From 6fa0767f0e3c9ec869f45f647d7018f37dc7410b Mon Sep 17 00:00:00 2001 From: Wayne Davison Date: Fri, 12 Oct 2007 22:12:29 +0000 Subject: [PATCH] Fixes from Matt. --- detect-renamed.diff | 117 +++++++++++++++++++++++++------------------- 1 file changed, 66 insertions(+), 51 deletions(-) diff --git a/detect-renamed.diff b/detect-renamed.diff index de09a23..a6c17d1 100644 --- a/detect-renamed.diff +++ b/detect-renamed.diff @@ -116,9 +116,9 @@ TODO: static void send_directory(int f, struct file_list *flist, char *fbuf, int len, int flags); -@@ -2034,6 +2076,25 @@ struct file_list *send_file_list(int f, - if (verbose > 2) - rprintf(FINFO, "send_file_list done\n"); +@@ -2154,6 +2196,25 @@ struct file_list *recv_file_list(int f) + + clean_flist(flist, relative_paths); + if (detect_renamed) { + int j = flist->used; @@ -139,9 +139,9 @@ 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[]; @@ -178,7 +178,7 @@ 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) +@@ -136,11 +140,121 @@ static int is_backup_file(char *fn) return k > 0 && strcmp(fn+k, backup_suffix) == 0; } @@ -264,7 +264,7 @@ 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 +272,22 @@ 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 +300,7 @@ 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 +@@ -162,6 +276,8 @@ static enum delret delete_item(char *fbu goto check_ret; /* OK: try to delete the directory. */ } @@ -308,7 +309,7 @@ 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 +@@ -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.) @@ -317,7 +318,7 @@ TODO: */ static enum delret delete_dir_contents(char *fname, int flags) { -@@ -227,7 +344,9 @@ 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; @@ -327,7 +328,7 @@ TODO: ret = non_perishable_cnt ? DR_NOT_EMPTY : DR_SUCCESS; if (!dirlist->used) -@@ -264,6 +383,8 @@ static enum delret delete_dir_contents(c +@@ -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; @@ -336,7 +337,7 @@ 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 +@@ -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 @@ -352,12 +353,14 @@ 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); +@@ -432,21 +559,28 @@ static void delete_in_dir(char *fbuf, st if (verbose > 2) rprintf(FINFO, "delete_in_dir(%s)\n", fbuf); @@ -391,19 +394,22 @@ 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 +@@ -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->used; i--; ) { -@@ -468,16 +606,23 @@ static void delete_in_dir(char *fbuf, st +@@ -468,16 +610,25 @@ static void delete_in_dir(char *fbuf, st f_name(fp, NULL)); continue; } @@ -425,12 +431,14 @@ TODO: + unexplored_dirs++; } ++ if (restore_dot) ++ fbuf[0] = '.'; + fbuf[dlen] = '\0'; + flist_free(dirlist); } -@@ -507,9 +652,9 @@ static void do_delete_pass(void) +@@ -507,9 +658,9 @@ static void do_delete_pass(void) || !S_ISDIR(st.st_mode)) continue; @@ -442,7 +450,7 @@ TODO: if (do_progress && !am_server) rprintf(FINFO, " \r"); -@@ -1101,6 +1246,7 @@ static void list_file_entry(struct file_ +@@ -1101,6 +1252,7 @@ static void list_file_entry(struct file_ } } @@ -450,7 +458,7 @@ TODO: static int phase = 0; static int dflt_perms; -@@ -1345,8 +1491,12 @@ static void recv_generator(char *fname, +@@ -1345,8 +1497,12 @@ static void recv_generator(char *fname, } } else if (delete_during && f_out != -1 && !phase && dry_run < 2 @@ -465,7 +473,7 @@ TODO: goto cleanup; } -@@ -1624,8 +1774,14 @@ static void recv_generator(char *fname, +@@ -1624,8 +1780,14 @@ static void recv_generator(char *fname, goto cleanup; } #endif @@ -481,7 +489,7 @@ 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 +@@ -1961,6 +2123,12 @@ void generate_files(int f_out, const cha if (verbose > 2) rprintf(FINFO, "generator starting pid=%ld\n", (long)getpid()); @@ -494,7 +502,7 @@ 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 +@@ -1971,7 +2139,7 @@ void generate_files(int f_out, const cha } do_progress = 0; @@ -503,7 +511,7 @@ 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 +@@ -2009,7 +2177,7 @@ void generate_files(int f_out, const cha dirdev = MAKEDEV(DEV_MAJOR(devp), DEV_MINOR(devp)); } else dirdev = MAKEDEV(0, 0); @@ -512,7 +520,7 @@ TODO: } } } -@@ -2054,7 +2216,21 @@ void generate_files(int f_out, const cha +@@ -2054,7 +2222,21 @@ void generate_files(int f_out, const cha } while ((cur_flist = cur_flist->next) != NULL); if (delete_during) @@ -578,18 +586,19 @@ TODO: delay_updates ? "delay-updates" : "partial-dir"); return 0; } -@@ -1883,6 +1887,8 @@ void server_options(char **args, int *ar - args[ac++] = "--super"; - if (size_only) - args[ac++] = "--size-only"; -+ if (detect_renamed) -+ args[ac++] = "--detect-renamed"; - } else { - if (skip_compress) { - if (asprintf(&arg, "--skip-compress=%s", skip_compress) < 0) +@@ -1890,6 +1894,9 @@ void server_options(char **args, int *ar + args[ac++] = arg; + } + } ++ /* Both sides need to know in case this disables incremental recursion. */ ++ if (detect_renamed) ++ args[ac++] = "--detect-renamed"; + + if (modify_window_set) { + if (asprintf(&arg, "--modify-window=%d", modify_window) < 0) --- old/rsync.yo +++ new/rsync.yo -@@ -385,6 +385,7 @@ 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 +606,19 @@ 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 -@@ -1425,6 +1426,15 @@ Note that the use of the bf(--delete) op +@@ -1424,6 +1425,21 @@ 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 -- 2.34.1