From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:36329) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UIj1c-0006b0-5E for qemu-devel@nongnu.org; Thu, 21 Mar 2013 13:11:39 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1UIj1V-0006b0-KL for qemu-devel@nongnu.org; Thu, 21 Mar 2013 13:11:36 -0400 Received: from mx1.redhat.com ([209.132.183.28]:40651) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UIizc-0005es-VO for qemu-devel@nongnu.org; Thu, 21 Mar 2013 13:09:33 -0400 Date: Thu, 21 Mar 2013 19:10:09 +0200 From: "Michael S. Tsirkin" Message-ID: <20130321171009.GC2994@redhat.com> References: <1363881940-27505-1-git-send-email-owasserm@redhat.com> <1363881940-27505-10-git-send-email-owasserm@redhat.com> <20130321161608.GE1925@redhat.com> <514B34FE.6010901@redhat.com> <20130321162912.GH1925@redhat.com> <514B37F8.80804@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <514B37F8.80804@redhat.com> Subject: Re: [Qemu-devel] [PATCH v3 9/9] coalesce adjacent iovecs List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Orit Wasserman Cc: pbonzini@redhat.com, chegu_vinod@hp.com, qemu-devel@nongnu.org, quintela@redhat.com On Thu, Mar 21, 2013 at 06:40:24PM +0200, Orit Wasserman wrote: > On 03/21/2013 06:29 PM, Michael S. Tsirkin wrote: > > On Thu, Mar 21, 2013 at 06:27:42PM +0200, Orit Wasserman wrote: > >> On 03/21/2013 06:16 PM, Michael S. Tsirkin wrote: > >>> On Thu, Mar 21, 2013 at 06:05:40PM +0200, Orit Wasserman wrote: > >>>> This way we send one big buffer instead of many small ones > >>>> > >>>> Signed-off-by: Orit Wasserman > >>> > >>> Why does this happen BTW? > >> > >> It happens in the last phase when we send the device state that consists of a lot > >> bytes and int field that are written using qemu_put_byte/be16/... > >> > > > > Confused I thought device_state does not use _nocopy? > > My idea of using vmsplice relies exactly on this: > > we can not splice device state ... > > qemu_put_buffer calls qemu_put_buffer_no_copy (you know code reuse) > So I guess we will need to add some flag if we want to use vmsplice or not > or split no_copy into external and internal. It won't be a big change Fair enough. Have time to look into this? Data copies is like 15% CPU, more with swap ... > > > >>> > >>>> --- > >>>> savevm.c | 21 +++++++++++++++++---- > >>>> 1 file changed, 17 insertions(+), 4 deletions(-) > >>>> > >>>> diff --git a/savevm.c b/savevm.c > >>>> index 50e8fb2..13a533b 100644 > >>>> --- a/savevm.c > >>>> +++ b/savevm.c > >>>> @@ -634,8 +634,14 @@ void qemu_put_buffer_no_copy(QEMUFile *f, const uint8_t *buf, int size) > >>>> abort(); > >>>> } > >>>> > >>>> - f->iov[f->iovcnt].iov_base = (uint8_t *)buf; > >>>> - f->iov[f->iovcnt++].iov_len = size; > >>>> + /* check for adjoint buffer and colace them */ > >>>> + if (f->iovcnt > 0 && buf == f->iov[f->iovcnt - 1].iov_base + > >>>> + f->iov[f->iovcnt - 1].iov_len) { > >>>> + f->iov[f->iovcnt - 1].iov_len += size; > >>>> + } else { > >>>> + f->iov[f->iovcnt].iov_base = (uint8_t *)buf; > >>>> + f->iov[f->iovcnt++].iov_len = size; > >>>> + } > >>>> > >>>> f->is_write = 1; > >>>> f->bytes_xfer += size; > >>>> @@ -690,8 +696,15 @@ void qemu_put_byte(QEMUFile *f, int v) > >>>> f->buf[f->buf_index++] = v; > >>>> f->is_write = 1; > >>>> f->bytes_xfer += 1; > >>>> - f->iov[f->iovcnt].iov_base = f->buf + (f->buf_index - 1); > >>>> - f->iov[f->iovcnt++].iov_len = 1; > >>>> + > >>>> + /* check for adjoint buffer and colace them */ > >>>> + if (f->iovcnt > 0 && f->buf + (f->buf_index - 1) == > >>>> + f->iov[f->iovcnt - 1].iov_base + f->iov[f->iovcnt - 1].iov_len) { > >>>> + f->iov[f->iovcnt - 1].iov_len += 1; > >>>> + } else { > >>>> + f->iov[f->iovcnt].iov_base = f->buf + (f->buf_index - 1); > >>>> + f->iov[f->iovcnt++].iov_len = 1; > >>>> + } > >>>> > >>>> if (f->buf_index >= IO_BUF_SIZE || f->iovcnt >= MAX_IOV_SIZE) { > >>>> qemu_fflush(f); > >>>> -- > >>>> 1.7.11.7