From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from tyo202.gate.nec.co.jp (TYO202.gate.nec.co.jp [210.143.35.52]) by dpdk.org (Postfix) with ESMTP id 0CAE85902 for ; Tue, 30 Sep 2014 13:12:04 +0200 (CEST) Received: from mailgate3.nec.co.jp ([10.7.69.192]) by tyo202.gate.nec.co.jp (8.13.8/8.13.4) with ESMTP id s8UBIih2025725 for ; Tue, 30 Sep 2014 20:18:44 +0900 (JST) Received: from mailsv3.nec.co.jp (imss61.nec.co.jp [10.7.69.156]) by mailgate3.nec.co.jp (8.11.7/3.7W-MAILGATE-NEC) with ESMTP id s8UBIh312916 for ; Tue, 30 Sep 2014 20:18:43 +0900 (JST) Received: from mail03.kamome.nec.co.jp (mail03.kamome.nec.co.jp [10.25.43.7]) by mailsv3.nec.co.jp (8.13.8/8.13.4) with ESMTP id s8UBIhqY010585 for ; Tue, 30 Sep 2014 20:18:43 +0900 (JST) Received: from bpxc99gp.gisp.nec.co.jp ([10.38.151.143] [10.38.151.143]) by mail02.kamome.nec.co.jp with ESMTP id BT-MMP-2237357; Tue, 30 Sep 2014 20:15:29 +0900 Received: from BPXM14GP.gisp.nec.co.jp ([169.254.1.136]) by BPXC15GP.gisp.nec.co.jp ([10.38.151.143]) with mapi id 14.03.0174.002; Tue, 30 Sep 2014 20:15:29 +0900 From: Hiroshi Shimamoto To: "dev@dpdk.org" Thread-Topic: [memnic PATCH v2 7/7] pmd: burst mbuf freeing in xmit Thread-Index: Ac/cn8kgpoARSvwTQxOtJV/Ci3mq+w== Date: Tue, 30 Sep 2014 11:15:28 +0000 Message-ID: <7F861DC0615E0C47A872E6F3C5FCDDBD02AE26EC@BPXM14GP.gisp.nec.co.jp> Accept-Language: ja-JP, en-US Content-Language: ja-JP X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.205.5.123] Content-Type: text/plain; charset="iso-2022-jp" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: Hayato Momma Subject: [dpdk-dev] [memnic PATCH v2 7/7] pmd: burst mbuf freeing in xmit X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 30 Sep 2014 11:12:05 -0000 From: Hiroshi Shimamoto In rte_pktmbuf_free(), there might be cache miss/memory stall issue. In small packet case, it could harm the performance. >>From the result of memnic-tester, in less than 1024 frame size the performance could be improved. Using Xeon E5-2697 v2 @ 2.70GHz, 4 vCPU. size | before | after 64 | 5.55Mpps | 5.83Mpps 128 | 5.44Mpps | 5.71Mpps 256 | 5.22Mpps | 5.40Mpps 512 | 4.52Mpps | 4.64Mpps 1024 | 3.73Mpps | 3.68Mpps 1280 | 3.22Mpps | 3.17Mpps 1518 | 2.93Mpps | 2.90Mpps Signed-off-by: Hiroshi Shimamoto Reviewed-by: Hayato Momma --- pmd/pmd_memnic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/pmd/pmd_memnic.c b/pmd/pmd_memnic.c index 875d3ea..59ee332 100644 --- a/pmd/pmd_memnic.c +++ b/pmd/pmd_memnic.c @@ -344,7 +344,7 @@ static uint16_t memnic_xmit_pkts(void *tx_queue, struct memnic_adapter *adapter =3D q->adapter; struct memnic_data *data =3D &adapter->nic->down; struct memnic_packet *p; - uint16_t nr; + uint16_t i, nr; int idx; struct rte_eth_stats *st =3D &adapter->stats[rte_lcore_id()]; uint64_t pkts, bytes, errs; @@ -408,9 +408,9 @@ retry: =20 rte_compiler_barrier(); p->status =3D MEMNIC_PKT_ST_FILLED; - - rte_pktmbuf_free(tx_pkts[nr]); } + for (i =3D 0; i < nr; i++) + rte_pktmbuf_free(tx_pkts[i]); =20 /* stats */ st->opackets +=3D pkts; --=20 1.8.3.1