summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2013-06-20 08:37:53 (GMT)
committerJunio C Hamano <gitster@pobox.com>2013-06-20 22:50:17 (GMT)
commit98eeb09e8acb6cbe0b0da3b1772b6676fe6d167f (patch)
tree00e9bbf279111957e80c02d8a537e120df7d33d2
parentca9199300eb0d485f5e03961bbbd9aff3484a1fa (diff)
downloadgit-98eeb09e8acb6cbe0b0da3b1772b6676fe6d167f.zip
git-98eeb09e8acb6cbe0b0da3b1772b6676fe6d167f.tar.gz
git-98eeb09e8acb6cbe0b0da3b1772b6676fe6d167f.tar.bz2
for_each_ref: load all loose refs before packed refs
If we are iterating through the refs using for_each_ref (or any of its sister functions), we can get into a race condition with a simultaneous "pack-refs --prune" that looks like this: 0. We have a large number of loose refs, and a few packed refs. refs/heads/z/foo is loose, with no matching entry in the packed-refs file. 1. Process A starts iterating through the refs. It loads the packed-refs file from disk, then starts lazily traversing through the loose ref directories. 2. Process B, running "pack-refs --prune", writes out the new packed-refs file. It then deletes the newly packed refs, including refs/heads/z/foo. 3. Meanwhile, process A has finally gotten to refs/heads/z (it traverses alphabetically). It descends, but finds nothing there. It checks its cached view of the packed-refs file, but it does not mention anything in "refs/heads/z/" at all (it predates the new file written by B in step 2). The traversal completes successfully without mentioning refs/heads/z/foo at all (the name, of course, isn't important; but the more refs you have and the farther down the alphabetical list a ref is, the more likely it is to hit the race). If refs/heads/z/foo did exist in the packed refs file at state 0, we would see an entry for it, but it would show whatever sha1 the ref had the last time it was packed (which could be an arbitrarily long time ago). This can be especially dangerous when process A is "git prune", as it means our set of reachable tips will be incomplete, and we may erroneously prune objects reachable from that tip (the same thing can happen if "repack -ad" is used, as it simply drops unreachable objects that are packed). This patch solves it by loading all of the loose refs for our traversal into our in-memory cache, and then refreshing the packed-refs cache. Because a pack-refs writer will always put the new packed-refs file into place before starting the prune, we know that any loose refs we fail to see will either truly be missing, or will have already been put in the packed-refs file by the time we refresh. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rw-r--r--refs.c39
1 files changed, 35 insertions, 4 deletions
diff --git a/refs.c b/refs.c
index 60f2507..787cc1c 100644
--- a/refs.c
+++ b/refs.c
@@ -750,6 +750,21 @@ static int do_for_each_entry_in_dirs(struct ref_dir *dir1,
}
/*
+ * Load all of the refs from the dir into our in-memory cache. The hard work
+ * of loading loose refs is done by get_ref_dir(), so we just need to recurse
+ * through all of the sub-directories. We do not even need to care about
+ * sorting, as traversal order does not matter to us.
+ */
+static void prime_ref_dir(struct ref_dir *dir)
+{
+ int i;
+ for (i = 0; i < dir->nr; i++) {
+ struct ref_entry *entry = dir->entries[i];
+ if (entry->flag & REF_DIR)
+ prime_ref_dir(get_ref_dir(entry));
+ }
+}
+/*
* Return true iff refname1 and refname2 conflict with each other.
* Two reference names conflict if one of them exactly matches the
* leading components of the other; e.g., "foo/bar" conflicts with
@@ -1603,15 +1618,31 @@ void warn_dangling_symref(FILE *fp, const char *msg_fmt, const char *refname)
static int do_for_each_entry(struct ref_cache *refs, const char *base,
each_ref_entry_fn fn, void *cb_data)
{
- struct packed_ref_cache *packed_ref_cache = get_packed_ref_cache(refs);
- struct ref_dir *packed_dir = get_packed_ref_dir(packed_ref_cache);
- struct ref_dir *loose_dir = get_loose_refs(refs);
+ struct packed_ref_cache *packed_ref_cache;
+ struct ref_dir *loose_dir;
+ struct ref_dir *packed_dir;
int retval = 0;
+ /*
+ * We must make sure that all loose refs are read before accessing the
+ * packed-refs file; this avoids a race condition in which loose refs
+ * are migrated to the packed-refs file by a simultaneous process, but
+ * our in-memory view is from before the migration. get_packed_ref_cache()
+ * takes care of making sure our view is up to date with what is on
+ * disk.
+ */
+ loose_dir = get_loose_refs(refs);
+ if (base && *base) {
+ loose_dir = find_containing_dir(loose_dir, base, 0);
+ }
+ if (loose_dir)
+ prime_ref_dir(loose_dir);
+
+ packed_ref_cache = get_packed_ref_cache(refs);
acquire_packed_ref_cache(packed_ref_cache);
+ packed_dir = get_packed_ref_dir(packed_ref_cache);
if (base && *base) {
packed_dir = find_containing_dir(packed_dir, base, 0);
- loose_dir = find_containing_dir(loose_dir, base, 0);
}
if (packed_dir && loose_dir) {