Re: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread Dan Nelson
In the last episode (Jul 09), Max Clark said: Hi all, I am doing research on dynamic tcp tunning, what ever happened with the patch below? http://groups.google.com/groups?hl=enlr=ie=UTF-8oe=UTF-8safe=offselm=200107150943.f6F9hhx06763%40earth.backplane.comrnum=1 It got commited to 4.x and

RE: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread Max Clark
Fantastic, this is exactly what I was looking for. When you say it's got a specific purpose, I am looking for something that will dynamically tune a 6Mbit/s, 220ms network link for bulk (500MB) file transfers. Is this what I think it is, or should I be looking at something else? Thanks in

Re: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread Dan Nelson
In the last episode (Jul 09), Max Clark said: When you say it's got a specific purpose, I am looking for something that will dynamically tune a 6Mbit/s, 220ms network link for bulk (500MB) file transfers. Is this what I think it is, or should I be looking at something else? Unless you're

RE: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread Max Clark
600/8*.220 = 165Kbytes or 1.32Mbit/s I understand the BDP concept and the calculation to then generate the tcp window sizes. What I don't understand is this... How in the world is a windows 2000 box running commercial software able to push this link to 625KByte/s (5Mbit/s) How can I

Re: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread Dan Nelson
In the last episode (Jul 09), Max Clark said: 600/8*.220 = 165Kbytes or 1.32Mbit/s I understand the BDP concept and the calculation to then generate the tcp window sizes. What I don't understand is this... How in the world is a windows 2000 box running commercial software able to

RE: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread Max Clark
Assuming zero (0) network latency what should I configure on my FreeBSD boxes to saturate a 6Mbit/s (750Kbyte/s) link? Thanks, Max -Original Message- From: Dan Nelson [mailto:[EMAIL PROTECTED] Sent: Wednesday, July 09, 2003 12:41 PM To: Max Clark Cc: [EMAIL PROTECTED] Subject: Re: What

Re: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread Dan Nelson
In the last episode (Jul 09), Max Clark said: Assuming zero (0) network latency what should I configure on my FreeBSD boxes to saturate a 6Mbit/s (750Kbyte/s) link? Assuming zero latency, absolutely nothing :) You can easily saturate a 100mbit LAN connection (which has like a 12K bw*d product)

RE: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread Max Clark
:) hehe... Okay, let's say how do I force my machine to think it doesn't have any latency and saturate a 6Mbit/s link even though the link has 220ms latency? -Original Message- From: Dan Nelson [mailto:[EMAIL PROTECTED] Sent: Wednesday, July 09, 2003 1:21 PM To: Max Clark Cc: [EMAIL

Re: What ever happened with this? eXperimental bandwidth delayproduct code

2003-07-09 Thread John-Mark Gurney
Max Clark wrote this message on Wed, Jul 09, 2003 at 13:27 -0700: :) hehe... Okay, let's say how do I force my machine to think it doesn't have any latency and saturate a 6Mbit/s link even though the link has 220ms latency? You might want to try: net.inet.tcp.sendspace=$((128*1024))