RE: [RFC] readdirplus implementations: xgetdents vs dirreadahead syscalls
From: Zuckerman, Boris
Date: Mon Jul 28 2014 - 10:31:17 EST
2 years ago I had that type of functionality implemented for Ibrix. It included readdir-ahead and lookup-ahead. We did not assume any new syscalls, simply detected readdir+ like interest on VFS level and pushed a wave of populating directory caches and plugging in dentry cache entries. It improved productivity of NFS readdir+ and SMB QueryDirectories more than 4x.
> -----Original Message-----
> From: linux-fsdevel-owner@xxxxxxxxxxxxxxx [mailto:linux-fsdevel-
> owner@xxxxxxxxxxxxxxx] On Behalf Of Abhijith Das
> Sent: Monday, July 28, 2014 8:22 AM
> To: Dave Chinner
> Cc: linux-kernel@xxxxxxxxxxxxxxx; linux-fsdevel; cluster-devel
> Subject: Re: [RFC] readdirplus implementations: xgetdents vs dirreadahead syscalls
> ----- Original Message -----
> > From: "Dave Chinner" <david@xxxxxxxxxxxxx>
> > To: "Zach Brown" <zab@xxxxxxxxxx>
> > Cc: "Abhijith Das" <adas@xxxxxxxxxx>, linux-kernel@xxxxxxxxxxxxxxx,
> > "linux-fsdevel" <linux-fsdevel@xxxxxxxxxxxxxxx>, "cluster-devel"
> > <cluster-devel@xxxxxxxxxx>
> > Sent: Friday, July 25, 2014 7:38:59 PM
> > Subject: Re: [RFC] readdirplus implementations: xgetdents vs
> > dirreadahead syscalls
> > On Fri, Jul 25, 2014 at 10:52:57AM -0700, Zach Brown wrote:
> > > On Fri, Jul 25, 2014 at 01:37:19PM -0400, Abhijith Das wrote:
> > > > Hi all,
> > > >
> > > > The topic of a readdirplus-like syscall had come up for discussion
> > > > at last year's LSF/MM collab summit. I wrote a couple of syscalls
> > > > with their GFS2 implementations to get at a directory's entries as
> > > > well as stat() info on the individual inodes.
> > > > I'm presenting these patches and some early test results on a
> > > > single-node
> > > > GFS2
> > > > filesystem.
> > > >
> > > > 1. dirreadahead() - This patchset is very simple compared to the
> > > > xgetdents() system
> > > > call below and scales very well for large directories in GFS2.
> > > > dirreadahead() is
> > > > designed to be called prior to getdents+stat operations.
> > >
> > > Hmm. Have you tried plumbing these read-ahead calls in under the
> > > normal
> > > getdents() syscalls?
> > The issue is not directory block readahead (which some filesystems
> > like XFS already have), but issuing inode readahead during the
> > getdents() syscall.
> > It's the semi-random, interleaved inode IO that is being optimised
> > here (i.e. queued, ordered, issued, cached), not the directory blocks
> > themselves. As such, why does this need to be done in the kernel?
> > This can all be done in userspace, and even hidden within the
> > readdir() or ftw/ntfw() implementations themselves so it's OS, kernel
> > and filesystem independent......
> I don't see how the sorting of the inode reads in disk block order can be accomplished in
> userland without knowing the fs-specific topology. From my observations, I've seen that
> the performance gain is the most when we can order the reads such that seek times are
> minimized on rotational media.
> I have not tested my patches against SSDs, but my guess would be that the
> performance impact would be minimal, if any.
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a
> message to majordomo@xxxxxxxxxxxxxxx More majordomo info at