Date: Fri, 26 Jun 2009 08:39:19 -0400
From: Vivek Goyal <vgoyal@redhat.com>
To: Gui Jianfeng <guijianfeng@cn.fujitsu.com>
Cc: linux-kernel@vger.kernel.org, containers@lists.linux-foundation.org,
       dm-devel@redhat.com, jens.axboe@oracle.com, nauman@google.com,
       dpshah@google.com, lizf@cn.fujitsu.com, mikew@google.com,
       fchecconi@gmail.com, paolo.valente@unimore.it, ryov@valinux.co.jp,
       fernando@oss.ntt.co.jp, s-uchida@ap.jp.nec.com, taka@valinux.co.jp,
       jmoyer@redhat.com, dhaval@linux.vnet.ibm.com, balbir@linux.vnet.ibm.com,
       righi.andrea@gmail.com, m-ikeda@ds.jp.nec.com, jbaron@redhat.com,
       agk@redhat.com, snitzer@redhat.com, akpm@linux-foundation.org,
       peterz@infradead.org
Subject: Re: [PATCH 2/2] io-controller: make rt preemption happen in the
	whole hierarchy
Message-ID: <20090626123919.GA9785@redhat.com>
References: <1245443858-8487-1-git-send-email-vgoyal@redhat.com> <1245443858-8487-21-git-send-email-vgoyal@redhat.com> <4A3F3648.7080007@cn.fujitsu.com> <20090622172123.GE15600@redhat.com> <4A4079B8.4020402@cn.fujitsu.com> <20090623140250.GA4262@redhat.com> <4A41EFE1.5050101@cn.fujitsu.com> <4A44833F.8040308@cn.fujitsu.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <4A44833F.8040308@cn.fujitsu.com>
User-Agent: Mutt/1.5.18 (2008-05-17)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2448
Lines: 77

On Fri, Jun 26, 2009 at 04:13:51PM +0800, Gui Jianfeng wrote:
> let rt queue preempt non-rt queue if needed.
> Make sure comparision happens at the same level.
> 
> Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com>
> ---
>  block/elevator-fq.c |   28 +++++++++++++++++++++++++++-
>  1 files changed, 27 insertions(+), 1 deletions(-)
> 
> diff --git a/block/elevator-fq.c b/block/elevator-fq.c
> index 1d4ec1f..21d38f5 100644
> --- a/block/elevator-fq.c
> +++ b/block/elevator-fq.c
> @@ -3742,6 +3742,31 @@ int elv_iosched_expire_ioq(struct request_queue *q, int slice_expired,
>  	return ret;
>  }
>  
> +static int check_rt_preemption(struct io_queue *ioq)
> +{
> +	struct hlist_node *node;
> +	struct hlist_head *hhead = &ioq->efqd->rt_ioq_list;
> +	struct io_queue *rt_ioq;
> +	struct io_entity *entity = &ioq->entity;
> +	struct io_entity *new_entity;
> +
> +	rcu_read_lock();
> +	hlist_for_each_entry_rcu(rt_ioq, node, hhead, rt_node) {
> +		new_entity = &rt_ioq->entity;
> +
> +		bfq_find_matching_entity(&entity, &new_entity);
> +
> +		if (new_entity->ioprio_class == IOPRIO_CLASS_RT &&
> +		    entity->ioprio_class != IOPRIO_CLASS_RT) {
> +			rcu_read_unlock();
> +			return 1;
> +		}
> +	}
> +	rcu_read_unlock();
> +
> +	return 0;
> +}
> +
>  /* Common layer function to select the next queue to dispatch from */
>  void *elv_fq_select_ioq(struct request_queue *q, int force)
>  {
> @@ -3823,7 +3848,8 @@ void *elv_fq_select_ioq(struct request_queue *q, int force)
>  	 */
>  	iog = ioq_to_io_group(ioq);
>  
> -	if (!elv_ioq_class_rt(ioq) && iog->busy_rt_queues) {
> +	if (!elv_ioq_class_rt(ioq) &&
> +	    (iog->busy_rt_queues || check_rt_preemption(ioq))) {
>  		/*

Hi Gui,

I am not able to understand why do we need above changes?

BFQ scheduler already takes care of selecting an RT queue for dispatch (if
the queue is entitled to).

In case a new RT queue backlogged while a BE queue is being served, we
do preemtion check to make sure RT queue gets to run as soon as possible.

In fact I think that busy_rt_queues infrastructure is also redundant and
I plan to get rid of it. 

Can you please help me understand what use case are you addressing with
above patch?

Thanks
Vivek
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/