aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/Kconfig
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/Kconfig')
-rw-r--r--net/ipv4/Kconfig21
1 files changed, 21 insertions, 0 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 567b03b1c349..712ebacacb62 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -433,5 +433,26 @@ config IP_TCPDIAG
433config IP_TCPDIAG_IPV6 433config IP_TCPDIAG_IPV6
434 def_bool (IP_TCPDIAG=y && IPV6=y) || (IP_TCPDIAG=m && IPV6) 434 def_bool (IP_TCPDIAG=y && IPV6=y) || (IP_TCPDIAG=m && IPV6)
435 435
436# TCP Reno is builtin (required as fallback)
437menu "TCP congestion control"
438 depends on INET
439
440config TCP_CONG_BIC
441 tristate "Binary Increase Congestion (BIC) control"
442 depends on INET
443 default y
444 ---help---
445 BIC-TCP is a sender-side only change that ensures a linear RTT
446 fairness under large windows while offering both scalability and
447 bounded TCP-friendliness. The protocol combines two schemes
448 called additive increase and binary search increase. When the
449 congestion window is large, additive increase with a large
450 increment ensures linear RTT fairness as well as good
451 scalability. Under small congestion windows, binary search
452 increase provides TCP friendliness.
453 See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
454
455endmenu
456
436source "net/ipv4/ipvs/Kconfig" 457source "net/ipv4/ipvs/Kconfig"
437 458