[dpdk-dev] [PATCH v2 3/5] testpmd: Change rxfreet default to 32

[Neil Horman]

On Tue, Sep 23, 2014 at 12:08:15PM +0100, Bruce Richardson wrote:
> To improve performance by using bulk alloc or vectored RX routines, we
> need to set rx free threshold (rxfreet) value to 32, so make this the
> testpmd default.
> 
> Thirty-two is the minimum setting needed to enable either the
> bulk alloc or vector RX routines inside the ixgbe driver, so it's
> best made the default for that reason. Please see
> "check_rx_burst_bulk_alloc_preconditions()" in ixgbe_rxtx.c, and
> RX function assignment logic in "ixgbe_dev_rx_queue_setup()" in
> the same file.
> 
> The difference in IO performance for testpmd when called without any
> optional parameters, and using 10G NICs using the ixgbe driver, can be
> significant - approx 25% or more.
> 
> Updates in V2:
> * Updated commit message with additional details
> 
> Signed-off-by: Bruce Richardson <bruce.richardson at intel.com>
> ---
>  app/test-pmd/testpmd.c | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 
> diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
> index 9f6cdc4..f76406f 100644
> --- a/app/test-pmd/testpmd.c
> +++ b/app/test-pmd/testpmd.c
> @@ -225,7 +225,9 @@ struct rte_eth_thresh tx_thresh = {
>  /*
>   * Configurable value of RX free threshold.
>   */
> -uint16_t rx_free_thresh = 0; /* Immediately free RX descriptors by default. */
> +uint16_t rx_free_thresh = 32; /* Refill RX descriptors once every 32 packets,
> +		This setting is needed for ixgbe to enable bulk alloc or vector
> +		receive functionality. */

I thought we were talking about making this a pmd private selectable item, or
allowing a reserved "let the pmd decide" setting.  Or are we saving that for a
later time?

Neil

>  
>  /*
>   * Configurable value of RX drop enable.
> -- 
> 1.9.3
> 
>