My understanding of RAID 0 is that the data is split and striped across all of the drives in the array. If there is only one drive in the array, then what is the point of a single drive RAID 0 array and how does it work?

From these ceph benchmarks it appears there is a tangible performance difference as compared to JBOD in at least some cases.

Despite my best Googling I could not find anything substantial. Thanks!

  • The difference is whatever the particular implementation wants it to be. It can be everything or nothing. There's really no such thing as "single drive RAID 0", so a particular RAID implementation can mean anything by it. Jan 23, 2013 at 5:05

6 Answers 6


In the case of this implementation (the LSI SAS2208 controller), JBOD does not use on-board cache, single disk RAID0 uses on-board write-back cache. The ceph benchmark explains it in the test setup. The performance increase comes from caching not striping. Most RAID controllers allow you to setup single disk RAID0 or RAID1 as a way to support JBOD, this controller is a little different in that it also supports JBOD (without any controller cache).

There are cases where RAID levels can use less disks than you normally think, and still provide increased performance or redundancy. For example Linux md RAID10 can be used with two or more disks, including odd numbers of disks, unlike traditional RAID10 which would require four or more disks and even numbers. Linux md RAID10 with two disks is faster than RAID1.


RAID-0 on single disk is used mostly on SSD disks, which acts as Cache disk (Intel Smart Response). When you activate "accelerate mode" for any HDD or RAID Volume via SSD Cache, IRST driver converts disk to RAID-0 Volume. If you are not using whole disk space, there will be automatically created second RAID-0 Volume, which can be used for other data. My example:

enter image description here

I am not sure, why it has to be in RAID mode, as I see no benefit from it. Maybe for some specific operations there is minor boost.


Another aspect to consider, is for the purpose of performance testing new equipment before putting it into use.

For example, your goal is to benchmark just how much performance will be boosted by adding more stripes to a RAID0 configuration. You start with a 1-disk RAID0, test it, then move to a 2-disk, test it, and so on. Your test results should reveal what improvements you will gain, by adding stripes, on your actual hardware. This is a great thing to know beforehand, because you can't do this once your disks are in use!

A tip if you are trying this: When adding stripes for the next test iteration, just delete the whole virtual disk and start fresh! This is near instant, as opposed to adding another disk into an existing RAID0 vdisk. (The reconstruction time can be huge.)


It's also useful to mention here that some server configurations require you to load the RAID regardless of how many physical disks are actually present.

For example, a server chasis where you can only access the disks through a controller board.

In this scenario, RAID 0 is the default setup.

  • For me JBOD is the default. With RAID0 I might have to work harder to bring up the drive on another system.
    – chicks
    Jun 21, 2015 at 13:42

Although this post is old. I thought I'll add input on this question.

Single disk RAID 0 is possible and is in used. I see it all the time. Typically someone will set up a single disk RAID 0 if the only want one hard drive to be seen by the operating system without associating it into a larger RAID like 1, 5, 6 etc. Someone may want to use this tactic if their controller does not support JBOD or HBA modes. The RAID controller will simply stipe a RAID 0 header on one drive instead of a couple or several. Also note this may also go to RAID controller limitations, as some may require more than one drive.


There is no such thing as a single drive RAID 0 array. In order to setup a RAID 0 array, you would need two or more disks. I think you are mis-reading the test setup in the article you reference.

However, you are correct, in that in a RAID 0 array (note not RAID 0 mode) data is striped across all disks in the array. This is an odd RAID level as there is no real redundancy, as a failure of one drive will fail your array. RAID 0 will give you the total amount of space available on all disks for your array as long as they are the same size, with no redundancy or fault tolerance. If they differ in size, each disk will be relegated to the size of the smallest disk in the array.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.