| To: | "Injong Rhee" <rhee@xxxxxxxxxxxx> |
|---|---|
| Subject: | Re: [RFT] BIC TCP delayed ack compensation |
| From: | Stephen Hemminger <shemminger@xxxxxxxx> |
| Date: | Wed, 23 Feb 2005 11:36:41 -0800 |
| Cc: | "'Hubert Tonneau'" <hubert.tonneau@xxxxxxxxxxxxxx>, "'cliff white'" <cliffw@xxxxxxxx>, "'Alexey Kuznetsov'" <kuznet@xxxxxxxxxxxxx>, <netdev@xxxxxxxxxxx>, "'David S. Miller'" <davem@xxxxxxxxxxxxx> |
| In-reply-to: | <200502231830.j1NIUC2T019474@uni07mr.unity.ncsu.edu> |
| Organization: | Open Source Development Lab |
| References: | <052Q0TU11@server5.heliogroup.fr> <200502231830.j1NIUC2T019474@uni07mr.unity.ncsu.edu> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
An interesting test would be to repeat the slow case: 2.6.10-ac11 over 100Mbps
With first TCP Reno (old default).
sysctl -w net.ipv4.tcp_bic=0
then TCP Westwood.
sysctl -w net.ipv4.tcp_bic=0
sysctl -w net.ipv4.tcp_westwood=1
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Bug-hunting, David S. Miller |
|---|---|
| Next by Date: | Re: Bug-hunting, Christian Schmid |
| Previous by Thread: | RE: [RFT] BIC TCP delayed ack compensation, Injong Rhee |
| Next by Thread: | RE: [RFT] BIC TCP delayed ack compensation, Injong Rhee |
| Indexes: | [Date] [Thread] [Top] [All Lists] |