From mboxrd@z Thu Jan 1 00:00:00 1970 From: John Heffner Subject: Re: 2.6.17 regression: Very slow net transfer from some hosts Date: Tue, 11 Apr 2006 20:32:12 -0400 Message-ID: <443C4A8C.8070407@psc.edu> References: <443C03E6.7080202@gentoo.org> <443C024C.2070107@psc.edu> <443C0B74.50305@gentoo.org> <443C09A7.2040900@psc.edu> <443C1738.20605@gentoo.org> <443C178B.3030805@psc.edu> <443C2BBA.5010804@gentoo.org> <20060411153315.4132b477@localhost.localdomain> <443C4471.7040407@gentoo.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Stephen Hemminger , netdev@vger.kernel.org, linux-kernel@vger.kernel.org Return-path: To: Daniel Drake In-Reply-To: <443C4471.7040407@gentoo.org> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Daniel Drake wrote: > Stephen Hemminger wrote: >> Turn off TCP window scaling, your performance will be limited but about >> as good as you can get with a corrupting firewall in between. [snip] > For anyone else interested, the ISP is NTL (UK). The fix: > > echo "4096 16384 131072 " > /proc/sys/net/ipv4/tcp_wmem > echo "4096 87380 174760 " > /proc/sys/net/ipv4/tcp_rmem For the record, I think Stephen's suggested workaround is better: echo 0 > /proc/sys/net/ipv4/tcp_window_scaling It will prevent the other end of the connection from using a window scale, so it "fixes" both directions of the connection, not just receiving. Thanks, -John