dccp ccid-3: use per-route RTO or TCP RTO as fallback

This makes RTAX_RTO_MIN also available to CCID-3, replacing the compile-time
RTO lower bound with a per-route tunable value.

The original Kconfig option solved the problem that a very low RTT (in the
order of HZ) can trigger too frequent and unnecessary reductions of the
sending rate.

This tunable does not affect the initial RTO value of 2 seconds specified in
RFC 5348, section 4.2 and Appendix B. But like the hardcoded Kconfig value,
it allows to adapt to network conditions.

The same effect as the original Kconfig option of 100ms is now achieved by

> ip route replace to unicast 192.168.0.0/24 rto_min 100j dev eth0

(assuming HZ=1000).

Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index cdb64922ba10cd2a647d390dd9bdc00e2e667ef4..271d524a4c8d53dc4fab4aa91fee28ea89fe4f62 100644 (file)
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -174,6 +174,9 @@ Per-route rto_min support
                > ip route change 10.0.0.0/24   rto_min 250j dev wlan0
                > ip route add    10.0.0.254/32 rto_min 800j dev wlan0
                > ip route show dev wlan0
+       CCID-3 also supports the rto_min setting: it is used to define the lower
+       bound for the expiry of the nofeedback timer. This can be useful on LANs
+       with very low RTTs (e.g., loopback, Gbit ethernet).
 
 
 Notes

diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig
index 8408398cd44e814cece7b9ec92615b1c615d32bd..0581143cb800d9b0b43bd86d0d2dcebf24abd3c1 100644 (file)
--- a/net/dccp/ccids/Kconfig
+++ b/net/dccp/ccids/Kconfig
@@ -47,37 +47,6 @@ config IP_DCCP_CCID3_DEBUG
 
          If in doubt, say N.
 
-config IP_DCCP_CCID3_RTO
-         int "Use higher bound for nofeedback timer"
-         default 100
-         depends on IP_DCCP_CCID3 && EXPERIMENTAL
-         ---help---
-           Use higher lower bound for nofeedback timer expiration.
-
-           The TFRC nofeedback timer normally expires after the maximum of 4
-           RTTs and twice the current send interval (RFC 3448, 4.3). On LANs
-           with a small RTT this can mean a high processing load and reduced
-           performance, since then the nofeedback timer is triggered very
-           frequently.
-
-           This option enables to set a higher lower bound for the nofeedback
-           value. Values in units of milliseconds can be set here.
-
-           A value of 0 disables this feature by enforcing the value specified
-           in RFC 3448. The following values have been suggested as bounds for
-           experimental use:
-               * 16-20ms to match the typical multimedia inter-frame interval
-               * 100ms as a reasonable compromise [default]
-               * 1000ms corresponds to the lower TCP RTO bound (RFC 2988, 2.4)
-
-           The default of 100ms is a compromise between a large value for
-           efficient DCCP implementations, and a small value to avoid disrupting
-           the network in times of congestion.
-
-           The purpose of the nofeedback timer is to slow DCCP down when there
-           is serious network congestion: experimenting with larger values should
-           therefore not be performed on WANs.
-
 config IP_DCCP_TFRC_LIB
        def_bool y if IP_DCCP_CCID3
 

diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 4340672a817cee58d27ddc63d7ac5c29bc8be2f2..278e170693229c7d0cc2af20ad6f6f1e8d9fe56c 100644 (file)
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -460,13 +460,12 @@ done_computing_x:
        sk->sk_write_space(sk);
 
        /*
-        * Update timeout interval for the nofeedback timer.
-        * We use a configuration option to increase the lower bound.
-        * This can help avoid triggering the nofeedback timer too
-        * often ('spinning') on LANs with small RTTs.
+        * Update timeout interval for the nofeedback timer. In order to control
+        * rate halving on networks with very low RTTs (<= 1 ms), use per-route
+        * tunable RTAX_RTO_MIN value as the lower bound.
         */
-       hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt, (CONFIG_IP_DCCP_CCID3_RTO *
-                                                      (USEC_PER_SEC / 1000)));
+       hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt,
+                                 USEC_PER_SEC/HZ * tcp_rto_min(sk));
        /*
         * Schedule no feedback timer to expire in
         * max(t_RTO, 2 * s/X)  =  max(t_RTO, 2 * t_ipi)

diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h
index b1864243be079cadfb63bbb05bb354cd371ef485..b7e569c22f3658f4c9366982902d05a43236a907 100644 (file)
--- a/net/dccp/ccids/ccid3.h
+++ b/net/dccp/ccids/ccid3.h
@@ -42,7 +42,7 @@
 #include "lib/tfrc.h"
 #include "../ccid.h"
 
-/* Two seconds as per RFC 3448 4.2 */
+/* Two seconds as per RFC 5348, 4.2 */
 #define TFRC_INITIAL_TIMEOUT      (2 * USEC_PER_SEC)
 
 /* In usecs - half the scheduling granularity as per RFC3448 4.6 */