Lines Matching +full:out +full:- +full:of +full:- +full:window

6 .\" Portions of this documentation were written at Keio University, Japan.
11 .\" 1. Redistributions of source code must retain the above copyright
12 .\"    notice, this list of conditions and the following disclaimer.
14 .\"    notice, this list of conditions and the following disclaimer in the
19 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
26 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
38 proportion of Explicit Congestion Notification (ECN) marks received from capable
41 DCTCP uses fraction of ECN marked packets to update congestion window.
42 The window reduction ratio is always <= 1/2.
43 Only when all of the packets are
44 marked, congestion window is halved.
46 In order to keep the accuracy of the ECN marked fraction, a DCTCP receiver
52 DCTCP implementation includes two minor modifications for the one-sided
68 branch of the
71 .Bl -tag -width ".Va slowstart"
75 window to half, if a CE is observed in the first window and
84 to the most recent observed window.
86 gain of 1 / ( 2 ^
90 A flag if the congestion window should be reduced by one half after slow start.
93 Controls if a DCTCP session should use IP ECT(0) marking when sending out
94 segments (default), or ECT(1) marking making use of L4S infrastructure.
119 .%U "http://research.microsoft.com/pubs/121386/dctcp-public.pdf"
122 .%P "63-74"
142 .An -nosplit