From owner-freebsd-net@freebsd.org  Tue Aug 25 14:07:57 2015
Return-Path: <owner-freebsd-net@freebsd.org>
Delivered-To: freebsd-net@mailman.ysv.freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org
 [IPv6:2001:1900:2254:206a::19:1])
 by mailman.ysv.freebsd.org (Postfix) with ESMTP id 4878899A3C5
 for <freebsd-net@mailman.ysv.freebsd.org>;
 Tue, 25 Aug 2015 14:07:57 +0000 (UTC) (envelope-from john@maxnet.ru)
Received: from basic.maxnet.ru (mx.maxnet.ru [195.112.97.17])
 by mx1.freebsd.org (Postfix) with ESMTP id C9920B6E
 for <freebsd-net@freebsd.org>; Tue, 25 Aug 2015 14:07:55 +0000 (UTC)
 (envelope-from john@maxnet.ru)
Received: from [217.15.204.72] (John.Office.Obninsk.MAXnet.ru [217.15.204.72]
 (may be forged))
 by basic.maxnet.ru (8.14.6/8.14.6) with ESMTP id t7PE7ldN014201
 for <freebsd-net@freebsd.org>; Tue, 25 Aug 2015 17:07:48 +0300 (MSK)
 (envelope-from john@maxnet.ru)
Message-ID: <55DC76B7.9060606@maxnet.ru>
Date: Tue, 25 Aug 2015 17:07:51 +0300
From: Evgeny Khorokhorin <john@maxnet.ru>
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64;
 rv:31.0) Gecko/20100101 Thunderbird/31.7.0
MIME-Version: 1.0
To: freebsd-net@freebsd.org
Subject: FreeBSD 10.2 , ospf vs. aggregated static routes, performance issue
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 7bit
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.20
Precedence: list
List-Id: Networking and TCP/IP with FreeBSD <freebsd-net.freebsd.org>
List-Unsubscribe: <https://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: <https://lists.freebsd.org/mailman/listinfo/freebsd-net>,
 <mailto:freebsd-net-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Tue, 25 Aug 2015 14:07:57 -0000

Hi,

I have 10.2-STABLE, 2 CPU Intel E5-2643v3, network Intel XL710 with 
1.4.0 driver from Intel
I know that going through routing table is very fast (rn_match). But I 
decided to optimize routing table.
I'm using 2 interfaces - ixl0 and ixl1.
Behind ixl0 I have 304 networks 172.16.. from /28 to /24 all via the 
same gw 1.1.1.1 (because ip on ixl0 with /30 mask). And behind ixl1 I 
have default route via 2.2.2.2.
That 304 172.16 networks I receive via OSPF (quagga). Now all is OK - on 
every interface I have up to 500kpps/395kpps, 4.5Gbps/1.57Gbps (rx/tx on 
ixl1 and tx/rx on ixl0).
If I disable OSPF and in zebra add static route 172.16.0.0/12 via 
1.1.1.1, the system works good until traffic grow up to 251kpps/181kpps 
, 2.27Gbps/637Mbps. After that the system is degrading: ixl's queue 
threads utilizes 100% CPU and I see many many traffic drops (netstat -i)
If I turn on ospfd and receive 304 more specific routes the problem 
disappears.

Where is the problem? Or I have misunderstanding about how FreeBSD uses 
routing table..
P.S. I use this machine as NAT. I checked this on ipfw and pf, all the same.

-- Cheers,
Evgeny