read-cache: split-index mode

This split-index mode is designed to keep write cost proportional to
the number of changes the user has made, not the size of the work
tree. (Read cost is another matter, to be dealt separately.)

This mode stores index info in a pair of $GIT_DIR/index and
$GIT_DIR/sharedindex.<SHA-1>. sharedindex is large and unchanged over
time while "index" is smaller and updated often. Format details are in
index-format.txt, although not everything is implemented in this
patch.

Shared indexes are not automatically removed, because it's unclear if
the shared index is needed by any (even temporary) indexes by just
looking at it. After a while you'll collect stale shared indexes. The
good news is one shared index is useable for long, until
$GIT_DIR/index becomes too big and sluggish that the new shared index
must be created.

The safest way to clean shared indexes is to turn off split index
mode, so shared files are all garbage, delete them all, then turn on
split index mode again.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 90 insertions, 0 deletions

diff --git a/split-index.c b/split-index.c
new file mode 100644
index 0000000000..63b52bb086
--- /dev/null
+++ b/split-index.c
@@ -0,0 +1,90 @@
+#include "cache.h"
+#include "split-index.h"
+
+struct split_index *init_split_index(struct index_state *istate)
+{
+	if (!istate->split_index) {
+		istate->split_index = xcalloc(1, sizeof(*istate->split_index));
+		istate->split_index->refcount = 1;
+	}
+	return istate->split_index;
+}
+
+int read_link_extension(struct index_state *istate,
+			 const void *data_, unsigned long sz)
+{
+	const unsigned char *data = data_;
+	struct split_index *si;
+	if (sz < 20)
+		return error("corrupt link extension (too short)");
+	si = init_split_index(istate);
+	hashcpy(si->base_sha1, data);
+	data += 20;
+	sz -= 20;
+	if (sz)
+		return error("garbage at the end of link extension");
+	return 0;
+}
+
+int write_link_extension(struct strbuf *sb,
+			 struct index_state *istate)
+{
+	struct split_index *si = istate->split_index;
+	strbuf_add(sb, si->base_sha1, 20);
+	return 0;
+}
+
+static void mark_base_index_entries(struct index_state *base)
+{
+	int i;
+	/*
+	 * To keep track of the shared entries between
+	 * istate->base->cache[] and istate->cache[], base entry
+	 * position is stored in each base entry. All positions start
+	 * from 1 instead of 0, which is resrved to say "this is a new
+	 * entry".
+	 */
+	for (i = 0; i < base->cache_nr; i++)
+		base->cache[i]->index = i + 1;
+}
+
+void merge_base_index(struct index_state *istate)
+{
+	struct split_index *si = istate->split_index;
+
+	mark_base_index_entries(si->base);
+	istate->cache_nr = si->base->cache_nr;
+	ALLOC_GROW(istate->cache, istate->cache_nr, istate->cache_alloc);
+	memcpy(istate->cache, si->base->cache,
+	       sizeof(*istate->cache) * istate->cache_nr);
+}
+
+void prepare_to_write_split_index(struct index_state *istate)
+{
+	struct split_index *si = init_split_index(istate);
+	/* take cache[] out temporarily */
+	si->saved_cache_nr = istate->cache_nr;
+	istate->cache_nr = 0;
+}
+
+void finish_writing_split_index(struct index_state *istate)
+{
+	struct split_index *si = init_split_index(istate);
+	istate->cache_nr = si->saved_cache_nr;
+}
+
+void discard_split_index(struct index_state *istate)
+{
+	struct split_index *si = istate->split_index;
+	if (!si)
+		return;
+	istate->split_index = NULL;
+	si->refcount--;
+	if (si->refcount)
+		return;
+	if (si->base) {
+		discard_index(si->base);
+		free(si->base);
+	}
+	free(si);
+}