TCP: fix cubic RTO reaction.
Proper TCP Cubic operation requires the knowledge of the maximum congestion window prior to the last congestion event. This restores and improves a bugfix previously added by jtl@ but subsequently removed due to a revert. Reported by: chengc_netapp.com Reviewed by: chengc_netapp.com, tuexen (mentor) Approved by: tuexen (mentor), rgrimes (mentor) MFC after: 2 weeks Sponsored by: NetApp, Inc. Differential Revision: https://reviews.freebsd.org/D25133
This commit is contained in:
parent
9dc7d8a246
commit
6e26dd0dbe
Notes:
svn2git
2020-12-20 02:59:44 +00:00
svn path=/head/; revision=362580
@ -313,10 +313,15 @@ cubic_cong_signal(struct cc_var *ccv, uint32_t type)
|
||||
* timeout has fired more than once, as there is a reasonable
|
||||
* chance the first one is a false alarm and may not indicate
|
||||
* congestion.
|
||||
* This will put Cubic firmly into the concave / TCP friendly
|
||||
* region, for a slower ramp-up after two consecutive RTOs.
|
||||
*/
|
||||
if (CCV(ccv, t_rxtshift) >= 2) {
|
||||
cubic_data->flags |= CUBICFLAG_CONG_EVENT;
|
||||
cubic_data->t_last_cong = ticks;
|
||||
cubic_data->max_cwnd = CCV(ccv, snd_cwnd_prev);
|
||||
cubic_data->K = cubic_k(cubic_data->max_cwnd /
|
||||
CCV(ccv, t_maxseg));
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
Loading…
Reference in New Issue
Block a user