From: Andi Kleen <andi@firstfloor.org>
To: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Andi Kleen <andi@firstfloor.org>, Florian Westphal <fw@strlen.de>,
kan.liang@intel.com, davem@davemloft.net,
linux-kernel@vger.kernel.org, intel-wired-lan@lists.osuosl.org,
netdev@vger.kernel.org, jeffrey.t.kirsher@intel.com,
mingo@redhat.com, peterz@infradead.org, kuznet@ms2.inr.ac.ru,
jmorris@namei.org, yoshfuji@linux-ipv6.org, kaber@trash.net,
akpm@linux-foundation.org, keescook@chromium.org,
viro@zeniv.linux.org.uk, gorcunov@openvz.org,
john.stultz@linaro.org, aduyck@mirantis.com, ben@decadent.org.uk,
decot@googlers.com, jesse.brandeburg@intel.com
Subject: Re: [RFC PATCH 00/30] Kernel NET policy
Date: Mon, 18 Jul 2016 12:43:57 -0700 [thread overview]
Message-ID: <20160718194357.GL5871@two.firstfloor.org> (raw)
In-Reply-To: <7a03a353-4c1e-2bb4-2550-f84fc4cc79ac@stressinduktion.org>
> I wonder if this can be attacked from a different angle. What would be
> missing to add support for this in user space? The first possibility
> that came to my mind is to just multiplex those hints in the kernel.
"just" is the handwaving part here -- you're proposing a micro kernel
approach where part of the multiplexing job that the kernel is doing
is farmed out to a message passing user space component.
I suspect this would be far more complicated to get right and
perform well than a straight forward monolithic kernel subsystem --
which is traditionally how Linux has approached things.
The daemon would always need to work with out of date state
compared to the latest, because it cannot do any locking with the
kernel state. So you end up with a complex distributed system with multiple
agents "fighting" with each other, and the tuning agent
never being able to keep up with the actual work.
Also of course it would be fundamentally less efficient than
kernel code doing that, just because of the additional context
switches needed.
-Andi
next prev parent reply other threads:[~2016-07-18 19:44 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-07-18 6:55 [RFC PATCH 00/30] Kernel NET policy kan.liang
2016-07-18 6:55 ` [RFC PATCH 01/30] net: introduce " kan.liang
2016-07-18 6:55 ` [RFC PATCH 02/30] net/netpolicy: init " kan.liang
2016-07-18 6:55 ` [RFC PATCH 03/30] i40e/netpolicy: Implement ndo_netpolicy_init kan.liang
2016-07-18 6:55 ` [RFC PATCH 04/30] net/netpolicy: get driver information kan.liang
2016-07-18 6:55 ` [RFC PATCH 05/30] i40e/netpolicy: implement ndo_get_irq_info kan.liang
2016-07-18 6:56 ` [RFC PATCH 06/30] net/netpolicy: get CPU information kan.liang
2016-07-18 6:56 ` [RFC PATCH 07/30] net/netpolicy: create CPU and queue mapping kan.liang
2016-07-18 6:56 ` [RFC PATCH 08/30] net/netpolicy: set and remove irq affinity kan.liang
2016-07-18 6:56 ` [RFC PATCH 09/30] net/netpolicy: enable and disable net policy kan.liang
2016-07-18 6:56 ` [RFC PATCH 10/30] net/netpolicy: introduce netpolicy object kan.liang
2016-07-18 6:56 ` [RFC PATCH 11/30] net/netpolicy: set net policy by policy name kan.liang
2016-07-18 6:56 ` [RFC PATCH 12/30] i40e/netpolicy: implement ndo_set_net_policy kan.liang
2016-07-18 6:56 ` [RFC PATCH 13/30] i40e/netpolicy: add three new net policies kan.liang
2016-07-18 6:56 ` [RFC PATCH 14/30] net/netpolicy: add MIX policy kan.liang
2016-07-18 6:56 ` [RFC PATCH 15/30] i40e/netpolicy: add MIX policy support kan.liang
2016-07-18 6:56 ` [RFC PATCH 16/30] net/netpolicy: net device hotplug kan.liang
2016-07-18 6:56 ` [RFC PATCH 17/30] net/netpolicy: support CPU hotplug kan.liang
2016-07-18 6:56 ` [RFC PATCH 18/30] net/netpolicy: handle channel changes kan.liang
2016-07-18 6:56 ` [RFC PATCH 19/30] net/netpolicy: implement netpolicy register kan.liang
2016-07-18 6:56 ` [RFC PATCH 20/30] net/netpolicy: introduce per socket netpolicy kan.liang
2016-07-18 6:56 ` [RFC PATCH 21/30] net/policy: introduce netpolicy_pick_queue kan.liang
2016-07-18 6:56 ` [RFC PATCH 22/30] net/netpolicy: set tx queues according to policy kan.liang
2016-07-18 6:56 ` [RFC PATCH 23/30] i40e/ethtool: support RX_CLS_LOC_ANY kan.liang
2016-07-18 16:21 ` Alexander Duyck
2016-07-18 6:56 ` [RFC PATCH 24/30] net/netpolicy: set rx queues according to policy kan.liang
2016-07-18 6:56 ` [RFC PATCH 25/30] net/netpolicy: introduce per task net policy kan.liang
2016-07-18 6:56 ` [RFC PATCH 26/30] net/netpolicy: set per task policy by proc kan.liang
2016-07-18 6:56 ` [RFC PATCH 27/30] net/netpolicy: fast path for finding the queues kan.liang
2016-07-18 6:56 ` [RFC PATCH 28/30] net/netpolicy: optimize for queue pair kan.liang
2016-07-18 6:56 ` [RFC PATCH 29/30] net/netpolicy: limit the total record number kan.liang
2016-07-18 6:56 ` [RFC PATCH 30/30] Documentation/networking: Document net policy kan.liang
2016-07-18 16:58 ` Randy Dunlap
2016-07-18 15:18 ` [RFC PATCH 00/30] Kernel NET policy Florian Westphal
2016-07-18 15:45 ` Andi Kleen
2016-07-18 17:52 ` Cong Wang
2016-07-18 20:14 ` Liang, Kan
2016-07-18 20:19 ` Cong Wang
2016-07-18 20:24 ` Liang, Kan
2016-07-18 19:04 ` Hannes Frederic Sowa
2016-07-18 19:43 ` Andi Kleen [this message]
2016-07-18 21:51 ` Hannes Frederic Sowa
2016-07-19 1:49 ` Liang, Kan
2016-07-19 5:03 ` David Miller
2016-07-19 13:43 ` Liang, Kan
2016-07-18 15:51 ` Liang, Kan
2016-07-18 16:17 ` Florian Westphal
2016-07-18 17:40 ` Liang, Kan
2016-07-18 16:34 ` Tom Herbert
2016-07-18 17:58 ` Liang, Kan
2016-07-18 16:22 ` Daniel Borkmann
2016-07-18 18:30 ` Liang, Kan
2016-07-18 20:51 ` Daniel Borkmann
2016-07-18 17:00 ` Alexander Duyck
2016-07-18 19:45 ` Liang, Kan
2016-07-18 19:49 ` Andi Kleen
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=20160718194357.GL5871@two.firstfloor.org \
--to=andi@firstfloor.org \
--cc=aduyck@mirantis.com \
--cc=akpm@linux-foundation.org \
--cc=ben@decadent.org.uk \
--cc=davem@davemloft.net \
--cc=decot@googlers.com \
--cc=fw@strlen.de \
--cc=gorcunov@openvz.org \
--cc=hannes@stressinduktion.org \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=jeffrey.t.kirsher@intel.com \
--cc=jesse.brandeburg@intel.com \
--cc=jmorris@namei.org \
--cc=john.stultz@linaro.org \
--cc=kaber@trash.net \
--cc=kan.liang@intel.com \
--cc=keescook@chromium.org \
--cc=kuznet@ms2.inr.ac.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=viro@zeniv.linux.org.uk \
--cc=yoshfuji@linux-ipv6.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).