diff mbox series

[v5,15/16] upload-pack.c: avoid enumerating hidden refs where possible

Message ID 8544a647798de68eb46f9f5c5b269d03ed3500a5.1689023520.git.me@ttaylorr.com (mailing list archive)
State Accepted
Commit 18b6b1b5c57bb4d1b2730b664fb1660b006ef7d3
Headers show
Series refs: implement jump lists for packed backend | expand

Commit Message

Taylor Blau July 10, 2023, 9:12 p.m. UTC
In a similar fashion as a previous commit, teach `upload-pack` to avoid
enumerating hidden references where possible.

Note, however, that there are certain cases where cannot avoid
enumerating even hidden references, in particular when either of:

  - `uploadpack.allowTipSHA1InWant`, or
  - `uploadpack.allowReachableSHA1InWant`

are set, corresponding to `ALLOW_TIP_SHA1` and `ALLOW_REACHABLE_SHA1`,
respectively.

When either of these bits are set, upload-pack's `is_our_ref()` function
needs to consider the `HIDDEN_REF` bit of the referent's object flags.
So we must visit all references, including the hidden ones, in order to
mark their referents with the `HIDDEN_REF` bit.

When neither `ALLOW_TIP_SHA1` nor `ALLOW_REACHABLE_SHA1` are set, the
`is_our_ref()` function considers only the `OUR_REF` bit, and not the
`HIDDEN_REF` one. `OUR_REF` is applied via `mark_our_ref()`, and only
to objects at the tips of non-hidden references, so we do not need to
visit hidden references in this case.

When neither of those bits are set, `upload-pack` can potentially avoid
enumerating a large number of references. In the same example as a
previous commit (linux.git with one hidden reference per commit,
"refs/pull/N"):

    $ printf 0000 >in
    $ hyperfine --warmup=1 \
      'git -c transfer.hideRefs=refs/pull upload-pack . <in' \
      'git.compile -c transfer.hideRefs=refs/pull -c uploadpack.allowTipSHA1InWant upload-pack . <in' \
      'git.compile -c transfer.hideRefs=refs/pull upload-pack . <in'
    Benchmark 1: git -c transfer.hideRefs=refs/pull upload-pack . <in
      Time (mean ± σ):     406.9 ms ±   1.1 ms    [User: 357.3 ms, System: 49.5 ms]
      Range (min … max):   405.7 ms … 409.2 ms    10 runs

    Benchmark 2: git.compile -c transfer.hideRefs=refs/pull -c uploadpack.allowTipSHA1InWant upload-pack . <in
      Time (mean ± σ):     406.5 ms ±   1.3 ms    [User: 356.5 ms, System: 49.9 ms]
      Range (min … max):   404.6 ms … 408.8 ms    10 runs

    Benchmark 3: git.compile -c transfer.hideRefs=refs/pull upload-pack . <in
      Time (mean ± σ):       4.7 ms ±   0.2 ms    [User: 0.7 ms, System: 3.9 ms]
      Range (min … max):     4.3 ms …   6.1 ms    472 runs

    Summary
      'git.compile -c transfer.hideRefs=refs/pull upload-pack . <in' ran
       86.62 ± 4.33 times faster than 'git.compile -c transfer.hideRefs=refs/pull -c uploadpack.allowTipSHA1InWant upload-pack . <in'
       86.70 ± 4.33 times faster than 'git -c transfer.hideRefs=refs/pull upload-pack . <in'

As above, we must visit every reference when
uploadPack.allowTipSHA1InWant is set. But when it is unset, we can visit
far fewer references.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 upload-pack.c | 37 +++++++++++++++++++++++++++++++------
 1 file changed, 31 insertions(+), 6 deletions(-)
diff mbox series

Patch

diff --git a/upload-pack.c b/upload-pack.c
index da4f17f64ac..db4709adb77 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -602,11 +602,36 @@  static int get_common_commits(struct upload_pack_data *data,
 	}
 }
 
+static int allow_hidden_refs(enum allow_uor allow_uor)
+{
+	if ((allow_uor & ALLOW_ANY_SHA1) == ALLOW_ANY_SHA1)
+		return 1;
+	return !(allow_uor & (ALLOW_TIP_SHA1 | ALLOW_REACHABLE_SHA1));
+}
+
+static void for_each_namespaced_ref_1(each_ref_fn fn,
+				      struct upload_pack_data *data)
+{
+	const char **excludes = NULL;
+	/*
+	 * If `data->allow_uor` allows fetching hidden refs, we need to
+	 * mark all references (including hidden ones), to check in
+	 * `is_our_ref()` below.
+	 *
+	 * Otherwise, we only care about whether each reference's object
+	 * has the OUR_REF bit set or not, so do not need to visit
+	 * hidden references.
+	 */
+	if (allow_hidden_refs(data->allow_uor))
+		excludes = hidden_refs_to_excludes(&data->hidden_refs);
+
+	for_each_namespaced_ref(excludes, fn, data);
+}
+
+
 static int is_our_ref(struct object *o, enum allow_uor allow_uor)
 {
-	int allow_hidden_ref = (allow_uor &
-				(ALLOW_TIP_SHA1 | ALLOW_REACHABLE_SHA1));
-	return o->flags & ((allow_hidden_ref ? HIDDEN_REF : 0) | OUR_REF);
+	return o->flags & ((allow_hidden_refs(allow_uor) ? 0 : HIDDEN_REF) | OUR_REF);
 }
 
 /*
@@ -855,7 +880,7 @@  static void deepen(struct upload_pack_data *data, int depth)
 		 * marked with OUR_REF.
 		 */
 		head_ref_namespaced(check_ref, data);
-		for_each_namespaced_ref(NULL, check_ref, data);
+		for_each_namespaced_ref_1(check_ref, data);
 
 		get_reachable_list(data, &reachable_shallows);
 		result = get_shallow_commits(&reachable_shallows,
@@ -1392,7 +1417,7 @@  void upload_pack(const int advertise_refs, const int stateless_rpc,
 		if (advertise_refs)
 			data.no_done = 1;
 		head_ref_namespaced(send_ref, &data);
-		for_each_namespaced_ref(NULL, send_ref, &data);
+		for_each_namespaced_ref_1(send_ref, &data);
 		if (!data.sent_capabilities) {
 			const char *refname = "capabilities^{}";
 			write_v0_ref(&data, refname, refname, null_oid());
@@ -1406,7 +1431,7 @@  void upload_pack(const int advertise_refs, const int stateless_rpc,
 		packet_flush(1);
 	} else {
 		head_ref_namespaced(check_ref, &data);
-		for_each_namespaced_ref(NULL, check_ref, &data);
+		for_each_namespaced_ref_1(check_ref, &data);
 	}
 
 	if (!advertise_refs) {