Ask Your Question
0

bdp bandwidth delay product how does server know its bandwidth?

asked 2018-07-16 16:18:51 +0000

anonymous user

Anonymous

All,

After lots of packet captures I have found the my slow throughput issue is due to a small window size. The scale is only at 4.

I know that the Window size scaling factor comes form the host using BDP (bandwidth X latency)

How does the host know its bandwidth? Does it use it nic card settings?

edit retag flag offensive close merge delete

Comments

What makes you conclude that small window sizes are the problem?

When you say:

The scale is only at 4.

do you mean the Window Scaling shift factor, or the resulting multiplier?

A multiplier of 4 (which results from a shift factor of 2), allows the host to advertise a window size of up to 262,140 bytes. A shift factor of 4 results in a multiplier of 16 and allows the host to advertise a window size of up to 1,048,560 bytes.

The Window Scaling factor limits the maximum window size that a host can advertise, but does not determine the actual window size that it uses. It's useful to know the scaling factor, but only in order to calculate what window sizes the host is actually advertising. In order to correctly calculate the actual window sizes, the capture has to include the TCP three-way handshake ...(more)

Jim Aragon gravatar imageJim Aragon ( 2018-07-17 02:46:18 +0000 )edit

Yes he knows his own bandwitdth by reading the NIC card setting. This setting is either negotiated or manually set. And the host does not know anythging about some bottlenecks on the path.

Christian_R gravatar imageChristian_R ( 2018-07-17 08:59:35 +0000 )edit

1 Answer

Sort by ยป oldest newest most voted
0

answered 2018-07-17 07:30:26 +0000

updated 2018-07-17 07:40:32 +0000

Hi, refer to this quite detailed article

So assuming you have Windows OS it controls RWIN size based on 2 factors: interface speed and selected Receive Window autotuning level:

"...So, as summary, the different states for AutoTuningLevel are as follows:

Normal (Default): 0x8 (Scale Factor of 8)

Restricted: 0x4 (Scale Factor of 4)

Highly Restricted: 0x2 (Scale Factor of 2)

Disable: No scale factor available

Experimental: 0xE (Scale Factor of 14)..."

Later, after connection is established, Windows OS uses current receive rate to update RWIN size accourdingly (unlike Scaling factor which is set in SYN packets, we can change RWIN size all the time connection is active).

I've just checked my Win 10 with 'Normal' autotuning level and indeed it shooses Scale Factor of 8 in every TCP connection.

Also as Jim said before it'd be nice to see PCAP and check if it is exactly the reason of low throughput.

edit flag offensive delete link more

Comments

This seems to be a spin-off of throughput issue dropped packet slow start discussing an iperf performance test over a 70+ms latency path. Links to the captures are available there ...

mrEEde gravatar imagemrEEde ( 2018-07-18 05:08:23 +0000 )edit

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

1 follower

Stats

Asked: 2018-07-16 16:18:51 +0000

Seen: 539 times

Last updated: Jul 17 '18