From mboxrd@z Thu Jan  1 00:00:00 1970
From: Rusty Russell <rusty@rustcorp.com.au>
Subject: Re: [PATCH] virtio-net: fill only rx queues which are being used
Date: Tue, 23 Apr 2013 13:43:04 +0930
Message-ID: <87obd5ga0f.fsf@rustcorp.com.au>
References: <1366677336-2278-1-git-send-email-sasha.levin@oracle.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: penberg@kernel.org, will.deacon@arm.com, marc.zyngier@arm.com,
	kvm@vger.kernel.org, asias@redhat.com, jasowang@redhat.com,
	Sasha Levin <sasha.levin@oracle.com>
To: Sasha Levin <sasha.levin@oracle.com>, mst@redhat.com
Return-path: <kvm-owner@vger.kernel.org>
Received: from ozlabs.org ([203.10.76.45]:55329 "EHLO ozlabs.org"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1751506Ab3DWEWG (ORCPT <rfc822;kvm@vger.kernel.org>);
	Tue, 23 Apr 2013 00:22:06 -0400
In-Reply-To: <1366677336-2278-1-git-send-email-sasha.levin@oracle.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

Sasha Levin <sasha.levin@oracle.com> writes:
> Due to MQ support we may allocate a whole bunch of rx queues but
> never use them. With this patch we'll safe the space used by
> the receive buffers until they are actually in use:

Idea is good, implementation needs a tiny tweak:

> @@ -912,8 +913,13 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
>  		dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
>  			 queue_pairs);
>  		return -EINVAL;
> -	} else
> +	} else {
> +		if (queue_pairs > vi->curr_queue_pairs)
> +			for (i = 0; i < queue_pairs; i++)
> +				if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
> +					schedule_delayed_work(&vi->refill, 0);
>  		vi->curr_queue_pairs = queue_pairs;
> +	}
>  
>  	return 0;
>  }

You don't want to refill existing queues, so you don't need the "if".

        for (i = vi->curr_queue_pairs; i < queue_pairs; i++) {
		if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
			schedule_delayed_work(&vi->refill, 0);

We don't free up buffers when we're reducing queues, but I consider that
a corner case.

Thanks,
Rusty.