netdev - Re: [RFC] random SYN drops causing connect() delays

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20100427.185602.221594952.davem@davemloft.net>
Date:	Tue, 27 Apr 2010 18:56:02 -0700 (PDT)
From:	David Miller <davem@...emloft.net>
To:	tgraf@...radead.org
Cc:	netdev@...r.kernel.org
Subject: Re: [RFC] random SYN drops causing connect() delays

From: Thomas Graf <tgraf@...radead.org>
Date: Mon, 12 Apr 2010 04:39:03 -0400

> On Mon, Apr 12, 2010 at 04:06:33AM -0400, Thomas Graf wrote:
>>  - While the issue is appearing, the acceptq seems to be overflowing. Both
>>    LISTENOVERFLOWS and LISTENDROPS are increasing although not by the exact
>>    number of delay occurences. inetdiag reports sk_max_ack_backlog to be 0
>>    therefore one possibility that comes to mind is that sk_ack_backlog
>>    underflows due to a race.
> 
> Forget about the underflow thought, inetdiag was reporting falsely.
> sk_max_ack_backlog is set to 128 as it should and the listen overflow
> happens normally. Still the fact remains that while the issue is appearing
> listen overflows are counted.

I can't reproduce on my system even with sched_child_runs_first set to '1'.

Are you running identd or something like that which intercepts the connections
to port 22 before 'sshd' actually gets it?
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html