Updated patches to work with the current trunk.

[rsync/rsync-patches.git] / detect-renamed-lax.diff

This patch adds the options --detect-renamed-lax and --detect-moved.
These modify the --detect-renamed algorithm to adopt a matching file
without verifying that the content is as expected.  The former blindly
accepts a file that matches in size and modified time.  The latter
requires that the filename also match (ignoring any renamed files).

This patch is EXPERIMENTAL, though it did work correctly in my light
testing.

To use this patch, run these commands for a successful build:

    patch -p1 <patches/detect-renamed.diff
    patch -p1 <patches/detect-renamed-lax.diff
    ./configure                                 (optional if already run)
    make

FIXME: If a run with --detect-renamed-lax stages a different-basename
destination file and then gets interrupted, a subsequent run that
switches to --detect-moved blindly accepts the staged file.

-- Matt McCutchen <hashproduct+rsync@gmail.com>

diff --git a/generator.c b/generator.c
index 35ba203..ac844ac 100644
--- a/generator.c
+++ b/generator.c
@@ -469,7 +469,9 @@ static int fattr_find(struct file_struct *f, char *fname)
 				continue;
 			}
 		}
-		ok_match = mid;
+		/* --detect-moved doesn't allow non-basename matches */
+		if (detect_renamed != 3)
+			ok_match = mid;
 		diff = u_strcmp(fmid->basename, f->basename);
 		if (diff == 0) {
 			good_match = mid;
@@ -1796,6 +1798,21 @@ static void recv_generator(char *fname, struct file_struct *file, int ndx,
 		fnamecmp = partialptr;
 		fnamecmp_type = FNAMECMP_PARTIAL_DIR;
 		statret = 0;
+		if (detect_renamed > 1 && unchanged_file(fnamecmp, file, &sx.st)) {
+			/* Adopt the partial file. */
+			finish_transfer(fname, fnamecmp, NULL, NULL, file, 1, 1);
+			handle_partial_dir(partialptr, PDIR_DELETE);
+			if (itemizing)
+				itemize(fnamecmp, file, ndx, -1, &sx,
+						ITEM_LOCAL_CHANGE, fnamecmp_type, NULL);
+#ifdef SUPPORT_HARD_LINKS
+			if (preserve_hard_links && F_IS_HLINKED(file))
+				finish_hard_link(file, fname, ndx, &sx.st, itemizing, code, -1);
+#endif
+			if (remove_source_files == 1)
+				goto return_with_success;
+			goto cleanup;
+		}
 	}
 
 	if (!do_xfers)
diff --git a/options.c b/options.c
index 7e454b3..1da38cb 100644
--- a/options.c
+++ b/options.c
@@ -744,6 +744,8 @@ void usage(enum logcode F)
   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,"     --detect-renamed        try to find renamed files to speed up the transfer\n");
+  rprintf(F,"     --detect-renamed-lax    ... and assume identical to source files (risky!)\n");
+  rprintf(F,"     --detect-moved          ... only if basenames match (less risky)\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");
@@ -939,7 +941,9 @@ 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 },
+  {"detect-renamed",   0,  POPT_ARG_VAL,    &detect_renamed, 1, 0, 0 },
+  {"detect-renamed-lax",0, POPT_ARG_VAL,    &detect_renamed, 2, 0, 0 },
+  {"detect-moved",     0,  POPT_ARG_VAL,    &detect_renamed, 3, 0, 0 },
   {"fuzzy",           'y', POPT_ARG_VAL,    &fuzzy_basis, 1, 0, 0 },
   {"no-fuzzy",         0,  POPT_ARG_VAL,    &fuzzy_basis, 0, 0, 0 },
   {"no-y",             0,  POPT_ARG_VAL,    &fuzzy_basis, 0, 0, 0 },
@@ -2480,8 +2484,14 @@ void server_options(char **args, int *argc_p)
 			args[ac++] = "--super";
 		if (size_only)
 			args[ac++] = "--size-only";
-		if (detect_renamed)
-			args[ac++] = "--detect-renamed";
+		if (detect_renamed) {
+			if (detect_renamed == 1)
+				args[ac++] = "--detect-renamed";
+			else if (detect_renamed == 2)
+				args[ac++] = "--detect-renamed-lax";
+			else
+				args[ac++] = "--detect-moved";
+		}
 		if (do_stats)
 			args[ac++] = "--stats";
 	} else {
diff --git a/rsync.yo b/rsync.yo
index 4df39b0..e254152 100644
--- a/rsync.yo
+++ b/rsync.yo
@@ -398,6 +398,8 @@ to the detailed description below for a complete description.  verb(
  -T, --temp-dir=DIR          create temporary files in directory DIR
  -y, --fuzzy                 find similar file for basis if no dest file
      --detect-renamed        try to find renamed files to speed the xfer
+     --detect-renamed-lax    ...& assume identical to src files (risky!)
+     --detect-moved          ... only if basenames match (less risky)
      --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
@@ -1621,6 +1623,17 @@ the bf(--partial-dir) option, that directory will be used instead.  These
 potential alternate-basis files will be removed as the transfer progresses.
 This option conflicts with bf(--inplace) and bf(--append).
 
+dit(bf(--detect-renamed-lax)) This version of bf(--detect-renamed)
+makes rsync hard-link em(dest/D) to em(dest/S) without verifying that
+em(src/S) and em(dest/S) have the same data.  This poses a significant risk
+of corrupting the destination by representing a new source file by an
+unrelated destination file that coincidentally passes the quick check with the
+source file.  Use this option only if you accept the risk and disk I/O is a
+bottleneck.
+
+dit(bf(--detect-moved)) A less risky variant of bf(--detect-renamed-lax) that
+only uses a destination file that has the same basename as the new source file.
+
 dit(bf(--compare-dest=DIR)) This option instructs rsync to use em(DIR) on
 the destination machine as an additional hierarchy to compare destination
 files against doing transfers (if the files are missing in the destination