Boston Linux & UNIX was originally founded in 1994 as part of The Boston Computer Society. We meet on the third Wednesday of each month at the Massachusetts Institute of Technology, in Building E51.

BLU Discuss list archive


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Discuss] SSD drives vs. Mechanical drives



> 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.



BLU is a member of BostonUserGroups
BLU is a member of BostonUserGroups
We also thank MIT for the use of their facilities.

Valid HTML 4.01! Valid CSS!



Boston Linux & Unix / webmaster@blu.org