From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:40659)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <stefanha@redhat.com>) id 1Zn1NQ-0000Fh-5g
	for qemu-devel@nongnu.org; Fri, 16 Oct 2015 05:32:41 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <stefanha@redhat.com>) id 1Zn1NL-00021x-5H
	for qemu-devel@nongnu.org; Fri, 16 Oct 2015 05:32:40 -0400
Date: Fri, 16 Oct 2015 11:32:31 +0200
From: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20151016093231.GH7432@stefanha-thinkpad.redhat.com>
References: <1444734655-3630-1-git-send-email-famz@redhat.com>
	<1444734655-3630-3-git-send-email-famz@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1444734655-3630-3-git-send-email-famz@redhat.com>
Subject: Re: [Qemu-devel] [PATCH v2 2/2] aio: Introduce aio-epoll.c
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: Fam Zheng <famz@redhat.com>
Cc: kwolf@redhat.com, pbonzini@redhat.com, qemu-devel@nongnu.org, qemu-block@nongnu.org

On Tue, Oct 13, 2015 at 07:10:55PM +0800, Fam Zheng wrote:
> +static bool aio_epoll_try_enable(AioContext *ctx)
> +{
> +    AioHandler *node;
> +    struct epoll_event event;
> +    if (!ctx->epoll_available) {
> +        return false;
> +    }

Why check this here since aio_epoll_check_poll() already checks it?

> +static int aio_epoll(AioContext *ctx, GPollFD *pfds,
> +                     unsigned npfd, int64_t timeout)
> +{
> +    AioHandler *node;
> +    int i, ret = 0;
> +    struct epoll_event events[128];

The strategy is to support up to 128 events per epoll_wait(2) call and
then wait for the next event loop iteration to harvest any remaining
events?

I just want to make sure I understand how this constant affects epoll
behavior.