From: "Michael S. Tsirkin" <mst@redhat.com>
To: Jason Wang <jasowang@redhat.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>, Xi Wang <xii@google.com>,
"David S. Miller" <davem@davemloft.net>,
netdev@vger.kernel.org, Maxim Krasnyansky <maxk@qti.qualcomm.com>,
Neal Cardwell <ncardwell@google.com>,
Eric Dumazet <edumazet@google.com>
Subject: Re: [PATCH v2] net-tun: restructure tun_do_read for better sleep/wakeup efficiency
Date: Tue, 20 May 2014 09:34:03 +0300 [thread overview]
Message-ID: <20140520063403.GB6653@redhat.com> (raw)
In-Reply-To: <537AF036.7010005@redhat.com>
On Tue, May 20, 2014 at 02:03:34PM +0800, Jason Wang wrote:
> On 05/20/2014 01:11 PM, Eric Dumazet wrote:
> > On Tue, 2014-05-20 at 12:44 +0800, Jason Wang wrote:
> >> On 05/19/2014 10:09 PM, Eric Dumazet wrote:
> >>> About the sk_data_ready() and wake_up_all(), you missed the whole part
> >>> of the patch I think.
> >>>
> >>> Check how sock_def_readable() does everything properly and efficiently,
> >>> including the async part.
> >> But this changes (sk_data_ready()) has nothing related to switching to
> >> use __skb_recv_datagram()
> >>
> > This is totally related.
> >
> > I think you did not yet understood this patch
>
> Sorry for being unclear, but I think you misunderstand my meaning.
> >
> > Compare wake_up_all() and sk_data_ready() speeds, you'll be surprised.
> >
> > You should ask to yourself : Why do we use wq_has_sleeper() in
> > networking stacks ?
>
> See my first reply, I don't have objection that uses sk_data_ready() in
> tun_net_xmit(). My only concern is using sk_data_ready() in
> tun_detach_all():
>
> - It was only called during tun destroying, so I believe we don't care
> about the performance in this condition.
> - sk_data_ready() was usually called when there's something new to be
> processed which is not case in tun_detach_all()
OK so what does userspace do to notice change in behaviour?
I don't ask that you write a test but can you show us in
pseudo-code?
> - Not sure it was a problem but sock_def_readable() will not wake up
> uninterruptible task during tun destroying.
But task_uninterruptible here would really mean some in-kernel caller
hooking into this function? is there a way to create this from
userspace? If not we don't care.
> - If we make sock_fasync() works for tun in the future, it may send
> SIGIO to user process during tun destroying which is not expected.
>
> Thanks
I don't get this last comment. The patch does not touch fasync paths
at all. How can it break them?
next prev parent reply other threads:[~2014-05-20 6:35 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-05-16 22:11 [PATCH v2] net-tun: restructure tun_do_read for better sleep/wakeup efficiency Xi Wang
2014-05-19 9:27 ` Jason Wang
2014-05-19 14:09 ` Eric Dumazet
2014-05-20 4:44 ` Jason Wang
2014-05-20 4:52 ` Eric Dumazet
2014-05-20 6:35 ` Michael S. Tsirkin
2014-05-20 5:11 ` Eric Dumazet
2014-05-20 6:03 ` Jason Wang
2014-05-20 6:34 ` Michael S. Tsirkin [this message]
2014-05-20 6:55 ` Jason Wang
2014-05-20 13:59 ` Eric Dumazet
2014-05-21 4:45 ` Jason Wang
2014-05-19 16:06 ` Michael S. Tsirkin
2014-05-20 4:51 ` Jason Wang
2014-05-20 6:22 ` Michael S. Tsirkin
2014-05-20 6:40 ` Jason Wang
2014-05-21 7:54 ` Michael S. Tsirkin
2014-05-21 19:51 ` David Miller
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=20140520063403.GB6653@redhat.com \
--to=mst@redhat.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=jasowang@redhat.com \
--cc=maxk@qti.qualcomm.com \
--cc=ncardwell@google.com \
--cc=netdev@vger.kernel.org \
--cc=xii@google.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).