ndt-users - Re: gigabit slower than fast-e
Subject: ndt-users list created
List archive
- From: Richard Carlson <>
- To: Jeremy Schafer <>, Bill Abbott <>
- Cc: Peter Van Epp <>,
- Subject: Re: gigabit slower than fast-e
- Date: Mon, 10 Mar 2008 06:41:22 -0400
Jeremy/Bill;
Just catching up from last weeks travel. Going to the URL below shows that the Rutgers NDT/NPAD server needs to be tuned to support larger TCP buffers. The following lines can be added to your /etc/sysctl.conf file to overcome this problem
# NEW parameter for 2.6.13 kernels. Set to Reno style CC
net.ipv4.tcp_congestion_control = reno
# TCP Tuning data added 7/28/05 RAC
# increase Linux TCP buffer limits
net.core.rmem_max = 33554432
net.core.wmem_max = 33554432
net.core.rmem_default = 65536
net.core.wmem_default = 65536
# increase Linux autotuning TCP buffer limits
net.ipv4.tcp_rmem = 4096 87380 16777216
net.ipv4.tcp_wmem = 4096 65535 16777216
Add the above lines and the run the "sudo /sbin/sysctl -p" command to set the new values.
Rich
At 04:25 PM 3/7/2008, Jeremy Schafer wrote:
Have you tried this URL?
http://ndt-nbp.rutgers.edu:8200/ServerData/pdb-a-linux-3.rutgers.edu:2008-03-07-20:09:59.html
Bill Abbott wrote:
I ran diag-client against this url from the server, here's the output:--
# ./diag-client ndt-nbp.rutgers.edu 8100 90 150
Using: rtt 90 ms and rate 150
Connected.
Control connection established.
port = 8003
Starting test.
peakwin=1688029 minpackets=3 maxpackets=1027 stepsize=256
Target run length is 2771751 packets (or a loss rate of 0.00003608%)
Requested DBP exceeds 1048576
Test 1a (5 seconds): Coarse Scan
Test 1b (5 seconds): ...
report url ServerData/pdb-a-linux-3.rutgers.edu:2008-03-07-20:09:59.html
I can't seem to get the page via browser, though, either the default page or the url above.
Jeremy Schafer
Network Architecture & Applications
AIM: ruoitjeremy
RUIM: jschafer
------------------------------------
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
- Re: gigabit slower than fast-e, (continued)
- Re: gigabit slower than fast-e, Jeremy Schafer, 03/07/2008
- Re: gigabit slower than fast-e, Richard Carlson, 03/07/2008
- Re: gigabit slower than fast-e, Matt Mathis, 03/07/2008
- Re: gigabit slower than fast-e, Peter Van Epp, 03/06/2008
- Re: gigabit slower than fast-e, Bill Abbott, 03/06/2008
- Re: gigabit slower than fast-e, Jeremy Schafer, 03/07/2008
- Re: gigabit slower than fast-e, Bill Abbott, 03/07/2008
- Re: gigabit slower than fast-e, Jeremy Schafer, 03/07/2008
- Re: gigabit slower than fast-e, Bill Abbott, 03/07/2008
- Re: gigabit slower than fast-e, Bill Abbott, 03/07/2008
- Re: gigabit slower than fast-e, Richard Carlson, 03/10/2008
- Re: gigabit slower than fast-e, Jeremy Schafer, 03/07/2008
- Re: gigabit slower than fast-e, Bill Abbott, 03/07/2008
- Re: gigabit slower than fast-e, Jeremy Schafer, 03/07/2008
- Re: gigabit slower than fast-e, Bill Abbott, 03/06/2008
- Re: gigabit slower than fast-e, Jeremy Schafer, 03/07/2008
Archive powered by MHonArc 2.6.16.