> -----Original Message----- > From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Thursday, March 1, 2018 7:42 AM > To: Zhang, Qi Z <qi.z.zh...@intel.com> > Cc: dev@dpdk.org; magnus.karls...@intei.com; Topel, Bjorn > <bjorn.to...@intel.com> > Subject: Re: [dpdk-dev] [RFC 1/7] net/af_xdp: new PMD driver > > On Tue, 27 Feb 2018 17:33:00 +0800 > Qi Zhang <qi.z.zh...@intel.com> wrote: > > > struct pmd_internals { > > + int sfd; > > + int if_index; > > + char if_name[0x100]; > > why not IFNAMSIZ? > > > + struct ether_addr eth_addr; > > + struct xdp_queue rx; > > + struct xdp_queue tx; > > + struct xdp_umem *umem; > > + struct rte_mempool *mb_pool; > > + > > + unsigned long rx_pkts; > > + unsigned long rx_bytes; > > + unsigned long rx_dropped; > > + > > + unsigned long tx_pkts; > > + unsigned long err_pkts; > > + unsigned long tx_bytes; > > why not per-queue stats? per-port stats are expensive
multi-queue is not supported in this implementation, but will be considered. Regards Qi > > > + uint16_t port_id; > > + uint16_t queue_idx; > > + int ring_size; > > + struct rte_ring *buf_ring; > > +};
