From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([208.118.235.92]:41990)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1UF3V9-0003Vm-MV
	for qemu-devel@nongnu.org; Mon, 11 Mar 2013 10:14:57 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1UF3V7-0008F4-Kt
	for qemu-devel@nongnu.org; Mon, 11 Mar 2013 10:14:55 -0400
Received: from mx1.redhat.com ([209.132.183.28]:15916)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1UF3V7-0008Ey-Bs
	for qemu-devel@nongnu.org; Mon, 11 Mar 2013 10:14:53 -0400
Message-ID: <513DE6D6.9000105@redhat.com>
Date: Mon, 11 Mar 2013 15:14:46 +0100
From: Paolo Bonzini <pbonzini@redhat.com>
MIME-Version: 1.0
References: <513DDFA3.1020308@dlhnet.de>
In-Reply-To: <513DDFA3.1020308@dlhnet.de>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [RFC] find_next_bit optimizations
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: Peter Lieven <pl@dlhnet.de>
Cc: Orit Wasserman <owasserm@redhat.com>, "qemu-devel@nongnu.org" <qemu-devel@nongnu.org>, Corentin Chary <corentin.chary@gmail.com>

Il 11/03/2013 14:44, Peter Lieven ha scritto:
> Hi,
> 
> I ever since had a few VMs which are very hard to migrate because of a
> lot of memory I/O. I found that finding the next dirty bit
> seemed to be one of the culprits (apart from removing locking which
> Paolo is working on).
> 
> I have to following proposal which seems to help a lot in my case. Just
> wanted to have some feedback.
> I applied the same unrolling idea like in buffer_is_zero().
> 
> Peter
> 
> --- a/util/bitops.c
> +++ b/util/bitops.c
> @@ -24,12 +24,13 @@ unsigned long find_next_bit(const unsigned long
> *addr, unsigned long size,
>      const unsigned long *p = addr + BITOP_WORD(offset);
>      unsigned long result = offset & ~(BITS_PER_LONG-1);
>      unsigned long tmp;
> +    unsigned long d0,d1,d2,d3;
> 
>      if (offset >= size) {
>          return size;
>      }
>      size -= result;
> -    offset %= BITS_PER_LONG;
> +    offset &= (BITS_PER_LONG-1);
>      if (offset) {
>          tmp = *(p++);
>          tmp &= (~0UL << offset);
> @@ -43,6 +44,18 @@ unsigned long find_next_bit(const unsigned long
> *addr, unsigned long size,
>          result += BITS_PER_LONG;
>      }
>      while (size & ~(BITS_PER_LONG-1)) {
> +        while (!(size & (4*BITS_PER_LONG-1))) {

This really means

       if (!(size & (4*BITS_PER_LONG-1))) {
           while (1) {
               ...
           }
       }

because the subtraction will not change the result of the "while" loop
condition.

What you want is probably "while (size & ~(4*BITS_PER_LONG-1))", which
in turn means "while (size >= 4*BITS_PER_LONG).

Please change both while loops to use a ">=" condition, it's easier to read.

Paolo

> +            d0 = *p;
> +            d1 = *(p+1);
> +            d2 = *(p+2);
> +            d3 = *(p+3);
> +            if (d0 || d1 || d2 || d3) {
> +                break;
> +            }
> +            p+=4;
> +            result += 4*BITS_PER_LONG;
> +            size -= 4*BITS_PER_LONG;
> +        }
>          if ((tmp = *(p++))) {
>              goto found_middle;
>          }