From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by dpdk.space (Postfix) with ESMTP id 211BDA067F for ; Thu, 28 Mar 2019 11:24:51 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 4EEF41B0FB; Thu, 28 Mar 2019 11:24:50 +0100 (CET) Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) by dpdk.org (Postfix) with ESMTP id F129F1B0F7 for ; Thu, 28 Mar 2019 11:24:47 +0100 (CET) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga004.jf.intel.com ([10.7.209.38]) by orsmga103.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 28 Mar 2019 03:24:47 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.60,280,1549958400"; d="scan'208";a="286643958" Received: from irsmsx109.ger.corp.intel.com ([163.33.3.23]) by orsmga004.jf.intel.com with ESMTP; 28 Mar 2019 03:24:45 -0700 Received: from irsmsx112.ger.corp.intel.com (10.108.20.5) by IRSMSX109.ger.corp.intel.com (163.33.3.23) with Microsoft SMTP Server (TLS) id 14.3.408.0; Thu, 28 Mar 2019 10:24:44 +0000 Received: from irsmsx108.ger.corp.intel.com ([169.254.11.7]) by irsmsx112.ger.corp.intel.com ([169.254.1.167]) with mapi id 14.03.0415.000; Thu, 28 Mar 2019 10:24:44 +0000 From: "Iremonger, Bernard" To: Yongseok Koh , "Lu, Wenzhuo" , "Wu, Jingjing" CC: "dev@dpdk.org" , "jerinj@marvell.com" , "Ananyev, Konstantin" Thread-Topic: [dpdk-dev] [PATCH v3] app/testpmd: make txonly mode generate multiple flows Thread-Index: AQHU5QjKTND6WUHPZ0OQJVVitee4/KYg01Kg Date: Thu, 28 Mar 2019 10:24:44 +0000 Message-ID: <8CEF83825BEC744B83065625E567D7C260D775EF@IRSMSX108.ger.corp.intel.com> References: <20171215211125.39177-1-yskoh@mellanox.com> <20190328015102.21920-1-yskoh@mellanox.com> In-Reply-To: <20190328015102.21920-1-yskoh@mellanox.com> Accept-Language: en-GB, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-titus-metadata-40: eyJDYXRlZ29yeUxhYmVscyI6IiIsIk1ldGFkYXRhIjp7Im5zIjoiaHR0cDpcL1wvd3d3LnRpdHVzLmNvbVwvbnNcL0ludGVsMyIsImlkIjoiMzc3YWYyZTQtNDA2ZC00ODcyLWJhMTUtMDQzYzFiYmNjOWQ2IiwicHJvcHMiOlt7Im4iOiJDVFBDbGFzc2lmaWNhdGlvbiIsInZhbHMiOlt7InZhbHVlIjoiQ1RQX05UIn1dfV19LCJTdWJqZWN0TGFiZWxzIjpbXSwiVE1DVmVyc2lvbiI6IjE3LjEwLjE4MDQuNDkiLCJUcnVzdGVkTGFiZWxIYXNoIjoiVDlvemxud25vSUh0azRXVmVQaWRZeTFLSmRPaFJTY2JlRXRkQWw2UkNyZCtiWHloaGZUOGhBU1lPU2lVNXg1YSJ9 x-ctpclassification: CTP_NT dlp-product: dlpe-windows dlp-version: 11.0.400.15 dlp-reaction: no-action x-originating-ip: [163.33.239.182] Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH v3] app/testpmd: make txonly mode generate multiple flows X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Message-ID: <20190328102444.lX4C9aEkXxONOOHk4p5D2RtFZnV4SvCIVNyqKN57bPk@z> Hi Yongseok, > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Yongseok Koh > Sent: Thursday, March 28, 2019 1:51 AM > To: Lu, Wenzhuo ; Wu, Jingjing > > Cc: dev@dpdk.org; jerinj@marvell.com; Ananyev, Konstantin > > Subject: [dpdk-dev] [PATCH v3] app/testpmd: make txonly mode generate > multiple flows >=20 > Testpmd can generate multiple flows without taking much cost and this cou= ld > be a simple traffic generator for developer's quick tests. If "--txonly-m= ulti- > flow" is specified in the command line, IP source address is varied to gn= erate > multiple flows. >=20 > Signed-off-by: Yongseok Koh > --- >=20 > v3: > * Add "--txonly-multi-flow" param to enable the feature. > * Replace __thread with RTE_PER_LCORE. >=20 > v2: > * Add detailed explanation in a comment. >=20 > app/test-pmd/parameters.c | 4 ++++ > app/test-pmd/testpmd.c | 3 +++ > app/test-pmd/testpmd.h | 2 ++ > app/test-pmd/txonly.c | 22 ++++++++++++++++++++++ > doc/guides/testpmd_app_ug/run_app.rst | 4 ++++ > 5 files changed, 35 insertions(+) >=20 > diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c index > 38b419767b..7b6b60905d 100644 > --- a/app/test-pmd/parameters.c > +++ b/app/test-pmd/parameters.c > @@ -173,6 +173,7 @@ usage(char* progname) > " Used mainly with PCAP drivers.\n"); > printf(" --txpkts=3DX[,Y]*: set TX segment sizes" > " or total packet length.\n"); > + printf(" --txonly-multi-flow: generate multiple flows in txonly > +mode\n"); > printf(" --disable-link-check: disable check on link status when " > "starting/stopping ports.\n"); > printf(" --no-lsc-interrupt: disable link status change interrupt.\n")= ; > @@ -632,6 +633,7 @@ launch_args_parse(int argc, char** argv) > { "no-flush-rx", 0, 0, 0 }, > { "flow-isolate-all", 0, 0, 0 }, > { "txpkts", 1, 0, 0 }, > + { "txonly-multi-flow", 0, 0, 0 }, > { "disable-link-check", 0, 0, 0 }, > { "no-lsc-interrupt", 0, 0, 0 }, > { "no-rmv-interrupt", 0, 0, 0 }, > @@ -1141,6 +1143,8 @@ launch_args_parse(int argc, char** argv) > else > rte_exit(EXIT_FAILURE, "bad > txpkts\n"); > } > + if (!strcmp(lgopts[opt_idx].name, "txonly-multi- > flow")) > + txonly_multi_flow =3D 1; > if (!strcmp(lgopts[opt_idx].name, "no-flush-rx")) > no_flush_rx =3D 1; > if (!strcmp(lgopts[opt_idx].name, "disable-link- > check")) diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c > index 216be47f92..b950e8cc55 100644 > --- a/app/test-pmd/testpmd.c > +++ b/app/test-pmd/testpmd.c > @@ -217,6 +217,9 @@ uint8_t tx_pkt_nb_segs =3D 1; /**< Number of > segments in TXONLY packets */ enum tx_pkt_split tx_pkt_split =3D > TX_PKT_SPLIT_OFF; /**< Split policy for packets to TX. */ >=20 > +int txonly_multi_flow; This should be "uint8_t txonly_multi_flow;" similar to other variables in = use, for example "uint8_t no_flush_rx =3D 0;" > +/**< Whether multiple flows are generated in TXONLY mode. */ > + > uint16_t nb_pkt_per_burst =3D DEF_PKT_BURST; /**< Number of packets per > burst. */ uint16_t mb_mempool_cache =3D DEF_MBUF_CACHE; /**< Size of > mbuf mempool cache. */ >=20 > diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h index > 85b791b6bb..668227bc55 100644 > --- a/app/test-pmd/testpmd.h > +++ b/app/test-pmd/testpmd.h > @@ -439,6 +439,8 @@ enum tx_pkt_split { >=20 > extern enum tx_pkt_split tx_pkt_split; >=20 > +extern int txonly_multi_flow; This should be "extern uint8_t txonly_multi_flow;" in line with the similar= variables in use, For example "extern uint8_t no_flush_rx;" =20 > + > extern uint16_t nb_pkt_per_burst; > extern uint16_t mb_mempool_cache; > extern int8_t rx_pthresh; > diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c index > 1f08b6ed37..def52a0487 100644 > --- a/app/test-pmd/txonly.c > +++ b/app/test-pmd/txonly.c > @@ -52,6 +52,7 @@ > #define IP_VHL_DEF (IP_VERSION | IP_HDRLEN) >=20 > static struct ipv4_hdr pkt_ip_hdr; /**< IP header of transmitted packe= ts. */ > +RTE_DEFINE_PER_LCORE(uint8_t, _ip_var); /**< IP address variation */ > static struct udp_hdr pkt_udp_hdr; /**< UDP header of transmitted > packets. */ >=20 > static void > @@ -164,6 +165,7 @@ pkt_burst_transmit(struct fwd_stream *fs) > uint16_t vlan_tci, vlan_tci_outer; > uint32_t retry; > uint64_t ol_flags =3D 0; > + uint8_t ip_var =3D RTE_PER_LCORE(_ip_var); > uint8_t i; > uint64_t tx_offloads; > #ifdef RTE_TEST_PMD_RECORD_CORE_CYCLES > @@ -237,6 +239,23 @@ pkt_burst_transmit(struct fwd_stream *fs) > copy_buf_to_pkt(ð_hdr, sizeof(eth_hdr), pkt, 0); > copy_buf_to_pkt(&pkt_ip_hdr, sizeof(pkt_ip_hdr), pkt, > sizeof(struct ether_hdr)); > + if (txonly_multi_flow) { > + struct ipv4_hdr *ip_hdr; > + uint32_t addr; > + > + ip_hdr =3D rte_pktmbuf_mtod_offset(pkt, > + struct ipv4_hdr *, > + sizeof(struct ether_hdr)); > + /* > + * Generate multiple flows by varying IP src addr. This > + * enables packets are well distributed by RSS in > + * receiver side if any and txonly mode can be a > decent > + * packet generator for developer's quick > performance > + * regression test. > + */ > + addr =3D (IP_DST_ADDR | (ip_var++ << 8)) + > rte_lcore_id(); > + ip_hdr->src_addr =3D rte_cpu_to_be_32(addr); > + } > copy_buf_to_pkt(&pkt_udp_hdr, sizeof(pkt_udp_hdr), pkt, > sizeof(struct ether_hdr) + > sizeof(struct ipv4_hdr)); > @@ -268,6 +287,9 @@ pkt_burst_transmit(struct fwd_stream *fs) > } > fs->tx_packets +=3D nb_tx; >=20 > + if (txonly_multi_flow) > + RTE_PER_LCORE(_ip_var) +=3D nb_tx; > + > #ifdef RTE_TEST_PMD_RECORD_BURST_STATS > fs->tx_burst_stats.pkt_burst_spread[nb_tx]++; > #endif > diff --git a/doc/guides/testpmd_app_ug/run_app.rst > b/doc/guides/testpmd_app_ug/run_app.rst > index 4495ed0382..b717b8c7b7 100644 > --- a/doc/guides/testpmd_app_ug/run_app.rst > +++ b/doc/guides/testpmd_app_ug/run_app.rst > @@ -324,6 +324,10 @@ The commandline options are: > Set TX segment sizes or total packet length. Valid for ``tx-only`` > and ``flowgen`` forwarding modes. >=20 > +* ``--txonly-multi-flow`` > + > + Generate multiple flows in txonly mode. > + > * ``--disable-link-check`` >=20 > Disable check on link status when starting/stopping ports. > -- > 2.11.0