Re: [PATCH] vhost: Make it more scalable by creating a vhost thread per device.

["Michael S. Tsirkin" <mst@redhat.com>]

On Fri, Apr 02, 2010 at 10:31:20AM -0700, Sridhar Samudrala wrote:
> Make vhost scalable by creating a separate vhost thread per vhost
> device. This provides better scaling across multiple guests and with
> multiple interfaces in a guest.

Thanks for looking into this. An alternative approach is
to simply replace create_singlethread_workqueue with
create_workqueue which would get us a thread per host CPU.

It seems that in theory this should be the optimal approach
wrt CPU locality, however, in practice a single thread
seems to get better numbers. I have a TODO to investigate this.
Could you try looking into this?

> 
> I am seeing better aggregated througput/latency when running netperf
> across multiple guests or multiple interfaces in a guest in parallel
> with this patch.

Any numbers? What happens to CPU utilization?

> Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
> 
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index a6a88df..29aa80f 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -339,8 +339,10 @@ static int vhost_net_open(struct inode *inode, struct file *f)
>  		return r;
>  	}
>  
> -	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT);
> -	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN);
> +	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT,
> +			&n->dev);
> +	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN,
> +			&n->dev);
>  	n->tx_poll_state = VHOST_NET_POLL_DISABLED;
>  
>  	f->private_data = n;
> @@ -643,25 +645,14 @@ static struct miscdevice vhost_net_misc = {
>  
>  int vhost_net_init(void)
>  {
> -	int r = vhost_init();
> -	if (r)
> -		goto err_init;
> -	r = misc_register(&vhost_net_misc);
> -	if (r)
> -		goto err_reg;
> -	return 0;
> -err_reg:
> -	vhost_cleanup();
> -err_init:
> -	return r;
> -
> +	return misc_register(&vhost_net_misc);
>  }
> +
>  module_init(vhost_net_init);
>  
>  void vhost_net_exit(void)
>  {
>  	misc_deregister(&vhost_net_misc);
> -	vhost_cleanup();
>  }
>  module_exit(vhost_net_exit);
>  
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 7bd7a1e..243f4d3 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -36,8 +36,6 @@ enum {
>  	VHOST_MEMORY_F_LOG = 0x1,
>  };
>  
> -static struct workqueue_struct *vhost_workqueue;
> -
>  static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
>  			    poll_table *pt)
>  {
> @@ -56,18 +54,19 @@ static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
>  	if (!((unsigned long)key & poll->mask))
>  		return 0;
>  
> -	queue_work(vhost_workqueue, &poll->work);
> +	queue_work(poll->dev->wq, &poll->work);
>  	return 0;
>  }
>  
>  /* Init poll structure */
>  void vhost_poll_init(struct vhost_poll *poll, work_func_t func,
> -		     unsigned long mask)
> +		     unsigned long mask, struct vhost_dev *dev)
>  {
>  	INIT_WORK(&poll->work, func);
>  	init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
>  	init_poll_funcptr(&poll->table, vhost_poll_func);
>  	poll->mask = mask;
> +	poll->dev = dev;
>  }
>  
>  /* Start polling a file. We add ourselves to file's wait queue. The caller must
> @@ -96,7 +95,7 @@ void vhost_poll_flush(struct vhost_poll *poll)
>  
>  void vhost_poll_queue(struct vhost_poll *poll)
>  {
> -	queue_work(vhost_workqueue, &poll->work);
> +	queue_work(poll->dev->wq, &poll->work);
>  }
>  
>  static void vhost_vq_reset(struct vhost_dev *dev,
> @@ -128,6 +127,11 @@ long vhost_dev_init(struct vhost_dev *dev,
>  		    struct vhost_virtqueue *vqs, int nvqs)
>  {
>  	int i;
> +
> +	dev->wq = create_singlethread_workqueue("vhost");
> +	if (!dev->wq)
> +		return -ENOMEM;
> +
>  	dev->vqs = vqs;
>  	dev->nvqs = nvqs;
>  	mutex_init(&dev->mutex);
> @@ -143,7 +147,7 @@ long vhost_dev_init(struct vhost_dev *dev,
>  		if (dev->vqs[i].handle_kick)
>  			vhost_poll_init(&dev->vqs[i].poll,
>  					dev->vqs[i].handle_kick,
> -					POLLIN);
> +					POLLIN, dev);
>  	}
>  	return 0;
>  }
> @@ -216,6 +220,8 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
>  	if (dev->mm)
>  		mmput(dev->mm);
>  	dev->mm = NULL;
> +
> +	destroy_workqueue(dev->wq);
>  }
>  
>  static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
> @@ -1095,16 +1101,3 @@ void vhost_disable_notify(struct vhost_virtqueue *vq)
>  		vq_err(vq, "Failed to enable notification at %p: %d\n",
>  		       &vq->used->flags, r);
>  }
> -
> -int vhost_init(void)
> -{
> -	vhost_workqueue = create_singlethread_workqueue("vhost");
> -	if (!vhost_workqueue)
> -		return -ENOMEM;
> -	return 0;
> -}
> -
> -void vhost_cleanup(void)
> -{
> -	destroy_workqueue(vhost_workqueue);
> -}
> diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
> index 44591ba..60fefd0 100644
> --- a/drivers/vhost/vhost.h
> +++ b/drivers/vhost/vhost.h
> @@ -29,10 +29,11 @@ struct vhost_poll {
>  	/* struct which will handle all actual work. */
>  	struct work_struct        work;
>  	unsigned long		  mask;
> +	struct vhost_dev	 *dev;
>  };
>  
>  void vhost_poll_init(struct vhost_poll *poll, work_func_t func,
> -		     unsigned long mask);
> +		     unsigned long mask, struct vhost_dev *dev);
>  void vhost_poll_start(struct vhost_poll *poll, struct file *file);
>  void vhost_poll_stop(struct vhost_poll *poll);
>  void vhost_poll_flush(struct vhost_poll *poll);
> @@ -110,6 +111,7 @@ struct vhost_dev {
>  	int nvqs;
>  	struct file *log_file;
>  	struct eventfd_ctx *log_ctx;
> +	struct workqueue_struct *wq;
>  };
>  
>  long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs);
> @@ -136,9 +138,6 @@ bool vhost_enable_notify(struct vhost_virtqueue *);
>  int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
>  		    unsigned int log_num, u64 len);
>  
> -int vhost_init(void);
> -void vhost_cleanup(void);
> -
>  #define vq_err(vq, fmt, ...) do {                                  \
>  		pr_debug(pr_fmt(fmt), ##__VA_ARGS__);       \
>  		if ((vq)->error_ctx)                               \
> 
> 
>