I'd prefer to make it apply automatically across all congestion controls
that do slow-start, and also make the max_ssthresh parameter
controllable via sysctl. This patch (attached) should implement this.
Note the default value for sysctl_tcp_max_ssthresh = 0, which disables
limited slow-start. This should make ABC apply during LSS as well.
Note the patch is compile-tested only! I can do some real testing if
you'd like to apply this Dave.
Thanks,
-John
Angelo P. Castellani wrote:
Forgot the patch..
Angelo P. Castellani ha scritto:
From: Angelo P. Castellani <[EMAIL PROTECTED]>
RFC3742: limited slow start
See http://www.ietf.org/rfc/rfc3742.txt
Signed-off-by: Angelo P. Castellani <[EMAIL PROTECTED]>
---
To allow code reutilization I've added the limited slow start
procedure as an exported symbol of linux tcp congestion control.
On large BDP networks canonical slow start should be avoided because
it requires large packet losses to converge, whereas at lower BDPs
slow start and limited slow start are identical. Large BDP is defined
through the max_ssthresh variable.
I think limited slow start could safely replace the canonical slow
start procedure in Linux.
Regards,
Angelo P. Castellani
p.s.: in the attached patch is added an exported function currently
used only by YeAH TCP
include/net/tcp.h | 1 +
net/ipv4/tcp_cong.c | 23 +++++++++++++++++++++++
2 files changed, 24 insertions(+)
------------------------------------------------------------------------
diff -uprN linux-2.6.20-a/include/net/tcp.h linux-2.6.20-c/include/net/tcp.h
--- linux-2.6.20-a/include/net/tcp.h 2007-02-04 19:44:54.000000000 +0100
+++ linux-2.6.20-c/include/net/tcp.h 2007-02-19 10:54:10.000000000 +0100
@@ -669,6 +669,7 @@ extern void tcp_get_allowed_congestion_c
extern int tcp_set_allowed_congestion_control(char *allowed);
extern int tcp_set_congestion_control(struct sock *sk, const char *name);
extern void tcp_slow_start(struct tcp_sock *tp);
+extern void tcp_limited_slow_start(struct tcp_sock *tp);
extern struct tcp_congestion_ops tcp_init_congestion_ops;
extern u32 tcp_reno_ssthresh(struct sock *sk);
diff -uprN linux-2.6.20-a/net/ipv4/tcp_cong.c linux-2.6.20-c/net/ipv4/tcp_cong.c
--- linux-2.6.20-a/net/ipv4/tcp_cong.c 2007-02-04 19:44:54.000000000 +0100
+++ linux-2.6.20-c/net/ipv4/tcp_cong.c 2007-02-19 10:54:10.000000000 +0100
@@ -297,6 +297,29 @@ void tcp_slow_start(struct tcp_sock *tp)
}
EXPORT_SYMBOL_GPL(tcp_slow_start);
+void tcp_limited_slow_start(struct tcp_sock *tp)
+{
+ /* RFC3742: limited slow start
+ * the window is increased by 1/K MSS for each arriving ACK,
+ * for K = int(cwnd/(0.5 max_ssthresh))
+ */
+
+ const int max_ssthresh = 100;
+
+ if (max_ssthresh > 0 && tp->snd_cwnd > max_ssthresh) {
+ u32 k = max(tp->snd_cwnd / (max_ssthresh >> 1), 1U);
+ if (++tp->snd_cwnd_cnt >= k) {
+ if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+ tp->snd_cwnd++;
+ tp->snd_cwnd_cnt = 0;
+ }
+ } else {
+ if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+ tp->snd_cwnd++;
+ }
+}
+EXPORT_SYMBOL_GPL(tcp_limited_slow_start);
+
/*
* TCP Reno congestion control
* This is special case used for fallback as well.
Add RFC3742 Limited Slow-Start, controlled by variable sysctl_tcp_max_ssthresh.
Signed-off-by: John Heffner <[EMAIL PROTECTED]>
---
commit 97033fa201705e6cfc68ce66f34ede3277c3d645
tree 5df4607728abce93aa05b31015a90f2ce369abff
parent 8a03d9a498eaf02c8a118752050a5154852c13bf
author John Heffner <[EMAIL PROTECTED]> Mon, 19 Feb 2007 15:52:16 -0500
committer John Heffner <[EMAIL PROTECTED]> Mon, 19 Feb 2007 15:52:16 -0500
include/linux/sysctl.h | 1 +
include/net/tcp.h | 1 +
net/ipv4/sysctl_net_ipv4.c | 8 ++++++++
net/ipv4/tcp_cong.c | 33 +++++++++++++++++++++++----------
4 files changed, 33 insertions(+), 10 deletions(-)
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 2c5fb38..a2dce72 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -438,6 +438,7 @@ enum
NET_CIPSOV4_RBM_STRICTVALID=121,
NET_TCP_AVAIL_CONG_CONTROL=122,
NET_TCP_ALLOWED_CONG_CONTROL=123,
+ NET_TCP_MAX_SSTHRESH=124,
};
enum {
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5c472f2..521da28 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -230,6 +230,7 @@ extern int sysctl_tcp_mtu_probing;
extern int sysctl_tcp_base_mss;
extern int sysctl_tcp_workaround_signed_windows;
extern int sysctl_tcp_slow_start_after_idle;
+extern int sysctl_tcp_max_ssthresh;
extern atomic_t tcp_memory_allocated;
extern atomic_t tcp_sockets_allocated;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0aa3047..d68effe 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -803,6 +803,14 @@ #endif /* CONFIG_NETLABEL */
.proc_handler = &proc_allowed_congestion_control,
.strategy = &strategy_allowed_congestion_control,
},
+ {
+ .ctl_name = NET_TCP_MAX_SSTHRESH,
+ .procname = "tcp_max_ssthresh",
+ .data = &sysctl_tcp_max_ssthresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
{ .ctl_name = 0 }
};
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index c1b34f1..7fd2910 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -12,6 +12,8 @@ #include <linux/types.h>
#include <linux/list.h>
#include <net/tcp.h>
+int sysctl_tcp_max_ssthresh = 0;
+
static DEFINE_SPINLOCK(tcp_cong_list_lock);
static LIST_HEAD(tcp_cong_list);
@@ -271,10 +273,13 @@ #endif
/*
- * Linear increase during slow start
+ * Slow start (exponential increase) with
+ * RFC3742 Limited Slow Start (fast linear increase) support.
*/
void tcp_slow_start(struct tcp_sock *tp)
{
+ int cnt = 0;
+
if (sysctl_tcp_abc) {
/* RFC3465: Slow Start
* TCP sender SHOULD increase cwnd by the number of
@@ -283,17 +288,25 @@ void tcp_slow_start(struct tcp_sock *tp)
*/
if (tp->bytes_acked < tp->mss_cache)
return;
-
- /* We MAY increase by 2 if discovered delayed ack */
- if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache) {
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- }
}
+
+ if (sysctl_tcp_max_ssthresh > 0 &&
+ tp->snd_cwnd > sysctl_tcp_max_ssthresh)
+ cnt += sysctl_tcp_max_ssthresh>>1;
+ else
+ cnt += tp->snd_cwnd;
+
+ /* RFC3465: We MAY increase by 2 if discovered delayed ack */
+ if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache)
+ cnt <<= 1;
tp->bytes_acked = 0;
-
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
+
+ tp->snd_cwnd_cnt += cnt;
+ while (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
+ if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+ tp->snd_cwnd++;
+ tp->snd_cwnd_cnt -= tp->snd_cwnd;
+ }
}
EXPORT_SYMBOL_GPL(tcp_slow_start);
