Enable ECN on multiple operating systems

Solaris

OSX

Linux

FreeBSD

notes to sort out:

[Tue Jun 21 2011]
What was the name of the bufferbloat-related sysctl parameter on Linux?
ECN? I’m drawing a blank. [07:43]
?
Got your plug?
Up and running.
heh
net.ipv4.tcp_ecn [07:44]
That’s it.
http://www.bufferbloat.net/projects/bloat/wiki/Dogfood_Principle I have it set to 2 which, as I recall, means “try ECN, but
fallback if it’s not there”
no, it’s worse than that
secondly this only applies to connections initiated from or to the
router [07:45]
dsack, and sack are good too
But it should help with NAT’ed connections, no?
I just got a guruplug version of openwrt built, but debian is WAY
easier to deal with.
no
proxied via something like polipo, yes [07:46]
Hmm. But the original problem you had here was that my crappy
Linksys didn’t grok ECN at all, and you had ECN = 1 on your Linux
box. Right?
right [07:47]
your router was not passing through the ECN bits - dying terribly.
Now you should be able to turn it on on the rest of your internal gear
So, if my plug router groks ECN, and I enable ECN on it, I gain …
what?
It’s a flow-control thing, isn’t it?
and have all the relative theoretical chocolaty goodness
yes
marking rather than dropping packets is a theoretical goodness [07:48]
Right. So, bottom line, I want to enable it on the plug, and
enable it (set to 2 or 1) on the various internal machines.
yes.
Interesting. Out of the box, the plug’s Debian has: [07:49]
net.ipv4.tcp_sack = 1
net.ipv4.tcp_ecn =
2
net.ipv4.tcp_dsack = 1

that are the best defaults for yesterday’s internet. The new hotness
is ecn
:)
The internal Ubuntu servers are similarly configured.
yep
ECN breakage was a real problem
Yes, but, IIRC, ecn=2 is essentially ecn=1, with a fallback to
oldness. [07:50]
in fact, we’ve fixed ECN, TOS, and Diffserv problems all over the
Linux stack in the last month.
ummmm
Or did I misunderstand your original explanation?
Or I was drunk…
ecn = 0 entirely disabled
ecn = 1 enabled
Right. I got that.
What is ecn=2?
ecn = 2…
I think means accept it if presented but don’t initiate it… Wait one
[07:51]
yea
Ah. So, ecn=2 on the router is fine, but I want ecn=1 on the
internal client machines.
so ecn=1 is good, and a fallback, like ecn=3 - if it existed, which
would have the desired fallback behavior would be good [07:52]
there’s a patch for that coming, I think
Sounds like I should leave the router at 2, in case there are
internal machines (e.g., windows breakage) that don’t do ECN.
heh
I’m not aware of ecn=1 breaking on ANYTHING except your old
router. You were the first, the last, and the worst.
but whatever
I’m just trying to grok this stuff. [07:53]
I’ll try 1 on the router, see what happens.
it helps to have qos on the router that applies it to streams that are
killing your life, rather than drops it… But that’s not a huge issue
for you as you have bandwidth to burn.
Man, this dream plug is sweet. Tiny, small footprint (physical and
electrical), quiet as all fuck, and real *nix, to boot.
thx for tryin it. How does the ‘dreamplug’ feel? Is it a better piece
of gear?
hahha
answered my question in advance [07:54]
Way better. I resurrected the GuruPlug, via the JTAG. Trying to
decide whether I have a use for it.
Or whether I should give it to someone (e.g., Costine) and spread
the love.
yea, I loved the openrd, but the interviening releases of sheevaplug
and guruplug left me cold. I’m also not happy with the wireless chip,
but that’s relatively minor.
spread the love, man….
That’s what I’m thinking. … Okay, time for a conf call. By then,
my kid should be awake and ready for waffles. [07:55]
BTW, the wireless is working just fine here.
I use rc.local to adjust the params via uapctl.
yea, well, start moving to the edge of the range and then watch your
ping times….
Not an issue here.

• dtaht plans to get one of these puppies too, after bmc is happy for a few
  weeks.
  I have four WAPs in this interference-laden place. :-)
• dtaht is using diversity mesh routing now with babel [07:56]
  babel + ahcpd is sweet
  sit down, plug in the laptop
  it figures out it’s on wired
  Something to look into, when I have time. If I ever have time
  again.
  unplug, it figures out you are on wireless
  Niiiice.
  streams, and connections, STAY UP
  Very sweet.
  Okay, time to make that call. Later.
  yea, it’s amazing how freeing it is to be able to plug in again.
  later [07:57]
  thx
  also the mesh routing ‘diversity’ means that I have several nodes that
  route over 5.x ghz and are aps over 2.4, and vice versa… Connect
  your neighbors
  whenever you get time I wanted to know how that meeting turned out.
  [07:58]
  What meeting? [08:00]
  some users group meeting of all the users groups [08:07]
  Right. I went to a lot of meetings last week. :-) That went
  well. We’re moving forward, trying to get common venues, common
  calendars, etc. [08:10]
  FYI, on Mac OS X: [08:12]
  \$ sysctl -a | egrep ‘ecn|sack’
  net.inet.tcp.ecn_initiate_out:
  0
  net.inet.tcp.ecn_negotiate_in: 0
  net.inet.tcp.sack:
  1
  net.inet.tcp.sack_maxholes:
  128
  net.inet.tcp.sack_globalmaxholes:
  65536
  net.inet.tcp.sack_globalholes: 0
  net.inet.ipsec.ecn:
  0
  net.inet6.ipsec6.ecn: 0
  
  heh. THANK YOU [08:22]
• dtaht wanted a mesh network in philly to implement.
  Another data point: (dancer:bmc) ~ \$ uname -s -r
  FreeBSD
  8.2-RELEASE
  (dancer:bmc) ~ \$ sysctl -a | egrep
  ‘sack|ecn’
  vfs.bufreusecnt: 932
  net.inet.tcp.ecn.maxretries:
  1
  net.inet.tcp.ecn.enable: 0
  net.inet.tcp.sack.globalholes:
  0
  net.inet.tcp.sack.globalmaxholes:
  65536
  net.inet.tcp.sack.maxholes: 128
  net.inet.tcp.sack.enable:
  1
  net.inet.sctp.enable_sack_immediately: [08:48]
  0
  net.inet.sctp.nr_sack_on_off: 0
  net.inet.sctp.sack_freq:
  2
  net.inet.sctp.delayed_sack_time: 200
  net.inet.sctp.strict_sacks:
  1
  net.inet.sctp.ecn_nonce: 0
  net.inet.sctp.ecn_enable:
  1
  
  sight [08:50]
  sigh [08:51]
  They’re all different.
  I have OpenSolaris here, too. Want that data point?
  sure
  Booting…
• dtaht just had 3 new olpcs arrive and is mildly distracted
  Nice. [08:52]
  They make good nightlights, I’m told.
  the 1.5s are better nightlights
  the 1.75s (I’m on the list) are cool
  I’m trying to convince them to add 5.x ghz support
  Every child should have that.
  hahahaha
  Hmm… SunOS 5.11. sysctl not found… [08:53]
  \$ ndd /dev/tcp \?|egrep -i ‘ecn|sack’
  tcp_sack_permitted
  (read and write)
  tcp_ecn_permitted (read and
  write)
  [08:58]
  (sunball:bmc) /etc \$ ndd -get /dev/tcp
  tcp_sack_permitted
  2
  (sunball:bmc) /etc \$ ndd -get /dev/tcp
  tcp_ecn_permitted
  1
  [08:59]
  
  http://download.oracle.com/docs/cd/E19963-01/html/821-1450/chapter4-31.html
  (Oracle Solaris Tunable Parameters Reference Manual)
  ecn: 0 (disabled), 1 (passive enabled), or 2 (active enabled)
  [09:00]
  Same values for SACK
  Defaults are as shown above. [09:01]
  excellent. [09:09]
  I just tweeted this: When you’ve spent the last decade mostly
  using Linux and BSD, the infrequent foray into Solaris feels like going
  to Mars. #unix
  So if I get you to turn it on, that will only leave about 2 billion
  computers left to fix and 10s of thousands or routers left to junk
  [09:10]
  heheheh
  solaris is like 1998
  I don’t even want to think about how one accomplishes this in
  HP/UX.
  Assuming it’s even possible.
  thx for the data I’m going to update the wiki in a bit
  Or, for that matter, AIX, which makes Mars seem familiar.
  hahahah
  do these things have sysctl.conf?
  I didn’t see a reference to an ndd.conf [09:11]
  http://www.sean.de/Solaris/soltune.html#ndd
  Worth skimming. [09:12]
  Of course, Solaris no longer has an /etc/rc.local, either.
  Instead, you’re supposed to create something in /etc/init.d
  (rc.local is fine), then symlink it to an “S” file in the appropriate
  runlevel directory (e.g., rc3.d).
  sigh
  Wait… [09:13]
  I just ran across this:
  To set parameters so they remain in effect after you reboot the
  system, add the parameter values to /etc/system when you want to
  configure parameters for all devices in the system.
  A startup script can also be used to set a ndd parameters across
  system reboots. Include the appropriate ndd command in a system startup
  script, such as the /etc/init.d/inetinit file or a customized script in
  /etc/rc2.d or /etc/rc3.d. Be sure to make a copy of any files before
  adding the ndd commands. [09:14]
  ERC>

http://www.vistax64.com/vista-general/53861-how-do-you-enable-ecn-explicit-congestion-notification.html
[09:15]
Gotta run. Back later.
ERC>