From mboxrd@z Thu Jan  1 00:00:00 1970
From: Arne Jansen <sensille@gmx.net>
Subject: Re: new metadata reader/writer locks in integration-test
Date: Wed, 20 Jul 2011 18:49:29 +0200
Message-ID: <4E270719.6080704@gmx.net>
References: <1311096438-sup-1263@shiny> <4E267BD4.5030200@gmx.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Cc: linux-btrfs <linux-btrfs@vger.kernel.org>
To: Chris Mason <chris.mason@oracle.com>
Return-path: <linux-btrfs-owner@vger.kernel.org>
In-Reply-To: <4E267BD4.5030200@gmx.net>
List-ID: <linux-btrfs.vger.kernel.org>

On 20.07.2011 08:55, Arne Jansen wrote:
> Hi Chris,
>
> On 19.07.2011 19:30, Chris Mason wrote:
>> Hi everyone,
>>
>> I've pushed out a new integration-test branch, and it includes a new
>> reader/writer locking scheme for the btree locks.
>>
>
> I rebased my for-chris branch containing the readahead patches for scrub
> to your integration-test branch. It had only trivial conflicts.
> Hopefully it can go into 3.1 as well.

The readahead series contained a stupid bug I introduced in v5.
The corrected version is pushed out.

>
> -Arne
>
>> We've seen a number of benchmarks dominated by contention on the root
>> node lock.  This changes our locks into a simple reader/writer lock.
>> They are based on mutexes so that we still take advantage of the mutex
>> adaptive spins for write locks (rwsemaphores were much slower).
>>
>> I'm also sending the individual commits, please do take a look.
>>
>> -chris
>