On Mon, 04 Mar 2002, Oleg Drokin wrote: > > But how much seeking is done on one 650 MB file that's been written onto > > an empty partition? I presume, not too much. > 162.5*2 seeks. (that's right, 2 seeks per each 4M of data) > This figure is for reading. > Writing is more complex due to journal.
So let's assume we read 4 M in half a second, so we seek four times per second, gives us like 80 ms penalty on a slow drive. That causes a performance drop to like 92% of the raw transfer rate, even when adding the same penalty for bus arbitration, we should still get 86% out. However, I hope to be able to play with the settings later, to figure what's going on there. -- Matthias Andree GPG encrypted mail welcome, unless it's unsolicited commercial email.
