Re: [PATCH RFC 03/11] net/mlx5e: Implement RX mapped page cache for page recycle

[Jesper Dangaard Brouer via iovisor-dev <iovisor-dev-9jONkmmOlFHEE9lA1F8Ukti2O/JbrIOy@public.gmane.org>]

On Wed,  7 Sep 2016 15:42:24 +0300 Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org> wrote:

> From: Tariq Toukan <tariqt-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> 
> Instead of reallocating and mapping pages for RX data-path,
> recycle already used pages in a per ring cache.
> 
> We ran pktgen single-stream benchmarks, with iptables-raw-drop:
> 
> Single stride, 64 bytes:
> * 4,739,057 - baseline
> * 4,749,550 - order0 no cache
> * 4,786,899 - order0 with cache
> 1% gain
> 
> Larger packets, no page cross, 1024 bytes:
> * 3,982,361 - baseline
> * 3,845,682 - order0 no cache
> * 4,127,852 - order0 with cache
> 3.7% gain
> 
> Larger packets, every 3rd packet crosses a page, 1500 bytes:
> * 3,731,189 - baseline
> * 3,579,414 - order0 no cache
> * 3,931,708 - order0 with cache
> 5.4% gain
> 
> Signed-off-by: Tariq Toukan <tariqt-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> Signed-off-by: Saeed Mahameed <saeedm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> ---
>  drivers/net/ethernet/mellanox/mlx5/core/en.h       | 16 ++++++
>  drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 15 ++++++
>  drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 57 ++++++++++++++++++++--
>  drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 16 ++++++
>  4 files changed, 99 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
> index 075cdfc..afbdf70 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
> @@ -287,6 +287,18 @@ struct mlx5e_rx_am { /* Adaptive Moderation */
>  	u8					tired;
>  };
>  
> +/* a single cache unit is capable to serve one napi call (for non-striding rq)
> + * or a MPWQE (for striding rq).
> + */
> +#define MLX5E_CACHE_UNIT	(MLX5_MPWRQ_PAGES_PER_WQE > NAPI_POLL_WEIGHT ? \
> +				 MLX5_MPWRQ_PAGES_PER_WQE : NAPI_POLL_WEIGHT)
> +#define MLX5E_CACHE_SIZE	(2 * roundup_pow_of_two(MLX5E_CACHE_UNIT))
> +struct mlx5e_page_cache {
> +	u32 head;
> +	u32 tail;
> +	struct mlx5e_dma_info page_cache[MLX5E_CACHE_SIZE];
> +};
> +
[...]
>  
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
> index c1cb510..8e02af3 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
> @@ -305,11 +305,55 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
>  	mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
>  }
>  
> +static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
> +				      struct mlx5e_dma_info *dma_info)
> +{
> +	struct mlx5e_page_cache *cache = &rq->page_cache;
> +	u32 tail_next = (cache->tail + 1) & (MLX5E_CACHE_SIZE - 1);
> +
> +	if (tail_next == cache->head) {
> +		rq->stats.cache_full++;
> +		return false;
> +	}
> +
> +	cache->page_cache[cache->tail] = *dma_info;
> +	cache->tail = tail_next;
> +	return true;
> +}
> +
> +static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq,
> +				      struct mlx5e_dma_info *dma_info)
> +{
> +	struct mlx5e_page_cache *cache = &rq->page_cache;
> +
> +	if (unlikely(cache->head == cache->tail)) {
> +		rq->stats.cache_empty++;
> +		return false;
> +	}
> +
> +	if (page_ref_count(cache->page_cache[cache->head].page) != 1) {
> +		rq->stats.cache_busy++;
> +		return false;
> +	}

Hmmm... doesn't this cause "blocking" of the page_cache recycle
facility until the page at the head of the queue gets (page) refcnt
decremented?  Real use-case could fairly easily block/cause this... 

> +
> +	*dma_info = cache->page_cache[cache->head];
> +	cache->head = (cache->head + 1) & (MLX5E_CACHE_SIZE - 1);
> +	rq->stats.cache_reuse++;
> +
> +	dma_sync_single_for_device(rq->pdev, dma_info->addr, PAGE_SIZE,
> +				   DMA_FROM_DEVICE);
> +	return true;
> +}
> +
>  static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
>  					  struct mlx5e_dma_info *dma_info)
>  {
> -	struct page *page = dev_alloc_page();
> +	struct page *page;
> +
> +	if (mlx5e_rx_cache_get(rq, dma_info))
> +		return 0;
>  
> +	page = dev_alloc_page();
>  	if (unlikely(!page))
>  		return -ENOMEM;

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  Author of http://www.iptv-analyzer.org
  LinkedIn: http://www.linkedin.com/in/brouer