Date: Thu, 6 Mar 2025 10:50:09 -0500 From: Cheng Cui <cc@freebsd.org> To: jaeyong yoo <y.jaeyong@gmail.com> Cc: freebsd-net@freebsd.org Subject: Re: Sending empty segment upon receiving partial ACK Message-ID: <979E9D00-755F-4E4D-9687-CAB957F4C8C8@freebsd.org> In-Reply-To: <CANud0TGXtjt1x_gFJxYMH1VhW6eWehHDszBn3DaBe0AhV8=Wfw@mail.gmail.com> References: <CANud0THEOnkWbuOn413AV_auSrY7-SysXThrTyigZMxujEdqEg@mail.gmail.com> <38B72ADC-B796-4BFC-8F94-2BD6E40C4231@freebsd.org> <CANud0TEUTakZkHj39J%2BJRyS9DHRgPr4FKxpgvjHcJao_Si01FQ@mail.gmail.com> <AB5BD54B-8CB0-4E71-92CE-83EBEAD9B46E@freebsd.org> <CANud0TGXtjt1x_gFJxYMH1VhW6eWehHDszBn3DaBe0AhV8=Wfw@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--Apple-Mail=_33C3C34F-6F43-4C39-A322-D59D095948EC Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 I see Bug=C2=A0285158 = <https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D285158>; is created. = Let's talk/track it there. thanks > On Mar 5, 2025, at 16:58, jaeyong yoo <y.jaeyong@gmail.com> wrote: >=20 > Yes it is data retransmission but my concern is that the > retransmission packet has the segment length of zero. > If there is nothing to send, why don't we just not send it. >=20 > What I meant by "no packets going out" is, that zero-length-segment > can be considered as ACK to acknowledge some received packets but the > sender of "zero-length-segment" did not receive any packets hence > nothing to ACK. That said, those retransmission packets are the pure > purpose of retransmissions and its segment length is zero, which seems > pure overhead. > Hope this makes it clear. >=20 > Thanks, > Jaeyong >=20 > 2025=EB=85=84 3=EC=9B=94 5=EC=9D=BC (=EC=88=98) =EC=98=A4=ED=9B=84 = 12:30, Cheng Cui <cc@freebsd.org>=EB=8B=98=EC=9D=B4 =EC=9E=91=EC=84=B1: >>=20 >>=20 >>=20 >> On Feb 26, 2025, at 10:21, jaeyong yoo <y.jaeyong@gmail.com> wrote: >>=20 >> Yes that behavior was observed during recovery phase and during that >> time frame, there were no packets going out to the other direction so >> there is no reason to send pure ACK (and the ack number for those 3 >> acks are the same and no possibility of challenge ack as well). >>=20 >>=20 >> Isn't loss recovery phase used for data retransmission? There should = be retransmitting packets. But what do you mean "no packets going out"? >>=20 >> Best Regards, >> Cheng Cui >>=20 >>=20 >>=20 Best Regards, Cheng Cui --Apple-Mail=_33C3C34F-6F43-4C39-A322-D59D095948EC Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=utf-8 <html><head><meta http-equiv=3D"content-type" content=3D"text/html; = charset=3Dutf-8"></head><body style=3D"overflow-wrap: break-word; = -webkit-nbsp-mode: space; line-break: after-white-space;">I see <a = href=3D"https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D285158"><b>Bug= 285158</b></a><span style=3D"font-family: -webkit-standard; = font-size: medium;"></span> is created. Let's talk/track it there. = thanks<br id=3D"lineBreakAtBeginningOfMessage"><div><br><blockquote = type=3D"cite"><div>On Mar 5, 2025, at 16:58, jaeyong yoo = <y.jaeyong@gmail.com> wrote:</div><br = class=3D"Apple-interchange-newline"><div><div>Yes it is data = retransmission but my concern is that the<br>retransmission packet has = the segment length of zero.<br>If there is nothing to send, why don't we = just not send it.<br><br>What I meant by "no packets going out" is, that = zero-length-segment<br>can be considered as ACK to acknowledge some = received packets but the<br>sender of "zero-length-segment" did not = receive any packets hence<br>nothing to ACK. That said, those = retransmission packets are the pure<br>purpose of retransmissions and = its segment length is zero, which seems<br>pure overhead.<br>Hope this = makes it clear.<br><br>Thanks,<br>Jaeyong<br><br>2025=EB=85=84 3=EC=9B=94 = 5=EC=9D=BC (=EC=88=98) =EC=98=A4=ED=9B=84 12:30, Cheng Cui = <cc@freebsd.org>=EB=8B=98=EC=9D=B4 =EC=9E=91=EC=84=B1:<br><blockquot= e type=3D"cite"><br><br><br>On Feb 26, 2025, at 10:21, jaeyong yoo = <y.jaeyong@gmail.com> wrote:<br><br>Yes that behavior was observed = during recovery phase and during that<br>time frame, there were no = packets going out to the other direction so<br>there is no reason to = send pure ACK (and the ack number for those 3<br>acks are the same and = no possibility of challenge ack as well).<br><br><br>Isn't loss recovery = phase used for data retransmission? There should be retransmitting = packets. But what do you mean "no packets going out"?<br><br>Best = Regards,<br>Cheng = Cui<br><br><br><br></blockquote></div></div></blockquote></div><br><div> <div>Best Regards,<br>Cheng Cui</div><div><br></div><br = class=3D"Apple-interchange-newline"> </div> <br></body></html>= --Apple-Mail=_33C3C34F-6F43-4C39-A322-D59D095948EC--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?979E9D00-755F-4E4D-9687-CAB957F4C8C8>