Date: Fri, 8 Jun 2012 15:02:53 -0700
From: Andrew Morton <akpm@linux-foundation.org>
To: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Boaz Harrosh <bharrosh@panasas.com>, Tao Ma <boyu.mt@taobao.com>,
        Nick Piggin <npiggin@kernel.dk>, "Dmitry V. Levin" <ldv@altlinux.org>,
        v9fs-developer@lists.sourceforge.net, linux-kernel@vger.kernel.org,
        linux-fsdevel@vger.kernel.org, linux-afs@lists.infradead.org,
        linux-btrfs@vger.kernel.org, ceph-devel@vger.kernel.org,
        linux-cifs@vger.kernel.org, samba-technical@lists.samba.org,
        codalist@TELEMANN.coda.cs.cmu.edu, ecryptfs@vger.kernel.org,
        osd-dev@open-osd.org, linux-ext4@vger.kernel.org,
        fuse-devel@lists.sourceforge.net, linux-mtd@lists.infradead.org,
        jfs-discussion@lists.sourceforge.net, logfs@logfs.org,
        linux-nfs@vger.kernel.org, linux-nilfs@vger.kernel.org,
        linux-ntfs-dev@lists.sourceforge.net, ocfs2-devel@oss.oracle.com,
        reiserfs-devel@vger.kernel.org
Subject: Re: [RFC, PATCH, RESEND] fs: push rcu_barrier() from
 deactivate_locked_super() to filesystems
Message-Id: <20120608150253.e42464a6.akpm@linux-foundation.org>
In-Reply-To: <1339191663-17693-1-git-send-email-kirill.shutemov@linux.intel.com>
References: <1339191663-17693-1-git-send-email-kirill.shutemov@linux.intel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-nfs-owner@vger.kernel.org

On Sat,  9 Jun 2012 00:41:03 +0300
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> wrote:

> There's no reason to call rcu_barrier() on every deactivate_locked_super().
> We only need to make sure that all delayed rcu free inodes are flushed
> before we destroy related cache.
> 
> Removing rcu_barrier() from deactivate_locked_super() affects some
> fas paths. E.g. on my machine exit_group() of a last process in IPC
> namespace takes 0.07538s. rcu_barrier() takes 0.05188s of that time.

What an unpleasant patch.  Is final-process-exiting-ipc-namespace a
sufficiently high-frequency operation to justify the change?

I don't really understand what's going on here.  Are you saying that
there is some filesystem against which we run deactivate_locked_super()
during exit_group(), and that this filesystem doesn't use rcu-freeing
of inodes?  The description needs this level of detail, please.


The implementation would be less unpleasant if we could do the
rcu_barrier() in kmem_cache_destroy().  I can't see a way of doing that
without adding a dedicated slab flag, which would require editing all
the filesystems anyway.


(kmem_cache_destroy() already has an rcu_barrier().  Can we do away
with the private rcu games in the vfs and switch to
SLAB_DESTROY_BY_RCU?)