net.inet.tcp.inflight_enable

Matthew Dillon dillon at apollo.backplane.com
Fri Jul 8 14:36:28 PDT 2005


:> Sorry, actually, I always set net.inet.tcp.inflight_enable to zero
:> both on DragonFlyBSD and FreeBSD in my experiences (I know it is zero
:> on DragonFlyBSD by default, but I want to make it sure), because
:> unfortunately it reduces throughput in my experiences in an unexpected
:> way.
:
:I'd like to show an example where TCP throughput was reduced by
:setting net.inet.tcp.inflight_enable=1.
:
:  http://www.demizu.org/~noritosi/memo/2005/0706/
:
:The first graph shows a TCP behavior when net.inet.tcp.inflight_enable=0.
:Since congestion window grows exponentially, it took 5 RTTs (about 100ms)
:to send 64KB data.
:
:The second graph shows a TCP behavior when net.inet.tcp.inflight_enable=1.
:Since congestion window is almost unchanged, it took 14 RTTs (about 300ms)
:to send 64KB data.
:
:When I sent larger data, the difference became much larger.
:(e.g., 167ms and 1330ms when I sent 512KB data.  RTT=20ms)
:
:(Note: according to the graphs,
: "cwnd = 3 * 2^RTT" vs. "cwnd = 3 + RTT/N (N is about 10?)")
:
:Regards,
:Noritoshi Demizu

    Try increasing net.inet.tcp.inflight_stab from 20 to 40 and
    see if that fixes ethe congestion window expansion problem.  I'm
    not sure why the congestion window isn't expanding.

					-Matt
					Matthew Dillon 
					<dillon at xxxxxxxxxxxxx>





More information about the Kernel mailing list