From: Al Viro <viro@ZenIV.linux.org.uk>
To: Oleg Drokin <green@linuxhacker.ru>
Cc: Mailing List <linux-kernel@vger.kernel.org>,
"<linux-fsdevel@vger.kernel.org>" <linux-fsdevel@vger.kernel.org>
Subject: Re: More parallel atomic_open/d_splice_alias fun with NFS and possibly more FSes.
Date: Tue, 5 Jul 2016 19:08:41 +0100 [thread overview]
Message-ID: <20160705180841.GO14480@ZenIV.linux.org.uk> (raw)
In-Reply-To: <6D633478-6B94-465E-84D7-C0BA59C5E5F5@linuxhacker.ru>
On Tue, Jul 05, 2016 at 12:33:09PM -0400, Oleg Drokin wrote:
> This also makes me question the whole thing some more. We are definitely in lookup
> when this hits, so the dentry is already new, yet it does not check off as
> d_in_lookup(). That also means that by skipping the ll_splice_alias we are failing
> to hash it and that causing needless lookups later?
> Looking some back into the history of commits, d_in_lookup() is to tell us
> that we are in the middle of lookup. How can we be in the middle of lookup
> path then and not have this set on a dentry? We know dentry was not
> substituted with anything here because we did not call into ll_split_alias().
> So what's going on then?
Lookup in directory locked exclusive, that's what... In unlink(), in your
testcase. And yes, this piece of 1/3 is incorrect; what I do not understand
is the logics of what you are doing with dcache in ll_splice_alias() and
in its caller ;-/
next prev parent reply other threads:[~2016-07-05 18:08 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-17 4:09 More parallel atomic_open/d_splice_alias fun with NFS and possibly more FSes Oleg Drokin
2016-06-17 4:29 ` Al Viro
2016-06-25 16:38 ` Oleg Drokin
2016-07-03 6:29 ` Al Viro
2016-07-04 0:08 ` Al Viro
2016-07-04 0:37 ` Oleg Drokin
2016-07-04 0:37 ` Oleg Drokin
2016-07-04 3:08 ` Al Viro
2016-07-04 3:55 ` Oleg Drokin
2016-07-04 3:55 ` Oleg Drokin
2016-07-05 2:25 ` Al Viro
2016-07-10 17:01 ` Oleg Drokin
2016-07-10 18:14 ` James Simmons
2016-07-11 1:01 ` Al Viro
2016-07-11 1:03 ` Al Viro
2016-07-11 22:54 ` lustre sendmsg stuff Oleg Drokin
2016-07-11 17:15 ` More parallel atomic_open/d_splice_alias fun with NFS and possibly more FSes James Simmons
2016-07-05 2:28 ` Oleg Drokin
2016-07-05 2:32 ` Oleg Drokin
2016-07-05 4:43 ` Oleg Drokin
2016-07-05 6:22 ` Oleg Drokin
2016-07-05 12:31 ` Al Viro
2016-07-05 13:51 ` Al Viro
2016-07-05 15:21 ` Oleg Drokin
2016-07-05 17:42 ` Al Viro
2016-07-05 18:12 ` Oleg Drokin
2016-07-05 16:33 ` Oleg Drokin
2016-07-05 18:08 ` Al Viro [this message]
2016-07-05 19:12 ` Oleg Drokin
2016-07-05 20:08 ` Al Viro
2016-07-05 20:21 ` Oleg Drokin
2016-07-06 0:29 ` Oleg Drokin
2016-07-06 3:20 ` Al Viro
2016-07-06 3:25 ` Oleg Drokin
2016-07-06 3:25 ` Oleg Drokin
2016-07-06 4:35 ` Oleg Drokin
2016-07-06 4:35 ` Oleg Drokin
2016-07-06 16:24 ` Oleg Drokin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20160705180841.GO14480@ZenIV.linux.org.uk \
--to=viro@zeniv.linux.org.uk \
--cc=green@linuxhacker.ru \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.