Re: [t13] generic problems with O/Q and the EXT commands

[Constantine Sapuntzakis]

This message is from the T13 list server.

Agreed. What I said was wrong - the locks in the buffer cache don't 
"ensure" anything. You can definitely write code at user and kernel 
level that ends up issuing simultaneous requests to the same sectors on 
a disk. And the disk driver doesn't really care or check.

Any mechanisms to try to avoid multiple simultaneous I/Os happen at a 
higher layer than the disk driver.

-Costa