linux/net/dccp
Gerrit Renker 1435562d7e dccp ccid-2: Replace broken RTT estimator with better algorithm
The current CCID-2 RTT estimator code is in parts broken and lags behind the
suggestions in RFC2988 of using scaled variants for SRTT/RTTVAR. 
That code is replaced by the present patch, which reuses the Linux TCP RTT
estimator code - reasons for this code duplication are given below.

Further details:
----------------
 1. The minimum RTO of previously one second has been replaced with TCP's, since
    RFC4341, sec. 5 says that the minimum of 1 sec. (suggested in RFC2988, 2.4)
    is not necessary. Instead, the TCP_RTO_MIN is used, which agrees with DCCP's
    concept of a default RTT (RFC 4340, 3.4). 
 2. The maximum RTO has been set to DCCP_RTO_MAX (64 sec), which agrees with 
    RFC2988, (2.5). 
 3. De-inlined the function ccid2_new_ack().
 4. Added a FIXME: the RTT is sampled several times per Ack Vector, which will
    give the wrong estimate. It should be replaced with one sample per Ack.
    However, at the moment this can not be resolved easily, since     
    - it depends on TX history code (which also needs some work),
    - the cleanest solution is not to use the `sent' time at all (saves 4 bytes
      per entry) and use DCCP timestamps / elapsed time to estimated the RTT,
      which however is non-trivial to get right (but needs to be done).

Reasons for reusing the Linux TCP estimator algorithm:   
------------------------------------------------------
Some time was spent to find a better alternative, using basic RFC2988 as a first
step. Further analysis and experimentation showed that the Linux TCP RTO
estimator is superior to a basic RFC2988 implementation. A summary is on
http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/ccid2/rto_estimator/

In addition, this estimator fared well in a recent empirical evaluation:

    Rewaskar, Sushant, Jasleen Kaur and F. Donelson Smith.
    A Performance Study of Loss Detection/Recovery in Real-world TCP
    Implementations. Proceedings of 15th IEEE International
    Conference on Network Protocols (ICNP-07). 2007.

Thus there is significant benefit in reusing the existing TCP code.


Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
2008-09-04 07:45:39 +02:00
..
ccids dccp ccid-2: Replace broken RTT estimator with better algorithm 2008-09-04 07:45:39 +02:00
ackvec.c dccp ccid-2: Separate option parsing from CCID processing 2008-09-04 07:45:37 +02:00
ackvec.h dccp ccid-2: Separate option parsing from CCID processing 2008-09-04 07:45:37 +02:00
ccid.c dccp: Auto-load (when supported) CCID plugins for negotiation 2008-09-04 07:45:31 +02:00
ccid.h dccp: Return-value convention of hc_tx_send_packet() 2008-09-04 07:45:38 +02:00
dccp.h dccp: Refine the wait-for-ccid mechanism 2008-09-04 07:45:38 +02:00
diag.c dccp ccid-2: Phase out the use of boolean Ack Vector sysctl 2008-09-04 07:45:31 +02:00
feat.c dccp ccid-2: Use feature-negotiation to report Ack Ratio changes 2008-09-04 07:45:32 +02:00
feat.h dccp: Debugging functions for feature negotiation 2008-09-04 07:45:32 +02:00
input.c dccp ccid-2: Consolidate Ack-Vector processing within main DCCP module 2008-09-04 07:45:37 +02:00
ipv4.c dccp: Cleanup routines for feature negotiation 2008-09-04 07:45:26 +02:00
ipv6.c dccp: Cleanup routines for feature negotiation 2008-09-04 07:45:26 +02:00
ipv6.h Remove obsolete #include <linux/config.h> 2006-06-30 19:25:36 +02:00
Kconfig dccp ccid-2: Remove old infrastructure 2008-09-04 07:45:37 +02:00
Makefile dccp ccid-2: Remove old infrastructure 2008-09-04 07:45:37 +02:00
minisocks.c dccp: Fix the adjustments to AWL and SWL 2008-09-04 07:45:35 +02:00
options.c dccp ccid-2: Separate option parsing from CCID processing 2008-09-04 07:45:37 +02:00
output.c dccp: Refine the wait-for-ccid mechanism 2008-09-04 07:45:38 +02:00
probe.c dccp: Reduce noise in output and convert to ktime_t 2008-09-04 07:45:36 +02:00
proto.c dccp: Refine the wait-for-ccid mechanism 2008-09-04 07:45:38 +02:00
sysctl.c dccp: Initialisation and type-checking of feature sysctls 2008-09-04 07:45:32 +02:00
timer.c dccp: Refine the wait-for-ccid mechanism 2008-09-04 07:45:38 +02:00