| /dpdk/doc/guides/nics/ |
| H A D | ice.rst | 89 In pipeline mode, a flow can be set at one specific stage by setting parameter 91 priority 0 located at the first pipeline stage which typically be used as a firewall 92 to drop the packet on a blocklist(we called it permission stage). At this stage, 94 !0 located at the second stage, typically packets are classified here and be steered to 95 specific queue or queue group (we called it distribution stage), At this stage, flow 99 all flows are virtually at the same pipeline stage. 356 stage.
|
| /dpdk/drivers/net/dpaa2/base/ |
| H A D | dpaa2_tlu_hash.c | 37 static unsigned int stage(unsigned int input) in stage() function 141 mix_tbl[i >> 2][j] = stage(input); in hash_init()
|
| /dpdk/drivers/net/hns3/ |
| H A D | hns3_intr.c | 2386 hw->reset.stage = RESET_STAGE_NONE; in hns3_reset_init() 2645 if (hw->reset.stage == RESET_STAGE_NONE) { in hns3_reset_pre() 2647 hw->reset.stage = RESET_STAGE_DOWN; in hns3_reset_pre() 2657 hw->reset.stage = RESET_STAGE_PREWAIT; in hns3_reset_pre() 2708 hw->reset.stage = RESET_STAGE_RESTORE; in hns3_reset_post() 2727 hw->reset.stage = RESET_STAGE_DONE; in hns3_reset_post() 2736 hw->reset.stage = RESET_STAGE_NONE; in hns3_reset_post() 2782 hw->reset.stage = RESET_STAGE_PREWAIT; in hns3_reset_fail_handle() 2794 hw->reset.stage = RESET_STAGE_NONE; in hns3_reset_fail_handle() 2854 hw->reset.stage = RESET_STAGE_WAIT; in hns3_reset_process() [all …]
|
| H A D | hns3_fdir.c | 162 uint8_t stage; member 196 uint8_t stage; member 209 uint8_t stage; member 217 uint8_t stage; member 287 req->stage = HNS3_FD_STAGE_1; in hns3_set_fd_key_config() 401 req1->stage = HNS3_FD_STAGE_1; in hns3_fd_tcam_config() 439 req->stage = HNS3_FD_STAGE_1; in hns3_fd_ad_config() 1111 req->stage = HNS3_FD_STAGE_1; in hns3_get_count()
|
| /dpdk/app/test/ |
| H A D | test_graph_perf.c | 285 graph_node_count_edges(uint32_t stage, uint16_t node, uint16_t nodes_per_stage, in graph_node_count_edges() argument 295 if (edge_map[stage + 1][i][node]) { in graph_node_count_edges() 298 rte_node_id_to_name(node_map[stage + 1][i])); in graph_node_count_edges() 299 node_data->next_nodes[edges] = node_map[stage + 1][i]; in graph_node_count_edges() 301 edge_map[stage + 1][i][node]; in graph_node_count_edges() 303 total_percent += edge_map[stage + 1][i][node]; in graph_node_count_edges()
|
| /dpdk/doc/guides/prog_guide/ |
| H A D | packet_framework.rst | 27 with the logic of each stage glued around a lookup table. 29 as well as the next stage to send the packet to. 494 On each pipeline iteration, the packets are pushed to the next pipeline stage: for the 4-stage pipe… 496 …kets (that just completed stage 2) are now executing stage 3, two packets (that just completed sta… 497 two packets (that just completed stage 0) are now executing stage 1 and two packets (next two packe… 498 are entering the pipeline to execute stage 0. 504 The current pipeline stage finalizes by prefetching the data structures required by the next pipeli… 520 For example, for the 4-stage pipeline, stage 0 is executed on packets 0 and 1 and then, 522 …e used: packets 2 and 3 (executing stage 1), packets 4 and 5 (executing stage 2) and packets 6 and… 609 For each pipeline stage, the described operations are applied to each of the two packets handled by… [all …]
|
| H A D | eventdev.rst | 122 In this case, each stage has a specified scheduling type. The application 164 create and configure an eventdev and use it for a two-stage atomic pipeline 378 the event to the next stage in the pipeline. 387 /* process mbuf using events[i].queue_id as pipeline stage */ 389 /* Send event to next stage in pipeline */
|
| H A D | traffic_metering_and_policing.rst | 28 The metering and policing stage typically sits on top of flow classification,
|
| H A D | ip_fragment_reassembly_lib.rst | 96 If at any stage of packet processing an error is encountered
|
| H A D | event_ethernet_tx_adapter.rst | 14 transmit stage of the application allowing the same application code to use eventdev
|
| /dpdk/doc/guides/tools/ |
| H A D | testeventdev.rst | 81 Set the scheduled type of each stage where ``type_list`` size 392 The producer(s) injects the events to eventdev based on the first stage sched type 398 reaches the last stage in the pipeline. On event termination, application 403 the timestamp in the event on the first stage and then on termination, it 519 stage and thus reduces the number of queues required to realize the use case 589 | | | nb_producers | At the last stage of the schedule list | 630 The producer(s) injects the events to eventdev based the first stage sched type 635 the last stage in the pipeline if the event type is ``atomic`` it is enqueued 637 ``atomic`` and enqueued onto the last stage queue. 751 stage and thus reduces the number of queues required to realize the use case.
|
| H A D | comp_perf.rst | 14 Then, the output buffers are fed into the decompression stage, and the resulting
|
| /dpdk/doc/guides/sample_app_ug/ |
| H A D | eventdev_pipeline.rst | 14 stage of work. This is useful for performance testing as well as quickly testing 45 * ``-W1000``: do 1000 cycles of work per packet in each stage 81 scheduling type at each stage, and parameters to options such as how many
|
| H A D | vhost_crypto.rst | 50 in experimental stage and may cause the problem like segmentation fault. If
|
| H A D | pipeline.rst | 102 During this stage, EAL layer is initialised and application specific arguments are parsed. Furtherm…
|
| H A D | ip_pipeline.rst | 107 At any stage, telnet client can be terminated using the quit command. 116 During this stage, EAL layer is initialised and application specific arguments are parsed. Furtherm…
|
| H A D | dist_app.rst | 132 statistics include the number of packets enqueued and dequeued at each stage
|
| /dpdk/drivers/net/bnx2x/ |
| H A D | ecore_init.h | 38 #define BLOCK_OPS_IDX(block, stage, end) \ argument 39 (2*(((block)*NUM_OF_INIT_PHASES) + (stage)) + (end)) 525 #define BLOCK_OPS_IDX(block, stage, end) \ argument 526 (2*(((block)*NUM_OF_INIT_PHASES) + (stage)) + (end))
|
| H A D | ecore_init_ops.h | 181 static void ecore_init_block(struct bnx2x_softc *sc, uint32_t block, uint32_t stage) in ecore_init_block() argument 184 INIT_OPS_OFFSETS(sc)[BLOCK_OPS_IDX(block, stage, in ecore_init_block() 187 INIT_OPS_OFFSETS(sc)[BLOCK_OPS_IDX(block, stage, in ecore_init_block()
|
| /dpdk/doc/guides/howto/ |
| H A D | debug_troubleshoot.rst | 45 Overview of pipeline stage of an application 163 * Extreme stalls in dequeue stage of the pipeline will cause 184 stage is not filling up the ring as required. 364 * If the failure is on the enqueue stage for events, check if queue depth 367 #. If there are performance drops in the enqueue stage 424 Using hooks or callbacks capture the packet middle of the pipeline stage
|
| /dpdk/drivers/event/opdl/ |
| H A D | opdl_ring.c | 54 struct opdl_stage *stage; /* back pointer */ member 806 s->shared.stage = s; in init_stage() 872 int ret = add_dep(dependent, dependency->deps[i]->stage, in add_dep() 1214 s->deps[0]->stage->index : 0); in opdl_ring_dump() 1216 fprintf(f, ",%u", s->deps[j]->stage->index); in opdl_ring_dump()
|
| /dpdk/doc/guides/contributing/ |
| H A D | design.rst | 135 application debug stage and are not relevant once debug phase is over. In this 137 statistics counters during the debug phase and at a later stage turn them off.
|
| /dpdk/doc/guides/eventdevs/ |
| H A D | sw.rst | 98 moved to the next stage in the scheduler. Default value is 1.
|
| /dpdk/drivers/net/iavf/ |
| H A D | iavf_generic_flow.h | 524 enum iavf_flow_classification_stage stage; member
|
| /dpdk/drivers/net/ice/ |
| H A D | ice_generic_flow.h | 508 enum ice_flow_classification_stage stage; member
|