Message-ID: <ZDk2kOVnUvyLMLKE@bullseye>
Date:   Fri, 14 Apr 2023 11:18:40 +0000
From:   Bobby Eshleman <bobbyeshleman@...il.com>
To:     Bobby Eshleman <bobby.eshleman@...edance.com>
Cc:     Stefan Hajnoczi <stefanha@...hat.com>,
        Stefano Garzarella <sgarzare@...hat.com>,
        "Michael S. Tsirkin" <mst@...hat.com>,
        Jason Wang <jasowang@...hat.com>,
        "David S. Miller" <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>,
        "K. Y. Srinivasan" <kys@...rosoft.com>,
        Haiyang Zhang <haiyangz@...rosoft.com>,
        Wei Liu <wei.liu@...nel.org>, Dexuan Cui <decui@...rosoft.com>,
        Bryan Tan <bryantan@...are.com>,
        Vishnu Dasa <vdasa@...are.com>,
        VMware PV-Drivers Reviewers <pv-drivers@...are.com>,
        kvm@...r.kernel.org, virtualization@...ts.linux-foundation.org,
        netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-hyperv@...r.kernel.org,
        Jiang Wang <jiang.wang@...edance.com>,
        Cong Wang <cong.wang@...edance.com>
Subject: Re: [PATCH RFC net-next v2 0/4] virtio/vsock: support datagrams

CC'ing Cong.

On Fri, Apr 14, 2023 at 12:25:56AM +0000, Bobby Eshleman wrote:
> Hey all!
> 
> This series introduces support for datagrams to virtio/vsock.
> 
> It is a spin-off (and smaller version) of this series from the summer: 
>   https://lore.kernel.org/all/cover.1660362668.git.bobby.eshleman@bytedance.com/
> 
> Please note that this is an RFC and should not be merged until
> associated changes are made to the virtio specification, which will
> follow after discussion from this series.
> 
> This series first supports datagrams in a basic form for virtio, and
> then optimizes the sendpath for all transports.
> 
> The result is a very fast datagram communication protocol that
> outperforms even UDP on multi-queue virtio-net w/ vhost on a variety
> of multi-threaded workload samples.
> 
> For those that are curious, some summary data comparing UDP and VSOCK
> DGRAM (N=5):
> 
> 	vCPUS: 16
> 	virtio-net queues: 16
> 	payload size: 4KB
> 	Setup: bare metal + vm (non-nested)
> 
> 	UDP: 287.59 MB/s
> 	VSOCK DGRAM: 509.2 MB/s
> 
> Some notes about the implementation...
> 
> This datagram implementation forces datagrams to self-throttle according
> to the threshold set by sk_sndbuf. It behaves similar to the credits
> used by streams in its effect on throughput and memory consumption, but
> it is not influenced by the receiving socket as credits are.
> 
> The device drops packets silently. There is room for improvement by
> building into the device and driver some intelligence around how to
> reduce frequency of kicking the virtqueue when packet loss is high. I
> think there is a good discussion to be had on this.
> 
> In this series I am also proposing that fairness be reexamined as an
> issue separate from datagrams, which differs from my previous series
> that coupled these issues. After further testing and reflection on the
> design, I do not believe that these need to be coupled and I do not
> believe this implementation introduces additional unfairness or
> exacerbates pre-existing unfairness.
> 
> I attempted to characterize vsock fairness by using a pool of processes
> to stress test the shared resources while measuring the performance of a
> lone stream socket. Given unfair preference for datagrams, we would
> assume that a lone stream socket would degrade much more when a pool of
> datagram sockets was stressing the system than when a pool of stream
> sockets are stressing the system. The result, however, showed no
> significant difference between the degradation of throughput of the lone
> stream socket when using a pool of datagrams to stress the queue over
> using a pool of streams. The absolute difference in throughput actually
> favored datagrams as interfering least as the mean difference was +16%
> compared to using streams to stress test (N=7), but it was not
> statistically significant. Workloads were matched for payload size and
> buffer size (to approximate memory consumption) and process count, and
> stress workloads were configured to start before and last long after the
> lifetime of the "lone" stream socket flow to ensure that competing flows
> were continuously hot.
> 
> Given the above data, I propose that vsock fairness be addressed
> independent of datagrams and to defer its implementation to a future
> series.
> 
> Signed-off-by: Bobby Eshleman <bobby.eshleman@...edance.com>
> ---
> Bobby Eshleman (3):
>       virtio/vsock: support dgram
>       virtio/vsock: add VIRTIO_VSOCK_F_DGRAM feature bit
>       vsock: Add lockless sendmsg() support
> 
> Jiang Wang (1):
>       tests: add vsock dgram tests
> 
>  drivers/vhost/vsock.c                   |  17 +-
>  include/net/af_vsock.h                  |  20 ++-
>  include/uapi/linux/virtio_vsock.h       |   2 +
>  net/vmw_vsock/af_vsock.c                | 287 ++++++++++++++++++++++++++++----
>  net/vmw_vsock/diag.c                    |  10 +-
>  net/vmw_vsock/hyperv_transport.c        |  15 +-
>  net/vmw_vsock/virtio_transport.c        |  10 +-
>  net/vmw_vsock/virtio_transport_common.c | 221 ++++++++++++++++++++----
>  net/vmw_vsock/vmci_transport.c          |  70 ++++++--
>  tools/testing/vsock/util.c              | 105 ++++++++++++
>  tools/testing/vsock/util.h              |   4 +
>  tools/testing/vsock/vsock_test.c        | 193 +++++++++++++++++++++
>  12 files changed, 859 insertions(+), 95 deletions(-)
> ---
> base-commit: ed72bd5a6790a0c3747cb32b0427f921bd03bb71
> change-id: 20230413-b4-vsock-dgram-3b6eba6a64e5
> 
> Best regards,
> -- 
> Bobby Eshleman <bobby.eshleman@...edance.com>
> 

Powered by blists - more mailing lists