Re: Too aggressive TCP ACKs
- Reply: Zhenlei Huang : "Re: Too aggressive TCP ACKs"
- In reply to: Zhenlei Huang : "Re: Too aggressive TCP ACKs"
- Go to: [ bottom of page ] [ top of archives ] [ this month ]
Date: Fri, 21 Oct 2022 18:16:21 UTC
> On 21. Oct 2022, at 17:00, Zhenlei Huang <zlei.huang@gmail.com> wrote: > > >> On Oct 21, 2022, at 10:34 PM, Michael Tuexen <michael.tuexen@lurchi.franken.de> wrote: >> >>> On 21. Oct 2022, at 16:19, Zhenlei Huang <zlei.huang@gmail.com> wrote: >>> >>> Hi, >>> >>> While I was repeating https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=258755, I observed a >>> strange behavior. The TCP ACKs from FreeBSD host are too aggressive. >>> >>> My setup is simple: >>> A B >>> [ MacOS ] <====> [ FreeBSD VM ] >>> 192.168.120.1 192.168.12.134 (disable tso and lro) >>> While A <--- B, i.e. A as server and B as client, the packets rate looks good. >>> >>> One session on B: >>> >>> root@:~ # iperf3 -c 192.168.120.1 -b 10m >>> Connecting to host 192.168.120.1, port 5201 >>> [ 5] local 192.168.120.134 port 54459 connected to 192.168.120.1 port 5201 >>> [ ID] Interval Transfer Bitrate Retr Cwnd >>> [ 5] 0.00-1.00 sec 1.25 MBytes 10.5 Mbits/sec 0 257 KBytes >>> [ 5] 1.00-2.00 sec 1.25 MBytes 10.5 Mbits/sec 0 257 KBytes >>> [ 5] 2.00-3.00 sec 1.12 MBytes 9.44 Mbits/sec 0 257 KBytes >>> [ 5] 3.00-4.00 sec 1.25 MBytes 10.5 Mbits/sec 0 257 KBytes >>> [ 5] 4.00-5.00 sec 1.12 MBytes 9.44 Mbits/sec 0 257 KBytes >>> [ 5] 5.00-6.00 sec 1.25 MBytes 10.5 Mbits/sec 0 257 KBytes >>> [ 5] 6.00-7.00 sec 1.12 MBytes 9.44 Mbits/sec 0 257 KBytes >>> [ 5] 7.00-8.00 sec 1.25 MBytes 10.5 Mbits/sec 0 257 KBytes >>> [ 5] 8.00-9.00 sec 1.12 MBytes 9.44 Mbits/sec 0 257 KBytes >>> [ 5] 9.00-10.00 sec 1.25 MBytes 10.5 Mbits/sec 0 257 KBytes >>> - - - - - - - - - - - - - - - - - - - - - - - - - >>> [ ID] Interval Transfer Bitrate Retr >>> [ 5] 0.00-10.00 sec 12.0 MBytes 10.1 Mbits/sec 0 sender >>> [ 5] 0.00-10.00 sec 12.0 MBytes 10.1 Mbits/sec receiver >>> >>> iperf Done. >>> >>> Another session on B: >>> >>> root@:~ # netstat -w 1 -I vmx0 >>> input vmx0 output >>> packets errs idrops bytes packets errs bytes colls >>> 0 0 0 0 0 0 0 0 >>> 0 0 0 0 0 0 0 0 >>> 342 0 0 22600 526 0 775724 0 >>> 150 0 0 9900 851 0 1281454 0 >>> 109 0 0 7194 901 0 1357850 0 >>> 126 0 0 8316 828 0 1246632 0 >>> 122 0 0 8052 910 0 1370780 0 >>> 109 0 0 7194 819 0 1233702 0 >>> 120 0 0 7920 910 0 1370780 0 >>> 110 0 0 7260 819 0 1233702 0 >>> 123 0 0 8118 910 0 1370780 0 >>> 109 0 0 7194 819 0 1233702 0 >>> 73 0 0 5088 465 0 686342 0 >>> 0 0 0 0 0 0 0 0 >>> 0 0 0 0 0 0 0 0 >>> >>> >>> >>> ================================================================ >>> >>> >>> While A ---> B, i.e. A as client and B as server, the ACKs sent from B looks strange. >>> >>> Session on A: >>> >>> % iperf3 -c 192.168.120.134 -b 10m >>> Connecting to host 192.168.120.134, port 5201 >>> [ 5] local 192.168.120.1 port 52370 connected to 192.168.120.134 port 5201 >>> [ ID] Interval Transfer Bitrate >>> [ 5] 0.00-1.00 sec 1.25 MBytes 10.5 Mbits/sec >>> [ 5] 1.00-2.00 sec 1.25 MBytes 10.5 Mbits/sec >>> [ 5] 2.00-3.00 sec 1.12 MBytes 9.44 Mbits/sec >>> [ 5] 3.00-4.00 sec 1.25 MBytes 10.5 Mbits/sec >>> [ 5] 4.00-5.00 sec 1.12 MBytes 9.44 Mbits/sec >>> [ 5] 5.00-6.00 sec 1.25 MBytes 10.5 Mbits/sec >>> [ 5] 6.00-7.00 sec 1.12 MBytes 9.44 Mbits/sec >>> [ 5] 7.00-8.00 sec 1.25 MBytes 10.5 Mbits/sec >>> [ 5] 8.00-9.00 sec 1.12 MBytes 9.44 Mbits/sec >>> [ 5] 9.00-10.00 sec 1.25 MBytes 10.5 Mbits/sec >>> - - - - - - - - - - - - - - - - - - - - - - - - - >>> [ ID] Interval Transfer Bitrate >>> [ 5] 0.00-10.00 sec 12.0 MBytes 10.1 Mbits/sec sender >>> [ 5] 0.00-10.00 sec 12.0 MBytes 10.1 Mbits/sec receiver >>> >>> iperf Done. >>> >>> Session on B: >>> >>> root@:~ # netstat -w 1 -I vmx0 >>> input vmx0 output >>> packets errs idrops bytes packets errs bytes colls >>> 0 0 0 0 0 0 0 0 >>> 0 0 0 0 0 0 0 0 >>> 649 0 0 960562 330 0 21800 0 >>> 819 0 0 1233702 415 0 27390 0 >>> 910 0 0 1370780 459 0 30294 0 >>> 819 0 0 1233702 415 0 27390 0 >>> 910 0 0 1370780 459 0 30294 0 >>> 910 0 0 1370780 460 0 30360 0 >>> 819 0 0 1233702 414 0 27324 0 >>> 910 0 0 1370780 460 0 30360 0 >>> 819 0 0 1233702 414 0 27324 0 >>> 910 0 0 1370780 460 0 30360 0 >>> 285 0 0 412287 147 0 9981 0 >>> 0 0 0 0 0 0 0 0 >>> 0 0 0 0 0 0 0 0 >>> 0 0 0 0 0 0 0 0 >>> >>> >>> The ACK packets replied from B (the FreeBSD VM) are too aggressive. They are >>> about one half of TCP packets received from A. >>> >>> I've tested with different bitrates, from 10m to 300m, all behave the same. >>> Tested with baremetal FreeBSD 13.1 Box as B (with intel em driver), the >>> bitrates is 1g, also behaves the same. >>> >>> Also tried different FreeBSD versions, 11.4, 12.3, stable/13 and current/14 all >>> behave the same. >>> >>> >>> My question is, is that the expected behavior of current default TCP stack? >> That is what I would expect. TCP (on FreeBSD) is acking every other packet. This >> is also what is specified. MacOS, at least newer versions, send less ACKs. > Thanks for fast response! > > My have old memories about SACK which helps TCP performance. This behavior > seems odd from my mind. But those memories date back to 2008, that is 14 years ago. I don't think anything has changed since then from a specification point of view > > The current implementation of TCP stack in FreeBSD head is too complexed for me. > Can you please point me the RFCs specifying this? So I can start over with a quick glue. Send an ACK for every other frame if everything is OK, send it immediately if there are some gaps: https://datatracker.ietf.org/doc/html/rfc9293#section-3.8.6.3 This applies also to the case where you use SACK. Best regards Michael > > Thanks! >> >> Best regards >> Michael >>> >>> >>> >>> Best regards, >>> Zhenlei >