ipv4: Use binary search to choose tcp PMTU probe_size
Current probe_size is chosen by doubling mss_cache,
the probing process will end shortly with a sub-optimal
mss size, and the link mtu will not be taken full
advantage of, in return, this will make user to tweak
tcp_base_mss with care.
Use binary search to choose probe_size in a fine
granularity manner, an optimal mss will be found
to boost performance as its maxmium.
In addition, introduce a sysctl_tcp_probe_threshold
to control when probing will stop in respect to
the width of search range.
Test env:
Docker instance with vxlan encapuslation(82599EB)
iperf -c 10.0.0.24 -t 60
before this patch:
1.26 Gbits/sec
After this patch: increase 26%
1.59 Gbits/sec
Signed-off-by: Fan Du <fan.du@intel.com>
Acked-by: John Heffner <johnwheffner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 1085e12f..e051d39 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -87,6 +87,7 @@
int sysctl_tcp_fwmark_accept;
int sysctl_tcp_mtu_probing;
int sysctl_tcp_base_mss;
+ int sysctl_tcp_probe_threshold;
struct ping_group_range ping_group_range;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 834089b..1ad82e3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -67,6 +67,9 @@
/* The least MTU to use for probing */
#define TCP_BASE_MSS 1024
+/* Specify interval when tcp mtu probing will stop */
+#define TCP_PROBE_THRESHOLD 8
+
/* After receiving this amount of duplicate ACKs fast retransmit starts. */
#define TCP_FASTRETRANS_THRESH 3
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d151539..d3c09c1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -883,6 +883,13 @@
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "tcp_probe_threshold",
+ .data = &init_net.ipv4.sysctl_tcp_probe_threshold,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
{ }
};
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5a2dfed..35790d9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2460,6 +2460,7 @@
}
net->ipv4.sysctl_tcp_ecn = 2;
net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
+ net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
return 0;
fail:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8bbd86c..ed024cb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1842,11 +1842,13 @@
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_buff *skb, *nskb, *next;
+ struct net *net = sock_net(sk);
int len;
int probe_size;
int size_needed;
int copy;
int mss_now;
+ int interval;
/* Not currently probing/verifying,
* not in recovery,
@@ -1859,11 +1861,17 @@
tp->rx_opt.num_sacks || tp->rx_opt.dsack)
return -1;
- /* Very simple search strategy: just double the MSS. */
+ /* Use binary search for probe_size between tcp_mss_base,
+ * and current mss_clamp. if (search_high - search_low)
+ * smaller than a threshold, backoff from probing.
+ */
mss_now = tcp_current_mss(sk);
- probe_size = 2 * tp->mss_cache;
+ probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high +
+ icsk->icsk_mtup.search_low) >> 1);
size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
- if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
+ interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low;
+ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
+ interval < max(1, net->ipv4.sysctl_tcp_probe_threshold)) {
/* TODO: set timer for probe_converge_event */
return -1;
}