<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: How to Calculate TCP throughput for long distance WAN links</title>
	<atom:link href="http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/feed/" rel="self" type="application/rss+xml" />
	<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/</link>
	<description>Studies in Data Center Networking, Virtualization, Computing</description>
	<lastBuildDate>Mon, 06 Feb 2012 01:52:15 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.2.1</generator>
	<item>
		<title>By: Guru</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-8623</link>
		<dc:creator>Guru</dc:creator>
		<pubDate>Fri, 03 Feb 2012 13:39:55 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-8623</guid>
		<description>Nice post.. referred it in my post

http://www.consultguru.me/post/2012/02/02/SQL-Server-Replication-Project-–-2-(Network).aspx

Guru</description>
		<content:encoded><![CDATA[<p>Nice post.. referred it in my post</p>
<p><a href="http://www.consultguru.me/post/2012/02/02/SQL-Server-Replication-Project-–-2-(Network).aspx" rel="nofollow">http://www.consultguru.me/post/2012/02/02/SQL-Server-Replication-Project-–-2-(Network).aspx</a></p>
<p>Guru</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Georgie</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-8374</link>
		<dc:creator>Georgie</dc:creator>
		<pubDate>Wed, 30 Nov 2011 13:45:39 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-8374</guid>
		<description>&quot; unless your TCP/IP stack on the server employs a TCP enhancement called “selective acknowledgements”, which most do not&quot;

In my experience any recent Linux 2.4/2.6 kernel and any modern Window$ system  have SACK enabled by default in the kernel.</description>
		<content:encoded><![CDATA[<p>&#8221; unless your TCP/IP stack on the server employs a TCP enhancement called “selective acknowledgements”, which most do not&#8221;</p>
<p>In my experience any recent Linux 2.4/2.6 kernel and any modern Window$ system  have SACK enabled by default in the kernel.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: uday</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-8153</link>
		<dc:creator>uday</dc:creator>
		<pubDate>Wed, 21 Sep 2011 17:38:53 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-8153</guid>
		<description>how to find the throughput,end to end delay,delivery ratio for the protocols using mcbr application as it is a single host application..
what all properties has to be set for that in nodes,sunet and mcbr and file statistics...
of scenario in qualnet 5.0 environment..</description>
		<content:encoded><![CDATA[<p>how to find the throughput,end to end delay,delivery ratio for the protocols using mcbr application as it is a single host application..<br />
what all properties has to be set for that in nodes,sunet and mcbr and file statistics&#8230;<br />
of scenario in qualnet 5.0 environment..</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: NBN fibre in small towns</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-8055</link>
		<dc:creator>NBN fibre in small towns</dc:creator>
		<pubDate>Sat, 20 Aug 2011 02:19:48 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-8055</guid>
		<description>[...] thus the further increase of latency.    Alright then Comrade, I&#039;ll humour you for a moment. Using this article as a base I will be doing some calculations.  Next I will use Tranquillity as my server, which is [...]</description>
		<content:encoded><![CDATA[<p>[...] thus the further increase of latency.    Alright then Comrade, I&#8217;ll humour you for a moment. Using this article as a base I will be doing some calculations.  Next I will use Tranquillity as my server, which is [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: John Tkaczewski</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-7837</link>
		<dc:creator>John Tkaczewski</dc:creator>
		<pubDate>Thu, 04 Aug 2011 01:21:23 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-7837</guid>
		<description>It is worth to mention that besides WAAS, there is a number of other commercial software vendors that provide accelerated file transfer software. At FileCatalyst, we use a UDP based protocol to send data at the maximum available link speed. Unlike other UDP based file transfer protocols, we use an efficient algorithm to keep track of lost pockets and we re-transmit only the missing data. 

With much fewer acknowledgments than any other TCP based protocol, the file transfer speed is not affected by the latency. And the speed loss is linear to the pocket loss (Which is impossible with large Window Sizes)

We also use our own built-in congestion control that is immune to latency and takes into the account the average latency of the link before slowing down.

We have an on-line calculator on our web site that provides a comparative of TCP over our UDP protocol. http://www.filecatalyst.com/web_demos/comparison_tool.html

I recognize that this is plug for a commercial product however this article explains exactly the same problem that we have been trying to fix for the last 5 years.</description>
		<content:encoded><![CDATA[<p>It is worth to mention that besides WAAS, there is a number of other commercial software vendors that provide accelerated file transfer software. At FileCatalyst, we use a UDP based protocol to send data at the maximum available link speed. Unlike other UDP based file transfer protocols, we use an efficient algorithm to keep track of lost pockets and we re-transmit only the missing data. </p>
<p>With much fewer acknowledgments than any other TCP based protocol, the file transfer speed is not affected by the latency. And the speed loss is linear to the pocket loss (Which is impossible with large Window Sizes)</p>
<p>We also use our own built-in congestion control that is immune to latency and takes into the account the average latency of the link before slowing down.</p>
<p>We have an on-line calculator on our web site that provides a comparative of TCP over our UDP protocol. <a href="http://www.filecatalyst.com/web_demos/comparison_tool.html" rel="nofollow">http://www.filecatalyst.com/web_demos/comparison_tool.html</a></p>
<p>I recognize that this is plug for a commercial product however this article explains exactly the same problem that we have been trying to fix for the last 5 years.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: knuckles</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-7486</link>
		<dc:creator>knuckles</dc:creator>
		<pubDate>Mon, 04 Jul 2011 21:56:20 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-7486</guid>
		<description>Hi...i&#039;m expecting about 1.5 Mbps on a link that i have. UDP works fine, however, TCP has yielded results close to 0.022 Mbps (essentially nothing!). Would the above tweaks be done on both ends of the network (being both PCs)? And also should a TcpWindowSize be added to the Interface Registry key where the network interface details exist? --&gt;(HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\ServicesTcpip\Parameters, Tcpip\Parameters\Interface)

Thanks!</description>
		<content:encoded><![CDATA[<p>Hi&#8230;i&#8217;m expecting about 1.5 Mbps on a link that i have. UDP works fine, however, TCP has yielded results close to 0.022 Mbps (essentially nothing!). Would the above tweaks be done on both ends of the network (being both PCs)? And also should a TcpWindowSize be added to the Interface Registry key where the network interface details exist? &#8211;&gt;(HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\ServicesTcpip\Parameters, Tcpip\Parameters\Interface)</p>
<p>Thanks!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: O3B and Google tag team: Rural Africa&#8217;s redemption? &#171; Tom Makau</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-6592</link>
		<dc:creator>O3B and Google tag team: Rural Africa&#8217;s redemption? &#171; Tom Makau</dc:creator>
		<pubDate>Tue, 26 Apr 2011 08:42:21 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-6592</guid>
		<description>[...] reach in a long time. To see how low latency is related to higher throughput see this tutorial here. The O3B idea is a great one and deserves all the support it can get so as to make it a [...]</description>
		<content:encoded><![CDATA[<p>[...] reach in a long time. To see how low latency is related to higher throughput see this tutorial here. The O3B idea is a great one and deserves all the support it can get so as to make it a [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Rolf Wiklund</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-6443</link>
		<dc:creator>Rolf Wiklund</dc:creator>
		<pubDate>Thu, 14 Apr 2011 11:17:54 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-6443</guid>
		<description>Hi Brad.
It looks that the window size is more important than the MTU?
Do you have any calc. about the MTU size impact?

I thinking mostly how to solv throughtput issues in DCI (40km)

Thanks
Rolf</description>
		<content:encoded><![CDATA[<p>Hi Brad.<br />
It looks that the window size is more important than the MTU?<br />
Do you have any calc. about the MTU size impact?</p>
<p>I thinking mostly how to solv throughtput issues in DCI (40km)</p>
<p>Thanks<br />
Rolf</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: soulhacker</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-6423</link>
		<dc:creator>soulhacker</dc:creator>
		<pubDate>Wed, 13 Apr 2011 06:53:00 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-6423</guid>
		<description>I just wonder how the latency comes out? If tcp mss is considered. Because the latency rises when tcp mss grows.</description>
		<content:encoded><![CDATA[<p>I just wonder how the latency comes out? If tcp mss is considered. Because the latency rises when tcp mss grows.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Abid</title>
		<link>http://bradhedlund.com/2008/12/19/how-to-calculate-tcp-throughput-for-long-distance-links/comment-page-2/#comment-4716</link>
		<dc:creator>Abid</dc:creator>
		<pubDate>Sun, 26 Dec 2010 16:12:54 +0000</pubDate>
		<guid isPermaLink="false">http://www.bradhedlund.com/?p=74#comment-4716</guid>
		<description>Hi Brad,
    Thanks for  excellent material  that you have posted. We have WAN link of 45Mbps between point a and point B. We use ODG(oracle dataguard) to transfer arch files between point A &amp; B. We have put WAAS devices at both points but still are getting 26Mbps of utilization. My n/w vendor/speciaalist asked me to increase the number of sessions ODG makes,we increased it to 9 from 4. However problem persists. What i understand is:
1: The throughput is dependent on Latency and  TCP window (WAAS vendors says he has tuned the device for max TCP window).
2: With WAAS devices in place, even one session should have shown utilization of 45Mbps.

PLease let us know if we are missign on anything..

Thanks
Abid</description>
		<content:encoded><![CDATA[<p>Hi Brad,<br />
    Thanks for  excellent material  that you have posted. We have WAN link of 45Mbps between point a and point B. We use ODG(oracle dataguard) to transfer arch files between point A &amp; B. We have put WAAS devices at both points but still are getting 26Mbps of utilization. My n/w vendor/speciaalist asked me to increase the number of sessions ODG makes,we increased it to 9 from 4. However problem persists. What i understand is:<br />
1: The throughput is dependent on Latency and  TCP window (WAAS vendors says he has tuned the device for max TCP window).<br />
2: With WAAS devices in place, even one session should have shown utilization of 45Mbps.</p>
<p>PLease let us know if we are missign on anything..</p>
<p>Thanks<br />
Abid</p>
]]></content:encoded>
	</item>
</channel>
</rss>

