>But what I postulate is that you can't physically write *the same* record >over and over more than 90 times per second on a 5400 rpm drive, >unless the >drive, OS, or filesystem implements something like wear-leveling, >where the >physical location of sectors is constantly changing.
It's still possible if the firmware lies about physical sync and, having noticed that you repeatedly overwrite the same LBA, just postpones writes in its queue and only actually flushes the last one. By precisely monitoring input power levels, the drive firmware knows how much it can write before its internal power reserves drop below unreliable levels and it also knows what's left in its write queue, accounting for every internal parameter. So it's still possible that some drives give you a much higher rate than our simple-minded theory predicts. Given the low cost of computing power now embarked in most devices, such behavior is quite possible. _______________________________________________ sqlite-users mailing list sqlite-users@sqlite.org http://sqlite.org:8080/cgi-bin/mailman/listinfo/sqlite-users
