Re: [PATCH] fadvise: perform WILLNEED readahead in a workqueue

[Eric Wong <normalperson@yhbt.net>]

Dave Chinner <david@fromorbit.com> wrote:
> On Sun, Dec 16, 2012 at 03:59:53AM +0000, Eric Wong wrote:
> > I want the first read() to happen sooner than it would under current
> > fadvise. 
> 
> You're not listening.  You do not need the kernel to be modified to
> avoid the latency of issuing 1GB of readahead on a file.
> 
> You don't need to do readahead before the first read. Nor do you do
> need to wait for 1GB of readhead to be issued before you do the
> first read.
> 
> You could do readahead *concurrently* with the first read, so the
> first read only blocks until the readahead of the first part of the
> file completes.  i.e. just do readahead() in a background thread and
> don't wait for it to complete before doing the first read.

What you describe with concurrent readahead() is _exactly_ what my test
program (in other email) does with the RA environment variable set.

I know I do not _need_ fadvise + background WILLNEED support in the
kernel.

But I think the kernel can make life easier and allow us to avoid doing
background threads or writing our own (inferior) caching in userspace.