[dpdk-stable] [PATCH v3 1/2] net/mlx5: optimize inline mbuf freeing

[Thomas Monjalon]

28/01/2021 10:14, Slava Ovsiienko:
> From: Ferruh Yigit <ferruh.yigit at intel.com>
> > On 1/22/2021 5:12 PM, Viacheslav Ovsiienko wrote:
> > > The mlx5 PMD supports packet data inlining by pushing data to the
> > > transmit descriptor. If packet is short enough and all data are
> > > inline, the mbuf is not needed for data send anymore and can be freed.
> > >
> > > The mbuf free was performed in the most inner loop building the
> > > transmit descriptors. This patch postpones the mbuf free transaction
> > > to the tx_burst routine exit, optimizing the loop and allowing the
> > > bulk freeing for the multiple mbufs in single pool API call.
> > >
> > > Cc: stable at dpdk.org
> > >
> > 
> > Hi Slava,
> > 
> > This patch is optimization for inline mbufs, right, it is not a fix, should it be
> > backported?
> Not critical, but nice to have this small optimization in LTS.
> 
> > 
> > cc'ed LTS maintainers.
> > 
> > I am dropping the stable to for now in the next-net, can add it later based on
> > discussion result.
> 
> OK, let's consider this backporting in dedicated way, thank you.

Consensus from techboard is to reject optimizations in LTS for now.
Some acceptance guidelines will be written soon.
Not sure this one will be considered.