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c
index bf4dfc23b96..7fc9161b8c8 100644
--- a/src/bin/pg_rewind/libpq_fetch.c
+++ b/src/bin/pg_rewind/libpq_fetch.c
@@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map)
 		entry = map->array[i];
 
 		/* If this is a relation file, copy the modified blocks */
-		execute_pagemap(&entry->pagemap, entry->path);
+		execute_pagemap(&entry->target_modified_pages, entry->path);
 
 		switch (entry->action)
 		{
@@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map)
 			case FILE_ACTION_COPY:
 				/* Truncate the old file out of the way, if any */
 				open_target_file(entry->path, true);
-				fetch_file_range(entry->path, 0, entry->newsize);
+				fetch_file_range(entry->path, 0, entry->source_size);
 				break;
 
 			case FILE_ACTION_TRUNCATE:
-				truncate_target_file(entry->path, entry->newsize);
+				truncate_target_file(entry->path, entry->source_size);
 				break;
 
 			case FILE_ACTION_COPY_TAIL:
-				fetch_file_range(entry->path, entry->oldsize, entry->newsize);
+				fetch_file_range(entry->path, entry->target_size, entry->source_size);
 				break;
 
 			case FILE_ACTION_REMOVE:
@@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map)
 			case FILE_ACTION_CREATE:
 				create_target(entry);
 				break;
+
+			case FILE_ACTION_UNDECIDED:
+				pg_fatal("no action decided for \"%s\"", entry->path);
+				break;
 		}
 	}
 
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 2229c86f9af..2baeb74ae93 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record)
 		if (forknum != MAIN_FORKNUM)
 			continue;
 
-		process_block_change(forknum, rnode, blkno);
+		process_target_wal_block_change(forknum, rnode, blkno);
 	}
 }
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index c9b9e480c0f..210984d302b 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -369,7 +369,7 @@ main(int argc, char **argv)
 				chkpttli);
 
 	/*
-	 * Build the filemap, by comparing the source and target data directories.
+	 * Collect information about all files in the target and source systems.
 	 */
 	filemap_create();
 	if (showprogress)
@@ -390,8 +390,12 @@ main(int argc, char **argv)
 		pg_log_info("reading WAL in target");
 	extractPageMap(datadir_target, chkptrec, lastcommontliIndex,
 				   ControlFile_target.checkPoint, restore_command);
-	filemap_finalize();
 
+	/*
+	 * We have collected all information we need from both systems. Decide
+	 * what to do with each file.
+	 */
+	filemap_finalize();
 	if (showprogress)
 		calculate_totals();
 
-- 
2.20.1


--------------D93EDEBFB124D563B723F4BD
Content-Type: text/x-patch; charset=UTF-8;
 name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa";
 filename*1="tch"



^ permalink  raw  reply  [nested|flat] 5+ messages in thread

* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making.
@ 2020-08-19 12:34 Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 5+ messages in thread

From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw)

Deciding what to do with each file is now a separate step after all the
necessary information has been gathered. It is more clear that way.
Previously, the decision-making was divided between process_source_file()
and process_target_file(), and it was a bit hard to piece together what the
overall rules were.
---
 src/bin/pg_rewind/copy_fetch.c  |  14 +-
 src/bin/pg_rewind/file_ops.c    |  16 +-
 src/bin/pg_rewind/filemap.c     | 569 ++++++++++++++++----------------
 src/bin/pg_rewind/filemap.h     |  67 ++--
 src/bin/pg_rewind/libpq_fetch.c |  12 +-
 src/bin/pg_rewind/parsexlog.c   |   2 +-
 src/bin/pg_rewind/pg_rewind.c   |   8 +-
 7 files changed, 371 insertions(+), 317 deletions(-)

diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c
index 1edab5f1867..18fad32600e 100644
--- a/src/bin/pg_rewind/copy_fetch.c
+++ b/src/bin/pg_rewind/copy_fetch.c
@@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map)
 	for (i = 0; i < map->narray; i++)
 	{
 		entry = map->array[i];
-		execute_pagemap(&entry->pagemap, entry->path);
+		execute_pagemap(&entry->target_modified_pages, entry->path);
 
 		switch (entry->action)
 		{
@@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map)
 				break;
 
 			case FILE_ACTION_COPY:
-				rewind_copy_file_range(entry->path, 0, entry->newsize, true);
+				rewind_copy_file_range(entry->path, 0, entry->source_size, true);
 				break;
 
 			case FILE_ACTION_TRUNCATE:
-				truncate_target_file(entry->path, entry->newsize);
+				truncate_target_file(entry->path, entry->source_size);
 				break;
 
 			case FILE_ACTION_COPY_TAIL:
-				rewind_copy_file_range(entry->path, entry->oldsize,
-									   entry->newsize, false);
+				rewind_copy_file_range(entry->path, entry->target_size,
+									   entry->source_size, false);
 				break;
 
 			case FILE_ACTION_CREATE:
@@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map)
 			case FILE_ACTION_REMOVE:
 				remove_target(entry);
 				break;
+
+			case FILE_ACTION_UNDECIDED:
+				pg_fatal("no action decided for \"%s\"", entry->path);
+				break;
 		}
 	}
 
diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c
index 55439db20ba..ec37d0b2e0d 100644
--- a/src/bin/pg_rewind/file_ops.c
+++ b/src/bin/pg_rewind/file_ops.c
@@ -126,8 +126,9 @@ void
 remove_target(file_entry_t *entry)
 {
 	Assert(entry->action == FILE_ACTION_REMOVE);
+	Assert(entry->target_exists);
 
-	switch (entry->type)
+	switch (entry->target_type)
 	{
 		case FILE_TYPE_DIRECTORY:
 			remove_target_dir(entry->path);
@@ -140,6 +141,10 @@ remove_target(file_entry_t *entry)
 		case FILE_TYPE_SYMLINK:
 			remove_target_symlink(entry->path);
 			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("undefined file type for \"%s\"", entry->path);
+			break;
 	}
 }
 
@@ -147,21 +152,26 @@ void
 create_target(file_entry_t *entry)
 {
 	Assert(entry->action == FILE_ACTION_CREATE);
+	Assert(!entry->target_exists);
 
-	switch (entry->type)
+	switch (entry->source_type)
 	{
 		case FILE_TYPE_DIRECTORY:
 			create_target_dir(entry->path);
 			break;
 
 		case FILE_TYPE_SYMLINK:
-			create_target_symlink(entry->path, entry->link_target);
+			create_target_symlink(entry->path, entry->source_link_target);
 			break;
 
 		case FILE_TYPE_REGULAR:
 			/* can't happen. Regular files are created with open_target_file. */
 			pg_fatal("invalid action (CREATE) for regular file");
 			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("undefined file type for \"%s\"", entry->path);
+			break;
 	}
 }
 
diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 1879257b66a..7971daeda5e 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path);
 static char *datasegpath(RelFileNode rnode, ForkNumber forknum,
 						 BlockNumber segno);
 static int	path_cmp(const void *a, const void *b);
+
+static file_entry_t *get_filemap_entry(const char *path, bool create);
 static int	final_filemap_cmp(const void *a, const void *b);
 static void filemap_list_to_array(filemap_t *map);
 static bool check_file_excluded(const char *path, bool is_source);
@@ -146,6 +148,65 @@ filemap_create(void)
 	filemap = map;
 }
 
+/* Look up or create entry for 'path' */
+static file_entry_t *
+get_filemap_entry(const char *path, bool create)
+{
+	filemap_t  *map = filemap;
+	file_entry_t *entry;
+	file_entry_t **e;
+	file_entry_t key;
+	file_entry_t *key_ptr;
+
+	if (map->array)
+	{
+		key.path = (char *) path;
+		key_ptr = &key;
+		e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
+					path_cmp);
+	}
+	else
+		e = NULL;
+
+	if (e)
+		entry = *e;
+	else if (!create)
+		entry = NULL;
+	else
+	{
+		/* Create a new entry for this file */
+		entry = pg_malloc(sizeof(file_entry_t));
+		entry->path = pg_strdup(path);
+		entry->isrelfile = isRelDataFile(path);
+		entry->action = FILE_ACTION_UNDECIDED;
+
+		entry->target_exists = false;
+		entry->target_type = FILE_TYPE_UNDEFINED;
+		entry->target_size = 0;
+		entry->target_link_target = NULL;
+		entry->target_modified_pages.bitmap = NULL;
+		entry->target_modified_pages.bitmapsize = 0;
+
+		entry->source_exists = false;
+		entry->source_type = FILE_TYPE_UNDEFINED;
+		entry->source_size = 0;
+		entry->source_link_target = NULL;
+
+		entry->next = NULL;
+
+		if (map->last)
+		{
+			map->last->next = entry;
+			map->last = entry;
+		}
+		else
+			map->first = map->last = entry;
+		map->nlist++;
+	}
+
+	return entry;
+}
+
 /*
  * Callback for processing source file list.
  *
@@ -154,25 +215,12 @@ filemap_create(void)
  * exists in the target and whether the size matches.
  */
 void
-process_source_file(const char *path, file_type_t type, size_t newsize,
+process_source_file(const char *path, file_type_t type, size_t size,
 					const char *link_target)
 {
-	bool		exists;
-	char		localpath[MAXPGPATH];
-	struct stat statbuf;
-	filemap_t  *map = filemap;
-	file_action_t action = FILE_ACTION_NONE;
-	size_t		oldsize = 0;
 	file_entry_t *entry;
 
-	Assert(map->array == NULL);
-
-	/*
-	 * Skip any files matching the exclusion filters. This has the effect to
-	 * remove all those files on the target.
-	 */
-	if (check_file_excluded(path, true))
-		return;
+	Assert(filemap->array == NULL);
 
 	/*
 	 * Pretend that pg_wal is a directory, even if it's really a symlink. We
@@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
 	if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK)
 		type = FILE_TYPE_DIRECTORY;
 
-	/*
-	 * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source.
-	 * This has the effect that all temporary files in the destination will be
-	 * removed.
-	 */
-	if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL)
-		return;
-	if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL)
-		return;
-
 	/*
 	 * sanity check: a filename that looks like a data file better be a
 	 * regular file
@@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
 	if (type != FILE_TYPE_REGULAR && isRelDataFile(path))
 		pg_fatal("data file \"%s\" in source is not a regular file", path);
 
-	snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path);
-
-	/* Does the corresponding file exist in the target data dir? */
-	if (lstat(localpath, &statbuf) < 0)
-	{
-		if (errno != ENOENT)
-			pg_fatal("could not stat file \"%s\": %m",
-					 localpath);
-
-		exists = false;
-	}
-	else
-		exists = true;
-
-	switch (type)
-	{
-		case FILE_TYPE_DIRECTORY:
-			if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0)
-			{
-				/* it's a directory in source, but not in target. Strange.. */
-				pg_fatal("\"%s\" is not a directory", localpath);
-			}
-
-			if (!exists)
-				action = FILE_ACTION_CREATE;
-			else
-				action = FILE_ACTION_NONE;
-			oldsize = 0;
-			break;
-
-		case FILE_TYPE_SYMLINK:
-			if (exists &&
-#ifndef WIN32
-				!S_ISLNK(statbuf.st_mode)
-#else
-				!pgwin32_is_junction(localpath)
-#endif
-				)
-			{
-				/*
-				 * It's a symbolic link in source, but not in target.
-				 * Strange..
-				 */
-				pg_fatal("\"%s\" is not a symbolic link", localpath);
-			}
-
-			if (!exists)
-				action = FILE_ACTION_CREATE;
-			else
-				action = FILE_ACTION_NONE;
-			oldsize = 0;
-			break;
-
-		case FILE_TYPE_REGULAR:
-			if (exists && !S_ISREG(statbuf.st_mode))
-				pg_fatal("\"%s\" is not a regular file", localpath);
-
-			if (!exists || !isRelDataFile(path))
-			{
-				/*
-				 * File exists in source, but not in target. Or it's a
-				 * non-data file that we have no special processing for. Copy
-				 * it in toto.
-				 *
-				 * An exception: PG_VERSIONs should be identical, but avoid
-				 * overwriting it for paranoia.
-				 */
-				if (pg_str_endswith(path, "PG_VERSION"))
-				{
-					action = FILE_ACTION_NONE;
-					oldsize = statbuf.st_size;
-				}
-				else
-				{
-					action = FILE_ACTION_COPY;
-					oldsize = 0;
-				}
-			}
-			else
-			{
-				/*
-				 * It's a data file that exists in both.
-				 *
-				 * If it's larger in target, we can truncate it. There will
-				 * also be a WAL record of the truncation in the source
-				 * system, so WAL replay would eventually truncate the target
-				 * too, but we might as well do it now.
-				 *
-				 * If it's smaller in the target, it means that it has been
-				 * truncated in the target, or enlarged in the source, or
-				 * both. If it was truncated in the target, we need to copy
-				 * the missing tail from the source system. If it was enlarged
-				 * in the source system, there will be WAL records in the
-				 * source system for the new blocks, so we wouldn't need to
-				 * copy them here. But we don't know which scenario we're
-				 * dealing with, and there's no harm in copying the missing
-				 * blocks now, so do it now.
-				 *
-				 * If it's the same size, do nothing here. Any blocks modified
-				 * in the target will be copied based on parsing the target
-				 * system's WAL, and any blocks modified in the source will be
-				 * updated after rewinding, when the source system's WAL is
-				 * replayed.
-				 */
-				oldsize = statbuf.st_size;
-				if (oldsize < newsize)
-					action = FILE_ACTION_COPY_TAIL;
-				else if (oldsize > newsize)
-					action = FILE_ACTION_TRUNCATE;
-				else
-					action = FILE_ACTION_NONE;
-			}
-			break;
-	}
-
-	/* Create a new entry for this file */
-	entry = pg_malloc(sizeof(file_entry_t));
-	entry->path = pg_strdup(path);
-	entry->type = type;
-	entry->action = action;
-	entry->oldsize = oldsize;
-	entry->newsize = newsize;
-	entry->link_target = link_target ? pg_strdup(link_target) : NULL;
-	entry->next = NULL;
-	entry->pagemap.bitmap = NULL;
-	entry->pagemap.bitmapsize = 0;
-	entry->isrelfile = isRelDataFile(path);
-
-	if (map->last)
-	{
-		map->last->next = entry;
-		map->last = entry;
-	}
-	else
-		map->first = map->last = entry;
-	map->nlist++;
+	/* Remember this source file */
+	entry = get_filemap_entry(path, true);
+	entry->source_exists = true;
+	entry->source_type = type;
+	entry->source_size = size;
+	entry->source_link_target = link_target ? pg_strdup(link_target) : NULL;
 }
 
 /*
@@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
  * deletion.
  */
 void
-process_target_file(const char *path, file_type_t type, size_t oldsize,
+process_target_file(const char *path, file_type_t type, size_t size,
 					const char *link_target)
 {
-	bool		exists;
-	char		localpath[MAXPGPATH];
-	struct stat statbuf;
-	file_entry_t key;
-	file_entry_t *key_ptr;
 	filemap_t  *map = filemap;
 	file_entry_t *entry;
 
@@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize,
 	 * from the target data folder all paths which have been filtered out from
 	 * the source data folder when processing the source files.
 	 */
-
-	snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path);
-	if (lstat(localpath, &statbuf) < 0)
-	{
-		if (errno != ENOENT)
-			pg_fatal("could not stat file \"%s\": %m",
-					 localpath);
-
-		exists = false;
-	}
-
 	if (map->array == NULL)
 	{
 		/* on first call, initialize lookup array */
@@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize,
 	}
 
 	/*
-	 * Like in process_source_file, pretend that xlog is always a  directory.
+	 * Like in process_source_file, pretend that pg_wal is always a directory.
 	 */
 	if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK)
 		type = FILE_TYPE_DIRECTORY;
 
-	key.path = (char *) path;
-	key_ptr = &key;
-	exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
-					  path_cmp) != NULL);
-
-	/* Remove any file or folder that doesn't exist in the source system. */
-	if (!exists)
-	{
-		entry = pg_malloc(sizeof(file_entry_t));
-		entry->path = pg_strdup(path);
-		entry->type = type;
-		entry->action = FILE_ACTION_REMOVE;
-		entry->oldsize = oldsize;
-		entry->newsize = 0;
-		entry->link_target = link_target ? pg_strdup(link_target) : NULL;
-		entry->next = NULL;
-		entry->pagemap.bitmap = NULL;
-		entry->pagemap.bitmapsize = 0;
-		entry->isrelfile = isRelDataFile(path);
-
-		if (map->last == NULL)
-			map->first = entry;
-		else
-			map->last->next = entry;
-		map->last = entry;
-		map->nlist++;
-	}
-	else
-	{
-		/*
-		 * We already handled all files that exist in the source system in
-		 * process_source_file().
-		 */
-	}
+	/* Remember this target file */
+	entry = get_filemap_entry(path, true);
+	entry->target_exists = true;
+	entry->target_type = type;
+	entry->target_size = size;
+	entry->target_link_target = link_target ? pg_strdup(link_target) : NULL;
 }
 
 /*
  * This callback gets called while we read the WAL in the target, for every
- * block that have changed in the target system. It makes note of all the
+ * block that have changed in the target system.  It makes note of all the
  * changed blocks in the pagemap of the file.
+ *
+ * NOTE: All the files on both systems must have already been added to the
+ * file map!
  */
 void
-process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno)
+process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode,
+								BlockNumber blkno)
 {
 	char	   *path;
-	file_entry_t key;
-	file_entry_t *key_ptr;
 	file_entry_t *entry;
 	BlockNumber blkno_inseg;
 	int			segno;
-	filemap_t  *map = filemap;
-	file_entry_t **e;
 
-	Assert(map->array);
+	Assert(filemap->array);
 
 	segno = blkno / RELSEG_SIZE;
 	blkno_inseg = blkno % RELSEG_SIZE;
 
 	path = datasegpath(rnode, forknum, segno);
-
-	key.path = (char *) path;
-	key_ptr = &key;
-
-	e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
-				path_cmp);
-	if (e)
-		entry = *e;
-	else
-		entry = NULL;
+	entry = get_filemap_entry(path, false);
 	pfree(path);
 
 	if (entry)
 	{
-		Assert(entry->isrelfile);
-
-		switch (entry->action)
-		{
-			case FILE_ACTION_NONE:
-			case FILE_ACTION_TRUNCATE:
-				/* skip if we're truncating away the modified block anyway */
-				if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize)
-					datapagemap_add(&entry->pagemap, blkno_inseg);
-				break;
+		int64		end_offset;
 
-			case FILE_ACTION_COPY_TAIL:
-
-				/*
-				 * skip the modified block if it is part of the "tail" that
-				 * we're copying anyway.
-				 */
-				if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize)
-					datapagemap_add(&entry->pagemap, blkno_inseg);
-				break;
+		Assert(entry->isrelfile);
 
-			case FILE_ACTION_COPY:
-			case FILE_ACTION_REMOVE:
-				break;
+		if (entry->target_type != FILE_TYPE_REGULAR)
+			pg_fatal("unexpected page modification for directory or symbolic link \"%s\"",
+					 entry->path);
 
-			case FILE_ACTION_CREATE:
-				pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path);
-		}
+		/*
+		 * If the block beyond the EOF in the source system, no need to
+		 * remember it now, because we're going to truncate it away from the
+		 * target anyway. Also no need to remember the block if it's beyond
+		 * the current EOF in the target system; we will copy it over with the
+		 * "tail" from the source system, anyway.
+		 */
+		end_offset = (blkno_inseg + 1) * BLCKSZ;
+		if (end_offset <= entry->source_size &&
+			end_offset <= entry->target_size)
+			datapagemap_add(&entry->target_modified_pages, blkno_inseg);
 	}
 	else
 	{
 		/*
 		 * If we don't have any record of this file in the file map, it means
-		 * that it's a relation that doesn't exist in the source system, and
-		 * it was subsequently removed in the target system, too. We can
-		 * safely ignore it.
+		 * that it's a relation that doesn't exist in the source system.  It
+		 * could exist in the target system; we haven't moved the target-only
+		 * entries from the linked list to the array yet!  But in any case, if
+		 * it doesn't exist in the source it will be removed from the target
+		 * too, and we can safely ignore it.
 		 */
 	}
 }
@@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map)
 	map->first = map->last = NULL;
 }
 
-void
-filemap_finalize(void)
-{
-	filemap_t  *map = filemap;
-
-	filemap_list_to_array(map);
-	qsort(map->array, map->narray, sizeof(file_entry_t *),
-		  final_filemap_cmp);
-}
-
 static const char *
 action_to_str(file_action_t action)
 {
@@ -643,26 +481,26 @@ calculate_totals(void)
 	{
 		entry = map->array[i];
 
-		if (entry->type != FILE_TYPE_REGULAR)
+		if (entry->source_type != FILE_TYPE_REGULAR)
 			continue;
 
-		map->total_size += entry->newsize;
+		map->total_size += entry->source_size;
 
 		if (entry->action == FILE_ACTION_COPY)
 		{
-			map->fetch_size += entry->newsize;
+			map->fetch_size += entry->source_size;
 			continue;
 		}
 
 		if (entry->action == FILE_ACTION_COPY_TAIL)
-			map->fetch_size += (entry->newsize - entry->oldsize);
+			map->fetch_size += (entry->source_size - entry->target_size);
 
-		if (entry->pagemap.bitmapsize > 0)
+		if (entry->target_modified_pages.bitmapsize > 0)
 		{
 			datapagemap_iterator_t *iter;
 			BlockNumber blk;
 
-			iter = datapagemap_iterate(&entry->pagemap);
+			iter = datapagemap_iterate(&entry->target_modified_pages);
 			while (datapagemap_next(iter, &blk))
 				map->fetch_size += BLCKSZ;
 
@@ -682,13 +520,13 @@ print_filemap(void)
 	{
 		entry = map->array[i];
 		if (entry->action != FILE_ACTION_NONE ||
-			entry->pagemap.bitmapsize > 0)
+			entry->target_modified_pages.bitmapsize > 0)
 		{
 			pg_log_debug("%s (%s)", entry->path,
 						 action_to_str(entry->action));
 
-			if (entry->pagemap.bitmapsize > 0)
-				datapagemap_print(&entry->pagemap);
+			if (entry->target_modified_pages.bitmapsize > 0)
+				datapagemap_print(&entry->target_modified_pages);
 		}
 	}
 	fflush(stdout);
@@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b)
 	else
 		return strcmp(fa->path, fb->path);
 }
+
+/*
+ * Decide what action to perform to a file.
+ */
+static file_action_t
+decide_file_action(file_entry_t *entry)
+{
+	const char *path = entry->path;
+
+	/*
+	 * Don't touch the control file. It is handled specially, after copying
+	 * all the other files.
+	 */
+	if (strcmp(path, "global/pg_control") == 0)
+		return FILE_ACTION_NONE;
+
+	/*
+	 * Remove all files matching the exclusion filters in the target.
+	 */
+	if (check_file_excluded(path, true))
+	{
+		if (entry->target_exists)
+			return FILE_ACTION_REMOVE;
+		else
+			return FILE_ACTION_NONE;
+	}
+
+	/*
+	 * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.*
+	 * in the target.
+	 */
+	if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL ||
+		strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL)
+	{
+		if (entry->target_exists)
+			return FILE_ACTION_REMOVE;
+		else
+			return FILE_ACTION_NONE;
+	}
+
+	/*
+	 * Handle cases where the file is missing from one of the systems.
+	 */
+	if (!entry->target_exists && entry->source_exists)
+	{
+		/*
+		 * File exists in source, but not in target. Copy it in toto. (If it's
+		 * a relation data file, WAL replay after rewinding should re-create
+		 * it anyway. But there's no harm in copying it now.)
+		 */
+		switch (entry->source_type)
+		{
+			case FILE_TYPE_DIRECTORY:
+			case FILE_TYPE_SYMLINK:
+				return FILE_ACTION_CREATE;
+			case FILE_TYPE_REGULAR:
+				return FILE_ACTION_COPY;
+			case FILE_TYPE_UNDEFINED:
+				pg_fatal("unknown file type for \"%s\"", entry->path);
+				break;
+		}
+	}
+	else if (entry->target_exists && !entry->source_exists)
+	{
+		/* File exists in target, but not source. Remove it. */
+		return FILE_ACTION_REMOVE;
+	}
+	else if (!entry->target_exists && !entry->source_exists)
+	{
+		/*
+		 * Doesn't exist in either server. Why does it have an entry in the
+		 * first place??
+		 */
+		return FILE_ACTION_NONE;
+	}
+
+	/*
+	 * Otherwise, the file exists on both systems
+	 */
+	Assert(entry->target_exists && entry->source_exists);
+
+	if (entry->source_type != entry->target_type)
+	{
+		/* But it's a different kind of object. Strange.. */
+		pg_fatal("file \"%s\" is of different type in source and target", entry->path);
+	}
+
+	/*
+	 * PG_VERSION files should be identical on both systems, but avoid
+	 * overwriting them for paranoia.
+	 */
+	if (pg_str_endswith(entry->path, "PG_VERSION"))
+		return FILE_ACTION_NONE;
+
+	switch (entry->source_type)
+	{
+		case FILE_TYPE_DIRECTORY:
+			return FILE_ACTION_NONE;
+
+		case FILE_TYPE_SYMLINK:
+			/* FIXME: Check if it points to the same target? */
+			return FILE_ACTION_NONE;
+
+		case FILE_TYPE_REGULAR:
+			if (!entry->isrelfile)
+			{
+				/*
+				 * It's a non-data file that we have no special processing
+				 * for. Copy it in toto.
+				 */
+				return FILE_ACTION_COPY;
+			}
+			else
+			{
+				/*
+				 * It's a data file that exists in both systems.
+				 *
+				 * If it's larger in target, we can truncate it. There will
+				 * also be a WAL record of the truncation in the source
+				 * system, so WAL replay would eventually truncate the target
+				 * too, but we might as well do it now.
+				 *
+				 * If it's smaller in the target, it means that it has been
+				 * truncated in the target, or enlarged in the source, or
+				 * both. If it was truncated in the target, we need to copy
+				 * the missing tail from the source system. If it was enlarged
+				 * in the source system, there will be WAL records in the
+				 * source system for the new blocks, so we wouldn't need to
+				 * copy them here. But we don't know which scenario we're
+				 * dealing with, and there's no harm in copying the missing
+				 * blocks now, so do it now.
+				 *
+				 * If it's the same size, do nothing here. Any blocks modified
+				 * in the target will be copied based on parsing the target
+				 * system's WAL, and any blocks modified in the source will be
+				 * updated after rewinding, when the source system's WAL is
+				 * replayed.
+				 */
+				if (entry->target_size < entry->source_size)
+					return FILE_ACTION_COPY_TAIL;
+				else if (entry->target_size > entry->source_size)
+					return FILE_ACTION_TRUNCATE;
+				else
+					return FILE_ACTION_NONE;
+			}
+			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("unknown file type for \"%s\"", path);
+			break;
+	}
+
+	/* unreachable */
+	pg_fatal("could not decide what to do with file \"%s\"", path);
+}
+
+/*
+ * Decide what to do with each file.
+ */
+void
+filemap_finalize()
+{
+	int			i;
+
+	filemap_list_to_array(filemap);
+
+	for (i = 0; i < filemap->narray; i++)
+	{
+		file_entry_t *entry = filemap->array[i];
+
+		entry->action = decide_file_action(entry);
+	}
+
+	/* Sort the actions to the order that they should be performed */
+	qsort(filemap->array, filemap->narray, sizeof(file_entry_t *),
+		  final_filemap_cmp);
+}
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 0cb7425170c..a5e8df57f40 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -14,17 +14,21 @@
 
 /*
  * For every file found in the local or remote system, we have a file entry
- * which says what we are going to do with the file. For relation files,
- * there is also a page map, marking pages in the file that were changed
- * locally.
- *
- * The enum values are sorted in the order we want actions to be processed.
+ * that contains information about the file on both systems.  For relation
+ * files, there is also a page map that marks pages in the file that were
+ * changed in the target after the last common checkpoint.  Each entry also
+ * contains an 'action' field, which says what we are going to do with the
+ * file.
  */
+
+/* these enum values are sorted in the order we want actions to be processed */
 typedef enum
 {
+	FILE_ACTION_UNDECIDED = 0,	/* not decided yet */
+
 	FILE_ACTION_CREATE,			/* create local directory or symbolic link */
 	FILE_ACTION_COPY,			/* copy whole file, overwriting if exists */
-	FILE_ACTION_COPY_TAIL,		/* copy tail from 'oldsize' to 'newsize' */
+	FILE_ACTION_COPY_TAIL,		/* copy tail from 'source_size' to 'target_size' */
 	FILE_ACTION_NONE,			/* no action (we might still copy modified
 								 * blocks based on the parsed WAL) */
 	FILE_ACTION_TRUNCATE,		/* truncate local file to 'newsize' bytes */
@@ -33,6 +37,8 @@ typedef enum
 
 typedef enum
 {
+	FILE_TYPE_UNDEFINED = 0,
+
 	FILE_TYPE_REGULAR,
 	FILE_TYPE_DIRECTORY,
 	FILE_TYPE_SYMLINK
@@ -41,19 +47,30 @@ typedef enum
 typedef struct file_entry_t
 {
 	char	   *path;
-	file_type_t type;
+	bool		isrelfile;		/* is it a relation data file? */
 
-	file_action_t action;
+	/*
+	 * Status of the file in the target.
+	 */
+	bool		target_exists;
+	file_type_t target_type;
+	size_t		target_size; /* for a regular file */
+	char	   *target_link_target; /* for a symlink */
 
-	/* for a regular file */
-	size_t		oldsize;
-	size_t		newsize;
-	bool		isrelfile;		/* is it a relation data file? */
+	datapagemap_t target_modified_pages;
 
-	datapagemap_t pagemap;
+	/*
+	 * Status of the file in the source.
+	 */
+	bool		source_exists;
+	file_type_t source_type;
+	size_t		source_size;
+	char	   *source_link_target; /* for a symlink */
 
-	/* for a symlink */
-	char	   *link_target;
+	/*
+	 * What will we do to the file?
+	 */
+	file_action_t action;
 
 	struct file_entry_t *next;
 } file_entry_t;
@@ -70,20 +87,19 @@ typedef struct filemap_t
 
 	/*
 	 * After processing all the remote files, the entries in the linked list
-	 * are moved to this array. After processing local files, too, all the
+	 * are moved to this array.  After processing local files, too, all the
 	 * local entries are added to the array by filemap_finalize, and sorted in
-	 * the final order. After filemap_finalize, all the entries are in the
+	 * the final order.  After filemap_finalize, all the entries are in the
 	 * array, and the linked list is empty.
 	 */
 	file_entry_t **array;
 	int			narray;			/* current length of array */
 
 	/*
-	 * Summary information. total_size is the total size of the source
-	 * cluster, and fetch_size is the number of bytes that needs to be copied.
+	 * Summary information.
 	 */
-	uint64		total_size;
-	uint64		fetch_size;
+	uint64		total_size;		/* total size of the source cluster */
+	uint64		fetch_size;		/* number of bytes that needs to be copied */
 } filemap_t;
 
 extern filemap_t *filemap;
@@ -94,11 +110,12 @@ extern void print_filemap(void);
 
 /* Functions for populating the filemap */
 extern void process_source_file(const char *path, file_type_t type,
-								size_t newsize, const char *link_target);
+								size_t size, const char *link_target);
 extern void process_target_file(const char *path, file_type_t type,
-								size_t newsize, const char *link_target);
-extern void process_block_change(ForkNumber forknum, RelFileNode rnode,
-								 BlockNumber blkno);
+								size_t size, const char *link_target);
+extern void process_target_wal_block_change(ForkNumber forknum,
+											RelFileNode rnode,
+											BlockNumber blkno);
 extern void filemap_finalize(void);
 
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c
index bf4dfc23b96..7fc9161b8c8 100644
--- a/src/bin/pg_rewind/libpq_fetch.c
+++ b/src/bin/pg_rewind/libpq_fetch.c
@@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map)
 		entry = map->array[i];
 
 		/* If this is a relation file, copy the modified blocks */
-		execute_pagemap(&entry->pagemap, entry->path);
+		execute_pagemap(&entry->target_modified_pages, entry->path);
 
 		switch (entry->action)
 		{
@@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map)
 			case FILE_ACTION_COPY:
 				/* Truncate the old file out of the way, if any */
 				open_target_file(entry->path, true);
-				fetch_file_range(entry->path, 0, entry->newsize);
+				fetch_file_range(entry->path, 0, entry->source_size);
 				break;
 
 			case FILE_ACTION_TRUNCATE:
-				truncate_target_file(entry->path, entry->newsize);
+				truncate_target_file(entry->path, entry->source_size);
 				break;
 
 			case FILE_ACTION_COPY_TAIL:
-				fetch_file_range(entry->path, entry->oldsize, entry->newsize);
+				fetch_file_range(entry->path, entry->target_size, entry->source_size);
 				break;
 
 			case FILE_ACTION_REMOVE:
@@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map)
 			case FILE_ACTION_CREATE:
 				create_target(entry);
 				break;
+
+			case FILE_ACTION_UNDECIDED:
+				pg_fatal("no action decided for \"%s\"", entry->path);
+				break;
 		}
 	}
 
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 2229c86f9af..2baeb74ae93 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record)
 		if (forknum != MAIN_FORKNUM)
 			continue;
 
-		process_block_change(forknum, rnode, blkno);
+		process_target_wal_block_change(forknum, rnode, blkno);
 	}
 }
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index c9b9e480c0f..210984d302b 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -369,7 +369,7 @@ main(int argc, char **argv)
 				chkpttli);
 
 	/*
-	 * Build the filemap, by comparing the source and target data directories.
+	 * Collect information about all files in the target and source systems.
 	 */
 	filemap_create();
 	if (showprogress)
@@ -390,8 +390,12 @@ main(int argc, char **argv)
 		pg_log_info("reading WAL in target");
 	extractPageMap(datadir_target, chkptrec, lastcommontliIndex,
 				   ControlFile_target.checkPoint, restore_command);
-	filemap_finalize();
 
+	/*
+	 * We have collected all information we need from both systems. Decide
+	 * what to do with each file.
+	 */
+	filemap_finalize();
 	if (showprogress)
 		calculate_totals();
 
-- 
2.20.1


--------------BF34D0120055DC3839060F92
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa";
 filename*1="tch"



^ permalink  raw  reply  [nested|flat] 5+ messages in thread

* [PATCH v3 2/5] Refactor pg_rewind for more clear decision making.
@ 2020-09-24 17:08 Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 5+ messages in thread

From: Heikki Linnakangas @ 2020-09-24 17:08 UTC (permalink / raw)

Deciding what to do with each file is now a separate step after all the
necessary information has been gathered. It is more clear that way.
Previously, the decision-making was divided between process_source_file()
and process_target_file(), and it was a bit hard to piece together what the
overall rules were.

Reviewed-by: Kyotaro Horiguchi, Soumyadeep Chakraborty
Discussion: https://www.postgresql.org/message-id/0c5b3783-af52-3ee5-f8fa-6e794061f70d%40iki.fi
---
 src/bin/pg_rewind/copy_fetch.c  |  14 +-
 src/bin/pg_rewind/file_ops.c    |  16 +-
 src/bin/pg_rewind/filemap.c     | 571 +++++++++++++++++---------------
 src/bin/pg_rewind/filemap.h     |  69 ++--
 src/bin/pg_rewind/libpq_fetch.c |  12 +-
 src/bin/pg_rewind/parsexlog.c   |   2 +-
 src/bin/pg_rewind/pg_rewind.c   |   8 +-
 7 files changed, 381 insertions(+), 311 deletions(-)

diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c
index 1edab5f1867..e4b8ce6aaf4 100644
--- a/src/bin/pg_rewind/copy_fetch.c
+++ b/src/bin/pg_rewind/copy_fetch.c
@@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map)
 	for (i = 0; i < map->narray; i++)
 	{
 		entry = map->array[i];
-		execute_pagemap(&entry->pagemap, entry->path);
+		execute_pagemap(&entry->target_pages_to_overwrite, entry->path);
 
 		switch (entry->action)
 		{
@@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map)
 				break;
 
 			case FILE_ACTION_COPY:
-				rewind_copy_file_range(entry->path, 0, entry->newsize, true);
+				rewind_copy_file_range(entry->path, 0, entry->source_size, true);
 				break;
 
 			case FILE_ACTION_TRUNCATE:
-				truncate_target_file(entry->path, entry->newsize);
+				truncate_target_file(entry->path, entry->source_size);
 				break;
 
 			case FILE_ACTION_COPY_TAIL:
-				rewind_copy_file_range(entry->path, entry->oldsize,
-									   entry->newsize, false);
+				rewind_copy_file_range(entry->path, entry->target_size,
+									   entry->source_size, false);
 				break;
 
 			case FILE_ACTION_CREATE:
@@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map)
 			case FILE_ACTION_REMOVE:
 				remove_target(entry);
 				break;
+
+			case FILE_ACTION_UNDECIDED:
+				pg_fatal("no action decided for \"%s\"", entry->path);
+				break;
 		}
 	}
 
diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c
index 55439db20ba..ec37d0b2e0d 100644
--- a/src/bin/pg_rewind/file_ops.c
+++ b/src/bin/pg_rewind/file_ops.c
@@ -126,8 +126,9 @@ void
 remove_target(file_entry_t *entry)
 {
 	Assert(entry->action == FILE_ACTION_REMOVE);
+	Assert(entry->target_exists);
 
-	switch (entry->type)
+	switch (entry->target_type)
 	{
 		case FILE_TYPE_DIRECTORY:
 			remove_target_dir(entry->path);
@@ -140,6 +141,10 @@ remove_target(file_entry_t *entry)
 		case FILE_TYPE_SYMLINK:
 			remove_target_symlink(entry->path);
 			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("undefined file type for \"%s\"", entry->path);
+			break;
 	}
 }
 
@@ -147,21 +152,26 @@ void
 create_target(file_entry_t *entry)
 {
 	Assert(entry->action == FILE_ACTION_CREATE);
+	Assert(!entry->target_exists);
 
-	switch (entry->type)
+	switch (entry->source_type)
 	{
 		case FILE_TYPE_DIRECTORY:
 			create_target_dir(entry->path);
 			break;
 
 		case FILE_TYPE_SYMLINK:
-			create_target_symlink(entry->path, entry->link_target);
+			create_target_symlink(entry->path, entry->source_link_target);
 			break;
 
 		case FILE_TYPE_REGULAR:
 			/* can't happen. Regular files are created with open_target_file. */
 			pg_fatal("invalid action (CREATE) for regular file");
 			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("undefined file type for \"%s\"", entry->path);
+			break;
 	}
 }
 
diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
index 1abc257177e..79e5bfdc7d1 100644
--- a/src/bin/pg_rewind/filemap.c
+++ b/src/bin/pg_rewind/filemap.c
@@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path);
 static char *datasegpath(RelFileNode rnode, ForkNumber forknum,
 						 BlockNumber segno);
 static int	path_cmp(const void *a, const void *b);
+
+static file_entry_t *get_filemap_entry(const char *path, bool create);
 static int	final_filemap_cmp(const void *a, const void *b);
 static void filemap_list_to_array(filemap_t *map);
 static bool check_file_excluded(const char *path, bool is_source);
@@ -146,33 +148,79 @@ filemap_create(void)
 	filemap = map;
 }
 
+/* Look up or create entry for 'path' */
+static file_entry_t *
+get_filemap_entry(const char *path, bool create)
+{
+	filemap_t  *map = filemap;
+	file_entry_t *entry;
+	file_entry_t **e;
+	file_entry_t key;
+	file_entry_t *key_ptr;
+
+	if (map->array)
+	{
+		key.path = (char *) path;
+		key_ptr = &key;
+		e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
+					path_cmp);
+	}
+	else
+		e = NULL;
+
+	if (e)
+		entry = *e;
+	else if (!create)
+		entry = NULL;
+	else
+	{
+		/* Create a new entry for this file */
+		entry = pg_malloc(sizeof(file_entry_t));
+		entry->path = pg_strdup(path);
+		entry->isrelfile = isRelDataFile(path);
+		entry->action = FILE_ACTION_UNDECIDED;
+
+		entry->target_exists = false;
+		entry->target_type = FILE_TYPE_UNDEFINED;
+		entry->target_size = 0;
+		entry->target_link_target = NULL;
+		entry->target_pages_to_overwrite.bitmap = NULL;
+		entry->target_pages_to_overwrite.bitmapsize = 0;
+
+		entry->source_exists = false;
+		entry->source_type = FILE_TYPE_UNDEFINED;
+		entry->source_size = 0;
+		entry->source_link_target = NULL;
+
+		entry->next = NULL;
+
+		if (map->last)
+		{
+			map->last->next = entry;
+			map->last = entry;
+		}
+		else
+			map->first = map->last = entry;
+		map->nlist++;
+	}
+
+	return entry;
+}
+
 /*
  * Callback for processing source file list.
  *
- * This is called once for every file in the source server. We decide what
- * action needs to be taken for the file, depending on whether the file
- * exists in the target and whether the size matches.
+ * This is called once for every file in the source server.  We record the
+ * type and size of file, so that decide_file_action() can later decide what
+ * to do with it.
  */
 void
-process_source_file(const char *path, file_type_t type, size_t newsize,
+process_source_file(const char *path, file_type_t type, size_t size,
 					const char *link_target)
 {
-	bool		exists;
-	char		localpath[MAXPGPATH];
-	struct stat statbuf;
-	filemap_t  *map = filemap;
-	file_action_t action = FILE_ACTION_NONE;
-	size_t		oldsize = 0;
 	file_entry_t *entry;
 
-	Assert(map->array == NULL);
-
-	/*
-	 * Skip any files matching the exclusion filters. This has the effect to
-	 * remove all those files on the target.
-	 */
-	if (check_file_excluded(path, true))
-		return;
+	Assert(filemap->array == NULL);
 
 	/*
 	 * Pretend that pg_wal is a directory, even if it's really a symlink. We
@@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
 	if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK)
 		type = FILE_TYPE_DIRECTORY;
 
-	/*
-	 * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source.
-	 * This has the effect that all temporary files in the destination will be
-	 * removed.
-	 */
-	if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL)
-		return;
-	if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL)
-		return;
-
 	/*
 	 * sanity check: a filename that looks like a data file better be a
 	 * regular file
@@ -199,158 +237,25 @@ process_source_file(const char *path, file_type_t type, size_t newsize,
 	if (type != FILE_TYPE_REGULAR && isRelDataFile(path))
 		pg_fatal("data file \"%s\" in source is not a regular file", path);
 
-	snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path);
-
-	/* Does the corresponding file exist in the target data dir? */
-	if (lstat(localpath, &statbuf) < 0)
-	{
-		if (errno != ENOENT)
-			pg_fatal("could not stat file \"%s\": %m",
-					 localpath);
-
-		exists = false;
-	}
-	else
-		exists = true;
-
-	switch (type)
-	{
-		case FILE_TYPE_DIRECTORY:
-			if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0)
-			{
-				/* it's a directory in source, but not in target. Strange.. */
-				pg_fatal("\"%s\" is not a directory", localpath);
-			}
-
-			if (!exists)
-				action = FILE_ACTION_CREATE;
-			else
-				action = FILE_ACTION_NONE;
-			oldsize = 0;
-			break;
-
-		case FILE_TYPE_SYMLINK:
-			if (exists &&
-#ifndef WIN32
-				!S_ISLNK(statbuf.st_mode)
-#else
-				!pgwin32_is_junction(localpath)
-#endif
-				)
-			{
-				/*
-				 * It's a symbolic link in source, but not in target.
-				 * Strange..
-				 */
-				pg_fatal("\"%s\" is not a symbolic link", localpath);
-			}
-
-			if (!exists)
-				action = FILE_ACTION_CREATE;
-			else
-				action = FILE_ACTION_NONE;
-			oldsize = 0;
-			break;
-
-		case FILE_TYPE_REGULAR:
-			if (exists && !S_ISREG(statbuf.st_mode))
-				pg_fatal("\"%s\" is not a regular file", localpath);
-
-			if (!exists || !isRelDataFile(path))
-			{
-				/*
-				 * File exists in source, but not in target. Or it's a
-				 * non-data file that we have no special processing for. Copy
-				 * it in toto.
-				 *
-				 * An exception: PG_VERSIONs should be identical, but avoid
-				 * overwriting it for paranoia.
-				 */
-				if (pg_str_endswith(path, "PG_VERSION"))
-				{
-					action = FILE_ACTION_NONE;
-					oldsize = statbuf.st_size;
-				}
-				else
-				{
-					action = FILE_ACTION_COPY;
-					oldsize = 0;
-				}
-			}
-			else
-			{
-				/*
-				 * It's a data file that exists in both.
-				 *
-				 * If it's larger in target, we can truncate it. There will
-				 * also be a WAL record of the truncation in the source
-				 * system, so WAL replay would eventually truncate the target
-				 * too, but we might as well do it now.
-				 *
-				 * If it's smaller in the target, it means that it has been
-				 * truncated in the target, or enlarged in the source, or
-				 * both. If it was truncated in the target, we need to copy
-				 * the missing tail from the source system. If it was enlarged
-				 * in the source system, there will be WAL records in the
-				 * source system for the new blocks, so we wouldn't need to
-				 * copy them here. But we don't know which scenario we're
-				 * dealing with, and there's no harm in copying the missing
-				 * blocks now, so do it now.
-				 *
-				 * If it's the same size, do nothing here. Any blocks modified
-				 * in the target will be copied based on parsing the target
-				 * system's WAL, and any blocks modified in the source will be
-				 * updated after rewinding, when the source system's WAL is
-				 * replayed.
-				 */
-				oldsize = statbuf.st_size;
-				if (oldsize < newsize)
-					action = FILE_ACTION_COPY_TAIL;
-				else if (oldsize > newsize)
-					action = FILE_ACTION_TRUNCATE;
-				else
-					action = FILE_ACTION_NONE;
-			}
-			break;
-	}
-
-	/* Create a new entry for this file */
-	entry = pg_malloc(sizeof(file_entry_t));
-	entry->path = pg_strdup(path);
-	entry->type = type;
-	entry->action = action;
-	entry->oldsize = oldsize;
-	entry->newsize = newsize;
-	entry->link_target = link_target ? pg_strdup(link_target) : NULL;
-	entry->next = NULL;
-	entry->pagemap.bitmap = NULL;
-	entry->pagemap.bitmapsize = 0;
-	entry->isrelfile = isRelDataFile(path);
-
-	if (map->last)
-	{
-		map->last->next = entry;
-		map->last = entry;
-	}
-	else
-		map->first = map->last = entry;
-	map->nlist++;
+	/* Remember this source file */
+	entry = get_filemap_entry(path, true);
+	entry->source_exists = true;
+	entry->source_type = type;
+	entry->source_size = size;
+	entry->source_link_target = link_target ? pg_strdup(link_target) : NULL;
 }
 
 /*
  * Callback for processing target file list.
  *
- * All source files must be already processed before calling this. This only
- * marks target data directory's files that didn't exist in the source for
- * deletion.
+ * All source files must be already processed before calling this.  We record
+ * the type and size of file, so that decide_file_action() can later decide
+ * what to do with it.
  */
 void
-process_target_file(const char *path, file_type_t type, size_t oldsize,
+process_target_file(const char *path, file_type_t type, size_t size,
 					const char *link_target)
 {
-	bool		exists;
-	file_entry_t key;
-	file_entry_t *key_ptr;
 	filemap_t  *map = filemap;
 	file_entry_t *entry;
 
@@ -359,7 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize,
 	 * from the target data folder all paths which have been filtered out from
 	 * the source data folder when processing the source files.
 	 */
-
 	if (map->array == NULL)
 	{
 		/* on first call, initialize lookup array */
@@ -377,120 +281,77 @@ process_target_file(const char *path, file_type_t type, size_t oldsize,
 	}
 
 	/*
-	 * Like in process_source_file, pretend that xlog is always a  directory.
+	 * Like in process_source_file, pretend that pg_wal is always a directory.
 	 */
 	if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK)
 		type = FILE_TYPE_DIRECTORY;
 
-	key.path = (char *) path;
-	key_ptr = &key;
-	exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
-					  path_cmp) != NULL);
-
-	/* Remove any file or folder that doesn't exist in the source system. */
-	if (!exists)
-	{
-		entry = pg_malloc(sizeof(file_entry_t));
-		entry->path = pg_strdup(path);
-		entry->type = type;
-		entry->action = FILE_ACTION_REMOVE;
-		entry->oldsize = oldsize;
-		entry->newsize = 0;
-		entry->link_target = link_target ? pg_strdup(link_target) : NULL;
-		entry->next = NULL;
-		entry->pagemap.bitmap = NULL;
-		entry->pagemap.bitmapsize = 0;
-		entry->isrelfile = isRelDataFile(path);
-
-		if (map->last == NULL)
-			map->first = entry;
-		else
-			map->last->next = entry;
-		map->last = entry;
-		map->nlist++;
-	}
-	else
-	{
-		/*
-		 * We already handled all files that exist in the source system in
-		 * process_source_file().
-		 */
-	}
+	/* Remember this target file */
+	entry = get_filemap_entry(path, true);
+	entry->target_exists = true;
+	entry->target_type = type;
+	entry->target_size = size;
+	entry->target_link_target = link_target ? pg_strdup(link_target) : NULL;
 }
 
 /*
  * This callback gets called while we read the WAL in the target, for every
- * block that have changed in the target system. It makes note of all the
- * changed blocks in the pagemap of the file.
+ * block that has changed in the target system.  It decides if the given
+ * 'blkno' in the target relfile needs to be overwritten from the source, and
+ * if so, records it in 'target_pages_to_overwrite' bitmap.
+ *
+ * NOTE: All the files on both systems must have already been added to the
+ * file map!
  */
 void
-process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno)
+process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode,
+								BlockNumber blkno)
 {
 	char	   *path;
-	file_entry_t key;
-	file_entry_t *key_ptr;
 	file_entry_t *entry;
 	BlockNumber blkno_inseg;
 	int			segno;
-	filemap_t  *map = filemap;
-	file_entry_t **e;
 
-	Assert(map->array);
+	Assert(filemap->array);
 
 	segno = blkno / RELSEG_SIZE;
 	blkno_inseg = blkno % RELSEG_SIZE;
 
 	path = datasegpath(rnode, forknum, segno);
-
-	key.path = (char *) path;
-	key_ptr = &key;
-
-	e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *),
-				path_cmp);
-	if (e)
-		entry = *e;
-	else
-		entry = NULL;
+	entry = get_filemap_entry(path, false);
 	pfree(path);
 
 	if (entry)
 	{
-		Assert(entry->isrelfile);
+		int64		end_offset;
 
-		switch (entry->action)
-		{
-			case FILE_ACTION_NONE:
-			case FILE_ACTION_TRUNCATE:
-				/* skip if we're truncating away the modified block anyway */
-				if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize)
-					datapagemap_add(&entry->pagemap, blkno_inseg);
-				break;
-
-			case FILE_ACTION_COPY_TAIL:
-
-				/*
-				 * skip the modified block if it is part of the "tail" that
-				 * we're copying anyway.
-				 */
-				if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize)
-					datapagemap_add(&entry->pagemap, blkno_inseg);
-				break;
+		Assert(entry->isrelfile);
 
-			case FILE_ACTION_COPY:
-			case FILE_ACTION_REMOVE:
-				break;
+		if (entry->target_type != FILE_TYPE_REGULAR)
+			pg_fatal("unexpected page modification for non-regular file \"%s\"",
+					 entry->path);
 
-			case FILE_ACTION_CREATE:
-				pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path);
-		}
+		/*
+		 * If the block beyond the EOF in the source system, no need to
+		 * remember it now, because we're going to truncate it away from the
+		 * target anyway. Also no need to remember the block if it's beyond
+		 * the current EOF in the target system; we will copy it over with the
+		 * "tail" from the source system, anyway.
+		 */
+		end_offset = (blkno_inseg + 1) * BLCKSZ;
+		if (end_offset <= entry->source_size &&
+			end_offset <= entry->target_size)
+			datapagemap_add(&entry->target_pages_to_overwrite, blkno_inseg);
 	}
 	else
 	{
 		/*
 		 * If we don't have any record of this file in the file map, it means
-		 * that it's a relation that doesn't exist in the source system, and
-		 * it was subsequently removed in the target system, too. We can
-		 * safely ignore it.
+		 * that it's a relation that doesn't exist in the source system.  It
+		 * could exist in the target system; we haven't moved the target-only
+		 * entries from the linked list to the array yet!  But in any case, if
+		 * it doesn't exist in the source it will be removed from the target
+		 * too, and we can safely ignore it.
 		 */
 	}
 }
@@ -505,6 +366,15 @@ check_file_excluded(const char *path, bool is_source)
 	int			excludeIdx;
 	const char *filename;
 
+	/*
+	 * Skip all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.*
+	 */
+	if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL ||
+		strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL)
+	{
+		return true;
+	}
+
 	/* check individual files... */
 	for (excludeIdx = 0; excludeFiles[excludeIdx].name != NULL; excludeIdx++)
 	{
@@ -581,16 +451,6 @@ filemap_list_to_array(filemap_t *map)
 	map->first = map->last = NULL;
 }
 
-void
-filemap_finalize(void)
-{
-	filemap_t  *map = filemap;
-
-	filemap_list_to_array(map);
-	qsort(map->array, map->narray, sizeof(file_entry_t *),
-		  final_filemap_cmp);
-}
-
 static const char *
 action_to_str(file_action_t action)
 {
@@ -631,26 +491,26 @@ calculate_totals(void)
 	{
 		entry = map->array[i];
 
-		if (entry->type != FILE_TYPE_REGULAR)
+		if (entry->source_type != FILE_TYPE_REGULAR)
 			continue;
 
-		map->total_size += entry->newsize;
+		map->total_size += entry->source_size;
 
 		if (entry->action == FILE_ACTION_COPY)
 		{
-			map->fetch_size += entry->newsize;
+			map->fetch_size += entry->source_size;
 			continue;
 		}
 
 		if (entry->action == FILE_ACTION_COPY_TAIL)
-			map->fetch_size += (entry->newsize - entry->oldsize);
+			map->fetch_size += (entry->source_size - entry->target_size);
 
-		if (entry->pagemap.bitmapsize > 0)
+		if (entry->target_pages_to_overwrite.bitmapsize > 0)
 		{
 			datapagemap_iterator_t *iter;
 			BlockNumber blk;
 
-			iter = datapagemap_iterate(&entry->pagemap);
+			iter = datapagemap_iterate(&entry->target_pages_to_overwrite);
 			while (datapagemap_next(iter, &blk))
 				map->fetch_size += BLCKSZ;
 
@@ -670,13 +530,13 @@ print_filemap(void)
 	{
 		entry = map->array[i];
 		if (entry->action != FILE_ACTION_NONE ||
-			entry->pagemap.bitmapsize > 0)
+			entry->target_pages_to_overwrite.bitmapsize > 0)
 		{
 			pg_log_debug("%s (%s)", entry->path,
 						 action_to_str(entry->action));
 
-			if (entry->pagemap.bitmapsize > 0)
-				datapagemap_print(&entry->pagemap);
+			if (entry->target_pages_to_overwrite.bitmapsize > 0)
+				datapagemap_print(&entry->target_pages_to_overwrite);
 		}
 	}
 	fflush(stdout);
@@ -825,3 +685,170 @@ final_filemap_cmp(const void *a, const void *b)
 	else
 		return strcmp(fa->path, fb->path);
 }
+
+/*
+ * Decide what action to perform to a file.
+ */
+static file_action_t
+decide_file_action(file_entry_t *entry)
+{
+	const char *path = entry->path;
+
+	/*
+	 * Don't touch the control file. It is handled specially, after copying
+	 * all the other files.
+	 */
+	if (strcmp(path, "global/pg_control") == 0)
+		return FILE_ACTION_NONE;
+
+	/*
+	 * Remove all files matching the exclusion filters in the target.
+	 */
+	if (check_file_excluded(path, true))
+	{
+		if (entry->target_exists)
+			return FILE_ACTION_REMOVE;
+		else
+			return FILE_ACTION_NONE;
+	}
+
+	/*
+	 * Handle cases where the file is missing from one of the systems.
+	 */
+	if (!entry->target_exists && entry->source_exists)
+	{
+		/*
+		 * File exists in source, but not in target. Copy it in toto. (If it's
+		 * a relation data file, WAL replay after rewinding should re-create
+		 * it anyway. But there's no harm in copying it now.)
+		 */
+		switch (entry->source_type)
+		{
+			case FILE_TYPE_DIRECTORY:
+			case FILE_TYPE_SYMLINK:
+				return FILE_ACTION_CREATE;
+			case FILE_TYPE_REGULAR:
+				return FILE_ACTION_COPY;
+			case FILE_TYPE_UNDEFINED:
+				pg_fatal("unknown file type for \"%s\"", entry->path);
+				break;
+		}
+	}
+	else if (entry->target_exists && !entry->source_exists)
+	{
+		/* File exists in target, but not source. Remove it. */
+		return FILE_ACTION_REMOVE;
+	}
+	else if (!entry->target_exists && !entry->source_exists)
+	{
+		/*
+		 * Doesn't exist in either server. Why does it have an entry in the
+		 * first place??
+		 */
+		Assert(false);
+		return FILE_ACTION_NONE;
+	}
+
+	/*
+	 * Otherwise, the file exists on both systems
+	 */
+	Assert(entry->target_exists && entry->source_exists);
+
+	if (entry->source_type != entry->target_type)
+	{
+		/* But it's a different kind of object. Strange.. */
+		pg_fatal("file \"%s\" is of different type in source and target", entry->path);
+	}
+
+	/*
+	 * PG_VERSION files should be identical on both systems, but avoid
+	 * overwriting them for paranoia.
+	 */
+	if (pg_str_endswith(entry->path, "PG_VERSION"))
+		return FILE_ACTION_NONE;
+
+	switch (entry->source_type)
+	{
+		case FILE_TYPE_DIRECTORY:
+			return FILE_ACTION_NONE;
+
+		case FILE_TYPE_SYMLINK:
+			/*
+			 * XXX: Should we check if it points to the same target?
+			 */
+			return FILE_ACTION_NONE;
+
+		case FILE_TYPE_REGULAR:
+			if (!entry->isrelfile)
+			{
+				/*
+				 * It's a non-data file that we have no special processing
+				 * for. Copy it in toto.
+				 */
+				return FILE_ACTION_COPY;
+			}
+			else
+			{
+				/*
+				 * It's a data file that exists in both systems.
+				 *
+				 * If it's larger in target, we can truncate it. There will
+				 * also be a WAL record of the truncation in the source
+				 * system, so WAL replay would eventually truncate the target
+				 * too, but we might as well do it now.
+				 *
+				 * If it's smaller in the target, it means that it has been
+				 * truncated in the target, or enlarged in the source, or
+				 * both. If it was truncated in the target, we need to copy
+				 * the missing tail from the source system. If it was enlarged
+				 * in the source system, there will be WAL records in the
+				 * source system for the new blocks, so we wouldn't need to
+				 * copy them here. But we don't know which scenario we're
+				 * dealing with, and there's no harm in copying the missing
+				 * blocks now, so do it now.
+				 *
+				 * If it's the same size, do nothing here. Any blocks modified
+				 * in the target will be copied based on parsing the target
+				 * system's WAL, and any blocks modified in the source will be
+				 * updated after rewinding, when the source system's WAL is
+				 * replayed.
+				 */
+				if (entry->target_size < entry->source_size)
+					return FILE_ACTION_COPY_TAIL;
+				else if (entry->target_size > entry->source_size)
+					return FILE_ACTION_TRUNCATE;
+				else
+					return FILE_ACTION_NONE;
+			}
+			break;
+
+		case FILE_TYPE_UNDEFINED:
+			pg_fatal("unknown file type for \"%s\"", path);
+			break;
+	}
+
+	/* unreachable */
+	pg_fatal("could not decide what to do with file \"%s\"", path);
+}
+
+/*
+ * Decide what to do with each file.
+ */
+void
+decide_file_actions()
+{
+	int			i;
+
+	filemap_list_to_array(filemap);
+
+	for (i = 0; i < filemap->narray; i++)
+	{
+		file_entry_t *entry = filemap->array[i];
+
+		entry->action = decide_file_action(entry);
+	}
+
+	/* Sort the actions to the order that they should be performed */
+	qsort(filemap->array, filemap->narray, sizeof(file_entry_t *),
+		  final_filemap_cmp);
+}
diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h
index 0cb7425170c..73c687e4e34 100644
--- a/src/bin/pg_rewind/filemap.h
+++ b/src/bin/pg_rewind/filemap.h
@@ -14,17 +14,21 @@
 
 /*
  * For every file found in the local or remote system, we have a file entry
- * which says what we are going to do with the file. For relation files,
- * there is also a page map, marking pages in the file that were changed
- * locally.
- *
- * The enum values are sorted in the order we want actions to be processed.
+ * that contains information about the file on both systems.  For relation
+ * files, there is also a page map that marks pages in the file that were
+ * changed in the target after the last common checkpoint.  Each entry also
+ * contains an 'action' field, which says what we are going to do with the
+ * file.
  */
+
+/* these enum values are sorted in the order we want actions to be processed */
 typedef enum
 {
+	FILE_ACTION_UNDECIDED = 0,	/* not decided yet */
+
 	FILE_ACTION_CREATE,			/* create local directory or symbolic link */
 	FILE_ACTION_COPY,			/* copy whole file, overwriting if exists */
-	FILE_ACTION_COPY_TAIL,		/* copy tail from 'oldsize' to 'newsize' */
+	FILE_ACTION_COPY_TAIL,		/* copy tail from 'source_size' to 'target_size' */
 	FILE_ACTION_NONE,			/* no action (we might still copy modified
 								 * blocks based on the parsed WAL) */
 	FILE_ACTION_TRUNCATE,		/* truncate local file to 'newsize' bytes */
@@ -33,6 +37,8 @@ typedef enum
 
 typedef enum
 {
+	FILE_TYPE_UNDEFINED = 0,
+
 	FILE_TYPE_REGULAR,
 	FILE_TYPE_DIRECTORY,
 	FILE_TYPE_SYMLINK
@@ -41,19 +47,34 @@ typedef enum
 typedef struct file_entry_t
 {
 	char	   *path;
-	file_type_t type;
+	bool		isrelfile;		/* is it a relation data file? */
 
-	file_action_t action;
+	/*
+	 * Status of the file in the target.
+	 */
+	bool		target_exists;
+	file_type_t target_type;
+	size_t		target_size; /* for a regular file */
+	char	   *target_link_target; /* for a symlink */
 
-	/* for a regular file */
-	size_t		oldsize;
-	size_t		newsize;
-	bool		isrelfile;		/* is it a relation data file? */
+	/*
+	 * Pages that were modified in the target and need to be replaced
+	 * from the source.
+	 */
+	datapagemap_t target_pages_to_overwrite;
 
-	datapagemap_t pagemap;
+	/*
+	 * Status of the file in the source.
+	 */
+	bool		source_exists;
+	file_type_t source_type;
+	size_t		source_size;
+	char	   *source_link_target; /* for a symlink */
 
-	/* for a symlink */
-	char	   *link_target;
+	/*
+	 * What will we do to the file?
+	 */
+	file_action_t action;
 
 	struct file_entry_t *next;
 } file_entry_t;
@@ -79,11 +100,10 @@ typedef struct filemap_t
 	int			narray;			/* current length of array */
 
 	/*
-	 * Summary information. total_size is the total size of the source
-	 * cluster, and fetch_size is the number of bytes that needs to be copied.
+	 * Summary information.
 	 */
-	uint64		total_size;
-	uint64		fetch_size;
+	uint64		total_size;		/* total size of the source cluster */
+	uint64		fetch_size;		/* number of bytes that needs to be copied */
 } filemap_t;
 
 extern filemap_t *filemap;
@@ -94,11 +114,12 @@ extern void print_filemap(void);
 
 /* Functions for populating the filemap */
 extern void process_source_file(const char *path, file_type_t type,
-								size_t newsize, const char *link_target);
+								size_t size, const char *link_target);
 extern void process_target_file(const char *path, file_type_t type,
-								size_t newsize, const char *link_target);
-extern void process_block_change(ForkNumber forknum, RelFileNode rnode,
-								 BlockNumber blkno);
-extern void filemap_finalize(void);
+								size_t size, const char *link_target);
+extern void process_target_wal_block_change(ForkNumber forknum,
+											RelFileNode rnode,
+											BlockNumber blkno);
+extern void decide_file_actions(void);
 
 #endif							/* FILEMAP_H */
diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c
index bf4dfc23b96..2fc4a784bdb 100644
--- a/src/bin/pg_rewind/libpq_fetch.c
+++ b/src/bin/pg_rewind/libpq_fetch.c
@@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map)
 		entry = map->array[i];
 
 		/* If this is a relation file, copy the modified blocks */
-		execute_pagemap(&entry->pagemap, entry->path);
+		execute_pagemap(&entry->target_pages_to_overwrite, entry->path);
 
 		switch (entry->action)
 		{
@@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map)
 			case FILE_ACTION_COPY:
 				/* Truncate the old file out of the way, if any */
 				open_target_file(entry->path, true);
-				fetch_file_range(entry->path, 0, entry->newsize);
+				fetch_file_range(entry->path, 0, entry->source_size);
 				break;
 
 			case FILE_ACTION_TRUNCATE:
-				truncate_target_file(entry->path, entry->newsize);
+				truncate_target_file(entry->path, entry->source_size);
 				break;
 
 			case FILE_ACTION_COPY_TAIL:
-				fetch_file_range(entry->path, entry->oldsize, entry->newsize);
+				fetch_file_range(entry->path, entry->target_size, entry->source_size);
 				break;
 
 			case FILE_ACTION_REMOVE:
@@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map)
 			case FILE_ACTION_CREATE:
 				create_target(entry);
 				break;
+
+			case FILE_ACTION_UNDECIDED:
+				pg_fatal("no action decided for \"%s\"", entry->path);
+				break;
 		}
 	}
 
diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c
index 2229c86f9af..2baeb74ae93 100644
--- a/src/bin/pg_rewind/parsexlog.c
+++ b/src/bin/pg_rewind/parsexlog.c
@@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record)
 		if (forknum != MAIN_FORKNUM)
 			continue;
 
-		process_block_change(forknum, rnode, blkno);
+		process_target_wal_block_change(forknum, rnode, blkno);
 	}
 }
diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c
index 5a7ab764db4..4760090d06e 100644
--- a/src/bin/pg_rewind/pg_rewind.c
+++ b/src/bin/pg_rewind/pg_rewind.c
@@ -369,7 +369,7 @@ main(int argc, char **argv)
 				chkpttli);
 
 	/*
-	 * Build the filemap, by comparing the source and target data directories.
+	 * Collect information about all files in the target and source systems.
 	 */
 	filemap_create();
 	if (showprogress)
@@ -390,8 +390,12 @@ main(int argc, char **argv)
 		pg_log_info("reading WAL in target");
 	extractPageMap(datadir_target, chkptrec, lastcommontliIndex,
 				   ControlFile_target.checkPoint, restore_command);
-	filemap_finalize();
 
+	/*
+	 * We have collected all information we need from both systems. Decide
+	 * what to do with each file.
+	 */
+	decide_file_actions();
 	if (showprogress)
 		calculate_totals();
 
-- 
2.20.1


--------------E5E97ECB089CAF17EDB11AD4
Content-Type: text/x-patch; charset=UTF-8;
 name="v3-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename*0="v3-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa";
 filename*1="tch"



^ permalink  raw  reply  [nested|flat] 5+ messages in thread

* [PATCH v54 1/5] Introduce an option to make logical replication database specific.
@ 2026-04-05 07:51 Antonin Houska <[email protected]>
  0 siblings, 0 replies; 5+ messages in thread

From: Antonin Houska @ 2026-04-05 07:51 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch adds a new option to logical replication output plugin, to declare
that it does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in the plugin for logical replication too, however that would
need thorough analysis of that plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 +-
 doc/src/sgml/logicaldecoding.sgml           |  4 ++
 src/backend/access/index/genam.c            |  8 +++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 +
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/decode.c    |  8 ++-
 src/backend/replication/logical/logical.c   |  3 ++
 src/backend/replication/logical/snapbuild.c | 54 +++++++++++++++++++--
 src/backend/replication/slot.c              |  2 +-
 src/backend/storage/ipc/procarray.c         | 23 ++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++-
 src/include/access/genam.h                  |  7 +++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/replication/output_plugin.h     |  1 +
 src/include/replication/snapbuild.h         |  3 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 +-
 src/include/storage/standbydefs.h           |  1 +
 20 files changed, 128 insertions(+), 19 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index 6dc49108997..28089d1053c 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -959,6 +959,7 @@ typedef struct OutputPluginOptions
 {
     OutputPluginOutputType output_type;
     bool        receive_rewrites;
+    bool        need_shared_catalogs;
 } OutputPluginOptions;
 </programlisting>
       <literal>output_type</literal> has to either be set to
@@ -969,6 +970,9 @@ typedef struct OutputPluginOptions
       also be called for changes made by heap rewrites during certain DDL
       operations.  These are of interest to plugins that handle DDL
       replication, but they require special handling.
+      <literal>need_shared_catalogs</literal> can be set to false if you are
+      sure the plugin functions do not access shared system catalogs. It can
+      speed up creation of replication slots that use this plugin.
      </para>
 
      <para>
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..44df2605068 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -394,6 +394,14 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9e8999bbb61..1a6c1456d2c 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7731,7 +7731,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index 57aaef57c61..4299d0bc867 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -381,7 +381,13 @@ standby_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 			{
 				xl_running_xacts *running = (xl_running_xacts *) XLogRecGetData(r);
 
-				SnapBuildProcessRunningXacts(builder, buf->origptr, running);
+
+				/*
+				 * If the plugin does not access shared catalogs, only keep
+				 * track of transactions in the current database.
+				 */
+				SnapBuildProcessRunningXacts(builder, buf->origptr, running,
+											 !ctx->options.need_shared_catalogs);
 
 				/*
 				 * Abort all transactions that we keep track of, that are
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20d0c542f3..8ceaf64d164 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -285,6 +285,9 @@ StartupDecodingContext(List *output_plugin_options,
 	ctx->write = do_write;
 	ctx->update_progress = update_progress;
 
+	/* Assume shared catalog access. The startup callback can change it. */
+	ctx->options.need_shared_catalogs = true;
+
 	ctx->output_plugin_options = output_plugin_options;
 
 	ctx->fast_forward = fast_forward;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..8ef2326c66d 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -154,6 +155,14 @@
 static ResourceOwner SavedResourceOwnerDuringExport = NULL;
 static bool ExportInProgress = false;
 
+/*
+ * If a backend is going to do logical decoding and the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 /* ->committed and ->catchange manipulation */
 static void SnapBuildPurgeOlderTxn(SnapBuild *builder);
 
@@ -170,7 +179,8 @@ static inline bool SnapBuildXidHasCatalogChanges(SnapBuild *builder, Transaction
 												 uint32 xinfo);
 
 /* xlog reading helper functions for SnapBuildProcessRunningXacts */
-static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running);
+static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn,
+								  xl_running_xacts *running, bool db_specific);
 static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff);
 
 /* serialization functions */
@@ -1136,7 +1146,8 @@ SnapBuildXidHasCatalogChanges(SnapBuild *builder, TransactionId xid,
  * anymore.
  */
 void
-SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+							 bool db_specific)
 {
 	ReorderBufferTXN *txn;
 	TransactionId xmin;
@@ -1149,12 +1160,21 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	if (builder->state < SNAPBUILD_CONSISTENT)
 	{
 		/* returns false if there's no point in performing cleanup just yet */
-		if (!SnapBuildFindSnapshot(builder, lsn, running))
+		if (!SnapBuildFindSnapshot(builder, lsn, running, db_specific))
 			return;
 	}
 	else
 		SnapBuildSerialize(builder, lsn);
 
+	/*
+	 * If database specific transaction info was used during startup, the info
+	 * for the whole cluster can make xmin go backwards. The code below
+	 * probably does not expect that, let's wait with the cleanup for the next
+	 * record.
+	 */
+	if (!NormalTransactionIdFollows(running->oldestRunningXid, builder->xmin))
+		return;
+
 	/*
 	 * Update range of interesting xids based on the running xacts
 	 * information. We don't increase ->xmax using it, because once we are in
@@ -1238,7 +1258,8 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
  * using the xl_running_xacts record.
  */
 static bool
-SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+					  bool db_specific)
 {
 	/* ---
 	 * Build catalog decoding snapshot incrementally using information about
@@ -1265,6 +1286,25 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * ---
 	 */
 
+	if (db_specific)
+	{
+		/*
+		 * If we must only keep track of transactions running in the current
+		 * database, we need transaction info from exactly that database.
+		 */
+		if (running->dbid != MyDatabaseId)
+		{
+			LogStandbySnapshot(MyDatabaseId);
+			return false;
+		}
+
+		/*
+		 * We'd better be able to check during scan if the plugin does not
+		 * lie.
+		 */
+		accessSharedCatalogsInDecoding = false;
+	}
+
 	/*
 	 * xl_running_xacts record is older than what we can use, we might not
 	 * have all necessary catalog rows anymore.
@@ -1465,7 +1505,11 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		/*
+		 * If the last transaction info was about specific database, so needs
+		 * to be the next one - at least until we're in the CONSISTENT state.
+		 */
+		LogStandbySnapshot(running->dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..9533515a63b 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1762,7 +1762,7 @@ ReplicationSlotReserveWal(void)
 		XLogRecPtr	flushptr;
 
 		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		flushptr = LogStandbySnapshot(InvalidOid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..c9a52277be1 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,13 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+
+/*
+ * Keep track of whether logical decoding in this backend promised not to
+ * access shared catalogs, as a safety check.  Somewhat misplaced, but ...
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 10c18d39ff8..13ae3ad4fbb 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -32,7 +32,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/replication/output_plugin.h b/src/include/replication/output_plugin.h
index 842fcde67f9..917f3cff232 100644
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -27,6 +27,7 @@ typedef struct OutputPluginOptions
 {
 	OutputPluginOutputType output_type;
 	bool		receive_rewrites;
+	bool		need_shared_catalogs;
 } OutputPluginOptions;
 
 /*
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index a22a83a2f23..d02530a912a 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -92,7 +92,8 @@ extern void SnapBuildProcessNewCid(SnapBuild *builder, TransactionId xid,
 								   XLogRecPtr lsn,
 								   xl_heap_new_cid *xlrec);
 extern void SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn,
-										 xl_running_xacts *running);
+										 xl_running_xacts *running,
+										 bool db_specific);
 extern void SnapBuildSerializationPoint(SnapBuild *builder, XLogRecPtr lsn);
 
 extern bool SnapBuildSnapshotExists(XLogRecPtr lsn);
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--cdhh4t7ukb6tnjoq
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v54-0002-Rename-cluster.c-h-repack.c-h.patch"



^ permalink  raw  reply  [nested|flat] 5+ messages in thread

end of thread, other threads:[~2026-04-05 07:51 UTC | newest]

Thread overview: 5+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-08-19 12:34 [PATCH v3 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]>
2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]>
2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]>
2020-09-24 17:08 [PATCH v3 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]>
2026-04-05 07:51 [PATCH v54 1/5] Introduce an option to make logical replication database specific. Antonin Houska <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox