Jim, You are the first response. This tweak just helps your computer, it doesn't really do much/anything for the overall connection, but if it is the 'weakest link in the chain' it at least pushes the bottlenect to the next place :)
the 60- entries are 'user' files, and the 10- are the defaults that come with the system. You can just put the 60- file in there (I find it easiest to just do it as root). To make it take effect, either reboot or issue service procps start if you are running Ubuntu. (The last command I found in the /etc/syscntl.d/README file - it is a short but good read before doing this tweak) ><> ... Jack On Fri, Apr 26, 2013 at 10:36 PM, Jim Peterson <[email protected]>wrote: > Hey Y'all, > > Were there any responses to this that I may have missed? > > While I have a very slow & crappy internet provider, I'd like to try this > to see if I can get even 10Kbps (yes, 10 K!) more. I don't have any 60-* in > my sysctl.d directory, only 10-*. Do I just add another 10-, or should I > put a 60- in here or somewhere else? > > Jim Peterson > > > On 04/25/2013 08:23 PM, Jack Coats wrote: > > After trying to optimize my new higher-performance internet link, I have > found > a few tips to tune up IP traffic. > > It is more kernel tweaks, like: > > /etc/syscntl.d/60--ipv4-tweak.conf > contains > # > http://blog.eukhost.com/webhosting/how-to-optimize-tcp-ip-stack-in-linux/ > # > # Default settings are: > # root@nomad2:/etc/sysctl.d# sysctl net.core.rmem_max > # net.core.rmem_max = 131071 > # root@nomad2:/etc/sysctl.d# sysctl net.core.wmem_max > # net.core.wmem_max = 131071 > # root:/etc/sysctl.d# sysctl net.ipv4.tcp_rmem > # net.ipv4.tcp_rmem = 4096 87380 4046048 > # root:/etc/sysctl.d# sysctl net.ipv4.tcp_wmem > # net.ipv4.tcp_wmem = 4096 16384 4046048 > # > # > # > # Increase TCP max buffer size setable using setsockopt () > net.core.rmem_max = 16777216 > net.core.wmem_max = 16777216 > # Increase Linux autotuning TCP buffer limits > # Min, default, and max number of bytes to use > # Set max to at least 4MB, or higher if you use very high BDP paths > net.ipv4.tcp_rmem = 4096 87380 16777216 > net.ipv4.tcp_wmem = 4096 65536 16777216 > > Ok, I've done this, and it seems to be about 5% faster. > Anyone have some additional suggestions? > > ><> ... Jack > > -- -- You received this message because you are subscribed to the Google Groups "NLUG" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/nlug-talk?hl=en --- You received this message because you are subscribed to the Google Groups "NLUG" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/groups/opt_out.
