core.fsync: introduce granular fsync control infrastructure

This commit introduces the infrastructure for the core.fsync
configuration knob. The repository components we want to sync
are identified by flags so that we can turn on or off syncing
for specific components.

If core.fsyncObjectFiles is set and the core.fsync configuration
also includes FSYNC_COMPONENT_LOOSE_OBJECT, we will fsync any
loose objects. This picks the strictest data integrity behavior
if core.fsync and core.fsyncObjectFiles are set to conflicting values.

This change introduces the currently unused fsync_component
helper, which will be used by a later patch that adds fsyncing to
the refs backend.

Actual configuration and documentation of the fsync components
list are in other patches in the series to separate review of
the underlying mechanism from the policy of how it's configured.

Helped-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Neeraj Singh <neerajsi@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 20 insertions, 10 deletions

diff --git a/builtin/fast-import.c b/builtin/fast-import.c
index b7105fcad9..f2c036a895 100644
--- a/builtin/fast-import.c
+++ b/builtin/fast-import.c
@@ -865,7 +865,7 @@ static void end_packfile(void)
 		struct tag *t;
 
 		close_pack_windows(pack_data);
-		finalize_hashfile(pack_file, cur_pack_oid.hash, 0);
+		finalize_hashfile(pack_file, cur_pack_oid.hash, FSYNC_COMPONENT_PACK, 0);
 		fixup_pack_header_footer(pack_data->pack_fd, pack_data->hash,
 					 pack_data->pack_name, object_count,
 					 cur_pack_oid.hash, pack_size);
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index c45273de3b..c5f12f14df 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -1290,7 +1290,7 @@ static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned cha
 			    nr_objects - nr_objects_initial);
 		stop_progress_msg(&progress, msg.buf);
 		strbuf_release(&msg);
-		finalize_hashfile(f, tail_hash, 0);
+		finalize_hashfile(f, tail_hash, FSYNC_COMPONENT_PACK, 0);
 		hashcpy(read_hash, pack_hash);
 		fixup_pack_header_footer(output_fd, pack_hash,
 					 curr_pack, nr_objects,
@@ -1512,7 +1512,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 	if (!from_stdin) {
 		close(input_fd);
 	} else {
-		fsync_or_die(output_fd, curr_pack_name);
+		fsync_component_or_die(FSYNC_COMPONENT_PACK, output_fd, curr_pack_name);
 		err = close(output_fd);
 		if (err)
 			die_errno(_("error while closing pack file"));
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 178e611f09..c14fee8e99 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -1199,16 +1199,26 @@ static void write_pack_file(void)
 			display_progress(progress_state, written);
 		}
 
-		/*
-		 * Did we write the wrong # entries in the header?
-		 * If so, rewrite it like in fast-import
-		 */
 		if (pack_to_stdout) {
-			finalize_hashfile(f, hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE);
+			/*
+			 * We never fsync when writing to stdout since we may
+			 * not be writing to an actual pack file. For instance,
+			 * the upload-pack code passes a pipe here. Calling
+			 * fsync on a pipe results in unnecessary
+			 * synchronization with the reader on some platforms.
+			 */
+			finalize_hashfile(f, hash, FSYNC_COMPONENT_NONE,
+					  CSUM_HASH_IN_STREAM | CSUM_CLOSE);
 		} else if (nr_written == nr_remaining) {
-			finalize_hashfile(f, hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE);
+			finalize_hashfile(f, hash, FSYNC_COMPONENT_PACK,
+					  CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE);
 		} else {
-			int fd = finalize_hashfile(f, hash, 0);
+			/*
+			 * If we wrote the wrong number of entries in the
+			 * header, rewrite it like in fast-import.
+			 */
+
+			int fd = finalize_hashfile(f, hash, FSYNC_COMPONENT_PACK, 0);
 			fixup_pack_header_footer(fd, hash, pack_tmp_name,
 						 nr_written, hash, offset);
 			close(fd);