From: Ravikiran G Thirumalai <kiran@in.ibm.com>
To: Andrew Morton <akpm@osdl.org>
Cc: greg@kroah.com, linux-kernel@vger.kernel.org,
viro@parcelfarce.linux.theplanet.co.uk, dipankar@in.ibm.com
Subject: Re: [patch] Use kref for struct file.f_count refcounter
Date: Tue, 27 Jul 2004 12:25:29 +0530 [thread overview]
Message-ID: <20040727065528.GB1270@obelix.in.ibm.com> (raw)
In-Reply-To: <20040726223036.281106c5.akpm@osdl.org>
On Mon, Jul 26, 2004 at 10:30:36PM -0700, Andrew Morton wrote:
> Ravikiran G Thirumalai <kiran@in.ibm.com> wrote:
> >
> > This patch makes use of the kref api for the
> > struct file.f_count refcounter. This depends
> > on the new kref apis kref_read and kref_put_last
> > added by means of my earlier patch today.
>
> Sorry, but I can't really see how this improves anything. It'll slow
> things down infinitesimally and it forces the reader to look elsewhere in
> the tree to see what's going on.
>
It doesn't improve anything in terms of performance or anything. It just
makes use of the kref api for refcounting. My next patchset will be to
extend the kref api to do lockfree refcounting, and eliminate
use of files_struct.file_lock on the reader side (lock free fd lookup) .
That improves performance for fd lookups -- for threaded workloads which
do lot of io. This was the step by step approach I am following to do
lockfree refcounting as was agreed earlier.
I can do a patch to just extend kref api for lockfree refcounting and
use them for for the lock free fd lookup patch directly if you like to see
it that way.
Thanks,
Kiran
next prev parent reply other threads:[~2004-07-27 6:56 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-07-26 15:03 Ravikiran G Thirumalai
2004-07-27 5:30 ` Andrew Morton
2004-07-27 6:55 ` Ravikiran G Thirumalai [this message]
2004-07-27 7:13 ` Andrew Morton
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=20040727065528.GB1270@obelix.in.ibm.com \
--to=kiran@in.ibm.com \
--cc=akpm@osdl.org \
--cc=dipankar@in.ibm.com \
--cc=greg@kroah.com \
--cc=linux-kernel@vger.kernel.org \
--cc=viro@parcelfarce.linux.theplanet.co.uk \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®