Virtualization - Oct 2015 - [PATCH net-next RFC 1/2] vhost: introduce vhost_has_work()

This path introduces a helper which can give a hint for whether or not
there's a work queued in the work list.

Signed-off-by: Jason Wang <jasowang at redhat.com>
---
 drivers/vhost/vhost.c | 6 ++++++
 drivers/vhost/vhost.h | 1 +
 2 files changed, 7 insertions(+)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index eec2f11..d42d11e 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -245,6 +245,12 @@ void vhost_work_queue(struct vhost_dev *dev, struct
vhost_work *work)
 }
 EXPORT_SYMBOL_GPL(vhost_work_queue);
 
+bool vhost_has_work(struct vhost_dev *dev)
+{
+	return !list_empty(&dev->work_list);
+}
+EXPORT_SYMBOL_GPL(vhost_has_work);
+
 void vhost_poll_queue(struct vhost_poll *poll)
 {
 	vhost_work_queue(poll->dev, &poll->work);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 4772862..ea0327d 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -37,6 +37,7 @@ struct vhost_poll {
 
 void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
 void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work);
+bool vhost_has_work(struct vhost_dev *dev);
 
 void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
 		     unsigned long mask, struct vhost_dev *dev);
-- 
1.8.3.1

This patch tries to poll for new added tx buffer for a while at the
end of tx processing. The maximum time spent on polling were limited
through a module parameter. To avoid block rx, the loop will end it
there's new other works queued on vhost so in fact socket receive
queue is also be polled.

busyloop_timeout = 50 gives us following improvement on TCP_RR test:

size/session/+thu%/+normalize%
    1/     1/   +5%/  -20%
    1/    50/  +17%/   +3%

Signed-off-by: Jason Wang <jasowang at redhat.com>
---
 drivers/vhost/net.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9eda69e..bbb522a 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -31,7 +31,9 @@
 #include "vhost.h"
 
 static int experimental_zcopytx = 1;
+static int busyloop_timeout = 50;
 module_param(experimental_zcopytx, int, 0444);
+module_param(busyloop_timeout, int, 0444);
 MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
 		                       " 1 -Enable; 0 - Disable");
 
@@ -287,12 +289,23 @@ static void vhost_zerocopy_callback(struct ubuf_info
*ubuf, bool success)
 	rcu_read_unlock_bh();
 }
 
+static bool tx_can_busy_poll(struct vhost_dev *dev,
+			     unsigned long endtime)
+{
+	unsigned long now = local_clock() >> 10;
+
+	return busyloop_timeout && !need_resched() &&
+	       !time_after(now, endtime) && !vhost_has_work(dev) &&
+	       single_task_running();
+}
+
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
 	struct vhost_virtqueue *vq = &nvq->vq;
+	unsigned long endtime;
 	unsigned out, in;
 	int head;
 	struct msghdr msg = {
@@ -331,6 +344,8 @@ static void handle_tx(struct vhost_net *net)
 			      % UIO_MAXIOV == nvq->done_idx))
 			break;
 
+		endtime  = (local_clock() >> 10) + busyloop_timeout;
+again:
 		head = vhost_get_vq_desc(vq, vq->iov,
 					 ARRAY_SIZE(vq->iov),
 					 &out, &in,
@@ -340,6 +355,10 @@ static void handle_tx(struct vhost_net *net)
 			break;
 		/* Nothing new?  Wait for eventfd to tell us they refilled. */
 		if (head == vq->num) {
+			if (tx_can_busy_poll(vq->dev, endtime)) {
+				cpu_relax();
+				goto again;
+			}
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
 				vhost_disable_notify(&net->dev, vq);
 				continue;
-- 
1.8.3.1

On Thu, Oct 22, 2015 at 01:27:28AM -0400, Jason Wang
wrote:
> This path introduces a helper which can give a hint for whether or not
> there's a work queued in the work list.
> 
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
>  drivers/vhost/vhost.c | 6 ++++++
>  drivers/vhost/vhost.h | 1 +
>  2 files changed, 7 insertions(+)
> 
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index eec2f11..d42d11e 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -245,6 +245,12 @@ void vhost_work_queue(struct vhost_dev *dev, struct
vhost_work *work)
>  }
>  EXPORT_SYMBOL_GPL(vhost_work_queue);
>  
> +bool vhost_has_work(struct vhost_dev *dev)
> +{
> +	return !list_empty(&dev->work_list);
> +}
> +EXPORT_SYMBOL_GPL(vhost_has_work);
> +
>  void vhost_poll_queue(struct vhost_poll *poll)
>  {
>  	vhost_work_queue(poll->dev, &poll->work);

This doesn't take a lock so it's unreliable.
I think it's ok in this case since it's just
an optimization - but pls document this.
> diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
> index 4772862..ea0327d 100644
> --- a/drivers/vhost/vhost.h
> +++ b/drivers/vhost/vhost.h
> @@ -37,6 +37,7 @@ struct vhost_poll {
>  
>  void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
>  void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work);
> +bool vhost_has_work(struct vhost_dev *dev);
>  
>  void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
>  		     unsigned long mask, struct vhost_dev *dev);
> -- 
> 1.8.3.1

On Thu, Oct 22, 2015 at 01:27:29AM -0400, Jason Wang
wrote:
> This patch tries to poll for new added tx buffer for a while at the
> end of tx processing. The maximum time spent on polling were limited
> through a module parameter. To avoid block rx, the loop will end it
> there's new other works queued on vhost so in fact socket receive
> queue is also be polled.
> 
> busyloop_timeout = 50 gives us following improvement on TCP_RR test:
> 
> size/session/+thu%/+normalize%
>     1/     1/   +5%/  -20%
>     1/    50/  +17%/   +3%
Is there a measureable increase in cpu utilization
with busyloop_timeout = 0?
> Signed-off-by: Jason Wang <jasowang at redhat.com>
We might be able to shave off the minor regression
by careful use of likely/unlikely, or maybe
deferring 
> ---
>  drivers/vhost/net.c | 19 +++++++++++++++++++
>  1 file changed, 19 insertions(+)
> 
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 9eda69e..bbb522a 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -31,7 +31,9 @@
>  #include "vhost.h"
>  
>  static int experimental_zcopytx = 1;
> +static int busyloop_timeout = 50;
>  module_param(experimental_zcopytx, int, 0444);
> +module_param(busyloop_timeout, int, 0444);
Pls add a description, including the units and the special
value 0.
>  MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
>  		                       " 1 -Enable; 0 - Disable");
>  
> @@ -287,12 +289,23 @@ static void vhost_zerocopy_callback(struct ubuf_info
*ubuf, bool success)
>  	rcu_read_unlock_bh();
>  }
>  
> +static bool tx_can_busy_poll(struct vhost_dev *dev,
> +			     unsigned long endtime)
> +{
> +	unsigned long now = local_clock() >> 10;
local_clock might go backwards if we jump between CPUs.
One way to fix would be to record the CPU id and break
out of loop if that changes.

Also - defer this until we actually know we need it?
> +
> +	return busyloop_timeout && !need_resched() &&
> +	       !time_after(now, endtime) && !vhost_has_work(dev)
&&
> +	       single_task_running();
signal pending as well?
> +}
> +
>  /* Expects to be always run from workqueue - which acts as
>   * read-size critical section for our kind of RCU. */
>  static void handle_tx(struct vhost_net *net)
>  {
>  	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
>  	struct vhost_virtqueue *vq = &nvq->vq;
> +	unsigned long endtime;
>  	unsigned out, in;
>  	int head;
>  	struct msghdr msg = {
> @@ -331,6 +344,8 @@ static void handle_tx(struct vhost_net *net)
>  			      % UIO_MAXIOV == nvq->done_idx))
>  			break;
>  
> +		endtime  = (local_clock() >> 10) + busyloop_timeout;
> +again:
>  		head = vhost_get_vq_desc(vq, vq->iov,
>  					 ARRAY_SIZE(vq->iov),
>  					 &out, &in,
> @@ -340,6 +355,10 @@ static void handle_tx(struct vhost_net *net)
>  			break;
>  		/* Nothing new?  Wait for eventfd to tell us they refilled. */
>  		if (head == vq->num) {
> +			if (tx_can_busy_poll(vq->dev, endtime)) {
> +				cpu_relax();
> +				goto again;
> +			}
>  			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
>  				vhost_disable_notify(&net->dev, vq);
>  				continue;
> -- 
> 1.8.3.1

On 10/22/2015 04:38 PM, Michael S. Tsirkin wrote:
> On Thu, Oct 22, 2015 at 01:27:28AM -0400, Jason Wang wrote:
>> > This path introduces a helper which can give a hint for whether or
not
>> > there's a work queued in the work list.
>> > 
>> > Signed-off-by: Jason Wang <jasowang at redhat.com>
>> > ---
>> >  drivers/vhost/vhost.c | 6 ++++++
>> >  drivers/vhost/vhost.h | 1 +
>> >  2 files changed, 7 insertions(+)
>> > 
>> > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
>> > index eec2f11..d42d11e 100644
>> > --- a/drivers/vhost/vhost.c
>> > +++ b/drivers/vhost/vhost.c
>> > @@ -245,6 +245,12 @@ void vhost_work_queue(struct vhost_dev *dev,
struct vhost_work *work)
>> >  }
>> >  EXPORT_SYMBOL_GPL(vhost_work_queue);
>> >  
>> > +bool vhost_has_work(struct vhost_dev *dev)
>> > +{
>> > +	return !list_empty(&dev->work_list);
>> > +}
>> > +EXPORT_SYMBOL_GPL(vhost_has_work);
>> > +
>> >  void vhost_poll_queue(struct vhost_poll *poll)
>> >  {
>> >  	vhost_work_queue(poll->dev, &poll->work);
> This doesn't take a lock so it's unreliable.
> I think it's ok in this case since it's just
> an optimization - but pls document this.
>
Ok, will do.