From mboxrd@z Thu Jan  1 00:00:00 1970
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Subject: Re: [RFC] RCU Judy array with distributed locking for FS extents
Date: Tue, 4 Jun 2013 14:57:17 -0400
Message-ID: <20130604185717.GA7138@Krystal>
References: <20130603052758.GA4278@Krystal> <20130603124011.4088.84338@localhost.localdomain> <20130603124601.GA2922@Krystal> <20130604115456.GB2099@devil.localdomain> <20130604142132.4088.42487@localhost.localdomain>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Dave Chinner <dchinner@redhat.com>,
	Linux FS Devel <linux-fsdevel@vger.kernel.org>,
	David Woodhouse <David.Woodhouse@intel.com>,
	"bo.li.liu@oracle.com" <bo.li.liu@oracle.com>,
	"rp@svcs.cs.pdx.edu" <rp@svcs.cs.pdx.edu>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Lai Jiangshan <laijs@cn.fujitsu.com>,
	Stephen Hemminger <shemminger@vyatta.com>,
	Alan Stern <stern@rowland.harvard.edu>
To: Chris Mason <clmason@fusionio.com>
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from mail.openrapids.net ([64.15.138.104]:38730 "EHLO
	blackscsi.openrapids.net" rhost-flags-OK-OK-OK-FAIL)
	by vger.kernel.org with ESMTP id S1750784Ab3FDS5Z (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Tue, 4 Jun 2013 14:57:25 -0400
Content-Disposition: inline
In-Reply-To: <20130604142132.4088.42487@localhost.localdomain>
Sender: linux-fsdevel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

* Chris Mason (clmason@fusionio.com) wrote:
[...]
> In terms of comparing the two, I'd rather compare in the kernel so we
> don't have any surprises.  Are you willing to port the judy code in?

I'm in a similar situation as yours on the Judy side: I still need to
clean up the API and extend its documentation (this is why the Judy code
is still in a development branch), and I'd prefer to have the API
stabilized on the userspace RCU side before porting it to the kernel.
Moreover, I see that it might be a good thing to create an API on top of
Judy to handle overlapping and non-overlapping sparse index ranges.
Ideally, I'd like to implement this and test it in user-space before
porting to the kernel.

I'd be very much interested in helping out in porting your skip list
code to Userspace RCU, I think this should be very much straightforward.
By the way, would you be willing to license it under LGPLv2.1 so it
could be integrated within the Userspace RCU code base ?

Thanks,

Mathieu

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com