[PATCH v3 2/2] upload-pack: use stdio in send_ref callbacks

From: Jacob Vosmaer <jacob@gitlab.com>
Date: Aug 31, 2021, 09:34 UTC
Message-ID: <20210831093444.28199-3-jacob@gitlab.com>
In-Reply-To: <20210831093444.28199-1-jacob@gitlab.com>

In both protocol v0 and v2, upload-pack writes one pktline packet per advertised ref to stdout. That means one or two write(2) syscalls per ref. This is problematic if these writes become network sends with high overhead.

This commit changes both send_ref callbacks to use buffered IO using stdio.

To give an example of the impact: I set up a single-threaded loop that calls ls-remote (with HTTP and protocol v2) on a local GitLab instance, on a repository with 11K refs. When I switch from Git v2.32.0 to this patch, I see a 40% reduction in CPU time for Git, and 65% for Gitaly (GitLab's Git RPC service).

So using buffered IO not only saves syscalls in upload-pack, it also saves time in things that consume upload-pack's output.

Helped-by: Jeff King <peff@peff.net>
Signed-off-by: Jacob Vosmaer <jacob@gitlab.com>
---
 ls-refs.c     |  4 ++--
 upload-pack.c | 11 ++++++++---
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/ls-refs.c b/ls-refs.c
index 88f6c3f60d..e6a2dbd962 100644
--- a/ls-refs.c
+++ b/ls-refs.c
@@ -105,7 +105,7 @@ static int send_ref(const char *refname, const struct object_id *oid,
 	}
 
 	strbuf_addch(&refline, '\n');
-	packet_write(1, refline.buf, refline.len);
+	packet_fwrite(stdout, refline.buf, refline.len);
 
 	strbuf_release(&refline);
 	return 0;
@@ -171,7 +171,7 @@ int ls_refs(struct repository *r, struct strvec *keys,
 		strvec_push(&data.prefixes, "");
 	for_each_fullref_in_prefixes(get_git_namespace(), data.prefixes.v,
 				     send_ref, &data, 0);
-	packet_flush(1);
+	packet_fflush(stdout);
 	strvec_clear(&data.prefixes);
 	return 0;
 }
diff --git a/upload-pack.c b/upload-pack.c
index 297b76fcb4..2fdd73dfcb 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -1207,7 +1207,7 @@ static int send_ref(const char *refname, const struct object_id *oid,
 
 		format_symref_info(&symref_info, &data->symref);
 		format_session_id(&session_id, data);
-		packet_write_fmt(1, "%s %s%c%s%s%s%s%s%s%s object-format=%s agent=%s\n",
+		packet_fwrite_fmt(stdout, "%s %s%c%s%s%s%s%s%s%s object-format=%s agent=%s\n",
 			     oid_to_hex(oid), refname_nons,
 			     0, capabilities,
 			     (data->allow_uor & ALLOW_TIP_SHA1) ?
@@ -1223,11 +1223,11 @@ static int send_ref(const char *refname, const struct object_id *oid,
 		strbuf_release(&symref_info);
 		strbuf_release(&session_id);
 	} else {
-		packet_write_fmt(1, "%s %s\n", oid_to_hex(oid), refname_nons);
+		packet_fwrite_fmt(stdout, "%s %s\n", oid_to_hex(oid), refname_nons);
 	}
 	capabilities = NULL;
 	if (!peel_iterated_oid(oid, &peeled))
-		packet_write_fmt(1, "%s %s^{}\n", oid_to_hex(&peeled), refname_nons);
+		packet_fwrite_fmt(stdout, "%s %s^{}\n", oid_to_hex(&peeled), refname_nons);
 	return 0;
 }
 
@@ -1348,6 +1348,11 @@ void upload_pack(struct upload_pack_options *options)
 		reset_timeout(data.timeout);
 		head_ref_namespaced(send_ref, &data);
 		for_each_namespaced_ref(send_ref, &data);
+		/* 
+		 * fflush stdout before calling advertise_shallow_grafts because send_ref
+		 * uses stdio.
+		 */
+		fflush_or_die(stdout);
 		advertise_shallow_grafts(1);
 		packet_flush(1);
 	} else {

-- 
2.32.0