[Discuss] SSD drives vs. Mechanical drives

[blu at nedharvey.com (Edward Ned Harvey (blu))]

> From: discuss-bounces+blu=nedharvey.com at blu.org [mailto:discuss-
> bounces+blu=nedharvey.com at blu.org] On Behalf Of Bill Bogstad
> 
> Guessing here....
> 
> 1.  SSDs are constantly moving data around in order to do wear leveling.

Sorry, that's not correct.  Wear leveling goes like this:

The OS requests to write Block 0.  Internally, the drive maintains a map, like NAT.  When the OS requests to write block 0, I'll actually write block 743, but I'll remember from now on, that Block 0 on the OS side of the interface, maps to 743 internally.  If the OS keeps requesting to overwrite block 0 over and over again, I just keep remapping OS Block 0 goes to 912, now 544, now ... whatever.  This way, no individual memory block *actually* gets overwritten and overwritten and overwritten.  The actually memory pages have the writes distributed amongst each other, approximately even.


> 2. Not all SSDs have batteries/super capacitors to finish those activities if
> power is lost.

In both SSD's and HDD's, there exists a volatile memory write buffer, which is vulnerable to power loss.  When the OS needs to know that some particular data has been flushed to nonvolatile storage, the OS issues a flush command to the drive.  The drive then flushes the volatile buffer, and signals the OS that the flush has completed.  Same is true for both SSD and HDD.