Re: [PATCH net-next 06/16] idpf: a use saner limit for default number of queues to allocate

[Maciej Fijalkowski]

On Wed, Mar 05, 2025 at 05:21:22PM +0100, Alexander Lobakin wrote:
> Currently, the maximum number of queues available for one vport is 16.
> This is hardcoded, but then the function calculating the optimal number
> of queues takes min(16, num_online_cpus()).
> On order to be able to allocate more queues, which will be then used for

nit: s/On/In

> XDP, stop hardcoding 16 and rely on what the device gives us. Instead of
> num_online_cpus(), which is considered suboptimal since at least 2013,
> use netif_get_num_default_rss_queues() to still have free queues in the
> pool.

Should we update older drivers as well?

> nr_cpu_ids number of Tx queues are needed only for lockless XDP sending,
> the regular stack doesn't benefit from that anyhow.
> On a 128-thread Xeon, this now gives me 32 regular Tx queues and leaves
> 224 free for XDP (128 of which will handle XDP_TX, .ndo_xdp_xmit(), and
> XSk xmit when enabled).
> 
> Signed-off-by: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
> ---
>  drivers/net/ethernet/intel/idpf/idpf_txrx.c     | 8 +-------
>  drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 2 +-
>  2 files changed, 2 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
> index c15833928ea1..2f221c0abad8 100644
> --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
> +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
> @@ -1234,13 +1234,7 @@ int idpf_vport_calc_total_qs(struct idpf_adapter *adapter, u16 vport_idx,
>  		num_req_tx_qs = vport_config->user_config.num_req_tx_qs;
>  		num_req_rx_qs = vport_config->user_config.num_req_rx_qs;
>  	} else {
> -		int num_cpus;
> -
> -		/* Restrict num of queues to cpus online as a default
> -		 * configuration to give best performance. User can always
> -		 * override to a max number of queues via ethtool.
> -		 */
> -		num_cpus = num_online_cpus();
> +		u32 num_cpus = netif_get_num_default_rss_queues();
>  
>  		dflt_splitq_txq_grps = min_t(int, max_q->max_txq, num_cpus);
>  		dflt_singleq_txqs = min_t(int, max_q->max_txq, num_cpus);
> diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
> index 3d2413b8684f..135af3cc243f 100644
> --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
> +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
> @@ -937,7 +937,7 @@ int idpf_vport_alloc_max_qs(struct idpf_adapter *adapter,
>  	max_tx_q = le16_to_cpu(caps->max_tx_q) / default_vports;
>  	if (adapter->num_alloc_vports < default_vports) {
>  		max_q->max_rxq = min_t(u16, max_rx_q, IDPF_MAX_Q);
> -		max_q->max_txq = min_t(u16, max_tx_q, IDPF_MAX_Q);
> +		max_q->max_txq = min_t(u16, max_tx_q, IDPF_LARGE_MAX_Q);
>  	} else {
>  		max_q->max_rxq = IDPF_MIN_Q;
>  		max_q->max_txq = IDPF_MIN_Q;
> -- 
> 2.48.1
>