[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <18fec8cd-fc91-736e-7c01-453a18f4e9c5@intel.com>
Date: Wed, 2 Aug 2023 18:11:35 +0200
From: Alexander Lobakin <aleksander.lobakin@...el.com>
To: Ratheesh Kannoth <rkannoth@...vell.com>
CC: <netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
<sgoutham@...vell.com>, <gakula@...vell.com>,
<sbhatta@...vell.com>, <hkelam@...vell.com>, <davem@...emloft.net>,
<edumazet@...gle.com>, <kuba@...nel.org>, <pabeni@...hat.com>
Subject: Re: [PATCH net] octeontx2-pf: Set maximum queue size to 16K
From: Ratheesh Kannoth <rkannoth@...vell.com>
Date: Wed, 2 Aug 2023 16:22:27 +0530
> page_pool_init() return error on requesting ring size > 32K.
> PF uses page pool for rx. octeon-tx2 Supported queue size
> are 16, 64, 256, 1K, 2K, 4K, 16K, 64K. If user try to
> configure larger ring size for rx, return error.
>
> Fixes: b2e3406a38f0 ("octeontx2-pf: Add support for page pool")
> Signed-off-by: Ratheesh Kannoth <rkannoth@...vell.com>
> ---
> drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
> index c47d91da32dc..978e371008d6 100644
> --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
> +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
> @@ -378,7 +378,7 @@ static void otx2_get_ringparam(struct net_device *netdev,
> struct otx2_nic *pfvf = netdev_priv(netdev);
> struct otx2_qset *qs = &pfvf->qset;
>
> - ring->rx_max_pending = Q_COUNT(Q_SIZE_MAX);
> + ring->rx_max_pending = 16384; /* Page pool support on RX */
This is very hardcodish. Why not limit the Page Pool size when creating
instead? It's perfectly fine to have a queue with 64k descriptors and a
Page Pool with only ("only" :D) 16k elements.
Page Pool size affects only the size of the embedded ptr_ring, which is
used for indirect (locking) recycling. I would even recommend to not go
past 2k for PP sizes, it makes no sense and only consumes memory.
> ring->rx_pending = qs->rqe_cnt ? qs->rqe_cnt : Q_COUNT(Q_SIZE_256);
> ring->tx_max_pending = Q_COUNT(Q_SIZE_MAX);
> ring->tx_pending = qs->sqe_cnt ? qs->sqe_cnt : Q_COUNT(Q_SIZE_4K);
Thanks,
Olek
Powered by blists - more mailing lists