files-backend: don't rewrite the packed-refs file unnecessarily

mhagger · gitster · commit 7c6bd25c7d65 · 2017-10-30T09:45:15.000+09:00
Even when we are deleting references, we needn't overwrite the `packed-refs` file if the references that we are deleting only exist as loose references. Implement this optimization as follows: * Add a function `is_packed_transaction_needed()`, which checks whether a given packed-refs transaction actually needs to be carried out (i.e., it returns false if the transaction obviously wouldn't have any effect). This function must be called while holding the `packed-refs` lock to avoid races. * Change `files_transaction_prepare()` to check whether the packed-refs transaction is actually needed. If not, squelch it, but continue holding the `packed-refs` lock until the end of the transaction to avoid races. This fixes a mild regression caused by dc39e09 (files_ref_store: use a transaction to update packed refs, 2017-09-08). Before that commit, unnecessary rewrites of `packed-refs` were suppressed by `repack_without_refs()`. But the transaction-based writing introduced by that commit didn't perform that optimization. Note that the pre-dc39e09942 code still had to *read* the whole `packed-refs` file to determine that the rewrite could be skipped, so the performance for the cases that the write could be elided was `O(N)` in the number of packed references both before and after dc39e09. But after that commit the constant factor increased. This commit reimplements the optimization of eliding unnecessary `packed-refs` rewrites. That, plus the fact that since cfa2e29 (packed_ref_store: get rid of the `ref_cache` entirely, 2017-03-17) we don't necessarily have to read the whole `packed-refs` file at all, means that deletes of one or a few loose references can now be done with `O(n lg N)` effort, where `n` is the number of loose references being deleted and `N` is the total number of packed references. This commit fixes two tests in t1409. Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu> Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/refs/files-backend.c b/refs/files-backend.c
@@ -2562,7 +2562,23 @@ static int files_transaction_prepare(struct ref_store *ref_store,
 			goto cleanup;
 		}
 		backend_data->packed_refs_locked = 1;
-		ret = ref_transaction_prepare(packed_transaction, err);
+
+		if (is_packed_transaction_needed(refs->packed_ref_store,
+						 packed_transaction)) {
+			ret = ref_transaction_prepare(packed_transaction, err);
+		} else {
+			/*
+			 * We can skip rewriting the `packed-refs`
+			 * file. But we do need to leave it locked, so
+			 * that somebody else doesn't pack a reference
+			 * that we are trying to delete.
+			 */
+			if (ref_transaction_abort(packed_transaction, err)) {
+				ret = TRANSACTION_GENERIC_ERROR;
+				goto cleanup;
+			}
+			backend_data->packed_transaction = NULL;
+		}
 	}
 
 cleanup:
diff --git a/refs/packed-backend.c b/refs/packed-backend.c
@@ -754,6 +754,100 @@ static int write_with_updates(struct packed_ref_store *refs,
 	return -1;
 }
 
+int is_packed_transaction_needed(struct ref_store *ref_store,
+				 struct ref_transaction *transaction)
+{
+	struct packed_ref_store *refs = packed_downcast(
+			ref_store,
+			REF_STORE_READ,
+			"is_packed_transaction_needed");
+	struct strbuf referent = STRBUF_INIT;
+	size_t i;
+	int ret;
+
+	if (!is_lock_file_locked(&refs->lock))
+		BUG("is_packed_transaction_needed() called while unlocked");
+
+	/*
+	 * We're only going to bother returning false for the common,
+	 * trivial case that references are only being deleted, their
+	 * old values are not being checked, and the old `packed-refs`
+	 * file doesn't contain any of those reference(s). This gives
+	 * false positives for some other cases that could
+	 * theoretically be optimized away:
+	 *
+	 * 1. It could be that the old value is being verified without
+	 *    setting a new value. In this case, we could verify the
+	 *    old value here and skip the update if it agrees. If it
+	 *    disagrees, we could either let the update go through
+	 *    (the actual commit would re-detect and report the
+	 *    problem), or come up with a way of reporting such an
+	 *    error to *our* caller.
+	 *
+	 * 2. It could be that a new value is being set, but that it
+	 *    is identical to the current packed value of the
+	 *    reference.
+	 *
+	 * Neither of these cases will come up in the current code,
+	 * because the only caller of this function passes to it a
+	 * transaction that only includes `delete` updates with no
+	 * `old_id`. Even if that ever changes, false positives only
+	 * cause an optimization to be missed; they do not affect
+	 * correctness.
+	 */
+
+	/*
+	 * Start with the cheap checks that don't require old
+	 * reference values to be read:
+	 */
+	for (i = 0; i < transaction->nr; i++) {
+		struct ref_update *update = transaction->updates[i];
+
+		if (update->flags & REF_HAVE_OLD)
+			/* Have to check the old value -> needed. */
+			return 1;
+
+		if ((update->flags & REF_HAVE_NEW) && !is_null_oid(&update->new_oid))
+			/* Have to set a new value -> needed. */
+			return 1;
+	}
+
+	/*
+	 * The transaction isn't checking any old values nor is it
+	 * setting any nonzero new values, so it still might be able
+	 * to be skipped. Now do the more expensive check: the update
+	 * is needed if any of the updates is a delete, and the old
+	 * `packed-refs` file contains a value for that reference.
+	 */
+	ret = 0;
+	for (i = 0; i < transaction->nr; i++) {
+		struct ref_update *update = transaction->updates[i];
+		unsigned int type;
+		struct object_id oid;
+
+		if (!(update->flags & REF_HAVE_NEW))
+			/*
+			 * This reference isn't being deleted -> not
+			 * needed.
+			 */
+			continue;
+
+		if (!refs_read_raw_ref(ref_store, update->refname,
+				       oid.hash, &referent, &type) ||
+		    errno != ENOENT) {
+			/*
+			 * We have to actually delete that reference
+			 * -> this transaction is needed.
+			 */
+			ret = 1;
+			break;
+		}
+	}
+
+	strbuf_release(&referent);
+	return ret;
+}
+
 struct packed_transaction_backend_data {
 	/* True iff the transaction owns the packed-refs lock. */
 	int own_lock;
diff --git a/refs/packed-backend.h b/refs/packed-backend.h
@@ -23,4 +23,13 @@ int packed_refs_lock(struct ref_store *ref_store, int flags, struct strbuf *err)
 void packed_refs_unlock(struct ref_store *ref_store);
 int packed_refs_is_locked(struct ref_store *ref_store);
 
+/*
+ * Return true if `transaction` really needs to be carried out against
+ * the specified packed_ref_store, or false if it can be skipped
+ * (i.e., because it is an obvious NOOP). `ref_store` must be locked
+ * before calling this function.
+ */
+int is_packed_transaction_needed(struct ref_store *ref_store,
+				 struct ref_transaction *transaction);
+
 #endif /* REFS_PACKED_BACKEND_H */
diff --git a/t/t1409-avoid-packing-refs.sh b/t/t1409-avoid-packing-refs.sh
@@ -26,7 +26,7 @@ test_expect_success 'setup' '
 	C=$(git rev-parse HEAD)
 '
 
-test_expect_failure 'do not create packed-refs file gratuitously' '
+test_expect_success 'do not create packed-refs file gratuitously' '
 	test_must_fail test -f .git/packed-refs &&
 	git update-ref refs/heads/foo $A &&
 	test_must_fail test -f .git/packed-refs &&
@@ -107,7 +107,7 @@ test_expect_success 'leave packed-refs untouched on verify of loose' '
 	check_packed_refs_marked
 '
 
-test_expect_failure 'leave packed-refs untouched on delete of loose' '
+test_expect_success 'leave packed-refs untouched on delete of loose' '
 	git pack-refs --all &&
 	git update-ref refs/heads/loose-delete $A &&
 	mark_packed_refs &&
