From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp69.ord1c.emailsrvr.com (smtp69.ord1c.emailsrvr.com [108.166.43.69]) by dpdk.org (Postfix) with ESMTP id 8A8272B99 for ; Sat, 18 Mar 2017 04:03:17 +0100 (CET) Received: from smtp17.relay.ord1c.emailsrvr.com (localhost [127.0.0.1]) by smtp17.relay.ord1c.emailsrvr.com (SMTP Server) with ESMTP id 038BC6019C for ; Fri, 17 Mar 2017 23:03:17 -0400 (EDT) X-Auth-ID: padam.singh@inventum.net Received: by smtp17.relay.ord1c.emailsrvr.com (Authenticated sender: padam.singh-AT-inventum.net) with ESMTPSA id 4BACC60116 for ; Fri, 17 Mar 2017 23:03:15 -0400 (EDT) X-Sender-Id: padam.singh@inventum.net Received: from [192.168.1.4] ([UNAVAILABLE]. [171.50.138.119]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384) by 0.0.0.0:465 (trex/5.7.12); Fri, 17 Mar 2017 23:03:16 -0400 From: Padam Jeet Singh Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Mime-Version: 1.0 (Mac OS X Mail 10.2 \(3259\)) Message-Id: <94242C63-25F0-4AB4-A8F9-F981083F3A38@inventum.net> Date: Sat, 18 Mar 2017 08:33:11 +0530 To: users@dpdk.org X-Mailer: Apple Mail (2.3259) Subject: [dpdk-users] Fragmentation and Reassembly issues X-BeenThere: users@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK usage discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 18 Mar 2017 03:03:17 -0000 Hi, I am using the IPv4 reassembly function = (rte_ipv4_frag_reassemble_packet) on RX, and IPv4 fragmentation function = (rte_ipv4_fragment_packet) on TX.=20 When I am putting this code into our production network, after a few = hours the Ethernet port=E2=80=99s TX stops working. All packets sent to = the PMD using rte_eth_tx_burst fail (returned 0 =3D no packets sent). If I disable the reassembly and drop all incoming fragments, but = continue to do fragmentation on TX (since the MTU is different on RX and = TX ports) then everything works normally. Any pointers on what could be wrong when forwarding packets using this = scheme? Thanks, Padam