Sign in with
Sign up | Sign in

Conclusion

SSD RAID: Do You Want A Cheap Array Or One Larger Drive?
By

This article aims at enthusiasts who want to maximize storage performance and those who want to know how to best spend their money: by either purchasing a single SSD or by going with a couple of low-budget, low-capacity solid state drives. Since most retail motherboards come with RAID functionality built-in, it makes sense to put an inexpensive SSD-based RAID array up against one powerful SSD. However, we found that this makes only limited sense. Let’s look at some details.

Zalman’s entry into the SSD segment is successful. The N-series SSD is based on the SandForce SF-1220 controller, which currently is one of the best architectures available. Companies like Adata, Corsair, G.Skill, and OCZ all offer solid state drives based on this platform, and they all deliver comparable performance and efficiency. The throughput of Zalman’s SSD0128N1 is at the top end of the SATA 3Gb/s range. PCMark Vantage storage application performance is nice as well, and the I/O performance of all SandForce SF-1200 SSDs is as high as it can be. Once again, we can only recommend looking at prices and warranty, as the performance differences between several SandForce products are too small to be turned into purchase criteria. The bottom line is that the Zalman N-series SSD is a great product.

Now let’s take a look at the SSD RAID performance results, as these aren’t as clear. First of all, we need to repeat that Kingston’s SSDNow V 30 GB drives are being replaced by the V100-series, employing a JMF-618 controller by JMicron. This means that the 30 GB capacity will be gone soon. But it could also represent an opportunity if stores want to clear their inventory. However, the SSDNow V 30 GB isn’t a great performer when it comes to I/O performance or write throughput. This is because of the Toshiba controller, which just isn’t very strong, and can only convince in sequential read testing.

Yet, two or even four of these entry-level drives will boost performance levels quite a bit. We found that throughput increases way over 600 MB/s and that write performance is much more consistent on RAID setups than it is on an individual drive. While almost all results benefit from utilizing two or even four drives in RAID 0, the RAID setups still cannot make up for the weaknesses of the aged Toshiba controller. Throughput is stellar; everything else is not.

Users who primarily want sequential throughput can of course consider an SSD RAID array. But for everyone else, we recommend investing in a single more enthusiast-oriented SSD for similar money. We did not only come to this conclusion because of the ambivalent performance results, but also because of the potential trouble you can run into if a RAID 0 array should ever fail. Since your entire array is lost if only one drive fails, we recommend staying away from such configurations unless really necessary for performance reasons--and back your data up regularly. The results would change if you were to use faster products for such an array, but then cost would increase quite a bit.

We didn’t measure power consumption or efficiency, because these items are mostly negligible if you aim at maximizing storage performance. Efficient SSDs require only 2-3 W at peak load situations, and using up to four would result in 10-15 W maximum power consumption based on modern drives. Have a look at our last SSD roundup for power consumption details. Zalman’s N-series is as power efficient as other SandForce drives, and the Kingston SSDNow V 30 GB is similarly low because it runs fewer flash memory channels.

We'll also dive into the implications of using an SSD-based RAID array on TRIM support in an upcoming story, so stay tuned!

Ask a Category Expert

Create a new thread in the Reviews comments forum about this subject

Example: Notebook, Android, SSD hard drive

Display all 56 comments.
This thread is closed for comments
Top Comments
  • 21 Hide
    Anonymous , December 3, 2010 4:31 AM
    How about a simple comparison of 2 of the smaller sandforce drives 2x60GB in raid vs one 120GB drive? There should be not much difference in price, which i assume people will pay (me included) if there is enough performance improvement. I see no point in comparing raid arrays of such low performing and phased out drives.
  • 20 Hide
    rossward , December 3, 2010 3:58 AM
    Why would you pick such inferior drive in the RAID array for this test? $150 for two 30GB drives isn't saving you any money. Why not get two of the Zalman N Series SSD0064N1 for $129 at a website I could name? You'd get MORE storage for LESS money. You'd also have a far superior controller in a two drive array. THAT is the best setup.
Other Comments
  • 0 Hide
    TheRockMonsi , December 3, 2010 3:18 AM
    Nice read. I didn't even consider this when looking at SSD's but I'm glad you shined some light on this. I guess for gaming it's best to go with one bigger SSD. Thanks for the article. :) 
  • 20 Hide
    rossward , December 3, 2010 3:58 AM
    Why would you pick such inferior drive in the RAID array for this test? $150 for two 30GB drives isn't saving you any money. Why not get two of the Zalman N Series SSD0064N1 for $129 at a website I could name? You'd get MORE storage for LESS money. You'd also have a far superior controller in a two drive array. THAT is the best setup.
  • 0 Hide
    juncture , December 3, 2010 4:14 AM
    rosswardWhy not get two of the Zalman N Series SSD0064N1 for $129 at a website I could name?

    Please tell me of this website! I can only find one of those SSD's for that price...

    On another note, after reading this article I think I made up my mind in a future build to have SSDs in raid for my OS and games paired with three 320gb HDDs I already own for more storage and backup. I am particularly interested in the read speeds more than anything.
  • 21 Hide
    Anonymous , December 3, 2010 4:31 AM
    How about a simple comparison of 2 of the smaller sandforce drives 2x60GB in raid vs one 120GB drive? There should be not much difference in price, which i assume people will pay (me included) if there is enough performance improvement. I see no point in comparing raid arrays of such low performing and phased out drives.
  • 8 Hide
    cangelini , December 3, 2010 4:49 AM
    EdisonmkHow about a simple comparison of 2 of the smaller sandforce drives 2x60GB in raid vs one 120GB drive? There should be not much difference in price, which i assume people will pay (me included) if there is enough performance improvement. I see no point in comparing raid arrays of such low performing and phased out drives.


    This is coming Edisonmk, just an FYI. In the same piece I'll also be comparing the dual-controller RevoDrive and quad-controller RevoDrive X2 (along with Intel's X25-M and OCZ's IBIS).

    Chris
  • 5 Hide
    physical , December 3, 2010 4:50 AM
    I agree... Apples to Oranges comparison isn't the best way to go forward with this.

    Pick a manufacturer, and a specific line of drives by that manufacturer, pick 4 low cap drives, 2 med cap drives, 1 high cap drive. Compare them! The final drive in these tests should be approx the same size.

    Test on all metrics per usual. Compare/Contrast results and provide Price/Performance analysis.
  • -4 Hide
    r_pad , December 3, 2010 5:13 AM
    I'd like to see the benchmarks on two 128GB Crucial RealSSD C300 in RAID 1.
  • 6 Hide
    DavC , December 3, 2010 5:57 AM
    r_padI'd like to see the benchmarks on two 128GB Crucial RealSSD C300 in RAID 1.

    in RAID1, i imagine the performance would be almost as good as a single 128GB Crucial RealSSD C300
  • 0 Hide
    knowom , December 3, 2010 9:18 AM
    I think raiding these would be nice and worth doing honestly most people looking for a SSD want them for the access time and sequential reads when it comes down to it and even the writes aren't horrendous for the S100 series I imagine in 2+ raid array setup they'd be very reasonable.

    http://www.newegg.com/Product/Product.aspx?Item=N82E16820139428
  • 4 Hide
    GullLars , December 3, 2010 10:58 AM
    Interresting test, but the comparisons are like comparing 4 paintball guns mounted on a stick with a common trigger to an AK-47.
    Redo the test with 1, 2, 3, and 4 SSD at 32 or 64GB compared against an SSD at 256GB using the same controller, and ffs, use a controller that is modern.
    I suggest SandForce or C300.
    I'm currently on an SSD RAID of 4x C300 64GB running on AMD SB850. I have 1150MB/s sequential read, 280MB/s sequential write, 32MB/s 4KB random read @ QD 1 (8k IOPS), 80MB/s 4KB random write at QD 1 (20k IOPS), 400MB/s 4KB random read at QD 32 (100k IOPS, maxed out at 2 drives), and 270MB/s 4KB random write at QD 32.
  • -5 Hide
    opmopadop , December 3, 2010 11:32 AM
    4x SSD = 10 to 15 watt... When most video catds use 30 watts at idle, and capable of hiting over 200 watts, it kinda seems silly to think about a measly 10 to 15 watts of power for RAID storage.

    Then again... I do have 2 rooms in the house with LED lighting...
  • 0 Hide
    nforce4max , December 3, 2010 12:03 PM
    I have one of these 30gb SSD from this brand and my results were a little better in other test than what you have gotten but I didn't get it as a os drive but as a paging drive. Modern hard drives are far to slow when it comes to random 4k and it shows up in games that have a very large memory foot print like GTA IV.
  • 7 Hide
    Scotteq , December 3, 2010 12:49 PM
    What about TRIM???

    My understanding is that although it is possible to connect a single SSD to a RAID controller and use TRIM, it is *not* possible to use TRIM on an array.

    Has this changed??????

    If not, then your RAID array's performance will inevitably decrease over time. And I would opine that end users would be better off buying a newer/faster/larger single drive.
  • 0 Hide
    scook9 , December 3, 2010 1:06 PM
    Interesting article, the take away for me is this.....maybe I would enjoy getting a 2nd Intel X25-M G2 80GB drive and do a RAID 0 hehe
  • 2 Hide
    nevertell , December 3, 2010 1:12 PM
    I don't think soft raid is good if you want speed.
  • 2 Hide
    Aoster87 , December 3, 2010 1:40 PM
    ScotteqWhat about TRIM???My understanding is that although it is possible to connect a single SSD to a RAID controller and use TRIM, it is *not* possible to use TRIM on an array.Has this changed??????If not, then your RAID array's performance will inevitably decrease over time. And I would opine that end users would be better off buying a newer/faster/larger single drive.


    Clearly explained in the last statement of the article: We'll also dive into the implications of using an SSD-based RAID array on TRIM support in an upcoming story, so stay tuned!
  • 1 Hide
    MU_Engineer , December 3, 2010 1:46 PM
    Quote:
    How about a simple comparison of 2 of the smaller sandforce drives 2x60GB in raid vs one 120GB drive? There should be not much difference in price, which i assume people will pay (me included) if there is enough performance improvement. I see no point in comparing raid arrays of such low performing and phased out drives.


    I was wondering this all along. They should have used better small drives like OCZ's 40 GB Vertex2, which use the SF-1222 controller, instead of the Kingston units. The performance of the smaller SandForce-based drives is supposedly similar to their larger variants, so that would give you the best idea of RAID vs. one big drive.
  • 1 Hide
    GullLars , December 3, 2010 2:01 PM
    Scotteqyour RAID array's performance will inevitably decrease over time. And I would opine that end users would be better off buying a newer/faster/larger single drive.

    Actually, performance degrades only to a certain point, depending on your usage patterns, and affect only write performance. With the performance level of RAIDs of decent new SSDs, you wouldn't notice it, but could meassure it after heavy usage with a benchmark.
  • 1 Hide
    MU_Engineer , December 3, 2010 2:06 PM
    Quote:
    Actually, performance degrades only to a certain point, depending on your usage patterns, and affect only write performance. With the performance level of RAIDs of decent new SSDs, you wouldn't notice it, but could meassure it after heavy usage with a benchmark.


    And if you can do so, not having write-heavy things on your SSDs helps a lot too. If you're on a desktop, you probably have a mechanical HDD for data. Putting some of the write-heavy folders on the mechanical HDD will result in very few writes to the SSD. I did this with my two-drive SSD RAID and after two months of use, the SSDs still report less than 64 GB of writes as compared to half a terabyte of reads on each SSD.
Display more comments