From: Jonathan Morton <chromatix99@gmail.com>
To: Dendari Marini <dendari92@gmail.com>
Cc: Andy Furniss <adf.lists@gmail.com>, cake@lists.bufferbloat.net
Subject: Re: [Cake] Getting Cake to work better with Steam and similar applications
Date: Tue, 25 Apr 2017 22:10:48 +0300 [thread overview]
Message-ID: <09DB0D8E-F63C-4126-8608-9EACDE99D2F1@gmail.com> (raw)
In-Reply-To: <CANCX+3MgboG1rsE578+QY54_9e+PJ+c_u5wOfnGPDujjP1hXqw@mail.gmail.com>
> On 25 Apr, 2017, at 21:22, Dendari Marini <dendari92@gmail.com> wrote:
>
> The good news is that using switch0 as inbound and pppoe0 as outbound works, and I was able to set up Steam as bulk using the interface on the ER-X (used DSCP 8 and used a custom DPI category). I confirmed this was working by looking at the bulk traffic increasing (using the "tc -s qdisc" command) and by starting another download (Steam gets pretty much nothing in this case).
>
> The bad news is this isn't enough to fix my gaming issue (still having ping spikes, latency variation and packet loss), and even using it with Steam configured to use just one connection didn't change much from my previous testing.
>
> So I'm really confused :\
> What could cause ping spikes in this case (assuming the multiple connections aren't the issue)?
As noted, it’s far more difficult to control latency from downstream of a bottleneck link. If a bulk sender decides to send burstily, those bursts will always collect in the dumb queue at the far end and delay other traffic. The only true solution is to install a smart queue at the upstream end - but that’s not under your control.
You may see some improvement from wholesale reducing the inbound bandwidth, to say 10Mbit. This is especially true given the high asymmetry of your connection, which might require dropped acks upstream to keep filled downstream - and dropped acks will tend to increase burstiness of sending on unpaced senders.
You should also try to ensure ECN is fully enabled on your LAN hosts, especially the ones running Steam. This will help to reduce retransmissions and loss-recovery cycles.
- Jonathan Morton
next prev parent reply other threads:[~2017-04-25 19:10 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-20 13:39 Dendari Marini
2017-04-20 13:43 ` Sebastian Moeller
2017-04-20 15:23 ` Dendari Marini
2017-04-20 15:32 ` Jonathan Morton
2017-04-20 16:05 ` Dendari Marini
2017-04-20 17:12 ` Andy Furniss
2017-04-20 17:36 ` Jonathan Morton
2017-04-20 18:35 ` Sebastian Moeller
2017-04-20 18:36 ` Sebastian Moeller
2017-04-21 8:34 ` Dendari Marini
2017-04-21 13:25 ` Sebastian Moeller
2017-04-21 13:27 ` Dendari Marini
2017-04-22 8:25 ` Dendari Marini
2017-04-22 9:36 ` Jonathan Morton
2017-04-22 12:50 ` xnoreq
2017-04-22 13:41 ` Tristan Seligmann
2017-04-22 13:51 ` Andy Furniss
2017-04-22 14:03 ` Andy Furniss
2017-04-22 16:38 ` Andy Furniss
2017-04-22 16:45 ` Dave Taht
2017-04-22 17:00 ` Tristan Seligmann
2017-04-22 20:24 ` Andy Furniss
2017-04-22 16:47 ` Sebastian Moeller
2017-04-22 21:56 ` Dendari Marini
2017-04-22 22:15 ` Sebastian Moeller
2017-04-23 12:32 ` David Lang
2017-04-24 7:55 ` Sebastian Moeller
2017-04-24 8:41 ` Dendari Marini
2017-04-24 11:34 ` Sebastian Moeller
2017-04-24 12:08 ` Dendari Marini
2017-04-24 12:35 ` Sebastian Moeller
2017-04-24 13:49 ` Dendari Marini
2017-04-24 15:42 ` Sebastian Moeller
2017-04-24 17:32 ` Sebastian Moeller
2017-04-25 10:26 ` Andy Furniss
2017-04-25 11:24 ` Dendari Marini
2017-04-25 12:58 ` Andy Furniss
2017-04-25 18:22 ` Dendari Marini
2017-04-25 19:10 ` Jonathan Morton [this message]
2017-04-25 20:44 ` Dendari Marini
2017-04-25 21:32 ` Andy Furniss
2017-04-25 22:33 ` Benjamin Cronce
2017-04-28 15:37 ` Dendari Marini
2017-04-29 15:11 ` Andy Furniss
2017-04-29 17:30 ` Jonathan Morton
2017-04-29 18:29 ` Andy Furniss
2017-04-30 0:05 ` Andy Furniss
2017-05-01 5:50 ` Jonathan Morton
2017-05-01 11:32 ` Andy Furniss
2017-05-01 12:08 ` Jonathan Morton
2017-05-01 13:03 ` Andy Furniss
2017-05-01 13:11 ` Jonathan Morton
2017-05-01 14:46 ` Andy Furniss
2017-04-25 21:06 ` Andy Furniss
2017-04-25 21:16 ` Neil Shepperd
2017-04-25 21:37 ` Andy Furniss
2017-04-25 21:43 ` Sebastian Moeller
2017-04-25 22:06 ` Andy Furniss
2017-04-25 22:29 ` Andy Furniss
2017-04-25 22:32 ` Andy Furniss
2017-04-22 22:35 ` Andy Furniss
2017-04-22 14:12 ` Sebastian Moeller
2017-04-20 18:16 ` Sebastian Moeller
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/cake.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=09DB0D8E-F63C-4126-8608-9EACDE99D2F1@gmail.com \
--to=chromatix99@gmail.com \
--cc=adf.lists@gmail.com \
--cc=cake@lists.bufferbloat.net \
--cc=dendari92@gmail.com \
/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