From owner-freebsd-net@FreeBSD.ORG Mon Aug 11 17:15:19 2014 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 7B4A3E3F for ; Mon, 11 Aug 2014 17:15:19 +0000 (UTC) Received: from h2.funkthat.com (gate2.funkthat.com [208.87.223.18]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "funkthat.com", Issuer "funkthat.com" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 290E82660 for ; Mon, 11 Aug 2014 17:15:18 +0000 (UTC) Received: from h2.funkthat.com (localhost [127.0.0.1]) by h2.funkthat.com (8.14.3/8.14.3) with ESMTP id s7BHFHeM034726 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 11 Aug 2014 10:15:18 -0700 (PDT) (envelope-from jmg@h2.funkthat.com) Received: (from jmg@localhost) by h2.funkthat.com (8.14.3/8.14.3/Submit) id s7BHFH6B034725; Mon, 11 Aug 2014 10:15:17 -0700 (PDT) (envelope-from jmg) Date: Mon, 11 Aug 2014 10:15:17 -0700 From: John-Mark Gurney To: Niu Zhixiong Subject: Re: A problem on TCP in High RTT Environment. Message-ID: <20140811171517.GW83475@funkthat.com> Mail-Followup-To: Niu Zhixiong , Michael Tuexen , "freebsd-net@freebsd.org" , Bill Yuan References: <3F6BC212-4223-4AAC-8668-A27075DC55C2@lurchi.franken.de> <20140810022350.GI83475@funkthat.com> <20140810033212.GL83475@funkthat.com> <20140810045355.GM83475@funkthat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.3i X-Operating-System: FreeBSD 7.2-RELEASE i386 X-PGP-Fingerprint: 54BA 873B 6515 3F10 9E88 9322 9CB1 8F74 6D3F A396 X-Files: The truth is out there X-URL: http://resnet.uoregon.edu/~gurney_j/ X-Resume: http://resnet.uoregon.edu/~gurney_j/resume.html X-TipJar: bitcoin:13Qmb6AeTgQecazTWph4XasEsP7nGRbAPE X-to-the-FBI-CIA-and-NSA: HI! HOW YA DOIN? can i haz chizburger? X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.2 (h2.funkthat.com [127.0.0.1]); Mon, 11 Aug 2014 10:15:18 -0700 (PDT) Cc: Michael Tuexen , Bill Yuan , "freebsd-net@freebsd.org" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 11 Aug 2014 17:15:19 -0000 Niu Zhixiong wrote this message on Sun, Aug 10, 2014 at 20:27 +0800: > Hi, I am not sure whether my last email is filtered by mailing list. > After disabled tso??? the speed become even poorer??? > This is the packets captures. Plz see google drive. > tcp_with_tso_off.pcapng.gz > So, the reason that this is also slow is that it only ever really has one segment on the wire at a time... This is similar to the previous packet capture... Which side was thie captured on? Was this the receiving side? Because it looks like packets are getting merged still... 22:19:25.628087 IP 10.0.10.2.62995 > 10.0.10.3.9000: Flags [.], seq 149171:152067, ack 1, win 32783, options [nop,nop,TS val 61731427 ecr 2405797018], length 2896 and as before: 22:19:25.634095 IP 10.0.10.2.62995 > 10.0.10.3.9000: Flags [.], seq 165099:166547, ack 1, win 32783, options [nop,nop,TS val 61731431 ecr 2405797022], length 1448 22:19:25.635084 IP 10.0.10.3.9000 > 10.0.10.2.62995: Flags [.], ack 167995, win 32745, options [nop,nop,TS val 2405797438 ecr 61731431], length 0 22:19:25.635097 IP 10.0.10.2.62995 > 10.0.10.3.9000: Flags [.], seq 166547:167995, ack 1, win 32783, options [nop,nop,TS val 61731431 ecr 2405797022], length 1448 22:19:25.636073 IP 10.0.10.2.62995 > 10.0.10.3.9000: Flags [.], seq 167995:170891, ack 1, win 32783, options [nop,nop,TS val 61731431 ecr 2405797022], length 2896 22:19:25.636266 IP 10.0.10.3.9000 > 10.0.10.2.62995: Flags [.], ack 170891, win 32745, options [nop,nop,TS val 2405797439 ecr 61731431], length 0 Though the other thing I noticed is that we appear to be ack'ing before the segment was received, which is a bit odd... And it happens quite consistantly... We really need someone who knows our TCP stack to comment on this... > On Sun, Aug 10, 2014 at 1:24 PM, Niu Zhixiong wrote: > > > Hi??? > > After disabled tso??? the speed become even poorer??? > > This is the packets captures. Plz see google drive. > > ??? > > tcp_with_tso_off.pcapng.gz > > > > ??? > > > > > > John-Mark Gurney ???2014???8???10????????????????????? > > > > Niu Zhixiong wrote this message on Sun, Aug 10, 2014 at 11:48 +0800: > >> > I am using Intel I350-T4 NIC. The LRO is closed by default. And by the > >> way, > >> > when I am using KVM-based virtual machine(virtio NIC) do the exactly > >> same > >> > test. The results are same. > >> > >> Have you tried disabling tso? I asked that in an earlier email, but > >> never heard from you if that changed anything... > >> > >> a lot of the trace looks like: > >> 19:29:57.223574 IP 10.0.10.2.61010 > 10.0.10.3.9000: . > >> 251521:257313(5792) ack 1 win 32783 > >> 19:29:57.223798 IP 10.0.10.3.9000 > 10.0.10.2.61010: . ack 257313 win > >> 32745 > >> 19:29:57.225570 IP 10.0.10.2.61010 > 10.0.10.3.9000: . > >> 257313:263105(5792) ack 1 win 32783 > >> > >> Notice how the ack comes back immediately, but for some reason, we decide > >> to > >> wait almost 2ms before sending out the next frame... > >> > >> For some reason, we just aren't filling our window out... tcptcace's > >> graphs shows the winow at 2MB, but we only ever have 4 segments > >> outstanding at once... > >> > >> > ifconfig igb0 > >> > igb0: flags=8843 metric 0 mtu > >> 1500 > >> > > >> options=403bb > >> > ether a0:36:9f:38:27:d0 > >> > inet 10.0.10.3 netmask 0xffffff00 broadcast 10.0.10.255 > >> > inet6 fe80::a236:9fff:fe38:27d0%igb0 prefixlen 64 scopeid 0x1 > >> > nd6 options=29 > >> > media: Ethernet autoselect (1000baseT ) > >> > status: active > >> > > >> > Regards, > >> > Niu Zhixiong > >> > ????????????????????????????????????????????? > >> > kaiaixi@gmail.com > >> > > >> > > >> > On Sun, Aug 10, 2014 at 11:32 AM, John-Mark Gurney > >> wrote: > >> > > >> > > Niu Zhixiong wrote this message on Sun, Aug 10, 2014 at 10:50 +0800: > >> > > > I am sorry that I upload a WRONG SCTP capture. But, the throughput > >> is > >> > > same. > >> > > > SCTP is double than TCP, about 18Mbps. > >> > > > ??? > >> > > > sctp_2.pcapng.gz > >> > > > < > >> > > > >> https://docs.google.com/file/d/0By8sTL79ob4tMlh4WDlTSndHX0k/edit?usp=drive_web > >> > > > > >> > > > ??? > >> > > > >> > > Ok, the owin graph is very interesting... We do have a full 2MB > >> window > >> > > on the receiver side, but for some reason, we only ever have just > >> under > >> > > 6k outstanding on the connection... > >> > > > >> > > So, it looks like we send for a short period of time, and then stop > >> > > sending... Do you have LRO enabled? I think it might be related to: > >> > > https://svnweb.freebsd.org/changeset/base/r256920 > >> > > > >> > > As I'm seeing >100ms gaps where the sender doesn't send any data, and > >> > > as soon as more than one ack comes in, the next segment goes out... > >> If > >> > > we only receive a single ack, then we wait for a timeout before > >> sending > >> > > the next segment.. > >> > > > >> > > Can you try to disable LRO on the receiving host? > >> > > > >> > > ifconfig -lro > >> > > > >> > > And see if that helps... If it does... Applying the patch, or > >> compiling > >> > > a more recent kernel from stable/10 that is after r257367 as that is > >> was > >> > > the date that the change was merged... > >> > > > >> > > > On Sun, Aug 10, 2014 at 10:42 AM, Niu Zhixiong > >> > > wrote: > >> > > > > >> > > > > I am sure that wnd is about 2MB all the time. > >> > > > > This is my latest capture, plz see Google Drive. > >> > > > > In the latest test, TCP(0s-120s) is about 9Mbps and SCTP(0s-120s) > >> is > >> > > about > >> > > > > 18Mbps. > >> > > > > (The bandwidth(20Mbps) and delay(200ms) is set by dummynet) > >> > > > > The SCTP and TCP are tested in same environment. > >> > > > > > >> > > > > ??? > >> > > > > sctp.pcapng.gz > >> > > > > < > >> > > > >> https://docs.google.com/file/d/0By8sTL79ob4tYl9sM2V5a19iNVU/edit?usp=drive_web > >> > > > > >> > > > > ?????? > >> > > > > tcp.pcapng.gz > >> > > > > < > >> > > > >> https://docs.google.com/file/d/0By8sTL79ob4tV0NMR1FYLUQ3MWs/edit?usp=drive_web > >> > > > > >> > > > > ??? > >> > > > > > >> > > > > > >> > > > > > >> > > > > Regards, > >> > > > > Niu Zhixiong > >> > > > > ????????????????????????????????????????????? > >> > > > > kaiaixi@gmail.com > >> > > > > > >> > > > > > >> > > > > On Sun, Aug 10, 2014 at 10:23 AM, John-Mark Gurney < > >> jmg@funkthat.com> > >> > > > > wrote: > >> > > > > > >> > > > >> Niu Zhixiong wrote this message on Sun, Aug 10, 2014 at 10:12 > >> +0800: > >> > > > >> > During the TCP4 transmission. > >> > > > >> > Proto Recv-Q Send-Q Local Address Foreign Address > >> > > > >> (state) > >> > > > >> > tcp4 0 2097346 10.0.10.2.13504 10.0.10.3.9000 > >> > > > >> > ESTABLISHED > >> > > > >> > >> > > > >> Ok, so you are getting a full 2MB in there, and w/ that, you > >> should > >> > > > >> easily be saturating your pipe... > >> > > > >> > >> > > > >> The next thing would be to get a tcpdump, and take a look at the > >> > > > >> window size.. Wireshark has lots of neat tools to make this > >> analysis > >> > > > >> easy... Another tool that is good is tcptrace.. It can output a > >> > > > >> variety of different graphs that will help you track down, and > >> see > >> > > > >> what part of the system is the problem... > >> > > > >> > >> > > > >> You probably only need a few tens of seconds of the tcpdump... > >> > > > >> > >> > > > >> > On Sun, Aug 10, 2014 at 4:58 AM, Michael Tuexen < > >> > > > >> > Michael.Tuexen@lurchi.franken.de> wrote: > >> > > > >> > > >> > > > >> > > > >> > > > >> > > On 09 Aug 2014, at 22:45, John-Mark Gurney >> > > >> > > wrote: > >> > > > >> > > > >> > > > >> > > > Michael Tuexen wrote this message on Sat, Aug 09, 2014 at > >> 21:51 > >> > > > >> +0200: > >> > > > >> > > >> > >> > > > >> > > >> On 09 Aug 2014, at 20:42, John-Mark Gurney < > >> jmg@funkthat.com> > >> > > > >> wrote: > >> > > > >> > > >> > >> > > > >> > > >>> Niu Zhixiong wrote this message on Fri, Aug 08, 2014 at > >> 20:34 > >> > > > >> +0800: > >> > > > >> > > >>>> Dear all, > >> > > > >> > > >>>> > >> > > > >> > > >>>> Last month, I send problems related to FTP/TCP in a > >> high RTT > >> > > > >> > > environment. > >> > > > >> > > >>>> After that, I setup a simulation environment(Dummynet) > >> to > >> > > test > >> > > > >> TCP > >> > > > >> > > and SCTP > >> > > > >> > > >>>> in high delay environment. After finishing the test, I > >> can > >> > > see > >> > > > >> TCP is > >> > > > >> > > >>>> always slower than SCTP. But, I think it is not > >> possible. > >> > > (Plz > >> > > > >> see the > >> > > > >> > > >>>> figure in the attachment). When the delay is 200ms(means > >> > > > >> RTT=400ms). > >> > > > >> > > >>>> Besides, the TCP is extremely slow. > >> > > > >> > > >>>> > >> > > > >> > > >>>> ALL BW=20Mbps, DELAY= 0 ~ 200MS, Packet LOSS = 0 (by > >> > > dummynet) > >> > > > >> > > >>>> > >> > > > >> > > >>>> This is my parameters: > >> > > > >> > > >>>> FreeBSD vfreetest0 10.0-RELEASE FreeBSD 10.0-RELEASE > >> #0: Thu > >> > > Aug > >> > > > >> 7 > >> > > > >> > > >>>> 11:04:15 HKT 2014 > >> > > > >> > > >>>> > >> > > > >> > > >>>> sysctl net.inet.tcp > >> > > > >> > > >>> > >> > > > >> > > >>> [...] > >> > > > >> > > >>> > >> > > > >> > > >>>> net.inet.tcp.recvbuf_auto: 0 > >> > > > >> > > >>> > >> > > > >> > > >>> [...] > >> > > > >> > > >>> > >> > > > >> > > >>>> net.inet.tcp.sendbuf_auto: 0 > >> > > > >> > > >>> > >> > > > >> > > >>> Try enabling this... This should allow the buffer to > >> grow > >> > > large > >> > > > >> enough > >> > > > >> > > >>> to deal w/ the higher latency... > >> > > > >> > > >>> > >> > > > >> > > >>> Also, make sure your program isn't setting the recv > >> buffer > >> > > size > >> > > > >> as that > >> > > > >> > > >>> will disable the auto growing... > >> > > > >> > > >> I think the program sets the buffer to 2MB, which it also > >> does > >> > > for > >> > > > >> SCTP. > >> > > > >> > > >> So having both statically at the same size makes sense > >> for the > >> > > > >> > > comparison. > >> > > > >> > > >> I remember that there was a bug in the combination of LRO > >> and > >> > > > >> delayed > >> > > > >> > > ACK, > >> > > > >> > > >> which was fixed, but I don't remember it was fixed before > >> > > 10.0... > >> > > > >> > > > > >> > > > >> > > > Sounds like disabling LRO and TSO would be a useful test > >> to see > >> > > if > >> > > > >> that > >> > > > >> > > > improves things... But hiren said that the fix made it, > >> so... > >> > > > >> > > > > >> > > > >> > > >>> If you use netstat -a, you should be able to see the > >> send-q > >> > > on the > >> > > > >> > > >>> sender grow as necessary... > >> > > > >> > > > > >> > > > >> > > > Also, getting the send-q output while it's running would > >> let us > >> > > know > >> > > > >> > > > if the buffer is getting to 2MB or not... > >> > > > >> > > That is correct. Niu: Can you provide this? -- John-Mark Gurney Voice: +1 415 225 5579 "All that I will do, has been done, All that I have, has not."