> -----Original Message----- > From: Andrew Rybchenko <andrew.rybche...@oktetlabs.ru> > Sent: Sunday, October 9, 2022 10:59 PM > To: Wang, YuanX <yuanx.w...@intel.com>; dev@dpdk.org > Cc: tho...@monjalon.net; ferruh.yi...@xilinx.com; m...@ashroe.eu; Li, > Xiaoyun <xiaoyun...@intel.com>; Singh, Aman Deep > <aman.deep.si...@intel.com>; Zhang, Yuying <yuying.zh...@intel.com>; > Zhang, Qi Z <qi.z.zh...@intel.com>; Yang, Qiming <qiming.y...@intel.com>; > jerinjac...@gmail.com; viachesl...@nvidia.com; > step...@networkplumber.org; Ding, Xuan <xuan.d...@intel.com>; > hpoth...@marvell.com; Tang, Yaqi <yaqi.t...@intel.com> > Subject: Re: [PATCH v9 0/4] support protocol based buffer split > > On 10/9/22 23:25, Yuan Wang wrote: > > Protocol type based buffer split consists of splitting a received > > packet into several separate segments based on the packet content. It > > is useful in some scenarios, such as GPU acceleration. The splitting > > will help to enable true zero copy and hence improve the performance > significantly. > > > > This patchset aims to support protocol header split based on current > > buffer split. When Rx queue is configured with > > RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT offload and corresponding protocol, > > packets received will be directly split into different mempools. > > > > Change log: > > v9: > > Define the intend behaviors for exact match and longest match. > > Add protocol headers repeat check. > > Add no proto-split after length-based split check. > > Add a helper function to short the check function. > > Refine the doc and commit log. > > With few minor fixes, applied to dpdk-next-net/main, thanks.
Sincere thanks to all the reviewers who provided valuable comments on this patch series. Regards, Xuan >
