Patch Detail
get:
Show a patch.
patch:
Update a patch.
put:
Update a patch.
GET /api/patches/67239/?format=api
{ "id": 67239, "url": "https://patches.dpdk.org/api/patches/67239/?format=api", "web_url": "https://patches.dpdk.org/project/dpdk/patch/20200326165644.866053-29-jerinj@marvell.com/", "project": { "id": 1, "url": "https://patches.dpdk.org/api/projects/1/?format=api", "name": "DPDK", "link_name": "dpdk", "list_id": "dev.dpdk.org", "list_email": "dev@dpdk.org", "web_url": "http://core.dpdk.org", "scm_url": "git://dpdk.org/dpdk", "webscm_url": "http://git.dpdk.org/dpdk", "list_archive_url": "https://inbox.dpdk.org/dev", "list_archive_url_format": "https://inbox.dpdk.org/dev/{}", "commit_url_format": "" }, "msgid": "<20200326165644.866053-29-jerinj@marvell.com>", "list_archive_url": "https://inbox.dpdk.org/dev/20200326165644.866053-29-jerinj@marvell.com", "date": "2020-03-26T16:56:44", "name": "[v2,28/28] doc: add l3fwd graph application user guide", "commit_ref": null, "pull_url": null, "state": "superseded", "archived": true, "hash": "adfec2582650d7076e00e4c07a9d3e8dd17a31ae", "submitter": { "id": 1188, "url": "https://patches.dpdk.org/api/people/1188/?format=api", "name": "Jerin Jacob Kollanukkaran", "email": "jerinj@marvell.com" }, "delegate": { "id": 1, "url": "https://patches.dpdk.org/api/users/1/?format=api", "username": "tmonjalo", "first_name": "Thomas", "last_name": "Monjalon", "email": "thomas@monjalon.net" }, "mbox": "https://patches.dpdk.org/project/dpdk/patch/20200326165644.866053-29-jerinj@marvell.com/mbox/", "series": [ { "id": 9068, "url": "https://patches.dpdk.org/api/series/9068/?format=api", "web_url": "https://patches.dpdk.org/project/dpdk/list/?series=9068", "date": "2020-03-26T16:56:16", "name": "graph: introduce graph subsystem", "version": 2, "mbox": "https://patches.dpdk.org/series/9068/mbox/" } ], "comments": "https://patches.dpdk.org/api/patches/67239/comments/", "check": "success", "checks": "https://patches.dpdk.org/api/patches/67239/checks/", "tags": {}, "related": [], "headers": { "Return-Path": "<dev-bounces@dpdk.org>", "X-Original-To": "patchwork@inbox.dpdk.org", "Delivered-To": "patchwork@inbox.dpdk.org", "Received": [ "from dpdk.org (dpdk.org [92.243.14.124])\n\tby inbox.dpdk.org (Postfix) with ESMTP id 38693A057C;\n\tThu, 26 Mar 2020 18:02:35 +0100 (CET)", "from [92.243.14.124] (localhost [127.0.0.1])\n\tby dpdk.org (Postfix) with ESMTP id 5B3831C139;\n\tThu, 26 Mar 2020 17:58:36 +0100 (CET)", "from mx0b-0016f401.pphosted.com (mx0a-0016f401.pphosted.com\n [67.231.148.174]) by dpdk.org (Postfix) with ESMTP id ACC201C131\n for <dev@dpdk.org>; Thu, 26 Mar 2020 17:58:34 +0100 (CET)", "from pps.filterd (m0045849.ppops.net [127.0.0.1])\n by mx0a-0016f401.pphosted.com (8.16.0.42/8.16.0.42) with SMTP id\n 02QGiTUk025262; Thu, 26 Mar 2020 09:58:32 -0700", "from sc-exch01.marvell.com ([199.233.58.181])\n by mx0a-0016f401.pphosted.com with ESMTP id 2ywg9nxgqx-1\n (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT);\n Thu, 26 Mar 2020 09:58:32 -0700", "from DC5-EXCH01.marvell.com (10.69.176.38) by SC-EXCH01.marvell.com\n (10.93.176.81) with Microsoft SMTP Server (TLS) id 15.0.1497.2;\n Thu, 26 Mar 2020 09:58:30 -0700", "from SC-EXCH01.marvell.com (10.93.176.81) by DC5-EXCH01.marvell.com\n (10.69.176.38) with Microsoft SMTP Server (TLS) id 15.0.1497.2;\n Thu, 26 Mar 2020 09:58:29 -0700", "from maili.marvell.com (10.93.176.43) by SC-EXCH01.marvell.com\n (10.93.176.81) with Microsoft SMTP Server id 15.0.1497.2 via Frontend\n Transport; Thu, 26 Mar 2020 09:58:29 -0700", "from jerin-lab.marvell.com (jerin-lab.marvell.com [10.28.34.14])\n by maili.marvell.com (Postfix) with ESMTP id 1A6A83F7040;\n Thu, 26 Mar 2020 09:58:24 -0700 (PDT)" ], "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com;\n h=from : to : cc :\n subject : date : message-id : in-reply-to : references : mime-version :\n content-transfer-encoding : content-type; s=pfpt0818;\n bh=qAjFHsCJ2f1J8bp9eSlI41hfrnjgw5q5Pf1GJo0PYR0=;\n b=y0y0Lj25NXkBe3QcXfeN/6kumfxROWjEqgZ7q0EENA0q62XZgJYSIESLjCMsZzs5ZPB0\n 2z87eOVBa/c7bNAJUoKssSwu5wlaBKNq9tOnovspqcCQujAhfns4eH9Na8UcbEFvAMTp\n LuIktS7ohdGbOzb8N7npbK0InToj6OBh9aW6+EFJyZj4S45eViVkhpvStErPdC61Q7W4\n dDRohmRcYkCurpav3V4fwB80hPQ3rvp9Wy/08B6b0J1uDfqQj7QlasM8DM7y6pJg1DpG\n A9danstVasneqE1v0/3raIdEOuuuILcug4BE0859LWo8zDtM7BYYioHP8zREYcvDmeUD kQ==", "From": "<jerinj@marvell.com>", "To": "Thomas Monjalon <thomas@monjalon.net>, John McNamara\n <john.mcnamara@intel.com>, Marko Kovacevic <marko.kovacevic@intel.com>,\n \"Ori Kam\" <orika@mellanox.com>,\n Bruce Richardson <bruce.richardson@intel.com>,\n \"Radu Nicolau\" <radu.nicolau@intel.com>, Akhil Goyal <akhil.goyal@nxp.com>,\n \"Tomasz Kantecki\" <tomasz.kantecki@intel.com>, Sunil Kumar Kori\n <skori@marvell.com>, Pavan Nikhilesh <pbhagavatula@marvell.com>, Nithin\n Dabilpuram <ndabilpuram@marvell.com>", "CC": "<dev@dpdk.org>, <david.marchand@redhat.com>, <mdr@ashroe.eu>,\n <mattias.ronnblom@ericsson.com>, <kirankumark@marvell.com>", "Date": "Thu, 26 Mar 2020 22:26:44 +0530", "Message-ID": "<20200326165644.866053-29-jerinj@marvell.com>", "X-Mailer": "git-send-email 2.25.1", "In-Reply-To": "<20200326165644.866053-1-jerinj@marvell.com>", "References": "<20200318213551.3489504-1-jerinj@marvell.com>\n <20200326165644.866053-1-jerinj@marvell.com>", "MIME-Version": "1.0", "Content-Transfer-Encoding": "8bit", "Content-Type": "text/plain", "X-Proofpoint-Virus-Version": "vendor=fsecure engine=2.50.10434:6.0.138, 18.0.645\n definitions=2020-03-26_08:2020-03-26,\n 2020-03-26 signatures=0", "Subject": "[dpdk-dev] [PATCH v2 28/28] doc: add l3fwd graph application user\n\tguide", "X-BeenThere": "dev@dpdk.org", "X-Mailman-Version": "2.1.15", "Precedence": "list", "List-Id": "DPDK patches and discussions <dev.dpdk.org>", "List-Unsubscribe": "<https://mails.dpdk.org/options/dev>,\n <mailto:dev-request@dpdk.org?subject=unsubscribe>", "List-Archive": "<http://mails.dpdk.org/archives/dev/>", "List-Post": "<mailto:dev@dpdk.org>", "List-Help": "<mailto:dev-request@dpdk.org?subject=help>", "List-Subscribe": "<https://mails.dpdk.org/listinfo/dev>,\n <mailto:dev-request@dpdk.org?subject=subscribe>", "Errors-To": "dev-bounces@dpdk.org", "Sender": "\"dev\" <dev-bounces@dpdk.org>" }, "content": "From: Nithin Dabilpuram <ndabilpuram@marvell.com>\n\nAdding the user guide for l3fwd graph application.\n\nSigned-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>\n---\n MAINTAINERS | 1 +\n doc/guides/rel_notes/release_20_05.rst | 8 +\n doc/guides/sample_app_ug/index.rst | 1 +\n doc/guides/sample_app_ug/intro.rst | 4 +\n doc/guides/sample_app_ug/l3_forward_graph.rst | 327 ++++++++++++++++++\n 5 files changed, 341 insertions(+)\n create mode 100644 doc/guides/sample_app_ug/l3_forward_graph.rst", "diff": "diff --git a/MAINTAINERS b/MAINTAINERS\nindex 1d2cf6caa..e8a87e119 100644\n--- a/MAINTAINERS\n+++ b/MAINTAINERS\n@@ -1583,6 +1583,7 @@ F: doc/guides/sample_app_ug/l3_forward.rst\n \n M: Nithin Dabilpuram <ndabilpuram@marvell.com>\n F: examples/l3fwd-graph/\n+F: doc/guides/sample_app_ug/l3_forward_graph.rst\n \n F: examples/link_status_interrupt/\n F: doc/guides/sample_app_ug/link_status_intr.rst\ndiff --git a/doc/guides/rel_notes/release_20_05.rst b/doc/guides/rel_notes/release_20_05.rst\nindex d208547ec..9d3e7bd69 100644\n--- a/doc/guides/rel_notes/release_20_05.rst\n+++ b/doc/guides/rel_notes/release_20_05.rst\n@@ -86,6 +86,14 @@ New Features\n that can be configured through ``rte_node_ip4_rewrite_add`` function.\n * Packet drop node: Frees the packets received to their respective mempool.\n \n+* **Added new l3fwd-graph sample application.**\n+\n+ Added an example application ``l3fwd-graph``. It demonstrates the usage of graph\n+ library and node library for packet processing. In addition to the library usage\n+ demonstration, this application can use for performance comparison with existing\n+ ``l3fwd`` (The static code without any nodes) with the modular ``l3fwd-graph``\n+ approach.\n+\n \n Removed Items\n -------------\ndiff --git a/doc/guides/sample_app_ug/index.rst b/doc/guides/sample_app_ug/index.rst\nindex ac3445147..cf9c1e44d 100644\n--- a/doc/guides/sample_app_ug/index.rst\n+++ b/doc/guides/sample_app_ug/index.rst\n@@ -29,6 +29,7 @@ Sample Applications User Guides\n l2_forward_event\n l2_forward_cat\n l3_forward\n+ l3_forward_graph\n l3_forward_power_man\n l3_forward_access_ctrl\n link_status_intr\ndiff --git a/doc/guides/sample_app_ug/intro.rst b/doc/guides/sample_app_ug/intro.rst\nindex 6cd0342a1..8ff223b16 100644\n--- a/doc/guides/sample_app_ug/intro.rst\n+++ b/doc/guides/sample_app_ug/intro.rst\n@@ -54,6 +54,10 @@ examples are highlighted below.\n forwarding, or ``l3fwd`` application does forwarding based on Internet\n Protocol, IPv4 or IPv6 like a simple router.\n \n+* :doc:`Network Layer 3 forwarding Graph<l3_forward_graph>`: The Network Layer3\n+ forwarding Graph, or ``l3fwd_graph`` application does forwarding based on IPv4\n+ like a simple router with DPDK Graph framework.\n+\n * :doc:`Hardware packet copying<ioat>`: The Hardware packet copying,\n or ``ioatfwd`` application demonstrates how to use IOAT rawdev driver for\n copying packets between two threads.\ndiff --git a/doc/guides/sample_app_ug/l3_forward_graph.rst b/doc/guides/sample_app_ug/l3_forward_graph.rst\nnew file mode 100644\nindex 000000000..73153f82b\n--- /dev/null\n+++ b/doc/guides/sample_app_ug/l3_forward_graph.rst\n@@ -0,0 +1,327 @@\n+.. SPDX-License-Identifier: BSD-3-Clause\n+ Copyright(C) 2020 Marvell International Ltd.\n+\n+L3 Forwarding Graph Sample Application\n+======================================\n+\n+The L3 Forwarding Graph application is a simple example of packet processing\n+using the DPDK Graph framework. The application performs L3 forwarding using\n+Graph framework and nodes written for graph framework.\n+\n+Overview\n+--------\n+\n+The application demonstrates the use of the graph framework and graph nodes\n+``ethdev_rx``, ``ip4_lookup``, ``ip4_rewrite``, ``ethdev_tx`` and ``pkt_drop`` in DPDK to\n+implement packet forwarding.\n+\n+The initialization is very similar to those of the :doc:`l3_forward`.\n+There is also additional initialization of graph for graph object creation\n+and configuration per lcore.\n+Run-time path is main thing that differs from L3 forwarding sample application.\n+Difference is that forwarding logic starting from Rx, followed by LPM lookup,\n+TTL update and finally Tx is implemented inside graph nodes. These nodes are\n+interconnected in graph framework. Application main loop needs to walk over\n+graph using ``rte_graph_walk()`` with graph objects created one per slave lcore.\n+\n+The lookup method is as per implementation of ``ip4_lookup`` graph node.\n+The ID of the output interface for the input packet is the next hop returned by\n+the LPM lookup. The set of LPM rules used by the application is statically\n+configured and provided to ``ip4_lookup`` graph node and ``ip4_rewrite`` graph node\n+using node control API ``rte_node_ip4_route_add()`` and ``rte_node_ip4_rewrite_add()``.\n+\n+In the sample application, only IPv4 forwarding is supported as of now.\n+\n+Compiling the Application\n+-------------------------\n+\n+To compile the sample application see :doc:`compiling`.\n+\n+The application is located in the ``l3fwd-graph`` sub-directory.\n+\n+Running the Application\n+-----------------------\n+\n+The application has a number of command line options similar to l3fwd::\n+\n+ ./l3fwd-graph [EAL options] -- -p PORTMASK\n+ [-P]\n+ --config(port,queue,lcore)[,(port,queue,lcore)]\n+ [--eth-dest=X,MM:MM:MM:MM:MM:MM]\n+ [--enable-jumbo [--max-pkt-len PKTLEN]]\n+ [--no-numa]\n+ [--per-port-pool]\n+\n+Where,\n+\n+* ``-p PORTMASK:`` Hexadecimal bitmask of ports to configure\n+\n+* ``-P:`` Optional, sets all ports to promiscuous mode so that packets are accepted regardless of the packet's Ethernet MAC destination address.\n+ Without this option, only packets with the Ethernet MAC destination address set to the Ethernet address of the port are accepted.\n+\n+* ``--config (port,queue,lcore)[,(port,queue,lcore)]:`` Determines which queues from which ports are mapped to which cores.\n+\n+* ``--eth-dest=X,MM:MM:MM:MM:MM:MM:`` Optional, ethernet destination for port X.\n+\n+* ``--enable-jumbo:`` Optional, enables jumbo frames.\n+\n+* ``--max-pkt-len:`` Optional, under the premise of enabling jumbo, maximum packet length in decimal (64-9600).\n+\n+* ``--no-numa:`` Optional, disables numa awareness.\n+\n+* ``--per-port-pool:`` Optional, set to use independent buffer pools per port. Without this option, single buffer pool is used for all ports.\n+\n+For example, consider a dual processor socket platform with 8 physical cores, where cores 0-7 and 16-23 appear on socket 0,\n+while cores 8-15 and 24-31 appear on socket 1.\n+\n+To enable L3 forwarding between two ports, assuming that both ports are in the same socket, using two cores, cores 1 and 2,\n+(which are in the same socket too), use the following command:\n+\n+.. code-block:: console\n+\n+ ./build/l3fwd-graph -l 1,2 -n 4 -- -p 0x3 --config=\"(0,0,1),(1,0,2)\"\n+\n+In this command:\n+\n+* The -l option enables cores 1, 2\n+\n+* The -p option enables ports 0 and 1\n+\n+* The --config option enables one queue on each port and maps each (port,queue) pair to a specific core.\n+ The following table shows the mapping in this example:\n+\n++----------+-----------+-----------+-------------------------------------+\n+| **Port** | **Queue** | **lcore** | **Description** |\n+| | | | |\n++----------+-----------+-----------+-------------------------------------+\n+| 0 | 0 | 1 | Map queue 0 from port 0 to lcore 1. |\n+| | | | |\n++----------+-----------+-----------+-------------------------------------+\n+| 1 | 0 | 2 | Map queue 0 from port 1 to lcore 2. |\n+| | | | |\n++----------+-----------+-----------+-------------------------------------+\n+\n+Refer to the *DPDK Getting Started Guide* for general information on running applications and\n+the Environment Abstraction Layer (EAL) options.\n+\n+.. _l3_fwd_graph_explanation:\n+\n+Explanation\n+-----------\n+\n+The following sections provide some explanation of the sample application code.\n+As mentioned in the overview section, the initialization is similar to that of\n+the :doc:`l3_forward`. Run-time path though similar in functionality to that of\n+:doc:`l3_forward`, major part of the implementation is in graph nodes via used\n+via ``librte_node`` library.\n+The following sections describe aspects that are specific to the L3 Forwarding\n+Graph sample application.\n+\n+Graph Node Pre-Init Configuration\n+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n+\n+After device configuration and device Rx, Tx queue setup is complete,\n+a minimal config of port id, num_rx_queues, num_tx_queues, mempools etc will\n+be passed to *ethdev_** node ctrl API ``rte_node_eth_config()``. This will be\n+lead to the clone of ``ethdev_rx`` and ``ethdev_tx`` nodes as ``ethdev_rx-X-Y`` and\n+``ethdev_tx-X`` where X, Y represent port id and queue id associated with them.\n+In case of ``ethdev_tx-X`` nodes, tx queue id assigned per instance of the node\n+is same as graph id.\n+\n+These cloned nodes along with existing static nodes such as ``ip4_lookup`` and\n+``ip4_rewrite`` will be used in graph creation to associate node's to lcore\n+specific graph object.\n+\n+.. code-block:: c\n+\n+ RTE_ETH_FOREACH_DEV(portid)\n+ {\n+\n+ /* ... */\n+ ret = rte_eth_dev_configure(portid, nb_rx_queue,\n+ n_tx_queue, &local_port_conf);\n+ /* ... */\n+\n+ /* Init one TX queue per couple (lcore,port) */\n+ queueid = 0;\n+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {\n+ /* ... */\n+ ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd,\n+ socketid, txconf);\n+ /* ... */\n+ queueid++;\n+ }\n+\n+ /* Setup ethdev node config */\n+ ethdev_conf[nb_conf].port_id = portid;\n+ ethdev_conf[nb_conf].num_rx_queues = nb_rx_queue;\n+ ethdev_conf[nb_conf].num_tx_queues = n_tx_queue;\n+ if (!per_port_pool)\n+ ethdev_conf[nb_conf].mp = pktmbuf_pool[0];\n+ else\n+ ethdev_conf[nb_conf].mp = pktmbuf_pool[portid];\n+ ethdev_conf[nb_conf].mp_count = NB_SOCKETS;\n+\n+ nb_conf++;\n+ printf(\"\\n\");\n+ }\n+\n+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {\n+ /* Init RX queues */\n+ for (queue = 0; queue < qconf->n_rx_queue; ++queue) {\n+ /* ... */\n+ if (!per_port_pool)\n+ ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd, socketid,\n+ &rxq_conf, pktmbuf_pool[0][socketid]);\n+ else\n+ ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd, socketid,\n+ &rxq_conf, pktmbuf_pool[portid][socketid]);\n+ /* ... */\n+ }\n+ }\n+\n+ /* Ethdev node config, skip rx queue mapping */\n+ ret = rte_node_eth_config(ethdev_conf, nb_conf, nb_graphs);\n+\n+Graph Initialization\n+~~~~~~~~~~~~~~~~~~~~\n+\n+Now a graph needs to be created with a specific set of nodes for every lcore.\n+A graph object returned after graph creation is a per lcore object and\n+cannot be shared between lcores. Since ``ethdev_tx-X`` node is per port node,\n+it can be associated with all the graphs created as all the lcores should have\n+Tx capability for every port. But ``ethdev_rx-X-Y`` node is created per\n+(port, rx_queue_id), so they should be associated with a graph based on\n+the application argument ``--config`` specifying rx queue mapping to lcore.\n+\n+.. note::\n+\n+ The Graph creation will fail if the passed set of shell node pattern's\n+ are not sufficient to meet their inter-dependency or even one node is not\n+ found with a given regex node pattern.\n+\n+.. code-block:: c\n+\n+ static const char *node_patterns[] = {\n+ \"ip4*\",\n+ \"ethdev_tx-*\",\n+ \"pkt_drop\",\n+ };\n+ uint16_t nb_patterns = RTE_DIM(node_patterns);\n+\n+ /* ... */\n+\n+ /* Create a graph object per lcore with common nodes and\n+ * lcore specific nodes based on application arguments\n+ */\n+ memset(&graph_conf, 0, sizeof(graph_conf));\n+\n+ /* Common set of nodes in every lcore's graph object */\n+ graph_conf.node_patterns = node_patterns;\n+\n+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {\n+ /* ... */\n+\n+ /* Skip graph creation if no source exists */\n+ if (!qconf->n_rx_queue)\n+ continue;\n+\n+ /* Add rx node patterns of this lcore based on --config */\n+ for (i = 0; i < qconf->n_rx_queue; i++) {\n+ graph_conf.node_patterns[nb_patterns + i] =\n+ qconf->rx_queue_list[i].node_name;\n+ }\n+\n+ graph_conf.nb_node_patterns = nb_patterns + i;\n+ graph_conf.socket_id = rte_lcore_to_socket_id(lcore_id);\n+\n+ snprintf(qconf->name, sizeof(qconf->name), \"worker_%u\", lcore_id);\n+\n+ graph_id = rte_graph_create(qconf->name, &graph_conf);\n+\n+ /* ... */\n+\n+ qconf->graph = rte_graph_lookup(qconf->name);\n+\n+ /* ... */\n+ }\n+\n+Forwarding data(Route, Next-Hop) addition\n+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n+\n+Once graph objects are created, node specific info like routes and rewrite\n+headers will be provided run-time using ``rte_node_ip4_route_add()`` and\n+``rte_node_ip4_rewrite_add()`` API.\n+\n+.. note::\n+\n+ Since currently ``ip4_lookup`` and ``ip4_rewrite`` nodes don't support\n+ lock-less mechanisms(RCU, etc) to add run-time forwarding data like route and\n+ rewrite data, forwarding data is added before packet processing loop is\n+ launched on slave lcore.\n+\n+.. code-block:: c\n+\n+ /* Add route to ip4 graph infra */\n+ for (i = 0; i < IPV4_L3FWD_LPM_NUM_ROUTES; i++) {\n+ /* ... */\n+\n+ dst_port = ipv4_l3fwd_lpm_route_array[i].if_out;\n+ next_hop = i;\n+\n+ /* ... */\n+ ret = rte_node_ip4_route_add(ipv4_l3fwd_lpm_route_array[i].ip,\n+ ipv4_l3fwd_lpm_route_array[i].depth, next_hop,\n+ RTE_NODE_IP4_LOOKUP_NEXT_REWRITE);\n+\n+ /* ... */\n+\n+ memcpy(rewrite_data, val_eth + dst_port, rewrite_len);\n+\n+ /* Add next hop for a given destination */\n+ ret = rte_node_ip4_rewrite_add(next_hop, rewrite_data,\n+ rewrite_len, dst_port);\n+\n+ RTE_LOG(INFO, L3FWD_GRAPH, \"Added route %s, next_hop %u\\n\",\n+ route_str, next_hop);\n+ }\n+\n+Packet Forwarding using Graph Walk\n+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n+\n+Now that all the device configurations are done, graph creations are done and\n+forwarding data is updated with nodes, slave lcores will be launched with graph\n+main loop. Graph main loop is very simple in the sense that it needs to\n+continuously call a non-blocking API ``rte_graph_walk()`` with it's lcore\n+specific graph object that was already created.\n+\n+.. note::\n+\n+ rte_graph_walk() will walk over all the sources nodes i.e ``ethdev_rx-X-Y``\n+ associated with a given graph and Rx the available packets and enqueue them\n+ to the following node ``ip4_lookup`` which then will enqueue them to ``ip4_rewrite``\n+ node if LPM lookup succeeds. ``ip4_rewrite`` node then will update Ethernet header\n+ as per next-hop data and transmit the packet via port 'Z' by enqueuing\n+ to ``ethdev_tx-Z`` node instance in its graph object.\n+\n+.. code-block:: c\n+\n+ /* Main processing loop */\n+ static int\n+ graph_main_loop(void *conf)\n+ {\n+ // ...\n+\n+ lcore_id = rte_lcore_id();\n+ qconf = &lcore_conf[lcore_id];\n+ graph = qconf->graph;\n+\n+ RTE_LOG(INFO, L3FWD_GRAPH,\n+ \"Entering main loop on lcore %u, graph %s(%p)\\n\", lcore_id,\n+ qconf->name, graph);\n+\n+ /* Walk over graph until signal to quit */\n+ while (likely(!force_quit))\n+ rte_graph_walk(graph);\n+ return 0;\n+ }\n", "prefixes": [ "v2", "28/28" ] }