From: Daniel Borkmann <dborkman@redhat.com>
To: Dan Ballard <dan@mindstab.net>
Cc: Lennart Poettering <lennart@poettering.net>,
kay.sievers@vrfy.org, Arnd Bergmann <arnd@arndb.de>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Eliezer Tamir <eliezer.tamir@linux.intel.com>,
Neil Horman <nhorman@tuxdriver.com>,
Li Zefan <lizefan@huawei.com>,
linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org,
netdev@vger.kernel.org,
Hannes Frederic Sowa <hannes@stressinduktion.org>
Subject: Re: [PATCH 1/1] Per socket value for max datagram queue length
Date: Wed, 22 Jan 2014 16:32:08 +0100 [thread overview]
Message-ID: <52DFE478.5030202@redhat.com> (raw)
In-Reply-To: <13e8aad86903481261581de7c29444e3@mindstab.net>
On 01/22/2014 04:11 PM, Dan Ballard wrote:
> Provides a new option for setsockopt SO_MAX_DGRAM_QLEN that sets and
> gets a socket specific max datagram queue length. Currently each socket
> has one but it's only ever initialized from
> /proc/sys/net/unix/max_dgram_qlen and then never adjustable later. Now
> each socket can have it individually tweaked during it's life.
>
> Signed-off-by: Dan Ballard <dan@mindstab.net>
> ---
> include/uapi/asm-generic/socket.h | 2 ++
> net/core/sock.c | 7 +++++++
> 2 files changed, 9 insertions(+)
>
> diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
> index 38f14d0..f8c3e6b 100644
> --- a/include/uapi/asm-generic/socket.h
> +++ b/include/uapi/asm-generic/socket.h
> @@ -80,4 +80,6 @@
>
> #define SO_MAX_PACING_RATE 47
>
> +#define SO_MAX_DGRAM_QLEN 48
> +
This needs to be added in more than just asm-generic, e.g.
have a look at SO_MAX_PACING_RATE or SO_BPF_EXTENSIONS.
Also you might need to rebase to current net-next head and
maybe describe use cases more in-depth; next to what Hannes
just commented.
> #endif /* __ASM_GENERIC_SOCKET_H */
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 5393b4b..1ff69d1 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -915,6 +915,10 @@ set_rcvbuf:
> sk->sk_max_pacing_rate);
> break;
>
> + case SO_MAX_DGRAM_QLEN:
> + sk->sk_max_ack_backlog = val;
> + break;
> +
> default:
> ret = -ENOPROTOOPT;
> break;
> @@ -1182,6 +1186,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
> v.val = sk->sk_max_pacing_rate;
> break;
>
> + case SO_MAX_DGRAM_QLEN:
> + v.val = sk->sk_max_ack_backlog;
> + break;
> default:
> return -ENOPROTOOPT;
> }
prev parent reply other threads:[~2014-01-22 15:32 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-22 15:11 [PATCH 1/1] Per socket value for max datagram queue length Dan Ballard
2014-01-22 15:20 ` Hannes Frederic Sowa
2014-01-22 15:32 ` Hannes Frederic Sowa
2014-01-22 15:30 ` Eric Dumazet
2014-01-22 15:32 ` Daniel Borkmann [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=52DFE478.5030202@redhat.com \
--to=dborkman@redhat.com \
--cc=arnd@arndb.de \
--cc=dan@mindstab.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=eliezer.tamir@linux.intel.com \
--cc=hannes@stressinduktion.org \
--cc=kay.sievers@vrfy.org \
--cc=lennart@poettering.net \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan@huawei.com \
--cc=netdev@vger.kernel.org \
--cc=nhorman@tuxdriver.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).