PDA

View Full Version : Phillip



Lobo
03-11-01, 08:01 PM
Phillip, just playing I changed my RWIN to 474500, here is pcpitstop:
Bandwidth Down 2857 Kbits/sec
Bandwidth Up 132 Kbits/sec
Average Ping 55 ms
Ping Loss 0%
TCP Receive Window 474500
External IP Address 24.
Internal IP Address 24.
Browser MSIE 5.5; Win 9x 4.90
IE current cache 1 MB
IE max cache 15 MB

Now next I will post yours, it slows RWIN of 474496, whats up :confused:

[ 03-11-2001: Message edited by: Lobo ]

Lobo
03-11-01, 08:03 PM
TCP options string = 020405b40103030301010402

MTU = 1500
MTU is fully optimized for broadband.

MSS = 1460
Maximum useful data in each packet = 1460, which is equal to MSS.

Default Receive Window (RWIN) = 474496
RWIN Scaling (RFC1323) = 3 bits
Unscaled Receive Window = 59312
For optimum performance, consider changing RWIN to a multiple of MSS.
Other values for RWIN that might work well with your current MTU/MSS:
513920 (MSS x 44 * scale factor of 8)
256960 (MSS x 44 * scale factor of 4)
128480 (MSS x 44 * scale factor of 2)
64240 (MSS x 44)

bandwidth * delay product:
Your RcvWindow limits you to: 18979.84 kbps (2372.48 KBytes/s) @ 200ms
Your RcvWindow limits you to: 7591.936 kbps (948.992 KBytes/s) @ 500ms

MTU Discovery (RFC1191) = ON

Time to live left = 54 hops
TTL value is ok.
Note: Since TTL is decreased by at least 1 with each hop, the value above is equal to your TTL minus the number of hops to forums.speedguide.net

Timestamps (RFC1323) = OFF

Selective Acknowledgements (RFC2018) = ON

IP type of service field (RFC1349)= 00000000
Precedence (priority) = 000 (routine)
Delay = 0 (normal delay)
Throughput = 0 (normal throughput)
Reliability = 0 (normal reliability)
Cost = 0 (normal cost)


7249 connections tested since 03-10-2001, 14:30 ET
Analyzer
:confused:

mpd
03-11-01, 08:48 PM
Lobo,

your data shows that the WIN value from the TCP header must be shifted left by a factor of three (the same as multiplying it by 8).

Now, if your RWIN is 474496, your original WIN value must have been 59312.

If the RWIN is 474500, then the WIN value must have been 59312.5. A rather strange value..

What I am trying to say is that the only valid RWIN values are the ones divisible by 2^shift_factor.

Mike.

dannjr
03-11-01, 09:33 PM
mpd
Not nessassssarly but here read this on Rwin.. Real good thread... http://forums.speedguide.net/cgi-bin/ultimatebb.cgi?ubb=get_topic&f=2&t=007975

Lobo
How much Latency do you have... whats your average ping and average Download...
What do you use with your connection
These are all factors ????
Two much Rwin can slow you down to...

Lobo
03-11-01, 09:45 PM
No looking at results from pcpitstop (WOOT) Speed is fine for 8:00 at night, pings are good, de rest is a secret :p :p :p :p

Philip
03-11-01, 10:53 PM
Dannjr, Mike is right.

There are only two values in TCP headers, an unscaled RWIN, and a scale factor... By definition you must have a whole unscaled number, multiplied by a scale factor that's a power of two.

Lobo, pcpitstop reads the RWIN value directly from the registry, while our Analyzer actually inspects your TCP packets, hence the difference.

[ 03-12-2001: Message edited by: Philip ]

rmrucker
03-11-01, 11:36 PM
I must applaud SpeedGuide, Philip and Mike on this. The TCP Analyzer is CORRECTLY reporting what the actual Receive Window is.

PC Pitstop is simply reporting back the exact number that YOU have entered into the registry as your "DefaultRcvWindow" -- these two are NOT necessarily the same thing.

SpeedGuide now has the ONLY tool that CORRECTLY reports RWIN over 65535. Their reported RWIN is the ONLY one you can trust.

Lobo
03-12-01, 10:01 AM
Ok, great work guys, thank you :)

dannjr
03-12-01, 11:58 PM
heheheheUHm never said right or wrong just gave another veiw on it :)
Oh yeah asked a question too...