From: Al Viro <viro@ZenIV.linux.org.uk>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCH 1/2] VFS: Cut down inode->i_op->xyz accesses in path walking
Date: Sat, 23 Jul 2011 00:40:13 +0100 [thread overview]
Message-ID: <20110722234013.GD31405@ZenIV.linux.org.uk> (raw)
In-Reply-To: <alpine.LFD.2.02.1107221037200.29055@i5.linux-foundation.org>
On Fri, Jul 22, 2011 at 10:37:58AM -0700, Linus Torvalds wrote:
>
> From: Linus Torvalds <torvalds@linux-foundation.org>
> Date: Fri, 22 Jul 2011 08:44:51 -0700
> Subject: [PATCH 1/2] VFS: Cut down inode->i_op->xyz accesses in path walking
>
> One of the biggest remaining unnecessary costs in path walking is the
> pointer chasing in inode operations. We already avoided the
> dentry->d_op derferences with the DCACHE_OP_xyz flags, this just starts
> doing the same thing for the i_op->xyz cases.
> + if (unlikely(inode->i_op->lookup))
> + dentry->d_flags |= DCACHE_OP_LOOKUP;
> + if (unlikely(inode->i_op->permission))
> + dentry->d_flags |= DCACHE_OP_PERMISSION;
> + if (unlikely(inode->i_op->follow_link))
> + dentry->d_flags |= DCACHE_OP_FOLLOW_LINK;
I'm not sure about that one... What happens after ln -s foo bar; rm bar;
touch bar;? IOW, where do you clean them?
Other than that, it needs rebase on top of #for-next - conflicts with
->permission() series.
next prev parent reply other threads:[~2011-07-22 23:40 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-22 17:37 VFS pathname walking cleanups (i_op and ACL access) Linus Torvalds
2011-07-22 17:37 ` [PATCH 1/2] VFS: Cut down inode->i_op->xyz accesses in path walking Linus Torvalds
2011-07-22 17:47 ` Christoph Hellwig
2011-07-22 23:40 ` Al Viro [this message]
2011-07-22 23:54 ` Linus Torvalds
2011-07-23 3:55 ` [PATCH] " Linus Torvalds
2011-07-23 13:35 ` Christoph Hellwig
2011-07-23 14:46 ` Al Viro
2011-07-23 14:51 ` Christoph Hellwig
2011-07-23 15:45 ` Linus Torvalds
[not found] ` <alpine.LFD.2.02.1107251852220.13796@i5.linux-foundation.org>
2011-07-26 3:05 ` Al Viro
2011-07-26 3:23 ` Linus Torvalds
2011-07-26 18:41 ` Al Viro
2011-07-26 18:45 ` Linus Torvalds
2011-08-07 6:06 ` Linus Torvalds
2011-08-07 6:51 ` Al Viro
2011-08-07 23:43 ` Linus Torvalds
2011-07-22 17:40 ` VFS pathname walking cleanups (i_op and ACL access) Christoph Hellwig
2011-07-22 17:45 ` [PATCH 2/2] vfs: move ACL cache lookup into generic code Linus Torvalds
2011-07-22 17:50 ` Christoph Hellwig
2011-07-22 17:54 ` Linus Torvalds
2011-07-23 2:34 ` [PATCH] " Linus Torvalds
2011-07-23 3:29 ` Al Viro
2011-07-23 3:42 ` Linus Torvalds
2011-07-23 4:31 ` Al Viro
2011-07-23 6:06 ` Al Viro
2011-07-25 8:15 ` Aneesh Kumar K.V
2011-07-25 8:16 ` Aneesh Kumar K.V
2011-07-23 7:47 ` Al Viro
2011-07-23 14:50 ` Christoph Hellwig
2011-07-23 15:32 ` Al Viro
2011-07-23 17:02 ` Al Viro
2011-07-23 17:31 ` Linus Torvalds
2011-07-23 18:20 ` Al Viro
2011-07-23 18:29 ` Linus Torvalds
2011-07-23 21:53 ` Al Viro
2011-07-23 22:38 ` Al Viro
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=20110722234013.GD31405@ZenIV.linux.org.uk \
--to=viro@zeniv.linux.org.uk \
--cc=hch@lst.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=torvalds@linux-foundation.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.