<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	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/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>soumitra.net Blog &#187; Google NYC</title>
	<atom:link href="http://soumitra.net/blog/index.php/archives/category/google-nyc/feed" rel="self" type="application/rss+xml" />
	<link>http://soumitra.net/blog</link>
	<description>(!) just another weblog</description>
	<lastBuildDate>Fri, 12 Feb 2010 22:00:18 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
			<item>
		<title>@ Google NYC &#8230;</title>
		<link>http://soumitra.net/blog/archives/43</link>
		<comments>http://soumitra.net/blog/archives/43#comments</comments>
		<pubDate>Fri, 06 Apr 2007 00:30:52 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/43</guid>
		<description><![CDATA[Maximizing usage of available power capacity is the key!
Power subscription at the facility level seems promising (whatever that means)
large systems should utilise power efficiently.
Q and A going on&#8230;
&#8230; almost ending, so i guess i can switch this off.
Oh
I forgot.
Conclusion (from Luiz&#8217;s slides):
Power/ energy efficient and fault tolerance are central to the design of large scale [...]]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/43/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>@ Google NYC &#8230;</title>
		<link>http://soumitra.net/blog/archives/42</link>
		<comments>http://soumitra.net/blog/archives/42#comments</comments>
		<pubDate>Fri, 06 Apr 2007 00:13:29 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/42</guid>
		<description><![CDATA[Power efficient datacenters:
Idle machines also consume power.
Compared to humans, power consumption for machines is waay high, since humans use less power while resting, but high while performing. Machines don&#8217;t have that high gap between idle and high activity power consumptions.
]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/42/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>@ Google NYC &#8230;</title>
		<link>http://soumitra.net/blog/archives/41</link>
		<comments>http://soumitra.net/blog/archives/41#comments</comments>
		<pubDate>Thu, 05 Apr 2007 23:59:35 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/41</guid>
		<description><![CDATA[&#8220;Fault Tolerance systems lie.
Disk failures: Failure rates < 1% per year.
Study conducted proves that irrespective of age, disk failed... (couldn't catch that)
also,  Temperature is not a major criterion for disk failures.
SMART disks&#8230;self monitoring. (!)
Even then, 56% of disks failing had no predictable behavior.
Well, more bad news: 70% of drives survive for 8 months. (So [...]]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/41/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>@ Google NYC &#8230;</title>
		<link>http://soumitra.net/blog/archives/37</link>
		<comments>http://soumitra.net/blog/archives/37#comments</comments>
		<pubDate>Thu, 05 Apr 2007 23:44:28 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/37</guid>
		<description><![CDATA[So on stage, Luiz Barroso!
&#8220;Single fault will bring down the large scale computer systems that use shared memory programming model, and fault containment is complex. A difficult problem&#8221;
]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/37/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>@ Google NYC &#8230;</title>
		<link>http://soumitra.net/blog/archives/39</link>
		<comments>http://soumitra.net/blog/archives/39#comments</comments>
		<pubDate>Thu, 05 Apr 2007 23:44:19 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/39</guid>
		<description><![CDATA[&#8220;The MHz race (Moore&#8217;s law) just makes the machines faster&#8230; the programs coded 10 yrs ago automatically run faster&#8230;
Additionally, power consumption increases and temperature management is a concern.
Ergo, cost increases with time.
So now, the equation becomes higher computing power = higher power bills= higher costs&#8221;
]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/39/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>@ Google NYC &#8230;</title>
		<link>http://soumitra.net/blog/archives/40</link>
		<comments>http://soumitra.net/blog/archives/40#comments</comments>
		<pubDate>Thu, 05 Apr 2007 23:43:59 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/40</guid>
		<description><![CDATA[&#8220;Power supply units of machines are less efficient. They can be made up to 90% efficient, though they are more expensive.
Multi-core processors solve the problem a bit, but there should be enough threads.&#8221;
]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/40/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>@ Google NYC &#8230;</title>
		<link>http://soumitra.net/blog/archives/38</link>
		<comments>http://soumitra.net/blog/archives/38#comments</comments>
		<pubDate>Thu, 05 Apr 2007 23:30:15 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/38</guid>
		<description><![CDATA[&#8220;Crosstalk at CMOS level, considering their  shrinking size. Disk drive failures are increasing&#8230;&#8221;
]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/38/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>@ Google NYC &#8230;</title>
		<link>http://soumitra.net/blog/archives/36</link>
		<comments>http://soumitra.net/blog/archives/36#comments</comments>
		<pubDate>Thu, 05 Apr 2007 23:20:28 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/36</guid>
		<description><![CDATA[Free beer and wine, and supposedly delicious hors d&#8217;oeuvres&#8230; ( i didn&#8217;t try any &#8230;yet!)
Mike here is giving out deets on the next in the Speaker series..
]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/36/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>@ Google NYC</title>
		<link>http://soumitra.net/blog/archives/35</link>
		<comments>http://soumitra.net/blog/archives/35#comments</comments>
		<pubDate>Thu, 05 Apr 2007 23:18:12 +0000</pubDate>
		<dc:creator>soumitra</dc:creator>
				<category><![CDATA[Google NYC]]></category>

		<guid isPermaLink="false">http://soumitra.net/blog/archives/35</guid>
		<description><![CDATA[Am sitting here at the Google&#8217;s NYC office&#8230; they have a Speaker series and i got myself invited.
So we&#8217;re all gathered here, and all guys are like filling in slowly. the talk was supposed to start at 7ish, but then the rush is so much that they&#8217;re still settling down.
Okay&#8230;just starting&#8230;
]]></description>
		<wfw:commentRss>http://soumitra.net/blog/archives/35/feed</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>

<!-- Dynamic Page Served (once) in 0.435 seconds -->

