dccp test-tree [Patch 1/1] ccid-3: use per-route min-RTO and/or TCP default

dccp test-tree [Patch 1/1] ccid-3: use per-route min-RTO and/or TCP default

[Gerrit Renker]

This patch relates to the similar one submitted last week for CCID-2.

It replaces the hardcoded (Kconfig) value of the minimum RTO value with
a reconfigurable, per-route value which falls back to the TCP minimum
RTO value.

Leando, Ivo, can you please have a look and indicate whether you are ok
with this? If yes I would like to also update the CCID-4 tree to make it
consistent with the test tree - for this reason the test tree has not yet
been updated.

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

This makes the TCP (per-route) RTO value also available to CCID-3, hence it
is now possible to influence this value at runtime rather than, as before,
via Kconfig.

The same effect as the default 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>
---
 net/dccp/ccids/Kconfig |   31 -------------------------------
 net/dccp/ccids/ccid3.c |    9 ++++-----
 2 files changed, 4 insertions(+), 36 deletions(-)

--- 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
 
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -461,12 +461,11 @@ done_computing_x:
 
 	/*
 	 * 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.
+	 * We use the current (per-route) value of the TCP RTO as lower bound
+	 * to slow down rate-halving on networks with small RTTs (loopback,
+	 * running DCCP in a virtual machine, Gbit ethernet, etc).
 	 */
-	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(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)

Re: dccp test-tree [Patch 1/1] ccid-3: use per-route min-RTO and/or TCP default

[Ivo Calado]

Acked-by: Ivo Calado <ivocalado@embedded.ufcg.edu.br>  for ccid4 subtree

On Mon, Aug 16, 2010 at 02:19, Gerrit Renker <gerrit@erg.abdn.ac.uk> wrote:
> This patch relates to the similar one submitted last week for CCID-2.
>
> It replaces the hardcoded (Kconfig) value of the minimum RTO value with
> a reconfigurable, per-route value which falls back to the TCP minimum
> RTO value.
>
> Leando, Ivo, can you please have a look and indicate whether you are ok
> with this? If yes I would like to also update the CCID-4 tree to make it
> consistent with the test tree - for this reason the test tree has not yet
> been updated.
>
>>>>>>>>>>>>>>>>>>>>>>>> Patch <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
> dccp ccid-3: use per-route RTO or TCP RTO as fallback
>
> This makes the TCP (per-route) RTO value also available to CCID-3, hence it
> is now possible to influence this value at runtime rather than, as before,
> via Kconfig.
>
> The same effect as the default 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>
> ---
>  net/dccp/ccids/Kconfig |   31 -------------------------------
>  net/dccp/ccids/ccid3.c |    9 ++++-----
>  2 files changed, 4 insertions(+), 36 deletions(-)
>
> --- 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
>
> --- a/net/dccp/ccids/ccid3.c
> +++ b/net/dccp/ccids/ccid3.c
> @@ -461,12 +461,11 @@ done_computing_x:
>
>        /*
>         * 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.
> +        * We use the current (per-route) value of the TCP RTO as lower bound
> +        * to slow down rate-halving on networks with small RTTs (loopback,
> +        * running DCCP in a virtual machine, Gbit ethernet, etc).
>         */
> -       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(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)
>



-- 
Ivo Augusto Andrade Rocha Calado
PhD candidate in Electrical Engineering
Embedded Systems and Pervasive Computing Lab - http://embedded.ufcg.edu.br
Electrical Engineering Department - http://dee.ufcg.edu.br/
Electrical Engineering and Informatics Center - http://www.ceei.ufcg.edu.br
Federal University of Campina Grande - http://www.ufcg.edu.br

PGP: 0xD7C3860A pgp.mit.edu
Putt's Law:
       Technology is dominated by two types of people:
               Those who understand what they do not manage.
               Those who manage what they do not understand.

Re: dccp test-tree [Patch 1/1] ccid-3: use per-route min-RTO and/or TCP default

[Gerrit Renker]

[-- Attachment #1: Type: text/plain, Size: 1240 bytes --]

Ivo,-
| Acked-by: Ivo Calado <ivocalado@embedded.ufcg.edu.br>  for ccid4 subtree
| 
| On Mon, Aug 16, 2010 at 02:19, Gerrit Renker <gerrit@erg.abdn.ac.uk> wrote:
| > This patch relates to the similar one submitted last week for CCID-2.
| >
| > It replaces the hardcoded (Kconfig) value of the minimum RTO value with
| > a reconfigurable, per-route value which falls back to the TCP minimum
| > RTO value.
| >
| > Leando, Ivo, can you please have a look and indicate whether you are ok
| > with this? If yes I would like to also update the CCID-4 tree to make it
| > consistent with the test tree - for this reason the test tree has not yet
| > been updated.
| >
| >>>>>>>>>>>>>>>>>>>>>>>> Patch <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
| > dccp ccid-3: use per-route RTO or TCP RTO as fallback
| >
Thank you for the (offline) review, I have revised the patch, uploaded the one for CCID-3
at 182be62cc2899ddf7adb0c7654792f7061373a8a of the test tree.

The corresponding (revised) patch for CCID-4 has been integrated into 

    http://eden-feed.erg.abdn.ac.uk/cgi-bin/gitweb.cgi?p=dccp_exp.git;a=commitdiff;h=57ebee26dc7125f5cff75f0153ef3cd2bfd03c1d

Please find attached the "inter-diff" of the changes I applied to the CCID-4 subtree.

[-- Attachment #2: ccid4_INTER.diff --]
[-- Type: text/x-diff, Size: 3188 bytes --]

--- a/net/dccp/ccids/Kconfig
+++ b/net/dccp/ccids/Kconfig
@@ -65,37 +65,6 @@ config IP_DCCP_CCID3_MEASURE_S_AS_MAX
 	---help---
 	  An experimental method based on tracking the maximum packet size.
 endchoice
-
-config IP_DCCP_CCID3_RTO
-	int "Use higher bound for nofeedback timer"
-	default 100
-	depends on IP_DCCP_CCID3
-	---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 5348, 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 5348. 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.
 endif	# IP_DCCP_CCID3
 
 config IP_DCCP_CCID4
@@ -114,8 +83,7 @@ config IP_DCCP_CCID4
 	  sending rate, possibly with Explicit Congestion Notification (ECN),
 	  while minimizing abrupt rate changes.
 
-	  CCID-4 is based an (expired) Internet-Draft which can be found at:
-	  http://tools.ietf.org/html/draft-ietf-dccp-ccid4
+	  CCID-4 is specified in RFC 5622.
 
 	  If in doubt, say N.
 
@@ -150,13 +118,6 @@ config IP_DCCP_CCID4_MEASURE_S_AS_MAX
 	---help---
 	  An experimental method based on tracking the maximum packet size.
 endchoice
-
-config IP_DCCP_CCID4_RTO
-	int "Use higher bound for nofeedback timer"
-	default 100
-	---help---
-	  This item does for CCID-3 as DCCP_CCID3_RTO does for CCID-3, please
-	  see the help text there.
 endif	# IP_DCCP_CCID4
 
 config IP_DCCP_TFRC_LIB
--- a/net/dccp/ccids/ccid4.c
+++ b/net/dccp/ccids/ccid4.c
@@ -445,12 +445,12 @@ done_computing_x:
 
 	/*
 	 * 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.
+	 * We use the current (per-route) value of the TCP RTO as lower bound
+	 * to slow down rate-halving on networks with small RTTs (loopback,
+	 * running DCCP in a virtual machine, Gbit ethernet, etc).
 	 */
-	hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt, (CONFIG_IP_DCCP_CCID4_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)