From: "Michael S. Tsirkin" <mst@redhat.com>
To: Bart Van Assche <bvanassche@acm.org>
Cc: Asias He <asias@redhat.com>, kvm-devel <kvm@vger.kernel.org>
Subject: Re: [PATCH 1/2] vhost: Reduce vhost_work_flush() wakeup latency
Date: Wed, 14 Aug 2013 14:37:39 +0300 [thread overview]
Message-ID: <20130814113739.GE5430@redhat.com> (raw)
In-Reply-To: <520B2B88.6020307@acm.org>
On Wed, Aug 14, 2013 at 09:02:32AM +0200, Bart Van Assche wrote:
> If the TIF_NEED_RESCHED task flag is set, wake up any vhost_work_flush()
> waiters before rescheduling instead of after rescheduling.
>
> Signed-off-by: Bart Van Assche <bvanassche@acm.org>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Cc: Asias He <asias@redhat.com>
Why exactly? It's not like flush needs to be extra fast ...
> ---
> drivers/vhost/vhost.c | 42 +++++++++++++++++++-----------------------
> 1 file changed, 19 insertions(+), 23 deletions(-)
>
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index e58cf00..e7ffc10 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -201,47 +201,43 @@ static void vhost_vq_reset(struct vhost_dev *dev,
> static int vhost_worker(void *data)
> {
> struct vhost_dev *dev = data;
> - struct vhost_work *work = NULL;
> - unsigned uninitialized_var(seq);
> + struct vhost_work *work;
> + unsigned seq;
> mm_segment_t oldfs = get_fs();
>
> set_fs(USER_DS);
> use_mm(dev->mm);
>
> - for (;;) {
> + spin_lock_irq(&dev->work_lock);
> + while (!kthread_should_stop()) {
> /* mb paired w/ kthread_stop */
> set_current_state(TASK_INTERRUPTIBLE);
> -
> - spin_lock_irq(&dev->work_lock);
> - if (work) {
> - work->done_seq = seq;
> - if (work->flushing)
> - wake_up_all(&work->done);
> - }
> -
> - if (kthread_should_stop()) {
> - spin_unlock_irq(&dev->work_lock);
> - __set_current_state(TASK_RUNNING);
> - break;
> - }
> if (!list_empty(&dev->work_list)) {
> work = list_first_entry(&dev->work_list,
> struct vhost_work, node);
> list_del_init(&work->node);
> seq = work->queue_seq;
> - } else
> - work = NULL;
> - spin_unlock_irq(&dev->work_lock);
> + spin_unlock_irq(&dev->work_lock);
>
> - if (work) {
> __set_current_state(TASK_RUNNING);
> work->fn(work);
> - if (need_resched())
> - schedule();
> - } else
> +
> + spin_lock_irq(&dev->work_lock);
> + work->done_seq = seq;
> + if (work->flushing)
> + wake_up_all(&work->done);
> + }
> + if (list_empty(&dev->work_list) || need_resched()) {
> + spin_unlock_irq(&dev->work_lock);
> +
> schedule();
>
> + spin_lock_irq(&dev->work_lock);
> + }
> }
> + spin_unlock_irq(&dev->work_lock);
> +
> + __set_current_state(TASK_RUNNING);
> unuse_mm(dev->mm);
> set_fs(oldfs);
> return 0;
> --
> 1.7.10.4
next prev parent reply other threads:[~2013-08-14 11:36 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-14 7:01 [PATCH 0/2] vhost_worker fixes Bart Van Assche
2013-08-14 7:02 ` [PATCH 1/2] vhost: Reduce vhost_work_flush() wakeup latency Bart Van Assche
2013-08-14 11:37 ` Michael S. Tsirkin [this message]
2013-08-14 15:22 ` Bart Van Assche
2013-08-14 17:58 ` Michael S. Tsirkin
2013-08-15 1:30 ` Asias He
2013-08-15 6:13 ` Bart Van Assche
2013-08-15 7:35 ` Michael S. Tsirkin
2013-08-14 7:03 ` [PATCH 2/2] vhost: Avoid that vhost_work_flush() returns early Bart Van Assche
2013-08-14 11:46 ` Michael S. Tsirkin
2013-08-14 15:19 ` Bart Van Assche
2013-08-14 11:39 ` [PATCH 0/2] vhost_worker fixes Michael S. Tsirkin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20130814113739.GE5430@redhat.com \
--to=mst@redhat.com \
--cc=asias@redhat.com \
--cc=bvanassche@acm.org \
--cc=kvm@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox