qemu-kvm/SOURCES/kvm-nbd-server-push-pending...

73 lines
2.4 KiB
Diff

From 170872370c6f3c916e741eb32d80431995d7a870 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 24 Mar 2023 11:47:20 +0100
Subject: [PATCH 4/5] nbd/server: push pending frames after sending reply
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 274: nbd: improve TLS performance of NBD server
RH-Bugzilla: 2035712
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [1/2] ab92c06c48810aa40380de0433dcac4c6e4be9a5 (ebblake/qemu-kvm)
qemu-nbd doesn't set TCP_NODELAY on the tcp socket.
Kernel waits for more data and avoids transmission of small packets.
Without TLS this is barely noticeable, but with TLS this really shows.
Booting a VM via qemu-nbd on localhost (with tls) takes more than
2 minutes on my system. tcpdump shows frequent wait periods, where no
packets get sent for a 40ms period.
Add explicit (un)corking when processing (and responding to) requests.
"TCP_CORK, &zero" after earlier "CORK, &one" will flush pending data.
VM Boot time:
main: no tls: 23s, with tls: 2m45s
patched: no tls: 14s, with tls: 15s
VM Boot time, qemu-nbd via network (same lan):
main: no tls: 18s, with tls: 1m50s
patched: no tls: 17s, with tls: 18s
Future optimization: if we could detect if there is another pending
request we could defer the uncork operation because more data would be
appended.
Signed-off-by: Florian Westphal <fw@strlen.de>
Message-Id: <20230324104720.2498-1-fw@strlen.de>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit bd2cd4a441ded163b62371790876f28a9b834317)
Signed-off-by: Eric Blake <eblake@redhat.com>
---
nbd/server.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/nbd/server.c b/nbd/server.c
index 4630dd7322..a5edc7f681 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -2647,6 +2647,8 @@ static coroutine_fn void nbd_trip(void *opaque)
goto disconnect;
}
+ qio_channel_set_cork(client->ioc, true);
+
if (ret < 0) {
/* It wans't -EIO, so, according to nbd_co_receive_request()
* semantics, we should return the error to the client. */
@@ -2672,6 +2674,7 @@ static coroutine_fn void nbd_trip(void *opaque)
goto disconnect;
}
+ qio_channel_set_cork(client->ioc, false);
done:
nbd_request_put(req);
nbd_client_put(client);
--
2.39.1