If this is your first visit, be sure to
check out the FAQ by clicking the
link above. You may have to register
before you can post: click the register link above to proceed. To start viewing messages,
select the forum that you want to visit from the selection below.
Are you trying to determine bit error rates? Are you trying to test until destruction? Is this a product line environment and you only have 5min to test each machine? How large is the SSD? What is it used for?
The typical process for a BER calculation it to run dozens (or even hundreds) of units for a long period (days or weeks) until a reasonable number of bit errors are encountered. Then statistically extrapolate that out to get an average BER.
So depending on the drive, to get even 1 bit in error you might need to run the test for several weeks on lots of SSDs. This is made harder because many drives self correct errors (but you can track this via the relocated sector count from the S.M.A.R.T. data). After weeks to continuous heavy use the drive's life will also be seriously reduced, again this depends on the drive type.
So I would suggest just running the disk test by itself. Set the duty cycle to 100%. Set the test pattern to be cyclic and set the test during to 10,080 minutes (7 days). Then see what happens. The drive might be so reliable that there are no errors in a week.
Comment