Merge branch 'jc/index-v4'

Trivially shrinks the on-disk size of the index file to save both I/O and
checksum overhead.

The topic should give a solid base to build on further updates, with the
code refactoring in its earlier parts, and the backward compatibility
mechanism in its later parts.

* jc/index-v4:
  index-v4: document the entry format
  unpack-trees: preserve the index file version of original
  update-index: upgrade/downgrade on-disk index version
  read-cache.c: write prefix-compressed names in the index
  read-cache.c: read prefix-compressed names in index on-disk version v4
  read-cache.c: move code to copy incore to ondisk cache to a helper function
  read-cache.c: move code to copy ondisk to incore cache to a helper function
  read-cache.c: report the header version we do not understand
  read-cache.c: make create_from_disk() report number of bytes it consumed
  read-cache.c: allow unaligned mapping of the index file
  cache.h: hide on-disk index details
  varint: make it available outside the context of pack

1 files changed, 4 insertions, 48 deletions

diff --git a/cache.h b/cache.h
index 5bf59ff5c3..d8f6f1e78e 100644
--- a/cache.h
+++ b/cache.h
@@ -105,6 +105,9 @@ struct cache_header {
 	unsigned int hdr_entries;
 };
 
+#define INDEX_FORMAT_LB 2
+#define INDEX_FORMAT_UB 4
+
 /*
  * The "cache_time" is just the low 32 bits of the
  * time. It doesn't matter if it overflows - we only
@@ -115,48 +118,6 @@ struct cache_time {
 	unsigned int nsec;
 };
 
-/*
- * dev/ino/uid/gid/size are also just tracked to the low 32 bits
- * Again - this is just a (very strong in practice) heuristic that
- * the inode hasn't changed.
- *
- * We save the fields in big-endian order to allow using the
- * index file over NFS transparently.
- */
-struct ondisk_cache_entry {
-	struct cache_time ctime;
-	struct cache_time mtime;
-	unsigned int dev;
-	unsigned int ino;
-	unsigned int mode;
-	unsigned int uid;
-	unsigned int gid;
-	unsigned int size;
-	unsigned char sha1[20];
-	unsigned short flags;
-	char name[FLEX_ARRAY]; /* more */
-};
-
-/*
- * This struct is used when CE_EXTENDED bit is 1
- * The struct must match ondisk_cache_entry exactly from
- * ctime till flags
- */
-struct ondisk_cache_entry_extended {
-	struct cache_time ctime;
-	struct cache_time mtime;
-	unsigned int dev;
-	unsigned int ino;
-	unsigned int mode;
-	unsigned int uid;
-	unsigned int gid;
-	unsigned int size;
-	unsigned char sha1[20];
-	unsigned short flags;
-	unsigned short flags2;
-	char name[FLEX_ARRAY]; /* more */
-};
-
 struct cache_entry {
 	struct cache_time ce_ctime;
 	struct cache_time ce_mtime;
@@ -253,9 +214,6 @@ static inline size_t ce_namelen(const struct cache_entry *ce)
 }
 
 #define ce_size(ce) cache_entry_size(ce_namelen(ce))
-#define ondisk_ce_size(ce) (((ce)->ce_flags & CE_EXTENDED) ? \
-			    ondisk_cache_entry_extended_size(ce_namelen(ce)) : \
-			    ondisk_cache_entry_size(ce_namelen(ce)))
 #define ce_stage(ce) ((CE_STAGEMASK & (ce)->ce_flags) >> CE_STAGESHIFT)
 #define ce_uptodate(ce) ((ce)->ce_flags & CE_UPTODATE)
 #define ce_skip_worktree(ce) ((ce)->ce_flags & CE_SKIP_WORKTREE)
@@ -306,13 +264,11 @@ static inline unsigned int canon_mode(unsigned int mode)
 	return S_IFGITLINK;
 }
 
-#define flexible_size(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7)
 #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1)
-#define ondisk_cache_entry_size(len) flexible_size(ondisk_cache_entry,len)
-#define ondisk_cache_entry_extended_size(len) flexible_size(ondisk_cache_entry_extended,len)
 
 struct index_state {
 	struct cache_entry **cache;
+	unsigned int version;
 	unsigned int cache_nr, cache_alloc, cache_changed;
 	struct string_list *resolve_undo;
 	struct cache_tree *cache_tree;