From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:43663)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <serge.fdrv@gmail.com>) id 1b5Kdn-0005St-1V
	for qemu-devel@nongnu.org; Tue, 24 May 2016 18:17:31 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <serge.fdrv@gmail.com>) id 1b5Kdh-0003gZ-2T
	for qemu-devel@nongnu.org; Tue, 24 May 2016 18:17:30 -0400
Received: from mail-lb0-x244.google.com ([2a00:1450:4010:c04::244]:35206)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <serge.fdrv@gmail.com>) id 1b5Kdg-0003gU-Qx
	for qemu-devel@nongnu.org; Tue, 24 May 2016 18:17:25 -0400
Received: by mail-lb0-x244.google.com with SMTP id sh2so1743460lbb.2
	for <qemu-devel@nongnu.org>; Tue, 24 May 2016 15:17:24 -0700 (PDT)
References: <1463196873-17737-1-git-send-email-cota@braap.org>
	<1463196873-17737-14-git-send-email-cota@braap.org>
	<574367EB.8030101@gmail.com> <20160524220755.GA25193@flamenco>
From: Sergey Fedorov <serge.fdrv@gmail.com>
Message-ID: <5744D2F1.2050009@gmail.com>
Date: Wed, 25 May 2016 01:17:21 +0300
MIME-Version: 1.0
In-Reply-To: <20160524220755.GA25193@flamenco>
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [PATCH v5 13/18] qht: support parallel writes
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel/>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: "Emilio G. Cota" <cota@braap.org>
Cc: QEMU Developers <qemu-devel@nongnu.org>, MTTCG Devel <mttcg@listserver.greensocs.com>, =?UTF-8?Q?Alex_Benn=c3=a9e?= <alex.bennee@linaro.org>, Paolo Bonzini <pbonzini@redhat.com>, Peter Crosthwaite <crosthwaite.peter@gmail.com>, Richard Henderson <rth@twiddle.net>

On 25/05/16 01:07, Emilio G. Cota wrote:
> On Mon, May 23, 2016 at 23:28:27 +0300, Sergey Fedorov wrote:
>> What if we turn qht::lock into a mutex and change the function as follows:
>>
>>     static inline
>>     struct qht_bucket *qht_bucket_lock__no_stale(struct qht *ht,
>>     uint32_t hash,
>>                                                  struct qht_map
>>     **pmap)       
>>     {
>>         struct qht_bucket *b;
>>         struct qht_map *map;
>>
>>         map = atomic_rcu_read(&ht->map);
>>         b = qht_map_to_bucket(map, hash);
>>
>>         qemu_spin_lock(&b->lock);
>>         /* 'ht->map' access is serialized by 'b->lock' here */
>>         if (likely(map == ht->map)) {
>>             /* no resize in progress; we're done */
>>             *pmap = map;
>>             return b;
>>         }
>>         qemu_spin_unlock(&b->lock);
>>
>>         /* resize in progress; retry grabbing 'ht->lock' */
>>         qemu_mutex_lock(&ht->lock);
>>         b = qht_map_to_bucket(ht->map, hash);
>>         *pmap = ht->map;
>>         qemu_spin_lock(&b->lock);
>>         qemu_mutex_unlock(&ht->lock);
>>
>>         return b;
>>     }
>>
>>
>> With this implementation we could:
>>  (1) get rid of qht_map::stale
>>  (2) don't waste cycles waiting for resize to complete
> I'll include this in v6.

How is it by perf?

Regards,
Sergey