<?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: SSD&#8217;s, Journaling, and noatime/relatime</title>
	<atom:link href="http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/feed/" rel="self" type="application/rss+xml" />
	<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/</link>
	<description>Musings about Open Source, Linux, and Life by Theodore Tso</description>
	<lastBuildDate>Mon, 22 Feb 2010 22:39:59 -0500</lastBuildDate>
	<generator>http://wordpress.org/?v=2.8.6</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Testing the Intel X25-M 80 GB Postville’s performance on the 8371 &#171; Information Overload</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-3048</link>
		<dc:creator>Testing the Intel X25-M 80 GB Postville’s performance on the 8371 &#171; Information Overload</dc:creator>
		<pubDate>Fri, 12 Feb 2010 11:36:17 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-3048</guid>
		<description>[...] 12 February 2010: the following results were achieved with the ext3 file system, using the noatime option. Contrary to my expectations it’s not better, but sucks [...]</description>
		<content:encoded><![CDATA[<p>[...] 12 February 2010: the following results were achieved with the ext3 file system, using the noatime option. Contrary to my expectations it’s not better, but sucks [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Carlos Mafra</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2972</link>
		<dc:creator>Carlos Mafra</dc:creator>
		<pubDate>Sun, 24 Jan 2010 16:41:34 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2972</guid>
		<description>Ah, I&#039;ve just found the answer to my question in #74!

dumpe2fs /dev/sda2 &#124;grep Lifetime</description>
		<content:encoded><![CDATA[<p>Ah, I&#8217;ve just found the answer to my question in #74!</p>
<p>dumpe2fs /dev/sda2 |grep Lifetime</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Carlos Mafra</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2891</link>
		<dc:creator>Carlos Mafra</dc:creator>
		<pubDate>Fri, 15 Jan 2010 10:52:53 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2891</guid>
		<description>Hi Ted, 
How do you use the ext4 information about the lifetime write in practice?
I&#039;ve seen your kernel commit:

commit afc32f7ee9febc020c73da61402351d4c90437f3
Author: Theodore Ts&#039;o 
Date:   Sat Feb 28 19:39:58 2009 -0500

    ext4: Track lifetime disk writes
    
    Add a new superblock value which tracks the lifetime amount of writes
    to the filesystem.  This is useful in estimating the amount of wear on
    solid state drives (SSD&#039;s) caused by writes to the filesystem.

but I don&#039;t know how I can actually see that information? Does it appear
in the output of some tool made for ext4?</description>
		<content:encoded><![CDATA[<p>Hi Ted,<br />
How do you use the ext4 information about the lifetime write in practice?<br />
I&#8217;ve seen your kernel commit:</p>
<p>commit afc32f7ee9febc020c73da61402351d4c90437f3<br />
Author: Theodore Ts&#8217;o<br />
Date:   Sat Feb 28 19:39:58 2009 -0500</p>
<p>    ext4: Track lifetime disk writes</p>
<p>    Add a new superblock value which tracks the lifetime amount of writes<br />
    to the filesystem.  This is useful in estimating the amount of wear on<br />
    solid state drives (SSD&#8217;s) caused by writes to the filesystem.</p>
<p>but I don&#8217;t know how I can actually see that information? Does it appear<br />
in the output of some tool made for ext4?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: tytso</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2855</link>
		<dc:creator>tytso</dc:creator>
		<pubDate>Sun, 03 Jan 2010 12:46:54 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2855</guid>
		<description>I should add that if you have a larger laptop, such as Lenovo Thinkpad T series, you can use two drives.  A 40GB or 80GB SSD drive where you have your OS and your home directory, and a 500GB 5400rpm hard drive where you have your build directories, music, images, etc.   That&#039;s what I do these days... the source tree is on the SSD for speed, but the build trees where the compiler deposits the object files is on a 500GB disk.  That way I get the best of both worlds.   I use the SSD for frequently accessed files or files where fast access will improve the &quot;feel&quot; of my system, and I use the hard drive for bulk storage, and writes which if slower (such as writing object files) won&#039;t hinder the overall speed of my system.

This is also very easy to do for a desktop, of course --- although these days I generally use my laptop instead of a desktop.</description>
		<content:encoded><![CDATA[<p>I should add that if you have a larger laptop, such as Lenovo Thinkpad T series, you can use two drives.  A 40GB or 80GB SSD drive where you have your OS and your home directory, and a 500GB 5400rpm hard drive where you have your build directories, music, images, etc.   That&#8217;s what I do these days&#8230; the source tree is on the SSD for speed, but the build trees where the compiler deposits the object files is on a 500GB disk.  That way I get the best of both worlds.   I use the SSD for frequently accessed files or files where fast access will improve the &#8220;feel&#8221; of my system, and I use the hard drive for bulk storage, and writes which if slower (such as writing object files) won&#8217;t hinder the overall speed of my system.</p>
<p>This is also very easy to do for a desktop, of course &#8212; although these days I generally use my laptop instead of a desktop.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: tytso</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2854</link>
		<dc:creator>tytso</dc:creator>
		<pubDate>Sun, 03 Jan 2010 12:42:39 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2854</guid>
		<description>@69: Wil,

Sorry, I missed the Z-P230 reference.  I must have been reading your post too quickly, and I probably mistook it for an Atom CPU part number....   My bad.  Yeah, as far as I can tell that Intel SSD was something cheap cheap cheap that was intended for sale directly to netbook manufacturers.   It has since disappeared without a trace.

Note BTW, that if price is an issue and you don&#039;t need that much capacity (how much do you need for a netbook or even a laptop if most of your software is on the cloud?  I need 80GB because I&#039;m a developer; if I nuked all of the source trees I could probably live with 40GB) you can also get a 40GB Kingston SSDNow V SSD which uses the Intel controller, but with half the flash channels.  You have to be careful though; the 64G and 128G Kinginston SSDNow V use the JMicron controller.  (V stands for value, which can sometimes also be another way of saying, buyer needs to be careful.  :-)

With OCZ, yes, you have to be careful.   They produce a large number of devices at different price points, and clearly at different levels of quality.</description>
		<content:encoded><![CDATA[<p>@69: Wil,</p>
<p>Sorry, I missed the Z-P230 reference.  I must have been reading your post too quickly, and I probably mistook it for an Atom CPU part number&#8230;.   My bad.  Yeah, as far as I can tell that Intel SSD was something cheap cheap cheap that was intended for sale directly to netbook manufacturers.   It has since disappeared without a trace.</p>
<p>Note BTW, that if price is an issue and you don&#8217;t need that much capacity (how much do you need for a netbook or even a laptop if most of your software is on the cloud?  I need 80GB because I&#8217;m a developer; if I nuked all of the source trees I could probably live with 40GB) you can also get a 40GB Kingston SSDNow V SSD which uses the Intel controller, but with half the flash channels.  You have to be careful though; the 64G and 128G Kinginston SSDNow V use the JMicron controller.  (V stands for value, which can sometimes also be another way of saying, buyer needs to be careful.  <img src='http://thunk.org/tytso/blog/wp-includes/images/smilies/icon_smile.gif' alt=':-)' class='wp-smiley' /> </p>
<p>With OCZ, yes, you have to be careful.   They produce a large number of devices at different price points, and clearly at different levels of quality.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Wil Barath</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2853</link>
		<dc:creator>Wil Barath</dc:creator>
		<pubDate>Sun, 03 Jan 2010 07:11:27 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2853</guid>
		<description>@69: I was comparing the Intel Z-P230 to an SD card.  They have very similar performance characteristics, in fact a high-end SD card outperforms the Intel SSD in all but max linear read, and even then by &lt;10%.  Pretty sad.</description>
		<content:encoded><![CDATA[<p>@69: I was comparing the Intel Z-P230 to an SD card.  They have very similar performance characteristics, in fact a high-end SD card outperforms the Intel SSD in all but max linear read, and even then by &lt;10%.  Pretty sad.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Wil Barath</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2852</link>
		<dc:creator>Wil Barath</dc:creator>
		<pubDate>Sun, 03 Jan 2010 07:06:53 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2852</guid>
		<description>That X25-M SSDSA2MH160G2R5 part is looking pretty inviting.  There&#039;s an OCZ part that&#039;s a little cheaper, faster, smaller.  

Really, if you have a laptop in the $1000+ range, what can anyone add to it that will improve the overall performance as much for the money as putting one of the above SSDs into it?  

I&#039;m sure the manufacturers know this, but it&#039;s hard to sell 1/10th the storage for the same money, regardless of the performance.

There&#039;s still the question of reliability.  Both Intel and OCZ state &quot;1.5M hours MTBF&quot; then offer a 1 or 2 year warranty.  Hello?  1.5M hours is 171 years!  If there&#039;s a shred of honesty behind their statements then they would back them with lifetime unrated replacement warranties.  So take both with a sack of salt.

I&#039;ll leave checking OCZ&#039;s track record on SSD parts as an exercise for the reader.  Spending that much money without doing research is something I would never encourage anyone to do.  BTW, that was a subtle hint to check OCZ&#039;s track record before buying their parts...</description>
		<content:encoded><![CDATA[<p>That X25-M SSDSA2MH160G2R5 part is looking pretty inviting.  There&#8217;s an OCZ part that&#8217;s a little cheaper, faster, smaller.  </p>
<p>Really, if you have a laptop in the $1000+ range, what can anyone add to it that will improve the overall performance as much for the money as putting one of the above SSDs into it?  </p>
<p>I&#8217;m sure the manufacturers know this, but it&#8217;s hard to sell 1/10th the storage for the same money, regardless of the performance.</p>
<p>There&#8217;s still the question of reliability.  Both Intel and OCZ state &#8220;1.5M hours MTBF&#8221; then offer a 1 or 2 year warranty.  Hello?  1.5M hours is 171 years!  If there&#8217;s a shred of honesty behind their statements then they would back them with lifetime unrated replacement warranties.  So take both with a sack of salt.</p>
<p>I&#8217;ll leave checking OCZ&#8217;s track record on SSD parts as an exercise for the reader.  Spending that much money without doing research is something I would never encourage anyone to do.  BTW, that was a subtle hint to check OCZ&#8217;s track record before buying their parts&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: tytso</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2851</link>
		<dc:creator>tytso</dc:creator>
		<pubDate>Sun, 03 Jan 2010 03:07:32 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2851</guid>
		<description>@68: Wil,

It wasn&#039;t clear to me you understood that the X25-M is fast, if you&#039;re comparing it to a SD card.  :-(

The Fusion IOXtreme drive is fast, yes, but it&#039;s also about 4 times the cost of an X25-M drive, and you can&#039;t boot off of one, and it won&#039;t fit in an laptop.  But sure, if you have a PCIE card, and you can afford it, and you need its speed, then it&#039;s a good choice.

The trick with using Iometer under Linux is apparently to put the options in the configuration file, but it&#039;s not at all well documented, and I don&#039;t have time to try to figure out the the config file from the sources --- but iometer is open source, so hopefully someone will get around to fixing it up and documenting it better for operation under Linux.</description>
		<content:encoded><![CDATA[<p>@68: Wil,</p>
<p>It wasn&#8217;t clear to me you understood that the X25-M is fast, if you&#8217;re comparing it to a SD card.  <img src='http://thunk.org/tytso/blog/wp-includes/images/smilies/icon_sad.gif' alt=':-(' class='wp-smiley' /> </p>
<p>The Fusion IOXtreme drive is fast, yes, but it&#8217;s also about 4 times the cost of an X25-M drive, and you can&#8217;t boot off of one, and it won&#8217;t fit in an laptop.  But sure, if you have a PCIE card, and you can afford it, and you need its speed, then it&#8217;s a good choice.</p>
<p>The trick with using Iometer under Linux is apparently to put the options in the configuration file, but it&#8217;s not at all well documented, and I don&#8217;t have time to try to figure out the the config file from the sources &#8212; but iometer is open source, so hopefully someone will get around to fixing it up and documenting it better for operation under Linux.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Wil Barath</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2850</link>
		<dc:creator>Wil Barath</dc:creator>
		<pubDate>Sat, 02 Jan 2010 22:52:37 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2850</guid>
		<description>hehe, yes, I know the X25 is fast.  I have been following it, the OCZ Vertex series, and some other pretenders.

The SuperTalent FusionIO PCIE 8x card, blows away all the SSD competition. It&#039;s not really an SSD - it&#039;s more like a NAND memory expansion with up to 2TB of address space.  It beats the X25m by a factor of 25 or more on random 4k block writes (off the top of my head.)

Having no Windows platform to run iometer on, and with the Linux binary having no command-line options to directly run tests (that I can find), also the documentation for the latest version of IoMeter currently dumping Perl code instead of running the script on the IoMeter website, I&#039;m afraid I&#039;m not going to get any mileage out of that app...

http://www.iometer.org/cgi-bin/jump.cgi?URL=http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/*checkout*/iometer/iometer/Docs/Iometer.pdf?rev=HEAD</description>
		<content:encoded><![CDATA[<p>hehe, yes, I know the X25 is fast.  I have been following it, the OCZ Vertex series, and some other pretenders.</p>
<p>The SuperTalent FusionIO PCIE 8x card, blows away all the SSD competition. It&#8217;s not really an SSD &#8211; it&#8217;s more like a NAND memory expansion with up to 2TB of address space.  It beats the X25m by a factor of 25 or more on random 4k block writes (off the top of my head.)</p>
<p>Having no Windows platform to run iometer on, and with the Linux binary having no command-line options to directly run tests (that I can find), also the documentation for the latest version of IoMeter currently dumping Perl code instead of running the script on the IoMeter website, I&#8217;m afraid I&#8217;m not going to get any mileage out of that app&#8230;</p>
<p><a href="http://www.iometer.org/cgi-bin/jump.cgi?URL=http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/" rel="nofollow">http://www.iometer.org/cgi-bin/jump.cgi?URL=http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/</a>*checkout*/iometer/iometer/Docs/Iometer.pdf?rev=HEAD</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: tytso</title>
		<link>http://thunk.org/tytso/blog/2009/03/01/ssds-journaling-and-noatimerelatime/comment-page-2/#comment-2849</link>
		<dc:creator>tytso</dc:creator>
		<pubDate>Sat, 02 Jan 2010 21:37:48 +0000</pubDate>
		<guid isPermaLink="false">http://thunk.org/tytso/blog/?p=328#comment-2849</guid>
		<description>Oops, the link to the X25-M product manual got filtered out.  Here it is:

http://download.intel.com/support/ssdc/hpssd/x25m/sb/x18mx25msatassdproductmanual34nm322296.pdf</description>
		<content:encoded><![CDATA[<p>Oops, the link to the X25-M product manual got filtered out.  Here it is:</p>
<p><a href="http://download.intel.com/support/ssdc/hpssd/x25m/sb/x18mx25msatassdproductmanual34nm322296.pdf" rel="nofollow">http://download.intel.com/support/ssdc/hpssd/x25m/sb/x18mx25msatassdproductmanual34nm322296.pdf</a></p>
]]></content:encoded>
	</item>
</channel>
</rss>

<!-- Dynamic Page Served (once) in 0.419 seconds -->
<!-- Cached page served by WP-Cache -->
