netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Hurley <peter@hurleysoftware.com>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>,
	Francois Romieu <romieu@fr.zoreil.com>,
	Eric Dumazet <edumazet@google.com>,
	David Miller <davem@davemloft.net>,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	Greg KH <gregkh@linuxfoundation.org>,
	dmaengine@vger.kernel.org,
	John Ogness <john.ogness@linutronix.de>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Andrew Morton <akpm@linux-foundation.org>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: Softirq priority inversion from "softirq: reduce latencies"
Date: Mon, 29 Feb 2016 10:53:25 -0800	[thread overview]
Message-ID: <56D493A5.403@hurleysoftware.com> (raw)
In-Reply-To: <1456770279.648.85.camel@edumazet-ThinkPad-T530>

On 02/29/2016 10:24 AM, Eric Dumazet wrote:
> On lun., 2016-02-29 at 10:05 -0800, Peter Hurley wrote:
> 
>> While I appreciate the attempt, that's not the problem.
>>
>> Just to be clear
>>
>> 		if (time_before(jiffies, end) && !need_resched() &&
>> 		    --max_restart)
>> 			goto restart;
>>
>> aborts softirq *even if 0ns have elapsed*, if NET_RX has woken a process.
> 
> 
> Sure, now remove the 1st and 2nd condition.

Well just removing the 2nd condition has everything working fine,
because that fixes the priority inversion.


> You would still 'abort' (ie wakeup ksoftirqd really) when --max_restart
> becomes 0

Sure. Which would mean there's contended heavy i/o load so the driver
has to fallback to non-DMA. That's an acceptable outcome.


> So, instead of some subtle load dependent bug, you know have a reliable
> trigger.

There's no "subtle load dependent bug" here.

The driver has a fallback mode of operation that it relies on without
DMA. Of course, as I already wrote, this has consequences.

If system resources are _actually contended_, then naturally, fighting
for cpu and i/o time is fine, and I'm happy to do that in ksoftirqd.

However, when system resources are _not_ contended, it makes no
sense to be forced to revert to ksoftirqd resolution, which is strictly
intended as fallback.

Or flipping your argument on its head, why not just _always_ execute
softirq in ksoftirqd?

  reply	other threads:[~2016-02-29 18:53 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-27 18:19 Softirq priority inversion from "softirq: reduce latencies" Peter Hurley
2016-02-27 20:13 ` Eric Dumazet
2016-02-27 20:29   ` Peter Hurley
2016-02-27 23:04     ` David Miller
2016-02-27 23:33       ` Peter Hurley
2016-02-28  1:59         ` Eric Dumazet
2016-02-28  2:10           ` Peter Hurley
2016-02-28  2:17             ` Eric Dumazet
2016-02-28  4:46             ` David Miller
2016-02-28  5:55 ` Mike Galbraith
2016-02-28 17:01   ` Francois Romieu
2016-02-29  4:58     ` Mike Galbraith
2016-02-29 15:03       ` Peter Hurley
2016-02-29 15:19         ` Eric Dumazet
2016-02-29 15:54           ` Peter Hurley
2016-02-29 16:21             ` Eric Dumazet
2016-02-29 18:05               ` Peter Hurley
2016-02-29 18:24                 ` Eric Dumazet
2016-02-29 18:53                   ` Peter Hurley [this message]
2016-02-29 19:14                     ` Thomas Gleixner
2016-02-29 20:24                       ` David Miller
2016-02-29 23:04                       ` Peter Hurley
2016-02-29 15:27         ` Eric Dumazet
2016-02-29 19:13           ` Peter Hurley
2016-02-29 19:43             ` Eric Dumazet
2016-02-29 15:40         ` Mike Galbraith
2016-02-29 15:58           ` Peter Hurley
2016-02-29 16:24             ` Eric Dumazet
2016-02-29 17:16         ` David Miller
2016-03-07 15:31       ` Sebastian Andrzej Siewior
2016-03-07 17:06         ` Mike Galbraith
2016-03-07 15:48 ` Sebastian Andrzej Siewior

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=56D493A5.403@hurleysoftware.com \
    --to=peter@hurleysoftware.com \
    --cc=akpm@linux-foundation.org \
    --cc=bigeasy@linutronix.de \
    --cc=davem@davemloft.net \
    --cc=dmaengine@vger.kernel.org \
    --cc=edumazet@google.com \
    --cc=eric.dumazet@gmail.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=john.ogness@linutronix.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=romieu@fr.zoreil.com \
    --cc=tglx@linutronix.de \
    --cc=umgwanakikbuti@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;
as well as URLs for NNTP newsgroup(s).