pg_rewind: Replace the hybrid list+array data structure with simplehash.

Now that simplehash can be used in frontend code, let's make use of it.

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

@@ -207,9 +207,9 @@ copy_executeFileMap(filemap_t *map)
 	file_entry_t *entry;
 	int			i;
 
-	for (i = 0; i < map->narray; i++)
+	for (i = 0; i < map->nentries; i++)
 	{
-		entry = map->array[i];
+		entry = map->entries[i];
 		execute_pagemap(&entry->target_pages_to_overwrite, entry->path);
 
 		switch (entry->action)

src/bin/pg_rewind/fetch.c

@@ -37,7 +37,7 @@ fetchSourceFileList(void)
  * Fetch all relation data files that are marked in the given data page map.
  */
 void
-executeFileMap(void)
+execute_file_actions(filemap_t *filemap)
 {
 	if (datadir_source)
 		copy_executeFileMap(filemap);

src/bin/pg_rewind/fetch.h

@@ -25,7 +25,7 @@
  */
 extern void fetchSourceFileList(void);
 extern char *fetchFile(const char *filename, size_t *filesize);
-extern void executeFileMap(void);
+extern void execute_file_actions(filemap_t *filemap);
 
 /* in libpq_fetch.c */
 extern void libpqProcessFileList(void);

src/bin/pg_rewind/filemap.h

@@ -12,15 +12,6 @@
 #include "storage/block.h"
 #include "storage/relfilenode.h"
 
-/*
- * For every file found in the local or remote system, we have a file entry
- * 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
 {
@@ -45,9 +36,21 @@ typedef enum
 	FILE_TYPE_SYMLINK
 } file_type_t;
 
+/*
+ * For every file found in the local or remote system, we have a file entry
+ * 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.
+ *
+ * When gathering information, these are kept in a hash table, private to
+ * filemap.c.  decide_file_actions() fills in the 'action' field, sorts all
+ * the entries, and returns them in an array, ready for executing the actions.
+ */
 typedef struct file_entry_t
 {
-	char	   *path;
+	uint32		status;			/* hash status */
+
+	const char *path;
 	bool		isrelfile;		/* is it a relation data file? */
 
 	/*
@@ -76,44 +79,25 @@ typedef struct file_entry_t
 	 * What will we do to the file?
 	 */
 	file_action_t action;
-
-	struct file_entry_t *next;
 } file_entry_t;
 
+/*
+ * This contains the final decisions on what to do with each file.
+ * 'entries' array contains an entry for each file, sorted in the order
+ * that their actions should executed.
+ */
 typedef struct filemap_t
 {
-	/*
-	 * New entries are accumulated to a linked list, in process_source_file
-	 * and process_target_file.
-	 */
-	file_entry_t *first;
-	file_entry_t *last;
-	int			nlist;			/* number of entries currently in list */
-
-	/*
-	 * After processing all the remote files, the entries in the linked list
-	 * are moved to this array. After processing local files, too, all the
-	 * local entries are added to the array by decide_file_actions(), and
-	 * sorted in the final order. After decide_file_actions(), 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.
-	 */
+	/* Summary information, filled by calculate_totals() */
 	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;
-
-extern void filemap_create(void);
-extern void calculate_totals(void);
-extern void print_filemap(void);
+	int			nentries;		/* size of 'entries' array */
+	file_entry_t *entries[FLEXIBLE_ARRAY_MEMBER];
+} filemap_t;
 
 /* Functions for populating the filemap */
+extern void filehash_init(void);
 extern void process_source_file(const char *path, file_type_t type,
 								size_t size, const char *link_target);
 extern void process_target_file(const char *path, file_type_t type,
@@ -121,6 +105,9 @@ extern void process_target_file(const char *path, file_type_t type,
 extern void process_target_wal_block_change(ForkNumber forknum,
 											RelFileNode rnode,
 											BlockNumber blkno);
-extern void decide_file_actions(void);
+
+extern filemap_t *decide_file_actions(void);
+extern void calculate_totals(filemap_t *filemap);
+extern void print_filemap(filemap_t *filemap);
 
 #endif							/* FILEMAP_H */

src/bin/pg_rewind/libpq_fetch.c

@@ -460,9 +460,9 @@ libpq_executeFileMap(filemap_t *map)
 				 PQresultErrorMessage(res));
 	PQclear(res);
 
-	for (i = 0; i < map->narray; i++)
+	for (i = 0; i < map->nentries; i++)
 	{
-		entry = map->array[i];
+		entry = map->entries[i];
 
 		/* If this is a relation file, copy the modified blocks */
 		execute_pagemap(&entry->target_pages_to_overwrite, entry->path);

src/bin/pg_rewind/pg_rewind.c

@@ -129,6 +129,7 @@ main(int argc, char **argv)
 	TimeLineID	endtli;
 	ControlFileData ControlFile_new;
 	bool		writerecoveryconf = false;
+	filemap_t  *filemap;
 
 	pg_logging_init(argv[0]);
 	set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pg_rewind"));
@@ -368,13 +369,16 @@ main(int argc, char **argv)
 				(uint32) (chkptrec >> 32), (uint32) chkptrec,
 				chkpttli);
 
+	/* Initialize the hash table to track the status of each file */
+	filehash_init();
+
 	/*
 	 * Collect information about all files in the target and source systems.
 	 */
-	filemap_create();
 	if (showprogress)
 		pg_log_info("reading source file list");
 	fetchSourceFileList();
+
 	if (showprogress)
 		pg_log_info("reading target file list");
 	traverse_datadir(datadir_target, &process_target_file);
@@ -395,13 +399,13 @@ main(int argc, char **argv)
 	 * We have collected all information we need from both systems. Decide
 	 * what to do with each file.
 	 */
-	decide_file_actions();
+	filemap = decide_file_actions();
 	if (showprogress)
-		calculate_totals();
+		calculate_totals(filemap);
 
 	/* this is too verbose even for verbose mode */
 	if (debug)
-		print_filemap();
+		print_filemap(filemap);
 
 	/*
 	 * Ok, we're ready to start copying things over.
@@ -421,7 +425,7 @@ main(int argc, char **argv)
 	 * modified the target directory and there is no turning back!
 	 */
 
-	executeFileMap();
+	execute_file_actions(filemap);
 
 	progress_report(true);