On Tue, 13 Jul 1999 15:49:05 -0300, Jeff Dike <jdike@karaya.com> said:
>> This is done already and automatically -- it's called readahead.
> I did point this out on my web page.
> Read ahead is good for small buffers, but performance-sensitive apps
> that deal with lots of data are going to try to avoid small buffers.
No, readahead also smooths over the latency hit when you move from one
buffer to the next. That works just as well with large buffers as for
small ones. "performance-sensitive apps that deal with lots of data"
often just use mmap, anyway.
--Stephen
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/