From: David Miller <davem@davemloft.net>
To: matthias.tafelmeier@gmx.net
Cc: netdev@vger.kernel.org, hagen@jauu.net, fw@strlen.de,
edumazet@google.com, daniel@iogearbox.net
Subject: Re: [PATCH v5] net: dev_weight: TX/RX orthogonality
Date: Thu, 29 Dec 2016 20:16:47 -0500 (EST) [thread overview]
Message-ID: <20161229.201647.324176080385260025.davem@davemloft.net> (raw)
In-Reply-To: <1483043841-10016-1-git-send-email-matthias.tafelmeier@gmx.net>
From: Matthias Tafelmeier <matthias.tafelmeier@gmx.net>
Date: Thu, 29 Dec 2016 21:37:21 +0100
> Oftenly, introducing side effects on packet processing on the other half
> of the stack by adjusting one of TX/RX via sysctl is not desirable.
> There are cases of demand for asymmetric, orthogonal configurability.
>
> This holds true especially for nodes where RPS for RFS usage on top is
> configured and therefore use the 'old dev_weight'. This is quite a
> common base configuration setup nowadays, even with NICs of superior processing
> support (e.g. aRFS).
>
> A good example use case are nodes acting as noSQL data bases with a
> large number of tiny requests and rather fewer but large packets as responses.
> It's affordable to have large budget and rx dev_weights for the
> requests. But as a side effect having this large a number on TX
> processed in one run can overwhelm drivers.
>
> This patch therefore introduces an independent configurability via sysctl to
> userland.
>
> Signed-off-by: Matthias Tafelmeier <matthias.tafelmeier@gmx.net>
Much better, applied, thanks.
next prev parent reply other threads:[~2016-12-30 1:16 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-26 9:49 [PATCH v1] net: dev_weight: TX/RX orthogonality Matthias Tafelmeier
2016-12-26 15:52 ` David Miller
[not found] ` <ae0712c3-61c6-432e-78d9-665d0c291c9f@gmx.net>
2016-12-26 16:58 ` [PATCH v1] net: dev_weight: TX/RX orthogonality,Re: " David Miller
2016-12-27 8:25 ` [PATCH] " Matthias Tafelmeier
2016-12-27 16:47 ` Marcelo Ricardo Leitner
2016-12-27 17:29 ` Matthias Tafelmeier
2016-12-28 9:42 ` [PATCH v3] " Matthias Tafelmeier
2016-12-28 19:17 ` David Miller
2016-12-29 9:58 ` [PATCH v4] " Matthias Tafelmeier
2016-12-29 19:08 ` David Miller
2016-12-29 19:23 ` Matthias Tafelmeier
2016-12-29 19:44 ` David Miller
2016-12-29 19:45 ` David Miller
2016-12-29 19:53 ` Matthias Tafelmeier
2016-12-29 20:37 ` [PATCH v5] " Matthias Tafelmeier
2016-12-30 1:16 ` David Miller [this message]
2017-02-13 20:22 ` Matthias Tafelmeier
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
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20161229.201647.324176080385260025.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=daniel@iogearbox.net \
--cc=edumazet@google.com \
--cc=fw@strlen.de \
--cc=hagen@jauu.net \
--cc=matthias.tafelmeier@gmx.net \
--cc=netdev@vger.kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).