<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: 2x 80Gb X25-M G2 - To RAID or not to RAID... in Archive</title>
    <link>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4781#M4643</link>
    <description>&lt;P&gt;As ambizytl states the real question is do you notice a difference? Below are AS SSD Benchmarks from a single drive and a raid 0 array.&lt;/P&gt;&lt;P&gt; &lt;/P&gt;&lt;P&gt;Notice the 4k (QD1) results don't improve with raid 0? If I was getting any benefit from running two drives in raid 0 I would not have switched to a single drive.  Some people will swear that raid 0 is much faster but from my experience at least it did nothing apart from inflate benchmark scores.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Let us know what your verdict is. &lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;X25-E x 2 ICH9r Raid 0 128k stripe&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;X25-M 160GB ICH9&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;</description>
    <pubDate>Wed, 17 Mar 2010 19:08:14 GMT</pubDate>
    <dc:creator>idata</dc:creator>
    <dc:date>2010-03-17T19:08:14Z</dc:date>
    <item>
      <title>2x 80Gb X25-M G2 - To RAID or not to RAID...</title>
      <link>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4776#M4638</link>
      <description>&lt;P&gt;Hello all,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I am relatively new to the forum and have read a lot of the posts, and they are quite informative.  I have 2 x 80GB X25-M Gen2 drives.  I am currently running them in RAID0 (hardware RAID).&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;After doing some reading in the forums, I understand that TRIM is not supported via RAID as it would require my RAID controller to support command passthrough - which none do currently (I have an EVGA x58 SLI Micro mobo - using the onboard controller).&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I don't have a problem running the drives as two distinct 80GB drives and in turn gaining TRIM support.  But my understanding is that RAID0 is a decent speed improvement even with SSD drives.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;My use is primarily gaming and working with Photoshop type applications.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;So I have a question, TRIM vs RAID0, which is better for overall performance?&lt;/P&gt;</description>
      <pubDate>Tue, 16 Mar 2010 14:10:18 GMT</pubDate>
      <guid>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4776#M4638</guid>
      <dc:creator>idata</dc:creator>
      <dc:date>2010-03-16T14:10:18Z</dc:date>
    </item>
    <item>
      <title>Re: 2x 80Gb X25-M G2 - To RAID or not to RAID...</title>
      <link>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4777#M4639</link>
      <description>&lt;P&gt;Raid 0 does not help random read/ writes speeds at low queue depths and it adds latency on a hard raid array. &lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;A lot of people think they are power users and therefore the queue depth will be high however even a power user is still only one person making demands on the storage system, which is very different to multiple people making simultaneous demands in a server environment. &lt;/P&gt;&lt;P&gt;People also forget that access time is so low with SSD's that the queue depth is kept lower than would be the case for a hard drive. &lt;/P&gt;&lt;P&gt;If you monitor your queue depth you will most like see that you queue depth does not go above one and if it does it only does it very briefly.&lt;/P&gt;&lt;P&gt;With regards to sequential speeds raid will improve performance, however most operations are random reads so this will only be a benefit in very specific circumstances. &lt;/P&gt;&lt;P&gt;I've had a soft and hard raid 0 set up with 2 x X25-E's and a single G2 set up. I can't tell the difference between those set ups with my usage patterns, which does not sound much different to what you describe. &lt;/P&gt;&lt;P&gt;Bottom line – unless you have a very specific requirement raid 0 is not going to make things any faster. Add to that the loss of TRIM and the higher risk of data loss with raid 0……&lt;/P&gt;</description>
      <pubDate>Tue, 16 Mar 2010 15:22:54 GMT</pubDate>
      <guid>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4777#M4639</guid>
      <dc:creator>idata</dc:creator>
      <dc:date>2010-03-16T15:22:54Z</dc:date>
    </item>
    <item>
      <title>Re: 2x 80Gb X25-M G2 - To RAID or not to RAID...</title>
      <link>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4778#M4640</link>
      <description>&lt;P&gt;Thanks for the quick and very detailed and easy to understand response.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;You indicate with a usage similar to mine - the RAID0 performance gain doesn't really offset the integrity offered via TRIM.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I will post my RAID performance figures and after un-RAIDing, the single disk performance.&lt;/P&gt;</description>
      <pubDate>Tue, 16 Mar 2010 16:18:13 GMT</pubDate>
      <guid>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4778#M4640</guid>
      <dc:creator>idata</dc:creator>
      <dc:date>2010-03-16T16:18:13Z</dc:date>
    </item>
    <item>
      <title>Re: 2x 80Gb X25-M G2 - To RAID or not to RAID...</title>
      <link>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4779#M4641</link>
      <description>&lt;P&gt;redux wrote:&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;...&lt;/P&gt;&lt;P&gt;With regards to sequential speeds raid will improve performance, however most operations are random reads so this will only be a benefit in very specific circumstances.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Bottom line – unless you have a very specific requirement raid 0 is not going to make things any faster. Add to that the loss of TRIM and the higher risk of data loss with raid 0……&lt;/P&gt;&lt;P&gt;Hi Redux, so I un-RAIDed my drives and run them separately now.  Running the same driver set, here are the performance differences according to CrystalDiskMark.  The benchmarks are substantially different, even for random @ almost 2x.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;B&gt;RST - RAID0&lt;/B&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;--------------------------------------------------&lt;/P&gt;&lt;P&gt;CrystalDiskMark 2.2 (C) 2007-2008 hiyohiyo&lt;/P&gt;&lt;P&gt;      Crystal Dew World : &lt;A href="http://crystalmark.info/" rel="nofollow noopener noreferrer"&gt;http://crystalmark.info/&lt;/A&gt;&lt;/P&gt;&lt;P&gt;--------------------------------------------------&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;   Sequential Read : 601.346 MB/s&lt;/P&gt;&lt;P&gt;  Sequential Write :  170.583 MB/s&lt;/P&gt;&lt;P&gt;Random Read 512KB :  392.803 MB/s&lt;/P&gt;&lt;P&gt;Random Write 512KB :  194.468 MB/s&lt;/P&gt;&lt;P&gt;   Random Read 4KB :   22.136 MB/s&lt;/P&gt;&lt;P&gt;  Random Write 4KB :  160.312 MB/s&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;         Test Size : 100 MB&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;B&gt;RST - NON-RAID&lt;/B&gt;&lt;/P&gt;&lt;P&gt;--------------------------------------------------&lt;/P&gt;&lt;P&gt;CrystalDiskMark 2.2 (C) 2007-2008 hiyohiyo&lt;/P&gt;&lt;P&gt;      Crystal Dew World : &lt;A href="http://crystalmark.info/" rel="nofollow noopener noreferrer"&gt;http://crystalmark.info/&lt;/A&gt;&lt;/P&gt;&lt;P&gt;--------------------------------------------------&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;   Sequential Read :  260.926 MB/s&lt;/P&gt;&lt;P&gt;  Sequential Write :   87.771 MB/s&lt;/P&gt;&lt;P&gt; Random Read 512KB :  193.150 MB/s&lt;/P&gt;&lt;P&gt;Random Write 512KB :   85.668 MB/s&lt;/P&gt;&lt;P&gt;   Random Read 4KB :   22.554 MB/s&lt;/P&gt;&lt;P&gt;  Random Write 4KB :   57.624 MB/s&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;         Test Size : 100 MB&lt;/P&gt;</description>
      <pubDate>Wed, 17 Mar 2010 13:52:01 GMT</pubDate>
      <guid>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4779#M4641</guid>
      <dc:creator>idata</dc:creator>
      <dc:date>2010-03-17T13:52:01Z</dc:date>
    </item>
    <item>
      <title>Re: 2x 80Gb X25-M G2 - To RAID or not to RAID...</title>
      <link>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4780#M4642</link>
      <description>&lt;P&gt;Running RAID0 is great for people who love to look at benchmark results. The question is how much of a difference do you see in your computer operation? The other question is is it worth the risk? Personally, I prefer to use my other 160GB SSD to periodically create a system image in case of disaster. What do you have in case of disaster? I don't enjoy spending lots of time reinstalling Windows along with all my programs, data, etc.&lt;/P&gt;</description>
      <pubDate>Wed, 17 Mar 2010 14:49:03 GMT</pubDate>
      <guid>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4780#M4642</guid>
      <dc:creator>idata</dc:creator>
      <dc:date>2010-03-17T14:49:03Z</dc:date>
    </item>
    <item>
      <title>Re: 2x 80Gb X25-M G2 - To RAID or not to RAID...</title>
      <link>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4781#M4643</link>
      <description>&lt;P&gt;As ambizytl states the real question is do you notice a difference? Below are AS SSD Benchmarks from a single drive and a raid 0 array.&lt;/P&gt;&lt;P&gt; &lt;/P&gt;&lt;P&gt;Notice the 4k (QD1) results don't improve with raid 0? If I was getting any benefit from running two drives in raid 0 I would not have switched to a single drive.  Some people will swear that raid 0 is much faster but from my experience at least it did nothing apart from inflate benchmark scores.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Let us know what your verdict is. &lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;X25-E x 2 ICH9r Raid 0 128k stripe&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;X25-M 160GB ICH9&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;</description>
      <pubDate>Wed, 17 Mar 2010 19:08:14 GMT</pubDate>
      <guid>https://community.solidigm.com/t5/archive/2x-80gb-x25-m-g2-to-raid-or-not-to-raid/m-p/4781#M4643</guid>
      <dc:creator>idata</dc:creator>
      <dc:date>2010-03-17T19:08:14Z</dc:date>
    </item>
  </channel>
</rss>

