a file that can't use it, while missing out on giving it to a file
that could use it.
+--- old/compat.c
++++ new/compat.c
+@@ -41,6 +41,7 @@ extern int checksum_seed;
+ extern int basis_dir_cnt;
+ extern int prune_empty_dirs;
+ extern int protocol_version;
++extern int detect_renamed;
+ extern int protect_args;
+ extern int preserve_uid;
+ extern int preserve_gid;
+@@ -108,6 +109,7 @@ 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
-@@ -57,6 +57,7 @@ extern int non_perishable_cnt;
+@@ -61,6 +61,7 @@ extern int non_perishable_cnt;
extern int prune_empty_dirs;
extern int copy_links;
extern int copy_unsafe_links;
extern int protocol_version;
extern int sanitize_paths;
extern struct stats stats;
-@@ -87,6 +88,8 @@ static int64 tmp_dev, tmp_ino;
+@@ -113,6 +114,8 @@ static int64 tmp_dev, tmp_ino;
#endif
- static char tmp_sum[MD4_SUM_LENGTH];
+ static char tmp_sum[MAX_DIGEST_LEN];
+struct file_list the_fattr_list;
+
- static char empty_sum[MD4_SUM_LENGTH];
+ static char empty_sum[MAX_DIGEST_LEN];
static int flist_count_offset; /* for --delete --progress */
-
-@@ -271,6 +274,45 @@ static mode_t from_wire_mode(int mode)
- return mode;
+ static int dir_count = 0;
+@@ -252,6 +255,45 @@ static int is_excluded(char *fname, int
+ return 0;
}
+static int fattr_compare(struct file_struct **file1, struct file_struct **file2)
+ return u_strcmp(f1->dirname, f2->dirname);
+}
+
- static void send_directory(int f, struct file_list *flist, int ndx,
+ static void send_directory(int f, struct file_list *flist,
char *fbuf, int len, int flags);
-@@ -1744,6 +1786,25 @@ struct file_list *recv_file_list(int f)
+@@ -2154,6 +2196,25 @@ struct file_list *recv_file_list(int f)
- clean_flist(flist, relative_paths, 1);
+ clean_flist(flist, relative_paths);
+ if (detect_renamed) {
-+ int j = flist->count;
-+ the_fattr_list.count = j;
++ int j = flist->used;
++ the_fattr_list.used = j;
+ the_fattr_list.files = new_array(struct file_struct *, j);
+ if (!the_fattr_list.files)
+ out_of_memory("recv_file_list");
+ the_fattr_list.high = j;
+ }
+
- if (inc_recurse) {
- qsort(dir_flist->files + dstart, dir_flist->count - dstart,
- sizeof dir_flist->files[0], (int (*)())file_compare);
+ 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[];
+extern int detect_renamed;
extern int whole_file;
extern int list_only;
- extern int new_root_dir;
-@@ -96,6 +97,7 @@ extern char *backup_suffix;
+ extern int read_batch;
+@@ -95,6 +96,7 @@ 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;
-
- int ignore_perishable = 0;
- int non_perishable_cnt = 0;
-@@ -103,6 +105,7 @@ int maybe_ATTRS_REPORT = 0;
+ #ifdef ICONV_OPTION
+ extern int ic_ndx;
+ #endif
+@@ -105,6 +107,7 @@ int maybe_ATTRS_REPORT = 0;
static dev_t dev_zero;
static int deletion_count = 0; /* used to implement --max-delete */
static int deldelay_size = 0, deldelay_cnt = 0;
static char *deldelay_buf = NULL;
static int deldelay_fd = -1;
-@@ -111,7 +114,8 @@ static int dir_tweaking;
- static int need_retouch_dir_times;
+@@ -114,7 +117,8 @@ static int need_retouch_dir_times;
+ static int need_retouch_dir_perms;
static const char *solo_file = NULL;
-/* For calling delete_item() and delete_dir_contents(). */
#define DEL_RECURSE (1<<1) /* recurse */
#define DEL_DIR_IS_EMPTY (1<<2) /* internal delete_FUNCTIONS use only */
-@@ -133,11 +137,120 @@ static int is_backup_file(char *fn)
+@@ -136,11 +140,121 @@ static int is_backup_file(char *fn)
return k > 0 && strcmp(fn+k, backup_suffix) == 0;
}
+ continue;
+ }
+ if (always_checksum) {
-+ /* We use the FLAG_SENT flag to indicate when we
++ /* We use the FLAG_FILE_SENT flag to indicate when we
+ * have computed the checksum for an entry. */
-+ if (!(f->flags & FLAG_SENT)) {
++ if (!(f->flags & FLAG_FILE_SENT)) {
+ if (fmid->modtime == f->modtime
+ && f_name_cmp(fmid, f) == 0)
+ return -1; /* assume we can't help */
-+ file_checksum(fname, (char*)F_SUM(f), F_LENGTH(f));
-+ f->flags |= FLAG_SENT;
++ file_checksum(fname, F_SUM(f), F_LENGTH(f));
++ f->flags |= FLAG_FILE_SENT;
+ }
+ diff = u_memcmp(F_SUM(fmid), F_SUM(f), checksum_len);
+ if (diff) {
+ 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];
+ /* 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
*/
static enum delret delete_item(char *fbuf, int mode, char *replace, int flags)
{
-@@ -159,6 +272,8 @@ static enum delret delete_item(char *fbu
+@@ -162,6 +276,8 @@ static enum delret delete_item(char *fbu
goto check_ret;
/* OK: try to delete the directory. */
}
if (!replace && max_delete >= 0 && ++deletion_count > max_delete)
return DR_AT_LIMIT;
-@@ -205,6 +320,8 @@ static enum delret delete_item(char *fbu
+@@ -208,6 +324,8 @@ 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.)
*/
static enum delret delete_dir_contents(char *fname, int flags)
{
-@@ -224,7 +341,9 @@ static enum delret delete_dir_contents(c
+@@ -227,7 +345,9 @@ static enum delret delete_dir_contents(c
save_filters = push_local_filters(fname, dlen);
non_perishable_cnt = 0;
+ file_extra_cnt -= SUM_EXTRA_CNT;
ret = non_perishable_cnt ? DR_NOT_EMPTY : DR_SUCCESS;
- if (!dirlist->count)
-@@ -261,6 +380,8 @@ static enum delret delete_dir_contents(c
+ if (!dirlist->used)
+@@ -264,6 +384,8 @@ 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;
if (delete_item(fname, fp->mode, NULL, flags) != DR_SUCCESS)
ret = DR_NOT_EMPTY;
}
-@@ -413,13 +534,17 @@ static void do_delayed_deletions(char *d
+@@ -416,13 +538,18 @@ 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
- * on exit). */
+-static void delete_in_dir(char *fbuf, struct file_struct *file, dev_t *fs_dev)
+ * on exit).
+ *
+ * Note: --detect-rename may use this routine with DEL_NO_DELETIONS set!
+ */
- static void delete_in_dir(struct file_list *flist, char *fbuf,
-- struct file_struct *file, dev_t *fs_dev)
-+ struct file_struct *file, dev_t *fs_dev, int flags)
++static void delete_in_dir(char *fbuf, struct file_struct *file, dev_t *fs_dev,
++ int flags)
{
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 (!flist) {
-@@ -430,21 +555,28 @@ static void delete_in_dir(struct file_li
+ if (!fbuf) {
+ change_local_filter_dir(NULL, 0, 0);
+@@ -432,21 +559,28 @@ static void delete_in_dir(char *fbuf, st
if (verbose > 2)
rprintf(FINFO, "delete_in_dir(%s)\n", fbuf);
if (one_file_system) {
if (file->flags & FLAG_TOP_DIR)
filesystem_dev = *fs_dev;
-@@ -454,6 +586,11 @@ static void delete_in_dir(struct file_li
+@@ -456,6 +590,14 @@ 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->count; i--; ) {
-@@ -466,16 +603,23 @@ static void delete_in_dir(struct file_li
+ for (i = dirlist->used; i--; ) {
+@@ -468,16 +610,25 @@ static void delete_in_dir(char *fbuf, st
f_name(fp, NULL));
continue;
}
+ strlcpy(p, fp->basename, remainder);
+ look_for_rename(fp, fbuf);
+ }
- if (flist_find(flist, fp) < 0) {
+ if (flist_find(cur_flist, fp) < 0) {
f_name(fp, delbuf);
- if (delete_during == 2) {
+ if (delete_during == 2 && !(flags & DEL_NO_DELETIONS)) {
+ unexplored_dirs++;
}
++ if (restore_dot)
++ fbuf[0] = '.';
+ fbuf[dlen] = '\0';
+
flist_free(dirlist);
}
-@@ -505,9 +649,9 @@ static void do_delete_pass(struct file_l
+@@ -507,9 +658,9 @@ static void do_delete_pass(void)
|| !S_ISDIR(st.st_mode))
continue;
-- delete_in_dir(flist, fbuf, file, &st.st_dev);
-+ delete_in_dir(flist, fbuf, file, &st.st_dev, 0);
+- delete_in_dir(fbuf, file, &st.st_dev);
++ delete_in_dir(fbuf, file, &st.st_dev, 0);
}
-- delete_in_dir(NULL, NULL, NULL, &dev_zero);
-+ delete_in_dir(NULL, NULL, NULL, &dev_zero, 0);
+- delete_in_dir(NULL, NULL, &dev_zero);
++ delete_in_dir(NULL, NULL, &dev_zero, 0);
if (do_progress && !am_server)
rprintf(FINFO, " \r");
-@@ -1041,6 +1185,7 @@ static int try_dests_non(struct file_str
- return j;
+@@ -1106,6 +1257,7 @@ static void list_file_entry(struct file_
+ }
}
+static struct bitbag *delayed_bits = NULL;
static int phase = 0;
static int dflt_perms;
-@@ -1237,8 +1382,12 @@ static void recv_generator(char *fname,
+@@ -1350,8 +1502,12 @@ static void recv_generator(char *fname,
}
}
else if (delete_during && f_out != -1 && !phase && dry_run < 2
-- && (file->flags & FLAG_XFER_DIR))
-- delete_in_dir(cur_flist, fname, file, &real_sx.st.st_dev);
-+ && (file->flags & FLAG_XFER_DIR)) {
+- && (file->flags & FLAG_CONTENT_DIR))
+- delete_in_dir(fname, file, &real_sx.st.st_dev);
++ && (file->flags & FLAG_CONTENT_DIR)) {
+ if (detect_renamed && real_ret != 0)
+ unexplored_dirs++;
-+ delete_in_dir(cur_flist, fname, file, &real_sx.st.st_dev,
++ delete_in_dir(fname, file, &real_sx.st.st_dev,
+ delete_during < 0 ? DEL_NO_DELETIONS : 0);
+ }
goto cleanup;
}
-@@ -1510,8 +1659,14 @@ static void recv_generator(char *fname,
- if (preserve_hard_links && F_HLINK_NOT_LAST(file))
+@@ -1629,8 +1785,14 @@ static void recv_generator(char *fname,
goto cleanup;
+ }
#endif
- if (stat_errno == ENOENT)
+ if (stat_errno == ENOENT) {
rsyserr(FERROR, stat_errno, "recv_generator: failed to stat %s",
full_fname(fname));
goto cleanup;
-@@ -1818,6 +1973,12 @@ void generate_files(int f_out, const cha
+@@ -1966,6 +2128,12 @@ void generate_files(int f_out, const cha
if (verbose > 2)
rprintf(FINFO, "generator starting pid=%ld\n", (long)getpid());
+ if (detect_renamed) {
-+ delayed_bits = bitbag_create(flist->count);
++ delayed_bits = bitbag_create(cur_flist->used);
+ if (!delete_before && !delete_during)
+ delete_during = -1;
+ }
+
- if (delete_before && !solo_file && cur_flist->count > 0)
- do_delete_pass(cur_flist);
+ if (delete_before && !solo_file && cur_flist->used > 0)
+ do_delete_pass();
if (delete_during == 2) {
-@@ -1828,7 +1989,7 @@ void generate_files(int f_out, const cha
+@@ -1976,7 +2144,7 @@ void generate_files(int f_out, const cha
}
do_progress = 0;
whole_file = 0;
if (verbose >= 2) {
rprintf(FINFO, "delta-transmission %s\n",
-@@ -1855,7 +2016,7 @@ void generate_files(int f_out, const cha
- dirdev = MAKEDEV(DEV_MAJOR(devp), DEV_MINOR(devp));
- } else
- dirdev = MAKEDEV(0, 0);
-- delete_in_dir(cur_flist, f_name(fp, fbuf), fp, &dirdev);
-+ delete_in_dir(cur_flist, f_name(fp, fbuf), fp, &dirdev, 0);
+@@ -2014,7 +2182,7 @@ void generate_files(int f_out, const cha
+ dirdev = MAKEDEV(DEV_MAJOR(devp), DEV_MINOR(devp));
+ } else
+ dirdev = MAKEDEV(0, 0);
+- delete_in_dir(f_name(fp, fbuf), fp, &dirdev);
++ delete_in_dir(f_name(fp, fbuf), fp, &dirdev, 0);
+ }
}
}
- for (i = cur_flist->low; i <= cur_flist->high; i++) {
-@@ -1909,7 +2070,21 @@ void generate_files(int f_out, const cha
+@@ -2059,7 +2227,21 @@ void generate_files(int f_out, const cha
} while ((cur_flist = cur_flist->next) != NULL);
if (delete_during)
-- delete_in_dir(NULL, NULL, NULL, &dev_zero);
-+ delete_in_dir(NULL, NULL, NULL, &dev_zero, 0);
+- delete_in_dir(NULL, NULL, &dev_zero);
++ delete_in_dir(NULL, NULL, &dev_zero, 0);
+ if (detect_renamed) {
+ if (delete_during < 0)
+ delete_during = 0;
+ detect_renamed = 0;
+
+ for (i = -1; (i = bitbag_next_bit(delayed_bits, i)) >= 0; ) {
-+ struct file_struct *file = flist->files[i];
++ struct file_struct *file = cur_flist->files[i];
+ if (local_name)
+ strlcpy(fbuf, local_name, sizeof fbuf);
+ else
rprintf(FINFO, "generate_files phase=%d\n", phase);
--- old/options.c
+++ new/options.c
-@@ -78,6 +78,7 @@ int am_generator = 0;
+@@ -80,6 +80,7 @@ int am_generator = 0;
int am_starting_up = 1;
int relative_paths = -1;
int implied_dirs = 1;
int numeric_ids = 0;
int allow_8bit_chars = 0;
int force_delete = 0;
-@@ -351,6 +352,7 @@ void usage(enum logcode F)
+@@ -383,6 +384,7 @@ void usage(enum logcode F)
rprintf(F," --modify-window=NUM compare mod-times with reduced accuracy\n");
rprintf(F," -T, --temp-dir=DIR create temporary files in directory DIR\n");
rprintf(F," -y, --fuzzy find similar file for basis if no dest file\n");
rprintf(F," --compare-dest=DIR also compare destination files relative to DIR\n");
rprintf(F," --copy-dest=DIR ... and include copies of unchanged files\n");
rprintf(F," --link-dest=DIR hardlink to files in DIR when unchanged\n");
-@@ -508,6 +510,7 @@ static struct poptOption long_options[]
+@@ -561,6 +563,7 @@ static struct poptOption long_options[]
{"compare-dest", 0, POPT_ARG_STRING, 0, OPT_COMPARE_DEST, 0, 0 },
{"copy-dest", 0, POPT_ARG_STRING, 0, OPT_COPY_DEST, 0, 0 },
{"link-dest", 0, POPT_ARG_STRING, 0, OPT_LINK_DEST, 0, 0 },
+ {"detect-renamed", 0, POPT_ARG_NONE, &detect_renamed, 0, 0, 0 },
{"fuzzy", 'y', POPT_ARG_NONE, &fuzzy_basis, 0, 0, 0 },
{"compress", 'z', POPT_ARG_NONE, 0, 'z', 0, 0 },
- {"compress-level", 0, POPT_ARG_INT, &def_compress_level, 'z', 0, 0 },
-@@ -1397,7 +1400,7 @@ int parse_arguments(int *argc, const cha
+ {"no-compress", 0, POPT_ARG_VAL, &do_compression, 0, 0, 0 },
+@@ -1532,7 +1535,7 @@ int parse_arguments(int *argc_p, const c
inplace = 1;
}
partial_dir = tmp_partialdir;
if (inplace) {
-@@ -1406,6 +1409,7 @@ int parse_arguments(int *argc, const cha
+@@ -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",
delay_updates ? "delay-updates" : "partial-dir");
return 0;
}
-@@ -1719,6 +1723,8 @@ void server_options(char **args,int *arg
+@@ -1885,6 +1889,8 @@ void server_options(char **args, int *ar
args[ac++] = "--super";
if (size_only)
args[ac++] = "--size-only";
+ if (detect_renamed)
+ args[ac++] = "--detect-renamed";
- }
-
- if (modify_window_set) {
+ } else {
+ if (skip_compress) {
+ if (asprintf(&arg, "--skip-compress=%s", skip_compress) < 0)
--- old/rsync.yo
+++ new/rsync.yo
-@@ -365,6 +365,7 @@ 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
--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
-@@ -1305,6 +1306,15 @@ Note that the use of the bf(--delete) op
+@@ -1430,6 +1431,21 @@ 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
files against doing transfers (if the files are missing in the destination
--- old/util.c
+++ new/util.c
-@@ -1026,6 +1026,32 @@ int handle_partial_dir(const char *fname
+@@ -1030,6 +1030,32 @@ int handle_partial_dir(const char *fname
return 1;
}
Matt McCutchen's Web Site / rsync / rsync-patches.git / blobdiff