From: Stefan Priebe - Profihost AG <s.priebe@profihost•ag>
To: "Ilpo Järvinen" <ilpo.jarvinen@helsinki•fi>
Cc: Eric Dumazet <eric.dumazet@gmail•com>,
Greg KH <gregkh@linuxfoundation•org>,
David Miller <davem@davemloft•net>,
jwboyer@gmail•com, hch@infradead•org,
Netdev <netdev@vger•kernel.org>,
david@fromorbit•com, stable@vger•kernel.org,
Greg KH <gregkh@suse•de>
Subject: Re: TCP sacked_out and fackets_out inconsistency (Was: Re: BUG: unable to handle kernel NULL pointer dereference at 000000000000002c)
Date: Wed, 08 Feb 2012 09:26:41 +0100 [thread overview]
Message-ID: <4F3231C1.9040509@profihost.ag> (raw)
In-Reply-To: <alpine.DEB.2.00.1202061151580.2966@wel-95.cs.helsinki.fi>
Hi Eric,
Am 06.02.2012 13:47, schrieb Ilpo Järvinen:
>>> Any idea about that? Is it due to my custom patch being buggy or is it
>>> anything you know which is missing in 3.0.X too?
>
> This warning is known to trigger every now and then...
>
>> Thats the tcp_fastretrans_alert()
>>
>> if (WARN_ON(!tp->sacked_out && tp->fackets_out))
>> tp->fackets_out = 0;
>>
>> I dont know if some recent patch addressed this issue.
>
> ...the recent fix from Neal to pick correct MSS might fix this but it
> is of course hard to confirm for sure (we'll see it indirectly eventually
> if there won't be anymore these rare splats). If one has infinite time it
> would be quite simple to see if changing mss setup triggers this and if
> the Neal's fix helped or not, however, I don't consider this particular
> inconsistency worth the effort.
>
> ...What I can say for sure is at least tp->fackets_out -= min(pkts_acked,
> tp->fackets_out); seems to fail when pkts_acked (u32) underflows due to
> the mss badness we used to have. So it could actually solve this for real.
>
> The effects of this counter inconsistency are not that devastating.
> Fackets_out mainly affect when recovery is triggered/which segments to
> mark lost in the recovery itself. Two extremes I can think of: recovery
> not triggered => RTO triggers and everyone is happy except some researcher
> who finds that odd and unwanted and needs to fix it :-); recovery in
> progress but works too much ahead, as if dupthresh (tp->reordering) would
> be slightly smaller (if in-order behavior in the network is assumed this
> is still fully safe, dupthresh is there to help in cases of minor
> reordering).
What do you think about this? Can anybody give me the commit id?
Stefan
next prev parent reply other threads:[~2012-02-08 8:26 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <4ED7C367.3070109@profihost.ag>
2011-12-01 18:23 ` BUG: unable to handle kernel NULL pointer dereference at 000000000000002c Christoph Hellwig
2011-12-01 20:20 ` Eric Dumazet
2011-12-01 20:37 ` Josh Boyer
2011-12-01 21:05 ` Eric Dumazet
2011-12-02 6:08 ` Stefan Priebe - Profihost AG
2011-12-02 6:17 ` David Miller
2011-12-02 7:19 ` Stefan Priebe - Profihost AG
2011-12-02 17:34 ` David Miller
2011-12-02 18:53 ` Greg KH
2011-12-09 19:01 ` Stefan Priebe
2011-12-09 19:21 ` David Miller
2011-12-10 9:03 ` Stefan Priebe
2012-01-30 8:38 ` Stefan Priebe - Profihost AG
2012-01-30 17:12 ` Greg KH
2012-01-30 17:21 ` David Miller
2012-01-30 18:07 ` David Miller
2012-01-30 18:53 ` Stefan Priebe
2012-01-30 21:48 ` David Miller
2012-01-30 21:56 ` Greg KH
2012-01-31 8:08 ` Stefan Priebe - Profihost AG
2012-02-01 21:21 ` David Miller
2012-02-02 12:55 ` Stefan Priebe - Profihost AG
2012-02-02 15:04 ` Eric Dumazet
2012-02-02 18:37 ` Stefan Priebe
2012-02-02 19:39 ` David Miller
2012-02-03 0:42 ` Greg KH
2012-02-03 6:48 ` Stefan Priebe - Profihost AG
2012-02-03 7:26 ` Eric Dumazet
2012-02-03 8:09 ` Stefan Priebe - Profihost AG
2012-02-03 11:04 ` Eric Dumazet
2012-02-03 15:53 ` Greg KH
2012-02-06 9:04 ` Stefan Priebe - Profihost AG
2012-02-06 9:19 ` Eric Dumazet
2012-02-06 12:47 ` TCP sacked_out and fackets_out inconsistency (Was: Re: BUG: unable to handle kernel NULL pointer dereference at 000000000000002c) Ilpo Järvinen
2012-02-08 8:26 ` Stefan Priebe - Profihost AG [this message]
2012-02-08 9:15 ` Eric Dumazet
2012-02-08 9:28 ` Eric Dumazet
2012-02-06 9:02 ` BUG: unable to handle kernel NULL pointer dereference at 000000000000002c Stefan Priebe - Profihost AG
2012-02-06 9:16 ` Eric Dumazet
2012-02-06 11:31 ` Stefan Priebe - Profihost AG
2012-02-08 8:24 ` Stefan Priebe - Profihost AG
2012-02-08 16:49 ` Greg KH
2012-02-09 6:43 ` Stefan Priebe - Profihost AG
2012-02-08 20:19 ` David Miller
2012-02-09 1:26 ` David Miller
2012-02-09 6:44 ` Stefan Priebe - Profihost AG
2012-02-09 22:13 ` David Miller
2012-02-10 7:04 ` Stefan Priebe - Profihost AG
2012-02-10 7:07 ` Eric Dumazet
2012-02-10 18:25 ` Eric Dumazet
2012-02-10 20:41 ` David Miller
2012-02-03 15:52 ` Greg KH
2011-12-12 9:45 ` Stefan Priebe - Profihost AG
2011-12-12 12:57 ` Stefan Priebe - Profihost AG
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=4F3231C1.9040509@profihost.ag \
--to=s.priebe@profihost$(echo .)ag \
--cc=davem@davemloft$(echo .)net \
--cc=david@fromorbit$(echo .)com \
--cc=eric.dumazet@gmail$(echo .)com \
--cc=gregkh@linuxfoundation$(echo .)org \
--cc=gregkh@suse$(echo .)de \
--cc=hch@infradead$(echo .)org \
--cc=ilpo.jarvinen@helsinki$(echo .)fi \
--cc=jwboyer@gmail$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=stable@vger$(echo .)kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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