The SSD Update: Vertex Gets Faster, New Indilinx Drives and Intel/MacBook Problems Resolved

73 Comments

View All Comments

• samsonite101 - Friday, April 10, 2009 - link

  I DO commend you for all this research you've been doing, and your articles are full of some very informative information, and I also appreciate the comments section here where people can post their opinions as well, as I find that it is nice to see more opinions from people and other professionals who can also share their knowledge and expertise into the collective.
  
  The only problem I have is how, in most of your SSD comparisons, you seem to compare apples with oranges a lot regarding the differences between SLC and MLC drives. It is a known factor, that MLC can only endure 10,000 writes per cell. And SLC can handle x10 of that. This is not some small amount. This is a significant difference. Not worth throwing aside. When I read your articles and they repeatedly profess that the Intel X-whatever-it-was drive is cream-of-the-crop holy-grail of all things, it just makes me wonder if you could be receiving payoffs from Intel to say such things. I can see where in the performance arena, it looks as though the popular Intel drive shines, but cost-wise, it does not, and reliability-wise, I don't see how any MLC drive can stand up to an SLC drive, period. Unless of course you could explain to me how this would be possible. I DO love Intel-based products, as I have built many servers using pure Intel parts, and I have a high regard for Intel for building reliable servers, but I just can't get past the whole MLC / SLC thing when it comes to reliability. For me, reliability is very important, as well as performance. I continually hear little remarks stating that the Samsungs just don't measure up, performance-wise, but you never mention much about the lifespan/endurance of SLC. At least I've never heard much mentioned about it. How about an article to compare various SSD drive's endurances and lifespans? If speed is the builder's main issue, then why not use top-performing, reliable SLC SSD pairs in RAID 0 or multiple SSD drives in RAID 5 or other configurations to get your speed, and reliability in one package? I just don't see how 10,000 writes of MLC is cream-of-the-crop, when the Samsung (for example) SLC drive is rated at 2,000,000 MTBF (that is much more than even a typical server-grade HDD which is typically around 1.2 million hours MTBF). Also, the last Samsung drive I bought only cost $175 bucks, and last I checked, the Intel one is around twice that. For the cheaper cost of a Samsung or similar SLC, and the proven reliability of one of them, you COULD actually run them in RAID (Redundant Array of INEXPENSIVE Drives) configurations and have the best of all worlds, plus get your big size back that MLC's typically brag about. Imagine a RAID 5 array with a fast controller and perhaps 5-10 SLC Samsung or similar drives. When they DO slow down after becoming well-used, they still are faster than HDD. So what's the big problem? I would just like to see more talk about the other factors that may influence a buyer to drift toward SLC or MLC. That is my main point. Sorry for the long rant, and I will accept all bashes. Thx
  
  Maybe you can shed some light on these issues I have, but I would say, that it might be helpful if when you post articles about SSD drives, you should also conduct more comparisons reflecting the SLC/MLC related differences, and more comparisons which test reliability, and lifespan, in addition to performance. The reader needs to know about these things as well, in order to make an informed decision on which drive he may want to buy.
  
  By the way, I am just writing this comment as an enthusiast. I am not a rep of any company that cares about SSD. These are just my personal opinions.

• anactoraaron - Thursday, June 25, 2009 - link

  You obviously did not read the first review. All of this was explained in great detail- including how nand flash works. Look up the initial review.

• Patanjali - Wednesday, April 15, 2009 - link

  As I understand it, if there is a good amount of spare space on the MLC SSD (that is, compared to the amount of the drive actually being rewritten to regularly), the wear-levelling routines will prevent the block write limitation of MLCs ever being an issue (other than a possible gradual reduction in capacity). Only if the drive is full enough to run out of blocks that can be swapped in to write to, will reliability be affected.
  
  Some servers may just tip the scales. Most consumer use would have the majority of drive space being write occasionaly, read mostly, with a few small areas getting higher write traffic that would easily be compensated for by having a few spare GB.
  
  However, I wonder if the wear-levelling routines might be contributing to the observed slowdown, perhaps due to the need to consult ever-growing usage-mapping tables that are themselves subject to wear-levelling. It depends how invasive the wear-levelling code is within the write code.

• LinkerX - Thursday, April 9, 2009 - link

  It would be nice if there was an updated review with firmware 1.1 and the supertalent drives. Also Anandtech should go into the bootcamp issues a bit more with mac.

• sotoa - Monday, April 6, 2009 - link

  Another great article to put things in perspective. I'm enjoying the tales of the SSD's. I'm hooked!

• MadBoris - Sunday, April 5, 2009 - link

  Anand, if at all possible try and mix in the recent Samsung 256GB SSD with it's new controller into your testing to see how it compares. While it isn't in the retail channel it is coming down through OEM's and folks buying new laptops are provided the option (like Dell and the 256GB SSD, etc.). So many of us making laptop purchases would benefit from seeing how this great bargain compares.
  
  I'm not paying more for a high end retail SSD than the actual laptop, but I would consider get an inexpensive high end SSD with more storage as an add on for half the price of it's retail counterparts.
  
  For a long time SSD's just had too many compromises, today for a laptop they are starting to make sense if one is willing to pay a little extra, but $800 is too much extra for a 160GB x-25M when a Samsung 256GB SSD is less than half the price on a new laptop purchase.
  
  So it looks like Intel will fix the x-25m issues with a new firmware, no doubt other mfr's can do the same over time.

• doclucas - Sunday, April 5, 2009 - link

  Yes, I keep checking AnandTech every day in hope to see a review and/or a comparison to the very interesting new 256GB Samsung PB22-J (MMDOE56G5MXP-0VB) with stated R/W speeds of 220MBps/200MBps respectively. It can be purchased in a very attractive price via OEM channels.
  I am sure most of the SSD articles' readers would be more than happy to have this information here, Anand.
  
  btw, thanks for the excellent SSD articles posted to date.

• LinkerX - Saturday, April 4, 2009 - link

  I have been using my vertex for a few days now and it is an amazing drive, but they need to fix the boot camp issues asap.

• geok1ng - Thursday, April 2, 2009 - link

  Not only AT saved my hard earned money by showing the problems with the Jmicrons SSDs- i was about to pull the triger over the OCZ Core SSD, but the last article closed the deal on the OCZ Vertex. Anandtech has been my favorite hardware site for the last 3 years but my respect has gone skyhigh with the SSDs series of articles. It is not about making good reviews for the company that pays the most, it is about writing reviews that force the companies to offer a better product.

• 7Enigma - Wednesday, April 1, 2009 - link

  This new firmware looks incredible!
  
  But I am left dumbfounded by OCZ's decision to share the firmware with competitors. Sure in a perfect world it is nice and snuggl-ly, but they have to be losing market-share, if not now once other manufacturers begin selling competing products. I'm glad they did it for competition (and thus cheaper prices for us consumers) but I just see it as a relatively stupid business move...