From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:56583)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <chenliang88@huawei.com>) id 1XrjQ4-000496-Pg
	for qemu-devel@nongnu.org; Fri, 21 Nov 2014 03:18:26 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <chenliang88@huawei.com>) id 1XrjPy-0002Qu-GB
	for qemu-devel@nongnu.org; Fri, 21 Nov 2014 03:18:20 -0500
Received: from szxga01-in.huawei.com ([119.145.14.64]:38422)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <chenliang88@huawei.com>) id 1XrjPx-0002Pk-4x
	for qemu-devel@nongnu.org; Fri, 21 Nov 2014 03:18:14 -0500
Message-ID: <546EF52A.9030103@huawei.com>
Date: Fri, 21 Nov 2014 16:17:46 +0800
From: ChenLiang <chenliang88@huawei.com>
MIME-Version: 1.0
References: <1415272128-8273-1-git-send-email-liang.z.li@intel.com>
	<1415272128-8273-3-git-send-email-liang.z.li@intel.com>
	<546EE9C6.10203@huawei.com>
	<F2CBF3009FA73547804AE4C663CAB28E44E161@shsmsx102.ccr.corp.intel.com>
In-Reply-To: <F2CBF3009FA73547804AE4C663CAB28E44E161@shsmsx102.ccr.corp.intel.com>
Content-Type: text/plain; charset="ISO-8859-1"
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [v2 2/2] migration: Implement multiple compression
 threads
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: "Li, Liang Z" <liang.z.li@intel.com>
Cc: "Zhang, Yang Z" <yang.z.zhang@intel.com>, "lcapitulino@redhat.com" <lcapitulino@redhat.com>, "qemu-devel@nongnu.org" <qemu-devel@nongnu.org>, "armbru@redhat.com" <armbru@redhat.com>

On 2014/11/21 15:38, Li, Liang Z wrote:

>>> +int migrate_compress_threads(void)
>>> +{
>>> +    MigrationState *s;
>>> +
>>> +    s = migrate_get_current();
>>> +
>>> +    return s->compress_thread_count;
>>> +}
>>> +
>>>  int migrate_use_xbzrle(void)
>>>  {
>>>      MigrationState *s;
>>> @@ -697,4 +795,5 @@ void migrate_fd_connect(MigrationState *s)
>>>  
>>>      qemu_thread_create(&s->thread, "migration", migration_thread, s,
>>>                         QEMU_THREAD_JOINABLE);
>>> +    migrate_compress_threads_create(s);
> 
> 
>> don't create compress_threads always.
>> It may be better:
> 
>> if (!migrate_use_xbzrle()) {
>>     migrate_compress_threads_create(s);
>> }
> 
> Thanks for your comments, in fact,  the multiple thread compression can co-work with xbrzle, which can help to accelerate live migration.


hmm, multiple thread compression can't co-work with xbzrle. xbzrle need guarantee
the cache at src is same to dest. But I dont see that below:

+    /* XBZRLE overflow or normal page */
+    if (bytes_sent == -1) {
+        bytes_sent = migrate_save_block_hdr(&param->migbuf, block,
+            offset, cont, RAM_SAVE_FLAG_COMPRESS_PAGE);
+        blen = migrate_qemu_add_compress(&param->migbuf, p,
+            TARGET_PAGE_SIZE, migrate_compress_level());
+        bytes_sent += blen;
+        atomic_inc(&acct_info.norm_pages);

the code don't update the cache of xbzrle at src.

> 
>> BTW, this patch is too big to review. Spliting it into some patch will be welcome.
> 
> I am doing it.
> 
> 
> 
> 
>