Merge branch 'cc/split-index-config'

The experimental "split index" feature has gained a few
configuration variables to make it easier to use.

* cc/split-index-config: (22 commits)
  Documentation/git-update-index: explain splitIndex.*
  Documentation/config: add splitIndex.sharedIndexExpire
  read-cache: use freshen_shared_index() in read_index_from()
  read-cache: refactor read_index_from()
  t1700: test shared index file expiration
  read-cache: unlink old sharedindex files
  config: add git_config_get_expiry() from gc.c
  read-cache: touch shared index files when used
  sha1_file: make check_and_freshen_file() non static
  Documentation/config: add splitIndex.maxPercentChange
  t1700: add tests for splitIndex.maxPercentChange
  read-cache: regenerate shared index if necessary
  config: add git_config_get_max_percent_split_change()
  Documentation/git-update-index: talk about core.splitIndex config var
  Documentation/config: add information for core.splitIndex
  t1700: add tests for core.splitIndex
  update-index: warn in case of split-index incoherency
  read-cache: add and then use tweak_split_index()
  split-index: add {add,remove}_split_index() functions
  config: add git_config_get_split_index()
  ...

Documentation/config.txt

@@ -334,6 +334,10 @@ core.trustctime::
 	crawlers and some backup systems).
 	See linkgit:git-update-index[1]. True by default.
 
+core.splitIndex::
+	If true, the split-index feature of the index will be used.
+	See linkgit:git-update-index[1]. False by default.
+
 core.untrackedCache::
 	Determines what to do about the untracked cache feature of the
 	index. It will be kept, if this variable is unset or set to
@@ -2850,6 +2854,31 @@ showbranch.default::
 	The default set of branches for linkgit:git-show-branch[1].
 	See linkgit:git-show-branch[1].
 
+splitIndex.maxPercentChange::
+	When the split index feature is used, this specifies the
+	percent of entries the split index can contain compared to the
+	total number of entries in both the split index and the shared
+	index before a new shared index is written.
+	The value should be between 0 and 100. If the value is 0 then
+	a new shared index is always written, if it is 100 a new
+	shared index is never written.
+	By default the value is 20, so a new shared index is written
+	if the number of entries in the split index would be greater
+	than 20 percent of the total number of entries.
+	See linkgit:git-update-index[1].
+
+splitIndex.sharedIndexExpire::
+	When the split index feature is used, shared index files that
+	were not modified since the time this variable specifies will
+	be removed when a new shared index file is created. The value
+	"now" expires all entries immediately, and "never" suppresses
+	expiration altogether.
+	The default value is "2.weeks.ago".
+	Note that a shared index file is considered modified (for the
+	purpose of expiration) each time a new split-index file is
+	either created based on it or read from it.
+	See linkgit:git-update-index[1].
+
 status.relativePaths::
 	By default, linkgit:git-status[1] shows paths relative to the
 	current directory. Setting this variable to `false` shows paths

Documentation/git-update-index.txt

@@ -163,14 +163,16 @@ may not support it yet.
 
 --split-index::
 --no-split-index::
-	Enable or disable split index mode. If enabled, the index is
-	split into two files, $GIT_DIR/index and $GIT_DIR/sharedindex.<SHA-1>.
-	Changes are accumulated in $GIT_DIR/index while the shared
-	index file contains all index entries stays unchanged. If
-	split-index mode is already enabled and `--split-index` is
-	given again, all changes in $GIT_DIR/index are pushed back to
-	the shared index file. This mode is designed for very large
-	indexes that take a significant amount of time to read or write.
+	Enable or disable split index mode. If split-index mode is
+	already enabled and `--split-index` is given again, all
+	changes in $GIT_DIR/index are pushed back to the shared index
+	file.
++
+These options take effect whatever the value of the `core.splitIndex`
+configuration variable (see linkgit:git-config[1]). But a warning is
+emitted when the change goes against the configured value, as the
+configured value will take effect next time the index is read and this
+will remove the intended effect of the option.
 
 --untracked-cache::
 --no-untracked-cache::
@@ -388,6 +390,31 @@ Although this bit looks similar to assume-unchanged bit, its goal is
 different from assume-unchanged bit's. Skip-worktree also takes
 precedence over assume-unchanged bit when both are set.
 
+Split index
+-----------
+
+This mode is designed for repositories with very large indexes, and
+aims at reducing the time it takes to repeatedly write these indexes.
+
+In this mode, the index is split into two files, $GIT_DIR/index and
+$GIT_DIR/sharedindex.<SHA-1>. Changes are accumulated in
+$GIT_DIR/index, the split index, while the shared index file contains
+all index entries and stays unchanged.
+
+All changes in the split index are pushed back to the shared index
+file when the number of entries in the split index reaches a level
+specified by the splitIndex.maxPercentChange config variable (see
+linkgit:git-config[1]).
+
+Each time a new shared index file is created, the old shared index
+files are deleted if their modification time is older than what is
+specified by the splitIndex.sharedIndexExpire config variable (see
+linkgit:git-config[1]).
+
+To avoid deleting a shared index file that is still used, its
+modification time is updated to the current time everytime a new split
+index based on the shared index file is either created or read from.
+
 Untracked cache
 ---------------
 

builtin/gc.c

@@ -64,17 +64,6 @@ static void report_pack_garbage(unsigned seen_bits, const char *path)
 		string_list_append(&pack_garbage, path);
 }
 
-static void git_config_date_string(const char *key, const char **output)
-{
-	if (git_config_get_string_const(key, output))
-		return;
-	if (strcmp(*output, "now")) {
-		unsigned long now = approxidate("now");
-		if (approxidate(*output) >= now)
-			git_die_config(key, _("Invalid %s: '%s'"), key, *output);
-	}
-}
-
 static void process_log_file(void)
 {
 	struct stat st;
@@ -131,9 +120,9 @@ static void gc_config(void)
 	git_config_get_int("gc.auto", &gc_auto_threshold);
 	git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit);
 	git_config_get_bool("gc.autodetach", &detach_auto);
-	git_config_date_string("gc.pruneexpire", &prune_expire);
-	git_config_date_string("gc.worktreepruneexpire", &prune_worktrees_expire);
-	git_config_date_string("gc.logexpiry", &gc_log_expire);
+	git_config_get_expiry("gc.pruneexpire", &prune_expire);
+	git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
+	git_config_get_expiry("gc.logexpiry", &gc_log_expire);
 
 	git_config(git_default_config, NULL);
 }

builtin/update-index.c

@@ -1099,17 +1099,20 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 	}
 
 	if (split_index > 0) {
-		init_split_index(&the_index);
-		the_index.cache_changed |= SPLIT_INDEX_ORDERED;
-	} else if (!split_index && the_index.split_index) {
-		/*
-		 * can't discard_split_index(&the_index); because that
-		 * will destroy split_index->base->cache[], which may
-		 * be shared with the_index.cache[]. So yeah we're
-		 * leaking a bit here.
-		 */
-		the_index.split_index = NULL;
-		the_index.cache_changed |= SOMETHING_CHANGED;
+		if (git_config_get_split_index() == 0)
+			warning(_("core.splitIndex is set to false; "
+				  "remove or change it, if you really want to "
+				  "enable split index"));
+		if (the_index.split_index)
+			the_index.cache_changed |= SPLIT_INDEX_ORDERED;
+		else
+			add_split_index(&the_index);
+	} else if (!split_index) {
+		if (git_config_get_split_index() == 1)
+			warning(_("core.splitIndex is set to true; "
+				  "remove or change it, if you really want to "
+				  "disable split index"));
+		remove_split_index(&the_index);
 	}
 
 	switch (untracked_cache) {

cache.h

@@ -1270,6 +1270,9 @@ extern int has_pack_index(const unsigned char *sha1);
 
 extern void assert_sha1_type(const unsigned char *sha1, enum object_type expect);
 
+/* Helper to check and "touch" a file */
+extern int check_and_freshen_file(const char *fn, int freshen);
+
 extern const signed char hexval_table[256];
 static inline unsigned int hexval(unsigned char c)
 {
@@ -1956,6 +1959,11 @@ extern int git_config_get_bool_or_int(const char *key, int *is_bool, int *dest);
 extern int git_config_get_maybe_bool(const char *key, int *dest);
 extern int git_config_get_pathname(const char *key, const char **dest);
 extern int git_config_get_untracked_cache(void);
+extern int git_config_get_split_index(void);
+extern int git_config_get_max_percent_split_change(void);
+
+/* This dies if the configured or default date is in the future */
+extern int git_config_get_expiry(const char *key, const char **output);
 
 /*
  * This is a hack for test programs like test-dump-untracked-cache to

config.c

@@ -1803,6 +1803,19 @@ int git_config_get_pathname(const char *key, const char **dest)
 	return ret;
 }
 
+int git_config_get_expiry(const char *key, const char **output)
+{
+	int ret = git_config_get_string_const(key, output);
+	if (ret)
+		return ret;
+	if (strcmp(*output, "now")) {
+		unsigned long now = approxidate("now");
+		if (approxidate(*output) >= now)
+			git_die_config(key, _("Invalid %s: '%s'"), key, *output);
+	}
+	return ret;
+}
+
 int git_config_get_untracked_cache(void)
 {
 	int val = -1;
@@ -1819,14 +1832,39 @@ int git_config_get_untracked_cache(void)
 		if (!strcasecmp(v, "keep"))
 			return -1;
 
-		error("unknown core.untrackedCache value '%s'; "
-		      "using 'keep' default value", v);
+		error(_("unknown core.untrackedCache value '%s'; "
+			"using 'keep' default value"), v);
 		return -1;
 	}
 
 	return -1; /* default value */
 }
 
+int git_config_get_split_index(void)
+{
+	int val;
+
+	if (!git_config_get_maybe_bool("core.splitindex", &val))
+		return val;
+
+	return -1; /* default value */
+}
+
+int git_config_get_max_percent_split_change(void)
+{
+	int val = -1;
+
+	if (!git_config_get_int("splitindex.maxpercentchange", &val)) {
+		if (0 <= val && val <= 100)
+			return val;
+
+		return error(_("splitIndex.maxPercentChange value '%d' "
+			       "should be between 0 and 100"), val);
+	}
+
+	return -1; /* default value */
+}
+
 NORETURN
 void git_die_config_linenr(const char *key, const char *filename, int linenr)
 {