Selecting a Disk Drive: How Not to Do Research

Back to article

Selecting a Disk Drive: How Not to Do Research

January 28, 2014

So the specification for the drive, beside the vibration, operating temperature, and other specifications, now Seagate – and likely soon other drive vendors – will be specifying the amount of I/O that can be done to a drive in a year.  55 TB is the equivalent of ~105 hours of operation at 146 MB/sec (the drive average performance).  ((55*1000*1000*1000*1000)/(146*1000*1000))/3600=104.6/((24*365) for the percentage per year).  So why would anyone buy a drive for an online backup and restore operation that could support drive utilization using average performance of .12% for the year as per the vendor specification?  

Now look at the last column.  This is the number of drive load/unloads, which is where the sliders that carry the read/write heads in hard disk drives land on the disk media at power down, and remain stationed on the disk until the power up cycle.  This has very little to do with reliability of the drive unless the values are exceeded, but is a good example of another limitation that manufacturers document for disk drives.  It is not discussed anywhere in the blog. 

What Matters in Disk Drive Research?

What matters in disk drive research is obtaining information beyond the surface of averages, and getting the raw numbers to do some basic analysis on data that really matters. You need to know:

1. The age of the drives as it affects the failure rate of the drive.

2. Whether the drives are burned in or not burned in, as it impacts the infant mortality.

3. How much data will be written to and read from each drive time and if over time the drives in question will hit the limits on the hard error rates. 

4. The load and unload cycles and if any of the failures exceed manufacturer specification. 

5. Average age does not tell you anything, and statistics such as standard deviation should be provided.  

6. Information on SMART data monitoring and if any of the drives had exceeded any of the SMART statistics before they are more likely to fail.

7. Information on vibration, heat or other environmental factors as it impacts groups of drives.  Will a set of new drives from a vendor get put into an area of the data center that is hotter or have racks with more vibration?

You must understand the manufacturer’s specifications in relationship to the planned usage. If, let’s say, you buy a commodity product like a home washing machine, but put it in a laundromat and it breaks after 3 months of usage, should you have expected it to last 3 years?  I think the same question should be asked of anyone using consumer technology and a commercial application.

Next month I’ll discuss best practices in selecting a disk drive. Stay tuned.

Photo courtesy of Shutterstock.

We have made updates to our Privacy Policy to reflect the implementation of the General Data Protection Regulation.
Thanks for your registration, follow us on our social networks to keep up-to-date