Message-ID: <CAK6E8=cgFKuGecTzSCSQ8z3YJ_163C0uwO9yRvfDSE7vOe9mJA@mail.gmail.com>
Date:   Tue, 8 Jun 2021 16:47:37 -0700
From:   Yuchung Cheng <ycheng@...gle.com>
To:     Kuniyuki Iwashima <kuniyu@...zon.co.jp>
Cc:     Andrii Nakryiko <andrii@...nel.org>,
        Alexei Starovoitov <ast@...nel.org>,
        Benjamin Herrenschmidt <benh@...zon.com>, bpf@...r.kernel.org,
        Daniel Borkmann <daniel@...earbox.net>,
        David Miller <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>, Martin Lau <kafai@...com>,
        Jakub Kicinski <kuba@...nel.org>,
        Kuniyuki Iwashima <kuni1840@...il.com>,
        LKML <linux-kernel@...r.kernel.org>,
        Neal Cardwell <ncardwell@...gle.com>,
        netdev <netdev@...r.kernel.org>
Subject: Re: [PATCH v7 bpf-next 00/11] Socket migration for SO_REUSEPORT.

On Tue, Jun 8, 2021 at 4:04 PM Kuniyuki Iwashima <kuniyu@...zon.co.jp> wrote:
>
> From:   Yuchung Cheng <ycheng@...gle.com>
> Date:   Tue, 8 Jun 2021 10:48:06 -0700
> > On Tue, May 25, 2021 at 11:42 PM Daniel Borkmann <daniel@...earbox.net> wrote:
> > >
> > > On 5/21/21 8:20 PM, Kuniyuki Iwashima wrote:
> > > > The SO_REUSEPORT option allows sockets to listen on the same port and to
> > > > accept connections evenly. However, there is a defect in the current
> > > > implementation [1]. When a SYN packet is received, the connection is tied
> > > > to a listening socket. Accordingly, when the listener is closed, in-flight
> > > > requests during the three-way handshake and child sockets in the accept
> > > > queue are dropped even if other listeners on the same port could accept
> > > > such connections.
> > > >
> > > > This situation can happen when various server management tools restart
> > > > server (such as nginx) processes. For instance, when we change nginx
> > > > configurations and restart it, it spins up new workers that respect the new
> > > > configuration and closes all listeners on the old workers, resulting in the
> > > > in-flight ACK of 3WHS is responded by RST.
> > > >
> > > > To avoid such a situation, users have to know deeply how the kernel handles
> > > > SYN packets and implement connection draining by eBPF [2]:
> > > >
> > > >    1. Stop routing SYN packets to the listener by eBPF.
> > > >    2. Wait for all timers to expire to complete requests
> > > >    3. Accept connections until EAGAIN, then close the listener.
> > > >
> > > >    or
> > > >
> > > >    1. Start counting SYN packets and accept syscalls using the eBPF map.
> > > >    2. Stop routing SYN packets.
> > > >    3. Accept connections up to the count, then close the listener.
> > > >
> > > > In either way, we cannot close a listener immediately. However, ideally,
> > > > the application need not drain the not yet accepted sockets because 3WHS
> > > > and tying a connection to a listener are just the kernel behaviour. The
> > > > root cause is within the kernel, so the issue should be addressed in kernel
> > > > space and should not be visible to user space. This patchset fixes it so
> > > > that users need not take care of kernel implementation and connection
> > > > draining. With this patchset, the kernel redistributes requests and
> > > > connections from a listener to the others in the same reuseport group
> > > > at/after close or shutdown syscalls.
> > > >
> > > > Although some software does connection draining, there are still merits in
> > > > migration. For some security reasons, such as replacing TLS certificates,
> > > > we may want to apply new settings as soon as possible and/or we may not be
> > > > able to wait for connection draining. The sockets in the accept queue have
> > > > not started application sessions yet. So, if we do not drain such sockets,
> > > > they can be handled by the newer listeners and could have a longer
> > > > lifetime. It is difficult to drain all connections in every case, but we
> > > > can decrease such aborted connections by migration. In that sense,
> > > > migration is always better than draining.
> > > >
> > > > Moreover, auto-migration simplifies user space logic and also works well in
> > > > a case where we cannot modify and build a server program to implement the
> > > > workaround.
> > > >
> > > > Note that the source and destination listeners MUST have the same settings
> > > > at the socket API level; otherwise, applications may face inconsistency and
> > > > cause errors. In such a case, we have to use the eBPF program to select a
> > > > specific listener or to cancel migration.
> > This looks to be a useful feature. What happens to migrating a
> > passively fast-opened socket in the old listener but it has not yet
> > been accepted (TFO is both a mini-socket and a full-socket)?
> > It gets tricky when the old and new listener have different TFO key
>
> The tricky situation can happen without this patch set. We can change
> the listener's TFO key when TCP_SYN_RECV sockets are still in the accept
> queue. The change is already handled properly, so it does not crash
> applications.
>
> In the normal 3WHS case, a full-socket is created after 3WHS. In the TFO
> case, a full-socket is created after validating the TFO cookie in the
> initial SYN packet.
>
> After that, the connection is basically handled via the full-socket, except
> for accept() syscall. So in the both cases, the mini-socket is poped out of
> old listener's queue, cloned, and put into the new listner's queue. Then we
> can accept() its full-socket via the cloned mini-socket.

Thanks, that makes sense. Eric is the expert in this part to review
the correctness. My only suggestion is to add some stats tracking the
mini-sockets that fail to migrate due to a variety of reasons (the
code locations that the requests need to be dropped). This can be
useful to evaluate the effectiveness of this new feature.

Powered by blists - more mailing lists