--- embedaddon/rsync/generator.c 2012/02/17 15:09:30 1.1.1.1 +++ embedaddon/rsync/generator.c 2013/07/22 00:20:20 1.1.1.1.2.1 @@ -78,6 +78,7 @@ extern char *basis_dir[MAX_BASIS_DIRS+1]; extern int compare_dest; extern int copy_dest; extern int link_dest; +extern int detect_renamed; extern int whole_file; extern int list_only; extern int read_batch; @@ -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 daemon_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; static dev_t dev_zero; static int deletion_count = 0; /* used to implement --max-delete */ +static int unexplored_dirs = 1; static int deldelay_size = 0, deldelay_cnt = 0; static char *deldelay_buf = NULL; static int deldelay_fd = -1; @@ -113,7 +116,7 @@ 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(). */ +/* For calling delete_item(), delete_dir_contents(), and delete_in_dir(). */ #define DEL_NO_UID_WRITE (1<<0) /* file/dir has our uid w/o write perm */ #define DEL_RECURSE (1<<1) /* if dir, delete all contents */ #define DEL_DIR_IS_EMPTY (1<<2) /* internal delete_FUNCTIONS use only */ @@ -122,6 +125,7 @@ static const char *solo_file = NULL; #define DEL_FOR_SYMLINK (1<<5) /* making room for a replacement symlink */ #define DEL_FOR_DEVICE (1<<6) /* making room for a replacement device */ #define DEL_FOR_SPECIAL (1<<7) /* making room for a replacement special */ +#define DEL_NO_DELETIONS (1<<9) /* just check for renames w/o deleting */ #define DEL_MAKE_ROOM (DEL_FOR_FILE|DEL_FOR_DIR|DEL_FOR_SYMLINK|DEL_FOR_DEVICE|DEL_FOR_SPECIAL) @@ -146,11 +150,121 @@ static int is_backup_file(char *fn) return k > 0 && strcmp(fn+k, backup_suffix) == 0; } +/* Search for a regular file that matches either (1) the size & modified + * time (plus the basename, if possible) or (2) the size & checksum. If + * we find an exact match down to the dirname, return -1 because we found + * an up-to-date file in the transfer, not a renamed file. */ +static int fattr_find(struct file_struct *f, char *fname) +{ + int low = the_fattr_list.low, high = the_fattr_list.high; + int mid, ok_match = -1, good_match = -1; + struct file_struct *fmid; + int diff; + + while (low <= high) { + mid = (low + high) / 2; + fmid = the_fattr_list.files[mid]; + if (F_LENGTH(fmid) != F_LENGTH(f)) { + if (F_LENGTH(fmid) < F_LENGTH(f)) + low = mid + 1; + else + high = mid - 1; + continue; + } + if (always_checksum) { + /* We use the FLAG_FILE_SENT flag to indicate when we + * have computed the checksum for an entry. */ + 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, F_SUM(f), F_LENGTH(f)); + f->flags |= FLAG_FILE_SENT; + } + diff = u_memcmp(F_SUM(fmid), F_SUM(f), checksum_len); + if (diff) { + if (diff < 0) + low = mid + 1; + else + high = mid - 1; + continue; + } + } else { + if (fmid->modtime != f->modtime) { + if (fmid->modtime < f->modtime) + low = mid + 1; + else + high = mid - 1; + continue; + } + } + ok_match = mid; + diff = u_strcmp(fmid->basename, f->basename); + if (diff == 0) { + good_match = mid; + if (fmid->dirname == f->dirname) + return -1; /* file is up-to-date */ + if (!fmid->dirname) { + low = mid + 1; + continue; + } + if (!f->dirname) { + high = mid - 1; + continue; + } + diff = u_strcmp(fmid->dirname, f->dirname); + if (diff == 0) + return -1; /* file is up-to-date */ + } + if (diff < 0) + low = mid + 1; + else + high = mid - 1; + } + + return good_match >= 0 ? good_match : ok_match; +} + +static void look_for_rename(struct file_struct *file, char *fname) +{ + struct file_struct *fp; + char *partialptr, *fn; + STRUCT_STAT st; + int ndx; + + if (!partial_dir || (ndx = fattr_find(file, fname)) < 0) + return; + + fp = the_fattr_list.files[ndx]; + fn = f_name(fp, NULL); + /* We don't provide an alternate-basis file if there is a basis file. */ + if (link_stat(fn, &st, 0) == 0) + return; + + 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; + } + } + + /* 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 * delete recursively. * * Note that fbuf must point to a MAXPATHLEN buffer if the mode indicates it's * a directory! (The buffer is used for recursion, but returned unchanged.) + * + * Also note: --detect-rename may use this routine with DEL_NO_DELETIONS set! */ static enum delret delete_item(char *fbuf, uint16 mode, uint16 flags) { @@ -177,6 +291,8 @@ static enum delret delete_item(char *fbuf, uint16 mode goto check_ret; /* OK: try to delete the directory. */ } + if (flags & DEL_NO_DELETIONS) + return DR_SUCCESS; if (!(flags & DEL_MAKE_ROOM) && max_delete >= 0 && ++deletion_count > max_delete) return DR_AT_LIMIT; @@ -232,6 +348,8 @@ static enum delret delete_item(char *fbuf, uint16 mode * 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.) + * + * Note: --detect-rename may use this routine with DEL_NO_DELETIONS set! */ static enum delret delete_dir_contents(char *fname, uint16 flags) { @@ -251,7 +369,9 @@ static enum delret delete_dir_contents(char *fname, ui save_filters = push_local_filters(fname, dlen); non_perishable_cnt = 0; + file_extra_cnt += SUM_EXTRA_CNT; dirlist = get_dirlist(fname, dlen, 0); + file_extra_cnt -= SUM_EXTRA_CNT; ret = non_perishable_cnt ? DR_NOT_EMPTY : DR_SUCCESS; if (!dirlist->used) @@ -291,7 +411,8 @@ static enum delret delete_dir_contents(char *fname, ui if (S_ISDIR(fp->mode)) { if (delete_dir_contents(fname, flags | DEL_RECURSE) != DR_SUCCESS) ret = DR_NOT_EMPTY; - } + } else if (detect_renamed && S_ISREG(fp->mode)) + look_for_rename(fp, fname); if (delete_item(fname, fp->mode, flags) != DR_SUCCESS) ret = DR_NOT_EMPTY; } @@ -456,13 +577,18 @@ static void do_delayed_deletions(char *delbuf) * 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(char *fbuf, struct file_struct *file, dev_t *fs_dev, + int del_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, restore_dot = 0; if (!fbuf) { change_local_filter_dir(NULL, 0, 0); @@ -476,17 +602,22 @@ static void delete_in_dir(char *fbuf, struct file_stru maybe_send_keepalive(); if (io_error && !ignore_errors) { - if (already_warned) + if (!already_warned) { + rprintf(FINFO, + "IO error encountered -- skipping file deletion\n"); + already_warned = 1; + } + if (!detect_renamed) return; - rprintf(FINFO, - "IO error encountered -- skipping file deletion\n"); - already_warned = 1; - return; + del_flags |= DEL_NO_DELETIONS; } dlen = strlen(fbuf); change_local_filter_dir(fbuf, dlen, F_DEPTH(file)); + if (detect_renamed) + unexplored_dirs--; + if (one_file_system) { if (file->flags & FLAG_TOP_DIR) filesystem_dev = *fs_dev; @@ -496,6 +627,14 @@ static void delete_in_dir(char *fbuf, struct file_stru dirlist = get_dirlist(fbuf, dlen, 0); + p = fbuf + dlen; + 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--; ) { @@ -508,6 +647,10 @@ static void delete_in_dir(char *fbuf, struct file_stru f_name(fp, NULL)); continue; } + if (detect_renamed && S_ISREG(fp->mode)) { + strlcpy(p, fp->basename, remainder); + look_for_rename(fp, fbuf); + } /* Here we want to match regardless of file type. Replacement * of a file with one of another type is handled separately by * a delete_item call with a DEL_MAKE_ROOM flag. */ @@ -516,14 +659,19 @@ static void delete_in_dir(char *fbuf, struct file_stru if (!(fp->mode & S_IWUSR) && !am_root && fp->flags & FLAG_OWNED_BY_US) flags |= DEL_NO_UID_WRITE; f_name(fp, delbuf); - if (delete_during == 2) { - if (!remember_delete(fp, delbuf, flags)) + if (delete_during == 2 && !(del_flags & DEL_NO_DELETIONS)) { + if (!remember_delete(fp, delbuf, del_flags | flags)) break; } else - delete_item(delbuf, fp->mode, flags); - } + delete_item(delbuf, fp->mode, del_flags | flags); + } else if (detect_renamed && S_ISDIR(fp->mode)) + unexplored_dirs++; } + if (restore_dot) + fbuf[0] = '.'; + fbuf[dlen] = '\0'; + flist_free(dirlist); } @@ -556,9 +704,9 @@ static void do_delete_pass(void) || !S_ISDIR(st.st_mode)) continue; - delete_in_dir(fbuf, file, &st.st_dev); + delete_in_dir(fbuf, file, &st.st_dev, 0); } - delete_in_dir(NULL, NULL, &dev_zero); + delete_in_dir(NULL, NULL, &dev_zero, 0); if (do_progress && !am_server) rprintf(FINFO, " \r"); @@ -1269,6 +1417,7 @@ static void list_file_entry(struct file_struct *f) } } +static struct bitbag *delayed_bits = NULL; static int phase = 0; static int dflt_perms; @@ -1558,9 +1707,12 @@ static void recv_generator(char *fname, struct file_st } else if (delete_during && f_out != -1 && !phase && !(file->flags & FLAG_MISSING_DIR)) { - if (file->flags & FLAG_CONTENT_DIR) - delete_in_dir(fname, file, &real_sx.st.st_dev); - else + if (file->flags & FLAG_CONTENT_DIR) { + if (detect_renamed && real_ret != 0) + unexplored_dirs++; + delete_in_dir(fname, file, &real_sx.st.st_dev, + delete_during < 0 ? DEL_NO_DELETIONS : 0); + } else change_local_filter_dir(fname, strlen(fname), F_DEPTH(file)); } goto cleanup; @@ -1844,8 +1996,14 @@ static void recv_generator(char *fname, struct file_st goto cleanup; } #endif - if (stat_errno == ENOENT) + if (stat_errno == ENOENT) { + if (detect_renamed && unexplored_dirs > 0 + && F_LENGTH(file)) { + bitbag_set_bit(delayed_bits, ndx); + return; + } goto notify_others; + } rsyserr(FERROR_XFER, stat_errno, "recv_generator: failed to stat %s", full_fname(fname)); goto cleanup; @@ -2254,6 +2412,12 @@ void generate_files(int f_out, const char *local_name) if (verbose > 2) rprintf(FINFO, "generator starting pid=%ld\n", (long)getpid()); + if (detect_renamed) { + delayed_bits = bitbag_create(cur_flist->used); + if (!delete_before && !delete_during) + delete_during = -1; + } + if (delete_before && !solo_file && cur_flist->used > 0) do_delete_pass(); if (delete_during == 2) { @@ -2264,7 +2428,7 @@ void generate_files(int f_out, const char *local_name) } do_progress = 0; - if (append_mode > 0 || whole_file < 0) + if (append_mode > 0 || detect_renamed || whole_file < 0) whole_file = 0; if (verbose >= 2) { rprintf(FINFO, "delta-transmission %s\n", @@ -2306,7 +2470,7 @@ void generate_files(int f_out, const char *local_name) dirdev = MAKEDEV(DEV_MAJOR(devp), DEV_MINOR(devp)); } else dirdev = MAKEDEV(0, 0); - delete_in_dir(fbuf, fp, &dirdev); + delete_in_dir(fbuf, fp, &dirdev, 0); } else change_local_filter_dir(fbuf, strlen(fbuf), F_DEPTH(fp)); } @@ -2353,7 +2517,21 @@ void generate_files(int f_out, const char *local_name) } while ((cur_flist = cur_flist->next) != NULL); if (delete_during) - 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 = cur_flist->files[i]; + if (local_name) + strlcpy(fbuf, local_name, sizeof fbuf); + else + f_name(file, fbuf); + recv_generator(fbuf, file, i, itemizing, code, f_out); + } + } phase++; if (verbose > 2) rprintf(FINFO, "generate_files phase=%d\n", phase);