[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <544e309c-9893-a0ed-ab8a-ccbf5d342dc6@Netapp.com>
Date: Thu, 1 Sep 2016 14:46:35 -0400
From: Anna Schumaker <Anna.Schumaker@...app.com>
To: Chunyan Zhang <zhang.lyra@...il.com>,
<trond.myklebust@...marydata.com>, <anna.schumaker@...app.com>,
<davem@...emloft.net>
CC: <linux-nfs@...r.kernel.org>, <netdev@...r.kernel.org>,
<linux-kernel@...r.kernel.org>, <ke.wang@...eadtrum.com>
Subject: Re: [PATCH] sunrpc: queue work on system_power_efficient_wq
On 09/01/2016 03:30 AM, Chunyan Zhang wrote:
> From: Ke Wang <ke.wang@...eadtrum.com>
>
> sunrpc uses workqueue to clean cache regulary. There is no real dependency
> of executing work on the cpu which queueing it.
>
> On a idle system, especially for a heterogeneous systems like big.LITTLE,
> it is observed that the big idle cpu was woke up many times just to service
> this work, which against the principle of power saving. It would be better
> if we can schedule it on a cpu which the scheduler believes to be the most
> appropriate one.
>
> After apply this patch, system_wq will be replaced by
> system_power_efficient_wq for sunrpc. This functionality is enabled when
> CONFIG_WQ_POWER_EFFICIENT is selected.
Makes sense to me, but I'm a little surprised that there isn't a "schedule_delayed_power_efficient_work()" function to match how the normal workqueue is used.
Thanks,
Anna
>
> Signed-off-by: Ke Wang <ke.wang@...eadtrum.com>
> ---
> net/sunrpc/cache.c | 5 +++--
> 1 file changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
> index 4d8e11f..8aabe12 100644
> --- a/net/sunrpc/cache.c
> +++ b/net/sunrpc/cache.c
> @@ -353,7 +353,7 @@ void sunrpc_init_cache_detail(struct cache_detail *cd)
> spin_unlock(&cache_list_lock);
>
> /* start the cleaning process */
> - schedule_delayed_work(&cache_cleaner, 0);
> + queue_delayed_work(system_power_efficient_wq, &cache_cleaner, 0);
> }
> EXPORT_SYMBOL_GPL(sunrpc_init_cache_detail);
>
> @@ -476,7 +476,8 @@ static void do_cache_clean(struct work_struct *work)
> delay = 0;
>
> if (delay)
> - schedule_delayed_work(&cache_cleaner, delay);
> + queue_delayed_work(system_power_efficient_wq,
> + &cache_cleaner, delay);
> }
>
>
>
Powered by blists - more mailing lists