X-Git-Url: https://mattmccutchen.net/rsync/rsync-patches.git/blobdiff_plain/cdcd21373a3358b21132ad227fe21a8543e45090..d4dd2dd52f48a66395428810389ef31cc0488db7:/detect-renamed.diff

diff --git a/detect-renamed.diff b/detect-renamed.diff
index 1518725..706ccd9 100644
--- a/detect-renamed.diff
+++ b/detect-renamed.diff
@@ -42,15 +42,14 @@ TODO:
  extern int protect_args;
  extern int preserve_uid;
  extern int preserve_gid;
-@@ -218,7 +219,7 @@ void setup_protocol(int f_out,int f_in)
- 	} else if (protocol_version >= 30) {
- 		if (recurse && allow_inc_recurse
- 		 && !delete_before && !delete_after && !delay_updates
--		 && !use_qsort && !prune_empty_dirs)
-+		 && !use_qsort && !prune_empty_dirs && !detect_renamed)
- 			inc_recurse = 1;
- 		need_messages_from_generator = 1;
- 	}
+@@ -107,6 +108,7 @@ void set_allow_inc_recurse(void)
+ 		allow_inc_recurse = 0;
+ 	else if (!am_sender
+ 	 && (delete_before || delete_after
++	  || detect_renamed
+ 	  || delay_updates || prune_empty_dirs))
+ 		allow_inc_recurse = 0;
+ 	else if (am_server && !local_server
 --- old/flist.c
 +++ new/flist.c
 @@ -61,6 +61,7 @@ extern int non_perishable_cnt;
@@ -60,8 +59,8 @@ TODO:
 +extern int detect_renamed;
  extern int protocol_version;
  extern int sanitize_paths;
- extern struct stats stats;
-@@ -113,6 +114,8 @@ static int64 tmp_dev, tmp_ino;
+ extern int need_unsorted_flist;
+@@ -117,6 +118,8 @@ static int64 tmp_dev, tmp_ino;
  #endif
  static char tmp_sum[MAX_DIGEST_LEN];
  
@@ -70,7 +69,7 @@ TODO:
  static char empty_sum[MAX_DIGEST_LEN];
  static int flist_count_offset; /* for --delete --progress */
  static int dir_count = 0;
-@@ -252,6 +255,45 @@ static int is_excluded(char *fname, int 
+@@ -256,6 +259,45 @@ static int is_excluded(char *fname, int 
  	return 0;
  }
  
@@ -116,9 +115,9 @@ TODO:
  static void send_directory(int f, struct file_list *flist,
  			   char *fbuf, int len, int flags);
  
-@@ -2021,6 +2063,25 @@ struct file_list *send_file_list(int f, 
- 	if (verbose > 2)
- 		rprintf(FINFO, "send_file_list done\n");
+@@ -2169,6 +2211,25 @@ struct file_list *recv_file_list(int f)
+ 
+ 	clean_flist(flist, relative_paths);
  
 +	if (detect_renamed) {
 +		int j = flist->used;
@@ -139,9 +138,9 @@ TODO:
 +		the_fattr_list.high = j;
 +	}
 +
- 	if (inc_recurse) {
- 		add_dirs_to_tree(-1, flist, dir_count);
- 		flist_done_allocating(flist);
+ 	if (protocol_version < 30) {
+ 		/* Recv the io_error flag */
+ 		if (ignore_errors)
 --- old/generator.c
 +++ new/generator.c
 @@ -79,6 +79,7 @@ extern char *basis_dir[];
@@ -152,15 +151,15 @@ TODO:
  extern int whole_file;
  extern int list_only;
  extern int read_batch;
-@@ -95,6 +96,7 @@ extern char *backup_suffix;
+@@ -96,6 +97,7 @@ extern char *backup_suffix;
  extern int backup_suffix_len;
  extern struct file_list *cur_flist, *first_flist, *dir_flist;
  extern struct filter_list_struct server_filter_list;
 +extern struct file_list the_fattr_list;
- #ifdef ICONV_OPTION
- extern int ic_ndx;
- #endif
-@@ -105,6 +107,7 @@ int maybe_ATTRS_REPORT = 0;
+ 
+ int ignore_perishable = 0;
+ int non_perishable_cnt = 0;
+@@ -103,6 +105,7 @@ int maybe_ATTRS_REPORT = 0;
  
  static dev_t dev_zero;
  static int deletion_count = 0; /* used to implement --max-delete */
@@ -168,7 +167,7 @@ TODO:
  static int deldelay_size = 0, deldelay_cnt = 0;
  static char *deldelay_buf = NULL;
  static int deldelay_fd = -1;
-@@ -114,7 +117,8 @@ static int need_retouch_dir_times;
+@@ -112,7 +115,8 @@ static int need_retouch_dir_times;
  static int need_retouch_dir_perms;
  static const char *solo_file = NULL;
  
@@ -178,7 +177,7 @@ TODO:
  #define DEL_RECURSE		(1<<1) /* recurse */
  #define DEL_DIR_IS_EMPTY	(1<<2) /* internal delete_FUNCTIONS use only */
  
-@@ -136,11 +140,120 @@ static int is_backup_file(char *fn)
+@@ -134,11 +138,121 @@ static int is_backup_file(char *fn)
  	return k > 0 && strcmp(fn+k, backup_suffix) == 0;
  }
  
@@ -264,7 +263,7 @@ TODO:
 +	STRUCT_STAT st;
 +	int ndx;
 +
-+	if ((ndx = fattr_find(file, fname)) < 0)
++	if (!partial_dir || (ndx = fattr_find(file, fname)) < 0)
 +		return;
 +
 +	fp = the_fattr_list.files[ndx];
@@ -272,21 +271,22 @@ TODO:
 +	/* We don't provide an alternate-basis file if there is a basis file. */
 +	if (link_stat(fn, &st, 0) == 0)
 +		return;
-+	if ((partialptr = partial_dir_fname(fn)) == NULL
-+	 || !handle_partial_dir(partialptr, PDIR_CREATE))
-+		return;
 +
-+	/* We only use the file if we can hard-link it into our tmp dir. */
-+	if (link(fname, partialptr) == 0) {
-+		if (verbose > 2) {
-+			rprintf(FINFO, "found renamed: %s => %s\n",
-+				fname, partialptr);
++	if (!dry_run) {
++		if ((partialptr = partial_dir_fname(fn)) == NULL
++		 || !handle_partial_dir(partialptr, PDIR_CREATE))
++			return;
++		/* We only use the file if we can hard-link it into our tmp dir. */
++		if (link(fname, partialptr) != 0) {
++			if (errno != EEXIST)
++				handle_partial_dir(partialptr, PDIR_DELETE);
++			return;
 +		}
-+		return;
 +	}
 +
-+	if (errno != EEXIST)
-+		handle_partial_dir(partialptr, PDIR_DELETE);
++	/* I think this falls into the -vv category with "%s is uptodate", etc. */
++	if (verbose > 1)
++		rprintf(FINFO, "found renamed: %s => %s\n", fname, fn);
 +}
 +
  /* Delete a file or directory.  If DEL_RECURSE is set in the flags, this will
@@ -299,7 +299,7 @@ TODO:
   */
  static enum delret delete_item(char *fbuf, int mode, char *replace, int flags)
  {
-@@ -162,6 +275,8 @@ static enum delret delete_item(char *fbu
+@@ -160,6 +274,8 @@ static enum delret delete_item(char *fbu
  			goto check_ret;
  		/* OK: try to delete the directory. */
  	}
@@ -308,7 +308,7 @@ TODO:
  
  	if (!replace && max_delete >= 0 && ++deletion_count > max_delete)
  		return DR_AT_LIMIT;
-@@ -208,6 +323,8 @@ static enum delret delete_item(char *fbu
+@@ -206,6 +322,8 @@ static enum delret delete_item(char *fbu
   * its contents, otherwise just checks for content.  Returns DR_SUCCESS or
   * DR_NOT_EMPTY.  Note that fname must point to a MAXPATHLEN buffer!  (The
   * buffer is used for recursion, but returned unchanged.)
@@ -317,7 +317,7 @@ TODO:
   */
  static enum delret delete_dir_contents(char *fname, int flags)
  {
-@@ -227,7 +344,9 @@ static enum delret delete_dir_contents(c
+@@ -225,7 +343,9 @@ static enum delret delete_dir_contents(c
  	save_filters = push_local_filters(fname, dlen);
  
  	non_perishable_cnt = 0;
@@ -327,7 +327,7 @@ TODO:
  	ret = non_perishable_cnt ? DR_NOT_EMPTY : DR_SUCCESS;
  
  	if (!dirlist->used)
-@@ -264,6 +383,8 @@ static enum delret delete_dir_contents(c
+@@ -262,6 +382,8 @@ static enum delret delete_dir_contents(c
  		if (S_ISDIR(fp->mode)
  		 && delete_dir_contents(fname, flags | DEL_RECURSE) != DR_SUCCESS)
  			ret = DR_NOT_EMPTY;
@@ -336,7 +336,7 @@ TODO:
  		if (delete_item(fname, fp->mode, NULL, flags) != DR_SUCCESS)
  			ret = DR_NOT_EMPTY;
  	}
-@@ -416,12 +537,17 @@ static void do_delayed_deletions(char *d
+@@ -414,13 +536,18 @@ static void do_delayed_deletions(char *d
   * all the --delete-WHEN options.  Note that the fbuf pointer must point to a
   * MAXPATHLEN buffer with the name of the directory in it (the functions we
   * call will append names onto the end, but the old dir value will be restored
@@ -352,12 +352,14 @@ TODO:
  	static int already_warned = 0;
  	struct file_list *dirlist;
 -	char delbuf[MAXPATHLEN];
+-	int dlen, i;
 +	char *p, delbuf[MAXPATHLEN];
 +	unsigned remainder;
- 	int dlen, i;
++	int dlen, i, restore_dot = 0;
  
  	if (!fbuf) {
-@@ -432,21 +558,28 @@ static void delete_in_dir(char *fbuf, st
+ 		change_local_filter_dir(NULL, 0, 0);
+@@ -430,21 +557,28 @@ static void delete_in_dir(char *fbuf, st
  	if (verbose > 2)
  		rprintf(FINFO, "delete_in_dir(%s)\n", fbuf);
  
@@ -391,19 +393,22 @@ TODO:
  	if (one_file_system) {
  		if (file->flags & FLAG_TOP_DIR)
  			filesystem_dev = *fs_dev;
-@@ -456,6 +589,11 @@ static void delete_in_dir(char *fbuf, st
+@@ -454,6 +588,14 @@ static void delete_in_dir(char *fbuf, st
  
  	dirlist = get_dirlist(fbuf, dlen, 0);
  
 +	p = fbuf + dlen;
-+	if (dlen != 1 || *fbuf != '/')
++	if (dlen == 1 && *fbuf == '.') {
++		restore_dot = 1;
++		p = fbuf;
++	} else if (dlen != 1 || *fbuf != '/')
 +		*p++ = '/';
 +	remainder = MAXPATHLEN - (p - fbuf);
 +
  	/* If an item in dirlist is not found in flist, delete it
  	 * from the filesystem. */
  	for (i = dirlist->used; i--; ) {
-@@ -468,16 +606,23 @@ static void delete_in_dir(char *fbuf, st
+@@ -466,16 +608,25 @@ static void delete_in_dir(char *fbuf, st
  					f_name(fp, NULL));
  			continue;
  		}
@@ -425,12 +430,14 @@ TODO:
 +			unexplored_dirs++;
  	}
  
++	if (restore_dot)
++		fbuf[0] = '.';
 +	fbuf[dlen] = '\0';
 +
  	flist_free(dirlist);
  }
  
-@@ -507,9 +652,9 @@ static void do_delete_pass(void)
+@@ -505,9 +656,9 @@ static void do_delete_pass(void)
  		 || !S_ISDIR(st.st_mode))
  			continue;
  
@@ -442,7 +449,7 @@ TODO:
  
  	if (do_progress && !am_server)
  		rprintf(FINFO, "                    \r");
-@@ -1101,6 +1246,7 @@ static void list_file_entry(struct file_
+@@ -1139,6 +1290,7 @@ static void list_file_entry(struct file_
  	}
  }
  
@@ -450,13 +457,13 @@ TODO:
  static int phase = 0;
  static int dflt_perms;
  
-@@ -1345,8 +1491,12 @@ static void recv_generator(char *fname, 
+@@ -1383,8 +1535,12 @@ static void recv_generator(char *fname, 
  			}
  		}
  		else if (delete_during && f_out != -1 && !phase && dry_run < 2
--		    && (file->flags & FLAG_XFER_DIR))
+-		    && (file->flags & FLAG_CONTENT_DIR))
 -			delete_in_dir(fname, file, &real_sx.st.st_dev);
-+		    && (file->flags & FLAG_XFER_DIR)) {
++		    && (file->flags & FLAG_CONTENT_DIR)) {
 +			if (detect_renamed && real_ret != 0)
 +				unexplored_dirs++;
 +			delete_in_dir(fname, file, &real_sx.st.st_dev,
@@ -465,7 +472,7 @@ TODO:
  		goto cleanup;
  	}
  
-@@ -1624,8 +1774,14 @@ static void recv_generator(char *fname, 
+@@ -1662,8 +1818,14 @@ static void recv_generator(char *fname, 
  			goto cleanup;
  		}
  #endif
@@ -481,7 +488,7 @@ TODO:
  		rsyserr(FERROR, stat_errno, "recv_generator: failed to stat %s",
  			full_fname(fname));
  		goto cleanup;
-@@ -1961,6 +2117,12 @@ void generate_files(int f_out, const cha
+@@ -2000,6 +2162,12 @@ void generate_files(int f_out, const cha
  	if (verbose > 2)
  		rprintf(FINFO, "generator starting pid=%ld\n", (long)getpid());
  
@@ -494,7 +501,7 @@ TODO:
  	if (delete_before && !solo_file && cur_flist->used > 0)
  		do_delete_pass();
  	if (delete_during == 2) {
-@@ -1971,7 +2133,7 @@ void generate_files(int f_out, const cha
+@@ -2010,7 +2178,7 @@ void generate_files(int f_out, const cha
  	}
  	do_progress = 0;
  
@@ -503,7 +510,7 @@ TODO:
  		whole_file = 0;
  	if (verbose >= 2) {
  		rprintf(FINFO, "delta-transmission %s\n",
-@@ -2009,7 +2171,7 @@ void generate_files(int f_out, const cha
+@@ -2048,7 +2216,7 @@ void generate_files(int f_out, const cha
  						dirdev = MAKEDEV(DEV_MAJOR(devp), DEV_MINOR(devp));
  					} else
  						dirdev = MAKEDEV(0, 0);
@@ -512,7 +519,7 @@ TODO:
  				}
  			}
  		}
-@@ -2054,7 +2216,21 @@ void generate_files(int f_out, const cha
+@@ -2091,7 +2259,21 @@ void generate_files(int f_out, const cha
  	} while ((cur_flist = cur_flist->next) != NULL);
  
  	if (delete_during)
@@ -561,7 +568,7 @@ TODO:
    {"fuzzy",           'y', POPT_ARG_NONE,   &fuzzy_basis, 0, 0, 0 },
    {"compress",        'z', POPT_ARG_NONE,   0, 'z', 0, 0 },
    {"no-compress",      0,  POPT_ARG_VAL,    &do_compression, 0, 0, 0 },
-@@ -1533,7 +1536,7 @@ int parse_arguments(int *argc_p, const c
+@@ -1532,7 +1535,7 @@ int parse_arguments(int *argc_p, const c
  		inplace = 1;
  	}
  
@@ -570,7 +577,7 @@ TODO:
  		partial_dir = tmp_partialdir;
  
  	if (inplace) {
-@@ -1542,6 +1545,7 @@ int parse_arguments(int *argc_p, const c
+@@ -1541,6 +1544,7 @@ int parse_arguments(int *argc_p, const c
  			snprintf(err_buf, sizeof err_buf,
  				 "--%s cannot be used with --%s\n",
  				 append_mode ? "append" : "inplace",
@@ -578,7 +585,7 @@ TODO:
  				 delay_updates ? "delay-updates" : "partial-dir");
  			return 0;
  		}
-@@ -1889,6 +1893,8 @@ void server_options(char **args, int *ar
+@@ -1885,6 +1889,8 @@ void server_options(char **args, int *ar
  			args[ac++] = "--super";
  		if (size_only)
  			args[ac++] = "--size-only";
@@ -589,7 +596,7 @@ TODO:
  			if (asprintf(&arg, "--skip-compress=%s", skip_compress) < 0)
 --- old/rsync.yo
 +++ new/rsync.yo
-@@ -389,6 +389,7 @@ to the detailed description below for a 
+@@ -384,6 +384,7 @@ to the detailed description below for a 
       --modify-window=NUM     compare mod-times with reduced accuracy
   -T, --temp-dir=DIR          create temporary files in directory DIR
   -y, --fuzzy                 find similar file for basis if no dest file
@@ -597,13 +604,19 @@ TODO:
       --compare-dest=DIR      also compare received files relative to DIR
       --copy-dest=DIR         ... and include copies of unchanged files
       --link-dest=DIR         hardlink to files in DIR when unchanged
-@@ -1417,6 +1418,15 @@ Note that the use of the bf(--delete) op
+@@ -1438,6 +1439,21 @@ Note that the use of the bf(--delete) op
  fuzzy-match files, so either use bf(--delete-after) or specify some
  filename exclusions if you need to prevent this.
  
-+dit(bf(--detect-renamed)) This option tells rsync to scan the receiving
-+side for files that have been renamed, and to use any that are found as
-+alternate basis files to help speed up the transfer.
++dit(bf(--detect-renamed)) With this option, for each new source file
++(call it em(src/S)), rsync looks for a file em(dest/D) anywhere in the
++destination that passes the quick check with em(src/S).  If such a em(dest/D)
++is found, rsync uses it as an alternate basis for transferring em(S).  The
++idea is that if em(src/S) was renamed from em(src/D) (as opposed to em(src/S)
++passing the quick check with em(dest/D) by coincidence), the delta-transfer
++algorithm will find that all the data matches between em(src/S) and em(dest/D),
++and the transfer will be really fast.
++
 +By default, alternate-basis files are hard-linked into a directory named
 +".~tmp~" in each file's destination directory, but if you've specified
 +the bf(--partial-dir) option, that directory will be used instead.  These
@@ -615,7 +628,7 @@ TODO:
  files against doing transfers (if the files are missing in the destination
 --- old/util.c
 +++ new/util.c
-@@ -1030,6 +1030,32 @@ int handle_partial_dir(const char *fname
+@@ -1042,6 +1042,32 @@ int handle_partial_dir(const char *fname
  	return 1;
  }