From: Eric Dumazet <edumazet@google.com>
To: "David S . Miller" <davem@davemloft.net>
Cc: netdev <netdev@vger.kernel.org>,
Eric Dumazet <edumazet@google.com>,
Eric Dumazet <eric.dumazet@gmail.com>
Subject: [PATCH net-next 11/12] tcp: Namespace-ify sysctl_tcp_pacing_ss_ratio
Date: Fri, 27 Oct 2017 07:47:31 -0700 [thread overview]
Message-ID: <20171027144732.23885-12-edumazet@google.com> (raw)
In-Reply-To: <20171027144732.23885-1-edumazet@google.com>
Also remove an obsolete comment about TCP pacing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/netns/ipv4.h | 1 +
include/net/tcp.h | 1 -
net/ipv4/sysctl_net_ipv4.c | 18 +++++++++---------
net/ipv4/tcp_input.c | 9 +--------
net/ipv4/tcp_ipv4.c | 1 +
5 files changed, 12 insertions(+), 18 deletions(-)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index e52c2124b32e799f32943621cc0cc55dc7d8413d..eb2dcf1cbe61bf392e1c186e6fd1a11b82d8bad2 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -152,6 +152,7 @@ struct netns_ipv4 {
int sysctl_tcp_min_rtt_wlen;
int sysctl_tcp_autocorking;
int sysctl_tcp_invalid_ratelimit;
+ int sysctl_tcp_pacing_ss_ratio;
struct inet_timewait_death_row tcp_death_row;
int sysctl_max_syn_backlog;
int sysctl_tcp_fastopen;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5869a822ecb1b8f350cb393b4b43343ccf206eb5..2a5f8261ca03b76061dfbe85bbcf0fa15e5f8b40 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -250,7 +250,6 @@ extern int sysctl_tcp_rmem[3];
#define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */
-extern int sysctl_tcp_pacing_ss_ratio;
extern int sysctl_tcp_pacing_ca_ratio;
extern atomic_long_t tcp_memory_allocated;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 6a9349c27f00b1a665b969fe0291d195ec473e3e..7f0dba852d471a6e78d508d0b87966e26d4ca621 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -492,15 +492,6 @@ static struct ctl_table ipv4_table[] = {
.mode = 0644,
.proc_handler = proc_allowed_congestion_control,
},
- {
- .procname = "tcp_pacing_ss_ratio",
- .data = &sysctl_tcp_pacing_ss_ratio,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &thousand,
- },
{
.procname = "tcp_pacing_ca_ratio",
.data = &sysctl_tcp_pacing_ca_ratio,
@@ -1145,6 +1136,15 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
+ {
+ .procname = "tcp_pacing_ss_ratio",
+ .data = &init_net.ipv4.sysctl_tcp_pacing_ss_ratio,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &thousand,
+ },
{ }
};
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index db4d458d0205027681f96498019a5fd0bb0303b8..29539d39e61a0b99267e6c9b8f63b8acf6ae6200 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -767,13 +767,6 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
tp->srtt_us = max(1U, srtt);
}
-/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
- * Note: TCP stack does not yet implement pacing.
- * FQ packet scheduler can be used to implement cheap but effective
- * TCP pacing, to smooth the burst on large writes when packets
- * in flight is significantly lower than cwnd (or rwin)
- */
-int sysctl_tcp_pacing_ss_ratio __read_mostly = 200;
int sysctl_tcp_pacing_ca_ratio __read_mostly = 120;
static void tcp_update_pacing_rate(struct sock *sk)
@@ -793,7 +786,7 @@ static void tcp_update_pacing_rate(struct sock *sk)
* end of slow start and should slow down.
*/
if (tp->snd_cwnd < tp->snd_ssthresh / 2)
- rate *= sysctl_tcp_pacing_ss_ratio;
+ rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
else
rate *= sysctl_tcp_pacing_ca_ratio;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6617aae18ba2e2ad23663708a39311b0e987522d..1d8fc663af51f4d248de73ee30e28db44ffc940a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2507,6 +2507,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_min_rtt_wlen = 300;
net->ipv4.sysctl_tcp_autocorking = 1;
net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2;
+ net->ipv4.sysctl_tcp_pacing_ss_ratio = 200;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
--
2.15.0.rc2.357.g7e34df9404-goog
next prev parent reply other threads:[~2017-10-27 14:48 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-27 14:47 [PATCH net-next 00/12] tcp: move 12 sysctls to namespaces Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 01/12] tcp: Namespace-ify sysctl_tcp_nometrics_save Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 02/12] tcp: Namespace-ify sysctl_tcp_moderate_rcvbuf Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 03/12] tcp: Namespace-ify sysctl_tcp_tso_win_divisor Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 04/12] tcp: Namespace-ify sysctl_tcp_workaround_signed_windows Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 05/12] tcp: Namespace-ify sysctl_tcp_limit_output_bytes Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 06/12] tcp: Namespace-ify sysctl_tcp_challenge_ack_limit Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 07/12] tcp: Namespace-ify sysctl_tcp_min_tso_segs Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 08/12] tcp: Namespace-ify sysctl_tcp_min_rtt_wlen Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 09/12] tcp: Namespace-ify sysctl_tcp_autocorking Eric Dumazet
2017-10-27 14:47 ` [PATCH net-next 10/12] tcp: Namespace-ify sysctl_tcp_invalid_ratelimit Eric Dumazet
2017-10-27 14:47 ` Eric Dumazet [this message]
2017-10-27 14:47 ` [PATCH net-next 12/12] tcp: Namespace-ify sysctl_tcp_pacing_ca_ratio Eric Dumazet
2017-10-28 10:25 ` [PATCH net-next 00/12] tcp: move 12 sysctls to namespaces 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=20171027144732.23885-12-edumazet@google.com \
--to=edumazet@google.com \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=netdev@vger.kernel.org \
/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).