On Wed, 2007-06-20 at 19:16 +0800, Daniel wrote:
On Tue, 2007-06-12 at 11:21 +0800, Daniel wrote:
On Sun, 2007-06-10 at 20:25 +0800, Daniel wrote:
-- Bazsi
Sorry about my last encoded email.
I use tproxy-2.0.1 and kernel 2.6.9 and a http proxy, and I cann't move forward to new versions for some reason.
Today when I stop stress and check /proc/net/tproxy later, I found 3 entries always there: cat /proc/net/tproxy 00006 470ba8c0:0000 0a0ba8c0:0581 00000000:0000 00010000 00000 000001 1181498811:997708128 00006 700ba8c0:0000 0a0ba8c0:5a9e 00000000:0000 00010000 00000 000001 1181489066:124306088 00006 e80ba8c0:0000 0a0ba8c0:4c86 00000000:0000 00010000 00000 000001 1181425010:475244912
The process which opened these sockets were killed or is it still running?
-- Bazsi
hi,
I think it's the http proxy who initialized these sockets, and it was still running then.
Hmm.. tproxy closes these entries if: 1) the proxy closes the associated fd 2) the process exits (which implies 1 above)
FYI: I'm working on releasing tproxy4 which will resolve all the fundamental issues (like this).
-- Bazsi
Good news! I read the post from netfilter.org and I think that's much better than nat-based approach. http://lists.netfilter.org/pipermail/netfilter-devel/2007-January/026472.htm... Regards Daniel tooldcas@163.com 2007-06-29