From: Neal Cardwell <ncardwell@google.com> To: "Bendik Rønning Opstad" <bro.devel@gmail.com> Cc: "David S. Miller" <davem@davemloft.net>, "Alexey Kuznetsov" <kuznet@ms2.inr.ac.ru>, "James Morris" <jmorris@namei.org>, "Hideaki YOSHIFUJI" <yoshfuji@linux-ipv6.org>, "Patrick McHardy" <kaber@trash.net>, "Jonathan Corbet" <corbet@lwn.net>, "Eric Dumazet" <edumazet@google.com>, "Tom Herbert" <tom@herbertland.com>, "Yuchung Cheng" <ycheng@google.com>, "Paolo Abeni" <pabeni@redhat.com>, "Erik Kline" <ek@google.com>, "Hannes Frederic Sowa" <hannes@stressinduktion.org>, "Al Viro" <viro@zeniv.linux.org.uk>, "Jiri Pirko" <jiri@resnulli.us>, "Alexander Duyck" <alexander.h.duyck@redhat.com>, "Florian Westphal" <fw@strlen.de>, "Daniel Lee" <Longinus00@gmail.com>, "Marcelo Ricardo Leitner" <mleitner@redhat.com>, "Daniel Borkmann" <daniel@iogearbox.net>, "Willem de Bruijn" <willemb@google.com>, "Linus Lüssing" <linus.luessing@c0d3.blue>, linux-doc@vger.kernel.org, LKML <linux-kernel@vger.kernel.org>, Netdev <netdev@vger.kernel.org>, linux-api@vger.kernel.org, "Andreas Petlund" <apetlund@simula.no>, "Carsten Griwodz" <griff@simula.no>, "Pål Halvorsen" <paalh@simula.no>, "Jonas Markussen" <jonassm@ifi.uio.no>, "Kristian Evensen" <kristian.evensen@gmail.com>, "Kenneth Klette Jonassen" <kennetkl@ifi.uio.no>, "Bendik Rønning Opstad" <bro.devel+kernel@gmail.com> Subject: Re: [PATCH RFC net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Date: Mon, 26 Oct 2015 10:50:11 -0400 [thread overview] Message-ID: <CADVnQykhCKU+5DyX1r73nRQjqw7qbM81yHgTzY5pG=h9kpj6Xw@mail.gmail.com> (raw) In-Reply-To: <1445633413-3532-3-git-send-email-bro.devel+kernel@gmail.com> On Fri, Oct 23, 2015 at 4:50 PM, Bendik Rønning Opstad <bro.devel@gmail.com> wrote: >@@ -2409,6 +2412,15 @@ static int do_tcp_setsockopt(struct sock *sk, int level, ... > + case TCP_RDB: > + if (val < 0 || val > 1) { > + err = -EINVAL; > + } else { > + tp->rdb = val; > + tp->nonagle = val; The semantics of the tp->nonagle bits are already a bit complex. My sense is that having a setsockopt of TCP_RDB transparently modify the nagle behavior is going to add more extra complexity and unanticipated behavior than is warranted given the slight possible gain in convenience to the app writer. What about a model where the application user just needs to remember to call setsockopt(TCP_NODELAY) if they want the TCP_RDB behavior to be sensible? I see your nice tests at https://github.com/bendikro/packetdrill/commit/9916b6c53e33dd04329d29b7d8baf703b2c2ac1b are already doing that. And my sense is that likewise most well-engineered "thin stream" apps will already be using setsockopt(TCP_NODELAY). Is that workable? neal
WARNING: multiple messages have this Message-ID (diff)
From: Neal Cardwell <ncardwell@google.com> To: "Bendik Rønning Opstad" <bro.devel@gmail.com> Cc: "David S. Miller" <davem@davemloft.net>, "Alexey Kuznetsov" <kuznet@ms2.inr.ac.ru>, "James Morris" <jmorris@namei.org>, "Hideaki YOSHIFUJI" <yoshfuji@linux-ipv6.org>, "Patrick McHardy" <kaber@trash.net>, "Jonathan Corbet" <corbet@lwn.net>, "Eric Dumazet" <edumazet@google.com>, "Tom Herbert" <tom@herbertland.com>, "Yuchung Cheng" <ycheng@google.com>, "Paolo Abeni" <pabeni@redhat.com>, "Erik Kline" <ek@google.com>, "Hannes Frederic Sowa" <hannes@stressinduktion.org>, "Al Viro" <viro@zeniv.linux.org.uk>, "Jiri Pirko" <jiri@resnulli.us>, "Alexander Duyck" <alexander.h.duyck@redhat.com>, "Florian Westphal" <fw@strlen.de>, "Daniel Lee" <Longinus00@gmail.com>, "Marcelo Ricardo Leitner" <mleitner@redhat.com>, "Daniel Borkmann" <daniel@iogearbox.net>, "Willem de Bruijn" <willemb@google.com>, "Linus Lüssing" <linus.luessing@c0d3.blue>, linux-doc@vger.kernel.org, LKML <linux-kernel@vger.kernel.org> Subject: Re: [PATCH RFC net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Date: Mon, 26 Oct 2015 10:50:11 -0400 [thread overview] Message-ID: <CADVnQykhCKU+5DyX1r73nRQjqw7qbM81yHgTzY5pG=h9kpj6Xw@mail.gmail.com> (raw) In-Reply-To: <1445633413-3532-3-git-send-email-bro.devel+kernel@gmail.com> On Fri, Oct 23, 2015 at 4:50 PM, Bendik Rønning Opstad <bro.devel@gmail.com> wrote: >@@ -2409,6 +2412,15 @@ static int do_tcp_setsockopt(struct sock *sk, int level, ... > + case TCP_RDB: > + if (val < 0 || val > 1) { > + err = -EINVAL; > + } else { > + tp->rdb = val; > + tp->nonagle = val; The semantics of the tp->nonagle bits are already a bit complex. My sense is that having a setsockopt of TCP_RDB transparently modify the nagle behavior is going to add more extra complexity and unanticipated behavior than is warranted given the slight possible gain in convenience to the app writer. What about a model where the application user just needs to remember to call setsockopt(TCP_NODELAY) if they want the TCP_RDB behavior to be sensible? I see your nice tests at https://github.com/bendikro/packetdrill/commit/9916b6c53e33dd04329d29b7d8baf703b2c2ac1b are already doing that. And my sense is that likewise most well-engineered "thin stream" apps will already be using setsockopt(TCP_NODELAY). Is that workable? neal
next prev parent reply other threads:[~2015-10-26 14:50 UTC|newest] Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top 2015-10-23 20:50 [PATCH RFC net-next 0/2] tcp: Redundant Data Bundling (RDB) Bendik Rønning Opstad 2015-10-23 20:50 ` Bendik Rønning Opstad 2015-10-23 20:50 ` [PATCH RFC net-next 1/2] tcp: Add DPIFL thin stream detection mechanism Bendik Rønning Opstad 2015-10-23 20:50 ` Bendik Rønning Opstad 2015-10-23 21:44 ` Eric Dumazet 2015-10-23 21:44 ` Eric Dumazet 2015-10-25 5:56 ` Bendik Rønning Opstad 2015-10-25 5:56 ` Bendik Rønning Opstad 2015-10-23 20:50 ` [PATCH RFC net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Bendik Rønning Opstad 2015-10-23 20:50 ` Bendik Rønning Opstad 2015-10-26 14:50 ` Neal Cardwell [this message] 2015-10-26 14:50 ` Neal Cardwell 2015-10-26 21:35 ` Andreas Petlund 2015-10-26 21:35 ` Andreas Petlund 2015-10-26 21:58 ` Yuchung Cheng 2015-10-26 21:58 ` Yuchung Cheng 2015-10-27 19:15 ` Jonas Markussen 2015-10-27 19:15 ` Jonas Markussen 2015-10-29 22:53 ` Bendik Rønning Opstad 2015-10-29 22:53 ` Bendik Rønning Opstad 2015-11-02 9:18 ` David Laight 2015-11-02 9:18 ` David Laight 2015-11-02 9:37 ` David Laight 2015-11-02 9:37 ` David Laight 2015-11-05 2:06 ` Bendik Rønning Opstad 2015-11-05 2:06 ` Bendik Rønning Opstad 2015-11-05 2:06 ` Bendik Rønning Opstad 2015-10-24 6:11 ` [PATCH RFC net-next 0/2] tcp: " Yuchung Cheng 2015-10-24 6:11 ` Yuchung Cheng 2015-10-24 6:11 ` Yuchung Cheng 2015-10-24 8:00 ` Jonas Markussen 2015-10-24 8:00 ` Jonas Markussen 2015-10-24 12:57 ` Eric Dumazet 2015-10-24 12:57 ` Eric Dumazet 2015-11-09 19:40 ` Bendik Rønning Opstad 2015-11-23 16:26 ` [PATCH RFC v2 " Bendik Rønning Opstad 2015-11-23 16:26 ` [PATCH RFC v2 net-next 1/2] tcp: Add DPIFL thin stream detection mechanism Bendik Rønning Opstad 2015-11-23 16:26 ` [PATCH RFC v2 net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Bendik Rønning Opstad 2015-11-23 17:43 ` Eric Dumazet 2015-11-23 20:05 ` Bendik Rønning Opstad 2016-02-02 19:23 ` [PATCH v3 net-next 0/2] tcp: " Bendik Rønning Opstad 2016-02-02 19:23 ` [PATCH v3 net-next 1/2] tcp: Add DPIFL thin stream detection mechanism Bendik Rønning Opstad 2016-02-02 19:23 ` [PATCH v3 net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Bendik Rønning Opstad 2016-02-02 20:35 ` Eric Dumazet 2016-02-03 18:17 ` Bendik Rønning Opstad 2016-02-03 19:34 ` Eric Dumazet [not found] ` <CAF8eE=VOuoNLQHtkRwM9ZG+vJ-uH2ufVW5y_pS24rGqWh4Qa2g@mail.gmail.com> 2016-02-08 17:30 ` Bendik Rønning Opstad 2016-02-08 17:38 ` Bendik Rønning Opstad 2016-02-16 13:51 ` [PATCH v4 net-next 0/2] tcp: " Bendik Rønning Opstad 2016-02-16 13:51 ` [PATCH v4 net-next 1/2] tcp: Add DPIFL thin stream detection mechanism Bendik Rønning Opstad 2016-02-16 13:51 ` [PATCH v4 net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Bendik Rønning Opstad 2016-02-18 15:18 ` Eric Dumazet 2016-02-19 14:12 ` Bendik Rønning Opstad 2016-02-24 21:12 ` [PATCH v5 net-next 0/2] tcp: " Bendik Rønning Opstad 2016-02-24 21:12 ` [PATCH v5 net-next 1/2] tcp: Add DPIFL thin stream detection mechanism Bendik Rønning Opstad 2016-02-24 21:12 ` [PATCH v5 net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Bendik Rønning Opstad 2016-03-02 19:52 ` David Miller 2016-03-02 22:33 ` Bendik Rønning Opstad 2016-03-03 18:06 ` [PATCH v6 net-next 0/2] tcp: " Bendik Rønning Opstad 2016-03-07 19:36 ` David Miller 2016-03-10 0:20 ` Yuchung Cheng 2016-03-10 1:45 ` Jonas Markussen 2016-03-10 2:27 ` Yuchung Cheng 2016-03-12 9:23 ` Jonas Markussen 2016-03-13 23:18 ` Bendik Rønning Opstad 2016-03-14 21:59 ` Yuchung Cheng 2016-03-18 14:25 ` Bendik Rønning Opstad 2016-03-03 18:06 ` [PATCH v6 net-next 1/2] tcp: Add DPIFL thin stream detection mechanism Bendik Rønning Opstad 2016-03-03 18:06 ` [PATCH v6 net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Bendik Rønning Opstad 2016-03-14 21:15 ` Eric Dumazet 2016-03-15 1:04 ` Rick Jones 2016-03-15 18:09 ` Yuchung Cheng 2016-03-18 17:58 ` Bendik Rønning Opstad 2016-03-14 21:54 ` Yuchung Cheng 2016-03-15 0:40 ` Bill Fink 2016-03-17 23:26 ` Bendik Rønning Opstad 2016-03-21 18:54 ` Yuchung Cheng 2016-06-16 17:12 ` Bendik Rønning Opstad 2016-06-22 14:56 ` [PATCH v7 net-next 0/2] tcp: " Bendik Rønning Opstad 2016-06-22 14:56 ` [PATCH v7 net-next 1/2] tcp: Add DPIFL thin stream detection mechanism Bendik Rønning Opstad 2016-06-22 14:56 ` [PATCH v7 net-next 2/2] tcp: Add Redundant Data Bundling (RDB) Bendik Rønning Opstad
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='CADVnQykhCKU+5DyX1r73nRQjqw7qbM81yHgTzY5pG=h9kpj6Xw@mail.gmail.com' \ --to=ncardwell@google.com \ --cc=Longinus00@gmail.com \ --cc=alexander.h.duyck@redhat.com \ --cc=apetlund@simula.no \ --cc=bro.devel+kernel@gmail.com \ --cc=bro.devel@gmail.com \ --cc=corbet@lwn.net \ --cc=daniel@iogearbox.net \ --cc=davem@davemloft.net \ --cc=edumazet@google.com \ --cc=ek@google.com \ --cc=fw@strlen.de \ --cc=griff@simula.no \ --cc=hannes@stressinduktion.org \ --cc=jiri@resnulli.us \ --cc=jmorris@namei.org \ --cc=jonassm@ifi.uio.no \ --cc=kaber@trash.net \ --cc=kennetkl@ifi.uio.no \ --cc=kristian.evensen@gmail.com \ --cc=kuznet@ms2.inr.ac.ru \ --cc=linus.luessing@c0d3.blue \ --cc=linux-api@vger.kernel.org \ --cc=linux-doc@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=mleitner@redhat.com \ --cc=netdev@vger.kernel.org \ --cc=paalh@simula.no \ --cc=pabeni@redhat.com \ --cc=tom@herbertland.com \ --cc=viro@zeniv.linux.org.uk \ --cc=willemb@google.com \ --cc=ycheng@google.com \ --cc=yoshfuji@linux-ipv6.org \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.