
<!-- CVSNO: query.php: 1: '' -->
<!-- CVSNO: query.php: 2: '' -->
<!-- CVSNO: query.php: 3: '0' --><?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"
	>
<channel>
	<title>Comments on: Roundup on Parallel Connections</title>
	<atom:link href="http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/</link>
	<description>Essential knowledge for making your web pages faster.</description>
	<pubDate>Fri, 29 Aug 2008 03:25:49 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.6</generator>
		<item>
		<title>By: assan37</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-137</link>
		<dc:creator>assan37</dc:creator>
		<pubDate>Wed, 30 Apr 2008 18:07:47 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-137</guid>
		<description>a , cheap tramadol, generic levitra, cialis on line, propecia, viagra cheap, zoloft, buy viagra now, buy tramadol, cheap prozac, purchase augmentin, cheapest viagra, buy rimonabant, order augmentin, cialis levitra viagra, purchase levitra, order prilosec,, prozac pills, purchase cheap levitra, soma, allegra, purchase tramadol,, buy antivert online, buy prednisone, nexium, viagra and levitra, buy prozac now,, cialis online,, buy pfizer viagra, cheap prednisone, generic soma, buying soma,, cheap soma, buy propecia, lasix, cheap cialis,, purchase soma, generic viagra, viagra online, propecia, buy prozac now, prozac pills, buying viagra online, lexapro, ultram er, cheap ultram, paxil, plavix, order viagra online, acomplia, generic cialis online, order ultram online, prednisone, zoloft, cheap ultram online, buy cheap acomplia online, buy soma online,, ultram 50mg, cheap cialis,, cheap zocor, purchase cheap tramadol,, ultram, cheap tramadol, order viagra, levitra, tramadol, buy viagra in usa, buy acomplia, buy prozac online, tramadol, cheap augmentin, levitra online, buy tramadol, viagra without a prescription,, buy rimonabant, cheap soma, buy cialis online, alternatives to viagra, viagra alternative, prozac, online tramadol, tramadol hcl, imitrex, cialis generic, buy online viagra, viagra tablets,</description>
		<content:encoded><![CDATA[<p>a , cheap tramadol, generic levitra, cialis on line, propecia, viagra cheap, zoloft, buy viagra now, buy tramadol, cheap prozac, purchase augmentin, cheapest viagra, buy rimonabant, order augmentin, cialis levitra viagra, purchase levitra, order prilosec,, prozac pills, purchase cheap levitra, soma, allegra, purchase tramadol,, buy antivert online, buy prednisone, nexium, viagra and levitra, buy prozac now,, cialis online,, buy pfizer viagra, cheap prednisone, generic soma, buying soma,, cheap soma, buy propecia, lasix, cheap cialis,, purchase soma, generic viagra, viagra online, propecia, buy prozac now, prozac pills, buying viagra online, lexapro, ultram er, cheap ultram, paxil, plavix, order viagra online, acomplia, generic cialis online, order ultram online, prednisone, zoloft, cheap ultram online, buy cheap acomplia online, buy soma online,, ultram 50mg, cheap cialis,, cheap zocor, purchase cheap tramadol,, ultram, cheap tramadol, order viagra, levitra, tramadol, buy viagra in usa, buy acomplia, buy prozac online, tramadol, cheap augmentin, levitra online, buy tramadol, viagra without a prescription,, buy rimonabant, cheap soma, buy cialis online, alternatives to viagra, viagra alternative, prozac, online tramadol, tramadol hcl, imitrex, cialis generic, buy online viagra, viagra tablets,</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steve Souders</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-126</link>
		<dc:creator>Steve Souders</dc:creator>
		<pubDate>Tue, 29 Apr 2008 04:47:59 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-126</guid>
		<description>tad - I created a Cuzillion page to test this:

http://stevesouders.com/cuzillion/?c0=bi2hfff2_0&#038;c1=bi2hfff2_0&#038;c2=bi2hfff2_0&#038;c3=bi2hfff2_0&#038;c4=bi2hfff2_0&#038;c5=bi2hfff2_0&#038;c6=bi2hfff2_0&#038;c7=bi2hfff2_0&#038;c8=bi2hfff2_0

On Opera 9.27 using the default values ("Max Connections Server" is 8) downloads 4 resources in parallel for a single hostname. If you uncheck "Reduce Max Persistent HTTP Connections" it drops to 2 in parallel. If recheck that and raise "Max Connections Server" to 16 it downloads 8 in parallel. Perhaps this is a terminology gap but the default behavior is 4 in parallel.</description>
		<content:encoded><![CDATA[<p>tad - I created a Cuzillion page to test this:</p>
<p><a href="http://stevesouders.com/cuzillion/?c0=bi2hfff2_0&#038;c1=bi2hfff2_0&#038;c2=bi2hfff2_0&#038;c3=bi2hfff2_0&#038;c4=bi2hfff2_0&#038;c5=bi2hfff2_0&#038;c6=bi2hfff2_0&#038;c7=bi2hfff2_0&#038;c8=bi2hfff2_0" rel="nofollow">http://stevesouders.com/cuzillion/?c0=bi2hfff2_0&#038;c1=bi2hfff2_0&#038;c2=bi2hfff2_0&#038;c3=bi2hfff2_0&#038;c4=bi2hfff2_0&#038;c5=bi2hfff2_0&#038;c6=bi2hfff2_0&#038;c7=bi2hfff2_0&#038;c8=bi2hfff2_0</a></p>
<p>On Opera 9.27 using the default values (&#8221;Max Connections Server&#8221; is 8) downloads 4 resources in parallel for a single hostname. If you uncheck &#8220;Reduce Max Persistent HTTP Connections&#8221; it drops to 2 in parallel. If recheck that and raise &#8220;Max Connections Server&#8221; to 16 it downloads 8 in parallel. Perhaps this is a terminology gap but the default behavior is 4 in parallel.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: tad</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-123</link>
		<dc:creator>tad</dc:creator>
		<pubDate>Mon, 28 Apr 2008 20:43:06 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-123</guid>
		<description>You list max connections per server for opera 9 as 4 but there site says 8:
http://www.opera.com/support/usingopera/operaini/index.dml#performance
Is that 8 for http 1.0?</description>
		<content:encoded><![CDATA[<p>You list max connections per server for opera 9 as 4 but there site says 8:<br />
<a href="http://www.opera.com/support/usingopera/operaini/index.dml#performance" rel="nofollow">http://www.opera.com/support/usingopera/operaini/index.dml#performance</a><br />
Is that 8 for http 1.0?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: David Chapman</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-109</link>
		<dc:creator>David Chapman</dc:creator>
		<pubDate>Mon, 07 Apr 2008 06:01:49 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-109</guid>
		<description>Pseudo parallel feeds such as multiple 'threads' for XMLHttpRequest don't help much unless being fed from different domains. Even then they depend on expanding excess serial capacity in the physical network link towards the client end.

There is but one serial physical network path into the client's browser, even if you choose to multiplex that into multiple packet feeds, by whatever method.

The web in spite of broadband is still, and will always be a serial network; subject to the speed limit of the slowest link, often grinding down below dail-up speeds.

Add a heavy application, whether it's an overweight AJAX library, Flash or Java, and you're lost for a very long time between where you've been and where you might get. This gets very boring after about 10 seconds.

Users simply bail out altogether before about 20 seconds.

The only real solution is to make your web apps small. Then test them on dial-up bandwidth!

This isn't going to change anytime soon. Serial links are not scalable; except by bandwidth improvement or improved compression by orders of magnitude. Although that's happening, demand for bandwidth is still happening even quicker.

Many designers get lulled into a sense of false satisfaction with loading times because they work in a situation where they have got excess serial capacity connecting them to the net.

Go down to your local library or campus where several hundred PC's share a link to the net and see if you're still satisfied, and whether 2 or 4 or 6 or even 20 virtual connections make any difference!

When you've got past the great long boring wait, remember that most people see (or don't see) your latest and greatest wonderful but overweight app that way.</description>
		<content:encoded><![CDATA[<p>Pseudo parallel feeds such as multiple &#8216;threads&#8217; for XMLHttpRequest don&#8217;t help much unless being fed from different domains. Even then they depend on expanding excess serial capacity in the physical network link towards the client end.</p>
<p>There is but one serial physical network path into the client&#8217;s browser, even if you choose to multiplex that into multiple packet feeds, by whatever method.</p>
<p>The web in spite of broadband is still, and will always be a serial network; subject to the speed limit of the slowest link, often grinding down below dail-up speeds.</p>
<p>Add a heavy application, whether it&#8217;s an overweight AJAX library, Flash or Java, and you&#8217;re lost for a very long time between where you&#8217;ve been and where you might get. This gets very boring after about 10 seconds.</p>
<p>Users simply bail out altogether before about 20 seconds.</p>
<p>The only real solution is to make your web apps small. Then test them on dial-up bandwidth!</p>
<p>This isn&#8217;t going to change anytime soon. Serial links are not scalable; except by bandwidth improvement or improved compression by orders of magnitude. Although that&#8217;s happening, demand for bandwidth is still happening even quicker.</p>
<p>Many designers get lulled into a sense of false satisfaction with loading times because they work in a situation where they have got excess serial capacity connecting them to the net.</p>
<p>Go down to your local library or campus where several hundred PC&#8217;s share a link to the net and see if you&#8217;re still satisfied, and whether 2 or 4 or 6 or even 20 virtual connections make any difference!</p>
<p>When you&#8217;ve got past the great long boring wait, remember that most people see (or don&#8217;t see) your latest and greatest wonderful but overweight app that way.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mike Belshe</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-80</link>
		<dc:creator>Mike Belshe</dc:creator>
		<pubDate>Mon, 24 Mar 2008 05:53:20 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-80</guid>
		<description>Server architectures (e.g. Apache) which are thread-per-connection have a harder time scaling with large numbers of keepalives.  Servers which use select/poll loops (e.g. Zeus) usually do not have this problem.

Zeus wrote a nice paper about the affect of KeepAlives on Apache in this paper: http://www.zeus.com/documents/en/ac/acceleration_apache.pdf

The paper is really about their proxy product, but ignore that; the analysis of how keepalives affect server performance is sound.</description>
		<content:encoded><![CDATA[<p>Server architectures (e.g. Apache) which are thread-per-connection have a harder time scaling with large numbers of keepalives.  Servers which use select/poll loops (e.g. Zeus) usually do not have this problem.</p>
<p>Zeus wrote a nice paper about the affect of KeepAlives on Apache in this paper: <a href="http://www.zeus.com/documents/en/ac/acceleration_apache.pdf" rel="nofollow">http://www.zeus.com/documents/en/ac/acceleration_apache.pdf</a></p>
<p>The paper is really about their proxy product, but ignore that; the analysis of how keepalives affect server performance is sound.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: soonvavoncize</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-66</link>
		<dc:creator>soonvavoncize</dc:creator>
		<pubDate>Sat, 22 Mar 2008 12:00:33 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-66</guid>
		<description>Snx for you job!
It has very much helped me!</description>
		<content:encoded><![CDATA[<p>Snx for you job!<br />
It has very much helped me!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: &#187; IE8/FF3 Going To 6 Parallel Connections / Wayne Pan's Blog - tech &#124; js &#124; ui &#124; ajax &#124; life &#124; mobile</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-64</link>
		<dc:creator>&#187; IE8/FF3 Going To 6 Parallel Connections / Wayne Pan's Blog - tech &#124; js &#124; ui &#124; ajax &#124; life &#124; mobile</dc:creator>
		<pubDate>Sat, 22 Mar 2008 00:51:28 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-64</guid>
		<description>[...] do subdomain hacks, css sprites, etc to deal with this. I&#8217;m psyched.Steve Souders also has a good wrap up along trying to answer the question of will this break the internet?    Posted by Wayne on Friday, [...]</description>
		<content:encoded><![CDATA[<p>[...] do subdomain hacks, css sprites, etc to deal with this. I&#8217;m psyched.Steve Souders also has a good wrap up along trying to answer the question of will this break the internet?    Posted by Wayne on Friday, [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steve Souders</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-63</link>
		<dc:creator>Steve Souders</dc:creator>
		<pubDate>Fri, 21 Mar 2008 16:30:38 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-63</guid>
		<description>Anyone have data measuring load times for _real users_ downloading pages with several (8+) static resources on HTTP/1.0 vs. HTTP/1.1?</description>
		<content:encoded><![CDATA[<p>Anyone have data measuring load times for _real users_ downloading pages with several (8+) static resources on HTTP/1.0 vs. HTTP/1.1?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: kl</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-62</link>
		<dc:creator>kl</dc:creator>
		<pubDate>Fri, 21 Mar 2008 15:53:52 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-62</guid>
		<description>Try lighttpd. It doesn't seem to have problem even with crazy numbers of persistent connections.</description>
		<content:encoded><![CDATA[<p>Try lighttpd. It doesn&#8217;t seem to have problem even with crazy numbers of persistent connections.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Patrick Meenan</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-57</link>
		<dc:creator>Patrick Meenan</dc:creator>
		<pubDate>Thu, 20 Mar 2008 15:07:36 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-57</guid>
		<description>FWIW, HTTP 1.0 CAN support persistent connections and the major browsers fully support it, just most servers didn't.  Using HTTP 1.0 with persistent connections allows AOL to get 4 parallel  persistent connections out of browsers that would normally only establish 2.

You loose being able to use e-tags or other 1.1-specific headers but it works great for static objects from a CDN.</description>
		<content:encoded><![CDATA[<p>FWIW, HTTP 1.0 CAN support persistent connections and the major browsers fully support it, just most servers didn&#8217;t.  Using HTTP 1.0 with persistent connections allows AOL to get 4 parallel  persistent connections out of browsers that would normally only establish 2.</p>
<p>You loose being able to use e-tags or other 1.1-specific headers but it works great for static objects from a CDN.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
