From 65b709982322d2cf4f9e66d90601d6dc0822abc8 Mon Sep 17 00:00:00 2001
From: Ben Peart <Ben.Peart@microsoft.com>
Date: Tue, 10 Jan 2017 18:47:14 +0000
Subject: [PATCH] gvfs: allow "virtualizing" objects

The idea is to allow blob objects to be missing from the local repository,
and to load them lazily on demand.

After discussing this idea on the mailing list, we will rename the feature
to "lazy clone" and work more on this.

Signed-off-by: Ben Peart <Ben.Peart@microsoft.com>
---
 config.c      |  5 +++++
 connected.c   |  3 +++
 environment.c |  1 +
 environment.h |  2 ++
 object-file.c | 23 +++++++++++++++++++++++
 5 files changed, 34 insertions(+)

diff --git a/config.c b/config.c
index c211a3268e23bb..b90d7cc41df3a2 100644
--- a/config.c
+++ b/config.c
@@ -1664,6 +1664,11 @@ int git_default_core_config(const char *var, const char *value,
 		return 0;
 	}
 
+	if (!strcmp(var, "core.virtualizeobjects")) {
+		core_virtualize_objects = git_config_bool(var, value);
+		return 0;
+	}
+
 	/* Add other config variables here and to Documentation/config.txt. */
 	return platform_core_config(var, value, ctx, cb);
 }
diff --git a/connected.c b/connected.c
index bc850e50ce4dcc..12b9f49cdfa801 100644
--- a/connected.c
+++ b/connected.c
@@ -1,4 +1,5 @@
 #include "git-compat-util.h"
+#include "environment.h"
 #include "gettext.h"
 #include "hex.h"
 #include "gvfs.h"
@@ -50,6 +51,8 @@ int check_connected(oid_iterate_fn fn, void *cb_data,
 	 */
 	if (gvfs_config_is_set(GVFS_FETCH_SKIP_REACHABILITY_AND_UPLOADPACK))
 		return 0;
+	if (core_virtualize_objects)
+		return 0;
 
 	if (!opt)
 		opt = &defaults;
diff --git a/environment.c b/environment.c
index b2435dca60ed3b..191399cac86e35 100644
--- a/environment.c
+++ b/environment.c
@@ -81,6 +81,7 @@ int core_gvfs;
 int merge_log_config = -1;
 int precomposed_unicode = -1; /* see probe_utf8_pathname_composition() */
 unsigned long pack_size_limit_cfg;
+int core_virtualize_objects;
 enum log_refs_config log_all_ref_updates = LOG_REFS_UNSET;
 int max_allowed_tree_depth =
 #ifdef _MSC_VER
diff --git a/environment.h b/environment.h
index 68a2aadbfa990b..9f6afee185095c 100644
--- a/environment.h
+++ b/environment.h
@@ -11,6 +11,8 @@ struct strvec;
 extern char comment_line_char;
 extern int auto_comment_line_char;
 
+extern int core_virtualize_objects;
+
 /*
  * Wrapper of getenv() that returns a strdup value. This value is kept
  * in argv to be freed later.
diff --git a/object-file.c b/object-file.c
index 8a3b8609eba97e..ab8ebba98351cc 100644
--- a/object-file.c
+++ b/object-file.c
@@ -43,6 +43,8 @@
 #include "setup.h"
 #include "submodule.h"
 #include "fsck.h"
+#include "trace.h"
+#include "hook.h"
 
 /* The maximum size for an object header. */
 #define MAX_HEADER_LEN 32
@@ -1552,6 +1554,20 @@ void disable_obj_read_lock(void)
 	pthread_mutex_destroy(&obj_read_mutex);
 }
 
+static int run_read_object_hook(const struct object_id *oid)
+{
+	struct run_hooks_opt opt = RUN_HOOKS_OPT_INIT;
+	int ret;
+	uint64_t start;
+
+	start = getnanotime();
+	strvec_push(&opt.args, oid_to_hex(oid));
+	ret = run_hooks_opt("read-object", &opt);
+	trace_performance_since(start, "run_read_object_hook");
+
+	return ret;
+}
+
 int fetch_if_missing = 1;
 
 static int do_oid_object_info_extended(struct repository *r,
@@ -1564,6 +1580,7 @@ static int do_oid_object_info_extended(struct repository *r,
 	int rtype;
 	const struct object_id *real = oid;
 	int already_retried = 0;
+	int tried_hook = 0;
 
 
 	if (flags & OBJECT_INFO_LOOKUP_REPLACE)
@@ -1575,6 +1592,7 @@ static int do_oid_object_info_extended(struct repository *r,
 	if (!oi)
 		oi = &blank_oi;
 
+retry:
 	co = find_cached_object(real);
 	if (co) {
 		if (oi->typep)
@@ -1606,6 +1624,11 @@ static int do_oid_object_info_extended(struct repository *r,
 			reprepare_packed_git(r);
 			if (find_pack_entry(r, real, &e))
 				break;
+			if (core_virtualize_objects && !tried_hook) {
+				tried_hook = 1;
+				if (!run_read_object_hook(oid))
+					goto retry;
+			}
 		}
 
 		/*