| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1270863015-19597-1-git-send-email-cristiklein@gmail.com>
Date: Sat, 10 Apr 2010 03:30:15 +0200
From: Cristian KLEIN <cristiklein@...il.com>
To: linux-kernel@...r.kernel.org
Cc: Cristian KLEIN <cristiklein@...il.com>
Subject: [PATCH] tcp: add setsockopt to disable slow start after idle
Allows user-space to override the sysctl
net.ipv4.tcp_slow_start_after_idle, on a per-socket bases, using
setsockopt().
Slow start after idle can harm some scientific applications which
interleave computation and communication. Assume we have an iterative
applications, each iteration consisting of a computation and a
communication phase. If the computation phase takes long enough (i.e.
more that 2*RTT), the communication phase will always slow start and
might never reach the wire speed.
This patch allows each application to disable slow start after idle,
just like we allow delay-sensitive applications (e.g. telnet, SSH) to
disable NAGLE.
Signed-off-by: Cristian KLEIN <cristiklein@...il.com>
---
include/linux/tcp.h | 4 +++-
net/ipv4/tcp.c | 10 ++++++++++
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_minisocks.c | 1 +
net/ipv4/tcp_output.c | 4 ++--
5 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index a778ee0..132aab0 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -105,6 +105,7 @@ enum {
#define TCP_COOKIE_TRANSACTIONS 15 /* TCP Cookie Transactions */
#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
+#define TCP_SLOW_START_AFTER_IDLE 18 /* Slow start after transmission idle */
/* for TCP_INFO socket option */
#define TCPI_OPT_TIMESTAMPS 1
@@ -345,7 +346,8 @@ struct tcp_sock {
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
thin_dupack : 1,/* Fast retransmit on first dupack */
- unused : 2;
+ slow_start_after_idle : 1,/* Slow start after transmission idle */
+ unused : 1;
/* RTT measurement */
u32 srtt; /* smoothed round trip time << 3 */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6afb6d8..3cf3863 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2252,6 +2252,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
}
break;
+ case TCP_SLOW_START_AFTER_IDLE:
+ if (val)
+ tp->slow_start_after_idle = 1;
+ else
+ tp->slow_start_after_idle = 0;
+ break;
+
case TCP_THIN_LINEAR_TIMEOUTS:
if (val < 0 || val > 1)
err = -EINVAL;
@@ -2497,6 +2504,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
case TCP_NODELAY:
val = !!(tp->nonagle&TCP_NAGLE_OFF);
break;
+ case TCP_SLOW_START_AFTER_IDLE:
+ val = tp->slow_start_after_idle;
+ break;
case TCP_CORK:
val = !!(tp->nonagle&TCP_NAGLE_CORK);
break;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f4df5f9..1380902 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1449,6 +1449,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
tcp_initialize_rcv_mss(newsk);
+ newtp->slow_start_after_idle = sysctl_tcp_slow_start_after_idle;
#ifdef CONFIG_TCP_MD5SIG
/* Copy over the MD5 key from the original socket */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 4199bc6..1e6f0bb 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -495,6 +495,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->rx_opt.ts_recent_stamp = 0;
newtp->tcp_header_len = sizeof(struct tcphdr);
}
+ newtp->slow_start_after_idle = sysctl_tcp_slow_start_after_idle;
#ifdef CONFIG_TCP_MD5SIG
newtp->md5sig_info = NULL; /*XXX*/
if (newtp->af_specific->md5_lookup(sk, newsk))
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f181b78..175d499 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -154,7 +154,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
struct inet_connection_sock *icsk = inet_csk(sk);
const u32 now = tcp_time_stamp;
- if (sysctl_tcp_slow_start_after_idle &&
+ if (tp->slow_start_after_idle &&
(!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto))
tcp_cwnd_restart(sk, __sk_dst_get(sk));
@@ -1279,7 +1279,7 @@ static void tcp_cwnd_validate(struct sock *sk)
if (tp->packets_out > tp->snd_cwnd_used)
tp->snd_cwnd_used = tp->packets_out;
- if (sysctl_tcp_slow_start_after_idle &&
+ if (tp->slow_start_after_idle &&
(s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto)
tcp_cwnd_application_limited(sk);
}
--
1.7.0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists