This message is from the T13 list server.
All of this is vendor unique. If the drive runs out of spare area, then it starts having bad blocks (i.e. you eventually end up with a drive failure). Note that drives, like any material object, do fail at some point, and there are a whole bunch of specs giving you this rate that people design to (MTBF, error rates, etc...). Drives generally don't verify writes (some tape drives do) unless explicitly told to do so. Getting this right is why there are drive engineers. Jim -----Original Message----- From: Marushak, Nathan [mailto:[EMAIL PROTECTED]] Sent: Monday, March 11, 2002 12:47 PM To: '[EMAIL PROTECTED]' Cc: Jeppsen, Roger C Subject: [t13] Drive Internal Block Reassignment & Write Verify This message is from the T13 list server. Hi all, I had a few questions I was hoping someone could answer. * Why was the Write Verify command removed from the specification in ATA/ATAPI-4? * ATA drives reassign bad blocks internally. * Any ideas for how many sectors are reserved, by the drive, for reassignment? * Any ideas concerning the frequency with which drives must perform a reassignment? * Since reassign is done internally, how do ATA drives detect/record ECC errors? Do the drives check on every write? * When the drives reassignment pool has been exhausted, what is the reporting mechanism back to the device on the next subsequent bad block? I greatly appreciate any information you may have. Thanks for your time. Regards, Nathan Marushak Senior Software Engineer intel* Corporation I/O & Bridges Division WORK: 480.554.0934 PAGER: 888.650.4273 EMAIL PAGE: [EMAIL PROTECTED]
