100BASE-T).
So if the ISP->CPE path behaves like this, would it perhaps be nice to
have the CPE->ISP direction behave the same way?
--
Mikael Abrahamssonemail: swm...@swm.pp.se
hours because I just couldn't make it work, so anyone being a
master at that, I'd be very helpful translating this into "tc" conf :)
--
Mikael Abrahamssonemail: swm...@swm.pp.se
TOS bits, perhaps this is what's missing?
--
Mikael Abrahamssonemail: swm...@swm.pp.se
essen congestion on hour own link, because most of the time a provider
core will never buffer 100ms, it just doesn't make sense.
--
Mikael Abrahamssonemail: swm...@swm.pp.se
llow at least per-user
fairness in the upstream and something that perhaps sent ACKs and other
smaller packets ahead of the queue of larger data packets.
--
Mikael Abrahamssonemail: swm...@swm.pp.se
r for speed might actually be the CPU of the CPE, so the
queueing mechanism should preferrably be able to prioritize and gracefully
handle the case where the links are not full but instead the CPE CPU is
insufficient and that's what causing congestion/drops.
--
Mikael Abrahamsson
what about trying to
achieve some of that without needing LEDBAT by using the above technique?
--
Mikael Abrahamssonemail: swm...@swm.pp.se
k ECN traffic, drop non-ECN traffic
Buffer depth > 50 ms = drop all draffic
The congestion signal to TCP at buffer depth 30 ms is the same for both
ECN and non-ECN traffic, so I don't see how this would increase the delay?
--
Mikael Abrahamssonemail: swm...@swm.pp.se
irement, so it would be good if any AQM standard actually defined this
mechanism and it was part of the description.
--
Mikael Abrahamssonemail: swm...@swm.pp.se
On Thu, 4 Jul 2013, ietfdbh wrote:
Hi,
What is QUIC? Is there a draft?
https://docs.google.com/document/d/1RNHkx_VvKWyWg6Lr8SZ-saqsQx7rFV-ev2jRFUoVD34/preview?sle=true
http://blog.chromium.org/2013/06/experimenting-with-quic.html
http://en.wikipedia.org/wiki/QUIC
--
Mikael Abrahamsson
ent and find it interesting.
--
Mikael Abrahamssonemail: swm...@swm.pp.se
into your
proposal. AQM/Bufferbloat movement could perhaps benefit from this, but
the current thinking is to make sure that all streams get equal access to
the media with minimal influence between them, not that much to decide
what packets within a stream to select for drop.
--
Mikael Abraha
ce you're reading it from
their name badge), you get presentations, video and audio and text all in
one, all in a standard web browser.
So before being jabber scribe was slightly complicated. Not so anymore.
--
Mikael Abrahamssonemail: swm...@swm.pp.se
be tens of milliseconds apart.
--
Mikael Abrahamssonemail: swm...@swm.pp.se
case can cope with the additional latency of starting a new
connection, it is RECOMMENDED to use short-lived connections, instead of
maintaining a long-lived persistent connection using aliveness checks.
--
Mikael Abrahamssonemail: swm...@swm.pp.se
aused all kinds of problems. I wish everybody would
turn it on and keep it on.
--
Mikael Abrahamssonemail: swm...@swm.pp.se
Linux."
Which OSes default to this on?
--
Mikael Abrahamssonemail: swm...@swm.pp.se
17 matches
Mail list logo