Re: [dpdk-dev] [PATCH] kni: fast data availability check in thread_single loop

[Ferruh Yigit <ferruh.yigit@intel.com>]

On 12/29/2016 11:23 PM, Sergey Vyazmitinov wrote:
> This allow to significant reduces packets processing latency.
> 
> Signed-off-by: Sergey Vyazmitinov <s.vyazmitinov@brain4net.com>
> ---
>  .../linuxapp/eal/include/exec-env/rte_kni_common.h |  6 ++++
>  lib/librte_eal/linuxapp/kni/kni_misc.c             | 33 ++++++++++++++++------
>  2 files changed, 30 insertions(+), 9 deletions(-)
> 
> diff --git a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h
> index 09713b0..8183a8e 100644
> --- a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h
> +++ b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_kni_common.h
> @@ -109,6 +109,12 @@ struct rte_kni_fifo {
>  	void *volatile buffer[];     /**< The buffer contains mbuf pointers */
>  };
>  
> +static inline int
> +kni_fifo_empty(struct rte_kni_fifo *fifo)
> +{
> +	return fifo->write == fifo->read;
> +}
> +
>  /*
>   * The kernel image of the rte_mbuf struct, with only the relevant fields.
>   * Padding is necessary to assure the offsets of these fields
> diff --git a/lib/librte_eal/linuxapp/kni/kni_misc.c b/lib/librte_eal/linuxapp/kni/kni_misc.c
> index 497db9b..4bf9bfa 100644
> --- a/lib/librte_eal/linuxapp/kni/kni_misc.c
> +++ b/lib/librte_eal/linuxapp/kni/kni_misc.c
> @@ -45,6 +45,7 @@ MODULE_AUTHOR("Intel Corporation");
>  MODULE_DESCRIPTION("Kernel Module for managing kni devices");
>  
>  #define KNI_RX_LOOP_NUM 1000
> +#define KNI_RX_DATA_LOOP_NUM 2500
>  
>  #define KNI_MAX_DEVICES 32
>  
> @@ -129,25 +130,39 @@ static struct pernet_operations kni_net_ops = {
>  #endif
>  };
>  
> -static int
> -kni_thread_single(void *data)
> +static inline void
> +kni_thread_single_rx_data_loop(struct kni_net *knet)
>  {
> -	struct kni_net *knet = data;
> -	int j;
>  	struct kni_dev *dev;
> +	int i;
>  
> -	while (!kthread_should_stop()) {
> -		down_read(&knet->kni_list_lock);
> -		for (j = 0; j < KNI_RX_LOOP_NUM; j++) {
> -			list_for_each_entry(dev, &knet->kni_list_head, list) {
> +	for (i = 0; i < KNI_RX_DATA_LOOP_NUM; ++i) {

When there are multiple KNI interfaces, and lets assume there is traffic
too, this will behave like:

KNI1x2500 data_packets + KNI2x2500 data_packets .... KNI10x2500

After data packets, KNI1 resp_packet + KNI2 resp_packets ...

Won't this scenario also may cause latency? And perhaps jitter according
KNI interface traffic loads?

This may be good for some use cases, but not sure if this is good for all.

> +		list_for_each_entry(dev, &knet->kni_list_head, list) {
> +			/* Burst dequeue from rx_q */
> +			if (!kni_fifo_empty((struct rte_kni_fifo *)dev->rx_q)) {

Do we need this check, since first thing in kni_net_rx_normal() is
checking if there is item in the queue?

>  #ifdef RTE_KNI_VHOST
>  				kni_chk_vhost_rx(dev);
>  #else
>  				kni_net_rx(dev);
>  #endif
> -				kni_net_poll_resp(dev);
>  			}
>  		}
> +	}
> +	list_for_each_entry(dev, &knet->kni_list_head, list) {
> +		kni_net_poll_resp(dev);
> +	}
> +}
> +
> +static int
> +kni_thread_single(void *data)
> +{
> +	struct kni_net *knet = data;
> +	int j;
> +
> +	while (!kthread_should_stop()) {
> +		down_read(&knet->kni_list_lock);
> +		for (j = 0; j < KNI_RX_LOOP_NUM; j++)
> +			kni_thread_single_rx_data_loop(knet);
>  		up_read(&knet->kni_list_lock);
>  #ifdef RTE_KNI_PREEMPT_DEFAULT
>  		/* reschedule out for a while */
>