linux r的数据是存在,[讨论+资料：]如何取RWIN的合理值以提高网络速度？

QUOTE

Tuning a Linux 2.4 systemEnabling and disabling some of the advanced features of TCP:(Usually it is a good idea for these to be enabled)

QUOTE

/proc/sys/net/ipv4/tcp_timestamps        /proc/sys/net/ipv4/tcp_window_scaling        /proc/sys/net/ipv4/tcp_sack

To enable all these features, for example, do the following as root:

QUOTE

echo 1 > /proc/sys/net/ipv4/tcp_timestamps        echo 1 > /proc/sys/net/ipv4/tcp_window_scaling        echo 1 > /proc/sys/net/ipv4/tcp_sack

Path MTU discovery can be enabled and disabled using the following boolean sysctl variable:

QUOTE

/proc/sys/net/ipv4/ip_no_pmtu_disc

But be on the lookout for blackholes if this is enabled, as indicated at the beginning of the document. Please see the following URL for additional documentation on sysctl variables:http://www.linuxhq.com/kernel/v2.4/doc/net...sysctl.txt.htmlTuning the default and maximum window sizes:

QUOTE

/proc/sys/net/core/rmem_default   - default receive window        /proc/sys/net/core/rmem_max       - maximum receive window        /proc/sys/net/core/wmem_default   - default send window        /proc/sys/net/core/wmem_max       - maximum send window        /proc/sys/net/ipv4/tcp_rmem       - memory reserved for TCP rcv buffers        /proc/sys/net/ipv4/tcp_wmem       - memory reserved for TCP snd buffers

The following values would be reasonable for path with a large BDP:

QUOTE

echo 8388608 > /proc/sys/net/core/wmem_max        echo 8388608 > /proc/sys/net/core/rmem_max        echo "4096 87380 4194304" > /proc/sys/net/ipv4/tcp_rmem        echo "4096 65536 4194304" > /proc/sys/net/ipv4/tcp_wmem

You will find a short description in LINUX-SOURCE_DIR/Documentation/networking/ip-sysctl.txtIf you would like these changes to be preserved across reboots, it may be a good idea to add these commands to your /etc/rc.d/rc.local file.Linux users may want to look into the Web100 project. In addition to providing complete instrumentation of the TCP stack, it has features for doing auto tuning of send and receive buffers.For paths with a very large BDP, it also has some features that will allow you to get better transfers.User testimonial: With the tuned TCP stacks it was possible to get a maximum throughput between 1.5 - 1.8 Mbit/s via a 2Mbit/s satellite link, measured with netperf.