<?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: It&#8217;s Still the Latency, Stupid&#8230;pt.1</title>
	<atom:link href="http://www.edgeblog.net/2007/its-still-the-latency-stupid/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/</link>
	<description>Notes from the edge</description>
	<lastBuildDate>Mon, 30 Jan 2012 19:27:12 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=</generator>
	<item>
		<title>By: Brandon</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-164390</link>
		<dc:creator>Brandon</dc:creator>
		<pubDate>Tue, 13 Dec 2011 21:20:24 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-164390</guid>
		<description>I&#039;m not sure that I agree with your conclusion in this article.  As latency increases window size should increase, not decrease.  Congestion windows are based off of packet loss, not latency.   You have an advertised window which is equal to the buffer space on the receiving host and then a congestion window that is cut in half every type there is a lost segment.   Latency doesn&#039;t come in to play for either of the windows, except that if you have a high latency network, you should increase those windows.

To use your sandbag analogy, if you are going over a wall you add another person (or hop) because the distance increased.  That now means to go at the same speed, you need two containers (increased window size).  The fact that latency increased won&#039;t affect your actual speed as long as you appropriately manage your buffers and windows.   That is however only the case when you are sending lots of data one way, if you are doing something real time (ssh, gaming) then latency is king.</description>
		<content:encoded><![CDATA[<p>I&#8217;m not sure that I agree with your conclusion in this article.  As latency increases window size should increase, not decrease.  Congestion windows are based off of packet loss, not latency.   You have an advertised window which is equal to the buffer space on the receiving host and then a congestion window that is cut in half every type there is a lost segment.   Latency doesn&#8217;t come in to play for either of the windows, except that if you have a high latency network, you should increase those windows.</p>
<p>To use your sandbag analogy, if you are going over a wall you add another person (or hop) because the distance increased.  That now means to go at the same speed, you need two containers (increased window size).  The fact that latency increased won&#8217;t affect your actual speed as long as you appropriately manage your buffers and windows.   That is however only the case when you are sending lots of data one way, if you are doing something real time (ssh, gaming) then latency is king.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: KdV</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-140119</link>
		<dc:creator>KdV</dc:creator>
		<pubDate>Mon, 08 Nov 2010 15:17:40 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-140119</guid>
		<description>I like your articles about the latency problem Sir. They are clear and informative, thank you! 

Greetings from the Netherlands,
Kees</description>
		<content:encoded><![CDATA[<p>I like your articles about the latency problem Sir. They are clear and informative, thank you! </p>
<p>Greetings from the Netherlands,<br />
Kees</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Cloud Performance – Why Long Distance Relationships Don’t Work &#171; Apparent Networks</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-139841</link>
		<dc:creator>Cloud Performance – Why Long Distance Relationships Don’t Work &#171; Apparent Networks</dc:creator>
		<pubDate>Thu, 04 Nov 2010 13:48:58 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-139841</guid>
		<description>[...] has a dramatic impact on the maximum achievable performance you will see from the cloud. As this example details the latency on a network connection can be a bigger factor in the end to end performance, [...]</description>
		<content:encoded><![CDATA[<p>[...] has a dramatic impact on the maximum achievable performance you will see from the cloud. As this example details the latency on a network connection can be a bigger factor in the end to end performance, [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sektormedia: Brain Ramblings &#187; Blog Archive &#187; Great Latency Discussion</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-139330</link>
		<dc:creator>Sektormedia: Brain Ramblings &#187; Blog Archive &#187; Great Latency Discussion</dc:creator>
		<pubDate>Tue, 26 Oct 2010 02:41:21 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-139330</guid>
		<description>[...] has a great article entitles It&#8217;s Still the Latency, Stupid&#8230;pt.1. A great thing for junior admins and other folks to read to get a good understanding of the Latency [...]</description>
		<content:encoded><![CDATA[<p>[...] has a great article entitles It&#8217;s Still the Latency, Stupid&#8230;pt.1. A great thing for junior admins and other folks to read to get a good understanding of the Latency [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Billy Guthrie</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-122744</link>
		<dc:creator>Billy Guthrie</dc:creator>
		<pubDate>Tue, 09 Mar 2010 03:07:26 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-122744</guid>
		<description>&gt;”You are saying that latency causes network problems and that by improving latency &gt;you can improve your network. I assert that this is false. If you have latency &gt;problems, they are a symptom of network congestion. If your network is suffering &gt;from serious congestion, it probably needs more bandwidth.”

hahahaha! That is classic (needs more bandwidth.)

Bill, great article!</description>
		<content:encoded><![CDATA[<p>&gt;”You are saying that latency causes network problems and that by improving latency &gt;you can improve your network. I assert that this is false. If you have latency &gt;problems, they are a symptom of network congestion. If your network is suffering &gt;from serious congestion, it probably needs more bandwidth.”</p>
<p>hahahaha! That is classic (needs more bandwidth.)</p>
<p>Bill, great article!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Dirk</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-103946</link>
		<dc:creator>Dirk</dc:creator>
		<pubDate>Mon, 27 Jul 2009 09:13:21 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-103946</guid>
		<description>Thanks for a well written article, I am about to give a training course on application profiling (with a specific tool) and one of the topics is latency impact on application performance. I would like to refer students to this article,
Bandwidth is becoming more available now in South Africa (still more expensive than US or Europe) but we too sit with the &quot;distance problem&quot;. (hey its a big country)They often ask you why applications in Cape Town are slower than Durban with the same link speed. 
And the deeper into Africa you get, the more prevalent the latency issue becomes, less POPs, poor connectivity so sometimes have to use satelite....

Kind Regards

Dirk</description>
		<content:encoded><![CDATA[<p>Thanks for a well written article, I am about to give a training course on application profiling (with a specific tool) and one of the topics is latency impact on application performance. I would like to refer students to this article,<br />
Bandwidth is becoming more available now in South Africa (still more expensive than US or Europe) but we too sit with the &#8220;distance problem&#8221;. (hey its a big country)They often ask you why applications in Cape Town are slower than Durban with the same link speed.<br />
And the deeper into Africa you get, the more prevalent the latency issue becomes, less POPs, poor connectivity so sometimes have to use satelite&#8230;.</p>
<p>Kind Regards</p>
<p>Dirk</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Josh Betz &#187; It&#8217;s still Latency</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-64497</link>
		<dc:creator>Josh Betz &#187; It&#8217;s still Latency</dc:creator>
		<pubDate>Sun, 25 May 2008 17:19:11 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-64497</guid>
		<description>[...] edgeblog » It&#8217;s Still the Latency, Stupid&#8230;pt.1. Here&#8217;s a great article about how your problems with network speed may have more to do with latency than bandwith.   Share and Enjoy: These icons link to social bookmarking sites where readers can share and discover new web pages. [...]</description>
		<content:encoded><![CDATA[<p>[...] edgeblog » It&#8217;s Still the Latency, Stupid&#8230;pt.1. Here&#8217;s a great article about how your problems with network speed may have more to do with latency than bandwith.   Share and Enjoy: These icons link to social bookmarking sites where readers can share and discover new web pages. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Munich Unix &#187; Blog Archive &#187; It&#8217;s Still the Latency, Stupid&#8230;</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-27277</link>
		<dc:creator>Munich Unix &#187; Blog Archive &#187; It&#8217;s Still the Latency, Stupid&#8230;</dc:creator>
		<pubDate>Mon, 29 Oct 2007 14:21:43 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-27277</guid>
		<description>[...] read more &#124; digg story [...]</description>
		<content:encoded><![CDATA[<p>[...] read more | digg story [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mark</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-14694</link>
		<dc:creator>Mark</dc:creator>
		<pubDate>Wed, 06 Jun 2007 10:56:59 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-14694</guid>
		<description>(stupid carrot sign)

less then 1ms.  I&#039;m not a rocket scientist but it looks to me like latency does have an impact.  

If you guys still dont get it, google &quot;long fat networks&quot;</description>
		<content:encoded><![CDATA[<p>(stupid carrot sign)</p>
<p>less then 1ms.  I&#8217;m not a rocket scientist but it looks to me like latency does have an impact.  </p>
<p>If you guys still dont get it, google &#8220;long fat networks&#8221;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mark</title>
		<link>http://www.edgeblog.net/2007/its-still-the-latency-stupid/comment-page-1/#comment-14693</link>
		<dc:creator>Mark</dc:creator>
		<pubDate>Wed, 06 Jun 2007 10:55:49 +0000</pubDate>
		<guid isPermaLink="false">http://www.edgeblog.net/2007/its-still-the-latency-stupid/#comment-14693</guid>
		<description>&#124;Continued from above&#124;

.....around 3.5 to 4mbs download speeds on a 11mb DSL circuit compared to seeing exactly 11mb (+/- 300kb) when the latency is </description>
		<content:encoded><![CDATA[<p>|Continued from above|</p>
<p>&#8230;..around 3.5 to 4mbs download speeds on a 11mb DSL circuit compared to seeing exactly 11mb (+/- 300kb) when the latency is</p>
]]></content:encoded>
	</item>
</channel>
</rss>

<!-- Dynamic Page Served (once) in 1.463 seconds -->

