From 8e514f8d0e782bf6a3ad452cc7f703a0b57b9b97 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>
---
 cache.h       |  2 ++
 config.c      |  5 +++++
 connected.c   |  2 ++
 environment.c |  1 +
 object-file.c | 22 ++++++++++++++++++++++
 5 files changed, 32 insertions(+)

diff --git a/cache.h b/cache.h
index 01d55d772bb793..2855f5996729b0 100644
--- a/cache.h
+++ b/cache.h
@@ -1095,6 +1095,8 @@ int use_optional_locks(void);
 extern char comment_line_char;
 extern int auto_comment_line_char;
 
+extern int core_virtualize_objects;
+
 enum log_refs_config {
 	LOG_REFS_UNSET = -1,
 	LOG_REFS_NONE = 0,
diff --git a/config.c b/config.c
index 735b92b3e90adc..c5da676165be6c 100644
--- a/config.c
+++ b/config.c
@@ -1765,6 +1765,11 @@ int git_default_core_config(const char *var, const char *value, void *cb)
 		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, cb);
 }
diff --git a/connected.c b/connected.c
index e9ae073015efe2..9cde030ece78e3 100644
--- a/connected.c
+++ b/connected.c
@@ -48,6 +48,8 @@ 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 fd676960d0edbe..a4592281278748 100644
--- a/environment.c
+++ b/environment.c
@@ -76,6 +76,7 @@ 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;
 
 #ifndef PROTECT_HFS_DEFAULT
diff --git a/object-file.c b/object-file.c
index 0071655b698063..07376cb4f5f2e1 100644
--- a/object-file.c
+++ b/object-file.c
@@ -33,6 +33,7 @@
 #include "object-store.h"
 #include "promisor-remote.h"
 #include "submodule.h"
+#include "hook.h"
 
 /* The maximum size for an object header. */
 #define MAX_HEADER_LEN 32
@@ -1525,6 +1526,20 @@ 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,
@@ -1537,6 +1552,7 @@ 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)
@@ -1548,6 +1564,7 @@ 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)
@@ -1582,6 +1599,11 @@ 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;
+			}
 		}
 
 		/*