From: "Dâniel Fraga" <fragabr@gmail.com>
To: "Ilpo Järvinen" <ilpo.jarvinen@helsinki.fi>
Cc: David Miller <davem@davemloft.net>,
thomas.jarosch@intra2net.com, billfink@mindspring.com,
Netdev <netdev@vger.kernel.org>, Patrick Hardy <kaber@trash.net>,
netfilter-devel@vger.kernel.org, kadlec@blackhole.kfki.hu
Subject: Re: [PATCH] tcp FRTO: in-order-only "TCP proxy" fragility workaround
Date: Thu, 11 Sep 2008 14:30:06 -0300 [thread overview]
Message-ID: <20080911143006.2f516569@tux> (raw)
In-Reply-To: <Pine.LNX.4.64.0809100942370.24708@wrl-59.cs.helsinki.fi>
On Thu, 11 Sep 2008 16:44:20 +0300 (EEST)
"Ilpo Järvinen" <ilpo.jarvinen@helsinki.fi> wrote:
> ...I guess it would be possible to remove SCHED_FEAT_HRTICK from
> /proc/sys/kernel/sched_features then while keeping the hrtimers
> otherwise enabled to test this.
>
> It's possible that hrtimers just affect on how easy it is to trigger
> but at least it seems an useful lead until proven otherwise.
You're right Ilpo. After days and days without the problem,
today it triggered (but I wasn't online at the time, so I couldn't grab
any data).
So, you're correct. HRtimers just affect on how easy it is to
trigger the issue. In other words: with high resolution timer enabled,
the problem appears more frequently.
At least if we discovered a way how to trigger this, we could
test it more easily. The problem is to wait a long time for it to
happen.
Just a curiosity: on your servers, do you use x86_64? It seems
this problem is very specific to x86_64 or appear more often on x86_64
than x86_32. It never happens on my x86_32 bit servers.
--
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2008-09-11 17:30 UTC|newest]
Thread overview: 118+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-03-26 8:47 Transfer stalls with NAT under 2.6.24.3 Sven Riedel
2008-03-26 9:24 ` Patrick McHardy
2008-03-26 10:21 ` Sven Riedel
2008-03-26 15:47 ` Patrick McHardy
2008-03-26 18:45 ` Jozsef Kadlecsik
2008-03-26 19:16 ` Krzysztof Oledzki
2008-03-31 6:53 ` Sven Riedel
2008-07-04 14:54 ` TCP connection stalls under 2.6.24.7 Thomas Jarosch
2008-07-04 20:58 ` Jozsef Kadlecsik
2008-07-04 21:04 ` Jozsef Kadlecsik
2008-07-07 9:18 ` Thomas Jarosch
2008-07-07 13:18 ` Thomas Jarosch
2008-07-10 13:17 ` Jozsef Kadlecsik
2008-07-10 14:12 ` Thomas Jarosch
2008-07-10 21:21 ` Jozsef Kadlecsik
2008-07-11 14:33 ` Thomas Jarosch
2008-07-15 11:47 ` Thomas Jarosch
2008-07-15 16:10 ` Thomas Jarosch
2008-07-15 18:30 ` Dâniel Fraga
2008-07-31 4:47 ` Dâniel Fraga
2008-07-31 7:39 ` Ilpo Järvinen
2008-08-02 12:24 ` Dâniel Fraga
2008-07-15 20:17 ` Ilpo Järvinen
2008-07-16 8:07 ` Thomas Jarosch
2008-07-16 9:03 ` Thomas Jarosch
2008-07-17 13:55 ` Ilpo Järvinen
2008-07-17 15:15 ` Thomas Jarosch
2008-07-17 15:53 ` Ilpo Järvinen
2008-07-18 9:14 ` Thomas Jarosch
2008-07-18 13:55 ` Ilpo Järvinen
2008-07-18 14:02 ` Thomas Jarosch
2008-07-19 7:35 ` Ilpo Järvinen
2008-07-25 10:00 ` Ilpo Järvinen
2008-07-25 13:00 ` Thomas Jarosch
2008-07-25 14:06 ` Ilpo Järvinen
2008-07-25 15:34 ` Thomas Jarosch
2008-07-31 7:39 ` Thomas Jarosch
2008-07-31 12:44 ` Dâniel Fraga
2008-07-31 13:47 ` Thomas Jarosch
2008-07-31 14:11 ` Dâniel Fraga
2008-08-06 18:53 ` Dâniel Fraga
2008-08-07 6:54 ` Ilpo Järvinen
2008-08-07 11:50 ` Denys Fedoryshchenko
2008-08-07 12:11 ` Thomas Jarosch
2008-08-07 12:14 ` Ilpo Järvinen
2008-08-07 12:23 ` Denys Fedoryshchenko
2008-08-08 9:56 ` Ilpo Järvinen
2008-08-08 10:32 ` Denys Fedoryshchenko
2008-08-07 11:33 ` [PATCH] tcp FRTO: in-order-only "TCP proxy" fragility workaround Ilpo Järvinen
2008-08-08 4:42 ` Bill Fink
2008-08-08 10:32 ` Ilpo Järvinen
2008-08-11 21:44 ` David Miller
2008-08-12 7:46 ` Thomas Jarosch
2008-08-12 8:18 ` David Miller
2008-08-12 17:43 ` Dâniel Fraga
2008-08-12 17:52 ` Ilpo Järvinen
2008-08-13 17:53 ` Dâniel Fraga
2008-08-13 18:34 ` Ilpo Järvinen
2008-08-15 4:34 ` Dâniel Fraga
2008-08-15 7:06 ` Ilpo Järvinen
2008-08-15 21:35 ` Dâniel Fraga
2008-08-15 22:06 ` Ilpo Järvinen
2008-08-15 23:57 ` Dâniel Fraga
2008-08-16 2:15 ` Dâniel Fraga
2008-08-16 7:10 ` Ilpo Järvinen
2008-08-16 19:18 ` Ilpo Järvinen
2008-08-17 0:36 ` Dâniel Fraga
2008-08-19 10:38 ` Ilpo Järvinen
2008-08-20 0:34 ` Dâniel Fraga
2008-08-20 7:57 ` Ilpo Järvinen
2008-08-20 12:37 ` Ilpo Järvinen
2008-08-22 21:32 ` Dâniel Fraga
2008-08-22 21:37 ` David Miller
2008-08-23 14:14 ` Dâniel Fraga
2008-08-23 14:38 ` Ilpo Järvinen
2008-08-24 19:38 ` Dâniel Fraga
2008-08-26 14:10 ` Ilpo Järvinen
2008-08-26 14:32 ` Ilpo Järvinen
2008-08-26 17:18 ` Dâniel Fraga
2008-08-26 20:40 ` Ilpo Järvinen
2008-08-26 21:17 ` Dâniel Fraga
2008-08-27 10:22 ` Ilpo Järvinen
2008-08-27 19:51 ` Dâniel Fraga
2008-08-27 20:32 ` Ilpo Järvinen
2008-08-27 20:50 ` Dâniel Fraga
2008-08-27 21:25 ` Ilpo Järvinen
2008-08-27 21:42 ` Dâniel Fraga
2008-08-27 22:24 ` Dâniel Fraga
2008-08-28 21:49 ` Dâniel Fraga
2008-08-29 13:07 ` Ilpo Järvinen
2008-08-29 17:41 ` Dâniel Fraga
2008-09-01 7:11 ` Ilpo Järvinen
2008-08-30 6:56 ` Dâniel Fraga
2008-09-01 7:11 ` Ilpo Järvinen
2008-09-07 8:17 ` Dâniel Fraga
2008-09-08 10:27 ` Ilpo Järvinen
2008-09-08 20:20 ` Dâniel Fraga
2008-09-11 13:44 ` Ilpo Järvinen
2008-09-11 17:30 ` Dâniel Fraga [this message]
2008-09-12 10:16 ` Ilpo Järvinen
2008-09-13 23:31 ` Dâniel Fraga
2008-09-16 12:10 ` Ilpo Järvinen
2008-09-16 14:24 ` Dâniel Fraga
2008-09-17 10:23 ` Ilpo Järvinen
2008-09-18 20:35 ` Dâniel Fraga
2008-09-18 21:04 ` Ilpo Järvinen
2008-09-21 3:02 ` Dâniel Fraga
2008-09-22 4:23 ` Dâniel Fraga
2008-09-22 11:22 ` Ilpo Järvinen
2008-09-22 16:13 ` Dâniel Fraga
2008-09-15 19:42 ` Dâniel Fraga
2008-09-11 18:12 ` Dâniel Fraga
2008-08-15 21:59 ` Dâniel Fraga
2008-08-13 8:00 ` Thomas Jarosch
2008-08-22 21:18 ` Ilpo Järvinen
2008-08-11 21:41 ` David Miller
-- strict thread matches above, loose matches on Subject: below --
2008-08-25 16:45 Thomas Jarosch
2008-08-26 12:03 ` Ilpo Järvinen
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=20080911143006.2f516569@tux \
--to=fragabr@gmail.com \
--cc=billfink@mindspring.com \
--cc=davem@davemloft.net \
--cc=ilpo.jarvinen@helsinki.fi \
--cc=kaber@trash.net \
--cc=kadlec@blackhole.kfki.hu \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
--cc=thomas.jarosch@intra2net.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.