Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 28AFA21838
MIME-Version: 1.0
References: <20180425214307.159264-1-edumazet@google.com> <CACSApvZF8CJqcRx7FGkMGitBiC6m0=_FT9XRZ=VV07U62wGM3Q@mail.gmail.com>
 <a2c405e1-0ebc-dd33-fb0d-575bf06a1ff6@gmail.com>
In-Reply-To: <a2c405e1-0ebc-dd33-fb0d-575bf06a1ff6@gmail.com>
From:   Andy Lutomirski <luto@kernel.org>
Date:   Thu, 26 Apr 2018 21:16:55 +0000
Message-ID: <CALCETrVBQD1tPUzc_t7HmoPfApTdFW+x-0DqL8+XHjrmEpYMXQ@mail.gmail.com>
Subject: Re: [PATCH v2 net-next 0/2] tcp: mmap: rework zerocopy receive
To:     Eric Dumazet <eric.dumazet@gmail.com>
Cc:     Soheil Hassas Yeganeh <soheil@google.com>,
        Eric Dumazet <edumazet@google.com>,
        "David S. Miller" <davem@davemloft.net>,
        Network Development <netdev@vger.kernel.org>,
        Andrew Lutomirski <luto@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Linux-MM <linux-mm@kvack.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

At the risk of further muddying the waters, there's another minor tweak
that could improve performance on certain workloads.  Currently you mmap()
a range for a given socket and then getsockopt() to receive.  If you made
it so you could mmap() something once for any number of sockets (by
mmapping /dev/misc/tcp_zero_receive or whatever), then the performance of
the getsockopt() bit would be identical, but you could release the mapping
for many sockets at once with only a single flush.  For some use cases,
this could be a big win.

You could also add this later easily enough, too.