linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Liang, Kan" <kan.liang@intel.com>
To: Florian Westphal <fw@strlen.de>
Cc: "davem@davemloft.net" <davem@davemloft.net>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"intel-wired-lan@lists.osuosl.org"
	<intel-wired-lan@lists.osuosl.org>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"Kirsher, Jeffrey T" <jeffrey.t.kirsher@intel.com>,
	"mingo@redhat.com" <mingo@redhat.com>,
	"peterz@infradead.org" <peterz@infradead.org>,
	"kuznet@ms2.inr.ac.ru" <kuznet@ms2.inr.ac.ru>,
	"jmorris@namei.org" <jmorris@namei.org>,
	"yoshfuji@linux-ipv6.org" <yoshfuji@linux-ipv6.org>,
	"kaber@trash.net" <kaber@trash.net>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	"keescook@chromium.org" <keescook@chromium.org>,
	"viro@zeniv.linux.org.uk" <viro@zeniv.linux.org.uk>,
	"gorcunov@openvz.org" <gorcunov@openvz.org>,
	"john.stultz@linaro.org" <john.stultz@linaro.org>,
	"aduyck@mirantis.com" <aduyck@mirantis.com>,
	"ben@decadent.org.uk" <ben@decadent.org.uk>,
	"decot@googlers.com" <decot@googlers.com>,
	"Brandeburg, Jesse" <jesse.brandeburg@intel.com>,
	"andi@firstfloor.org" <andi@firstfloor.org>
Subject: RE: [RFC PATCH 00/30] Kernel NET policy
Date: Mon, 18 Jul 2016 15:51:22 +0000	[thread overview]
Message-ID: <37D7C6CF3E00A74B8858931C1DB2F07712C1968E@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <20160718151841.GA19066@breakpoint.cc>



> >
> > It is a big challenge to get good network performance. First, the
> > network performance is not good with default system settings. Second,
> > it is too difficult to do automatic tuning for all possible workloads,
> > since workloads have different requirements. Some workloads may want
> high throughput.
> 
> Seems you did lots of tests to find optimal settings for a given base policy.
> 
Yes. Current test only base on Intel i40e driver. The optimal settings should
vary for other devices. But adding settings for new device is not hard.

> What is missing in the kernel UAPI so userspace could do these settings on its
> own, without adding this policy stuff to the kernel?

The main purpose of the proposal is to simplify the configuration. Too many
options will let them confuse. 
For normal users, they just need to tell the kernel that they want high throughput
for the application. The kernel will take care of the rest.
So, I don't think we need an interface for user to set their own policy settings.

> 
> It seems strange to me to add such policies to the kernel.

But kernel is the only place which can merge all user's requests.

> Addmittingly, documentation of some settings is non-existent and one needs
> various different tools to set this (sysctl, procfs, sysfs, ethtool, etc).
> 
> But all of these details could be hidden from user.
> Have you looked at tuna for instance?

Not yet. Is there similar settings for network?

Thanks,
Kan

  parent reply	other threads:[~2016-07-18 15:51 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
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 [this message]
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=37D7C6CF3E00A74B8858931C1DB2F07712C1968E@SHSMSX103.ccr.corp.intel.com \
    --to=kan.liang@intel.com \
    --cc=aduyck@mirantis.com \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=ben@decadent.org.uk \
    --cc=davem@davemloft.net \
    --cc=decot@googlers.com \
    --cc=fw@strlen.de \
    --cc=gorcunov@openvz.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=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).