From owner-freebsd-net@FreeBSD.ORG  Sat May 24 07:40:58 2014
Return-Path: <owner-freebsd-net@FreeBSD.ORG>
Delivered-To: freebsd-net@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115])
 (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits))
 (No client certificate requested)
 by hub.freebsd.org (Postfix) with ESMTPS id EE4DC99B
 for <freebsd-net@freebsd.org>; Sat, 24 May 2014 07:40:58 +0000 (UTC)
Received: from mx7.valuehost.ru (mx7.valuehost.ru [217.112.42.214])
 by mx1.freebsd.org (Postfix) with ESMTP id 823A623B3
 for <freebsd-net@freebsd.org>; Sat, 24 May 2014 07:40:58 +0000 (UTC)
Received: (from mail@localhost)
 by mx7.valuehost.ru (8.12.9/8.13.1) id s4O7exfL030220
 for freebsd-net@freebsd.org; Sat, 24 May 2014 11:40:59 +0400 (MSD)
X-Authentication-Warning: mx7.valuehost.ru: mail set sender to @ using -f
Received: from localhost (localhost [127.0.0.1]) by mail.valuehost.ru
 (Horde) with HTTP for <ppb@mail.valuehost.ru>; Sat, 24 May 2014 11:40:59
 +0400
Message-ID: <1400917259.c526ccc8386cc@mail.valuehost.ru>
Date: Sat, 24 May 2014 11:40:59 +0400
From: ppb@.SYNTAX-ERROR
To: freebsd-net@freebsd.org
Subject: Re: mbuf_cluster (FAIL SLEEP)
MIME-Version: 1.0
Content-Type: text/plain; charset="windows-1251"
Content-Disposition: inline
Content-Transfer-Encoding: 7bit
User-Agent: Internet Messaging Program (IMP) 4.0-cvs
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.18
Precedence: list
List-Id: Networking and TCP/IP with FreeBSD <freebsd-net.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/options/freebsd-net>,
 <mailto:freebsd-net-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-net/>
List-Post: <mailto:freebsd-net@freebsd.org>
List-Help: <mailto:freebsd-net-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-net>,
 <mailto:freebsd-net-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Sat, 24 May 2014 07:40:59 -0000

> Yes, this is normal and it doesn't mean what you might expect.  It's a
> generic failure counter, not an allocation failure counter.  eg: if an
> object that was just freed fails to fit in a per-cpu free items cache it
> counts as a "FAIL".

Hello, thank you for answer Peter.
But what do think about this:

--------------------------------------
# netstat -an |wc -l
29616
# netstat -an | grep -c TIME_WAIT
27800

+
kernel stops showing realtime LA: show normal top, but no changes at first line
output:
load averages:  2.36,  2.32,  2.28
                 ^	^	^
                 |	|	|
--------------------------------------

sysctl net.inet.tcp.msl and tcpdrop do not help,
after killing TIME_WAIT this connection state start grow again till 27800.

I have to reboot servers couse some apache process goes to <defunct> state
and stop responding.
Normal traffic and no ddos at this moment.

Again, this problem (netstat & LA) happen at the same time.....