Aren
/
NetBSD
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
140,364 Commits 606 Branches 0 Tags 3.1 GiB
Commit Graph

13 Commits

Author SHA1 Message Date
yamt b8690cc289 tcp_sack_option: ignore sack beyond snd_max. 2005-05-08 04:46:20 +00:00
kurahone f7707899c1 Added sysctl tunable limits for the number of maximum SACK holes 
per connection and per system.

Idea taken from FreeBSD.
 2005-04-05 01:07:17 +00:00
kurahone 0eb940bc75 TCP/SACK changes from FreeBSD. 
Ignore the SACK option if
 * The packet is not an ACK.
 * The ACK is outside of snd_una -> snd_max
 2005-03-18 21:25:09 +00:00
yamt df05ca7085 simplify data receiver side sack processing. 
- introduce t_segqlen, the number of segments in segq/timeq.
  the name is from freebsd.
- rather than maintaining a copy of sack blocks (rcv_sack_block[]),
  build it directly from the segment list when needed.
 2005-03-16 00:39:56 +00:00
yamt 0446b7c3e3 - use full sized segments unless we actually have SACKs to send. 
- avoid TSO duplicate D-SACK.
- send SACKs regardless of TF_ACKNOW.
- don't clear rcv_sack_num when transmitting.

discussed on tech-net@.
 2005-03-16 00:38:27 +00:00
yamt a0f802e2ac tcp_sack_option: handle the case that the right-most sack'ed block is expanded. 
a fix from Noritoshi Demizu (FreeBSD PR/78226) via Kentaro A. Kurahone.
 2005-03-08 11:27:14 +00:00
yamt e55b9169d1 tcp_sack_option: fix the cases that some sack blocks go into a hole. 2005-03-07 10:27:39 +00:00
yamt ff614e1114 tcp_sack_option: fix a typo(?), which can cause to ignore valid blocks. 2005-03-07 09:40:35 +00:00
yamt ed8b840f26 tcp_sack_option: the max number of sack blocks in a packet is 4, not 3. 2005-03-07 09:32:51 +00:00
yamt e16a97f90b - unwrap short lines. 
- remove unneeded parenthesis.
- whitespace.
 2005-03-06 23:06:40 +00:00
yamt fd5005e8d7 don't assume alignment of sack options. 2005-03-06 23:05:56 +00:00
yamt 1152380a6b wrap long lines. 2005-03-06 23:05:20 +00:00
jonathan 4ae1f36dc9 Commit TCP SACK patches from Kentaro A. Karahone's patch at: 
http://www.sigusr1.org/~kurahone/tcp-sack-netbsd-02152005.diff.gz

Fixes in that patch for pre-existing TCP pcb initializations were already
committed to NetBSD-current, so are not included in this commit.

The SACK patch has been observed to correctly negotiate and respond,
to SACKs in wide-area traffic.

There are two indepenently-observed, as-yet-unresolved anomalies:
First, seeing unexplained delays between in fast retransmission
(potentially explainable by an 0.2sec RTT between adjacent
ethernet/wifi NICs); and second, peculiar and unepxlained TCP
retransmits observed over an ath0 card.

After discussion with several interested developers, I'm committing
this now, as-is, for more eyes to use and look over.  Current hypothesis
is that the anomalies above may in fact be due to link/level (hardware,
driver, HAL, firmware) abberations in the test setup, affecting  both
Kentaro's  wired-Ethernet NIC and in my two (different) WiFi NICs.
 2005-02-28 16:20:59 +00:00