[Bug 2441] xfwp not IPv6-aware
bugzilla-daemon at freedesktop.org
bugzilla-daemon at freedesktop.org
Tue Feb 1 18:47:21 PST 2005
Please do not reply to this email: if you want to comment on the bug, go to
the URL shown below and enter yourcomments there.
https://bugs.freedesktop.org/show_bug.cgi?id=2441
ajax at nwnk.net changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |ajax at nwnk.net
------- Additional Comments From ajax at nwnk.net 2005-02-01 18:47 -------
(In reply to comment #2)
> xfwp still has several advantages including the fact that it doesn't suck - the
> ssh forwarding always adds a very high latency penalty on the clients (similar
> to a 10base5 line running over tons of hubs)
not really. i ran a quick test of XSync latency over various transports on my
machine (2xP3 700MHz) and got the following numbers:
Direct connection, PF_UNIX transport: 0.125ms
Direct connection, PF_INET transport: 0.302ms
lbxproxy: 0.411ms
xfwp: 0.633ms
ssh2 forwarding, no compression: 0.900ms
ssh2 forwarding, compression: 1.044ms
(for reference, 'ping 127.0.0.1' gave a latency of 0.135ms)
this is pretty close to best case latency, since we're not touching the network
at all. once the bits are on the network they travel at the same speed and it's
just a matter of how many bits you move...
0.3ms doesn't really count as a very high latency penalty. yes, there's
processing delay for adding compression and encryption, but given a modern CPU
this is balanced by the lowered packet count.
> and running multiple clients over a
> ssh connections makes it even worse.
again, not sure how this could be true. since ssh multiplexes all X connections
over a single stream they share the benefits of compression and lowered packet
count, as well as Nagling to the channel bandwidth faster.
none of which is to say xfwp shouldn't have ipv6 support of course.
--
Configure bugmail: https://bugs.freedesktop.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.
More information about the xorg-bugzilla-noise
mailing list