"Salvatore Benedetto" <emitrax@xxxxxxxxx> wrote: > 2008/8/14 François Revol <revol@xxxxxxx>: > >> Prop # 33: Read-ahead feature > > numbers don't really fit well here, it went into shipping specific > > stuff :) > > > > I still have some stuff from last SoC that could be used, but the > > cache > > has been a moving target all along... > Could you please at least commit the code somewhere in the repository > so > someone else can have a look at it if you don't have time? > > It's getting dusty in your hard drive. ;-) On mine as well :-) It's not really usable as is, I think, though; for some reason it was developed pretty much separately (with superfluous code duplication), and I don't think it's worth trying to integrate it. The new I/O scheduler makes that stuff a lot easier to do, anyway. All we need is the logic to detect sequential access for read-ahead (and to decrease the page utilization), and that's pretty simple, anyway. Bye, Axel.