There's a voice in my head saying "that should happen on open(2), not
read(2)". Am I just hallucinating? More to the point, why do we get
this repeated (and annoying) disk activity under 1.3.~80 but not
1.2.x? Can the new bdflush be tuned to wait longer before flushing,
and if so, how?
>might be a stupid question, but is there no way doing event based reads
>on files [selects and/or blocking reads at the end of the file] ?
Not under Unix.
-zefram