From: Andre Noll <maan@tuebingen.mpg.de>
Date: Mon, 17 Apr 2017 17:06:37 +0000 (+0200)
Subject: Implement --checksum.
X-Git-Tag: v1.0.0~25^2~4
X-Git-Url: http://git.tue.mpg.de/?a=commitdiff_plain;h=b01b9e2b9d8e63ea13119096dceb19f436aef544;p=dss.git

Implement --checksum.

It is considered good practice to run rsync with --checksum from time
to time. This patch implements the feature via the new --checksum
option.

The probabilistic approach was chosen so that dss does not need to
remember which snapshots were created with --checksum.
---

diff --git a/dss.c b/dss.c
index 5e2ef46..3e626ab 100644
--- a/dss.c
+++ b/dss.c
@@ -1347,6 +1347,7 @@ static void create_rsync_argv(char ***argv, int64_t *num)
 	char *logname;
 	int i = 0, j, N = OPT_GIVEN(DSS, RSYNC_OPTION);
 	struct snapshot_list sl;
+	static bool seeded;
 
 	dss_get_snapshot_list(&sl);
 	assert(!name_of_reference_snapshot);
@@ -1357,6 +1358,14 @@ static void create_rsync_argv(char ***argv, int64_t *num)
 	(*argv)[i++] = dss_strdup("rsync");
 	(*argv)[i++] = dss_strdup("-a");
 	(*argv)[i++] = dss_strdup("--delete");
+	if (!seeded) {
+		srandom((unsigned)time(NULL)); /* no need to be fancy here */
+		seeded = true;
+	}
+	if (1000 * (random() / (RAND_MAX + 1.0)) < OPT_UINT32_VAL(DSS, CHECKSUM)) {
+		DSS_NOTICE_LOG(("adding --checksum to rsync options\n"));
+		(*argv)[i++] = dss_strdup("--checksum");
+	}
 	for (j = 0; j < N; j++)
 		(*argv)[i++] = dss_strdup(lls_string_val(j,
 			OPT_RESULT(DSS, RSYNC_OPTION)));
diff --git a/dss.suite b/dss.suite
index e7473cb..e69cc28 100644
--- a/dss.suite
+++ b/dss.suite
@@ -109,6 +109,29 @@ caption = Subcommands
 			Set this if the user that runs dss is different from the user on the
 			remote host.
 		[/help]
+	[option checksum]
+		summary = run rsync with --checksum occasionally
+		typestr = permille
+		arg_info = required_arg
+		arg_type = uint32
+		default_val = 0
+		[help]
+			If a file on the backup becomes corrupt in a way that file size
+			and modification time still match the original file, rsync will not
+			consider the file for transfer ("quick check"). Hence the corruption
+			stays on the backup until the file is modified on the source.
+			The --checksum option of rsync disables the quick check and compares
+			the contents of each file, fixing such corruptions. Since computing
+			the checksums adds a significant slowdown due to a lot of disk I/O,
+			the option is not enabled by default.
+
+			The argument to the --checksum option of dss is a number between 0
+			and 1000, inclusively, which determines the probability of adding
+			--checksum to the rsync options each time a snapshot is created. The
+			default value zero means to never add the option. The value 100 will
+			create every tenth snapshot (on average) using checksums, and the
+			value 1000 will always pass --checksum to rsync.
+		[/help]
 	[option rsync-option]
 		short_opt = O
 		summary = further rsync options