[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAF=yD-K=r-9_Em9Ckunht9hdT2bR8eA9w0RwP5avf9Rgj4Ahrg@mail.gmail.com>
Date: Mon, 26 Feb 2018 11:56:55 -0500
From: Willem de Bruijn <willemdebruijn.kernel@...il.com>
To: Sowmini Varadhan <sowmini.varadhan@...cle.com>
Cc: Network Development <netdev@...r.kernel.org>,
David Miller <davem@...emloft.net>,
Santosh Shilimkar <santosh.shilimkar@...cle.com>
Subject: Re: [PATCH V3 net-next 0/3] RDS: optimized notification for zerocopy completion
On Sun, Feb 25, 2018 at 6:21 PM, Sowmini Varadhan
<sowmini.varadhan@...cle.com> wrote:
> RDS applications use predominantly request-response, transacation
> based IPC, so that ingress and egress traffic are well-balanced,
> and it is possible/desirable to reduce system-call overhead by
> piggybacking the notifications for zerocopy completion response
> with data.
>
> Moreover, it has been pointed out that socket functions block
> if sk_err is non-zero, thus if the RDS code does not plan/need
> to use sk_error_queue path for completion notification, it
> is preferable to remove the sk_errror_queue related paths in
> RDS.
>
> Both of these goals are implemented in this series.
>
> v2: removed sk_error_queue support
> v3: incorporated additional code review comments (details in each patch)
>
> Sowmini Varadhan (3):
> selftests/net: revert the zerocopy Rx path for PF_RDS
> rds: deliver zerocopy completion notification with data
> selftests/net: reap zerocopy completions passed up as ancillary data.
>
> include/uapi/linux/errqueue.h | 2 -
> include/uapi/linux/rds.h | 7 ++
> net/rds/af_rds.c | 7 +-
> net/rds/message.c | 38 ++++-----
> net/rds/rds.h | 2 +
> net/rds/recv.c | 31 +++++++-
> tools/testing/selftests/net/msg_zerocopy.c | 120 ++++++++++++----------------
> 7 files changed, 111 insertions(+), 96 deletions(-)
For the series:
Acked-by Willem de Bruijn <willemb@...gle.com>
Small item I missed in v2: the recvmsg in patch 3 should fail hard with
error() on an unexpected errno. Not worth sending a v4 just for that.
Powered by blists - more mailing lists