Development issues regarding the cerowrt test router project
 help / color / mirror / Atom feed
From: Dave Taht <dave.taht@gmail.com>
To: "cerowrt-devel@lists.bufferbloat.net"
	<cerowrt-devel@lists.bufferbloat.net>
Subject: [Cerowrt-devel] netflix through a sony BDP-S185 blue-ray player
Date: Mon, 17 Mar 2014 07:42:32 -0700	[thread overview]
Message-ID: <CAA93jw4sjRZ-3P+GMGbai4NdV+jYof_A4=e0RpV3KNAKsbq0cw@mail.gmail.com> (raw)

I tested netflix through a  sony BDP-S185 blue-ray player this morning.

It doesn't appear to be using  upnp,  and aside  from  one  glitch on
startup, streamed  a dr  who episode fine through  a 7mbit
down,768Mbit up SQM'd DSL system during a set of rrul tests, falling
back to 900kbit/sec.

ECN was enabled in both directions. I did something a little unusual
(by accident) on the test, running qfq+codel on the rrul client. I later
repeated the test with sch_fq to no ill effect.

(Linux puck 3.13.1-pie-4 #1 SMP PREEMPT Fri Jan 31 17:44:17 PST 2014
x86_64 x86_64 x86_64 GNU/Linux)

It is unclear to me how much buffering netflix clients have.

Later on I restarted sqm (with ecn disabled), which interrupted
playback briefly during the restart,
but was otherwise fine.

Plots & screenshots

http://snapon.lab.bufferbloat.net/~d/netflix/


config queue 'ge00'
    option interface 'ge00'
    option script 'simple.qos'
    option qdisc_advanced '1'
    option ingress_ecn 'ECN'
    option qdisc_really_really_advanced '1'
    option etarget 'auto'
    option linklayer 'atm'
    option overhead '40'
    option enabled '1'
    option download '6400'
    option upload '684'
    option qdisc 'fq_codel'
    option egress_ecn 'ECN'

root@lorna-gw:/etc/config# tc -s qdisc show dev ifb0
qdisc htb 1: root refcnt 2 r2q 10 default 12 direct_packets_stat 0
 Sent 2167186854 bytes 1564144 pkt (dropped 0, overlimits 1574115 requeues 0)
 backlog 0b 0p requeues 0
qdisc fq_codel 110: parent 1:11 limit 1001p flows 1024 quantum 500
target 5.0ms interval 100.0ms ecn
 Sent 636 bytes 4 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
  maxpacket 256 drop_overlimit 0 new_flow_count 1 ecn_mark 0
  new_flows_len 1 old_flows_len 0
qdisc fq_codel 120: parent 1:12 limit 1001p flows 1024 quantum 1500
target 5.0ms interval 100.0ms ecn
 Sent 2167186218 bytes 1564140 pkt (dropped 1858, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
  maxpacket 1749 drop_overlimit 0 new_flow_count 211883 ecn_mark 1443
  new_flows_len 1 old_flows_len 9
qdisc fq_codel 130: parent 1:13 limit 1001p flows 1024 quantum 300
target 5.0ms interval 100.0ms ecn
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
  maxpacket 256 drop_overlimit 0 new_flow_count 0 ecn_mark 0
  new_flows_len 0 old_flows_len 0

root@lorna-gw:/etc/config# tc -s qdisc show dev ge00
qdisc htb 1: root refcnt 2 r2q 10 default 12 direct_packets_stat 0
 Sent 195266734 bytes 760801 pkt (dropped 0, overlimits 431552 requeues 0)
 backlog 0b 0p requeues 0
qdisc fq_codel 110: parent 1:11 limit 1001p flows 1024 quantum 300
target 18.0ms interval 113.0ms ecn
 Sent 19141745 bytes 91385 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
  maxpacket 742 drop_overlimit 0 new_flow_count 35799 ecn_mark 0
  new_flows_len 1 old_flows_len 2
qdisc fq_codel 120: parent 1:12 limit 1001p flows 1024 quantum 300
target 18.0ms interval 113.0ms ecn
 Sent 176124989 bytes 669416 pkt (dropped 4835, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
  maxpacket 1749 drop_overlimit 0 new_flow_count 84298 ecn_mark 9065
  new_flows_len 1 old_flows_len 5
qdisc fq_codel 130: parent 1:13 limit 1001p flows 1024 quantum 300
target 18.0ms interval 113.0ms ecn
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0
  maxpacket 256 drop_overlimit 0 new_flow_count 0 ecn_mark 0
  new_flows_len 0 old_flows_len 0
qdisc ingress ffff: parent ffff:fff1 ----------------
 Sent 1867078978 bytes 1591897 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0


-- 
Dave Täht

Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.html

             reply	other threads:[~2014-03-17 14:42 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-03-17 14:42 Dave Taht [this message]
2014-03-20  1:29 ` Jim Reisert AD1C
2014-03-20  1:32   ` Jim Reisert AD1C
2014-03-20  2:17     ` Dave Taht
2014-03-20  2:26       ` Jim Reisert AD1C
2014-03-20 16:30 Jim Reisert AD1C

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://lists.bufferbloat.net/postorius/lists/cerowrt-devel.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAA93jw4sjRZ-3P+GMGbai4NdV+jYof_A4=e0RpV3KNAKsbq0cw@mail.gmail.com' \
    --to=dave.taht@gmail.com \
    --cc=cerowrt-devel@lists.bufferbloat.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox