[Gluster-Maintainers] Release 5: New option noatime

Amar Tumballi atumball at redhat.com
Fri Sep 28 04:37:58 UTC 2018

On Thu, Sep 27, 2018 at 6:40 PM Shyam Ranganathan <srangana at redhat.com>

> On 09/27/2018 09:08 AM, Shyam Ranganathan wrote:
> > Writing this to solicit opinions on merging this [1] change that
> > introduces an option late in the release cycle.
> >
> > I went through the code, and most changes are standard option handling
> > and basic xlator scaffolding, other than the change in posix xlator code
> > that handles the flag to not set atime and the code in utime xlator that
> > conditionally sets the flag. (of which IMO the latter is more important
> > than the former, as posix is just acting on the flag).
> >
> > The option if enabled would hence not update atime for the following
> > FOPs, opendir, open, read, and would continue updating atime on the
> > following FOPs fallocate and zerofill (which also update mtime, so the
> > AFR self heal on time change would kick in anyways).
> >
> > As the option suggests, with it enables atime is almost meaningless and
> > hence it almost does not matter where we update it and where not. Just
> > considering the problem where atime changes cause AFR to trigger a heal,
> > and the FOPs above that strictly only change atime handled with this
> > option, I am looking at this as functionally workable.
> >

Thanks for all these details, Shyam! Helps many to understand what the
feature is.

> > So IMO we can accept this even though it is late, but would like to hear
> > from others if this needs to be deferred till release-6.
> >

I am all for accepting this for glusterfs-5.0! Two reasons, in one of the
quick setup we tried, it helped to get elastic search run smoothly on
glusterfs mounts. 2nd, we did hear from Anuradha/Ram in another email
thread (Cloudsync with AFR) that it helped them in solving the issue.

This particular patch makes the overhead of ctime feature much much lesser!


> > Shyam
> [1] Patch under review: https://review.gluster.org/c/glusterfs/+/21281
> _______________________________________________
> maintainers mailing list
> maintainers at gluster.org
> https://lists.gluster.org/mailman/listinfo/maintainers

Amar Tumballi (amarts)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/maintainers/attachments/20180928/ac0760ed/attachment.html>

More information about the maintainers mailing list