From: Josh Snyder <josh@code406.com>
To: Willy Tarreau <w@1wt.eu>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
Tom Herbert <tom@herbertland.com>,
Tolga Ceylan <tolga.ceylan@gmail.com>,
Aaron Conole <aconole@bytheb.org>,
"David S. Miller" <davem@davemloft.net>,
Linux Kernel Network Developers <netdev@vger.kernel.org>
Subject: Re: [PATCH 1/1] net: Add SO_REUSEPORT_LISTEN_OFF socket option as drain mode
Date: Fri, 18 Dec 2015 08:33:45 -0800 [thread overview]
Message-ID: <CAO5YkUSL=k3UxmuqkGN666YSvH-=UGKCZvRgqqBnnr1EPRqRtw@mail.gmail.com> (raw)
In-Reply-To: <20151216161514.GA3476@1wt.eu>
I was also puzzled that binding succeeded. Looking into the code paths
involved, in inet_csk_get_port, we quickly goto have_snum. From there, we end
up dropping into tb_found. Since !hlist_empty(&tb->owners), we end up checking
that (tb->fastreuseport > 0 && sk->sk_reuseport && uid_eq(tb->fastuid, uid)).
This test passes, so we goto success and bind.
Crucially, we are checking the fastreuseport field on the inet_bind_bucket, and
not the sk_reuseport variable on the other sockets in the bucket. Since this
bit is set based on sk_reuseport at the time the first socket binds (see
tb_not_found), I can see no reason why sockets need to keep SO_REUSEPORT set
beyond initial binding.
Given this, I believe Willy's patch elegantly solves the problem at hand.
Josh
On Wed, Dec 16, 2015 at 8:15 AM, Willy Tarreau <w@1wt.eu> wrote:
> Hi Eric,
>
> On Wed, Dec 16, 2015 at 08:38:14AM +0100, Willy Tarreau wrote:
>> On Tue, Dec 15, 2015 at 01:21:15PM -0800, Eric Dumazet wrote:
>> > On Tue, 2015-12-15 at 20:44 +0100, Willy Tarreau wrote:
>> >
>> > > Thus do you think it's worth adding a new option as Tolga proposed ?
>> >
>> >
>> > I thought we tried hard to avoid adding the option but determined
>> > we could not avoid it ;)
>>
>> Not yet, your other proposal of disabling SO_REUSEPORT makes sense if
>> we combine it with the proposal to change the score in my patch. If
>> we say that a socket which has SO_REUSEPORT scores higher, then the
>> connections which don't want to accept new connections anymore will
>> simply have to drop it an not be elected. I find this even cleaner
>> since the sole purpose of the loop is to find the best socket in case
>> of SO_REUSEPORT.
>
> So I tried this and am pretty satisfied with the results, as I couldn't
> see any single reset on 4.4-rc5 with it. On 4.1 I got a few very rare
> resets at the exact moment the new process binds to the socket, because
> I suspect some ACKs end up in the wrong queue exactly there. But
> apparently the changes you did in 4.4 totally got rid of this, which is
> great!
>
> I suspected that I could enter a situation where a new process could
> fail to bind if generations n-1 and n-2 were still present, because
> n-2 would be running without SO_REUSEPORT and that should make this
> test fail in inet_csk_bind_conflict(), but it never failed for me :
>
> if ((!reuse || !sk2->sk_reuse ||
> sk2->sk_state == TCP_LISTEN) &&
> (!reuseport || !sk2->sk_reuseport ||
> (sk2->sk_state != TCP_TIME_WAIT &&
> !uid_eq(uid, sock_i_uid(sk2))))) {
> ...
>
> So I'm clearly missing something and can't spot what. I mean, I'd
> prefer to see my patch occasionally fail than not understanding why
> it always works! If anyone has an suggestion I'm interested.
>
> Here's the updated patch.
>
> Best regards,
> Willy
>
next prev parent reply other threads:[~2015-12-18 16:33 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-27 0:30 [PATCH 1/1] net: Add SO_REUSEPORT_LISTEN_OFF socket option as drain mode Tolga Ceylan
2015-09-27 1:04 ` Eric Dumazet
2015-09-27 1:37 ` Tolga Ceylan
2015-09-27 1:44 ` Aaron Conole
2015-09-27 2:02 ` Tolga Ceylan
2015-09-27 2:24 ` Eric Dumazet
2015-11-11 5:41 ` Tom Herbert
2015-11-11 6:19 ` Eric Dumazet
2015-11-11 17:05 ` Tom Herbert
2015-11-11 17:23 ` Eric Dumazet
2015-11-11 18:23 ` Tom Herbert
2015-11-11 18:43 ` Eric Dumazet
2015-11-12 1:09 ` Eric Dumazet
2015-12-15 16:14 ` Willy Tarreau
2015-12-15 17:10 ` Eric Dumazet
2015-12-15 17:43 ` Willy Tarreau
2015-12-15 18:21 ` Eric Dumazet
2015-12-15 19:44 ` Willy Tarreau
2015-12-15 21:21 ` Eric Dumazet
2015-12-16 7:38 ` Willy Tarreau
2015-12-16 16:15 ` Willy Tarreau
2015-12-18 16:33 ` Josh Snyder [this message]
2015-12-18 18:58 ` Willy Tarreau
2015-12-19 2:38 ` Eric Dumazet
2015-12-19 7:00 ` Willy Tarreau
2015-12-21 20:38 ` Tom Herbert
2015-12-21 20:41 ` Willy Tarreau
2016-03-24 5:10 ` Tolga Ceylan
2016-03-24 6:12 ` Willy Tarreau
2016-03-24 14:13 ` Eric Dumazet
2016-03-24 14:22 ` Willy Tarreau
2016-03-24 14:45 ` Eric Dumazet
2016-03-24 15:30 ` Willy Tarreau
2016-03-24 16:33 ` Eric Dumazet
2016-03-24 16:50 ` Willy Tarreau
2016-03-24 17:01 ` Eric Dumazet
2016-03-24 17:26 ` Tom Herbert
2016-03-24 17:55 ` Daniel Borkmann
2016-03-24 18:20 ` Tolga Ceylan
2016-03-24 18:24 ` Willy Tarreau
2016-03-24 18:37 ` Eric Dumazet
2016-03-24 22:40 ` Yann Ylavic
2016-03-24 22:49 ` Eric Dumazet
2016-03-24 23:40 ` Yann Ylavic
2016-03-24 23:54 ` Tom Herbert
2016-03-25 0:01 ` Yann Ylavic
2016-03-25 5:28 ` Willy Tarreau
2016-03-25 6:49 ` Eric Dumazet
2016-03-25 8:53 ` Willy Tarreau
2016-03-25 11:21 ` Yann Ylavic
2016-03-25 13:17 ` Eric Dumazet
2016-03-25 0:25 ` David Miller
2016-03-25 0:24 ` David Miller
2016-03-24 18:00 ` Willy Tarreau
2016-03-24 18:21 ` Willy Tarreau
2016-03-24 18:32 ` Eric Dumazet
2016-03-25 15:29 Craig Gallek
2016-03-25 16:21 ` Alexei Starovoitov
2016-03-25 16:31 ` Craig Gallek
2016-03-25 17:00 ` Eric Dumazet
2016-03-25 18:31 ` Willem de Bruijn
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAO5YkUSL=k3UxmuqkGN666YSvH-=UGKCZvRgqqBnnr1EPRqRtw@mail.gmail.com' \
--to=josh@code406.com \
--cc=aconole@bytheb.org \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=tolga.ceylan@gmail.com \
--cc=tom@herbertland.com \
--cc=w@1wt.eu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).