public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Badalian Vyacheslav <slavon@bigtelecom.ru>
To: Jarek Poplawski <jarkao2@gmail.com>
Cc: Chris Caputo <ccaputo@alt.net>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Denys Fedoryschenko <denys@visp.net.lb>,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: deadlocks if use htb
Date: Thu, 15 Jan 2009 10:12:20 +0300	[thread overview]
Message-ID: <496EE1D4.6010709@bigtelecom.ru> (raw)
In-Reply-To: <20090115065322.GA4190@ff.dom.local>


> On Wed, Jan 14, 2009 at 06:02:04PM +0000, Chris Caputo wrote:
> ...
>   
>> That said, I would not recommend just the three for -stable unless they 
>> get a much wider amount of testing, on multiple platforms.  I don't see 
>> that as likely to happen, plus Peter says they are incomplete, so maybe it 
>> is just best to recommend that 2.6.28 users getting crashes while using 
>> HTB try these specific patches at first, and then the rest of the patches 
>> if they do not work.
>>     
>
> The main problem is my patches, at least the tested ones, harm htb's
> exactness, and I doubt I could convince anybody to merege them, at
> least before your case. It was only reported by two users here (plus
> one more on private), and looked like something very rare. After your
> report it looks much more necessary.
>
> If there is nothing better, I can recommend it, but IMHO the best
> candidate for this is the testing patch #4 from this thread, which
> alas wasn't even tested... So, Chris, if you could give it a try in
> the meantime (without any other patches)?
>
> Thanks,
> Jarek P.
>
> (resend testing patch #4 - for 2.6.27 or 2.6.28)
> ---
>
> diff -Nurp a2.6.27.7/net/sched/sch_htb.c b2.6.27.7/net/sched/sch_htb.c
> --- a2.6.27.7/net/sched/sch_htb.c	2008-12-11 08:16:16.000000000 +0000
> +++ b2.6.27.7/net/sched/sch_htb.c	2008-12-15 10:44:32.000000000 +0000
> @@ -924,6 +924,7 @@ static struct sk_buff *htb_dequeue(struc
>  		}
>  	}
>  	sch->qstats.overlimits++;
> +	qdisc_watchdog_cancel(&q->watchdog);
>  	qdisc_watchdog_schedule(&q->watchdog, next_event);
>  fin:
>  	return skb;
>
>   
Hello all.
I also can say this, maybe its help:
At old kernels my servers do 100% soft interupt if traffic more 600mbs.
Without your patches at new kernel i get crash only at heavy network
load PCs (more then 400mbs-500mbs). Servers that get 100-200 mbs not
crashed long time.
I remember that i not test patch #4, because you sat what its only
another way to temporary fix and mainline problem in hrtimer , but i try
turn on HiRes and Dynamic Tics in kernel - its not help for me.
Best Regals. Slavon

  reply	other threads:[~2009-01-15  7:12 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20081010075640.GA5204@ff.dom.local>
     [not found] ` <48EF17EA.5020306@bigtelecom.ru>
     [not found]   ` <20081010090426.GA6054@ff.dom.local>
     [not found]     ` <20081010095129.GB6054@ff.dom.local>
     [not found]       ` <48F6FB3E.7060903@bigtelecom.ru>
     [not found]         ` <20081016084027.GA17632@ff.dom.local>
     [not found]           ` <48FEC302.5090707@bigtelecom.ru>
2008-10-22  7:02             ` deadlocks if use htb Jarek Poplawski
2008-12-10 15:14               ` Badalian Vyacheslav
2008-12-11  8:46                 ` Jarek Poplawski
2008-12-15 11:13                   ` Jarek Poplawski
2008-12-16  7:37                     ` Badalian Vyacheslav
2008-12-18  6:43                     ` Badalian Vyacheslav
2008-12-18  8:17                       ` Jarek Poplawski
2008-12-18 11:23                         ` Badalian Vyacheslav
2008-12-18 11:37                           ` Jarek Poplawski
2009-01-14  2:43                         ` Chris Caputo
2009-01-14  6:39                           ` Jarek Poplawski
2009-01-14 12:17                             ` Denys Fedoryschenko
2009-01-14 12:36                               ` Jarek Poplawski
2009-01-14 12:41                                 ` Denys Fedoryschenko
2009-01-14 12:50                               ` Peter Zijlstra
2009-01-14 13:04                                 ` Jarek Poplawski
2009-01-14 13:05                                 ` Denys Fedoryschenko
2009-01-14 13:12                                   ` Jarek Poplawski
2009-01-14 13:15                                     ` Peter Zijlstra
2009-01-14 13:19                                       ` Denys Fedoryschenko
2009-01-14 13:26                                       ` Jarek Poplawski
2009-01-14 13:32                                         ` Peter Zijlstra
2009-01-14 13:57                                           ` Jarek Poplawski
2009-01-14 14:13                                           ` Jarek Poplawski
2009-01-14 14:28                                             ` Peter Zijlstra
2009-01-14 14:39                                               ` Jarek Poplawski
2009-01-15  9:01                                               ` Jarek Poplawski
2009-01-15 10:46                                                 ` Peter Zijlstra
2009-01-15 10:54                                                   ` Jarek Poplawski
2009-01-14 18:02                                 ` Chris Caputo
2009-01-15  6:53                                   ` Jarek Poplawski
2009-01-15  7:12                                     ` Badalian Vyacheslav [this message]
2009-01-15  8:09                                       ` Jarek Poplawski
2009-01-15  9:01                                         ` Denys Fedoryschenko
2009-01-15  9:06                                           ` Jarek Poplawski
2009-01-15  9:40                                             ` Badalian Vyacheslav
2009-01-15  9:54                                               ` Jarek Poplawski
2009-01-15  9:57                                                 ` Denys Fedoryschenko
2009-01-15 10:06                                                   ` Jarek Poplawski
2009-01-15 10:10                                                   ` Jarek Poplawski
2009-01-15 10:40                                                     ` Denys Fedoryschenko
2009-01-15  7:26                                     ` Chris Caputo
2009-01-15  7:54                                       ` Jarek Poplawski
2009-01-15  9:45                                         ` Jarek Poplawski
2009-01-15 12:00                                           ` Chris Caputo
2009-01-15 12:18                                             ` Jarek Poplawski
2009-01-15 13:53                                               ` Chris Caputo
2009-01-16  6:51                                                 ` Badalian Vyacheslav
2009-01-19  5:46                                     ` David Miller
2009-01-19  6:57                                       ` [PATCH] " Jarek Poplawski
2009-01-19  7:42                                         ` Badalian Vyacheslav
2009-01-19  7:57                                           ` Jarek Poplawski
2009-01-20  1:29                                             ` David Miller

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=496EE1D4.6010709@bigtelecom.ru \
    --to=slavon@bigtelecom.ru \
    --cc=a.p.zijlstra@chello.nl \
    --cc=ccaputo@alt.net \
    --cc=denys@visp.net.lb \
    --cc=jarkao2@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /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