[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20170131163042.GF8649@oracle.com>
Date: Tue, 31 Jan 2017 11:30:42 -0500
From: Sowmini Varadhan <sowmini.varadhan@...cle.com>
To: John Fastabend <john.fastabend@...il.com>
Cc: bjorn.topel@...il.com, jasowang@...hat.com, ast@...com,
alexander.duyck@...il.com, brouer@...hat.com,
john.r.fastabend@...el.com, netdev@...r.kernel.org
Subject: Re: [RFC PATCH 0/2] rx zero copy interface for af_packet
On (01/27/17 13:33), John Fastabend wrote:
>
> This is an experimental implementation of rx zero copy for af_packet.
> Its a bit rough and likely has errors but the plan is to clean it up
> over the next few months.
>
> And seeing I said I would post it in another thread a few days back
> here it is.
One question/comment about this: sure, this saves us an skb copy
on the rx side, but at least for the Tx side, I think there may
be a trade-off between the overhead from the skb setup and the
ease of offloading checksum (and UFO where it is available) to
consider, even for PF_PACKET.
Using PF_PACKET works well for stateless datagram protocols like
UDP, and for UDP sockets, we find that just switching to Jumbo
(to simulate a poor-man's-UFO) gives us significant improvement
in both throughput and latency for our RDBMS workloads - and
having the sk_buff facilitates using existing driver-kernel interfaces
for offload easily, so while we may gain some perf improvment by shaving
of the sk_buff overhead, the trade-off needs to be considered.
--Sowmini
Powered by blists - more mailing lists