Obviously my memory needs a backup 😊 Thanks /Ingemar
> -----Original Message----- > From: Eric Dumazet <eric.duma...@gmail.com> > Sent: den 10 december 2020 11:44 > To: Ingemar Johansson S <ingemar.s.johans...@ericsson.com>; Jakub Kicinski > <k...@kernel.org>; Neal Cardwell <ncardwell.ker...@gmail.com> > Cc: David Miller <da...@davemloft.net>; netdev@vger.kernel.org; Neal > Cardwell <ncardw...@google.com>; Yuchung Cheng <ych...@google.com>; > Soheil Hassas Yeganeh <soh...@google.com>; Eric Dumazet > <eduma...@google.com> > Subject: Re: [PATCH net] tcp: fix cwnd-limited bug for TSO deferral where we > send nothing > > > > On 12/10/20 10:50 AM, Ingemar Johansson S wrote: > > Hi > > Slighty off topic > > It is a smaller mystery why I am listed as having reported this artifact ?. > > I don't have any memory that I did so.. strange 😐. > > > > I think this was your report : > > https://mailarchive.ietf.org/arch/msg/tcpm/3U--r1vC81blOfZ5JwAYWIbm4vE/ > > Have fun ! > > > Regards > > Ingemar > > > >> -----Original Message----- > >> From: Jakub Kicinski <k...@kernel.org> > >> Sent: den 10 december 2020 01:14 > >> To: Neal Cardwell <ncardwell.ker...@gmail.com> > >> Cc: David Miller <da...@davemloft.net>; netdev@vger.kernel.org; Neal > >> Cardwell <ncardw...@google.com>; Ingemar Johansson S > >> <ingemar.s.johans...@ericsson.com>; Yuchung Cheng > >> <ych...@google.com>; Soheil Hassas Yeganeh <soh...@google.com>; Eric > >> Dumazet <eduma...@google.com> > >> Subject: Re: [PATCH net] tcp: fix cwnd-limited bug for TSO deferral where > we > >> send nothing > >> > >> On Tue, 8 Dec 2020 22:57:59 -0500 Neal Cardwell wrote: > >>> From: Neal Cardwell <ncardw...@google.com> > >>> > >>> When cwnd is not a multiple of the TSO skb size of N*MSS, we can get > >>> into persistent scenarios where we have the following sequence: > >>> > >>> (1) ACK for full-sized skb of N*MSS arrives > >>> -> tcp_write_xmit() transmit full-sized skb with N*MSS > >>> -> move pacing release time forward > >>> -> exit tcp_write_xmit() because pacing time is in the future > >>> > >>> (2) TSQ callback or TCP internal pacing timer fires > >>> -> try to transmit next skb, but TSO deferral finds remainder of > >>> available cwnd is not big enough to trigger an immediate send > >>> now, so we defer sending until the next ACK. > >>> > >>> (3) repeat... > >>> > >>> So we can get into a case where we never mark ourselves as > >>> cwnd-limited for many seconds at a time, even with > >>> bulk/infinite-backlog senders, because: > >>> > >>> o In case (1) above, every time in tcp_write_xmit() we have enough > >>> cwnd to send a full-sized skb, we are not fully using the cwnd > >>> (because cwnd is not a multiple of the TSO skb size). So every time we > >>> send data, we are not cwnd limited, and so in the cwnd-limited > >>> tracking code in tcp_cwnd_validate() we mark ourselves as not > >>> cwnd-limited. > >>> > >>> o In case (2) above, every time in tcp_write_xmit() that we try to > >>> transmit the "remainder" of the cwnd but defer, we set the local > >>> variable is_cwnd_limited to true, but we do not send any packets, so > >>> sent_pkts is zero, so we don't call the cwnd-limited logic to update > >>> tp->is_cwnd_limited. > >>> > >>> Fixes: ca8a22634381 ("tcp: make cwnd-limited checks measurement- > based, > >>> and gentler") > >>> Reported-by: Ingemar Johansson <ingemar.s.johans...@ericsson.com> > >>> Signed-off-by: Neal Cardwell <ncardw...@google.com> > >>> Signed-off-by: Yuchung Cheng <ych...@google.com> > >>> Acked-by: Soheil Hassas Yeganeh <soh...@google.com> > >>> Signed-off-by: Eric Dumazet <eduma...@google.com> > >> > >> Applied, thank you!
smime.p7s
Description: S/MIME cryptographic signature
