@@ -163,6 +163,22 @@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_n
add_index_entry(istate, new_entry, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
}
+/*
+ * stat_data only stores file sizes as an unsigned int. Any file that is an
+ * exact multiple of 4GiB will get a cached file size of zero. Unfortunately,
+ * this is a special flag used by the racy update logic. Substitute a new file
+ * size if a non-zero sized file would would be cached as zero. 1U<<31 is used
+ * as the substitute because it is the furthest away from 0 and 4GiB.
+ */
+static inline unsigned int munge_st_size(off_t st_size) {
+ unsigned int sd_size = (unsigned int) st_size;
+
+ if (!sd_size && st_size)
+ return 1U<<31;
+ else
+ return sd_size;
+}
+
void fill_stat_data(struct stat_data *sd, struct stat *st)
{
sd->sd_ctime.sec = (unsigned int)st->st_ctime;
@@ -173,7 +189,7 @@ void fill_stat_data(struct stat_data *sd, struct stat *st)
sd->sd_ino = st->st_ino;
sd->sd_uid = st->st_uid;
sd->sd_gid = st->st_gid;
- sd->sd_size = st->st_size;
+ sd->sd_size = munge_st_size(st->st_size);
}
int match_stat_data(const struct stat_data *sd, struct stat *st)
@@ -212,7 +228,7 @@ int match_stat_data(const struct stat_data *sd, struct stat *st)
changed |= INODE_CHANGED;
#endif
- if (sd->sd_size != (unsigned int) st->st_size)
+ if (sd->sd_size != munge_st_size(st->st_size))
changed |= DATA_CHANGED;
return changed;
Git cache stores file sizes using uint32_t. This causes any file that is a multiple of 2^32 to have a cached file size of zero. Zero is a special value used by racily clean. This causes git to rehash every file that is a multiple of 2^32 every time git status or git commit is run. This patch mitigates the problem by making all files that are a multiple of 2^32 appear to have a size of 1 instead of zero. Signed-off-by: Jason D. Hatton <jhatton@globalfinishing.com> --- read-cache.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-)