]> git.michaelhowe.org Git - packages/o/openafs.git/commit
rx: Don't limit the # of packets sent in recovery
authorSimon Wilkinson <sxw@your-file-system.com>
Sat, 18 Jun 2011 12:17:07 +0000 (13:17 +0100)
committerDerrick Brashear <shadow@dementia.org>
Sat, 9 Jul 2011 05:06:31 +0000 (22:06 -0700)
commit4a4dab852e67c6a9bc720f5d5a5ecb815a70ca83
tree5d8cc95f02e6f02e504145cb31268d81041e4d10
parentc4e359b69a9f5e8a21cc06f7338595404d290cd2
rx: Don't limit the # of packets sent in recovery

The RX transmit engine limits the number of packets sent whilst in
loss recovery to one per invocation of the transmit engine. As the
engine cannot be called by the application thread whilst in recovery,
this means that we end up being limited to one packet per ACK received,
which means that despite a growing congestion window we'll only send
one packet per RTT (in effect, a congenstion window of 1).

This will remain the case until we exit recovery, and all of a sudden
can send a large number of packets. If this is larger than the current
capacity of the network, we'll probably end straight back in recovery
again.

Let the congestion window do its job, by removing this arbitrary limit.

Reviewed-on: http://gerrit.openafs.org/4868
Reviewed-by: Derrick Brashear <shadow@dementia.org>
Reviewed-by: Jeffrey Altman <jaltman@openafs.org>
Tested-by: Jeffrey Altman <jaltman@openafs.org>
Tested-by: BuildBot <buildbot@rampaginggeek.com>
(cherry picked from commit 91b351e88bdb56bfdfc2f5f16f64bb7522796581)

Change-Id: I673980bdee6d1316cb363f12d32c96fb2577cb27
Reviewed-on: http://gerrit.openafs.org/4940
Reviewed-by: Derrick Brashear <shadow@dementia.org>
Tested-by: Derrick Brashear <shadow@dementia.org>
src/rx/rx.c