> -----Original Message----- > From: Andrew Rybchenko <[email protected]> > Sent: Sunday, October 9, 2022 10:59 PM > To: Wang, YuanX <[email protected]>; [email protected] > Cc: [email protected]; [email protected]; [email protected]; Li, > Xiaoyun <[email protected]>; Singh, Aman Deep > <[email protected]>; Zhang, Yuying <[email protected]>; > Zhang, Qi Z <[email protected]>; Yang, Qiming <[email protected]>; > [email protected]; [email protected]; > [email protected]; Ding, Xuan <[email protected]>; > [email protected]; Tang, Yaqi <[email protected]> > 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 >
