Re: [PATCH net-next v7 9/9] xen-netback: Aggregate TX unmap operations

[Zoltan Kiss <zoltan.kiss@citrix.com>]

Hi,

I'm thinking about revoking this patch: it's value is pretty small, but 
it causes performance regression on Win7 guests. And probably it is not 
the best solution for this problem. It might be the delay it takes the 
dealloc thread to be scheduled is enough.
What do you think?

Zoli

On 06/03/14 21:48, Zoltan Kiss wrote:
> Unmapping causes TLB flushing, therefore we should make it in the largest
> possible batches. However we shouldn't starve the guest for too long. So if
> the guest has space for at least two big packets and we don't have at least a
> quarter ring to unmap, delay it for at most 1 milisec.
>
> Signed-off-by: Zoltan Kiss <zoltan.kiss@citrix.com>
> ---
> v4:
> - use bool for tx_dealloc_work_todo
>
> v6:
> - rebase tx_dealloc_work_todo due to missing ;
>
> diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
> index d1cd8ce..95498c8 100644
> --- a/drivers/net/xen-netback/common.h
> +++ b/drivers/net/xen-netback/common.h
> @@ -118,6 +118,8 @@ struct xenvif {
>   	u16 dealloc_ring[MAX_PENDING_REQS];
>   	struct task_struct *dealloc_task;
>   	wait_queue_head_t dealloc_wq;
> +	struct timer_list dealloc_delay;
> +	bool dealloc_delay_timed_out;
>
>   	/* Use kthread for guest RX */
>   	struct task_struct *task;
> diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
> index 40aa500..f925af5 100644
> --- a/drivers/net/xen-netback/interface.c
> +++ b/drivers/net/xen-netback/interface.c
> @@ -407,6 +407,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
>   			  .desc = i };
>   		vif->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
>   	}
> +	init_timer(&vif->dealloc_delay);
>
>   	/*
>   	 * Initialise a dummy MAC address. We choose the numerically
> @@ -557,6 +558,7 @@ void xenvif_disconnect(struct xenvif *vif)
>   	}
>
>   	if (vif->dealloc_task) {
> +		del_timer_sync(&vif->dealloc_delay);
>   		kthread_stop(vif->dealloc_task);
>   		vif->dealloc_task = NULL;
>   	}
> diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
> index bb65c7c..c098276 100644
> --- a/drivers/net/xen-netback/netback.c
> +++ b/drivers/net/xen-netback/netback.c
> @@ -135,6 +135,11 @@ static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif)
>   		vif->pending_prod + vif->pending_cons;
>   }
>
> +static inline pending_ring_idx_t nr_free_slots(struct xen_netif_tx_back_ring *ring)
> +{
> +	return ring->nr_ents -	(ring->sring->req_prod - ring->rsp_prod_pvt);
> +}
> +
>   bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed)
>   {
>   	RING_IDX prod, cons;
> @@ -1932,9 +1937,36 @@ static inline int tx_work_todo(struct xenvif *vif)
>   	return 0;
>   }
>
> +static void xenvif_dealloc_delay(unsigned long data)
> +{
> +	struct xenvif *vif = (struct xenvif *)data;
> +
> +	vif->dealloc_delay_timed_out = true;
> +	wake_up(&vif->dealloc_wq);
> +}
> +
>   static inline bool tx_dealloc_work_todo(struct xenvif *vif)
>   {
> -	return vif->dealloc_cons != vif->dealloc_prod;
> +	if (vif->dealloc_cons != vif->dealloc_prod) {
> +		if ((nr_free_slots(&vif->tx) > 2 * XEN_NETBK_LEGACY_SLOTS_MAX) &&
> +		    (vif->dealloc_prod - vif->dealloc_cons < MAX_PENDING_REQS / 4) &&
> +		    !vif->dealloc_delay_timed_out) {
> +			if (!timer_pending(&vif->dealloc_delay)) {
> +				vif->dealloc_delay.function =
> +					xenvif_dealloc_delay;
> +				vif->dealloc_delay.data = (unsigned long)vif;
> +				mod_timer(&vif->dealloc_delay,
> +					  jiffies + msecs_to_jiffies(1));
> +
> +			}
> +			return false;
> +		}
> +		del_timer_sync(&vif->dealloc_delay);
> +		vif->dealloc_delay_timed_out = false;
> +		return true;
> +	}
> +
> +	return false;
>   }
>
>   void xenvif_unmap_frontend_rings(struct xenvif *vif)
>