<?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: 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>
	<lastBuildDate>Sat, 04 Feb 2012 09:46:28 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.2.1</generator>
	<item>
		<title>By: Steve Souders</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3668</link>
		<dc:creator>Steve Souders</dc:creator>
		<pubDate>Sat, 14 Jan 2012 16:31:12 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3668</guid>
		<description>@Boundless: You could try using different hostnames such as www1., www2., etc.</description>
		<content:encoded><![CDATA[<p>@Boundless: You could try using different hostnames such as www1., www2., etc.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Boundless</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3667</link>
		<dc:creator>Boundless</dc:creator>
		<pubDate>Sat, 14 Jan 2012 16:20:02 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3667</guid>
		<description>Ah hah !

I forced my test page to only give 4 live streams instead of 8, and it works in Chrome and Safari. I then opened 2 additional streams, for a total of 6, and it&#039;s ok. But a 7th will not open. So Chrome and Safari are enforcing the 6-connection limit. I double checked this by closing one active stream, at which point the blocked 7th window showed video.

How do I defeat this limit ???</description>
		<content:encoded><![CDATA[<p>Ah hah !</p>
<p>I forced my test page to only give 4 live streams instead of 8, and it works in Chrome and Safari. I then opened 2 additional streams, for a total of 6, and it&#8217;s ok. But a 7th will not open. So Chrome and Safari are enforcing the 6-connection limit. I double checked this by closing one active stream, at which point the blocked 7th window showed video.</p>
<p>How do I defeat this limit ???</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Boundless</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3666</link>
		<dc:creator>Boundless</dc:creator>
		<pubDate>Sat, 14 Jan 2012 16:10:56 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3666</guid>
		<description>If the problem is due to the maximum number of connections per server, how can I circumvent it ? Can I have multiple ports to access a given media server, and distribute the load from a given page over them ? Would using different port numbers make my media server appear to be multiple servers ?

Isn&#039;t Firefox enforcing the limit ?</description>
		<content:encoded><![CDATA[<p>If the problem is due to the maximum number of connections per server, how can I circumvent it ? Can I have multiple ports to access a given media server, and distribute the load from a given page over them ? Would using different port numbers make my media server appear to be multiple servers ?</p>
<p>Isn&#8217;t Firefox enforcing the limit ?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Boundless</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3665</link>
		<dc:creator>Boundless</dc:creator>
		<pubDate>Sat, 14 Jan 2012 16:06:15 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3665</guid>
		<description>I have a custom media server whose job is to source MJPEG video streams from multiple cameras. It is intended for viewing several dozen cameras simultaneously at high frame rates in a single page. I have tested it with the latest Firefox with 8 cameras simultaneously in a single page, even when I open several additional video streams, and it is OK. But there is blocking in Chrome and Safari when I try to open additional pages using the same instance of the browser. There is a continuous connection for each camera since the video is live and therefore continuous.

Is the problem with Chrome and Safari a result of the limit of the maximum number of connections per server ? But the tables show Firefox supports only 6, whereas more than 8 is OK.</description>
		<content:encoded><![CDATA[<p>I have a custom media server whose job is to source MJPEG video streams from multiple cameras. It is intended for viewing several dozen cameras simultaneously at high frame rates in a single page. I have tested it with the latest Firefox with 8 cameras simultaneously in a single page, even when I open several additional video streams, and it is OK. But there is blocking in Chrome and Safari when I try to open additional pages using the same instance of the browser. There is a continuous connection for each camera since the video is live and therefore continuous.</p>
<p>Is the problem with Chrome and Safari a result of the limit of the maximum number of connections per server ? But the tables show Firefox supports only 6, whereas more than 8 is OK.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steve Souders</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3491</link>
		<dc:creator>Steve Souders</dc:creator>
		<pubDate>Wed, 28 Sep 2011 20:12:10 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3491</guid>
		<description>@MNot: My attempt to highlight good blog posts from the past. ;-)

@Jean-Philippe: I&#039;m pretty sure request 1&amp;3 would be considered the same hostname.</description>
		<content:encoded><![CDATA[<p>@MNot: My attempt to highlight good blog posts from the past. ;-)</p>
<p>@Jean-Philippe: I&#8217;m pretty sure request 1&#038;3 would be considered the same hostname.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jean-Philippe</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3486</link>
		<dc:creator>Jean-Philippe</dc:creator>
		<pubDate>Wed, 28 Sep 2011 16:11:33 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3486</guid>
		<description>@steve
In IE6, would these 3 URL be considered as distinct from the max connection perspective ?

http://server1.xx?cgi    (which map to 199.199.199.199)
http://199.199.199.199?cgi
http://?cgi           (from a html which is on server1.xx)

Thanks.</description>
		<content:encoded><![CDATA[<p>@steve<br />
In IE6, would these 3 URL be considered as distinct from the max connection perspective ?</p>
<p><a href="http://server1.xx?cgi" rel="nofollow">http://server1.xx?cgi</a>    (which map to 199.199.199.199)<br />
<a href="http://199.199.199.199?cgi" rel="nofollow">http://199.199.199.199?cgi</a><br />
<a href="http://?cgi" rel="nofollow">http://?cgi</a>           (from a html which is on server1.xx)</p>
<p>Thanks.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mark Nottingham</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3198</link>
		<dc:creator>Mark Nottingham</dc:creator>
		<pubDate>Thu, 31 Mar 2011 21:46:55 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3198</guid>
		<description>Hah - just realised this is a really old post (about two years old!). You mentioned it on twitter and I assumed it was new. D&#039;oh.</description>
		<content:encoded><![CDATA[<p>Hah &#8211; just realised this is a really old post (about two years old!). You mentioned it on twitter and I assumed it was new. D&#8217;oh.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mark Nottingham</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3197</link>
		<dc:creator>Mark Nottingham</dc:creator>
		<pubDate>Thu, 31 Mar 2011 21:46:00 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-3197</guid>
		<description>Hey Steve,

Almost two years ago, HTTPbis removed the connection limit, after discussion with browser vendors:
  http://trac.tools.ietf.org/wg/httpbis/trac/ticket/131

The problem with using too many connections isn&#039;t really server load; dealing with large numbers of conns server-side is fairly well-understood these days. The real problem is its effect on congestion control. E.g., if your browser uses 8 connections each to 10 sharded hosts, and the initial congestion window is a conservative 3, it means that about a third of a megabyte can be in flight, all at once, causing havoc for other applications. 

Jim Gettys was railing on this subject this week at IETF Prague; in combination with bufferbloat, it is unfriendly to other applications, as well as potentially worsening browse performance.

Off to bed here,</description>
		<content:encoded><![CDATA[<p>Hey Steve,</p>
<p>Almost two years ago, HTTPbis removed the connection limit, after discussion with browser vendors:<br />
  <a href="http://trac.tools.ietf.org/wg/httpbis/trac/ticket/131" rel="nofollow">http://trac.tools.ietf.org/wg/httpbis/trac/ticket/131</a></p>
<p>The problem with using too many connections isn&#8217;t really server load; dealing with large numbers of conns server-side is fairly well-understood these days. The real problem is its effect on congestion control. E.g., if your browser uses 8 connections each to 10 sharded hosts, and the initial congestion window is a conservative 3, it means that about a third of a megabyte can be in flight, all at once, causing havoc for other applications. </p>
<p>Jim Gettys was railing on this subject this week at IETF Prague; in combination with bufferbloat, it is unfriendly to other applications, as well as potentially worsening browse performance.</p>
<p>Off to bed here,</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steve Souders</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-2243</link>
		<dc:creator>Steve Souders</dc:creator>
		<pubDate>Fri, 30 Jul 2010 02:13:27 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-2243</guid>
		<description>@John Rossen: There&#039;s overhead in establishing a new connection. The studies I did at Yahoo! found that too many simultaneous connections worsens performance. In most cases, it would be better to use fewer persistent connections.</description>
		<content:encoded><![CDATA[<p>@John Rossen: There&#8217;s overhead in establishing a new connection. The studies I did at Yahoo! found that too many simultaneous connections worsens performance. In most cases, it would be better to use fewer persistent connections.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: John Rossen</title>
		<link>http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-2242</link>
		<dc:creator>John Rossen</dc:creator>
		<pubDate>Thu, 29 Jul 2010 19:35:16 +0000</pubDate>
		<guid isPermaLink="false">http://www.stevesouders.com/blog/2008/03/20/roundup-on-parallel-connections/#comment-2242</guid>
		<description>n the post above, when you say “parallel connections”, its actually “parallel persistent connections” – right?

Firefox allows max 15 connections per server (which are the “Connection:close” types), and max 6 “persistent” connections per server (“connection:keep-alive”). Since the max number of non “keep-alive” connections are more, is there a strong reason to go for persistent connections?

If I serve 15 resources from a domain for my webpage, getting them all in parallel with “connection:close” should be faster than fetching them 6 at a time, with keep-alive tcp connections. Isn’t it?</description>
		<content:encoded><![CDATA[<p>n the post above, when you say “parallel connections”, its actually “parallel persistent connections” – right?</p>
<p>Firefox allows max 15 connections per server (which are the “Connection:close” types), and max 6 “persistent” connections per server (“connection:keep-alive”). Since the max number of non “keep-alive” connections are more, is there a strong reason to go for persistent connections?</p>
<p>If I serve 15 resources from a domain for my webpage, getting them all in parallel with “connection:close” should be faster than fetching them 6 at a time, with keep-alive tcp connections. Isn’t it?</p>
]]></content:encoded>
	</item>
</channel>
</rss>

