From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ZXSHCAS1.zhaoxin.com (unknown [203.148.12.81]) by dpdk.org (Postfix) with ESMTP id 106DA4CAB for ; Sat, 29 Dec 2018 08:14:41 +0100 (CET) Received: from zxbjmbx1.zhaoxin.com (10.29.252.163) by ZXSHCAS1.zhaoxin.com (10.28.252.161) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1261.35; Sat, 29 Dec 2018 15:14:36 +0800 Received: from zxbjmbx2.zhaoxin.com (10.29.252.164) by zxbjmbx1.zhaoxin.com (10.29.252.163) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1261.35; Sat, 29 Dec 2018 15:14:35 +0800 Received: from zxbjmbx2.zhaoxin.com ([fe80::4d77:9dba:64a8:8ec3]) by zxbjmbx2.zhaoxin.com ([fe80::4d77:9dba:64a8:8ec3%4]) with mapi id 15.01.1261.035; Sat, 29 Dec 2018 15:14:35 +0800 From: "Vic Wang(BJ-RD)" To: "users@dpdk.org" Thread-Topic: it seems something wrong in pktgen . Thread-Index: AdSfRiYSJ2Zbqp4XRgirUGViTIdOYQ== Date: Sat, 29 Dec 2018 07:14:35 +0000 Message-ID: <16587cc6ccff461b972d20d29730cc5f@zhaoxin.com> Accept-Language: zh-CN, en-US Content-Language: zh-CN X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.29.24.77] MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.15 Subject: [dpdk-users] it seems something wrong in pktgen . 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, 29 Dec 2018 07:14:44 -0000 Hi, I use dpdk and pktgen-dpdk to test the performance of the platform performa= nce . The system configuration as follows: Senders: Intel i5-6600k with two sumsang ddr4 drams (dual channel), one int= el XL710 40G NIC. Command: ./pktgen -C 0xf -n 2 -- -P -m "2.0,3.1" The packet size set to 64 bytes. Receiver: Intel i5-660k with two sumsang ddr4 drams(dual channel), one inte= l XL710 40G NIC. Command: ./testpmd -C 0xf -n2 -- -i --portmask=3D0x3 --coremask=3D0xc However, when starting to forward the packets, the pktgen will stop after s= ending severl thousands packets . I trace the question, and I found it seems something wrong in pktgen progra= m. In the pktgen_send_pkts, if the pg_pktmbuf_alloc_bulk fails because nobufs,= it can't goto the pktgen_send_burst forever. So it can't free mbuf in the = pktgen_send_burst , and it will be failed every loop when pg_pktmbuf_alloc_= bulk. >static __inline__ void >pktgen_send_pkts(port_info_t *info, uint16_t qid, struct rte_mempool *mp) >{ > uint32_t flags; > int rc =3D 0; > > flags =3D rte_atomic32_read(&info->port_flags); > > if (flags & SEND_FOREVER) { > rc =3D pg_pktmbuf_alloc_bulk(mp, > info->q[qid].tx_mbufs.m_table, > info->tx_burst); > if (rc =3D=3D 0) { > info->q[qid].tx_mbufs.len =3D info->tx_burst; > info->q[qid].tx_cnt +=3D info->tx_burst; > > pktgen_send_burst(info, qid); > } > } else { > int64_t txCnt; This is my thought, please comment me. Best Regards! VicWang ????? ????????????????????????????????????????????????????? CONFIDENTIAL NOTE: This email contains confidential or legally privileged information and is f= or the sole use of its intended recipient. Any unauthorized review, use, co= pying or forwarding of this email or the content of this email is strictly = prohibited.