Intel Responds to Fragmentation with New X25-M Firmware
 

The 8820 firmware has completely renewed my faith in the X25-M. The weak link has been eradicated, and I’m thoroughly impressed with the renewed performance it will bring to all M series drive users. I am also thoroughly pleased with Intel for being so open to feedback from the reviewers.

That said, there was a nagging thought in my mind throughout all of my testing. If write speeds to the flash memory were constant at 80 MB/sec, how could it possibly shuffle around enough data to defragment those areas on a subsequent write pass while still accepting new data at full speed? I’ve studied flash memory technology for some time now, and the math simply does not work. I thought on it and my background in electronics kicked in a bit: The new write ‘waveform’ seemed clipped to 80 MB/sec.

http://www.pcper.com/article.php?aid...e=expert&pid=1