cholla Posted January 22, 2005 CID Share Posted January 22, 2005 Hi all: I have seen others post part of this test.I find some conflicting results in it. first are the outbound & inbound tests download & upload.If they are then why do I get a RTT of 716 ms at this speed 121.24Kb/s.Why does it report this Cable modem/DSL/T1 link found when I have dialup.What does this mean:This connection is network limited 99.96% of the time.Can anyone explain the checking for mismatch results near the bottom or any of the checking for results.or are these results or just telling me what the test is " checking for" & not results of this specific test.The "checking for" sections are over my head.So if anyone can explain them in more simple terms I would appreciate it. Thanks Cholla PS CA3LE I tried the spell check on this it has a small problem it will not go on unless you make the first correction it finds it did not like RTT in this post otherwise I could use its help,sometimes. WEB100 Enabled Statistics: Checking for Middleboxes . . . . . . . . . . . . . . . . . . Done running 10s outbound test (client to server) . . . . . 121.24Kb/s running 10s inbound test (server to client) . . . . . . 112.99kb/s ------ Client System Details ------ OS data: Name = Windows 98, Architecture = x86, Version = 4.10 Java data: Vendor = Sun Microsystems Inc., Version = 1.4.2_06 ------ Web100 Detailed Analysis ------ Cable modem/DSL/T1 lin k found.Link set to Full Duplex mode Information: throughput is limited by other network traffic. Good network cable(s) found Normal duplex operation found. Web100 reports the Round trip time = 716.0 msec; the Packet size = 1460 Bytes; and No packet loss was observed. This connection is network limited 99.96% of the time. Contact your local network administrator to report a network problem Web100 reports TCP negotiated the optional Performance Settings to: RFC 2018 Selective Acknowledgment: ON RFC 896 Nagle Algorithm: ON RFC 3168 Explicit Congestion Notification: OFF RFC 1323 Time Stamping: OFF RFC 1323 Window Scaling: ON Packet size is preserved End-to-End Server IP addresses are preserved End-to-End Client IP addresses are preserved End-to-End WEB100 Kernel Variables: Client: localhost/127.0.0.1 AckPktsIn: 50 AckPktsOut: 0 BytesRetrans: 0 CongAvoid: 49 CongestionOverCount: 0 CongestionSignals: 0 CountRTT: 50 CurCwnd: 14600 CurMSS: 1460 CurRTO: 1430 CurRwinRcvd: 268640 CurRwinSent: 5840 CurSsthresh: 2920 DSACKDups: 0 DataBytesIn: 0 DataBytesOut: 157680 DataPktsIn: 0 DataPktsOut: 108 DupAcksIn: 0 ECNEnabled: 0 FastRetran: 0 MaxCwnd: 14600 MaxMSS: 1460 MaxRTO: 1520 MaxRTT: 960 MaxRwinRcvd: 268640 MaxRwinSent: 5840 MaxSsthresh: 2920 MinMSS: 1460 MinRTO: 910 MinRTT: 500 MinRwinRcvd: 33580 MinRwinSent: 5840 NagleEnabled: 1 OtherReductions: 0 PktsIn: 50 PktsOut: 108 PktsRetrans: 0 X_Rcvbuf: 103424 SACKEnabled: 3 SACKsRcvd: 0 SendStall: 0 SlowStart: 1 SampleRTT: 950 SmoothedRTT: 910 X_Sndbuf: 103424 SndLimTimeRwin: 0 SndLimTimeCwnd: 10796501 SndLimTimeSender: 3535 SndLimTransRwin: 0 SndLimTransCwnd: 1 SndLimTransSender: 1 SndLimBytesRwin: 0 SndLimBytesCwnd: 157680 SndLimBytesSender: 0 SubsequentTimeouts: 0 SumRTT: 35800 Timeouts: 0 TimestampsEnabled: 0 WinScaleRcvd: 3 WinScaleSent: 7 DupAcksOut: 0 StartTimeUsec: 956012 Duration: 10818741 c2sData: 2 c2sAck: 2 s2cData: 9 s2cAck: 2 Checking for mismatch condition (cwndtime > .3) [0.99>.3], (MaxSsthresh > 0) [2920>0], (PktsRetrans/sec > 2) [0>2], (estimate > 2) [15.55>2] Checking for mismatch on uplink (speed > 50 [0.11>50], (xmitspeed < 5) [0.12<5] (rwintime > .9) [0>.9], (loss < .01) [1.0E<.01] Checking for excessive errors condition (loss/sec > .15) [1.0E>.15], (cwndtime > .6) [0.99>.6], (loss < .01) [1.0E<.01], (MaxSsthresh > 0) [2920>0] Checking for 10 Mbps link (speed < 9.5) [0.11<9.5], (speed > 3.0) [0.11>3.0] (xmitspeed < 9.5) [0.12<9.5] (loss < .01) [1.0E<.01], (link > 0) [100>0] Checking for Wireless link (sendtime = 0) [3.27=0], (speed < 5) [0.11<5] (Estimate > 50 [15.55>50], (Rwintime > 90) [0>.90] (RwinTrans/CwndTrans = 1) [0/1=1], (link > 0) [100>0] Checking for DSL/Cable Modem link (speed < 2) [0.11<2], (SndLimTransSender = 0) [1=0] (SendTime = 0) [3.273137237690689E-4=0], (link > 0) [100>0] Checking for half-duplex condition (rwintime > .95) [0>.95], (RwinTrans/sec > 30) [0>30], (SenderTrans/sec > 30) [0.10>30], OR (link <= 10) [100<=10] Checking for congestion (cwndtime > .02) [0.99>.02], (mismatch = 0) [0=0] (MaxSsthresh > 0) [2920>0] bw = 15.55 based on packet size = 11Kbits, RTT = 716.0msec, and loss = 1.0E-6 The theoretical network limit is 15.55 Mbps The transmit buffer (101.0 KByte) limits the application to 1.10 Mbps Your receive buffer (262.0 KByte) limits the application to 2.86 Mbps The network based flow control limits the application to 0.15 Mbps Client Data reports link is 'T1', Client Acks report link is 'T1' Server Data reports link is '10 Gig', Server Acks report link is 'T1' Quote Link to comment Share on other sites More sharing options...
xs1 Posted January 22, 2005 CID Share Posted January 22, 2005 The smallest scores are called "cable/dsl" . Theirs nothing smaller it can be called in the scripting. If you were faster, it would bump you up to a " ethernet 10mb + " stature. Faster then that its 100mb , etc. SO even if you are on dialup the only thing it can call you is "cable/dsl" since its made to mesure broadband connections. Network limited 99 % means that your ISP has you cap controlled, and not fully burstable 10/10 or 100/100 like vanburen (that is IF you actualy were on broadband). "Information: throughput is limited by other network traffic." Quote Link to comment Share on other sites More sharing options...
cholla Posted January 22, 2005 Author CID Share Posted January 22, 2005 .s1: You awnsered about the dsl/cable part now I know why it reports & about the cap thats what I thought it might mean my isp didn't admit that when I asked their tech.About the"Information: throughput is limited by other network traffic." I did know that just not what "This connection is network limited 99.96% of the time" meant for sure until you explained it.I thought the RTT seemed high if the outbound & inbound actually are download & upload tests & the speed reported by them is correct. I am still not sure about this it would seem to indicate high latency.My isp blocks ping & tracert so I can't test this way . Cholla Quote Link to comment Share on other sites More sharing options...
VanBuren Posted January 22, 2005 CID Share Posted January 22, 2005 the test probl measured RTT when you was uploading/downloading, thats why its so high this The theoretical network limit is 15.55 Mbps The transmit buffer (101.0 KByte) limits the application to 1.10 Mbps Your receive buffer (262.0 KByte) limits the application to 2.86 Mbps The network based flow control limits the application to 0.15 Mbps is based on the formula below ((Maximum Bandwidth x Maximum Latency) / 8 ) / MSS = multiplyer ( round up to the nearest even whole number) multiplyer x MSS = optimal RWIN so a connection with a 1500 download cap with a maximum latency of 300 ms and a MSS of 1460 (1500 x 300) / 8 = 56250 / 1460 = Multiplyer = 39 39 x 1460 = 56940 as Optimal RWIN if you reverse that and know RWIN and latency and MSS you can calculate Bandwidth and thats what its doing VanBuren Quote Link to comment Share on other sites More sharing options...
cholla Posted January 22, 2005 Author CID Share Posted January 22, 2005 Hi VanBuran: thanks for the formula I copied it & put it in my documents file.Unless I am missing something the test did not give me theMaximum latency or the download cap.I have to have one of these to reverse work the formula.I also would like to know if this actually is an upload & download test .If it is is it so short it doesn't really tell you much.I guess "10s inbound test (server to client)" would be 10 seconds long & would be the download test. They just phrase it oddly.What do you think? or one of the other members I would like your imput too. Thanks Cholla Quote Link to comment Share on other sites More sharing options...
VanBuren Posted January 23, 2005 CID Share Posted January 23, 2005 Unless I am missing something the test did not give me theMaximum latency Web100 reports the Round trip time = 716.0 msec or the download cap.I have to have one of these to reverse work the formulaand you need a buffersize MaxRwinRcvd: 268640, MinRwinRcvd: 33580 now you have the values you need to calculate this... Your receive buffer (262.0 KByte) limits the application to 2.86 Mbps As you can see they say you have a receivebuffer of 262 KByte, that i dont think is fully accurate, cos the test reporting MaxRwinRcvd: 268640. anyway lets put these things in the formula multiplyer x MSS = optimal RWIN multiplyer = (optimal RWIN / MSS) multiplyer = 262000 / 1460 = 179 ((Maximum Bandwidth x Maximum Latency) / 8 ) / MSS = multiplyer ((Maximum Bandwidth x Maximum Latency) / 8 ) = multiplyer x MSS ((Maximum Bandwidth x 716) / 8 ) = 179 x 1460 Maximum Bandwidth x 89,5 = 261340 Maximum Bandwidth = 261340 / 89,5 = 2920 Kbps pretty close compared to them Your receive buffer (262.0 KByte) limits the application to 2.86 Mbps They probl just rounded the multiplyer diffrent from me...... VanBuren Quote Link to comment Share on other sites More sharing options...
cholla Posted January 23, 2005 Author CID Share Posted January 23, 2005 Thank you VanBuran: I guess I just needed the extra detail I did not think of RTT as the total latency for some reason.The figure you came up with 2920kbps matches this reading in the test I think would be this the number matches they just didn't put the kbps after it.the reading is MaxSsthresh & CurSsthresh both have 2920 as their reading.Do you think this is their term for maximum bandwidth or the reading is just the same number? Anyway I think I learned something thanks VanBuran. Cholla Quote Link to comment Share on other sites More sharing options...
VanBuren Posted January 23, 2005 CID Share Posted January 23, 2005 no problem Cholla i have no idea what MaxSsthresh & CurSsthresh stands for VanBuren Quote Link to comment Share on other sites More sharing options...
MICROWAVE Posted January 24, 2005 CID Share Posted January 24, 2005 no problem Cholla i have no idea what MaxSsthresh & CurSsthresh stands for Quote Link to comment Share on other sites More sharing options...
VanBuren Posted January 24, 2005 CID Share Posted January 24, 2005 Maximum Slowstart Threshold Category, is its meaning if that helps... and the other is Current......... Microwave dern thats above my knowledge that must be a bad thing, i want a fast start VanBuren Quote Link to comment Share on other sites More sharing options...
MICROWAVE Posted January 24, 2005 CID Share Posted January 24, 2005 dern thats above my knowledge Quote Link to comment Share on other sites More sharing options...
VanBuren Posted January 24, 2005 CID Share Posted January 24, 2005 Quote Link to comment Share on other sites More sharing options...
xs1 Posted January 24, 2005 CID Share Posted January 24, 2005 Maximum Slowstart Threshold Category, is its meaning if that helps... and the other is Current......... Microwave Looks like someones trying to get in the super geek catigory with us now O_O Quote Link to comment Share on other sites More sharing options...
cholla Posted January 24, 2005 Author CID Share Posted January 24, 2005 Hi Microwave: Thanks I just asked because they matched what VanBuran came up with for the maximum bandwidth.At least they were both 2920.A lot of the readings of the test above are beyond my knowlege. Cholla Quote Link to comment Share on other sites More sharing options...
MICROWAVE Posted January 24, 2005 CID Share Posted January 24, 2005 Looks like someones trying to get in the super geek catigory with us now O_O Trying? ya mean I haven been accepted to the super geek club yet?? Microwave Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.