[v4,3/4] core.fsync: new option to harden the index

Commit Message

Neeraj Singh (WINDOWS-SFS) Feb. 1, 2022, 3:33 a.m. UTC

From: Neeraj Singh <[e-mail]>

This commit introduces the new ability for the user to harden
the index. In the event of a system crash, the index must be
durable for the user to actually find a file that has been added
to the repo and then deleted from the working tree.

We use the presence of the COMMIT_LOCK flag and absence of the
alternate_index_output as a proxy for determining whether we're
updating the persistent index of the repo or some temporary
index. We don't sync these temporary indexes.

Signed-off-by: Neeraj Singh <[e-mail]>
---
 Documentation/config/core.txt |  1 +
 cache.h                       |  4 +++-
 config.c                      |  1 +
 read-cache.c                  | 19 +++++++++++++------
 4 files changed, 18 insertions(+), 7 deletions(-)

Patch

diff --git a/Documentation/config/core.txt b/Documentation/config/core.txt
index 4f1747ec871..8e5b7a795ab 100644
--- a/Documentation/config/core.txt
+++ b/Documentation/config/core.txt
@@ -561,6 +561,7 @@  core.fsync::
 * `pack` hardens objects added to the repo in packfile form.
 * `pack-metadata` hardens packfile bitmaps and indexes.
 * `commit-graph` hardens the commit graph file.
+* `index` hardens the index when it is modified.
 * `objects` is an aggregate option that includes `loose-objects`, `pack`,
   `pack-metadata`, and `commit-graph`.
 * `default` is an aggregate option that is equivalent to `objects,-loose-object`
diff --git a/cache.h b/cache.h
index b3cd7d928de..9f3c1ec4c42 100644
--- a/cache.h
+++ b/cache.h
@@ -1004,6 +1004,7 @@  enum fsync_component {
 	FSYNC_COMPONENT_PACK			= 1 << 1,
 	FSYNC_COMPONENT_PACK_METADATA		= 1 << 2,
 	FSYNC_COMPONENT_COMMIT_GRAPH		= 1 << 3,
+	FSYNC_COMPONENT_INDEX			= 1 << 4,
 };
 
 #define FSYNC_COMPONENTS_DEFAULT (FSYNC_COMPONENT_PACK | \
@@ -1018,7 +1019,8 @@  enum fsync_component {
 #define FSYNC_COMPONENTS_ALL (FSYNC_COMPONENT_LOOSE_OBJECT | \
 			      FSYNC_COMPONENT_PACK | \
 			      FSYNC_COMPONENT_PACK_METADATA | \
-			      FSYNC_COMPONENT_COMMIT_GRAPH)
+			      FSYNC_COMPONENT_COMMIT_GRAPH | \
+			      FSYNC_COMPONENT_INDEX)
 
 
 /*
diff --git a/config.c b/config.c
index 224563c7b3e..325644e3c2c 100644
--- a/config.c
+++ b/config.c
@@ -1221,6 +1221,7 @@  static const struct fsync_component_entry {
 	{ "pack", FSYNC_COMPONENT_PACK },
 	{ "pack-metadata", FSYNC_COMPONENT_PACK_METADATA },
 	{ "commit-graph", FSYNC_COMPONENT_COMMIT_GRAPH },
+	{ "index", FSYNC_COMPONENT_INDEX },
 	{ "objects", FSYNC_COMPONENTS_OBJECTS },
 	{ "default", FSYNC_COMPONENTS_DEFAULT },
 	{ "all", FSYNC_COMPONENTS_ALL },
diff --git a/read-cache.c b/read-cache.c
index a0de70195c8..eb02439ab4b 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -2837,7 +2837,7 @@  static int record_ieot(void)
  * rely on it.
  */
 static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
-			  int strip_extensions)
+			  int strip_extensions, unsigned flags)
 {
 	uint64_t start = getnanotime();
 	struct hashfile *f;
@@ -2851,6 +2851,7 @@  static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
 	struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
 	int drop_cache_tree = istate->drop_cache_tree;
 	off_t offset;
+	int csum_fsync_flag;
 	int ieot_entries = 1;
 	struct index_entry_offset_table *ieot = NULL;
 	int nr, nr_threads;
@@ -3081,7 +3082,13 @@  static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
 			return -1;
 	}
 
-	finalize_hashfile(f, istate->oid.hash, FSYNC_COMPONENT_NONE, CSUM_HASH_IN_STREAM);
+	csum_fsync_flag = 0;
+	if (!alternate_index_output && (flags & COMMIT_LOCK))
+		csum_fsync_flag = CSUM_FSYNC;
+
+	finalize_hashfile(f, istate->oid.hash, FSYNC_COMPONENT_INDEX,
+			  CSUM_HASH_IN_STREAM | csum_fsync_flag);
+
 	if (close_tempfile_gently(tempfile)) {
 		error(_("could not close '%s'"), get_tempfile_path(tempfile));
 		return -1;
@@ -3136,7 +3143,7 @@  static int do_write_locked_index(struct index_state *istate, struct lock_file *l
 	 */
 	trace2_region_enter_printf("index", "do_write_index", the_repository,
 				   "%s", get_lock_file_path(lock));
-	ret = do_write_index(istate, lock->tempfile, 0);
+	ret = do_write_index(istate, lock->tempfile, 0, flags);
 	trace2_region_leave_printf("index", "do_write_index", the_repository,
 				   "%s", get_lock_file_path(lock));
 
@@ -3230,7 +3237,7 @@  static int clean_shared_index_files(const char *current_hex)
 }
 
 static int write_shared_index(struct index_state *istate,
-			      struct tempfile **temp)
+			      struct tempfile **temp, unsigned flags)
 {
 	struct split_index *si = istate->split_index;
 	int ret, was_full = !istate->sparse_index;
@@ -3240,7 +3247,7 @@  static int write_shared_index(struct index_state *istate,
 
 	trace2_region_enter_printf("index", "shared/do_write_index",
 				   the_repository, "%s", get_tempfile_path(*temp));
-	ret = do_write_index(si->base, *temp, 1);
+	ret = do_write_index(si->base, *temp, 1, flags);
 	trace2_region_leave_printf("index", "shared/do_write_index",
 				   the_repository, "%s", get_tempfile_path(*temp));
 
@@ -3349,7 +3356,7 @@  int write_locked_index(struct index_state *istate, struct lock_file *lock,
 			ret = do_write_locked_index(istate, lock, flags);
 			goto out;
 		}
-		ret = write_shared_index(istate, &temp);
+		ret = write_shared_index(istate, &temp, flags);
 
 		saved_errno = errno;
 		if (is_tempfile_active(temp))