ndt-users list created

[Richard Carlson <>]

Hi Ken;

It certainly looks like there is a problem with the path between your 
server and client.  I'd recommend looking at every link to see if there is 
a duplex mismatch somewhere.

I've removed some lines to emphasis the interesting parts.

Rich
At 07:47 AM 11/9/2006, Ken Bellars wrote:

> running 10s outbound test (client-to-server [C2S]) . . . . . 37.73Mb/s
> running 10s inbound test (server-to-client [S2C]) . . . . . . 1.07Mb/s
> The slowest link in the end-to-end path is a 100 Mbps Full duplex Fast 
> Ethernet subnet

OK asymmeteric throughput on a FastE network.  This usually indicates some 
type of non-congestive loss condition.


> Web100 reports the Round trip time = 13.26 msec; the Packet size = 1460 
> Bytes; and
> There were 123 packets retransmitted, 288 duplicate acks received, and 337 
> SACK blocks received
> The connection stalled 22 times due to packet loss
> The connection was idle 4.84 seconds (40.33%) of the time

From below, there were 1218 pkts sent and at least 10% of them were 
retransmissions.  Timeouts caused the connection to sit idle for over %40 
of the test time.  This means that no traffic was flowing during these time 
periods.


> Excessive packet loss is impacting your performance, check the 
> auto-negotiate function on your local PC and network switch

The loss rate is high so I'm suggesting you look for a duplex mismatch 
condition.  This is kind of a backdoor for me because the regular duplex 
mismatch test didn't detect a fault.


> ================ MORE DETAILS =================
> WEB100 Kernel Variables:
>
> CurCwnd: 1460
>
> CurSsthresh: 2920

SSthresh is only 2 packets,  and CWND is only 1.  Typical of duplex 
mismatch conditions.

> DataBytesOut: 1802640
> DataPktsOut: 1218
> DupAcksIn: 288
> FastRetran: 60

retransmitted 60 pkts using the fast retransmit method

> MaxCwnd: 13140
> MaxMSS: 1460
> MaxRTO: 364
> MaxRTT: 216
> MaxRwinRcvd: 100000
> MaxRwinSent: 6144
> MaxSsthresh: 5840

SSThresh reached a max of 4 pkts.

> MinMSS: 1460
> MinRTO: 204
> MinRTT: 0
> MinRwinRcvd: 90596
> MinRwinSent: 5840
> NagleEnabled: 1
> OtherReductions: 0
> PktsIn: 773
> PktsOut: 1218
> PktsRetrans: 123
> RcvWinScale: 10
> SACKEnabled: 3
> SACKsRcvd: 337
> SendStall: 0
> SlowStart: 122
> SampleRTT: 4
> SmoothedRTT: 8
> SndWinScale: 1
> SndLimTimeRwin: 0
> SndLimTimeCwnd: 11004506
> SndLimTimeSender: 1664505
> SndLimTransRwin: 0
> SndLimTransCwnd: 1
> SndLimTransSender: 1
> SndLimBytesRwin: 0
> SndLimBytesCwnd: 1802640
> SndLimBytesSender: 0
> SubsequentTimeouts: 0
> SumRTT: 5080
> Timeouts: 22
> TimestampsEnabled: 0
> WinScaleRcvd: 1
> WinScaleSent: 10
> DupAcksOut: 0
> StartTimeUsec: 915639
> Duration: 12669246
> c2sData: 5
> c2sAck: 5
> s2cData: 6
> s2cAck: 4
> half_duplex: 0
> link: 100
> congestion: 1
> bad_cable: 0
> mismatch: 0
> spd: 1.14
> bw: 3.24
> loss: 0.067323481
> avgrtt: 13.26
> waitsec: 4.84
> timesec: 12.00
> order: 0.3726
> rwintime: 0.0000
> sendtime: 0.1314
> cwndtime: 0.8686
> rwin: 0.7629
> swin: 256.0000
> cwin: 0.1003
> rttsec: 0.013264
> Sndbuf: 33554432
> aspd: 0.00000
> CWND-Limited: 9467.70
>
> The theoretical network limit is 3.24 Mbps
> The NDT server has a 16384.0 KByte buffer which limits the throughput to 
> 19300.36 Mbps
> Your PC/Workstation has a 97.0 KByte buffer which limits the throughput to 
> 57.51 Mbps
> The network based flow control limits the throughput to 7.56 Mbps
>
> Client Data reports link is 'FastE', Client Acks report link is 'FastE'
> Server Data reports link is 'OC-12', Server Acks report link is 'T3'
>
>
> ===========================================
>
> Rich,
>
> I will appreciate your response.
>
> Regards
> Kenny
>
>
>
>
>
>
> On 10/20/06, Richard Carlson 
> <<mailto:>> wrote:
> Hi Kenny;
>
> I've trimmed the email and have some comments below.
>
> At 10:15 AM 10/17/2006, Ken Bellars wrote:
> >Rich,
> >
> >Thanks so much for walking me through building my own NDT. The first
> >suggestion actually fixed the problem.
> >
> >Now its running cool but I think there is still a problem (most likely the
> >last.).
> >
> >My C2S speed is far greater than the S2C. See below.
> >
> >------------------------------------------------------------------------- 
> --------
> >
> >click START to re-test
> >Connected to: 
> <<http://196.207.6.22>http://196.207.6.22><http://196.207.6.22>196.207.6.22 
> --  Using IPv4 address
> >Checking for Middleboxes . . . . . . . . . . . . . . . . . .  Done
> >checking for firewalls . . . . . . . . . . . . . . . . . . .  Done
> >
> >running 10s outbound test ( Client -to- Server [C2S] ) . . . . . 44.25Mb/s
> >running 10s inbound test ( Server -to- Client [S2C] ) . . . . . . 1.48Mb/s
>
> This is reporting that server is unable to fully utilize the
> network.  Fortunately, the NDT "Statists" and "More Details" pages should
> help explain why.  Look at these pages and send me a copy if you need help
> interpreting the results.
>
> >The slowest link in the end-to-end path is a 10 Gbps 10 Gigabit
> >Ethernet/OC-192 subnet
>
> The NDT server performs some raw packet timing calculations to determine
> the bottleneck link capacity.  I suspect that you are using a new PC with a
> 1 GE NIC and that NIC is doing interrupt coalescing, handling multiple
> receive packets on a single interrupt.  This means that the NDT is finding
> out how fast the NIC can transfer packets across the memory bus, not across
> the network.  Until I can fix this bug, turning interrupt coalescing off
> should correct the problem (at the expense of more CPU utilization).
>
> >Information: Other network traffic is congesting the link
>
> This is probably a misleading message.  My plan is to update the congestion
> detected signature in the next few months.
>
> >[ S2C ]: Excessive packet queuing detected
>
> This is saying that the server can send data to the NIC faster than the NIC
> can push it out into the network.  This is typical for modern servers and
> clients stuck behind slow links (DSL/Cable modem).  The word "Information"
> in blue indicated that it is a hot-link that you can click on to get more
> information.
>
> Let us know what you find.
>
> Rich
> >click START to re-test
> >
> >------------------------------------------------------------------------- 
> --------
> >
> >[snip snip snip]
>
> ------------------------------------
>
>
>
> Richard A. Carlson                              e-mail: 
> <mailto:>
> Network Engineer                                phone:  (734) 352-7043
> Internet2                                       fax:    (734) 913-4255
> 1000 Oakbrook Dr; Suite 300
> Ann Arbor,  MI  48104

------------------------------------



Richard A. Carlson                              e-mail: 

Network Engineer                                phone:  (734) 352-7043
Internet2                                       fax:    (734) 913-4255
1000 Oakbrook Dr; Suite 300
Ann Arbor,  MI  48104