On Fri, 23 Sep 2005, Rik van Riel wrote: > On Wed, 21 Sep 2005, Behdad Esfahbod wrote: > > > First is that why (according to my experiements) the readahead > > syscall is not async? If I want to readahead 200 files, I > > believe somehow queueing them all should give a better > > performance than calling readahead on one, waiting for it to be > > read, calling on the next. Isn't that true? > > sys_readahead is meant to be relatively simple > > Also, since the bulk of the time spent will be spent on IO, > and the disk can only do one IO at a time anyway, I don't > know if queueing them all will really help much... Well, I was thinking about the elevator nature of the IO scheduler. When queueing them all, they can be read all in one move across the disk, instead of randomly jumply around the disk once per file... Thanks Rik, --behdad http://behdad.org/ -- Kernelnewbies: Help each other learn about the Linux kernel. Archive: http://mail.nl.linux.org/kernelnewbies/ FAQ: http://kernelnewbies.org/faq/
