From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: Sivaprasad Tummala <Sivaprasad.Tummala@intel.com>,
Zhihong Wang <zhihong.wang@intel.com>,
Xiaolong Ye <xiaolong.ye@intel.com>
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH v1] vhost: dequeue zero copy with linear buffers
Date: Thu, 9 Apr 2020 16:08:55 +0200 [thread overview]
Message-ID: <90524d39-8924-6aff-1495-14eab4f0123b@redhat.com> (raw)
In-Reply-To: <20200326080349.4181-1-Sivaprasad.Tummala@intel.com>
On 3/26/20 9:03 AM, Sivaprasad Tummala wrote:
> Removed the linear buffer and zero_copy compatibility restriction.
>
> Applications that requires packets contained in a single buffer
> will enable linear buffer in vhost library. This restriction
> is not allowing zero_copy mode for such cases.
As discussed off-list, this restriction makes sense because we cannot
control how the guest splits the packets into chained descriptors.
So as soon as the zero-copy is enabled, we cannot guarantee the
application that buffers will be linear.
Regards,
Maxime
> Signed-off-by: Sivaprasad Tummala <Sivaprasad.Tummala@intel.com>
> ---
> lib/librte_vhost/socket.c | 6 ------
> 1 file changed, 6 deletions(-)
>
> diff --git a/lib/librte_vhost/socket.c b/lib/librte_vhost/socket.c
> index 7c8012179..e1afc290e 100644
> --- a/lib/librte_vhost/socket.c
> +++ b/lib/librte_vhost/socket.c
> @@ -920,12 +920,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
> ret = -1;
> goto out_mutex;
> }
> - if (vsocket->linearbuf) {
> - VHOST_LOG_CONFIG(ERR,
> - "error: zero copy is incompatible with linear buffers\n");
> - ret = -1;
> - goto out_mutex;
> - }
> vsocket->supported_features &= ~(1ULL << VIRTIO_F_IN_ORDER);
> vsocket->features &= ~(1ULL << VIRTIO_F_IN_ORDER);
>
>
prev parent reply other threads:[~2020-04-09 14:09 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-26 8:03 Sivaprasad Tummala
2020-04-09 14:08 ` Maxime Coquelin [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=90524d39-8924-6aff-1495-14eab4f0123b@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=Sivaprasad.Tummala@intel.com \
--cc=dev@dpdk.org \
--cc=xiaolong.ye@intel.com \
--cc=zhihong.wang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).